From 47661ee1821fc3a6b5ae07aac37410d6ccada976 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 18 Jun 2021 13:18:46 +0200 Subject: [PATCH 001/426] memory: tegra: Add compile-test stub for tegra_mc_probe_device() The tegra_mc_probe_device() symbol is only available when the TEGRA_MC Kconfig option is enabled. Provide a stub if that's not the case so that the driver can be compile-tested. Reported-by: kernel test robot Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20210618111846.1286166-1-thierry.reding@gmail.com Signed-off-by: Krzysztof Kozlowski --- include/soc/tegra/mc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index e19c2504a14b..1066b1194a5a 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -237,14 +237,19 @@ unsigned int tegra_mc_get_emem_device_count(struct tegra_mc *mc); #ifdef CONFIG_TEGRA_MC struct tegra_mc *devm_tegra_memory_controller_get(struct device *dev); +int tegra_mc_probe_device(struct tegra_mc *mc, struct device *dev); #else static inline struct tegra_mc * devm_tegra_memory_controller_get(struct device *dev) { return ERR_PTR(-ENODEV); } + +static inline int +tegra_mc_probe_device(struct tegra_mc *mc, struct device *dev) +{ + return -ENODEV; +} #endif -int tegra_mc_probe_device(struct tegra_mc *mc, struct device *dev); - #endif /* __SOC_TEGRA_MC_H__ */ From bf3ec9deaa33889630722c47f7bb86ba58872ea7 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 21 Jun 2021 16:00:36 +0200 Subject: [PATCH 002/426] dt-bindings: arm-smmu: Fix json-schema syntax Commit 4287861dca9d ("dt-bindings: arm-smmu: Add Tegra186 compatible string") introduced a jsonschema syntax error as a result of a rebase gone wrong. Fix it. Fixes: 4287861dca9d ("dt-bindings: arm-smmu: Add Tegra186 compatible string") Reported-by: Rob Herring Signed-off-by: Thierry Reding Acked-by: Rob Herring Link: https://lore.kernel.org/r/20210621140036.2879563-1-thierry.reding@gmail.com Signed-off-by: Krzysztof Kozlowski --- Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index 1181b590db71..03f2b2d4db30 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -52,16 +52,14 @@ properties: items: - const: marvell,ap806-smmu-500 - const: arm,mmu-500 - - description: NVIDIA SoCs that program two ARM MMU-500s identically - items: - description: NVIDIA SoCs that require memory controller interaction and may program multiple ARM MMU-500s identically with the memory controller interleaving translations between multiple instances for improved performance. items: - enum: - - const: nvidia,tegra194-smmu - - const: nvidia,tegra186-smmu + - nvidia,tegra194-smmu + - nvidia,tegra186-smmu - const: nvidia,smmu-500 - items: - const: arm,mmu-500 From cc3ddee97cff034cea4d095de4a484c92a219bf5 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 21 Jan 2021 10:08:59 +0100 Subject: [PATCH 003/426] vboxsf: Honor excl flag to the dir-inode create op Honor the excl flag to the dir-inode create op, instead of behaving as if it is always set. Note the old behavior still worked most of the time since a non-exclusive open only calls the create op, if there is a race and the file is created between the dentry lookup and the calling of the create call. While at it change the type of the is_dir parameter to the vboxsf_dir_create() helper from an int to a bool, to be consistent with the use of bool for the excl parameter. Fixes: 0fd169576648 ("fs: Add VirtualBox guest shared folder (vboxsf) support") Signed-off-by: Hans de Goede --- fs/vboxsf/dir.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index eac6788fc6cf..6ff84343edca 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -253,7 +253,7 @@ static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry, } static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, - umode_t mode, int is_dir) + umode_t mode, bool is_dir, bool excl) { struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); @@ -261,10 +261,12 @@ static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, int err; params.handle = SHFL_HANDLE_NIL; - params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW | - SHFL_CF_ACT_FAIL_IF_EXISTS | - SHFL_CF_ACCESS_READWRITE | - (is_dir ? SHFL_CF_DIRECTORY : 0); + params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW | SHFL_CF_ACCESS_READWRITE; + if (is_dir) + params.create_flags |= SHFL_CF_DIRECTORY; + if (excl) + params.create_flags |= SHFL_CF_ACT_FAIL_IF_EXISTS; + params.info.attr.mode = (mode & 0777) | (is_dir ? SHFL_TYPE_DIRECTORY : SHFL_TYPE_FILE); params.info.attr.additional = SHFLFSOBJATTRADD_NOTHING; @@ -292,14 +294,14 @@ static int vboxsf_dir_mkfile(struct user_namespace *mnt_userns, struct inode *parent, struct dentry *dentry, umode_t mode, bool excl) { - return vboxsf_dir_create(parent, dentry, mode, 0); + return vboxsf_dir_create(parent, dentry, mode, false, excl); } static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns, struct inode *parent, struct dentry *dentry, umode_t mode) { - return vboxsf_dir_create(parent, dentry, mode, 1); + return vboxsf_dir_create(parent, dentry, mode, true, true); } static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) From ab0c29687bc7a890d1a86ac376b0b0fd78b2d9b6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 21 Jan 2021 10:22:27 +0100 Subject: [PATCH 004/426] vboxsf: Make vboxsf_dir_create() return the handle for the created file Make vboxsf_dir_create() optionally return the vboxsf-handle for the created file. This is a preparation patch for adding atomic_open support. Fixes: 0fd169576648 ("fs: Add VirtualBox guest shared folder (vboxsf) support") Signed-off-by: Hans de Goede --- fs/vboxsf/dir.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 6ff84343edca..87d5b2fef592 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -253,7 +253,7 @@ static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry, } static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, - umode_t mode, bool is_dir, bool excl) + umode_t mode, bool is_dir, bool excl, u64 *handle_ret) { struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent); struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); @@ -278,30 +278,34 @@ static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry, if (params.result != SHFL_FILE_CREATED) return -EPERM; - vboxsf_close(sbi->root, params.handle); - err = vboxsf_dir_instantiate(parent, dentry, ¶ms.info); if (err) - return err; + goto out; /* parent directory access/change time changed */ sf_parent_i->force_restat = 1; - return 0; +out: + if (err == 0 && handle_ret) + *handle_ret = params.handle; + else + vboxsf_close(sbi->root, params.handle); + + return err; } static int vboxsf_dir_mkfile(struct user_namespace *mnt_userns, struct inode *parent, struct dentry *dentry, umode_t mode, bool excl) { - return vboxsf_dir_create(parent, dentry, mode, false, excl); + return vboxsf_dir_create(parent, dentry, mode, false, excl, NULL); } static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns, struct inode *parent, struct dentry *dentry, umode_t mode) { - return vboxsf_dir_create(parent, dentry, mode, true, true); + return vboxsf_dir_create(parent, dentry, mode, true, true, NULL); } static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) From 02f840f90764f22f5c898901849bdbf0cee752ba Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 21 Jan 2021 10:55:03 +0100 Subject: [PATCH 005/426] vboxsf: Add vboxsf_[create|release]_sf_handle() helpers Factor out the code to create / release a struct vboxsf_handle into 2 new helper functions. This is a preparation patch for adding atomic_open support. Fixes: 0fd169576648 ("fs: Add VirtualBox guest shared folder (vboxsf) support") Signed-off-by: Hans de Goede --- fs/vboxsf/file.c | 73 ++++++++++++++++++++++++++++------------------ fs/vboxsf/vfsmod.h | 7 +++++ 2 files changed, 52 insertions(+), 28 deletions(-) diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c index c4ab5996d97a..864c2fad23be 100644 --- a/fs/vboxsf/file.c +++ b/fs/vboxsf/file.c @@ -20,18 +20,40 @@ struct vboxsf_handle { struct list_head head; }; -static int vboxsf_file_open(struct inode *inode, struct file *file) +struct vboxsf_handle *vboxsf_create_sf_handle(struct inode *inode, + u64 handle, u32 access_flags) { struct vboxsf_inode *sf_i = VBOXSF_I(inode); + struct vboxsf_handle *sf_handle; + + sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL); + if (!sf_handle) + return ERR_PTR(-ENOMEM); + + /* the host may have given us different attr then requested */ + sf_i->force_restat = 1; + + /* init our handle struct and add it to the inode's handles list */ + sf_handle->handle = handle; + sf_handle->root = VBOXSF_SBI(inode->i_sb)->root; + sf_handle->access_flags = access_flags; + kref_init(&sf_handle->refcount); + + mutex_lock(&sf_i->handle_list_mutex); + list_add(&sf_handle->head, &sf_i->handle_list); + mutex_unlock(&sf_i->handle_list_mutex); + + return sf_handle; +} + +static int vboxsf_file_open(struct inode *inode, struct file *file) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb); struct shfl_createparms params = {}; struct vboxsf_handle *sf_handle; u32 access_flags = 0; int err; - sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL); - if (!sf_handle) - return -ENOMEM; - /* * We check the value of params.handle afterwards to find out if * the call succeeded or failed, as the API does not seem to cleanly @@ -83,24 +105,15 @@ static int vboxsf_file_open(struct inode *inode, struct file *file) err = vboxsf_create_at_dentry(file_dentry(file), ¶ms); if (err == 0 && params.handle == SHFL_HANDLE_NIL) err = (params.result == SHFL_FILE_EXISTS) ? -EEXIST : -ENOENT; - if (err) { - kfree(sf_handle); + if (err) return err; + + sf_handle = vboxsf_create_sf_handle(inode, params.handle, access_flags); + if (IS_ERR(sf_handle)) { + vboxsf_close(sbi->root, params.handle); + return PTR_ERR(sf_handle); } - /* the host may have given us different attr then requested */ - sf_i->force_restat = 1; - - /* init our handle struct and add it to the inode's handles list */ - sf_handle->handle = params.handle; - sf_handle->root = VBOXSF_SBI(inode->i_sb)->root; - sf_handle->access_flags = access_flags; - kref_init(&sf_handle->refcount); - - mutex_lock(&sf_i->handle_list_mutex); - list_add(&sf_handle->head, &sf_i->handle_list); - mutex_unlock(&sf_i->handle_list_mutex); - file->private_data = sf_handle; return 0; } @@ -114,22 +127,26 @@ static void vboxsf_handle_release(struct kref *refcount) kfree(sf_handle); } -static int vboxsf_file_release(struct inode *inode, struct file *file) +void vboxsf_release_sf_handle(struct inode *inode, struct vboxsf_handle *sf_handle) { struct vboxsf_inode *sf_i = VBOXSF_I(inode); - struct vboxsf_handle *sf_handle = file->private_data; - - /* - * When a file is closed on our (the guest) side, we want any subsequent - * accesses done on the host side to see all changes done from our side. - */ - filemap_write_and_wait(inode->i_mapping); mutex_lock(&sf_i->handle_list_mutex); list_del(&sf_handle->head); mutex_unlock(&sf_i->handle_list_mutex); kref_put(&sf_handle->refcount, vboxsf_handle_release); +} + +static int vboxsf_file_release(struct inode *inode, struct file *file) +{ + /* + * When a file is closed on our (the guest) side, we want any subsequent + * accesses done on the host side to see all changes done from our side. + */ + filemap_write_and_wait(inode->i_mapping); + + vboxsf_release_sf_handle(inode, file->private_data); return 0; } diff --git a/fs/vboxsf/vfsmod.h b/fs/vboxsf/vfsmod.h index 6a7a9cedebc6..9047befa66c5 100644 --- a/fs/vboxsf/vfsmod.h +++ b/fs/vboxsf/vfsmod.h @@ -18,6 +18,8 @@ #define VBOXSF_SBI(sb) ((struct vboxsf_sbi *)(sb)->s_fs_info) #define VBOXSF_I(i) container_of(i, struct vboxsf_inode, vfs_inode) +struct vboxsf_handle; + struct vboxsf_options { unsigned long ttl; kuid_t uid; @@ -80,6 +82,11 @@ extern const struct file_operations vboxsf_reg_fops; extern const struct address_space_operations vboxsf_reg_aops; extern const struct dentry_operations vboxsf_dentry_ops; +/* from file.c */ +struct vboxsf_handle *vboxsf_create_sf_handle(struct inode *inode, + u64 handle, u32 access_flags); +void vboxsf_release_sf_handle(struct inode *inode, struct vboxsf_handle *sf_handle); + /* from utils.c */ struct inode *vboxsf_new_inode(struct super_block *sb); int vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode, From 52dfd86aa568e433b24357bb5fc725560f1e22d8 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 21 Jan 2021 12:54:18 +0100 Subject: [PATCH 006/426] vboxsf: Add support for the atomic_open directory-inode op Opening a new file is done in 2 steps on regular filesystems: 1. Call the create inode-op on the parent-dir to create an inode to hold the meta-data related to the file. 2. Call the open file-op to get a handle for the file. vboxsf however does not really use disk-backed inodes because it is based on passing through file-related system-calls through to the hypervisor. So both steps translate to an open(2) call being passed through to the hypervisor. With the handle returned by the first call immediately being closed again. Making 2 open calls for a single open(..., O_CREATE, ...) calls has 2 problems: a) It is not really efficient. b) It actually breaks some apps. An example of b) is doing a git clone inside a vboxsf mount. When git clone tries to create a tempfile to store the pak files which is downloading the following happens: 1. vboxsf_dir_mkfile() gets called with a mode of 0444 and succeeds. 2. vboxsf_file_open() gets called with file->f_flags containing O_RDWR. When the host is a Linux machine this fails because doing a open(..., O_RDWR) on a file which exists and has mode 0444 results in an -EPERM error. Other network-filesystems and fuse avoid the problem of needing to pass 2 open() calls to the other side by using the atomic_open directory-inode op. This commit fixes git clone not working inside a vboxsf mount, by adding support for the atomic_open directory-inode op. As an added bonus this should also make opening new files faster. The atomic_open implementation is modelled after the atomic_open implementations from the 9p and fuse code. Fixes: 0fd169576648 ("fs: Add VirtualBox guest shared folder (vboxsf) support") Reported-by: Ludovic Pouzenc Signed-off-by: Hans de Goede --- fs/vboxsf/dir.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 87d5b2fef592..c4769a9396c5 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -308,6 +308,53 @@ static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns, return vboxsf_dir_create(parent, dentry, mode, true, true, NULL); } +static int vboxsf_dir_atomic_open(struct inode *parent, struct dentry *dentry, + struct file *file, unsigned int flags, umode_t mode) +{ + struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); + struct vboxsf_handle *sf_handle; + struct dentry *res = NULL; + u64 handle; + int err; + + if (d_in_lookup(dentry)) { + res = vboxsf_dir_lookup(parent, dentry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + dentry = res; + } + + /* Only creates */ + if (!(flags & O_CREAT) || d_really_is_positive(dentry)) + return finish_no_open(file, res); + + err = vboxsf_dir_create(parent, dentry, mode, false, flags & O_EXCL, &handle); + if (err) + goto out; + + sf_handle = vboxsf_create_sf_handle(d_inode(dentry), handle, SHFL_CF_ACCESS_READWRITE); + if (IS_ERR(sf_handle)) { + vboxsf_close(sbi->root, handle); + err = PTR_ERR(sf_handle); + goto out; + } + + err = finish_open(file, dentry, generic_file_open); + if (err) { + /* This also closes the handle passed to vboxsf_create_sf_handle() */ + vboxsf_release_sf_handle(d_inode(dentry), sf_handle); + goto out; + } + + file->private_data = sf_handle; + file->f_mode |= FMODE_CREATED; +out: + dput(res); + return err; +} + static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry) { struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb); @@ -428,6 +475,7 @@ const struct inode_operations vboxsf_dir_iops = { .lookup = vboxsf_dir_lookup, .create = vboxsf_dir_mkfile, .mkdir = vboxsf_dir_mkdir, + .atomic_open = vboxsf_dir_atomic_open, .rmdir = vboxsf_dir_unlink, .unlink = vboxsf_dir_unlink, .rename = vboxsf_dir_rename, From ca46ad2214473df1a6a9496be17156d65ba89b9f Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Jun 2021 18:37:42 +0930 Subject: [PATCH 007/426] ARM: dts: aspeed: Fix AST2600 machines line names Tacoma and Rainier both have a line-names array that is too long: gpio gpiochip0: gpio-line-names is length 232 but should be at most length 208 This was probably copied from an AST2500 device tree that did have more GPIOs on the controller. Fixes: e9b24b55ca4f ("ARM: dts: aspeed: rainier: Add gpio line names") Fixes: 2f68e4e7df67 ("ARM: dts: aspeed: tacoma: Add gpio line names") Link: https://lore.kernel.org/r/20210624090742.56640-1-joel@jms.id.au Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts | 5 +---- arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts | 5 +---- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts index 941c0489479a..481d0ee1f85f 100644 --- a/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts +++ b/arch/arm/boot/dts/aspeed-bmc-ibm-rainier.dts @@ -280,10 +280,7 @@ /*W0-W7*/ "","","","","","","","", /*X0-X7*/ "","","","","","","","", /*Y0-Y7*/ "","","","","","","","", - /*Z0-Z7*/ "","","","","","","","", - /*AA0-AA7*/ "","","","","","","","", - /*AB0-AB7*/ "","","","","","","","", - /*AC0-AC7*/ "","","","","","","",""; + /*Z0-Z7*/ "","","","","","","",""; pin_mclr_vpp { gpio-hog; diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts index e863ec088970..48038b2ef3df 100644 --- a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts +++ b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts @@ -136,10 +136,7 @@ /*W0-W7*/ "","","","","","","","", /*X0-X7*/ "","","","","","","","", /*Y0-Y7*/ "","","","","","","","", - /*Z0-Z7*/ "","","","","","","","", - /*AA0-AA7*/ "","","","","","","","", - /*AB0-AB7*/ "","","","","","","","", - /*AC0-AC7*/ "","","","","","","",""; + /*Z0-Z7*/ "","","","","","","",""; }; &fmc { From 1988e0d84161dabd99d1c27033fbd6ee439bf432 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 4 Jun 2021 01:18:30 +0200 Subject: [PATCH 008/426] drm/panel: nt35510: Do not fail if DSI read fails Failing to read the MTP over DSI should not bring down the system and make us bail out from using the display, it turns out that this happens when toggling the display off and on, and that write is often still working so the display output is just fine. Printing an error is enough. Tested by killing the Gnome session repeatedly on the Samsung Skomer. Fixes: 899f24ed8d3a ("drm/panel: Add driver for Novatek NT35510-based panels") Cc: Stephan Gerhold Reported-by: newbyte@disroot.org Acked-by: Stefan Hansson Signed-off-by: Linus Walleij Link: https://patchwork.freedesktop.org/patch/msgid/20210603231830.3200040-1-linus.walleij@linaro.org --- drivers/gpu/drm/panel/panel-novatek-nt35510.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35510.c b/drivers/gpu/drm/panel/panel-novatek-nt35510.c index ef70140c5b09..873cbd38e6d3 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt35510.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt35510.c @@ -706,9 +706,7 @@ static int nt35510_power_on(struct nt35510 *nt) if (ret) return ret; - ret = nt35510_read_id(nt); - if (ret) - return ret; + nt35510_read_id(nt); /* Set up stuff in manufacturer control, page 1 */ ret = nt35510_send_long(nt, dsi, MCS_CMD_MAUCCTR, From 812bae32e5d50914f75a6e036d3bde39ca86b0c3 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Fri, 16 Apr 2021 02:51:13 -0500 Subject: [PATCH 009/426] ARM: dts: aspeed: Update e3c246d4i vuart properties This device-tree was merged with a provisional vuart IRQ-polarity property that was still under review and ended up taking a somewhat different form. This patch updates it to match the final form of the new vuart properties, which additionally allow specifying the SIRQ number and LPC address. Signed-off-by: Zev Weiss Reviewed-by: Andrew Jeffery Fixes: ca03042f0f12 ("serial: 8250_aspeed_vuart: add aspeed, lpc-io-reg and aspeed, lpc-interrupts DT properties") Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/20210416075113.18047-1-zev@bewilderbeest.net Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts b/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts index 33e413ca07e4..9b4cf5ebe6d5 100644 --- a/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts +++ b/arch/arm/boot/dts/aspeed-bmc-asrock-e3c246d4i.dts @@ -4,6 +4,7 @@ #include "aspeed-g5.dtsi" #include #include +#include /{ model = "ASRock E3C246D4I BMC"; @@ -73,7 +74,8 @@ &vuart { status = "okay"; - aspeed,sirq-active-high; + aspeed,lpc-io-reg = <0x2f8>; + aspeed,lpc-interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; }; &mac0 { From 2d6608b57c50c54c3e46649110e8ea5a40959c30 Mon Sep 17 00:00:00 2001 From: Andrew Jeffery Date: Fri, 25 Jun 2021 15:40:17 +0930 Subject: [PATCH 010/426] ARM: dts: tacoma: Add phase corrections for eMMC The degree values were reversed out from the magic tap values of 7 (in) and 15 + inversion (out) initially suggested by Aspeed. With the patch tacoma survives several gigabytes of reads and writes using dd while without it locks up randomly during the boot process. Signed-off-by: Andrew Jeffery Link: https://lore.kernel.org/r/20210625061017.1149942-1-andrew@aj.id.au Fixes: 2fc88f92359d ("mmc: sdhci-of-aspeed: Expose clock phase controls") Fixes: 961216c135a8 ("ARM: dts: aspeed: Add Rainier system") Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts index 48038b2ef3df..e33153dcaea8 100644 --- a/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts +++ b/arch/arm/boot/dts/aspeed-bmc-opp-tacoma.dts @@ -186,6 +186,7 @@ &emmc { status = "okay"; + clk-phase-mmc-hs200 = <36>, <270>; }; &fsim0 { From faffd1b2bde3ee428d6891961f6a60f8e08749d6 Mon Sep 17 00:00:00 2001 From: Andrew Jeffery Date: Mon, 28 Jun 2021 11:06:05 +0930 Subject: [PATCH 011/426] ARM: dts: everest: Add phase corrections for eMMC The values were determined experimentally via boot tests, not by measuring the bus behaviour with a scope. We plan to do scope measurements to confirm or refine the values and will update the devicetree if necessary once these have been obtained. However, with the patch we can write and read data without issue, where as booting the system without the patch failed at the point of mounting the rootfs. Signed-off-by: Andrew Jeffery Link: https://lore.kernel.org/r/20210628013605.1257346-1-andrew@aj.id.au Fixes: 2fc88f92359d ("mmc: sdhci-of-aspeed: Expose clock phase controls") Fixes: a5c5168478d7 ("ARM: dts: aspeed: Add Everest BMC machine") Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts index d26a9e16ff7c..53c049daf853 100644 --- a/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts +++ b/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts @@ -2832,6 +2832,7 @@ &emmc { status = "okay"; + clk-phase-mmc-hs200 = <180>, <180>; }; &fsim0 { From ab4a49d36010564c70fe5586a4c2b1985866616f Mon Sep 17 00:00:00 2001 From: "B. J. Wyman" Date: Thu, 10 Jun 2021 20:29:41 +0000 Subject: [PATCH 012/426] ARM: dts: aspeed: everest: PSU #3 address change The third power supply had an I2C address conflict with another device in the system. The device will have the address changed from 6Ah to 6Dh. Signed-off-by: B. J. Wyman Reviewed-by: Eddie James Link: https://lore.kernel.org/r/20210610202940.3650554-1-bjwyman@gmail.com Fixes: d66d720b64e5 ("ARM: dts: aspeed: everest: Add power supply i2c devices") Signed-off-by: Joel Stanley --- arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts index 53c049daf853..aa24cac8e5be 100644 --- a/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts +++ b/arch/arm/boot/dts/aspeed-bmc-ibm-everest.dts @@ -406,15 +406,15 @@ reg = <0x69>; }; - power-supply@6a { - compatible = "ibm,cffps"; - reg = <0x6a>; - }; - power-supply@6b { compatible = "ibm,cffps"; reg = <0x6b>; }; + + power-supply@6d { + compatible = "ibm,cffps"; + reg = <0x6d>; + }; }; &i2c4 { From 0fc4dcc13f090c941abfab453a24945a4005b350 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Tue, 29 Jun 2021 11:39:07 +0200 Subject: [PATCH 013/426] bpf, devmap: Convert remaining READ_ONCE() to rcu_dereference_check() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There were a couple of READ_ONCE()-invocations left-over by the devmap RCU conversion. Convert these to rcu_dereference_check() as well to avoid complaints from sparse. Fixes: 782347b6bcad ("xdp: Add proper __rcu annotations to redirect map entries") Reported-by: kernel test robot Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Reviewed-by: Paul E. McKenney Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210629093907.573598-1-toke@redhat.com --- kernel/bpf/devmap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2546dafd6672..fdc20892837c 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -558,7 +558,8 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { - dst = READ_ONCE(dtab->netdev_map[i]); + dst = rcu_dereference_check(dtab->netdev_map[i], + rcu_read_lock_bh_held()); if (!is_valid_dst(dst, xdp, exclude_ifindex)) continue; @@ -654,7 +655,8 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { - dst = READ_ONCE(dtab->netdev_map[i]); + dst = rcu_dereference_check(dtab->netdev_map[i], + rcu_read_lock_bh_held()); if (!dst || dst->dev->ifindex == exclude_ifindex) continue; From 56ea7ed103b46970e171eb1c95916f393d64eeff Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Thu, 13 May 2021 17:31:03 -0700 Subject: [PATCH 014/426] igc: Fix use-after-free error during reset Cleans the next descriptor to watch (next_to_watch) when cleaning the TX ring. Failure to do so can cause invalid memory accesses. If igc_poll() runs while the controller is being reset this can lead to the driver try to free a skb that was already freed. Log message: [ 101.525242] refcount_t: underflow; use-after-free. [ 101.525251] WARNING: CPU: 1 PID: 646 at lib/refcount.c:28 refcount_warn_saturate+0xab/0xf0 [ 101.525259] Modules linked in: sch_etf(E) sch_mqprio(E) rfkill(E) intel_rapl_msr(E) intel_rapl_common(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) binfmt_misc(E) kvm_intel(E) kvm(E) irqbypass(E) crc32_pclmul(E) ghash_clmulni_intel(E) aesni_intel(E) mei_wdt(E) libaes(E) crypto_simd(E) cryptd(E) glue_helper(E) snd_hda_codec_hdmi(E) rapl(E) intel_cstate(E) snd_hda_intel(E) snd_intel_dspcfg(E) sg(E) soundwire_intel(E) intel_uncore(E) at24(E) soundwire_generic_allocation(E) iTCO_wdt(E) soundwire_cadence(E) intel_pmc_bxt(E) serio_raw(E) snd_hda_codec(E) iTCO_vendor_support(E) watchdog(E) snd_hda_core(E) snd_hwdep(E) snd_soc_core(E) snd_compress(E) snd_pcsp(E) soundwire_bus(E) snd_pcm(E) evdev(E) snd_timer(E) mei_me(E) snd(E) soundcore(E) mei(E) configfs(E) ip_tables(E) x_tables(E) autofs4(E) ext4(E) crc32c_generic(E) crc16(E) mbcache(E) jbd2(E) sd_mod(E) t10_pi(E) crc_t10dif(E) crct10dif_generic(E) i915(E) ahci(E) libahci(E) ehci_pci(E) igb(E) xhci_pci(E) ehci_hcd(E) [ 101.525303] drm_kms_helper(E) dca(E) xhci_hcd(E) libata(E) crct10dif_pclmul(E) cec(E) crct10dif_common(E) tsn(E) igc(E) e1000e(E) ptp(E) i2c_i801(E) crc32c_intel(E) psmouse(E) i2c_algo_bit(E) i2c_smbus(E) scsi_mod(E) lpc_ich(E) pps_core(E) usbcore(E) drm(E) button(E) video(E) [ 101.525318] CPU: 1 PID: 646 Comm: irq/37-enp7s0-T Tainted: G E 5.10.30-rt37-tsn1-rt-ipipe #ipipe [ 101.525320] Hardware name: SIEMENS AG SIMATIC IPC427D/A5E31233588, BIOS V17.02.09 03/31/2017 [ 101.525322] RIP: 0010:refcount_warn_saturate+0xab/0xf0 [ 101.525325] Code: 05 31 48 44 01 01 e8 f0 c6 42 00 0f 0b c3 80 3d 1f 48 44 01 00 75 90 48 c7 c7 78 a8 f3 a6 c6 05 0f 48 44 01 01 e8 d1 c6 42 00 <0f> 0b c3 80 3d fe 47 44 01 00 0f 85 6d ff ff ff 48 c7 c7 d0 a8 f3 [ 101.525327] RSP: 0018:ffffbdedc0917cb8 EFLAGS: 00010286 [ 101.525329] RAX: 0000000000000000 RBX: ffff98fd6becbf40 RCX: 0000000000000001 [ 101.525330] RDX: 0000000000000001 RSI: ffffffffa6f2700c RDI: 00000000ffffffff [ 101.525332] RBP: ffff98fd6becc14c R08: ffffffffa7463d00 R09: ffffbdedc0917c50 [ 101.525333] R10: ffffffffa74c3578 R11: 0000000000000034 R12: 00000000ffffff00 [ 101.525335] R13: ffff98fd6b0b1000 R14: 0000000000000039 R15: ffff98fd6be35c40 [ 101.525337] FS: 0000000000000000(0000) GS:ffff98fd6e240000(0000) knlGS:0000000000000000 [ 101.525339] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 101.525341] CR2: 00007f34135a3a70 CR3: 0000000150210003 CR4: 00000000001706e0 [ 101.525343] Call Trace: [ 101.525346] sock_wfree+0x9c/0xa0 [ 101.525353] unix_destruct_scm+0x7b/0xa0 [ 101.525358] skb_release_head_state+0x40/0x90 [ 101.525362] skb_release_all+0xe/0x30 [ 101.525364] napi_consume_skb+0x57/0x160 [ 101.525367] igc_poll+0xb7/0xc80 [igc] [ 101.525376] ? sched_clock+0x5/0x10 [ 101.525381] ? sched_clock_cpu+0xe/0x100 [ 101.525385] net_rx_action+0x14c/0x410 [ 101.525388] __do_softirq+0xe9/0x2f4 [ 101.525391] __local_bh_enable_ip+0xe3/0x110 [ 101.525395] ? irq_finalize_oneshot.part.47+0xe0/0xe0 [ 101.525398] irq_forced_thread_fn+0x6a/0x80 [ 101.525401] irq_thread+0xe8/0x180 [ 101.525403] ? wake_threads_waitq+0x30/0x30 [ 101.525406] ? irq_thread_check_affinity+0xd0/0xd0 [ 101.525408] kthread+0x183/0x1a0 [ 101.525412] ? kthread_park+0x80/0x80 [ 101.525415] ret_from_fork+0x22/0x30 Fixes: 13b5b7fd6a4a ("igc: Add support for Tx/Rx rings") Reported-by: Erez Geva Signed-off-by: Vinicius Costa Gomes Tested-by: Dvora Fuxbrumer Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 95323095094d..1d00a63eb935 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -232,6 +232,8 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); } + tx_buffer->next_to_watch = NULL; + /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; i++; From 7b292608db23ccbbfbfa50cdb155d01725d7a52e Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Thu, 13 May 2021 17:31:04 -0700 Subject: [PATCH 015/426] igb: Fix use-after-free error during reset Cleans the next descriptor to watch (next_to_watch) when cleaning the TX ring. Failure to do so can cause invalid memory accesses. If igb_poll() runs while the controller is reset this can lead to the driver try to free a skb that was already freed. (The crash is harder to reproduce with the igb driver, but the same potential problem exists as the code is identical to igc) Fixes: 7cc6fd4c60f2 ("igb: Don't bother clearing Tx buffer_info in igb_clean_tx_ring") Signed-off-by: Vinicius Costa Gomes Reported-by: Erez Geva Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 7e6435dc7e80..a61e2e5e95c0 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4835,6 +4835,8 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) DMA_TO_DEVICE); } + tx_buffer->next_to_watch = NULL; + /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; i++; From 05682a0a61b6cbecd97a0f37f743b2cbfd516977 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 21 May 2021 12:50:19 -0700 Subject: [PATCH 016/426] igc: change default return of igc_read_phy_reg() Static analysis reports this problem igc_main.c:4944:20: warning: The left operand of '&' is a garbage value if (!(phy_data & SR_1000T_REMOTE_RX_STATUS) && ~~~~~~~~ ^ phy_data is set by the call to igc_read_phy_reg() only if there is a read_reg() op, else it is unset and a 0 is returned. Change the return to -EOPNOTSUPP. Fixes: 208983f099d9 ("igc: Add watchdog") Signed-off-by: Tom Rix Tested-by: Dvora Fuxbrumer Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 9e0bbb2e55e3..5901ed9fb545 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -578,7 +578,7 @@ static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data) if (hw->phy.ops.read_reg) return hw->phy.ops.read_reg(hw, offset, data); - return 0; + return -EOPNOTSUPP; } void igc_reinit_locked(struct igc_adapter *); From dd2aefcd5e37989ae5f90afdae44bbbf3a2990da Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 12 Jun 2021 15:46:09 +0200 Subject: [PATCH 017/426] ixgbe: Fix an error handling path in 'ixgbe_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 6fabd715e6d8 ("ixgbe: Implement PCIe AER support") Signed-off-by: Christophe JAILLET Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ffff69efd78a..913253f8ecb4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -11067,6 +11067,7 @@ err_ioremap: disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From c6bc9e5ce5d37cb3e6b552f41b92a193db1806ab Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 12 Jun 2021 22:00:05 +0200 Subject: [PATCH 018/426] igc: Fix an error handling path in 'igc_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: c9a11c23ceb6 ("igc: Add netdev") Signed-off-by: Christophe JAILLET Tested-by: Dvora Fuxbrumer Acked-by: Sasha Neftin Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 1d00a63eb935..e29aadbc6744 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6056,6 +6056,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From fea03b1cebd653cd095f2e9a58cfe1c85661c363 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 12 Jun 2021 22:08:33 +0200 Subject: [PATCH 019/426] igb: Fix an error handling path in 'igb_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 40a914fa72ab ("igb: Add support for pci-e Advanced Error Reporting") Signed-off-by: Christophe JAILLET Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a61e2e5e95c0..abc239b736fb 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3615,6 +3615,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From e85e14d68f517ef12a5fb8123fff65526b35b6cd Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 16 Jun 2021 07:00:36 +0200 Subject: [PATCH 020/426] fm10k: Fix an error handling path in 'fm10k_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 19ae1b3fb99c ("fm10k: Add support for PCI power management and error handling") Signed-off-by: Christophe JAILLET Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index dbcae92bb18d..adfa2768f024 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -2227,6 +2227,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_netdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From 4589075608420bc49fcef6e98279324bf2bb91ae Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 16 Jun 2021 07:05:53 +0200 Subject: [PATCH 021/426] e1000e: Fix an error handling path in 'e1000_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 111b9dc5c981 ("e1000e: add aer support") Signed-off-by: Christophe JAILLET Acked-by: Sasha Neftin Tested-by: Dvora Fuxbrumer Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e1000e/netdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index d150dade06cf..757a54c39eef 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7664,6 +7664,7 @@ err_flashmap: err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: From af30cbd2f4d6d66a9b6094e0aa32420bc8b20e08 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 16 Jun 2021 07:53:02 +0200 Subject: [PATCH 022/426] iavf: Fix an error handling path in 'iavf_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 5eae00c57f5e ("i40evf: main driver core") Signed-off-by: Christophe JAILLET Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index e612c24fa384..44bafedd09f2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3798,6 +3798,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_pci_reg: err_dma: From 6c19d772618fea40d9681f259368f284a330fd90 Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Thu, 22 Apr 2021 10:19:23 +0000 Subject: [PATCH 023/426] igb: Check if num of q_vectors is smaller than max before array access Ensure that the adapter->q_vector[MAX_Q_VECTORS] array isn't accessed beyond its size. It was fixed by using a local variable num_q_vectors as a limit for loop index, and ensure that num_q_vectors is not bigger than MAX_Q_VECTORS. Fixes: 047e0030f1e6 ("igb: add new data structure for handling interrupts and NAPI") Signed-off-by: Aleksandr Loktionov Reviewed-by: Grzegorz Siwik Reviewed-by: Arkadiusz Kubalewski Reviewed-by: Slawomir Laba Reviewed-by: Sylwester Dziedziuch Reviewed-by: Mateusz Palczewski Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index abc239b736fb..9470ba891483 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -931,6 +931,7 @@ static void igb_configure_msix(struct igb_adapter *adapter) **/ static int igb_request_msix(struct igb_adapter *adapter) { + unsigned int num_q_vectors = adapter->num_q_vectors; struct net_device *netdev = adapter->netdev; int i, err = 0, vector = 0, free_vector = 0; @@ -939,7 +940,13 @@ static int igb_request_msix(struct igb_adapter *adapter) if (err) goto err_out; - for (i = 0; i < adapter->num_q_vectors; i++) { + if (num_q_vectors > MAX_Q_VECTORS) { + num_q_vectors = MAX_Q_VECTORS; + dev_warn(&adapter->pdev->dev, + "The number of queue vectors (%d) is higher than max allowed (%d)\n", + adapter->num_q_vectors, MAX_Q_VECTORS); + } + for (i = 0; i < num_q_vectors; i++) { struct igb_q_vector *q_vector = adapter->q_vector[i]; vector++; From 382a7c20d9253bcd5715789b8179528d0f3de72c Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Fri, 11 Jun 2021 22:42:17 +0000 Subject: [PATCH 024/426] igb: Fix position of assignment to *ring Assignment to *ring should be done after correctness check of the argument queue. Fixes: 91db364236c8 ("igb: Refactor igb_configure_cbs()") Signed-off-by: Jedrzej Jagielski Acked-by: Vinicius Costa Gomes Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 9470ba891483..171a7a629b20 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1685,14 +1685,15 @@ static bool is_any_txtime_enabled(struct igb_adapter *adapter) **/ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue) { - struct igb_ring *ring = adapter->tx_ring[queue]; struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; + struct igb_ring *ring; u32 tqavcc, tqavctrl; u16 value; WARN_ON(hw->mac.type != e1000_i210); WARN_ON(queue < 0 || queue > 1); + ring = adapter->tx_ring[queue]; /* If any of the Qav features is enabled, configure queues as SR and * with HIGH PRIO. If none is, then configure them with LOW PRIO and From a3609ac24c18947737f5bc1746b8735814c521d1 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 29 Jun 2021 06:43:05 +0200 Subject: [PATCH 025/426] net: usb: asix: ax88772: suspend PHY on driver probe After probe/bind sequence is the PHY in active state, even if interface is stopped. As result, on some systems like Samsung Exynos5250 SoC based Arndale board, the ASIX PHY will be able to negotiate the link but fail to transmit the data. To handle it, suspend the PHY on probe. Fixes: e532a096be0e ("net: usb: asix: ax88772: add phylib support") Signed-off-by: Oleksij Rempel Reported-by: Marek Szyprowski Tested-by: Marek Szyprowski Signed-off-by: David S. Miller --- drivers/net/usb/asix_devices.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index aec97b021a73..2c115216420a 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -701,6 +701,7 @@ static int ax88772_init_phy(struct usbnet *dev) return ret; } + phy_suspend(priv->phydev); priv->phydev->mac_managed_pm = 1; phy_attached_info(priv->phydev); From b18114476a1432ad1db5d5605bc8cd131814d264 Mon Sep 17 00:00:00 2001 From: Baowen Zheng Date: Tue, 29 Jun 2021 09:22:11 +0200 Subject: [PATCH 026/426] openvswitch: Optimize operation for key comparison In the current implement when comparing two flow keys, we will return result after comparing the whole key from start to end. In our optimization, we will return result in the first none-zero comparison, then we will improve the flow table looking up efficiency. Signed-off-by: Baowen Zheng Signed-off-by: Louis Peens Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- net/openvswitch/flow_table.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index c89c8da99f1a..d4a2db0b2299 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -670,13 +670,13 @@ static bool cmp_key(const struct sw_flow_key *key1, { const long *cp1 = (const long *)((const u8 *)key1 + key_start); const long *cp2 = (const long *)((const u8 *)key2 + key_start); - long diffs = 0; int i; for (i = key_start; i < key_end; i += sizeof(long)) - diffs |= *cp1++ ^ *cp2++; + if (*cp1++ ^ *cp2++) + return false; - return diffs == 0; + return true; } static bool flow_cmp_masked_key(const struct sw_flow *flow, From 996af62167d0e0ec69b938a3561e96f84ffff1aa Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 29 Jun 2021 15:22:37 +0800 Subject: [PATCH 027/426] net/802/mrp: fix memleak in mrp_request_join() I got kmemleak report when doing fuzz test: BUG: memory leak unreferenced object 0xffff88810c239500 (size 64): comm "syz-executor940", pid 882, jiffies 4294712870 (age 14.631s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 01 00 00 00 01 02 00 04 ................ backtrace: [<00000000a323afa4>] slab_alloc_node mm/slub.c:2972 [inline] [<00000000a323afa4>] slab_alloc mm/slub.c:2980 [inline] [<00000000a323afa4>] __kmalloc+0x167/0x340 mm/slub.c:4130 [<000000005034ca11>] kmalloc include/linux/slab.h:595 [inline] [<000000005034ca11>] mrp_attr_create net/802/mrp.c:276 [inline] [<000000005034ca11>] mrp_request_join+0x265/0x550 net/802/mrp.c:530 [<00000000fcfd81f3>] vlan_mvrp_request_join+0x145/0x170 net/8021q/vlan_mvrp.c:40 [<000000009258546e>] vlan_dev_open+0x477/0x890 net/8021q/vlan_dev.c:292 [<0000000059acd82b>] __dev_open+0x281/0x410 net/core/dev.c:1609 [<000000004e6dc695>] __dev_change_flags+0x424/0x560 net/core/dev.c:8767 [<00000000471a09af>] rtnl_configure_link+0xd9/0x210 net/core/rtnetlink.c:3122 [<0000000037a4672b>] __rtnl_newlink+0xe08/0x13e0 net/core/rtnetlink.c:3448 [<000000008d5d0fda>] rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3488 [<000000004882fe39>] rtnetlink_rcv_msg+0x369/0xa10 net/core/rtnetlink.c:5552 [<00000000907e6c54>] netlink_rcv_skb+0x134/0x3d0 net/netlink/af_netlink.c:2504 [<00000000e7d7a8c4>] netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] [<00000000e7d7a8c4>] netlink_unicast+0x4a0/0x6a0 net/netlink/af_netlink.c:1340 [<00000000e0645d50>] netlink_sendmsg+0x78e/0xc90 net/netlink/af_netlink.c:1929 [<00000000c24559b7>] sock_sendmsg_nosec net/socket.c:654 [inline] [<00000000c24559b7>] sock_sendmsg+0x139/0x170 net/socket.c:674 [<00000000fc210bc2>] ____sys_sendmsg+0x658/0x7d0 net/socket.c:2350 [<00000000be4577b5>] ___sys_sendmsg+0xf8/0x170 net/socket.c:2404 Calling mrp_request_leave() after mrp_request_join(), the attr->state is set to MRP_APPLICANT_VO, mrp_attr_destroy() won't be called in last TX event in mrp_uninit_applicant(), the attr of applicant will be leaked. To fix this leak, iterate and free each attr of applicant before rerturning from mrp_uninit_applicant(). Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller --- net/802/mrp.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/net/802/mrp.c b/net/802/mrp.c index bea6e43d45a0..35e04cc5390c 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -292,6 +292,19 @@ static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr) kfree(attr); } +static void mrp_attr_destroy_all(struct mrp_applicant *app) +{ + struct rb_node *node, *next; + struct mrp_attr *attr; + + for (node = rb_first(&app->mad); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct mrp_attr, node); + mrp_attr_destroy(app, attr); + } +} + static int mrp_pdu_init(struct mrp_applicant *app) { struct sk_buff *skb; @@ -895,6 +908,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); + mrp_attr_destroy_all(app); mrp_pdu_queue(app); spin_unlock_bh(&app->lock); From a34dcbfa1475f18a8f1b1dc3dedb76d746874e61 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 29 Jun 2021 11:19:44 +0300 Subject: [PATCH 028/426] sctp: prevent info leak in sctp_make_heartbeat() The "hbinfo" struct has a 4 byte hole at the end so we have to zero it out to prevent stack information from being disclosed. Fixes: fe59379b9ab7 ("sctp: do the basic send and recv for PLPMTUD probe") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- net/sctp/sm_make_chunk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 6c08e5048d38..b8fa8f1a7277 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1163,7 +1163,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport, __u32 probe_size) { - struct sctp_sender_hb_info hbinfo; + struct sctp_sender_hb_info hbinfo = {}; struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0, From 42ca63f980842918560b25f0244307fd83b4777c Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 29 Jun 2021 19:53:28 +0800 Subject: [PATCH 029/426] net/802/garp: fix memleak in garp_request_join() I got kmemleak report when doing fuzz test: BUG: memory leak unreferenced object 0xffff88810c909b80 (size 64): comm "syz", pid 957, jiffies 4295220394 (age 399.090s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 08 00 00 00 01 02 00 04 ................ backtrace: [<00000000ca1f2e2e>] garp_request_join+0x285/0x3d0 [<00000000bf153351>] vlan_gvrp_request_join+0x15b/0x190 [<0000000024005e72>] vlan_dev_open+0x706/0x980 [<00000000dc20c4d4>] __dev_open+0x2bb/0x460 [<0000000066573004>] __dev_change_flags+0x501/0x650 [<0000000035b42f83>] rtnl_configure_link+0xee/0x280 [<00000000a5e69de0>] __rtnl_newlink+0xed5/0x1550 [<00000000a5258f4a>] rtnl_newlink+0x66/0x90 [<00000000506568ee>] rtnetlink_rcv_msg+0x439/0xbd0 [<00000000b7eaeae1>] netlink_rcv_skb+0x14d/0x420 [<00000000c373ce66>] netlink_unicast+0x550/0x750 [<00000000ec74ce74>] netlink_sendmsg+0x88b/0xda0 [<00000000381ff246>] sock_sendmsg+0xc9/0x120 [<000000008f6a2db3>] ____sys_sendmsg+0x6e8/0x820 [<000000008d9c1735>] ___sys_sendmsg+0x145/0x1c0 [<00000000aa39dd8b>] __sys_sendmsg+0xfe/0x1d0 Calling garp_request_leave() after garp_request_join(), the attr->state is set to GARP_APPLICANT_VO, garp_attr_destroy() won't be called in last transmit event in garp_uninit_applicant(), the attr of applicant will be leaked. To fix this leak, iterate and free each attr of applicant before rerturning from garp_uninit_applicant(). Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller --- net/802/garp.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/net/802/garp.c b/net/802/garp.c index 400bd857e5f5..f6012f8e59f0 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -203,6 +203,19 @@ static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr kfree(attr); } +static void garp_attr_destroy_all(struct garp_applicant *app) +{ + struct rb_node *node, *next; + struct garp_attr *attr; + + for (node = rb_first(&app->gid); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct garp_attr, node); + garp_attr_destroy(app, attr); + } +} + static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; @@ -609,6 +622,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); + garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); From 0dbffbb5335a1e3aa6855e4ee317e25e669dd302 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Jun 2021 07:12:45 -0700 Subject: [PATCH 030/426] net: annotate data race around sk_ll_usec sk_ll_usec is read locklessly from sk_can_busy_loop() while another thread can change its value in sock_setsockopt() This is correct but needs annotations. BUG: KCSAN: data-race in __skb_try_recv_datagram / sock_setsockopt write to 0xffff88814eb5f904 of 4 bytes by task 14011 on cpu 0: sock_setsockopt+0x1287/0x2090 net/core/sock.c:1175 __sys_setsockopt+0x14f/0x200 net/socket.c:2100 __do_sys_setsockopt net/socket.c:2115 [inline] __se_sys_setsockopt net/socket.c:2112 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2112 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88814eb5f904 of 4 bytes by task 14001 on cpu 1: sk_can_busy_loop include/net/busy_poll.h:41 [inline] __skb_try_recv_datagram+0x14f/0x320 net/core/datagram.c:273 unix_dgram_recvmsg+0x14c/0x870 net/unix/af_unix.c:2101 unix_seqpacket_recvmsg+0x5a/0x70 net/unix/af_unix.c:2067 ____sys_recvmsg+0x15d/0x310 include/linux/uio.h:244 ___sys_recvmsg net/socket.c:2598 [inline] do_recvmmsg+0x35c/0x9f0 net/socket.c:2692 __sys_recvmmsg net/socket.c:2771 [inline] __do_sys_recvmmsg net/socket.c:2794 [inline] __se_sys_recvmmsg net/socket.c:2787 [inline] __x64_sys_recvmmsg+0xcf/0x150 net/socket.c:2787 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x00000000 -> 0x00000101 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 14001 Comm: syz-executor.3 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/busy_poll.h | 2 +- net/core/sock.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 73af4a64a599..40296ed976a9 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -38,7 +38,7 @@ static inline bool net_busy_loop_on(void) static inline bool sk_can_busy_loop(const struct sock *sk) { - return sk->sk_ll_usec && !signal_pending(current); + return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current); } bool sk_busy_loop_end(void *p, unsigned long start_time); diff --git a/net/core/sock.c b/net/core/sock.c index ba1c0f75cd45..dd9599656c40 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1201,7 +1201,7 @@ set_sndbuf: if (val < 0) ret = -EINVAL; else - sk->sk_ll_usec = val; + WRITE_ONCE(sk->sk_ll_usec, val); } break; case SO_PREFER_BUSY_POLL: From 873a1e3d207ae587a7a1cc1d84545146b449ea5d Mon Sep 17 00:00:00 2001 From: Harman Kalra Date: Tue, 29 Jun 2021 22:30:04 +0530 Subject: [PATCH 031/426] octeontx2-af: cn10k: Setting up lmtst map table Introducing a new mailbox to support updating lmt entries and common lmt base address scheme i.e. multiple pcifuncs can share lmt region to reduce L1 cache pressure for application. Parameters passed to mailbox includes the primary pcifunc value whose lmt regions will be shared by other secondary pcifuncs. Here secondary pcifunc will be the one who is calling the mailbox. For example: By default each pcifunc has its own LMT base address: PCIFUNC1 LMT_BASE_ADDR A PCIFUNC2 LMT_BASE_ADDR B PCIFUNC3 LMT_BASE_ADDR C PCIFUNC4 LMT_BASE_ADDR D Application will choose PCIFUNC1 as base/primary pcifunc and as and when other pcifunc(secondary pcifuncs) gets probed, this mailbox will be called and LMTST table will be updated as: PCIFUNC1 LMT_BASE_ADDR A PCIFUNC2 LMT_BASE_ADDR A PCIFUNC3 LMT_BASE_ADDR A PCIFUNC4 LMT_BASE_ADDR A On FLR lmtst map table gets resetted to the default lmt base addresses for all secondary pcifuncs. Signed-off-by: Harman Kalra Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/mbox.h | 7 + .../net/ethernet/marvell/octeontx2/af/rvu.c | 1 + .../net/ethernet/marvell/octeontx2/af/rvu.h | 4 + .../ethernet/marvell/octeontx2/af/rvu_cn10k.c | 140 ++++++++++++++++++ .../ethernet/marvell/octeontx2/af/rvu_reg.h | 5 + .../marvell/octeontx2/af/rvu_struct.h | 3 +- 6 files changed, 159 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 770d86262838..638db868125a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -134,6 +134,8 @@ M(MSIX_OFFSET, 0x005, msix_offset, msg_req, msix_offset_rsp) \ M(VF_FLR, 0x006, vf_flr, msg_req, msg_rsp) \ M(PTP_OP, 0x007, ptp_op, ptp_req, ptp_rsp) \ M(GET_HW_CAP, 0x008, get_hw_cap, msg_req, get_hw_cap_rsp) \ +M(LMTST_TBL_SETUP, 0x00a, lmtst_tbl_setup, lmtst_tbl_setup_req, \ + msg_rsp) \ M(SET_VF_PERM, 0x00b, set_vf_perm, set_vf_perm, msg_rsp) \ /* CGX mbox IDs (range 0x200 - 0x3FF) */ \ M(CGX_START_RXTX, 0x200, cgx_start_rxtx, msg_req, msg_rsp) \ @@ -1278,6 +1280,11 @@ struct set_vf_perm { u64 flags; }; +struct lmtst_tbl_setup_req { + struct mbox_msghdr hdr; + u16 base_pcifunc; +}; + /* CPT mailbox error codes * Range 901 - 1000. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 0b092949d7ac..10cddf1ac7b9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2333,6 +2333,7 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc) rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSOW); rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSO); rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NPA); + rvu_reset_lmt_map_tbl(rvu, pcifunc); rvu_detach_rsrcs(rvu, NULL, pcifunc); mutex_unlock(&rvu->flr_lock); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 9e5d9ba6f01e..3c0a7e981f72 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -243,6 +243,7 @@ struct rvu_pfvf { u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */ u8 nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */ u8 nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */ + u64 lmt_base_addr; /* Preseving the pcifunc's lmtst base addr*/ unsigned long flags; }; @@ -754,6 +755,9 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot); int rvu_set_channels_base(struct rvu *rvu); void rvu_program_channels(struct rvu *rvu); +/* CN10K RVU - LMT*/ +void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc); + #ifdef CONFIG_DEBUG_FS void rvu_dbg_init(struct rvu *rvu); void rvu_dbg_exit(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c index 7d9e71c6965f..87f56e1f32e3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c @@ -10,6 +10,146 @@ #include "cgx.h" #include "rvu_reg.h" +/* RVU LMTST */ +#define LMT_TBL_OP_READ 0 +#define LMT_TBL_OP_WRITE 1 +#define LMT_MAP_TABLE_SIZE (128 * 1024) +#define LMT_MAPTBL_ENTRY_SIZE 16 + +/* Function to perform operations (read/write) on lmtst map table */ +static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val, + int lmt_tbl_op) +{ + void __iomem *lmt_map_base; + u64 tbl_base; + + tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE); + + lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE); + if (!lmt_map_base) { + dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n"); + return -ENOMEM; + } + + if (lmt_tbl_op == LMT_TBL_OP_READ) { + *val = readq(lmt_map_base + index); + } else { + writeq((*val), (lmt_map_base + index)); + /* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S + * changes effective. Write 1 for flush and read is being used as a + * barrier and sets up a data dependency. Write to 0 after a write + * to 1 to complete the flush. + */ + rvu_write64(rvu, BLKADDR_APR, APR_AF_LMT_CTL, BIT_ULL(0)); + rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CTL); + rvu_write64(rvu, BLKADDR_APR, APR_AF_LMT_CTL, 0x00); + } + + iounmap(lmt_map_base); + return 0; +} + +static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc) +{ + return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) + + (pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE; +} + +int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu, + struct lmtst_tbl_setup_req *req, + struct msg_rsp *rsp) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc); + u32 pri_tbl_idx, sec_tbl_idx; + int err = 0; + u64 val; + + /* Reconfiguring lmtst map table in lmt region shared mode i.e. make + * multiple PF_FUNCs to share an LMTLINE region, so primary/base + * pcifunc (which is passed as an argument to mailbox) is the one + * whose lmt base address will be shared among other secondary + * pcifunc (will be the one who is calling this mailbox). + */ + if (req->base_pcifunc) { + /* Calculating the LMT table index equivalent to primary + * pcifunc. + */ + pri_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->base_pcifunc); + + /* Truncating secondary pcifunc to calculate the LMT table index + * equivalent to secondary pcifunc. + */ + sec_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->hdr.pcifunc); + /* Read the base lmt addr of the secondary pcifunc */ + err = lmtst_map_table_ops(rvu, sec_tbl_idx, &val, + LMT_TBL_OP_READ); + if (err) { + dev_err(rvu->dev, + "Failed to read LMT map table: index 0x%x err %d\n", + sec_tbl_idx, err); + goto error; + } + + /* Storing the seondary's lmt base address as this needs to be + * reverted in FLR. Also making sure this default value doesn't + * get overwritten on multiple calls to this mailbox. + */ + if (!pfvf->lmt_base_addr) + pfvf->lmt_base_addr = val; + + /* Read the base lmt addr of the primary pcifunc */ + err = lmtst_map_table_ops(rvu, pri_tbl_idx, &val, + LMT_TBL_OP_READ); + if (err) { + dev_err(rvu->dev, + "Failed to read LMT map table: index 0x%x err %d\n", + pri_tbl_idx, err); + goto error; + } + + /* Update the base lmt addr of secondary with primary's base + * lmt addr. + */ + err = lmtst_map_table_ops(rvu, sec_tbl_idx, &val, + LMT_TBL_OP_WRITE); + if (err) { + dev_err(rvu->dev, + "Failed to update LMT map table: index 0x%x err %d\n", + sec_tbl_idx, err); + goto error; + } + } + +error: + return err; +} + +/* Resetting the lmtst map table to original base addresses */ +void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + u32 tbl_idx; + int err; + + if (is_rvu_otx2(rvu)) + return; + + if (pfvf->lmt_base_addr) { + /* This corresponds to lmt map table index */ + tbl_idx = rvu_get_lmtst_tbl_index(rvu, pcifunc); + /* Reverting back original lmt base addr for respective + * pcifunc. + */ + err = lmtst_map_table_ops(rvu, tbl_idx, &pfvf->lmt_base_addr, + LMT_TBL_OP_WRITE); + if (err) + dev_err(rvu->dev, + "Failed to update LMT map table: index 0x%x err %d\n", + tbl_idx, err); + pfvf->lmt_base_addr = 0; + } +} + int rvu_set_channels_base(struct rvu *rvu) { struct rvu_hwinfo *hw = rvu->hw; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 76837d5e19c6..61bafe956aae 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -692,4 +692,9 @@ #define LBK_LINK_CFG_ID_MASK GENMASK_ULL(11, 6) #define LBK_LINK_CFG_BASE_MASK GENMASK_ULL(5, 0) +/* APR */ +#define APR_AF_LMT_CFG (0x000ull) +#define APR_AF_LMT_MAP_BASE (0x008ull) +#define APR_AF_LMT_CTL (0x010ull) + #endif /* RVU_REG_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index 14aa8e37ea41..5bbe6727d11d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -35,7 +35,8 @@ enum rvu_block_addr_e { BLKADDR_NDC_NPA0 = 0xeULL, BLKADDR_NDC_NIX1_RX = 0x10ULL, BLKADDR_NDC_NIX1_TX = 0x11ULL, - BLK_COUNT = 0x12ULL, + BLKADDR_APR = 0x16ULL, + BLK_COUNT = 0x17ULL, }; /* RVU Block Type Enumeration */ From 893ae97214c385be02f8ec097298cc48c7f0d905 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Tue, 29 Jun 2021 22:30:05 +0530 Subject: [PATCH 032/426] octeontx2-af: cn10k: Support configurable LMTST regions This patch extends the lmtst_tbl_setup_req mbox to support run time LMTST configuration. RVU PF/VF and DPDK/ODP allocates a LMT region, creates a translation entry for a device via VFIO IOCTLs. This IOVA is shared with AF through above mbox. AF then uses RVU_SMMU transulation Widget and gets PA for the IOVA and updates the LMTtable entry for that device. Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/mbox.h | 3 + .../ethernet/marvell/octeontx2/af/rvu_cn10k.c | 130 +++++++++++++----- .../ethernet/marvell/octeontx2/af/rvu_reg.h | 5 + 3 files changed, 103 insertions(+), 35 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 638db868125a..9672cbf8a90a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -1283,6 +1283,9 @@ struct set_vf_perm { struct lmtst_tbl_setup_req { struct mbox_msghdr hdr; u16 base_pcifunc; + u8 use_local_lmt_region; + u64 lmt_iova; + u64 rsvd[4]; }; /* CPT mailbox error codes diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c index 87f56e1f32e3..8d48b64485c6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c @@ -55,14 +55,101 @@ static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc) (pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE; } +static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc, + u64 iova, u64 *lmt_addr) +{ + u64 pa, val, pf; + int err; + + if (!iova) { + dev_err(rvu->dev, "%s Requested Null address for transulation\n", __func__); + return -EINVAL; + } + + rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova); + pf = rvu_get_pf(pcifunc) & 0x1F; + val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 | + ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF); + rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val); + + err = rvu_poll_reg(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS, BIT_ULL(0), false); + if (err) { + dev_err(rvu->dev, "%s LMTLINE iova transulation failed\n", __func__); + return err; + } + val = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS); + if (val & ~0x1ULL) { + dev_err(rvu->dev, "%s LMTLINE iova transulation failed err:%llx\n", __func__, val); + return -EIO; + } + /* PA[51:12] = RVU_AF_SMMU_TLN_FLIT1[60:21] + * PA[11:0] = IOVA[11:0] + */ + pa = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TLN_FLIT1) >> 21; + pa &= GENMASK_ULL(39, 0); + *lmt_addr = (pa << 12) | (iova & 0xFFF); + + return 0; +} + +static int rvu_update_lmtaddr(struct rvu *rvu, u16 pcifunc, u64 lmt_addr) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + u32 tbl_idx; + int err = 0; + u64 val; + + /* Read the current lmt addr of pcifunc */ + tbl_idx = rvu_get_lmtst_tbl_index(rvu, pcifunc); + err = lmtst_map_table_ops(rvu, tbl_idx, &val, LMT_TBL_OP_READ); + if (err) { + dev_err(rvu->dev, + "Failed to read LMT map table: index 0x%x err %d\n", + tbl_idx, err); + return err; + } + + /* Storing the seondary's lmt base address as this needs to be + * reverted in FLR. Also making sure this default value doesn't + * get overwritten on multiple calls to this mailbox. + */ + if (!pfvf->lmt_base_addr) + pfvf->lmt_base_addr = val; + + /* Update the LMT table with new addr */ + err = lmtst_map_table_ops(rvu, tbl_idx, &lmt_addr, LMT_TBL_OP_WRITE); + if (err) { + dev_err(rvu->dev, + "Failed to update LMT map table: index 0x%x err %d\n", + tbl_idx, err); + return err; + } + return 0; +} + int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu, struct lmtst_tbl_setup_req *req, struct msg_rsp *rsp) { - struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc); - u32 pri_tbl_idx, sec_tbl_idx; + u64 lmt_addr, val; + u32 pri_tbl_idx; int err = 0; - u64 val; + + /* Check if PF_FUNC wants to use it's own local memory as LMTLINE + * region, if so, convert that IOVA to physical address and + * populate LMT table with that address + */ + if (req->use_local_lmt_region) { + err = rvu_get_lmtaddr(rvu, req->hdr.pcifunc, + req->lmt_iova, &lmt_addr); + if (err < 0) + return err; + + /* Update the lmt addr for this PFFUNC in the LMT table */ + err = rvu_update_lmtaddr(rvu, req->hdr.pcifunc, lmt_addr); + if (err) + return err; + } /* Reconfiguring lmtst map table in lmt region shared mode i.e. make * multiple PF_FUNCs to share an LMTLINE region, so primary/base @@ -76,27 +163,6 @@ int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu, */ pri_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->base_pcifunc); - /* Truncating secondary pcifunc to calculate the LMT table index - * equivalent to secondary pcifunc. - */ - sec_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->hdr.pcifunc); - /* Read the base lmt addr of the secondary pcifunc */ - err = lmtst_map_table_ops(rvu, sec_tbl_idx, &val, - LMT_TBL_OP_READ); - if (err) { - dev_err(rvu->dev, - "Failed to read LMT map table: index 0x%x err %d\n", - sec_tbl_idx, err); - goto error; - } - - /* Storing the seondary's lmt base address as this needs to be - * reverted in FLR. Also making sure this default value doesn't - * get overwritten on multiple calls to this mailbox. - */ - if (!pfvf->lmt_base_addr) - pfvf->lmt_base_addr = val; - /* Read the base lmt addr of the primary pcifunc */ err = lmtst_map_table_ops(rvu, pri_tbl_idx, &val, LMT_TBL_OP_READ); @@ -104,24 +170,18 @@ int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu, dev_err(rvu->dev, "Failed to read LMT map table: index 0x%x err %d\n", pri_tbl_idx, err); - goto error; + return err; } /* Update the base lmt addr of secondary with primary's base * lmt addr. */ - err = lmtst_map_table_ops(rvu, sec_tbl_idx, &val, - LMT_TBL_OP_WRITE); - if (err) { - dev_err(rvu->dev, - "Failed to update LMT map table: index 0x%x err %d\n", - sec_tbl_idx, err); - goto error; - } + err = rvu_update_lmtaddr(rvu, req->hdr.pcifunc, val); + if (err) + return err; } -error: - return err; + return 0; } /* Resetting the lmtst map table to original base addresses */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 61bafe956aae..8b01ef6e2c99 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -49,6 +49,11 @@ #define RVU_AF_PFX_VF_BAR4_ADDR (0x5400 | (a) << 4) #define RVU_AF_PFX_VF_BAR4_CFG (0x5600 | (a) << 4) #define RVU_AF_PFX_LMTLINE_ADDR (0x5800 | (a) << 4) +#define RVU_AF_SMMU_ADDR_REQ (0x6000) +#define RVU_AF_SMMU_TXN_REQ (0x6008) +#define RVU_AF_SMMU_ADDR_RSP_STS (0x6010) +#define RVU_AF_SMMU_ADDR_TLN (0x6018) +#define RVU_AF_SMMU_TLN_FLIT1 (0x6030) /* Admin function's privileged PF/VF registers */ #define RVU_PRIV_CONST (0x8000000) From 5c0512072f6517326d9fba083c4467f173ddd984 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Tue, 29 Jun 2021 22:30:06 +0530 Subject: [PATCH 033/426] octeontx2-pf: cn10k: Use runtime allocated LMTLINE region The current driver uses static LMTST region allocated by firmware. This memory gets populated as PF/VF BAR2. RVU PF/VF driver ioremap the memory as device memory for NIX/NPA operation. Since the memory is mapped as device memory we see performance degration. To address this issue this patch implements runtime memory allocation. RVU PF/VF allocates memory during device probe and share the base address with RVU AF. RVU AF then configure the LMT MAP table accordingly. Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../ethernet/marvell/octeontx2/nic/cn10k.c | 93 ++++++++----------- .../ethernet/marvell/octeontx2/nic/cn10k.h | 3 +- .../marvell/octeontx2/nic/otx2_common.h | 7 +- .../ethernet/marvell/octeontx2/nic/otx2_pf.c | 17 ++-- .../marvell/octeontx2/nic/otx2_txrx.h | 1 + .../ethernet/marvell/octeontx2/nic/otx2_vf.c | 12 +-- 6 files changed, 57 insertions(+), 76 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index 1b08896b46d2..184de9466286 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -22,69 +22,52 @@ static struct dev_hw_ops cn10k_hw_ops = { .refill_pool_ptrs = cn10k_refill_pool_ptrs, }; -int cn10k_pf_lmtst_init(struct otx2_nic *pf) +int cn10k_lmtst_init(struct otx2_nic *pfvf) { - int size, num_lines; - u64 base; - if (!test_bit(CN10K_LMTST, &pf->hw.cap_flag)) { - pf->hw_ops = &otx2_hw_ops; + struct lmtst_tbl_setup_req *req; + int qcount, err; + + if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) { + pfvf->hw_ops = &otx2_hw_ops; return 0; } - pf->hw_ops = &cn10k_hw_ops; - base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) + - (MBOX_SIZE * (pf->total_vfs + 1)); + pfvf->hw_ops = &cn10k_hw_ops; + qcount = pfvf->hw.max_queues; + /* LMTST lines allocation + * qcount = num_online_cpus(); + * NPA = TX + RX + XDP. + * NIX = TX * 32 (For Burst SQE flush). + */ + pfvf->tot_lmt_lines = (qcount * 3) + (qcount * 32); + pfvf->npa_lmt_lines = qcount * 3; + pfvf->nix_lmt_size = LMT_BURST_SIZE * LMT_LINE_SIZE; - size = pci_resource_len(pf->pdev, PCI_MBOX_BAR_NUM) - - (MBOX_SIZE * (pf->total_vfs + 1)); - - pf->hw.lmt_base = ioremap(base, size); - - if (!pf->hw.lmt_base) { - dev_err(pf->dev, "Unable to map PF LMTST region\n"); + mutex_lock(&pfvf->mbox.lock); + req = otx2_mbox_alloc_msg_lmtst_tbl_setup(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); return -ENOMEM; } - /* FIXME: Get the num of LMTST lines from LMT table */ - pf->tot_lmt_lines = size / LMT_LINE_SIZE; - num_lines = (pf->tot_lmt_lines - NIX_LMTID_BASE) / - pf->hw.tx_queues; - /* Number of LMT lines per SQ queues */ - pf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines; + req->use_local_lmt_region = true; + + err = qmem_alloc(pfvf->dev, &pfvf->dync_lmt, pfvf->tot_lmt_lines, + LMT_LINE_SIZE); + if (err) { + mutex_unlock(&pfvf->mbox.lock); + return err; + } + pfvf->hw.lmt_base = (u64 *)pfvf->dync_lmt->base; + req->lmt_iova = (u64)pfvf->dync_lmt->iova; + + err = otx2_sync_mbox_msg(&pfvf->mbox); + mutex_unlock(&pfvf->mbox.lock); - pf->nix_lmt_size = pf->nix_lmt_lines * LMT_LINE_SIZE; return 0; } - -int cn10k_vf_lmtst_init(struct otx2_nic *vf) -{ - int size, num_lines; - - if (!test_bit(CN10K_LMTST, &vf->hw.cap_flag)) { - vf->hw_ops = &otx2_hw_ops; - return 0; - } - - vf->hw_ops = &cn10k_hw_ops; - size = pci_resource_len(vf->pdev, PCI_MBOX_BAR_NUM); - vf->hw.lmt_base = ioremap_wc(pci_resource_start(vf->pdev, - PCI_MBOX_BAR_NUM), - size); - if (!vf->hw.lmt_base) { - dev_err(vf->dev, "Unable to map VF LMTST region\n"); - return -ENOMEM; - } - - vf->tot_lmt_lines = size / LMT_LINE_SIZE; - /* LMTST lines per SQ */ - num_lines = (vf->tot_lmt_lines - NIX_LMTID_BASE) / - vf->hw.tx_queues; - vf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines; - vf->nix_lmt_size = vf->nix_lmt_lines * LMT_LINE_SIZE; - return 0; -} -EXPORT_SYMBOL(cn10k_vf_lmtst_init); +EXPORT_SYMBOL(cn10k_lmtst_init); int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) { @@ -93,9 +76,11 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) struct otx2_snd_queue *sq; sq = &pfvf->qset.sq[qidx]; - sq->lmt_addr = (__force u64 *)((u64)pfvf->hw.nix_lmt_base + + sq->lmt_addr = (u64 *)((u64)pfvf->hw.nix_lmt_base + (qidx * pfvf->nix_lmt_size)); + sq->lmt_id = pfvf->npa_lmt_lines + (qidx * LMT_BURST_SIZE); + /* Get memory to put this msg */ aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox); if (!aq) @@ -158,15 +143,13 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx) { - struct otx2_nic *pfvf = dev; - int lmt_id = NIX_LMTID_BASE + (qidx * pfvf->nix_lmt_lines); u64 val = 0, tar_addr = 0; /* FIXME: val[0:10] LMT_ID. * [12:15] no of LMTST - 1 in the burst. * [19:63] data size of each LMTST in the burst except first. */ - val = (lmt_id & 0x7FF); + val = (sq->lmt_id & 0x7FF); /* Target address for LMTST flush tells HW how many 128bit * words are present. * tar_addr[6:4] size of first LMTST - 1 in units of 128b. diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h index 71292a4cf1f3..1a1ae334477d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h @@ -12,8 +12,7 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq); void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx); int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); -int cn10k_pf_lmtst_init(struct otx2_nic *pf); -int cn10k_vf_lmtst_init(struct otx2_nic *vf); +int cn10k_lmtst_init(struct otx2_nic *pfvf); int cn10k_free_all_ipolicers(struct otx2_nic *pfvf); int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf); int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 234b330f3183..20a9c69f020f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -218,8 +218,8 @@ struct otx2_hw { unsigned long cap_flag; #define LMT_LINE_SIZE 128 -#define NIX_LMTID_BASE 72 /* RX + TX + XDP */ - void __iomem *lmt_base; +#define LMT_BURST_SIZE 32 /* 32 LMTST lines for burst SQE flush */ + u64 *lmt_base; u64 *npa_lmt_base; u64 *nix_lmt_base; }; @@ -363,8 +363,9 @@ struct otx2_nic { /* Block address of NIX either BLKADDR_NIX0 or BLKADDR_NIX1 */ int nix_blkaddr; /* LMTST Lines info */ + struct qmem *dync_lmt; u16 tot_lmt_lines; - u16 nix_lmt_lines; + u16 npa_lmt_lines; u32 nix_lmt_size; struct otx2_ptp *ptp; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 59912f73417b..088c28df849d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1533,10 +1533,10 @@ int otx2_open(struct net_device *netdev) if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) { /* Reserve LMT lines for NPA AURA batch free */ - pf->hw.npa_lmt_base = (__force u64 *)pf->hw.lmt_base; + pf->hw.npa_lmt_base = pf->hw.lmt_base; /* Reserve LMT lines for NIX TX */ - pf->hw.nix_lmt_base = (__force u64 *)((u64)pf->hw.npa_lmt_base + - (NIX_LMTID_BASE * LMT_LINE_SIZE)); + pf->hw.nix_lmt_base = (u64 *)((u64)pf->hw.npa_lmt_base + + (pf->npa_lmt_lines * LMT_LINE_SIZE)); } err = otx2_init_hw_resources(pf); @@ -2526,7 +2526,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_detach_rsrc; - err = cn10k_pf_lmtst_init(pf); + err = cn10k_lmtst_init(pf); if (err) goto err_detach_rsrc; @@ -2630,8 +2630,8 @@ err_del_mcam_entries: err_ptp_destroy: otx2_ptp_destroy(pf); err_detach_rsrc: - if (hw->lmt_base) - iounmap(hw->lmt_base); + if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) + qmem_free(pf->dev, pf->dync_lmt); otx2_detach_resources(&pf->mbox); err_disable_mbox_intr: otx2_disable_mbox_intr(pf); @@ -2772,9 +2772,8 @@ static void otx2_remove(struct pci_dev *pdev) otx2_mcam_flow_del(pf); otx2_shutdown_tc(pf); otx2_detach_resources(&pf->mbox); - if (pf->hw.lmt_base) - iounmap(pf->hw.lmt_base); - + if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) + qmem_free(pf->dev, pf->dync_lmt); otx2_disable_mbox_intr(pf); otx2_pfaf_mbox_destroy(pf); pci_free_irq_vectors(pf->pdev); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 52486c1f0973..2f144e2cf436 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -83,6 +83,7 @@ struct otx2_snd_queue { u16 num_sqbs; u16 sqe_thresh; u8 sqe_per_sqb; + u32 lmt_id; u64 io_addr; u64 *aura_fc_addr; u64 *lmt_addr; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 13a908f75ba0..a8bee5aefec1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -609,7 +609,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_detach_rsrc; - err = cn10k_vf_lmtst_init(vf); + err = cn10k_lmtst_init(vf); if (err) goto err_detach_rsrc; @@ -667,8 +667,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_unreg_netdev: unregister_netdev(netdev); err_detach_rsrc: - if (hw->lmt_base) - iounmap(hw->lmt_base); + if (test_bit(CN10K_LMTST, &vf->hw.cap_flag)) + qmem_free(vf->dev, vf->dync_lmt); otx2_detach_resources(&vf->mbox); err_disable_mbox_intr: otx2vf_disable_mbox_intr(vf); @@ -700,10 +700,8 @@ static void otx2vf_remove(struct pci_dev *pdev) destroy_workqueue(vf->otx2_wq); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); - - if (vf->hw.lmt_base) - iounmap(vf->hw.lmt_base); - + if (test_bit(CN10K_LMTST, &vf->hw.cap_flag)) + qmem_free(vf->dev, vf->dync_lmt); otx2vf_vfaf_mbox_destroy(vf); pci_free_irq_vectors(vf->pdev); pci_set_drvdata(pdev, NULL); From b71d09871566a20ae8a1064e50f1e94813b18482 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 29 Jun 2021 23:32:15 +0300 Subject: [PATCH 034/426] net: dsa: return -EOPNOTSUPP when driver does not implement .port_lag_join The DSA core has a layered structure, and even though we end up returning 0 (success) to user space when setting a bonding/team upper that can't be offloaded, some parts of the framework actually need to know that we couldn't offload that. For example, if dsa_switch_lag_join returns 0 as it currently does, dsa_port_lag_join has no way to tell a successful offload from a software fallback, and it will call dsa_port_bridge_join afterwards. Then we'll think we're offloading the bridge master of the LAG, when in fact we're not even offloading the LAG. In turn, this will make us set skb->offload_fwd_mark = true, which is incorrect and the bridge doesn't like it. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/switch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/dsa/switch.c b/net/dsa/switch.c index af71b8638098..248455145982 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -427,7 +427,7 @@ static int dsa_switch_lag_join(struct dsa_switch *ds, info->port, info->lag, info->info); - return 0; + return -EOPNOTSUPP; } static int dsa_switch_lag_leave(struct dsa_switch *ds, @@ -440,7 +440,7 @@ static int dsa_switch_lag_leave(struct dsa_switch *ds, return ds->ops->crosschip_lag_leave(ds, info->sw_index, info->port, info->lag); - return 0; + return -EOPNOTSUPP; } static int dsa_switch_mdb_add(struct dsa_switch *ds, From 5a3c680aa2c12c90c44af383fe6882a39875ab81 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Tue, 29 Jun 2021 17:14:19 -0700 Subject: [PATCH 035/426] net: bcmgenet: ensure EXT_ENERGY_DET_MASK is clear Setting the EXT_ENERGY_DET_MASK bit allows the port energy detection logic of the internal PHY to prevent the system from sleeping. Some internal PHYs will report that energy is detected when the network interface is closed which can prevent the system from going to sleep if WoL is enabled when the interface is brought down. Since the driver does not support waking the system on this logic, this commit clears the bit whenever the internal PHY is powered up and the other logic for manipulating the bit is removed since it serves no useful function. Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Doug Berger Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 17 ++--------------- .../net/ethernet/broadcom/genet/bcmgenet_wol.c | 6 ------ 2 files changed, 2 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 41f7f078cd27..35e9956e930c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1640,7 +1640,8 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv, switch (mode) { case GENET_POWER_PASSIVE: - reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); + reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS | + EXT_ENERGY_DET_MASK); if (GENET_IS_V5(priv)) { reg &= ~(EXT_PWR_DOWN_PHY_EN | EXT_PWR_DOWN_PHY_RD | @@ -3292,7 +3293,6 @@ static int bcmgenet_open(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); unsigned long dma_ctrl; - u32 reg; int ret; netif_dbg(priv, ifup, dev, "bcmgenet_open\n"); @@ -3318,12 +3318,6 @@ static int bcmgenet_open(struct net_device *dev) bcmgenet_set_hw_addr(priv, dev->dev_addr); - if (priv->internal_phy) { - reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg |= EXT_ENERGY_DET_MASK; - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - } - /* Disable RX/TX DMA and flush TX queues */ dma_ctrl = bcmgenet_dma_disable(priv); @@ -4139,7 +4133,6 @@ static int bcmgenet_resume(struct device *d) struct bcmgenet_priv *priv = netdev_priv(dev); struct bcmgenet_rxnfc_rule *rule; unsigned long dma_ctrl; - u32 reg; int ret; if (!netif_running(dev)) @@ -4176,12 +4169,6 @@ static int bcmgenet_resume(struct device *d) if (rule->state != BCMGENET_RXNFC_STATE_UNUSED) bcmgenet_hfb_create_rxnfc_filter(priv, rule); - if (priv->internal_phy) { - reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg |= EXT_ENERGY_DET_MASK; - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - } - /* Disable RX/TX DMA and flush TX queues */ dma_ctrl = bcmgenet_dma_disable(priv); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index facde824bcaa..e31a5a397f11 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -186,12 +186,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, reg |= CMD_RX_EN; bcmgenet_umac_writel(priv, reg, UMAC_CMD); - if (priv->hw_params->flags & GENET_HAS_EXT) { - reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); - reg &= ~EXT_ENERGY_DET_MASK; - bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - } - reg = UMAC_IRQ_MPD_R; if (hfb_enable) reg |= UMAC_IRQ_HFB_SM | UMAC_IRQ_HFB_MM; From 650b2a846dddf33321489597287e6d825ec1d0ba Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 29 Jun 2021 23:30:36 -0400 Subject: [PATCH 036/426] sctp: check pl.raise_count separately from its increment As Marcelo's suggestion this will make code more clear to read. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/transport.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 5f23804f21c7..397a6244dd97 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -335,10 +335,13 @@ void sctp_transport_pl_recv(struct sctp_transport *t) t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } - } else if (t->pl.state == SCTP_PL_COMPLETE && ++t->pl.raise_count == 30) { - /* Raise probe_size again after 30 * interval in Search Complete */ - t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; + } else if (t->pl.state == SCTP_PL_COMPLETE) { + t->pl.raise_count++; + if (t->pl.raise_count == 30) { + /* Raise probe_size again after 30 * interval in Search Complete */ + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; + } } } From 1d11fa231cabeae09a95cb3e4cf1d9dd34e00f08 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 29 Jun 2021 23:34:08 -0400 Subject: [PATCH 037/426] sctp: move 198 addresses from unusable to private scope MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The doc draft-stewart-tsvwg-sctp-ipv4-00 that restricts 198 addresses was never published. These addresses as private addresses should be allowed to use in SCTP. As Michael Tuexen suggested, this patch is to move 198 addresses from unusable to private scope. Reported-by: Sérgio Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/constants.h | 4 +--- net/sctp/protocol.c | 3 ++- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 265fffa33dad..5859e0a16a58 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -360,8 +360,7 @@ enum { #define SCTP_SCOPE_POLICY_MAX SCTP_SCOPE_POLICY_LINK /* Based on IPv4 scoping , - * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 198.18.0.0/24, - * 192.88.99.0/24. + * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 192.88.99.0/24. * Also, RFC 8.4, non-unicast addresses are not considered valid SCTP * addresses. */ @@ -369,7 +368,6 @@ enum { ((htonl(INADDR_BROADCAST) == a) || \ ipv4_is_multicast(a) || \ ipv4_is_zeronet(a) || \ - ipv4_is_test_198(a) || \ ipv4_is_anycast_6to4(a)) /* Flags used for the bind address copy functions. */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 3c1fbf38f4f7..ec0f52567c16 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -398,7 +398,8 @@ static enum sctp_scope sctp_v4_scope(union sctp_addr *addr) retval = SCTP_SCOPE_LINK; } else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) || ipv4_is_private_172(addr->v4.sin_addr.s_addr) || - ipv4_is_private_192(addr->v4.sin_addr.s_addr)) { + ipv4_is_private_192(addr->v4.sin_addr.s_addr) || + ipv4_is_test_198(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_PRIVATE; } else { retval = SCTP_SCOPE_GLOBAL; From 7da467d82d1ed4fb317aff836f99709169e73f10 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:26 +0200 Subject: [PATCH 038/426] net: dsa: mv88e6xxx: enable .port_set_policy() on Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit f3a2cd326e44 ("net: dsa: mv88e6xxx: introduce .port_set_policy") introduced .port_set_policy() method with implementation for several models, but forgot to add Topaz, which can use the 6352 implementation. Use the 6352 implementation of .port_set_policy() on Topaz. Signed-off-by: Marek Behún Fixes: f3a2cd326e44 ("net: dsa: mv88e6xxx: introduce .port_set_policy") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 961fa6b75cad..6bcee3e012d4 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3583,6 +3583,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_set_speed_duplex = mv88e6341_port_set_speed_duplex, .port_max_speed_mode = mv88e6341_port_max_speed_mode, .port_tag_remap = mv88e6095_port_tag_remap, + .port_set_policy = mv88e6352_port_set_policy, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_ucast_flood = mv88e6352_port_set_ucast_flood, .port_set_mcast_flood = mv88e6352_port_set_mcast_flood, @@ -4383,6 +4384,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_set_speed_duplex = mv88e6341_port_set_speed_duplex, .port_max_speed_mode = mv88e6341_port_max_speed_mode, .port_tag_remap = mv88e6095_port_tag_remap, + .port_set_policy = mv88e6352_port_set_policy, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_ucast_flood = mv88e6352_port_set_ucast_flood, .port_set_mcast_flood = mv88e6352_port_set_mcast_flood, From 11527f3c4725640e6c40a2b7654e303f45e82a6c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:27 +0200 Subject: [PATCH 039/426] net: dsa: mv88e6xxx: use correct .stats_set_histogram() on Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 40cff8fca9e3 ("net: dsa: mv88e6xxx: Fix stats histogram mode") introduced wrong .stats_set_histogram() method for Topaz family. The Peridot method should be used instead. Signed-off-by: Marek Behún Fixes: 40cff8fca9e3 ("net: dsa: mv88e6xxx: Fix stats histogram mode") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 6bcee3e012d4..b125d3227dbd 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3597,7 +3597,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_set_cmode = mv88e6341_port_set_cmode, .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, - .stats_set_histogram = mv88e6095_g1_stats_set_histogram, + .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, .stats_get_stats = mv88e6390_stats_get_stats, @@ -4398,7 +4398,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_set_cmode = mv88e6341_port_set_cmode, .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, - .stats_set_histogram = mv88e6095_g1_stats_set_histogram, + .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, .stats_get_strings = mv88e6320_stats_get_strings, .stats_get_stats = mv88e6390_stats_get_stats, From 3709488790022c85720f991bff50d48ed5a36e6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:28 +0200 Subject: [PATCH 040/426] net: dsa: mv88e6xxx: enable .rmu_disable() on Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 9e5baf9b36367 ("net: dsa: mv88e6xxx: add RMU disable op") introduced .rmu_disable() method with implementation for several models, but forgot to add Topaz, which can use the Peridot implementation. Use the Peridot implementation of .rmu_disable() on Topaz. Signed-off-by: Marek Behún Fixes: 9e5baf9b36367 ("net: dsa: mv88e6xxx: add RMU disable op") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index b125d3227dbd..d4b05c10e5f2 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3607,6 +3607,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -4408,6 +4409,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, From c07fff3492acae41cedbabea395b644dd5872b8c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:29 +0200 Subject: [PATCH 041/426] net: dsa: mv88e6xxx: enable devlink ATU hash param for Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 23e8b470c7788 ("net: dsa: mv88e6xxx: Add devlink param for ATU hash algorithm.") introduced ATU hash algorithm access via devlink, but did not enable it for Topaz. Enable this feature also for Topaz. Signed-off-by: Marek Behún Fixes: 23e8b470c7788 ("net: dsa: mv88e6xxx: Add devlink param for ATU hash algorithm.") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d4b05c10e5f2..354ff0b84b7f 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3608,6 +3608,8 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, + .atu_get_hash = mv88e6165_g1_atu_get_hash, + .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -4410,6 +4412,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, + .atu_get_hash = mv88e6165_g1_atu_get_hash, + .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, From a03b98d68367b18e5db6d6850e2cc18754fba94a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:30 +0200 Subject: [PATCH 042/426] net: dsa: mv88e6xxx: enable SerDes RX stats for Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 0df952873636a ("mv88e6xxx: Add serdes Rx statistics") added support for RX statistics on SerDes ports for Peridot. This same implementation is also valid for Topaz, but was not enabled at the time. We need to use the generic .serdes_get_lane() method instead of the Peridot specific one in the stats methods so that on Topaz the proper one is used. Signed-off-by: Marek Behún Fixes: 0df952873636a ("mv88e6xxx: Add serdes Rx statistics") Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 6 ++++++ drivers/net/dsa/mv88e6xxx/serdes.c | 6 +++--- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 354ff0b84b7f..1e95a0facbd4 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3623,6 +3623,9 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .serdes_irq_enable = mv88e6390_serdes_irq_enable, .serdes_irq_status = mv88e6390_serdes_irq_status, .gpio_ops = &mv88e6352_gpio_ops, + .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, + .serdes_get_strings = mv88e6390_serdes_get_strings, + .serdes_get_stats = mv88e6390_serdes_get_stats, .phylink_validate = mv88e6341_phylink_validate, }; @@ -4429,6 +4432,9 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, + .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, + .serdes_get_strings = mv88e6390_serdes_get_strings, + .serdes_get_stats = mv88e6390_serdes_get_stats, .phylink_validate = mv88e6341_phylink_validate, }; diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index e4fbef81bc52..b1d46dd8eaab 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -722,7 +722,7 @@ static struct mv88e6390_serdes_hw_stat mv88e6390_serdes_hw_stats[] = { int mv88e6390_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port) { - if (mv88e6390_serdes_get_lane(chip, port) < 0) + if (mv88e6xxx_serdes_get_lane(chip, port) < 0) return 0; return ARRAY_SIZE(mv88e6390_serdes_hw_stats); @@ -734,7 +734,7 @@ int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, struct mv88e6390_serdes_hw_stat *stat; int i; - if (mv88e6390_serdes_get_lane(chip, port) < 0) + if (mv88e6xxx_serdes_get_lane(chip, port) < 0) return 0; for (i = 0; i < ARRAY_SIZE(mv88e6390_serdes_hw_stats); i++) { @@ -770,7 +770,7 @@ int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, int lane; int i; - lane = mv88e6390_serdes_get_lane(chip, port); + lane = mv88e6xxx_serdes_get_lane(chip, port); if (lane < 0) return 0; From 953b0dcbe2e3f7bee98cc3bca2ec82c8298e9c16 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 1 Jul 2021 00:22:31 +0200 Subject: [PATCH 043/426] net: dsa: mv88e6xxx: enable SerDes PCS register dump via ethtool -d on Topaz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit bf3504cea7d7e ("net: dsa: mv88e6xxx: Add 6390 family PCS registers to ethtool -d") added support for dumping SerDes PCS registers via ethtool -d for Peridot. The same implementation is also valid for Topaz, but was not enabled at the time. Signed-off-by: Marek Behún Fixes: bf3504cea7d7e ("net: dsa: mv88e6xxx: Add 6390 family PCS registers to ethtool -d") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 1e95a0facbd4..beb41572d04e 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3626,6 +3626,8 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .phylink_validate = mv88e6341_phylink_validate, }; @@ -4435,6 +4437,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .phylink_validate = mv88e6341_phylink_validate, }; From 6f14078e3ee59ccc5806f7bff0f25f94a6d3ff80 Mon Sep 17 00:00:00 2001 From: Sunil Kumar Kori Date: Wed, 30 Jun 2021 15:40:57 +0530 Subject: [PATCH 044/426] octeontx2-af: DMAC filter support in MAC block MAC block supports 32 dmac filters which are logically divided among all attached LMACS. For example MAC block0 having one LMAC then maximum supported filters are 32 where as MAC block1 having 4 enabled LMACS them maximum supported filteres are 8 for each LMAC. This patch adds mbox handlers to add/delete/update mac entry in DMAC filter table. Signed-off-by: Sunil Kumar Kori Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/cgx.c | 264 +++++++++++++++++- .../net/ethernet/marvell/octeontx2/af/cgx.h | 7 + .../marvell/octeontx2/af/lmac_common.h | 12 +- .../net/ethernet/marvell/octeontx2/af/mbox.h | 48 +++- .../net/ethernet/marvell/octeontx2/af/rvu.h | 2 + .../ethernet/marvell/octeontx2/af/rvu_cgx.c | 109 ++++++++ .../ethernet/marvell/octeontx2/af/rvu_nix.c | 3 + 7 files changed, 425 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index fac6474ad694..bc413f96b430 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -86,6 +86,22 @@ bool is_lmac_valid(struct cgx *cgx, int lmac_id) return test_bit(lmac_id, &cgx->lmac_bmap); } +/* Helper function to get sequential index + * given the enabled LMAC of a CGX + */ +static int get_sequence_id_of_lmac(struct cgx *cgx, int lmac_id) +{ + int tmp, id = 0; + + for_each_set_bit(tmp, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + if (tmp == lmac_id) + break; + id++; + } + + return id; +} + struct mac_ops *get_mac_ops(void *cgxd) { if (!cgxd) @@ -211,37 +227,229 @@ static u64 mac2u64 (u8 *mac_addr) return mac; } +static void cfg2mac(u64 cfg, u8 *mac_addr) +{ + int i, index = 0; + + for (i = ETH_ALEN - 1; i >= 0; i--, index++) + mac_addr[i] = (cfg >> (8 * index)) & 0xFF; +} + int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr) { struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); struct mac_ops *mac_ops; + int index, id; u64 cfg; + /* access mac_ops to know csr_offset */ mac_ops = cgx_dev->mac_ops; + /* copy 6bytes from macaddr */ /* memcpy(&cfg, mac_addr, 6); */ cfg = mac2u64 (mac_addr); - cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (lmac_id * 0x8)), + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max; + + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg | CGX_DMAC_CAM_ADDR_ENABLE | ((u64)lmac_id << 49)); cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); - cfg |= CGX_DMAC_CTL0_CAM_ENABLE; + cfg |= (CGX_DMAC_CTL0_CAM_ENABLE | CGX_DMAC_BCAST_MODE | + CGX_DMAC_MCAST_MODE); cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); return 0; } +int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); + struct mac_ops *mac_ops; + int index, idx; + u64 cfg = 0; + int id; + + if (!lmac) + return -ENODEV; + + mac_ops = cgx_dev->mac_ops; + /* Get available index where entry is to be installed */ + idx = rvu_alloc_rsrc(&lmac->mac_to_index_bmap); + if (idx < 0) + return idx; + + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max + idx; + + cfg = mac2u64 (mac_addr); + cfg |= CGX_DMAC_CAM_ADDR_ENABLE; + cfg |= ((u64)lmac_id << 49); + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg); + + cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); + cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_CAM_ACCEPT); + + if (is_multicast_ether_addr(mac_addr)) { + cfg &= ~GENMASK_ULL(2, 1); + cfg |= CGX_DMAC_MCAST_MODE_CAM; + lmac->mcast_filters_count++; + } else if (!lmac->mcast_filters_count) { + cfg |= CGX_DMAC_MCAST_MODE; + } + + cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); + + return idx; +} + +int cgx_lmac_addr_reset(u8 cgx_id, u8 lmac_id) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); + struct mac_ops *mac_ops; + u8 index = 0, id; + u64 cfg; + + if (!lmac) + return -ENODEV; + + mac_ops = cgx_dev->mac_ops; + /* Restore index 0 to its default init value as done during + * cgx_lmac_init + */ + set_bit(0, lmac->mac_to_index_bmap.bmap); + + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max + index; + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), 0); + + /* Reset CGXX_CMRX_RX_DMAC_CTL0 register to default state */ + cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); + cfg &= ~CGX_DMAC_CAM_ACCEPT; + cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_MCAST_MODE); + cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); + + return 0; +} + +/* Allows caller to change macaddress associated with index + * in dmac filter table including index 0 reserved for + * interface mac address + */ +int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct mac_ops *mac_ops; + struct lmac *lmac; + u64 cfg; + int id; + + lmac = lmac_pdata(lmac_id, cgx_dev); + if (!lmac) + return -ENODEV; + + mac_ops = cgx_dev->mac_ops; + /* Validate the index */ + if (index >= lmac->mac_to_index_bmap.max) + return -EINVAL; + + /* ensure index is already set */ + if (!test_bit(index, lmac->mac_to_index_bmap.bmap)) + return -EINVAL; + + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max + index; + + cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8))); + cfg &= ~CGX_RX_DMAC_ADR_MASK; + cfg |= mac2u64 (mac_addr); + + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg); + return 0; +} + +int cgx_lmac_addr_del(u8 cgx_id, u8 lmac_id, u8 index) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); + struct mac_ops *mac_ops; + u8 mac[ETH_ALEN]; + u64 cfg; + int id; + + if (!lmac) + return -ENODEV; + + mac_ops = cgx_dev->mac_ops; + /* Validate the index */ + if (index >= lmac->mac_to_index_bmap.max) + return -EINVAL; + + /* Skip deletion for reserved index i.e. index 0 */ + if (index == 0) + return 0; + + rvu_free_rsrc(&lmac->mac_to_index_bmap, index); + + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max + index; + + /* Read MAC address to check whether it is ucast or mcast */ + cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8))); + + cfg2mac(cfg, mac); + if (is_multicast_ether_addr(mac)) + lmac->mcast_filters_count--; + + if (!lmac->mcast_filters_count) { + cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); + cfg &= ~GENMASK_ULL(2, 1); + cfg |= CGX_DMAC_MCAST_MODE; + cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); + } + + cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), 0); + + return 0; +} + +int cgx_lmac_addr_max_entries_get(u8 cgx_id, u8 lmac_id) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); + + if (lmac) + return lmac->mac_to_index_bmap.max; + + return 0; +} + u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id) { struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev); struct mac_ops *mac_ops; + int index; u64 cfg; + int id; mac_ops = cgx_dev->mac_ops; - cfg = cgx_read(cgx_dev, 0, CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8); + id = get_sequence_id_of_lmac(cgx_dev, lmac_id); + + index = id * lmac->mac_to_index_bmap.max; + + cfg = cgx_read(cgx_dev, 0, CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8); return cfg & CGX_RX_DMAC_ADR_MASK; } @@ -297,35 +505,51 @@ int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable) void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable) { struct cgx *cgx = cgx_get_pdata(cgx_id); + struct lmac *lmac = lmac_pdata(lmac_id, cgx); + u16 max_dmac = lmac->mac_to_index_bmap.max; struct mac_ops *mac_ops; + int index, i; u64 cfg = 0; + int id; if (!cgx) return; + id = get_sequence_id_of_lmac(cgx, lmac_id); + mac_ops = cgx->mac_ops; if (enable) { /* Enable promiscuous mode on LMAC */ cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); - cfg &= ~(CGX_DMAC_CAM_ACCEPT | CGX_DMAC_MCAST_MODE); - cfg |= CGX_DMAC_BCAST_MODE; + cfg &= ~CGX_DMAC_CAM_ACCEPT; + cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_MCAST_MODE); cgx_write(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); - cfg = cgx_read(cgx, 0, - (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8)); - cfg &= ~CGX_DMAC_CAM_ADDR_ENABLE; - cgx_write(cgx, 0, - (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8), cfg); + for (i = 0; i < max_dmac; i++) { + index = id * max_dmac + i; + cfg = cgx_read(cgx, 0, + (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8)); + cfg &= ~CGX_DMAC_CAM_ADDR_ENABLE; + cgx_write(cgx, 0, + (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8), cfg); + } } else { /* Disable promiscuous mode */ cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); cfg |= CGX_DMAC_CAM_ACCEPT | CGX_DMAC_MCAST_MODE; cgx_write(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg); - cfg = cgx_read(cgx, 0, - (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8)); - cfg |= CGX_DMAC_CAM_ADDR_ENABLE; - cgx_write(cgx, 0, - (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8), cfg); + for (i = 0; i < max_dmac; i++) { + index = id * max_dmac + i; + cfg = cgx_read(cgx, 0, + (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8)); + if ((cfg & CGX_RX_DMAC_ADR_MASK) != 0) { + cfg |= CGX_DMAC_CAM_ADDR_ENABLE; + cgx_write(cgx, 0, + (CGXX_CMRX_RX_DMAC_CAM0 + + index * 0x8), + cfg); + } + } } } @@ -1234,6 +1458,15 @@ static int cgx_lmac_init(struct cgx *cgx) } lmac->cgx = cgx; + lmac->mac_to_index_bmap.max = + MAX_DMAC_ENTRIES_PER_CGX / cgx->lmac_count; + err = rvu_alloc_bitmap(&lmac->mac_to_index_bmap); + if (err) + return err; + + /* Reserve first entry for default MAC address */ + set_bit(0, lmac->mac_to_index_bmap.bmap); + init_waitqueue_head(&lmac->wq_cmd_cmplt); mutex_init(&lmac->cmd_lock); spin_lock_init(&lmac->event_cb_lock); @@ -1274,6 +1507,7 @@ static int cgx_lmac_exit(struct cgx *cgx) continue; cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, false); cgx_configure_interrupt(cgx, lmac, lmac->lmac_id, true); + kfree(lmac->mac_to_index_bmap.bmap); kfree(lmac->name); kfree(lmac); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 12521262164a..0c613f83a41c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -23,6 +23,7 @@ #define CGX_ID_MASK 0x7 #define MAX_LMAC_PER_CGX 4 +#define MAX_DMAC_ENTRIES_PER_CGX 32 #define CGX_FIFO_LEN 65536 /* 64K for both Rx & Tx */ #define CGX_OFFSET(x) ((x) * MAX_LMAC_PER_CGX) @@ -46,6 +47,7 @@ #define CGXX_CMRX_RX_DMAC_CTL0 (0x1F8 + mac_ops->csr_offset) #define CGX_DMAC_CTL0_CAM_ENABLE BIT_ULL(3) #define CGX_DMAC_CAM_ACCEPT BIT_ULL(3) +#define CGX_DMAC_MCAST_MODE_CAM BIT_ULL(2) #define CGX_DMAC_MCAST_MODE BIT_ULL(1) #define CGX_DMAC_BCAST_MODE BIT_ULL(0) #define CGXX_CMRX_RX_DMAC_CAM0 (0x200 + mac_ops->csr_offset) @@ -139,7 +141,11 @@ int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat); int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable); int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable); int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr); +int cgx_lmac_addr_reset(u8 cgx_id, u8 lmac_id); u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id); +int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr); +int cgx_lmac_addr_del(u8 cgx_id, u8 lmac_id, u8 index); +int cgx_lmac_addr_max_entries_get(u8 cgx_id, u8 lmac_id); void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable); void cgx_lmac_enadis_rx_pause_fwding(void *cgxd, int lmac_id, bool enable); int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable); @@ -165,4 +171,5 @@ u8 cgx_get_lmacid(void *cgxd, u8 lmac_index); unsigned long cgx_get_lmac_bmap(void *cgxd); void cgx_lmac_write(int cgx_id, int lmac_id, u64 offset, u64 val); u64 cgx_lmac_read(int cgx_id, int lmac_id, u64 offset); +int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index); #endif /* CGX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h index 45706fd87120..a8b7b1c7a1d5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h @@ -10,17 +10,19 @@ #include "rvu.h" #include "cgx.h" /** - * struct lmac + * struct lmac - per lmac locks and properties * @wq_cmd_cmplt: waitq to keep the process blocked until cmd completion * @cmd_lock: Lock to serialize the command interface * @resp: command response * @link_info: link related information + * @mac_to_index_bmap: Mac address to CGX table index mapping * @event_cb: callback for linkchange events * @event_cb_lock: lock for serializing callback with unregister + * @cgx: parent cgx port + * @mcast_filters_count: Number of multicast filters installed + * @lmac_id: lmac port id * @cmd_pend: flag set before new command is started * flag cleared after command response is received - * @cgx: parent cgx port - * @lmac_id: lmac port id * @name: lmac port name */ struct lmac { @@ -29,12 +31,14 @@ struct lmac { struct mutex cmd_lock; u64 resp; struct cgx_link_user_info link_info; + struct rsrc_bmap mac_to_index_bmap; struct cgx_event_cb event_cb; /* lock for serializing callback with unregister */ spinlock_t event_cb_lock; - bool cmd_pend; struct cgx *cgx; + u8 mcast_filters_count; u8 lmac_id; + bool cmd_pend; char *name; }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 9672cbf8a90a..f5ec39de026a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -165,7 +165,15 @@ M(CGX_SET_LINK_MODE, 0x214, cgx_set_link_mode, cgx_set_link_mode_req,\ M(CGX_FEATURES_GET, 0x215, cgx_features_get, msg_req, \ cgx_features_info_msg) \ M(RPM_STATS, 0x216, rpm_stats, msg_req, rpm_stats_rsp) \ - /* NPA mbox IDs (range 0x400 - 0x5FF) */ \ +M(CGX_MAC_ADDR_ADD, 0x217, cgx_mac_addr_add, cgx_mac_addr_add_req, \ + cgx_mac_addr_add_rsp) \ +M(CGX_MAC_ADDR_DEL, 0x218, cgx_mac_addr_del, cgx_mac_addr_del_req, \ + msg_rsp) \ +M(CGX_MAC_MAX_ENTRIES_GET, 0x219, cgx_mac_max_entries_get, msg_req, \ + cgx_max_dmac_entries_get_rsp) \ +M(CGX_MAC_ADDR_RESET, 0x21A, cgx_mac_addr_reset, msg_req, msg_rsp) \ +M(CGX_MAC_ADDR_UPDATE, 0x21B, cgx_mac_addr_update, cgx_mac_addr_update_req, \ + msg_rsp) \ /* NPA mbox IDs (range 0x400 - 0x5FF) */ \ M(NPA_LF_ALLOC, 0x400, npa_lf_alloc, \ npa_lf_alloc_req, npa_lf_alloc_rsp) \ @@ -403,6 +411,38 @@ struct cgx_mac_addr_set_or_get { u8 mac_addr[ETH_ALEN]; }; +/* Structure for requesting the operation to + * add DMAC filter entry into CGX interface + */ +struct cgx_mac_addr_add_req { + struct mbox_msghdr hdr; + u8 mac_addr[ETH_ALEN]; +}; + +/* Structure for response against the operation to + * add DMAC filter entry into CGX interface + */ +struct cgx_mac_addr_add_rsp { + struct mbox_msghdr hdr; + u8 index; +}; + +/* Structure for requesting the operation to + * delete DMAC filter entry from CGX interface + */ +struct cgx_mac_addr_del_req { + struct mbox_msghdr hdr; + u8 index; +}; + +/* Structure for response against the operation to + * get maximum supported DMAC filter entries + */ +struct cgx_max_dmac_entries_get_rsp { + struct mbox_msghdr hdr; + u8 max_dmac_filters; +}; + struct cgx_link_user_info { uint64_t link_up:1; uint64_t full_duplex:1; @@ -501,6 +541,12 @@ struct cgx_set_link_mode_rsp { int status; }; +struct cgx_mac_addr_update_req { + struct mbox_msghdr hdr; + u8 mac_addr[ETH_ALEN]; + u8 index; +}; + #define RVU_LMAC_FEAT_FC BIT_ULL(0) /* pause frames */ #define RVU_LMAC_FEAT_PTP BIT_ULL(1) /* precision time protocol */ #define RVU_MAC_VERSION BIT_ULL(2) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 3c0a7e981f72..bc0d24507033 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -657,6 +657,8 @@ void rvu_cgx_enadis_rx_bp(struct rvu *rvu, int pf, bool enable); int rvu_cgx_start_stop_io(struct rvu *rvu, u16 pcifunc, bool start); int rvu_cgx_nix_cuml_stats(struct rvu *rvu, void *cgxd, int lmac_id, int index, int rxtxflag, u64 *stat); +void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc); + /* NPA APIs */ int rvu_npa_init(struct rvu *rvu); void rvu_npa_freemem(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 6e2bf4fcd29c..9c6f4ba2d726 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -454,6 +454,31 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) return 0; } +void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc) +{ + int pf = rvu_get_pf(pcifunc); + int i = 0, lmac_count = 0; + u8 max_dmac_filters; + u8 cgx_id, lmac_id; + void *cgx_dev; + + if (!is_cgx_config_permitted(rvu, pcifunc)) + return; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgx_dev = cgx_get_pdata(cgx_id); + lmac_count = cgx_get_lmac_cnt(cgx_dev); + max_dmac_filters = MAX_DMAC_ENTRIES_PER_CGX / lmac_count; + + for (i = 0; i < max_dmac_filters; i++) + cgx_lmac_addr_del(cgx_id, lmac_id, i); + + /* As cgx_lmac_addr_del does not clear entry for index 0 + * so it needs to be done explicitly + */ + cgx_lmac_addr_reset(cgx_id, lmac_id); +} + int rvu_mbox_handler_cgx_start_rxtx(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { @@ -557,6 +582,63 @@ int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu, return 0; } +int rvu_mbox_handler_cgx_mac_addr_add(struct rvu *rvu, + struct cgx_mac_addr_add_req *req, + struct cgx_mac_addr_add_rsp *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + int rc = 0; + + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + rc = cgx_lmac_addr_add(cgx_id, lmac_id, req->mac_addr); + if (rc >= 0) { + rsp->index = rc; + return 0; + } + + return rc; +} + +int rvu_mbox_handler_cgx_mac_addr_del(struct rvu *rvu, + struct cgx_mac_addr_del_req *req, + struct msg_rsp *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + return cgx_lmac_addr_del(cgx_id, lmac_id, req->index); +} + +int rvu_mbox_handler_cgx_mac_max_entries_get(struct rvu *rvu, + struct msg_req *req, + struct cgx_max_dmac_entries_get_rsp + *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + + /* If msg is received from PFs(which are not mapped to CGX LMACs) + * or VF then no entries are allocated for DMAC filters at CGX level. + * So returning zero. + */ + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) { + rsp->max_dmac_filters = 0; + return 0; + } + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + rsp->max_dmac_filters = cgx_lmac_addr_max_entries_get(cgx_id, lmac_id); + return 0; +} + int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu, struct cgx_mac_addr_set_or_get *req, struct cgx_mac_addr_set_or_get *rsp) @@ -953,3 +1035,30 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu, rsp->status = cgx_set_link_mode(cgxd, req->args, cgx_idx, lmac); return 0; } + +int rvu_mbox_handler_cgx_mac_addr_reset(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + return cgx_lmac_addr_reset(cgx_id, lmac_id); +} + +int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu, + struct cgx_mac_addr_update_req *req, + struct msg_rsp *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + u8 cgx_id, lmac_id; + + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + return cgx_lmac_addr_update(cgx_id, lmac_id, req->mac_addr, req->index); +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index d6f8210652c5..aeae37704428 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -346,6 +346,9 @@ static void nix_interface_deinit(struct rvu *rvu, u16 pcifunc, u8 nixlf) /* Free and disable any MCAM entries used by this NIX LF */ rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf); + + /* Disable DMAC filters used */ + rvu_cgx_disable_dmac_entries(rvu, pcifunc); } int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu, From dbc52debf95f8f902f74309e7ae0de38e1ed4e4c Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Wed, 30 Jun 2021 15:40:58 +0530 Subject: [PATCH 045/426] octeontx2-af: Debugfs support for DMAC filters Add debugfs support to display CGX/RPM DMAC filter table associated with pf. cat /sys/kernel/debug/octeontx2/cgx/cgx0/lmac0/mac_filter PCI dev RVUPF BROADCAST MULTICAST FILTER-MODE 0002:02:00.0 PF2 ACCEPT ACCEPT UNICAST DMAC-INDEX ADDRESS 0 00:0f:b7:06:17:06 1 1a:1b:1c:1d:1e:01 2 1a:1b:1c:1d:1e:02 Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/cgx.c | 28 ++++++ .../net/ethernet/marvell/octeontx2/af/cgx.h | 3 + .../net/ethernet/marvell/octeontx2/af/rvu.h | 1 + .../ethernet/marvell/octeontx2/af/rvu_cgx.c | 2 +- .../marvell/octeontx2/af/rvu_debugfs.c | 88 +++++++++++++++++-- 5 files changed, 113 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index bc413f96b430..9169849881bf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -266,6 +266,34 @@ int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr) return 0; } +u64 cgx_read_dmac_ctrl(void *cgxd, int lmac_id) +{ + struct mac_ops *mac_ops; + struct cgx *cgx = cgxd; + + if (!cgxd || !is_lmac_valid(cgxd, lmac_id)) + return 0; + + cgx = cgxd; + /* Get mac_ops to know csr offset */ + mac_ops = cgx->mac_ops; + + return cgx_read(cgxd, lmac_id, CGXX_CMRX_RX_DMAC_CTL0); +} + +u64 cgx_read_dmac_entry(void *cgxd, int index) +{ + struct mac_ops *mac_ops; + struct cgx *cgx; + + if (!cgxd) + return 0; + + cgx = cgxd; + mac_ops = cgx->mac_ops; + return cgx_read(cgx, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 8))); +} + int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr) { struct cgx *cgx_dev = cgx_get_pdata(cgx_id); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 0c613f83a41c..237ba2b56210 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -52,6 +52,7 @@ #define CGX_DMAC_BCAST_MODE BIT_ULL(0) #define CGXX_CMRX_RX_DMAC_CAM0 (0x200 + mac_ops->csr_offset) #define CGX_DMAC_CAM_ADDR_ENABLE BIT_ULL(48) +#define CGX_DMAC_CAM_ENTRY_LMACID GENMASK_ULL(50, 49) #define CGXX_CMRX_RX_DMAC_CAM1 0x400 #define CGX_RX_DMAC_ADR_MASK GENMASK_ULL(47, 0) #define CGXX_CMRX_TX_STAT0 0x700 @@ -172,4 +173,6 @@ unsigned long cgx_get_lmac_bmap(void *cgxd); void cgx_lmac_write(int cgx_id, int lmac_id, u64 offset, u64 val); u64 cgx_lmac_read(int cgx_id, int lmac_id, u64 offset); int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index); +u64 cgx_read_dmac_ctrl(void *cgxd, int lmac_id); +u64 cgx_read_dmac_entry(void *cgxd, int index); #endif /* CGX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index bc0d24507033..10e58a5d5861 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -744,6 +744,7 @@ void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature); u32 rvu_cgx_get_fifolen(struct rvu *rvu); void *rvu_first_cgx_pdata(struct rvu *rvu); +int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id); int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf, int type); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 9c6f4ba2d726..6cc8fbb7190c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -63,7 +63,7 @@ static u16 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id) return rvu->cgxlmac2pf_map[CGX_OFFSET(cgx_id) + lmac_id]; } -static int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id) +int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id) { unsigned long pfmap; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 3cc3c6fd1d84..370d4ca1e5ed 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -1971,10 +1971,9 @@ static int cgx_print_stats(struct seq_file *s, int lmac_id) return err; } -static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused) +static int rvu_dbg_derive_lmacid(struct seq_file *filp, int *lmac_id) { struct dentry *current_dir; - int err, lmac_id; char *buf; current_dir = filp->file->f_path.dentry->d_parent; @@ -1982,17 +1981,87 @@ static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused) if (!buf) return -EINVAL; - err = kstrtoint(buf + 1, 10, &lmac_id); - if (!err) { - err = cgx_print_stats(filp, lmac_id); - if (err) - return err; - } + return kstrtoint(buf + 1, 10, lmac_id); +} + +static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused) +{ + int lmac_id, err; + + err = rvu_dbg_derive_lmacid(filp, &lmac_id); + if (!err) + return cgx_print_stats(filp, lmac_id); + return err; } RVU_DEBUG_SEQ_FOPS(cgx_stat, cgx_stat_display, NULL); +static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id) +{ + struct pci_dev *pdev = NULL; + void *cgxd = s->private; + char *bcast, *mcast; + u16 index, domain; + u8 dmac[ETH_ALEN]; + struct rvu *rvu; + u64 cfg, mac; + int pf; + + rvu = pci_get_drvdata(pci_get_device(PCI_VENDOR_ID_CAVIUM, + PCI_DEVID_OCTEONTX2_RVU_AF, NULL)); + if (!rvu) + return -ENODEV; + + pf = cgxlmac_to_pf(rvu, cgx_get_cgxid(cgxd), lmac_id); + domain = 2; + + pdev = pci_get_domain_bus_and_slot(domain, pf + 1, 0); + if (!pdev) + return 0; + + cfg = cgx_read_dmac_ctrl(cgxd, lmac_id); + bcast = cfg & CGX_DMAC_BCAST_MODE ? "ACCEPT" : "REJECT"; + mcast = cfg & CGX_DMAC_MCAST_MODE ? "ACCEPT" : "REJECT"; + + seq_puts(s, + "PCI dev RVUPF BROADCAST MULTICAST FILTER-MODE\n"); + seq_printf(s, "%s PF%d %9s %9s", + dev_name(&pdev->dev), pf, bcast, mcast); + if (cfg & CGX_DMAC_CAM_ACCEPT) + seq_printf(s, "%12s\n\n", "UNICAST"); + else + seq_printf(s, "%16s\n\n", "PROMISCUOUS"); + + seq_puts(s, "\nDMAC-INDEX ADDRESS\n"); + + for (index = 0 ; index < 32 ; index++) { + cfg = cgx_read_dmac_entry(cgxd, index); + /* Display enabled dmac entries associated with current lmac */ + if (lmac_id == FIELD_GET(CGX_DMAC_CAM_ENTRY_LMACID, cfg) && + FIELD_GET(CGX_DMAC_CAM_ADDR_ENABLE, cfg)) { + mac = FIELD_GET(CGX_RX_DMAC_ADR_MASK, cfg); + u64_to_ether_addr(mac, dmac); + seq_printf(s, "%7d %pM\n", index, dmac); + } + } + + return 0; +} + +static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *filp, void *unused) +{ + int err, lmac_id; + + err = rvu_dbg_derive_lmacid(filp, &lmac_id); + if (!err) + return cgx_print_dmac_flt(filp, lmac_id); + + return err; +} + +RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL); + static void rvu_dbg_cgx_init(struct rvu *rvu) { struct mac_ops *mac_ops; @@ -2029,6 +2098,9 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) debugfs_create_file("stats", 0600, rvu->rvu_dbg.lmac, cgx, &rvu_dbg_cgx_stat_fops); + debugfs_create_file("mac_filter", 0600, + rvu->rvu_dbg.lmac, cgx, + &rvu_dbg_cgx_dmac_flt_fops); } } } From 79d2be385e9eabe4403eb85bcc7d3efc6b936a76 Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Wed, 30 Jun 2021 15:40:59 +0530 Subject: [PATCH 046/426] octeontx2-pf: offload DMAC filters to CGX/RPM block DMAC filtering can be achieved by either NPC MCAM rules or CGX/RPM MAC filters. Currently we are achieving this by NPC MCAM rules. This patch offloads DMAC filters to CGX/RPM MAC filters instead of NPC MCAM rules. Offloading DMAC filter to CGX/RPM block helps in reducing traffic to NPC block and save MCAM rules Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../ethernet/marvell/octeontx2/nic/Makefile | 2 +- .../marvell/octeontx2/nic/otx2_common.c | 3 + .../marvell/octeontx2/nic/otx2_common.h | 11 + .../marvell/octeontx2/nic/otx2_dmac_flt.c | 173 +++++++++++++ .../marvell/octeontx2/nic/otx2_flows.c | 229 +++++++++++++++++- .../ethernet/marvell/octeontx2/nic/otx2_pf.c | 9 + 6 files changed, 417 insertions(+), 10 deletions(-) create mode 100644 drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 457c94793e63..3254b02205ca 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ - otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o + otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o rvu_nicvf-y := otx2_vf.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index cf7875d51d87..7cccd802c4ed 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -210,6 +210,9 @@ int otx2_set_mac_address(struct net_device *netdev, void *p) /* update dmac field in vlan offload rule */ if (pfvf->flags & OTX2_FLAG_RX_VLAN_SUPPORT) otx2_install_rxvlan_offload_flow(pfvf); + /* update dmac address in ntuple and DMAC filter list */ + if (pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT) + otx2_dmacflt_update_pfmac_flow(pfvf); } else { return -EPERM; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 20a9c69f020f..8fd58cd07f50 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -288,6 +288,9 @@ struct otx2_flow_config { u16 tc_flower_offset; u16 ntuple_max_flows; u16 tc_max_flows; + u8 dmacflt_max_flows; + u8 *bmap_to_dmacindex; + unsigned long dmacflt_bmap; struct list_head flow_list; }; @@ -329,6 +332,7 @@ struct otx2_nic { #define OTX2_FLAG_TC_FLOWER_SUPPORT BIT_ULL(11) #define OTX2_FLAG_TC_MATCHALL_EGRESS_ENABLED BIT_ULL(12) #define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED BIT_ULL(13) +#define OTX2_FLAG_DMACFLTR_SUPPORT BIT_ULL(14) u64 flags; struct otx2_qset qset; @@ -834,4 +838,11 @@ int otx2_init_tc(struct otx2_nic *nic); void otx2_shutdown_tc(struct otx2_nic *nic); int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data); +/* CGX/RPM DMAC filters support */ +int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf); +int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u8 bit_pos); +int otx2_dmacflt_remove(struct otx2_nic *pf, const u8 *mac, u8 bit_pos); +int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos); +void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf); +void otx2_dmacflt_update_pfmac_flow(struct otx2_nic *pfvf); #endif /* OTX2_COMMON_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c new file mode 100644 index 000000000000..ffe3e94562d0 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell OcteonTx2 RVU Physcial Function ethernet driver + * + * Copyright (C) 2021 Marvell. + */ + +#include "otx2_common.h" + +static int otx2_dmacflt_do_add(struct otx2_nic *pf, const u8 *mac, + u8 *dmac_index) +{ + struct cgx_mac_addr_add_req *req; + struct cgx_mac_addr_add_rsp *rsp; + int err; + + mutex_lock(&pf->mbox.lock); + + req = otx2_mbox_alloc_msg_cgx_mac_addr_add(&pf->mbox); + if (!req) { + mutex_unlock(&pf->mbox.lock); + return -ENOMEM; + } + + ether_addr_copy(req->mac_addr, mac); + err = otx2_sync_mbox_msg(&pf->mbox); + + if (!err) { + rsp = (struct cgx_mac_addr_add_rsp *) + otx2_mbox_get_rsp(&pf->mbox.mbox, 0, &req->hdr); + *dmac_index = rsp->index; + } + + mutex_unlock(&pf->mbox.lock); + return err; +} + +static int otx2_dmacflt_add_pfmac(struct otx2_nic *pf) +{ + struct cgx_mac_addr_set_or_get *req; + int err; + + mutex_lock(&pf->mbox.lock); + + req = otx2_mbox_alloc_msg_cgx_mac_addr_set(&pf->mbox); + if (!req) { + mutex_unlock(&pf->mbox.lock); + return -ENOMEM; + } + + ether_addr_copy(req->mac_addr, pf->netdev->dev_addr); + err = otx2_sync_mbox_msg(&pf->mbox); + + mutex_unlock(&pf->mbox.lock); + return err; +} + +int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u8 bit_pos) +{ + u8 *dmacindex; + + /* Store dmacindex returned by CGX/RPM driver which will + * be used for macaddr update/remove + */ + dmacindex = &pf->flow_cfg->bmap_to_dmacindex[bit_pos]; + + if (ether_addr_equal(mac, pf->netdev->dev_addr)) + return otx2_dmacflt_add_pfmac(pf); + else + return otx2_dmacflt_do_add(pf, mac, dmacindex); +} + +static int otx2_dmacflt_do_remove(struct otx2_nic *pfvf, const u8 *mac, + u8 dmac_index) +{ + struct cgx_mac_addr_del_req *req; + int err; + + mutex_lock(&pfvf->mbox.lock); + req = otx2_mbox_alloc_msg_cgx_mac_addr_del(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); + return -ENOMEM; + } + + req->index = dmac_index; + + err = otx2_sync_mbox_msg(&pfvf->mbox); + mutex_unlock(&pfvf->mbox.lock); + + return err; +} + +static int otx2_dmacflt_remove_pfmac(struct otx2_nic *pf) +{ + struct msg_req *req; + int err; + + mutex_lock(&pf->mbox.lock); + req = otx2_mbox_alloc_msg_cgx_mac_addr_reset(&pf->mbox); + if (!req) { + mutex_unlock(&pf->mbox.lock); + return -ENOMEM; + } + + err = otx2_sync_mbox_msg(&pf->mbox); + + mutex_unlock(&pf->mbox.lock); + return err; +} + +int otx2_dmacflt_remove(struct otx2_nic *pf, const u8 *mac, + u8 bit_pos) +{ + u8 dmacindex = pf->flow_cfg->bmap_to_dmacindex[bit_pos]; + + if (ether_addr_equal(mac, pf->netdev->dev_addr)) + return otx2_dmacflt_remove_pfmac(pf); + else + return otx2_dmacflt_do_remove(pf, mac, dmacindex); +} + +/* CGX/RPM blocks support max unicast entries of 32. + * on typical configuration MAC block associated + * with 4 lmacs, each lmac will have 8 dmac entries + */ +int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf) +{ + struct cgx_max_dmac_entries_get_rsp *rsp; + struct msg_req *msg; + int err; + + mutex_lock(&pf->mbox.lock); + msg = otx2_mbox_alloc_msg_cgx_mac_max_entries_get(&pf->mbox); + + if (!msg) { + mutex_unlock(&pf->mbox.lock); + return -ENOMEM; + } + + err = otx2_sync_mbox_msg(&pf->mbox); + if (err) + goto out; + + rsp = (struct cgx_max_dmac_entries_get_rsp *) + otx2_mbox_get_rsp(&pf->mbox.mbox, 0, &msg->hdr); + pf->flow_cfg->dmacflt_max_flows = rsp->max_dmac_filters; + +out: + mutex_unlock(&pf->mbox.lock); + return err; +} + +int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos) +{ + struct cgx_mac_addr_update_req *req; + int rc; + + mutex_lock(&pf->mbox.lock); + + req = otx2_mbox_alloc_msg_cgx_mac_addr_update(&pf->mbox); + + if (!req) { + mutex_unlock(&pf->mbox.lock); + rc = -ENOMEM; + } + + ether_addr_copy(req->mac_addr, mac); + req->index = pf->flow_cfg->bmap_to_dmacindex[bit_pos]; + rc = otx2_sync_mbox_msg(&pf->mbox); + + mutex_unlock(&pf->mbox.lock); + return rc; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 8c97106bdd1c..4d9de525802d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -18,6 +18,12 @@ struct otx2_flow { bool is_vf; u8 rss_ctx_id; int vf; + bool dmac_filter; +}; + +enum dmac_req { + DMAC_ADDR_UPDATE, + DMAC_ADDR_DEL }; static void otx2_clear_ntuple_flow_info(struct otx2_nic *pfvf, struct otx2_flow_config *flow_cfg) @@ -219,6 +225,22 @@ int otx2_mcam_flow_init(struct otx2_nic *pf) if (!pf->mac_table) return -ENOMEM; + otx2_dmacflt_get_max_cnt(pf); + + /* DMAC filters are not allocated */ + if (!pf->flow_cfg->dmacflt_max_flows) + return 0; + + pf->flow_cfg->bmap_to_dmacindex = + devm_kzalloc(pf->dev, sizeof(u8) * + pf->flow_cfg->dmacflt_max_flows, + GFP_KERNEL); + + if (!pf->flow_cfg->bmap_to_dmacindex) + return -ENOMEM; + + pf->flags |= OTX2_FLAG_DMACFLTR_SUPPORT; + return 0; } @@ -280,6 +302,12 @@ int otx2_add_macfilter(struct net_device *netdev, const u8 *mac) { struct otx2_nic *pf = netdev_priv(netdev); + if (bitmap_weight(&pf->flow_cfg->dmacflt_bmap, + pf->flow_cfg->dmacflt_max_flows)) + netdev_warn(netdev, + "Add %pM to CGX/RPM DMAC filters list as well\n", + mac); + return otx2_do_add_macfilter(pf, mac); } @@ -351,12 +379,22 @@ static void otx2_add_flow_to_list(struct otx2_nic *pfvf, struct otx2_flow *flow) list_add(&flow->list, head); } +static int otx2_get_maxflows(struct otx2_flow_config *flow_cfg) +{ + if (flow_cfg->nr_flows == flow_cfg->ntuple_max_flows || + bitmap_weight(&flow_cfg->dmacflt_bmap, + flow_cfg->dmacflt_max_flows)) + return flow_cfg->ntuple_max_flows + flow_cfg->dmacflt_max_flows; + else + return flow_cfg->ntuple_max_flows; +} + int otx2_get_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc, u32 location) { struct otx2_flow *iter; - if (location >= pfvf->flow_cfg->ntuple_max_flows) + if (location >= otx2_get_maxflows(pfvf->flow_cfg)) return -EINVAL; list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) { @@ -378,7 +416,7 @@ int otx2_get_all_flows(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc, int idx = 0; int err = 0; - nfc->data = pfvf->flow_cfg->ntuple_max_flows; + nfc->data = otx2_get_maxflows(pfvf->flow_cfg); while ((!err || err == -ENOENT) && idx < rule_cnt) { err = otx2_get_flow(pfvf, nfc, location); if (!err) @@ -760,6 +798,32 @@ int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp, return 0; } +static int otx2_is_flow_rule_dmacfilter(struct otx2_nic *pfvf, + struct ethtool_rx_flow_spec *fsp) +{ + struct ethhdr *eth_mask = &fsp->m_u.ether_spec; + struct ethhdr *eth_hdr = &fsp->h_u.ether_spec; + u64 ring_cookie = fsp->ring_cookie; + u32 flow_type; + + if (!(pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)) + return false; + + flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); + + /* CGX/RPM block dmac filtering configured for white listing + * check for action other than DROP + */ + if (flow_type == ETHER_FLOW && ring_cookie != RX_CLS_FLOW_DISC && + !ethtool_get_flow_spec_ring_vf(ring_cookie)) { + if (is_zero_ether_addr(eth_mask->h_dest) && + is_valid_ether_addr(eth_hdr->h_dest)) + return true; + } + + return false; +} + static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow) { u64 ring_cookie = flow->flow_spec.ring_cookie; @@ -818,14 +882,46 @@ static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow) return err; } +static int otx2_add_flow_with_pfmac(struct otx2_nic *pfvf, + struct otx2_flow *flow) +{ + struct otx2_flow *pf_mac; + struct ethhdr *eth_hdr; + + pf_mac = kzalloc(sizeof(*pf_mac), GFP_KERNEL); + if (!pf_mac) + return -ENOMEM; + + pf_mac->entry = 0; + pf_mac->dmac_filter = true; + pf_mac->location = pfvf->flow_cfg->ntuple_max_flows; + memcpy(&pf_mac->flow_spec, &flow->flow_spec, + sizeof(struct ethtool_rx_flow_spec)); + pf_mac->flow_spec.location = pf_mac->location; + + /* Copy PF mac address */ + eth_hdr = &pf_mac->flow_spec.h_u.ether_spec; + ether_addr_copy(eth_hdr->h_dest, pfvf->netdev->dev_addr); + + /* Install DMAC filter with PF mac address */ + otx2_dmacflt_add(pfvf, eth_hdr->h_dest, 0); + + otx2_add_flow_to_list(pfvf, pf_mac); + pfvf->flow_cfg->nr_flows++; + set_bit(0, &pfvf->flow_cfg->dmacflt_bmap); + + return 0; +} + int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) { struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; struct ethtool_rx_flow_spec *fsp = &nfc->fs; struct otx2_flow *flow; + struct ethhdr *eth_hdr; bool new = false; + int err = 0; u32 ring; - int err; ring = ethtool_get_flow_spec_ring(fsp->ring_cookie); if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT)) @@ -834,16 +930,15 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) if (ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC) return -EINVAL; - if (fsp->location >= flow_cfg->ntuple_max_flows) + if (fsp->location >= otx2_get_maxflows(flow_cfg)) return -EINVAL; flow = otx2_find_flow(pfvf, fsp->location); if (!flow) { - flow = kzalloc(sizeof(*flow), GFP_ATOMIC); + flow = kzalloc(sizeof(*flow), GFP_KERNEL); if (!flow) return -ENOMEM; flow->location = fsp->location; - flow->entry = flow_cfg->flow_ent[flow->location]; new = true; } /* struct copy */ @@ -852,7 +947,54 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) if (fsp->flow_type & FLOW_RSS) flow->rss_ctx_id = nfc->rss_context; - err = otx2_add_flow_msg(pfvf, flow); + if (otx2_is_flow_rule_dmacfilter(pfvf, &flow->flow_spec)) { + eth_hdr = &flow->flow_spec.h_u.ether_spec; + + /* Sync dmac filter table with updated fields */ + if (flow->dmac_filter) + return otx2_dmacflt_update(pfvf, eth_hdr->h_dest, + flow->entry); + + if (bitmap_full(&flow_cfg->dmacflt_bmap, + flow_cfg->dmacflt_max_flows)) { + netdev_warn(pfvf->netdev, + "Can't insert the rule %d as max allowed dmac filters are %d\n", + flow->location + + flow_cfg->dmacflt_max_flows, + flow_cfg->dmacflt_max_flows); + err = -EINVAL; + if (new) + kfree(flow); + return err; + } + + /* Install PF mac address to DMAC filter list */ + if (!test_bit(0, &flow_cfg->dmacflt_bmap)) + otx2_add_flow_with_pfmac(pfvf, flow); + + flow->dmac_filter = true; + flow->entry = find_first_zero_bit(&flow_cfg->dmacflt_bmap, + flow_cfg->dmacflt_max_flows); + fsp->location = flow_cfg->ntuple_max_flows + flow->entry; + flow->flow_spec.location = fsp->location; + flow->location = fsp->location; + + set_bit(flow->entry, &flow_cfg->dmacflt_bmap); + otx2_dmacflt_add(pfvf, eth_hdr->h_dest, flow->entry); + + } else { + if (flow->location >= pfvf->flow_cfg->ntuple_max_flows) { + netdev_warn(pfvf->netdev, + "Can't insert non dmac ntuple rule at %d, allowed range %d-0\n", + flow->location, + flow_cfg->ntuple_max_flows - 1); + err = -EINVAL; + } else { + flow->entry = flow_cfg->flow_ent[flow->location]; + err = otx2_add_flow_msg(pfvf, flow); + } + } + if (err) { if (new) kfree(flow); @@ -890,20 +1032,70 @@ static int otx2_remove_flow_msg(struct otx2_nic *pfvf, u16 entry, bool all) return err; } +static void otx2_update_rem_pfmac(struct otx2_nic *pfvf, int req) +{ + struct otx2_flow *iter; + struct ethhdr *eth_hdr; + bool found = false; + + list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) { + if (iter->dmac_filter && iter->entry == 0) { + eth_hdr = &iter->flow_spec.h_u.ether_spec; + if (req == DMAC_ADDR_DEL) { + otx2_dmacflt_remove(pfvf, eth_hdr->h_dest, + 0); + clear_bit(0, &pfvf->flow_cfg->dmacflt_bmap); + found = true; + } else { + ether_addr_copy(eth_hdr->h_dest, + pfvf->netdev->dev_addr); + otx2_dmacflt_update(pfvf, eth_hdr->h_dest, 0); + } + break; + } + } + + if (found) { + list_del(&iter->list); + kfree(iter); + pfvf->flow_cfg->nr_flows--; + } +} + int otx2_remove_flow(struct otx2_nic *pfvf, u32 location) { struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; struct otx2_flow *flow; int err; - if (location >= flow_cfg->ntuple_max_flows) + if (location >= otx2_get_maxflows(flow_cfg)) return -EINVAL; flow = otx2_find_flow(pfvf, location); if (!flow) return -ENOENT; - err = otx2_remove_flow_msg(pfvf, flow->entry, false); + if (flow->dmac_filter) { + struct ethhdr *eth_hdr = &flow->flow_spec.h_u.ether_spec; + + /* user not allowed to remove dmac filter with interface mac */ + if (ether_addr_equal(pfvf->netdev->dev_addr, eth_hdr->h_dest)) + return -EPERM; + + err = otx2_dmacflt_remove(pfvf, eth_hdr->h_dest, + flow->entry); + clear_bit(flow->entry, &flow_cfg->dmacflt_bmap); + /* If all dmac filters are removed delete macfilter with + * interface mac address and configure CGX/RPM block in + * promiscuous mode + */ + if (bitmap_weight(&flow_cfg->dmacflt_bmap, + flow_cfg->dmacflt_max_flows) == 1) + otx2_update_rem_pfmac(pfvf, DMAC_ADDR_DEL); + } else { + err = otx2_remove_flow_msg(pfvf, flow->entry, false); + } + if (err) return err; @@ -1100,3 +1292,22 @@ int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable) mutex_unlock(&pf->mbox.lock); return rsp_hdr->rc; } + +void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf) +{ + struct otx2_flow *iter; + struct ethhdr *eth_hdr; + + list_for_each_entry(iter, &pf->flow_cfg->flow_list, list) { + if (iter->dmac_filter) { + eth_hdr = &iter->flow_spec.h_u.ether_spec; + otx2_dmacflt_add(pf, eth_hdr->h_dest, + iter->entry); + } + } +} + +void otx2_dmacflt_update_pfmac_flow(struct otx2_nic *pfvf) +{ + otx2_update_rem_pfmac(pfvf, DMAC_ADDR_UPDATE); +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 088c28df849d..f300b807a85b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1110,6 +1110,11 @@ static int otx2_cgx_config_loopback(struct otx2_nic *pf, bool enable) struct msg_req *msg; int err; + if (enable && bitmap_weight(&pf->flow_cfg->dmacflt_bmap, + pf->flow_cfg->dmacflt_max_flows)) + netdev_warn(pf->netdev, + "CGX/RPM internal loopback might not work as DMAC filters are active\n"); + mutex_lock(&pf->mbox.lock); if (enable) msg = otx2_mbox_alloc_msg_cgx_intlbk_enable(&pf->mbox); @@ -1644,6 +1649,10 @@ int otx2_open(struct net_device *netdev) /* Restore pause frame settings */ otx2_config_pause_frm(pf); + /* Install DMAC Filters */ + if (pf->flags & OTX2_FLAG_DMACFLTR_SUPPORT) + otx2_dmacflt_reinstall_flows(pf); + err = otx2_rxtx_enable(pf, true); if (err) goto err_tx_stop_queues; From 856a5c97268d474282360c8a3cf4f37f6036dbec Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:37:06 +0530 Subject: [PATCH 047/426] net: wwan: iosm: fix uevent reporting Change uevent env variable name to IOSM_EVENT & correct reporting format to key=value pair. Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_uevent.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_uevent.c b/drivers/net/wwan/iosm/iosm_ipc_uevent.c index 2229d752926c..d12188ffed7e 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_uevent.c +++ b/drivers/net/wwan/iosm/iosm_ipc_uevent.c @@ -37,7 +37,7 @@ void ipc_uevent_send(struct device *dev, char *uevent) /* Store the device and event information */ info->dev = dev; - snprintf(info->uevent, MAX_UEVENT_LEN, "%s: %s", dev_name(dev), uevent); + snprintf(info->uevent, MAX_UEVENT_LEN, "IOSM_EVENT=%s", uevent); /* Schedule uevent in process context using work queue */ schedule_work(&info->work); From 3bcfc0a2d3199d0a83d47ed67ad57a1c2f5a16d7 Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:37:31 +0530 Subject: [PATCH 048/426] net: wwan: iosm: remove reduandant check Remove reduandant IP session id check since required checks are in place under caller. Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_imem_ops.c | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index 46f76e8aae92..e4e9461b603e 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -24,15 +24,7 @@ int ipc_imem_sys_wwan_open(struct iosm_imem *ipc_imem, int if_id) return -EIO; } - /* check for the interafce id - * if if_id 1 to 8 then create IP MUX channel sessions. - * To start MUX session from 0 as network interface id would start - * from 1 so map it to if_id = if_id - 1 - */ - if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END) - return ipc_mux_open_session(ipc_imem->mux, if_id - 1); - - return -EINVAL; + return ipc_mux_open_session(ipc_imem->mux, if_id - 1); } /* Release a net link to CP. */ @@ -83,13 +75,8 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, goto out; } - if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END) - /* Route the UL packet through IP MUX Layer */ - ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, - if_id - 1, skb); - else - dev_err(ipc_imem->dev, - "invalid if_id %d: ", if_id); + /* Route the UL packet through IP MUX Layer */ + ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, if_id - 1, skb); out: return ret; } From 5bb4eea0c5f5b9383a543293966bdf20e54988aa Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:37:45 +0530 Subject: [PATCH 049/426] net: wwan: iosm: correct link-id handling Link ID to be kept intact with MBIM session ID Ex: ID 0 should be associated to MBIM session ID 0. Reported-by: Loic Poulain Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_imem_ops.c | 6 +++--- drivers/net/wwan/iosm/iosm_ipc_imem_ops.h | 6 +++--- drivers/net/wwan/iosm/iosm_ipc_mux_codec.c | 2 +- drivers/net/wwan/iosm/iosm_ipc_wwan.c | 4 ++-- 4 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index e4e9461b603e..0a472ce77370 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -24,7 +24,7 @@ int ipc_imem_sys_wwan_open(struct iosm_imem *ipc_imem, int if_id) return -EIO; } - return ipc_mux_open_session(ipc_imem->mux, if_id - 1); + return ipc_mux_open_session(ipc_imem->mux, if_id); } /* Release a net link to CP. */ @@ -33,7 +33,7 @@ void ipc_imem_sys_wwan_close(struct iosm_imem *ipc_imem, int if_id, { if (ipc_imem->mux && if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END) - ipc_mux_close_session(ipc_imem->mux, if_id - 1); + ipc_mux_close_session(ipc_imem->mux, if_id); } /* Tasklet call to do uplink transfer. */ @@ -76,7 +76,7 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, } /* Route the UL packet through IP MUX Layer */ - ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, if_id - 1, skb); + ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, if_id, skb); out: return ret; } diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h index fd356dafbdd6..2007fe23e9a5 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -27,11 +27,11 @@ #define BOOT_CHECK_DEFAULT_TIMEOUT 400 /* IP MUX channel range */ -#define IP_MUX_SESSION_START 1 -#define IP_MUX_SESSION_END 8 +#define IP_MUX_SESSION_START 0 +#define IP_MUX_SESSION_END 7 /* Default IP MUX channel */ -#define IP_MUX_SESSION_DEFAULT 1 +#define IP_MUX_SESSION_DEFAULT 0 /** * ipc_imem_sys_port_open - Open a port link to CP. diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c index e634ffc6ec08..562de275797a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c @@ -288,7 +288,7 @@ static int ipc_mux_net_receive(struct iosm_mux *ipc_mux, int if_id, /* Pass the packet to the netif layer. */ dest_skb->priority = service_class; - return ipc_wwan_receive(wwan, dest_skb, false, if_id + 1); + return ipc_wwan_receive(wwan, dest_skb, false, if_id); } /* Decode Flow Credit Table in the block */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index c999c64001f4..84e37c4b0f74 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -252,8 +252,8 @@ int ipc_wwan_receive(struct iosm_wwan *ipc_wwan, struct sk_buff *skb_arg, skb->pkt_type = PACKET_HOST; - if (if_id < (IP_MUX_SESSION_START - 1) || - if_id > (IP_MUX_SESSION_END - 1)) { + if (if_id < IP_MUX_SESSION_START || + if_id > IP_MUX_SESSION_END) { ret = -EINVAL; goto free; } From c302e3a1c86f78421d58ef564ba22519b0b039c0 Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:39:17 +0530 Subject: [PATCH 050/426] net: wwan: iosm: fix netdev tx stats Update tx stats on successful packet consume, drop. Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_wwan.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index 84e37c4b0f74..e0c19c59c5f6 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -107,6 +107,7 @@ static int ipc_wwan_link_transmit(struct sk_buff *skb, { struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); struct iosm_wwan *ipc_wwan = priv->ipc_wwan; + unsigned int len = skb->len; int if_id = priv->if_id; int ret; @@ -123,6 +124,8 @@ static int ipc_wwan_link_transmit(struct sk_buff *skb, /* Return code of zero is success */ if (ret == 0) { + netdev->stats.tx_packets++; + netdev->stats.tx_bytes += len; ret = NETDEV_TX_OK; } else if (ret == -EBUSY) { ret = NETDEV_TX_BUSY; @@ -140,7 +143,8 @@ exit: ret); dev_kfree_skb_any(skb); - return ret; + netdev->stats.tx_dropped++; + return NETDEV_TX_OK; } /* Ops structure for wwan net link */ From d7340f46beae05227f5f4a1c8cb18e81e0c3fe0e Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Thu, 1 Jul 2021 20:39:34 +0530 Subject: [PATCH 051/426] net: wwan: iosm: set default mtu Set netdev default mtu size to 1500. Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index e0c19c59c5f6..b2357ad5d517 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -162,6 +162,7 @@ static void ipc_wwan_setup(struct net_device *iosm_dev) iosm_dev->priv_flags |= IFF_NO_QUEUE; iosm_dev->type = ARPHRD_NONE; + iosm_dev->mtu = ETH_DATA_LEN; iosm_dev->min_mtu = ETH_MIN_MTU; iosm_dev->max_mtu = ETH_MAX_MTU; From 5d43f951b1ac797450bb4d230fdc960b739bea04 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:52 +0800 Subject: [PATCH 052/426] ptp: add ptp virtual clock driver framework This patch is to add ptp virtual clock driver framework utilizing timecounter/cyclecounter. The patch just exports two essential APIs for PTP driver. - ptp_vclock_register() - ptp_vclock_unregister() Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/Makefile | 2 +- drivers/ptp/ptp_private.h | 15 ++++ drivers/ptp/ptp_vclock.c | 150 +++++++++++++++++++++++++++++++ include/linux/ptp_clock_kernel.h | 4 +- 4 files changed, 169 insertions(+), 2 deletions(-) create mode 100644 drivers/ptp/ptp_vclock.c diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile index 8673d1743faa..28a6fe342d3e 100644 --- a/drivers/ptp/Makefile +++ b/drivers/ptp/Makefile @@ -3,7 +3,7 @@ # Makefile for PTP 1588 clock support. # -ptp-y := ptp_clock.o ptp_chardev.o ptp_sysfs.o +ptp-y := ptp_clock.o ptp_chardev.o ptp_sysfs.o ptp_vclock.o ptp_kvm-$(CONFIG_X86) := ptp_kvm_x86.o ptp_kvm_common.o ptp_kvm-$(CONFIG_HAVE_ARM_SMCCC) := ptp_kvm_arm.o ptp_kvm_common.o obj-$(CONFIG_PTP_1588_CLOCK) += ptp.o diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 6b97155148f1..853b79b6b30e 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -48,6 +48,19 @@ struct ptp_clock { struct kthread_delayed_work aux_work; }; +#define info_to_vclock(d) container_of((d), struct ptp_vclock, info) +#define cc_to_vclock(d) container_of((d), struct ptp_vclock, cc) +#define dw_to_vclock(d) container_of((d), struct ptp_vclock, refresh_work) + +struct ptp_vclock { + struct ptp_clock *pclock; + struct ptp_clock_info info; + struct ptp_clock *clock; + struct cyclecounter cc; + struct timecounter tc; + spinlock_t lock; /* protects tc/cc */ +}; + /* * The function queue_cnt() is safe for readers to call without * holding q->lock. Readers use this function to verify that the queue @@ -89,4 +102,6 @@ extern const struct attribute_group *ptp_groups[]; int ptp_populate_pin_groups(struct ptp_clock *ptp); void ptp_cleanup_pin_groups(struct ptp_clock *ptp); +struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock); +void ptp_vclock_unregister(struct ptp_vclock *vclock); #endif diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c new file mode 100644 index 000000000000..fc9205cc504d --- /dev/null +++ b/drivers/ptp/ptp_vclock.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * PTP virtual clock driver + * + * Copyright 2021 NXP + */ +#include +#include "ptp_private.h" + +#define PTP_VCLOCK_CC_SHIFT 31 +#define PTP_VCLOCK_CC_MULT (1 << PTP_VCLOCK_CC_SHIFT) +#define PTP_VCLOCK_FADJ_SHIFT 9 +#define PTP_VCLOCK_FADJ_DENOMINATOR 15625ULL +#define PTP_VCLOCK_REFRESH_INTERVAL (HZ * 2) + +static int ptp_vclock_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + unsigned long flags; + s64 adj; + + adj = (s64)scaled_ppm << PTP_VCLOCK_FADJ_SHIFT; + adj = div_s64(adj, PTP_VCLOCK_FADJ_DENOMINATOR); + + spin_lock_irqsave(&vclock->lock, flags); + timecounter_read(&vclock->tc); + vclock->cc.mult = PTP_VCLOCK_CC_MULT + adj; + spin_unlock_irqrestore(&vclock->lock, flags); + + return 0; +} + +static int ptp_vclock_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + unsigned long flags; + + spin_lock_irqsave(&vclock->lock, flags); + timecounter_adjtime(&vclock->tc, delta); + spin_unlock_irqrestore(&vclock->lock, flags); + + return 0; +} + +static int ptp_vclock_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + unsigned long flags; + u64 ns; + + spin_lock_irqsave(&vclock->lock, flags); + ns = timecounter_read(&vclock->tc); + spin_unlock_irqrestore(&vclock->lock, flags); + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int ptp_vclock_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + u64 ns = timespec64_to_ns(ts); + unsigned long flags; + + spin_lock_irqsave(&vclock->lock, flags); + timecounter_init(&vclock->tc, &vclock->cc, ns); + spin_unlock_irqrestore(&vclock->lock, flags); + + return 0; +} + +static long ptp_vclock_refresh(struct ptp_clock_info *ptp) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + struct timespec64 ts; + + ptp_vclock_gettime(&vclock->info, &ts); + + return PTP_VCLOCK_REFRESH_INTERVAL; +} + +static const struct ptp_clock_info ptp_vclock_info = { + .owner = THIS_MODULE, + .name = "ptp virtual clock", + /* The maximum ppb value that long scaled_ppm can support */ + .max_adj = 32767999, + .adjfine = ptp_vclock_adjfine, + .adjtime = ptp_vclock_adjtime, + .gettime64 = ptp_vclock_gettime, + .settime64 = ptp_vclock_settime, + .do_aux_work = ptp_vclock_refresh, +}; + +static u64 ptp_vclock_read(const struct cyclecounter *cc) +{ + struct ptp_vclock *vclock = cc_to_vclock(cc); + struct ptp_clock *ptp = vclock->pclock; + struct timespec64 ts = {}; + + if (ptp->info->gettimex64) + ptp->info->gettimex64(ptp->info, &ts, NULL); + else + ptp->info->gettime64(ptp->info, &ts); + + return timespec64_to_ns(&ts); +} + +static const struct cyclecounter ptp_vclock_cc = { + .read = ptp_vclock_read, + .mask = CYCLECOUNTER_MASK(32), + .mult = PTP_VCLOCK_CC_MULT, + .shift = PTP_VCLOCK_CC_SHIFT, +}; + +struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock) +{ + struct ptp_vclock *vclock; + + vclock = kzalloc(sizeof(*vclock), GFP_KERNEL); + if (!vclock) + return NULL; + + vclock->pclock = pclock; + vclock->info = ptp_vclock_info; + vclock->cc = ptp_vclock_cc; + + snprintf(vclock->info.name, PTP_CLOCK_NAME_LEN, "ptp%d_virt", + pclock->index); + + spin_lock_init(&vclock->lock); + + vclock->clock = ptp_clock_register(&vclock->info, &pclock->dev); + if (IS_ERR_OR_NULL(vclock->clock)) { + kfree(vclock); + return NULL; + } + + timecounter_init(&vclock->tc, &vclock->cc, 0); + ptp_schedule_worker(vclock->clock, PTP_VCLOCK_REFRESH_INTERVAL); + + return vclock; +} + +void ptp_vclock_unregister(struct ptp_vclock *vclock) +{ + ptp_clock_unregister(vclock->clock); + kfree(vclock); +} diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index aba237c0b3a2..b6fb771ee524 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -11,7 +11,9 @@ #include #include #include +#include +#define PTP_CLOCK_NAME_LEN 32 /** * struct ptp_clock_request - request PTP clock event * @@ -134,7 +136,7 @@ struct ptp_system_timestamp { struct ptp_clock_info { struct module *owner; - char name[16]; + char name[PTP_CLOCK_NAME_LEN]; s32 max_adj; int n_alarm; int n_ext_ts; From 73f37068d540eba5f93ba3a0019bf479d35ebd76 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:53 +0800 Subject: [PATCH 053/426] ptp: support ptp physical/virtual clocks conversion Support ptp physical/virtual clocks conversion via sysfs. There will be a new attribute n_vclocks under ptp physical clock sysfs. - In default, the value is 0 meaning only ptp physical clock is in use. - Setting the value can create corresponding number of ptp virtual clocks to use. But current physical clock is guaranteed to stay free running. - Setting the value back to 0 can delete virtual clocks and back use physical clock again. Another new attribute max_vclocks control the maximum number of ptp vclocks. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- Documentation/ABI/testing/sysfs-ptp | 20 ++++ drivers/ptp/ptp_clock.c | 26 ++++++ drivers/ptp/ptp_private.h | 21 +++++ drivers/ptp/ptp_sysfs.c | 138 ++++++++++++++++++++++++++++ 4 files changed, 205 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-ptp b/Documentation/ABI/testing/sysfs-ptp index 2363ad810ddb..d378f57c1b73 100644 --- a/Documentation/ABI/testing/sysfs-ptp +++ b/Documentation/ABI/testing/sysfs-ptp @@ -33,6 +33,13 @@ Description: frequency adjustment value (a positive integer) in parts per billion. +What: /sys/class/ptp/ptpN/max_vclocks +Date: May 2021 +Contact: Yangbo Lu +Description: + This file contains the maximum number of ptp vclocks. + Write integer to re-configure it. + What: /sys/class/ptp/ptpN/n_alarms Date: September 2010 Contact: Richard Cochran @@ -61,6 +68,19 @@ Description: This file contains the number of programmable pins offered by the PTP hardware clock. +What: /sys/class/ptp/ptpN/n_vclocks +Date: May 2021 +Contact: Yangbo Lu +Description: + This file contains the number of virtual PTP clocks in + use. By default, the value is 0 meaning that only the + physical clock is in use. Setting the value creates + the corresponding number of virtual clocks and causes + the physical clock to become free running. Setting the + value back to 0 deletes the virtual clocks and + switches the physical clock back to normal, adjustable + operation. + What: /sys/class/ptp/ptpN/pins Date: March 2014 Contact: Richard Cochran diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index a23a37a4d5dc..7334f478dde7 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -76,6 +76,11 @@ static int ptp_clock_settime(struct posix_clock *pc, const struct timespec64 *tp { struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); + if (ptp_vclock_in_use(ptp)) { + pr_err("ptp: virtual clock in use\n"); + return -EBUSY; + } + return ptp->info->settime64(ptp->info, tp); } @@ -97,6 +102,11 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) struct ptp_clock_info *ops; int err = -EOPNOTSUPP; + if (ptp_vclock_in_use(ptp)) { + pr_err("ptp: virtual clock in use\n"); + return -EBUSY; + } + ops = ptp->info; if (tx->modes & ADJ_SETOFFSET) { @@ -161,6 +171,7 @@ static void ptp_clock_release(struct device *dev) ptp_cleanup_pin_groups(ptp); mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); + mutex_destroy(&ptp->n_vclocks_mux); ida_simple_remove(&ptp_clocks_map, ptp->index); kfree(ptp); } @@ -208,6 +219,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, spin_lock_init(&ptp->tsevq.lock); mutex_init(&ptp->tsevq_mux); mutex_init(&ptp->pincfg_mux); + mutex_init(&ptp->n_vclocks_mux); init_waitqueue_head(&ptp->tsev_wq); if (ptp->info->do_aux_work) { @@ -221,6 +233,14 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, ptp->pps_source->lookup_cookie = ptp; } + /* PTP virtual clock is being registered under physical clock */ + if (parent->class && parent->class->name && + strcmp(parent->class->name, "ptp") == 0) + ptp->is_virtual_clock = true; + + if (!ptp->is_virtual_clock) + ptp->max_vclocks = PTP_DEFAULT_MAX_VCLOCKS; + err = ptp_populate_pin_groups(ptp); if (err) goto no_pin_groups; @@ -270,6 +290,7 @@ no_pin_groups: kworker_err: mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); + mutex_destroy(&ptp->n_vclocks_mux); ida_simple_remove(&ptp_clocks_map, index); no_slot: kfree(ptp); @@ -280,6 +301,11 @@ EXPORT_SYMBOL(ptp_clock_register); int ptp_clock_unregister(struct ptp_clock *ptp) { + if (ptp_vclock_in_use(ptp)) { + pr_err("ptp: virtual clock in use\n"); + return -EBUSY; + } + ptp->defunct = 1; wake_up_interruptible(&ptp->tsev_wq); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 853b79b6b30e..87cb55953b69 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -18,6 +18,7 @@ #define PTP_MAX_TIMESTAMPS 128 #define PTP_BUF_TIMESTAMPS 30 +#define PTP_DEFAULT_MAX_VCLOCKS 20 struct timestamp_event_queue { struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS]; @@ -46,6 +47,10 @@ struct ptp_clock { const struct attribute_group *pin_attr_groups[2]; struct kthread_worker *kworker; struct kthread_delayed_work aux_work; + unsigned int max_vclocks; + unsigned int n_vclocks; + struct mutex n_vclocks_mux; /* protect concurrent n_vclocks access */ + bool is_virtual_clock; }; #define info_to_vclock(d) container_of((d), struct ptp_vclock, info) @@ -74,6 +79,22 @@ static inline int queue_cnt(struct timestamp_event_queue *q) return cnt < 0 ? PTP_MAX_TIMESTAMPS + cnt : cnt; } +/* Check if ptp virtual clock is in use */ +static inline bool ptp_vclock_in_use(struct ptp_clock *ptp) +{ + bool in_use = false; + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) + return true; + + if (!ptp->is_virtual_clock && ptp->n_vclocks) + in_use = true; + + mutex_unlock(&ptp->n_vclocks_mux); + + return in_use; +} + /* * see ptp_chardev.c */ diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index be076a91e20e..0b05041783a5 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -3,6 +3,7 @@ * PTP 1588 clock support - sysfs interface. * * Copyright (C) 2010 OMICRON electronics GmbH + * Copyright 2021 NXP */ #include #include @@ -148,6 +149,137 @@ out: } static DEVICE_ATTR(pps_enable, 0220, NULL, pps_enable_store); +static int unregister_vclock(struct device *dev, void *data) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + struct ptp_clock_info *info = ptp->info; + struct ptp_vclock *vclock; + u8 *num = data; + + vclock = info_to_vclock(info); + dev_info(dev->parent, "delete virtual clock ptp%d\n", + vclock->clock->index); + + ptp_vclock_unregister(vclock); + (*num)--; + + /* For break. Not error. */ + if (*num == 0) + return -EINVAL; + + return 0; +} + +static ssize_t n_vclocks_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + ssize_t size; + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) + return -ERESTARTSYS; + + size = snprintf(page, PAGE_SIZE - 1, "%d\n", ptp->n_vclocks); + + mutex_unlock(&ptp->n_vclocks_mux); + + return size; +} + +static ssize_t n_vclocks_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + struct ptp_vclock *vclock; + int err = -EINVAL; + u32 num, i; + + if (kstrtou32(buf, 0, &num)) + return err; + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) + return -ERESTARTSYS; + + if (num > ptp->max_vclocks) { + dev_err(dev, "max value is %d\n", ptp->max_vclocks); + goto out; + } + + /* Need to create more vclocks */ + if (num > ptp->n_vclocks) { + for (i = 0; i < num - ptp->n_vclocks; i++) { + vclock = ptp_vclock_register(ptp); + if (!vclock) + goto out; + + dev_info(dev, "new virtual clock ptp%d\n", + vclock->clock->index); + } + } + + /* Need to delete vclocks */ + if (num < ptp->n_vclocks) { + i = ptp->n_vclocks - num; + device_for_each_child_reverse(dev, &i, + unregister_vclock); + } + + if (num == 0) + dev_info(dev, "only physical clock in use now\n"); + else + dev_info(dev, "guarantee physical clock free running\n"); + + ptp->n_vclocks = num; + mutex_unlock(&ptp->n_vclocks_mux); + + return count; +out: + mutex_unlock(&ptp->n_vclocks_mux); + return err; +} +static DEVICE_ATTR_RW(n_vclocks); + +static ssize_t max_vclocks_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + ssize_t size; + + size = snprintf(page, PAGE_SIZE - 1, "%d\n", ptp->max_vclocks); + + return size; +} + +static ssize_t max_vclocks_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + u32 max; + + if (kstrtou32(buf, 0, &max) || max == 0) + return -EINVAL; + + if (max == ptp->max_vclocks) + return count; + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) + return -ERESTARTSYS; + + if (max < ptp->n_vclocks) { + mutex_unlock(&ptp->n_vclocks_mux); + return -EINVAL; + } + + ptp->max_vclocks = max; + + mutex_unlock(&ptp->n_vclocks_mux); + + return count; +} +static DEVICE_ATTR_RW(max_vclocks); + static struct attribute *ptp_attrs[] = { &dev_attr_clock_name.attr, @@ -162,6 +294,8 @@ static struct attribute *ptp_attrs[] = { &dev_attr_fifo.attr, &dev_attr_period.attr, &dev_attr_pps_enable.attr, + &dev_attr_n_vclocks.attr, + &dev_attr_max_vclocks.attr, NULL }; @@ -183,6 +317,10 @@ static umode_t ptp_is_attribute_visible(struct kobject *kobj, } else if (attr == &dev_attr_pps_enable.attr) { if (!info->pps) mode = 0; + } else if (attr == &dev_attr_n_vclocks.attr || + attr == &dev_attr_max_vclocks.attr) { + if (ptp->is_virtual_clock) + mode = 0; } return mode; From 44c494c8e30e35713c7d11ca3c5ab332cbfabacf Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:54 +0800 Subject: [PATCH 054/426] ptp: track available ptp vclocks information Track available ptp vclocks information. Record index values of available ptp vclocks during registering and unregistering. This is preparation for supporting ptp vclocks info query through ethtool. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 15 ++++++++++++++- drivers/ptp/ptp_private.h | 1 + drivers/ptp/ptp_sysfs.c | 28 +++++++++++++++++++++++++--- 3 files changed, 40 insertions(+), 4 deletions(-) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 7334f478dde7..9205a9362a9d 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -196,6 +196,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, { struct ptp_clock *ptp; int err = 0, index, major = MAJOR(ptp_devt); + size_t size; if (info->n_alarm > PTP_MAX_ALARMS) return ERR_PTR(-EINVAL); @@ -238,9 +239,17 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, strcmp(parent->class->name, "ptp") == 0) ptp->is_virtual_clock = true; - if (!ptp->is_virtual_clock) + if (!ptp->is_virtual_clock) { ptp->max_vclocks = PTP_DEFAULT_MAX_VCLOCKS; + size = sizeof(int) * ptp->max_vclocks; + ptp->vclock_index = kzalloc(size, GFP_KERNEL); + if (!ptp->vclock_index) { + err = -ENOMEM; + goto no_mem_for_vclocks; + } + } + err = ptp_populate_pin_groups(ptp); if (err) goto no_pin_groups; @@ -285,6 +294,8 @@ no_clock: no_pps: ptp_cleanup_pin_groups(ptp); no_pin_groups: + kfree(ptp->vclock_index); +no_mem_for_vclocks: if (ptp->kworker) kthread_destroy_worker(ptp->kworker); kworker_err: @@ -309,6 +320,8 @@ int ptp_clock_unregister(struct ptp_clock *ptp) ptp->defunct = 1; wake_up_interruptible(&ptp->tsev_wq); + kfree(ptp->vclock_index); + if (ptp->kworker) { kthread_cancel_delayed_work_sync(&ptp->aux_work); kthread_destroy_worker(ptp->kworker); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 87cb55953b69..f75fadd9b244 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -49,6 +49,7 @@ struct ptp_clock { struct kthread_delayed_work aux_work; unsigned int max_vclocks; unsigned int n_vclocks; + int *vclock_index; struct mutex n_vclocks_mux; /* protect concurrent n_vclocks access */ bool is_virtual_clock; }; diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index 0b05041783a5..6a36590ca77a 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -213,6 +213,9 @@ static ssize_t n_vclocks_store(struct device *dev, if (!vclock) goto out; + *(ptp->vclock_index + ptp->n_vclocks + i) = + vclock->clock->index; + dev_info(dev, "new virtual clock ptp%d\n", vclock->clock->index); } @@ -223,6 +226,9 @@ static ssize_t n_vclocks_store(struct device *dev, i = ptp->n_vclocks - num; device_for_each_child_reverse(dev, &i, unregister_vclock); + + for (i = 1; i <= ptp->n_vclocks - num; i++) + *(ptp->vclock_index + ptp->n_vclocks - i) = -1; } if (num == 0) @@ -256,6 +262,9 @@ static ssize_t max_vclocks_store(struct device *dev, const char *buf, size_t count) { struct ptp_clock *ptp = dev_get_drvdata(dev); + unsigned int *vclock_index; + int err = -EINVAL; + size_t size; u32 max; if (kstrtou32(buf, 0, &max) || max == 0) @@ -267,16 +276,29 @@ static ssize_t max_vclocks_store(struct device *dev, if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) return -ERESTARTSYS; - if (max < ptp->n_vclocks) { - mutex_unlock(&ptp->n_vclocks_mux); - return -EINVAL; + if (max < ptp->n_vclocks) + goto out; + + size = sizeof(int) * max; + vclock_index = kzalloc(size, GFP_KERNEL); + if (!vclock_index) { + err = -ENOMEM; + goto out; } + size = sizeof(int) * ptp->n_vclocks; + memcpy(vclock_index, ptp->vclock_index, size); + + kfree(ptp->vclock_index); + ptp->vclock_index = vclock_index; ptp->max_vclocks = max; mutex_unlock(&ptp->n_vclocks_mux); return count; +out: + mutex_unlock(&ptp->n_vclocks_mux); + return err; } static DEVICE_ATTR_RW(max_vclocks); From acb288e8047b7569fbc9af6fa6e9405315345103 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:55 +0800 Subject: [PATCH 055/426] ptp: add kernel API ptp_get_vclocks_index() Add kernel API ptp_get_vclocks_index() to get all ptp vclocks index on pclock. This is preparation for supporting ptp vclocks info query through ethtool. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 3 ++- drivers/ptp/ptp_private.h | 2 ++ drivers/ptp/ptp_vclock.c | 35 ++++++++++++++++++++++++++++++++ include/linux/ptp_clock_kernel.h | 14 +++++++++++++ 4 files changed, 53 insertions(+), 1 deletion(-) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 9205a9362a9d..f012fa581cf4 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -24,10 +24,11 @@ #define PTP_PPS_EVENT PPS_CAPTUREASSERT #define PTP_PPS_MODE (PTP_PPS_DEFAULTS | PPS_CANWAIT | PPS_TSFMT_TSPEC) +struct class *ptp_class; + /* private globals */ static dev_t ptp_devt; -static struct class *ptp_class; static DEFINE_IDA(ptp_clocks_map); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index f75fadd9b244..dba6be477067 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -96,6 +96,8 @@ static inline bool ptp_vclock_in_use(struct ptp_clock *ptp) return in_use; } +extern struct class *ptp_class; + /* * see ptp_chardev.c */ diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index fc9205cc504d..cefab29a0592 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -148,3 +148,38 @@ void ptp_vclock_unregister(struct ptp_vclock *vclock) ptp_clock_unregister(vclock->clock); kfree(vclock); } + +int ptp_get_vclocks_index(int pclock_index, int **vclock_index) +{ + char name[PTP_CLOCK_NAME_LEN] = ""; + struct ptp_clock *ptp; + struct device *dev; + int num = 0; + + if (pclock_index < 0) + return num; + + snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", pclock_index); + dev = class_find_device_by_name(ptp_class, name); + if (!dev) + return num; + + ptp = dev_get_drvdata(dev); + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) { + put_device(dev); + return num; + } + + *vclock_index = kzalloc(sizeof(int) * ptp->n_vclocks, GFP_KERNEL); + if (!(*vclock_index)) + goto out; + + memcpy(*vclock_index, ptp->vclock_index, sizeof(int) * ptp->n_vclocks); + num = ptp->n_vclocks; +out: + mutex_unlock(&ptp->n_vclocks_mux); + put_device(dev); + return num; +} +EXPORT_SYMBOL(ptp_get_vclocks_index); diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index b6fb771ee524..300a984fec87 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -306,6 +306,18 @@ int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay); */ void ptp_cancel_worker_sync(struct ptp_clock *ptp); +/** + * ptp_get_vclocks_index() - get all vclocks index on pclock, and + * caller is responsible to free memory + * of vclock_index + * + * @pclock_index: phc index of ptp pclock. + * @vclock_index: pointer to pointer of vclock index. + * + * return number of vclocks. + */ +int ptp_get_vclocks_index(int pclock_index, int **vclock_index); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -325,6 +337,8 @@ static inline int ptp_schedule_worker(struct ptp_clock *ptp, { return -EOPNOTSUPP; } static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) { } +static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) +{ return 0; } #endif From c156174a67070042d51d2c866146d3c934d5468c Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:56 +0800 Subject: [PATCH 056/426] ethtool: add a new command for getting PHC virtual clocks Add an interface for getting PHC (PTP Hardware Clock) virtual clocks, which are based on PHC physical clock providing hardware timestamp to network packets. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 22 +++++ include/linux/ethtool.h | 10 +++ include/uapi/linux/ethtool_netlink.h | 15 ++++ net/ethtool/Makefile | 2 +- net/ethtool/common.c | 13 +++ net/ethtool/netlink.c | 10 +++ net/ethtool/netlink.h | 2 + net/ethtool/phc_vclocks.c | 94 ++++++++++++++++++++ 8 files changed, 167 insertions(+), 1 deletion(-) create mode 100644 net/ethtool/phc_vclocks.c diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 6ea91e41593f..c86628e6a235 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -212,6 +212,7 @@ Userspace to kernel: ``ETHTOOL_MSG_FEC_SET`` set FEC settings ``ETHTOOL_MSG_MODULE_EEPROM_GET`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET`` get standard statistics + ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` get PHC virtual clocks info ===================================== ================================ Kernel to userspace: @@ -250,6 +251,7 @@ Kernel to userspace: ``ETHTOOL_MSG_FEC_NTF`` FEC settings ``ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET_REPLY`` standard statistics + ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY`` PHC virtual clocks info ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1477,6 +1479,25 @@ Low and high bounds are inclusive, for example: etherStatsPkts512to1023Octets 512 1023 ============================= ==== ==== +PHC_VCLOCKS_GET +=============== + +Query device PHC virtual clocks information. + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_PHC_VCLOCKS_HEADER`` nested request header + ==================================== ====== ========================== + +Kernel response contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_PHC_VCLOCKS_HEADER`` nested reply header + ``ETHTOOL_A_PHC_VCLOCKS_NUM`` u32 PHC virtual clocks number + ``ETHTOOL_A_PHC_VCLOCKS_INDEX`` s32 PHC index array + ==================================== ====== ========================== + Request translation =================== @@ -1575,4 +1596,5 @@ are netlink only. n/a ``ETHTOOL_MSG_CABLE_TEST_ACT`` n/a ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT`` n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET`` + n/a ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` =================================== ===================================== diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 29dbb603bc91..232daaec56e4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -757,6 +757,16 @@ void ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, enum ethtool_link_mode_bit_indices link_mode); +/** + * ethtool_get_phc_vclocks - Derive phc vclocks information, and caller + * is responsible to free memory of vclock_index + * @dev: pointer to net_device structure + * @vclock_index: pointer to pointer of vclock index + * + * Return number of phc vclocks + */ +int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index); + /** * ethtool_sprintf - Write formatted string to ethtool string data * @data: Pointer to start of string to update diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index c7135c9c37a5..b3b93710eff7 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -46,6 +46,7 @@ enum { ETHTOOL_MSG_FEC_SET, ETHTOOL_MSG_MODULE_EEPROM_GET, ETHTOOL_MSG_STATS_GET, + ETHTOOL_MSG_PHC_VCLOCKS_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -88,6 +89,7 @@ enum { ETHTOOL_MSG_FEC_NTF, ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY, ETHTOOL_MSG_STATS_GET_REPLY, + ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -440,6 +442,19 @@ enum { ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) }; +/* PHC VCLOCKS */ + +enum { + ETHTOOL_A_PHC_VCLOCKS_UNSPEC, + ETHTOOL_A_PHC_VCLOCKS_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_PHC_VCLOCKS_NUM, /* u32 */ + ETHTOOL_A_PHC_VCLOCKS_INDEX, /* array, s32 */ + + /* add new constants above here */ + __ETHTOOL_A_PHC_VCLOCKS_CNT, + ETHTOOL_A_PHC_VCLOCKS_MAX = (__ETHTOOL_A_PHC_VCLOCKS_CNT - 1) +}; + /* CABLE TEST */ enum { diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 723c9a8a8cdf..0a19470efbfb 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ - tunnels.o fec.o eeprom.o stats.o + tunnels.o fec.o eeprom.o stats.o phc_vclocks.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c index f9dcbad84788..798231b07676 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "common.h" @@ -554,6 +555,18 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) return 0; } +int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index) +{ + struct ethtool_ts_info info = { }; + int num = 0; + + if (!__ethtool_get_ts_info(dev, &info)) + num = ptp_get_vclocks_index(info.phc_index, vclock_index); + + return num; +} +EXPORT_SYMBOL(ethtool_get_phc_vclocks); + const struct ethtool_phy_ops *ethtool_phy_ops; void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops) diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index a7346346114f..73e0f5b626bf 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -248,6 +248,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops, [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, + [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -958,6 +959,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_stats_get_policy, .maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_phc_vclocks_get_policy, + .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 3e25a47fd482..3fc395c86702 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -347,6 +347,7 @@ extern const struct ethnl_request_ops ethnl_tsinfo_request_ops; extern const struct ethnl_request_ops ethnl_fec_request_ops; extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops; extern const struct ethnl_request_ops ethnl_stats_request_ops; +extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -382,6 +383,7 @@ extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1]; extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; +extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/phc_vclocks.c b/net/ethtool/phc_vclocks.c new file mode 100644 index 000000000000..637b2f5297d5 --- /dev/null +++ b/net/ethtool/phc_vclocks.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 NXP + */ +#include "netlink.h" +#include "common.h" + +struct phc_vclocks_req_info { + struct ethnl_req_info base; +}; + +struct phc_vclocks_reply_data { + struct ethnl_reply_data base; + int num; + int *index; +}; + +#define PHC_VCLOCKS_REPDATA(__reply_base) \ + container_of(__reply_base, struct phc_vclocks_reply_data, base) + +const struct nla_policy ethnl_phc_vclocks_get_policy[] = { + [ETHTOOL_A_PHC_VCLOCKS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + data->num = ethtool_get_phc_vclocks(dev, &data->index); + ethnl_ops_complete(dev); + + return ret; +} + +static int phc_vclocks_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct phc_vclocks_reply_data *data = + PHC_VCLOCKS_REPDATA(reply_base); + int len = 0; + + if (data->num > 0) { + len += nla_total_size(sizeof(u32)); + len += nla_total_size(sizeof(s32) * data->num); + } + + return len; +} + +static int phc_vclocks_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct phc_vclocks_reply_data *data = + PHC_VCLOCKS_REPDATA(reply_base); + + if (data->num <= 0) + return 0; + + if (nla_put_u32(skb, ETHTOOL_A_PHC_VCLOCKS_NUM, data->num) || + nla_put(skb, ETHTOOL_A_PHC_VCLOCKS_INDEX, + sizeof(s32) * data->num, data->index)) + return -EMSGSIZE; + + return 0; +} + +static void phc_vclocks_cleanup_data(struct ethnl_reply_data *reply_base) +{ + const struct phc_vclocks_reply_data *data = + PHC_VCLOCKS_REPDATA(reply_base); + + kfree(data->index); +} + +const struct ethnl_request_ops ethnl_phc_vclocks_request_ops = { + .request_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, + .reply_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, + .hdr_attr = ETHTOOL_A_PHC_VCLOCKS_HEADER, + .req_info_size = sizeof(struct phc_vclocks_req_info), + .reply_data_size = sizeof(struct phc_vclocks_reply_data), + + .prepare_data = phc_vclocks_prepare_data, + .reply_size = phc_vclocks_reply_size, + .fill_reply = phc_vclocks_fill_reply, + .cleanup_data = phc_vclocks_cleanup_data, +}; From 895487a3a10fb3a177e20dcde875515d46ccd4df Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:57 +0800 Subject: [PATCH 057/426] ptp: add kernel API ptp_convert_timestamp() Add kernel API ptp_convert_timestamp() to convert raw hardware timestamp to a specified ptp vclock time. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_vclock.c | 34 ++++++++++++++++++++++++++++++++ include/linux/ptp_clock_kernel.h | 13 ++++++++++++ 2 files changed, 47 insertions(+) diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index cefab29a0592..e0f87c57749a 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -183,3 +183,37 @@ out: return num; } EXPORT_SYMBOL(ptp_get_vclocks_index); + +void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, + int vclock_index) +{ + char name[PTP_CLOCK_NAME_LEN] = ""; + struct ptp_vclock *vclock; + struct ptp_clock *ptp; + unsigned long flags; + struct device *dev; + u64 ns; + + snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", vclock_index); + dev = class_find_device_by_name(ptp_class, name); + if (!dev) + return; + + ptp = dev_get_drvdata(dev); + if (!ptp->is_virtual_clock) { + put_device(dev); + return; + } + + vclock = info_to_vclock(ptp->info); + + ns = ktime_to_ns(hwtstamps->hwtstamp); + + spin_lock_irqsave(&vclock->lock, flags); + ns = timecounter_cyc2time(&vclock->tc, ns); + spin_unlock_irqrestore(&vclock->lock, flags); + + put_device(dev); + hwtstamps->hwtstamp = ns_to_ktime(ns); +} +EXPORT_SYMBOL(ptp_convert_timestamp); diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 300a984fec87..71fac9237725 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -12,6 +12,7 @@ #include #include #include +#include #define PTP_CLOCK_NAME_LEN 32 /** @@ -318,6 +319,15 @@ void ptp_cancel_worker_sync(struct ptp_clock *ptp); */ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); +/** + * ptp_convert_timestamp() - convert timestamp to a ptp vclock time + * + * @hwtstamps: skb_shared_hwtstamps structure pointer + * @vclock_index: phc index of ptp vclock. + */ +void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, + int vclock_index); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -339,6 +349,9 @@ static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) { } static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } +static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, + int vclock_index) +{ } #endif From 6c9a0a0f2333b1e3c29fef47a8b12131fce4905b Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:58 +0800 Subject: [PATCH 058/426] mptcp: setsockopt: convert to mptcp_setsockopt_sol_socket_timestamping() Split timestamping handling into a new function mptcp_setsockopt_sol_socket_timestamping(). This is preparation for extending SO_TIMESTAMPING for PHC binding, since optval will no longer be integer. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- net/mptcp/sockopt.c | 57 +++++++++++++++++++++++++++++++-------------- 1 file changed, 40 insertions(+), 17 deletions(-) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 092d1f635d27..ea38cbcd2ad4 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -157,19 +157,7 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); - switch (optname) { - case SO_TIMESTAMP_OLD: - case SO_TIMESTAMP_NEW: - case SO_TIMESTAMPNS_OLD: - case SO_TIMESTAMPNS_NEW: - sock_set_timestamp(sk, optname, !!val); - break; - case SO_TIMESTAMPING_NEW: - case SO_TIMESTAMPING_OLD: - sock_set_timestamping(sk, optname, val); - break; - } - + sock_set_timestamp(sk, optname, !!val); unlock_sock_fast(ssk, slow); } @@ -178,7 +166,8 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam } static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, - sockptr_t optval, unsigned int optlen) + sockptr_t optval, + unsigned int optlen) { int val, ret; @@ -205,14 +194,45 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: - case SO_TIMESTAMPING_OLD: - case SO_TIMESTAMPING_NEW: return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val); } return -ENOPROTOOPT; } +static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, + int optname, + sockptr_t optval, + unsigned int optlen) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + int val, ret; + + ret = mptcp_get_int_option(msk, optval, optlen, &val); + if (ret) + return ret; + + ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, + KERNEL_SOCKPTR(&val), sizeof(val)); + if (ret) + return ret; + + lock_sock(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow = lock_sock_fast(ssk); + + sock_set_timestamping(sk, optname, val); + unlock_sock_fast(ssk, slow); + } + + release_sock(sk); + + return 0; +} + static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval, unsigned int optlen) { @@ -299,9 +319,12 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: + return mptcp_setsockopt_sol_socket_int(msk, optname, optval, + optlen); case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: - return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen); + return mptcp_setsockopt_sol_socket_timestamping(msk, optname, + optval, optlen); case SO_LINGER: return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen); case SO_RCVLOWAT: From d463126e23f112629edb01594141ca437a92a108 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:59 +0800 Subject: [PATCH 059/426] net: sock: extend SO_TIMESTAMPING for PHC binding Since PTP virtual clock support is added, there can be several PTP virtual clocks based on one PTP physical clock for timestamping. This patch is to extend SO_TIMESTAMPING API to support PHC (PTP Hardware Clock) binding by adding a new flag SOF_TIMESTAMPING_BIND_PHC. When PTP virtual clocks are in use, user space can configure to bind one for timestamping, but PTP physical clock is not supported and not needed to bind. This patch is preparation for timestamp conversion from raw timestamp to a specific PTP virtual clock time in core net. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/net/sock.h | 8 +++- include/uapi/linux/net_tstamp.h | 17 ++++++++- net/core/sock.c | 65 +++++++++++++++++++++++++++++++-- net/ethtool/common.c | 1 + net/mptcp/sockopt.c | 23 +++++++++--- 5 files changed, 101 insertions(+), 13 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 8bdd80027ffb..f23cb259b0e2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -316,7 +316,9 @@ struct bpf_local_storage; * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only - * @sk_tsflags: SO_TIMESTAMPING socket options + * @sk_tsflags: SO_TIMESTAMPING flags + * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock + * for timestamping * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals @@ -493,6 +495,7 @@ struct sock { seqlock_t sk_stamp_seq; #endif u16 sk_tsflags; + int sk_bind_phc; u8 sk_shutdown; u32 sk_tskey; atomic_t sk_zckey; @@ -2755,7 +2758,8 @@ void sock_def_readable(struct sock *sk); int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); void sock_set_timestamp(struct sock *sk, int optname, bool valbool); -int sock_set_timestamping(struct sock *sk, int optname, int val); +int sock_set_timestamping(struct sock *sk, int optname, + struct so_timestamping timestamping); void sock_enable_timestamps(struct sock *sk); void sock_no_linger(struct sock *sk); diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 7ed0b3d1c00a..fcc61c73a666 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -13,7 +13,7 @@ #include #include /* for SO_TIMESTAMPING */ -/* SO_TIMESTAMPING gets an integer bit field comprised of these values */ +/* SO_TIMESTAMPING flags */ enum { SOF_TIMESTAMPING_TX_HARDWARE = (1<<0), SOF_TIMESTAMPING_TX_SOFTWARE = (1<<1), @@ -30,8 +30,9 @@ enum { SOF_TIMESTAMPING_OPT_STATS = (1<<12), SOF_TIMESTAMPING_OPT_PKTINFO = (1<<13), SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14), + SOF_TIMESTAMPING_BIND_PHC = (1 << 15), - SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_TX_SWHW, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_BIND_PHC, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; @@ -46,6 +47,18 @@ enum { SOF_TIMESTAMPING_TX_SCHED | \ SOF_TIMESTAMPING_TX_ACK) +/** + * struct so_timestamping - SO_TIMESTAMPING parameter + * + * @flags: SO_TIMESTAMPING flags + * @bind_phc: Index of PTP virtual clock bound to sock. This is available + * if flag SOF_TIMESTAMPING_BIND_PHC is set. + */ +struct so_timestamping { + int flags; + int bind_phc; +}; + /** * struct hwtstamp_config - %SIOCGHWTSTAMP and %SIOCSHWTSTAMP parameter * diff --git a/net/core/sock.c b/net/core/sock.c index dd9599656c40..cad107112204 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,6 +139,8 @@ #include #include +#include + static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); @@ -810,8 +812,47 @@ void sock_set_timestamp(struct sock *sk, int optname, bool valbool) } } -int sock_set_timestamping(struct sock *sk, int optname, int val) +static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) { + struct net *net = sock_net(sk); + struct net_device *dev = NULL; + bool match = false; + int *vclock_index; + int i, num; + + if (sk->sk_bound_dev_if) + dev = dev_get_by_index(net, sk->sk_bound_dev_if); + + if (!dev) { + pr_err("%s: sock not bind to device\n", __func__); + return -EOPNOTSUPP; + } + + num = ethtool_get_phc_vclocks(dev, &vclock_index); + for (i = 0; i < num; i++) { + if (*(vclock_index + i) == phc_index) { + match = true; + break; + } + } + + if (num > 0) + kfree(vclock_index); + + if (!match) + return -EINVAL; + + sk->sk_bind_phc = phc_index; + + return 0; +} + +int sock_set_timestamping(struct sock *sk, int optname, + struct so_timestamping timestamping) +{ + int val = timestamping.flags; + int ret; + if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; @@ -832,6 +873,12 @@ int sock_set_timestamping(struct sock *sk, int optname, int val) !(val & SOF_TIMESTAMPING_OPT_TSONLY)) return -EINVAL; + if (val & SOF_TIMESTAMPING_BIND_PHC) { + ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc); + if (ret) + return ret; + } + sk->sk_tsflags = val; sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); @@ -907,6 +954,7 @@ EXPORT_SYMBOL(sock_set_mark); int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct so_timestamping timestamping; struct sock_txtime sk_txtime; struct sock *sk = sock->sk; int val; @@ -1073,7 +1121,15 @@ set_sndbuf: case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: - ret = sock_set_timestamping(sk, optname, val); + if (optlen == sizeof(timestamping)) { + if (copy_from_sockptr(×tamping, optval, + sizeof(timestamping))) + return -EFAULT; + } else { + memset(×tamping, 0, sizeof(timestamping)); + timestamping.flags = val; + } + ret = sock_set_timestamping(sk, optname, timestamping); break; case SO_RCVLOWAT: @@ -1348,6 +1404,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; + struct so_timestamping timestamping; } v; int lv = sizeof(int); @@ -1451,7 +1508,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_TIMESTAMPING_OLD: - v.val = sk->sk_tsflags; + lv = sizeof(v.timestamping); + v.timestamping.flags = sk->sk_tsflags; + v.timestamping.bind_phc = sk->sk_bind_phc; break; case SO_RCVTIMEO_OLD: diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 798231b07676..c63e0739dc6a 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -398,6 +398,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = { [const_ilog2(SOF_TIMESTAMPING_OPT_STATS)] = "option-stats", [const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo", [const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw", + [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc", }; static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index ea38cbcd2ad4..8c03afac5ca0 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -207,14 +207,25 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - int val, ret; + struct so_timestamping timestamping; + int ret; - ret = mptcp_get_int_option(msk, optval, optlen, &val); - if (ret) - return ret; + if (optlen == sizeof(timestamping)) { + if (copy_from_sockptr(×tamping, optval, + sizeof(timestamping))) + return -EFAULT; + } else if (optlen == sizeof(int)) { + memset(×tamping, 0, sizeof(timestamping)); + + if (copy_from_sockptr(×tamping.flags, optval, sizeof(int))) + return -EFAULT; + } else { + return -EINVAL; + } ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, - KERNEL_SOCKPTR(&val), sizeof(val)); + KERNEL_SOCKPTR(×tamping), + sizeof(timestamping)); if (ret) return ret; @@ -224,7 +235,7 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk, struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); - sock_set_timestamping(sk, optname, val); + sock_set_timestamping(sk, optname, timestamping); unlock_sock_fast(ssk, slow); } From d7c08826558811e1bf88de3750a7051f27d0e25c Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:12:00 +0800 Subject: [PATCH 060/426] net: socket: support hardware timestamp conversion to PHC bound This patch is to support hardware timestamp conversion to PHC bound. This applies to both RX and TX since their skb handling (for TX, it's skb clone in error queue) all goes through __sock_recv_timestamp. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- net/socket.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/net/socket.c b/net/socket.c index bd9233da2497..0b2dad3bdf7f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -104,6 +104,7 @@ #include #include #include +#include #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; @@ -873,12 +874,18 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && - !skb_is_swtx_tstamp(skb, false_tstamp) && - ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { - empty = 0; - if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && - !skb_is_err_queue(skb)) - put_ts_pktinfo(msg, skb); + !skb_is_swtx_tstamp(skb, false_tstamp)) { + if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC) + ptp_convert_timestamp(shhwtstamps, sk->sk_bind_phc); + + if (ktime_to_timespec64_cond(shhwtstamps->hwtstamp, + tss.ts + 2)) { + empty = 0; + + if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && + !skb_is_err_queue(skb)) + put_ts_pktinfo(msg, skb); + } } if (!empty) { if (sock_flag(sk, SOCK_TSTAMP_NEW)) From 2214d7032479e50ff1fa7276e6efe1df08173fbf Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:12:01 +0800 Subject: [PATCH 061/426] selftests/net: timestamping: support binding PHC Support binding PHC of PTP vclock for timestamping. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- tools/testing/selftests/net/timestamping.c | 55 ++++++++++++++-------- 1 file changed, 35 insertions(+), 20 deletions(-) diff --git a/tools/testing/selftests/net/timestamping.c b/tools/testing/selftests/net/timestamping.c index 21091be70688..aee631c5284e 100644 --- a/tools/testing/selftests/net/timestamping.c +++ b/tools/testing/selftests/net/timestamping.c @@ -47,7 +47,7 @@ static void usage(const char *error) { if (error) printf("invalid option: %s\n", error); - printf("timestamping interface option*\n\n" + printf("timestamping [bind_phc_index] [option]*\n\n" "Options:\n" " IP_MULTICAST_LOOP - looping outgoing multicasts\n" " SO_TIMESTAMP - normal software time stamping, ms resolution\n" @@ -58,6 +58,7 @@ static void usage(const char *error) " SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n" " SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n" " SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n" + " SOF_TIMESTAMPING_BIND_PHC - request to bind a PHC of PTP vclock\n" " SIOCGSTAMP - check last socket time stamp\n" " SIOCGSTAMPNS - more accurate socket time stamp\n" " PTPV2 - use PTPv2 messages\n"); @@ -311,7 +312,6 @@ static void recvpacket(int sock, int recvmsg_flags, int main(int argc, char **argv) { - int so_timestamping_flags = 0; int so_timestamp = 0; int so_timestampns = 0; int siocgstamp = 0; @@ -325,6 +325,8 @@ int main(int argc, char **argv) struct ifreq device; struct ifreq hwtstamp; struct hwtstamp_config hwconfig, hwconfig_requested; + struct so_timestamping so_timestamping_get = { 0, -1 }; + struct so_timestamping so_timestamping = { 0, -1 }; struct sockaddr_in addr; struct ip_mreq imr; struct in_addr iaddr; @@ -342,7 +344,12 @@ int main(int argc, char **argv) exit(1); } - for (i = 2; i < argc; i++) { + if (argc >= 3 && sscanf(argv[2], "%d", &so_timestamping.bind_phc) == 1) + val = 3; + else + val = 2; + + for (i = val; i < argc; i++) { if (!strcasecmp(argv[i], "SO_TIMESTAMP")) so_timestamp = 1; else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS")) @@ -356,17 +363,19 @@ int main(int argc, char **argv) else if (!strcasecmp(argv[i], "PTPV2")) ptpv2 = 1; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_TX_HARDWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_TX_SOFTWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_RX_HARDWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_RX_SOFTWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_SOFTWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE; + so_timestamping.flags |= SOF_TIMESTAMPING_RAW_HARDWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_BIND_PHC")) + so_timestamping.flags |= SOF_TIMESTAMPING_BIND_PHC; else usage(argv[i]); } @@ -385,10 +394,10 @@ int main(int argc, char **argv) hwtstamp.ifr_data = (void *)&hwconfig; memset(&hwconfig, 0, sizeof(hwconfig)); hwconfig.tx_type = - (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ? + (so_timestamping.flags & SOF_TIMESTAMPING_TX_HARDWARE) ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; hwconfig.rx_filter = - (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ? + (so_timestamping.flags & SOF_TIMESTAMPING_RX_HARDWARE) ? ptpv2 ? HWTSTAMP_FILTER_PTP_V2_L4_SYNC : HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE; hwconfig_requested = hwconfig; @@ -413,6 +422,9 @@ int main(int argc, char **argv) sizeof(struct sockaddr_in)) < 0) bail("bind"); + if (setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, interface, if_len)) + bail("bind device"); + /* set multicast group for outgoing packets */ inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */ addr.sin_addr = iaddr; @@ -444,10 +456,9 @@ int main(int argc, char **argv) &enabled, sizeof(enabled)) < 0) bail("setsockopt SO_TIMESTAMPNS"); - if (so_timestamping_flags && - setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, - &so_timestamping_flags, - sizeof(so_timestamping_flags)) < 0) + if (so_timestamping.flags && + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping, + sizeof(so_timestamping)) < 0) bail("setsockopt SO_TIMESTAMPING"); /* request IP_PKTINFO for debugging purposes */ @@ -468,14 +479,18 @@ int main(int argc, char **argv) else printf("SO_TIMESTAMPNS %d\n", val); - if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) { + len = sizeof(so_timestamping_get); + if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping_get, + &len) < 0) { printf("%s: %s\n", "getsockopt SO_TIMESTAMPING", strerror(errno)); } else { - printf("SO_TIMESTAMPING %d\n", val); - if (val != so_timestamping_flags) - printf(" not the expected value %d\n", - so_timestamping_flags); + printf("SO_TIMESTAMPING flags %d, bind phc %d\n", + so_timestamping_get.flags, so_timestamping_get.bind_phc); + if (so_timestamping_get.flags != so_timestamping.flags || + so_timestamping_get.bind_phc != so_timestamping.bind_phc) + printf(" not expected, flags %d, bind phc %d\n", + so_timestamping.flags, so_timestamping.bind_phc); } /* send packets forever every five seconds */ From 5ce15f2783332dce99ef04e2bdc927f0fa84105d Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:12:02 +0800 Subject: [PATCH 062/426] MAINTAINERS: add entry for PTP virtual clock driver Add entry for PTP virtual clock driver. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 88449b7a4c95..ca7287ee775b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14890,6 +14890,13 @@ F: drivers/net/phy/dp83640* F: drivers/ptp/* F: include/linux/ptp_cl* +PTP VIRTUAL CLOCK SUPPORT +M: Yangbo Lu +L: netdev@vger.kernel.org +S: Maintained +F: drivers/ptp/ptp_vclock.c +F: net/ethtool/phc_vclocks.c + PTRACE SUPPORT M: Oleg Nesterov S: Maintained From 4f408e1fa6e10b6da72691233369172bac7d9e9b Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Wed, 30 Jun 2021 14:36:17 -0400 Subject: [PATCH 063/426] ibmvnic: retry reset if there are no other resets Normally, if a reset fails due to failover or other communication error there is another reset (eg: FAILOVER) in the queue and we would process that reset. But if we are unable to communicate with PHYP or VIOS after H_FREE_CRQ, there would be no other resets in the queue and the adapter would be in an undefined state even though it was in the OPEN state earlier. While starting the reset we set the carrier to off state so we won't even get the timeout resets. If the last queued reset fails, retry it as a hard reset (after the usual 60 second settling time). Signed-off-by: Sukadev Bhattiprolu Reviewed-by: Dany Madden Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 374a75d4faea..ed77191d19f4 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2420,9 +2420,10 @@ out: static void __ibmvnic_reset(struct work_struct *work) { - struct ibmvnic_rwi *rwi; struct ibmvnic_adapter *adapter; bool saved_state = false; + struct ibmvnic_rwi *tmprwi; + struct ibmvnic_rwi *rwi; unsigned long flags; u32 reset_state; int rc = 0; @@ -2489,7 +2490,7 @@ static void __ibmvnic_reset(struct work_struct *work) } else { rc = do_reset(adapter, rwi, reset_state); } - kfree(rwi); + tmprwi = rwi; adapter->last_reset_time = jiffies; if (rc) @@ -2497,8 +2498,23 @@ static void __ibmvnic_reset(struct work_struct *work) rwi = get_next_rwi(adapter); + /* + * If there is another reset queued, free the previous rwi + * and process the new reset even if previous reset failed + * (the previous reset could have failed because of a fail + * over for instance, so process the fail over). + * + * If there are no resets queued and the previous reset failed, + * the adapter would be in an undefined state. So retry the + * previous reset as a hard reset. + */ + if (rwi) + kfree(tmprwi); + else if (rc) + rwi = tmprwi; + if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER || - rwi->reset_reason == VNIC_RESET_MOBILITY)) + rwi->reset_reason == VNIC_RESET_MOBILITY || rc)) adapter->force_reset_recovery = true; } From 09ef17863f37235fe4e65a7d991e487b9ff6e553 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 30 Jun 2021 20:18:20 -0400 Subject: [PATCH 064/426] Documentation: add more details in tipc.rst kernel-doc for TIPC is too simple, we need to add more information for it. This patch is to extend the abstract, and add the Features and Links items. Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- Documentation/networking/tipc.rst | 121 +++++++++++++++++++++++++++++- 1 file changed, 118 insertions(+), 3 deletions(-) diff --git a/Documentation/networking/tipc.rst b/Documentation/networking/tipc.rst index 76775f24cdc8..ab63d298cca2 100644 --- a/Documentation/networking/tipc.rst +++ b/Documentation/networking/tipc.rst @@ -4,10 +4,125 @@ Linux Kernel TIPC ================= -TIPC (Transparent Inter Process Communication) is a protocol that is -specially designed for intra-cluster communication. +Introduction +============ -For more information about TIPC, see http://tipc.sourceforge.net. +TIPC (Transparent Inter Process Communication) is a protocol that is specially +designed for intra-cluster communication. It can be configured to transmit +messages either on UDP or directly across Ethernet. Message delivery is +sequence guaranteed, loss free and flow controlled. Latency times are shorter +than with any other known protocol, while maximal throughput is comparable to +that of TCP. + +TIPC Features +------------- + +- Cluster wide IPC service + + Have you ever wished you had the convenience of Unix Domain Sockets even when + transmitting data between cluster nodes? Where you yourself determine the + addresses you want to bind to and use? Where you don't have to perform DNS + lookups and worry about IP addresses? Where you don't have to start timers + to monitor the continuous existence of peer sockets? And yet without the + downsides of that socket type, such as the risk of lingering inodes? + + Welcome to the Transparent Inter Process Communication service, TIPC in short, + which gives you all of this, and a lot more. + +- Service Addressing + + A fundamental concept in TIPC is that of Service Addressing which makes it + possible for a programmer to chose his own address, bind it to a server + socket and let client programs use only that address for sending messages. + +- Service Tracking + + A client wanting to wait for the availability of a server, uses the Service + Tracking mechanism to subscribe for binding and unbinding/close events for + sockets with the associated service address. + + The service tracking mechanism can also be used for Cluster Topology Tracking, + i.e., subscribing for availability/non-availability of cluster nodes. + + Likewise, the service tracking mechanism can be used for Cluster Connectivity + Tracking, i.e., subscribing for up/down events for individual links between + cluster nodes. + +- Transmission Modes + + Using a service address, a client can send datagram messages to a server socket. + + Using the same address type, it can establish a connection towards an accepting + server socket. + + It can also use a service address to create and join a Communication Group, + which is the TIPC manifestation of a brokerless message bus. + + Multicast with very good performance and scalability is available both in + datagram mode and in communication group mode. + +- Inter Node Links + + Communication between any two nodes in a cluster is maintained by one or two + Inter Node Links, which both guarantee data traffic integrity and monitor + the peer node's availability. + +- Cluster Scalability + + By applying the Overlapping Ring Monitoring algorithm on the inter node links + it is possible to scale TIPC clusters up to 1000 nodes with a maintained + neighbor failure discovery time of 1-2 seconds. For smaller clusters this + time can be made much shorter. + +- Neighbor Discovery + + Neighbor Node Discovery in the cluster is done by Ethernet broadcast or UDP + multicast, when any of those services are available. If not, configured peer + IP addresses can be used. + +- Configuration + + When running TIPC in single node mode no configuration whatsoever is needed. + When running in cluster mode TIPC must as a minimum be given a node address + (before Linux 4.17) and told which interface to attach to. The "tipc" + configuration tool makes is possible to add and maintain many more + configuration parameters. + +- Performance + + TIPC message transfer latency times are better than in any other known protocol. + Maximal byte throughput for inter-node connections is still somewhat lower than + for TCP, while they are superior for intra-node and inter-container throughput + on the same host. + +- Language Support + + The TIPC user API has support for C, Python, Perl, Ruby, D and Go. + +More Information +---------------- + +- How to set up TIPC: + + http://tipc.io/getting_started.html + +- How to program with TIPC: + + http://tipc.io/programming.html + +- How to contribute to TIPC: + +- http://tipc.io/contacts.html + +- More details about TIPC specification: + + http://tipc.io/protocol.html + + +Implementation +============== + +TIPC is implemented as a kernel module in net/tipc/ directory. TIPC Base Types --------------- From ca75bcf0a83b6cc7f53a593d98ec7121c4839b43 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 1 Jul 2021 10:15:09 +0200 Subject: [PATCH 065/426] net: remove the caif_hsi driver The caif_hsi driver relies on a cfhsi_get_ops symbol using symbol_get, but this symbol is not provided anywhere in the kernel tree. Remove this driver given that it is dead code. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- drivers/net/caif/Kconfig | 9 - drivers/net/caif/Makefile | 3 - drivers/net/caif/caif_hsi.c | 1454 ----------------------------------- include/net/caif/caif_hsi.h | 200 ----- 4 files changed, 1666 deletions(-) delete mode 100644 drivers/net/caif/caif_hsi.c delete mode 100644 include/net/caif/caif_hsi.h diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig index a77124bc1f4b..709660cb38f8 100644 --- a/drivers/net/caif/Kconfig +++ b/drivers/net/caif/Kconfig @@ -20,15 +20,6 @@ config CAIF_TTY identified as N_CAIF. When this ldisc is opened from user space it will redirect the TTY's traffic into the CAIF stack. -config CAIF_HSI - tristate "CAIF HSI transport driver" - depends on CAIF - default n - help - The CAIF low level driver for CAIF over HSI. - Be aware that if you enable this then you also need to - enable a low-level HSI driver. - config CAIF_VIRTIO tristate "CAIF virtio transport driver" depends on CAIF && HAS_DMA diff --git a/drivers/net/caif/Makefile b/drivers/net/caif/Makefile index b1918c8c126c..97f664f8016c 100644 --- a/drivers/net/caif/Makefile +++ b/drivers/net/caif/Makefile @@ -4,8 +4,5 @@ ccflags-$(CONFIG_CAIF_DEBUG) := -DDEBUG # Serial interface obj-$(CONFIG_CAIF_TTY) += caif_serial.o -# HSI interface -obj-$(CONFIG_CAIF_HSI) += caif_hsi.o - # Virtio interface obj-$(CONFIG_CAIF_VIRTIO) += caif_virtio.o diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c deleted file mode 100644 index 3d63b15bbaa1..000000000000 --- a/drivers/net/caif/caif_hsi.c +++ /dev/null @@ -1,1454 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) ST-Ericsson AB 2010 - * Author: Daniel Martensson - * Dmitry.Tarnyagin / dmitry.tarnyagin@lockless.no - */ - -#define pr_fmt(fmt) KBUILD_MODNAME fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Daniel Martensson"); -MODULE_DESCRIPTION("CAIF HSI driver"); - -/* Returns the number of padding bytes for alignment. */ -#define PAD_POW2(x, pow) ((((x)&((pow)-1)) == 0) ? 0 :\ - (((pow)-((x)&((pow)-1))))) - -static const struct cfhsi_config hsi_default_config = { - - /* Inactivity timeout on HSI, ms */ - .inactivity_timeout = HZ, - - /* Aggregation timeout (ms) of zero means no aggregation is done*/ - .aggregation_timeout = 1, - - /* - * HSI link layer flow-control thresholds. - * Threshold values for the HSI packet queue. Flow-control will be - * asserted when the number of packets exceeds q_high_mark. It will - * not be de-asserted before the number of packets drops below - * q_low_mark. - * Warning: A high threshold value might increase throughput but it - * will at the same time prevent channel prioritization and increase - * the risk of flooding the modem. The high threshold should be above - * the low. - */ - .q_high_mark = 100, - .q_low_mark = 50, - - /* - * HSI padding options. - * Warning: must be a base of 2 (& operation used) and can not be zero ! - */ - .head_align = 4, - .tail_align = 4, -}; - -#define ON 1 -#define OFF 0 - -static LIST_HEAD(cfhsi_list); - -static void cfhsi_inactivity_tout(struct timer_list *t) -{ - struct cfhsi *cfhsi = from_timer(cfhsi, t, inactivity_timer); - - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - /* Schedule power down work queue. */ - if (!test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - queue_work(cfhsi->wq, &cfhsi->wake_down_work); -} - -static void cfhsi_update_aggregation_stats(struct cfhsi *cfhsi, - const struct sk_buff *skb, - int direction) -{ - struct caif_payload_info *info; - int hpad, tpad, len; - - info = (struct caif_payload_info *)&skb->cb; - hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align); - tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align); - len = skb->len + hpad + tpad; - - if (direction > 0) - cfhsi->aggregation_len += len; - else if (direction < 0) - cfhsi->aggregation_len -= len; -} - -static bool cfhsi_can_send_aggregate(struct cfhsi *cfhsi) -{ - int i; - - if (cfhsi->cfg.aggregation_timeout == 0) - return true; - - for (i = 0; i < CFHSI_PRIO_BEBK; ++i) { - if (cfhsi->qhead[i].qlen) - return true; - } - - /* TODO: Use aggregation_len instead */ - if (cfhsi->qhead[CFHSI_PRIO_BEBK].qlen >= CFHSI_MAX_PKTS) - return true; - - return false; -} - -static struct sk_buff *cfhsi_dequeue(struct cfhsi *cfhsi) -{ - struct sk_buff *skb; - int i; - - for (i = 0; i < CFHSI_PRIO_LAST; ++i) { - skb = skb_dequeue(&cfhsi->qhead[i]); - if (skb) - break; - } - - return skb; -} - -static int cfhsi_tx_queue_len(struct cfhsi *cfhsi) -{ - int i, len = 0; - for (i = 0; i < CFHSI_PRIO_LAST; ++i) - len += skb_queue_len(&cfhsi->qhead[i]); - return len; -} - -static void cfhsi_abort_tx(struct cfhsi *cfhsi) -{ - struct sk_buff *skb; - - for (;;) { - spin_lock_bh(&cfhsi->lock); - skb = cfhsi_dequeue(cfhsi); - if (!skb) - break; - - cfhsi->ndev->stats.tx_errors++; - cfhsi->ndev->stats.tx_dropped++; - cfhsi_update_aggregation_stats(cfhsi, skb, -1); - spin_unlock_bh(&cfhsi->lock); - kfree_skb(skb); - } - cfhsi->tx_state = CFHSI_TX_STATE_IDLE; - if (!test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - mod_timer(&cfhsi->inactivity_timer, - jiffies + cfhsi->cfg.inactivity_timeout); - spin_unlock_bh(&cfhsi->lock); -} - -static int cfhsi_flush_fifo(struct cfhsi *cfhsi) -{ - char buffer[32]; /* Any reasonable value */ - size_t fifo_occupancy; - int ret; - - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - do { - ret = cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops, - &fifo_occupancy); - if (ret) { - netdev_warn(cfhsi->ndev, - "%s: can't get FIFO occupancy: %d.\n", - __func__, ret); - break; - } else if (!fifo_occupancy) - /* No more data, exitting normally */ - break; - - fifo_occupancy = min(sizeof(buffer), fifo_occupancy); - set_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits); - ret = cfhsi->ops->cfhsi_rx(buffer, fifo_occupancy, - cfhsi->ops); - if (ret) { - clear_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits); - netdev_warn(cfhsi->ndev, - "%s: can't read data: %d.\n", - __func__, ret); - break; - } - - ret = 5 * HZ; - ret = wait_event_interruptible_timeout(cfhsi->flush_fifo_wait, - !test_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits), ret); - - if (ret < 0) { - netdev_warn(cfhsi->ndev, - "%s: can't wait for flush complete: %d.\n", - __func__, ret); - break; - } else if (!ret) { - ret = -ETIMEDOUT; - netdev_warn(cfhsi->ndev, - "%s: timeout waiting for flush complete.\n", - __func__); - break; - } - } while (1); - - return ret; -} - -static int cfhsi_tx_frm(struct cfhsi_desc *desc, struct cfhsi *cfhsi) -{ - int nfrms = 0; - int pld_len = 0; - struct sk_buff *skb; - u8 *pfrm = desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ; - - skb = cfhsi_dequeue(cfhsi); - if (!skb) - return 0; - - /* Clear offset. */ - desc->offset = 0; - - /* Check if we can embed a CAIF frame. */ - if (skb->len < CFHSI_MAX_EMB_FRM_SZ) { - struct caif_payload_info *info; - int hpad; - int tpad; - - /* Calculate needed head alignment and tail alignment. */ - info = (struct caif_payload_info *)&skb->cb; - - hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align); - tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align); - - /* Check if frame still fits with added alignment. */ - if ((skb->len + hpad + tpad) <= CFHSI_MAX_EMB_FRM_SZ) { - u8 *pemb = desc->emb_frm; - desc->offset = CFHSI_DESC_SHORT_SZ; - *pemb = (u8)(hpad - 1); - pemb += hpad; - - /* Update network statistics. */ - spin_lock_bh(&cfhsi->lock); - cfhsi->ndev->stats.tx_packets++; - cfhsi->ndev->stats.tx_bytes += skb->len; - cfhsi_update_aggregation_stats(cfhsi, skb, -1); - spin_unlock_bh(&cfhsi->lock); - - /* Copy in embedded CAIF frame. */ - skb_copy_bits(skb, 0, pemb, skb->len); - - /* Consume the SKB */ - consume_skb(skb); - skb = NULL; - } - } - - /* Create payload CAIF frames. */ - while (nfrms < CFHSI_MAX_PKTS) { - struct caif_payload_info *info; - int hpad; - int tpad; - - if (!skb) - skb = cfhsi_dequeue(cfhsi); - - if (!skb) - break; - - /* Calculate needed head alignment and tail alignment. */ - info = (struct caif_payload_info *)&skb->cb; - - hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align); - tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align); - - /* Fill in CAIF frame length in descriptor. */ - desc->cffrm_len[nfrms] = hpad + skb->len + tpad; - - /* Fill head padding information. */ - *pfrm = (u8)(hpad - 1); - pfrm += hpad; - - /* Update network statistics. */ - spin_lock_bh(&cfhsi->lock); - cfhsi->ndev->stats.tx_packets++; - cfhsi->ndev->stats.tx_bytes += skb->len; - cfhsi_update_aggregation_stats(cfhsi, skb, -1); - spin_unlock_bh(&cfhsi->lock); - - /* Copy in CAIF frame. */ - skb_copy_bits(skb, 0, pfrm, skb->len); - - /* Update payload length. */ - pld_len += desc->cffrm_len[nfrms]; - - /* Update frame pointer. */ - pfrm += skb->len + tpad; - - /* Consume the SKB */ - consume_skb(skb); - skb = NULL; - - /* Update number of frames. */ - nfrms++; - } - - /* Unused length fields should be zero-filled (according to SPEC). */ - while (nfrms < CFHSI_MAX_PKTS) { - desc->cffrm_len[nfrms] = 0x0000; - nfrms++; - } - - /* Check if we can piggy-back another descriptor. */ - if (cfhsi_can_send_aggregate(cfhsi)) - desc->header |= CFHSI_PIGGY_DESC; - else - desc->header &= ~CFHSI_PIGGY_DESC; - - return CFHSI_DESC_SZ + pld_len; -} - -static void cfhsi_start_tx(struct cfhsi *cfhsi) -{ - struct cfhsi_desc *desc = (struct cfhsi_desc *)cfhsi->tx_buf; - int len, res; - - netdev_dbg(cfhsi->ndev, "%s.\n", __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - do { - /* Create HSI frame. */ - len = cfhsi_tx_frm(desc, cfhsi); - if (!len) { - spin_lock_bh(&cfhsi->lock); - if (unlikely(cfhsi_tx_queue_len(cfhsi))) { - spin_unlock_bh(&cfhsi->lock); - res = -EAGAIN; - continue; - } - cfhsi->tx_state = CFHSI_TX_STATE_IDLE; - /* Start inactivity timer. */ - mod_timer(&cfhsi->inactivity_timer, - jiffies + cfhsi->cfg.inactivity_timeout); - spin_unlock_bh(&cfhsi->lock); - break; - } - - /* Set up new transfer. */ - res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops); - if (WARN_ON(res < 0)) - netdev_err(cfhsi->ndev, "%s: TX error %d.\n", - __func__, res); - } while (res < 0); -} - -static void cfhsi_tx_done(struct cfhsi *cfhsi) -{ - netdev_dbg(cfhsi->ndev, "%s.\n", __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - /* - * Send flow on if flow off has been previously signalled - * and number of packets is below low water mark. - */ - spin_lock_bh(&cfhsi->lock); - if (cfhsi->flow_off_sent && - cfhsi_tx_queue_len(cfhsi) <= cfhsi->cfg.q_low_mark && - cfhsi->cfdev.flowctrl) { - - cfhsi->flow_off_sent = 0; - cfhsi->cfdev.flowctrl(cfhsi->ndev, ON); - } - - if (cfhsi_can_send_aggregate(cfhsi)) { - spin_unlock_bh(&cfhsi->lock); - cfhsi_start_tx(cfhsi); - } else { - mod_timer(&cfhsi->aggregation_timer, - jiffies + cfhsi->cfg.aggregation_timeout); - spin_unlock_bh(&cfhsi->lock); - } - - return; -} - -static void cfhsi_tx_done_cb(struct cfhsi_cb_ops *cb_ops) -{ - struct cfhsi *cfhsi; - - cfhsi = container_of(cb_ops, struct cfhsi, cb_ops); - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - cfhsi_tx_done(cfhsi); -} - -static int cfhsi_rx_desc(struct cfhsi_desc *desc, struct cfhsi *cfhsi) -{ - int xfer_sz = 0; - int nfrms = 0; - u16 *plen = NULL; - u8 *pfrm = NULL; - - if ((desc->header & ~CFHSI_PIGGY_DESC) || - (desc->offset > CFHSI_MAX_EMB_FRM_SZ)) { - netdev_err(cfhsi->ndev, "%s: Invalid descriptor.\n", - __func__); - return -EPROTO; - } - - /* Check for embedded CAIF frame. */ - if (desc->offset) { - struct sk_buff *skb; - int len = 0; - pfrm = ((u8 *)desc) + desc->offset; - - /* Remove offset padding. */ - pfrm += *pfrm + 1; - - /* Read length of CAIF frame (little endian). */ - len = *pfrm; - len |= ((*(pfrm+1)) << 8) & 0xFF00; - len += 2; /* Add FCS fields. */ - - /* Sanity check length of CAIF frame. */ - if (unlikely(len > CFHSI_MAX_CAIF_FRAME_SZ)) { - netdev_err(cfhsi->ndev, "%s: Invalid length.\n", - __func__); - return -EPROTO; - } - - /* Allocate SKB (OK even in IRQ context). */ - skb = alloc_skb(len + 1, GFP_ATOMIC); - if (!skb) { - netdev_err(cfhsi->ndev, "%s: Out of memory !\n", - __func__); - return -ENOMEM; - } - caif_assert(skb != NULL); - - skb_put_data(skb, pfrm, len); - - skb->protocol = htons(ETH_P_CAIF); - skb_reset_mac_header(skb); - skb->dev = cfhsi->ndev; - - netif_rx_any_context(skb); - - /* Update network statistics. */ - cfhsi->ndev->stats.rx_packets++; - cfhsi->ndev->stats.rx_bytes += len; - } - - /* Calculate transfer length. */ - plen = desc->cffrm_len; - while (nfrms < CFHSI_MAX_PKTS && *plen) { - xfer_sz += *plen; - plen++; - nfrms++; - } - - /* Check for piggy-backed descriptor. */ - if (desc->header & CFHSI_PIGGY_DESC) - xfer_sz += CFHSI_DESC_SZ; - - if ((xfer_sz % 4) || (xfer_sz > (CFHSI_BUF_SZ_RX - CFHSI_DESC_SZ))) { - netdev_err(cfhsi->ndev, - "%s: Invalid payload len: %d, ignored.\n", - __func__, xfer_sz); - return -EPROTO; - } - return xfer_sz; -} - -static int cfhsi_rx_desc_len(struct cfhsi_desc *desc) -{ - int xfer_sz = 0; - int nfrms = 0; - u16 *plen; - - if ((desc->header & ~CFHSI_PIGGY_DESC) || - (desc->offset > CFHSI_MAX_EMB_FRM_SZ)) { - - pr_err("Invalid descriptor. %x %x\n", desc->header, - desc->offset); - return -EPROTO; - } - - /* Calculate transfer length. */ - plen = desc->cffrm_len; - while (nfrms < CFHSI_MAX_PKTS && *plen) { - xfer_sz += *plen; - plen++; - nfrms++; - } - - if (xfer_sz % 4) { - pr_err("Invalid payload len: %d, ignored.\n", xfer_sz); - return -EPROTO; - } - return xfer_sz; -} - -static int cfhsi_rx_pld(struct cfhsi_desc *desc, struct cfhsi *cfhsi) -{ - int rx_sz = 0; - int nfrms = 0; - u16 *plen = NULL; - u8 *pfrm = NULL; - - /* Sanity check header and offset. */ - if (WARN_ON((desc->header & ~CFHSI_PIGGY_DESC) || - (desc->offset > CFHSI_MAX_EMB_FRM_SZ))) { - netdev_err(cfhsi->ndev, "%s: Invalid descriptor.\n", - __func__); - return -EPROTO; - } - - /* Set frame pointer to start of payload. */ - pfrm = desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ; - plen = desc->cffrm_len; - - /* Skip already processed frames. */ - while (nfrms < cfhsi->rx_state.nfrms) { - pfrm += *plen; - rx_sz += *plen; - plen++; - nfrms++; - } - - /* Parse payload. */ - while (nfrms < CFHSI_MAX_PKTS && *plen) { - struct sk_buff *skb; - u8 *pcffrm = NULL; - int len; - - /* CAIF frame starts after head padding. */ - pcffrm = pfrm + *pfrm + 1; - - /* Read length of CAIF frame (little endian). */ - len = *pcffrm; - len |= ((*(pcffrm + 1)) << 8) & 0xFF00; - len += 2; /* Add FCS fields. */ - - /* Sanity check length of CAIF frames. */ - if (unlikely(len > CFHSI_MAX_CAIF_FRAME_SZ)) { - netdev_err(cfhsi->ndev, "%s: Invalid length.\n", - __func__); - return -EPROTO; - } - - /* Allocate SKB (OK even in IRQ context). */ - skb = alloc_skb(len + 1, GFP_ATOMIC); - if (!skb) { - netdev_err(cfhsi->ndev, "%s: Out of memory !\n", - __func__); - cfhsi->rx_state.nfrms = nfrms; - return -ENOMEM; - } - caif_assert(skb != NULL); - - skb_put_data(skb, pcffrm, len); - - skb->protocol = htons(ETH_P_CAIF); - skb_reset_mac_header(skb); - skb->dev = cfhsi->ndev; - - netif_rx_any_context(skb); - - /* Update network statistics. */ - cfhsi->ndev->stats.rx_packets++; - cfhsi->ndev->stats.rx_bytes += len; - - pfrm += *plen; - rx_sz += *plen; - plen++; - nfrms++; - } - - return rx_sz; -} - -static void cfhsi_rx_done(struct cfhsi *cfhsi) -{ - int res; - int desc_pld_len = 0, rx_len, rx_state; - struct cfhsi_desc *desc = NULL; - u8 *rx_ptr, *rx_buf; - struct cfhsi_desc *piggy_desc = NULL; - - desc = (struct cfhsi_desc *)cfhsi->rx_buf; - - netdev_dbg(cfhsi->ndev, "%s\n", __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - /* Update inactivity timer if pending. */ - spin_lock_bh(&cfhsi->lock); - mod_timer_pending(&cfhsi->inactivity_timer, - jiffies + cfhsi->cfg.inactivity_timeout); - spin_unlock_bh(&cfhsi->lock); - - if (cfhsi->rx_state.state == CFHSI_RX_STATE_DESC) { - desc_pld_len = cfhsi_rx_desc_len(desc); - - if (desc_pld_len < 0) - goto out_of_sync; - - rx_buf = cfhsi->rx_buf; - rx_len = desc_pld_len; - if (desc_pld_len > 0 && (desc->header & CFHSI_PIGGY_DESC)) - rx_len += CFHSI_DESC_SZ; - if (desc_pld_len == 0) - rx_buf = cfhsi->rx_flip_buf; - } else { - rx_buf = cfhsi->rx_flip_buf; - - rx_len = CFHSI_DESC_SZ; - if (cfhsi->rx_state.pld_len > 0 && - (desc->header & CFHSI_PIGGY_DESC)) { - - piggy_desc = (struct cfhsi_desc *) - (desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ + - cfhsi->rx_state.pld_len); - - cfhsi->rx_state.piggy_desc = true; - - /* Extract payload len from piggy-backed descriptor. */ - desc_pld_len = cfhsi_rx_desc_len(piggy_desc); - if (desc_pld_len < 0) - goto out_of_sync; - - if (desc_pld_len > 0) { - rx_len = desc_pld_len; - if (piggy_desc->header & CFHSI_PIGGY_DESC) - rx_len += CFHSI_DESC_SZ; - } - - /* - * Copy needed information from the piggy-backed - * descriptor to the descriptor in the start. - */ - memcpy(rx_buf, (u8 *)piggy_desc, - CFHSI_DESC_SHORT_SZ); - } - } - - if (desc_pld_len) { - rx_state = CFHSI_RX_STATE_PAYLOAD; - rx_ptr = rx_buf + CFHSI_DESC_SZ; - } else { - rx_state = CFHSI_RX_STATE_DESC; - rx_ptr = rx_buf; - rx_len = CFHSI_DESC_SZ; - } - - /* Initiate next read */ - if (test_bit(CFHSI_AWAKE, &cfhsi->bits)) { - /* Set up new transfer. */ - netdev_dbg(cfhsi->ndev, "%s: Start RX.\n", - __func__); - - res = cfhsi->ops->cfhsi_rx(rx_ptr, rx_len, - cfhsi->ops); - if (WARN_ON(res < 0)) { - netdev_err(cfhsi->ndev, "%s: RX error %d.\n", - __func__, res); - cfhsi->ndev->stats.rx_errors++; - cfhsi->ndev->stats.rx_dropped++; - } - } - - if (cfhsi->rx_state.state == CFHSI_RX_STATE_DESC) { - /* Extract payload from descriptor */ - if (cfhsi_rx_desc(desc, cfhsi) < 0) - goto out_of_sync; - } else { - /* Extract payload */ - if (cfhsi_rx_pld(desc, cfhsi) < 0) - goto out_of_sync; - if (piggy_desc) { - /* Extract any payload in piggyback descriptor. */ - if (cfhsi_rx_desc(piggy_desc, cfhsi) < 0) - goto out_of_sync; - /* Mark no embedded frame after extracting it */ - piggy_desc->offset = 0; - } - } - - /* Update state info */ - memset(&cfhsi->rx_state, 0, sizeof(cfhsi->rx_state)); - cfhsi->rx_state.state = rx_state; - cfhsi->rx_ptr = rx_ptr; - cfhsi->rx_len = rx_len; - cfhsi->rx_state.pld_len = desc_pld_len; - cfhsi->rx_state.piggy_desc = desc->header & CFHSI_PIGGY_DESC; - - if (rx_buf != cfhsi->rx_buf) - swap(cfhsi->rx_buf, cfhsi->rx_flip_buf); - return; - -out_of_sync: - netdev_err(cfhsi->ndev, "%s: Out of sync.\n", __func__); - print_hex_dump_bytes("--> ", DUMP_PREFIX_NONE, - cfhsi->rx_buf, CFHSI_DESC_SZ); - schedule_work(&cfhsi->out_of_sync_work); -} - -static void cfhsi_rx_slowpath(struct timer_list *t) -{ - struct cfhsi *cfhsi = from_timer(cfhsi, t, rx_slowpath_timer); - - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - cfhsi_rx_done(cfhsi); -} - -static void cfhsi_rx_done_cb(struct cfhsi_cb_ops *cb_ops) -{ - struct cfhsi *cfhsi; - - cfhsi = container_of(cb_ops, struct cfhsi, cb_ops); - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - if (test_and_clear_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits)) - wake_up_interruptible(&cfhsi->flush_fifo_wait); - else - cfhsi_rx_done(cfhsi); -} - -static void cfhsi_wake_up(struct work_struct *work) -{ - struct cfhsi *cfhsi = NULL; - int res; - int len; - long ret; - - cfhsi = container_of(work, struct cfhsi, wake_up_work); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - if (unlikely(test_bit(CFHSI_AWAKE, &cfhsi->bits))) { - /* It happenes when wakeup is requested by - * both ends at the same time. */ - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - return; - } - - /* Activate wake line. */ - cfhsi->ops->cfhsi_wake_up(cfhsi->ops); - - netdev_dbg(cfhsi->ndev, "%s: Start waiting.\n", - __func__); - - /* Wait for acknowledge. */ - ret = CFHSI_WAKE_TOUT; - ret = wait_event_interruptible_timeout(cfhsi->wake_up_wait, - test_and_clear_bit(CFHSI_WAKE_UP_ACK, - &cfhsi->bits), ret); - if (unlikely(ret < 0)) { - /* Interrupted by signal. */ - netdev_err(cfhsi->ndev, "%s: Signalled: %ld.\n", - __func__, ret); - - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - cfhsi->ops->cfhsi_wake_down(cfhsi->ops); - return; - } else if (!ret) { - bool ca_wake = false; - size_t fifo_occupancy = 0; - - /* Wakeup timeout */ - netdev_dbg(cfhsi->ndev, "%s: Timeout.\n", - __func__); - - /* Check FIFO to check if modem has sent something. */ - WARN_ON(cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops, - &fifo_occupancy)); - - netdev_dbg(cfhsi->ndev, "%s: Bytes in FIFO: %u.\n", - __func__, (unsigned) fifo_occupancy); - - /* Check if we misssed the interrupt. */ - WARN_ON(cfhsi->ops->cfhsi_get_peer_wake(cfhsi->ops, - &ca_wake)); - - if (ca_wake) { - netdev_err(cfhsi->ndev, "%s: CA Wake missed !.\n", - __func__); - - /* Clear the CFHSI_WAKE_UP_ACK bit to prevent race. */ - clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - - /* Continue execution. */ - goto wake_ack; - } - - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - cfhsi->ops->cfhsi_wake_down(cfhsi->ops); - return; - } -wake_ack: - netdev_dbg(cfhsi->ndev, "%s: Woken.\n", - __func__); - - /* Clear power up bit. */ - set_bit(CFHSI_AWAKE, &cfhsi->bits); - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - - /* Resume read operation. */ - netdev_dbg(cfhsi->ndev, "%s: Start RX.\n", __func__); - res = cfhsi->ops->cfhsi_rx(cfhsi->rx_ptr, cfhsi->rx_len, cfhsi->ops); - - if (WARN_ON(res < 0)) - netdev_err(cfhsi->ndev, "%s: RX err %d.\n", __func__, res); - - /* Clear power up acknowledment. */ - clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - - spin_lock_bh(&cfhsi->lock); - - /* Resume transmit if queues are not empty. */ - if (!cfhsi_tx_queue_len(cfhsi)) { - netdev_dbg(cfhsi->ndev, "%s: Peer wake, start timer.\n", - __func__); - /* Start inactivity timer. */ - mod_timer(&cfhsi->inactivity_timer, - jiffies + cfhsi->cfg.inactivity_timeout); - spin_unlock_bh(&cfhsi->lock); - return; - } - - netdev_dbg(cfhsi->ndev, "%s: Host wake.\n", - __func__); - - spin_unlock_bh(&cfhsi->lock); - - /* Create HSI frame. */ - len = cfhsi_tx_frm((struct cfhsi_desc *)cfhsi->tx_buf, cfhsi); - - if (likely(len > 0)) { - /* Set up new transfer. */ - res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops); - if (WARN_ON(res < 0)) { - netdev_err(cfhsi->ndev, "%s: TX error %d.\n", - __func__, res); - cfhsi_abort_tx(cfhsi); - } - } else { - netdev_err(cfhsi->ndev, - "%s: Failed to create HSI frame: %d.\n", - __func__, len); - } -} - -static void cfhsi_wake_down(struct work_struct *work) -{ - long ret; - struct cfhsi *cfhsi = NULL; - size_t fifo_occupancy = 0; - int retry = CFHSI_WAKE_TOUT; - - cfhsi = container_of(work, struct cfhsi, wake_down_work); - netdev_dbg(cfhsi->ndev, "%s.\n", __func__); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - /* Deactivate wake line. */ - cfhsi->ops->cfhsi_wake_down(cfhsi->ops); - - /* Wait for acknowledge. */ - ret = CFHSI_WAKE_TOUT; - ret = wait_event_interruptible_timeout(cfhsi->wake_down_wait, - test_and_clear_bit(CFHSI_WAKE_DOWN_ACK, - &cfhsi->bits), ret); - if (ret < 0) { - /* Interrupted by signal. */ - netdev_err(cfhsi->ndev, "%s: Signalled: %ld.\n", - __func__, ret); - return; - } else if (!ret) { - bool ca_wake = true; - - /* Timeout */ - netdev_err(cfhsi->ndev, "%s: Timeout.\n", __func__); - - /* Check if we misssed the interrupt. */ - WARN_ON(cfhsi->ops->cfhsi_get_peer_wake(cfhsi->ops, - &ca_wake)); - if (!ca_wake) - netdev_err(cfhsi->ndev, "%s: CA Wake missed !.\n", - __func__); - } - - /* Check FIFO occupancy. */ - while (retry) { - WARN_ON(cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops, - &fifo_occupancy)); - - if (!fifo_occupancy) - break; - - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(1); - retry--; - } - - if (!retry) - netdev_err(cfhsi->ndev, "%s: FIFO Timeout.\n", __func__); - - /* Clear AWAKE condition. */ - clear_bit(CFHSI_AWAKE, &cfhsi->bits); - - /* Cancel pending RX requests. */ - cfhsi->ops->cfhsi_rx_cancel(cfhsi->ops); -} - -static void cfhsi_out_of_sync(struct work_struct *work) -{ - struct cfhsi *cfhsi = NULL; - - cfhsi = container_of(work, struct cfhsi, out_of_sync_work); - - rtnl_lock(); - dev_close(cfhsi->ndev); - rtnl_unlock(); -} - -static void cfhsi_wake_up_cb(struct cfhsi_cb_ops *cb_ops) -{ - struct cfhsi *cfhsi = NULL; - - cfhsi = container_of(cb_ops, struct cfhsi, cb_ops); - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - set_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - wake_up_interruptible(&cfhsi->wake_up_wait); - - if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits)) - return; - - /* Schedule wake up work queue if the peer initiates. */ - if (!test_and_set_bit(CFHSI_WAKE_UP, &cfhsi->bits)) - queue_work(cfhsi->wq, &cfhsi->wake_up_work); -} - -static void cfhsi_wake_down_cb(struct cfhsi_cb_ops *cb_ops) -{ - struct cfhsi *cfhsi = NULL; - - cfhsi = container_of(cb_ops, struct cfhsi, cb_ops); - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - /* Initiating low power is only permitted by the host (us). */ - set_bit(CFHSI_WAKE_DOWN_ACK, &cfhsi->bits); - wake_up_interruptible(&cfhsi->wake_down_wait); -} - -static void cfhsi_aggregation_tout(struct timer_list *t) -{ - struct cfhsi *cfhsi = from_timer(cfhsi, t, aggregation_timer); - - netdev_dbg(cfhsi->ndev, "%s.\n", - __func__); - - cfhsi_start_tx(cfhsi); -} - -static netdev_tx_t cfhsi_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct cfhsi *cfhsi = NULL; - int start_xfer = 0; - int timer_active; - int prio; - - if (!dev) - return -EINVAL; - - cfhsi = netdev_priv(dev); - - switch (skb->priority) { - case TC_PRIO_BESTEFFORT: - case TC_PRIO_FILLER: - case TC_PRIO_BULK: - prio = CFHSI_PRIO_BEBK; - break; - case TC_PRIO_INTERACTIVE_BULK: - prio = CFHSI_PRIO_VI; - break; - case TC_PRIO_INTERACTIVE: - prio = CFHSI_PRIO_VO; - break; - case TC_PRIO_CONTROL: - default: - prio = CFHSI_PRIO_CTL; - break; - } - - spin_lock_bh(&cfhsi->lock); - - /* Update aggregation statistics */ - cfhsi_update_aggregation_stats(cfhsi, skb, 1); - - /* Queue the SKB */ - skb_queue_tail(&cfhsi->qhead[prio], skb); - - /* Sanity check; xmit should not be called after unregister_netdev */ - if (WARN_ON(test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))) { - spin_unlock_bh(&cfhsi->lock); - cfhsi_abort_tx(cfhsi); - return -EINVAL; - } - - /* Send flow off if number of packets is above high water mark. */ - if (!cfhsi->flow_off_sent && - cfhsi_tx_queue_len(cfhsi) > cfhsi->cfg.q_high_mark && - cfhsi->cfdev.flowctrl) { - cfhsi->flow_off_sent = 1; - cfhsi->cfdev.flowctrl(cfhsi->ndev, OFF); - } - - if (cfhsi->tx_state == CFHSI_TX_STATE_IDLE) { - cfhsi->tx_state = CFHSI_TX_STATE_XFER; - start_xfer = 1; - } - - if (!start_xfer) { - /* Send aggregate if it is possible */ - bool aggregate_ready = - cfhsi_can_send_aggregate(cfhsi) && - del_timer(&cfhsi->aggregation_timer) > 0; - spin_unlock_bh(&cfhsi->lock); - if (aggregate_ready) - cfhsi_start_tx(cfhsi); - return NETDEV_TX_OK; - } - - /* Delete inactivity timer if started. */ - timer_active = del_timer_sync(&cfhsi->inactivity_timer); - - spin_unlock_bh(&cfhsi->lock); - - if (timer_active) { - struct cfhsi_desc *desc = (struct cfhsi_desc *)cfhsi->tx_buf; - int len; - int res; - - /* Create HSI frame. */ - len = cfhsi_tx_frm(desc, cfhsi); - WARN_ON(!len); - - /* Set up new transfer. */ - res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops); - if (WARN_ON(res < 0)) { - netdev_err(cfhsi->ndev, "%s: TX error %d.\n", - __func__, res); - cfhsi_abort_tx(cfhsi); - } - } else { - /* Schedule wake up work queue if the we initiate. */ - if (!test_and_set_bit(CFHSI_WAKE_UP, &cfhsi->bits)) - queue_work(cfhsi->wq, &cfhsi->wake_up_work); - } - - return NETDEV_TX_OK; -} - -static const struct net_device_ops cfhsi_netdevops; - -static void cfhsi_setup(struct net_device *dev) -{ - int i; - struct cfhsi *cfhsi = netdev_priv(dev); - dev->features = 0; - dev->type = ARPHRD_CAIF; - dev->flags = IFF_POINTOPOINT | IFF_NOARP; - dev->mtu = CFHSI_MAX_CAIF_FRAME_SZ; - dev->priv_flags |= IFF_NO_QUEUE; - dev->needs_free_netdev = true; - dev->netdev_ops = &cfhsi_netdevops; - for (i = 0; i < CFHSI_PRIO_LAST; ++i) - skb_queue_head_init(&cfhsi->qhead[i]); - cfhsi->cfdev.link_select = CAIF_LINK_HIGH_BANDW; - cfhsi->cfdev.use_frag = false; - cfhsi->cfdev.use_stx = false; - cfhsi->cfdev.use_fcs = false; - cfhsi->ndev = dev; - cfhsi->cfg = hsi_default_config; -} - -static int cfhsi_open(struct net_device *ndev) -{ - struct cfhsi *cfhsi = netdev_priv(ndev); - int res; - - clear_bit(CFHSI_SHUTDOWN, &cfhsi->bits); - - /* Initialize state vaiables. */ - cfhsi->tx_state = CFHSI_TX_STATE_IDLE; - cfhsi->rx_state.state = CFHSI_RX_STATE_DESC; - - /* Set flow info */ - cfhsi->flow_off_sent = 0; - - /* - * Allocate a TX buffer with the size of a HSI packet descriptors - * and the necessary room for CAIF payload frames. - */ - cfhsi->tx_buf = kzalloc(CFHSI_BUF_SZ_TX, GFP_KERNEL); - if (!cfhsi->tx_buf) { - res = -ENODEV; - goto err_alloc_tx; - } - - /* - * Allocate a RX buffer with the size of two HSI packet descriptors and - * the necessary room for CAIF payload frames. - */ - cfhsi->rx_buf = kzalloc(CFHSI_BUF_SZ_RX, GFP_KERNEL); - if (!cfhsi->rx_buf) { - res = -ENODEV; - goto err_alloc_rx; - } - - cfhsi->rx_flip_buf = kzalloc(CFHSI_BUF_SZ_RX, GFP_KERNEL); - if (!cfhsi->rx_flip_buf) { - res = -ENODEV; - goto err_alloc_rx_flip; - } - - /* Initialize aggregation timeout */ - cfhsi->cfg.aggregation_timeout = hsi_default_config.aggregation_timeout; - - /* Initialize recieve vaiables. */ - cfhsi->rx_ptr = cfhsi->rx_buf; - cfhsi->rx_len = CFHSI_DESC_SZ; - - /* Initialize spin locks. */ - spin_lock_init(&cfhsi->lock); - - /* Set up the driver. */ - cfhsi->cb_ops.tx_done_cb = cfhsi_tx_done_cb; - cfhsi->cb_ops.rx_done_cb = cfhsi_rx_done_cb; - cfhsi->cb_ops.wake_up_cb = cfhsi_wake_up_cb; - cfhsi->cb_ops.wake_down_cb = cfhsi_wake_down_cb; - - /* Initialize the work queues. */ - INIT_WORK(&cfhsi->wake_up_work, cfhsi_wake_up); - INIT_WORK(&cfhsi->wake_down_work, cfhsi_wake_down); - INIT_WORK(&cfhsi->out_of_sync_work, cfhsi_out_of_sync); - - /* Clear all bit fields. */ - clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits); - clear_bit(CFHSI_WAKE_DOWN_ACK, &cfhsi->bits); - clear_bit(CFHSI_WAKE_UP, &cfhsi->bits); - clear_bit(CFHSI_AWAKE, &cfhsi->bits); - - /* Create work thread. */ - cfhsi->wq = alloc_ordered_workqueue(cfhsi->ndev->name, WQ_MEM_RECLAIM); - if (!cfhsi->wq) { - netdev_err(cfhsi->ndev, "%s: Failed to create work queue.\n", - __func__); - res = -ENODEV; - goto err_create_wq; - } - - /* Initialize wait queues. */ - init_waitqueue_head(&cfhsi->wake_up_wait); - init_waitqueue_head(&cfhsi->wake_down_wait); - init_waitqueue_head(&cfhsi->flush_fifo_wait); - - /* Setup the inactivity timer. */ - timer_setup(&cfhsi->inactivity_timer, cfhsi_inactivity_tout, 0); - /* Setup the slowpath RX timer. */ - timer_setup(&cfhsi->rx_slowpath_timer, cfhsi_rx_slowpath, 0); - /* Setup the aggregation timer. */ - timer_setup(&cfhsi->aggregation_timer, cfhsi_aggregation_tout, 0); - - /* Activate HSI interface. */ - res = cfhsi->ops->cfhsi_up(cfhsi->ops); - if (res) { - netdev_err(cfhsi->ndev, - "%s: can't activate HSI interface: %d.\n", - __func__, res); - goto err_activate; - } - - /* Flush FIFO */ - res = cfhsi_flush_fifo(cfhsi); - if (res) { - netdev_err(cfhsi->ndev, "%s: Can't flush FIFO: %d.\n", - __func__, res); - goto err_net_reg; - } - return res; - - err_net_reg: - cfhsi->ops->cfhsi_down(cfhsi->ops); - err_activate: - destroy_workqueue(cfhsi->wq); - err_create_wq: - kfree(cfhsi->rx_flip_buf); - err_alloc_rx_flip: - kfree(cfhsi->rx_buf); - err_alloc_rx: - kfree(cfhsi->tx_buf); - err_alloc_tx: - return res; -} - -static int cfhsi_close(struct net_device *ndev) -{ - struct cfhsi *cfhsi = netdev_priv(ndev); - u8 *tx_buf, *rx_buf, *flip_buf; - - /* going to shutdown driver */ - set_bit(CFHSI_SHUTDOWN, &cfhsi->bits); - - /* Delete timers if pending */ - del_timer_sync(&cfhsi->inactivity_timer); - del_timer_sync(&cfhsi->rx_slowpath_timer); - del_timer_sync(&cfhsi->aggregation_timer); - - /* Cancel pending RX request (if any) */ - cfhsi->ops->cfhsi_rx_cancel(cfhsi->ops); - - /* Destroy workqueue */ - destroy_workqueue(cfhsi->wq); - - /* Store bufferes: will be freed later. */ - tx_buf = cfhsi->tx_buf; - rx_buf = cfhsi->rx_buf; - flip_buf = cfhsi->rx_flip_buf; - /* Flush transmit queues. */ - cfhsi_abort_tx(cfhsi); - - /* Deactivate interface */ - cfhsi->ops->cfhsi_down(cfhsi->ops); - - /* Free buffers. */ - kfree(tx_buf); - kfree(rx_buf); - kfree(flip_buf); - return 0; -} - -static void cfhsi_uninit(struct net_device *dev) -{ - struct cfhsi *cfhsi = netdev_priv(dev); - ASSERT_RTNL(); - symbol_put(cfhsi_get_device); - list_del(&cfhsi->list); -} - -static const struct net_device_ops cfhsi_netdevops = { - .ndo_uninit = cfhsi_uninit, - .ndo_open = cfhsi_open, - .ndo_stop = cfhsi_close, - .ndo_start_xmit = cfhsi_xmit -}; - -static void cfhsi_netlink_parms(struct nlattr *data[], struct cfhsi *cfhsi) -{ - int i; - - if (!data) { - pr_debug("no params data found\n"); - return; - } - - i = __IFLA_CAIF_HSI_INACTIVITY_TOUT; - /* - * Inactivity timeout in millisecs. Lowest possible value is 1, - * and highest possible is NEXT_TIMER_MAX_DELTA. - */ - if (data[i]) { - u32 inactivity_timeout = nla_get_u32(data[i]); - /* Pre-calculate inactivity timeout. */ - cfhsi->cfg.inactivity_timeout = inactivity_timeout * HZ / 1000; - if (cfhsi->cfg.inactivity_timeout == 0) - cfhsi->cfg.inactivity_timeout = 1; - else if (cfhsi->cfg.inactivity_timeout > NEXT_TIMER_MAX_DELTA) - cfhsi->cfg.inactivity_timeout = NEXT_TIMER_MAX_DELTA; - } - - i = __IFLA_CAIF_HSI_AGGREGATION_TOUT; - if (data[i]) - cfhsi->cfg.aggregation_timeout = nla_get_u32(data[i]); - - i = __IFLA_CAIF_HSI_HEAD_ALIGN; - if (data[i]) - cfhsi->cfg.head_align = nla_get_u32(data[i]); - - i = __IFLA_CAIF_HSI_TAIL_ALIGN; - if (data[i]) - cfhsi->cfg.tail_align = nla_get_u32(data[i]); - - i = __IFLA_CAIF_HSI_QHIGH_WATERMARK; - if (data[i]) - cfhsi->cfg.q_high_mark = nla_get_u32(data[i]); - - i = __IFLA_CAIF_HSI_QLOW_WATERMARK; - if (data[i]) - cfhsi->cfg.q_low_mark = nla_get_u32(data[i]); -} - -static int caif_hsi_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[], - struct netlink_ext_ack *extack) -{ - cfhsi_netlink_parms(data, netdev_priv(dev)); - netdev_state_change(dev); - return 0; -} - -static const struct nla_policy caif_hsi_policy[__IFLA_CAIF_HSI_MAX + 1] = { - [__IFLA_CAIF_HSI_INACTIVITY_TOUT] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_AGGREGATION_TOUT] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_HEAD_ALIGN] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_TAIL_ALIGN] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_QHIGH_WATERMARK] = { .type = NLA_U32, .len = 4 }, - [__IFLA_CAIF_HSI_QLOW_WATERMARK] = { .type = NLA_U32, .len = 4 }, -}; - -static size_t caif_hsi_get_size(const struct net_device *dev) -{ - int i; - size_t s = 0; - for (i = __IFLA_CAIF_HSI_UNSPEC + 1; i < __IFLA_CAIF_HSI_MAX; i++) - s += nla_total_size(caif_hsi_policy[i].len); - return s; -} - -static int caif_hsi_fill_info(struct sk_buff *skb, const struct net_device *dev) -{ - struct cfhsi *cfhsi = netdev_priv(dev); - - if (nla_put_u32(skb, __IFLA_CAIF_HSI_INACTIVITY_TOUT, - cfhsi->cfg.inactivity_timeout) || - nla_put_u32(skb, __IFLA_CAIF_HSI_AGGREGATION_TOUT, - cfhsi->cfg.aggregation_timeout) || - nla_put_u32(skb, __IFLA_CAIF_HSI_HEAD_ALIGN, - cfhsi->cfg.head_align) || - nla_put_u32(skb, __IFLA_CAIF_HSI_TAIL_ALIGN, - cfhsi->cfg.tail_align) || - nla_put_u32(skb, __IFLA_CAIF_HSI_QHIGH_WATERMARK, - cfhsi->cfg.q_high_mark) || - nla_put_u32(skb, __IFLA_CAIF_HSI_QLOW_WATERMARK, - cfhsi->cfg.q_low_mark)) - return -EMSGSIZE; - - return 0; -} - -static int caif_hsi_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - struct netlink_ext_ack *extack) -{ - struct cfhsi *cfhsi = NULL; - struct cfhsi_ops *(*get_ops)(void); - - ASSERT_RTNL(); - - cfhsi = netdev_priv(dev); - cfhsi_netlink_parms(data, cfhsi); - - get_ops = symbol_get(cfhsi_get_ops); - if (!get_ops) { - pr_err("%s: failed to get the cfhsi_ops\n", __func__); - return -ENODEV; - } - - /* Assign the HSI device. */ - cfhsi->ops = (*get_ops)(); - if (!cfhsi->ops) { - pr_err("%s: failed to get the cfhsi_ops\n", __func__); - goto err; - } - - /* Assign the driver to this HSI device. */ - cfhsi->ops->cb_ops = &cfhsi->cb_ops; - if (register_netdevice(dev)) { - pr_warn("%s: caif_hsi device registration failed\n", __func__); - goto err; - } - /* Add CAIF HSI device to list. */ - list_add_tail(&cfhsi->list, &cfhsi_list); - - return 0; -err: - symbol_put(cfhsi_get_ops); - return -ENODEV; -} - -static struct rtnl_link_ops caif_hsi_link_ops __read_mostly = { - .kind = "cfhsi", - .priv_size = sizeof(struct cfhsi), - .setup = cfhsi_setup, - .maxtype = __IFLA_CAIF_HSI_MAX, - .policy = caif_hsi_policy, - .newlink = caif_hsi_newlink, - .changelink = caif_hsi_changelink, - .get_size = caif_hsi_get_size, - .fill_info = caif_hsi_fill_info, -}; - -static void __exit cfhsi_exit_module(void) -{ - struct list_head *list_node; - struct list_head *n; - struct cfhsi *cfhsi; - - rtnl_link_unregister(&caif_hsi_link_ops); - - rtnl_lock(); - list_for_each_safe(list_node, n, &cfhsi_list) { - cfhsi = list_entry(list_node, struct cfhsi, list); - unregister_netdevice(cfhsi->ndev); - } - rtnl_unlock(); -} - -static int __init cfhsi_init_module(void) -{ - return rtnl_link_register(&caif_hsi_link_ops); -} - -module_init(cfhsi_init_module); -module_exit(cfhsi_exit_module); diff --git a/include/net/caif/caif_hsi.h b/include/net/caif/caif_hsi.h deleted file mode 100644 index 552cf68d28d2..000000000000 --- a/include/net/caif/caif_hsi.h +++ /dev/null @@ -1,200 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson AB 2010 - * Author: Daniel Martensson / daniel.martensson@stericsson.com - * Dmitry.Tarnyagin / dmitry.tarnyagin@stericsson.com - */ - -#ifndef CAIF_HSI_H_ -#define CAIF_HSI_H_ - -#include -#include -#include - -/* - * Maximum number of CAIF frames that can reside in the same HSI frame. - */ -#define CFHSI_MAX_PKTS 15 - -/* - * Maximum number of bytes used for the frame that can be embedded in the - * HSI descriptor. - */ -#define CFHSI_MAX_EMB_FRM_SZ 96 - -/* - * Decides if HSI buffers should be prefilled with 0xFF pattern for easier - * debugging. Both TX and RX buffers will be filled before the transfer. - */ -#define CFHSI_DBG_PREFILL 0 - -/* Structure describing a HSI packet descriptor. */ -#pragma pack(1) /* Byte alignment. */ -struct cfhsi_desc { - u8 header; - u8 offset; - u16 cffrm_len[CFHSI_MAX_PKTS]; - u8 emb_frm[CFHSI_MAX_EMB_FRM_SZ]; -}; -#pragma pack() /* Default alignment. */ - -/* Size of the complete HSI packet descriptor. */ -#define CFHSI_DESC_SZ (sizeof(struct cfhsi_desc)) - -/* - * Size of the complete HSI packet descriptor excluding the optional embedded - * CAIF frame. - */ -#define CFHSI_DESC_SHORT_SZ (CFHSI_DESC_SZ - CFHSI_MAX_EMB_FRM_SZ) - -/* - * Maximum bytes transferred in one transfer. - */ -#define CFHSI_MAX_CAIF_FRAME_SZ 4096 - -#define CFHSI_MAX_PAYLOAD_SZ (CFHSI_MAX_PKTS * CFHSI_MAX_CAIF_FRAME_SZ) - -/* Size of the complete HSI TX buffer. */ -#define CFHSI_BUF_SZ_TX (CFHSI_DESC_SZ + CFHSI_MAX_PAYLOAD_SZ) - -/* Size of the complete HSI RX buffer. */ -#define CFHSI_BUF_SZ_RX ((2 * CFHSI_DESC_SZ) + CFHSI_MAX_PAYLOAD_SZ) - -/* Bitmasks for the HSI descriptor. */ -#define CFHSI_PIGGY_DESC (0x01 << 7) - -#define CFHSI_TX_STATE_IDLE 0 -#define CFHSI_TX_STATE_XFER 1 - -#define CFHSI_RX_STATE_DESC 0 -#define CFHSI_RX_STATE_PAYLOAD 1 - -/* Bitmasks for power management. */ -#define CFHSI_WAKE_UP 0 -#define CFHSI_WAKE_UP_ACK 1 -#define CFHSI_WAKE_DOWN_ACK 2 -#define CFHSI_AWAKE 3 -#define CFHSI_WAKELOCK_HELD 4 -#define CFHSI_SHUTDOWN 5 -#define CFHSI_FLUSH_FIFO 6 - -#ifndef CFHSI_INACTIVITY_TOUT -#define CFHSI_INACTIVITY_TOUT (1 * HZ) -#endif /* CFHSI_INACTIVITY_TOUT */ - -#ifndef CFHSI_WAKE_TOUT -#define CFHSI_WAKE_TOUT (3 * HZ) -#endif /* CFHSI_WAKE_TOUT */ - -#ifndef CFHSI_MAX_RX_RETRIES -#define CFHSI_MAX_RX_RETRIES (10 * HZ) -#endif - -/* Structure implemented by the CAIF HSI driver. */ -struct cfhsi_cb_ops { - void (*tx_done_cb) (struct cfhsi_cb_ops *drv); - void (*rx_done_cb) (struct cfhsi_cb_ops *drv); - void (*wake_up_cb) (struct cfhsi_cb_ops *drv); - void (*wake_down_cb) (struct cfhsi_cb_ops *drv); -}; - -/* Structure implemented by HSI device. */ -struct cfhsi_ops { - int (*cfhsi_up) (struct cfhsi_ops *dev); - int (*cfhsi_down) (struct cfhsi_ops *dev); - int (*cfhsi_tx) (u8 *ptr, int len, struct cfhsi_ops *dev); - int (*cfhsi_rx) (u8 *ptr, int len, struct cfhsi_ops *dev); - int (*cfhsi_wake_up) (struct cfhsi_ops *dev); - int (*cfhsi_wake_down) (struct cfhsi_ops *dev); - int (*cfhsi_get_peer_wake) (struct cfhsi_ops *dev, bool *status); - int (*cfhsi_fifo_occupancy) (struct cfhsi_ops *dev, size_t *occupancy); - int (*cfhsi_rx_cancel)(struct cfhsi_ops *dev); - struct cfhsi_cb_ops *cb_ops; -}; - -/* Structure holds status of received CAIF frames processing */ -struct cfhsi_rx_state { - int state; - int nfrms; - int pld_len; - int retries; - bool piggy_desc; -}; - -/* Priority mapping */ -enum { - CFHSI_PRIO_CTL = 0, - CFHSI_PRIO_VI, - CFHSI_PRIO_VO, - CFHSI_PRIO_BEBK, - CFHSI_PRIO_LAST, -}; - -struct cfhsi_config { - u32 inactivity_timeout; - u32 aggregation_timeout; - u32 head_align; - u32 tail_align; - u32 q_high_mark; - u32 q_low_mark; -}; - -/* Structure implemented by CAIF HSI drivers. */ -struct cfhsi { - struct caif_dev_common cfdev; - struct net_device *ndev; - struct platform_device *pdev; - struct sk_buff_head qhead[CFHSI_PRIO_LAST]; - struct cfhsi_cb_ops cb_ops; - struct cfhsi_ops *ops; - int tx_state; - struct cfhsi_rx_state rx_state; - struct cfhsi_config cfg; - int rx_len; - u8 *rx_ptr; - u8 *tx_buf; - u8 *rx_buf; - u8 *rx_flip_buf; - spinlock_t lock; - int flow_off_sent; - struct list_head list; - struct work_struct wake_up_work; - struct work_struct wake_down_work; - struct work_struct out_of_sync_work; - struct workqueue_struct *wq; - wait_queue_head_t wake_up_wait; - wait_queue_head_t wake_down_wait; - wait_queue_head_t flush_fifo_wait; - struct timer_list inactivity_timer; - struct timer_list rx_slowpath_timer; - - /* TX aggregation */ - int aggregation_len; - struct timer_list aggregation_timer; - - unsigned long bits; -}; -extern struct platform_driver cfhsi_driver; - -/** - * enum ifla_caif_hsi - CAIF HSI NetlinkRT parameters. - * @IFLA_CAIF_HSI_INACTIVITY_TOUT: Inactivity timeout before - * taking the HSI wakeline down, in milliseconds. - * When using RT Netlink to create, destroy or configure a CAIF HSI interface, - * enum ifla_caif_hsi is used to specify the configuration attributes. - */ -enum ifla_caif_hsi { - __IFLA_CAIF_HSI_UNSPEC, - __IFLA_CAIF_HSI_INACTIVITY_TOUT, - __IFLA_CAIF_HSI_AGGREGATION_TOUT, - __IFLA_CAIF_HSI_HEAD_ALIGN, - __IFLA_CAIF_HSI_TAIL_ALIGN, - __IFLA_CAIF_HSI_QHIGH_WATERMARK, - __IFLA_CAIF_HSI_QLOW_WATERMARK, - __IFLA_CAIF_HSI_MAX -}; - -struct cfhsi_ops *cfhsi_get_ops(void); - -#endif /* CAIF_HSI_H_ */ From 71158bb1f2d2da61385c58fc1114e1a1c19984ba Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 30 Jun 2021 13:42:13 +0200 Subject: [PATCH 066/426] tcp: consistently disable header prediction for mptcp The MPTCP receive path is hooked only into the TCP slow-path. The DSS presence allows plain MPTCP traffic to hit that consistently. Since commit e1ff9e82e2ea ("net: mptcp: improve fallback to TCP"), when an MPTCP socket falls back to TCP, it can hit the TCP receive fast-path, and delay or stop triggering the event notification. Address the issue explicitly disabling the header prediction for MPTCP sockets. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/200 Fixes: e1ff9e82e2ea ("net: mptcp: improve fallback to TCP") Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/net/tcp.h b/include/net/tcp.h index e668f1bf780d..17df9b047ee4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -686,6 +686,10 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp) static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { + /* mptcp hooks are only on the slow path */ + if (sk_is_mptcp((struct sock *)tp)) + return; + tp->pred_flags = htonl((tp->tcp_header_len << 26) | ntohl(TCP_FLAG_ACK) | snd_wnd); From 18a419bad63b7f68a1979e28459782518e7b6bbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Jun 2021 09:42:44 -0700 Subject: [PATCH 067/426] udp: annotate data races around unix_sk(sk)->gso_size Accesses to unix_sk(sk)->gso_size are lockless. Add READ_ONCE()/WRITE_ONCE() around them. BUG: KCSAN: data-race in udp_lib_setsockopt / udpv6_sendmsg write to 0xffff88812d78f47c of 2 bytes by task 10849 on cpu 1: udp_lib_setsockopt+0x3b3/0x710 net/ipv4/udp.c:2696 udpv6_setsockopt+0x63/0x90 net/ipv6/udp.c:1630 sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3265 __sys_setsockopt+0x18f/0x200 net/socket.c:2104 __do_sys_setsockopt net/socket.c:2115 [inline] __se_sys_setsockopt net/socket.c:2112 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2112 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88812d78f47c of 2 bytes by task 10852 on cpu 0: udpv6_sendmsg+0x161/0x16b0 net/ipv6/udp.c:1299 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:642 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2337 ___sys_sendmsg net/socket.c:2391 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2477 __do_sys_sendmmsg net/socket.c:2506 [inline] __se_sys_sendmmsg net/socket.c:2503 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2503 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000 -> 0x0005 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 10852 Comm: syz-executor.0 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Reported-by: syzbot Signed-off-by: David S. Miller --- net/ipv4/udp.c | 6 +++--- net/ipv6/udp.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 62682807b4b2..62cd4cd52e84 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1102,7 +1102,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); - ipc.gso_size = up->gso_size; + ipc.gso_size = READ_ONCE(up->gso_size); if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); @@ -2695,7 +2695,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, case UDP_SEGMENT: if (val < 0 || val > USHRT_MAX) return -EINVAL; - up->gso_size = val; + WRITE_ONCE(up->gso_size, val); break; case UDP_GRO: @@ -2790,7 +2790,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, break; case UDP_SEGMENT: - val = up->gso_size; + val = READ_ONCE(up->gso_size); break; case UDP_GRO: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 368972dbd919..0cc7ba531b34 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1296,7 +1296,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); ipcm6_init(&ipc6); - ipc6.gso_size = up->gso_size; + ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; From b6c8801038234a6d837dfc683d79676d4022ad79 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 1 Jul 2021 14:02:20 +0200 Subject: [PATCH 068/426] ARM: dts: qcom-apq8060: Correct Ethernet node name and drop bogus irq property make dtbs_check: ethernet-ebi2@2,0: $nodename:0: 'ethernet-ebi2@2,0' does not match '^ethernet(@.*)?$' ethernet-ebi2@2,0: 'smsc,irq-active-low' does not match any of the regexes: 'pinctrl-[0-9]+' There is no "smsc,irq-active-low" property, as active low is the default. Signed-off-by: Geert Uytterhoeven Reviewed-by: Linus Walleij Signed-off-by: David S. Miller --- arch/arm/boot/dts/qcom-apq8060-dragonboard.dts | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts b/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts index dace8ffeb991..0a4ffd10c484 100644 --- a/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts +++ b/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts @@ -581,7 +581,7 @@ * EBI2. This has a 25MHz chrystal next to it, so no * clocking is needed. */ - ethernet-ebi2@2,0 { + ethernet@2,0 { compatible = "smsc,lan9221", "smsc,lan9115"; reg = <2 0x0 0x100>; /* @@ -598,8 +598,6 @@ phy-mode = "mii"; reg-io-width = <2>; smsc,force-external-phy; - /* IRQ on edge falling = active low */ - smsc,irq-active-low; smsc,irq-push-pull; /* From 19373d0233d04ede649eee4269922e20dd133cf2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 1 Jul 2021 14:02:21 +0200 Subject: [PATCH 069/426] dt-bindings: net: sms911x: Convert to json-schema Convert the Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller Device Tree binding documentation to json-schema. Document missing properties. Make "phy-mode" not required, as many DTS files do not have it, and the Linux drivers falls back to PHY_INTERFACE_MODE_NA. Correct nodename in example. Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- .../devicetree/bindings/net/gpmc-eth.txt | 2 +- .../devicetree/bindings/net/smsc,lan9115.yaml | 110 ++++++++++++++++++ .../devicetree/bindings/net/smsc911x.txt | 43 ------- 3 files changed, 111 insertions(+), 44 deletions(-) create mode 100644 Documentation/devicetree/bindings/net/smsc,lan9115.yaml delete mode 100644 Documentation/devicetree/bindings/net/smsc911x.txt diff --git a/Documentation/devicetree/bindings/net/gpmc-eth.txt b/Documentation/devicetree/bindings/net/gpmc-eth.txt index f7da3d73ca1b..32821066a85b 100644 --- a/Documentation/devicetree/bindings/net/gpmc-eth.txt +++ b/Documentation/devicetree/bindings/net/gpmc-eth.txt @@ -13,7 +13,7 @@ Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt For the properties relevant to the ethernet controller connected to the GPMC refer to the binding documentation of the device. For example, the documentation -for the SMSC 911x is Documentation/devicetree/bindings/net/smsc911x.txt +for the SMSC 911x is Documentation/devicetree/bindings/net/smsc,lan9115.yaml Child nodes need to specify the GPMC bus address width using the "bank-width" property but is possible that an ethernet controller also has a property to diff --git a/Documentation/devicetree/bindings/net/smsc,lan9115.yaml b/Documentation/devicetree/bindings/net/smsc,lan9115.yaml new file mode 100644 index 000000000000..f86667cbcca8 --- /dev/null +++ b/Documentation/devicetree/bindings/net/smsc,lan9115.yaml @@ -0,0 +1,110 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/smsc,lan9115.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller + +maintainers: + - Shawn Guo + +allOf: + - $ref: ethernet-controller.yaml# + +properties: + compatible: + oneOf: + - const: smsc,lan9115 + - items: + - enum: + - smsc,lan89218 + - smsc,lan9117 + - smsc,lan9118 + - smsc,lan9220 + - smsc,lan9221 + - const: smsc,lan9115 + + reg: + maxItems: 1 + + reg-shift: true + + reg-io-width: + enum: [ 2, 4 ] + default: 2 + + interrupts: + minItems: 1 + items: + - description: + LAN interrupt line + - description: + Optional PME (power management event) interrupt that is able to wake + up the host system with a 50ms pulse on network activity + + clocks: + maxItems: 1 + + phy-mode: true + + smsc,irq-active-high: + type: boolean + description: Indicates the IRQ polarity is active-high + + smsc,irq-push-pull: + type: boolean + description: Indicates the IRQ type is push-pull + + smsc,force-internal-phy: + type: boolean + description: Forces SMSC LAN controller to use internal PHY + + smsc,force-external-phy: + type: boolean + description: Forces SMSC LAN controller to use external PHY + + smsc,save-mac-address: + type: boolean + description: + Indicates that MAC address needs to be saved before resetting the + controller + + reset-gpios: + maxItems: 1 + description: + A GPIO line connected to the RESET (active low) signal of the device. + On many systems this is wired high so the device goes out of reset at + power-on, but if it is under program control, this optional GPIO can + wake up in response to it. + + vdd33a-supply: + description: 3.3V analog power supply + + vddvario-supply: + description: IO logic power supply + +required: + - compatible + - reg + - interrupts + +# There are lots of bus-specific properties ("qcom,*", "samsung,*", "fsl,*", +# "gpmc,*", ...) to be found, that actually depend on the compatible value of +# the parent node. +additionalProperties: true + +examples: + - | + #include + + ethernet@f4000000 { + compatible = "smsc,lan9220", "smsc,lan9115"; + reg = <0xf4000000 0x2000000>; + phy-mode = "mii"; + interrupt-parent = <&gpio1>; + interrupts = <31>, <32>; + reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; + reg-io-width = <4>; + smsc,irq-push-pull; + }; diff --git a/Documentation/devicetree/bindings/net/smsc911x.txt b/Documentation/devicetree/bindings/net/smsc911x.txt deleted file mode 100644 index acfafc8e143c..000000000000 --- a/Documentation/devicetree/bindings/net/smsc911x.txt +++ /dev/null @@ -1,43 +0,0 @@ -* Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller - -Required properties: -- compatible : Should be "smsc,lan", "smsc,lan9115" -- reg : Address and length of the io space for SMSC LAN -- interrupts : one or two interrupt specifiers - - The first interrupt is the SMSC LAN interrupt line - - The second interrupt (if present) is the PME (power - management event) interrupt that is able to wake up the host - system with a 50ms pulse on network activity -- phy-mode : See ethernet.txt file in the same directory - -Optional properties: -- reg-shift : Specify the quantity to shift the register offsets by -- reg-io-width : Specify the size (in bytes) of the IO accesses that - should be performed on the device. Valid value for SMSC LAN is - 2 or 4. If it's omitted or invalid, the size would be 2. -- smsc,irq-active-high : Indicates the IRQ polarity is active-high -- smsc,irq-push-pull : Indicates the IRQ type is push-pull -- smsc,force-internal-phy : Forces SMSC LAN controller to use - internal PHY -- smsc,force-external-phy : Forces SMSC LAN controller to use - external PHY -- smsc,save-mac-address : Indicates that mac address needs to be saved - before resetting the controller -- reset-gpios : a GPIO line connected to the RESET (active low) signal - of the device. On many systems this is wired high so the device goes - out of reset at power-on, but if it is under program control, this - optional GPIO can wake up in response to it. -- vdd33a-supply, vddvario-supply : 3.3V analog and IO logic power supplies - -Examples: - -lan9220@f4000000 { - compatible = "smsc,lan9220", "smsc,lan9115"; - reg = <0xf4000000 0x2000000>; - phy-mode = "mii"; - interrupt-parent = <&gpio1>; - interrupts = <31>, <32>; - reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; - reg-io-width = <4>; - smsc,irq-push-pull; -}; From 6b28a86d6c0bb02119f386ec2f56efde909e9bcb Mon Sep 17 00:00:00 2001 From: Mohammad Athari Bin Ismail Date: Wed, 30 Jun 2021 17:59:35 +0800 Subject: [PATCH 070/426] net: stmmac: Terminate FPE workqueue in suspend Add stmmac_fpe_stop_wq() in stmmac_suspend() to terminate FPE workqueue during suspend. So, in suspend mode, there will be no FPE workqueue available. Without this fix, new additional FPE workqueue will be created in every suspend->resume cycle. Fixes: 5a5586112b92 ("net: stmmac: support FPE link partner hand-shaking procedure") Signed-off-by: Mohammad Athari Bin Ismail Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8d9d6ecf8c63..7b8404a21544 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7171,6 +7171,7 @@ int stmmac_suspend(struct device *dev) priv->plat->rx_queues_to_use, false); stmmac_fpe_handshake(priv, false); + stmmac_fpe_stop_wq(priv); } priv->speed = SPEED_UNKNOWN; From 2342ae10d1272d411a468a85a67647dd115b344f Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 1 Jul 2021 22:18:24 +0200 Subject: [PATCH 071/426] gve: Fix an error handling path in 'gve_probe()' If the 'register_netdev() call fails, we must release the resources allocated by the previous 'gve_init_priv()' call, as already done in the remove function. Add a new label and the missing 'gve_teardown_priv_resources()' in the error handling path. Fixes: 893ce44df565 ("gve: Add basic driver framework for Compute Engine Virtual NIC") Signed-off-by: Christophe JAILLET Reviewed-by: Catherine Sullivan Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 867e87af3432..44262c9f9ec2 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1565,7 +1565,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = register_netdev(dev); if (err) - goto abort_with_wq; + goto abort_with_gve_init; dev_info(&pdev->dev, "GVE version %s\n", gve_version_str); dev_info(&pdev->dev, "GVE queue format %d\n", (int)priv->queue_format); @@ -1573,6 +1573,9 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) queue_work(priv->gve_wq, &priv->service_task); return 0; +abort_with_gve_init: + gve_teardown_priv_resources(priv); + abort_with_wq: destroy_workqueue(priv->gve_wq); From 6dce38b4b7ffb39539b49feca2b3ce34dbaadf02 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 1 Jul 2021 22:18:37 +0200 Subject: [PATCH 072/426] gve: Propagate error codes to caller If 'gve_probe()' fails, we should propagate the error code, instead of hard coding a -ENXIO value. Make sure that all error handling paths set a correct value for 'err'. Signed-off-by: Christophe JAILLET Reviewed-by: Catherine Sullivan Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 44262c9f9ec2..c03984b26db4 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1469,7 +1469,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = pci_enable_device(pdev); if (err) - return -ENXIO; + return err; err = pci_request_regions(pdev, "gvnic-cfg"); if (err) @@ -1512,6 +1512,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev = alloc_etherdev_mqs(sizeof(*priv), max_tx_queues, max_rx_queues); if (!dev) { dev_err(&pdev->dev, "could not allocate netdev\n"); + err = -ENOMEM; goto abort_with_db_bar; } SET_NETDEV_DEV(dev, &pdev->dev); @@ -1593,7 +1594,7 @@ abort_with_pci_region: abort_with_enabled: pci_disable_device(pdev); - return -ENXIO; + return err; } static void gve_remove(struct pci_dev *pdev) From 5140aaa4604ba96685dc04b4d2dde3384bbaecef Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Jul 2021 17:44:07 +0200 Subject: [PATCH 073/426] s390: iucv: Avoid field over-reading memcpy() In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally reading across neighboring array fields. Add a wrapping struct to serve as the memcpy() source so the compiler can perform appropriate bounds checking, avoiding this future warning: In function '__fortify_memcpy', inlined from 'iucv_message_pending' at net/iucv/iucv.c:1663:4: ./include/linux/fortify-string.h:246:4: error: call to '__read_overflow2_field' declared with attribute error: detected read beyond size of field (2nd parameter) Signed-off-by: Kees Cook Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- net/iucv/iucv.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 349c6ac3313f..e6795d5a546a 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1635,14 +1635,16 @@ struct iucv_message_pending { u8 iptype; u32 ipmsgid; u32 iptrgcls; - union { - u32 iprmmsg1_u32; - u8 iprmmsg1[4]; - } ln1msg1; - union { - u32 ipbfln1f; - u8 iprmmsg2[4]; - } ln1msg2; + struct { + union { + u32 iprmmsg1_u32; + u8 iprmmsg1[4]; + } ln1msg1; + union { + u32 ipbfln1f; + u8 iprmmsg2[4]; + } ln1msg2; + } rmmsg; u32 res1[3]; u32 ipbfln2f; u8 ippollfg; @@ -1660,10 +1662,10 @@ static void iucv_message_pending(struct iucv_irq_data *data) msg.id = imp->ipmsgid; msg.class = imp->iptrgcls; if (imp->ipflags1 & IUCV_IPRMDATA) { - memcpy(msg.rmmsg, imp->ln1msg1.iprmmsg1, 8); + memcpy(msg.rmmsg, &imp->rmmsg, 8); msg.length = 8; } else - msg.length = imp->ln1msg2.ipbfln1f; + msg.length = imp->rmmsg.ln1msg2.ipbfln1f; msg.reply_size = imp->ipbfln2f; path->handler->message_pending(path, &msg); } From 37d220b58d52d6da88b928e11bffd83f88c6ac79 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 24 Jun 2021 12:36:41 +0200 Subject: [PATCH 074/426] selftest: netfilter: add test case for unreplied tcp connections TCP connections in UNREPLIED state (only SYN seen) can be kept alive indefinitely, as each SYN re-sets the timeout. This means that even if a peer has closed its socket the entry never times out. This also prevents re-evaluation of configured NAT rules. Add a test case that sets SYN timeout to 10 seconds, then check that the nat redirection added later eventually takes effect. This is based off a repro script from Antonio Ojea. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 2 +- .../netfilter/conntrack_tcp_unreplied.sh | 167 ++++++++++++++++++ 2 files changed, 168 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index cd6430b39982..8748199ac109 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -5,7 +5,7 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ - ipip-conntrack-mtu.sh + ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh b/tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh new file mode 100755 index 000000000000..e7d7bf13cff5 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh @@ -0,0 +1,167 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Check that UNREPLIED tcp conntrack will eventually timeout. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +waittime=20 +sfx=$(mktemp -u "XXXXXXXX") +ns1="ns1-$sfx" +ns2="ns2-$sfx" + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup() { + ip netns pids $ns1 | xargs kill 2>/dev/null + ip netns pids $ns2 | xargs kill 2>/dev/null + + ip netns del $ns1 + ip netns del $ns2 +} + +ipv4() { + echo -n 192.168.$1.2 +} + +check_counter() +{ + ns=$1 + name=$2 + expect=$3 + local lret=0 + + cnt=$(ip netns exec $ns2 nft list counter inet filter "$name" | grep -q "$expect") + if [ $? -ne 0 ]; then + echo "ERROR: counter $name in $ns2 has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns2 nft list counter inet filter "$name" 1>&2 + lret=1 + fi + + return $lret +} + +# Create test namespaces +ip netns add $ns1 || exit 1 + +trap cleanup EXIT + +ip netns add $ns2 || exit 1 + +# Connect the namespace to the host using a veth pair +ip -net $ns1 link add name veth1 type veth peer name veth2 +ip -net $ns1 link set netns $ns2 dev veth2 + +ip -net $ns1 link set up dev lo +ip -net $ns2 link set up dev lo +ip -net $ns1 link set up dev veth1 +ip -net $ns2 link set up dev veth2 + +ip -net $ns2 addr add 10.11.11.2/24 dev veth2 +ip -net $ns2 route add default via 10.11.11.1 + +ip netns exec $ns2 sysctl -q net.ipv4.conf.veth2.forwarding=1 + +# add a rule inside NS so we enable conntrack +ip netns exec $ns1 iptables -A INPUT -m state --state established,related -j ACCEPT + +ip -net $ns1 addr add 10.11.11.1/24 dev veth1 +ip -net $ns1 route add 10.99.99.99 via 10.11.11.2 + +# Check connectivity works +ip netns exec $ns1 ping -q -c 2 10.11.11.2 >/dev/null || exit 1 + +ip netns exec $ns2 nc -l -p 8080 < /dev/null & + +# however, conntrack entries are there + +ip netns exec $ns2 nft -f - < $ns2 to the virtual ip" +ip netns exec $ns1 bash -c 'while true ; do + nc -p 60000 10.99.99.99 80 + sleep 1 + done' & + +sleep 1 + +ip netns exec $ns2 nft -f - </dev/null | wc -l) +if [ $count -eq 0 ]; then + echo "ERROR: $ns2 did not pick up tcp connection from peer" + exit 1 +fi + +echo "INFO: NAT redirect added in ns $ns2, waiting for $waittime seconds for nat to take effect" +for i in $(seq 1 $waittime); do + echo -n "." + + sleep 1 + + count=$(ip netns exec $ns2 conntrack -L -p tcp --reply-port-src 8080 2>/dev/null | wc -l) + if [ $count -gt 0 ]; then + echo + echo "PASS: redirection took effect after $i seconds" + break + fi + + m=$((i%20)) + if [ $m -eq 0 ]; then + echo " waited for $i seconds" + fi +done + +expect="packets 1 bytes 60" +check_counter "$ns2" "redir" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +if [ $ret -eq 0 ];then + echo "PASS: redirection counter has expected values" +else + echo "ERROR: no tcp connection was redirected" +fi + +exit $ret From e15d4cdf27cb0c1e977270270b2cea12e0955edd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 24 Jun 2021 12:36:42 +0200 Subject: [PATCH 075/426] netfilter: conntrack: do not renew entry stuck in tcp SYN_SENT state Consider: client -----> conntrack ---> Host client sends a SYN, but $Host is unreachable/silent. Client eventually gives up and the conntrack entry will time out. However, if the client is restarted with same addr/port pair, it may prevent the conntrack entry from timing out. This is noticeable when the existing conntrack entry has no NAT transformation or an outdated one and port reuse happens either on client or due to a NAT middlebox. This change prevents refresh of the timeout for SYN retransmits, so entry is going away after nf_conntrack_tcp_timeout_syn_sent seconds (default: 60). Entry will be re-created on next connection attempt, but then nat rules will be evaluated again. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_tcp.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index f7e8baf59b51..eb4de92077a8 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1134,6 +1134,16 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } + + if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) { + /* do not renew timeout on SYN retransmit. + * + * Else port reuse by client or NAT middlebox can keep + * entry alive indefinitely (including nat info). + */ + return NF_ACCEPT; + } + /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection * pickup with loose=1. Avoid large ESTABLISHED timeout. */ From 4ca041f919f13783b0b03894783deee00dbca19a Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 24 Jun 2021 20:57:18 +0100 Subject: [PATCH 076/426] netfilter: nf_tables: Fix dereference of null pointer flow In the case where chain->flags & NFT_CHAIN_HW_OFFLOAD is false then nft_flow_rule_create is not called and flow is NULL. The subsequent error handling execution via label err_destroy_flow_rule will lead to a null pointer dereference on flow when calling nft_flow_rule_destroy. Since the error path to err_destroy_flow_rule has to cater for null and non-null flows, only call nft_flow_rule_destroy if flow is non-null to fix this issue. Addresses-Coverity: ("Explicity null dereference") Fixes: 3c5e44622011 ("netfilter: nf_tables: memleak in hw offload abort path") Signed-off-by: Colin Ian King Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 390d4466567f..de182d1f7c4e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3446,7 +3446,8 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return 0; err_destroy_flow_rule: - nft_flow_rule_destroy(flow); + if (flow) + nft_flow_rule_destroy(flow); err_release_rule: nf_tables_rule_release(&ctx, rule); err_release_expr: From a23f89a9990684a0ca0cac4a2857c15d338ebe2d Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 1 Jul 2021 08:02:24 +0300 Subject: [PATCH 077/426] netfilter: conntrack: nf_ct_gre_keymap_flush() removal nf_ct_gre_keymap_flush() is useless. It is called from nf_conntrack_cleanup_net_list() only and tries to remove nf_ct_gre_keymap entries from pernet gre keymap list. Though: a) at this point the list should already be empty, all its entries were deleted during the conntracks cleanup, because nf_conntrack_cleanup_net_list() executes nf_ct_iterate_cleanup(kill_all) before nf_conntrack_proto_pernet_fini(): nf_conntrack_cleanup_net_list +- nf_ct_iterate_cleanup | nf_ct_put | nf_conntrack_put | nf_conntrack_destroy | destroy_conntrack | destroy_gre_conntrack | nf_ct_gre_keymap_destroy `- nf_conntrack_proto_pernet_fini nf_ct_gre_keymap_flush b) Let's say we find that the keymap list is not empty. This means netns still has a conntrack associated with gre, in which case we should not free its memory, because this will lead to a double free and related crashes. However I doubt it could have gone unnoticed for years, obviously this does not happen in real life. So I think we can remove both nf_ct_gre_keymap_flush() and nf_conntrack_proto_pernet_fini(). Signed-off-by: Vasily Averin Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 1 - net/netfilter/nf_conntrack_core.c | 1 - net/netfilter/nf_conntrack_proto.c | 7 ------- net/netfilter/nf_conntrack_proto_gre.c | 13 ------------- 4 files changed, 22 deletions(-) diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 09f2efea0b97..13807ea94cd2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -30,7 +30,6 @@ void nf_conntrack_cleanup_net(struct net *net); void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list); void nf_conntrack_proto_pernet_init(struct net *net); -void nf_conntrack_proto_pernet_fini(struct net *net); int nf_conntrack_proto_init(void); void nf_conntrack_proto_fini(void); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 96ba19fc8155..085a11f1eb43 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2457,7 +2457,6 @@ i_see_dead_people: } list_for_each_entry(net, net_exit_list, exit_list) { - nf_conntrack_proto_pernet_fini(net); nf_conntrack_ecache_pernet_fini(net); nf_conntrack_expect_pernet_fini(net); free_percpu(net->ct.stat); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 55647409a9be..8f7a9837349c 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -697,13 +697,6 @@ void nf_conntrack_proto_pernet_init(struct net *net) #endif } -void nf_conntrack_proto_pernet_fini(struct net *net) -{ -#ifdef CONFIG_NF_CT_PROTO_GRE - nf_ct_gre_keymap_flush(net); -#endif -} - module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, &nf_conntrack_htable_size, 0600); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index db11e403d818..728eeb0aea87 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -55,19 +55,6 @@ static inline struct nf_gre_net *gre_pernet(struct net *net) return &net->ct.nf_ct_proto.gre; } -void nf_ct_gre_keymap_flush(struct net *net) -{ - struct nf_gre_net *net_gre = gre_pernet(net); - struct nf_ct_gre_keymap *km, *tmp; - - spin_lock_bh(&keymap_lock); - list_for_each_entry_safe(km, tmp, &net_gre->keymap_list, list) { - list_del_rcu(&km->list); - kfree_rcu(km, rcu); - } - spin_unlock_bh(&keymap_lock); -} - static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, const struct nf_conntrack_tuple *t) { From c23a9fd209bc6f8c1fa6ee303fdf037d784a1627 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 1 Jul 2021 08:02:49 +0300 Subject: [PATCH 078/426] netfilter: ctnetlink: suspicious RCU usage in ctnetlink_dump_helpinfo Two patches listed below removed ctnetlink_dump_helpinfo call from under rcu_read_lock. Now its rcu_dereference generates following warning: ============================= WARNING: suspicious RCU usage 5.13.0+ #5 Not tainted ----------------------------- net/netfilter/nf_conntrack_netlink.c:221 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 stack backtrace: CPU: 1 PID: 2251 Comm: conntrack Not tainted 5.13.0+ #5 Call Trace: dump_stack+0x7f/0xa1 ctnetlink_dump_helpinfo+0x134/0x150 [nf_conntrack_netlink] ctnetlink_fill_info+0x2c2/0x390 [nf_conntrack_netlink] ctnetlink_dump_table+0x13f/0x370 [nf_conntrack_netlink] netlink_dump+0x10c/0x370 __netlink_dump_start+0x1a7/0x260 ctnetlink_get_conntrack+0x1e5/0x250 [nf_conntrack_netlink] nfnetlink_rcv_msg+0x613/0x993 [nfnetlink] netlink_rcv_skb+0x50/0x100 nfnetlink_rcv+0x55/0x120 [nfnetlink] netlink_unicast+0x181/0x260 netlink_sendmsg+0x23f/0x460 sock_sendmsg+0x5b/0x60 __sys_sendto+0xf1/0x160 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x36/0x70 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: 49ca022bccc5 ("netfilter: ctnetlink: don't dump ct extensions of unconfirmed conntracks") Fixes: 0b35f6031a00 ("netfilter: Remove duplicated rcu_read_lock.") Signed-off-by: Vasily Averin Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 4e1a9dba7077..e81af33b233b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -218,6 +218,7 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb, if (!help) return 0; + rcu_read_lock(); helper = rcu_dereference(help->helper); if (!helper) goto out; @@ -233,9 +234,11 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb, nla_nest_end(skb, nest_helper); out: + rcu_read_unlock(); return 0; nla_put_failure: + rcu_read_unlock(); return -1; } From 633fa666401c42f9a106a509b7702c58c84524e2 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 1 Jul 2021 15:16:53 +0200 Subject: [PATCH 079/426] net/sched: sch_taprio: fix typo in comment I have checked that the IEEE standard 802.1Q-2018 section 8.6.9.4.5 is called AdminGateStates. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- net/sched/sch_taprio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 66fe2b82af9a..07b30d0601d7 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -564,7 +564,7 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch) /* if there's no entry, it means that the schedule didn't * start yet, so force all gates to be open, this is in * accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5 - * "AdminGateSates" + * "AdminGateStates" */ gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; From bde3c8ffdd4153a3e9f0b0d51d972b30113b35ac Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 1 Jul 2021 22:41:19 +0200 Subject: [PATCH 080/426] gve: Simplify code and axe the use of a deprecated API The wrappers in include/linux/pci-dma-compat.h should go away. Replace 'pci_set_dma_mask/pci_set_consistent_dma_mask' by an equivalent and less verbose 'dma_set_mask_and_coherent()' call. Signed-off-by: Christophe JAILLET Reviewed-by: Catherine Sullivan Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_main.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index c03984b26db4..099a2bc5ae67 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1477,19 +1477,12 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { dev_err(&pdev->dev, "Failed to set dma mask: err=%d\n", err); goto abort_with_pci_region; } - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - if (err) { - dev_err(&pdev->dev, - "Failed to set consistent dma mask: err=%d\n", err); - goto abort_with_pci_region; - } - reg_bar = pci_iomap(pdev, GVE_REGISTER_BAR, 0); if (!reg_bar) { dev_err(&pdev->dev, "Failed to map pci bar!\n"); From 40fc3054b45820c28ea3c65e2c86d041dc244a8a Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Fri, 2 Jul 2021 02:47:00 +0300 Subject: [PATCH 081/426] net: ipv6: fix return value of ip6_skb_dst_mtu Commit 628a5c561890 ("[INET]: Add IP(V6)_PMTUDISC_RPOBE") introduced ip6_skb_dst_mtu with return value of signed int which is inconsistent with actually returned values. Also 2 users of this function actually assign its value to unsigned int variable and only __xfrm6_output assigns result of this function to signed variable but actually uses as unsigned in further comparisons and calls. Change this function to return unsigned int value. Fixes: 628a5c561890 ("[INET]: Add IP(V6)_PMTUDISC_RPOBE") Reviewed-by: David Ahern Signed-off-by: Vadim Fedorenko Signed-off-by: David S. Miller --- include/net/ip6_route.h | 2 +- net/ipv6/xfrm6_output.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f14149df5a65..625a38ccb5d9 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -263,7 +263,7 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst, int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); -static inline int ip6_skb_dst_mtu(struct sk_buff *skb) +static inline unsigned int ip6_skb_dst_mtu(struct sk_buff *skb) { int mtu; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 57fa27c1cdf9..d0d280077721 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -49,7 +49,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; - int mtu; + unsigned int mtu; bool toobig; #ifdef CONFIG_NETFILTER From 1bfa4d0cb5adf954e0f4870a3ecb7cb19506320c Mon Sep 17 00:00:00 2001 From: Bailey Forrest Date: Thu, 1 Jul 2021 20:13:36 -0700 Subject: [PATCH 082/426] gve: DQO: Remove incorrect prefetch The prefetch is incorrectly using the dma address instead of the virtual address. It's supposed to be: prefetch((char *)buf_state->page_info.page_address + buf_state->page_info.page_offset) However, after correcting this mistake, there is no evidence of performance improvement. Fixes: 9b8dd5e5ea48 ("gve: DQO: Add RX path") Signed-off-by: Bailey Forrest Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 77bb8227f89b..8500621b2cd4 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -566,13 +566,6 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, return 0; } - /* Prefetch the payload header. */ - prefetch((char *)buf_state->addr + buf_state->page_info.page_offset); -#if L1_CACHE_BYTES < 128 - prefetch((char *)buf_state->addr + buf_state->page_info.page_offset + - L1_CACHE_BYTES); -#endif - if (eop && buf_len <= priv->rx_copybreak) { rx->skb_head = gve_rx_copy(priv->dev, napi, &buf_state->page_info, buf_len, 0); From 8955b90c3cdad199137809aac8ccbbb585355913 Mon Sep 17 00:00:00 2001 From: wenxu Date: Fri, 2 Jul 2021 11:34:31 +0800 Subject: [PATCH 083/426] net/sched: act_ct: fix err check for nf_conntrack_confirm The confirm operation should be checked. If there are any failed, the packet should be dropped like in ovs and netfilter. Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct") Signed-off-by: wenxu Signed-off-by: David S. Miller --- net/sched/act_ct.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index a656baa321fe..a62f404d0e16 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1026,7 +1026,8 @@ do_nat: /* This will take care of sending queued events * even if the connection is already confirmed. */ - nf_conntrack_confirm(skb); + if (nf_conntrack_confirm(skb) != NF_ACCEPT) + goto drop; } if (!skip_add) From 561022acb1ce62e50f7a8258687a21b84282a4cb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Jul 2021 13:09:03 -0700 Subject: [PATCH 084/426] tcp: annotate data races around tp->mtu_info While tp->mtu_info is read while socket is owned, the write sides happen from err handlers (tcp_v[46]_mtu_reduced) which only own the socket spinlock. Fixes: 563d34d05786 ("tcp: dont drop MTU reduction indications") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv6/tcp_ipv6.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e66ad6bfe808..b9dc2d6197be 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -342,7 +342,7 @@ void tcp_v4_mtu_reduced(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - mtu = tcp_sk(sk)->mtu_info; + mtu = READ_ONCE(tcp_sk(sk)->mtu_info); dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -546,7 +546,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) if (sk->sk_state == TCP_LISTEN) goto out; - tp->mtu_info = info; + WRITE_ONCE(tp->mtu_info, info); if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); } else { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 578ab6305c3f..593c32fe57ed 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -352,7 +352,7 @@ static void tcp_v6_mtu_reduced(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info); + dst = inet6_csk_update_pmtu(sk, READ_ONCE(tcp_sk(sk)->mtu_info)); if (!dst) return; @@ -443,7 +443,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!ip6_sk_accept_pmtu(sk)) goto out; - tp->mtu_info = ntohl(info); + WRITE_ONCE(tp->mtu_info, ntohl(info)); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, From 81b4a0cc7565b08cadd0d02bae3434f127d1d72a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Jul 2021 07:41:01 -0700 Subject: [PATCH 085/426] sock: fix error in sock_setsockopt() Some tests are failing, John bisected the issue to a recent commit. sock_set_timestamp() parameters should be : 1) sk 2) optname 3) valbool Fixes: 371087aa476a ("sock: expose so_timestamp options for mptcp") Signed-off-by: Eric Dumazet Bisected-by: John Sperbeck Cc: Paolo Abeni Cc: Florian Westphal Cc: Mat Martineau Reviewed-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index cad107112204..1c4b0468bc2c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1116,7 +1116,7 @@ set_sndbuf: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: - sock_set_timestamp(sk, valbool, optname); + sock_set_timestamp(sk, optname, valbool); break; case SO_TIMESTAMPING_NEW: From a019abd8022061b917da767cd1a66ed823724eab Mon Sep 17 00:00:00 2001 From: Wolfgang Bumiller Date: Fri, 2 Jul 2021 14:07:36 +0200 Subject: [PATCH 086/426] net: bridge: sync fdb to new unicast-filtering ports Since commit 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.") bridges with `vlan_filtering 1` and only 1 auto-port don't set IFF_PROMISC for unicast-filtering-capable ports. Normally on port changes `br_manage_promisc` is called to update the promisc flags and unicast filters if necessary, but it cannot distinguish between *new* ports and ones losing their promisc flag, and new ports end up not receiving the MAC address list. Fix this by calling `br_fdb_sync_static` in `br_add_if` after the port promisc flags are updated and the unicast filter was supposed to have been filled. Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.") Signed-off-by: Wolfgang Bumiller Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_if.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f7d2f472ae24..6e4a32354a13 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -562,7 +562,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, struct net_bridge_port *p; int err = 0; unsigned br_hr, dev_hr; - bool changed_addr; + bool changed_addr, fdb_synced = false; /* Don't allow bridging non-ethernet like devices. */ if ((dev->flags & IFF_LOOPBACK) || @@ -652,6 +652,19 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, list_add_rcu(&p->list, &br->port_list); nbp_update_port_count(br); + if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) { + /* When updating the port count we also update all ports' + * promiscuous mode. + * A port leaving promiscuous mode normally gets the bridge's + * fdb synced to the unicast filter (if supported), however, + * `br_port_clear_promisc` does not distinguish between + * non-promiscuous ports and *new* ports, so we need to + * sync explicitly here. + */ + fdb_synced = br_fdb_sync_static(br, p) == 0; + if (!fdb_synced) + netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n"); + } netdev_update_features(br->dev); @@ -701,6 +714,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, return 0; err7: + if (fdb_synced) + br_fdb_unsync_static(br, p); list_del_rcu(&p->list); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); From 77ac5e40c44eb78333fbc38482d61fc2af7dda0a Mon Sep 17 00:00:00 2001 From: Louis Peens Date: Fri, 2 Jul 2021 11:21:38 +0200 Subject: [PATCH 087/426] net/sched: act_ct: remove and free nf_table callbacks When cleaning up the nf_table in tcf_ct_flow_table_cleanup_work there is no guarantee that the callback list, added to by nf_flow_table_offload_add_cb, is empty. This means that it is possible that the flow_block_cb memory allocated will be lost. Fix this by iterating the list and freeing the flow_block_cb entries before freeing the nf_table entry (via freeing ct_ft). Fixes: 978703f42549 ("netfilter: flowtable: Add API for registering to flow table events") Signed-off-by: Louis Peens Signed-off-by: Yinjun Zhang Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- net/sched/act_ct.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index a62f404d0e16..1b4b3514c94f 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -322,11 +322,22 @@ err_alloc: static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { + struct flow_block_cb *block_cb, *tmp_cb; struct tcf_ct_flow_table *ct_ft; + struct flow_block *block; ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table, rwork); nf_flow_table_free(&ct_ft->nf_ft); + + /* Remove any remaining callbacks before cleanup */ + block = &ct_ft->nf_ft.flow_block; + down_write(&ct_ft->nf_ft.flow_block_lock); + list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) { + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + } + up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); module_put(THIS_MODULE); From 7cc93d888df764a13f196e3d4aef38869f7dd217 Mon Sep 17 00:00:00 2001 From: Louis Peens Date: Fri, 2 Jul 2021 11:21:39 +0200 Subject: [PATCH 088/426] nfp: flower-ct: remove callback delete deadlock The current location of the callback delete can lead to a race condition where deleting the callback requires a write_lock on the nf_table, but at the same time another thread from netfilter could have taken a read lock on the table before trying to offload. Since the driver is taking a rtnl_lock this can lead into a deadlock situation, where the netfilter offload will wait for the cls_flower rtnl_lock to be released, but this cannot happen since this is waiting for the nf_table read_lock to be released before it can delete the callback. Solve this by completely removing the nf_flow_table_offload_del_cb call, as this will now be cleaned up by act_ct itself when cleaning up the specific nf_table. Fixes: 62268e78145f ("nfp: flower-ct: add nft callback stubs") Signed-off-by: Louis Peens Signed-off-by: Yinjun Zhang Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/netronome/nfp/flower/conntrack.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index 273d529d43c2..128020b1573e 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -1141,20 +1141,7 @@ int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent) nfp_fl_ct_clean_flow_entry(ct_entry); kfree(ct_map_ent); - /* If this is the last pre_ct_rule it means that it is - * very likely that the nft table will be cleaned up next, - * as this happens on the removal of the last act_ct flow. - * However we cannot deregister the callback on the removal - * of the last nft flow as this runs into a deadlock situation. - * So deregister the callback on removal of the last pre_ct flow - * and remove any remaining nft flow entries. We also cannot - * save this state and delete the callback later since the - * nft table would already have been freed at that time. - */ if (!zt->pre_ct_count) { - nf_flow_table_offload_del_cb(zt->nft, - nfp_fl_ct_handle_nft_flow, - zt); zt->nft = NULL; nfp_fl_ct_clean_nft_entries(zt); } From b22580233d473dbf7bbfa4f6549c09e2c80e9e64 Mon Sep 17 00:00:00 2001 From: Ronak Doshi Date: Thu, 1 Jul 2021 23:44:27 -0700 Subject: [PATCH 089/426] vmxnet3: fix cksum offload issues for tunnels with non-default udp ports Commit dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload support") added support for encapsulation offload. However, the inner offload capability is to be restricted to UDP tunnels with default Vxlan and Geneve ports. This patch fixes the issue for tunnels with non-default ports using features check capability and filtering appropriate features for such tunnels. Fixes: dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload support") Signed-off-by: Ronak Doshi Acked-by: Guolin Yang Signed-off-by: David S. Miller --- drivers/net/vmxnet3/vmxnet3_ethtool.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index c0bd9cbc43b1..1b483cf2b1ca 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -1,7 +1,7 @@ /* * Linux driver for VMware's vmxnet3 ethernet NIC. * - * Copyright (C) 2008-2020, VMware, Inc. All Rights Reserved. + * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -26,6 +26,10 @@ #include "vmxnet3_int.h" +#include +#include + +#define VXLAN_UDP_PORT 8472 struct vmxnet3_stat_desc { char desc[ETH_GSTRING_LEN]; @@ -262,6 +266,8 @@ netdev_features_t vmxnet3_features_check(struct sk_buff *skb, if (VMXNET3_VERSION_GE_4(adapter) && skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) { u8 l4_proto = 0; + u16 port; + struct udphdr *udph; switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): @@ -274,8 +280,20 @@ netdev_features_t vmxnet3_features_check(struct sk_buff *skb, return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } - if (l4_proto != IPPROTO_UDP) + switch (l4_proto) { + case IPPROTO_UDP: + udph = udp_hdr(skb); + port = be16_to_cpu(udph->dest); + /* Check if offloaded port is supported */ + if (port != GENEVE_UDP_PORT && + port != IANA_VXLAN_UDP_PORT && + port != VXLAN_UDP_PORT) { + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + break; + default: return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } } return features; } From b43c8909be52f2baca8884f967b418a88424494a Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 3 Jul 2021 00:38:43 +0200 Subject: [PATCH 090/426] udp: properly flush normal packet at GRO time If an UDP packet enters the GRO engine but is not eligible for aggregation and is not targeting an UDP tunnel, udp_gro_receive() will not set the flush bit, and packet could delayed till the next napi flush. Fix the issue ensuring non GROed packets traverse skb_gro_flush_final(). Reported-and-tested-by: Matthias Treydte Fixes: 18f25dc39990 ("udp: skip L4 aggregation for UDP tunnel packets") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/ipv4/udp_offload.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 54e06b88af69..9dde1e5fb449 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -525,8 +525,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) - pp = call_gro_receive(udp_gro_receive_segment, head, skb); - return pp; + return call_gro_receive(udp_gro_receive_segment, head, skb); + + /* no GRO, be sure flush the current packet */ + goto out; } if (NAPI_GRO_CB(skb)->encap_mark || From 6ff63a150b5556012589ae59efac1b5eeb7d32c3 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 3 Jul 2021 21:17:27 +0200 Subject: [PATCH 091/426] net: marvell: always set skb_shared_info in mvneta_swbm_add_rx_fragment Always set skb_shared_info data structure in mvneta_swbm_add_rx_fragment routine even if the fragment contains only the ethernet FCS. Fixes: 039fbc47f9f1 ("net: mvneta: alloc skb_shared_info on the mvneta_rx_swbm stack") Signed-off-by: Lorenzo Bianconi Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 361bc4fbe20b..76a7777c746d 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2299,19 +2299,19 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, skb_frag_off_set(frag, pp->rx_offset_correction); skb_frag_size_set(frag, data_len); __skb_frag_set_page(frag, page); - - /* last fragment */ - if (len == *size) { - struct skb_shared_info *sinfo; - - sinfo = xdp_get_shared_info_from_buff(xdp); - sinfo->nr_frags = xdp_sinfo->nr_frags; - memcpy(sinfo->frags, xdp_sinfo->frags, - sinfo->nr_frags * sizeof(skb_frag_t)); - } } else { page_pool_put_full_page(rxq->page_pool, page, true); } + + /* last fragment */ + if (len == *size) { + struct skb_shared_info *sinfo; + + sinfo = xdp_get_shared_info_from_buff(xdp); + sinfo->nr_frags = xdp_sinfo->nr_frags; + memcpy(sinfo->frags, xdp_sinfo->frags, + sinfo->nr_frags * sizeof(skb_frag_t)); + } *size -= len; } From 55eac20617ca84129273ab248f4d7bfe456967de Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 5 Jul 2021 16:53:06 +0800 Subject: [PATCH 092/426] ptp: fix NULL pointer dereference in ptp_clock_register Fix NULL pointer dereference in ptp_clock_register. The argument "parent" of ptp_clock_register may be NULL pointer. Fixes: 73f37068d540 ("ptp: support ptp physical/virtual clocks conversion") Reported-by: kernel test robot Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index f012fa581cf4..ce6d9fc85607 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -236,7 +236,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } /* PTP virtual clock is being registered under physical clock */ - if (parent->class && parent->class->name && + if (parent && parent->class && parent->class->name && strcmp(parent->class->name, "ptp") == 0) ptp->is_virtual_clock = true; From f6a175cfcc8df578adfdf06b05c82b3b8c8b5cfd Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 5 Jul 2021 17:46:17 +0800 Subject: [PATCH 093/426] ptp: fix format string mismatch in ptp_sysfs.c Fix format string mismatch in ptp_sysfs.c. Use %u for unsigned int. Fixes: 73f37068d540 ("ptp: support ptp physical/virtual clocks conversion") Reported-by: kernel test robot Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_sysfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index 6a36590ca77a..b3d96b747292 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -179,7 +179,7 @@ static ssize_t n_vclocks_show(struct device *dev, if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) return -ERESTARTSYS; - size = snprintf(page, PAGE_SIZE - 1, "%d\n", ptp->n_vclocks); + size = snprintf(page, PAGE_SIZE - 1, "%u\n", ptp->n_vclocks); mutex_unlock(&ptp->n_vclocks_mux); @@ -252,7 +252,7 @@ static ssize_t max_vclocks_show(struct device *dev, struct ptp_clock *ptp = dev_get_drvdata(dev); ssize_t size; - size = snprintf(page, PAGE_SIZE - 1, "%d\n", ptp->max_vclocks); + size = snprintf(page, PAGE_SIZE - 1, "%u\n", ptp->max_vclocks); return size; } From 81c52c42afd92b741289208c65e5063b9e23ffb4 Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Mon, 5 Jul 2021 18:26:53 +0800 Subject: [PATCH 094/426] net: stmmac: separate the tas basetime calculation function Separate the TAS basetime calculation function so that it can be called by other functions. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 3 ++ .../net/ethernet/stmicro/stmmac/stmmac_tc.c | 38 ++++++++++++------- 2 files changed, 28 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index e735134e8487..fcdb1d20389b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -349,6 +349,9 @@ void stmmac_enable_rx_queue(struct stmmac_priv *priv, u32 queue); void stmmac_disable_tx_queue(struct stmmac_priv *priv, u32 queue); void stmmac_enable_tx_queue(struct stmmac_priv *priv, u32 queue); int stmmac_xsk_wakeup(struct net_device *dev, u32 queue, u32 flags); +struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time, + ktime_t current_time, + u64 cycle_time); #if IS_ENABLED(CONFIG_STMMAC_SELFTESTS) void stmmac_selftest_run(struct net_device *dev, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 92dab609d4f8..596626c71189 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -711,6 +711,29 @@ static int tc_setup_cls(struct stmmac_priv *priv, return ret; } +struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time, + ktime_t current_time, + u64 cycle_time) +{ + struct timespec64 time; + + if (ktime_after(old_base_time, current_time)) { + time = ktime_to_timespec64(old_base_time); + } else { + s64 n; + ktime_t base_time; + + n = div64_s64(ktime_sub_ns(current_time, old_base_time), + cycle_time); + base_time = ktime_add_ns(old_base_time, + (n + 1) * cycle_time); + + time = ktime_to_timespec64(base_time); + } + + return time; +} + static int tc_setup_taprio(struct stmmac_priv *priv, struct tc_taprio_qopt_offload *qopt) { @@ -814,19 +837,8 @@ static int tc_setup_taprio(struct stmmac_priv *priv, /* Adjust for real system time */ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time); current_time_ns = timespec64_to_ktime(current_time); - if (ktime_after(qopt->base_time, current_time_ns)) { - time = ktime_to_timespec64(qopt->base_time); - } else { - ktime_t base_time; - s64 n; - - n = div64_s64(ktime_sub_ns(current_time_ns, qopt->base_time), - qopt->cycle_time); - base_time = ktime_add_ns(qopt->base_time, - (n + 1) * qopt->cycle_time); - - time = ktime_to_timespec64(base_time); - } + time = stmmac_calc_tas_basetime(qopt->base_time, current_time_ns, + qopt->cycle_time); priv->plat->est->btr[0] = (u32)time.tv_nsec; priv->plat->est->btr[1] = (u32)time.tv_sec; From b2aae654a4794ef898ad33a179f341eb610f6b85 Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Mon, 5 Jul 2021 18:26:54 +0800 Subject: [PATCH 095/426] net: stmmac: add mutex lock to protect est parameters Add a mutex lock to protect est structure parameters so that the EST parameters can be updated by other threads. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 12 +++++++++++- include/linux/stmmac.h | 1 + 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 596626c71189..2e3cdf540168 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -796,14 +796,18 @@ static int tc_setup_taprio(struct stmmac_priv *priv, GFP_KERNEL); if (!plat->est) return -ENOMEM; + + mutex_init(&priv->plat->est->lock); } else { memset(plat->est, 0, sizeof(*plat->est)); } size = qopt->num_entries; + mutex_lock(&priv->plat->est->lock); priv->plat->est->gcl_size = size; priv->plat->est->enable = qopt->enable; + mutex_unlock(&priv->plat->est->lock); for (i = 0; i < size; i++) { s64 delta_ns = qopt->entries[i].interval; @@ -834,6 +838,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->gcl[i] = delta_ns | (gates << wid); } + mutex_lock(&priv->plat->est->lock); /* Adjust for real system time */ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time); current_time_ns = timespec64_to_ktime(current_time); @@ -847,8 +852,10 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC); priv->plat->est->ctr[1] = (u32)ctr; - if (fpe && !priv->dma_cap.fpesel) + if (fpe && !priv->dma_cap.fpesel) { + mutex_unlock(&priv->plat->est->lock); return -EOPNOTSUPP; + } /* Actual FPE register configuration will be done after FPE handshake * is success. @@ -857,6 +864,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); if (ret) { netdev_err(priv->dev, "failed to configure EST\n"); goto disable; @@ -872,9 +880,11 @@ static int tc_setup_taprio(struct stmmac_priv *priv, return 0; disable: + mutex_lock(&priv->plat->est->lock); priv->plat->est->enable = false; stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); priv->plat->fpe_cfg->enable = false; stmmac_fpe_configure(priv, priv->ioaddr, diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index d5ae621d66ba..09157b8a5810 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -115,6 +115,7 @@ struct stmmac_axi { #define EST_GCL 1024 struct stmmac_est { + struct mutex lock; int enable; u32 btr_offset[2]; u32 btr[2]; From e9e3720002f61cd637a49ecafae77cac230eefae Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Mon, 5 Jul 2021 18:26:55 +0800 Subject: [PATCH 096/426] net: stmmac: ptp: update tas basetime after ptp adjust After adjusting the ptp time, the Qbv base time may be the past time of the new current time. dwmac5 hardware limited the base time cannot be set as past time. This patch add a btr_reserve to store the base time get from qopt, then calculate the base time and reset the Qbv configuration after ptp time adjust. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/stmmac_ptp.c | 41 ++++++++++++++++++- .../net/ethernet/stmicro/stmmac/stmmac_tc.c | 6 ++- include/linux/stmmac.h | 1 + 3 files changed, 46 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 4e86cdf2bc9f..580cc035536b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -62,7 +62,8 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) u32 sec, nsec; u32 quotient, reminder; int neg_adj = 0; - bool xmac; + bool xmac, est_rst = false; + int ret; xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; @@ -75,10 +76,48 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) sec = quotient; nsec = reminder; + /* If EST is enabled, disabled it before adjust ptp time. */ + if (priv->plat->est && priv->plat->est->enable) { + est_rst = true; + mutex_lock(&priv->plat->est->lock); + priv->plat->est->enable = false; + stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, + priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); + } + spin_lock_irqsave(&priv->ptp_lock, flags); stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj, xmac); spin_unlock_irqrestore(&priv->ptp_lock, flags); + /* Caculate new basetime and re-configured EST after PTP time adjust. */ + if (est_rst) { + struct timespec64 current_time, time; + ktime_t current_time_ns, basetime; + u64 cycle_time; + + mutex_lock(&priv->plat->est->lock); + priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time); + current_time_ns = timespec64_to_ktime(current_time); + time.tv_nsec = priv->plat->est->btr_reserve[0]; + time.tv_sec = priv->plat->est->btr_reserve[1]; + basetime = timespec64_to_ktime(time); + cycle_time = priv->plat->est->ctr[1] * NSEC_PER_SEC + + priv->plat->est->ctr[0]; + time = stmmac_calc_tas_basetime(basetime, + current_time_ns, + cycle_time); + + priv->plat->est->btr[0] = (u32)time.tv_nsec; + priv->plat->est->btr[1] = (u32)time.tv_sec; + priv->plat->est->enable = true; + ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, + priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); + if (ret) + netdev_err(priv->dev, "failed to configure EST\n"); + } + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 2e3cdf540168..4f3b6437b114 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -739,7 +739,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, { u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep; struct plat_stmmacenet_data *plat = priv->plat; - struct timespec64 time, current_time; + struct timespec64 time, current_time, qopt_time; ktime_t current_time_ns; bool fpe = false; int i, ret = 0; @@ -848,6 +848,10 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->btr[0] = (u32)time.tv_nsec; priv->plat->est->btr[1] = (u32)time.tv_sec; + qopt_time = ktime_to_timespec64(qopt->base_time); + priv->plat->est->btr_reserve[0] = (u32)qopt_time.tv_nsec; + priv->plat->est->btr_reserve[1] = (u32)qopt_time.tv_sec; + ctr = qopt->cycle_time; priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC); priv->plat->est->ctr[1] = (u32)ctr; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 09157b8a5810..a6f03b36fc4f 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -117,6 +117,7 @@ struct stmmac_axi { struct stmmac_est { struct mutex lock; int enable; + u32 btr_reserve[2]; u32 btr_offset[2]; u32 btr[2]; u32 ctr[2]; From 5a0ae9872d5cb5f27590eed168d4b3b144350ed7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Mon, 5 Jul 2021 12:38:41 +0200 Subject: [PATCH 097/426] bpf, samples: Add -fno-asynchronous-unwind-tables to BPF Clang invocation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The samples/bpf Makefile currently compiles BPF files in a way that will produce an .eh_frame section, which will in turn confuse libbpf and produce errors when loading BPF programs, like: libbpf: elf: skipping unrecognized data section(32) .eh_frame libbpf: elf: skipping relo section(33) .rel.eh_frame for section(32) .eh_frame Fix this by instruction Clang not to produce this section, as it's useless for BPF anyway. Suggested-by: Daniel Borkmann Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210705103841.180260-1-toke@redhat.com --- samples/bpf/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 520434ea966f..036998d11ded 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -331,6 +331,7 @@ $(obj)/%.o: $(src)/%.c -Wno-gnu-variable-sized-type-not-at-end \ -Wno-address-of-packed-member -Wno-tautological-compare \ -Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \ + -fno-asynchronous-unwind-tables \ -I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \ -O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \ $(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \ From 2620e92ae6ed83260eb46d214554cd308ee35d92 Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Mon, 28 Jun 2021 17:18:15 +0800 Subject: [PATCH 098/426] bpf, samples: Fix xdpsock with '-M' parameter missing unload process Execute the following command and exit, then execute it again, the following error will be reported: $ sudo ./samples/bpf/xdpsock -i ens4f2 -M ^C $ sudo ./samples/bpf/xdpsock -i ens4f2 -M libbpf: elf: skipping unrecognized data section(16) .eh_frame libbpf: elf: skipping relo section(17) .rel.eh_frame for section(16) .eh_frame libbpf: Kernel error message: XDP program already attached ERROR: link set xdp fd failed Commit c9d27c9e8dc7 ("samples: bpf: Do not unload prog within xdpsock") removed the unloading prog code because of the presence of bpf_link. This is fine if XDP_SHARED_UMEM is disabled, but if it is enabled, unloading the prog is still needed. Fixes: c9d27c9e8dc7 ("samples: bpf: Do not unload prog within xdpsock") Signed-off-by: Wang Hai Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Cc: Maciej Fijalkowski Link: https://lore.kernel.org/bpf/20210628091815.2373487-1-wanghai38@huawei.com --- samples/bpf/xdpsock_user.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 53e300f860bb..33d0bdebbed8 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -96,6 +96,7 @@ static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; static int opt_timeout = 1000; static bool opt_need_wakeup = true; static u32 opt_num_xsks = 1; +static u32 prog_id; static bool opt_busy_poll; static bool opt_reduced_cap; @@ -461,6 +462,23 @@ static void *poller(void *arg) return NULL; } +static void remove_xdp_program(void) +{ + u32 curr_prog_id = 0; + + if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(EXIT_FAILURE); + } + + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given interface\n"); + else + printf("program on interface changed, not removing\n"); +} + static void int_exit(int sig) { benchmark_done = true; @@ -471,6 +489,9 @@ static void __exit_with_error(int error, const char *file, const char *func, { fprintf(stderr, "%s:%s:%i: errno: %d/\"%s\"\n", file, func, line, error, strerror(error)); + + if (opt_num_xsks > 1) + remove_xdp_program(); exit(EXIT_FAILURE); } @@ -490,6 +511,9 @@ static void xdpsock_cleanup(void) if (write(sock, &cmd, sizeof(int)) < 0) exit_with_error(errno); } + + if (opt_num_xsks > 1) + remove_xdp_program(); } static void swap_mac_addresses(void *data) @@ -857,6 +881,10 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, if (ret) exit_with_error(-ret); + ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags); + if (ret) + exit_with_error(-ret); + xsk->app_stats.rx_empty_polls = 0; xsk->app_stats.fill_fail_polls = 0; xsk->app_stats.copy_tx_sendtos = 0; From bc832065b60f973771ff3e657214bb21b559833c Mon Sep 17 00:00:00 2001 From: Gu Shengxian Date: Mon, 5 Jul 2021 18:35:43 -0700 Subject: [PATCH 099/426] bpftool: Properly close va_list 'ap' by va_end() on error va_list 'ap' was opened but not closed by va_end() in error case. It should be closed by va_end() before the return. Fixes: aa52bcbe0e72 ("tools: bpftool: Fix json dump crash on powerpc") Signed-off-by: Gu Shengxian Signed-off-by: Daniel Borkmann Cc: Jiri Olsa Link: https://lore.kernel.org/bpf/20210706013543.671114-1-gushengxian507419@gmail.com --- tools/bpf/bpftool/jit_disasm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index e7e7eee9f172..24734f2249d6 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -43,11 +43,13 @@ static int fprintf_json(void *out, const char *fmt, ...) { va_list ap; char *s; + int err; va_start(ap, fmt); - if (vasprintf(&s, fmt, ap) < 0) - return -1; + err = vasprintf(&s, fmt, ap); va_end(ap); + if (err < 0) + return -1; if (!oper_count) { int i; From fb5dad4084f0ea6b6df5fe90f157531ca6e20681 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 8 Jun 2021 14:39:54 +0200 Subject: [PATCH 100/426] KVM: selftests: introduce P44V64 for z196 and EC12 Older machines like z196 and zEC12 do only support 44 bits of physical addresses. Make this the default and check via IBC if we are on a later machine. We then add P47V64 as an additional model. Reviewed-by: David Hildenbrand Reviewed-by: Thomas Huth Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger Link: https://lore.kernel.org/kvm/20210701153853.33063-1-borntraeger@de.ibm.com/ Fixes: 1bc603af73dd ("KVM: selftests: introduce P47V64 for s390x") --- tools/testing/selftests/kvm/include/kvm_util.h | 3 ++- tools/testing/selftests/kvm/lib/guest_modes.c | 16 ++++++++++++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 5 +++++ 3 files changed, 23 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 35739567189e..74d73532fce9 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -44,6 +44,7 @@ enum vm_guest_mode { VM_MODE_P40V48_64K, VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ VM_MODE_P47V64_4K, + VM_MODE_P44V64_4K, NUM_VM_MODES, }; @@ -61,7 +62,7 @@ enum vm_guest_mode { #elif defined(__s390x__) -#define VM_MODE_DEFAULT VM_MODE_P47V64_4K +#define VM_MODE_DEFAULT VM_MODE_P44V64_4K #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 16) diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index 25bff307c71f..c330f414ef96 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -22,6 +22,22 @@ void guest_modes_append_default(void) } } #endif +#ifdef __s390x__ + { + int kvm_fd, vm_fd; + struct kvm_s390_vm_cpu_processor info; + + kvm_fd = open_kvm_dev_path_or_exit(); + vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, 0); + kvm_device_access(vm_fd, KVM_S390_VM_CPU_MODEL, + KVM_S390_VM_CPU_PROCESSOR, &info, false); + close(vm_fd); + close(kvm_fd); + /* Starting with z13 we have 47bits of physical address */ + if (info.ibc >= 0x30) + guest_mode_append(VM_MODE_P47V64_4K, true, true); + } +#endif } void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index a2b732cf96ea..8606000c439e 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -176,6 +176,7 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", + [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); @@ -194,6 +195,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { { 40, 48, 0x10000, 16 }, { 0, 0, 0x1000, 12 }, { 47, 64, 0x1000, 12 }, + { 44, 64, 0x1000, 12 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -282,6 +284,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) case VM_MODE_P47V64_4K: vm->pgtable_levels = 5; break; + case VM_MODE_P44V64_4K: + vm->pgtable_levels = 5; + break; default: TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); } From cd4220d23bf3f43cf720e82bdee681f383433ae2 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 1 Jul 2021 17:42:24 +0200 Subject: [PATCH 101/426] KVM: selftests: do not require 64GB in set_memory_region_test Unless the user sets overcommit_memory or has plenty of swap, the latest changes to the testcase will result in ENOMEM failures for hosts with less than 64GB RAM. As we do not use much of the allocated memory, we can use MAP_NORESERVE to avoid this error. Cc: Zenghui Yu Cc: vkuznets@redhat.com Cc: wanghaibin.wang@huawei.com Cc: stable@vger.kernel.org Fixes: 309505dd5685 ("KVM: selftests: Fix mapping length truncation in m{,un}map()") Tested-by: Zenghui Yu Link: https://lore.kernel.org/kvm/20210701160425.33666-1-borntraeger@de.ibm.com/ Signed-off-by: Christian Borntraeger --- tools/testing/selftests/kvm/set_memory_region_test.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index d8812f27648c..d31f54ac4e98 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -377,7 +377,8 @@ static void test_add_max_memory_regions(void) (max_mem_slots - 1), MEM_REGION_SIZE >> 10); mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment, - PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0); TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host"); mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1)); From c4edc3ccbc63947e697bd2e30afca8bfaa144998 Mon Sep 17 00:00:00 2001 From: Ali Abdallah Date: Thu, 20 May 2021 12:53:11 +0200 Subject: [PATCH 102/426] netfilter: conntrack: improve RST handling when tuple is re-used If we receive a SYN packet in original direction on an existing connection tracking entry, we let this SYN through because conntrack might be out-of-sync. Conntrack gets back in sync when server responds with SYN/ACK and state gets updated accordingly. However, if server replies with RST, this packet might be marked as INVALID because td_maxack value reflects the *old* conntrack state and not the state of the originator of the RST. Avoid td_maxack-based checks if previous packet was a SYN. Unfortunately that is not be enough: an out of order ACK in original direction updates last_index, so we still end up marking valid RST. Thus disable the sequence check when we are not in established state and the received RST has a sequence of 0. Because marking RSTs as invalid usually leads to unwanted timeouts, also skip RST sequence checks if a conntrack entry is already closing. Such entries can already be evicted via GC in case the table is full. Co-developed-by: Florian Westphal Signed-off-by: Florian Westphal Signed-off-by: Ali Abdallah Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_tcp.c | 53 +++++++++++++++++--------- 1 file changed, 36 insertions(+), 17 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index eb4de92077a8..b8ff67671e93 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -823,6 +823,22 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; } +static bool tcp_can_early_drop(const struct nf_conn *ct) +{ + switch (ct->proto.tcp.state) { + case TCP_CONNTRACK_FIN_WAIT: + case TCP_CONNTRACK_LAST_ACK: + case TCP_CONNTRACK_TIME_WAIT: + case TCP_CONNTRACK_CLOSE: + case TCP_CONNTRACK_CLOSE_WAIT: + return true; + default: + break; + } + + return false; +} + /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_tcp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -1030,9 +1046,28 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, if (index != TCP_RST_SET) break; - if (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) { + /* If we are closing, tuple might have been re-used already. + * last_index, last_ack, and all other ct fields used for + * sequence/window validation are outdated in that case. + * + * As the conntrack can already be expired by GC under pressure, + * just skip validation checks. + */ + if (tcp_can_early_drop(ct)) + goto in_window; + + /* td_maxack might be outdated if we let a SYN through earlier */ + if ((ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) && + ct->proto.tcp.last_index != TCP_SYN_SET) { u32 seq = ntohl(th->seq); + /* If we are not in established state and SEQ=0 this is most + * likely an answer to a SYN we let go through above (last_index + * can be updated due to out-of-order ACKs). + */ + if (seq == 0 && !nf_conntrack_tcp_established(ct)) + break; + if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) { /* Invalid RST */ spin_unlock_bh(&ct->lock); @@ -1165,22 +1200,6 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, return NF_ACCEPT; } -static bool tcp_can_early_drop(const struct nf_conn *ct) -{ - switch (ct->proto.tcp.state) { - case TCP_CONNTRACK_FIN_WAIT: - case TCP_CONNTRACK_LAST_ACK: - case TCP_CONNTRACK_TIME_WAIT: - case TCP_CONNTRACK_CLOSE: - case TCP_CONNTRACK_CLOSE_WAIT: - return true; - default: - break; - } - - return false; -} - #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include From 1da4cd82dd180224503e745ccf3220e3490d8897 Mon Sep 17 00:00:00 2001 From: Ali Abdallah Date: Thu, 27 May 2021 09:19:06 +0200 Subject: [PATCH 103/426] netfilter: conntrack: add new sysctl to disable RST check This patch adds a new sysctl tcp_ignore_invalid_rst to disable marking out of segments RSTs as INVALID. Signed-off-by: Ali Abdallah Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/nf_conntrack-sysctl.rst | 6 ++++++ include/net/netns/conntrack.h | 1 + net/netfilter/nf_conntrack_proto_tcp.c | 6 +++++- net/netfilter/nf_conntrack_standalone.c | 10 ++++++++++ 4 files changed, 22 insertions(+), 1 deletion(-) diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index 0467b30e4abe..d31ed6c1cb0d 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -110,6 +110,12 @@ nf_conntrack_tcp_be_liberal - BOOLEAN Be conservative in what you do, be liberal in what you accept from others. If it's non-zero, we mark only out of window RST segments as INVALID. +nf_conntrack_tcp_ignore_invalid_rst - BOOLEAN + - 0 - disabled (default) + - 1 - enabled + + If it's 1, we don't mark out of window RST segments as INVALID. + nf_conntrack_tcp_loose - BOOLEAN - 0 - disabled - not 0 - enabled (default) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index c3094b83a525..37e5300c7e5a 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -27,6 +27,7 @@ struct nf_tcp_net { u8 tcp_loose; u8 tcp_be_liberal; u8 tcp_max_retrans; + u8 tcp_ignore_invalid_rst; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) unsigned int offload_timeout; unsigned int offload_pickup; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index b8ff67671e93..3259416f2ea4 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1068,7 +1068,8 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, if (seq == 0 && !nf_conntrack_tcp_established(ct)) break; - if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) { + if (before(seq, ct->proto.tcp.seen[!dir].td_maxack) && + !tn->tcp_ignore_invalid_rst) { /* Invalid RST */ spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst"); @@ -1466,6 +1467,9 @@ void nf_conntrack_tcp_init_net(struct net *net) */ tn->tcp_be_liberal = 0; + /* If it's non-zero, we turn off RST sequence number check */ + tn->tcp_ignore_invalid_rst = 0; + /* Max number of the retransmitted packets without receiving an (acceptable) * ACK from the destination. If this number is reached, a shorter timer * will be started. diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index f57a951c9b5e..214d9f9e499b 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -579,6 +579,7 @@ enum nf_ct_sysctl_index { #endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, + NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST, NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, @@ -798,6 +799,14 @@ static struct ctl_table nf_ct_sysctl_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + [NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST] = { + .procname = "nf_conntrack_tcp_ignore_invalid_rst", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, [NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = { .procname = "nf_conntrack_tcp_max_retrans", .maxlen = sizeof(u8), @@ -1004,6 +1013,7 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, XASSIGN(LOOSE, &tn->tcp_loose); XASSIGN(LIBERAL, &tn->tcp_be_liberal); XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans); + XASSIGN(IGNORE_INVALID_RST, &tn->tcp_ignore_invalid_rst); #undef XASSIGN #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) From cf4466ea47db891be785f867ca7f99e0cd9898c6 Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Sun, 27 Jun 2021 18:19:18 +0200 Subject: [PATCH 104/426] netfilter: conntrack: Mark access for KCSAN KCSAN detected an data race with ipc/sem.c that is intentional. As nf_conntrack_lock() uses the same algorithm: Update nf_conntrack_core as well: nf_conntrack_lock() contains a1) spin_lock() a2) smp_load_acquire(nf_conntrack_locks_all). a1) actually accesses one lock from an array of locks. nf_conntrack_locks_all() contains b1) nf_conntrack_locks_all=true (normal write) b2) spin_lock() b3) spin_unlock() b2 and b3 are done for every lock. This guarantees that nf_conntrack_locks_all() prevents any concurrent nf_conntrack_lock() owners: If a thread past a1), then b2) will block until that thread releases the lock. If the threat is before a1, then b3)+a1) ensure the write b1) is visible, thus a2) is guaranteed to see the updated value. But: This is only the latest time when b1) becomes visible. It may also happen that b1) is visible an undefined amount of time before the b3). And thus KCSAN will notice a data race. In addition, the compiler might be too clever. Solution: Use WRITE_ONCE(). Signed-off-by: Manfred Spraul Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 085a11f1eb43..83c52df85870 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -149,7 +149,15 @@ static void nf_conntrack_all_lock(void) spin_lock(&nf_conntrack_locks_all_lock); - nf_conntrack_locks_all = true; + /* For nf_contrack_locks_all, only the latest time when another + * CPU will see an update is controlled, by the "release" of the + * spin_lock below. + * The earliest time is not controlled, an thus KCSAN could detect + * a race when nf_conntract_lock() reads the variable. + * WRITE_ONCE() is used to ensure the compiler will not + * optimize the write. + */ + WRITE_ONCE(nf_conntrack_locks_all, true); for (i = 0; i < CONNTRACK_LOCKS; i++) { spin_lock(&nf_conntrack_locks[i]); From 6ac4bac4ce48604cf0f4b04d61884552520ca55e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 5 Jul 2021 17:45:36 +0200 Subject: [PATCH 105/426] netfilter: nft_last: honor NFTA_LAST_SET on restoration NFTA_LAST_SET tells us if this expression has ever seen a packet, do not ignore this attribute when restoring the ruleset. Fixes: 836382dc2471 ("netfilter: nf_tables: add last expression") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_last.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 913ac45167f2..bbb352b64c73 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -23,15 +23,21 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, { struct nft_last_priv *priv = nft_expr_priv(expr); u64 last_jiffies; + u32 last_set = 0; int err; - if (tb[NFTA_LAST_MSECS]) { + if (tb[NFTA_LAST_SET]) { + last_set = ntohl(nla_get_be32(tb[NFTA_LAST_SET])); + if (last_set == 1) + priv->last_set = 1; + } + + if (last_set && tb[NFTA_LAST_MSECS]) { err = nf_msecs_to_jiffies64(tb[NFTA_LAST_MSECS], &last_jiffies); if (err < 0) return err; priv->last_jiffies = jiffies + (unsigned long)last_jiffies; - priv->last_set = 1; } return 0; From d1b5b80da7058883758df2b5b7f506d4d4f9a5fa Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 5 Jul 2021 20:14:21 +0200 Subject: [PATCH 106/426] netfilter: nft_last: incorrect arithmetics when restoring last used Subtract the jiffies that have passed by to current jiffies to fix last used restoration. Fixes: 836382dc2471 ("netfilter: nf_tables: add last expression") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_last.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index bbb352b64c73..8088b99f2ee3 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -37,7 +37,7 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; - priv->last_jiffies = jiffies + (unsigned long)last_jiffies; + priv->last_jiffies = jiffies - (unsigned long)last_jiffies; } return 0; From 8550ff8d8c75416e984d9c4b082845e57e560984 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Mon, 5 Jul 2021 13:54:51 +0300 Subject: [PATCH 107/426] skbuff: Release nfct refcount on napi stolen or re-used skbs When multiple SKBs are merged to a new skb under napi GRO, or SKB is re-used by napi, if nfct was set for them in the driver, it will not be released while freeing their stolen head state or on re-use. Release nfct on napi's stolen or re-used SKBs, and in gro_list_prepare, check conntrack metadata diff. Fixes: 5c6b94604744 ("net/mlx5e: CT: Handle misses after executing CT action") Reviewed-by: Roi Dayan Signed-off-by: Paul Blakey Signed-off-by: David S. Miller --- net/core/dev.c | 13 +++++++++++++ net/core/skbuff.c | 1 + 2 files changed, 14 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index c253c2aafe97..177a5aec0b6b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6008,6 +6008,18 @@ static void gro_list_prepare(const struct list_head *head, diffs = memcmp(skb_mac_header(p), skb_mac_header(skb), maclen); + + diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); + + if (!diffs) { + struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT); + struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT); + + diffs |= (!!p_ext) ^ (!!skb_ext); + if (!diffs && unlikely(skb_ext)) + diffs |= p_ext->chain ^ skb_ext->chain; + } + NAPI_GRO_CB(p)->same_flow = !diffs; } } @@ -6270,6 +6282,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); skb_ext_reset(skb); + nf_reset_ct(skb); napi->skb = skb; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 12aabcda6db2..f63de967ac25 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -943,6 +943,7 @@ void __kfree_skb_defer(struct sk_buff *skb) void napi_skb_free_stolen_head(struct sk_buff *skb) { + nf_reset_ct(skb); skb_dst_drop(skb); skb_ext_put(skb); napi_skb_cache_put(skb); From be5d1b61a2ad28c7e57fe8bfa277373e8ecffcdc Mon Sep 17 00:00:00 2001 From: Nguyen Dinh Phi Date: Tue, 6 Jul 2021 07:19:12 +0800 Subject: [PATCH 108/426] tcp: fix tcp_init_transfer() to not reset icsk_ca_initialized This commit fixes a bug (found by syzkaller) that could cause spurious double-initializations for congestion control modules, which could cause memory leaks or other problems for congestion control modules (like CDG) that allocate memory in their init functions. The buggy scenario constructed by syzkaller was something like: (1) create a TCP socket (2) initiate a TFO connect via sendto() (3) while socket is in TCP_SYN_SENT, call setsockopt(TCP_CONGESTION), which calls: tcp_set_congestion_control() -> tcp_reinit_congestion_control() -> tcp_init_congestion_control() (4) receive ACK, connection is established, call tcp_init_transfer(), set icsk_ca_initialized=0 (without first calling cc->release()), call tcp_init_congestion_control() again. Note that in this sequence tcp_init_congestion_control() is called twice without a cc->release() call in between. Thus, for CC modules that allocate memory in their init() function, e.g, CDG, a memory leak may occur. The syzkaller tool managed to find a reproducer that triggered such a leak in CDG. The bug was introduced when that commit 8919a9b31eb4 ("tcp: Only init congestion control if not initialized already") introduced icsk_ca_initialized and set icsk_ca_initialized to 0 in tcp_init_transfer(), missing the possibility for a sequence like the one above, where a process could call setsockopt(TCP_CONGESTION) in state TCP_SYN_SENT (i.e. after the connect() or TFO open sendmsg()), which would call tcp_init_congestion_control(). It did not intend to reset any initialization that the user had already explicitly made; it just missed the possibility of that particular sequence (which syzkaller managed to find). Fixes: 8919a9b31eb4 ("tcp: Only init congestion control if not initialized already") Reported-by: syzbot+f1e24a0594d4e3a895d3@syzkaller.appspotmail.com Signed-off-by: Nguyen Dinh Phi Acked-by: Neal Cardwell Tested-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e6ca5a1f3b59..a5a8d0a378b2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5922,8 +5922,8 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); tp->snd_cwnd_stamp = tcp_jiffies32; - icsk->icsk_ca_initialized = 0; bpf_skops_established(sk, bpf_op, skb); + /* Initialize congestion control unless BPF initialized it already: */ if (!icsk->icsk_ca_initialized) tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); From b648eba4c69e5819880b4907e7fcb2bb576069ab Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:06 +0000 Subject: [PATCH 109/426] bonding: fix suspicious RCU usage in bond_ipsec_add_sa() To dereference bond->curr_active_slave, it uses rcu_dereference(). But it and the caller doesn't acquire RCU so a warning occurs. So add rcu_read_lock(). Test commands: ip link add dummy0 type dummy ip link add bond0 type bond ip link set dummy0 master bond0 ip link set dummy0 up ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 \ mode transport \ reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel \ src 14.0.0.52/24 dst 14.0.0.70/24 proto tcp offload \ dev bond0 dir in Splat looks like: ============================= WARNING: suspicious RCU usage 5.13.0-rc3+ #1168 Not tainted ----------------------------- drivers/net/bonding/bond_main.c:411 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by ip/684: #0: ffffffff9a2757c0 (&net->xfrm.xfrm_cfg_mutex){+.+.}-{3:3}, at: xfrm_netlink_rcv+0x59/0x80 [xfrm_user] 55.191733][ T684] stack backtrace: CPU: 0 PID: 684 Comm: ip Not tainted 5.13.0-rc3+ #1168 Call Trace: dump_stack+0xa4/0xe5 bond_ipsec_add_sa+0x18c/0x1f0 [bonding] xfrm_dev_state_add+0x2a9/0x770 ? memcpy+0x38/0x60 xfrm_add_sa+0x2278/0x3b10 [xfrm_user] ? xfrm_get_policy+0xaa0/0xaa0 [xfrm_user] ? register_lock_class+0x1750/0x1750 xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? netlink_ack+0x9d0/0x9d0 ? netlink_deliver_tap+0x17c/0xa50 xfrm_netlink_rcv+0x68/0x80 [xfrm_user] netlink_unicast+0x41c/0x610 ? netlink_attachskb+0x710/0x710 netlink_sendmsg+0x6b9/0xb70 [ ... ] Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0ff7567bd04f..d4d718e04dcc 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -403,10 +403,12 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) struct net_device *bond_dev = xs->xso.dev; struct bonding *bond; struct slave *slave; + int err; if (!bond_dev) return -EINVAL; + rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); xs->xso.real_dev = slave->dev; @@ -415,10 +417,13 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) if (!(slave->dev->xfrmdev_ops && slave->dev->xfrmdev_ops->xdo_dev_state_add)) { slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n"); + rcu_read_unlock(); return -EINVAL; } - return slave->dev->xfrmdev_ops->xdo_dev_state_add(xs); + err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs); + rcu_read_unlock(); + return err; } /** From 105cd17a866017b45f3c45901b394c711c97bf40 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:07 +0000 Subject: [PATCH 110/426] bonding: fix null dereference in bond_ipsec_add_sa() If bond doesn't have real device, bond->curr_active_slave is null. But bond_ipsec_add_sa() dereferences bond->curr_active_slave without null checking. So, null-ptr-deref would occur. Test commands: ip link add bond0 type bond ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi \ 0x07 mode transport reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel src 14.0.0.52/24 \ dst 14.0.0.70/24 proto tcp offload dev bond0 dir in Splat looks like: KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 4 PID: 680 Comm: ip Not tainted 5.13.0-rc3+ #1168 RIP: 0010:bond_ipsec_add_sa+0xc4/0x2e0 [bonding] Code: 85 21 02 00 00 4d 8b a6 48 0c 00 00 e8 75 58 44 ce 85 c0 0f 85 14 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 e2 48 c1 ea 03 <80> 3c 02 00 0f 85 fc 01 00 00 48 8d bb e0 02 00 00 4d 8b 2c 24 48 RSP: 0018:ffff88810946f508 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff88810b4e8040 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffffffff8fe34280 RDI: ffff888115abe100 RBP: ffff88810946f528 R08: 0000000000000003 R09: fffffbfff2287e11 R10: 0000000000000001 R11: ffff888115abe0c8 R12: 0000000000000000 R13: ffffffffc0aea9a0 R14: ffff88800d7d2000 R15: ffff88810b4e8330 FS: 00007efc5552e680(0000) GS:ffff888119c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055c2530dbf40 CR3: 0000000103056004 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: xfrm_dev_state_add+0x2a9/0x770 ? memcpy+0x38/0x60 xfrm_add_sa+0x2278/0x3b10 [xfrm_user] ? xfrm_get_policy+0xaa0/0xaa0 [xfrm_user] ? register_lock_class+0x1750/0x1750 xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? netlink_ack+0x9d0/0x9d0 ? netlink_deliver_tap+0x17c/0xa50 xfrm_netlink_rcv+0x68/0x80 [xfrm_user] netlink_unicast+0x41c/0x610 ? netlink_attachskb+0x710/0x710 netlink_sendmsg+0x6b9/0xb70 [ ...] Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d4d718e04dcc..5466b24ceab6 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -411,6 +411,11 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); + if (!slave) { + rcu_read_unlock(); + return -ENODEV; + } + xs->xso.real_dev = slave->dev; bond->xs = xs; From 09adf7566d436322ced595b166dea48b06852efe Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:08 +0000 Subject: [PATCH 111/426] net: netdevsim: use xso.real_dev instead of xso.dev in callback functions of struct xfrmdev_ops There are two pointers in struct xfrm_state_offload, *dev, *real_dev. These are used in callback functions of struct xfrmdev_ops. The *dev points whether bonding interface or real interface. If bonding ipsec offload is used, it points bonding interface If not, it points real interface. And real_dev always points real interface. So, netdevsim should always use real_dev instead of dev. Of course, real_dev always not be null. Test commands: ip netns add A ip netns exec A bash modprobe netdevsim echo "1 1" > /sys/bus/netdevsim/new_device ip link add bond0 type bond mode active-backup ip link set eth0 master bond0 ip link set eth0 up ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 mode \ transport reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel src 14.0.0.52/24 \ dst 14.0.0.70/24 proto tcp offload dev bond0 dir in Splat looks like: BUG: spinlock bad magic on CPU#5, kworker/5:1/53 lock: 0xffff8881068c2cc8, .magic: 11121314, .owner: /-1, .owner_cpu: -235736076 CPU: 5 PID: 53 Comm: kworker/5:1 Not tainted 5.13.0-rc3+ #1168 Workqueue: events linkwatch_event Call Trace: dump_stack+0xa4/0xe5 do_raw_spin_lock+0x20b/0x270 ? rwlock_bug.part.1+0x90/0x90 _raw_spin_lock_nested+0x5f/0x70 bond_get_stats+0xe4/0x4c0 [bonding] ? rcu_read_lock_sched_held+0xc0/0xc0 ? bond_neigh_init+0x2c0/0x2c0 [bonding] ? dev_get_alias+0xe2/0x190 ? dev_get_port_parent_id+0x14a/0x360 ? rtnl_unregister+0x190/0x190 ? dev_get_phys_port_name+0xa0/0xa0 ? memset+0x1f/0x40 ? memcpy+0x38/0x60 ? rtnl_phys_switch_id_fill+0x91/0x100 dev_get_stats+0x8c/0x270 rtnl_fill_stats+0x44/0xbe0 ? nla_put+0xbe/0x140 rtnl_fill_ifinfo+0x1054/0x3ad0 [ ... ] Fixes: 272c2330adc9 ("xfrm: bail early on slave pass over skb") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/netdevsim/ipsec.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c index 3811f1bde84e..b80ed2ffd45e 100644 --- a/drivers/net/netdevsim/ipsec.c +++ b/drivers/net/netdevsim/ipsec.c @@ -85,7 +85,7 @@ static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { const char aes_gcm_name[] = "rfc4106(gcm(aes))"; - struct net_device *dev = xs->xso.dev; + struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; @@ -134,7 +134,7 @@ static int nsim_ipsec_add_sa(struct xfrm_state *xs) u16 sa_idx; int ret; - dev = xs->xso.dev; + dev = xs->xso.real_dev; ns = netdev_priv(dev); ipsec = &ns->ipsec; @@ -194,7 +194,7 @@ static int nsim_ipsec_add_sa(struct xfrm_state *xs) static void nsim_ipsec_del_sa(struct xfrm_state *xs) { - struct netdevsim *ns = netdev_priv(xs->xso.dev); + struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; u16 sa_idx; @@ -211,7 +211,7 @@ static void nsim_ipsec_del_sa(struct xfrm_state *xs) static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { - struct netdevsim *ns = netdev_priv(xs->xso.dev); + struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; ipsec->ok++; From 2de7e4f67599affc97132bd07e30e3bd59d0b777 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:09 +0000 Subject: [PATCH 112/426] ixgbevf: use xso.real_dev instead of xso.dev in callback functions of struct xfrmdev_ops There are two pointers in struct xfrm_state_offload, *dev, *real_dev. These are used in callback functions of struct xfrmdev_ops. The *dev points whether bonding interface or real interface. If bonding ipsec offload is used, it points bonding interface If not, it points real interface. And real_dev always points real interface. So, ixgbevf should always use real_dev instead of dev. Of course, real_dev always not be null. Test commands: ip link add bond0 type bond #eth0 is ixgbevf interface ip link set eth0 master bond0 ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 mode \ transport reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel src 14.0.0.52/24 \ dst 14.0.0.70/24 proto tcp offload dev bond0 dir in Splat looks like: KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 6 PID: 688 Comm: ip Not tainted 5.13.0-rc3+ #1168 RIP: 0010:ixgbevf_ipsec_find_empty_idx+0x28/0x1b0 [ixgbevf] Code: 00 00 0f 1f 44 00 00 55 53 48 89 fb 48 83 ec 08 40 84 f6 0f 84 9c 00 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 01 0f 8e 4c 01 00 00 66 81 3b 00 04 0f RSP: 0018:ffff8880089af390 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffff8880089af4f8 R08: 0000000000000003 R09: fffffbfff4287e11 R10: 0000000000000001 R11: ffff888005de8908 R12: 0000000000000000 R13: ffff88810936a000 R14: ffff88810936a000 R15: ffff888004d78040 FS: 00007fdf9883a680(0000) GS:ffff88811a400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055bc14adbf40 CR3: 000000000b87c005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ixgbevf_ipsec_add_sa+0x1bf/0x9c0 [ixgbevf] ? rcu_read_lock_sched_held+0x91/0xc0 ? ixgbevf_ipsec_parse_proto_keys.isra.9+0x280/0x280 [ixgbevf] ? lock_acquire+0x191/0x720 ? bond_ipsec_add_sa+0x48/0x350 [bonding] ? lockdep_hardirqs_on_prepare+0x3e0/0x3e0 ? rcu_read_lock_held+0x91/0xa0 ? rcu_read_lock_sched_held+0xc0/0xc0 bond_ipsec_add_sa+0x193/0x350 [bonding] xfrm_dev_state_add+0x2a9/0x770 ? memcpy+0x38/0x60 xfrm_add_sa+0x2278/0x3b10 [xfrm_user] ? xfrm_get_policy+0xaa0/0xaa0 [xfrm_user] ? register_lock_class+0x1750/0x1750 xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 [ ... ] Fixes: 272c2330adc9 ("xfrm: bail early on slave pass over skb") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbevf/ipsec.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index caaea2c920a6..e3e4676af9e4 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -211,7 +211,7 @@ struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec, static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { - struct net_device *dev = xs->xso.dev; + struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; @@ -260,12 +260,15 @@ static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, **/ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs) { - struct net_device *dev = xs->xso.dev; - struct ixgbevf_adapter *adapter = netdev_priv(dev); - struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct net_device *dev = xs->xso.real_dev; + struct ixgbevf_adapter *adapter; + struct ixgbevf_ipsec *ipsec; u16 sa_idx; int ret; + adapter = netdev_priv(dev); + ipsec = adapter->ipsec; + if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { netdev_err(dev, "Unsupported protocol 0x%04x for IPsec offload\n", xs->id.proto); @@ -383,11 +386,14 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs) **/ static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs) { - struct net_device *dev = xs->xso.dev; - struct ixgbevf_adapter *adapter = netdev_priv(dev); - struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct net_device *dev = xs->xso.real_dev; + struct ixgbevf_adapter *adapter; + struct ixgbevf_ipsec *ipsec; u16 sa_idx; + adapter = netdev_priv(dev); + ipsec = adapter->ipsec; + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX; From a22c39b831a081da9b2c488bd970a4412d926f30 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:10 +0000 Subject: [PATCH 113/426] bonding: fix suspicious RCU usage in bond_ipsec_del_sa() To dereference bond->curr_active_slave, it uses rcu_dereference(). But it and the caller doesn't acquire RCU so a warning occurs. So add rcu_read_lock(). Test commands: ip netns add A ip netns exec A bash modprobe netdevsim echo "1 1" > /sys/bus/netdevsim/new_device ip link add bond0 type bond ip link set eth0 master bond0 ip link set eth0 up ip link set bond0 up ip x s add proto esp dst 14.1.1.1 src 15.1.1.1 spi 0x07 mode \ transport reqid 0x07 replay-window 32 aead 'rfc4106(gcm(aes))' \ 0x44434241343332312423222114131211f4f3f2f1 128 sel src 14.0.0.52/24 \ dst 14.0.0.70/24 proto tcp offload dev bond0 dir in ip x s f Splat looks like: ============================= WARNING: suspicious RCU usage 5.13.0-rc3+ #1168 Not tainted ----------------------------- drivers/net/bonding/bond_main.c:448 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 2 locks held by ip/705: #0: ffff888106701780 (&net->xfrm.xfrm_cfg_mutex){+.+.}-{3:3}, at: xfrm_netlink_rcv+0x59/0x80 [xfrm_user] #1: ffff8880075b0098 (&x->lock){+.-.}-{2:2}, at: xfrm_state_delete+0x16/0x30 stack backtrace: CPU: 6 PID: 705 Comm: ip Not tainted 5.13.0-rc3+ #1168 Call Trace: dump_stack+0xa4/0xe5 bond_ipsec_del_sa+0x16a/0x1c0 [bonding] __xfrm_state_delete+0x51f/0x730 xfrm_state_delete+0x1e/0x30 xfrm_state_flush+0x22f/0x390 xfrm_flush_sa+0xd8/0x260 [xfrm_user] ? xfrm_flush_policy+0x290/0x290 [xfrm_user] xfrm_user_rcv_msg+0x331/0x660 [xfrm_user] ? rcu_read_lock_sched_held+0x91/0xc0 ? xfrm_user_state_lookup.constprop.39+0x320/0x320 [xfrm_user] ? find_held_lock+0x3a/0x1c0 ? mutex_lock_io_nested+0x1210/0x1210 ? sched_clock_cpu+0x18/0x170 netlink_rcv_skb+0x121/0x350 [ ... ] Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5466b24ceab6..aa9c469ebbb5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -444,21 +444,24 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) if (!bond_dev) return; + rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); if (!slave) - return; + goto out; xs->xso.real_dev = slave->dev; if (!(slave->dev->xfrmdev_ops && slave->dev->xfrmdev_ops->xdo_dev_state_delete)) { slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__); - return; + goto out; } slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs); +out: + rcu_read_unlock(); } /** From b121693381b112b78c076dea171ee113e237c0e4 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:11 +0000 Subject: [PATCH 114/426] bonding: disallow setting nested bonding + ipsec offload bonding interface can be nested and it supports ipsec offload. So, it allows setting the nested bonding + ipsec scenario. But code does not support this scenario. So, it should be disallowed. interface graph: bond2 | bond1 | eth0 The nested bonding + ipsec offload may not a real usecase. So, disallowing this scenario is fine. Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index aa9c469ebbb5..f7b89743fab9 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -419,8 +419,9 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) xs->xso.real_dev = slave->dev; bond->xs = xs; - if (!(slave->dev->xfrmdev_ops - && slave->dev->xfrmdev_ops->xdo_dev_state_add)) { + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_add || + netif_is_bond_master(slave->dev)) { slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n"); rcu_read_unlock(); return -EINVAL; @@ -453,8 +454,9 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) xs->xso.real_dev = slave->dev; - if (!(slave->dev->xfrmdev_ops - && slave->dev->xfrmdev_ops->xdo_dev_state_delete)) { + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_delete || + netif_is_bond_master(slave->dev)) { slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__); goto out; } @@ -479,8 +481,9 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) return true; - if (!(slave_dev->xfrmdev_ops - && slave_dev->xfrmdev_ops->xdo_dev_offload_ok)) { + if (!slave_dev->xfrmdev_ops || + !slave_dev->xfrmdev_ops->xdo_dev_offload_ok || + netif_is_bond_master(slave_dev)) { slave_warn(bond_dev, slave_dev, "%s: no slave xdo_dev_offload_ok\n", __func__); return false; } From 9a5605505d9c7dbfdb89cc29a8f5fc5cf9fd2334 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:12 +0000 Subject: [PATCH 115/426] bonding: Add struct bond_ipesc to manage SA bonding has been supporting ipsec offload. When SA is added, bonding just passes SA to its own active real interface. But it doesn't manage SA. So, when events(add/del real interface, active real interface change, etc) occur, bonding can't handle that well because It doesn't manage SA. So some problems(panic, UAF, refcnt leak)occur. In order to make it stable, it should manage SA. That's the reason why struct bond_ipsec is added. When a new SA is added to bonding interface, it is stored in the bond_ipsec list. And the SA is passed to a current active real interface. If events occur, it uses bond_ipsec data to handle these events. bond->ipsec_list is protected by bond->ipsec_lock. If a current active real interface is changed, the following logic works. 1. delete all SAs from old active real interface 2. Add all SAs to the new active real interface. 3. If a new active real interface doesn't support ipsec offload or SA's option, it sets real_dev to NULL. Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 139 +++++++++++++++++++++++++++----- include/net/bonding.h | 9 ++- 2 files changed, 127 insertions(+), 21 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index f7b89743fab9..165fa55cfb38 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -401,6 +401,7 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, static int bond_ipsec_add_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; + struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; int err; @@ -416,9 +417,6 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) return -ENODEV; } - xs->xso.real_dev = slave->dev; - bond->xs = xs; - if (!slave->dev->xfrmdev_ops || !slave->dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(slave->dev)) { @@ -427,11 +425,63 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) return -EINVAL; } + ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC); + if (!ipsec) { + rcu_read_unlock(); + return -ENOMEM; + } + xs->xso.real_dev = slave->dev; + err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs); + if (!err) { + ipsec->xs = xs; + INIT_LIST_HEAD(&ipsec->list); + spin_lock_bh(&bond->ipsec_lock); + list_add(&ipsec->list, &bond->ipsec_list); + spin_unlock_bh(&bond->ipsec_lock); + } else { + kfree(ipsec); + } rcu_read_unlock(); return err; } +static void bond_ipsec_add_sa_all(struct bonding *bond) +{ + struct net_device *bond_dev = bond->dev; + struct bond_ipsec *ipsec; + struct slave *slave; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (!slave) + goto out; + + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_add || + netif_is_bond_master(slave->dev)) { + spin_lock_bh(&bond->ipsec_lock); + if (!list_empty(&bond->ipsec_list)) + slave_warn(bond_dev, slave->dev, + "%s: no slave xdo_dev_state_add\n", + __func__); + spin_unlock_bh(&bond->ipsec_lock); + goto out; + } + + spin_lock_bh(&bond->ipsec_lock); + list_for_each_entry(ipsec, &bond->ipsec_list, list) { + ipsec->xs->xso.real_dev = slave->dev; + if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs)) { + slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__); + ipsec->xs->xso.real_dev = NULL; + } + } + spin_unlock_bh(&bond->ipsec_lock); +out: + rcu_read_unlock(); +} + /** * bond_ipsec_del_sa - clear out this specific SA * @xs: pointer to transformer state struct @@ -439,6 +489,7 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) static void bond_ipsec_del_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; + struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; @@ -452,7 +503,10 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) if (!slave) goto out; - xs->xso.real_dev = slave->dev; + if (!xs->xso.real_dev) + goto out; + + WARN_ON(xs->xso.real_dev != slave->dev); if (!slave->dev->xfrmdev_ops || !slave->dev->xfrmdev_ops->xdo_dev_state_delete || @@ -463,6 +517,48 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs); out: + spin_lock_bh(&bond->ipsec_lock); + list_for_each_entry(ipsec, &bond->ipsec_list, list) { + if (ipsec->xs == xs) { + list_del(&ipsec->list); + kfree(ipsec); + break; + } + } + spin_unlock_bh(&bond->ipsec_lock); + rcu_read_unlock(); +} + +static void bond_ipsec_del_sa_all(struct bonding *bond) +{ + struct net_device *bond_dev = bond->dev; + struct bond_ipsec *ipsec; + struct slave *slave; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (!slave) { + rcu_read_unlock(); + return; + } + + spin_lock_bh(&bond->ipsec_lock); + list_for_each_entry(ipsec, &bond->ipsec_list, list) { + if (!ipsec->xs->xso.real_dev) + continue; + + if (!slave->dev->xfrmdev_ops || + !slave->dev->xfrmdev_ops->xdo_dev_state_delete || + netif_is_bond_master(slave->dev)) { + slave_warn(bond_dev, slave->dev, + "%s: no slave xdo_dev_state_delete\n", + __func__); + } else { + slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs); + } + ipsec->xs->xso.real_dev = NULL; + } + spin_unlock_bh(&bond->ipsec_lock); rcu_read_unlock(); } @@ -474,22 +570,27 @@ out: static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; - struct bonding *bond = netdev_priv(bond_dev); - struct slave *curr_active = rcu_dereference(bond->curr_active_slave); - struct net_device *slave_dev = curr_active->dev; + struct net_device *real_dev; + struct slave *curr_active; + struct bonding *bond; + + bond = netdev_priv(bond_dev); + curr_active = rcu_dereference(bond->curr_active_slave); + real_dev = curr_active->dev; if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) return true; - if (!slave_dev->xfrmdev_ops || - !slave_dev->xfrmdev_ops->xdo_dev_offload_ok || - netif_is_bond_master(slave_dev)) { - slave_warn(bond_dev, slave_dev, "%s: no slave xdo_dev_offload_ok\n", __func__); + if (!xs->xso.real_dev) + return false; + + if (!real_dev->xfrmdev_ops || + !real_dev->xfrmdev_ops->xdo_dev_offload_ok || + netif_is_bond_master(real_dev)) { return false; } - xs->xso.real_dev = slave_dev; - return slave_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); + return real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); } static const struct xfrmdev_ops bond_xfrmdev_ops = { @@ -1006,8 +1107,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) return; #ifdef CONFIG_XFRM_OFFLOAD - if (old_active && bond->xs) - bond_ipsec_del_sa(bond->xs); + bond_ipsec_del_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ if (new_active) { @@ -1082,10 +1182,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) } #ifdef CONFIG_XFRM_OFFLOAD - if (new_active && bond->xs) { - xfrm_dev_state_flush(dev_net(bond->dev), bond->dev, true); - bond_ipsec_add_sa(bond->xs); - } + bond_ipsec_add_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ /* resend IGMP joins since active slave has changed or @@ -3343,6 +3440,7 @@ static int bond_master_netdev_event(unsigned long event, return bond_event_changename(event_bond); case NETDEV_UNREGISTER: bond_remove_proc_entry(event_bond); + xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true); break; case NETDEV_REGISTER: bond_create_proc_entry(event_bond); @@ -4910,7 +5008,8 @@ void bond_setup(struct net_device *bond_dev) #ifdef CONFIG_XFRM_OFFLOAD /* set up xfrm device ops (only supported in active-backup right now) */ bond_dev->xfrmdev_ops = &bond_xfrmdev_ops; - bond->xs = NULL; + INIT_LIST_HEAD(&bond->ipsec_list); + spin_lock_init(&bond->ipsec_lock); #endif /* CONFIG_XFRM_OFFLOAD */ /* don't acquire bond device's netif_tx_lock when transmitting */ diff --git a/include/net/bonding.h b/include/net/bonding.h index 15335732e166..625d9c72dee3 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -201,6 +201,11 @@ struct bond_up_slave { */ #define BOND_LINK_NOCHANGE -1 +struct bond_ipsec { + struct list_head list; + struct xfrm_state *xs; +}; + /* * Here are the locking policies for the two bonding locks: * Get rcu_read_lock when reading or RTNL when writing slave list. @@ -249,7 +254,9 @@ struct bonding { #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; #ifdef CONFIG_XFRM_OFFLOAD - struct xfrm_state *xs; + struct list_head ipsec_list; + /* protecting ipsec_list */ + spinlock_t ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ }; From 955b785ec6b3b2f9b91914d6eeac8ee66ee29239 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:13 +0000 Subject: [PATCH 116/426] bonding: fix suspicious RCU usage in bond_ipsec_offload_ok() To dereference bond->curr_active_slave, it uses rcu_dereference(). But it and the caller doesn't acquire RCU so a warning occurs. So add rcu_read_lock(). Splat looks like: WARNING: suspicious RCU usage 5.13.0-rc6+ #1179 Not tainted drivers/net/bonding/bond_main.c:571 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by ping/974: #0: ffff888109e7db70 (sk_lock-AF_INET){+.+.}-{0:0}, at: raw_sendmsg+0x1303/0x2cb0 stack backtrace: CPU: 2 PID: 974 Comm: ping Not tainted 5.13.0-rc6+ #1179 Call Trace: dump_stack+0xa4/0xe5 bond_ipsec_offload_ok+0x1f4/0x260 [bonding] xfrm_output+0x179/0x890 xfrm4_output+0xfa/0x410 ? __xfrm4_output+0x4b0/0x4b0 ? __ip_make_skb+0xecc/0x2030 ? xfrm4_udp_encap_rcv+0x800/0x800 ? ip_local_out+0x21/0x3a0 ip_send_skb+0x37/0xa0 raw_sendmsg+0x1bfd/0x2cb0 Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 165fa55cfb38..780f87869e36 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -573,24 +573,34 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) struct net_device *real_dev; struct slave *curr_active; struct bonding *bond; + int err; bond = netdev_priv(bond_dev); + rcu_read_lock(); curr_active = rcu_dereference(bond->curr_active_slave); real_dev = curr_active->dev; - if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) - return true; + if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { + err = true; + goto out; + } - if (!xs->xso.real_dev) - return false; + if (!xs->xso.real_dev) { + err = false; + goto out; + } if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_offload_ok || netif_is_bond_master(real_dev)) { - return false; + err = false; + goto out; } - return real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); + err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); +out: + rcu_read_unlock(); + return err; } static const struct xfrmdev_ops bond_xfrmdev_ops = { From 168e696a36792a4a3b2525a06249e7472ef90186 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Jul 2021 15:38:14 +0000 Subject: [PATCH 117/426] bonding: fix incorrect return value of bond_ipsec_offload_ok() bond_ipsec_offload_ok() is called to check whether the interface supports ipsec offload or not. bonding interface support ipsec offload only in active-backup mode. So, if a bond interface is not in active-backup mode, it should return false but it returns true. Fixes: a3b658cfb664 ("bonding: allow xfrm offload setup post-module-load") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 780f87869e36..d22d78303311 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -581,7 +581,7 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) real_dev = curr_active->dev; if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { - err = true; + err = false; goto out; } From 22b6d14992b733e9421a475f4d43df24629737ab Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 4 Jun 2021 12:37:44 -0700 Subject: [PATCH 118/426] scftorture: Avoid false-positive warnings in scftorture_invoker() If the call to set_cpus_allowed_ptr() in scftorture_invoker() fails, a later WARN_ONCE() complains. But with the advent of 570a752b7a9b ("lib/smp_processor_id: Use is_percpu_thread() instead of nr_cpus_allowed"), this complaint can be drowned out by complaints from smp_processor_id(). The rationale for this change is that scftorture's kthreads are not marked with PF_NO_SETAFFINITY, which means that a system administrator could change affinity at any time. However, scftorture is a torture test, and the system administrator might well have a valid test-the-test reason for changing affinity. This commit therefore changes to raw_smp_processor_id() in order to avoid the noise, and also adds a WARN_ON_ONCE() to the call to set_cpus_allowed_ptr() in order to directly detect immediate failure. There is no WARN_ON_ONCE() within the test loop, allowing human-reflex-based affinity resetting, if desired. Signed-off-by: Paul E. McKenney --- kernel/scftorture.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 2377cbb32474..29e8fc5d91a7 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -405,15 +405,15 @@ static int scftorture_invoker(void *arg) VERBOSE_SCFTORTOUT("scftorture_invoker %d: task started", scfp->cpu); cpu = scfp->cpu % nr_cpu_ids; - set_cpus_allowed_ptr(current, cpumask_of(cpu)); + WARN_ON_ONCE(set_cpus_allowed_ptr(current, cpumask_of(cpu))); set_user_nice(current, MAX_NICE); if (holdoff) schedule_timeout_interruptible(holdoff * HZ); - VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, smp_processor_id()); + VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, raw_smp_processor_id()); // Make sure that the CPU is affinitized appropriately during testing. - curcpu = smp_processor_id(); + curcpu = raw_smp_processor_id(); WARN_ONCE(curcpu != scfp->cpu % nr_cpu_ids, "%s: Wanted CPU %d, running on %d, nr_cpu_ids = %d\n", __func__, scfp->cpu, curcpu, nr_cpu_ids); From 05bc276cf243d90b9f1eb6ae2962f41eeb53a741 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 10 Jun 2021 09:24:43 -0700 Subject: [PATCH 119/426] refscale: Avoid false-positive warnings in ref_scale_reader() If the call to set_cpus_allowed_ptr() in ref_scale_reader() fails, a later WARN_ONCE() complains. But with the advent of 570a752b7a9b ("lib/smp_processor_id: Use is_percpu_thread() instead of nr_cpus_allowed"), this complaint can be drowned out by complaints from smp_processor_id(). The rationale for this change is that refscale's kthreads are not marked with PF_NO_SETAFFINITY, which means that a system administrator could change affinity at any time. However, refscale is a performance/stress test, and the system administrator might well have a valid test-the-test reason for changing affinity. This commit therefore changes to raw_smp_processor_id() in order to avoid the noise, and also adds a WARN_ON_ONCE() to the call to set_cpus_allowed_ptr() in order to directly detect immediate failure. There is no WARN_ON_ONCE() within the test loop, allowing human-reflex-based affinity resetting, if desired. Signed-off-by: Paul E. McKenney --- kernel/rcu/refscale.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c index 313d4547cbc7..d998a76fb542 100644 --- a/kernel/rcu/refscale.c +++ b/kernel/rcu/refscale.c @@ -487,13 +487,13 @@ ref_scale_reader(void *arg) s64 duration; VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: task started", me); - set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); + WARN_ON_ONCE(set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids))); set_user_nice(current, MAX_NICE); atomic_inc(&n_init); if (holdoff) schedule_timeout_interruptible(holdoff * HZ); repeat: - VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id()); + VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, raw_smp_processor_id()); // Wait for signal that this reader can start. wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) || @@ -503,7 +503,7 @@ repeat: goto end; // Make sure that the CPU is affinitized appropriately during testing. - WARN_ON_ONCE(smp_processor_id() != me); + WARN_ON_ONCE(raw_smp_processor_id() != me); WRITE_ONCE(rt->start_reader, 0); if (!atomic_dec_return(&n_started)) From 1d10bf55d85d34eb73dd8263635f43fd72135d2d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 25 May 2021 10:12:45 -0700 Subject: [PATCH 120/426] rcu-tasks: Don't delete holdouts within trc_inspect_reader() As Yanfei pointed out, although invoking trc_del_holdout() is safe from the viewpoint of the integrity of the holdout list itself, the put_task_struct() invoked by trc_del_holdout() can result in use-after-free errors due to later accesses to this task_struct structure by the RCU Tasks Trace grace-period kthread. This commit therefore removes this call to trc_del_holdout() from trc_inspect_reader() in favor of the grace-period thread's existing call to trc_del_holdout(), thus eliminating that particular class of use-after-free errors. Reported-by: "Xu, Yanfei" Signed-off-by: Paul E. McKenney --- kernel/rcu/tasks.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 03a118d1c003..3d5cb6cb8a6d 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -953,10 +953,9 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) in_qs = likely(!t->trc_reader_nesting); } - // Mark as checked. Because this is called from the grace-period - // kthread, also remove the task from the holdout list. + // Mark as checked so that the grace-period kthread will + // remove it from the holdout list. t->trc_reader_checked = true; - trc_del_holdout(t); if (in_qs) return true; // Already in quiescent state, done!!! From ad1f37970875eef98eeaf478f55045f388b794a5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 6 Jul 2021 12:18:02 +0100 Subject: [PATCH 121/426] octeontx2-pf: Fix assigned error return value that is never used Currently when the call to otx2_mbox_alloc_msg_cgx_mac_addr_update fails the error return variable rc is being assigned -ENOMEM and does not return early. rc is then re-assigned and the error case is not handled correctly. Fix this by returning -ENOMEM rather than assigning rc. Addresses-Coverity: ("Unused value") Fixes: 79d2be385e9e ("octeontx2-pf: offload DMAC filters to CGX/RPM block") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c index ffe3e94562d0..383a6b5cb698 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dmac_flt.c @@ -161,7 +161,7 @@ int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos) if (!req) { mutex_unlock(&pf->mbox.lock); - rc = -ENOMEM; + return -ENOMEM; } ether_addr_copy(req->mac_addr, mac); From ccd27f05ae7b8ebc40af5b004e94517a919aa862 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 6 Jul 2021 11:13:35 +0200 Subject: [PATCH 122/426] ipv6: fix 'disable_policy' for fwd packets The goal of commit df789fe75206 ("ipv6: Provide ipv6 version of "disable_policy" sysctl") was to have the disable_policy from ipv4 available on ipv6. However, it's not exactly the same mechanism. On IPv4, all packets coming from an interface, which has disable_policy set, bypass the policy check. For ipv6, this is done only for local packets, ie for packets destinated to an address configured on the incoming interface. Let's align ipv6 with ipv4 so that the 'disable_policy' sysctl has the same effect for both protocols. My first approach was to create a new kind of route cache entries, to be able to set DST_NOPOLICY without modifying routes. This would have added a lot of code. Because the local delivery path is already handled, I choose to focus on the forwarding path to minimize code churn. Fixes: df789fe75206 ("ipv6: Provide ipv6 version of "disable_policy" sysctl") Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 984050f35c61..d4ee2169afd8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -479,7 +479,9 @@ int ip6_forward(struct sk_buff *skb) if (skb_warn_if_lro(skb)) goto drop; - if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { + if (!net->ipv6.devconf_all->disable_policy && + !idev->cnf.disable_policy && + !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } From a9ab9cce9367a2cc02a3c7eb57a004dc0b8f380d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 25 May 2021 11:28:40 -0700 Subject: [PATCH 123/426] rcu-tasks: Don't delete holdouts within trc_wait_for_one_reader() Invoking trc_del_holdout() from within trc_wait_for_one_reader() is only a performance optimization because the RCU Tasks Trace grace-period kthread will eventually do this within check_all_holdout_tasks_trace(). But it is not a particularly important performance optimization because it only applies to the grace-period kthread, of which there is but one. This commit therefore removes this invocation of trc_del_holdout() in favor of the one in check_all_holdout_tasks_trace() in the grace-period kthread. Reported-by: "Xu, Yanfei" Signed-off-by: Paul E. McKenney --- kernel/rcu/tasks.h | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 3d5cb6cb8a6d..8536c55df514 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -982,7 +982,6 @@ static void trc_wait_for_one_reader(struct task_struct *t, // The current task had better be in a quiescent state. if (t == current) { t->trc_reader_checked = true; - trc_del_holdout(t); WARN_ON_ONCE(t->trc_reader_nesting); return; } From 2a2ed5618a0e8a890d948b88b368c0459f35136c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 4 Jul 2021 13:59:35 -0700 Subject: [PATCH 124/426] rcu: Fix pr_info() formats and values in show_rcu_gp_kthreads() This commit changes from "%lx" to "%x" and from "0x1ffffL" to "0x1ffff" to match the change in type between the old field ->state (unsigned long) and the new field ->__state (unsigned int). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_stall.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 3f937b20814f..6c76988cc019 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -795,9 +795,9 @@ void show_rcu_gp_kthreads(void) jr = j - data_race(rcu_state.gp_req_activity); js = j - data_race(rcu_state.gp_start); jw = j - data_race(rcu_state.gp_wake_time); - pr_info("%s: wait state: %s(%d) ->state: %#lx ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n", + pr_info("%s: wait state: %s(%d) ->state: %#x ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n", rcu_state.name, gp_state_getname(rcu_state.gp_state), - rcu_state.gp_state, t ? t->__state : 0x1ffffL, t ? t->rt_priority : 0xffU, + rcu_state.gp_state, t ? t->__state : 0x1ffff, t ? t->rt_priority : 0xffU, js, ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq), (long)data_race(rcu_state.gp_seq), (long)data_race(rcu_get_root()->gp_seq_needed), From af0efa050caa66e8f304c42c94c76cb6c480cb7e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Tue, 6 Jul 2021 14:23:55 +0200 Subject: [PATCH 125/426] libbpf: Restore errno return for functions that were already returning it MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The update to streamline libbpf error reporting intended to change all functions to return the errno as a negative return value if LIBBPF_STRICT_DIRECT_ERRS is set. However, if the flag is *not* set, the return value changes for the two functions that were already returning a negative errno unconditionally: bpf_link__unpin() and perf_buffer__poll(). This is a user-visible API change that breaks applications; so let's revert these two functions back to unconditionally returning a negative errno value. Fixes: e9fc3ce99b34 ("libbpf: Streamline error reporting for high-level APIs") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210706122355.236082-1-toke@redhat.com --- tools/lib/bpf/libbpf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 1e04ce724240..6f5e2757bb3c 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -10136,7 +10136,7 @@ int bpf_link__unpin(struct bpf_link *link) err = unlink(link->pin_path); if (err != 0) - return libbpf_err_errno(err); + return -errno; pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path); zfree(&link->pin_path); @@ -11197,7 +11197,7 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms); if (cnt < 0) - return libbpf_err_errno(cnt); + return -errno; for (i = 0; i < cnt; i++) { struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr; From d322957ebfb9c21c2c72b66680f7c3ccd724e081 Mon Sep 17 00:00:00 2001 From: Duncan Roe Date: Wed, 7 Jul 2021 10:57:51 +1000 Subject: [PATCH 126/426] netfilter: uapi: refer to nfnetlink_conntrack.h, not nf_conntrack_netlink.h nf_conntrack_netlink.h does not exist, refer to nfnetlink_conntrack.h instead. Signed-off-by: Duncan Roe Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_log.h | 2 +- include/uapi/linux/netfilter/nfnetlink_queue.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/netfilter/nfnetlink_log.h b/include/uapi/linux/netfilter/nfnetlink_log.h index 45c8d3b027e0..0af9c113d665 100644 --- a/include/uapi/linux/netfilter/nfnetlink_log.h +++ b/include/uapi/linux/netfilter/nfnetlink_log.h @@ -61,7 +61,7 @@ enum nfulnl_attr_type { NFULA_HWTYPE, /* hardware type */ NFULA_HWHEADER, /* hardware header */ NFULA_HWLEN, /* hardware header length */ - NFULA_CT, /* nf_conntrack_netlink.h */ + NFULA_CT, /* nfnetlink_conntrack.h */ NFULA_CT_INFO, /* enum ip_conntrack_info */ NFULA_VLAN, /* nested attribute: packet vlan info */ NFULA_L2HDR, /* full L2 header */ diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index bcb2cb5d40b9..aed90c4df0c8 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -51,11 +51,11 @@ enum nfqnl_attr_type { NFQA_IFINDEX_PHYSOUTDEV, /* __u32 ifindex */ NFQA_HWADDR, /* nfqnl_msg_packet_hw */ NFQA_PAYLOAD, /* opaque data payload */ - NFQA_CT, /* nf_conntrack_netlink.h */ + NFQA_CT, /* nfnetlink_conntrack.h */ NFQA_CT_INFO, /* enum ip_conntrack_info */ NFQA_CAP_LEN, /* __u32 length of captured packet */ NFQA_SKB_INFO, /* __u32 skb meta information */ - NFQA_EXP, /* nf_conntrack_netlink.h */ + NFQA_EXP, /* nfnetlink_conntrack.h */ NFQA_UID, /* __u32 sk uid */ NFQA_GID, /* __u32 sk gid */ NFQA_SECCTX, /* security context string */ From 54afaae34ee49e98c1c902b444b42832551d090c Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 23 Jun 2021 17:54:54 +0200 Subject: [PATCH 127/426] btrfs: zoned: fix types for u64 division in btrfs_reclaim_bgs_work The types in calculation of the used percentage in the reclaiming messages are both u64, though bg->length is either 1GiB (non-zoned) or the zone size in the zoned mode. The upper limit on zone size is 8GiB so this could theoretically overflow in the future, right now the values fit. Fixes: 18bb8bbf13c1 ("btrfs: zoned: automatically reclaim zones") CC: stable@vger.kernel.org # 5.13 Reviewed-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 38b127b9edfc..d4c8dc550889 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1540,7 +1540,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) goto next; btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used", - bg->start, div_u64(bg->used * 100, bg->length)); + bg->start, div64_u64(bg->used * 100, bg->length)); trace_btrfs_reclaim_block_group(bg); ret = btrfs_relocate_chunk(fs_info, bg->start); if (ret) From 5f93e776c6734cea989aeb4f2d6c97e521baa683 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 29 Jun 2021 03:16:46 +0900 Subject: [PATCH 128/426] btrfs: zoned: print unusable percentage when reclaiming block groups When we're automatically reclaiming a zone, because its zone_unusable value is above the reclaim threshold, we're only logging how much percent of the zone's capacity are used, but not how much of the capacity is unusable. Also print the percentage of the unusable space in the block group before we're reclaiming it. Example: BTRFS info (device sdg): reclaiming chunk 230686720 with 13% used 86% unusable CC: stable@vger.kernel.org # 5.13 Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index d4c8dc550889..fec7a34b27f3 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1501,6 +1501,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) mutex_lock(&fs_info->reclaim_bgs_lock); spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->reclaim_bgs)) { + u64 zone_unusable; int ret = 0; bg = list_first_entry(&fs_info->reclaim_bgs, @@ -1534,13 +1535,22 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) goto next; } + /* + * Cache the zone_unusable value before turning the block group + * to read only. As soon as the blog group is read only it's + * zone_unusable value gets moved to the block group's read-only + * bytes and isn't available for calculations anymore. + */ + zone_unusable = bg->zone_unusable; ret = inc_block_group_ro(bg, 0); up_write(&space_info->groups_sem); if (ret < 0) goto next; - btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used", - bg->start, div64_u64(bg->used * 100, bg->length)); + btrfs_info(fs_info, + "reclaiming chunk %llu with %llu%% used %llu%% unusable", + bg->start, div_u64(bg->used * 100, bg->length), + div64_u64(zone_unusable * 100, bg->length)); trace_btrfs_reclaim_block_group(bg); ret = btrfs_relocate_chunk(fs_info, bg->start); if (ret) From 1cb3db1cf383a3c7dbda1aa0ce748b0958759947 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 29 Jun 2021 14:43:05 +0100 Subject: [PATCH 129/426] btrfs: fix deadlock with concurrent chunk allocations involving system chunks When a task attempting to allocate a new chunk verifies that there is not currently enough free space in the system space_info and there is another task that allocated a new system chunk but it did not finish yet the creation of the respective block group, it waits for that other task to finish creating the block group. This is to avoid exhaustion of the system chunk array in the superblock, which is limited, when we have a thundering herd of tasks allocating new chunks. This problem was described and fixed by commit eafa4fd0ad0607 ("btrfs: fix exhaustion of the system chunk array due to concurrent allocations"). However there are two very similar scenarios where this can lead to a deadlock: 1) Task B allocated a new system chunk and task A is waiting on task B to finish creation of the respective system block group. However before task B ends its transaction handle and finishes the creation of the system block group, it attempts to allocate another chunk (like a data chunk for an fallocate operation for a very large range). Task B will be unable to progress and allocate the new chunk, because task A set space_info->chunk_alloc to 1 and therefore it loops at btrfs_chunk_alloc() waiting for task A to finish its chunk allocation and set space_info->chunk_alloc to 0, but task A is waiting on task B to finish creation of the new system block group, therefore resulting in a deadlock; 2) Task B allocated a new system chunk and task A is waiting on task B to finish creation of the respective system block group. By the time that task B enter the final phase of block group allocation, which happens at btrfs_create_pending_block_groups(), when it modifies the extent tree, the device tree or the chunk tree to insert the items for some new block group, it needs to allocate a new chunk, so it ends up at btrfs_chunk_alloc() and keeps looping there because task A has set space_info->chunk_alloc to 1, but task A is waiting for task B to finish creation of the new system block group and release the reserved system space, therefore resulting in a deadlock. In short, the problem is if a task B needs to allocate a new chunk after it previously allocated a new system chunk and if another task A is currently waiting for task B to complete the allocation of the new system chunk. Unfortunately this deadlock scenario introduced by the previous fix for the system chunk array exhaustion problem does not have a simple and short fix, and requires a big change to rework the chunk allocation code so that chunk btree updates are all made in the first phase of chunk allocation. And since this deadlock regression is being frequently hit on zoned filesystems and the system chunk array exhaustion problem is triggered in more extreme cases (originally observed on PowerPC with a node size of 64K when running the fallocate tests from stress-ng), revert the changes from that commit. The next patch in the series, with a subject of "btrfs: rework chunk allocation to avoid exhaustion of the system chunk array" does the necessary changes to fix the system chunk array exhaustion problem. Reported-by: Naohiro Aota Link: https://lore.kernel.org/linux-btrfs/20210621015922.ewgbffxuawia7liz@naota-xeon/ Fixes: eafa4fd0ad0607 ("btrfs: fix exhaustion of the system chunk array due to concurrent allocations") CC: stable@vger.kernel.org # 5.12+ Tested-by: Shin'ichiro Kawasaki Tested-by: Naohiro Aota Signed-off-by: Filipe Manana Tested-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 58 +----------------------------------------- fs/btrfs/transaction.c | 5 ---- fs/btrfs/transaction.h | 7 ----- 3 files changed, 1 insertion(+), 69 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index fec7a34b27f3..a26209f98279 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3377,7 +3377,6 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type) */ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type) { - struct btrfs_transaction *cur_trans = trans->transaction; struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_space_info *info; u64 left; @@ -3392,7 +3391,6 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type) lockdep_assert_held(&fs_info->chunk_mutex); info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM); -again: spin_lock(&info->lock); left = info->total_bytes - btrfs_space_info_used(info, true); spin_unlock(&info->lock); @@ -3411,58 +3409,6 @@ again: if (left < thresh) { u64 flags = btrfs_system_alloc_profile(fs_info); - u64 reserved = atomic64_read(&cur_trans->chunk_bytes_reserved); - - /* - * If there's not available space for the chunk tree (system - * space) and there are other tasks that reserved space for - * creating a new system block group, wait for them to complete - * the creation of their system block group and release excess - * reserved space. We do this because: - * - * *) We can end up allocating more system chunks than necessary - * when there are multiple tasks that are concurrently - * allocating block groups, which can lead to exhaustion of - * the system array in the superblock; - * - * *) If we allocate extra and unnecessary system block groups, - * despite being empty for a long time, and possibly forever, - * they end not being added to the list of unused block groups - * because that typically happens only when deallocating the - * last extent from a block group - which never happens since - * we never allocate from them in the first place. The few - * exceptions are when mounting a filesystem or running scrub, - * which add unused block groups to the list of unused block - * groups, to be deleted by the cleaner kthread. - * And even when they are added to the list of unused block - * groups, it can take a long time until they get deleted, - * since the cleaner kthread might be sleeping or busy with - * other work (deleting subvolumes, running delayed iputs, - * defrag scheduling, etc); - * - * This is rare in practice, but can happen when too many tasks - * are allocating blocks groups in parallel (via fallocate()) - * and before the one that reserved space for a new system block - * group finishes the block group creation and releases the space - * reserved in excess (at btrfs_create_pending_block_groups()), - * other tasks end up here and see free system space temporarily - * not enough for updating the chunk tree. - * - * We unlock the chunk mutex before waiting for such tasks and - * lock it again after the wait, otherwise we would deadlock. - * It is safe to do so because allocating a system chunk is the - * first thing done while allocating a new block group. - */ - if (reserved > trans->chunk_bytes_reserved) { - const u64 min_needed = reserved - thresh; - - mutex_unlock(&fs_info->chunk_mutex); - wait_event(cur_trans->chunk_reserve_wait, - atomic64_read(&cur_trans->chunk_bytes_reserved) <= - min_needed); - mutex_lock(&fs_info->chunk_mutex); - goto again; - } /* * Ignore failure to create system chunk. We might end up not @@ -3477,10 +3423,8 @@ again: ret = btrfs_block_rsv_add(fs_info->chunk_root, &fs_info->chunk_block_rsv, thresh, BTRFS_RESERVE_NO_FLUSH); - if (!ret) { - atomic64_add(thresh, &cur_trans->chunk_bytes_reserved); + if (!ret) trans->chunk_bytes_reserved += thresh; - } } } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 50318231c1a8..443c348bc6f3 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -260,7 +260,6 @@ static inline int extwriter_counter_read(struct btrfs_transaction *trans) void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_transaction *cur_trans = trans->transaction; if (!trans->chunk_bytes_reserved) return; @@ -269,8 +268,6 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv, trans->chunk_bytes_reserved, NULL); - atomic64_sub(trans->chunk_bytes_reserved, &cur_trans->chunk_bytes_reserved); - cond_wake_up(&cur_trans->chunk_reserve_wait); trans->chunk_bytes_reserved = 0; } @@ -386,8 +383,6 @@ loop: spin_lock_init(&cur_trans->dropped_roots_lock); INIT_LIST_HEAD(&cur_trans->releasing_ebs); spin_lock_init(&cur_trans->releasing_ebs_lock); - atomic64_set(&cur_trans->chunk_bytes_reserved, 0); - init_waitqueue_head(&cur_trans->chunk_reserve_wait); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(fs_info, &cur_trans->dirty_pages, IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 07d76029f598..a18d67796b54 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -96,13 +96,6 @@ struct btrfs_transaction { spinlock_t releasing_ebs_lock; struct list_head releasing_ebs; - - /* - * The number of bytes currently reserved, by all transaction handles - * attached to this transaction, for metadata extents of the chunk tree. - */ - atomic64_t chunk_bytes_reserved; - wait_queue_head_t chunk_reserve_wait; }; #define __TRANS_FREEZABLE (1U << 0) From 79bd37120b149532af5b21953643ed74af69654f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 29 Jun 2021 14:43:06 +0100 Subject: [PATCH 130/426] btrfs: rework chunk allocation to avoid exhaustion of the system chunk array Commit eafa4fd0ad0607 ("btrfs: fix exhaustion of the system chunk array due to concurrent allocations") fixed a problem that resulted in exhausting the system chunk array in the superblock when there are many tasks allocating chunks in parallel. Basically too many tasks enter the first phase of chunk allocation without previous tasks having finished their second phase of allocation, resulting in too many system chunks being allocated. That was originally observed when running the fallocate tests of stress-ng on a PowerPC machine, using a node size of 64K. However that commit also introduced a deadlock where a task in phase 1 of the chunk allocation waited for another task that had allocated a system chunk to finish its phase 2, but that other task was waiting on an extent buffer lock held by the first task, therefore resulting in both tasks not making any progress. That change was later reverted by a patch with the subject "btrfs: fix deadlock with concurrent chunk allocations involving system chunks", since there is no simple and short solution to address it and the deadlock is relatively easy to trigger on zoned filesystems, while the system chunk array exhaustion is not so common. This change reworks the chunk allocation to avoid the system chunk array exhaustion. It accomplishes that by making the first phase of chunk allocation do the updates of the device items in the chunk btree and the insertion of the new chunk item in the chunk btree. This is done while under the protection of the chunk mutex (fs_info->chunk_mutex), in the same critical section that checks for available system space, allocates a new system chunk if needed and reserves system chunk space. This way we do not have chunk space reserved until the second phase completes. The same logic is applied to chunk removal as well, since it keeps reserved system space long after it is done updating the chunk btree. For direct allocation of system chunks, the previous behaviour remains, because otherwise we would deadlock on extent buffers of the chunk btree. Changes to the chunk btree are by large done by chunk allocation and chunk removal, which first reserve chunk system space and then later do changes to the chunk btree. The other remaining cases are uncommon and correspond to adding a device, removing a device and resizing a device. All these other cases do not pre-reserve system space, they modify the chunk btree right away, so they don't hold reserved space for a long period like chunk allocation and chunk removal do. The diff of this change is huge, but more than half of it is just addition of comments describing both how things work regarding chunk allocation and removal, including both the new behavior and the parts of the old behavior that did not change. CC: stable@vger.kernel.org # 5.12+ Tested-by: Shin'ichiro Kawasaki Tested-by: Naohiro Aota Signed-off-by: Filipe Manana Tested-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 285 ++++++++++++++++++++++++++++---- fs/btrfs/block-group.h | 6 +- fs/btrfs/ctree.c | 67 ++------ fs/btrfs/transaction.c | 10 +- fs/btrfs/transaction.h | 2 +- fs/btrfs/volumes.c | 361 +++++++++++++++++++++++++++++++---------- fs/btrfs/volumes.h | 5 +- 7 files changed, 549 insertions(+), 187 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index a26209f98279..c557327b4545 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2207,6 +2207,13 @@ error: return ret; } +/* + * This function, insert_block_group_item(), belongs to the phase 2 of chunk + * allocation. + * + * See the comment at btrfs_chunk_alloc() for details about the chunk allocation + * phases. + */ static int insert_block_group_item(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { @@ -2229,15 +2236,19 @@ static int insert_block_group_item(struct btrfs_trans_handle *trans, return btrfs_insert_item(trans, root, &key, &bgi, sizeof(bgi)); } +/* + * This function, btrfs_create_pending_block_groups(), belongs to the phase 2 of + * chunk allocation. + * + * See the comment at btrfs_chunk_alloc() for details about the chunk allocation + * phases. + */ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *block_group; int ret = 0; - if (!trans->can_flush_pending_bgs) - return; - while (!list_empty(&trans->new_bgs)) { int index; @@ -2252,6 +2263,13 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) ret = insert_block_group_item(trans, block_group); if (ret) btrfs_abort_transaction(trans, ret); + if (!block_group->chunk_item_inserted) { + mutex_lock(&fs_info->chunk_mutex); + ret = btrfs_chunk_alloc_add_chunk_item(trans, block_group); + mutex_unlock(&fs_info->chunk_mutex); + if (ret) + btrfs_abort_transaction(trans, ret); + } ret = btrfs_finish_chunk_alloc(trans, block_group->start, block_group->length); if (ret) @@ -2275,8 +2293,9 @@ next: btrfs_trans_release_chunk_metadata(trans); } -int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, - u64 type, u64 chunk_offset, u64 size) +struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans, + u64 bytes_used, u64 type, + u64 chunk_offset, u64 size) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *cache; @@ -2286,7 +2305,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, cache = btrfs_create_block_group_cache(fs_info, chunk_offset); if (!cache) - return -ENOMEM; + return ERR_PTR(-ENOMEM); cache->length = size; set_free_space_tree_thresholds(cache); @@ -2300,7 +2319,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, ret = btrfs_load_block_group_zone_info(cache, true); if (ret) { btrfs_put_block_group(cache); - return ret; + return ERR_PTR(ret); } ret = exclude_super_stripes(cache); @@ -2308,7 +2327,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, /* We may have excluded something, so call this just in case */ btrfs_free_excluded_extents(cache); btrfs_put_block_group(cache); - return ret; + return ERR_PTR(ret); } add_new_free_space(cache, chunk_offset, chunk_offset + size); @@ -2335,7 +2354,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, if (ret) { btrfs_remove_free_space_cache(cache); btrfs_put_block_group(cache); - return ret; + return ERR_PTR(ret); } /* @@ -2354,7 +2373,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, btrfs_update_delayed_refs_rsv(trans); set_avail_alloc_bits(fs_info, type); - return 0; + return cache; } /* @@ -3232,11 +3251,203 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type) return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); } +static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) +{ + struct btrfs_block_group *bg; + int ret; + + /* + * Check if we have enough space in the system space info because we + * will need to update device items in the chunk btree and insert a new + * chunk item in the chunk btree as well. This will allocate a new + * system block group if needed. + */ + check_system_chunk(trans, flags); + + bg = btrfs_alloc_chunk(trans, flags); + if (IS_ERR(bg)) { + ret = PTR_ERR(bg); + goto out; + } + + /* + * If this is a system chunk allocation then stop right here and do not + * add the chunk item to the chunk btree. This is to prevent a deadlock + * because this system chunk allocation can be triggered while COWing + * some extent buffer of the chunk btree and while holding a lock on a + * parent extent buffer, in which case attempting to insert the chunk + * item (or update the device item) would result in a deadlock on that + * parent extent buffer. In this case defer the chunk btree updates to + * the second phase of chunk allocation and keep our reservation until + * the second phase completes. + * + * This is a rare case and can only be triggered by the very few cases + * we have where we need to touch the chunk btree outside chunk allocation + * and chunk removal. These cases are basically adding a device, removing + * a device or resizing a device. + */ + if (flags & BTRFS_BLOCK_GROUP_SYSTEM) + return 0; + + ret = btrfs_chunk_alloc_add_chunk_item(trans, bg); + /* + * Normally we are not expected to fail with -ENOSPC here, since we have + * previously reserved space in the system space_info and allocated one + * new system chunk if necessary. However there are two exceptions: + * + * 1) We may have enough free space in the system space_info but all the + * existing system block groups have a profile which can not be used + * for extent allocation. + * + * This happens when mounting in degraded mode. For example we have a + * RAID1 filesystem with 2 devices, lose one device and mount the fs + * using the other device in degraded mode. If we then allocate a chunk, + * we may have enough free space in the existing system space_info, but + * none of the block groups can be used for extent allocation since they + * have a RAID1 profile, and because we are in degraded mode with a + * single device, we are forced to allocate a new system chunk with a + * SINGLE profile. Making check_system_chunk() iterate over all system + * block groups and check if they have a usable profile and enough space + * can be slow on very large filesystems, so we tolerate the -ENOSPC and + * try again after forcing allocation of a new system chunk. Like this + * we avoid paying the cost of that search in normal circumstances, when + * we were not mounted in degraded mode; + * + * 2) We had enough free space info the system space_info, and one suitable + * block group to allocate from when we called check_system_chunk() + * above. However right after we called it, the only system block group + * with enough free space got turned into RO mode by a running scrub, + * and in this case we have to allocate a new one and retry. We only + * need do this allocate and retry once, since we have a transaction + * handle and scrub uses the commit root to search for block groups. + */ + if (ret == -ENOSPC) { + const u64 sys_flags = btrfs_system_alloc_profile(trans->fs_info); + struct btrfs_block_group *sys_bg; + + sys_bg = btrfs_alloc_chunk(trans, sys_flags); + if (IS_ERR(sys_bg)) { + ret = PTR_ERR(sys_bg); + btrfs_abort_transaction(trans, ret); + goto out; + } + + ret = btrfs_chunk_alloc_add_chunk_item(trans, sys_bg); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + + ret = btrfs_chunk_alloc_add_chunk_item(trans, bg); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + } else if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } +out: + btrfs_trans_release_chunk_metadata(trans); + + return ret; +} + /* - * If force is CHUNK_ALLOC_FORCE: + * Chunk allocation is done in 2 phases: + * + * 1) Phase 1 - through btrfs_chunk_alloc() we allocate device extents for + * the chunk, the chunk mapping, create its block group and add the items + * that belong in the chunk btree to it - more specifically, we need to + * update device items in the chunk btree and add a new chunk item to it. + * + * 2) Phase 2 - through btrfs_create_pending_block_groups(), we add the block + * group item to the extent btree and the device extent items to the devices + * btree. + * + * This is done to prevent deadlocks. For example when COWing a node from the + * extent btree we are holding a write lock on the node's parent and if we + * trigger chunk allocation and attempted to insert the new block group item + * in the extent btree right way, we could deadlock because the path for the + * insertion can include that parent node. At first glance it seems impossible + * to trigger chunk allocation after starting a transaction since tasks should + * reserve enough transaction units (metadata space), however while that is true + * most of the time, chunk allocation may still be triggered for several reasons: + * + * 1) When reserving metadata, we check if there is enough free space in the + * metadata space_info and therefore don't trigger allocation of a new chunk. + * However later when the task actually tries to COW an extent buffer from + * the extent btree or from the device btree for example, it is forced to + * allocate a new block group (chunk) because the only one that had enough + * free space was just turned to RO mode by a running scrub for example (or + * device replace, block group reclaim thread, etc), so we can not use it + * for allocating an extent and end up being forced to allocate a new one; + * + * 2) Because we only check that the metadata space_info has enough free bytes, + * we end up not allocating a new metadata chunk in that case. However if + * the filesystem was mounted in degraded mode, none of the existing block + * groups might be suitable for extent allocation due to their incompatible + * profile (for e.g. mounting a 2 devices filesystem, where all block groups + * use a RAID1 profile, in degraded mode using a single device). In this case + * when the task attempts to COW some extent buffer of the extent btree for + * example, it will trigger allocation of a new metadata block group with a + * suitable profile (SINGLE profile in the example of the degraded mount of + * the RAID1 filesystem); + * + * 3) The task has reserved enough transaction units / metadata space, but when + * it attempts to COW an extent buffer from the extent or device btree for + * example, it does not find any free extent in any metadata block group, + * therefore forced to try to allocate a new metadata block group. + * This is because some other task allocated all available extents in the + * meanwhile - this typically happens with tasks that don't reserve space + * properly, either intentionally or as a bug. One example where this is + * done intentionally is fsync, as it does not reserve any transaction units + * and ends up allocating a variable number of metadata extents for log + * tree extent buffers. + * + * We also need this 2 phases setup when adding a device to a filesystem with + * a seed device - we must create new metadata and system chunks without adding + * any of the block group items to the chunk, extent and device btrees. If we + * did not do it this way, we would get ENOSPC when attempting to update those + * btrees, since all the chunks from the seed device are read-only. + * + * Phase 1 does the updates and insertions to the chunk btree because if we had + * it done in phase 2 and have a thundering herd of tasks allocating chunks in + * parallel, we risk having too many system chunks allocated by many tasks if + * many tasks reach phase 1 without the previous ones completing phase 2. In the + * extreme case this leads to exhaustion of the system chunk array in the + * superblock. This is easier to trigger if using a btree node/leaf size of 64K + * and with RAID filesystems (so we have more device items in the chunk btree). + * This has happened before and commit eafa4fd0ad0607 ("btrfs: fix exhaustion of + * the system chunk array due to concurrent allocations") provides more details. + * + * For allocation of system chunks, we defer the updates and insertions into the + * chunk btree to phase 2. This is to prevent deadlocks on extent buffers because + * if the chunk allocation is triggered while COWing an extent buffer of the + * chunk btree, we are holding a lock on the parent of that extent buffer and + * doing the chunk btree updates and insertions can require locking that parent. + * This is for the very few and rare cases where we update the chunk btree that + * are not chunk allocation or chunk removal: adding a device, removing a device + * or resizing a device. + * + * The reservation of system space, done through check_system_chunk(), as well + * as all the updates and insertions into the chunk btree must be done while + * holding fs_info->chunk_mutex. This is important to guarantee that while COWing + * an extent buffer from the chunks btree we never trigger allocation of a new + * system chunk, which would result in a deadlock (trying to lock twice an + * extent buffer of the chunk btree, first time before triggering the chunk + * allocation and the second time during chunk allocation while attempting to + * update the chunks btree). The system chunk array is also updated while holding + * that mutex. The same logic applies to removing chunks - we must reserve system + * space, update the chunk btree and the system chunk array in the superblock + * while holding fs_info->chunk_mutex. + * + * This function, btrfs_chunk_alloc(), belongs to phase 1. + * + * If @force is CHUNK_ALLOC_FORCE: * - return 1 if it successfully allocates a chunk, * - return errors including -ENOSPC otherwise. - * If force is NOT CHUNK_ALLOC_FORCE: + * If @force is NOT CHUNK_ALLOC_FORCE: * - return 0 if it doesn't need to allocate a new chunk, * - return 1 if it successfully allocates a chunk, * - return errors including -ENOSPC otherwise. @@ -3253,6 +3464,13 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, /* Don't re-enter if we're already allocating a chunk */ if (trans->allocating_chunk) return -ENOSPC; + /* + * If we are removing a chunk, don't re-enter or we would deadlock. + * System space reservation and system chunk allocation is done by the + * chunk remove operation (btrfs_remove_chunk()). + */ + if (trans->removing_chunk) + return -ENOSPC; space_info = btrfs_find_space_info(fs_info, flags); ASSERT(space_info); @@ -3316,13 +3534,7 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, force_metadata_allocation(fs_info); } - /* - * Check if we have enough space in SYSTEM chunk because we may need - * to update devices. - */ - check_system_chunk(trans, flags); - - ret = btrfs_alloc_chunk(trans, flags); + ret = do_chunk_alloc(trans, flags); trans->allocating_chunk = false; spin_lock(&space_info->lock); @@ -3341,22 +3553,6 @@ out: space_info->chunk_alloc = 0; spin_unlock(&space_info->lock); mutex_unlock(&fs_info->chunk_mutex); - /* - * When we allocate a new chunk we reserve space in the chunk block - * reserve to make sure we can COW nodes/leafs in the chunk tree or - * add new nodes/leafs to it if we end up needing to do it when - * inserting the chunk item and updating device items as part of the - * second phase of chunk allocation, performed by - * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a - * large number of new block groups to create in our transaction - * handle's new_bgs list to avoid exhausting the chunk block reserve - * in extreme cases - like having a single transaction create many new - * block groups when starting to write out the free space caches of all - * the block groups that were made dirty during the lifetime of the - * transaction. - */ - if (trans->chunk_bytes_reserved >= (u64)SZ_2M) - btrfs_create_pending_block_groups(trans); return ret; } @@ -3409,14 +3605,31 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type) if (left < thresh) { u64 flags = btrfs_system_alloc_profile(fs_info); + struct btrfs_block_group *bg; /* * Ignore failure to create system chunk. We might end up not * needing it, as we might not need to COW all nodes/leafs from * the paths we visit in the chunk tree (they were already COWed * or created in the current transaction for example). + * + * Also, if our caller is allocating a system chunk, do not + * attempt to insert the chunk item in the chunk btree, as we + * could deadlock on an extent buffer since our caller may be + * COWing an extent buffer from the chunk btree. */ - ret = btrfs_alloc_chunk(trans, flags); + bg = btrfs_alloc_chunk(trans, flags); + if (IS_ERR(bg)) { + ret = PTR_ERR(bg); + } else if (!(type & BTRFS_BLOCK_GROUP_SYSTEM)) { + /* + * If we fail to add the chunk item here, we end up + * trying again at phase 2 of chunk allocation, at + * btrfs_create_pending_block_groups(). So ignore + * any error here. + */ + btrfs_chunk_alloc_add_chunk_item(trans, bg); + } } if (!ret) { diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 7b927425dc71..c72a71efcb18 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -97,6 +97,7 @@ struct btrfs_block_group { unsigned int removed:1; unsigned int to_copy:1; unsigned int relocating_repair:1; + unsigned int chunk_item_inserted:1; int disk_cache_state; @@ -268,8 +269,9 @@ void btrfs_reclaim_bgs_work(struct work_struct *work); void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info); void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg); int btrfs_read_block_groups(struct btrfs_fs_info *info); -int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, - u64 type, u64 chunk_offset, u64 size); +struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans, + u64 bytes_used, u64 type, + u64 chunk_offset, u64 size); void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans); int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, bool do_chunk_alloc); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 4bc3ca2cbd7d..c5c08c87e130 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -364,49 +364,6 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return 0; } -static struct extent_buffer *alloc_tree_block_no_bg_flush( - struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 parent_start, - const struct btrfs_disk_key *disk_key, - int level, - u64 hint, - u64 empty_size, - enum btrfs_lock_nesting nest) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - struct extent_buffer *ret; - - /* - * If we are COWing a node/leaf from the extent, chunk, device or free - * space trees, make sure that we do not finish block group creation of - * pending block groups. We do this to avoid a deadlock. - * COWing can result in allocation of a new chunk, and flushing pending - * block groups (btrfs_create_pending_block_groups()) can be triggered - * when finishing allocation of a new chunk. Creation of a pending block - * group modifies the extent, chunk, device and free space trees, - * therefore we could deadlock with ourselves since we are holding a - * lock on an extent buffer that btrfs_create_pending_block_groups() may - * try to COW later. - * For similar reasons, we also need to delay flushing pending block - * groups when splitting a leaf or node, from one of those trees, since - * we are holding a write lock on it and its parent or when inserting a - * new root node for one of those trees. - */ - if (root == fs_info->extent_root || - root == fs_info->chunk_root || - root == fs_info->dev_root || - root == fs_info->free_space_root) - trans->can_flush_pending_bgs = false; - - ret = btrfs_alloc_tree_block(trans, root, parent_start, - root->root_key.objectid, disk_key, level, - hint, empty_size, nest); - trans->can_flush_pending_bgs = true; - - return ret; -} - /* * does the dirty work in cow of a single block. The parent block (if * supplied) is updated to point to the new cow copy. The new buffer is marked @@ -455,8 +412,9 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent) parent_start = parent->start; - cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key, - level, search_start, empty_size, nest); + cow = btrfs_alloc_tree_block(trans, root, parent_start, + root->root_key.objectid, &disk_key, level, + search_start, empty_size, nest); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -2458,9 +2416,9 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, else btrfs_node_key(lower, &lower_key, 0); - c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level, - root->node->start, 0, - BTRFS_NESTING_NEW_ROOT); + c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, + &lower_key, level, root->node->start, 0, + BTRFS_NESTING_NEW_ROOT); if (IS_ERR(c)) return PTR_ERR(c); @@ -2589,8 +2547,9 @@ static noinline int split_node(struct btrfs_trans_handle *trans, mid = (c_nritems + 1) / 2; btrfs_node_key(c, &disk_key, mid); - split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level, - c->start, 0, BTRFS_NESTING_SPLIT); + split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, + &disk_key, level, c->start, 0, + BTRFS_NESTING_SPLIT); if (IS_ERR(split)) return PTR_ERR(split); @@ -3381,10 +3340,10 @@ again: * BTRFS_NESTING_SPLIT_THE_SPLITTENING if we need to, but for now just * use BTRFS_NESTING_NEW_ROOT. */ - right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0, - l->start, 0, num_doubles ? - BTRFS_NESTING_NEW_ROOT : - BTRFS_NESTING_SPLIT); + right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, + &disk_key, 0, l->start, 0, + num_doubles ? BTRFS_NESTING_NEW_ROOT : + BTRFS_NESTING_SPLIT); if (IS_ERR(right)) return PTR_ERR(right); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 443c348bc6f3..14b9fdc8aaa9 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -254,8 +254,11 @@ static inline int extwriter_counter_read(struct btrfs_transaction *trans) } /* - * To be called after all the new block groups attached to the transaction - * handle have been created (btrfs_create_pending_block_groups()). + * To be called after doing the chunk btree updates right after allocating a new + * chunk (after btrfs_chunk_alloc_add_chunk_item() is called), when removing a + * chunk after all chunk btree updates and after finishing the second phase of + * chunk allocation (btrfs_create_pending_block_groups()) in case some block + * group had its chunk item insertion delayed to the second phase. */ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) { @@ -264,8 +267,6 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) if (!trans->chunk_bytes_reserved) return; - WARN_ON_ONCE(!list_empty(&trans->new_bgs)); - btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv, trans->chunk_bytes_reserved, NULL); trans->chunk_bytes_reserved = 0; @@ -696,7 +697,6 @@ again: h->fs_info = root->fs_info; h->type = type; - h->can_flush_pending_bgs = true; INIT_LIST_HEAD(&h->new_bgs); smp_mb(); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index a18d67796b54..ba45065f9451 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -132,7 +132,7 @@ struct btrfs_trans_handle { short aborted; bool adding_csums; bool allocating_chunk; - bool can_flush_pending_bgs; + bool removing_chunk; bool reloc_reserved; bool in_fsync; struct btrfs_root *root; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 782e16795bc4..c6c14315b1c9 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1745,19 +1745,14 @@ again: extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); } else { - btrfs_handle_fs_error(fs_info, ret, "Slot search failed"); goto out; } *dev_extent_len = btrfs_dev_extent_length(leaf, extent); ret = btrfs_del_item(trans, root, path); - if (ret) { - btrfs_handle_fs_error(fs_info, ret, - "Failed to remove dev extent item"); - } else { + if (ret == 0) set_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags); - } out: btrfs_free_path(path); return ret; @@ -2942,7 +2937,7 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) u32 cur; struct btrfs_key key; - mutex_lock(&fs_info->chunk_mutex); + lockdep_assert_held(&fs_info->chunk_mutex); array_size = btrfs_super_sys_array_size(super_copy); ptr = super_copy->sys_chunk_array; @@ -2972,7 +2967,6 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) cur += len; } } - mutex_unlock(&fs_info->chunk_mutex); return ret; } @@ -3012,6 +3006,29 @@ struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info, return em; } +static int remove_chunk_item(struct btrfs_trans_handle *trans, + struct map_lookup *map, u64 chunk_offset) +{ + int i; + + /* + * Removing chunk items and updating the device items in the chunks btree + * requires holding the chunk_mutex. + * See the comment at btrfs_chunk_alloc() for the details. + */ + lockdep_assert_held(&trans->fs_info->chunk_mutex); + + for (i = 0; i < map->num_stripes; i++) { + int ret; + + ret = btrfs_update_device(trans, map->stripes[i].dev); + if (ret) + return ret; + } + + return btrfs_free_chunk(trans, chunk_offset); +} + int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -3032,14 +3049,16 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) return PTR_ERR(em); } map = em->map_lookup; - mutex_lock(&fs_info->chunk_mutex); - check_system_chunk(trans, map->type); - mutex_unlock(&fs_info->chunk_mutex); /* - * Take the device list mutex to prevent races with the final phase of - * a device replace operation that replaces the device object associated - * with map stripes (dev-replace.c:btrfs_dev_replace_finishing()). + * First delete the device extent items from the devices btree. + * We take the device_list_mutex to avoid racing with the finishing phase + * of a device replace operation. See the comment below before acquiring + * fs_info->chunk_mutex. Note that here we do not acquire the chunk_mutex + * because that can result in a deadlock when deleting the device extent + * items from the devices btree - COWing an extent buffer from the btree + * may result in allocating a new metadata chunk, which would attempt to + * lock again fs_info->chunk_mutex. */ mutex_lock(&fs_devices->device_list_mutex); for (i = 0; i < map->num_stripes; i++) { @@ -3061,18 +3080,73 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) btrfs_clear_space_info_full(fs_info); mutex_unlock(&fs_info->chunk_mutex); } - - ret = btrfs_update_device(trans, device); - if (ret) { - mutex_unlock(&fs_devices->device_list_mutex); - btrfs_abort_transaction(trans, ret); - goto out; - } } mutex_unlock(&fs_devices->device_list_mutex); - ret = btrfs_free_chunk(trans, chunk_offset); - if (ret) { + /* + * We acquire fs_info->chunk_mutex for 2 reasons: + * + * 1) Just like with the first phase of the chunk allocation, we must + * reserve system space, do all chunk btree updates and deletions, and + * update the system chunk array in the superblock while holding this + * mutex. This is for similar reasons as explained on the comment at + * the top of btrfs_chunk_alloc(); + * + * 2) Prevent races with the final phase of a device replace operation + * that replaces the device object associated with the map's stripes, + * because the device object's id can change at any time during that + * final phase of the device replace operation + * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the + * replaced device and then see it with an ID of + * BTRFS_DEV_REPLACE_DEVID, which would cause a failure when updating + * the device item, which does not exists on the chunk btree. + * The finishing phase of device replace acquires both the + * device_list_mutex and the chunk_mutex, in that order, so we are + * safe by just acquiring the chunk_mutex. + */ + trans->removing_chunk = true; + mutex_lock(&fs_info->chunk_mutex); + + check_system_chunk(trans, map->type); + + ret = remove_chunk_item(trans, map, chunk_offset); + /* + * Normally we should not get -ENOSPC since we reserved space before + * through the call to check_system_chunk(). + * + * Despite our system space_info having enough free space, we may not + * be able to allocate extents from its block groups, because all have + * an incompatible profile, which will force us to allocate a new system + * block group with the right profile, or right after we called + * check_system_space() above, a scrub turned the only system block group + * with enough free space into RO mode. + * This is explained with more detail at do_chunk_alloc(). + * + * So if we get -ENOSPC, allocate a new system chunk and retry once. + */ + if (ret == -ENOSPC) { + const u64 sys_flags = btrfs_system_alloc_profile(fs_info); + struct btrfs_block_group *sys_bg; + + sys_bg = btrfs_alloc_chunk(trans, sys_flags); + if (IS_ERR(sys_bg)) { + ret = PTR_ERR(sys_bg); + btrfs_abort_transaction(trans, ret); + goto out; + } + + ret = btrfs_chunk_alloc_add_chunk_item(trans, sys_bg); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + + ret = remove_chunk_item(trans, map, chunk_offset); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + } else if (ret) { btrfs_abort_transaction(trans, ret); goto out; } @@ -3087,6 +3161,15 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) } } + mutex_unlock(&fs_info->chunk_mutex); + trans->removing_chunk = false; + + /* + * We are done with chunk btree updates and deletions, so release the + * system space we previously reserved (with check_system_chunk()). + */ + btrfs_trans_release_chunk_metadata(trans); + ret = btrfs_remove_block_group(trans, chunk_offset, em); if (ret) { btrfs_abort_transaction(trans, ret); @@ -3094,6 +3177,10 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) } out: + if (trans->removing_chunk) { + mutex_unlock(&fs_info->chunk_mutex); + trans->removing_chunk = false; + } /* once for us */ free_extent_map(em); return ret; @@ -4860,13 +4947,12 @@ static int btrfs_add_system_chunk(struct btrfs_fs_info *fs_info, u32 array_size; u8 *ptr; - mutex_lock(&fs_info->chunk_mutex); + lockdep_assert_held(&fs_info->chunk_mutex); + array_size = btrfs_super_sys_array_size(super_copy); if (array_size + item_size + sizeof(disk_key) - > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) { - mutex_unlock(&fs_info->chunk_mutex); + > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) return -EFBIG; - } ptr = super_copy->sys_chunk_array + array_size; btrfs_cpu_key_to_disk(&disk_key, key); @@ -4875,7 +4961,6 @@ static int btrfs_add_system_chunk(struct btrfs_fs_info *fs_info, memcpy(ptr, chunk, item_size); item_size += sizeof(disk_key); btrfs_set_super_sys_array_size(super_copy, array_size + item_size); - mutex_unlock(&fs_info->chunk_mutex); return 0; } @@ -5225,13 +5310,14 @@ static int decide_stripe_size(struct btrfs_fs_devices *fs_devices, } } -static int create_chunk(struct btrfs_trans_handle *trans, +static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans, struct alloc_chunk_ctl *ctl, struct btrfs_device_info *devices_info) { struct btrfs_fs_info *info = trans->fs_info; struct map_lookup *map = NULL; struct extent_map_tree *em_tree; + struct btrfs_block_group *block_group; struct extent_map *em; u64 start = ctl->start; u64 type = ctl->type; @@ -5241,7 +5327,7 @@ static int create_chunk(struct btrfs_trans_handle *trans, map = kmalloc(map_lookup_size(ctl->num_stripes), GFP_NOFS); if (!map) - return -ENOMEM; + return ERR_PTR(-ENOMEM); map->num_stripes = ctl->num_stripes; for (i = 0; i < ctl->ndevs; ++i) { @@ -5263,7 +5349,7 @@ static int create_chunk(struct btrfs_trans_handle *trans, em = alloc_extent_map(); if (!em) { kfree(map); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags); em->map_lookup = map; @@ -5279,12 +5365,12 @@ static int create_chunk(struct btrfs_trans_handle *trans, if (ret) { write_unlock(&em_tree->lock); free_extent_map(em); - return ret; + return ERR_PTR(ret); } write_unlock(&em_tree->lock); - ret = btrfs_make_block_group(trans, 0, type, start, ctl->chunk_size); - if (ret) + block_group = btrfs_make_block_group(trans, 0, type, start, ctl->chunk_size); + if (IS_ERR(block_group)) goto error_del_extent; for (i = 0; i < map->num_stripes; i++) { @@ -5304,7 +5390,7 @@ static int create_chunk(struct btrfs_trans_handle *trans, check_raid56_incompat_flag(info, type); check_raid1c34_incompat_flag(info, type); - return 0; + return block_group; error_del_extent: write_lock(&em_tree->lock); @@ -5316,34 +5402,36 @@ error_del_extent: /* One for the tree reference */ free_extent_map(em); - return ret; + return block_group; } -int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type) +struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans, + u64 type) { struct btrfs_fs_info *info = trans->fs_info; struct btrfs_fs_devices *fs_devices = info->fs_devices; struct btrfs_device_info *devices_info = NULL; struct alloc_chunk_ctl ctl; + struct btrfs_block_group *block_group; int ret; lockdep_assert_held(&info->chunk_mutex); if (!alloc_profile_is_valid(type, 0)) { ASSERT(0); - return -EINVAL; + return ERR_PTR(-EINVAL); } if (list_empty(&fs_devices->alloc_list)) { if (btrfs_test_opt(info, ENOSPC_DEBUG)) btrfs_debug(info, "%s: no writable device", __func__); - return -ENOSPC; + return ERR_PTR(-ENOSPC); } if (!(type & BTRFS_BLOCK_GROUP_TYPE_MASK)) { btrfs_err(info, "invalid chunk type 0x%llx requested", type); ASSERT(0); - return -EINVAL; + return ERR_PTR(-EINVAL); } ctl.start = find_next_chunk(info); @@ -5353,46 +5441,43 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type) devices_info = kcalloc(fs_devices->rw_devices, sizeof(*devices_info), GFP_NOFS); if (!devices_info) - return -ENOMEM; + return ERR_PTR(-ENOMEM); ret = gather_device_info(fs_devices, &ctl, devices_info); - if (ret < 0) + if (ret < 0) { + block_group = ERR_PTR(ret); goto out; + } ret = decide_stripe_size(fs_devices, &ctl, devices_info); - if (ret < 0) + if (ret < 0) { + block_group = ERR_PTR(ret); goto out; + } - ret = create_chunk(trans, &ctl, devices_info); + block_group = create_chunk(trans, &ctl, devices_info); out: kfree(devices_info); - return ret; + return block_group; } /* - * Chunk allocation falls into two parts. The first part does work - * that makes the new allocated chunk usable, but does not do any operation - * that modifies the chunk tree. The second part does the work that - * requires modifying the chunk tree. This division is important for the - * bootstrap process of adding storage to a seed btrfs. + * This function, btrfs_finish_chunk_alloc(), belongs to phase 2. + * + * See the comment at btrfs_chunk_alloc() for details about the chunk allocation + * phases. */ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, u64 chunk_offset, u64 chunk_size) { struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_root *extent_root = fs_info->extent_root; - struct btrfs_root *chunk_root = fs_info->chunk_root; - struct btrfs_key key; struct btrfs_device *device; - struct btrfs_chunk *chunk; - struct btrfs_stripe *stripe; struct extent_map *em; struct map_lookup *map; - size_t item_size; u64 dev_offset; u64 stripe_size; - int i = 0; + int i; int ret = 0; em = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size); @@ -5400,53 +5485,117 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, return PTR_ERR(em); map = em->map_lookup; - item_size = btrfs_chunk_item_size(map->num_stripes); stripe_size = em->orig_block_len; - chunk = kzalloc(item_size, GFP_NOFS); - if (!chunk) { - ret = -ENOMEM; - goto out; - } - /* * Take the device list mutex to prevent races with the final phase of * a device replace operation that replaces the device object associated * with the map's stripes, because the device object's id can change * at any time during that final phase of the device replace operation - * (dev-replace.c:btrfs_dev_replace_finishing()). + * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the + * replaced device and then see it with an ID of BTRFS_DEV_REPLACE_DEVID, + * resulting in persisting a device extent item with such ID. */ mutex_lock(&fs_info->fs_devices->device_list_mutex); for (i = 0; i < map->num_stripes; i++) { device = map->stripes[i].dev; dev_offset = map->stripes[i].physical; - ret = btrfs_update_device(trans, device); - if (ret) - break; ret = btrfs_alloc_dev_extent(trans, device, chunk_offset, dev_offset, stripe_size); if (ret) break; } - if (ret) { - mutex_unlock(&fs_info->fs_devices->device_list_mutex); + mutex_unlock(&fs_info->fs_devices->device_list_mutex); + + free_extent_map(em); + return ret; +} + +/* + * This function, btrfs_chunk_alloc_add_chunk_item(), typically belongs to the + * phase 1 of chunk allocation. It belongs to phase 2 only when allocating system + * chunks. + * + * See the comment at btrfs_chunk_alloc() for details about the chunk allocation + * phases. + */ +int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans, + struct btrfs_block_group *bg) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_root *extent_root = fs_info->extent_root; + struct btrfs_root *chunk_root = fs_info->chunk_root; + struct btrfs_key key; + struct btrfs_chunk *chunk; + struct btrfs_stripe *stripe; + struct extent_map *em; + struct map_lookup *map; + size_t item_size; + int i; + int ret; + + /* + * We take the chunk_mutex for 2 reasons: + * + * 1) Updates and insertions in the chunk btree must be done while holding + * the chunk_mutex, as well as updating the system chunk array in the + * superblock. See the comment on top of btrfs_chunk_alloc() for the + * details; + * + * 2) To prevent races with the final phase of a device replace operation + * that replaces the device object associated with the map's stripes, + * because the device object's id can change at any time during that + * final phase of the device replace operation + * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the + * replaced device and then see it with an ID of BTRFS_DEV_REPLACE_DEVID, + * which would cause a failure when updating the device item, which does + * not exists, or persisting a stripe of the chunk item with such ID. + * Here we can't use the device_list_mutex because our caller already + * has locked the chunk_mutex, and the final phase of device replace + * acquires both mutexes - first the device_list_mutex and then the + * chunk_mutex. Using any of those two mutexes protects us from a + * concurrent device replace. + */ + lockdep_assert_held(&fs_info->chunk_mutex); + + em = btrfs_get_chunk_map(fs_info, bg->start, bg->length); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + btrfs_abort_transaction(trans, ret); + return ret; + } + + map = em->map_lookup; + item_size = btrfs_chunk_item_size(map->num_stripes); + + chunk = kzalloc(item_size, GFP_NOFS); + if (!chunk) { + ret = -ENOMEM; + btrfs_abort_transaction(trans, ret); goto out; } + for (i = 0; i < map->num_stripes; i++) { + struct btrfs_device *device = map->stripes[i].dev; + + ret = btrfs_update_device(trans, device); + if (ret) + goto out; + } + stripe = &chunk->stripe; for (i = 0; i < map->num_stripes; i++) { - device = map->stripes[i].dev; - dev_offset = map->stripes[i].physical; + struct btrfs_device *device = map->stripes[i].dev; + const u64 dev_offset = map->stripes[i].physical; btrfs_set_stack_stripe_devid(stripe, device->devid); btrfs_set_stack_stripe_offset(stripe, dev_offset); memcpy(stripe->dev_uuid, device->uuid, BTRFS_UUID_SIZE); stripe++; } - mutex_unlock(&fs_info->fs_devices->device_list_mutex); - btrfs_set_stack_chunk_length(chunk, chunk_size); + btrfs_set_stack_chunk_length(chunk, bg->length); btrfs_set_stack_chunk_owner(chunk, extent_root->root_key.objectid); btrfs_set_stack_chunk_stripe_len(chunk, map->stripe_len); btrfs_set_stack_chunk_type(chunk, map->type); @@ -5458,15 +5607,18 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID; key.type = BTRFS_CHUNK_ITEM_KEY; - key.offset = chunk_offset; + key.offset = bg->start; ret = btrfs_insert_item(trans, chunk_root, &key, chunk, item_size); - if (ret == 0 && map->type & BTRFS_BLOCK_GROUP_SYSTEM) { - /* - * TODO: Cleanup of inserted chunk root in case of - * failure. - */ + if (ret) + goto out; + + bg->chunk_item_inserted = 1; + + if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) { ret = btrfs_add_system_chunk(fs_info, &key, chunk, item_size); + if (ret) + goto out; } out: @@ -5479,16 +5631,41 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; u64 alloc_profile; - int ret; + struct btrfs_block_group *meta_bg; + struct btrfs_block_group *sys_bg; + + /* + * When adding a new device for sprouting, the seed device is read-only + * so we must first allocate a metadata and a system chunk. But before + * adding the block group items to the extent, device and chunk btrees, + * we must first: + * + * 1) Create both chunks without doing any changes to the btrees, as + * otherwise we would get -ENOSPC since the block groups from the + * seed device are read-only; + * + * 2) Add the device item for the new sprout device - finishing the setup + * of a new block group requires updating the device item in the chunk + * btree, so it must exist when we attempt to do it. The previous step + * ensures this does not fail with -ENOSPC. + * + * After that we can add the block group items to their btrees: + * update existing device item in the chunk btree, add a new block group + * item to the extent btree, add a new chunk item to the chunk btree and + * finally add the new device extent items to the devices btree. + */ alloc_profile = btrfs_metadata_alloc_profile(fs_info); - ret = btrfs_alloc_chunk(trans, alloc_profile); - if (ret) - return ret; + meta_bg = btrfs_alloc_chunk(trans, alloc_profile); + if (IS_ERR(meta_bg)) + return PTR_ERR(meta_bg); alloc_profile = btrfs_system_alloc_profile(fs_info); - ret = btrfs_alloc_chunk(trans, alloc_profile); - return ret; + sys_bg = btrfs_alloc_chunk(trans, alloc_profile); + if (IS_ERR(sys_bg)) + return PTR_ERR(sys_bg); + + return 0; } static inline int btrfs_chunk_max_errors(struct map_lookup *map) @@ -7415,10 +7592,18 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) total_dev++; } else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) { struct btrfs_chunk *chunk; + + /* + * We are only called at mount time, so no need to take + * fs_info->chunk_mutex. Plus, to avoid lockdep warnings, + * we always lock first fs_info->chunk_mutex before + * acquiring any locks on the chunk tree. This is a + * requirement for chunk allocation, see the comment on + * top of btrfs_chunk_alloc() for details. + */ + ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags)); chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); - mutex_lock(&fs_info->chunk_mutex); ret = read_one_chunk(&found_key, leaf, chunk); - mutex_unlock(&fs_info->chunk_mutex); if (ret) goto error; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index c7fc7caf575c..55a8ba244716 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -450,7 +450,8 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *map, struct btrfs_io_geometry *io_geom); int btrfs_read_sys_array(struct btrfs_fs_info *fs_info); int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info); -int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type); +struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans, + u64 type); void btrfs_mapping_tree_free(struct extent_map_tree *tree); blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num); @@ -509,6 +510,8 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info, u64 logical); int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, u64 chunk_offset, u64 chunk_size); +int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans, + struct btrfs_block_group *bg); int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset); struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info, u64 logical, u64 length); From abb99cfdaf0759f8a619e5fecf52ccccdf310c8c Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Mon, 28 Jun 2021 17:57:28 +0900 Subject: [PATCH 131/426] btrfs: properly split extent_map for REQ_OP_ZONE_APPEND Damien reported a test failure with btrfs/209. The test itself ran fine, but the fsck ran afterwards reported a corrupted filesystem. The filesystem corruption happens because we're splitting an extent and then writing the extent twice. We have to split the extent though, because we're creating too large extents for a REQ_OP_ZONE_APPEND operation. When dumping the extent tree, we can see two EXTENT_ITEMs at the same start address but different lengths. $ btrfs inspect dump-tree /dev/nullb1 -t extent ... item 19 key (269484032 EXTENT_ITEM 126976) itemoff 15470 itemsize 53 refs 1 gen 7 flags DATA extent data backref root FS_TREE objectid 257 offset 786432 count 1 item 20 key (269484032 EXTENT_ITEM 262144) itemoff 15417 itemsize 53 refs 1 gen 7 flags DATA extent data backref root FS_TREE objectid 257 offset 786432 count 1 The duplicated EXTENT_ITEMs originally come from wrongly split extent_map in extract_ordered_extent(). Since extract_ordered_extent() uses create_io_em() to split an existing extent_map, we will have split->orig_start != split->start. Then, it will be logged with non-zero "extent data offset". Finally, the logged entries are replayed into a duplicated EXTENT_ITEM. Introduce and use proper splitting function for extent_map. The function is intended to be simple and specific usage for extract_ordered_extent() e.g. not supporting compression case (we do not allow splitting compressed extent_map anyway). There was a question raised by Qu, in summary why we want to split the extent map (and not the bio): The problem is not the limit on the zone end, which as you mention is the same as the block group end. The problem is that data write use zone append (ZA) operations. ZA BIOs cannot be split so a large extent may need to be processed with multiple ZA BIOs, While that is also true for regular writes, the major difference is that ZA are "nameless" write operation giving back the written sectors on completion. And ZA operations may be reordered by the block layer (not intentionally though). Combine both of these characteristics and you can see that the data for a large extent may end up being shuffled when written resulting in data corruption and the impossibility to map the extent to some start sector. To avoid this problem, zoned btrfs uses the principle "one data extent == one ZA BIO". So large extents need to be split. This is unfortunate, but we can revisit this later and optimize, e.g. merge back together the fragments of an extent once written if they actually were written sequentially in the zone. Reported-by: Damien Le Moal Fixes: d22002fd37bd ("btrfs: zoned: split ordered extent when bio is sent") CC: stable@vger.kernel.org # 5.12+ CC: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/inode.c | 147 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 118 insertions(+), 29 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e6eb20987351..8f60314c36c5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2271,13 +2271,127 @@ static blk_status_t btrfs_submit_bio_start(struct inode *inode, struct bio *bio, return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); } +/* + * Split an extent_map at [start, start + len] + * + * This function is intended to be used only for extract_ordered_extent(). + */ +static int split_zoned_em(struct btrfs_inode *inode, u64 start, u64 len, + u64 pre, u64 post) +{ + struct extent_map_tree *em_tree = &inode->extent_tree; + struct extent_map *em; + struct extent_map *split_pre = NULL; + struct extent_map *split_mid = NULL; + struct extent_map *split_post = NULL; + int ret = 0; + int modified; + unsigned long flags; + + /* Sanity check */ + if (pre == 0 && post == 0) + return 0; + + split_pre = alloc_extent_map(); + if (pre) + split_mid = alloc_extent_map(); + if (post) + split_post = alloc_extent_map(); + if (!split_pre || (pre && !split_mid) || (post && !split_post)) { + ret = -ENOMEM; + goto out; + } + + ASSERT(pre + post < len); + + lock_extent(&inode->io_tree, start, start + len - 1); + write_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, start, len); + if (!em) { + ret = -EIO; + goto out_unlock; + } + + ASSERT(em->len == len); + ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); + ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE); + + flags = em->flags; + clear_bit(EXTENT_FLAG_PINNED, &em->flags); + clear_bit(EXTENT_FLAG_LOGGING, &flags); + modified = !list_empty(&em->list); + + /* First, replace the em with a new extent_map starting from * em->start */ + split_pre->start = em->start; + split_pre->len = (pre ? pre : em->len - post); + split_pre->orig_start = split_pre->start; + split_pre->block_start = em->block_start; + split_pre->block_len = split_pre->len; + split_pre->orig_block_len = split_pre->block_len; + split_pre->ram_bytes = split_pre->len; + split_pre->flags = flags; + split_pre->compress_type = em->compress_type; + split_pre->generation = em->generation; + + replace_extent_mapping(em_tree, em, split_pre, modified); + + /* + * Now we only have an extent_map at: + * [em->start, em->start + pre] if pre != 0 + * [em->start, em->start + em->len - post] if pre == 0 + */ + + if (pre) { + /* Insert the middle extent_map */ + split_mid->start = em->start + pre; + split_mid->len = em->len - pre - post; + split_mid->orig_start = split_mid->start; + split_mid->block_start = em->block_start + pre; + split_mid->block_len = split_mid->len; + split_mid->orig_block_len = split_mid->block_len; + split_mid->ram_bytes = split_mid->len; + split_mid->flags = flags; + split_mid->compress_type = em->compress_type; + split_mid->generation = em->generation; + add_extent_mapping(em_tree, split_mid, modified); + } + + if (post) { + split_post->start = em->start + em->len - post; + split_post->len = post; + split_post->orig_start = split_post->start; + split_post->block_start = em->block_start + em->len - post; + split_post->block_len = split_post->len; + split_post->orig_block_len = split_post->block_len; + split_post->ram_bytes = split_post->len; + split_post->flags = flags; + split_post->compress_type = em->compress_type; + split_post->generation = em->generation; + add_extent_mapping(em_tree, split_post, modified); + } + + /* Once for us */ + free_extent_map(em); + /* Once for the tree */ + free_extent_map(em); + +out_unlock: + write_unlock(&em_tree->lock); + unlock_extent(&inode->io_tree, start, start + len - 1); +out: + free_extent_map(split_pre); + free_extent_map(split_mid); + free_extent_map(split_post); + + return ret; +} + static blk_status_t extract_ordered_extent(struct btrfs_inode *inode, struct bio *bio, loff_t file_offset) { struct btrfs_ordered_extent *ordered; - struct extent_map *em = NULL, *em_new = NULL; - struct extent_map_tree *em_tree = &inode->extent_tree; u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT; + u64 file_len; u64 len = bio->bi_iter.bi_size; u64 end = start + len; u64 ordered_end; @@ -2317,41 +2431,16 @@ static blk_status_t extract_ordered_extent(struct btrfs_inode *inode, goto out; } + file_len = ordered->num_bytes; pre = start - ordered->disk_bytenr; post = ordered_end - end; ret = btrfs_split_ordered_extent(ordered, pre, post); if (ret) goto out; - - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, ordered->file_offset, len); - if (!em) { - read_unlock(&em_tree->lock); - ret = -EIO; - goto out; - } - read_unlock(&em_tree->lock); - - ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); - /* - * We cannot reuse em_new here but have to create a new one, as - * unpin_extent_cache() expects the start of the extent map to be the - * logical offset of the file, which does not hold true anymore after - * splitting. - */ - em_new = create_io_em(inode, em->start + pre, len, - em->start + pre, em->block_start + pre, len, - len, len, BTRFS_COMPRESS_NONE, - BTRFS_ORDERED_REGULAR); - if (IS_ERR(em_new)) { - ret = PTR_ERR(em_new); - goto out; - } - free_extent_map(em_new); + ret = split_zoned_em(inode, file_offset, file_len, pre, post); out: - free_extent_map(em); btrfs_put_ordered_extent(ordered); return errno_to_blk_status(ret); From 9cc0b837e14ae913581ec1ea6e979a738f71b0fd Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 6 Jul 2021 01:32:38 +0900 Subject: [PATCH 132/426] btrfs: don't block if we can't acquire the reclaim lock If we can't acquire the reclaim_bgs_lock on block group reclaim, we block until it is free. This can potentially stall for a long time. While reclaim of block groups is necessary for a good user experience on a zoned file system, there still is no need to block as it is best effort only, just like when we're deleting unused block groups. CC: stable@vger.kernel.org # 5.13 Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c557327b4545..9e7d9d0c763d 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1498,7 +1498,15 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) return; - mutex_lock(&fs_info->reclaim_bgs_lock); + /* + * Long running balances can keep us blocked here for eternity, so + * simply skip reclaim if we're unable to get the mutex. + */ + if (!mutex_trylock(&fs_info->reclaim_bgs_lock)) { + btrfs_exclop_finish(fs_info); + return; + } + spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->reclaim_bgs)) { u64 zone_unusable; From ea32af47f00a046a1f953370514d6d946efe0152 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 7 Jul 2021 12:23:45 +0100 Subject: [PATCH 133/426] btrfs: zoned: fix wrong mutex unlock on failure to allocate log root tree When syncing the log, if we fail to allocate the root node for the log root tree: 1) We are unlocking fs_info->tree_log_mutex, but at this point we have not yet locked this mutex; 2) We have locked fs_info->tree_root->log_mutex, but we end up not unlocking it; So fix this by unlocking fs_info->tree_root->log_mutex instead of fs_info->tree_log_mutex. Fixes: e75f9fd194090e ("btrfs: zoned: move log tree node allocation out of log_root_tree->log_mutex") CC: stable@vger.kernel.org # 5.13+ Reviewed-by: Nikolay Borisov Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index cab451d19547..dc6eb088d73e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3173,7 +3173,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (!log_root_tree->node) { ret = btrfs_alloc_log_tree_node(trans, log_root_tree); if (ret) { - mutex_unlock(&fs_info->tree_log_mutex); + mutex_unlock(&fs_info->tree_root->log_mutex); goto out; } } From 5616e895ecc56db8ba959e53638031a21353e0e2 Mon Sep 17 00:00:00 2001 From: SanjayKumar Jeyakumar Date: Wed, 7 Jul 2021 10:59:14 +0530 Subject: [PATCH 134/426] tools/runqslower: Use __state instead of state Commit 2f064a59a11f ("sched: Change task_struct::state") renamed task->state to task->__state in task_struct. Fix runqslower to use the new name of the field. Fixes: 2f064a59a11f ("sched: Change task_struct::state") Signed-off-by: SanjayKumar Jeyakumar Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210707052914.21473-1-vjsanjay@gmail.com --- tools/bpf/runqslower/runqslower.bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c index 645530ca7e98..ab9353f2fd46 100644 --- a/tools/bpf/runqslower/runqslower.bpf.c +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -74,7 +74,7 @@ int handle__sched_switch(u64 *ctx) u32 pid; /* ivcsw: treat like an enqueue event and store timestamp */ - if (prev->state == TASK_RUNNING) + if (prev->__state == TASK_RUNNING) trace_enqueue(prev); pid = next->pid; From 0d472c69c6a5e22cef9e5809e2f6d0ccd5934f4a Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 7 Jul 2021 15:50:57 +0800 Subject: [PATCH 135/426] stmmac: dwmac-loongson: Fix unsigned comparison to zero plat->phy_interface is unsigned integer, so the condition can't be less than zero and the warning will never printed. Fixes: 30bba69d7db4 ("stmmac: pci: Add dwmac support for Loongson") Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index e108b0d2bd28..4c9a37dd0d3f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -49,9 +49,9 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id { struct plat_stmmacenet_data *plat; struct stmmac_resources res; - bool mdio = false; - int ret, i; struct device_node *np; + int ret, i, phy_mode; + bool mdio = false; np = dev_of_node(&pdev->dev); @@ -108,10 +108,11 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (plat->bus_id < 0) plat->bus_id = pci_dev_id(pdev); - plat->phy_interface = device_get_phy_mode(&pdev->dev); - if (plat->phy_interface < 0) + phy_mode = device_get_phy_mode(&pdev->dev); + if (phy_mode < 0) dev_err(&pdev->dev, "phy_mode not found\n"); + plat->phy_interface = phy_mode; plat->interface = PHY_INTERFACE_MODE_GMII; pci_set_master(pdev); From eca81f09145d765c21dd8fb1ba5d874ca255c32c Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 7 Jul 2021 15:53:35 +0800 Subject: [PATCH 136/426] stmmac: platform: Fix signedness bug in stmmac_probe_config_dt() The "plat->phy_interface" variable is an enum and in this context GCC will treat it as an unsigned int so the error handling is never triggered. Fixes: b9f0b2f634c0 ("net: stmmac: platform: fix probe for ACPI devices") Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 072eff8079d0..5ca710844cc1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -397,6 +397,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat; struct stmmac_dma_cfg *dma_cfg; + int phy_mode; void *ret; int rc; @@ -412,10 +413,11 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) eth_zero_addr(mac); } - plat->phy_interface = device_get_phy_mode(&pdev->dev); - if (plat->phy_interface < 0) - return ERR_PTR(plat->phy_interface); + phy_mode = device_get_phy_mode(&pdev->dev); + if (phy_mode < 0) + return ERR_PTR(phy_mode); + plat->phy_interface = phy_mode; plat->interface = stmmac_of_get_mac_mode(np); if (plat->interface < 0) plat->interface = plat->phy_interface; From 24b671aad4eae423e1abf5b7f08d9a5235458b8d Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 7 Jul 2021 16:15:29 +0800 Subject: [PATCH 137/426] selftests: icmp_redirect: remove from checking for IPv6 route get If the kernel doesn't enable option CONFIG_IPV6_SUBTREES, the RTA_SRC info will not be exported to userspace in rt6_fill_node(). And ip cmd will not print "from ::" to the route output. So remove this check. Fixes: ec8105352869 ("selftests: Add redirect tests") Signed-off-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/icmp_redirect.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index c19ecc6a8614..3a111ac1edc3 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -315,7 +315,7 @@ check_exception() if [ "$with_redirect" = "yes" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ - grep -q "${H2_N2_IP6} from :: via ${R2_LLADDR} dev br0.*${mtu}" + grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0.*${mtu}" elif [ -n "${mtu}" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ grep -q "${mtu}" From 0e02bf5de46ae30074a2e1a8194a422a84482a1a Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 7 Jul 2021 16:15:30 +0800 Subject: [PATCH 138/426] selftests: icmp_redirect: IPv6 PMTU info should be cleared after redirect After redirecting, it's already a new path. So the old PMTU info should be cleared. The IPv6 test "mtu exception plus redirect" should only has redirect info without old PMTU. The IPv4 test can not be changed because of legacy. Fixes: ec8105352869 ("selftests: Add redirect tests") Signed-off-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/icmp_redirect.sh | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index 3a111ac1edc3..ecbf57f264ed 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -313,9 +313,10 @@ check_exception() fi log_test $? 0 "IPv4: ${desc}" - if [ "$with_redirect" = "yes" ]; then + # No PMTU info for test "redirect" and "mtu exception plus redirect" + if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ - grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0.*${mtu}" + grep -v "mtu" | grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0" elif [ -n "${mtu}" ]; then ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ grep -q "${mtu}" From 1d719254c139fb62fb8056fb496b6fd007e71550 Mon Sep 17 00:00:00 2001 From: Wei Li Date: Mon, 28 Jun 2021 11:04:09 +0800 Subject: [PATCH 139/426] tools: bpf: Fix error in 'make -C tools/ bpf_install' make[2]: *** No rule to make target 'install'. Stop. make[1]: *** [Makefile:122: runqslower_install] Error 2 make: *** [Makefile:116: bpf_install] Error 2 There is no rule for target 'install' in tools/bpf/runqslower/Makefile, and there is no need to install it, so just remove 'runqslower_install'. Fixes: 9c01546d26d2 ("tools/bpf: Add runqslower tool to tools/bpf") Signed-off-by: Wei Li Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210628030409.3459095-1-liwei391@huawei.com --- tools/bpf/Makefile | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 39bb322707b4..b11cfc86a3d0 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -97,7 +97,7 @@ clean: bpftool_clean runqslower_clean resolve_btfids_clean $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf $(Q)$(RM) -r -- $(OUTPUT)feature -install: $(PROGS) bpftool_install runqslower_install +install: $(PROGS) bpftool_install $(call QUIET_INSTALL, bpf_jit_disasm) $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin $(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm @@ -118,9 +118,6 @@ bpftool_clean: runqslower: $(call descend,runqslower) -runqslower_install: - $(call descend,runqslower,install) - runqslower_clean: $(call descend,runqslower,clean) @@ -131,5 +128,5 @@ resolve_btfids_clean: $(call descend,resolve_btfids,clean) .PHONY: all install clean bpftool bpftool_install bpftool_clean \ - runqslower runqslower_install runqslower_clean \ + runqslower runqslower_clean \ resolve_btfids resolve_btfids_clean From 271dbc31843244e5192f0f8a8be0da26995f944a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 7 Jul 2021 13:01:00 +0300 Subject: [PATCH 140/426] sock: unlock on error in sock_setsockopt() If copy_from_sockptr() then we need to unlock before returning. Fixes: d463126e23f1 ("net: sock: extend SO_TIMESTAMPING for PHC binding") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- net/core/sock.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 1c4b0468bc2c..a3eea6e0b30a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1123,8 +1123,10 @@ set_sndbuf: case SO_TIMESTAMPING_OLD: if (optlen == sizeof(timestamping)) { if (copy_from_sockptr(×tamping, optval, - sizeof(timestamping))) - return -EFAULT; + sizeof(timestamping))) { + ret = -EFAULT; + break; + } } else { memset(×tamping, 0, sizeof(timestamping)); timestamping.flags = val; From 92c4bed59bc0ef2a92b99ca1fe1c7107ffa3125c Mon Sep 17 00:00:00 2001 From: "Roy, UjjaL" Date: Wed, 7 Jul 2021 23:48:33 +0530 Subject: [PATCH 141/426] ipmr: Fix indentation issue Fixed indentation by removing extra spaces. Signed-off-by: Roy, UjjaL Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7b12a40dd465..2dda856ca260 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2119,7 +2119,7 @@ int ip_mr_input(struct sk_buff *skb) raw_rcv(mroute_sk, skb); return 0; } - } + } } /* already under rcu_read_lock() */ From 9615fe36b31d926f1c5107013b772dc226a6a7ca Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 7 Jul 2021 21:10:51 -0700 Subject: [PATCH 142/426] skbuff: Fix build with SKB extensions disabled We will fail to build with CONFIG_SKB_EXTENSIONS disabled after 8550ff8d8c75 ("skbuff: Release nfct refcount on napi stolen or re-used skbs") since there is an unconditionally use of skb_ext_find() without an appropriate stub. Simply build the code conditionally and properly guard against both COFNIG_SKB_EXTENSIONS as well as CONFIG_NET_TC_SKB_EXT being disabled. Fixes: Fixes: 8550ff8d8c75 ("skbuff: Release nfct refcount on napi stolen or re-used skbs") Signed-off-by: Florian Fainelli Reviewed-by: Roi Dayan Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 177a5aec0b6b..03c95a0867bb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6010,7 +6010,7 @@ static void gro_list_prepare(const struct list_head *head, maclen); diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); - +#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) if (!diffs) { struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT); struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT); @@ -6019,6 +6019,7 @@ static void gro_list_prepare(const struct list_head *head, if (!diffs && unlikely(skb_ext)) diffs |= p_ext->chain ^ skb_ext->chain; } +#endif NAPI_GRO_CB(p)->same_flow = !diffs; } From 65e2e6c1c20104ed19060a38f4edbf14e9f9a9a5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:51 +0200 Subject: [PATCH 143/426] pwm: sprd: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to sprd_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 8aae4b02e8a6 ("pwm: sprd: Add Spreadtrum PWM support") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-sprd.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/pwm/pwm-sprd.c b/drivers/pwm/pwm-sprd.c index f2a85e8dd941..7004f55bbf11 100644 --- a/drivers/pwm/pwm-sprd.c +++ b/drivers/pwm/pwm-sprd.c @@ -183,13 +183,10 @@ static int sprd_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, } } - if (state->period != cstate->period || - state->duty_cycle != cstate->duty_cycle) { - ret = sprd_pwm_config(spc, pwm, state->duty_cycle, - state->period); - if (ret) - return ret; - } + ret = sprd_pwm_config(spc, pwm, state->duty_cycle, + state->period); + if (ret) + return ret; sprd_pwm_write(spc, pwm->hwpwm, SPRD_PWM_ENABLE, 1); } else if (cstate->enabled) { From fe8255f80b8617bc67a58f4ca2b54b3b9b32ff84 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:52 +0200 Subject: [PATCH 144/426] pwm: spear: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to spear_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 98761ce4b91b ("pwm: spear: Implement .apply() callback") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-spear.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/pwm/pwm-spear.c b/drivers/pwm/pwm-spear.c index 48c31dac2f32..54c7990967dd 100644 --- a/drivers/pwm/pwm-spear.c +++ b/drivers/pwm/pwm-spear.c @@ -177,12 +177,9 @@ static int spear_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } - if (state->period != pwm->state.period || - state->duty_cycle != pwm->state.duty_cycle) { - err = spear_pwm_config(chip, pwm, state->duty_cycle, state->period); - if (err) - return err; - } + err = spear_pwm_config(chip, pwm, state->duty_cycle, state->period); + if (err) + return err; if (!pwm->state.enabled) return spear_pwm_enable(chip, pwm); From 25f70b8f3d15b8c188ecb49c6007b86f3e775c20 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:53 +0200 Subject: [PATCH 145/426] pwm: tiecap: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to ecap_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 0ca7acd84766 ("pwm: tiecap: Implement .apply() callback") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-tiecap.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/pwm/pwm-tiecap.c b/drivers/pwm/pwm-tiecap.c index dec3f1fb150c..35eb19a5a0d1 100644 --- a/drivers/pwm/pwm-tiecap.c +++ b/drivers/pwm/pwm-tiecap.c @@ -189,16 +189,13 @@ static int ecap_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } - if (state->period != pwm->state.period || - state->duty_cycle != pwm->state.duty_cycle) { - if (state->period > NSEC_PER_SEC) - return -ERANGE; + if (state->period > NSEC_PER_SEC) + return -ERANGE; - err = ecap_pwm_config(chip, pwm, state->duty_cycle, - state->period, enabled); - if (err) - return err; - } + err = ecap_pwm_config(chip, pwm, state->duty_cycle, + state->period, enabled); + if (err) + return err; if (!enabled) return ecap_pwm_enable(chip, pwm); From 7d6d4aaf2809f209c7d6bcab2f9ae76797051cfa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:54 +0200 Subject: [PATCH 146/426] pwm: berlin: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to berlin_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 30dffb42fcd4 ("pwm: berlin: Implement .apply() callback") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-berlin.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/pwm/pwm-berlin.c b/drivers/pwm/pwm-berlin.c index 5537b5f6dd5d..e157273fd2f7 100644 --- a/drivers/pwm/pwm-berlin.c +++ b/drivers/pwm/pwm-berlin.c @@ -190,12 +190,9 @@ static int berlin_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } - if (state->period != pwm->state.period || - state->duty_cycle != pwm->state.duty_cycle) { - err = berlin_pwm_config(chip, pwm, state->duty_cycle, state->period); - if (err) - return err; - } + err = berlin_pwm_config(chip, pwm, state->duty_cycle, state->period); + if (err) + return err; if (!enabled) return berlin_pwm_enable(chip, pwm); From f4a8e31ed84ec646c158824f423cb22d1f362bbf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 1 Jul 2021 10:27:55 +0200 Subject: [PATCH 147/426] pwm: ep93xx: Ensure configuring period and duty_cycle isn't wrongly skipped MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As the last call to ep93xx_pwm_apply() might have exited early if state->enabled was false, the values for period and duty_cycle stored in pwm->state might not have been written to hardware and it must be ensured that they are configured before enabling the PWM. Fixes: 6d45374af539 ("pwm: ep93xx: Implement .apply callback") Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-ep93xx.c | 91 +++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 48 deletions(-) diff --git a/drivers/pwm/pwm-ep93xx.c b/drivers/pwm/pwm-ep93xx.c index 8a3d781e6514..fc3cb7d669c6 100644 --- a/drivers/pwm/pwm-ep93xx.c +++ b/drivers/pwm/pwm-ep93xx.c @@ -64,6 +64,11 @@ static int ep93xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, int ret; struct ep93xx_pwm *ep93xx_pwm = to_ep93xx_pwm(chip); bool enabled = state->enabled; + void __iomem *base = ep93xx_pwm->base; + unsigned long long c; + unsigned long period_cycles; + unsigned long duty_cycles; + unsigned long term; if (state->polarity != pwm->state.polarity) { if (enabled) { @@ -97,58 +102,48 @@ static int ep93xx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } - if (state->period != pwm->state.period || - state->duty_cycle != pwm->state.duty_cycle) { - struct ep93xx_pwm *ep93xx_pwm = to_ep93xx_pwm(chip); - void __iomem *base = ep93xx_pwm->base; - unsigned long long c; - unsigned long period_cycles; - unsigned long duty_cycles; - unsigned long term; - - /* - * The clock needs to be enabled to access the PWM registers. - * Configuration can be changed at any time. - */ - if (!pwm_is_enabled(pwm)) { - ret = clk_prepare_enable(ep93xx_pwm->clk); - if (ret) - return ret; - } - - c = clk_get_rate(ep93xx_pwm->clk); - c *= state->period; - do_div(c, 1000000000); - period_cycles = c; - - c = period_cycles; - c *= state->duty_cycle; - do_div(c, state->period); - duty_cycles = c; - - if (period_cycles < 0x10000 && duty_cycles < 0x10000) { - term = readw(base + EP93XX_PWMx_TERM_COUNT); - - /* Order is important if PWM is running */ - if (period_cycles > term) { - writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT); - writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE); - } else { - writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE); - writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT); - } - ret = 0; - } else { - ret = -EINVAL; - } - - if (!pwm_is_enabled(pwm)) - clk_disable_unprepare(ep93xx_pwm->clk); - + /* + * The clock needs to be enabled to access the PWM registers. + * Configuration can be changed at any time. + */ + if (!pwm_is_enabled(pwm)) { + ret = clk_prepare_enable(ep93xx_pwm->clk); if (ret) return ret; } + c = clk_get_rate(ep93xx_pwm->clk); + c *= state->period; + do_div(c, 1000000000); + period_cycles = c; + + c = period_cycles; + c *= state->duty_cycle; + do_div(c, state->period); + duty_cycles = c; + + if (period_cycles < 0x10000 && duty_cycles < 0x10000) { + term = readw(base + EP93XX_PWMx_TERM_COUNT); + + /* Order is important if PWM is running */ + if (period_cycles > term) { + writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT); + writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE); + } else { + writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE); + writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT); + } + ret = 0; + } else { + ret = -EINVAL; + } + + if (!pwm_is_enabled(pwm)) + clk_disable_unprepare(ep93xx_pwm->clk); + + if (ret) + return ret; + if (!enabled) { ret = clk_prepare_enable(ep93xx_pwm->clk); if (ret) From c7bb4b89033b764eb07db4e060548a6311d801ee Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Jul 2021 00:21:09 -0700 Subject: [PATCH 148/426] ipv6: tcp: drop silly ICMPv6 packet too big messages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While TCP stack scales reasonably well, there is still one part that can be used to DDOS it. IPv6 Packet too big messages have to lookup/insert a new route, and if abused by attackers, can easily put hosts under high stress, with many cpus contending on a spinlock while one is stuck in fib6_run_gc() ip6_protocol_deliver_rcu() icmpv6_rcv() icmpv6_notify() tcp_v6_err() tcp_v6_mtu_reduced() inet6_csk_update_pmtu() ip6_rt_update_pmtu() __ip6_rt_update_pmtu() ip6_rt_cache_alloc() ip6_dst_alloc() dst_alloc() ip6_dst_gc() fib6_run_gc() spin_lock_bh() ... Some of our servers have been hit by malicious ICMPv6 packets trying to _increase_ the MTU/MSS of TCP flows. We believe these ICMPv6 packets are a result of a bug in one ISP stack, since they were blindly sent back for _every_ (small) packet sent to them. These packets are for one TCP flow: 09:24:36.266491 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 09:24:36.266509 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 09:24:36.316688 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 09:24:36.316704 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 09:24:36.608151 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240 TCP stack can filter some silly requests : 1) MTU below IPV6_MIN_MTU can be filtered early in tcp_v6_err() 2) tcp_v6_mtu_reduced() can drop requests trying to increase current MSS. This tests happen before the IPv6 routing stack is entered, thus removing the potential contention and route exhaustion. Note that IPv6 stack was performing these checks, but too late (ie : after the route has been added, and after the potential garbage collect war) v2: fix typo caught by Martin, thanks ! v3: exports tcp_mtu_to_mss(), caught by David, thanks ! Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reviewed-by: Maciej Żenczykowski Cc: Martin KaFai Lau Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 1 + net/ipv6/tcp_ipv6.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bde781f46b41..29553fce8502 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1732,6 +1732,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } +EXPORT_SYMBOL(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 593c32fe57ed..323989927a0a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -348,11 +348,20 @@ failure: static void tcp_v6_mtu_reduced(struct sock *sk) { struct dst_entry *dst; + u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - dst = inet6_csk_update_pmtu(sk, READ_ONCE(tcp_sk(sk)->mtu_info)); + mtu = READ_ONCE(tcp_sk(sk)->mtu_info); + + /* Drop requests trying to increase our current mss. + * Check done in __ip6_rt_update_pmtu() is too late. + */ + if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache) + return; + + dst = inet6_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -433,6 +442,8 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } if (type == ICMPV6_PKT_TOOBIG) { + u32 mtu = ntohl(info); + /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). @@ -443,7 +454,11 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!ip6_sk_accept_pmtu(sk)) goto out; - WRITE_ONCE(tp->mtu_info, ntohl(info)); + if (mtu < IPV6_MIN_MTU) + goto out; + + WRITE_ONCE(tp->mtu_info, mtu); + if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, From debdd8e31895fdd1e2cfeb7a5aff1c83e49a91ba Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Thu, 8 Jul 2021 11:04:08 -0700 Subject: [PATCH 149/426] ptp: Relocate lookup cookie to correct block. An earlier commit set the pps_lookup cookie, but the line was somehow added to the wrong code block. Correct this. Fixes: 8602e40fc813 ("ptp: Set lookup cookie when creating a PTP PPS source.") Signed-off-by: Jonathan Lemon Signed-off-by: Dario Binacchi Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index ce6d9fc85607..4dfc52e06704 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -232,7 +232,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, pr_err("failed to create ptp aux_worker %d\n", err); goto kworker_err; } - ptp->pps_source->lookup_cookie = ptp; } /* PTP virtual clock is being registered under physical clock */ @@ -268,6 +267,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, pr_err("failed to register pps source\n"); goto no_pps; } + ptp->pps_source->lookup_cookie = ptp; } /* Initialize a new device of our class in our clock structure. */ From b9d233ea21f192702f8bbf3f5f640e2dde308b25 Mon Sep 17 00:00:00 2001 From: Gatis Peisenieks Date: Thu, 8 Jul 2021 12:49:04 +0300 Subject: [PATCH 150/426] atl1c: fix Mikrotik 10/25G NIC detection Since Mikrotik 10/25G NIC MDIO op emulation is not 100% reliable, on rare occasions it can happen that some physical functions of the NIC do not get initialized due to timeouted early MDIO op. This changes the atl1c probe on Mikrotik 10/25G NIC not to depend on MDIO op emulation. Signed-off-by: Gatis Peisenieks Signed-off-by: David S. Miller --- drivers/net/ethernet/atheros/atl1c/atl1c_hw.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c index 7dff20350865..f19370c33444 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c @@ -594,6 +594,11 @@ int atl1c_phy_init(struct atl1c_hw *hw) int ret_val; u16 mii_bmcr_data = BMCR_RESET; + if (hw->nic_type == athr_mt) { + hw->phy_configured = true; + return 0; + } + if ((atl1c_read_phy_reg(hw, MII_PHYSID1, &hw->phy_id1) != 0) || (atl1c_read_phy_reg(hw, MII_PHYSID2, &hw->phy_id2) != 0)) { dev_err(&pdev->dev, "Error get phy ID\n"); From c34269041185dad1bab7a34f42ef9fab967a1684 Mon Sep 17 00:00:00 2001 From: Aaron Ma Date: Thu, 8 Jul 2021 21:17:10 +0800 Subject: [PATCH 151/426] mt76: mt7921: continue to probe driver when fw already downloaded When reboot system, no power cycles, firmware is already downloaded, return -EIO will break driver as error: mt7921e: probe of 0000:03:00.0 failed with error -5 Skip firmware download and continue to probe. Signed-off-by: Aaron Ma Fixes: 1c099ab44727c ("mt76: mt7921: add MCU support") Signed-off-by: David S. Miller --- drivers/net/wireless/mediatek/mt76/mt7921/mcu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index c2c4dc196802..cd690c64f65b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -931,7 +931,7 @@ static int mt7921_load_firmware(struct mt7921_dev *dev) ret = mt76_get_field(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY); if (ret) { dev_dbg(dev->mt76.dev, "Firmware is already download\n"); - return -EIO; + goto fw_loaded; } ret = mt7921_load_patch(dev); @@ -949,6 +949,7 @@ static int mt7921_load_firmware(struct mt7921_dev *dev) return -EIO; } +fw_loaded: mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_FWDL], false); #ifdef CONFIG_PM From 015fe6fd29c4b9ac0f61b8c4455ef88e6018b9cc Mon Sep 17 00:00:00 2001 From: Shahjada Abul Husain Date: Thu, 8 Jul 2021 21:51:56 +0530 Subject: [PATCH 152/426] cxgb4: fix IRQ free race during driver unload IRQs are requested during driver's ndo_open() and then later freed up in disable_interrupts() during driver unload. A race exists where driver can set the CXGB4_FULL_INIT_DONE flag in ndo_open() after the disable_interrupts() in driver unload path checks it, and hence misses calling free_irq(). Fix by unregistering netdevice first and sync with driver's ndo_open(). This ensures disable_interrupts() checks the flag correctly and frees up the IRQs properly. Fixes: b37987e8db5f ("cxgb4: Disable interrupts and napi before unregistering netdev") Signed-off-by: Shahjada Abul Husain Signed-off-by: Raju Rangoju Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 18 ++++++++++-------- drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c | 3 +++ 2 files changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 9a2b166d651e..dbf9a0e6601d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2643,6 +2643,9 @@ static void detach_ulds(struct adapter *adap) { unsigned int i; + if (!is_uld(adap)) + return; + mutex_lock(&uld_mutex); list_del(&adap->list_node); @@ -7141,10 +7144,13 @@ static void remove_one(struct pci_dev *pdev) */ destroy_workqueue(adapter->workq); - if (is_uld(adapter)) { - detach_ulds(adapter); - t4_uld_clean_up(adapter); - } + detach_ulds(adapter); + + for_each_port(adapter, i) + if (adapter->port[i]->reg_state == NETREG_REGISTERED) + unregister_netdev(adapter->port[i]); + + t4_uld_clean_up(adapter); adap_free_hma_mem(adapter); @@ -7152,10 +7158,6 @@ static void remove_one(struct pci_dev *pdev) cxgb4_free_mps_ref_entries(adapter); - for_each_port(adapter, i) - if (adapter->port[i]->reg_state == NETREG_REGISTERED) - unregister_netdev(adapter->port[i]); - debugfs_remove_recursive(adapter->debugfs_root); if (!is_t4(adapter->params.chip)) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c index 743af9e654aa..17faac715882 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c @@ -581,6 +581,9 @@ void t4_uld_clean_up(struct adapter *adap) { unsigned int i; + if (!is_uld(adap)) + return; + mutex_lock(&uld_mutex); for (i = 0; i < CXGB4_ULD_MAX; i++) { if (!adap->uld[i].handle) From 96248d6da65744e1baaa29e5c4e5dc233e29838b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 8 Jul 2021 10:33:10 -0700 Subject: [PATCH 153/426] net: microchip: sparx5: fix kconfig warning PHY_SPARX5_SERDES depends on OF so SPARX5_SWITCH should also depend on OF since 'select' does not follow any dependencies. WARNING: unmet direct dependencies detected for PHY_SPARX5_SERDES Depends on [n]: (ARCH_SPARX5 || COMPILE_TEST [=n]) && OF [=n] && HAS_IOMEM [=y] Selected by [y]: - SPARX5_SWITCH [=y] && NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_MICROCHIP [=y] && NET_SWITCHDEV [=y] && HAS_IOMEM [=y] Fixes: 3cfa11bac9bb ("net: sparx5: add the basic sparx5 driver") Signed-off-by: Randy Dunlap Cc: Lars Povlsen Cc: Steen Hegelund Cc: UNGLinuxDriver@microchip.com Cc: linux-arm-kernel@lists.infradead.org Cc: "David S. Miller" Cc: Jakub Kicinski Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/sparx5/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig index a80419d8d4b5..ac403d43c74c 100644 --- a/drivers/net/ethernet/microchip/sparx5/Kconfig +++ b/drivers/net/ethernet/microchip/sparx5/Kconfig @@ -2,6 +2,7 @@ config SPARX5_SWITCH tristate "Sparx5 switch driver" depends on NET_SWITCHDEV depends on HAS_IOMEM + depends on OF select PHYLINK select PHY_SPARX5_SERDES select RESET_CONTROLLER From 27fa107d3b8d13a57cdd7c7a40bd6548d4b9cef8 Mon Sep 17 00:00:00 2001 From: Ivan Mikhaylov Date: Thu, 8 Jul 2021 15:27:52 +0300 Subject: [PATCH 154/426] net/ncsi: fix restricted cast warning of sparse Sparse reports: net/ncsi/ncsi-rsp.c:406:24: warning: cast to restricted __be32 net/ncsi/ncsi-manage.c:732:33: warning: cast to restricted __be32 net/ncsi/ncsi-manage.c:756:25: warning: cast to restricted __be32 net/ncsi/ncsi-manage.c:779:25: warning: cast to restricted __be32 Signed-off-by: Ivan Mikhaylov Signed-off-by: David S. Miller --- net/ncsi/ncsi-manage.c | 6 +++--- net/ncsi/ncsi-rsp.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index ca04b6df1341..42b54a3da2e6 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -700,7 +700,7 @@ static int ncsi_oem_gma_handler_bcm(struct ncsi_cmd_arg *nca) nca->payload = NCSI_OEM_BCM_CMD_GMA_LEN; memset(data, 0, NCSI_OEM_BCM_CMD_GMA_LEN); - *(unsigned int *)data = ntohl(NCSI_OEM_MFR_BCM_ID); + *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_BCM_ID); data[5] = NCSI_OEM_BCM_CMD_GMA; nca->data = data; @@ -724,7 +724,7 @@ static int ncsi_oem_gma_handler_mlx(struct ncsi_cmd_arg *nca) nca->payload = NCSI_OEM_MLX_CMD_GMA_LEN; memset(&u, 0, sizeof(u)); - u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID); + u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID); u.data_u8[5] = NCSI_OEM_MLX_CMD_GMA; u.data_u8[6] = NCSI_OEM_MLX_CMD_GMA_PARAM; @@ -747,7 +747,7 @@ static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca) int ret = 0; memset(&u, 0, sizeof(u)); - u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID); + u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID); u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF; u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM; memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET], diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 888ccc2d4e34..04bc50be5c01 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -403,7 +403,7 @@ static int ncsi_rsp_handler_ev(struct ncsi_request *nr) /* Update to VLAN mode */ cmd = (struct ncsi_cmd_ev_pkt *)skb_network_header(nr->cmd); ncm->enable = 1; - ncm->data[0] = ntohl(cmd->mode); + ncm->data[0] = ntohl((__force __be32)cmd->mode); return 0; } From abd2fddc94a619b96bf41c60429d4c32bd118e17 Mon Sep 17 00:00:00 2001 From: Ivan Mikhaylov Date: Thu, 8 Jul 2021 15:27:53 +0300 Subject: [PATCH 155/426] net/ncsi: add NCSI Intel OEM command to keep PHY up This allows to keep PHY link up and prevents any channel resets during the host load. It is KEEP_PHY_LINK_UP option(Veto bit) in i210 datasheet which block PHY reset and power state changes. Signed-off-by: Ivan Mikhaylov Signed-off-by: David S. Miller --- net/ncsi/Kconfig | 6 ++++++ net/ncsi/internal.h | 5 +++++ net/ncsi/ncsi-manage.c | 45 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 56 insertions(+) diff --git a/net/ncsi/Kconfig b/net/ncsi/Kconfig index 93309081f5a4..ea1dd32b6b1f 100644 --- a/net/ncsi/Kconfig +++ b/net/ncsi/Kconfig @@ -17,3 +17,9 @@ config NCSI_OEM_CMD_GET_MAC help This allows to get MAC address from NCSI firmware and set them back to controller. +config NCSI_OEM_CMD_KEEP_PHY + bool "Keep PHY Link up" + depends on NET_NCSI + help + This allows to keep PHY link up and prevents any channel resets during + the host load. diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index cbbb0de4750a..0b6cfd3b31e0 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -78,6 +78,9 @@ enum { /* OEM Vendor Manufacture ID */ #define NCSI_OEM_MFR_MLX_ID 0x8119 #define NCSI_OEM_MFR_BCM_ID 0x113d +#define NCSI_OEM_MFR_INTEL_ID 0x157 +/* Intel specific OEM command */ +#define NCSI_OEM_INTEL_CMD_KEEP_PHY 0x20 /* CMD ID for Keep PHY up */ /* Broadcom specific OEM Command */ #define NCSI_OEM_BCM_CMD_GMA 0x01 /* CMD ID for Get MAC */ /* Mellanox specific OEM Command */ @@ -86,6 +89,7 @@ enum { #define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */ #define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */ /* OEM Command payload lengths*/ +#define NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN 7 #define NCSI_OEM_BCM_CMD_GMA_LEN 12 #define NCSI_OEM_MLX_CMD_GMA_LEN 8 #define NCSI_OEM_MLX_CMD_SMAF_LEN 60 @@ -271,6 +275,7 @@ enum { ncsi_dev_state_probe_mlx_gma, ncsi_dev_state_probe_mlx_smaf, ncsi_dev_state_probe_cis, + ncsi_dev_state_probe_keep_phy, ncsi_dev_state_probe_gvi, ncsi_dev_state_probe_gc, ncsi_dev_state_probe_gls, diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 42b54a3da2e6..89c7742cd72e 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -689,6 +689,35 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, return 0; } +#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) + +static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca) +{ + unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN]; + int ret = 0; + + nca->payload = NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN; + + memset(data, 0, NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN); + *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID); + + data[4] = NCSI_OEM_INTEL_CMD_KEEP_PHY; + + /* PHY Link up attribute */ + data[6] = 0x1; + + nca->data = data; + + ret = ncsi_xmit_cmd(nca); + if (ret) + netdev_err(nca->ndp->ndev.dev, + "NCSI: Failed to transmit cmd 0x%x during configure\n", + nca->type); + return ret; +} + +#endif + #if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) /* NCSI OEM Command APIs */ @@ -1392,7 +1421,23 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) } nd->state = ncsi_dev_state_probe_gvi; + if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)) + nd->state = ncsi_dev_state_probe_keep_phy; break; +#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) + case ncsi_dev_state_probe_keep_phy: + ndp->pending_req_num = 1; + + nca.type = NCSI_PKT_CMD_OEM; + nca.package = ndp->active_package->id; + nca.channel = 0; + ret = ncsi_oem_keep_phy_intel(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_probe_gvi; + break; +#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */ case ncsi_dev_state_probe_gvi: case ncsi_dev_state_probe_gc: case ncsi_dev_state_probe_gls: From 163f5de509a8ec193df94a9b9afbeb1a9e3f46a6 Mon Sep 17 00:00:00 2001 From: Ivan Mikhaylov Date: Thu, 8 Jul 2021 15:27:54 +0300 Subject: [PATCH 156/426] net/ncsi: add dummy response handler for Intel boards Add the dummy response handler for Intel boards to prevent incorrect handling of OEM commands. Signed-off-by: Ivan Mikhaylov Signed-off-by: David S. Miller --- net/ncsi/ncsi-rsp.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 04bc50be5c01..d48374894817 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -699,12 +699,19 @@ static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr) return 0; } +/* Response handler for Intel card */ +static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr) +{ + return 0; +} + static struct ncsi_rsp_oem_handler { unsigned int mfr_id; int (*handler)(struct ncsi_request *nr); } ncsi_rsp_oem_handlers[] = { { NCSI_OEM_MFR_MLX_ID, ncsi_rsp_handler_oem_mlx }, - { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm } + { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm }, + { NCSI_OEM_MFR_INTEL_ID, ncsi_rsp_handler_oem_intel } }; /* Response handler for OEM command */ From 2b452550a203d88112eaf0ba9fc4b750a000b496 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 8 Jul 2021 18:55:32 -0700 Subject: [PATCH 157/426] net: bcmgenet: Ensure all TX/RX queues DMAs are disabled Make sure that we disable each of the TX and RX queues in the TDMA and RDMA control registers. This is a correctness change to be symmetrical with the code that enables the TX and RX queues. Tested-by: Maxime Ripard Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 35e9956e930c..db74241935ab 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3238,15 +3238,21 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv, /* Returns a reusable dma control register value */ static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) { + unsigned int i; u32 reg; u32 dma_ctrl; /* disable DMA */ dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN; + for (i = 0; i < priv->hw_params->tx_queues; i++) + dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT)); reg = bcmgenet_tdma_readl(priv, DMA_CTRL); reg &= ~dma_ctrl; bcmgenet_tdma_writel(priv, reg, DMA_CTRL); + dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN; + for (i = 0; i < priv->hw_params->rx_queues; i++) + dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT)); reg = bcmgenet_rdma_readl(priv, DMA_CTRL); reg &= ~dma_ctrl; bcmgenet_rdma_writel(priv, reg, DMA_CTRL); From f263a81451c12da5a342d90572e317e611846f2c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 7 Jul 2021 15:38:47 -0700 Subject: [PATCH 158/426] bpf: Track subprog poke descriptors correctly and fix use-after-free Subprograms are calling map_poke_track(), but on program release there is no hook to call map_poke_untrack(). However, on program release, the aux memory (and poke descriptor table) is freed even though we still have a reference to it in the element list of the map aux data. When we run map_poke_run(), we then end up accessing free'd memory, triggering KASAN in prog_array_map_poke_run(): [...] [ 402.824689] BUG: KASAN: use-after-free in prog_array_map_poke_run+0xc2/0x34e [ 402.824698] Read of size 4 at addr ffff8881905a7940 by task hubble-fgs/4337 [ 402.824705] CPU: 1 PID: 4337 Comm: hubble-fgs Tainted: G I 5.12.0+ #399 [ 402.824715] Call Trace: [ 402.824719] dump_stack+0x93/0xc2 [ 402.824727] print_address_description.constprop.0+0x1a/0x140 [ 402.824736] ? prog_array_map_poke_run+0xc2/0x34e [ 402.824740] ? prog_array_map_poke_run+0xc2/0x34e [ 402.824744] kasan_report.cold+0x7c/0xd8 [ 402.824752] ? prog_array_map_poke_run+0xc2/0x34e [ 402.824757] prog_array_map_poke_run+0xc2/0x34e [ 402.824765] bpf_fd_array_map_update_elem+0x124/0x1a0 [...] The elements concerned are walked as follows: for (i = 0; i < elem->aux->size_poke_tab; i++) { poke = &elem->aux->poke_tab[i]; [...] The access to size_poke_tab is a 4 byte read, verified by checking offsets in the KASAN dump: [ 402.825004] The buggy address belongs to the object at ffff8881905a7800 which belongs to the cache kmalloc-1k of size 1024 [ 402.825008] The buggy address is located 320 bytes inside of 1024-byte region [ffff8881905a7800, ffff8881905a7c00) The pahole output of bpf_prog_aux: struct bpf_prog_aux { [...] /* --- cacheline 5 boundary (320 bytes) --- */ u32 size_poke_tab; /* 320 4 */ [...] In general, subprograms do not necessarily manage their own data structures. For example, BTF func_info and linfo are just pointers to the main program structure. This allows reference counting and cleanup to be done on the latter which simplifies their management a bit. The aux->poke_tab struct, however, did not follow this logic. The initial proposed fix for this use-after-free bug further embedded poke data tracking into the subprogram with proper reference counting. However, Daniel and Alexei questioned why we were treating these objects special; I agree, its unnecessary. The fix here removes the per subprogram poke table allocation and map tracking and instead simply points the aux->poke_tab pointer at the main programs poke table. This way, map tracking is simplified to the main program and we do not need to manage them per subprogram. This also means, bpf_prog_free_deferred(), which unwinds the program reference counting and kfrees objects, needs to ensure that we don't try to double free the poke_tab when free'ing the subprog structures. This is easily solved by NULL'ing the poke_tab pointer. The second detail is to ensure that per subprogram JIT logic only does fixups on poke_tab[] entries it owns. To do this, we add a pointer in the poke structure to point at the subprogram value so JITs can easily check while walking the poke_tab structure if the current entry belongs to the current program. The aux pointer is stable and therefore suitable for such comparison. On the jit_subprogs() error path, we omit cleaning up the poke->aux field because these are only ever referenced from the JIT side, but on error we will never make it to the JIT, so its fine to leave them dangling. Removing these pointers would complicate the error path for no reason. However, we do need to untrack all poke descriptors from the main program as otherwise they could race with the freeing of JIT memory from the subprograms. Lastly, a748c6975dea3 ("bpf: propagate poke descriptors to subprograms") had an off-by-one on the subprogram instruction index range check as it was testing 'insn_idx >= subprog_start && insn_idx <= subprog_end'. However, subprog_end is the next subprogram's start instruction. Fixes: a748c6975dea3 ("bpf: propagate poke descriptors to subprograms") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210707223848.14580-2-john.fastabend@gmail.com --- arch/x86/net/bpf_jit_comp.c | 3 ++ include/linux/bpf.h | 1 + kernel/bpf/core.c | 8 ++++- kernel/bpf/verifier.c | 60 +++++++++++++------------------------ 4 files changed, 32 insertions(+), 40 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e835164189f1..4b951458c9fc 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -570,6 +570,9 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) for (i = 0; i < prog->aux->size_poke_tab; i++) { poke = &prog->aux->poke_tab[i]; + if (poke->aux && poke->aux != prog->aux) + continue; + WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable)); if (poke->reason != BPF_POKE_REASON_TAIL_CALL) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f309fc1509f2..e8e2b0393ca9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -780,6 +780,7 @@ struct bpf_jit_poke_descriptor { void *tailcall_target; void *tailcall_bypass; void *bypass_addr; + void *aux; union { struct { struct bpf_map *map; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 034ad93a1ad7..9b1577498373 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2236,8 +2236,14 @@ static void bpf_prog_free_deferred(struct work_struct *work) #endif if (aux->dst_trampoline) bpf_trampoline_put(aux->dst_trampoline); - for (i = 0; i < aux->func_cnt; i++) + for (i = 0; i < aux->func_cnt; i++) { + /* We can just unlink the subprog poke descriptor table as + * it was originally linked to the main program and is also + * released along with it. + */ + aux->func[i]->aux->poke_tab = NULL; bpf_jit_free(aux->func[i]); + } if (aux->func_cnt) { kfree(aux->func); bpf_prog_unlock_free(aux->prog); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index be38bb930bf1..42a4063de7cd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -12121,33 +12121,19 @@ static int jit_subprogs(struct bpf_verifier_env *env) goto out_free; func[i]->is_func = 1; func[i]->aux->func_idx = i; - /* the btf and func_info will be freed only at prog->aux */ + /* Below members will be freed only at prog->aux */ func[i]->aux->btf = prog->aux->btf; func[i]->aux->func_info = prog->aux->func_info; + func[i]->aux->poke_tab = prog->aux->poke_tab; + func[i]->aux->size_poke_tab = prog->aux->size_poke_tab; for (j = 0; j < prog->aux->size_poke_tab; j++) { - u32 insn_idx = prog->aux->poke_tab[j].insn_idx; - int ret; + struct bpf_jit_poke_descriptor *poke; - if (!(insn_idx >= subprog_start && - insn_idx <= subprog_end)) - continue; - - ret = bpf_jit_add_poke_descriptor(func[i], - &prog->aux->poke_tab[j]); - if (ret < 0) { - verbose(env, "adding tail call poke descriptor failed\n"); - goto out_free; - } - - func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1; - - map_ptr = func[i]->aux->poke_tab[ret].tail_call.map; - ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux); - if (ret < 0) { - verbose(env, "tracking tail call prog failed\n"); - goto out_free; - } + poke = &prog->aux->poke_tab[j]; + if (poke->insn_idx < subprog_end && + poke->insn_idx >= subprog_start) + poke->aux = func[i]->aux; } /* Use bpf_prog_F_tag to indicate functions in stack traces. @@ -12178,18 +12164,6 @@ static int jit_subprogs(struct bpf_verifier_env *env) cond_resched(); } - /* Untrack main program's aux structs so that during map_poke_run() - * we will not stumble upon the unfilled poke descriptors; each - * of the main program's poke descs got distributed across subprogs - * and got tracked onto map, so we are sure that none of them will - * be missed after the operation below - */ - for (i = 0; i < prog->aux->size_poke_tab; i++) { - map_ptr = prog->aux->poke_tab[i].tail_call.map; - - map_ptr->ops->map_poke_untrack(map_ptr, prog->aux); - } - /* at this point all bpf functions were successfully JITed * now populate all bpf_calls with correct addresses and * run last pass of JIT @@ -12267,14 +12241,22 @@ static int jit_subprogs(struct bpf_verifier_env *env) bpf_prog_jit_attempt_done(prog); return 0; out_free: + /* We failed JIT'ing, so at this point we need to unregister poke + * descriptors from subprogs, so that kernel is not attempting to + * patch it anymore as we're freeing the subprog JIT memory. + */ + for (i = 0; i < prog->aux->size_poke_tab; i++) { + map_ptr = prog->aux->poke_tab[i].tail_call.map; + map_ptr->ops->map_poke_untrack(map_ptr, prog->aux); + } + /* At this point we're guaranteed that poke descriptors are not + * live anymore. We can just unlink its descriptor table as it's + * released with the main prog. + */ for (i = 0; i < env->subprog_cnt; i++) { if (!func[i]) continue; - - for (j = 0; j < func[i]->aux->size_poke_tab; j++) { - map_ptr = func[i]->aux->poke_tab[j].tail_call.map; - map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux); - } + func[i]->aux->poke_tab = NULL; bpf_jit_free(func[i]); } kfree(func); From 1fb5ba29ad0835c5cbfc69a27f9c2733cb65726e Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 7 Jul 2021 15:38:48 -0700 Subject: [PATCH 159/426] bpf: Selftest to verify mixing bpf2bpf calls and tailcalls with insn patch This adds some extra noise to the tailcall_bpf2bpf4 tests that will cause verify to patch insns. This then moves around subprog start/end insn index and poke descriptor insn index to ensure that verify and JIT will continue to track these correctly. If done correctly verifier should pass this program same as before and JIT should emit tail call logic. Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210707223848.14580-3-john.fastabend@gmail.com --- .../selftests/bpf/prog_tests/tailcalls.c | 36 +++++++++++++------ .../selftests/bpf/progs/tailcall_bpf2bpf4.c | 18 ++++++++++ 2 files changed, 44 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index ee27d68d2a1c..b5940e6ca67c 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -715,6 +715,8 @@ out: bpf_object__close(obj); } +#include "tailcall_bpf2bpf4.skel.h" + /* test_tailcall_bpf2bpf_4 checks that tailcall counter is correctly preserved * across tailcalls combined with bpf2bpf calls. for making sure that tailcall * counter behaves correctly, bpf program will go through following flow: @@ -727,10 +729,15 @@ out: * the loop begins. At the end of the test make sure that the global counter is * equal to 31, because tailcall counter includes the first two tailcalls * whereas global counter is incremented only on loop presented on flow above. + * + * The noise parameter is used to insert bpf_map_update calls into the logic + * to force verifier to patch instructions. This allows us to ensure jump + * logic remains correct with instruction movement. */ -static void test_tailcall_bpf2bpf_4(void) +static void test_tailcall_bpf2bpf_4(bool noise) { - int err, map_fd, prog_fd, main_fd, data_fd, i, val; + int err, map_fd, prog_fd, main_fd, data_fd, i; + struct tailcall_bpf2bpf4__bss val; struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; @@ -774,11 +781,6 @@ static void test_tailcall_bpf2bpf_4(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); - data_map = bpf_object__find_map_by_name(obj, "tailcall.bss"); if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map))) return; @@ -787,10 +789,22 @@ static void test_tailcall_bpf2bpf_4(void) if (CHECK_FAIL(map_fd < 0)) return; + i = 0; + val.noise = noise; + val.count = 0; + err = bpf_map_update_elem(data_fd, &i, &val, BPF_ANY); + if (CHECK_FAIL(err)) + goto out; + + err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, + &duration, &retval, NULL); + CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n", + err, errno, retval); + i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val != 31, "tailcall count", "err %d errno %d count %d\n", - err, errno, val); + CHECK(err || val.count != 31, "tailcall count", "err %d errno %d count %d\n", + err, errno, val.count); out: bpf_object__close(obj); @@ -815,5 +829,7 @@ void test_tailcalls(void) if (test__start_subtest("tailcall_bpf2bpf_3")) test_tailcall_bpf2bpf_3(); if (test__start_subtest("tailcall_bpf2bpf_4")) - test_tailcall_bpf2bpf_4(); + test_tailcall_bpf2bpf_4(false); + if (test__start_subtest("tailcall_bpf2bpf_5")) + test_tailcall_bpf2bpf_4(true); } diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c index 77df6d4db895..e89368a50b97 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -2,6 +2,13 @@ #include #include +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} nop_table SEC(".maps"); + struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); __uint(max_entries, 3); @@ -10,10 +17,21 @@ struct { } jmp_table SEC(".maps"); int count = 0; +int noise = 0; + +__always_inline int subprog_noise(void) +{ + __u32 key = 0; + + bpf_map_lookup_elem(&nop_table, &key); + return 0; +} __noinline int subprog_tail_2(struct __sk_buff *skb) { + if (noise) + subprog_noise(); bpf_tail_call_static(skb, &jmp_table, 2); return skb->len * 3; } From 3efe180d5105d367ae1dfadb97892ab93a89a783 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 6 Jul 2021 08:51:25 +0200 Subject: [PATCH 160/426] drm/qxl: add NULL check for bo->resource MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When allocations fails that can be NULL now. Signed-off-by: Christian König Reported-by: Daniel Bristot de Oliveira Tested-by: Daniel Bristot de Oliveira Tested-by: Roberto Sassu Fixes: bfa3357ef9ab ("drm/ttm: allocate resource object instead of embedding it v2") Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210708114710.8186-1-christian.koenig@amd.com --- drivers/gpu/drm/qxl/qxl_ttm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index 19fd39d9a00c..37a1b6a6ad6d 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -127,7 +127,7 @@ static void qxl_bo_move_notify(struct ttm_buffer_object *bo, struct qxl_bo *qbo; struct qxl_device *qdev; - if (!qxl_ttm_bo_is_qxl_bo(bo)) + if (!qxl_ttm_bo_is_qxl_bo(bo) || !bo->resource) return; qbo = to_qxl_bo(bo); qdev = to_qxl(qbo->tbo.base.dev); From 34e0fc345ae728cd974d9ee09832abf62cf054c6 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 9 Jul 2021 14:08:12 +0200 Subject: [PATCH 161/426] arm64: tegra: Enable audio IOMMU support on Tegra194 Add iommus and interconnects properties to the sound device tree node on Tegra194. This ensures that the correct SID is used for translation of physical to I/O virtual addresses and that the path to system memory is properly described, which in turn can impact the range of memory that the device can address. Fixes: c7289b1c8a4e ("arm64: tegra: Enable SMMU support on Tegra194") Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra194.dtsi | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index b7d532841390..0e6eeb1a1c1a 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -2469,6 +2469,11 @@ * for 8x and 11.025x sample rate streams. */ assigned-clock-rates = <258000000>; + + interconnects = <&mc TEGRA194_MEMORY_CLIENT_APEDMAR &emc>, + <&mc TEGRA194_MEMORY_CLIENT_APEDMAW &emc>; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_APE>; }; tcu: tcu { From c667dcd4dfcd515ad2c9b3953a33d742985a0b5e Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 8 Jul 2021 12:39:32 +0200 Subject: [PATCH 162/426] arm64: tegra: Enable SMMU support for USB on Tegra194 As of commit c7289b1c8a4e ("arm64: tegra: Enable SMMU support on Tegra194"), SMMU support is enabled system-wide on Tegra194. However, there was a bit of overlap between the SMMU enablement and the USB support addition, so the USB device tree nodes are missing the iommus and interconnects properties. This in turn leads to SMMU faults for these devices, since by default the ARM SMMU will fault. Add the iommus and interconnects properties to the XUSB and XUDC device tree nodes to restore their functionality. Fixes: c7289b1c8a4e ("arm64: tegra: Enable SMMU support on Tegra194") Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra194.dtsi | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index 0e6eeb1a1c1a..076d5efc4c3d 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -948,6 +948,10 @@ <&bpmp TEGRA194_CLK_XUSB_SS>, <&bpmp TEGRA194_CLK_XUSB_FS>; clock-names = "dev", "ss", "ss_src", "fs_src"; + interconnects = <&mc TEGRA194_MEMORY_CLIENT_XUSB_DEVR &emc>, + <&mc TEGRA194_MEMORY_CLIENT_XUSB_DEVW &emc>; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_XUSB_DEV>; power-domains = <&bpmp TEGRA194_POWER_DOMAIN_XUSBB>, <&bpmp TEGRA194_POWER_DOMAIN_XUSBA>; power-domain-names = "dev", "ss"; @@ -977,6 +981,10 @@ "xusb_ss", "xusb_ss_src", "xusb_hs_src", "xusb_fs_src", "pll_u_480m", "clk_m", "pll_e"; + interconnects = <&mc TEGRA194_MEMORY_CLIENT_XUSB_HOSTR &emc>, + <&mc TEGRA194_MEMORY_CLIENT_XUSB_HOSTW &emc>; + interconnect-names = "dma-mem", "write"; + iommus = <&smmu TEGRA194_SID_XUSB_HOST>; power-domains = <&bpmp TEGRA194_POWER_DOMAIN_XUSBC>, <&bpmp TEGRA194_POWER_DOMAIN_XUSBA>; From c78eaeebe855fd93f2e77142ffd0404a54070d84 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 9 Jul 2021 17:09:53 +0300 Subject: [PATCH 163/426] net: moxa: fix UAF in moxart_mac_probe In case of netdev registration failure the code path will jump to init_fail label: init_fail: netdev_err(ndev, "init failed\n"); moxart_mac_free_memory(ndev); irq_map_fail: free_netdev(ndev); return ret; So, there is no need to call free_netdev() before jumping to error handling path, since it can cause UAF or double-free bug. Fixes: 6c821bd9edc9 ("net: Add MOXA ART SoCs ethernet driver") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/ethernet/moxa/moxart_ether.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 5249b64f4fc5..49def6934cad 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -540,10 +540,8 @@ static int moxart_mac_probe(struct platform_device *pdev) SET_NETDEV_DEV(ndev, &pdev->dev); ret = register_netdev(ndev); - if (ret) { - free_netdev(ndev); + if (ret) goto init_fail; - } netdev_dbg(ndev, "%s: IRQ=%d address=%pM\n", __func__, ndev->irq, ndev->dev_addr); From ad297cd2db8953e2202970e9504cab247b6c7cb4 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 9 Jul 2021 17:24:18 +0300 Subject: [PATCH 164/426] net: qcom/emac: fix UAF in emac_remove adpt is netdev private data and it cannot be used after free_netdev() call. Using adpt after free_netdev() can cause UAF bug. Fix it by moving free_netdev() at the end of the function. Fixes: 54e19bc74f33 ("net: qcom/emac: do not use devm on internal phy pdev") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 8543bf3c3484..ad655f0a4965 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -735,12 +735,13 @@ static int emac_remove(struct platform_device *pdev) put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); - free_netdev(netdev); if (adpt->phy.digital) iounmap(adpt->phy.digital); iounmap(adpt->phy.base); + free_netdev(netdev); + return 0; } From 0336f8ffece62f882ab3012820965a786a983f70 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 9 Jul 2021 17:58:29 +0300 Subject: [PATCH 165/426] net: ti: fix UAF in tlan_remove_one priv is netdev private data and it cannot be used after free_netdev() call. Using priv after free_netdev() can cause UAF bug. Fix it by moving free_netdev() at the end of the function. Fixes: 1e0a8b13d355 ("tlan: cancel work at remove path") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/tlan.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 0b2ce4bdc2c3..e0cb713193ea 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -313,9 +313,8 @@ static void tlan_remove_one(struct pci_dev *pdev) pci_release_regions(pdev); #endif - free_netdev(dev); - cancel_work_sync(&priv->tlan_tqueue); + free_netdev(dev); } static void tlan_start(struct net_device *dev) From 43b90bfad34bcb81b8a5bc7dc650800f4be1787e Mon Sep 17 00:00:00 2001 From: Alexander Ovechkin Date: Fri, 9 Jul 2021 18:28:23 +0300 Subject: [PATCH 166/426] net: send SYNACK packet with accepted fwmark commit e05a90ec9e16 ("net: reflect mark on tcp syn ack packets") fixed IPv4 only. This part is for the IPv6 side. Fixes: e05a90ec9e16 ("net: reflect mark on tcp syn ack packets") Signed-off-by: Alexander Ovechkin Acked-by: Dmitry Yakunin Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 323989927a0a..0ce52d46e4f8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -555,7 +555,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, + err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); From 358ed624207012f03318235017ac6fb41f8af592 Mon Sep 17 00:00:00 2001 From: Talal Ahmad Date: Fri, 9 Jul 2021 11:43:06 -0400 Subject: [PATCH 167/426] tcp: call sk_wmem_schedule before sk_mem_charge in zerocopy path sk_wmem_schedule makes sure that sk_forward_alloc has enough bytes for charging that is going to be done by sk_mem_charge. In the transmit zerocopy path, there is sk_mem_charge but there was no call to sk_wmem_schedule. This change adds that call. Without this call to sk_wmem_schedule, sk_forward_alloc can go negetive which is a bug because sk_forward_alloc is a per-socket space that has been forward charged so this can't be negative. Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY") Signed-off-by: Talal Ahmad Reviewed-by: Willem de Bruijn Reviewed-by: Wei Wang Reviewed-by: Soheil Hassas Yeganeh Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d5ab5f243640..8cb44040ec68 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1375,6 +1375,9 @@ new_segment: } pfrag->offset += copy; } else { + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_space; + err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); From 28b34f01a73435a754956ebae826e728c03ffa38 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Fri, 9 Jul 2021 18:16:09 +0200 Subject: [PATCH 168/426] net: do not reuse skbuff allocated from skbuff_fclone_cache in the skb cache Some socket buffers allocated in the fclone cache (in __alloc_skb) can end-up in the following path[1]: napi_skb_finish __kfree_skb_defer napi_skb_cache_put The issue is napi_skb_cache_put is not fclone friendly and will put those skbuff in the skb cache to be reused later, although this cache only expects skbuff allocated from skbuff_head_cache. When this happens the skbuff is eventually freed using the wrong origin cache, and we can see traces similar to: [ 1223.947534] cache_from_obj: Wrong slab cache. skbuff_head_cache but object is from skbuff_fclone_cache [ 1223.948895] WARNING: CPU: 3 PID: 0 at mm/slab.h:442 kmem_cache_free+0x251/0x3e0 [ 1223.950211] Modules linked in: [ 1223.950680] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.13.0+ #474 [ 1223.951587] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-3.fc34 04/01/2014 [ 1223.953060] RIP: 0010:kmem_cache_free+0x251/0x3e0 Leading sometimes to other memory related issues. Fix this by using __kfree_skb for fclone skbuff, similar to what is done the other place __kfree_skb_defer is called. [1] At least in setups using veth pairs and tunnels. Building a kernel with KASAN we can for example see packets allocated in sk_stream_alloc_skb hit the above path and later the issue arises when the skbuff is reused. Fixes: 9243adfc311a ("skbuff: queue NAPI_MERGED_FREE skbs into NAPI cache instead of freeing") Cc: Alexander Lobakin Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index 03c95a0867bb..64b21f0a2048 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6234,6 +6234,8 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi, case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); + else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) + __kfree_skb(skb); else __kfree_skb_defer(skb); break; From c26d6586e97a69ef9b429cc577ca4c9d2d2ec7cd Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Wed, 9 Jun 2021 13:23:07 -0400 Subject: [PATCH 169/426] drm/vmwgfx: Fix implicit declaration error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The declarations of ttm_range_man_init and ttm_range_man_fini have been moved to ttm_range_manager.h so we have to add it to the include list. Signed-off-by: Zack Rusin Reported-by: Randy Dunlap Fixes: 3eb7d96e9415 ("drm/ttm: flip over the range manager to self allocated nodes") Cc: Christian König Cc: Matthew Auld Reviewed-by: Martin Krastev Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210609172307.131929-10-zackr@vmware.com --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 6f5ea00973e0..45aeeca9b8f6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include From 34bd46bcf3de72cbffcdc42d3fa67e543d1c869b Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Tue, 15 Jun 2021 14:23:35 -0400 Subject: [PATCH 170/426] drm/vmwgfx: Fix a bad merge in otable batch takedown Change 2ef4fb92363c ("drm/vmwgfx: Make sure bo's are unpinned before putting them back") caused a conflict in one of the drm trees and the merge commit 68a32ba14177 ("Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm") accidently re-added code that the original change was removing. Fixed by removing the incorrect buffer unpin - it has already been unpinned two lines above. Fixes: 68a32ba14177 ("Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm") Signed-off-by: Zack Rusin Reviewed-by: Martin Krastev Link: https://patchwork.freedesktop.org/patch/msgid/20210615182336.995192-4-zackr@vmware.com --- drivers/gpu/drm/vmwgfx/vmwgfx_mob.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c index 5648664f71bc..f2d625415458 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c @@ -354,7 +354,6 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv, ttm_bo_unpin(bo); ttm_bo_unreserve(bo); - ttm_bo_unpin(batch->otable_bo); ttm_bo_put(batch->otable_bo); batch->otable_bo = NULL; } From 9992a078b1771da354ac1f9737e1e639b687caa2 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 9 Jul 2021 11:45:02 +0800 Subject: [PATCH 171/426] net: ip_tunnel: fix mtu calculation for ETHER tunnel devices Commit 28e104d00281 ("net: ip_tunnel: fix mtu calculation") removed dev->hard_header_len subtraction when calculate MTU for tunnel devices as there is an overhead for device that has header_ops. But there are ETHER tunnel devices, like gre_tap or erspan, which don't have header_ops but set dev->hard_header_len during setup. This makes pkts greater than (MTU - ETH_HLEN) could not be xmited. Fix it by subtracting the ETHER tunnel devices' dev->hard_header_len for MTU calculation. Fixes: 28e104d00281 ("net: ip_tunnel: fix mtu calculation") Reported-by: Jianlin Shi Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- net/ipv4/ip_tunnel.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index f6cc26de5ed3..0dca00745ac3 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) } dev->needed_headroom = t_hlen + hlen; - mtu -= t_hlen; + mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0); if (mtu < IPV4_MIN_MTU) mtu = IPV4_MIN_MTU; @@ -348,6 +348,9 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU - t_hlen; + if (dev->type == ARPHRD_ETHER) + dev->max_mtu -= dev->hard_header_len; + ip_tunnel_add(itn, nt); return nt; @@ -489,11 +492,14 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; pkt_size = skb->len - tunnel_hlen; + pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; - if (df) + if (df) { mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen); - else + mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; + } else { mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + } if (skb_valid_dst(skb)) skb_dst_update_pmtu_no_confirm(skb, mtu); @@ -972,6 +978,9 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) int t_hlen = tunnel->hlen + sizeof(struct iphdr); int max_mtu = IP_MAX_MTU - t_hlen; + if (dev->type == ARPHRD_ETHER) + max_mtu -= dev->hard_header_len; + if (new_mtu < ETH_MIN_MTU) return -EINVAL; @@ -1149,6 +1158,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], if (tb[IFLA_MTU]) { unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr)); + if (dev->type == ARPHRD_ETHER) + max -= dev->hard_header_len; + mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max); } From 67a9c94317402b826fc3db32afc8f39336803d97 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 9 Jul 2021 17:35:18 +0000 Subject: [PATCH 172/426] net: validate lwtstate->data before returning from skb_tunnel_info() skb_tunnel_info() returns pointer of lwtstate->data as ip_tunnel_info type without validation. lwtstate->data can have various types such as mpls_iptunnel_encap, etc and these are not compatible. So skb_tunnel_info() should validate before returning that pointer. Splat looks like: BUG: KASAN: slab-out-of-bounds in vxlan_get_route+0x418/0x4b0 [vxlan] Read of size 2 at addr ffff888106ec2698 by task ping/811 CPU: 1 PID: 811 Comm: ping Not tainted 5.13.0+ #1195 Call Trace: dump_stack_lvl+0x56/0x7b print_address_description.constprop.8.cold.13+0x13/0x2ee ? vxlan_get_route+0x418/0x4b0 [vxlan] ? vxlan_get_route+0x418/0x4b0 [vxlan] kasan_report.cold.14+0x83/0xdf ? vxlan_get_route+0x418/0x4b0 [vxlan] vxlan_get_route+0x418/0x4b0 [vxlan] [ ... ] vxlan_xmit_one+0x148b/0x32b0 [vxlan] [ ... ] vxlan_xmit+0x25c5/0x4780 [vxlan] [ ... ] dev_hard_start_xmit+0x1ae/0x6e0 __dev_queue_xmit+0x1f39/0x31a0 [ ... ] neigh_xmit+0x2f9/0x940 mpls_xmit+0x911/0x1600 [mpls_iptunnel] lwtunnel_xmit+0x18f/0x450 ip_finish_output2+0x867/0x2040 [ ... ] Fixes: 61adedf3e3f1 ("route: move lwtunnel state to dst_entry") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/net/dst_metadata.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 56cb3c38569a..14efa0ded75d 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -45,7 +45,9 @@ skb_tunnel_info(const struct sk_buff *skb) return &md_dst->u.tun_info; dst = skb_dst(skb); - if (dst && dst->lwtstate) + if (dst && dst->lwtstate && + (dst->lwtstate->type == LWTUNNEL_ENCAP_IP || + dst->lwtstate->type == LWTUNNEL_ENCAP_IP6)) return lwt_tun_info(dst->lwtstate); return NULL; From 0c71929b5893e410e0efbe1bbeca6f19a5f19956 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:46 -0700 Subject: [PATCH 173/426] mptcp: fix warning in __skb_flow_dissect() when do syn cookie for subflow join I did stress test with wrk[1] and webfsd[2] with the assistance of mptcp-tools[3]: Server side: ./use_mptcp.sh webfsd -4 -R /tmp/ -p 8099 Client side: ./use_mptcp.sh wrk -c 200 -d 30 -t 4 http://192.168.174.129:8099/ and got the following warning message: [ 55.552626] TCP: request_sock_subflow: Possible SYN flooding on port 8099. Sending cookies. Check SNMP counters. [ 55.553024] ------------[ cut here ]------------ [ 55.553027] WARNING: CPU: 0 PID: 10 at net/core/flow_dissector.c:984 __skb_flow_dissect+0x280/0x1650 ... [ 55.553117] CPU: 0 PID: 10 Comm: ksoftirqd/0 Not tainted 5.12.0+ #18 [ 55.553121] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 02/27/2020 [ 55.553124] RIP: 0010:__skb_flow_dissect+0x280/0x1650 ... [ 55.553133] RSP: 0018:ffffb79580087770 EFLAGS: 00010246 [ 55.553137] RAX: 0000000000000000 RBX: ffffffff8ddb58e0 RCX: ffffb79580087888 [ 55.553139] RDX: ffffffff8ddb58e0 RSI: ffff8f7e4652b600 RDI: 0000000000000000 [ 55.553141] RBP: ffffb79580087858 R08: 0000000000000000 R09: 0000000000000008 [ 55.553143] R10: 000000008c622965 R11: 00000000d3313a5b R12: ffff8f7e4652b600 [ 55.553146] R13: ffff8f7e465c9062 R14: 0000000000000000 R15: ffffb79580087888 [ 55.553149] FS: 0000000000000000(0000) GS:ffff8f7f75e00000(0000) knlGS:0000000000000000 [ 55.553152] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 55.553154] CR2: 00007f73d1d19000 CR3: 0000000135e10004 CR4: 00000000003706f0 [ 55.553160] Call Trace: [ 55.553166] ? __sha256_final+0x67/0xd0 [ 55.553173] ? sha256+0x7e/0xa0 [ 55.553177] __skb_get_hash+0x57/0x210 [ 55.553182] subflow_init_req_cookie_join_save+0xac/0xc0 [ 55.553189] subflow_check_req+0x474/0x550 [ 55.553195] ? ip_route_output_key_hash+0x67/0x90 [ 55.553200] ? xfrm_lookup_route+0x1d/0xa0 [ 55.553207] subflow_v4_route_req+0x8e/0xd0 [ 55.553212] tcp_conn_request+0x31e/0xab0 [ 55.553218] ? selinux_socket_sock_rcv_skb+0x116/0x210 [ 55.553224] ? tcp_rcv_state_process+0x179/0x6d0 [ 55.553229] tcp_rcv_state_process+0x179/0x6d0 [ 55.553235] tcp_v4_do_rcv+0xaf/0x220 [ 55.553239] tcp_v4_rcv+0xce4/0xd80 [ 55.553243] ? ip_route_input_rcu+0x246/0x260 [ 55.553248] ip_protocol_deliver_rcu+0x35/0x1b0 [ 55.553253] ip_local_deliver_finish+0x44/0x50 [ 55.553258] ip_local_deliver+0x6c/0x110 [ 55.553262] ? ip_rcv_finish_core.isra.19+0x5a/0x400 [ 55.553267] ip_rcv+0xd1/0xe0 ... After debugging, I found in __skb_flow_dissect(), skb->dev and skb->sk are both NULL, then net is NULL, and trigger WARN_ON_ONCE(!net), actually net is always NULL in this code path, as skb->dev is set to NULL in tcp_v4_rcv(), and skb->sk is never set. Code snippet in __skb_flow_dissect() that trigger warning: 975 if (skb) { 976 if (!net) { 977 if (skb->dev) 978 net = dev_net(skb->dev); 979 else if (skb->sk) 980 net = sock_net(skb->sk); 981 } 982 } 983 984 WARN_ON_ONCE(!net); So, using seq and transport header derived hash. [1] https://github.com/wg/wrk [2] https://github.com/ourway/webfsd [3] https://github.com/pabeni/mptcp-tools Fixes: 9466a1ccebbe ("mptcp: enable JOIN requests even if cookies are in use") Suggested-by: Paolo Abeni Suggested-by: Florian Westphal Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/syncookies.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c index abe0fd099746..37127781aee9 100644 --- a/net/mptcp/syncookies.c +++ b/net/mptcp/syncookies.c @@ -37,7 +37,21 @@ static spinlock_t join_entry_locks[COOKIE_JOIN_SLOTS] __cacheline_aligned_in_smp static u32 mptcp_join_entry_hash(struct sk_buff *skb, struct net *net) { - u32 i = skb_get_hash(skb) ^ net_hash_mix(net); + static u32 mptcp_join_hash_secret __read_mostly; + struct tcphdr *th = tcp_hdr(skb); + u32 seq, i; + + net_get_random_once(&mptcp_join_hash_secret, + sizeof(mptcp_join_hash_secret)); + + if (th->syn) + seq = TCP_SKB_CB(skb)->seq; + else + seq = TCP_SKB_CB(skb)->seq - 1; + + i = jhash_3words(seq, net_hash_mix(net), + (__force __u32)th->source << 16 | (__force __u32)th->dest, + mptcp_join_hash_secret); return i % ARRAY_SIZE(join_entries); } From 030d37bd1cd2443a1f21db47eb301899bfa45a2a Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:47 -0700 Subject: [PATCH 174/426] mptcp: remove redundant req destruct in subflow_check_req() In subflow_check_req(), if subflow sport is mismatch, will put msk, destroy token, and destruct req, then return -EPERM, which can be done by subflow_req_destructor() via: tcp_conn_request() |--__reqsk_free() |--subflow_req_destructor() So we should remove these redundant code, otherwise will call tcp_v4_reqsk_destructor() twice, and may double free inet_rsk(req)->ireq_opt. Fixes: 5bc56388c74f ("mptcp: add port number check for MP_JOIN") Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/subflow.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 66d0b1893d26..b15e2017168d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -214,11 +214,6 @@ again: ntohs(inet_sk(sk_listener)->inet_sport), ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { - sock_put((struct sock *)subflow_req->msk); - mptcp_token_destroy_request(req); - tcp_request_sock_ops.destructor(req); - subflow_req->msk = NULL; - subflow_req->mp_join = 0; SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); return -EPERM; } From 8547ea5f52dd8ef19b69c25c41b1415481b3503b Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:48 -0700 Subject: [PATCH 175/426] mptcp: fix syncookie process if mptcp can not_accept new subflow Lots of "TCP: tcp_fin: Impossible, sk->sk_state=7" in client side when doing stress testing using wrk and webfsd. There are at least two cases may trigger this warning: 1.mptcp is in syncookie, and server recv MP_JOIN SYN request, in subflow_check_req(), the mptcp_can_accept_new_subflow() return false, so subflow_init_req_cookie_join_save() isn't called, i.e. not store the data present in the MP_JOIN syn request and the random nonce in hash table - join_entries[], but still send synack. When recv 3rd-ack, mptcp_token_join_cookie_init_state() will return false, and 3rd-ack is dropped, then if mptcp conn is closed by client, client will send a DATA_FIN and a MPTCP FIN, the DATA_FIN doesn't have MP_CAPABLE or MP_JOIN, so mptcp_subflow_init_cookie_req() will return 0, and pass the cookie check, MP_JOIN request is fallback to normal TCP. Server will send a TCP FIN if closed, in client side, when process TCP FIN, it will do reset, the code path is: tcp_data_queue()->mptcp_incoming_options() ->check_fully_established()->mptcp_subflow_reset(). mptcp_subflow_reset() will set sock state to TCP_CLOSE, so tcp_fin will hit TCP_CLOSE, and print the warning. 2.mptcp is in syncookie, and server recv 3rd-ack, in mptcp_subflow_init_cookie_req(), mptcp_can_accept_new_subflow() return false, and subflow_req->mp_join is not set to 1, so in subflow_syn_recv_sock() will not reset the MP_JOIN subflow, but fallback to normal TCP, and then the same thing happens when server will send a TCP FIN if closed. For case1, subflow_check_req() return -EPERM, then tcp_conn_request() will drop MP_JOIN SYN. For case2, let subflow_syn_recv_sock() call mptcp_can_accept_new_subflow(), and do fatal fallback, send reset. Fixes: 9466a1ccebbe ("mptcp: enable JOIN requests even if cookies are in use") Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/subflow.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index b15e2017168d..966f777d35ce 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -225,6 +225,8 @@ again: if (unlikely(req->syncookie)) { if (mptcp_can_accept_new_subflow(subflow_req->msk)) subflow_init_req_cookie_join_save(subflow_req, skb); + else + return -EPERM; } pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, @@ -264,9 +266,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, if (!mptcp_token_join_cookie_init_state(subflow_req, skb)) return -EINVAL; - if (mptcp_can_accept_new_subflow(subflow_req->msk)) - subflow_req->mp_join = 1; - + subflow_req->mp_join = 1; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; } From 6787b7e350d3552651a3422d3d8980fbc8d65368 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:49 -0700 Subject: [PATCH 176/426] mptcp: avoid processing packet if a subflow reset If check_fully_established() causes a subflow reset, it should not continue to process the packet in tcp_data_queue(). Add a return value to mptcp_incoming_options(), and return false if a subflow has been reset, else return true. Then drop the packet in tcp_data_queue()/tcp_rcv_state_process() if mptcp_incoming_options() return false. Fixes: d582484726c4 ("mptcp: fix fallback for MP_JOIN subflows") Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/net/mptcp.h | 5 +++-- net/ipv4/tcp_input.c | 19 +++++++++++++++---- net/mptcp/options.c | 19 +++++++++++++------ 3 files changed, 31 insertions(+), 12 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index cb580b06152f..8b5af683a818 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -105,7 +105,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts); -void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); +bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts); @@ -227,9 +227,10 @@ static inline bool mptcp_established_options(struct sock *sk, return false; } -static inline void mptcp_incoming_options(struct sock *sk, +static inline bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { + return true; } static inline void mptcp_skb_ext_move(struct sk_buff *to, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a5a8d0a378b2..149ceb5c94ff 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4247,6 +4247,9 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) { trace_tcp_receive_reset(sk); + /* mptcp can't tell us to ignore reset pkts, + * so just ignore the return value of mptcp_incoming_options(). + */ if (sk_is_mptcp(sk)) mptcp_incoming_options(sk, skb); @@ -4941,8 +4944,13 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) bool fragstolen; int eaten; - if (sk_is_mptcp(sk)) - mptcp_incoming_options(sk, skb); + /* If a subflow has been reset, the packet should not continue + * to be processed, drop the packet. + */ + if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) { + __kfree_skb(skb); + return; + } if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { __kfree_skb(skb); @@ -6523,8 +6531,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_CLOSING: case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { - if (sk_is_mptcp(sk)) - mptcp_incoming_options(sk, skb); + /* If a subflow has been reset, the packet should not + * continue to be processed, drop the packet. + */ + if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) + goto discard; break; } fallthrough; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b5850afea343..4452455aef7f 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1035,7 +1035,8 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, return hmac == mp_opt->ahmac; } -void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) +/* Return false if a subflow has been reset, else return true */ +bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); @@ -1053,12 +1054,16 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) __mptcp_check_push(subflow->conn, sk); __mptcp_data_acked(subflow->conn); mptcp_data_unlock(subflow->conn); - return; + return true; } mptcp_get_options(sk, skb, &mp_opt); + + /* The subflow can be in close state only if check_fully_established() + * just sent a reset. If so, tell the caller to ignore the current packet. + */ if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) - return; + return sk->sk_state != TCP_CLOSE; if (mp_opt.fastclose && msk->local_key == mp_opt.rcvr_key) { @@ -1100,7 +1105,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) } if (!mp_opt.dss) - return; + return true; /* we can't wait for recvmsg() to update the ack_seq, otherwise * monodirectional flows will stuck @@ -1119,12 +1124,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) schedule_work(&msk->work)) sock_hold(subflow->conn); - return; + return true; } mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) - return; + return true; memset(mpext, 0, sizeof(*mpext)); @@ -1153,6 +1158,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) if (mpext->csum_reqd) mpext->csum = mp_opt.csum; } + + return true; } static void mptcp_set_rwin(const struct tcp_sock *tp) From a7da441621c7945fbfd43ed239c93b8073cda502 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 9 Jul 2021 17:20:50 -0700 Subject: [PATCH 177/426] selftests: mptcp: fix case multiple subflows limited by server After patch "mptcp: fix syncookie process if mptcp can not_accept new subflow", if subflow is limited, MP_JOIN SYN is dropped, and no SYN/ACK will be replied. So in case "multiple subflows limited by server", the expected SYN/ACK number should be 1. Fixes: 00587187ad30 ("selftests: mptcp: add test cases for mptcp join tests with syn cookies") Reported-by: kernel test robot Signed-off-by: Jianguo Wu Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 9a191c1a5de8..f02f4de2f3a0 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1409,7 +1409,7 @@ syncookies_tests() ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflows limited by server w cookies" 2 2 1 + chk_join_nr "subflows limited by server w cookies" 2 1 1 # test signal address with cookies reset_with_cookies From ce599c516386f09ca30848a1a4eb93d3fffbe187 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 9 Jul 2021 17:20:51 -0700 Subject: [PATCH 178/426] mptcp: properly account bulk freed memory After commit 879526030c8b ("mptcp: protect the rx path with the msk socket spinlock") the rmem currently used by a given msk is really sk_rmem_alloc - rmem_released. The safety check in mptcp_data_ready() does not take the above in due account, as a result legit incoming data is kept in subflow receive queue with no reason, delaying or blocking MPTCP-level ack generation. This change addresses the issue introducing a new helper to fetch the rmem memory and using it as needed. Additionally add a MIB counter for the exceptional event described above - the peer is misbehaving. Finally, introduce the required annotation when rmem_released is updated. Fixes: 879526030c8b ("mptcp: protect the rx path with the msk socket spinlock") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/211 Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/mib.c | 1 + net/mptcp/mib.h | 1 + net/mptcp/protocol.c | 12 +++++++----- net/mptcp/protocol.h | 10 +++++++++- 4 files changed, 18 insertions(+), 6 deletions(-) diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 52ea2517e856..ff2cc0e3273d 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -44,6 +44,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), + SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED), SNMP_MIB_SENTINEL }; diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 193466c9b549..0663cb12b448 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -37,6 +37,7 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ + MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */ __MPTCP_MIB_MAX }; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7a5afa8c6866..a88924947815 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -474,7 +474,7 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) bool cleanup, rx_empty; cleanup = (space > 0) && (space >= (old_space << 1)); - rx_empty = !atomic_read(&sk->sk_rmem_alloc); + rx_empty = !__mptcp_rmem(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); @@ -720,8 +720,10 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) + if (__mptcp_rmem(sk) > sk_rbuf) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); return; + } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); @@ -1754,7 +1756,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, if (!(flags & MSG_PEEK)) { /* we will bulk release the skb memory later */ skb->destructor = NULL; - msk->rmem_released += skb->truesize; + WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); __skb_unlink(skb, &msk->receive_queue); __kfree_skb(skb); } @@ -1873,7 +1875,7 @@ static void __mptcp_update_rmem(struct sock *sk) atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, msk->rmem_released); - msk->rmem_released = 0; + WRITE_ONCE(msk->rmem_released, 0); } static void __mptcp_splice_receive_queue(struct sock *sk) @@ -2380,7 +2382,7 @@ static int __mptcp_init_sock(struct sock *sk) msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->wmem_reserved = 0; - msk->rmem_released = 0; + WRITE_ONCE(msk->rmem_released, 0); msk->tx_pending_data = 0; msk->first = NULL; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 426ed80fe72f..0f0c026c5f8b 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -296,9 +296,17 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk) return (struct mptcp_sock *)sk; } +/* the msk socket don't use the backlog, also account for the bulk + * free memory + */ +static inline int __mptcp_rmem(const struct sock *sk) +{ + return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released); +} + static inline int __mptcp_space(const struct sock *sk) { - return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_released); + return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk)); } static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk) From 222722bc6ebfabf5d54467070f05cf9c0a55ea8c Mon Sep 17 00:00:00 2001 From: Yunjian Wang Date: Sat, 10 Jul 2021 11:32:49 +0800 Subject: [PATCH 179/426] virtio_net: check virtqueue_add_sgs() return value As virtqueue_add_sgs() can fail, we should check the return value. Addresses-Coverity-ID: 1464439 ("Unchecked return value") Signed-off-by: Yunjian Wang Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b0b81458ca94..13952e2dba5e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1743,6 +1743,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, { struct scatterlist *sgs[4], hdr, stat; unsigned out_num = 0, tmp; + int ret; /* Caller should know better */ BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)); @@ -1762,7 +1763,12 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, sgs[out_num] = &stat; BUG_ON(out_num + 1 > ARRAY_SIZE(sgs)); - virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC); + ret = virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC); + if (ret < 0) { + dev_warn(&vi->vdev->dev, + "Failed to add sgs for command vq: %d\n.", ret); + return false; + } if (unlikely(!virtqueue_kick(vi->cvq))) return vi->ctrl->status == VIRTIO_NET_OK; From 84f7e0bb4809f4497124b6b6904c07c8a0c73c58 Mon Sep 17 00:00:00 2001 From: kernel test robot Date: Sun, 11 Jul 2021 18:12:56 +0200 Subject: [PATCH 180/426] dsa: fix for_each_child.cocci warnings For_each_available_child_of_node should have of_node_put() before return around line 423. Generated by: scripts/coccinelle/iterators/for_each_child.cocci CC: Alexander Lobakin Reported-by: kernel test robot Signed-off-by: kernel test robot Signed-off-by: Julia Lawall Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz_common.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index a7e5ac60baef..1542bfb8b5e5 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -419,8 +419,10 @@ int ksz_switch_register(struct ksz_device *dev, if (of_property_read_u32(port, "reg", &port_num)) continue; - if (!(dev->port_mask & BIT(port_num))) + if (!(dev->port_mask & BIT(port_num))) { + of_node_put(port); return -EINVAL; + } of_get_phy_mode(port, &dev->ports[port_num].interface); } From a5de4be0aaaa66a2fa98e8a33bdbed3bd0682804 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Sun, 11 Jul 2021 18:38:15 +0200 Subject: [PATCH 181/426] net: phy: marvell10g: fix differentiation of 88X3310 from 88X3340 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It seems that we cannot differentiate 88X3310 from 88X3340 by simply looking at bit 3 of revision ID. This only works on revisions A0 and A1. On revision B0, this bit is always 1. Instead use the 3.d00d register for differentiation, since this register contains information about number of ports on the device. Fixes: 9885d016ffa9 ("net: phy: marvell10g: add separate structure for 88X3340") Signed-off-by: Marek Behún Reported-by: Matteo Croce Tested-by: Matteo Croce Signed-off-by: David S. Miller --- drivers/net/phy/marvell10g.c | 40 +++++++++++++++++++++++++++++++----- include/linux/marvell_phy.h | 6 +----- 2 files changed, 36 insertions(+), 10 deletions(-) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index bbbc6ac8fa82..53a433442803 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -78,6 +78,11 @@ enum { /* Temperature read register (88E2110 only) */ MV_PCS_TEMP = 0x8042, + /* Number of ports on the device */ + MV_PCS_PORT_INFO = 0xd00d, + MV_PCS_PORT_INFO_NPORTS_MASK = 0x0380, + MV_PCS_PORT_INFO_NPORTS_SHIFT = 7, + /* These registers appear at 0x800X and 0xa00X - the 0xa00X control * registers appear to set themselves to the 0x800X when AN is * restarted, but status registers appear readable from either. @@ -966,6 +971,30 @@ static const struct mv3310_chip mv2111_type = { #endif }; +static int mv3310_get_number_of_ports(struct phy_device *phydev) +{ + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_PORT_INFO); + if (ret < 0) + return ret; + + ret &= MV_PCS_PORT_INFO_NPORTS_MASK; + ret >>= MV_PCS_PORT_INFO_NPORTS_SHIFT; + + return ret + 1; +} + +static int mv3310_match_phy_device(struct phy_device *phydev) +{ + return mv3310_get_number_of_ports(phydev) == 1; +} + +static int mv3340_match_phy_device(struct phy_device *phydev) +{ + return mv3310_get_number_of_ports(phydev) == 4; +} + static int mv211x_match_phy_device(struct phy_device *phydev, bool has_5g) { int val; @@ -994,7 +1023,8 @@ static int mv2111_match_phy_device(struct phy_device *phydev) static struct phy_driver mv3310_drivers[] = { { .phy_id = MARVELL_PHY_ID_88X3310, - .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .match_phy_device = mv3310_match_phy_device, .name = "mv88x3310", .driver_data = &mv3310_type, .get_features = mv3310_get_features, @@ -1011,8 +1041,9 @@ static struct phy_driver mv3310_drivers[] = { .set_loopback = genphy_c45_loopback, }, { - .phy_id = MARVELL_PHY_ID_88X3340, - .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK, + .phy_id = MARVELL_PHY_ID_88X3310, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .match_phy_device = mv3340_match_phy_device, .name = "mv88x3340", .driver_data = &mv3340_type, .get_features = mv3310_get_features, @@ -1069,8 +1100,7 @@ static struct phy_driver mv3310_drivers[] = { module_phy_driver(mv3310_drivers); static struct mdio_device_id __maybe_unused mv3310_tbl[] = { - { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_88X33X0_MASK }, - { MARVELL_PHY_ID_88X3340, MARVELL_PHY_ID_88X33X0_MASK }, + { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E2110, MARVELL_PHY_ID_MASK }, { }, }; diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index acee44b9db26..0f06c2287b52 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -22,14 +22,10 @@ #define MARVELL_PHY_ID_88E1545 0x01410ea0 #define MARVELL_PHY_ID_88E1548P 0x01410ec0 #define MARVELL_PHY_ID_88E3016 0x01410e60 +#define MARVELL_PHY_ID_88X3310 0x002b09a0 #define MARVELL_PHY_ID_88E2110 0x002b09b0 #define MARVELL_PHY_ID_88X2222 0x01410f10 -/* PHY IDs and mask for Alaska 10G PHYs */ -#define MARVELL_PHY_ID_88X33X0_MASK 0xfffffff8 -#define MARVELL_PHY_ID_88X3310 0x002b09a0 -#define MARVELL_PHY_ID_88X3340 0x002b09a8 - /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 From 04bef83a3358946bfc98a5ecebd1b0003d83d882 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 11 Jul 2021 12:56:28 +0300 Subject: [PATCH 182/426] net: bridge: multicast: fix PIM hello router port marking race When a PIM hello packet is received on a bridge port with multicast snooping enabled, we mark it as a router port automatically, that includes adding that port the router port list. The multicast lock protects that list, but it is not acquired in the PIM message case leading to a race condition, we need to take it to fix the race. Cc: stable@vger.kernel.org Fixes: 91b02d3d133b ("bridge: mcast: add router port on PIM hello message") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 53c3a9d80d9c..3bbbc6d7b7c3 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3264,7 +3264,9 @@ static void br_multicast_pim(struct net_bridge *br, pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; + spin_lock(&br->multicast_lock); br_ip4_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); } static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, From 000b7287b67555fee39d39fff75229dedde0dcbf Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 11 Jul 2021 12:56:29 +0300 Subject: [PATCH 183/426] net: bridge: multicast: fix MRD advertisement router port marking race When an MRD advertisement is received on a bridge port with multicast snooping enabled, we mark it as a router port automatically, that includes adding that port to the router port list. The multicast lock protects that list, but it is not acquired in the MRD advertisement case leading to a race condition, we need to take it to fix the race. Cc: stable@vger.kernel.org Cc: linus.luessing@c0d3.blue Fixes: 4b3087c7e37f ("bridge: Snoop Multicast Router Advertisements") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3bbbc6d7b7c3..d0434dc8c03b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3277,7 +3277,9 @@ static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, igmp_hdr(skb)->type != IGMP_MRDISC_ADV) return -ENOMSG; + spin_lock(&br->multicast_lock); br_ip4_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); return 0; } @@ -3345,7 +3347,9 @@ static void br_ip6_multicast_mrd_rcv(struct net_bridge *br, if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) return; + spin_lock(&br->multicast_lock); br_ip6_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); } static int br_multicast_ipv6_rcv(struct net_bridge *br, From 9c6882608bce249a8918744ecdb65748534e3f17 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 10 Jul 2021 02:45:59 +0100 Subject: [PATCH 184/426] io_uring: use right task for exiting checks When we use delayed_work for fallback execution of requests, current will be not of the submitter task, and so checks in io_req_task_submit() may not behave as expected. Currently, it leaves inline completions not flushed, so making io_ring_exit_work() to hang. Use the submitter task for all those checks. Cc: stable@vger.kernel.org Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/cb413c715bed0bc9c98b169059ea9c8a2c770715.1625881431.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index d94fb5835a20..118215211bb2 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2016,7 +2016,7 @@ static void io_req_task_submit(struct io_kiocb *req) /* ctx stays valid until unlock, even if we drop all ours ctx->refs */ mutex_lock(&ctx->uring_lock); - if (!(current->flags & PF_EXITING) && !current->in_execve) + if (!(req->task->flags & PF_EXITING) && !req->task->in_execve) __io_queue_sqe(req); else io_req_complete_failed(req, -EFAULT); From 1b48773f9fd09f311d1166ce1dd50652ebe05218 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 11 Jul 2021 22:41:13 +0100 Subject: [PATCH 185/426] io_uring: fix io_drain_req() io_drain_req() return whether the request has been consumed or not, not an error code. Fix a stupid mistake slipped from optimisation patches. Reported-by: syzbot+ba6fcd859210f4e9e109@syzkaller.appspotmail.com Fixes: 76cc33d79175a ("io_uring: refactor io_req_defer()") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/4d3c53c4274ffff307c8ae062fc7fda63b978df2.1626039606.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 118215211bb2..0cac361bf6b8 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6019,11 +6019,13 @@ static bool io_drain_req(struct io_kiocb *req) ret = io_req_prep_async(req); if (ret) - return ret; + goto fail; io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); if (!de) { - io_req_complete_failed(req, -ENOMEM); + ret = -ENOMEM; +fail: + io_req_complete_failed(req, ret); return true; } From 5937e00017f1d1dd4551e723ebfa306671f27843 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 15 Jun 2021 09:09:14 -0500 Subject: [PATCH 186/426] xfs: Fix multiple fall-through warnings for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix the following warnings by replacing /* fallthrough */ comments, and its variants, with the new pseudo-keyword macro fallthrough: fs/xfs/libxfs/xfs_attr.c:487:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:500:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:532:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:594:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:607:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:1410:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:1445:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] fs/xfs/libxfs/xfs_attr.c:1473:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Notice that Clang doesn't recognize /* fallthrough */ comments as implicit fall-through markings, so in order to globally enable -Wimplicit-fallthrough for Clang, these comments need to be replaced with fallthrough; in the whole codebase. Link: https://github.com/KSPP/linux/issues/115 Reviewed-by: Kees Cook Signed-off-by: Gustavo A. R. Silva --- fs/xfs/libxfs/xfs_attr.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index d9d7d5137b73..191d51725988 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -483,7 +483,7 @@ xfs_attr_set_iter( if (error) return error; - /* fallthrough */ + fallthrough; case XFS_DAS_RM_LBLK: /* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */ dac->dela_state = XFS_DAS_RM_LBLK; @@ -496,7 +496,7 @@ xfs_attr_set_iter( return -EAGAIN; } - /* fallthrough */ + fallthrough; case XFS_DAS_RD_LEAF: /* * This is the last step for leaf format. Read the block with @@ -528,7 +528,7 @@ xfs_attr_set_iter( return error; } - /* fallthrough */ + fallthrough; case XFS_DAS_ALLOC_NODE: /* * If there was an out-of-line value, allocate the blocks we @@ -590,7 +590,7 @@ xfs_attr_set_iter( if (error) return error; - /* fallthrough */ + fallthrough; case XFS_DAS_RM_NBLK: /* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */ dac->dela_state = XFS_DAS_RM_NBLK; @@ -603,7 +603,7 @@ xfs_attr_set_iter( return -EAGAIN; } - /* fallthrough */ + fallthrough; case XFS_DAS_CLR_FLAG: /* * The last state for node format. Look up the old attr and @@ -1406,7 +1406,7 @@ xfs_attr_remove_iter( state = dac->da_state; } - /* fallthrough */ + fallthrough; case XFS_DAS_RMTBLK: dac->dela_state = XFS_DAS_RMTBLK; @@ -1441,7 +1441,7 @@ xfs_attr_remove_iter( return -EAGAIN; } - /* fallthrough */ + fallthrough; case XFS_DAS_RM_NAME: /* * If we came here fresh from a transaction roll, reattach all @@ -1469,7 +1469,7 @@ xfs_attr_remove_iter( return -EAGAIN; } - /* fallthrough */ + fallthrough; case XFS_DAS_RM_SHRINK: /* * If the result is small enough, push it all into the inode. From d5c9d0a207f4c61734ccd4b51818788e8b86296a Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 00:44:53 -0500 Subject: [PATCH 187/426] mt76: mt7921: Fix fall-through warning for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix the following warning by explicitly adding a break statement: drivers/net/wireless/mediatek/mt76/mt7921/main.c:392:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva --- drivers/net/wireless/mediatek/mt76/mt7921/main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 7fd21049ff5a..63ec140c9c37 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -389,6 +389,7 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, case WLAN_CIPHER_SUITE_WEP104: if (!mvif->wep_sta) return -EOPNOTSUPP; + break; case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: From 4020f26b368c3e72450afedaefc2fd07ba301d20 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 00:47:57 -0500 Subject: [PATCH 188/426] nfp: flower-ct: Fix fall-through warning for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix the following warning by explicitly adding a break statement: drivers/net/ethernet/netronome/nfp/flower/conntrack.c:1175:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva --- drivers/net/ethernet/netronome/nfp/flower/conntrack.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index 273d529d43c2..684bb3efe0cf 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -1172,6 +1172,7 @@ int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent) nfp_ct_map_params); nfp_fl_ct_clean_flow_entry(ct_map_ent->ct_entry); kfree(ct_map_ent); + break; default: break; } From 81eb1d17115fba5ea67a4939a136888a7ec05c32 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 00:51:03 -0500 Subject: [PATCH 189/426] drm/i915: Fix fall-through warning for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix a warning by explicitly adding a return; statement: drivers/gpu/drm/i915/gem/i915_gem_shrinker.c:65:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva --- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index f4fb68e8955a..e382b7f2353b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -62,6 +62,7 @@ static void try_to_writeback(struct drm_i915_gem_object *obj, switch (obj->mm.madv) { case I915_MADV_DONTNEED: i915_gem_object_truncate(obj); + return; case __I915_MADV_PURGED: return; } From 2fa9fd69b3ee015a873e44f7c645ad7bcb79d290 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:35 +0100 Subject: [PATCH 190/426] clk: renesas: rzg2l: Add multi clock PM support Add multi clock PM support for cpg driver. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-2-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/renesas-rzg2l-cpg.c | 49 ++++++++++++++----------- 1 file changed, 28 insertions(+), 21 deletions(-) diff --git a/drivers/clk/renesas/renesas-rzg2l-cpg.c b/drivers/clk/renesas/renesas-rzg2l-cpg.c index 5009b9e48b13..1941f13bd922 100644 --- a/drivers/clk/renesas/renesas-rzg2l-cpg.c +++ b/drivers/clk/renesas/renesas-rzg2l-cpg.c @@ -594,42 +594,49 @@ static int rzg2l_cpg_attach_dev(struct generic_pm_domain *unused, struct device { struct device_node *np = dev->of_node; struct of_phandle_args clkspec; + bool once = true; struct clk *clk; int error; int i = 0; while (!of_parse_phandle_with_args(np, "clocks", "#clock-cells", i, &clkspec)) { - if (rzg2l_cpg_is_pm_clk(&clkspec)) - goto found; + if (rzg2l_cpg_is_pm_clk(&clkspec)) { + if (once) { + once = false; + error = pm_clk_create(dev); + if (error) { + of_node_put(clkspec.np); + goto err; + } + } + clk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); + if (IS_ERR(clk)) { + error = PTR_ERR(clk); + goto fail_destroy; + } - of_node_put(clkspec.np); + error = pm_clk_add_clk(dev, clk); + if (error) { + dev_err(dev, "pm_clk_add_clk failed %d\n", + error); + goto fail_put; + } + } else { + of_node_put(clkspec.np); + } i++; } return 0; -found: - clk = of_clk_get_from_provider(&clkspec); - of_node_put(clkspec.np); - - if (IS_ERR(clk)) - return PTR_ERR(clk); - - error = pm_clk_create(dev); - if (error) - goto fail_put; - - error = pm_clk_add_clk(dev, clk); - if (error) - goto fail_destroy; - - return 0; +fail_put: + clk_put(clk); fail_destroy: pm_clk_destroy(dev); -fail_put: - clk_put(clk); +err: return error; } From e93c1373613fb2f3e59db5f13271f155820e6a67 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:36 +0100 Subject: [PATCH 191/426] clk: renesas: r9a07g044: Rename divider table As per RZ/G2L HW Manual (Rev.0.50), CPG_PL3A_DDIV,CPG_PL3B_DDIV and CPG_PL2_DDIV(for P0) shares same divider table entries. Rename clk_div_table dtable_3b to clk_div_table dtable_1_32 so that it can be reused. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-3-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a07g044-cpg.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c index 50b5269586a4..d5803fb1242e 100644 --- a/drivers/clk/renesas/r9a07g044-cpg.c +++ b/drivers/clk/renesas/r9a07g044-cpg.c @@ -42,12 +42,13 @@ enum clk_ids { }; /* Divider tables */ -static const struct clk_div_table dtable_3b[] = { +static const struct clk_div_table dtable_1_32[] = { {0, 1}, {1, 2}, {2, 4}, {3, 8}, {4, 32}, + {0, 0}, }; static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { @@ -72,10 +73,10 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { /* Core output clk */ DEF_FIXED("I", R9A07G044_CLK_I, CLK_PLL1, 1, 1), DEF_DIV("P0", R9A07G044_CLK_P0, CLK_PLL2_DIV16, DIVPL2A, - dtable_3b, CLK_DIVIDER_HIWORD_MASK), + dtable_1_32, CLK_DIVIDER_HIWORD_MASK), DEF_FIXED("TSU", R9A07G044_CLK_TSU, CLK_PLL2_DIV20, 1, 1), DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV8, - DIVPL3B, dtable_3b, CLK_DIVIDER_HIWORD_MASK), + DIVPL3B, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), }; static struct rzg2l_mod_clk r9a07g044_mod_clks[] = { From fd8c3f6c36eb093039d4aeb20cceee00c7c6ba1a Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:37 +0100 Subject: [PATCH 192/426] clk: renesas: r9a07g044: Fix P1 Clock As per RZ/G2L HW Manual(Rev.0.50) P1 is sourced from pll3_div2_4. So fix the clock definitions for P1. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-4-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a07g044-cpg.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c index d5803fb1242e..d895c1cef1fa 100644 --- a/drivers/clk/renesas/r9a07g044-cpg.c +++ b/drivers/clk/renesas/r9a07g044-cpg.c @@ -30,8 +30,8 @@ enum clk_ids { CLK_PLL2_DIV20, CLK_PLL3, CLK_PLL3_DIV2, + CLK_PLL3_DIV2_4, CLK_PLL3_DIV4, - CLK_PLL3_DIV8, CLK_PLL4, CLK_PLL5, CLK_PLL5_DIV2, @@ -67,15 +67,15 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { DEF_FIXED(".pll2_div20", CLK_PLL2_DIV20, CLK_PLL2, 1, 20), DEF_FIXED(".pll3_div2", CLK_PLL3_DIV2, CLK_PLL3, 1, 2), + DEF_FIXED(".pll3_div2_4", CLK_PLL3_DIV2_4, CLK_PLL3_DIV2, 1, 4), DEF_FIXED(".pll3_div4", CLK_PLL3_DIV4, CLK_PLL3, 1, 4), - DEF_FIXED(".pll3_div8", CLK_PLL3_DIV8, CLK_PLL3, 1, 8), /* Core output clk */ DEF_FIXED("I", R9A07G044_CLK_I, CLK_PLL1, 1, 1), DEF_DIV("P0", R9A07G044_CLK_P0, CLK_PLL2_DIV16, DIVPL2A, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), DEF_FIXED("TSU", R9A07G044_CLK_TSU, CLK_PLL2_DIV20, 1, 1), - DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV8, + DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV2_4, DIVPL3B, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), }; From 668756f7299d2d3c75add17cb415717e247450ef Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:38 +0100 Subject: [PATCH 193/426] clk: renesas: r9a07g044: Add P2 Clock support Add support for P2 clock which is sourced from pll3_div2_4_2. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-5-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a07g044-cpg.c | 4 ++++ drivers/clk/renesas/renesas-rzg2l-cpg.h | 1 + 2 files changed, 5 insertions(+) diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c index d895c1cef1fa..70df4feda417 100644 --- a/drivers/clk/renesas/r9a07g044-cpg.c +++ b/drivers/clk/renesas/r9a07g044-cpg.c @@ -31,6 +31,7 @@ enum clk_ids { CLK_PLL3, CLK_PLL3_DIV2, CLK_PLL3_DIV2_4, + CLK_PLL3_DIV2_4_2, CLK_PLL3_DIV4, CLK_PLL4, CLK_PLL5, @@ -68,6 +69,7 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { DEF_FIXED(".pll3_div2", CLK_PLL3_DIV2, CLK_PLL3, 1, 2), DEF_FIXED(".pll3_div2_4", CLK_PLL3_DIV2_4, CLK_PLL3_DIV2, 1, 4), + DEF_FIXED(".pll3_div2_4_2", CLK_PLL3_DIV2_4_2, CLK_PLL3_DIV2_4, 1, 2), DEF_FIXED(".pll3_div4", CLK_PLL3_DIV4, CLK_PLL3, 1, 4), /* Core output clk */ @@ -77,6 +79,8 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { DEF_FIXED("TSU", R9A07G044_CLK_TSU, CLK_PLL2_DIV20, 1, 1), DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV2_4, DIVPL3B, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), + DEF_DIV("P2", R9A07G044_CLK_P2, CLK_PLL3_DIV2_4_2, + DIVPL3A, dtable_1_32, CLK_DIVIDER_HIWORD_MASK), }; static struct rzg2l_mod_clk r9a07g044_mod_clks[] = { diff --git a/drivers/clk/renesas/renesas-rzg2l-cpg.h b/drivers/clk/renesas/renesas-rzg2l-cpg.h index 3948bdd8afc9..a6a3bade1985 100644 --- a/drivers/clk/renesas/renesas-rzg2l-cpg.h +++ b/drivers/clk/renesas/renesas-rzg2l-cpg.h @@ -21,6 +21,7 @@ #define DDIV_PACK(offset, bitpos, size) \ (((offset) << 20) | ((bitpos) << 12) | ((size) << 8)) #define DIVPL2A DDIV_PACK(CPG_PL2_DDIV, 0, 3) +#define DIVPL3A DDIV_PACK(CPG_PL3A_DDIV, 0, 3) #define DIVPL3B DDIV_PACK(CPG_PL3A_DDIV, 4, 3) /** From c3e67ad6f5a2c698a055fb297c6f9962f5145edd Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 26 Jun 2021 09:13:39 +0100 Subject: [PATCH 194/426] dt-bindings: clock: r9a07g044-cpg: Update clock/reset definitions Update clock and reset definitions as per RZ/G2L_clock_list_r02_02.xlsx and RZ/G2L HW(Rev.0.50) manual. Update {GIC,IA55,SCIF} clock and reset entries in the CPG driver, and separate reset from module clocks in order to handle them efficiently. Update the SCIF0 clock and reset index in the SoC DTSI. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20210626081344.5783-6-biju.das.jz@bp.renesas.com Link: https://lore.kernel.org/r/20210626081344.5783-7-biju.das.jz@bp.renesas.com Link: https://lore.kernel.org/r/20210626081344.5783-8-biju.das.jz@bp.renesas.com [geert: Squashed 3 commits] Signed-off-by: Geert Uytterhoeven --- arch/arm64/boot/dts/renesas/r9a07g044.dtsi | 4 +- drivers/clk/renesas/r9a07g044-cpg.c | 62 +++--- drivers/clk/renesas/renesas-rzg2l-cpg.c | 59 +++--- drivers/clk/renesas/renesas-rzg2l-cpg.h | 36 +++- include/dt-bindings/clock/r9a07g044-cpg.h | 236 ++++++++++++++++----- 5 files changed, 278 insertions(+), 119 deletions(-) diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi index 734c8adeceba..01482d227506 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi @@ -82,10 +82,10 @@ ; interrupt-names = "eri", "rxi", "txi", "bri", "dri", "tei"; - clocks = <&cpg CPG_MOD R9A07G044_CLK_SCIF0>; + clocks = <&cpg CPG_MOD R9A07G044_SCIF0_CLK_PCK>; clock-names = "fck"; power-domains = <&cpg>; - resets = <&cpg R9A07G044_CLK_SCIF0>; + resets = <&cpg R9A07G044_SCIF0_RST_SYSTEM_N>; status = "disabled"; }; diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c index 70df4feda417..ae24e0397d3c 100644 --- a/drivers/clk/renesas/r9a07g044-cpg.c +++ b/drivers/clk/renesas/r9a07g044-cpg.c @@ -84,34 +84,40 @@ static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = { }; static struct rzg2l_mod_clk r9a07g044_mod_clks[] = { - DEF_MOD("gic", R9A07G044_CLK_GIC600, - R9A07G044_CLK_P1, - 0x514, BIT(0), (BIT(0) | BIT(1))), - DEF_MOD("ia55", R9A07G044_CLK_IA55, - R9A07G044_CLK_P1, - 0x518, (BIT(0) | BIT(1)), BIT(0)), - DEF_MOD("scif0", R9A07G044_CLK_SCIF0, - R9A07G044_CLK_P0, - 0x584, BIT(0), BIT(0)), - DEF_MOD("scif1", R9A07G044_CLK_SCIF1, - R9A07G044_CLK_P0, - 0x584, BIT(1), BIT(1)), - DEF_MOD("scif2", R9A07G044_CLK_SCIF2, - R9A07G044_CLK_P0, - 0x584, BIT(2), BIT(2)), - DEF_MOD("scif3", R9A07G044_CLK_SCIF3, - R9A07G044_CLK_P0, - 0x584, BIT(3), BIT(3)), - DEF_MOD("scif4", R9A07G044_CLK_SCIF4, - R9A07G044_CLK_P0, - 0x584, BIT(4), BIT(4)), - DEF_MOD("sci0", R9A07G044_CLK_SCI0, - R9A07G044_CLK_P0, - 0x588, BIT(0), BIT(0)), + DEF_MOD("gic", R9A07G044_GIC600_GICCLK, R9A07G044_CLK_P1, + 0x514, 0), + DEF_MOD("ia55_pclk", R9A07G044_IA55_PCLK, R9A07G044_CLK_P2, + 0x518, 0), + DEF_MOD("ia55_clk", R9A07G044_IA55_CLK, R9A07G044_CLK_P1, + 0x518, 1), + DEF_MOD("scif0", R9A07G044_SCIF0_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 0), + DEF_MOD("scif1", R9A07G044_SCIF1_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 1), + DEF_MOD("scif2", R9A07G044_SCIF2_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 2), + DEF_MOD("scif3", R9A07G044_SCIF3_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 3), + DEF_MOD("scif4", R9A07G044_SCIF4_CLK_PCK, R9A07G044_CLK_P0, + 0x584, 4), + DEF_MOD("sci0", R9A07G044_SCI0_CLKP, R9A07G044_CLK_P0, + 0x588, 0), +}; + +static struct rzg2l_reset r9a07g044_resets[] = { + DEF_RST(R9A07G044_GIC600_GICRESET_N, 0x814, 0), + DEF_RST(R9A07G044_GIC600_DBG_GICRESET_N, 0x814, 1), + DEF_RST(R9A07G044_IA55_RESETN, 0x818, 0), + DEF_RST(R9A07G044_SCIF0_RST_SYSTEM_N, 0x884, 0), + DEF_RST(R9A07G044_SCIF1_RST_SYSTEM_N, 0x884, 1), + DEF_RST(R9A07G044_SCIF2_RST_SYSTEM_N, 0x884, 2), + DEF_RST(R9A07G044_SCIF3_RST_SYSTEM_N, 0x884, 3), + DEF_RST(R9A07G044_SCIF4_RST_SYSTEM_N, 0x884, 4), + DEF_RST(R9A07G044_SCI0_RST, 0x888, 0), }; static const unsigned int r9a07g044_crit_mod_clks[] __initconst = { - MOD_CLK_BASE + R9A07G044_CLK_GIC600, + MOD_CLK_BASE + R9A07G044_GIC600_GICCLK, }; const struct rzg2l_cpg_info r9a07g044_cpg_info = { @@ -128,5 +134,9 @@ const struct rzg2l_cpg_info r9a07g044_cpg_info = { /* Module Clocks */ .mod_clks = r9a07g044_mod_clks, .num_mod_clks = ARRAY_SIZE(r9a07g044_mod_clks), - .num_hw_mod_clks = R9A07G044_CLK_MIPI_DSI_PIN + 1, + .num_hw_mod_clks = R9A07G044_TSU_PCLK + 1, + + /* Resets */ + .resets = r9a07g044_resets, + .num_resets = ARRAY_SIZE(r9a07g044_resets), }; diff --git a/drivers/clk/renesas/renesas-rzg2l-cpg.c b/drivers/clk/renesas/renesas-rzg2l-cpg.c index 1941f13bd922..e7c59af2a1d8 100644 --- a/drivers/clk/renesas/renesas-rzg2l-cpg.c +++ b/drivers/clk/renesas/renesas-rzg2l-cpg.c @@ -47,9 +47,9 @@ #define SDIV(val) DIV_RSMASK(val, 0, 0x7) #define CLK_ON_R(reg) (reg) -#define CLK_MON_R(reg) (0x680 - 0x500 + (reg)) -#define CLK_RST_R(reg) (0x800 - 0x500 + (reg)) -#define CLK_MRST_R(reg) (0x980 - 0x500 + (reg)) +#define CLK_MON_R(reg) (0x180 + (reg)) +#define CLK_RST_R(reg) (reg) +#define CLK_MRST_R(reg) (0x180 + (reg)) #define GET_REG_OFFSET(val) ((val >> 20) & 0xfff) #define GET_REG_SAMPLL_CLK1(val) ((val >> 22) & 0xfff) @@ -78,6 +78,7 @@ struct rzg2l_cpg_priv { struct clk **clks; unsigned int num_core_clks; unsigned int num_mod_clks; + unsigned int num_resets; unsigned int last_dt_core_clk; struct raw_notifier_head notifiers; @@ -315,15 +316,13 @@ fail: * * @hw: handle between common and hardware-specific interfaces * @off: register offset - * @onoff: ON/MON bits - * @reset: reset bits + * @bit: ON/MON bit * @priv: CPG/MSTP private data */ struct mstp_clock { struct clk_hw hw; u16 off; - u8 onoff; - u8 reset; + u8 bit; struct rzg2l_cpg_priv *priv; }; @@ -337,6 +336,7 @@ static int rzg2l_mod_clock_endisable(struct clk_hw *hw, bool enable) struct device *dev = priv->dev; unsigned long flags; unsigned int i; + u32 bitmask = BIT(clock->bit); u32 value; if (!clock->off) { @@ -349,9 +349,9 @@ static int rzg2l_mod_clock_endisable(struct clk_hw *hw, bool enable) spin_lock_irqsave(&priv->rmw_lock, flags); if (enable) - value = (clock->onoff << 16) | clock->onoff; + value = (bitmask << 16) | bitmask; else - value = clock->onoff << 16; + value = bitmask << 16; writel(value, priv->base + CLK_ON_R(reg)); spin_unlock_irqrestore(&priv->rmw_lock, flags); @@ -360,7 +360,7 @@ static int rzg2l_mod_clock_endisable(struct clk_hw *hw, bool enable) return 0; for (i = 1000; i > 0; --i) { - if (((readl(priv->base + CLK_MON_R(reg))) & clock->onoff)) + if (((readl(priv->base + CLK_MON_R(reg))) & bitmask)) break; cpu_relax(); } @@ -388,6 +388,7 @@ static int rzg2l_mod_clock_is_enabled(struct clk_hw *hw) { struct mstp_clock *clock = to_mod_clock(hw); struct rzg2l_cpg_priv *priv = clock->priv; + u32 bitmask = BIT(clock->bit); u32 value; if (!clock->off) { @@ -397,7 +398,7 @@ static int rzg2l_mod_clock_is_enabled(struct clk_hw *hw) value = readl(priv->base + CLK_MON_R(clock->off)); - return !(value & clock->onoff); + return !(value & bitmask); } static const struct clk_ops rzg2l_mod_clock_ops = { @@ -457,8 +458,7 @@ rzg2l_cpg_register_mod_clk(const struct rzg2l_mod_clk *mod, init.num_parents = 1; clock->off = mod->off; - clock->onoff = mod->onoff; - clock->reset = mod->reset; + clock->bit = mod->bit; clock->priv = priv; clock->hw.init = &init; @@ -483,12 +483,11 @@ static int rzg2l_cpg_reset(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->mod_clks[id].off; - u32 dis = info->mod_clks[id].reset; + unsigned int reg = info->resets[id].off; + u32 dis = BIT(info->resets[id].bit); u32 we = dis << 16; - dev_dbg(rcdev->dev, "reset name:%s id:%ld offset:0x%x\n", - info->mod_clks[id].name, id, CLK_RST_R(reg)); + dev_dbg(rcdev->dev, "reset id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); /* Reset module */ writel(we, priv->base + CLK_RST_R(reg)); @@ -507,11 +506,10 @@ static int rzg2l_cpg_assert(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->mod_clks[id].off; - u32 value = info->mod_clks[id].reset << 16; + unsigned int reg = info->resets[id].off; + u32 value = BIT(info->resets[id].bit) << 16; - dev_dbg(rcdev->dev, "assert name:%s id:%ld offset:0x%x\n", - info->mod_clks[id].name, id, CLK_RST_R(reg)); + dev_dbg(rcdev->dev, "assert id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); writel(value, priv->base + CLK_RST_R(reg)); return 0; @@ -522,12 +520,12 @@ static int rzg2l_cpg_deassert(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->mod_clks[id].off; - u32 dis = info->mod_clks[id].reset; + unsigned int reg = info->resets[id].off; + u32 dis = BIT(info->resets[id].bit); u32 value = (dis << 16) | dis; - dev_dbg(rcdev->dev, "deassert name:%s id:%ld offset:0x%x\n", - info->mod_clks[id].name, id, CLK_RST_R(reg)); + dev_dbg(rcdev->dev, "deassert id:%ld offset:0x%x\n", id, + CLK_RST_R(reg)); writel(value, priv->base + CLK_RST_R(reg)); return 0; @@ -538,8 +536,8 @@ static int rzg2l_cpg_status(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->mod_clks[id].off; - u32 bitmask = info->mod_clks[id].reset; + unsigned int reg = info->resets[id].off; + u32 bitmask = BIT(info->resets[id].bit); return !(readl(priv->base + CLK_MRST_R(reg)) & bitmask); } @@ -554,9 +552,11 @@ static const struct reset_control_ops rzg2l_cpg_reset_ops = { static int rzg2l_cpg_reset_xlate(struct reset_controller_dev *rcdev, const struct of_phandle_args *reset_spec) { + struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); + const struct rzg2l_cpg_info *info = priv->info; unsigned int id = reset_spec->args[0]; - if (id >= rcdev->nr_resets) { + if (id >= rcdev->nr_resets || !info->resets[id].off) { dev_err(rcdev->dev, "Invalid reset index %u\n", id); return -EINVAL; } @@ -571,7 +571,7 @@ static int rzg2l_cpg_reset_controller_register(struct rzg2l_cpg_priv *priv) priv->rcdev.dev = priv->dev; priv->rcdev.of_reset_n_cells = 1; priv->rcdev.of_xlate = rzg2l_cpg_reset_xlate; - priv->rcdev.nr_resets = priv->num_mod_clks; + priv->rcdev.nr_resets = priv->num_resets; return devm_reset_controller_register(priv->dev, &priv->rcdev); } @@ -699,6 +699,7 @@ static int __init rzg2l_cpg_probe(struct platform_device *pdev) priv->clks = clks; priv->num_core_clks = info->num_total_core_clks; priv->num_mod_clks = info->num_hw_mod_clks; + priv->num_resets = info->num_resets; priv->last_dt_core_clk = info->last_dt_core_clk; for (i = 0; i < nclks; i++) diff --git a/drivers/clk/renesas/renesas-rzg2l-cpg.h b/drivers/clk/renesas/renesas-rzg2l-cpg.h index a6a3bade1985..63695280ce8b 100644 --- a/drivers/clk/renesas/renesas-rzg2l-cpg.h +++ b/drivers/clk/renesas/renesas-rzg2l-cpg.h @@ -77,26 +77,40 @@ enum clk_types { * @id: clock index in array containing all Core and Module Clocks * @parent: id of parent clock * @off: register offset - * @onoff: ON/MON bits - * @reset: reset bits + * @bit: ON/MON bit */ struct rzg2l_mod_clk { const char *name; unsigned int id; unsigned int parent; u16 off; - u8 onoff; - u8 reset; + u8 bit; }; -#define DEF_MOD(_name, _id, _parent, _off, _onoff, _reset) \ - [_id] = { \ +#define DEF_MOD(_name, _id, _parent, _off, _bit) \ + { \ .name = _name, \ - .id = MOD_CLK_BASE + _id, \ + .id = MOD_CLK_BASE + (_id), \ .parent = (_parent), \ .off = (_off), \ - .onoff = (_onoff), \ - .reset = (_reset) \ + .bit = (_bit), \ + } + +/** + * struct rzg2l_reset - Reset definitions + * + * @off: register offset + * @bit: reset bit + */ +struct rzg2l_reset { + u16 off; + u8 bit; +}; + +#define DEF_RST(_id, _off, _bit) \ + [_id] = { \ + .off = (_off), \ + .bit = (_bit) \ } /** @@ -127,6 +141,10 @@ struct rzg2l_cpg_info { unsigned int num_mod_clks; unsigned int num_hw_mod_clks; + /* Resets */ + const struct rzg2l_reset *resets; + unsigned int num_resets; + /* Critical Module Clocks that should not be disabled */ const unsigned int *crit_mod_clks; unsigned int num_crit_mod_clks; diff --git a/include/dt-bindings/clock/r9a07g044-cpg.h b/include/dt-bindings/clock/r9a07g044-cpg.h index 1d8986563fc5..0728ad07ff7a 100644 --- a/include/dt-bindings/clock/r9a07g044-cpg.h +++ b/include/dt-bindings/clock/r9a07g044-cpg.h @@ -32,58 +32,188 @@ #define R9A07G044_OSCCLK 21 /* R9A07G044 Module Clocks */ -#define R9A07G044_CLK_GIC600 0 -#define R9A07G044_CLK_IA55 1 -#define R9A07G044_CLK_SYC 2 -#define R9A07G044_CLK_DMAC 3 -#define R9A07G044_CLK_SYSC 4 -#define R9A07G044_CLK_MTU 5 -#define R9A07G044_CLK_GPT 6 -#define R9A07G044_CLK_ETH0 7 -#define R9A07G044_CLK_ETH1 8 -#define R9A07G044_CLK_I2C0 9 -#define R9A07G044_CLK_I2C1 10 -#define R9A07G044_CLK_I2C2 11 -#define R9A07G044_CLK_I2C3 12 -#define R9A07G044_CLK_SCIF0 13 -#define R9A07G044_CLK_SCIF1 14 -#define R9A07G044_CLK_SCIF2 15 -#define R9A07G044_CLK_SCIF3 16 -#define R9A07G044_CLK_SCIF4 17 -#define R9A07G044_CLK_SCI0 18 -#define R9A07G044_CLK_SCI1 19 -#define R9A07G044_CLK_GPIO 20 -#define R9A07G044_CLK_SDHI0 21 -#define R9A07G044_CLK_SDHI1 22 -#define R9A07G044_CLK_USB0 23 -#define R9A07G044_CLK_USB1 24 -#define R9A07G044_CLK_CANFD 25 -#define R9A07G044_CLK_SSI0 26 -#define R9A07G044_CLK_SSI1 27 -#define R9A07G044_CLK_SSI2 28 -#define R9A07G044_CLK_SSI3 29 -#define R9A07G044_CLK_MHU 30 -#define R9A07G044_CLK_OSTM0 31 -#define R9A07G044_CLK_OSTM1 32 -#define R9A07G044_CLK_OSTM2 33 -#define R9A07G044_CLK_WDT0 34 -#define R9A07G044_CLK_WDT1 35 -#define R9A07G044_CLK_WDT2 36 -#define R9A07G044_CLK_WDT_PON 37 -#define R9A07G044_CLK_GPU 38 -#define R9A07G044_CLK_ISU 39 -#define R9A07G044_CLK_H264 40 -#define R9A07G044_CLK_CRU 41 -#define R9A07G044_CLK_MIPI_DSI 42 -#define R9A07G044_CLK_LCDC 43 -#define R9A07G044_CLK_SRC 44 -#define R9A07G044_CLK_RSPI0 45 -#define R9A07G044_CLK_RSPI1 46 -#define R9A07G044_CLK_RSPI2 47 -#define R9A07G044_CLK_ADC 48 -#define R9A07G044_CLK_TSU_PCLK 49 -#define R9A07G044_CLK_SPI 50 -#define R9A07G044_CLK_MIPI_DSI_V 51 -#define R9A07G044_CLK_MIPI_DSI_PIN 52 +#define R9A07G044_CA55_SCLK 0 +#define R9A07G044_CA55_PCLK 1 +#define R9A07G044_CA55_ATCLK 2 +#define R9A07G044_CA55_GICCLK 3 +#define R9A07G044_CA55_PERICLK 4 +#define R9A07G044_CA55_ACLK 5 +#define R9A07G044_CA55_TSCLK 6 +#define R9A07G044_GIC600_GICCLK 7 +#define R9A07G044_IA55_CLK 8 +#define R9A07G044_IA55_PCLK 9 +#define R9A07G044_MHU_PCLK 10 +#define R9A07G044_SYC_CNT_CLK 11 +#define R9A07G044_DMAC_ACLK 12 +#define R9A07G044_DMAC_PCLK 13 +#define R9A07G044_OSTM0_PCLK 14 +#define R9A07G044_OSTM1_PCLK 15 +#define R9A07G044_OSTM2_PCLK 16 +#define R9A07G044_MTU_X_MCK_MTU3 17 +#define R9A07G044_POE3_CLKM_POE 18 +#define R9A07G044_GPT_PCLK 19 +#define R9A07G044_POEG_A_CLKP 20 +#define R9A07G044_POEG_B_CLKP 21 +#define R9A07G044_POEG_C_CLKP 22 +#define R9A07G044_POEG_D_CLKP 23 +#define R9A07G044_WDT0_PCLK 24 +#define R9A07G044_WDT0_CLK 25 +#define R9A07G044_WDT1_PCLK 26 +#define R9A07G044_WDT1_CLK 27 +#define R9A07G044_WDT2_PCLK 28 +#define R9A07G044_WDT2_CLK 29 +#define R9A07G044_SPI_CLK2 30 +#define R9A07G044_SPI_CLK 31 +#define R9A07G044_SDHI0_IMCLK 32 +#define R9A07G044_SDHI0_IMCLK2 33 +#define R9A07G044_SDHI0_CLK_HS 34 +#define R9A07G044_SDHI0_ACLK 35 +#define R9A07G044_SDHI1_IMCLK 36 +#define R9A07G044_SDHI1_IMCLK2 37 +#define R9A07G044_SDHI1_CLK_HS 38 +#define R9A07G044_SDHI1_ACLK 39 +#define R9A07G044_GPU_CLK 40 +#define R9A07G044_GPU_AXI_CLK 41 +#define R9A07G044_GPU_ACE_CLK 42 +#define R9A07G044_ISU_ACLK 43 +#define R9A07G044_ISU_PCLK 44 +#define R9A07G044_H264_CLK_A 45 +#define R9A07G044_H264_CLK_P 46 +#define R9A07G044_CRU_SYSCLK 47 +#define R9A07G044_CRU_VCLK 48 +#define R9A07G044_CRU_PCLK 49 +#define R9A07G044_CRU_ACLK 50 +#define R9A07G044_MIPI_DSI_PLLCLK 51 +#define R9A07G044_MIPI_DSI_SYSCLK 52 +#define R9A07G044_MIPI_DSI_ACLK 53 +#define R9A07G044_MIPI_DSI_PCLK 54 +#define R9A07G044_MIPI_DSI_VCLK 55 +#define R9A07G044_MIPI_DSI_LPCLK 56 +#define R9A07G044_LCDC_CLK_A 57 +#define R9A07G044_LCDC_CLK_P 58 +#define R9A07G044_LCDC_CLK_D 59 +#define R9A07G044_SSI0_PCLK2 60 +#define R9A07G044_SSI0_PCLK_SFR 61 +#define R9A07G044_SSI1_PCLK2 62 +#define R9A07G044_SSI1_PCLK_SFR 63 +#define R9A07G044_SSI2_PCLK2 64 +#define R9A07G044_SSI2_PCLK_SFR 65 +#define R9A07G044_SSI3_PCLK2 66 +#define R9A07G044_SSI3_PCLK_SFR 67 +#define R9A07G044_SRC_CLKP 68 +#define R9A07G044_USB_U2H0_HCLK 69 +#define R9A07G044_USB_U2H1_HCLK 70 +#define R9A07G044_USB_U2P_EXR_CPUCLK 71 +#define R9A07G044_USB_PCLK 72 +#define R9A07G044_ETH0_CLK_AXI 73 +#define R9A07G044_ETH0_CLK_CHI 74 +#define R9A07G044_ETH1_CLK_AXI 75 +#define R9A07G044_ETH1_CLK_CHI 76 +#define R9A07G044_I2C0_PCLK 77 +#define R9A07G044_I2C1_PCLK 78 +#define R9A07G044_I2C2_PCLK 79 +#define R9A07G044_I2C3_PCLK 80 +#define R9A07G044_SCIF0_CLK_PCK 81 +#define R9A07G044_SCIF1_CLK_PCK 82 +#define R9A07G044_SCIF2_CLK_PCK 83 +#define R9A07G044_SCIF3_CLK_PCK 84 +#define R9A07G044_SCIF4_CLK_PCK 85 +#define R9A07G044_SCI0_CLKP 86 +#define R9A07G044_SCI1_CLKP 87 +#define R9A07G044_IRDA_CLKP 88 +#define R9A07G044_RSPI0_CLKB 89 +#define R9A07G044_RSPI1_CLKB 90 +#define R9A07G044_RSPI2_CLKB 91 +#define R9A07G044_CANFD_PCLK 92 +#define R9A07G044_GPIO_HCLK 93 +#define R9A07G044_ADC_ADCLK 94 +#define R9A07G044_ADC_PCLK 95 +#define R9A07G044_TSU_PCLK 96 + +/* R9A07G044 Resets */ +#define R9A07G044_CA55_RST_1_0 0 +#define R9A07G044_CA55_RST_1_1 1 +#define R9A07G044_CA55_RST_3_0 2 +#define R9A07G044_CA55_RST_3_1 3 +#define R9A07G044_CA55_RST_4 4 +#define R9A07G044_CA55_RST_5 5 +#define R9A07G044_CA55_RST_6 6 +#define R9A07G044_CA55_RST_7 7 +#define R9A07G044_CA55_RST_8 8 +#define R9A07G044_CA55_RST_9 9 +#define R9A07G044_CA55_RST_10 10 +#define R9A07G044_CA55_RST_11 11 +#define R9A07G044_CA55_RST_12 12 +#define R9A07G044_GIC600_GICRESET_N 13 +#define R9A07G044_GIC600_DBG_GICRESET_N 14 +#define R9A07G044_IA55_RESETN 15 +#define R9A07G044_MHU_RESETN 16 +#define R9A07G044_DMAC_ARESETN 17 +#define R9A07G044_DMAC_RST_ASYNC 18 +#define R9A07G044_SYC_RESETN 19 +#define R9A07G044_OSTM0_PRESETZ 20 +#define R9A07G044_OSTM1_PRESETZ 21 +#define R9A07G044_OSTM2_PRESETZ 22 +#define R9A07G044_MTU_X_PRESET_MTU3 23 +#define R9A07G044_POE3_RST_M_REG 24 +#define R9A07G044_GPT_RST_C 25 +#define R9A07G044_POEG_A_RST 26 +#define R9A07G044_POEG_B_RST 27 +#define R9A07G044_POEG_C_RST 28 +#define R9A07G044_POEG_D_RST 29 +#define R9A07G044_WDT0_PRESETN 30 +#define R9A07G044_WDT1_PRESETN 31 +#define R9A07G044_WDT2_PRESETN 32 +#define R9A07G044_SPI_RST 33 +#define R9A07G044_SDHI0_IXRST 34 +#define R9A07G044_SDHI1_IXRST 35 +#define R9A07G044_GPU_RESETN 36 +#define R9A07G044_GPU_AXI_RESETN 37 +#define R9A07G044_GPU_ACE_RESETN 38 +#define R9A07G044_ISU_ARESETN 39 +#define R9A07G044_ISU_PRESETN 40 +#define R9A07G044_H264_X_RESET_VCP 41 +#define R9A07G044_H264_CP_PRESET_P 42 +#define R9A07G044_CRU_CMN_RSTB 43 +#define R9A07G044_CRU_PRESETN 44 +#define R9A07G044_CRU_ARESETN 45 +#define R9A07G044_MIPI_DSI_CMN_RSTB 46 +#define R9A07G044_MIPI_DSI_ARESET_N 47 +#define R9A07G044_MIPI_DSI_PRESET_N 48 +#define R9A07G044_LCDC_RESET_N 49 +#define R9A07G044_SSI0_RST_M2_REG 50 +#define R9A07G044_SSI1_RST_M2_REG 51 +#define R9A07G044_SSI2_RST_M2_REG 52 +#define R9A07G044_SSI3_RST_M2_REG 53 +#define R9A07G044_SRC_RST 54 +#define R9A07G044_USB_U2H0_HRESETN 55 +#define R9A07G044_USB_U2H1_HRESETN 56 +#define R9A07G044_USB_U2P_EXL_SYSRST 57 +#define R9A07G044_USB_PRESETN 58 +#define R9A07G044_ETH0_RST_HW_N 59 +#define R9A07G044_ETH1_RST_HW_N 60 +#define R9A07G044_I2C0_MRST 61 +#define R9A07G044_I2C1_MRST 62 +#define R9A07G044_I2C2_MRST 63 +#define R9A07G044_I2C3_MRST 64 +#define R9A07G044_SCIF0_RST_SYSTEM_N 65 +#define R9A07G044_SCIF1_RST_SYSTEM_N 66 +#define R9A07G044_SCIF2_RST_SYSTEM_N 67 +#define R9A07G044_SCIF3_RST_SYSTEM_N 68 +#define R9A07G044_SCIF4_RST_SYSTEM_N 69 +#define R9A07G044_SCI0_RST 70 +#define R9A07G044_SCI1_RST 71 +#define R9A07G044_IRDA_RST 72 +#define R9A07G044_RSPI0_RST 73 +#define R9A07G044_RSPI1_RST 74 +#define R9A07G044_RSPI2_RST 75 +#define R9A07G044_CANFD_RSTP_N 76 +#define R9A07G044_CANFD_RSTC_N 77 +#define R9A07G044_GPIO_RSTN 78 +#define R9A07G044_GPIO_PORT_RESETN 79 +#define R9A07G044_GPIO_SPARE_RESETN 80 +#define R9A07G044_ADC_PRESETN 81 +#define R9A07G044_ADC_ADRST_N 82 +#define R9A07G044_TSU_PRESETN 83 #endif /* __DT_BINDINGS_CLOCK_R9A07G044_CPG_H__ */ From ffe000217c5068c5da07ccb1c0f8cce7ad767435 Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Thu, 24 Jun 2021 12:47:32 -0500 Subject: [PATCH 195/426] dma-buf/sync_file: Don't leak fences on merge failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Each add_fence() call does a dma_fence_get() on the relevant fence. In the error path, we weren't calling dma_fence_put() so all those fences got leaked. Also, in the krealloc_array failure case, we weren't freeing the fences array. Instead, ensure that i and fences are always zero-initialized and dma_fence_put() all the fences and kfree(fences) on every error path. Signed-off-by: Jason Ekstrand Reviewed-by: Christian König Fixes: a02b9dc90d84 ("dma-buf/sync_file: refactor fence storage in struct sync_file") Cc: Gustavo Padovan Cc: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20210624174732.1754546-1-jason@jlekstrand.net Signed-off-by: Christian König --- drivers/dma-buf/sync_file.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 20d9bddbb985..394e6e1e9686 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -211,8 +211,8 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { struct sync_file *sync_file; - struct dma_fence **fences, **nfences, **a_fences, **b_fences; - int i, i_a, i_b, num_fences, a_num_fences, b_num_fences; + struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences; + int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences; sync_file = sync_file_alloc(); if (!sync_file) @@ -236,7 +236,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, * If a sync_file can only be created with sync_file_merge * and sync_file_create, this is a reasonable assumption. */ - for (i = i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { + for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { struct dma_fence *pt_a = a_fences[i_a]; struct dma_fence *pt_b = b_fences[i_b]; @@ -277,15 +277,16 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, fences = nfences; } - if (sync_file_set_fence(sync_file, fences, i) < 0) { - kfree(fences); + if (sync_file_set_fence(sync_file, fences, i) < 0) goto err; - } strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; err: + while (i) + dma_fence_put(fences[--i]); + kfree(fences); fput(sync_file->file); return NULL; From 5f34b1eb2f8d4bba7d6352e767ef84bee9096d97 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 12 Jul 2021 10:00:43 +0100 Subject: [PATCH 196/426] arm64: fix strlen() with CONFIG_KASAN_HW_TAGS When the kernel is built with CONFIG_KASAN_HW_TAGS and the CPU supports MTE, memory accesses are checked at 16-byte granularity, and out-of-bounds accesses can result in tag check faults. Our current implementation of strlen() makes unaligned 16-byte accesses (within a naturally aligned 4096-byte window), and can trigger tag check faults. This can be seen at boot time, e.g. | BUG: KASAN: invalid-access in __pi_strlen+0x14/0x150 | Read at addr f4ff0000c0028300 by task swapper/0/0 | Pointer tag: [f4], memory tag: [fe] | | CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.13.0-09550-g03c2813535a2-dirty #20 | Hardware name: linux,dummy-virt (DT) | Call trace: | dump_backtrace+0x0/0x1b0 | show_stack+0x1c/0x30 | dump_stack_lvl+0x68/0x84 | print_address_description+0x7c/0x2b4 | kasan_report+0x138/0x38c | __do_kernel_fault+0x190/0x1c4 | do_tag_check_fault+0x78/0x90 | do_mem_abort+0x44/0xb4 | el1_abort+0x40/0x60 | el1h_64_sync_handler+0xb0/0xd0 | el1h_64_sync+0x78/0x7c | __pi_strlen+0x14/0x150 | __register_sysctl_table+0x7c4/0x890 | register_leaf_sysctl_tables+0x1a4/0x210 | register_leaf_sysctl_tables+0xc8/0x210 | __register_sysctl_paths+0x22c/0x290 | register_sysctl_table+0x2c/0x40 | sysctl_init+0x20/0x30 | proc_sys_init+0x3c/0x48 | proc_root_init+0x80/0x9c | start_kernel+0x640/0x69c | __primary_switched+0xc0/0xc8 To fix this, we can reduce the (strlen-internal) MIN_PAGE_SIZE to 16 bytes when CONFIG_KASAN_HW_TAGS is selected. This will cause strlen() to align the base pointer downwards to a 16-byte boundary, and to discard the additional prefix bytes without counting them. All subsequent accesses will be 16-byte aligned 16-byte LDPs. While the comments say the body of the loop will access 32 bytes, this is performed as two 16-byte acceses, with the second made only if the first did not encounter a NUL byte, so the body of the loop will not over-read across a 16-byte boundary. No other string routines are affected. The other str*() routines will not make any access which straddles a 16-byte boundary, and the mem*() routines will only make acceses which straddle a 16-byte boundary when which is entirely within the bounds of the relevant base and size arguments. Fixes: 325a1de81287 ("arm64: Import updated version of Cortex Strings' strlen") Signed-off-by: Mark Rutland Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Marco Elver Cc: Robin Murphy Cc: Will Deacon Reviewed-by: Catalin Marinas Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20210712090043.20847-1-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/lib/strlen.S | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S index 35fbdb7d6e1a..1648790e91b3 100644 --- a/arch/arm64/lib/strlen.S +++ b/arch/arm64/lib/strlen.S @@ -8,6 +8,7 @@ #include #include +#include /* Assumptions: * @@ -42,7 +43,16 @@ #define REP8_7f 0x7f7f7f7f7f7f7f7f #define REP8_80 0x8080808080808080 +/* + * When KASAN_HW_TAGS is in use, memory is checked at MTE_GRANULE_SIZE + * (16-byte) granularity, and we must ensure that no access straddles this + * alignment boundary. + */ +#ifdef CONFIG_KASAN_HW_TAGS +#define MIN_PAGE_SIZE MTE_GRANULE_SIZE +#else #define MIN_PAGE_SIZE 4096 +#endif /* Since strings are short on average, we check the first 16 bytes of the string for a NUL character. In order to do an unaligned ldp From e62e074814862cffd8e60a1bdf52d6b592a03675 Mon Sep 17 00:00:00 2001 From: Carlos Bilbao Date: Thu, 8 Jul 2021 07:15:42 -0400 Subject: [PATCH 197/426] arm64: Add missing header in two files Add missing header on include/asm/smp_plat.h, as it calls function cpu_logical_map(). Also include it on kernel/cpufeature.c since it has calls to functions cpu_panic_kernel() and cpu_die_early(). Both files call functions defined on this header, make the header dependencies less fragile. Signed-off-by: Carlos Bilbao Acked-by: Mark Rutland Link: https://lore.kernel.org/r/4325940.LvFx2qVVIh@iron-maiden Signed-off-by: Will Deacon --- arch/arm64/include/asm/smp_plat.h | 1 + arch/arm64/kernel/cpufeature.c | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h index 99ad77df8f52..97ddc6c203b7 100644 --- a/arch/arm64/include/asm/smp_plat.h +++ b/arch/arm64/include/asm/smp_plat.h @@ -10,6 +10,7 @@ #include +#include #include struct mpidr_hash { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 125d5c9471ac..0ead8bfedf20 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -81,6 +81,7 @@ #include #include #include +#include #include #include #include From c1132702c71f4b95db9435bac5fdc912881563e0 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 12 Jul 2021 13:10:00 +0100 Subject: [PATCH 198/426] Revert "arm64: cache: Lower ARCH_DMA_MINALIGN to 64 (L1_CACHE_BYTES)" This reverts commit 65688d2a05deb9f0671a7e2301eadbfe7e27c9e9. Unfortunately, the original Qualcomm Kryo cores integrated into the MSM8996 SoC feature an L2 cache with 128-byte lines which sits above the Point of Coherency. Consequently, we must restore ARCH_DMA_MINALIGN to its former ugly self so that non-coherent DMA can be performed safely on devices built using this SoC. Thanks to Jeffrey Hugo for confirming this with a hardware designer. Link: https://lore.kernel.org/r/CAOCk7NqdpUZFMSXfGjw0_1NaSK5gyTLgpS9kSdZn1jmBy-QkfA@mail.gmail.com/ Reported-by: Yassine Oudjana Link: https://lore.kernel.org/r/uHgsRacR8hJ7nW-I-pIcehzg-lNIn7NJvaL7bP9tfAftFsBjsgaY2qTjG9zyBgxHkjNL1WPNrD7YVv2JVD2_Wy-a5VTbcq-1xEi8ZnwrXBo=@protonmail.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/cache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index a9c0716e7440..a074459f8f2f 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -47,7 +47,7 @@ * cache before the transfer is done, causing old data to be seen by * the CPU. */ -#define ARCH_DMA_MINALIGN L1_CACHE_BYTES +#define ARCH_DMA_MINALIGN (128) #ifdef CONFIG_KASAN_SW_TAGS #define ARCH_SLAB_MINALIGN (1ULL << KASAN_SHADOW_SCALE_SHIFT) From 38e0c99249f8f12e1450234a0f7fb357a1b73843 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 24 Jun 2021 10:50:58 +0100 Subject: [PATCH 199/426] firmware: arm_scmi: Simplify device probe function on the bus MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the driver core calls the probe callback it already checked that the devices match, so there is no need to call the match callback again. Link: https://lore.kernel.org/r/20210624095059.4010157-1-sudeep.holla@arm.com Suggested-by: Uwe Kleine-König Tested-by: Cristian Marussi Reviewed-by: Cristian Marussi Acked-by: Uwe Kleine-König Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 784cf0027da3..dc113ad37ad9 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -104,11 +104,6 @@ static int scmi_dev_probe(struct device *dev) { struct scmi_driver *scmi_drv = to_scmi_driver(dev->driver); struct scmi_device *scmi_dev = to_scmi_dev(dev); - const struct scmi_device_id *id; - - id = scmi_dev_match_id(scmi_dev, scmi_drv); - if (!id) - return -ENODEV; if (!scmi_dev->handle) return -EPROBE_DEFER; From 5e469dac326555d2038d199a6329458cc82a34e5 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 24 Jun 2021 10:50:59 +0100 Subject: [PATCH 200/426] firmware: arm_scmi: Ensure drivers provide a probe function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bus probe callback calls the driver callback without further checking. Better be safe than sorry and refuse registration of a driver without a probe function to prevent a NULL pointer exception. Link: https://lore.kernel.org/r/20210624095059.4010157-2-sudeep.holla@arm.com Fixes: 933c504424a2 ("firmware: arm_scmi: add scmi protocol bus to enumerate protocol devices") Reported-by: Uwe Kleine-König Tested-by: Cristian Marussi Reviewed-by: Cristian Marussi Acked-by: Uwe Kleine-König Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index dc113ad37ad9..6c7e24935eca 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -134,6 +134,9 @@ int scmi_driver_register(struct scmi_driver *driver, struct module *owner, { int retval; + if (!driver->probe) + return -EINVAL; + retval = scmi_protocol_device_request(driver->id_table); if (retval) return retval; From 7a691f16ccad05d770f813d9c4b4337a30c6d63f Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 7 Jul 2021 14:50:28 +0100 Subject: [PATCH 201/426] firmware: arm_scmi: Fix possible scmi_linux_errmap buffer overflow The scmi_linux_errmap buffer access index is supposed to depend on the array size to prevent element out of bounds access. It uses SCMI_ERR_MAX to check bounds but that can mismatch with the array size. It also changes the success into -EIO though scmi_linux_errmap is never used in case of success, it is expected to work for success case too. It is slightly confusing code as the negative of the error code is used as index to the buffer. Fix it by negating it at the start and make it more readable. Link: https://lore.kernel.org/r/20210707135028.1869642-1-sudeep.holla@arm.com Reported-by: kernel test robot Reported-by: Dan Carpenter Reviewed-by: Cristian Marussi Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 66e5e694be7d..36d80661d473 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -47,7 +47,6 @@ enum scmi_error_codes { SCMI_ERR_GENERIC = -8, /* Generic Error */ SCMI_ERR_HARDWARE = -9, /* Hardware Error */ SCMI_ERR_PROTOCOL = -10,/* Protocol Error */ - SCMI_ERR_MAX }; /* List of all SCMI devices active in system */ @@ -166,8 +165,10 @@ static const int scmi_linux_errmap[] = { static inline int scmi_to_linux_errno(int errno) { - if (errno < SCMI_SUCCESS && errno > SCMI_ERR_MAX) - return scmi_linux_errmap[-errno]; + int err_idx = -errno; + + if (err_idx >= SCMI_SUCCESS && err_idx < ARRAY_SIZE(scmi_linux_errmap)) + return scmi_linux_errmap[err_idx]; return -EIO; } From 92743071464fca5acbbe812d9a0d88de3eaaad36 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 21 Jun 2021 22:16:51 +0200 Subject: [PATCH 202/426] firmware: arm_ffa: Ensure drivers provide a probe function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bus probe callback calls the driver callback without further checking. Better be safe than sorry and refuse registration of a driver without a probe function to prevent a NULL pointer exception. Link: https://lore.kernel.org/r/20210621201652.127611-1-u.kleine-koenig@pengutronix.de Fixes: e781858488b9 ("firmware: arm_ffa: Add initial FFA bus support for device enumeration") Signed-off-by: Uwe Kleine-König Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/bus.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 83166e02b191..d2cc24319626 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -99,6 +99,9 @@ int ffa_driver_register(struct ffa_driver *driver, struct module *owner, { int ret; + if (!driver->probe) + return -EINVAL; + driver->driver.bus = &ffa_bus_type; driver->driver.name = driver->name; driver->driver.owner = owner; From e362547addc39e4bb18ad5bdfd59ce4d512d0c08 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 21 Jun 2021 22:16:52 +0200 Subject: [PATCH 203/426] firmware: arm_ffa: Simplify probe function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the driver core calls the probe callback it already checked that the devices match, so there is no need to call the match callback again. Link: https://lore.kernel.org/r/20210621201652.127611-2-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/bus.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index d2cc24319626..00fe595a5bc8 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -46,9 +46,6 @@ static int ffa_device_probe(struct device *dev) struct ffa_driver *ffa_drv = to_ffa_driver(dev->driver); struct ffa_device *ffa_dev = to_ffa_dev(dev); - if (!ffa_device_match(dev, dev->driver)) - return -ENODEV; - return ffa_drv->probe(ffa_dev); } From ba684a31d3626c86cd9097e12d6ed57d224d077d Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 22 Jun 2021 17:22:02 +0100 Subject: [PATCH 204/426] firmware: arm_ffa: Fix the comment style clang produces the following warning: drivers/firmware/arm_ffa/driver.c:123: warning: expecting prototype for FF(). Prototype was for FFA_PAGE_SIZE() instead This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst Fix the same by removing the kernel-doc style comment here. Link: https://lore.kernel.org/r/20210622162202.3485866-1-sudeep.holla@arm.com Reported-by: kernel test robot Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index b1edb4b2e94a..88b822575ac4 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -120,7 +120,7 @@ #define PACK_TARGET_INFO(s, r) \ (FIELD_PREP(SENDER_ID_MASK, (s)) | FIELD_PREP(RECEIVER_ID_MASK, (r))) -/** +/* * FF-A specification mentions explicitly about '4K pages'. This should * not be confused with the kernel PAGE_SIZE, which is the translation * granule kernel is configured and may be one among 4K, 16K and 64K. From dd925db6f07556061c11ab1fbfa4a0145ae6b438 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 7 Jul 2021 14:47:39 +0100 Subject: [PATCH 205/426] firmware: arm_ffa: Fix a possible ffa_linux_errmap buffer overflow The ffa_linux_errmap buffer access index is supposed to range from 0-8 but it ranges from 1-9 instead. It reads one element out of bounds. It also changes the success into -EINVAL though ffa_to_linux_errno is never used in case of success, it is expected to work for success case too. It is slightly confusing code as the negative of the error code is used as index to the buffer. Fix it by negating it at the start and make it more readable. Link: https://lore.kernel.org/r/20210707134739.1869481-1-sudeep.holla@arm.com Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 88b822575ac4..c9fb56afbcb4 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -149,8 +149,10 @@ static const int ffa_linux_errmap[] = { static inline int ffa_to_linux_errno(int errno) { - if (errno < FFA_RET_SUCCESS && errno >= -ARRAY_SIZE(ffa_linux_errmap)) - return ffa_linux_errmap[-errno]; + int err_idx = -errno; + + if (err_idx >= 0 && err_idx < ARRAY_SIZE(ffa_linux_errmap)) + return ffa_linux_errmap[err_idx]; return -EINVAL; } From 40751c6c9bea6a5cfede7c61ee5f3cb1ab857029 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Wed, 7 Jul 2021 15:48:40 -0500 Subject: [PATCH 206/426] scripts/spdxcheck.py: Strictly read license files in utf-8 Commit bc41a7f36469 ("LICENSES: Add the CC-BY-4.0 license") unfortunately introduced LICENSES/dual/CC-BY-4.0 in UTF-8 Unicode text While python will barf at it with: FAIL: 'ascii' codec can't decode byte 0xe2 in position 2109: ordinal not in range(128) Traceback (most recent call last): File "scripts/spdxcheck.py", line 244, in spdx = read_spdxdata(repo) File "scripts/spdxcheck.py", line 47, in read_spdxdata for l in open(el.path).readlines(): File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode return codecs.ascii_decode(input, self.errors)[0] UnicodeDecodeError: 'ascii' codec can't decode byte 0xe2 in position 2109: ordinal not in range(128) While it is indeed debatable if 'Licensor.' used in the license file needs unicode quotes, instead, force spdxcheck to read utf-8. Reported-by: Rahul T R Signed-off-by: Nishanth Menon Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210707204840.30891-1-nm@ti.com Signed-off-by: Jonathan Corbet --- scripts/spdxcheck.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index 3e784cf9f401..ebd06ae642c9 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -44,7 +44,7 @@ def read_spdxdata(repo): continue exception = None - for l in open(el.path).readlines(): + for l in open(el.path, encoding="utf-8").readlines(): if l.startswith('Valid-License-Identifier:'): lid = l.split(':')[1].strip().upper() if lid in spdx.licenses: From 1adee589cd6da2ead7f1b5dd82419eac59a2e2b0 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 11:03:35 -0500 Subject: [PATCH 207/426] kernel: debug: Fix unreachable code in gdb_serial_stub() Fix the following warning: kernel/debug/gdbstub.c:1049:4: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] fallthrough; ^ include/linux/compiler_attributes.h:210:41: note: expanded from macro 'fallthrough' # define fallthrough __attribute__((__fallthrough__) by placing the fallthrough; statement inside ifdeffery. Reported-by: kernel test robot Signed-off-by: Gustavo A. R. Silva --- kernel/debug/gdbstub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index 8372897402f4..b6f28fad4307 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -1045,8 +1045,8 @@ int gdb_serial_stub(struct kgdb_state *ks) gdb_cmd_detachkill(ks); return DBG_PASS_EVENT; } -#endif fallthrough; +#endif case 'C': /* Exception passing */ tmp = gdb_cmd_exception_pass(ks); if (tmp > 0) From e8865537a68bb3032f449f5eb108fa8cd76ebb6d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 11:09:13 -0500 Subject: [PATCH 208/426] fcntl: Fix unreachable code in do_fcntl() Fix the following warning: fs/fcntl.c:373:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] fallthrough; ^ include/linux/compiler_attributes.h:210:41: note: expanded from macro 'fallthrough' # define fallthrough __attribute__((__fallthrough__)) by placing the fallthrough; statement inside ifdeffery. Reported-by: kernel test robot Signed-off-by: Gustavo A. R. Silva --- fs/fcntl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fcntl.c b/fs/fcntl.c index dfc72f15be7f..f946bec8f1f1 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -369,8 +369,8 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: -#endif fallthrough; +#endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) From 1eb5f4a3ddd949af1abe947c02ad990c013dd620 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 11:13:49 -0500 Subject: [PATCH 209/426] mtd: cfi_util: Fix unreachable code issue Fix the following warning: drivers/mtd/chips/cfi_util.c:112:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] fallthrough; ^ include/linux/compiler_attributes.h:210:41: note: expanded from macro 'fallthrough' # define fallthrough __attribute__((__fallthrough__)) ^ drivers/mtd/chips/cfi_util.c:168:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] fallthrough; ^ include/linux/compiler_attributes.h:210:41: note: expanded from macro 'fallthrough' # define fallthrough __attribute__((__fallthrough__)) by placing the fallthrough; statement inside ifdeffery. Reported-by: kernel test robot Signed-off-by: Gustavo A. R. Silva --- drivers/mtd/chips/cfi_util.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c index 99b7986002f0..6a6a2a21d2ed 100644 --- a/drivers/mtd/chips/cfi_util.c +++ b/drivers/mtd/chips/cfi_util.c @@ -108,8 +108,8 @@ map_word cfi_build_cmd(u_long cmd, struct map_info *map, struct cfi_private *cfi #if BITS_PER_LONG >= 64 case 8: onecmd |= (onecmd << (chip_mode * 32)); -#endif fallthrough; +#endif case 4: onecmd |= (onecmd << (chip_mode * 16)); fallthrough; @@ -164,8 +164,8 @@ unsigned long cfi_merge_status(map_word val, struct map_info *map, #if BITS_PER_LONG >= 64 case 8: res |= (onestat >> (chip_mode * 32)); -#endif fallthrough; +#endif case 4: res |= (onestat >> (chip_mode * 16)); fallthrough; From a1739c307a072e46473a2ba239eb60e6d711c96c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 11 Jul 2021 15:31:47 -0700 Subject: [PATCH 210/426] net: hdlc: rename 'mod_init' & 'mod_exit' functions to be module-specific Rename module_init & module_exit functions that are named "mod_init" and "mod_exit" so that they are unique in both the System.map file and in initcall_debug output instead of showing up as almost anonymous "mod_init". This is helpful for debugging and in determining how long certain module_init calls take to execute. Signed-off-by: Randy Dunlap Cc: Krzysztof Halasa Cc: netdev@vger.kernel.org Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Martin Schiller Cc: linux-x25@vger.kernel.org Signed-off-by: David S. Miller --- drivers/net/wan/hdlc_cisco.c | 8 ++++---- drivers/net/wan/hdlc_fr.c | 8 ++++---- drivers/net/wan/hdlc_ppp.c | 8 ++++---- drivers/net/wan/hdlc_raw.c | 8 ++++---- drivers/net/wan/hdlc_raw_eth.c | 8 ++++---- drivers/net/wan/hdlc_x25.c | 8 ++++---- 6 files changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index 349ca18088e8..c54fdae950fb 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -364,19 +364,19 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } -static int __init mod_init(void) +static int __init hdlc_cisco_init(void) { register_hdlc_protocol(&proto); return 0; } -static void __exit mod_exit(void) +static void __exit hdlc_cisco_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_cisco_init); +module_exit(hdlc_cisco_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("Cisco HDLC protocol support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 72250fe0a1df..25e3564ce118 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -1279,19 +1279,19 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } -static int __init mod_init(void) +static int __init hdlc_fr_init(void) { register_hdlc_protocol(&proto); return 0; } -static void __exit mod_exit(void) +static void __exit hdlc_fr_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_fr_init); +module_exit(hdlc_fr_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("Frame-Relay protocol support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 834be2ae3e9e..b81ecf432a0c 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -705,20 +705,20 @@ static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } -static int __init mod_init(void) +static int __init hdlc_ppp_init(void) { skb_queue_head_init(&tx_queue); register_hdlc_protocol(&proto); return 0; } -static void __exit mod_exit(void) +static void __exit hdlc_ppp_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_ppp_init); +module_exit(hdlc_ppp_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("PPP protocol support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_raw.c b/drivers/net/wan/hdlc_raw.c index 388fcc09b4dd..54d28496fefd 100644 --- a/drivers/net/wan/hdlc_raw.c +++ b/drivers/net/wan/hdlc_raw.c @@ -90,7 +90,7 @@ static int raw_ioctl(struct net_device *dev, struct ifreq *ifr) } -static int __init mod_init(void) +static int __init hdlc_raw_init(void) { register_hdlc_protocol(&proto); return 0; @@ -98,14 +98,14 @@ static int __init mod_init(void) -static void __exit mod_exit(void) +static void __exit hdlc_raw_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_raw_init); +module_exit(hdlc_raw_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("Raw HDLC protocol support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_raw_eth.c b/drivers/net/wan/hdlc_raw_eth.c index c70a518b8b47..927596276a07 100644 --- a/drivers/net/wan/hdlc_raw_eth.c +++ b/drivers/net/wan/hdlc_raw_eth.c @@ -110,7 +110,7 @@ static int raw_eth_ioctl(struct net_device *dev, struct ifreq *ifr) } -static int __init mod_init(void) +static int __init hdlc_eth_init(void) { register_hdlc_protocol(&proto); return 0; @@ -118,14 +118,14 @@ static int __init mod_init(void) -static void __exit mod_exit(void) +static void __exit hdlc_eth_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_eth_init); +module_exit(hdlc_eth_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("Ethernet encapsulation support for generic HDLC"); diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index d2bf72bf3bd7..9b7ebf8bd85c 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -365,19 +365,19 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } -static int __init mod_init(void) +static int __init hdlc_x25_init(void) { register_hdlc_protocol(&proto); return 0; } -static void __exit mod_exit(void) +static void __exit hdlc_x25_exit(void) { unregister_hdlc_protocol(&proto); } -module_init(mod_init); -module_exit(mod_exit); +module_init(hdlc_x25_init); +module_exit(hdlc_x25_exit); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("X.25 protocol support for generic HDLC"); From 5796015fa968a3349027a27dcd04c71d95c53ba5 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Mon, 12 Jul 2021 09:45:06 +0300 Subject: [PATCH 211/426] ipv6: allocate enough headroom in ip6_finish_output2() When TEE target mirrors traffic to another interface, sk_buff may not have enough headroom to be processed correctly. ip_finish_output2() detect this situation for ipv4 and allocates new skb with enogh headroom. However ipv6 lacks this logic in ip_finish_output2 and it leads to skb_under_panic: skbuff: skb_under_panic: text:ffffffffc0866ad4 len:96 put:24 head:ffff97be85e31800 data:ffff97be85e317f8 tail:0x58 end:0xc0 dev:gre0 ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:110! invalid opcode: 0000 [#1] SMP PTI CPU: 2 PID: 393 Comm: kworker/2:2 Tainted: G OE 5.13.0 #13 Hardware name: Virtuozzo KVM, BIOS 1.11.0-2.vz7.4 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:skb_panic+0x48/0x4a Call Trace: skb_push.cold.111+0x10/0x10 ipgre_header+0x24/0xf0 [ip_gre] neigh_connected_output+0xae/0xf0 ip6_finish_output2+0x1a8/0x5a0 ip6_output+0x5c/0x110 nf_dup_ipv6+0x158/0x1000 [nf_dup_ipv6] tee_tg6+0x2e/0x40 [xt_TEE] ip6t_do_table+0x294/0x470 [ip6_tables] nf_hook_slow+0x44/0xc0 nf_hook.constprop.34+0x72/0xe0 ndisc_send_skb+0x20d/0x2e0 ndisc_send_ns+0xd1/0x210 addrconf_dad_work+0x3c8/0x540 process_one_work+0x1d1/0x370 worker_thread+0x30/0x390 kthread+0x116/0x130 ret_from_fork+0x22/0x30 Signed-off-by: Vasily Averin Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d4ee2169afd8..01bea76e3891 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -60,10 +60,38 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + unsigned int hh_len = LL_RESERVED_SPACE(dev); + int delta = hh_len - skb_headroom(skb); const struct in6_addr *nexthop; struct neighbour *neigh; int ret; + /* Be paranoid, rather than too clever. */ + if (unlikely(delta > 0) && dev->header_ops) { + /* pskb_expand_head() might crash, if skb is shared */ + if (skb_shared(skb)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (likely(nskb)) { + if (skb->sk) + skb_set_owner_w(skb, skb->sk); + consume_skb(skb); + } else { + kfree_skb(skb); + } + skb = nskb; + } + if (skb && + pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { + kfree_skb(skb); + skb = NULL; + } + if (!skb) { + IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); + return -ENOMEM; + } + } + if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); From 71ce9d92fc7089f287c3e95a981bdec7545a8588 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 12 Jul 2021 15:37:50 +0100 Subject: [PATCH 212/426] octeontx2-pf: Fix uninitialized boolean variable pps In the case where act->id is FLOW_ACTION_POLICE and also act->police.rate_bytes_ps > 0 or act->police.rate_pkt_ps is not > 0 the boolean variable pps contains an uninitialized value when function otx2_tc_act_set_police is called. Fix this by initializing pps to false. Addresses-Coverity: ("Uninitialized scalar variable)" Fixes: 68fbff68dbea ("octeontx2-pf: Add police action for TC flower") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 905fc02a7dfe..972b202b9884 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -288,7 +288,7 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic, struct otx2_nic *priv; u32 burst, mark = 0; u8 nr_police = 0; - bool pps; + bool pps = false; u64 rate; int i; From efdb6720b44b2f016d2a04b2c84e577e57ed84bd Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 11 Jul 2021 20:10:49 -0700 Subject: [PATCH 213/426] mm/rmap: fix munlocking Anon THP with mlocked ptes Many thanks to Kirill for reminding that PageDoubleMap cannot be relied on to warn of pte mappings in the Anon THP case; and a scan of subpages does not seem appropriate here. Note how follow_trans_huge_pmd() does not even mark an Anon THP as mlocked when compound_mapcount != 1: multiple mlocking of Anon THP is avoided, so simply return from page_mlock() in this case. Link: https://lore.kernel.org/lkml/cfa154c-d595-406-eb7d-eb9df730f944@google.com/ Fixes: d9770fcc1c0c ("mm/rmap: fix old bug: munlocking THP missed other mlocks") Reported-by: Kirill A. Shutemov Signed-off-by: Hugh Dickins Acked-by: Kirill A. Shutemov Cc: Andrew Morton Cc: Alistair Popple Cc: Jason Gunthorpe Cc: Ralph Campbell Cc: Christoph Hellwig Cc: Yang Shi Cc: Shakeel Butt Signed-off-by: Linus Torvalds --- mm/rmap.c | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index 795f9d5f8386..b9eb5c12f3fe 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1440,21 +1440,20 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* * If the page is mlock()d, we cannot swap it out. */ - if (!(flags & TTU_IGNORE_MLOCK)) { - if (vma->vm_flags & VM_LOCKED) { - /* PTE-mapped THP are never marked as mlocked */ - if (!PageTransCompound(page) || - (PageHead(page) && !PageDoubleMap(page))) { - /* - * Holding pte lock, we do *not* need - * mmap_lock here - */ - mlock_vma_page(page); - } - ret = false; - page_vma_mapped_walk_done(&pvmw); - break; - } + if (!(flags & TTU_IGNORE_MLOCK) && + (vma->vm_flags & VM_LOCKED)) { + /* + * PTE-mapped THP are never marked as mlocked: so do + * not set it on a DoubleMap THP, nor on an Anon THP + * (which may still be PTE-mapped after DoubleMap was + * cleared). But stop unmapping even in those cases. + */ + if (!PageTransCompound(page) || (PageHead(page) && + !PageDoubleMap(page) && !PageAnon(page))) + mlock_vma_page(page); + page_vma_mapped_walk_done(&pvmw); + ret = false; + break; } /* Unexpected PMD-mapped THP? */ @@ -1986,8 +1985,10 @@ static bool page_mlock_one(struct page *page, struct vm_area_struct *vma, */ if (vma->vm_flags & VM_LOCKED) { /* - * PTE-mapped THP are never marked as mlocked, but - * this function is never called when PageDoubleMap(). + * PTE-mapped THP are never marked as mlocked; but + * this function is never called on a DoubleMap THP, + * nor on an Anon THP (which may still be PTE-mapped + * after DoubleMap was cleared). */ mlock_vma_page(page); /* @@ -2022,6 +2023,10 @@ void page_mlock(struct page *page) VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); + /* Anon THP are only marked as mlocked when singly mapped */ + if (PageTransCompound(page) && PageAnon(page)) + return; + rmap_walk(page, &rwc); } From 79789db03fdd77510cfb35cb4b3bd52b6c50c901 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 12 Jul 2021 16:32:07 +0100 Subject: [PATCH 214/426] mm: Make copy_huge_page() always available Rewrite copy_huge_page() and move it into mm/util.c so it's always available. Fixes an exposure of uninitialised memory on configurations with HUGETLB and UFFD enabled and MIGRATION disabled. Fixes: 8cc5fcbb5be8 ("mm, hugetlb: fix racy resv_huge_pages underflow on UFFDIO_COPY") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Mike Kravetz Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 5 ----- include/linux/mm.h | 1 + mm/migrate.c | 48 ----------------------------------------- mm/util.c | 10 +++++++++ 4 files changed, 11 insertions(+), 53 deletions(-) diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 9b7b7cd3bae9..23dadf7aeba8 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -51,7 +51,6 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); -extern void copy_huge_page(struct page *dst, struct page *src); #else static inline void putback_movable_pages(struct list_head *l) {} @@ -77,10 +76,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, { return -ENOSYS; } - -static inline void copy_huge_page(struct page *dst, struct page *src) -{ -} #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION diff --git a/include/linux/mm.h b/include/linux/mm.h index 57453dba41b9..7ca22e6e694a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -906,6 +906,7 @@ void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); +void copy_huge_page(struct page *dst, struct page *src); /* * Compound pages have a destructor function. Provide a diff --git a/mm/migrate.c b/mm/migrate.c index 23cbd9de030b..34a9ad3e0a4f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -536,54 +536,6 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, return MIGRATEPAGE_SUCCESS; } -/* - * Gigantic pages are so large that we do not guarantee that page++ pointer - * arithmetic will work across the entire page. We need something more - * specialized. - */ -static void __copy_gigantic_page(struct page *dst, struct page *src, - int nr_pages) -{ - int i; - struct page *dst_base = dst; - struct page *src_base = src; - - for (i = 0; i < nr_pages; ) { - cond_resched(); - copy_highpage(dst, src); - - i++; - dst = mem_map_next(dst, dst_base, i); - src = mem_map_next(src, src_base, i); - } -} - -void copy_huge_page(struct page *dst, struct page *src) -{ - int i; - int nr_pages; - - if (PageHuge(src)) { - /* hugetlbfs page */ - struct hstate *h = page_hstate(src); - nr_pages = pages_per_huge_page(h); - - if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) { - __copy_gigantic_page(dst, src, nr_pages); - return; - } - } else { - /* thp page */ - BUG_ON(!PageTransHuge(src)); - nr_pages = thp_nr_pages(src); - } - - for (i = 0; i < nr_pages; i++) { - cond_resched(); - copy_highpage(dst + i, src + i); - } -} - /* * Copy the page to its new location */ diff --git a/mm/util.c b/mm/util.c index 99c6cc77de9e..9043d03750a7 100644 --- a/mm/util.c +++ b/mm/util.c @@ -731,6 +731,16 @@ int __page_mapcount(struct page *page) } EXPORT_SYMBOL_GPL(__page_mapcount); +void copy_huge_page(struct page *dst, struct page *src) +{ + unsigned i, nr = compound_nr(src); + + for (i = 0; i < nr; i++) { + cond_resched(); + copy_highpage(nth_page(dst, i), nth_page(src, i)); + } +} + int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; int sysctl_overcommit_ratio __read_mostly = 50; unsigned long sysctl_overcommit_kbytes __read_mostly; From 7fef2edf7cc753b51f7ccc74993971b0a9c81eca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 12 Jul 2021 17:50:01 +0200 Subject: [PATCH 215/426] sd: don't mess with SD_MINORS for CONFIG_DEBUG_BLOCK_EXT_DEVT No need to give up the original sd minor even with this option, and if we did we'd also need to fix the number of minors for this configuration to actually work. Fixes: 7c3f828b522b0 ("block: refactor device number setup in __device_add_disk") Reported-by: Guenter Roeck Signed-off-by: Christoph Hellwig Tested-by: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/scsi/sd.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 6d2d63629a90..b8d55af763f9 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -98,11 +98,7 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD); MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC); MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC); -#if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT) #define SD_MINORS 16 -#else -#define SD_MINORS 0 -#endif static void sd_config_discard(struct scsi_disk *, unsigned int); static void sd_config_write_same(struct scsi_disk *); From ed01ad3a2fac8fff63f441ead4f8653da053c65b Mon Sep 17 00:00:00 2001 From: Rae Moar Date: Thu, 1 Jul 2021 17:52:31 +0000 Subject: [PATCH 216/426] kunit: tool: Fix error messages for cases of no tests and wrong TAP header This patch addresses misleading error messages reported by kunit_tool in two cases. First, in the case of TAP output having an incorrect header format or missing a header, the parser used to output an error message of 'no tests run!'. Now the parser outputs an error message of 'could not parse test results!'. As an example: Before: $ ./tools/testing/kunit/kunit.py parse /dev/null [ERROR] no tests run! ... After: $ ./tools/testing/kunit/kunit.py parse /dev/null [ERROR] could not parse test results! ... Second, in the case of TAP output with the correct header but no tests, the parser used to output an error message of 'could not parse test results!'. Now the parser outputs an error message of 'no tests run!'. As an example: Before: $ echo -e 'TAP version 14\n1..0' | ./tools/testing/kunit/kunit.py parse [ERROR] could not parse test results! After: $ echo -e 'TAP version 14\n1..0' | ./tools/testing/kunit/kunit.py parse [ERROR] no tests run! Additionally, this patch also corrects the tests in kunit_tool_test.py and adds a test to check the error in the case of TAP output with the correct header but no tests. Signed-off-by: Rae Moar Reviewed-by: David Gow Reviewed-by: Daniel Latypov Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit_parser.py | 6 ++++-- tools/testing/kunit/kunit_tool_test.py | 16 +++++++++++++--- ...st_is_test_passed-no_tests_run_no_header.log} | 0 ...t_is_test_passed-no_tests_run_with_header.log | 2 ++ 4 files changed, 19 insertions(+), 5 deletions(-) rename tools/testing/kunit/test_data/{test_is_test_passed-no_tests_run.log => test_is_test_passed-no_tests_run_no_header.log} (100%) create mode 100644 tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index c3c524b79db8..b88db3f51dc5 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -338,9 +338,11 @@ def bubble_up_suite_errors(test_suites: Iterable[TestSuite]) -> TestStatus: def parse_test_result(lines: LineStream) -> TestResult: consume_non_diagnostic(lines) if not lines or not parse_tap_header(lines): - return TestResult(TestStatus.NO_TESTS, [], lines) + return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines) expected_test_suite_num = parse_test_plan(lines) - if not expected_test_suite_num: + if expected_test_suite_num == 0: + return TestResult(TestStatus.NO_TESTS, [], lines) + elif expected_test_suite_num is None: return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines) test_suites = [] for i in range(1, expected_test_suite_num + 1): diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index bdae0e5f6197..75045aa0f8a1 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -157,8 +157,18 @@ class KUnitParserTest(unittest.TestCase): kunit_parser.TestStatus.FAILURE, result.status) + def test_no_header(self): + empty_log = test_data_path('test_is_test_passed-no_tests_run_no_header.log') + with open(empty_log) as file: + result = kunit_parser.parse_run_tests( + kunit_parser.extract_tap_lines(file.readlines())) + self.assertEqual(0, len(result.suites)) + self.assertEqual( + kunit_parser.TestStatus.FAILURE_TO_PARSE_TESTS, + result.status) + def test_no_tests(self): - empty_log = test_data_path('test_is_test_passed-no_tests_run.log') + empty_log = test_data_path('test_is_test_passed-no_tests_run_with_header.log') with open(empty_log) as file: result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines(file.readlines())) @@ -173,7 +183,7 @@ class KUnitParserTest(unittest.TestCase): with open(crash_log) as file: result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines(file.readlines())) - print_mock.assert_any_call(StrContains('no tests run!')) + print_mock.assert_any_call(StrContains('could not parse test results!')) print_mock.stop() file.close() @@ -309,7 +319,7 @@ class KUnitJsonTest(unittest.TestCase): result["sub_groups"][1]["test_cases"][0]) def test_no_tests_json(self): - result = self._json_for('test_is_test_passed-no_tests_run.log') + result = self._json_for('test_is_test_passed-no_tests_run_with_header.log') self.assertEqual(0, len(result['sub_groups'])) class StrContains(str): diff --git a/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_no_header.log similarity index 100% rename from tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log rename to tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_no_header.log diff --git a/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log new file mode 100644 index 000000000000..5f48ee659d40 --- /dev/null +++ b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log @@ -0,0 +1,2 @@ +TAP version 14 +1..0 From a72fa6304342a3ad749955fd9007695f761e12d6 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Wed, 23 Jun 2021 13:17:21 -0700 Subject: [PATCH 217/426] Documentation: kunit: drop obsolete note about uml_abort for coverage Commit b6d5799b0b58 ("kunit: Add 'kunit_shutdown' option") changes KUnit to call kernel_halt() by default when done testing. This fixes the issue with not having .gcda files due to not calling atexit() handlers, and therefore we can stop recommending people manually tweak UML code. The need to use older versions of GCC (<=6) remains however, due to linktime issues, same as before. Note: There also might still be issues with .gcda files as well in newer versions. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- Documentation/dev-tools/kunit/running_tips.rst | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/Documentation/dev-tools/kunit/running_tips.rst b/Documentation/dev-tools/kunit/running_tips.rst index 7d99386cf94a..d1626d548fa5 100644 --- a/Documentation/dev-tools/kunit/running_tips.rst +++ b/Documentation/dev-tools/kunit/running_tips.rst @@ -86,19 +86,7 @@ Generating code coverage reports under UML .. note:: TODO(brendanhiggins@google.com): There are various issues with UML and versions of gcc 7 and up. You're likely to run into missing ``.gcda`` - files or compile errors. We know one `faulty GCC commit - `_ - but not how we'd go about getting this fixed. The compile errors still - need some investigation. - -.. note:: - TODO(brendanhiggins@google.com): for recent versions of Linux - (5.10-5.12, maybe earlier), there's a bug with gcov counters not being - flushed in UML. This translates to very low (<1%) reported coverage. This is - related to the above issue and can be worked around by replacing the - one call to ``uml_abort()`` (it's in ``os_dump_core()``) with a plain - ``exit()``. - + files or compile errors. This is different from the "normal" way of getting coverage information that is documented in Documentation/dev-tools/gcov.rst. From 58c965d84e14196e762c803c50c7b207a9e352bc Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Wed, 23 Jun 2021 12:09:19 -0700 Subject: [PATCH 218/426] kunit: tool: remove unnecessary "annotations" import The import was working around the fact "tuple[T]" was used instead of typing.Tuple[T]. Convert it to use type.Tuple to be consistent with how the rest of the code is anotated. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Tested-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit_kernel.py | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 90bc007f1f93..2c6f916ccbaf 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,15 +6,13 @@ # Author: Felix Guo # Author: Brendan Higgins -from __future__ import annotations import importlib.util import logging import subprocess import os import shutil import signal -from typing import Iterator -from typing import Optional +from typing import Iterator, Optional, Tuple from contextlib import ExitStack @@ -208,7 +206,7 @@ def get_source_tree_ops(arch: str, cross_compile: Optional[str]) -> LinuxSourceT raise ConfigError(arch + ' is not a valid arch') def get_source_tree_ops_from_qemu_config(config_path: str, - cross_compile: Optional[str]) -> tuple[ + cross_compile: Optional[str]) -> Tuple[ str, LinuxSourceTreeOperations]: # The module name/path has very little to do with where the actual file # exists (I learned this through experimentation and could not find it From df4b0807ca1a62822342d404b863eff933d15762 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 12 Jul 2021 19:52:58 +0000 Subject: [PATCH 219/426] kunit: tool: Assert the version requirement Commit 87c9c1631788 ("kunit: tool: add support for QEMU") on the 'next' tree adds 'from __future__ import annotations' in 'kunit_kernel.py'. Because it is supported on only >=3.7 Python, people using older Python will get below error: Traceback (most recent call last): File "./tools/testing/kunit/kunit.py", line 20, in import kunit_kernel File "/home/sjpark/linux/tools/testing/kunit/kunit_kernel.py", line 9 from __future__ import annotations ^ SyntaxError: future feature annotations is not defined This commit adds a version assertion in 'kunit.py', so that people get more explicit error message like below: Traceback (most recent call last): File "./tools/testing/kunit/kunit.py", line 15, in assert sys.version_info >= (3, 7), "Python version is too old" AssertionError: Python version is too old Signed-off-by: SeongJae Park Acked-by: Daniel Latypov Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index be8d8d4a4e08..6276ce0c0196 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -12,6 +12,8 @@ import sys import os import time +assert sys.version_info >= (3, 7), "Python version is too old" + from collections import namedtuple from enum import Enum, auto From 0c0f6299ba71faf610e311605e09e96331c45f28 Mon Sep 17 00:00:00 2001 From: Paolo Pisati Date: Wed, 30 Jun 2021 16:57:40 +0200 Subject: [PATCH 220/426] selftests: memory-hotplug: avoid spamming logs with dump_page(), ratio limit hot-remove error test While the offline memory test obey ratio limit, the same test with error injection does not and tries to offline all the hotpluggable memory, spamming system logs with hundreds of thousands of dump_page() entries, slowing system down (to the point the test itself timesout and gets terminated) and excessive fs occupation: ... [ 9784.393354] page:c00c0000007d1b40 refcount:3 mapcount:0 mapping:c0000001fc03e950 index:0xe7b [ 9784.393355] def_blk_aops [ 9784.393356] flags: 0x3ffff800002062(referenced|active|workingset|private) [ 9784.393358] raw: 003ffff800002062 c0000001b9343a68 c0000001b9343a68 c0000001fc03e950 [ 9784.393359] raw: 0000000000000e7b c000000006607b18 00000003ffffffff c00000000490d000 [ 9784.393359] page dumped because: migration failure [ 9784.393360] page->mem_cgroup:c00000000490d000 [ 9784.393416] migrating pfn 1f46d failed ret:1 ... $ grep "page dumped because: migration failure" /var/log/kern.log | wc -l 2405558 $ ls -la /var/log/kern.log -rw-r----- 1 syslog adm 2256109539 Jun 30 14:19 /var/log/kern.log Signed-off-by: Paolo Pisati Acked-by: Krzysztof Kozlowski Signed-off-by: Shuah Khan --- tools/testing/selftests/memory-hotplug/mem-on-off-test.sh | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh index b37585e6aa38..46a97f318f58 100755 --- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh +++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh @@ -282,7 +282,9 @@ done # echo $error > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error for memory in `hotpluggable_online_memory`; do - offline_memory_expect_fail $memory + if [ $((RANDOM % 100)) -lt $ratio ]; then + offline_memory_expect_fail $memory + fi done echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error From 422969bbb5af2f7226cf75cdb4aae02f46299dc2 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 9 Jul 2021 13:26:20 -0700 Subject: [PATCH 221/426] scsi: core: Fix the documentation of the scsi_execute() time parameter The unit of the scsi_execute() timeout parameter is 1/HZ seconds instead of one second, just like the timeouts used in the block layer. Fix the documentation header above the definition of the scsi_execute() macro. Link: https://lore.kernel.org/r/20210709202638.9480-3-bvanassche@acm.org Fixes: "[SCSI] use scatter lists for all block pc requests and simplify hw handlers" # v2.6.16.28 Cc: "James E.J. Bottomley" Cc: Hannes Reinecke Cc: Ming Lei Cc: John Garry Reviewed-by: Avri Altman Reviewed-by: Hannes Reinecke Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 8f9727e525aa..7456a26aef51 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -194,7 +194,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason) * @bufflen: len of buffer * @sense: optional sense buffer * @sshdr: optional decoded sense header - * @timeout: request timeout in seconds + * @timeout: request timeout in HZ * @retries: number of times to retry request * @flags: flags for ->cmd_flags * @rq_flags: flags for ->rq_flags From fbf1a58701ecbf61211476277a77eaada6c091d4 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Sat, 10 Jul 2021 20:36:23 -0700 Subject: [PATCH 222/426] scsi: fas216: Fix a build error Use SAM_STAT_GOOD instead of GOOD since GOOD has been removed. Link: https://lore.kernel.org/r/20210711033623.11267-1-bvanassche@acm.org Fixes: 3d45cefc8edd ("scsi: core: Drop obsolete Linux-specific SCSI status codes") Fixes: df1303147649 ("scsi: fas216: Use get_status_byte() to avoid using Linux-specific status codes") Cc: Hannes Reinecke Reviewed-by: Hannes Reinecke Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/arm/fas216.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c index 30ed3d23635a..6baa9b36367d 100644 --- a/drivers/scsi/arm/fas216.c +++ b/drivers/scsi/arm/fas216.c @@ -2010,7 +2010,7 @@ static void fas216_rq_sns_done(FAS216_Info *info, struct scsi_cmnd *SCpnt, "request sense complete, result=0x%04x%02x%02x", result, SCpnt->SCp.Message, SCpnt->SCp.Status); - if (result != DID_OK || SCpnt->SCp.Status != GOOD) + if (result != DID_OK || SCpnt->SCp.Status != SAM_STAT_GOOD) /* * Something went wrong. Make sure that we don't * have valid data in the sense buffer that could From 93aa71ad7379900e61c8adff6a710a4c18c7c99b Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Thu, 1 Jul 2021 13:56:59 -0600 Subject: [PATCH 223/426] scsi: core: Fix bad pointer dereference when ehandler kthread is invalid Commit 66a834d09293 ("scsi: core: Fix error handling of scsi_host_alloc()") changed the allocation logic to call put_device() to perform host cleanup with the assumption that IDA removal and stopping the kthread would properly be performed in scsi_host_dev_release(). However, in the unlikely case that the error handler thread fails to spawn, shost->ehandler is set to ERR_PTR(-ENOMEM). The error handler cleanup code in scsi_host_dev_release() will call kthread_stop() if shost->ehandler != NULL which will always be the case whether the kthread was successfully spawned or not. In the case that it failed to spawn this has the nasty side effect of trying to dereference an invalid pointer when kthread_stop() is called. The following splat provides an example of this behavior in the wild: scsi host11: error handler thread failed to spawn, error = -4 Kernel attempted to read user page (10c) - exploit attempt? (uid: 0) BUG: Kernel NULL pointer dereference on read at 0x0000010c Faulting instruction address: 0xc00000000818e9a8 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: ibmvscsi(+) scsi_transport_srp dm_multipath dm_mirror dm_region hash dm_log dm_mod fuse overlay squashfs loop CPU: 12 PID: 274 Comm: systemd-udevd Not tainted 5.13.0-rc7 #1 NIP: c00000000818e9a8 LR: c0000000089846e8 CTR: 0000000000007ee8 REGS: c000000037d12ea0 TRAP: 0300 Not tainted (5.13.0-rc7) MSR: 800000000280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 28228228 XER: 20040001 CFAR: c0000000089846e4 DAR: 000000000000010c DSISR: 40000000 IRQMASK: 0 GPR00: c0000000089846e8 c000000037d13140 c000000009cc1100 fffffffffffffffc GPR04: 0000000000000001 0000000000000000 0000000000000000 c000000037dc0000 GPR08: 0000000000000000 c000000037dc0000 0000000000000001 00000000fffff7ff GPR12: 0000000000008000 c00000000a049000 c000000037d13d00 000000011134d5a0 GPR16: 0000000000001740 c0080000190d0000 c0080000190d1740 c000000009129288 GPR20: c000000037d13bc0 0000000000000001 c000000037d13bc0 c0080000190b7898 GPR24: c0080000190b7708 0000000000000000 c000000033bb2c48 0000000000000000 GPR28: c000000046b28280 0000000000000000 000000000000010c fffffffffffffffc NIP [c00000000818e9a8] kthread_stop+0x38/0x230 LR [c0000000089846e8] scsi_host_dev_release+0x98/0x160 Call Trace: [c000000033bb2c48] 0xc000000033bb2c48 (unreliable) [c0000000089846e8] scsi_host_dev_release+0x98/0x160 [c00000000891e960] device_release+0x60/0x100 [c0000000087e55c4] kobject_release+0x84/0x210 [c00000000891ec78] put_device+0x28/0x40 [c000000008984ea4] scsi_host_alloc+0x314/0x430 [c0080000190b38bc] ibmvscsi_probe+0x54/0xad0 [ibmvscsi] [c000000008110104] vio_bus_probe+0xa4/0x4b0 [c00000000892a860] really_probe+0x140/0x680 [c00000000892aefc] driver_probe_device+0x15c/0x200 [c00000000892b63c] device_driver_attach+0xcc/0xe0 [c00000000892b740] __driver_attach+0xf0/0x200 [c000000008926f28] bus_for_each_dev+0xa8/0x130 [c000000008929ce4] driver_attach+0x34/0x50 [c000000008928fc0] bus_add_driver+0x1b0/0x300 [c00000000892c798] driver_register+0x98/0x1a0 [c00000000810eb60] __vio_register_driver+0x80/0xe0 [c0080000190b4a30] ibmvscsi_module_init+0x9c/0xdc [ibmvscsi] [c0000000080121d0] do_one_initcall+0x60/0x2d0 [c000000008261abc] do_init_module+0x7c/0x320 [c000000008265700] load_module+0x2350/0x25b0 [c000000008265cb4] __do_sys_finit_module+0xd4/0x160 [c000000008031110] system_call_exception+0x150/0x2d0 [c00000000800d35c] system_call_common+0xec/0x278 Fix this be nulling shost->ehandler when the kthread fails to spawn. Link: https://lore.kernel.org/r/20210701195659.3185475-1-tyreld@linux.ibm.com Fixes: 66a834d09293 ("scsi: core: Fix error handling of scsi_host_alloc()") Cc: stable@vger.kernel.org Reviewed-by: Ming Lei Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/hosts.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 929a3b043ad7..3f6f14f0cafb 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -488,6 +488,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) shost_printk(KERN_WARNING, shost, "error handler thread failed to spawn, error = %ld\n", PTR_ERR(shost->ehandler)); + shost->ehandler = NULL; goto fail; } From 8b3bdd99c092bbaeaa7d9eecb1a3e5dc9112002b Mon Sep 17 00:00:00 2001 From: Steffen Maier Date: Fri, 2 Jul 2021 18:09:22 +0200 Subject: [PATCH 224/426] scsi: zfcp: Report port fc_security as unknown early during remote cable pull On remote cable pull, a zfcp_port keeps its status and only gets ZFCP_STATUS_PORT_LINK_TEST added. Only after an ADISC timeout, we would actually start port recovery and remove ZFCP_STATUS_COMMON_UNBLOCKED which zfcp_sysfs_port_fc_security_show() detected and reported as "unknown" instead of the old and possibly stale zfcp_port->connection_info. Add check for ZFCP_STATUS_PORT_LINK_TEST for timely "unknown" report. Link: https://lore.kernel.org/r/20210702160922.2667874-1-maier@linux.ibm.com Fixes: a17c78460093 ("scsi: zfcp: report FC Endpoint Security in sysfs") Cc: #5.7+ Reviewed-by: Benjamin Block Signed-off-by: Steffen Maier Signed-off-by: Martin K. Petersen --- drivers/s390/scsi/zfcp_sysfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index 544efd4c42f0..b8cd75a872ee 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -487,6 +487,7 @@ static ssize_t zfcp_sysfs_port_fc_security_show(struct device *dev, if (0 == (status & ZFCP_STATUS_COMMON_OPEN) || 0 == (status & ZFCP_STATUS_COMMON_UNBLOCKED) || 0 == (status & ZFCP_STATUS_PORT_PHYS_OPEN) || + 0 != (status & ZFCP_STATUS_PORT_LINK_TEST) || 0 != (status & ZFCP_STATUS_COMMON_ERP_FAILED) || 0 != (status & ZFCP_STATUS_COMMON_ACCESS_BOXED)) i = sprintf(buf, "unknown\n"); From bb6beabf2f79ea063750bf16e78b61e5a50f2d5c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 8 Jul 2021 09:57:23 -0700 Subject: [PATCH 225/426] scsi: pm8001: Clean up kernel-doc and comments Fix kernel-doc warnings then test again, wash, rinse, find more, then repeat more/again. Also fix spellos, some grammar, and some punctuation. ../drivers/scsi/pm8001/pm8001_ctl.c:557: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst ** pm8001_ctl_fatal_log_show - fatal error logging ../drivers/scsi/pm8001/pm8001_ctl.c:577: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst ** non_fatal_log_show - non fatal error logging ../drivers/scsi/pm8001/pm8001_ctl.c:622: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst ** pm8001_ctl_gsm_log_show - gsm dump collection Link: https://lore.kernel.org/r/20210708165723.8594-1-rdunlap@infradead.org Cc: Jack Wang Cc: linux-scsi@vger.kernel.org Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Acked-by: Jack Wang Signed-off-by: Randy Dunlap Signed-off-by: Martin K. Petersen --- drivers/scsi/pm8001/pm8001_ctl.c | 48 +++++++++++++++-------------- drivers/scsi/pm8001/pm8001_hwi.c | 18 +++++------ drivers/scsi/pm8001/pm8001_init.c | 29 +++++++++--------- drivers/scsi/pm8001/pm8001_sas.c | 41 +++++++++++++------------ drivers/scsi/pm8001/pm80xx_hwi.c | 50 +++++++++++++++---------------- 5 files changed, 97 insertions(+), 89 deletions(-) diff --git a/drivers/scsi/pm8001/pm8001_ctl.c b/drivers/scsi/pm8001/pm8001_ctl.c index 0b8802beb7ce..ec05c42e8ee6 100644 --- a/drivers/scsi/pm8001/pm8001_ctl.c +++ b/drivers/scsi/pm8001/pm8001_ctl.c @@ -77,7 +77,7 @@ DEVICE_ATTR(interface_rev, S_IRUGO, pm8001_ctl_mpi_interface_rev_show, NULL); * @attr: device attribute (unused) * @buf: the buffer returned * - * A sysfs 'read only' shost attribute. + * A sysfs 'read-only' shost attribute. */ static ssize_t controller_fatal_error_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -149,7 +149,7 @@ static ssize_t pm8001_ctl_ila_version_show(struct device *cdev, static DEVICE_ATTR(ila_version, 0444, pm8001_ctl_ila_version_show, NULL); /** - * pm8001_ctl_inactive_fw_version_show - Inacative firmware version number + * pm8001_ctl_inactive_fw_version_show - Inactive firmware version number * @cdev: pointer to embedded class device * @attr: device attribute (unused) * @buf: the buffer returned @@ -396,6 +396,7 @@ static DEVICE_ATTR(aap_log, S_IRUGO, pm8001_ctl_aap_log_show, NULL); * @cdev:pointer to embedded class device * @attr: device attribute (unused) * @buf: the buffer returned + * * A sysfs 'read-only' shost attribute. */ static ssize_t pm8001_ctl_ib_queue_log_show(struct device *cdev, @@ -430,6 +431,7 @@ static DEVICE_ATTR(ib_log, S_IRUGO, pm8001_ctl_ib_queue_log_show, NULL); * @cdev:pointer to embedded class device * @attr: device attribute (unused) * @buf: the buffer returned + * * A sysfs 'read-only' shost attribute. */ @@ -464,6 +466,7 @@ static DEVICE_ATTR(ob_log, S_IRUGO, pm8001_ctl_ob_queue_log_show, NULL); * @cdev:pointer to embedded class device * @attr: device attribute (unused) * @buf:the buffer returned + * * A sysfs 'read-only' shost attribute. */ static ssize_t pm8001_ctl_bios_version_show(struct device *cdev, @@ -555,13 +558,13 @@ static ssize_t pm8001_ctl_iop_log_show(struct device *cdev, static DEVICE_ATTR(iop_log, S_IRUGO, pm8001_ctl_iop_log_show, NULL); /** - ** pm8001_ctl_fatal_log_show - fatal error logging - ** @cdev:pointer to embedded class device - ** @attr: device attribute - ** @buf: the buffer returned - ** - ** A sysfs 'read-only' shost attribute. - **/ + * pm8001_ctl_fatal_log_show - fatal error logging + * @cdev:pointer to embedded class device + * @attr: device attribute + * @buf: the buffer returned + * + * A sysfs 'read-only' shost attribute. + */ static ssize_t pm8001_ctl_fatal_log_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -575,13 +578,13 @@ static ssize_t pm8001_ctl_fatal_log_show(struct device *cdev, static DEVICE_ATTR(fatal_log, S_IRUGO, pm8001_ctl_fatal_log_show, NULL); /** - ** non_fatal_log_show - non fatal error logging - ** @cdev:pointer to embedded class device - ** @attr: device attribute - ** @buf: the buffer returned - ** - ** A sysfs 'read-only' shost attribute. - **/ + * non_fatal_log_show - non fatal error logging + * @cdev:pointer to embedded class device + * @attr: device attribute + * @buf: the buffer returned + * + * A sysfs 'read-only' shost attribute. + */ static ssize_t non_fatal_log_show(struct device *cdev, struct device_attribute *attr, char *buf) { @@ -620,12 +623,13 @@ static ssize_t non_fatal_count_store(struct device *cdev, static DEVICE_ATTR_RW(non_fatal_count); /** - ** pm8001_ctl_gsm_log_show - gsm dump collection - ** @cdev:pointer to embedded class device - ** @attr: device attribute (unused) - ** @buf: the buffer returned - ** A sysfs 'read-only' shost attribute. - **/ + * pm8001_ctl_gsm_log_show - gsm dump collection + * @cdev:pointer to embedded class device + * @attr: device attribute (unused) + * @buf: the buffer returned + * + * A sysfs 'read-only' shost attribute. + */ static ssize_t pm8001_ctl_gsm_log_show(struct device *cdev, struct device_attribute *attr, char *buf) { diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 33f8217577b1..17c0f26e683a 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -384,7 +384,7 @@ static void update_outbnd_queue_table(struct pm8001_hba_info *pm8001_ha, /** * pm8001_bar4_shift - function is called to shift BAR base address - * @pm8001_ha : our hba card infomation + * @pm8001_ha : our hba card information * @shiftValue : shifting value in memory bar. */ int pm8001_bar4_shift(struct pm8001_hba_info *pm8001_ha, u32 shiftValue) @@ -1151,7 +1151,7 @@ static void pm8001_hw_chip_rst(struct pm8001_hba_info *pm8001_ha) } /** - * pm8001_chip_iounmap - which maped when initialized. + * pm8001_chip_iounmap - which mapped when initialized. * @pm8001_ha: our hba card information */ void pm8001_chip_iounmap(struct pm8001_hba_info *pm8001_ha) @@ -1187,10 +1187,10 @@ pm8001_chip_intx_interrupt_enable(struct pm8001_hba_info *pm8001_ha) pm8001_cw32(pm8001_ha, 0, MSGU_ODCR, ODCR_CLEAR_ALL); } - /** - * pm8001_chip_intx_interrupt_disable- disable PM8001 chip interrupt - * @pm8001_ha: our hba card information - */ +/** + * pm8001_chip_intx_interrupt_disable - disable PM8001 chip interrupt + * @pm8001_ha: our hba card information + */ static void pm8001_chip_intx_interrupt_disable(struct pm8001_hba_info *pm8001_ha) { @@ -1876,8 +1876,8 @@ static void pm8001_send_read_log(struct pm8001_hba_info *pm8001_ha, * @piomb: the message contents of this outbound message. * * When FW has completed a ssp request for example a IO request, after it has - * filled the SG data with the data, it will trigger this event represent - * that he has finished the job,please check the coresponding buffer. + * filled the SG data with the data, it will trigger this event representing + * that he has finished the job; please check the corresponding buffer. * So we will tell the caller who maybe waiting the result to tell upper layer * that the task has been finished. */ @@ -3522,7 +3522,7 @@ hw_event_phy_down(struct pm8001_hba_info *pm8001_ha, void *piomb) * * when sas layer find a device it will notify LLDD, then the driver register * the domain device to FW, this event is the return device ID which the FW - * has assigned, from now,inter-communication with FW is no longer using the + * has assigned, from now, inter-communication with FW is no longer using the * SAS address, use device ID which FW assigned. */ int pm8001_mpi_reg_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index 313248c7bab9..47db7e0beae6 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -233,7 +233,7 @@ static irqreturn_t pm8001_interrupt_handler_msix(int irq, void *opaque) /** * pm8001_interrupt_handler_intx - main INTx interrupt handler. * @irq: interrupt number - * @dev_id: sas_ha structure. The HBA is retrieved from sas_has structure. + * @dev_id: sas_ha structure. The HBA is retrieved from sas_ha structure. */ static irqreturn_t pm8001_interrupt_handler_intx(int irq, void *dev_id) @@ -439,9 +439,9 @@ err_out: } /** - * pm8001_ioremap - remap the pci high physical address to kernal virtual + * pm8001_ioremap - remap the pci high physical address to kernel virtual * address so that we can access them. - * @pm8001_ha:our hba structure. + * @pm8001_ha: our hba structure. */ static int pm8001_ioremap(struct pm8001_hba_info *pm8001_ha) { @@ -652,7 +652,7 @@ static void pm8001_post_sas_ha_init(struct Scsi_Host *shost, * pm8001_init_sas_add - initialize sas address * @pm8001_ha: our ha struct. * - * Currently we just set the fixed SAS address to our HBA,for manufacture, + * Currently we just set the fixed SAS address to our HBA, for manufacture, * it should read from the EEPROM */ static void pm8001_init_sas_add(struct pm8001_hba_info *pm8001_ha) @@ -790,7 +790,7 @@ struct pm8001_mpi3_phy_pg_trx_config { }; /** - * pm8001_get_internal_phy_settings : Retrieves the internal PHY settings + * pm8001_get_internal_phy_settings - Retrieves the internal PHY settings * @pm8001_ha : our adapter * @phycfg : PHY config page to populate */ @@ -810,7 +810,7 @@ void pm8001_get_internal_phy_settings(struct pm8001_hba_info *pm8001_ha, } /** - * pm8001_get_external_phy_settings : Retrieves the external PHY settings + * pm8001_get_external_phy_settings - Retrieves the external PHY settings * @pm8001_ha : our adapter * @phycfg : PHY config page to populate */ @@ -830,7 +830,7 @@ void pm8001_get_external_phy_settings(struct pm8001_hba_info *pm8001_ha, } /** - * pm8001_get_phy_mask : Retrieves the mask that denotes if a PHY is int/ext + * pm8001_get_phy_mask - Retrieves the mask that denotes if a PHY is int/ext * @pm8001_ha : our adapter * @phymask : The PHY mask */ @@ -868,7 +868,7 @@ void pm8001_get_phy_mask(struct pm8001_hba_info *pm8001_ha, int *phymask) } /** - * pm8001_set_phy_settings_ven_117c_12G() : Configure ATTO 12Gb PHY settings + * pm8001_set_phy_settings_ven_117c_12G() - Configure ATTO 12Gb PHY settings * @pm8001_ha : our adapter */ static @@ -903,7 +903,7 @@ int pm8001_set_phy_settings_ven_117c_12G(struct pm8001_hba_info *pm8001_ha) } /** - * pm8001_configure_phy_settings : Configures PHY settings based on vendor ID. + * pm8001_configure_phy_settings - Configures PHY settings based on vendor ID. * @pm8001_ha : our hba. */ static int pm8001_configure_phy_settings(struct pm8001_hba_info *pm8001_ha) @@ -1053,8 +1053,8 @@ intx: * @ent: pci device id * * This function is the main initialization function, when register a new - * pci driver it is invoked, all struct an hardware initilization should be done - * here, also, register interrupt + * pci driver it is invoked, all struct and hardware initialization should be + * done here, also, register interrupt. */ static int pm8001_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -1172,10 +1172,11 @@ err_out_enable: return rc; } -/* +/** * pm8001_init_ccb_tag - allocate memory to CCB and tag. * @pm8001_ha: our hba card information. * @shost: scsi host which has been allocated outside. + * @pdev: pci device. */ static int pm8001_init_ccb_tag(struct pm8001_hba_info *pm8001_ha, struct Scsi_Host *shost, @@ -1270,7 +1271,7 @@ static void pm8001_pci_remove(struct pci_dev *pdev) * pm8001_pci_suspend - power management suspend main entry point * @dev: Device struct * - * Returns 0 success, anything else error. + * Return: 0 on success, anything else on error. */ static int __maybe_unused pm8001_pci_suspend(struct device *dev) { @@ -1315,7 +1316,7 @@ static int __maybe_unused pm8001_pci_suspend(struct device *dev) * pm8001_pci_resume - power management resume main entry point * @dev: Device struct * - * Returns 0 success, anything else error. + * Return: 0 on success, anything else on error. */ static int __maybe_unused pm8001_pci_resume(struct device *dev) { diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index 6f33d821e545..48548a95327b 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -98,14 +98,16 @@ void pm8001_tag_init(struct pm8001_hba_info *pm8001_ha) pm8001_tag_free(pm8001_ha, i); } - /** - * pm8001_mem_alloc - allocate memory for pm8001. - * @pdev: pci device. - * @virt_addr: the allocated virtual address - * @pphys_addr_hi: the physical address high byte address. - * @pphys_addr_lo: the physical address low byte address. - * @mem_size: memory size. - */ +/** + * pm8001_mem_alloc - allocate memory for pm8001. + * @pdev: pci device. + * @virt_addr: the allocated virtual address + * @pphys_addr: DMA address for this device + * @pphys_addr_hi: the physical address high byte address. + * @pphys_addr_lo: the physical address low byte address. + * @mem_size: memory size. + * @align: requested byte alignment + */ int pm8001_mem_alloc(struct pci_dev *pdev, void **virt_addr, dma_addr_t *pphys_addr, u32 *pphys_addr_hi, u32 *pphys_addr_lo, u32 mem_size, u32 align) @@ -339,7 +341,7 @@ static int pm8001_task_prep_ssp_tm(struct pm8001_hba_info *pm8001_ha, } /** - * pm8001_task_prep_ssp - the dispatcher function,prepare ssp data for ssp task + * pm8001_task_prep_ssp - the dispatcher function, prepare ssp data for ssp task * @pm8001_ha: our hba card information * @ccb: the ccb which attached to ssp task */ @@ -554,10 +556,10 @@ void pm8001_ccb_task_free(struct pm8001_hba_info *pm8001_ha, pm8001_tag_free(pm8001_ha, ccb_idx); } - /** - * pm8001_alloc_dev - find a empty pm8001_device - * @pm8001_ha: our hba card information - */ +/** + * pm8001_alloc_dev - find a empty pm8001_device + * @pm8001_ha: our hba card information + */ static struct pm8001_device *pm8001_alloc_dev(struct pm8001_hba_info *pm8001_ha) { u32 dev; @@ -705,7 +707,7 @@ static void pm8001_tmf_timedout(struct timer_list *t) * @parameter: ssp task parameter. * * when errors or exception happened, we may want to do something, for example - * abort the issued task which result in this execption, it is done by calling + * abort the issued task which result in this exception, it is done by calling * this function, note it is also with the task execute interface. */ static int pm8001_exec_internal_tmf_task(struct domain_device *dev, @@ -984,11 +986,12 @@ void pm8001_open_reject_retry( } /** - * pm8001_I_T_nexus_reset() - * Standard mandates link reset for ATA (type 0) and hard reset for - * SSP (type 1) , only for RECOVERY - * @dev: the device structure for the device to reset. - */ + * pm8001_I_T_nexus_reset() - reset the initiator/target connection + * @dev: the device structure for the device to reset. + * + * Standard mandates link reset for ATA (type 0) and hard reset for + * SSP (type 1), only for RECOVERY + */ int pm8001_I_T_nexus_reset(struct domain_device *dev) { int rc = TMF_RESP_FUNC_FAILED; diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 45ecd9639977..6ffe17b849ae 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -140,7 +140,7 @@ ssize_t pm80xx_get_fatal_dump(struct device *cdev, pm8001_ha->fatal_bar_loc = 0; } - /* Read until accum_len is retrived */ + /* Read until accum_len is retrieved */ accum_len = pm8001_mr32(fatal_table_address, MPI_FATAL_EDUMP_TABLE_ACCUM_LEN); /* Determine length of data between previously stored transfer length @@ -1011,7 +1011,7 @@ static int mpi_init_check(struct pm8001_hba_info *pm8001_ha) value); return -EBUSY; } - /* check the MPI-State for initialization upto 100ms*/ + /* check the MPI-State for initialization up to 100ms*/ max_wait_count = 5;/* 100 msec */ do { msleep(FW_READY_INTERVAL); @@ -1093,7 +1093,7 @@ static int init_pci_device_addresses(struct pm8001_hba_info *pm8001_ha) value = pm8001_cr32(pm8001_ha, 0, MSGU_SCRATCH_PAD_0); - /** + /* * lower 26 bits of SCRATCHPAD0 register describes offset within the * PCIe BAR where the MPI configuration table is present */ @@ -1101,7 +1101,7 @@ static int init_pci_device_addresses(struct pm8001_hba_info *pm8001_ha) pm8001_dbg(pm8001_ha, DEV, "Scratchpad 0 Offset: 0x%x value 0x%x\n", offset, value); - /** + /* * Upper 6 bits describe the offset within PCI config space where BAR * is located. */ @@ -1109,7 +1109,7 @@ static int init_pci_device_addresses(struct pm8001_hba_info *pm8001_ha) pcibar = get_pci_bar_index(pcilogic); pm8001_dbg(pm8001_ha, INIT, "Scratchpad 0 PCI BAR: %d\n", pcibar); - /** + /* * Make sure the offset falls inside the ioremapped PCI BAR */ if (offset > pm8001_ha->io_mem[pcibar].memsize) { @@ -1121,7 +1121,7 @@ static int init_pci_device_addresses(struct pm8001_hba_info *pm8001_ha) pm8001_ha->main_cfg_tbl_addr = base_addr = pm8001_ha->io_mem[pcibar].memvirtaddr + offset; - /** + /* * Validate main configuration table address: first DWord should read * "PMCS" */ @@ -1385,7 +1385,7 @@ pm80xx_get_encrypt_info(struct pm8001_hba_info *pm8001_ha) } /** - * pm80xx_encrypt_update - update flash with encryption informtion + * pm80xx_encrypt_update - update flash with encryption information * @pm8001_ha: our hba card information. */ static int pm80xx_encrypt_update(struct pm8001_hba_info *pm8001_ha) @@ -1422,7 +1422,7 @@ static int pm80xx_encrypt_update(struct pm8001_hba_info *pm8001_ha) } /** - * pm80xx_chip_init - the main init function that initialize whole PM8001 chip. + * pm80xx_chip_init - the main init function that initializes whole PM8001 chip. * @pm8001_ha: our hba card information */ static int pm80xx_chip_init(struct pm8001_hba_info *pm8001_ha) @@ -1541,7 +1541,7 @@ static int mpi_uninit_check(struct pm8001_hba_info *pm8001_ha) } /** - * pm80xx_fatal_errors - returns non zero *ONLY* when fatal errors + * pm80xx_fatal_errors - returns non-zero *ONLY* when fatal errors * @pm8001_ha: our hba card information * * Fatal errors are recoverable only after a host reboot. @@ -1576,8 +1576,8 @@ pm80xx_fatal_errors(struct pm8001_hba_info *pm8001_ha) } /** - * pm80xx_chip_soft_rst - soft reset the PM8001 chip, so that the clear all - * the FW register status to the originated status. + * pm80xx_chip_soft_rst - soft reset the PM8001 chip, so that all + * FW register status are reset to the originated status. * @pm8001_ha: our hba card information */ @@ -1895,13 +1895,13 @@ static void pm80xx_send_read_log(struct pm8001_hba_info *pm8001_ha, } /** - * mpi_ssp_completion- process the event that FW response to the SSP request. + * mpi_ssp_completion - process the event that FW response to the SSP request. * @pm8001_ha: our hba card information * @piomb: the message contents of this outbound message. * * When FW has completed a ssp request for example a IO request, after it has - * filled the SG data with the data, it will trigger this event represent - * that he has finished the job,please check the coresponding buffer. + * filled the SG data with the data, it will trigger this event representing + * that he has finished the job; please check the corresponding buffer. * So we will tell the caller who maybe waiting the result to tell upper layer * that the task has been finished. */ @@ -3217,7 +3217,7 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * pm80xx_hw_event_ack_req- For PM8001,some events need to acknowage to FW. + * pm80xx_hw_event_ack_req- For PM8001, some events need to acknowledge to FW. * @pm8001_ha: our hba card information * @Qnum: the outbound queue message number. * @SEA: source of event to ack @@ -3275,7 +3275,7 @@ static void hw_event_port_recover(struct pm8001_hba_info *pm8001_ha, } /** - * hw_event_sas_phy_up -FW tells me a SAS phy up event. + * hw_event_sas_phy_up - FW tells me a SAS phy up event. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -3353,7 +3353,7 @@ hw_event_sas_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * hw_event_sata_phy_up -FW tells me a SATA phy up event. + * hw_event_sata_phy_up - FW tells me a SATA phy up event. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -3400,7 +3400,7 @@ hw_event_sata_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * hw_event_phy_down -we should notify the libsas the phy is down. + * hw_event_phy_down - we should notify the libsas the phy is down. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -3500,7 +3500,7 @@ static int mpi_phy_start_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * mpi_thermal_hw_event -The hw event has come. + * mpi_thermal_hw_event - a thermal hw event has come. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -3530,7 +3530,7 @@ static int mpi_thermal_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb) } /** - * mpi_hw_event -The hw event has come. + * mpi_hw_event - The hw event has come. * @pm8001_ha: our hba card information * @piomb: IO message buffer */ @@ -4025,7 +4025,7 @@ static void process_one_iomb(struct pm8001_hba_info *pm8001_ha, void *piomb) case OPC_OUB_SET_DEV_INFO: pm8001_dbg(pm8001_ha, MSG, "OPC_OUB_SET_DEV_INFO\n"); break; - /* spcv specifc commands */ + /* spcv specific commands */ case OPC_OUB_PHY_START_RESP: pm8001_dbg(pm8001_ha, MSG, "OPC_OUB_PHY_START_RESP opcode:%x\n", opc); @@ -4186,7 +4186,7 @@ static void build_smp_cmd(u32 deviceID, __le32 hTag, } /** - * pm80xx_chip_smp_req - send a SMP task to FW + * pm80xx_chip_smp_req - send an SMP task to FW * @pm8001_ha: our hba card information. * @ccb: the ccb information this request used. */ @@ -4346,7 +4346,7 @@ static int check_enc_sat_cmd(struct sas_task *task) } /** - * pm80xx_chip_ssp_io_req - send a SSP task to FW + * pm80xx_chip_ssp_io_req - send an SSP task to FW * @pm8001_ha: our hba card information. * @ccb: the ccb information this request used. */ @@ -4750,13 +4750,13 @@ pm80xx_chip_phy_start_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id) payload.ase_sh_lm_slr_phyid = cpu_to_le32(SPINHOLD_DISABLE | LINKMODE_AUTO | pm8001_ha->link_rate | phy_id); /* SSC Disable and SAS Analog ST configuration */ - /** + /* payload.ase_sh_lm_slr_phyid = cpu_to_le32(SSC_DISABLE_30 | SAS_ASE | SPINHOLD_DISABLE | LINKMODE_AUTO | LINKRATE_15 | LINKRATE_30 | LINKRATE_60 | phy_id); Have to add "SAS PHY Analog Setup SPASTI 1 Byte" Based on need - **/ + */ payload.sas_identify.dev_type = SAS_END_DEVICE; payload.sas_identify.initiator_bits = SAS_PROTOCOL_ALL; From aa0dc6a73309f1fc779f4560a60ee766a3891adc Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Wed, 7 Jul 2021 13:47:56 +0530 Subject: [PATCH 226/426] scsi: mpi3mr: Fix W=1 compilation warnings Fix for the following W=1 compilation warning: 'strncpy' output may be truncated copying 16 bytes from a string of length 64 Link: https://lore.kernel.org/r/20210707081756.20922-1-sreekanth.reddy@broadcom.com Reported-by: kernel test robot Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpi3mr/mpi3mr_fw.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 9eceafca59bc..2dba2b0af166 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -2607,14 +2607,13 @@ static int mpi3mr_issue_iocinit(struct mpi3mr_ioc *mrioc) goto out; } drv_info->information_length = cpu_to_le32(data_len); - strncpy(drv_info->driver_signature, "Broadcom", sizeof(drv_info->driver_signature)); - strncpy(drv_info->os_name, utsname()->sysname, sizeof(drv_info->os_name)); - drv_info->os_name[sizeof(drv_info->os_name) - 1] = 0; - strncpy(drv_info->os_version, utsname()->release, sizeof(drv_info->os_version)); - drv_info->os_version[sizeof(drv_info->os_version) - 1] = 0; - strncpy(drv_info->driver_name, MPI3MR_DRIVER_NAME, sizeof(drv_info->driver_name)); - strncpy(drv_info->driver_version, MPI3MR_DRIVER_VERSION, sizeof(drv_info->driver_version)); - strncpy(drv_info->driver_release_date, MPI3MR_DRIVER_RELDATE, sizeof(drv_info->driver_release_date)); + strscpy(drv_info->driver_signature, "Broadcom", sizeof(drv_info->driver_signature)); + strscpy(drv_info->os_name, utsname()->sysname, sizeof(drv_info->os_name)); + strscpy(drv_info->os_version, utsname()->release, sizeof(drv_info->os_version)); + strscpy(drv_info->driver_name, MPI3MR_DRIVER_NAME, sizeof(drv_info->driver_name)); + strscpy(drv_info->driver_version, MPI3MR_DRIVER_VERSION, sizeof(drv_info->driver_version)); + strscpy(drv_info->driver_release_date, MPI3MR_DRIVER_RELDATE, + sizeof(drv_info->driver_release_date)); drv_info->driver_capabilities = 0; memcpy((u8 *)&mrioc->driver_info, (u8 *)drv_info, sizeof(mrioc->driver_info)); From 053c16ac89050ef0e8ab9dc1edaf157bf104c8c6 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 30 Jun 2021 17:51:17 -0700 Subject: [PATCH 227/426] scsi: ufs: core: Add missing host_lock in ufshcd_vops_setup_xfer_req() This patch adds a host_lock which existed before on ufshcd_vops_setup_xfer_req(). Link: https://lore.kernel.org/r/20210701005117.3846179-1-jaegeuk@kernel.org Fixes: a45f937110fa ("scsi: ufs: Optimize host lock on transfer requests send/compl paths") Cc: Stanley Chu Cc: Can Guo Cc: Bean Huo Cc: Bart Van Assche Cc: Asutosh Das Reviewed-by: Bart Van Assche Signed-off-by: Jaegeuk Kim Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index c98d540ac044..194755c9ddfe 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -1229,8 +1229,13 @@ static inline int ufshcd_vops_pwr_change_notify(struct ufs_hba *hba, static inline void ufshcd_vops_setup_xfer_req(struct ufs_hba *hba, int tag, bool is_scsi_cmd) { - if (hba->vops && hba->vops->setup_xfer_req) - return hba->vops->setup_xfer_req(hba, tag, is_scsi_cmd); + if (hba->vops && hba->vops->setup_xfer_req) { + unsigned long flags; + + spin_lock_irqsave(hba->host->host_lock, flags); + hba->vops->setup_xfer_req(hba, tag, is_scsi_cmd); + spin_unlock_irqrestore(hba->host->host_lock, flags); + } } static inline void ufshcd_vops_setup_task_mgmt(struct ufs_hba *hba, From e181ad43887c6b6b5995e9b191666f04242d77eb Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 21:24:07 -0500 Subject: [PATCH 228/426] drm/msm: Fix fall-through warning in msm_gem_new_impl() Fix the following fall-through warning: drivers/gpu/drm/msm/msm_gem.c: In function 'msm_gem_new_impl': drivers/gpu/drm/msm/msm_gem.c:1170:6: warning: this statement may fall through [-Wimplicit-fallthrough=] 1170 | if (priv->has_cached_coherent) | ^ drivers/gpu/drm/msm/msm_gem.c:1173:2: note: here 1173 | default: | ^~~~~~~ by replacing the /* fallthrough */ comment with fallthrough; Reported-by: Stephen Rothwell Signed-off-by: Gustavo A. R. Silva --- drivers/gpu/drm/msm/msm_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 141178754231..1e8a971a86f2 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -1169,7 +1169,7 @@ static int msm_gem_new_impl(struct drm_device *dev, case MSM_BO_CACHED_COHERENT: if (priv->has_cached_coherent) break; - /* fallthrough */ + fallthrough; default: DRM_DEV_ERROR(dev->dev, "invalid cache flag: %x\n", (flags & MSM_BO_CACHE_MASK)); From 432b52eea3dcf48083bafa4b2b6ef5b054ead609 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 12 Jul 2021 12:16:57 +0200 Subject: [PATCH 229/426] ARM: shmobile: defconfig: Restore graphical consoles As of commit f611b1e7624ccdbd ("drm: Avoid circular dependencies for CONFIG_FB"), CONFIG_FB is no longer auto-enabled. While CONFIG_FB may be considered unneeded for systems where graphics is provided by a DRM driver, R-Mobile A1 still relies on a frame buffer device driver for graphics support. Restore support for graphics on R-Mobile A1 and graphical consoles on DRM-based systems by explicitly enabling CONFIG_FB in the defconfig for Renesas ARM systems. Fixes: f611b1e7624ccdbd ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/2a4474be1d2c00c6ca97c2714844ea416a9ea9a9.1626084948.git.geert+renesas@glider.be --- arch/arm/configs/shmobile_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig index 66c8b0980a0a..d9a27e4e0914 100644 --- a/arch/arm/configs/shmobile_defconfig +++ b/arch/arm/configs/shmobile_defconfig @@ -135,6 +135,7 @@ CONFIG_DRM_SII902X=y CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_I2C_ADV7511=y CONFIG_DRM_I2C_ADV7511_AUDIO=y +CONFIG_FB=y CONFIG_FB_SH_MOBILE_LCDC=y CONFIG_BACKLIGHT_PWM=y CONFIG_BACKLIGHT_AS3711=y From 8b43ced64d2baca72a13caf2a7182f2853e054bd Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Tue, 13 Jul 2021 11:31:56 +0200 Subject: [PATCH 230/426] nvme-tcp: use __dev_get_by_name instead dev_get_by_name for OPT_HOST_IFACE dev_get_by_name() finds network device by name but it also increases the reference count. If a nvme-tcp queue is present and the network device driver is removed before nvme_tcp, we will face the following continuous log: "kernel:unregister_netdevice: waiting for to become free. Usage count = 2" And rmmod further halts. Similar case arises during reboot/shutdown with nvme-tcp queue present and both never completes. To fix this, use __dev_get_by_name() which finds network device by name without increasing any reference counter. Fixes: 3ede8f72a9a2 ("nvme-tcp: allow selecting the network interface for connections") Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Prabhakar Kushwaha Reviewed-by: Sagi Grimberg [hch: remove the ->ndev member entirely] Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 12acfe05cd68..8cb15ee5b249 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -123,7 +123,6 @@ struct nvme_tcp_ctrl { struct blk_mq_tag_set admin_tag_set; struct sockaddr_storage addr; struct sockaddr_storage src_addr; - struct net_device *ndev; struct nvme_ctrl ctrl; struct work_struct err_work; @@ -2533,8 +2532,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, } if (opts->mask & NVMF_OPT_HOST_IFACE) { - ctrl->ndev = dev_get_by_name(&init_net, opts->host_iface); - if (!ctrl->ndev) { + if (!__dev_get_by_name(&init_net, opts->host_iface)) { pr_err("invalid interface passed: %s\n", opts->host_iface); ret = -ENODEV; From e4b9852a0f4afe40604afb442e3af4452722050a Mon Sep 17 00:00:00 2001 From: Casey Chen Date: Wed, 7 Jul 2021 14:14:31 -0700 Subject: [PATCH 231/426] nvme-pci: fix multiple races in nvme_setup_io_queues Below two paths could overlap each other if we power off a drive quickly after powering it on. There are multiple races in nvme_setup_io_queues() because of shutdown_lock missing and improper use of NVMEQ_ENABLED bit. nvme_reset_work() nvme_remove() nvme_setup_io_queues() nvme_dev_disable() ... ... A1 clear NVMEQ_ENABLED bit for admin queue lock retry: B1 nvme_suspend_io_queues() A2 pci_free_irq() admin queue B2 nvme_suspend_queue() admin queue A3 pci_free_irq_vectors() nvme_pci_disable() A4 nvme_setup_irqs(); B3 pci_free_irq_vectors() ... unlock A5 queue_request_irq() for admin queue set NVMEQ_ENABLED bit ... nvme_create_io_queues() A6 result = queue_request_irq(); set NVMEQ_ENABLED bit ... fail to allocate enough IO queues: A7 nvme_suspend_io_queues() goto retry If B3 runs in between A1 and A2, it will crash if irqaction haven't been freed by A2. B2 is supposed to free admin queue IRQ but it simply can't fulfill the job as A1 has cleared NVMEQ_ENABLED bit. Fix: combine A1 A2 so IRQ get freed as soon as the NVMEQ_ENABLED bit gets cleared. After solved #1, A2 could race with B3 if A2 is freeing IRQ while B3 is checking irqaction. A3 also could race with B2 if B2 is freeing IRQ while A3 is checking irqaction. Fix: A2 and A3 take lock for mutual exclusion. A3 could race with B3 since they could run free_msi_irqs() in parallel. Fix: A3 takes lock for mutual exclusion. A4 could fail to allocate all needed IRQ vectors if A3 and A4 are interrupted by B3. Fix: A4 takes lock for mutual exclusion. If A5/A6 happened after B2/B1, B3 will crash since irqaction is not NULL. They are just allocated by A5/A6. Fix: Lock queue_request_irq() and setting of NVMEQ_ENABLED bit. A7 could get chance to pci_free_irq() for certain IO queue while B3 is checking irqaction. Fix: A7 takes lock. nvme_dev->online_queues need to be protected by shutdown_lock. Since it is not atomic, both paths could modify it using its own copy. Co-developed-by: Yuanyuan Zhong Signed-off-by: Casey Chen Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 66 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 58 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d3c5086673bc..46698cabef81 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1554,6 +1554,28 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid) wmb(); /* ensure the first interrupt sees the initialization */ } +/* + * Try getting shutdown_lock while setting up IO queues. + */ +static int nvme_setup_io_queues_trylock(struct nvme_dev *dev) +{ + /* + * Give up if the lock is being held by nvme_dev_disable. + */ + if (!mutex_trylock(&dev->shutdown_lock)) + return -ENODEV; + + /* + * Controller is in wrong state, fail early. + */ + if (dev->ctrl.state != NVME_CTRL_CONNECTING) { + mutex_unlock(&dev->shutdown_lock); + return -ENODEV; + } + + return 0; +} + static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) { struct nvme_dev *dev = nvmeq->dev; @@ -1582,8 +1604,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) goto release_cq; nvmeq->cq_vector = vector; - nvme_init_queue(nvmeq, qid); + result = nvme_setup_io_queues_trylock(dev); + if (result) + return result; + nvme_init_queue(nvmeq, qid); if (!polled) { result = queue_request_irq(nvmeq); if (result < 0) @@ -1591,10 +1616,12 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) } set_bit(NVMEQ_ENABLED, &nvmeq->flags); + mutex_unlock(&dev->shutdown_lock); return result; release_sq: dev->online_queues--; + mutex_unlock(&dev->shutdown_lock); adapter_delete_sq(dev, qid); release_cq: adapter_delete_cq(dev, qid); @@ -2167,7 +2194,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) if (nr_io_queues == 0) return 0; - clear_bit(NVMEQ_ENABLED, &adminq->flags); + /* + * Free IRQ resources as soon as NVMEQ_ENABLED bit transitions + * from set to unset. If there is a window to it is truely freed, + * pci_free_irq_vectors() jumping into this window will crash. + * And take lock to avoid racing with pci_free_irq_vectors() in + * nvme_dev_disable() path. + */ + result = nvme_setup_io_queues_trylock(dev); + if (result) + return result; + if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags)) + pci_free_irq(pdev, 0, adminq); if (dev->cmb_use_sqes) { result = nvme_cmb_qdepth(dev, nr_io_queues, @@ -2183,14 +2221,17 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) result = nvme_remap_bar(dev, size); if (!result) break; - if (!--nr_io_queues) - return -ENOMEM; + if (!--nr_io_queues) { + result = -ENOMEM; + goto out_unlock; + } } while (1); adminq->q_db = dev->dbs; retry: /* Deregister the admin queue's interrupt */ - pci_free_irq(pdev, 0, adminq); + if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags)) + pci_free_irq(pdev, 0, adminq); /* * If we enable msix early due to not intx, disable it again before @@ -2199,8 +2240,10 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) pci_free_irq_vectors(pdev); result = nvme_setup_irqs(dev, nr_io_queues); - if (result <= 0) - return -EIO; + if (result <= 0) { + result = -EIO; + goto out_unlock; + } dev->num_vecs = result; result = max(result - 1, 1); @@ -2214,8 +2257,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) */ result = queue_request_irq(adminq); if (result) - return result; + goto out_unlock; set_bit(NVMEQ_ENABLED, &adminq->flags); + mutex_unlock(&dev->shutdown_lock); result = nvme_create_io_queues(dev); if (result || dev->online_queues < 2) @@ -2224,6 +2268,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) if (dev->online_queues - 1 < dev->max_qid) { nr_io_queues = dev->online_queues - 1; nvme_disable_io_queues(dev); + result = nvme_setup_io_queues_trylock(dev); + if (result) + return result; nvme_suspend_io_queues(dev); goto retry; } @@ -2232,6 +2279,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) dev->io_queues[HCTX_TYPE_READ], dev->io_queues[HCTX_TYPE_POLL]); return 0; +out_unlock: + mutex_unlock(&dev->shutdown_lock); + return result; } static void nvme_del_queue_end(struct request *req, blk_status_t error) From 251ef6f71be2adfd09546a26643426fe62585173 Mon Sep 17 00:00:00 2001 From: Casey Chen Date: Wed, 7 Jul 2021 14:14:32 -0700 Subject: [PATCH 232/426] nvme-pci: do not call nvme_dev_remove_admin from nvme_remove nvme_dev_remove_admin could free dev->admin_q and the admin_tagset while they are being accessed by nvme_dev_disable(), which can be called by nvme_reset_work via nvme_remove_dead_ctrl. Commit cb4bfda62afa ("nvme-pci: fix hot removal during error handling") intended to avoid requests being stuck on a removed controller by killing the admin queue. But the later fix c8e9e9b7646e ("nvme-pci: unquiesce admin queue on shutdown"), together with nvme_dev_disable(dev, true) right before nvme_dev_remove_admin() could help dispatch requests and fail them early, so we don't need nvme_dev_remove_admin() any more. Fixes: cb4bfda62afa ("nvme-pci: fix hot removal during error handling") Signed-off-by: Casey Chen Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 46698cabef81..320051f5a3dd 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3012,7 +3012,6 @@ static void nvme_remove(struct pci_dev *pdev) if (!pci_device_is_present(pdev)) { nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD); nvme_dev_disable(dev, true); - nvme_dev_remove_admin(dev); } flush_work(&dev->ctrl.reset_work); From 52f83955aaf91b22f46765b007b4404ce85b2133 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 12 Jul 2021 14:08:01 +0100 Subject: [PATCH 233/426] firmware: arm_scmi: Fix kernel doc warnings Kernel doc validation script is unhappy and complains with the below set of warnings. | Function parameter or member 'fast_switch_possible' not described in 'scmi_perf_proto_ops' | Function parameter or member 'power_scale_mw_get' not described in 'scmi_perf_proto_ops' | cannot understand function prototype: 'struct scmi_sensor_reading ' | cannot understand function prototype: 'struct scmi_range_attrs ' | cannot understand function prototype: 'struct scmi_sensor_axis_info ' | cannot understand function prototype: 'struct scmi_sensor_intervals_info ' Fix them adding appropriate documents or missing keywords. Link: https://lore.kernel.org/r/20210712130801.2436492-2-sudeep.holla@arm.com Reviewed-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 79d0a1237e6c..80e781c51ddc 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -101,6 +101,10 @@ struct scmi_clk_proto_ops { * to sustained performance level mapping * @est_power_get: gets the estimated power cost for a given performance domain * at a given frequency + * @fast_switch_possible: indicates if fast DVFS switching is possible or not + * for a given device + * @power_scale_mw_get: indicates if the power values provided are in milliWatts + * or in some other (abstract) scale */ struct scmi_perf_proto_ops { int (*limits_set)(const struct scmi_protocol_handle *ph, u32 domain, @@ -153,7 +157,7 @@ struct scmi_power_proto_ops { }; /** - * scmi_sensor_reading - represent a timestamped read + * struct scmi_sensor_reading - represent a timestamped read * * Used by @reading_get_timestamped method. * @@ -167,7 +171,7 @@ struct scmi_sensor_reading { }; /** - * scmi_range_attrs - specifies a sensor or axis values' range + * struct scmi_range_attrs - specifies a sensor or axis values' range * @min_range: The minimum value which can be represented by the sensor/axis. * @max_range: The maximum value which can be represented by the sensor/axis. */ @@ -177,7 +181,7 @@ struct scmi_range_attrs { }; /** - * scmi_sensor_axis_info - describes one sensor axes + * struct scmi_sensor_axis_info - describes one sensor axes * @id: The axes ID. * @type: Axes type. Chosen amongst one of @enum scmi_sensor_class. * @scale: Power-of-10 multiplier applied to the axis unit. @@ -205,8 +209,8 @@ struct scmi_sensor_axis_info { }; /** - * scmi_sensor_intervals_info - describes number and type of available update - * intervals + * struct scmi_sensor_intervals_info - describes number and type of available + * update intervals * @segmented: Flag for segmented intervals' representation. When True there * will be exactly 3 intervals in @desc, with each entry * representing a member of a segment in this order: From 5ff6319d46cee22c9cd6f39a377e32c444f9a7b0 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 12 Jul 2021 11:27:48 +0100 Subject: [PATCH 234/426] firmware: arm_scpi: Fix kernel doc warnings Kernel doc validation script is unhappy and complains with the below set of warnings. | Function parameter or member 'device_domain_id' not described in 'scpi_ops' | Function parameter or member 'get_transition_latency' not described in 'scpi_ops' | Function parameter or member 'add_opps_to_device' not described in 'scpi_ops' | Function parameter or member 'sensor_get_capability' not described in 'scpi_ops' | Function parameter or member 'sensor_get_info' not described in 'scpi_ops' | Function parameter or member 'sensor_get_value' not described in 'scpi_ops' | Function parameter or member 'device_get_power_state' not described in 'scpi_ops' | Function parameter or member 'device_set_power_state' not described in 'scpi_ops' Fix them adding appropriate documents or missing keywords. Link: https://lore.kernel.org/r/20210712130801.2436492-1-sudeep.holla@arm.com Reviewed-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scpi_protocol.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index afbf8037d8db..d2176a56828a 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -51,6 +51,14 @@ struct scpi_sensor_info { * OPP is an index to the list return by @dvfs_get_info * @dvfs_get_info: returns the DVFS capabilities of the given power * domain. It includes the OPP list and the latency information + * @device_domain_id: gets the scpi domain id for a given device + * @get_transition_latency: gets the DVFS transition latency for a given device + * @add_opps_to_device: adds all the OPPs for a given device + * @sensor_get_capability: get the list of capabilities for the sensors + * @sensor_get_info: get the information of the specified sensor + * @sensor_get_value: gets the current value of the sensor + * @device_get_power_state: gets the power state of a power domain + * @device_set_power_state: sets the power state of a power domain */ struct scpi_ops { u32 (*get_version)(void); From b98cf55ec0bd88bdba725845c743e94ecaf57b7e Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 12 Jul 2021 15:35:04 +0100 Subject: [PATCH 235/426] firmware: arm_scmi: Fix kernel doc warnings about return values Kernel doc validation script still complains about the following: |No description found for return value of 'scmi_get_protocol_device' |No description found for return value of 'scmi_devm_notifier_register' |No description found for return value of 'scmi_devm_notifier_unregister' Fix adding missing Return kernel-doc statements. Link: https://lore.kernel.org/r/20210712143504.33541-1-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 2 ++ drivers/firmware/arm_scmi/notify.c | 4 ++++ 2 files changed, 6 insertions(+) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 36d80661d473..1cbd2b06e523 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1138,6 +1138,8 @@ scmi_txrx_setup(struct scmi_info *info, struct device *dev, int prot_id) * @proto_id and @name: if device was still not existent it is created as a * child of the specified SCMI instance @info and its transport properly * initialized as usual. + * + * Return: A properly initialized scmi device, NULL otherwise. */ static inline struct scmi_device * scmi_get_protocol_device(struct device_node *np, struct scmi_info *info, diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c index d860bebd984a..0efd20cd9d69 100644 --- a/drivers/firmware/arm_scmi/notify.c +++ b/drivers/firmware/arm_scmi/notify.c @@ -1457,6 +1457,8 @@ static void scmi_devm_release_notifier(struct device *dev, void *res) * * Generic devres managed helper to register a notifier_block against a * protocol event. + * + * Return: 0 on Success */ static int scmi_devm_notifier_register(struct scmi_device *sdev, u8 proto_id, u8 evt_id, @@ -1523,6 +1525,8 @@ static int scmi_devm_notifier_match(struct device *dev, void *res, void *data) * Generic devres managed helper to explicitly un-register a notifier_block * against a protocol event, which was previously registered using the above * @scmi_devm_notifier_register. + * + * Return: 0 on Success */ static int scmi_devm_notifier_unregister(struct scmi_device *sdev, u8 proto_id, u8 evt_id, From 187a002b07e8089f0b5657eafec50b5d05625569 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 28 Jun 2021 18:00:42 +0100 Subject: [PATCH 236/426] firmware: arm_scmi: Avoid padding in sensor message structure scmi_resp_sensor_reading_complete structure is meant to represent an SCMI asynchronous reading complete message. The readings field with a 64bit type forces padding and breaks reads in scmi_sensor_reading_get. Split it in two adjacent 32bit readings_low/high subfields to avoid the padding within the structure. Alternatively we could to mark the structure packed. Link: https://lore.kernel.org/r/20210628170042.34105-1-cristian.marussi@arm.com Fixes: e2083d3673916 ("firmware: arm_scmi: Add SCMI v3.0 sensors timestamped reads") Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/sensors.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c index 2c88aa221559..308471586381 100644 --- a/drivers/firmware/arm_scmi/sensors.c +++ b/drivers/firmware/arm_scmi/sensors.c @@ -166,7 +166,8 @@ struct scmi_msg_sensor_reading_get { struct scmi_resp_sensor_reading_complete { __le32 id; - __le64 readings; + __le32 readings_low; + __le32 readings_high; }; struct scmi_sensor_reading_resp { @@ -717,7 +718,8 @@ static int scmi_sensor_reading_get(const struct scmi_protocol_handle *ph, resp = t->rx.buf; if (le32_to_cpu(resp->id) == sensor_id) - *value = get_unaligned_le64(&resp->readings); + *value = + get_unaligned_le64(&resp->readings_low); else ret = -EPROTO; } From bdb8742dc6f7c599c3d61959234fe4c23638727b Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 12 Jul 2021 15:18:18 +0100 Subject: [PATCH 237/426] firmware: arm_scmi: Fix range check for the maximum number of pending messages SCMI message headers carry a sequence number and such field is sized to allow for MSG_TOKEN_MAX distinct numbers; moreover zero is not really an acceptable maximum number of pending in-flight messages. Fix accordingly the checks performed on the value exported by transports in scmi_desc.max_msg Link: https://lore.kernel.org/r/20210712141833.6628-3-cristian.marussi@arm.com Reported-by: Vincent Guittot Signed-off-by: Cristian Marussi [sudeep.holla: updated the patch title and error message] Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 1cbd2b06e523..9b2e8d42a992 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1026,8 +1026,9 @@ static int __scmi_xfer_info_init(struct scmi_info *sinfo, const struct scmi_desc *desc = sinfo->desc; /* Pre-allocated messages, no more than what hdr.seq can support */ - if (WARN_ON(desc->max_msg >= MSG_TOKEN_MAX)) { - dev_err(dev, "Maximum message of %d exceeds supported %ld\n", + if (WARN_ON(!desc->max_msg || desc->max_msg > MSG_TOKEN_MAX)) { + dev_err(dev, + "Invalid maximum messages %d, not in range [1 - %lu]\n", desc->max_msg, MSG_TOKEN_MAX); return -EINVAL; } From 0af778269a522c988ef0b4188556aba97fb420cc Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Mon, 12 Jul 2021 16:55:44 +0800 Subject: [PATCH 238/426] fbmem: Do not delete the mode that is still in use The execution of fb_delete_videomode() is not based on the result of the previous fbcon_mode_deleted(). As a result, the mode is directly deleted, regardless of whether it is still in use, which may cause UAF. ================================================================== BUG: KASAN: use-after-free in fb_mode_is_equal+0x36e/0x5e0 \ drivers/video/fbdev/core/modedb.c:924 Read of size 4 at addr ffff88807e0ddb1c by task syz-executor.0/18962 CPU: 2 PID: 18962 Comm: syz-executor.0 Not tainted 5.10.45-rc1+ #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ... Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x137/0x1be lib/dump_stack.c:118 print_address_description+0x6c/0x640 mm/kasan/report.c:385 __kasan_report mm/kasan/report.c:545 [inline] kasan_report+0x13d/0x1e0 mm/kasan/report.c:562 fb_mode_is_equal+0x36e/0x5e0 drivers/video/fbdev/core/modedb.c:924 fbcon_mode_deleted+0x16a/0x220 drivers/video/fbdev/core/fbcon.c:2746 fb_set_var+0x1e1/0xdb0 drivers/video/fbdev/core/fbmem.c:975 do_fb_ioctl+0x4d9/0x6e0 drivers/video/fbdev/core/fbmem.c:1108 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl+0xfb/0x170 fs/ioctl.c:739 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 18960: kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track+0x3d/0x70 mm/kasan/common.c:56 kasan_set_free_info+0x17/0x30 mm/kasan/generic.c:355 __kasan_slab_free+0x108/0x140 mm/kasan/common.c:422 slab_free_hook mm/slub.c:1541 [inline] slab_free_freelist_hook+0xd6/0x1a0 mm/slub.c:1574 slab_free mm/slub.c:3139 [inline] kfree+0xca/0x3d0 mm/slub.c:4121 fb_delete_videomode+0x56a/0x820 drivers/video/fbdev/core/modedb.c:1104 fb_set_var+0x1f3/0xdb0 drivers/video/fbdev/core/fbmem.c:978 do_fb_ioctl+0x4d9/0x6e0 drivers/video/fbdev/core/fbmem.c:1108 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl+0xfb/0x170 fs/ioctl.c:739 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 13ff178ccd6d ("fbcon: Call fbcon_mode_deleted/new_modelist directly") Signed-off-by: Zhen Lei Cc: # v5.3+ Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210712085544.2828-1-thunder.leizhen@huawei.com --- drivers/video/fbdev/core/fbmem.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 98f193078c05..1c855145711b 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -970,13 +970,11 @@ fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var) fb_var_to_videomode(&mode2, &info->var); /* make sure we don't delete the videomode of current var */ ret = fb_mode_is_equal(&mode1, &mode2); - - if (!ret) - fbcon_mode_deleted(info, &mode1); - - if (!ret) - fb_delete_videomode(&mode1, &info->modelist); - + if (!ret) { + ret = fbcon_mode_deleted(info, &mode1); + if (!ret) + fb_delete_videomode(&mode1, &info->modelist); + } return ret ? -EINVAL : 0; } From 8cdd23c23c3d481a43b4aa03dcb5738812831115 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 12 Jul 2021 14:46:37 -0700 Subject: [PATCH 239/426] arm64: Restrict ARM64_BTI_KERNEL to clang 12.0.0 and newer Commit 97fed779f2a6 ("arm64: bti: Provide Kconfig for kernel mode BTI") disabled CONFIG_ARM64_BTI_KERNEL when CONFIG_GCOV_KERNEL was enabled and compiling with clang because of warnings that were seen with allmodconfig because LLVM was not emitting PAC/BTI instructions for compiler generated functions: | warning: some functions compiled with BTI and some compiled without BTI | warning: not setting BTI in feature flags This dependency was fine for avoiding the warnings with allmodconfig until commit 51c2ee6d121c ("Kconfig: Introduce ARCH_WANTS_NO_INSTR and CC_HAS_NO_PROFILE_FN_ATTR"), which prevents CONFIG_GCOV_KERNEL from being enabled with clang 12.0.0 or older because those versions do not support the no_profile_instrument_function attribute. As a result, CONFIG_ARM64_BTI_KERNEL gets enabled with allmodconfig and there are more warnings like the ones above due to CONFIG_KASAN, which suffers from the same problem as CONFIG_GCOV_KERNEL. This was most likely not noticed at the time because allmodconfig + CONFIG_GCOV_KERNEL=n was not tested. defconfig + CONFIG_KASAN=y is enough to reproduce the same warnings as above. The root cause of the warnings was resolved in LLVM during the 12.0.0 release so rather than play whack-a-mole with the dependencies, just update CONFIG_ARM64_BTI_KERNEL to require clang 12.0.0, which will have all of the issues ironed out. Link: https://github.com/ClangBuiltLinux/linux/issues/1428 Link: https://github.com/ClangBuiltLinux/continuous-integration2/runs/3010034706?check_suite_focus=true Link: https://github.com/ClangBuiltLinux/continuous-integration2/runs/3010035725?check_suite_focus=true Link: https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc76fcc4cc9 Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20210712214636.3134425-1-nathan@kernel.org Signed-off-by: Will Deacon --- arch/arm64/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index e07e7de9ac49..b5b13a932561 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1605,7 +1605,8 @@ config ARM64_BTI_KERNEL depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697 depends on !CC_IS_GCC || GCC_VERSION >= 100100 - depends on !(CC_IS_CLANG && GCOV_KERNEL) + # https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc76fcc4cc9 + depends on !CC_IS_CLANG || CLANG_VERSION >= 120000 depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help Build the kernel with Branch Target Identification annotations From 798c511548b946ae9ec123b0dfe197a5f29e63ec Mon Sep 17 00:00:00 2001 From: Jingwen Chen Date: Thu, 1 Jul 2021 10:19:17 +0800 Subject: [PATCH 240/426] drm/amdgpu: SRIOV flr_work should take write_lock [Why] If flr_work takes read_lock, then other threads who takes read_lock can access hardware when host is doing vf flr. [How] flr_work should take write_lock to avoid this case. Signed-off-by: Jingwen Chen Reviewed-by: Monk Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 3ee481557fc9..ff2307d7ee0f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -252,7 +252,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) * otherwise the mailbox msg will be ruined/reseted by * the VF FLR. */ - if (!down_read_trylock(&adev->reset_sem)) + if (!down_write_trylock(&adev->reset_sem)) return; amdgpu_virt_fini_data_exchange(adev); @@ -268,7 +268,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) flr_done: atomic_set(&adev->in_gpu_reset, 0); - up_read(&adev->reset_sem); + up_write(&adev->reset_sem); /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 48e588d3c409..9f7aac435d69 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -273,7 +273,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) * otherwise the mailbox msg will be ruined/reseted by * the VF FLR. */ - if (!down_read_trylock(&adev->reset_sem)) + if (!down_write_trylock(&adev->reset_sem)) return; amdgpu_virt_fini_data_exchange(adev); @@ -289,7 +289,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) flr_done: atomic_set(&adev->in_gpu_reset, 0); - up_read(&adev->reset_sem); + up_write(&adev->reset_sem); /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) From 43a44c5322d1030d8f36ad679307c61f5b4e3716 Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Fri, 2 Jul 2021 18:35:14 -0400 Subject: [PATCH 241/426] drm/amdgpu: Return error if no RAS In amdgpu_ras_query_error_count() return an error if the device doesn't support RAS. This prevents that function from having to always set the values of the integer pointers (if set), and thus prevents function side effects--always to have to set values of integers if integer pointers set, regardless of whether RAS is supported or not--with this change this side effect is mitigated. Also, if no pointers are set, don't count, since we've no way of reporting the counts. Also, give this function a kernel-doc. Cc: Alexander Deucher Cc: John Clements Cc: Hawking Zhang Reported-by: Tom Rix Fixes: a46751fbcde505 ("drm/amdgpu: Fix RAS function interface") Signed-off-by: Luben Tuikov Reviewed-by: Alexander Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 49 ++++++++++++++++++------- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 6 +-- 2 files changed, 38 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index c13b02caf8c3..fc66aca28594 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -809,7 +809,7 @@ static int amdgpu_ras_enable_all_features(struct amdgpu_device *adev, /* query/inject/cure begin */ int amdgpu_ras_query_error_status(struct amdgpu_device *adev, - struct ras_query_if *info) + struct ras_query_if *info) { struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head); struct ras_err_data err_data = {0, 0, 0, NULL}; @@ -1043,17 +1043,32 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, return ret; } -/* get the total error counts on all IPs */ -void amdgpu_ras_query_error_count(struct amdgpu_device *adev, - unsigned long *ce_count, - unsigned long *ue_count) +/** + * amdgpu_ras_query_error_count -- Get error counts of all IPs + * adev: pointer to AMD GPU device + * ce_count: pointer to an integer to be set to the count of correctible errors. + * ue_count: pointer to an integer to be set to the count of uncorrectible + * errors. + * + * If set, @ce_count or @ue_count, count and return the corresponding + * error counts in those integer pointers. Return 0 if the device + * supports RAS. Return -EOPNOTSUPP if the device doesn't support RAS. + */ +int amdgpu_ras_query_error_count(struct amdgpu_device *adev, + unsigned long *ce_count, + unsigned long *ue_count) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_manager *obj; unsigned long ce, ue; if (!adev->ras_enabled || !con) - return; + return -EOPNOTSUPP; + + /* Don't count since no reporting. + */ + if (!ce_count && !ue_count) + return 0; ce = 0; ue = 0; @@ -1061,9 +1076,11 @@ void amdgpu_ras_query_error_count(struct amdgpu_device *adev, struct ras_query_if info = { .head = obj->head, }; + int res; - if (amdgpu_ras_query_error_status(adev, &info)) - return; + res = amdgpu_ras_query_error_status(adev, &info); + if (res) + return res; ce += info.ce_count; ue += info.ue_count; @@ -1074,6 +1091,8 @@ void amdgpu_ras_query_error_count(struct amdgpu_device *adev, if (ue_count) *ue_count = ue; + + return 0; } /* query/inject/cure end */ @@ -2137,9 +2156,10 @@ static void amdgpu_ras_counte_dw(struct work_struct *work) /* Cache new values. */ - amdgpu_ras_query_error_count(adev, &ce_count, &ue_count); - atomic_set(&con->ras_ce_count, ce_count); - atomic_set(&con->ras_ue_count, ue_count); + if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) { + atomic_set(&con->ras_ce_count, ce_count); + atomic_set(&con->ras_ue_count, ue_count); + } pm_runtime_mark_last_busy(dev->dev); Out: @@ -2312,9 +2332,10 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev, /* Those are the cached values at init. */ - amdgpu_ras_query_error_count(adev, &ce_count, &ue_count); - atomic_set(&con->ras_ce_count, ce_count); - atomic_set(&con->ras_ue_count, ue_count); + if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) { + atomic_set(&con->ras_ce_count, ce_count); + atomic_set(&con->ras_ue_count, ue_count); + } return 0; cleanup: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index 256cea5d34f2..b504ed8c9b50 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -490,9 +490,9 @@ int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev, void amdgpu_ras_resume(struct amdgpu_device *adev); void amdgpu_ras_suspend(struct amdgpu_device *adev); -void amdgpu_ras_query_error_count(struct amdgpu_device *adev, - unsigned long *ce_count, - unsigned long *ue_count); +int amdgpu_ras_query_error_count(struct amdgpu_device *adev, + unsigned long *ce_count, + unsigned long *ue_count); /* error handling functions */ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, From e9cfe00ba8bd437da149a3c52712d4a73e249f45 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Wed, 16 Jun 2021 17:11:12 -0400 Subject: [PATCH 242/426] drm/amd/display: Fix updating infoframe for DCN3.1 eDP [Why] We're only treating TMDS as a valid target for infoframe updates which results in PSR being unable to transition from state 4 to state 5. [How] Also allow infoframe updates for DCN3.1 - following how we handle this path for earlier ASIC as well. Signed-off-by: Nicholas Kazlauskas Reviewed-by: Eric Yang Acked-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index fc1fc1a4bf8b..836864a5a5dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -390,7 +390,7 @@ void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx) is_hdmi_tmds = dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal); is_dp = dc_is_dp_signal(pipe_ctx->stream->signal); - if (!is_hdmi_tmds) + if (!is_hdmi_tmds && !is_dp) return; if (is_hdmi_tmds) From dce9d910eb9e54c97e830637f4e3383a11bb7556 Mon Sep 17 00:00:00 2001 From: Wesley Chalmers Date: Wed, 16 Jun 2021 16:11:23 -0400 Subject: [PATCH 243/426] Revert "drm/amd/display: Always write repeater mode regardless of LTTPR" This reverts commit 2b7605d73b97e2fa28e0817242e66ca968d2a7cb Some displays are not lighting up when put in LTTPR Transparent Mode Signed-off-by: Wesley Chalmers Reviewed-by: Jun Lei Acked-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index b8832bdde2bc..6860827159ba 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1620,11 +1620,12 @@ enum dc_status dpcd_configure_lttpr_mode(struct dc_link *link, struct link_train { enum dc_status status = DC_OK; - if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) - status = configure_lttpr_mode_non_transparent(link, lt_settings); - else + if (lt_settings->lttpr_mode == LTTPR_MODE_TRANSPARENT) status = configure_lttpr_mode_transparent(link); + else if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) + status = configure_lttpr_mode_non_transparent(link, lt_settings); + return status; } From 9849e71ac0793c956883da3ca780484d3a226316 Mon Sep 17 00:00:00 2001 From: Dmytro Laktyushkin Date: Tue, 15 Jun 2021 15:11:31 -0400 Subject: [PATCH 244/426] drm/amd/display: remove faulty assert Signed-off-by: Dmytro Laktyushkin Reviewed-by: Wenjing Liu Acked-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 6860827159ba..6da226bf11d5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1785,7 +1785,6 @@ bool perform_link_training_with_retries( link_enc = stream->link_enc; else link_enc = link->link_enc; - ASSERT(link_enc); /* We need to do this before the link training to ensure the idle pattern in SST * mode will be sent right after the link training From 21cf0293d500f198ad886cbdcd3ff65f82b35edf Mon Sep 17 00:00:00 2001 From: Xiaomeng Hou Date: Thu, 1 Jul 2021 14:09:18 +0800 Subject: [PATCH 245/426] drm/amd/pm: drop smu_v13_0_1.c|h files for yellow carp Since there's nothing special in smu implementation for yellow carp, it's better to reuse the common smu_v13_0 interfaces and drop the specific smu_v13_0_1.c|h files. v2: remove the duplicate register offset and shift mask header files as well. Signed-off-by: Xiaomeng Hou Reviewed-by: Lijo Lazar Reviewed-by: Kevin Wang Signed-off-by: Alex Deucher --- .../include/asic_reg/mp/mp_13_0_1_offset.h | 355 ------------ .../include/asic_reg/mp/mp_13_0_1_sh_mask.h | 531 ------------------ drivers/gpu/drm/amd/pm/inc/smu_v13_0.h | 1 + drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h | 57 -- drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile | 2 +- .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 24 + .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c | 311 ---------- .../drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c | 39 +- 8 files changed, 57 insertions(+), 1263 deletions(-) delete mode 100644 drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h delete mode 100644 drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h delete mode 100644 drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h delete mode 100644 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h deleted file mode 100644 index dfacc6b5d89d..000000000000 --- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h +++ /dev/null @@ -1,355 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - * - */ -#ifndef _mp_13_0_1_OFFSET_HEADER -#define _mp_13_0_1_OFFSET_HEADER - - - -// addressBlock: mp_SmuMp0_SmnDec -// base address: 0x0 -#define regMP0_SMN_C2PMSG_32 0x0060 -#define regMP0_SMN_C2PMSG_32_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_33 0x0061 -#define regMP0_SMN_C2PMSG_33_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_34 0x0062 -#define regMP0_SMN_C2PMSG_34_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_35 0x0063 -#define regMP0_SMN_C2PMSG_35_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_36 0x0064 -#define regMP0_SMN_C2PMSG_36_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_37 0x0065 -#define regMP0_SMN_C2PMSG_37_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_38 0x0066 -#define regMP0_SMN_C2PMSG_38_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_39 0x0067 -#define regMP0_SMN_C2PMSG_39_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_40 0x0068 -#define regMP0_SMN_C2PMSG_40_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_41 0x0069 -#define regMP0_SMN_C2PMSG_41_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_42 0x006a -#define regMP0_SMN_C2PMSG_42_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_43 0x006b -#define regMP0_SMN_C2PMSG_43_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_44 0x006c -#define regMP0_SMN_C2PMSG_44_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_45 0x006d -#define regMP0_SMN_C2PMSG_45_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_46 0x006e -#define regMP0_SMN_C2PMSG_46_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_47 0x006f -#define regMP0_SMN_C2PMSG_47_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_48 0x0070 -#define regMP0_SMN_C2PMSG_48_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_49 0x0071 -#define regMP0_SMN_C2PMSG_49_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_50 0x0072 -#define regMP0_SMN_C2PMSG_50_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_51 0x0073 -#define regMP0_SMN_C2PMSG_51_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_52 0x0074 -#define regMP0_SMN_C2PMSG_52_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_53 0x0075 -#define regMP0_SMN_C2PMSG_53_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_54 0x0076 -#define regMP0_SMN_C2PMSG_54_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_55 0x0077 -#define regMP0_SMN_C2PMSG_55_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_56 0x0078 -#define regMP0_SMN_C2PMSG_56_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_57 0x0079 -#define regMP0_SMN_C2PMSG_57_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_58 0x007a -#define regMP0_SMN_C2PMSG_58_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_59 0x007b -#define regMP0_SMN_C2PMSG_59_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_60 0x007c -#define regMP0_SMN_C2PMSG_60_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_61 0x007d -#define regMP0_SMN_C2PMSG_61_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_62 0x007e -#define regMP0_SMN_C2PMSG_62_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_63 0x007f -#define regMP0_SMN_C2PMSG_63_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_64 0x0080 -#define regMP0_SMN_C2PMSG_64_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_65 0x0081 -#define regMP0_SMN_C2PMSG_65_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_66 0x0082 -#define regMP0_SMN_C2PMSG_66_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_67 0x0083 -#define regMP0_SMN_C2PMSG_67_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_68 0x0084 -#define regMP0_SMN_C2PMSG_68_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_69 0x0085 -#define regMP0_SMN_C2PMSG_69_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_70 0x0086 -#define regMP0_SMN_C2PMSG_70_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_71 0x0087 -#define regMP0_SMN_C2PMSG_71_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_72 0x0088 -#define regMP0_SMN_C2PMSG_72_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_73 0x0089 -#define regMP0_SMN_C2PMSG_73_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_74 0x008a -#define regMP0_SMN_C2PMSG_74_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_75 0x008b -#define regMP0_SMN_C2PMSG_75_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_76 0x008c -#define regMP0_SMN_C2PMSG_76_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_77 0x008d -#define regMP0_SMN_C2PMSG_77_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_78 0x008e -#define regMP0_SMN_C2PMSG_78_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_79 0x008f -#define regMP0_SMN_C2PMSG_79_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_80 0x0090 -#define regMP0_SMN_C2PMSG_80_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_81 0x0091 -#define regMP0_SMN_C2PMSG_81_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_82 0x0092 -#define regMP0_SMN_C2PMSG_82_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_83 0x0093 -#define regMP0_SMN_C2PMSG_83_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_84 0x0094 -#define regMP0_SMN_C2PMSG_84_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_85 0x0095 -#define regMP0_SMN_C2PMSG_85_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_86 0x0096 -#define regMP0_SMN_C2PMSG_86_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_87 0x0097 -#define regMP0_SMN_C2PMSG_87_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_88 0x0098 -#define regMP0_SMN_C2PMSG_88_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_89 0x0099 -#define regMP0_SMN_C2PMSG_89_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_90 0x009a -#define regMP0_SMN_C2PMSG_90_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_91 0x009b -#define regMP0_SMN_C2PMSG_91_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_92 0x009c -#define regMP0_SMN_C2PMSG_92_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_93 0x009d -#define regMP0_SMN_C2PMSG_93_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_94 0x009e -#define regMP0_SMN_C2PMSG_94_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_95 0x009f -#define regMP0_SMN_C2PMSG_95_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_96 0x00a0 -#define regMP0_SMN_C2PMSG_96_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_97 0x00a1 -#define regMP0_SMN_C2PMSG_97_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_98 0x00a2 -#define regMP0_SMN_C2PMSG_98_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_99 0x00a3 -#define regMP0_SMN_C2PMSG_99_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_100 0x00a4 -#define regMP0_SMN_C2PMSG_100_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_101 0x00a5 -#define regMP0_SMN_C2PMSG_101_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_102 0x00a6 -#define regMP0_SMN_C2PMSG_102_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_103 0x00a7 -#define regMP0_SMN_C2PMSG_103_BASE_IDX 0 -#define regMP0_SMN_IH_CREDIT 0x00c1 -#define regMP0_SMN_IH_CREDIT_BASE_IDX 0 -#define regMP0_SMN_IH_SW_INT 0x00c2 -#define regMP0_SMN_IH_SW_INT_BASE_IDX 0 -#define regMP0_SMN_IH_SW_INT_CTRL 0x00c3 -#define regMP0_SMN_IH_SW_INT_CTRL_BASE_IDX 0 - - -// addressBlock: mp_SmuMp1_SmnDec -// base address: 0x0 -#define regMP1_SMN_C2PMSG_32 0x0260 -#define regMP1_SMN_C2PMSG_32_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_33 0x0261 -#define regMP1_SMN_C2PMSG_33_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_34 0x0262 -#define regMP1_SMN_C2PMSG_34_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_35 0x0263 -#define regMP1_SMN_C2PMSG_35_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_36 0x0264 -#define regMP1_SMN_C2PMSG_36_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_37 0x0265 -#define regMP1_SMN_C2PMSG_37_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_38 0x0266 -#define regMP1_SMN_C2PMSG_38_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_39 0x0267 -#define regMP1_SMN_C2PMSG_39_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_40 0x0268 -#define regMP1_SMN_C2PMSG_40_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_41 0x0269 -#define regMP1_SMN_C2PMSG_41_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_42 0x026a -#define regMP1_SMN_C2PMSG_42_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_43 0x026b -#define regMP1_SMN_C2PMSG_43_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_44 0x026c -#define regMP1_SMN_C2PMSG_44_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_45 0x026d -#define regMP1_SMN_C2PMSG_45_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_46 0x026e -#define regMP1_SMN_C2PMSG_46_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_47 0x026f -#define regMP1_SMN_C2PMSG_47_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_48 0x0270 -#define regMP1_SMN_C2PMSG_48_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_49 0x0271 -#define regMP1_SMN_C2PMSG_49_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_50 0x0272 -#define regMP1_SMN_C2PMSG_50_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_51 0x0273 -#define regMP1_SMN_C2PMSG_51_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_52 0x0274 -#define regMP1_SMN_C2PMSG_52_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_53 0x0275 -#define regMP1_SMN_C2PMSG_53_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_54 0x0276 -#define regMP1_SMN_C2PMSG_54_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_55 0x0277 -#define regMP1_SMN_C2PMSG_55_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_56 0x0278 -#define regMP1_SMN_C2PMSG_56_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_57 0x0279 -#define regMP1_SMN_C2PMSG_57_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_58 0x027a -#define regMP1_SMN_C2PMSG_58_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_59 0x027b -#define regMP1_SMN_C2PMSG_59_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_60 0x027c -#define regMP1_SMN_C2PMSG_60_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_61 0x027d -#define regMP1_SMN_C2PMSG_61_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_62 0x027e -#define regMP1_SMN_C2PMSG_62_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_63 0x027f -#define regMP1_SMN_C2PMSG_63_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_64 0x0280 -#define regMP1_SMN_C2PMSG_64_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_65 0x0281 -#define regMP1_SMN_C2PMSG_65_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_66 0x0282 -#define regMP1_SMN_C2PMSG_66_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_67 0x0283 -#define regMP1_SMN_C2PMSG_67_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_68 0x0284 -#define regMP1_SMN_C2PMSG_68_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_69 0x0285 -#define regMP1_SMN_C2PMSG_69_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_70 0x0286 -#define regMP1_SMN_C2PMSG_70_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_71 0x0287 -#define regMP1_SMN_C2PMSG_71_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_72 0x0288 -#define regMP1_SMN_C2PMSG_72_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_73 0x0289 -#define regMP1_SMN_C2PMSG_73_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_74 0x028a -#define regMP1_SMN_C2PMSG_74_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_75 0x028b -#define regMP1_SMN_C2PMSG_75_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_76 0x028c -#define regMP1_SMN_C2PMSG_76_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_77 0x028d -#define regMP1_SMN_C2PMSG_77_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_78 0x028e -#define regMP1_SMN_C2PMSG_78_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_79 0x028f -#define regMP1_SMN_C2PMSG_79_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_80 0x0290 -#define regMP1_SMN_C2PMSG_80_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_81 0x0291 -#define regMP1_SMN_C2PMSG_81_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_82 0x0292 -#define regMP1_SMN_C2PMSG_82_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_83 0x0293 -#define regMP1_SMN_C2PMSG_83_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_84 0x0294 -#define regMP1_SMN_C2PMSG_84_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_85 0x0295 -#define regMP1_SMN_C2PMSG_85_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_86 0x0296 -#define regMP1_SMN_C2PMSG_86_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_87 0x0297 -#define regMP1_SMN_C2PMSG_87_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_88 0x0298 -#define regMP1_SMN_C2PMSG_88_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_89 0x0299 -#define regMP1_SMN_C2PMSG_89_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_90 0x029a -#define regMP1_SMN_C2PMSG_90_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_91 0x029b -#define regMP1_SMN_C2PMSG_91_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_92 0x029c -#define regMP1_SMN_C2PMSG_92_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_93 0x029d -#define regMP1_SMN_C2PMSG_93_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_94 0x029e -#define regMP1_SMN_C2PMSG_94_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_95 0x029f -#define regMP1_SMN_C2PMSG_95_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_96 0x02a0 -#define regMP1_SMN_C2PMSG_96_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_97 0x02a1 -#define regMP1_SMN_C2PMSG_97_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_98 0x02a2 -#define regMP1_SMN_C2PMSG_98_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_99 0x02a3 -#define regMP1_SMN_C2PMSG_99_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_100 0x02a4 -#define regMP1_SMN_C2PMSG_100_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_101 0x02a5 -#define regMP1_SMN_C2PMSG_101_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_102 0x02a6 -#define regMP1_SMN_C2PMSG_102_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_103 0x02a7 -#define regMP1_SMN_C2PMSG_103_BASE_IDX 0 -#define regMP1_SMN_IH_CREDIT 0x02c1 -#define regMP1_SMN_IH_CREDIT_BASE_IDX 0 -#define regMP1_SMN_IH_SW_INT 0x02c2 -#define regMP1_SMN_IH_SW_INT_BASE_IDX 0 -#define regMP1_SMN_IH_SW_INT_CTRL 0x02c3 -#define regMP1_SMN_IH_SW_INT_CTRL_BASE_IDX 0 -#define regMP1_SMN_FPS_CNT 0x02c4 -#define regMP1_SMN_FPS_CNT_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH0 0x0340 -#define regMP1_SMN_EXT_SCRATCH0_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH1 0x0341 -#define regMP1_SMN_EXT_SCRATCH1_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH2 0x0342 -#define regMP1_SMN_EXT_SCRATCH2_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH3 0x0343 -#define regMP1_SMN_EXT_SCRATCH3_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH4 0x0344 -#define regMP1_SMN_EXT_SCRATCH4_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH5 0x0345 -#define regMP1_SMN_EXT_SCRATCH5_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH6 0x0346 -#define regMP1_SMN_EXT_SCRATCH6_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH7 0x0347 -#define regMP1_SMN_EXT_SCRATCH7_BASE_IDX 0 - - -#endif diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h deleted file mode 100644 index 2d5e8b58e693..000000000000 --- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h +++ /dev/null @@ -1,531 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - * - */ -#ifndef _mp_13_0_1_SH_MASK_HEADER -#define _mp_13_0_1_SH_MASK_HEADER - - -// addressBlock: mp_SmuMp0_SmnDec -//MP0_SMN_C2PMSG_32 -#define MP0_SMN_C2PMSG_32__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_32__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_33 -#define MP0_SMN_C2PMSG_33__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_33__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_34 -#define MP0_SMN_C2PMSG_34__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_34__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_35 -#define MP0_SMN_C2PMSG_35__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_35__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_36 -#define MP0_SMN_C2PMSG_36__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_36__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_37 -#define MP0_SMN_C2PMSG_37__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_37__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_38 -#define MP0_SMN_C2PMSG_38__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_38__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_39 -#define MP0_SMN_C2PMSG_39__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_39__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_40 -#define MP0_SMN_C2PMSG_40__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_40__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_41 -#define MP0_SMN_C2PMSG_41__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_41__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_42 -#define MP0_SMN_C2PMSG_42__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_42__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_43 -#define MP0_SMN_C2PMSG_43__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_43__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_44 -#define MP0_SMN_C2PMSG_44__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_44__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_45 -#define MP0_SMN_C2PMSG_45__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_45__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_46 -#define MP0_SMN_C2PMSG_46__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_46__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_47 -#define MP0_SMN_C2PMSG_47__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_47__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_48 -#define MP0_SMN_C2PMSG_48__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_48__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_49 -#define MP0_SMN_C2PMSG_49__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_49__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_50 -#define MP0_SMN_C2PMSG_50__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_50__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_51 -#define MP0_SMN_C2PMSG_51__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_51__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_52 -#define MP0_SMN_C2PMSG_52__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_52__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_53 -#define MP0_SMN_C2PMSG_53__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_53__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_54 -#define MP0_SMN_C2PMSG_54__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_54__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_55 -#define MP0_SMN_C2PMSG_55__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_55__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_56 -#define MP0_SMN_C2PMSG_56__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_56__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_57 -#define MP0_SMN_C2PMSG_57__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_57__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_58 -#define MP0_SMN_C2PMSG_58__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_58__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_59 -#define MP0_SMN_C2PMSG_59__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_59__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_60 -#define MP0_SMN_C2PMSG_60__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_60__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_61 -#define MP0_SMN_C2PMSG_61__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_61__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_62 -#define MP0_SMN_C2PMSG_62__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_62__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_63 -#define MP0_SMN_C2PMSG_63__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_63__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_64 -#define MP0_SMN_C2PMSG_64__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_64__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_65 -#define MP0_SMN_C2PMSG_65__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_65__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_66 -#define MP0_SMN_C2PMSG_66__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_66__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_67 -#define MP0_SMN_C2PMSG_67__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_67__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_68 -#define MP0_SMN_C2PMSG_68__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_68__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_69 -#define MP0_SMN_C2PMSG_69__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_69__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_70 -#define MP0_SMN_C2PMSG_70__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_70__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_71 -#define MP0_SMN_C2PMSG_71__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_71__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_72 -#define MP0_SMN_C2PMSG_72__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_72__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_73 -#define MP0_SMN_C2PMSG_73__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_73__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_74 -#define MP0_SMN_C2PMSG_74__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_74__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_75 -#define MP0_SMN_C2PMSG_75__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_75__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_76 -#define MP0_SMN_C2PMSG_76__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_76__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_77 -#define MP0_SMN_C2PMSG_77__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_77__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_78 -#define MP0_SMN_C2PMSG_78__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_78__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_79 -#define MP0_SMN_C2PMSG_79__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_79__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_80 -#define MP0_SMN_C2PMSG_80__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_80__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_81 -#define MP0_SMN_C2PMSG_81__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_81__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_82 -#define MP0_SMN_C2PMSG_82__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_82__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_83 -#define MP0_SMN_C2PMSG_83__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_83__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_84 -#define MP0_SMN_C2PMSG_84__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_84__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_85 -#define MP0_SMN_C2PMSG_85__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_85__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_86 -#define MP0_SMN_C2PMSG_86__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_86__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_87 -#define MP0_SMN_C2PMSG_87__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_87__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_88 -#define MP0_SMN_C2PMSG_88__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_88__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_89 -#define MP0_SMN_C2PMSG_89__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_89__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_90 -#define MP0_SMN_C2PMSG_90__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_90__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_91 -#define MP0_SMN_C2PMSG_91__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_91__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_92 -#define MP0_SMN_C2PMSG_92__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_92__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_93 -#define MP0_SMN_C2PMSG_93__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_93__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_94 -#define MP0_SMN_C2PMSG_94__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_94__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_95 -#define MP0_SMN_C2PMSG_95__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_95__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_96 -#define MP0_SMN_C2PMSG_96__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_96__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_97 -#define MP0_SMN_C2PMSG_97__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_97__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_98 -#define MP0_SMN_C2PMSG_98__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_98__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_99 -#define MP0_SMN_C2PMSG_99__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_99__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_100 -#define MP0_SMN_C2PMSG_100__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_100__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_101 -#define MP0_SMN_C2PMSG_101__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_101__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_102 -#define MP0_SMN_C2PMSG_102__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_102__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_103 -#define MP0_SMN_C2PMSG_103__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_103__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_IH_CREDIT -#define MP0_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT 0x0 -#define MP0_SMN_IH_CREDIT__CLIENT_ID__SHIFT 0x10 -#define MP0_SMN_IH_CREDIT__CREDIT_VALUE_MASK 0x00000003L -#define MP0_SMN_IH_CREDIT__CLIENT_ID_MASK 0x00FF0000L -//MP0_SMN_IH_SW_INT -#define MP0_SMN_IH_SW_INT__ID__SHIFT 0x0 -#define MP0_SMN_IH_SW_INT__VALID__SHIFT 0x8 -#define MP0_SMN_IH_SW_INT__ID_MASK 0x000000FFL -#define MP0_SMN_IH_SW_INT__VALID_MASK 0x00000100L -//MP0_SMN_IH_SW_INT_CTRL -#define MP0_SMN_IH_SW_INT_CTRL__INT_MASK__SHIFT 0x0 -#define MP0_SMN_IH_SW_INT_CTRL__INT_ACK__SHIFT 0x8 -#define MP0_SMN_IH_SW_INT_CTRL__INT_MASK_MASK 0x00000001L -#define MP0_SMN_IH_SW_INT_CTRL__INT_ACK_MASK 0x00000100L - - -// addressBlock: mp_SmuMp1Pub_CruDec -//MP1_FIRMWARE_FLAGS -#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT 0x0 -#define MP1_FIRMWARE_FLAGS__RESERVED__SHIFT 0x1 -#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK 0x00000001L -#define MP1_FIRMWARE_FLAGS__RESERVED_MASK 0xFFFFFFFEL - - -// addressBlock: mp_SmuMp1_SmnDec -//MP1_SMN_C2PMSG_32 -#define MP1_SMN_C2PMSG_32__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_32__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_33 -#define MP1_SMN_C2PMSG_33__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_33__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_34 -#define MP1_SMN_C2PMSG_34__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_34__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_35 -#define MP1_SMN_C2PMSG_35__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_35__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_36 -#define MP1_SMN_C2PMSG_36__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_36__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_37 -#define MP1_SMN_C2PMSG_37__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_37__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_38 -#define MP1_SMN_C2PMSG_38__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_38__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_39 -#define MP1_SMN_C2PMSG_39__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_39__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_40 -#define MP1_SMN_C2PMSG_40__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_40__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_41 -#define MP1_SMN_C2PMSG_41__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_41__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_42 -#define MP1_SMN_C2PMSG_42__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_42__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_43 -#define MP1_SMN_C2PMSG_43__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_43__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_44 -#define MP1_SMN_C2PMSG_44__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_44__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_45 -#define MP1_SMN_C2PMSG_45__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_45__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_46 -#define MP1_SMN_C2PMSG_46__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_46__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_47 -#define MP1_SMN_C2PMSG_47__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_47__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_48 -#define MP1_SMN_C2PMSG_48__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_48__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_49 -#define MP1_SMN_C2PMSG_49__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_49__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_50 -#define MP1_SMN_C2PMSG_50__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_50__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_51 -#define MP1_SMN_C2PMSG_51__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_51__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_52 -#define MP1_SMN_C2PMSG_52__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_52__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_53 -#define MP1_SMN_C2PMSG_53__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_53__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_54 -#define MP1_SMN_C2PMSG_54__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_54__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_55 -#define MP1_SMN_C2PMSG_55__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_55__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_56 -#define MP1_SMN_C2PMSG_56__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_56__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_57 -#define MP1_SMN_C2PMSG_57__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_57__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_58 -#define MP1_SMN_C2PMSG_58__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_58__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_59 -#define MP1_SMN_C2PMSG_59__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_59__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_60 -#define MP1_SMN_C2PMSG_60__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_60__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_61 -#define MP1_SMN_C2PMSG_61__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_61__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_62 -#define MP1_SMN_C2PMSG_62__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_62__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_63 -#define MP1_SMN_C2PMSG_63__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_63__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_64 -#define MP1_SMN_C2PMSG_64__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_64__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_65 -#define MP1_SMN_C2PMSG_65__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_65__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_66 -#define MP1_SMN_C2PMSG_66__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_66__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_67 -#define MP1_SMN_C2PMSG_67__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_67__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_68 -#define MP1_SMN_C2PMSG_68__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_68__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_69 -#define MP1_SMN_C2PMSG_69__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_69__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_70 -#define MP1_SMN_C2PMSG_70__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_70__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_71 -#define MP1_SMN_C2PMSG_71__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_71__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_72 -#define MP1_SMN_C2PMSG_72__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_72__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_73 -#define MP1_SMN_C2PMSG_73__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_73__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_74 -#define MP1_SMN_C2PMSG_74__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_74__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_75 -#define MP1_SMN_C2PMSG_75__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_75__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_76 -#define MP1_SMN_C2PMSG_76__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_76__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_77 -#define MP1_SMN_C2PMSG_77__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_77__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_78 -#define MP1_SMN_C2PMSG_78__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_78__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_79 -#define MP1_SMN_C2PMSG_79__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_79__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_80 -#define MP1_SMN_C2PMSG_80__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_80__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_81 -#define MP1_SMN_C2PMSG_81__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_81__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_82 -#define MP1_SMN_C2PMSG_82__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_82__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_83 -#define MP1_SMN_C2PMSG_83__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_83__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_84 -#define MP1_SMN_C2PMSG_84__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_84__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_85 -#define MP1_SMN_C2PMSG_85__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_85__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_86 -#define MP1_SMN_C2PMSG_86__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_86__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_87 -#define MP1_SMN_C2PMSG_87__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_87__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_88 -#define MP1_SMN_C2PMSG_88__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_88__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_89 -#define MP1_SMN_C2PMSG_89__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_89__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_90 -#define MP1_SMN_C2PMSG_90__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_90__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_91 -#define MP1_SMN_C2PMSG_91__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_91__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_92 -#define MP1_SMN_C2PMSG_92__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_92__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_93 -#define MP1_SMN_C2PMSG_93__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_93__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_94 -#define MP1_SMN_C2PMSG_94__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_94__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_95 -#define MP1_SMN_C2PMSG_95__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_95__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_96 -#define MP1_SMN_C2PMSG_96__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_96__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_97 -#define MP1_SMN_C2PMSG_97__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_97__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_98 -#define MP1_SMN_C2PMSG_98__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_98__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_99 -#define MP1_SMN_C2PMSG_99__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_99__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_100 -#define MP1_SMN_C2PMSG_100__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_100__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_101 -#define MP1_SMN_C2PMSG_101__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_101__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_102 -#define MP1_SMN_C2PMSG_102__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_102__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_103 -#define MP1_SMN_C2PMSG_103__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_103__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_IH_CREDIT -#define MP1_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT 0x0 -#define MP1_SMN_IH_CREDIT__CLIENT_ID__SHIFT 0x10 -#define MP1_SMN_IH_CREDIT__CREDIT_VALUE_MASK 0x00000003L -#define MP1_SMN_IH_CREDIT__CLIENT_ID_MASK 0x00FF0000L -//MP1_SMN_IH_SW_INT -#define MP1_SMN_IH_SW_INT__ID__SHIFT 0x0 -#define MP1_SMN_IH_SW_INT__VALID__SHIFT 0x8 -#define MP1_SMN_IH_SW_INT__ID_MASK 0x000000FFL -#define MP1_SMN_IH_SW_INT__VALID_MASK 0x00000100L -//MP1_SMN_IH_SW_INT_CTRL -#define MP1_SMN_IH_SW_INT_CTRL__INT_MASK__SHIFT 0x0 -#define MP1_SMN_IH_SW_INT_CTRL__INT_ACK__SHIFT 0x8 -#define MP1_SMN_IH_SW_INT_CTRL__INT_MASK_MASK 0x00000001L -#define MP1_SMN_IH_SW_INT_CTRL__INT_ACK_MASK 0x00000100L -//MP1_SMN_FPS_CNT -#define MP1_SMN_FPS_CNT__COUNT__SHIFT 0x0 -#define MP1_SMN_FPS_CNT__COUNT_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH0 -#define MP1_SMN_EXT_SCRATCH0__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH0__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH1 -#define MP1_SMN_EXT_SCRATCH1__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH1__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH2 -#define MP1_SMN_EXT_SCRATCH2__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH2__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH3 -#define MP1_SMN_EXT_SCRATCH3__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH3__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH4 -#define MP1_SMN_EXT_SCRATCH4__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH4__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH5 -#define MP1_SMN_EXT_SCRATCH5__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH5__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH6 -#define MP1_SMN_EXT_SCRATCH6__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH6__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH7 -#define MP1_SMN_EXT_SCRATCH7__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH7__DATA_MASK 0xFFFFFFFFL - - -#endif diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h index 6119a36b2cba..3fea2430dec0 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h @@ -26,6 +26,7 @@ #include "amdgpu_smu.h" #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF +#define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x03 #define SMU13_DRIVER_IF_VERSION_ALDE 0x07 /* MP Apertures */ diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h deleted file mode 100644 index b6c976a4d578..000000000000 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h +++ /dev/null @@ -1,57 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#ifndef __SMU_V13_0_1_H__ -#define __SMU_V13_0_1_H__ - -#include "amdgpu_smu.h" - -#define SMU13_0_1_DRIVER_IF_VERSION_INV 0xFFFFFFFF -#define SMU13_0_1_DRIVER_IF_VERSION_YELLOW_CARP 0x3 - -/* MP Apertures */ -#define MP0_Public 0x03800000 -#define MP0_SRAM 0x03900000 -#define MP1_Public 0x03b00000 -#define MP1_SRAM 0x03c00004 - -/* address block */ -#define smnMP1_FIRMWARE_FLAGS 0x3010024 - - -#if defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) - -int smu_v13_0_1_check_fw_status(struct smu_context *smu); - -int smu_v13_0_1_check_fw_version(struct smu_context *smu); - -int smu_v13_0_1_fini_smc_tables(struct smu_context *smu); - -int smu_v13_0_1_get_vbios_bootup_values(struct smu_context *smu); - -int smu_v13_0_1_set_default_dpm_tables(struct smu_context *smu); - -int smu_v13_0_1_set_driver_table_location(struct smu_context *smu); - -int smu_v13_0_1_gfx_off_control(struct smu_context *smu, bool enable); -#endif -#endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile b/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile index 9b3a8503f5cd..d4c4c495762c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'smu manager' sub-component of powerplay. # It provides the smu management services for the driver. -SMU13_MGR = smu_v13_0.o aldebaran_ppt.o smu_v13_0_1.o yellow_carp_ppt.o +SMU13_MGR = smu_v13_0.o aldebaran_ppt.o yellow_carp_ppt.o AMD_SWSMU_SMU13MGR = $(addprefix $(AMD_SWSMU_PATH)/smu13/,$(SMU13_MGR)) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index a3dc7194aaf8..a421ba85bd6d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -210,6 +210,9 @@ int smu_v13_0_check_fw_version(struct smu_context *smu) case CHIP_ALDEBARAN: smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_ALDE; break; + case CHIP_YELLOW_CARP: + smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_YELLOW_CARP; + break; default: dev_err(smu->adev->dev, "smu unsupported asic type:%d.\n", smu->adev->asic_type); smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_INV; @@ -694,6 +697,27 @@ failed: return ret; } +int smu_v13_0_gfx_off_control(struct smu_context *smu, bool enable) +{ + int ret = 0; + struct amdgpu_device *adev = smu->adev; + + switch (adev->asic_type) { + case CHIP_YELLOW_CARP: + if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) + return 0; + if (enable) + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_AllowGfxOff, NULL); + else + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DisallowGfxOff, NULL); + break; + default: + break; + } + + return ret; +} + int smu_v13_0_system_features_control(struct smu_context *smu, bool en) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c deleted file mode 100644 index 61917b49f2bf..000000000000 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c +++ /dev/null @@ -1,311 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ - -//#include - -#define SWSMU_CODE_LAYER_L3 - -#include "amdgpu.h" -#include "amdgpu_smu.h" -#include "smu_v13_0_1.h" -#include "soc15_common.h" -#include "smu_cmn.h" -#include "atomfirmware.h" -#include "amdgpu_atomfirmware.h" -#include "amdgpu_atombios.h" -#include "atom.h" - -#include "asic_reg/mp/mp_13_0_1_offset.h" -#include "asic_reg/mp/mp_13_0_1_sh_mask.h" - -/* - * DO NOT use these for err/warn/info/debug messages. - * Use dev_err, dev_warn, dev_info and dev_dbg instead. - * They are more MGPU friendly. - */ -#undef pr_err -#undef pr_warn -#undef pr_info -#undef pr_debug - -int smu_v13_0_1_check_fw_status(struct smu_context *smu) -{ - struct amdgpu_device *adev = smu->adev; - uint32_t mp1_fw_flags; - - mp1_fw_flags = RREG32_PCIE(MP1_Public | - (smnMP1_FIRMWARE_FLAGS & 0xffffffff)); - - if ((mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) >> - MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT) - return 0; - - return -EIO; -} - -int smu_v13_0_1_check_fw_version(struct smu_context *smu) -{ - uint32_t if_version = 0xff, smu_version = 0xff; - uint16_t smu_major; - uint8_t smu_minor, smu_debug; - int ret = 0; - - ret = smu_cmn_get_smc_version(smu, &if_version, &smu_version); - if (ret) - return ret; - - smu_major = (smu_version >> 16) & 0xffff; - smu_minor = (smu_version >> 8) & 0xff; - smu_debug = (smu_version >> 0) & 0xff; - - switch (smu->adev->asic_type) { - case CHIP_YELLOW_CARP: - smu->smc_driver_if_version = SMU13_0_1_DRIVER_IF_VERSION_YELLOW_CARP; - break; - - default: - dev_err(smu->adev->dev, "smu unsupported asic type:%d.\n", smu->adev->asic_type); - smu->smc_driver_if_version = SMU13_0_1_DRIVER_IF_VERSION_INV; - break; - } - - dev_info(smu->adev->dev, "smu fw reported version = 0x%08x (%d.%d.%d)\n", - smu_version, smu_major, smu_minor, smu_debug); - - /* - * 1. if_version mismatch is not critical as our fw is designed - * to be backward compatible. - * 2. New fw usually brings some optimizations. But that's visible - * only on the paired driver. - * Considering above, we just leave user a warning message instead - * of halt driver loading. - */ - if (if_version != smu->smc_driver_if_version) { - dev_info(smu->adev->dev, "smu driver if version = 0x%08x, smu fw if version = 0x%08x, " - "smu fw version = 0x%08x (%d.%d.%d)\n", - smu->smc_driver_if_version, if_version, - smu_version, smu_major, smu_minor, smu_debug); - dev_warn(smu->adev->dev, "SMU driver if version not matched\n"); - } - - return ret; -} - -int smu_v13_0_1_fini_smc_tables(struct smu_context *smu) -{ - struct smu_table_context *smu_table = &smu->smu_table; - - kfree(smu_table->clocks_table); - smu_table->clocks_table = NULL; - - kfree(smu_table->metrics_table); - smu_table->metrics_table = NULL; - - kfree(smu_table->watermarks_table); - smu_table->watermarks_table = NULL; - - return 0; -} - -static int smu_v13_0_1_atom_get_smu_clockinfo(struct amdgpu_device *adev, - uint8_t clk_id, - uint8_t syspll_id, - uint32_t *clk_freq) -{ - struct atom_get_smu_clock_info_parameters_v3_1 input = {0}; - struct atom_get_smu_clock_info_output_parameters_v3_1 *output; - int ret, index; - - input.clk_id = clk_id; - input.syspll_id = syspll_id; - input.command = GET_SMU_CLOCK_INFO_V3_1_GET_CLOCK_FREQ; - index = get_index_into_master_table(atom_master_list_of_command_functions_v2_1, - getsmuclockinfo); - - ret = amdgpu_atom_execute_table(adev->mode_info.atom_context, index, - (uint32_t *)&input); - if (ret) - return -EINVAL; - - output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)&input; - *clk_freq = le32_to_cpu(output->atom_smu_outputclkfreq.smu_clock_freq_hz) / 10000; - - return 0; -} - -int smu_v13_0_1_get_vbios_bootup_values(struct smu_context *smu) -{ - int ret, index; - uint16_t size; - uint8_t frev, crev; - struct atom_common_table_header *header; - struct atom_firmware_info_v3_4 *v_3_4; - struct atom_firmware_info_v3_3 *v_3_3; - struct atom_firmware_info_v3_1 *v_3_1; - - index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, - firmwareinfo); - - ret = amdgpu_atombios_get_data_table(smu->adev, index, &size, &frev, &crev, - (uint8_t **)&header); - if (ret) - return ret; - - if (header->format_revision != 3) { - dev_err(smu->adev->dev, "unknown atom_firmware_info version! for smu13\n"); - return -EINVAL; - } - - switch (header->content_revision) { - case 0: - case 1: - case 2: - v_3_1 = (struct atom_firmware_info_v3_1 *)header; - smu->smu_table.boot_values.revision = v_3_1->firmware_revision; - smu->smu_table.boot_values.gfxclk = v_3_1->bootup_sclk_in10khz; - smu->smu_table.boot_values.uclk = v_3_1->bootup_mclk_in10khz; - smu->smu_table.boot_values.socclk = 0; - smu->smu_table.boot_values.dcefclk = 0; - smu->smu_table.boot_values.vddc = v_3_1->bootup_vddc_mv; - smu->smu_table.boot_values.vddci = v_3_1->bootup_vddci_mv; - smu->smu_table.boot_values.mvddc = v_3_1->bootup_mvddc_mv; - smu->smu_table.boot_values.vdd_gfx = v_3_1->bootup_vddgfx_mv; - smu->smu_table.boot_values.cooling_id = v_3_1->coolingsolution_id; - break; - case 3: - v_3_3 = (struct atom_firmware_info_v3_3 *)header; - smu->smu_table.boot_values.revision = v_3_3->firmware_revision; - smu->smu_table.boot_values.gfxclk = v_3_3->bootup_sclk_in10khz; - smu->smu_table.boot_values.uclk = v_3_3->bootup_mclk_in10khz; - smu->smu_table.boot_values.socclk = 0; - smu->smu_table.boot_values.dcefclk = 0; - smu->smu_table.boot_values.vddc = v_3_3->bootup_vddc_mv; - smu->smu_table.boot_values.vddci = v_3_3->bootup_vddci_mv; - smu->smu_table.boot_values.mvddc = v_3_3->bootup_mvddc_mv; - smu->smu_table.boot_values.vdd_gfx = v_3_3->bootup_vddgfx_mv; - smu->smu_table.boot_values.cooling_id = v_3_3->coolingsolution_id; - break; - case 4: - default: - v_3_4 = (struct atom_firmware_info_v3_4 *)header; - smu->smu_table.boot_values.revision = v_3_4->firmware_revision; - smu->smu_table.boot_values.gfxclk = v_3_4->bootup_sclk_in10khz; - smu->smu_table.boot_values.uclk = v_3_4->bootup_mclk_in10khz; - smu->smu_table.boot_values.socclk = 0; - smu->smu_table.boot_values.dcefclk = 0; - smu->smu_table.boot_values.vddc = v_3_4->bootup_vddc_mv; - smu->smu_table.boot_values.vddci = v_3_4->bootup_vddci_mv; - smu->smu_table.boot_values.mvddc = v_3_4->bootup_mvddc_mv; - smu->smu_table.boot_values.vdd_gfx = v_3_4->bootup_vddgfx_mv; - smu->smu_table.boot_values.cooling_id = v_3_4->coolingsolution_id; - break; - } - - smu->smu_table.boot_values.format_revision = header->format_revision; - smu->smu_table.boot_values.content_revision = header->content_revision; - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_SOCCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.socclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_DCEFCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.dcefclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_ECLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.eclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_VCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.vclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_DCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.dclk); - - if ((smu->smu_table.boot_values.format_revision == 3) && - (smu->smu_table.boot_values.content_revision >= 2)) - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL1_0_FCLK_ID, - (uint8_t)SMU11_SYSPLL1_2_ID, - &smu->smu_table.boot_values.fclk); - - return 0; -} - -int smu_v13_0_1_set_default_dpm_tables(struct smu_context *smu) -{ - struct smu_table_context *smu_table = &smu->smu_table; - - return smu_cmn_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false); -} - -int smu_v13_0_1_set_driver_table_location(struct smu_context *smu) -{ - struct smu_table *driver_table = &smu->smu_table.driver_table; - int ret = 0; - - if (!driver_table->mc_address) - return 0; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_SetDriverDramAddrHigh, - upper_32_bits(driver_table->mc_address), - NULL); - - if (ret) - return ret; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_SetDriverDramAddrLow, - lower_32_bits(driver_table->mc_address), - NULL); - - return ret; -} - -int smu_v13_0_1_gfx_off_control(struct smu_context *smu, bool enable) -{ - int ret = 0; - struct amdgpu_device *adev = smu->adev; - - switch (adev->asic_type) { - case CHIP_YELLOW_CARP: - if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) - return 0; - if (enable) - ret = smu_cmn_send_smc_msg(smu, SMU_MSG_AllowGfxOff, NULL); - else - ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DisallowGfxOff, NULL); - break; - default: - break; - } - - return ret; -} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index 18a1ffdca227..de92f713a911 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -25,7 +25,7 @@ #include "amdgpu.h" #include "amdgpu_smu.h" -#include "smu_v13_0_1.h" +#include "smu_v13_0.h" #include "smu13_driver_if_yellow_carp.h" #include "yellow_carp_ppt.h" #include "smu_v13_0_1_ppsmc.h" @@ -186,6 +186,22 @@ err0_out: return -ENOMEM; } +static int yellow_carp_fini_smc_tables(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + + kfree(smu_table->clocks_table); + smu_table->clocks_table = NULL; + + kfree(smu_table->metrics_table); + smu_table->metrics_table = NULL; + + kfree(smu_table->watermarks_table); + smu_table->watermarks_table = NULL; + + return 0; +} + static int yellow_carp_system_features_control(struct smu_context *smu, bool en) { struct smu_feature *feature = &smu->smu_feature; @@ -659,6 +675,13 @@ static ssize_t yellow_carp_get_gpu_metrics(struct smu_context *smu, return sizeof(struct gpu_metrics_v2_1); } +static int yellow_carp_set_default_dpm_tables(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + + return smu_cmn_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false); +} + static int yellow_carp_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABLE_COMMAND type, long input[], uint32_t size) { @@ -1203,17 +1226,17 @@ static int yellow_carp_set_fine_grain_gfx_freq_parameters(struct smu_context *sm } static const struct pptable_funcs yellow_carp_ppt_funcs = { - .check_fw_status = smu_v13_0_1_check_fw_status, - .check_fw_version = smu_v13_0_1_check_fw_version, + .check_fw_status = smu_v13_0_check_fw_status, + .check_fw_version = smu_v13_0_check_fw_version, .init_smc_tables = yellow_carp_init_smc_tables, - .fini_smc_tables = smu_v13_0_1_fini_smc_tables, - .get_vbios_bootup_values = smu_v13_0_1_get_vbios_bootup_values, + .fini_smc_tables = yellow_carp_fini_smc_tables, + .get_vbios_bootup_values = smu_v13_0_get_vbios_bootup_values, .system_features_control = yellow_carp_system_features_control, .send_smc_msg_with_param = smu_cmn_send_smc_msg_with_param, .send_smc_msg = smu_cmn_send_smc_msg, .dpm_set_vcn_enable = yellow_carp_dpm_set_vcn_enable, .dpm_set_jpeg_enable = yellow_carp_dpm_set_jpeg_enable, - .set_default_dpm_table = smu_v13_0_1_set_default_dpm_tables, + .set_default_dpm_table = yellow_carp_set_default_dpm_tables, .read_sensor = yellow_carp_read_sensor, .is_dpm_running = yellow_carp_is_dpm_running, .set_watermarks_table = yellow_carp_set_watermarks_table, @@ -1222,8 +1245,8 @@ static const struct pptable_funcs yellow_carp_ppt_funcs = { .get_gpu_metrics = yellow_carp_get_gpu_metrics, .get_enabled_mask = smu_cmn_get_enabled_32_bits_mask, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, - .set_driver_table_location = smu_v13_0_1_set_driver_table_location, - .gfx_off_control = smu_v13_0_1_gfx_off_control, + .set_driver_table_location = smu_v13_0_set_driver_table_location, + .gfx_off_control = smu_v13_0_gfx_off_control, .post_init = yellow_carp_post_smu_init, .mode2_reset = yellow_carp_mode2_reset, .get_dpm_ultimate_freq = yellow_carp_get_dpm_ultimate_freq, From 834b8245d6bbd57900ca6c79d7f9e0279a8d51c2 Mon Sep 17 00:00:00 2001 From: Xiaomeng Hou Date: Wed, 7 Jul 2021 16:50:01 +0800 Subject: [PATCH 246/426] drm/amd/display: update header file name Update the register header file name. Signed-off-by: Xiaomeng Hou Reviewed-by: Aaron Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c index 66db5e988bc1..dad4a4c18bcf 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c @@ -31,8 +31,8 @@ #include "dcn31_smu.h" #include "yellow_carp_offset.h" -#include "mp/mp_13_0_1_offset.h" -#include "mp/mp_13_0_1_sh_mask.h" +#include "mp/mp_13_0_2_offset.h" +#include "mp/mp_13_0_2_sh_mask.h" #define REG(reg_name) \ (MP0_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name) From fa8f311e9e3aa1d41f31f8b28f975c65f0b25c03 Mon Sep 17 00:00:00 2001 From: Emily Deng Date: Tue, 12 May 2020 18:27:21 +0800 Subject: [PATCH 247/426] drm/amdgpu: Correct the irq numbers for virtual crtc The irq number should be decided by num_crtc, and the num_crtc could change by parameter. Signed-off-by: Emily Deng Reviewed by: Monk Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/dce_virtual.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index 33324427b555..7e0d8c092c7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -766,7 +766,7 @@ static const struct amdgpu_irq_src_funcs dce_virtual_crtc_irq_funcs = { static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev) { - adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VBLANK6 + 1; + adev->crtc_irq.num_types = adev->mode_info.num_crtc; adev->crtc_irq.funcs = &dce_virtual_crtc_irq_funcs; } From 5017bf8214d929f6ff45c46ec21cd3c1bfc03dad Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Wed, 7 Jul 2021 12:42:34 -0400 Subject: [PATCH 248/426] drm/amdkfd: handle fault counters on invalid address prange is NULL if vm fault retry on invalid address, for this case, can not use prange to get pdd, use adev to get gpuidx and then get pdd instead, then increase pdd vm fault counter. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 30 +++++++++++++++++----------- 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 9a71d8919bd6..c7b364e4a287 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -2375,21 +2375,27 @@ static bool svm_range_skip_recover(struct svm_range *prange) static void svm_range_count_fault(struct amdgpu_device *adev, struct kfd_process *p, - struct svm_range *prange, int32_t gpuidx) + int32_t gpuidx) { struct kfd_process_device *pdd; - if (gpuidx == MAX_GPU_INSTANCE) - /* fault is on different page of same range - * or fault is skipped to recover later - */ - pdd = svm_range_get_pdd_by_adev(prange, adev); - else - /* fault recovered - * or fault cannot recover because GPU no access on the range - */ - pdd = kfd_process_device_from_gpuidx(p, gpuidx); + /* fault is on different page of same range + * or fault is skipped to recover later + * or fault is on invalid virtual address + */ + if (gpuidx == MAX_GPU_INSTANCE) { + uint32_t gpuid; + int r; + r = kfd_process_gpuid_from_kgd(p, adev, &gpuid, &gpuidx); + if (r < 0) + return; + } + + /* fault is recovered + * or fault cannot recover because GPU no access on the range + */ + pdd = kfd_process_device_from_gpuidx(p, gpuidx); if (pdd) WRITE_ONCE(pdd->faults, pdd->faults + 1); } @@ -2525,7 +2531,7 @@ out_unlock_svms: mutex_unlock(&svms->lock); mmap_read_unlock(mm); - svm_range_count_fault(adev, p, prange, gpuidx); + svm_range_count_fault(adev, p, gpuidx); mmput(mm); out: From c010efb7f0bc0c3cb2cd26b000f71d4bd0c427cd Mon Sep 17 00:00:00 2001 From: Zhan Liu Date: Thu, 8 Jul 2021 00:51:52 -0400 Subject: [PATCH 249/426] drm/amdgpu/display - only update eDP's backlight level when necessary [Why] The original logic is to update eDP's backlight level on every amdgpu dm atomic commit, which causes excessive DMUB write. As a result, when playing game or moving window around, DMUB timeout and system lagging are observed. [How] We only need to update eDP's backlight level when current level doesn't match requested level. Signed-off-by: Zhan Liu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 01e1062dc235..d3a2a5ff57e9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9191,7 +9191,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) /* restore the backlight level */ - if (dm->backlight_dev) + if (dm->backlight_dev && (amdgpu_dm_backlight_get_level(dm) != dm->brightness[0])) amdgpu_dm_backlight_set_level(dm, dm->brightness[0]); #endif /* From 99e7d65cccc8f54581eb961a50da676b79c966d0 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Wed, 7 Jul 2021 17:55:55 -0400 Subject: [PATCH 250/426] drm/amdkfd: Allow CPU access for all VRAM BOs The thunk needs to mmap all BOs for CPU access to allow the debugger to access them. Invisible ones are mapped with PROT_NONE. Fixes: 71df0368e9b6 ("drm/amdgpu: Implement mmap as GEM object function") Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 3b8e1ee8c475..eb82739b3080 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1393,8 +1393,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM; alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ? - AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : - AMDGPU_GEM_CREATE_NO_CPU_ACCESS; + AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0; } else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) { domain = alloc_domain = AMDGPU_GEM_DOMAIN_GTT; alloc_flags = 0; From 9be26ddf88de5621f071a1e4f7725ce1015b5036 Mon Sep 17 00:00:00 2001 From: "Emily.Deng" Date: Thu, 1 Oct 2020 12:41:50 +0800 Subject: [PATCH 251/426] drm/amdgpu: Restore msix after FLR After FLR, the msix will be cleared, so need to re-enable it. Signed-off-by: Peng Ju Zhou Signed-off-by: Emily.Deng Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 32ce0e679dc7..83af307e97cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -278,6 +278,21 @@ static bool amdgpu_msi_ok(struct amdgpu_device *adev) return true; } +static void amdgpu_restore_msix(struct amdgpu_device *adev) +{ + u16 ctrl; + + pci_read_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, &ctrl); + if (!(ctrl & PCI_MSIX_FLAGS_ENABLE)) + return; + + /* VF FLR */ + ctrl &= ~PCI_MSIX_FLAGS_ENABLE; + pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl); + ctrl |= PCI_MSIX_FLAGS_ENABLE; + pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl); +} + /** * amdgpu_irq_init - initialize interrupt handling * @@ -569,6 +584,9 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev) { int i, j, k; + if (amdgpu_sriov_vf(adev)) + amdgpu_restore_msix(adev); + for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) { if (!adev->irq.client[i].sources) continue; From 06055d2e1ce83ba02b0073ff6f4fdb883fdb05c0 Mon Sep 17 00:00:00 2001 From: Chengming Gui Date: Fri, 9 Jul 2021 16:23:48 +0800 Subject: [PATCH 252/426] drm/amd/pm: Fix BACO state setting for Beige_Goby Correct BACO state setting for Beige_Goby Signed-off-by: Chengming Gui Reviewed-by: Jiansong Chen Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index 388c5cb5c647..0a5d46ac9ccd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1528,6 +1528,7 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) case CHIP_SIENNA_CICHLID: case CHIP_NAVY_FLOUNDER: case CHIP_DIMGREY_CAVEFISH: + case CHIP_BEIGE_GOBY: if (amdgpu_runtime_pm == 2) ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_EnterBaco, From f5cc09acece432d536c2e62c791b52760a25fa5c Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:51:34 -0400 Subject: [PATCH 253/426] Revert "drm/amdkfd: Add memory sync before TLB flush on unmap" This reverts commit 3be4dca197010d1328df8b11febc8c40491be498. Reason for revert: it causes regressions on several Asics. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 67541c30327a..a10e3823b660 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1566,29 +1566,13 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, i, args->n_devices); goto unmap_memory_from_gpu_failed; } + kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); args->n_success = i+1; } - mutex_unlock(&p->mutex); - - err = amdgpu_amdkfd_gpuvm_sync_memory(dev->kgd, (struct kgd_mem *) mem, true); - if (err) { - pr_debug("Sync memory failed, wait interrupted by user signal\n"); - goto sync_memory_failed; - } - - /* Flush TLBs after waiting for the page table updates to complete */ - for (i = 0; i < args->n_devices; i++) { - peer = kfd_device_by_id(devices_arr[i]); - if (WARN_ON_ONCE(!peer)) - continue; - peer_pdd = kfd_get_process_device_data(peer, p); - if (WARN_ON_ONCE(!peer_pdd)) - continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); - } - kfree(devices_arr); + mutex_unlock(&p->mutex); + return 0; bind_process_to_device_failed: @@ -1596,7 +1580,6 @@ get_mem_obj_from_handle_failed: unmap_memory_from_gpu_failed: mutex_unlock(&p->mutex); copy_from_user_failed: -sync_memory_failed: kfree(devices_arr); return err; } From 22762e376612be51a47c96d977bdc103c7a4436c Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:55:03 -0400 Subject: [PATCH 254/426] Revert "drm/amdgpu: Fix warning of Function parameter or member not described" This reverts commit 7a68d188d1c4a9d947369acaa19040a58baaaeda. Reason for revert: the related commit is reverted. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 79cfa2d68487..6b43ebab68a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1816,7 +1816,6 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, * @adev: amdgpu_device pointer * @bo_va: requested BO and VM object * @clear: if true clear the entries - * @table_freed: return true if page table is freed * * Fill in the page table entries for @bo_va. * From c37387c354c81eaf17bdc463727dcad1c951c0db Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:57:11 -0400 Subject: [PATCH 255/426] Revert "drm/amdkfd: Make TLB flush conditional on mapping" This reverts commit 31f33243788dcbae8bd2819ed83923a73f7dfd30. Reason for revert: it causes regressions on several Asics. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 2 +- .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 19 +++++++-------- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 23 ++++++++----------- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 3 +-- 4 files changed, 20 insertions(+), 27 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index db16b3e83694..cf62f43a03da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -269,7 +269,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, uint64_t *size); int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( - struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, bool *table_freed); + struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_sync_memory( diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index eb82739b3080..4fb15750b9bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1057,8 +1057,7 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem, static int update_gpuvm_pte(struct kgd_mem *mem, struct kfd_mem_attachment *entry, - struct amdgpu_sync *sync, - bool *table_freed) + struct amdgpu_sync *sync) { struct amdgpu_bo_va *bo_va = entry->bo_va; struct amdgpu_device *adev = entry->adev; @@ -1069,7 +1068,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem, return ret; /* Update the page tables */ - ret = amdgpu_vm_bo_update(adev, bo_va, false, table_freed); + ret = amdgpu_vm_bo_update(adev, bo_va, false); if (ret) { pr_err("amdgpu_vm_bo_update failed\n"); return ret; @@ -1081,8 +1080,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem, static int map_bo_to_gpuvm(struct kgd_mem *mem, struct kfd_mem_attachment *entry, struct amdgpu_sync *sync, - bool no_update_pte, - bool *table_freed) + bool no_update_pte) { int ret; @@ -1099,7 +1097,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem, if (no_update_pte) return 0; - ret = update_gpuvm_pte(mem, entry, sync, table_freed); + ret = update_gpuvm_pte(mem, entry, sync); if (ret) { pr_err("update_gpuvm_pte() failed\n"); goto update_gpuvm_pte_failed; @@ -1596,8 +1594,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( } int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( - struct kgd_dev *kgd, struct kgd_mem *mem, - void *drm_priv, bool *table_freed) + struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv) { struct amdgpu_device *adev = get_amdgpu_device(kgd); struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv); @@ -1685,7 +1682,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( entry->va, entry->va + bo_size, entry); ret = map_bo_to_gpuvm(mem, entry, ctx.sync, - is_invalid_userptr, table_freed); + is_invalid_userptr); if (ret) { pr_err("Failed to map bo to gpuvm\n"); goto out_unreserve; @@ -2135,7 +2132,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) continue; kfd_mem_dmaunmap_attachment(mem, attachment); - ret = update_gpuvm_pte(mem, attachment, &sync, NULL); + ret = update_gpuvm_pte(mem, attachment, &sync); if (ret) { pr_err("%s: update PTE failed\n", __func__); /* make sure this gets validated again */ @@ -2341,7 +2338,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) continue; kfd_mem_dmaunmap_attachment(mem, attachment); - ret = update_gpuvm_pte(mem, attachment, &sync_obj, NULL); + ret = update_gpuvm_pte(mem, attachment, &sync_obj); if (ret) { pr_debug("Memory eviction: update PTE failed. Try again\n"); goto validate_map_fail; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index a10e3823b660..84894cd81ced 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1393,7 +1393,6 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, long err = 0; int i; uint32_t *devices_arr = NULL; - bool table_freed = false; dev = kfd_device_by_id(GET_GPU_ID(args->handle)); if (!dev) @@ -1451,8 +1450,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, goto get_mem_obj_from_handle_failed; } err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu( - peer->kgd, (struct kgd_mem *)mem, - peer_pdd->drm_priv, &table_freed); + peer->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv); if (err) { pr_err("Failed to map to gpu %d/%d\n", i, args->n_devices); @@ -1470,17 +1468,16 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, } /* Flush TLBs after waiting for the page table updates to complete */ - if (table_freed) { - for (i = 0; i < args->n_devices; i++) { - peer = kfd_device_by_id(devices_arr[i]); - if (WARN_ON_ONCE(!peer)) - continue; - peer_pdd = kfd_get_process_device_data(peer, p); - if (WARN_ON_ONCE(!peer_pdd)) - continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); - } + for (i = 0; i < args->n_devices; i++) { + peer = kfd_device_by_id(devices_arr[i]); + if (WARN_ON_ONCE(!peer)) + continue; + peer_pdd = kfd_get_process_device_data(peer, p); + if (WARN_ON_ONCE(!peer_pdd)) + continue; + kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); } + kfree(devices_arr); return err; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 21ec8a18cad2..8a2c6fc438c0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -714,8 +714,7 @@ static int kfd_process_alloc_gpuvm(struct kfd_process_device *pdd, if (err) goto err_alloc_mem; - err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, - pdd->drm_priv, NULL); + err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, pdd->drm_priv); if (err) goto err_map_mem; From d605094394ee35afd22f8adbe4a4b7b5f0c143a2 Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:58:16 -0400 Subject: [PATCH 256/426] Revert "drm/amdgpu: Add table_freed parameter to amdgpu_vm_bo_update" This reverts commit 075e8080c1a7571563171a07fa9ce47c4bc80044. Reason for revert: the related commit is reverted. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 10 +++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 76fe5b71e35d..30fa1f61e0e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -781,7 +781,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false, NULL); + r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false); if (r) return r; @@ -792,7 +792,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) { bo_va = fpriv->csa_va; BUG_ON(!bo_va); - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; @@ -811,7 +811,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (bo_va == NULL) continue; - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index b3404c43a911..d0d9bc445d7b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -612,7 +612,7 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, if (operation == AMDGPU_VA_OP_MAP || operation == AMDGPU_VA_OP_REPLACE) { - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) goto error; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 6b43ebab68a1..078c068937fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1758,7 +1758,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit(¶ms, fence); if (table_freed) - *table_freed = *table_freed || params.table_freed; + *table_freed = params.table_freed; error_unlock: amdgpu_vm_eviction_unlock(vm); @@ -1823,7 +1823,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, * 0 for success, -EINVAL for failure. */ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, - bool clear, bool *table_freed) + bool clear) { struct amdgpu_bo *bo = bo_va->base.bo; struct amdgpu_vm *vm = bo_va->base.vm; @@ -1902,7 +1902,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, resv, mapping->start, mapping->last, update_flags, mapping->offset, mem, - pages_addr, last_update, table_freed); + pages_addr, last_update, NULL); if (r) return r; } @@ -2154,7 +2154,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) { /* Per VM BOs never need to bo cleared in the page tables */ - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; } @@ -2173,7 +2173,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, else clear = true; - r = amdgpu_vm_bo_update(adev, bo_va, clear, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, clear); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index ddb85a85cbba..f8fa653d4da7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -406,7 +406,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, struct dma_fence **fence, bool *free_table); int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, - bool clear, bool *table_freed); + bool clear); bool amdgpu_vm_evictable(struct amdgpu_bo *bo); void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, struct amdgpu_bo *bo, bool evicted); From 5adcd7458a78120dddec6b53c9619acd8f4d5931 Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Fri, 9 Jul 2021 14:59:20 -0400 Subject: [PATCH 257/426] Revert "drm/amdkfd: Add heavy-weight TLB flush after unmapping" This reverts commit 1098d658bef05e5fee634aab0b6a1fa590cfca24. Reason for revert: it causes regressions on several Asics. Signed-off-by: Eric Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 84894cd81ced..e48acdd03c1a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1563,7 +1563,6 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, i, args->n_devices); goto unmap_memory_from_gpu_failed; } - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); args->n_success = i+1; } kfree(devices_arr); From adefab4ef308f43c80537bd28e059eed7f3517e4 Mon Sep 17 00:00:00 2001 From: Aaron Liu Date: Tue, 13 Jul 2021 14:54:47 +0800 Subject: [PATCH 258/426] drm/amd/pm: Add waiting for response of mode-reset message for yellow carp Remove mdelay process and use smu_cmn_send_smc_msg_with_param to send mode-reset message to SMC. Signed-off-by: Aaron Liu Reviewed-by: Evan Quan Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index de92f713a911..0cfeb9fc7c03 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -298,13 +298,9 @@ static int yellow_carp_mode_reset(struct smu_context *smu, int type) if (index < 0) return index == -EACCES ? 0 : index; - mutex_lock(&smu->message_lock); - - ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, type); - - mutex_unlock(&smu->message_lock); - - mdelay(10); + ret = smu_cmn_send_smc_msg_with_param(smu, (uint16_t)index, type, NULL); + if (ret) + dev_err(smu->adev->dev, "Failed to mode reset!\n"); return ret; } From 01757f536ac825e3614d583fee9acb48c64ed084 Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Tue, 13 Jul 2021 10:48:24 +0800 Subject: [PATCH 259/426] net: Use nlmsg_unicast() instead of netlink_unicast() It has 'if (err >0 )' statement in nlmsg_unicast(), so use nlmsg_unicast() instead of netlink_unicast(), this looks more concise. v2: remove the change in netfilter. Signed-off-by: Yajun Deng Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 2 +- net/ipv4/inet_diag.c | 5 +---- net/ipv4/raw_diag.c | 7 ++----- net/ipv4/udp_diag.c | 6 ++---- net/mptcp/mptcp_diag.c | 6 ++---- net/netlink/af_netlink.c | 2 +- net/sctp/diag.c | 6 ++---- net/unix/diag.c | 6 ++---- 8 files changed, 13 insertions(+), 27 deletions(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a933bd6345b1..9fe13e4f5d08 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1376,7 +1376,7 @@ static void nl_fib_input(struct sk_buff *skb) portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ - netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT); + nlmsg_unicast(net->ipv4.fibnl, skb, portid); } static int __net_init nl_fib_lookup_init(struct net *net) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e65f4ef024a4..ef7897226f08 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -580,10 +580,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, nlmsg_free(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); out: if (sk) diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index 1b5b8af27aaf..ccacbde30a2c 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -119,11 +119,8 @@ static int raw_diag_dump_one(struct netlink_callback *cb, return err; } - err = netlink_unicast(net->diag_nlsk, rep, - NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + return err; } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index b2cee9a307d4..1ed8c4d78e5c 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -77,10 +77,8 @@ static int udp_dump_one(struct udp_table *tbl, kfree_skb(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: if (sk) sock_put(sk); diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index 8f88ddeab6a2..f48eb6315bbb 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -57,10 +57,8 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb, kfree_skb(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: sock_put(sk); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index d233ac4a91b6..380f95aacdec 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2471,7 +2471,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, nlmsg_end(skb, rep); - netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); + nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); } EXPORT_SYMBOL(netlink_ack); diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 493fc01e5d2b..760b367644c1 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -284,10 +284,8 @@ static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p) goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: return err; } diff --git a/net/unix/diag.c b/net/unix/diag.c index 9ff64f9df1f3..7e7d7f45685a 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -295,10 +295,8 @@ again: goto again; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, - MSG_DONTWAIT); - if (err > 0) - err = 0; + err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + out: if (sk) sock_put(sk); From e56c6bbd98dc1cefb6f9c5d795fd29016e4f2fe7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 13 Jul 2021 12:33:50 +0300 Subject: [PATCH 260/426] net: ocelot: fix switchdev objects synced for wrong netdev with LAG offload The point with a *dev and a *brport_dev is that when we have a LAG net device that is a bridge port, *dev is an ocelot net device and *brport_dev is the bonding/team net device. The ocelot net device beneath the LAG does not exist from the bridge's perspective, so we need to sync the switchdev objects belonging to the brport_dev and not to the dev. Fixes: e4bd44e89dcf ("net: ocelot: replay switchdev events when joining bridge") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot_net.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 3e89e34f86d5..e9d260d84bf3 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1298,6 +1298,7 @@ static int ocelot_netdevice_lag_leave(struct net_device *dev, } static int ocelot_netdevice_changeupper(struct net_device *dev, + struct net_device *brport_dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; @@ -1307,11 +1308,11 @@ static int ocelot_netdevice_changeupper(struct net_device *dev, if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) - err = ocelot_netdevice_bridge_join(dev, dev, + err = ocelot_netdevice_bridge_join(dev, brport_dev, info->upper_dev, extack); else - err = ocelot_netdevice_bridge_leave(dev, dev, + err = ocelot_netdevice_bridge_leave(dev, brport_dev, info->upper_dev); } if (netif_is_lag_master(info->upper_dev)) { @@ -1346,7 +1347,7 @@ ocelot_netdevice_lag_changeupper(struct net_device *dev, if (ocelot_port->bond != dev) return NOTIFY_OK; - err = ocelot_netdevice_changeupper(lower, info); + err = ocelot_netdevice_changeupper(lower, dev, info); if (err) return notifier_from_errno(err); } @@ -1385,7 +1386,7 @@ static int ocelot_netdevice_event(struct notifier_block *unused, struct netdev_notifier_changeupper_info *info = ptr; if (ocelot_netdevice_dev_check(dev)) - return ocelot_netdevice_changeupper(dev, info); + return ocelot_netdevice_changeupper(dev, dev, info); if (netif_is_lag_master(dev)) return ocelot_netdevice_lag_changeupper(dev, info); From b0b33b048dcfbd7da82c3cde4fab02751dfab4d6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 13 Jul 2021 12:37:19 +0300 Subject: [PATCH 261/426] net: dsa: sja1105: fix address learning getting disabled on the CPU port In May 2019 when commit 640f763f98c2 ("net: dsa: sja1105: Add support for Spanning Tree Protocol") was introduced, the comment that "STP does not get called for the CPU port" was true. This changed after commit 0394a63acfe2 ("net: dsa: enable and disable all ports") in August 2019 and went largely unnoticed, because the sja1105_bridge_stp_state_set() method did nothing different compared to the static setup done by sja1105_init_mac_settings(). With the ability to turn address learning off introduced by the blamed commit, there is a new priv->learn_ena port mask in the driver. When sja1105_bridge_stp_state_set() gets called and we are in BR_STATE_LEARNING or later, address learning is enabled or not depending on priv->learn_ena & BIT(port). So what happens is that priv->learn_ena is not being set from anywhere for the CPU port, and the static configuration done by sja1105_init_mac_settings() is being overwritten. To solve this, acknowledge that the static configuration of STP state is no longer necessary because the STP state is being set by the DSA core now, but what is necessary is to set priv->learn_ena for the CPU port. Fixes: 4d9423549501 ("net: dsa: sja1105: offload bridge port flags to device") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 4f0545605f6b..ced8c9cb29c2 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -122,14 +122,12 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) for (i = 0; i < ds->num_ports; i++) { mac[i] = default_mac; - if (i == dsa_upstream_port(priv->ds, i)) { - /* STP doesn't get called for CPU port, so we need to - * set the I/O parameters statically. - */ - mac[i].dyn_learn = true; - mac[i].ingress = true; - mac[i].egress = true; - } + + /* Let sja1105_bridge_stp_state_set() keep address learning + * enabled for the CPU port. + */ + if (dsa_is_cpu_port(ds, i)) + priv->learn_ena |= BIT(i); } return 0; From deb7178eb940e2c5caca1b1db084a69b2e59b4c9 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Tue, 13 Jul 2021 13:58:53 +0300 Subject: [PATCH 262/426] net: fddi: fix UAF in fza_probe fp is netdev private data and it cannot be used after free_netdev() call. Using fp after free_netdev() can cause UAF bug. Fix it by moving free_netdev() after error message. Fixes: 61414f5ec983 ("FDDI: defza: Add support for DEC FDDIcontroller 700 TURBOchannel adapter") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/fddi/defza.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 14f07050b6b1..0de2c4552f5e 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -1504,9 +1504,8 @@ err_out_resource: release_mem_region(start, len); err_out_kfree: - free_netdev(dev); - pr_err("%s: initialization failure, aborting!\n", fp->name); + free_netdev(dev); return ret; } From 2e7ea96924acc502929c3ffa0fcbdaeec00b2208 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 11:51:58 -0500 Subject: [PATCH 263/426] cpufreq: Fix fall-through warning for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix a fallthrough warning by simply dropping the empty default case at the bottom. Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva --- drivers/cpufreq/longhaul.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 182a4dbca095..c538a153ee82 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -942,8 +942,6 @@ static int __init longhaul_init(void) return cpufreq_register_driver(&longhaul_driver); case 10: pr_err("Use acpi-cpufreq driver for VIA C7\n"); - default: - ; } return -ENODEV; From f28100cb9c9645c07cbd22431278ac9492f6a01c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Tue, 13 Jul 2021 16:21:27 +0200 Subject: [PATCH 264/426] sfc: fix lack of XDP TX queues - error XDP TX failed (-22) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes: e26ca4b53582 sfc: reduce the number of requested xdp ev queues The buggy commit intended to allocate less channels for XDP in order to be more unlikely to reach the limit of 32 channels of the driver. The idea was to use each IRQ/eventqeue for more XDP TX queues than before, calculating which is the maximum number of TX queues that one event queue can handle. For example, in EF10 each event queue could handle up to 8 queues, better than the 4 they were handling before the change. This way, it would have to allocate half of channels than before for XDP TX. The problem is that the TX queues are also contained inside the channel structs, and there are only 4 queues per channel. Reducing the number of channels means also reducing the number of queues, resulting in not having the desired number of 1 queue per CPU. This leads to getting errors on XDP_TX and XDP_REDIRECT if they're executed from a high numbered CPU, because there only exist queues for the low half of CPUs, actually. If XDP_TX/REDIRECT is executed in a low numbered CPU, the error doesn't happen. This is the error in the logs (repeated many times, even rate limited): sfc 0000:5e:00.0 ens3f0np0: XDP TX failed (-22) This errors happens in function efx_xdp_tx_buffers, where it expects to have a dedicated XDP TX queue per CPU. Reverting the change makes again more likely to reach the limit of 32 channels in machines with many CPUs. If this happen, no XDP_TX/REDIRECT will be possible at all, and we will have this log error messages: At interface probe: sfc 0000:5e:00.0: Insufficient resources for 12 XDP event queues (24 other channels, max 32) At every subsequent XDP_TX/REDIRECT failure, rate limited: sfc 0000:5e:00.0 ens3f0np0: XDP TX failed (-22) However, without reverting the change, it makes the user to think that everything is OK at probe time, but later it fails in an unpredictable way, depending on the CPU that handles the packet. It is better to restore the predictable behaviour. If the user sees the error message at probe time, he/she can try to configure the best way it fits his/her needs. At least, he/she will have 2 options: - Accept that XDP_TX/REDIRECT is not available (he/she may not need it) - Load sfc module with modparam 'rss_cpus' with a lower number, thus creating less normal RX queues/channels, letting more free resources for XDP, with some performance penalty. Anyway, let the calculation of maximum TX queues that can be handled by a single event queue, and use it only if it's less than the number of TX queues per channel. This doesn't happen in practice, but could happen if some constant values are tweaked in the future, such us EFX_MAX_TXQ_PER_CHANNEL, EFX_MAX_EVQ_SIZE or EFX_MAX_DMAQ_SIZE. Related mailing list thread: https://lore.kernel.org/bpf/20201215104327.2be76156@carbon/ Signed-off-by: Íñigo Huguet Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_channels.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index a3ca406a3561..5b71f8a03a6d 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -152,6 +152,7 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, * maximum size. */ tx_per_ev = EFX_MAX_EVQ_SIZE / EFX_TXQ_MAX_ENT(efx); + tx_per_ev = min(tx_per_ev, EFX_MAX_TXQ_PER_CHANNEL); n_xdp_tx = num_possible_cpus(); n_xdp_ev = DIV_ROUND_UP(n_xdp_tx, tx_per_ev); @@ -181,7 +182,7 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, efx->xdp_tx_queue_count = 0; } else { efx->n_xdp_channels = n_xdp_ev; - efx->xdp_tx_per_channel = EFX_MAX_TXQ_PER_CHANNEL; + efx->xdp_tx_per_channel = tx_per_ev; efx->xdp_tx_queue_count = n_xdp_tx; n_channels += n_xdp_ev; netif_dbg(efx, drv, efx->net_dev, From 788bc000d4c2f25232db19ab3a0add0ba4e27671 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Tue, 13 Jul 2021 16:21:28 +0200 Subject: [PATCH 265/426] sfc: ensure correct number of XDP queues MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 99ba0ea616aa ("sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues") intended to fix a problem caused by a round up when calculating the number of XDP channels and queues. However, this was not the real problem. The real problem was that the number of XDP TX queues had been reduced to half in commit e26ca4b53582 ("sfc: reduce the number of requested xdp ev queues"), but the variable xdp_tx_queue_count had remained the same. Once the correct number of XDP TX queues is created again in the previous patch of this series, this also can be reverted since the error doesn't actually exist. Only in the case that there is a bug in the code we can have different values in xdp_queue_number and efx->xdp_tx_queue_count. Because of this, and per Edward Cree's suggestion, I add instead a WARN_ON to catch if it happens again in the future. Note that the number of allocated queues can be higher than the number of used ones due to the round up, as explained in the existing comment in the code. That's why we also have to stop increasing xdp_queue_number beyond efx->xdp_tx_queue_count. Signed-off-by: Íñigo Huguet Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_channels.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index 5b71f8a03a6d..bb48a139dd15 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -892,18 +892,20 @@ int efx_set_channels(struct efx_nic *efx) if (efx_channel_is_xdp_tx(channel)) { efx_for_each_channel_tx_queue(tx_queue, channel) { tx_queue->queue = next_queue++; - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", - channel->channel, tx_queue->label, - xdp_queue_number, tx_queue->queue); + /* We may have a few left-over XDP TX * queues owing to xdp_tx_queue_count * not dividing evenly by EFX_MAX_TXQ_PER_CHANNEL. * We still allocate and probe those * TXQs, but never use them. */ - if (xdp_queue_number < efx->xdp_tx_queue_count) + if (xdp_queue_number < efx->xdp_tx_queue_count) { + netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", + channel->channel, tx_queue->label, + xdp_queue_number, tx_queue->queue); efx->xdp_tx_queues[xdp_queue_number] = tx_queue; - xdp_queue_number++; + xdp_queue_number++; + } } } else { efx_for_each_channel_tx_queue(tx_queue, channel) { @@ -915,8 +917,7 @@ int efx_set_channels(struct efx_nic *efx) } } } - if (xdp_queue_number) - efx->xdp_tx_queue_count = xdp_queue_number; + WARN_ON(xdp_queue_number != efx->xdp_tx_queue_count); rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); if (rc) From d2a16bde77322fca6b6f36ebe19097a1c3c46f74 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Tue, 13 Jul 2021 16:21:29 +0200 Subject: [PATCH 266/426] sfc: add logs explaining XDP_TX/REDIRECT is not available MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If it's not possible to allocate enough channels for XDP, XDP_TX and XDP_REDIRECT don't work. However, only a message saying that not enough channels were available was shown, but not saying what are the consequences in that case. The user didn't know if he/she can use XDP or not, if the performance is reduced, or what. Signed-off-by: Íñigo Huguet Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_channels.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index bb48a139dd15..e5b0d795c301 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -170,6 +170,8 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, netif_err(efx, drv, efx->net_dev, "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n", n_xdp_ev, n_channels, max_channels); + netif_err(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT will not work on this interface"); efx->n_xdp_channels = 0; efx->xdp_tx_per_channel = 0; efx->xdp_tx_queue_count = 0; @@ -177,6 +179,8 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, netif_err(efx, drv, efx->net_dev, "Insufficient resources for %d XDP TX queues (%d other channels, max VIs %d)\n", n_xdp_tx, n_channels, efx->max_vis); + netif_err(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT will not work on this interface"); efx->n_xdp_channels = 0; efx->xdp_tx_per_channel = 0; efx->xdp_tx_queue_count = 0; From 420405ecde061fde76d67bd3a67577a563ea758e Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 13 Jul 2021 10:49:26 -0700 Subject: [PATCH 267/426] configfs: fix the read and write iterators Commit 7fe1e79b59ba ("configfs: implement the .read_iter and .write_iter methods") changed the simple_read_from_buffer() calls into copy_to_iter() calls and the simple_write_to_buffer() calls into copy_from_iter() calls. The simple*buffer() methods update the file offset (*ppos) but the read and write iterators not yet. Make the read and write iterators update the file offset (iocb->ki_pos). This patch has been tested as follows: # modprobe target_core_user # dd if=/sys/kernel/config/target/dbroot bs=1 /var/target 12+0 records in 12+0 records out 12 bytes copied, 9.5539e-05 s, 126 kB/s # cd /sys/kernel/config/acpi/table # mkdir test # cd test # dmesg -c >/dev/null; printf 'SSDT\x8\0\0\0abcdefghijklmnopqrstuvwxyz' | dd of=aml bs=1; dmesg -c 34+0 records in 34+0 records out 34 bytes copied, 0.010627 s, 3.2 kB/s [ 261.056551] ACPI configfs: invalid table length Reported-by: Yanko Kaneti Cc: Yanko Kaneti Fixes: 7fe1e79b59ba ("configfs: implement the .read_iter and .write_iter methods") Signed-off-by: Bart Van Assche Signed-off-by: Christoph Hellwig --- fs/configfs/file.c | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 2f63bf3a7325..5a0be9985bae 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -91,7 +91,10 @@ static ssize_t configfs_read_iter(struct kiocb *iocb, struct iov_iter *to) } pr_debug("%s: count = %zd, pos = %lld, buf = %s\n", __func__, iov_iter_count(to), iocb->ki_pos, buffer->page); - retval = copy_to_iter(buffer->page, buffer->count, to); + if (iocb->ki_pos >= buffer->count) + goto out; + retval = copy_to_iter(buffer->page + iocb->ki_pos, + buffer->count - iocb->ki_pos, to); iocb->ki_pos += retval; if (retval == 0) retval = -EFAULT; @@ -162,7 +165,10 @@ static ssize_t configfs_bin_read_iter(struct kiocb *iocb, struct iov_iter *to) buffer->needs_read_fill = 0; } - retval = copy_to_iter(buffer->bin_buffer, buffer->bin_buffer_size, to); + if (iocb->ki_pos >= buffer->bin_buffer_size) + goto out; + retval = copy_to_iter(buffer->bin_buffer + iocb->ki_pos, + buffer->bin_buffer_size - iocb->ki_pos, to); iocb->ki_pos += retval; if (retval == 0) retval = -EFAULT; @@ -171,21 +177,28 @@ out: return retval; } -static int fill_write_buffer(struct configfs_buffer *buffer, +/* Fill [buffer, buffer + pos) with data coming from @from. */ +static int fill_write_buffer(struct configfs_buffer *buffer, loff_t pos, struct iov_iter *from) { + loff_t to_copy; int copied; + u8 *to; if (!buffer->page) buffer->page = (char *)__get_free_pages(GFP_KERNEL, 0); if (!buffer->page) return -ENOMEM; - copied = copy_from_iter(buffer->page, SIMPLE_ATTR_SIZE - 1, from); + to_copy = SIMPLE_ATTR_SIZE - 1 - pos; + if (to_copy <= 0) + return 0; + to = buffer->page + pos; + copied = copy_from_iter(to, to_copy, from); buffer->needs_read_fill = 1; /* if buf is assumed to contain a string, terminate it by \0, * so e.g. sscanf() can scan the string easily */ - buffer->page[copied] = 0; + to[copied] = 0; return copied ? : -EFAULT; } @@ -217,7 +230,7 @@ static ssize_t configfs_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t len; mutex_lock(&buffer->mutex); - len = fill_write_buffer(buffer, from); + len = fill_write_buffer(buffer, iocb->ki_pos, from); if (len > 0) len = flush_write_buffer(file, buffer, len); if (len > 0) @@ -272,7 +285,9 @@ static ssize_t configfs_bin_write_iter(struct kiocb *iocb, buffer->bin_buffer_size = end_offset; } - len = copy_from_iter(buffer->bin_buffer, buffer->bin_buffer_size, from); + len = copy_from_iter(buffer->bin_buffer + iocb->ki_pos, + buffer->bin_buffer_size - iocb->ki_pos, from); + iocb->ki_pos += len; out: mutex_unlock(&buffer->mutex); return len ? : -EFAULT; From f336a009f8e3dd0b47168565584608a4a62cbbb4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:09:06 -0500 Subject: [PATCH 268/426] math-emu: Fix fall-through warning Fix the following fallthrough warning (nds32-randconfig with GCC): include/math-emu/op-common.h:332:8: warning: this statement may fall through [-Wimplicit-fallthrough=] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- include/math-emu/op-common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h index 143568d64b20..4b57bbba588a 100644 --- a/include/math-emu/op-common.h +++ b/include/math-emu/op-common.h @@ -338,7 +338,7 @@ do { \ FP_SET_EXCEPTION(FP_EX_INVALID | FP_EX_INVALID_ISI); \ break; \ } \ - /* FALLTHRU */ \ + fallthrough; \ \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \ case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO): \ From c8698340e0e5897c30811f8e7e86bcebe53e0519 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:13:40 -0500 Subject: [PATCH 269/426] video: fbdev: Fix fall-through warning for Clang Fix the following fallthrough warning (arm64-randconfig with Clang): drivers/video/fbdev/xilinxfb.c:244:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/video/fbdev/xilinxfb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/fbdev/xilinxfb.c b/drivers/video/fbdev/xilinxfb.c index ffbf900648d9..438e2c78142f 100644 --- a/drivers/video/fbdev/xilinxfb.c +++ b/drivers/video/fbdev/xilinxfb.c @@ -241,6 +241,8 @@ xilinx_fb_blank(int blank_mode, struct fb_info *fbi) case FB_BLANK_POWERDOWN: /* turn off panel */ xilinx_fb_out32(drvdata, REG_CTRL, 0); + break; + default: break; } From 223fa873facce6eef165009294d01e18c191c609 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:18:14 -0500 Subject: [PATCH 270/426] scsi: libsas: Fix fall-through warning for Clang Fix the following fallthrough warning (arm64-randconfig with Clang): drivers/scsi/libsas/sas_discover.c:467:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/scsi/libsas/sas_discover.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index 9f5068f3bcfb..dd205414e505 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -461,7 +461,7 @@ static void sas_discover_domain(struct work_struct *work) break; #else pr_notice("ATA device seen but CONFIG_SCSI_SAS_ATA=N so cannot attach\n"); - /* Fall through */ + fallthrough; #endif /* Fall through - only for the #else condition above. */ default: From 54325d0849d60ed52ee9316f76d116b52b53669b Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:21:22 -0500 Subject: [PATCH 271/426] PCI: Fix fall-through warning for Clang Fix the following fallthrough warning (arm64-randconfig with Clang): drivers/pci/proc.c:234:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/pci/proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index 9bab07302bbf..d32fbfc93ea9 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -230,8 +230,8 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd, break; } /* If arch decided it can't, fall through... */ -#endif /* HAVE_PCI_MMAP */ fallthrough; +#endif /* HAVE_PCI_MMAP */ default: ret = -EINVAL; break; From f95deaeca8e106af891061e5f9c745dc7dc172c0 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:23:21 -0500 Subject: [PATCH 272/426] mmc: jz4740: Fix fall-through warning for Clang Fix the following fallthrough warning (mips-randconfig with Clang): drivers/mmc/host/jz4740_mmc.c:792:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/mmc/host/jz4740_mmc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index 0db17bcc9c16..cb1a64a5c256 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -789,6 +789,8 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid) break; } } + fallthrough; + case JZ4740_MMC_STATE_DONE: break; } From 5a1ab5c0299a7b3b9e7ec52c327f44d98b8e001d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:25:06 -0500 Subject: [PATCH 273/426] iommu/arm-smmu-v3: Fix fall-through warning for Clang Fix the following fallthrough warning (arm64-randconfig with Clang): drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c:382:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index dd20b01771c4..235f9bdaeaf2 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -379,6 +379,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) switch (idx) { case CMDQ_ERR_CERROR_ABT_IDX: dev_err(smmu->dev, "retrying command fetch\n"); + return; case CMDQ_ERR_CERROR_NONE_IDX: return; case CMDQ_ERR_CERROR_ATC_INV_IDX: From 41614014a7afbbce5b61bfce5ce89ee3455143e7 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:27:08 -0500 Subject: [PATCH 274/426] dmaengine: ipu: Fix fall-through warning for Clang Fix the following fallthrough warnings (arm64-randconfig): drivers/dma/ipu/ipu_idmac.c:621:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] rivers/dma/ipu/ipu_idmac.c:981:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/dma/ipu/ipu_idmac.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c index 104ad420abbe..baab1ca9f621 100644 --- a/drivers/dma/ipu/ipu_idmac.c +++ b/drivers/dma/ipu/ipu_idmac.c @@ -618,6 +618,7 @@ static int ipu_enable_channel(struct idmac *idmac, struct idmac_channel *ichan) case IDMAC_SDC_1: case IDMAC_IC_7: ipu_channel_set_priority(ipu, channel, true); + break; default: break; } @@ -978,6 +979,7 @@ static int ipu_init_channel(struct idmac *idmac, struct idmac_channel *ichan) case IDMAC_SDC_0: case IDMAC_SDC_1: n_desc = 4; + break; default: break; } From d4e81342ea2399cf92e98ea5c0d025bcf8a3d065 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 14:43:09 -0500 Subject: [PATCH 275/426] s390: Fix fall-through warnings for Clang Fix the following fallthrough warnings: drivers/s390/net/ctcm_fsms.c:1457:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] drivers/s390/net/qeth_l3_main.c:437:3: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] drivers/s390/char/tape_char.c:374:4: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] arch/s390/kernel/uprobes.c:129:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- arch/s390/kernel/uprobes.c | 1 + drivers/s390/char/tape_char.c | 2 -- drivers/s390/net/ctcm_fsms.c | 1 + drivers/s390/net/qeth_l3_main.c | 1 + 4 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c index bbf8622bbf5d..bd3ef121c379 100644 --- a/arch/s390/kernel/uprobes.c +++ b/arch/s390/kernel/uprobes.c @@ -126,6 +126,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, case DIE_SSTEP: if (uprobe_post_sstep_notifier(regs)) return NOTIFY_STOP; + break; default: break; } diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c index 8abb42923307..cc8237afeffa 100644 --- a/drivers/s390/char/tape_char.c +++ b/drivers/s390/char/tape_char.c @@ -371,8 +371,6 @@ __tapechar_ioctl(struct tape_device *device, case MTSEEK: if (device->required_tapemarks) tape_std_terminate_write(device); - default: - ; } rc = tape_mtop(device, op.mt_op, op.mt_count); diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c index b341075397d9..377e3689d1d4 100644 --- a/drivers/s390/net/ctcm_fsms.c +++ b/drivers/s390/net/ctcm_fsms.c @@ -1454,6 +1454,7 @@ again: get_ccwdev_lock(ch->cdev), saveflags); if (rc != 0) ctcm_ccw_check_rc(ch, rc, "normal RX"); + break; default: break; } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index d308ff744a29..f0d6f205c53c 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -434,6 +434,7 @@ static int qeth_l3_correct_routing_type(struct qeth_card *card, if (qeth_is_ipafunc_supported(card, prot, IPA_OSA_MC_ROUTER)) return 0; + goto out_inval; default: goto out_inval; } From d6a48a476a5de8bdfbdd6040aa5a48955fc49e44 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 14:48:28 -0500 Subject: [PATCH 276/426] dmaengine: ti: k3-udma: Fix fall-through warning for Clang Fix the following fallthrough warning: drivers/dma/ti/k3-udma.c:4951:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- drivers/dma/ti/k3-udma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 96ad21869ba7..a35858610780 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -4948,6 +4948,7 @@ static int setup_resources(struct udma_dev *ud) ud->tchan_cnt), ud->rchan_cnt - bitmap_weight(ud->rchan_map, ud->rchan_cnt)); + break; default: break; } From b51883d47d37c3f3fa80d6bcd8cc3a57d5b95130 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 14:50:47 -0500 Subject: [PATCH 277/426] power: supply: Fix fall-through warnings for Clang Fix the following fallthrough warnings: drivers/power/supply/ab8500_fg.c:1730:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] drivers/power/supply/abx500_chargalg.c:1155:3: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- drivers/power/supply/ab8500_fg.c | 2 ++ drivers/power/supply/abx500_chargalg.c | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index 3d45ed0157c6..a6ebdb269fdd 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -1728,6 +1728,7 @@ static void ab8500_fg_algorithm_calibrate(struct ab8500_fg *di) break; case AB8500_FG_CALIB_WAIT: dev_dbg(di->dev, "Calibration WFI\n"); + break; default: break; } @@ -2224,6 +2225,7 @@ static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data) queue_work(di->fg_wq, &di->fg_work); break; } + break; default: break; } diff --git a/drivers/power/supply/abx500_chargalg.c b/drivers/power/supply/abx500_chargalg.c index a17849bfacbf..b72826cf6794 100644 --- a/drivers/power/supply/abx500_chargalg.c +++ b/drivers/power/supply/abx500_chargalg.c @@ -1150,6 +1150,7 @@ static int abx500_chargalg_get_ext_psy_data(struct device *dev, void *data) default: break; } + break; default: break; } From 2feeb52859fc1ab94cd35b61ada3a6ac4ff24243 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 30 Jun 2021 19:44:13 +0300 Subject: [PATCH 278/426] drm/i915/gt: Fix -EDEADLK handling regression MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The conversion to ww mutexes failed to address the fence code which already returns -EDEADLK when we run out of fences. Ww mutexes on the other hand treat -EDEADLK as an internal errno value indicating a need to restart the operation due to a deadlock. So now when the fence code returns -EDEADLK the higher level code erroneously restarts everything instead of returning the error to userspace as is expected. To remedy this let's switch the fence code to use a different errno value for this. -ENOBUFS seems like a semi-reasonable unique choice. Apart from igt the only user of this I could find is sna, and even there all we do is dump the current fence registers from debugfs into the X server log. So no user visible functionality is affected. If we really cared about preserving this we could of course convert back to -EDEADLK higher up, but doesn't seem like that's worth the hassle here. Not quite sure which commit specifically broke this, but I'll just attribute it to the general gem ww mutex work. Cc: stable@vger.kernel.org Cc: Maarten Lankhorst Cc: Thomas Hellström Testcase: igt/gem_pread/exhaustion Testcase: igt/gem_pwrite/basic-exhaustion Testcase: igt/gem_fenced_exec_thrash/too-many-fences Fixes: 80f0b679d6f0 ("drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2.") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20210630164413.25481-1-ville.syrjala@linux.intel.com Reviewed-by: Maarten Lankhorst (cherry picked from commit 78d2ad7eb4e1f0e9cd5d79788446b6092c21d3e0) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index cac7f3f44642..f8948de72036 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -348,7 +348,7 @@ static struct i915_fence_reg *fence_find(struct i915_ggtt *ggtt) if (intel_has_pending_fb_unpin(ggtt->vm.i915)) return ERR_PTR(-EAGAIN); - return ERR_PTR(-EDEADLK); + return ERR_PTR(-ENOBUFS); } int __i915_vma_pin_fence(struct i915_vma *vma) From 4796372e7c117b84bfd929526f48e23c79030dcd Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 14:58:18 -0500 Subject: [PATCH 279/426] ASoC: Mediatek: MT8183: Fix fall-through warning for Clang Fix the following fallthrough warning: sound/soc/mediatek/mt8183/mt8183-dai-adda.c:342:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- sound/soc/mediatek/mt8183/mt8183-dai-adda.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/mediatek/mt8183/mt8183-dai-adda.c b/sound/soc/mediatek/mt8183/mt8183-dai-adda.c index 2b758a18c2ea..5b8a274419ed 100644 --- a/sound/soc/mediatek/mt8183/mt8183-dai-adda.c +++ b/sound/soc/mediatek/mt8183/mt8183-dai-adda.c @@ -341,6 +341,7 @@ static int set_mtkaif_rx(struct mtk_base_afe *afe) case MT8183_MTKAIF_PROTOCOL_1: regmap_write(afe->regmap, AFE_AUD_PAD_TOP, 0x31); regmap_write(afe->regmap, AFE_ADDA_MTKAIF_CFG0, 0x0); + break; default: break; } From bc431d2153cc290573531601b5004babe7011568 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:38:58 -0500 Subject: [PATCH 280/426] MIPS: Fix fall-through warnings for Clang Fix the following fallthrough warnings: arch/mips/mm/tlbex.c:1386:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] arch/mips/mm/tlbex.c:2173:3: error: unannotated fall-through between switch labels [-Werror,-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- arch/mips/mm/tlbex.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index cd4afcdf3725..9adad24c2e65 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1383,6 +1383,7 @@ static void build_r4000_tlb_refill_handler(void) switch (boot_cpu_type()) { default: if (sizeof(long) == 4) { + fallthrough; case CPU_LOONGSON2EF: /* Loongson2 ebase is different than r4k, we have more space */ if ((p - tlb_handler) > 64) @@ -2169,6 +2170,7 @@ static void build_r4000_tlb_load_handler(void) default: if (cpu_has_mips_r2_exec_hazard) { uasm_i_ehb(&p); + fallthrough; case CPU_CAVIUM_OCTEON: case CPU_CAVIUM_OCTEON_PLUS: From cf6678aec2530701f8e13b7551d131599c33e5ca Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 13:41:16 -0500 Subject: [PATCH 281/426] MIPS: Fix unreachable code issue Fix the following warning (mips-randconfig): arch/mips/include/asm/fpu.h:79:3: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] Originally, the /* fallthrough */ comment was introduced by commit: 597ce1723e0f ("MIPS: Support for 64-bit FP with O32 binaries") and it was wrongly replaced with fallthrough; by commit: c9b029903466 ("MIPS: Use fallthrough for arch/mips") As the original comment is actually useful, fix this issue by removing unreachable fallthrough; statement and place the original /* fallthrough */ comment back. Fixes: c9b029903466 ("MIPS: Use fallthrough for arch/mips") Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60edca25.k00ut905IFBjPyt5%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- arch/mips/include/asm/fpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index 08f9dd6903b7..86310d6e1035 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -76,7 +76,7 @@ static inline int __enable_fpu(enum fpu_mode mode) /* we only have a 32-bit FPU */ return SIGFPE; #endif - fallthrough; + /* fallthrough */ case FPU_32BIT: if (cpu_has_fre) { /* clear FRE */ From bcb9928a155444dbd212473e60241ca0a7f641e1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 13 Jul 2021 12:40:21 +0300 Subject: [PATCH 282/426] net: dsa: properly check for the bridge_leave methods in dsa_switch_bridge_leave() This was not caught because there is no switch driver which implements the .port_bridge_join but not .port_bridge_leave method, but it should nonetheless be fixed, as in certain conditions (driver development) it might lead to NULL pointer dereference. Fixes: f66a6a69f97a ("net: dsa: permit cross-chip bridging between all trees in the system") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- net/dsa/switch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 248455145982..5ece05dfd8f2 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -113,11 +113,11 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, int err, port; if (dst->index == info->tree_index && ds->index == info->sw_index && - ds->ops->port_bridge_join) + ds->ops->port_bridge_leave) ds->ops->port_bridge_leave(ds, info->port, info->br); if ((dst->index != info->tree_index || ds->index != info->sw_index) && - ds->ops->crosschip_bridge_join) + ds->ops->crosschip_bridge_leave) ds->ops->crosschip_bridge_leave(ds, info->tree_index, info->sw_index, info->port, info->br); From 479857a9bcc86e808216daae8ca1c9213b9e117a Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Jul 2021 19:19:03 -0500 Subject: [PATCH 283/426] powerpc/powernv: Fix fall-through warning for Clang Fix the following fallthrough warnings (powernv_defconfig and powerpc64): drivers/char/powernv-op-panel.c:78:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: Nathan Chancellor Signed-off-by: Gustavo A. R. Silva --- drivers/char/powernv-op-panel.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/char/powernv-op-panel.c b/drivers/char/powernv-op-panel.c index 027484ecfb0d..3c99696b145e 100644 --- a/drivers/char/powernv-op-panel.c +++ b/drivers/char/powernv-op-panel.c @@ -75,6 +75,7 @@ static int __op_panel_update_display(void) rc); break; } + break; case OPAL_SUCCESS: break; default: From ce36c94214f0d534aad4adb4219cc046270948fb Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 5 Jul 2021 08:56:57 +0200 Subject: [PATCH 284/426] iommu/qcom: Revert "iommu/arm: Cleanup resources in case of probe error path" QCOM IOMMU driver calls bus_set_iommu() for every IOMMU device controller, what fails for the second and latter IOMMU devices. This is intended and must be not fatal to the driver registration process. Also the cleanup path should take care of the runtime PM state, what is missing in the current patch. Revert relevant changes to the QCOM IOMMU driver until a proper fix is prepared. This partially reverts commit 249c9dc6aa0db74a0f7908efd04acf774e19b155. Fixes: 249c9dc6aa0d ("iommu/arm: Cleanup resources in case of probe error path") Suggested-by: Will Deacon Signed-off-by: Marek Szyprowski Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210705065657.30356-1-m.szyprowski@samsung.com Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu/qcom_iommu.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index 25ed444ff94d..021cf8f65ffc 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -849,12 +849,10 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) ret = iommu_device_register(&qcom_iommu->iommu, &qcom_iommu_ops, dev); if (ret) { dev_err(dev, "Failed to register iommu\n"); - goto err_sysfs_remove; + return ret; } - ret = bus_set_iommu(&platform_bus_type, &qcom_iommu_ops); - if (ret) - goto err_unregister_device; + bus_set_iommu(&platform_bus_type, &qcom_iommu_ops); if (qcom_iommu->local_base) { pm_runtime_get_sync(dev); @@ -863,13 +861,6 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) } return 0; - -err_unregister_device: - iommu_device_unregister(&qcom_iommu->iommu); - -err_sysfs_remove: - iommu_device_sysfs_remove(&qcom_iommu->iommu); - return ret; } static int qcom_iommu_device_remove(struct platform_device *pdev) From 37764b952e1b39053defc7ebe5dcd8c4e3e78de9 Mon Sep 17 00:00:00 2001 From: Sanjay Kumar Date: Mon, 12 Jul 2021 15:13:15 +0800 Subject: [PATCH 285/426] iommu/vt-d: Global devTLB flush when present context entry changed This fixes a bug in context cache clear operation. The code was not following the correct invalidation flow. A global device TLB invalidation should be added after the IOTLB invalidation. At the same time, it uses the domain ID from the context entry. But in scalable mode, the domain ID is in PASID table entry, not context entry. Fixes: 7373a8cc38197 ("iommu/vt-d: Setup context and enable RID2PASID support") Cc: stable@vger.kernel.org # v5.0+ Signed-off-by: Sanjay Kumar Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210712071315.3416543-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a6a07d985709..57270290d62b 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2429,10 +2429,11 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, return 0; } -static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn) +static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8 devfn) { - unsigned long flags; + struct intel_iommu *iommu = info->iommu; struct context_entry *context; + unsigned long flags; u16 did_old; if (!iommu) @@ -2444,7 +2445,16 @@ static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn spin_unlock_irqrestore(&iommu->lock, flags); return; } - did_old = context_domain_id(context); + + if (sm_supported(iommu)) { + if (hw_pass_through && domain_type_is_si(info->domain)) + did_old = FLPT_DEFAULT_DID; + else + did_old = info->domain->iommu_did[iommu->seq_id]; + } else { + did_old = context_domain_id(context); + } + context_clear_entry(context); __iommu_flush_cache(iommu, context, sizeof(*context)); spin_unlock_irqrestore(&iommu->lock, flags); @@ -2462,6 +2472,8 @@ static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn 0, 0, DMA_TLB_DSI_FLUSH); + + __iommu_flush_dev_iotlb(info, 0, MAX_AGAW_PFN_WIDTH); } static inline void unlink_domain_info(struct device_domain_info *info) @@ -4425,9 +4437,9 @@ out_free_dmar: static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque) { - struct intel_iommu *iommu = opaque; + struct device_domain_info *info = opaque; - domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff); + domain_context_clear_one(info, PCI_BUS_NUM(alias), alias & 0xff); return 0; } @@ -4437,12 +4449,13 @@ static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *op * devices, unbinding the driver from any one of them will possibly leave * the others unable to operate. */ -static void domain_context_clear(struct intel_iommu *iommu, struct device *dev) +static void domain_context_clear(struct device_domain_info *info) { - if (!iommu || !dev || !dev_is_pci(dev)) + if (!info->iommu || !info->dev || !dev_is_pci(info->dev)) return; - pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu); + pci_for_each_dma_alias(to_pci_dev(info->dev), + &domain_context_clear_one_cb, info); } static void __dmar_remove_one_dev_info(struct device_domain_info *info) @@ -4466,7 +4479,7 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) iommu_disable_dev_iotlb(info); if (!dev_is_real_dma_subdevice(info->dev)) - domain_context_clear(iommu, info->dev); + domain_context_clear(info); intel_pasid_free_table(info->dev); } From 474dd1c6506411752a9b2f2233eec11f1733a099 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 12 Jul 2021 15:17:12 +0800 Subject: [PATCH 286/426] iommu/vt-d: Fix clearing real DMA device's scalable-mode context entries The commit 2b0140c69637e ("iommu/vt-d: Use pci_real_dma_dev() for mapping") fixes an issue of "sub-device is removed where the context entry is cleared for all aliases". But this commit didn't consider the PASID entry and PASID table in VT-d scalable mode. This fix increases the coverage of scalable mode. Suggested-by: Sanjay Kumar Fixes: 8038bdb855331 ("iommu/vt-d: Only clear real DMA device's context entries") Fixes: 2b0140c69637e ("iommu/vt-d: Use pci_real_dma_dev() for mapping") Cc: stable@vger.kernel.org # v5.6+ Cc: Jon Derrick Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210712071712.3416949-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 57270290d62b..dd22fc7d5176 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4472,14 +4472,13 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) iommu = info->iommu; domain = info->domain; - if (info->dev) { + if (info->dev && !dev_is_real_dma_subdevice(info->dev)) { if (dev_is_pci(info->dev) && sm_supported(iommu)) intel_pasid_tear_down_entry(iommu, info->dev, PASID_RID2PASID, false); iommu_disable_dev_iotlb(info); - if (!dev_is_real_dma_subdevice(info->dev)) - domain_context_clear(info); + domain_context_clear(info); intel_pasid_free_table(info->dev); } From c987b65a574fad8b598d6f58f010d8f630327428 Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Mon, 12 Jul 2021 12:12:32 +0200 Subject: [PATCH 287/426] iommu/rockchip: Fix physical address decoding Restore bits 39 to 32 at correct position. It reverses the operation done in rk_dma_addr_dte_v2(). Fixes: c55356c534aa ("iommu: rockchip: Add support for iommu v2") Reported-by: Dan Carpenter Signed-off-by: Benjamin Gaignard Link: https://lore.kernel.org/r/20210712101232.318589-1-benjamin.gaignard@collabora.com Signed-off-by: Joerg Roedel --- drivers/iommu/rockchip-iommu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 94b9d8e5b9a4..9febfb7f3025 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -544,12 +544,14 @@ static inline u32 rk_dma_addr_dte(dma_addr_t dt_dma) } #define DT_HI_MASK GENMASK_ULL(39, 32) +#define DTE_BASE_HI_MASK GENMASK(11, 4) #define DT_SHIFT 28 static inline phys_addr_t rk_dte_addr_phys_v2(u32 addr) { - return (phys_addr_t)(addr & RK_DTE_PT_ADDRESS_MASK) | - ((addr & DT_HI_MASK) << DT_SHIFT); + u64 addr64 = addr; + return (phys_addr_t)(addr64 & RK_DTE_PT_ADDRESS_MASK) | + ((addr64 & DTE_BASE_HI_MASK) << DT_SHIFT); } static inline u32 rk_dma_addr_dte_v2(dma_addr_t dt_dma) From 0abb33bfca0fb74df76aac03e90ce685016ef7be Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 13 Jul 2021 14:04:31 +0100 Subject: [PATCH 288/426] drm/i915/gtt: drop the page table optimisation We skip filling out the pt with scratch entries if the va range covers the entire pt, since we later have to fill it with the PTEs for the object pages anyway. However this might leave open a small window where the PTEs don't point to anything valid for the HW to consume. When for example using 2M GTT pages this fill_px() showed up as being quite significant in perf measurements, and ends up being completely wasted since we ignore the pt and just use the pde directly. Anyway, currently we have our PTE construction split between alloc and insert, which is probably slightly iffy nowadays, since the alloc doesn't actually allocate anything anymore, instead it just sets up the page directories and points the PTEs at the scratch page. Later when we do the insert step we re-program the PTEs again. Better might be to squash the alloc and insert into a single step, then bringing back this optimisation(along with some others) should be possible. Fixes: 14826673247e ("drm/i915: Only initialize partially filled pagetables") Signed-off-by: Matthew Auld Cc: Jon Bloomfield Cc: Chris Wilson Cc: Daniel Vetter Cc: # v4.15+ Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210713130431.2392740-1-matthew.auld@intel.com (cherry picked from commit 8f88ca76b3942d82e2c1cea8735ec368d89ecc15) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 21c8b7350b7a..da4f5eb43ac2 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -303,10 +303,7 @@ static void __gen8_ppgtt_alloc(struct i915_address_space * const vm, __i915_gem_object_pin_pages(pt->base); i915_gem_object_make_unshrinkable(pt->base); - if (lvl || - gen8_pt_count(*start, end) < I915_PDES || - intel_vgpu_active(vm->i915)) - fill_px(pt, vm->scratch[lvl]->encode); + fill_px(pt, vm->scratch[lvl]->encode); spin_lock(&pd->lock); if (likely(!pd->entry[idx])) { From 49afa7f6c714ab3f5cb2a4c835f7f9dddc0bb2c1 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 8 Jul 2021 09:36:58 +0800 Subject: [PATCH 289/426] perf pmu: Skip invalid hybrid pmu On hybrid platform, such as Alderlake, if atom CPUs are offlined, the kernel still exports the sysfs path '/sys/devices/cpu_atom/' for 'cpu_atom' pmu but the file '/sys/devices/cpu_atom/cpus' is empty, which indicates this is an invalid pmu. Need to check and skip the invalid hybrid pmu. Before: # perf list ... branch-instructions OR cpu_atom/branch-instructions/ [Kernel PMU event] branch-instructions OR cpu_core/branch-instructions/ [Kernel PMU event] branch-misses OR cpu_atom/branch-misses/ [Kernel PMU event] branch-misses OR cpu_core/branch-misses/ [Kernel PMU event] bus-cycles OR cpu_atom/bus-cycles/ [Kernel PMU event] bus-cycles OR cpu_core/bus-cycles/ [Kernel PMU event] ... The cpu_atom events are still displayed even if atom CPUs are offlined. After: # perf list ... branch-instructions OR cpu_core/branch-instructions/ [Kernel PMU event] branch-misses OR cpu_core/branch-misses/ [Kernel PMU event] bus-cycles OR cpu_core/bus-cycles/ [Kernel PMU event] ... Now only cpu_core events are displayed. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210708013701.20347-2-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 44b90d638ad5..a1bd7007a8b4 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -950,6 +950,13 @@ static struct perf_pmu *pmu_lookup(const char *name) LIST_HEAD(format); LIST_HEAD(aliases); __u32 type; + bool is_hybrid = perf_pmu__hybrid_mounted(name); + + /* + * Check pmu name for hybrid and the pmu may be invalid in sysfs + */ + if (!strncmp(name, "cpu_", 4) && !is_hybrid) + return NULL; /* * The pmu data we store & need consists of the pmu @@ -978,7 +985,7 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->is_uncore = pmu_is_uncore(name); if (pmu->is_uncore) pmu->id = pmu_id(name); - pmu->is_hybrid = perf_pmu__hybrid_mounted(name); + pmu->is_hybrid = is_hybrid; pmu->max_precise = pmu_max_precise(name); pmu_add_cpu_aliases(&aliases, pmu); pmu_add_sys_aliases(&aliases, pmu); From 490e9a8fb4a3d74602668ef2e4cc29608e9b00a6 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 8 Jul 2021 09:36:59 +0800 Subject: [PATCH 290/426] perf tests: Fix 'Parse event definition strings' on core-only system If the atom CPUs are offlined, the 'cpu_atom' is not valid. We don't need the test case for 'cpu_atom'. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210708013701.20347-3-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/parse-events.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 56a7b6a14195..8d4866739255 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -6,6 +6,7 @@ #include "tests.h" #include "debug.h" #include "pmu.h" +#include "pmu-hybrid.h" #include #include #include @@ -1596,6 +1597,13 @@ static int test__hybrid_raw1(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); + if (!perf_pmu__hybrid_mounted("cpu_atom")) { + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); + return 0; + } + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); @@ -1620,13 +1628,9 @@ static int test__hybrid_cache_event(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", 0x2 == (evsel->core.attr.config & 0xffffffff)); - - evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x10002 == (evsel->core.attr.config & 0xffffffff)); return 0; } @@ -2028,7 +2032,7 @@ static struct evlist_test test__hybrid_events[] = { .id = 7, }, { - .name = "cpu_core/LLC-loads/,cpu_atom/LLC-load-misses/", + .name = "cpu_core/LLC-loads/", .check = test__hybrid_cache_event, .id = 8, }, From 212f3d97abc8be09549de12cedb290f47b4dce5a Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 8 Jul 2021 09:37:00 +0800 Subject: [PATCH 291/426] perf tests: Fix 'Roundtrip evsel->name' on core-only system If the atom CPUs are offlined, the 'cpu_atom' is not valid. Perf will not create two events for one hw event, so the evsel->idx doesn't need to be divided by 2 before comparing. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210708013701.20347-4-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/evsel-roundtrip-name.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 5ebf56331904..4e09f0a312af 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -5,6 +5,7 @@ #include "tests.h" #include "debug.h" #include "pmu.h" +#include "pmu-hybrid.h" #include #include @@ -102,7 +103,7 @@ int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int { int err = 0, ret = 0; - if (perf_pmu__has_hybrid()) + if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) return perf_evsel__name_array_test(evsel__hw_names, 2); err = perf_evsel__name_array_test(evsel__hw_names, 1); From de3d5fd83c9b1099b0d207b41a222dc451184a63 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 8 Jul 2021 09:37:01 +0800 Subject: [PATCH 292/426] perf tests: Fix 'Convert perf time to TSC' on core-only system If the atom CPUs are offlined, the 'cpu_atom' is not valid. We don't need the test case for 'cpu_atom'. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210708013701.20347-5-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/perf-time-to-tsc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 85d75b9b25a1..7c56bc1f4cff 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -21,6 +21,7 @@ #include "mmap.h" #include "tests.h" #include "pmu.h" +#include "pmu-hybrid.h" #define CHECK__(x) { \ while ((x) < 0) { \ @@ -93,7 +94,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe * For hybrid "cycles:u", it creates two events. * Init the second evsel here. */ - if (perf_pmu__has_hybrid()) { + if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) { evsel = evsel__next(evsel); evsel->core.attr.comm = 1; evsel->core.attr.disabled = 1; From e0a7ef2a62e4f61a751bccfc79b9e7acb51474de Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Wed, 7 Jul 2021 13:56:52 +0800 Subject: [PATCH 293/426] perf stat: Merge uncore events by default for hybrid platform On a hybrid platform, by default 'perf stat' aggregates and reports the event counts per PMU. For example, # perf stat -e cycles -a true Performance counter stats for 'system wide': 1,400,445 cpu_core/cycles/ 680,881 cpu_atom/cycles/ 0.001770773 seconds time elapsed But for uncore events that's not a suitable method. Uncore has nothing to do with hybrid. So for uncore events, we aggregate event counts from all PMUs and report the counts without PMUs. Before: # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true Performance counter stats for 'system wide': 2,058 uncore_arb_0/event=0x81,umask=0x1/ 2,028 uncore_arb_1/event=0x81,umask=0x1/ 0 uncore_arb_0/event=0x84,umask=0x1/ 0 uncore_arb_1/event=0x84,umask=0x1/ 0.000614498 seconds time elapsed After: # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true Performance counter stats for 'system wide': 3,996 arb/event=0x81,umask=0x1/ 0 arb/event=0x84,umask=0x1/ 0.000630046 seconds time elapsed Of course, we also keep the '--no-merge' working for uncore events. # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ --no-merge true Performance counter stats for 'system wide': 1,952 uncore_arb_0/event=0x81,umask=0x1/ 1,921 uncore_arb_1/event=0x81,umask=0x1/ 0 uncore_arb_0/event=0x84,umask=0x1/ 0 uncore_arb_1/event=0x84,umask=0x1/ 0.000575536 seconds time elapsed Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Kan Liang Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20210707055652.962-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 3 --- tools/perf/util/stat-display.c | 14 +++++++++++++- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d25cb8088e8c..634375937db9 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2445,9 +2445,6 @@ int cmd_stat(int argc, const char **argv) evlist__check_cpu_maps(evsel_list); - if (perf_pmu__has_hybrid()) - stat_config.no_merge = true; - /* * Initialize thread_map with comm names, * so we could print it out on output. diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 83a2bc02df15..588601000f3f 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -596,6 +596,18 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c } } +static bool is_uncore(struct evsel *evsel) +{ + struct perf_pmu *pmu = evsel__find_pmu(evsel); + + return pmu && pmu->is_uncore; +} + +static bool hybrid_uniquify(struct evsel *evsel) +{ + return perf_pmu__has_hybrid() && !is_uncore(evsel); +} + static bool collect_data(struct perf_stat_config *config, struct evsel *counter, void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data, bool first), @@ -604,7 +616,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter, if (counter->merged_stat) return false; cb(config, counter, data, true); - if (config->no_merge) + if (config->no_merge || hybrid_uniquify(counter)) uniquify_event_name(counter); else if (counter->auto_merge_stats) collect_all_aliases(config, counter, cb, data); From 376a947653f6214f397ef1c5aa2b7b7fc7b68c49 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 09:55:30 -0300 Subject: [PATCH 294/426] tools headers UAPI: Sync files changed by the memfd_secret new syscall To pick the changes in this cset: 7bb7f2ac24a028b2 ("arch, mm: wire up memfd_secret system call where relevant") That silences these perf build warnings and add support for those new syscalls in tools such as 'perf trace'. For instance, this is now possible: # perf trace -v -e memfd_secret event qualifier tracepoint filter: (common_pid != 13375 && common_pid != 3713) && (id == 447) ^C# That is the filter expression attached to the raw_syscalls:sys_{enter,exit} tracepoints. $ grep memfd_secret tools/perf/arch/x86/entry/syscalls/syscall_64.tbl 447 common memfd_secret sys_memfd_secret $ This addresses these perf build warnings: Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/unistd.h' differs from latest version at 'arch/arm64/include/uapi/asm/unistd.h' diff -u tools/arch/arm64/include/uapi/asm/unistd.h arch/arm64/include/uapi/asm/unistd.h Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl Cc: Linus Torvalds Cc: Mike Rapoport Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/unistd.h | 1 + tools/include/uapi/asm-generic/unistd.h | 7 ++++++- tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 1 + 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h index f83a70e07df8..ce2ee8f1e361 100644 --- a/tools/arch/arm64/include/uapi/asm/unistd.h +++ b/tools/arch/arm64/include/uapi/asm/unistd.h @@ -20,5 +20,6 @@ #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS #define __ARCH_WANT_SYS_CLONE3 +#define __ARCH_WANT_MEMFD_SECRET #include diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index f211961ce1da..a9d6fcd95f42 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -873,8 +873,13 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) #define __NR_landlock_restrict_self 446 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) +#ifdef __ARCH_WANT_MEMFD_SECRET +#define __NR_memfd_secret 447 +__SYSCALL(__NR_memfd_secret, sys_memfd_secret) +#endif + #undef __NR_syscalls -#define __NR_syscalls 447 +#define __NR_syscalls 448 /* * 32 bit systems traditionally used different diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index af973e400053..f6b57799c1ea 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -368,6 +368,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +447 common memfd_secret sys_memfd_secret # # Due to a historical design error, certain syscalls are numbered differently From 50e98924d72dc730fe1f1646977205adf608dccd Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 13 Jul 2021 11:19:07 +0200 Subject: [PATCH 295/426] libperf: Fix build error with LIBPFM4=1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix build error with LIBPFM4=1: CC util/pfm.o util/pfm.c: In function ‘parse_libpfm_events_option’: util/pfm.c:102:30: error: ‘struct evsel’ has no member named ‘leader’ 102 | evsel->leader = grp_leader; | ^~ Committer notes: There is this entry in 'make -C tools/perf build-test' to test the build with libpfm: $ grep libpfm tools/perf/tests/make make_with_libpfm4 := LIBPFM4=1 run += make_with_libpfm4 $ But the test machine lacked libpfm-devel, now its installed and further cases like this shouldn't happen. Committer testing: Before this patch this fails, after applying it: $ make -C tools/perf build-test make: Entering directory '/var/home/acme/git/perf/tools/perf' - tarpkg: ./tests/perf-targz-src-pkg . make_static: make LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 -j24 DESTDIR=/tmp/tmp.KzFSfvGRQa make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1 make_with_libpfm4_O: make LIBPFM4=1 make_install_prefix_O: make install prefix=/tmp/krava make_no_auxtrace_O: make NO_AUXTRACE=1 $ rpm -q libpfm-devel libpfm-devel-4.11.0-4.fc34.x86_64 $ FIXME: This shows a need for 'build-test' to bail out when a build option is specified that has no required library devel files installed. Fixes: fba7c86601e2e42d ("libperf: Move 'leader' from tools/perf to perf_evsel::leader") Signed-off-by: Heiko Carstens Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210713091907.1555560-1-hca@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pfm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index dd9ed56e0504..756295dedccc 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -99,7 +99,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, grp_leader = evsel; if (grp_evt > -1) { - evsel->leader = grp_leader; + evsel__set_leader(evsel, grp_leader); grp_leader->core.nr_members++; grp_evt++; } From 506c1da44fee32ba1d3a70413289ad58c772bba6 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Tue, 18 May 2021 15:05:50 +0000 Subject: [PATCH 296/426] cifs: use the expiry output of dns_query to schedule next resolution We recently fixed DNS resolution of the server hostname during reconnect. However, server IP address may change, even when the old one continues to server (although sub-optimally). We should schedule the next DNS resolution based on the TTL of the DNS record used for the last resolution. This way, we resolve the server hostname again when a DNS record expires. Signed-off-by: Shyam Prasad N Reviewed-by: Paulo Alcantara (SUSE) Cc: # v5.11+ Signed-off-by: Steve French --- fs/cifs/cifs_dfs_ref.c | 2 +- fs/cifs/cifsglob.h | 4 +++ fs/cifs/connect.c | 55 +++++++++++++++++++++++++++++++++++++++--- fs/cifs/dns_resolve.c | 10 +++++--- fs/cifs/dns_resolve.h | 2 +- fs/cifs/misc.c | 2 +- 6 files changed, 65 insertions(+), 10 deletions(-) diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 57f91311fdaa..fa131da01a5f 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -176,7 +176,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata, } } - rc = dns_resolve_server_name_to_ip(name, &srvIP); + rc = dns_resolve_server_name_to_ip(name, &srvIP, NULL); if (rc < 0) { cifs_dbg(FYI, "%s: Failed to resolve server part of %s to IP: %d\n", __func__, name, rc); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 3c2e117bb926..ade7080f7eaa 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -75,6 +75,9 @@ #define SMB_ECHO_INTERVAL_MAX 600 #define SMB_ECHO_INTERVAL_DEFAULT 60 +/* dns resolution interval in seconds */ +#define SMB_DNS_RESOLVE_INTERVAL_DEFAULT 600 + /* maximum number of PDUs in one compound */ #define MAX_COMPOUND 5 @@ -646,6 +649,7 @@ struct TCP_Server_Info { /* point to the SMBD connection if RDMA is used instead of socket */ struct smbd_connection *smbd_conn; struct delayed_work echo; /* echo ping workqueue job */ + struct delayed_work resolve; /* dns resolution workqueue job */ char *smallbuf; /* pointer to current "small" buffer */ char *bigbuf; /* pointer to current "big" buffer */ /* Total size of this PDU. Only valid from cifs_demultiplex_thread */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 01dc45178f66..f1a7e63ab58f 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -78,6 +78,8 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) int rc; int len; char *unc, *ipaddr = NULL; + time64_t expiry, now; + unsigned long ttl = SMB_DNS_RESOLVE_INTERVAL_DEFAULT; if (!server->hostname) return -EINVAL; @@ -91,13 +93,13 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) } scnprintf(unc, len, "\\\\%s", server->hostname); - rc = dns_resolve_server_name_to_ip(unc, &ipaddr); + rc = dns_resolve_server_name_to_ip(unc, &ipaddr, &expiry); kfree(unc); if (rc < 0) { cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n", __func__, server->hostname, rc); - return rc; + goto requeue_resolve; } spin_lock(&cifs_tcp_ses_lock); @@ -106,7 +108,45 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) spin_unlock(&cifs_tcp_ses_lock); kfree(ipaddr); - return !rc ? -1 : 0; + /* rc == 1 means success here */ + if (rc) { + now = ktime_get_real_seconds(); + if (expiry && expiry > now) + /* + * To make sure we don't use the cached entry, retry 1s + * after expiry. + */ + ttl = (expiry - now + 1); + } + rc = !rc ? -1 : 0; + +requeue_resolve: + cifs_dbg(FYI, "%s: next dns resolution scheduled for %lu seconds in the future\n", + __func__, ttl); + mod_delayed_work(cifsiod_wq, &server->resolve, (ttl * HZ)); + + return rc; +} + + +static void cifs_resolve_server(struct work_struct *work) +{ + int rc; + struct TCP_Server_Info *server = container_of(work, + struct TCP_Server_Info, resolve.work); + + mutex_lock(&server->srv_mutex); + + /* + * Resolve the hostname again to make sure that IP address is up-to-date. + */ + rc = reconn_set_ipaddr_from_hostname(server); + if (rc) { + cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", + __func__, rc); + } + + mutex_unlock(&server->srv_mutex); } #ifdef CONFIG_CIFS_DFS_UPCALL @@ -680,6 +720,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) spin_unlock(&cifs_tcp_ses_lock); cancel_delayed_work_sync(&server->echo); + cancel_delayed_work_sync(&server->resolve); spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; @@ -1260,6 +1301,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) spin_unlock(&cifs_tcp_ses_lock); cancel_delayed_work_sync(&server->echo); + cancel_delayed_work_sync(&server->resolve); if (from_reconnect) /* @@ -1342,6 +1384,7 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx) INIT_LIST_HEAD(&tcp_ses->tcp_ses_list); INIT_LIST_HEAD(&tcp_ses->smb_ses_list); INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); + INIT_DELAYED_WORK(&tcp_ses->resolve, cifs_resolve_server); INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server); mutex_init(&tcp_ses->reconnect_mutex); memcpy(&tcp_ses->srcaddr, &ctx->srcaddr, @@ -1427,6 +1470,12 @@ smbd_connected: /* queue echo request delayed work */ queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval); + /* queue dns resolution delayed work */ + cifs_dbg(FYI, "%s: next dns resolution scheduled for %d seconds in the future\n", + __func__, SMB_DNS_RESOLVE_INTERVAL_DEFAULT); + + queue_delayed_work(cifsiod_wq, &tcp_ses->resolve, (SMB_DNS_RESOLVE_INTERVAL_DEFAULT * HZ)); + return tcp_ses; out_err_crypto_release: diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index d15b82d569ef..8c616aaeb7c4 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -24,6 +24,7 @@ * dns_resolve_server_name_to_ip - Resolve UNC server name to ip address. * @unc: UNC path specifying the server (with '/' as delimiter) * @ip_addr: Where to return the IP address. + * @expiry: Where to return the expiry time for the dns record. * * The IP address will be returned in string form, and the caller is * responsible for freeing it. @@ -31,7 +32,7 @@ * Returns length of result on success, -ve on error. */ int -dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) +dns_resolve_server_name_to_ip(const char *unc, char **ip_addr, time64_t *expiry) { struct sockaddr_storage ss; const char *hostname, *sep; @@ -66,13 +67,14 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) /* Perform the upcall */ rc = dns_query(current->nsproxy->net_ns, NULL, hostname, len, - NULL, ip_addr, NULL, false); + NULL, ip_addr, expiry, false); if (rc < 0) cifs_dbg(FYI, "%s: unable to resolve: %*.*s\n", __func__, len, len, hostname); else - cifs_dbg(FYI, "%s: resolved: %*.*s to %s\n", - __func__, len, len, hostname, *ip_addr); + cifs_dbg(FYI, "%s: resolved: %*.*s to %s expiry %llu\n", + __func__, len, len, hostname, *ip_addr, + expiry ? (*expiry) : 0); return rc; name_is_IP_address: diff --git a/fs/cifs/dns_resolve.h b/fs/cifs/dns_resolve.h index 5be060b82b13..9fa2807ef79e 100644 --- a/fs/cifs/dns_resolve.h +++ b/fs/cifs/dns_resolve.h @@ -12,7 +12,7 @@ #define _DNS_RESOLVE_H #ifdef __KERNEL__ -extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr); +extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr, time64_t *expiry); #endif /* KERNEL */ #endif /* _DNS_RESOLVE_H */ diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 184138b4eb8c..844abeb2b48f 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1187,7 +1187,7 @@ int match_target_ip(struct TCP_Server_Info *server, cifs_dbg(FYI, "%s: target name: %s\n", __func__, target + 2); - rc = dns_resolve_server_name_to_ip(target, &tip); + rc = dns_resolve_server_name_to_ip(target, &tip, NULL); if (rc < 0) goto out; From 50630b3f1ada0bf412d3f28e73bac310448d9d6f Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Tue, 13 Jul 2021 12:22:59 +1000 Subject: [PATCH 297/426] cifs: Do not use the original cruid when following DFS links for multiuser mounts Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=213565 cruid should only be used for the initial mount and after this we should use the current users credentials. Ignore the original cruid mount argument when creating a new context for a multiuser mount following a DFS link. Fixes: 24e0a1eff9e2 ("cifs: switch to new mount api") Cc: stable@vger.kernel.org # 5.11+ Reported-by: Xiaoli Feng Signed-off-by: Ronnie Sahlberg Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/cifs_dfs_ref.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index fa131da01a5f..007427ba75e5 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -211,6 +211,10 @@ char *cifs_compose_mount_options(const char *sb_mountdata, else noff = tkn_e - (sb_mountdata + off) + 1; + if (strncasecmp(sb_mountdata + off, "cruid=", 6) == 0) { + off += noff; + continue; + } if (strncasecmp(sb_mountdata + off, "unc=", 4) == 0) { off += noff; continue; From c9c9c6815f9004ee1ec87401ed0796853bd70f1b Mon Sep 17 00:00:00 2001 From: Hyunchul Lee Date: Mon, 12 Jul 2021 19:34:02 +0900 Subject: [PATCH 298/426] cifs: fix the out of range assignment to bit fields in parse_server_interfaces Because the out of range assignment to bit fields are compiler-dependant, the fields could have wrong value. Signed-off-by: Hyunchul Lee Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index e4c8f603dd58..232d528df230 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -557,8 +557,8 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, p = buf; while (bytes_left >= sizeof(*p)) { info->speed = le64_to_cpu(p->LinkSpeed); - info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE); - info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE); + info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0; + info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE) ? 1 : 0; cifs_dbg(FYI, "%s: adding iface %zu\n", __func__, *iface_count); cifs_dbg(FYI, "%s: speed %zu bps\n", __func__, info->speed); From 9e5c772954406829e928dbe59891d08938ead04b Mon Sep 17 00:00:00 2001 From: Zheyu Ma Date: Wed, 14 Jul 2021 14:54:19 +0000 Subject: [PATCH 299/426] drm/ttm: add a check against null pointer dereference MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When calling ttm_range_man_fini(), 'man' may be uninitialized, which may cause a null pointer dereference bug. Fix this by checking if it is a null pointer. This log reveals it: [ 7.902580 ] BUG: kernel NULL pointer dereference, address: 0000000000000058 [ 7.905721 ] RIP: 0010:ttm_range_man_fini+0x40/0x160 [ 7.911826 ] Call Trace: [ 7.911826 ] radeon_ttm_fini+0x167/0x210 [ 7.911826 ] radeon_bo_fini+0x15/0x40 [ 7.913767 ] rs400_fini+0x55/0x80 [ 7.914358 ] radeon_device_fini+0x3c/0x140 [ 7.914358 ] radeon_driver_unload_kms+0x5c/0xe0 [ 7.914358 ] radeon_driver_load_kms+0x13a/0x200 [ 7.914358 ] ? radeon_driver_unload_kms+0xe0/0xe0 [ 7.914358 ] drm_dev_register+0x1db/0x290 [ 7.914358 ] radeon_pci_probe+0x16a/0x230 [ 7.914358 ] local_pci_probe+0x4a/0xb0 Signed-off-by: Zheyu Ma Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/1626274459-8148-1-git-send-email-zheyuma97@gmail.com Signed-off-by: Christian König --- drivers/gpu/drm/ttm/ttm_range_manager.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c index 03395386e8a7..f4b08a8705b3 100644 --- a/drivers/gpu/drm/ttm/ttm_range_manager.c +++ b/drivers/gpu/drm/ttm/ttm_range_manager.c @@ -181,6 +181,9 @@ int ttm_range_man_fini(struct ttm_device *bdev, struct drm_mm *mm = &rman->mm; int ret; + if (!man) + return 0; + ttm_resource_manager_set_used(man, false); ret = ttm_resource_manager_evict_all(bdev, man); From 14158aa4510439c611759d57b74ac01ebcca0081 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 14 Jul 2021 11:02:37 -0500 Subject: [PATCH 300/426] usb: gadget: fsl_qe_udc: Fix fall-through warning for Clang Fix the following fallthrough warning (powerpc-randconfig): drivers/usb/gadget/udc/fsl_qe_udc.c:589:4: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60ef0750.I8J+C6KAtb0xVOAa%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/usb/gadget/udc/fsl_qe_udc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index 8e8588933628..15db7a3868fe 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -586,6 +586,7 @@ static int qe_ep_init(struct qe_udc *udc, case USB_SPEED_FULL: if (max <= 1023) break; + fallthrough; default: goto en_done; } From afbd0d299289a0faaa605af74982f87ad75468fc Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 14 Jul 2021 11:05:55 -0500 Subject: [PATCH 301/426] dmaengine: mpc512x: Fix fall-through warning for Clang Fix the following fallthrough warning (powerpc-randconfig): drivers/dma/mpc512x_dma.c:816:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60ef0750.I8J+C6KAtb0xVOAa%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- drivers/dma/mpc512x_dma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c index c1a69149c8bf..4a51fdbf5aa9 100644 --- a/drivers/dma/mpc512x_dma.c +++ b/drivers/dma/mpc512x_dma.c @@ -813,6 +813,7 @@ inline bool is_buswidth_valid(u8 buswidth, bool is_mpc8308) case 16: if (is_mpc8308) return false; + break; case 1: case 2: case 4: From d08c84e01afa7a7eee6badab25d5420fa847f783 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 14 Jul 2021 13:06:38 -0300 Subject: [PATCH 302/426] perf sched: Cast PTHREAD_STACK_MIN to int as it may turn into sysconf(__SC_THREAD_STACK_MIN_VALUE) In fedora rawhide the PTHREAD_STACK_MIN define may end up expanded to a sysconf() call, and that will return 'long int', breaking the build: 45 fedora:rawhide : FAIL gcc version 11.1.1 20210623 (Red Hat 11.1.1-6) (GCC) builtin-sched.c: In function 'create_tasks': /git/perf-5.14.0-rc1/tools/include/linux/kernel.h:43:24: error: comparison of distinct pointer types lacks a cast [-Werror] 43 | (void) (&_max1 == &_max2); \ | ^~ builtin-sched.c:673:34: note: in expansion of macro 'max' 673 | (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); | ^~~ cc1: all warnings being treated as errors $ grep __sysconf /usr/include/*/*.h /usr/include/bits/pthread_stack_min-dynamic.h:extern long int __sysconf (int __name) __THROW; /usr/include/bits/pthread_stack_min-dynamic.h:# define PTHREAD_STACK_MIN __sysconf (__SC_THREAD_STACK_MIN_VALUE) /usr/include/bits/time.h:extern long int __sysconf (int); /usr/include/bits/time.h:# define CLK_TCK ((__clock_t) __sysconf (2)) /* 2 is _SC_CLK_TCK */ $ So cast it to int to cope with that. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 954ce2f594e9..aaf1cde476c9 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -670,7 +670,7 @@ static void create_tasks(struct perf_sched *sched) err = pthread_attr_init(&attr); BUG_ON(err); err = pthread_attr_setstacksize(&attr, - (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); + (size_t) max(16 * 1024, (int)PTHREAD_STACK_MIN)); BUG_ON(err); err = pthread_mutex_lock(&sched->start_work_mutex); BUG_ON(err); From 104aba8dd7dca85d82e94aba07e71994ccdaf4cf Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 14 Jul 2021 11:10:40 -0500 Subject: [PATCH 303/426] powerpc/smp: Fix fall-through warning for Clang Fix the following fallthrough warning: arch/powerpc/platforms/powermac/smp.c:149:3: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/60ef0750.I8J+C6KAtb0xVOAa%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva --- arch/powerpc/platforms/powermac/smp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index bdfea6d6ab69..3256a316e884 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -146,6 +146,7 @@ static inline void psurge_clr_ipi(int cpu) switch(psurge_type) { case PSURGE_DUAL: out_8(psurge_sec_intr, ~0); + break; case PSURGE_NONE: break; default: From b7eb335e26a9c7f258c96b3962c283c379d3ede0 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 12 Jul 2021 00:57:54 -0500 Subject: [PATCH 304/426] Makefile: Enable -Wimplicit-fallthrough for Clang With the recent fixes for fallthrough warnings, it is now possible to enable -Wimplicit-fallthrough for Clang. It's important to mention that since we have adopted the use of the pseudo-keyword macro fallthrough; we also want to avoid having more /* fall through */ comments being introduced. Notice that contrary to GCC, Clang doesn't recognize any comments as implicit fall-through markings when the -Wimplicit-fallthrough option is enabled. So, in order to avoid having more comments being introduced, we have to use the option -Wimplicit-fallthrough=5 for GCC, which similar to Clang, will cause a warning in case a code comment is intended to be used as a fall-through marking. Co-developed-by: Kees Cook Signed-off-by: Kees Cook Signed-off-by: Gustavo A. R. Silva --- Makefile | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/Makefile b/Makefile index c3f9bd191b89..eaa692976851 100644 --- a/Makefile +++ b/Makefile @@ -797,12 +797,6 @@ KBUILD_CFLAGS += -Wno-gnu # source of a reference will be _MergedGlobals and not on of the whitelisted names. # See modpost pattern 2 KBUILD_CFLAGS += -mno-global-merge -else - -# Warn about unmarked fall-throughs in switch statement. -# Disabled for clang while comment to attribute conversion happens and -# https://github.com/ClangBuiltLinux/linux/issues/636 is discussed. -KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough,) endif # These warnings generated too much noise in a regular build. @@ -983,6 +977,9 @@ NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) # warn about C99 declaration after statement KBUILD_CFLAGS += -Wdeclaration-after-statement +# Warn about unmarked fall-throughs in switch statement. +KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=5,$(call cc-option,-Wimplicit-fallthrough,)) + # Variable Length Arrays (VLAs) should not be used anywhere in the kernel KBUILD_CFLAGS += -Wvla From f8f0edabcc09fafd695ed2adc0eb825104e35d5c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 1 Jul 2021 08:19:28 +0100 Subject: [PATCH 305/426] KVM: selftests: x86: Address missing vm_install_exception_handler conversions Commit b78f4a59669 ("KVM: selftests: Rename vm_handle_exception") raced with a couple of new x86 tests, missing two vm_handle_exception to vm_install_exception_handler conversions. Help the two broken tests to catch up with the new world. Cc: Andrew Jones CC: Ricardo Koller Cc: Paolo Bonzini Signed-off-by: Marc Zyngier Message-Id: <20210701071928.2971053-1-maz@kernel.org> Reviewed-by: Andrew Jones Reviewed-by: Ricardo Koller Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/x86_64/hyperv_features.c | 2 +- tools/testing/selftests/kvm/x86_64/mmu_role_test.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 42bd658f52a8..af27c7e829c1 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -615,7 +615,7 @@ int main(void) vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); pr_info("Testing access to Hyper-V specific MSRs\n"); guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva), diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c index 523371cf8e8f..da2325fcad87 100644 --- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c @@ -71,7 +71,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val) /* Set up a #PF handler to eat the RSVD #PF and signal all done! */ vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_handle_exception(vm, PF_VECTOR, guest_pf_handler); + vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler); r = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r); From f0414b078dd11641a7a64027c2741396f47718fd Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 24 Jun 2021 17:18:53 -0700 Subject: [PATCH 306/426] Revert "KVM: x86: WARN and reject loading KVM if NX is supported but not enabled" Let KVM load if EFER.NX=0 even if NX is supported, the analysis and testing (or lack thereof) for the non-PAE host case was garbage. If the kernel won't be using PAE paging, .Ldefault_entry in head_32.S skips over the entire EFER sequence. Hopefully that can be changed in the future to allow KVM to require EFER.NX, but the motivation behind KVM's requirement isn't yet merged. Reverting and revisiting the mess at a later date is by far the safest approach. This reverts commit 8bbed95d2cb6e5de8a342d761a89b0a04faed7be. Fixes: 8bbed95d2cb6 ("KVM: x86: WARN and reject loading KVM if NX is supported but not enabled") Signed-off-by: Sean Christopherson Message-Id: <20210625001853.318148-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 17468d983fbd..cf10d196ca65 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10981,9 +10981,6 @@ int kvm_arch_hardware_setup(void *opaque) int r; rdmsrl_safe(MSR_EFER, &host_efer); - if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) && - !(host_efer & EFER_NX))) - return -EIO; if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); From 4bf48e3c0aafd32b960d341c4925b48f416f14a5 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Jun 2021 16:05:46 -0700 Subject: [PATCH 307/426] KVM: x86: Use guest MAXPHYADDR from CPUID.0x8000_0008 iff TDP is enabled Ignore the guest MAXPHYADDR reported by CPUID.0x8000_0008 if TDP, i.e. NPT, is disabled, and instead use the host's MAXPHYADDR. Per AMD'S APM: Maximum guest physical address size in bits. This number applies only to guests using nested paging. When this field is zero, refer to the PhysAddrSize field for the maximum guest physical address size. Fixes: 24c82e576b78 ("KVM: Sanitize cpuid") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210623230552.4027702-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c42613cfb5ba..1a4217b3e185 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -940,8 +940,14 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); unsigned phys_as = entry->eax & 0xff; - if (!g_phys_as) + /* + * Use bare metal's MAXPHADDR if the CPU doesn't report guest + * MAXPHYADDR separately, or if TDP (NPT) is disabled, as the + * guest version "applies only to guests using nested paging". + */ + if (!g_phys_as || !tdp_enabled) g_phys_as = phys_as; + entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); From e39f00f60ebd2e7b295c37a05e6349df656d3eb8 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Jun 2021 16:05:47 -0700 Subject: [PATCH 308/426] KVM: x86: Use kernel's x86_phys_bits to handle reduced MAXPHYADDR Use boot_cpu_data.x86_phys_bits instead of the raw CPUID information to enumerate the MAXPHYADDR for KVM guests when TDP is disabled (the guest version is only relevant to NPT/TDP). When using shadow paging, any reductions to the host's MAXPHYADDR apply to KVM and its guests as well, i.e. using the raw CPUID info will cause KVM to misreport the number of PA bits available to the guest. Unconditionally zero out the "Physical Address bit reduction" entry. For !TDP, the adjustment is already done, and for TDP enumerating the host's reduction is wrong as the reduction does not apply to GPAs. Fixes: 9af9b94068fb ("x86/cpu/AMD: Handle SME reduction in physical address size") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210623230552.4027702-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 1a4217b3e185..ca7866d63e98 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -941,11 +941,18 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) unsigned phys_as = entry->eax & 0xff; /* - * Use bare metal's MAXPHADDR if the CPU doesn't report guest - * MAXPHYADDR separately, or if TDP (NPT) is disabled, as the - * guest version "applies only to guests using nested paging". + * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as + * the guest operates in the same PA space as the host, i.e. + * reductions in MAXPHYADDR for memory encryption affect shadow + * paging, too. + * + * If TDP is enabled but an explicit guest MAXPHYADDR is not + * provided, use the raw bare metal MAXPHYADDR as reductions to + * the HPAs do not affect GPAs. */ - if (!g_phys_as || !tdp_enabled) + if (!tdp_enabled) + g_phys_as = boot_cpu_data.x86_phys_bits; + else if (!g_phys_as) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); @@ -970,12 +977,18 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) case 0x8000001a: case 0x8000001e: break; - /* Support memory encryption cpuid if host supports it */ case 0x8000001F: - if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) + if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; - else + } else { cpuid_entry_override(entry, CPUID_8000_001F_EAX); + + /* + * Enumerate '0' for "PA bits reduction", the adjusted + * MAXPHYADDR is enumerated directly (see 0x80000008). + */ + entry->ebx &= ~GENMASK(11, 6); + } break; /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: From fc9bf2e087efcd81bda2e52d09616d2a1bf982a8 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Jun 2021 16:05:49 -0700 Subject: [PATCH 309/426] KVM: x86/mmu: Do not apply HPA (memory encryption) mask to GPAs Ignore "dynamic" host adjustments to the physical address mask when generating the masks for guest PTEs, i.e. the guest PA masks. The host physical address space and guest physical address space are two different beasts, e.g. even though SEV's C-bit is the same bit location for both host and guest, disabling SME in the host (which clears shadow_me_mask) does not affect the guest PTE->GPA "translation". For non-SEV guests, not dropping bits is the correct behavior. Assuming KVM and userspace correctly enumerate/configure guest MAXPHYADDR, bits that are lost as collateral damage from memory encryption are treated as reserved bits, i.e. KVM will never get to the point where it attempts to generate a gfn using the affected bits. And if userspace wants to create a bogus vCPU, then userspace gets to deal with the fallout of hardware doing odd things with bad GPAs. For SEV guests, not dropping the C-bit is technically wrong, but it's a moot point because KVM can't read SEV guest's page tables in any case since they're always encrypted. Not to mention that the current KVM code is also broken since sme_me_mask does not have to be non-zero for SEV to be supported by KVM. The proper fix would be to teach all of KVM to correctly handle guest private memory, but that's a task for the future. Fixes: d0ec49d4de90 ("kvm/x86/svm: Support Secure Memory Encryption within KVM") Cc: stable@vger.kernel.org Cc: Brijesh Singh Cc: Tom Lendacky Signed-off-by: Sean Christopherson Message-Id: <20210623230552.4027702-5-seanjc@google.com> [Use a new header instead of adding header guards to paging_tmpl.h. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 2 ++ arch/x86/kvm/mmu/paging.h | 14 ++++++++++++++ arch/x86/kvm/mmu/paging_tmpl.h | 4 ++-- arch/x86/kvm/mmu/spte.h | 6 ------ 4 files changed, 18 insertions(+), 8 deletions(-) create mode 100644 arch/x86/kvm/mmu/paging.h diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 00732757cc60..b888385d1933 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -53,6 +53,8 @@ #include #include "trace.h" +#include "paging.h" + extern bool itlb_multihit_kvm_mitigation; int __read_mostly nx_huge_pages = -1; diff --git a/arch/x86/kvm/mmu/paging.h b/arch/x86/kvm/mmu/paging.h new file mode 100644 index 000000000000..de8ab323bb70 --- /dev/null +++ b/arch/x86/kvm/mmu/paging.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Shadow paging constants/helpers that don't need to be #undef'd. */ +#ifndef __KVM_X86_PAGING_H +#define __KVM_X86_PAGING_H + +#define GUEST_PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) +#define PT64_LVL_ADDR_MASK(level) \ + (GUEST_PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT64_LEVEL_BITS))) - 1)) +#define PT64_LVL_OFFSET_MASK(level) \ + (GUEST_PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT64_LEVEL_BITS))) - 1)) +#endif /* __KVM_X86_PAGING_H */ + diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 490a028ddabe..ee044d357b5f 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -24,7 +24,7 @@ #define pt_element_t u64 #define guest_walker guest_walker64 #define FNAME(name) paging##64_##name - #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK + #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl) #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT64_INDEX(addr, level) @@ -57,7 +57,7 @@ #define pt_element_t u64 #define guest_walker guest_walkerEPT #define FNAME(name) ept_##name - #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK + #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl) #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT64_INDEX(addr, level) diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 7a5ce9314107..eb7b227fc6cf 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -38,12 +38,6 @@ static_assert(SPTE_TDP_AD_ENABLED_MASK == 0); #else #define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) #endif -#define PT64_LVL_ADDR_MASK(level) \ - (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ - * PT64_LEVEL_BITS))) - 1)) -#define PT64_LVL_OFFSET_MASK(level) \ - (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ - * PT64_LEVEL_BITS))) - 1)) #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ | shadow_x_mask | shadow_nx_mask | shadow_me_mask) From 76ff371b67cb12fb635396234468abcf6a466f16 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 24 Jun 2021 19:03:54 -0700 Subject: [PATCH 310/426] KVM: SVM: Revert clearing of C-bit on GPA in #NPF handler Don't clear the C-bit in the #NPF handler, as it is a legal GPA bit for non-SEV guests, and for SEV guests the C-bit is dropped before the GPA hits the NPT in hardware. Clearing the bit for non-SEV guests causes KVM to mishandle #NPFs with that collide with the host's C-bit. Although the APM doesn't explicitly state that the C-bit is not reserved for non-SEV, Tom Lendacky confirmed that the following snippet about the effective reduction due to the C-bit does indeed apply only to SEV guests. Note that because guest physical addresses are always translated through the nested page tables, the size of the guest physical address space is not impacted by any physical address space reduction indicated in CPUID 8000_001F[EBX]. If the C-bit is a physical address bit however, the guest physical address space is effectively reduced by 1 bit. And for SEV guests, the APM clearly states that the bit is dropped before walking the nested page tables. If the C-bit is an address bit, this bit is masked from the guest physical address when it is translated through the nested page tables. Consequently, the hypervisor does not need to be aware of which pages the guest has chosen to mark private. Note, the bogus C-bit clearing was removed from legacy #PF handler in commit 6d1b867d0456 ("KVM: SVM: Don't strip the C-bit from CR2 on #PF interception"). Fixes: 0ede79e13224 ("KVM: SVM: Clear C-bit from the page fault address") Cc: Peter Gonda Cc: Brijesh Singh Cc: Tom Lendacky Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210625020354.431829-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8834822c00cd..ca5614a48b21 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1923,7 +1923,7 @@ static int npf_interception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2); + u64 fault_address = svm->vmcb->control.exit_info_2; u64 error_code = svm->vmcb->control.exit_info_1; trace_kvm_page_fault(fault_address, error_code); From 23fa2e46a5556f787ce2ea1a315d3ab93cced204 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Sat, 26 Jun 2021 15:03:04 +0800 Subject: [PATCH 311/426] KVM: mmio: Fix use-after-free Read in kvm_vm_ioctl_unregister_coalesced_mmio BUG: KASAN: use-after-free in kvm_vm_ioctl_unregister_coalesced_mmio+0x7c/0x1ec arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:183 Read of size 8 at addr ffff0000c03a2500 by task syz-executor083/4269 CPU: 5 PID: 4269 Comm: syz-executor083 Not tainted 5.10.0 #7 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x2d0 arch/arm64/kernel/stacktrace.c:132 show_stack+0x28/0x34 arch/arm64/kernel/stacktrace.c:196 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x110/0x164 lib/dump_stack.c:118 print_address_description+0x78/0x5c8 mm/kasan/report.c:385 __kasan_report mm/kasan/report.c:545 [inline] kasan_report+0x148/0x1e4 mm/kasan/report.c:562 check_memory_region_inline mm/kasan/generic.c:183 [inline] __asan_load8+0xb4/0xbc mm/kasan/generic.c:252 kvm_vm_ioctl_unregister_coalesced_mmio+0x7c/0x1ec arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:183 kvm_vm_ioctl+0xe30/0x14c4 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:3755 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __arm64_sys_ioctl+0xf88/0x131c fs/ioctl.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall arch/arm64/kernel/syscall.c:48 [inline] el0_svc_common arch/arm64/kernel/syscall.c:158 [inline] do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:220 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670 Allocated by task 4269: stack_trace_save+0x80/0xb8 kernel/stacktrace.c:121 kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc+0xdc/0x120 mm/kasan/common.c:461 kasan_kmalloc+0xc/0x14 mm/kasan/common.c:475 kmem_cache_alloc_trace include/linux/slab.h:450 [inline] kmalloc include/linux/slab.h:552 [inline] kzalloc include/linux/slab.h:664 [inline] kvm_vm_ioctl_register_coalesced_mmio+0x78/0x1cc arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:146 kvm_vm_ioctl+0x7e8/0x14c4 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:3746 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __arm64_sys_ioctl+0xf88/0x131c fs/ioctl.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall arch/arm64/kernel/syscall.c:48 [inline] el0_svc_common arch/arm64/kernel/syscall.c:158 [inline] do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:220 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670 Freed by task 4269: stack_trace_save+0x80/0xb8 kernel/stacktrace.c:121 kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track+0x38/0x6c mm/kasan/common.c:56 kasan_set_free_info+0x20/0x40 mm/kasan/generic.c:355 __kasan_slab_free+0x124/0x150 mm/kasan/common.c:422 kasan_slab_free+0x10/0x1c mm/kasan/common.c:431 slab_free_hook mm/slub.c:1544 [inline] slab_free_freelist_hook mm/slub.c:1577 [inline] slab_free mm/slub.c:3142 [inline] kfree+0x104/0x38c mm/slub.c:4124 coalesced_mmio_destructor+0x94/0xa4 arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:102 kvm_iodevice_destructor include/kvm/iodev.h:61 [inline] kvm_io_bus_unregister_dev+0x248/0x280 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:4374 kvm_vm_ioctl_unregister_coalesced_mmio+0x158/0x1ec arch/arm64/kvm/../../../virt/kvm/coalesced_mmio.c:186 kvm_vm_ioctl+0xe30/0x14c4 arch/arm64/kvm/../../../virt/kvm/kvm_main.c:3755 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __arm64_sys_ioctl+0xf88/0x131c fs/ioctl.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall arch/arm64/kernel/syscall.c:48 [inline] el0_svc_common arch/arm64/kernel/syscall.c:158 [inline] do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:220 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670 If kvm_io_bus_unregister_dev() return -ENOMEM, we already call kvm_iodevice_destructor() inside this function to delete 'struct kvm_coalesced_mmio_dev *dev' from list and free the dev, but kvm_iodevice_destructor() is called again, it will lead the above issue. Let's check the the return value of kvm_io_bus_unregister_dev(), only call kvm_iodevice_destructor() if the return value is 0. Cc: Paolo Bonzini Cc: kvm@vger.kernel.org Reported-by: Hulk Robot Signed-off-by: Kefeng Wang Message-Id: <20210626070304.143456-1-wangkefeng.wang@huawei.com> Cc: stable@vger.kernel.org Fixes: 5d3c4c79384a ("KVM: Stop looking for coalesced MMIO zones if the bus is destroyed", 2021-04-20) Signed-off-by: Paolo Bonzini --- virt/kvm/coalesced_mmio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index f08f5e82460b..0be80c213f7f 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -186,7 +186,6 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, coalesced_mmio_in_range(dev, zone->addr, zone->size)) { r = kvm_io_bus_unregister_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev); - kvm_iodevice_destructor(&dev->dev); /* * On failure, unregister destroys all devices on the @@ -196,6 +195,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, */ if (r) break; + kvm_iodevice_destructor(&dev->dev); } } From 7234c362ccb3c2228f06f19f93b132de9cfa7ae4 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Mon, 28 Jun 2021 15:43:54 +0800 Subject: [PATCH 312/426] KVM: x86/pmu: Clear anythread deprecated bit when 0xa leaf is unsupported on the SVM The AMD platform does not support the functions Ah CPUID leaf. The returned results for this entry should all remain zero just like the native does: AMD host: 0x0000000a 0x00: eax=0x00000000 ebx=0x00000000 ecx=0x00000000 edx=0x00000000 (uncanny) AMD guest: 0x0000000a 0x00: eax=0x00000000 ebx=0x00000000 ecx=0x00000000 edx=0x00008000 Fixes: cadbaa039b99 ("perf/x86/intel: Make anythread filter support conditional") Signed-off-by: Like Xu Message-Id: <20210628074354.33848-1-likexu@tencent.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index ca7866d63e98..739be5da3bca 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -765,7 +765,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS); edx.split.bit_width_fixed = cap.bit_width_fixed; - edx.split.anythread_deprecated = 1; + if (cap.version) + edx.split.anythread_deprecated = 1; edx.split.reserved1 = 0; edx.split.reserved2 = 0; From 3b0462726e7ef281c35a7a4ae33e93ee2bc9975b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 14 Jul 2021 15:47:49 +0200 Subject: [PATCH 313/426] cgroup: verify that source is a string The following sequence can be used to trigger a UAF: int fscontext_fd = fsopen("cgroup"); int fd_null = open("/dev/null, O_RDONLY); int fsconfig(fscontext_fd, FSCONFIG_SET_FD, "source", fd_null); close_range(3, ~0U, 0); The cgroup v1 specific fs parser expects a string for the "source" parameter. However, it is perfectly legitimate to e.g. specify a file descriptor for the "source" parameter. The fs parser doesn't know what a filesystem allows there. So it's a bug to assume that "source" is always of type fs_value_is_string when it can reasonably also be fs_value_is_file. This assumption in the cgroup code causes a UAF because struct fs_parameter uses a union for the actual value. Access to that union is guarded by the param->type member. Since the cgroup paramter parser didn't check param->type but unconditionally moved param->string into fc->source a close on the fscontext_fd would trigger a UAF during put_fs_context() which frees fc->source thereby freeing the file stashed in param->file causing a UAF during a close of the fd_null. Fix this by verifying that param->type is actually a string and report an error if not. In follow up patches I'll add a new generic helper that can be used here and by other filesystems instead of this error-prone copy-pasta fix. But fixing it in here first makes backporting a it to stable a lot easier. Fixes: 8d2451f4994f ("cgroup1: switch to option-by-option parsing") Reported-by: syzbot+283ce5a46486d6acdbaf@syzkaller.appspotmail.com Cc: Christoph Hellwig Cc: Alexander Viro Cc: Dmitry Vyukov Cc: Cc: syzkaller-bugs Signed-off-by: Christian Brauner Signed-off-by: Linus Torvalds --- kernel/cgroup/cgroup-v1.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index ee93b6e89587..527917c0b30b 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -912,6 +912,8 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { if (strcmp(param->key, "source") == 0) { + if (param->type != fs_value_is_string) + return invalf(fc, "Non-string source"); if (fc->source) return invalf(fc, "Multiple sources not supported"); fc->source = param->string; From d1d488d813703618f0dd93f0e4c4a05928114aa8 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 14 Jul 2021 15:47:50 +0200 Subject: [PATCH 314/426] fs: add vfs_parse_fs_param_source() helper Add a simple helper that filesystems can use in their parameter parser to parse the "source" parameter. A few places open-coded this function and that already caused a bug in the cgroup v1 parser that we fixed. Let's make it harder to get this wrong by introducing a helper which performs all necessary checks. Link: https://syzkaller.appspot.com/bug?id=6312526aba5beae046fdae8f00399f87aab48b12 Cc: Christoph Hellwig Cc: Alexander Viro Cc: Dmitry Vyukov Signed-off-by: Christian Brauner Signed-off-by: Linus Torvalds --- fs/fs_context.c | 54 +++++++++++++++++++++++++------------- include/linux/fs_context.h | 2 ++ kernel/cgroup/cgroup-v1.c | 14 ++++------ 3 files changed, 43 insertions(+), 27 deletions(-) diff --git a/fs/fs_context.c b/fs/fs_context.c index 2834d1afa6e8..de1985eae535 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -79,6 +79,35 @@ static int vfs_parse_sb_flag(struct fs_context *fc, const char *key) return -ENOPARAM; } +/** + * vfs_parse_fs_param_source - Handle setting "source" via parameter + * @fc: The filesystem context to modify + * @param: The parameter + * + * This is a simple helper for filesystems to verify that the "source" they + * accept is sane. + * + * Returns 0 on success, -ENOPARAM if this is not "source" parameter, and + * -EINVAL otherwise. In the event of failure, supplementary error information + * is logged. + */ +int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param) +{ + if (strcmp(param->key, "source") != 0) + return -ENOPARAM; + + if (param->type != fs_value_is_string) + return invalf(fc, "Non-string source"); + + if (fc->source) + return invalf(fc, "Multiple sources"); + + fc->source = param->string; + param->string = NULL; + return 0; +} +EXPORT_SYMBOL(vfs_parse_fs_param_source); + /** * vfs_parse_fs_param - Add a single parameter to a superblock config * @fc: The filesystem context to modify @@ -122,15 +151,9 @@ int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param) /* If the filesystem doesn't take any arguments, give it the * default handling of source. */ - if (strcmp(param->key, "source") == 0) { - if (param->type != fs_value_is_string) - return invalf(fc, "VFS: Non-string source"); - if (fc->source) - return invalf(fc, "VFS: Multiple sources"); - fc->source = param->string; - param->string = NULL; - return 0; - } + ret = vfs_parse_fs_param_source(fc, param); + if (ret != -ENOPARAM) + return ret; return invalf(fc, "%s: Unknown parameter '%s'", fc->fs_type->name, param->key); @@ -504,16 +527,11 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) struct legacy_fs_context *ctx = fc->fs_private; unsigned int size = ctx->data_size; size_t len = 0; + int ret; - if (strcmp(param->key, "source") == 0) { - if (param->type != fs_value_is_string) - return invalf(fc, "VFS: Legacy: Non-string source"); - if (fc->source) - return invalf(fc, "VFS: Legacy: Multiple sources"); - fc->source = param->string; - param->string = NULL; - return 0; - } + ret = vfs_parse_fs_param_source(fc, param); + if (ret != -ENOPARAM) + return ret; if (ctx->param_type == LEGACY_FS_MONOLITHIC_PARAMS) return invalf(fc, "VFS: Legacy: Can't mix monolithic and individual options"); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 37e1e8f7f08d..e2bc16300c82 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -139,6 +139,8 @@ extern int vfs_parse_fs_string(struct fs_context *fc, const char *key, extern int generic_parse_monolithic(struct fs_context *fc, void *data); extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); +extern int vfs_parse_fs_param_source(struct fs_context *fc, + struct fs_parameter *param); /* * sget() wrappers to be called from the ->get_tree() op. diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 527917c0b30b..8d6bf56ed77a 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -911,15 +911,11 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { - if (strcmp(param->key, "source") == 0) { - if (param->type != fs_value_is_string) - return invalf(fc, "Non-string source"); - if (fc->source) - return invalf(fc, "Multiple sources not supported"); - fc->source = param->string; - param->string = NULL; - return 0; - } + int ret; + + ret = vfs_parse_fs_param_source(fc, param); + if (ret != -ENOPARAM) + return ret; for_each_subsys(ss, i) { if (strcmp(param->key, ss->legacy_name)) continue; From fa2c02e5798c17c89cbb3135940086ebe07e5c9f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 14 Jul 2021 14:28:02 -0300 Subject: [PATCH 315/426] tools headers: Remove broken definition of __LITTLE_ENDIAN The linux/kconfig.h file was copied from the kernel but the line where with the generated/autoconf.h include from where the CONFIG_ entries would come from was deleted, as tools/ build system don't create that file, so we ended up always defining just __LITTLE_ENDIAN as CONFIG_CPU_BIG_ENDIAN was nowhere to be found. This in turn ended up breaking the build in some systems where __LITTLE_ENDIAN was already defined, such as the androind NDK. So just ditch that block that depends on the CONFIG_CPU_BIG_ENDIAN define. The kconfig.h file was copied just to get IS_ENABLED() and a 'make -C tools/all' doesn't breaks with this removal. Fixes: 93281c4a96572a34 ("x86/insn: Add an insn_decode() API") Cc: Adrian Hunter Cc: Borislav Petkov Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lore.kernel.org/lkml/YO8hK7lqJcIWuBzx@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/kconfig.h | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tools/include/linux/kconfig.h b/tools/include/linux/kconfig.h index 1555a0c4f345..13b86bd3b746 100644 --- a/tools/include/linux/kconfig.h +++ b/tools/include/linux/kconfig.h @@ -4,12 +4,6 @@ /* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */ -#ifdef CONFIG_CPU_BIG_ENDIAN -#define __BIG_ENDIAN 4321 -#else -#define __LITTLE_ENDIAN 1234 -#endif - #define __ARG_PLACEHOLDER_1 0, #define __take_second_arg(__ignored, val, ...) val From 83d1fc92d4cdd1ea2d229347ddf11ea2aa751059 Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 24 Jun 2021 17:43:02 +0100 Subject: [PATCH 316/426] perf cs-etm: Split Coresight decode by aux records Populate the auxtrace queues using AUX records rather than whole auxtrace buffers so that the decoder is reset between each aux record. This is similar to the auxtrace_queues__process_index() -> auxtrace_queues__add_indexed_event() flow where perf_session__peek_event() is used to read AUXTRACE events out of random positions in the file based on the auxtrace index. But now we loop over all PERF_RECORD_AUX events instead of AUXTRACE buffers. For each PERF_RECORD_AUX event, we find the corresponding AUXTRACE buffer using the index, and add a fragment of that buffer to the auxtrace queues. No other changes to decoding were made, apart from populating the auxtrace queues. The result of decoding is identical to before, except in cases where decoding failed completely, due to not resetting the decoder. The reason for this change is because AUX records are emitted any time tracing is disabled, for example when the process is scheduled out. Because ETM was disabled and enabled again, the decoder also needs to be reset to force the search for a sync packet. Otherwise there would be fatal decoding errors. Testing ======= Testing was done with the following script, to diff the decoding results between the patched and un-patched versions of perf: #!/bin/bash set -ex $1 script -i $3 $4 > split.script $2 script -i $3 $4 > default.script diff split.script default.script | head -n 20 And it was run like this, with various itrace options depending on the quantity of synthesised events: compare.sh ./perf-patched ./perf-default perf-per-cpu-2-threads.data --itrace=i100000ns No changes in output were observed in the following scenarios: * Simple per-cpu perf record -e cs_etm/@tmc_etr0/u top * Per-thread, single thread perf record -e cs_etm/@tmc_etr0/u --per-thread ./threads_C * Per-thread multiple threads (but only one thread collected data): perf record -e cs_etm/@tmc_etr0/u --per-thread --pid 4596,4597 * Per-thread multiple threads (both threads collected data): perf record -e cs_etm/@tmc_etr0/u --per-thread --pid 4596,4597 * Per-cpu explicit threads: perf record -e cs_etm/@tmc_etr0/u --pid 853,854 * System-wide (per-cpu): perf record -e cs_etm/@tmc_etr0/u -a * No data collected (no aux buffers) Can happen with any command when run for a short period * Containing truncated records Can happen with any command * Containing aux records with 0 size Can happen with any command * Snapshot mode (various files with and without buffer wrap) perf record -e cs_etm/@tmc_etr0/u -a --snapshot Some differences were observed in the following scenario: * Snapshot mode (with duplicate buffers) perf record -e cs_etm/@tmc_etr0/u -a --snapshot Fewer samples are generated in snapshot mode if duplicate buffers were gathered because buffers with the same offset are now only added once. This gives different, but more correct results and no duplicate data is decoded any more. Signed-off-by: James Clark Reviewed-by: Mathieu Poirier Tested-by: Leo Yan Cc: Al Grant Cc: Alexander Shishkin Cc: Anshuman Khandual Cc: Branislav Rankov Cc: Denis Nikitin Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Suzuki Poulouse Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: http://lore.kernel.org/lkml/20210624164303.28632-2-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 168 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 167 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 32ad92d3e454..22f8326547eb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2683,6 +2683,172 @@ static u64 *cs_etm__create_meta_blk(u64 *buff_in, int *buff_in_offset, return metadata; } +/** + * Puts a fragment of an auxtrace buffer into the auxtrace queues based + * on the bounds of aux_event, if it matches with the buffer that's at + * file_offset. + * + * Normally, whole auxtrace buffers would be added to the queue. But we + * want to reset the decoder for every PERF_RECORD_AUX event, and the decoder + * is reset across each buffer, so splitting the buffers up in advance has + * the same effect. + */ +static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_offset, size_t sz, + struct perf_record_aux *aux_event, struct perf_sample *sample) +{ + int err; + char buf[PERF_SAMPLE_MAX_SIZE]; + union perf_event *auxtrace_event_union; + struct perf_record_auxtrace *auxtrace_event; + union perf_event auxtrace_fragment; + __u64 aux_offset, aux_size; + + struct cs_etm_auxtrace *etm = container_of(session->auxtrace, + struct cs_etm_auxtrace, + auxtrace); + + /* + * There should be a PERF_RECORD_AUXTRACE event at the file_offset that we got + * from looping through the auxtrace index. + */ + err = perf_session__peek_event(session, file_offset, buf, + PERF_SAMPLE_MAX_SIZE, &auxtrace_event_union, NULL); + if (err) + return err; + auxtrace_event = &auxtrace_event_union->auxtrace; + if (auxtrace_event->header.type != PERF_RECORD_AUXTRACE) + return -EINVAL; + + if (auxtrace_event->header.size < sizeof(struct perf_record_auxtrace) || + auxtrace_event->header.size != sz) { + return -EINVAL; + } + + /* + * In per-thread mode, CPU is set to -1, but TID will be set instead. See + * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match. + */ + if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) || + auxtrace_event->cpu != sample->cpu) + return 1; + + if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) { + /* + * Clamp size in snapshot mode. The buffer size is clamped in + * __auxtrace_mmap__read() for snapshots, so the aux record size doesn't reflect + * the buffer size. + */ + aux_size = min(aux_event->aux_size, auxtrace_event->size); + + /* + * In this mode, the head also points to the end of the buffer so aux_offset + * needs to have the size subtracted so it points to the beginning as in normal mode + */ + aux_offset = aux_event->aux_offset - aux_size; + } else { + aux_size = aux_event->aux_size; + aux_offset = aux_event->aux_offset; + } + + if (aux_offset >= auxtrace_event->offset && + aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) { + /* + * If this AUX event was inside this buffer somewhere, create a new auxtrace event + * based on the sizes of the aux event, and queue that fragment. + */ + auxtrace_fragment.auxtrace = *auxtrace_event; + auxtrace_fragment.auxtrace.size = aux_size; + auxtrace_fragment.auxtrace.offset = aux_offset; + file_offset += aux_offset - auxtrace_event->offset + auxtrace_event->header.size; + + pr_debug3("CS ETM: Queue buffer size: %#"PRI_lx64" offset: %#"PRI_lx64 + " tid: %d cpu: %d\n", aux_size, aux_offset, sample->tid, sample->cpu); + return auxtrace_queues__add_event(&etm->queues, session, &auxtrace_fragment, + file_offset, NULL); + } + + /* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */ + return 1; +} + +static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event, + u64 offset __maybe_unused, void *data __maybe_unused) +{ + struct perf_sample sample; + int ret; + struct auxtrace_index_entry *ent; + struct auxtrace_index *auxtrace_index; + struct evsel *evsel; + size_t i; + + /* Don't care about any other events, we're only queuing buffers for AUX events */ + if (event->header.type != PERF_RECORD_AUX) + return 0; + + if (event->header.size < sizeof(struct perf_record_aux)) + return -EINVAL; + + /* Truncated Aux records can have 0 size and shouldn't result in anything being queued. */ + if (!event->aux.aux_size) + return 0; + + /* + * Parse the sample, we need the sample_id_all data that comes after the event so that the + * CPU or PID can be matched to an AUXTRACE buffer's CPU or PID. + */ + evsel = evlist__event2evsel(session->evlist, event); + if (!evsel) + return -EINVAL; + ret = evsel__parse_sample(evsel, event, &sample); + if (ret) + return ret; + + /* + * Loop through the auxtrace index to find the buffer that matches up with this aux event. + */ + list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) { + for (i = 0; i < auxtrace_index->nr; i++) { + ent = &auxtrace_index->entries[i]; + ret = cs_etm__queue_aux_fragment(session, ent->file_offset, + ent->sz, &event->aux, &sample); + /* + * Stop search on error or successful values. Continue search on + * 1 ('not found') + */ + if (ret != 1) + return ret; + } + } + + /* + * Couldn't find the buffer corresponding to this aux record, something went wrong. Warn but + * don't exit with an error because it will still be possible to decode other aux records. + */ + pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64 + " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu); + return 0; +} + +static int cs_etm__queue_aux_records(struct perf_session *session) +{ + struct auxtrace_index *index = list_first_entry_or_null(&session->auxtrace_index, + struct auxtrace_index, list); + if (index && index->nr > 0) + return perf_session__peek_events(session, session->header.data_offset, + session->header.data_size, + cs_etm__queue_aux_records_cb, NULL); + + /* + * We would get here if there are no entries in the index (either no auxtrace + * buffers or no index at all). Fail silently as there is the possibility of + * queueing them in cs_etm__process_auxtrace_event() if etm->data_queued is still + * false. + * + * In that scenario, buffers will not be split by AUX records. + */ + return 0; +} + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session) { @@ -2883,7 +3049,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (err) goto err_delete_thread; - err = auxtrace_queues__process_index(&etm->queues, session); + err = cs_etm__queue_aux_records(session); if (err) goto err_delete_thread; From 775da83005cb61d4c213c636df9337da05714ff1 Mon Sep 17 00:00:00 2001 From: Jinzhou Su Date: Tue, 13 Jul 2021 09:26:11 +0800 Subject: [PATCH 317/426] drm/amdgpu: add another Renoir DID Add new PCI device id. Signed-off-by: Jinzhou Su Reviewed-by: Huang Rui Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 5.11.x --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 71beb0db0125..abb928894eac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1168,6 +1168,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, /* Renoir */ + {0x1002, 0x15E7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, {0x1002, 0x1638, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, {0x1002, 0x164C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, From 4a5c155a5ab372516a1a5ddd29473f8f696feb79 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 15 Jul 2021 04:02:22 +0700 Subject: [PATCH 318/426] MAINTAINERS: Add Suravee Suthikulpanit as Reviewer for AMD IOMMU (AMD-Vi) To help review changes related to AMD IOMMU. Signed-off-by: Suravee Suthikulpanit Link: https://lore.kernel.org/r/1626296542-30454-1-git-send-email-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index a61f4f3b78a9..f2b60e955593 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -933,6 +933,7 @@ F: drivers/video/fbdev/geode/ AMD IOMMU (AMD-VI) M: Joerg Roedel +R: Suravee Suthikulpanit L: iommu@lists.linux-foundation.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git From 21de80b53b3727c33d0771c5a28114be5803d157 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Fri, 2 Jul 2021 20:29:31 -0500 Subject: [PATCH 319/426] LICENSES/dual/CC-BY-4.0: Git rid of "smart quotes" A couple of exotic quote characters came in with this license text; they can confuse software that is not expecting non-ASCII text. Switch to normal quotes here, with no changes to the actual license text. Reported-by: Rahul T R Signed-off-by: Nishanth Menon CC: Greg Kroah-Hartman Acked-by: Thomas Gleixner Acked-by: Thorsten Leemhuis Acked-by: Randy Dunlap Link: https://lore.kernel.org/r/20210703012931.30604-1-nm@ti.com Signed-off-by: Jonathan Corbet --- LICENSES/dual/CC-BY-4.0 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/LICENSES/dual/CC-BY-4.0 b/LICENSES/dual/CC-BY-4.0 index 45a81b8e4669..869cad3d1643 100644 --- a/LICENSES/dual/CC-BY-4.0 +++ b/LICENSES/dual/CC-BY-4.0 @@ -392,7 +392,7 @@ Section 8 -- Interpretation. Creative Commons is not a party to its public licenses. Notwithstanding, Creative Commons may elect to apply one of its public licenses to material it publishes and in those instances -will be considered the “Licensor.” The text of the Creative Commons +will be considered the "Licensor." The text of the Creative Commons public licenses is dedicated to the public domain under the CC0 Public Domain Dedication. Except for the limited purpose of indicating that material is shared under a Creative Commons public license or as From 842f697776926b06ada93b16658cdd77cc0ef710 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 1 Jul 2021 13:31:52 +0200 Subject: [PATCH 320/426] Documentation/features: Update the ARCH_HAS_TICK_BROADCAST entry Risc-V gained support recently. Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/YN2nqOVHgGDt4Iid@gmail.com Signed-off-by: Jonathan Corbet --- .../features/time/arch-tick-broadcast/arch-support.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/features/time/arch-tick-broadcast/arch-support.txt b/Documentation/features/time/arch-tick-broadcast/arch-support.txt index 8639fe8315f5..8dcaab070c7b 100644 --- a/Documentation/features/time/arch-tick-broadcast/arch-support.txt +++ b/Documentation/features/time/arch-tick-broadcast/arch-support.txt @@ -22,7 +22,7 @@ | openrisc: | TODO | | parisc: | TODO | | powerpc: | ok | - | riscv: | TODO | + | riscv: | ok | | s390: | TODO | | sh: | ok | | sparc: | TODO | From d3fb38266afefc6424d7179c14936c5908d5e2f2 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 1 Jul 2021 13:31:17 +0200 Subject: [PATCH 321/426] Documentation/features: Add THREAD_INFO_IN_TASK feature matrix Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/YN2nhV5F0hBVNPuX@gmail.com Signed-off-by: Jonathan Corbet --- .../core/thread-info-in-task/arch-support.txt | 32 +++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 Documentation/features/core/thread-info-in-task/arch-support.txt diff --git a/Documentation/features/core/thread-info-in-task/arch-support.txt b/Documentation/features/core/thread-info-in-task/arch-support.txt new file mode 100644 index 000000000000..9f0259bbd7df --- /dev/null +++ b/Documentation/features/core/thread-info-in-task/arch-support.txt @@ -0,0 +1,32 @@ +# +# Feature name: thread-info-in-task +# Kconfig: THREAD_INFO_IN_TASK +# description: arch makes use of the core kernel facility to embedd thread_info in task_struct +# + ----------------------- + | arch |status| + ----------------------- + | alpha: | TODO | + | arc: | TODO | + | arm: | TODO | + | arm64: | ok | + | csky: | TODO | + | h8300: | TODO | + | hexagon: | TODO | + | ia64: | TODO | + | m68k: | TODO | + | microblaze: | TODO | + | mips: | TODO | + | nds32: | ok | + | nios2: | TODO | + | openrisc: | TODO | + | parisc: | TODO | + | powerpc: | ok | + | riscv: | ok | + | s390: | ok | + | sh: | TODO | + | sparc: | TODO | + | um: | TODO | + | x86: | ok | + | xtensa: | TODO | + ----------------------- From 530c4374e21ae750c5fa5aa67b36a97635ddb379 Mon Sep 17 00:00:00 2001 From: Hu Haowen Date: Sun, 20 Jun 2021 09:04:44 +0800 Subject: [PATCH 322/426] docs/zh_CN: add a missing space character "LinusTorvalds" is not pretty. Replace it with "Linus Torvalds". Signed-off-by: Hu Haowen Link: https://lore.kernel.org/r/20210620010444.24813-1-src.res@email.cn Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/process/2.Process.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/translations/zh_CN/process/2.Process.rst b/Documentation/translations/zh_CN/process/2.Process.rst index 229629e305ca..4a6ed0219494 100644 --- a/Documentation/translations/zh_CN/process/2.Process.rst +++ b/Documentation/translations/zh_CN/process/2.Process.rst @@ -47,7 +47,7 @@ （顺便说一句，值得注意的是，合并窗口期间集成的更改并不是凭空产生的；它们是经 提前收集、测试和分级的。稍后将详细描述该过程的工作方式。） -合并窗口持续大约两周。在这段时间结束时，LinusTorvalds将声明窗口已关闭，并 +合并窗口持续大约两周。在这段时间结束时，Linus Torvalds将声明窗口已关闭，并 释放第一个“rc”内核。例如，对于目标为5.6的内核，在合并窗口结束时发生的释放 将被称为5.6-rc1。-rc1 版本是一个信号，表示合并新特性的时间已经过去，稳定下一 个内核的时间已经到来。 @@ -168,7 +168,7 @@ Greg Kroah-Hartman领导。稳定团队将使用5.x.y编号方案不定期地发 补丁如何进入内核 ---------------- -只有一个人可以将补丁合并到主线内核存储库中：LinusTorvalds。但是，在进入 +只有一个人可以将补丁合并到主线内核存储库中：Linus Torvalds。但是，在进入 2.6.38内核的9500多个补丁中，只有112个（大约1.3%）是由Linus自己直接选择的。 内核项目已经发展到一个没有一个开发人员可以在没有支持的情况下检查和选择每个 补丁的规模。内核开发人员处理这种增长的方式是使用围绕信任链构建的助理系统。 From d549c66766ee42175e2f4a47219b4103ddab4ffa Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Tue, 22 Jun 2021 13:33:27 +0200 Subject: [PATCH 323/426] dt-bindings: net: dsa: sja1105: Fix indentation warnings Some of the lines aren't properly indented, causing yamllint to warn about them: .../nxp,sja1105.yaml:70:17: [warning] wrong indentation: expected 18 but found 16 (indentation) Use the proper indentation to fix those warnings. Signed-off-by: Thierry Reding Fixes: 070f5b701d559ae1 ("dt-bindings: net: dsa: sja1105: add SJA1110 bindings") Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20210622113327.3613595-1-thierry.reding@gmail.com Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml index 0b8a05dd52e6..f978f8719d8e 100644 --- a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml +++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml @@ -67,8 +67,8 @@ properties: reg: oneOf: - enum: - - 0 - - 1 + - 0 + - 1 required: - compatible From 004d62eb4e57db3c391ed0df007cc11c93b6fbeb Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Thu, 1 Jul 2021 22:55:00 +0300 Subject: [PATCH 324/426] kvm: debugfs: fix memory leak in kvm_create_vm_debugfs In commit bc9e9e672df9 ("KVM: debugfs: Reuse binary stats descriptors") loop for filling debugfs_stat_data was copy-pasted 2 times, but in the second loop pointers are saved over pointers allocated in the first loop. All this causes is a memory leak, fix it. Fixes: bc9e9e672df9 ("KVM: debugfs: Reuse binary stats descriptors") Signed-off-by: Pavel Skripkin Reviewed-by: Jing Zhang Message-Id: <20210701195500.27097-1-paskripkin@gmail.com> Reviewed-by: Jing Zhang Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f7445c3bcd90..6980dabe9df5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -935,7 +935,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) stat_data->kvm = kvm; stat_data->desc = pdesc; stat_data->kind = KVM_STAT_VCPU; - kvm->debugfs_stat_data[i] = stat_data; + kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); From 6f2f86ec28fb68cf6a342767a35f7b13703aa96f Mon Sep 17 00:00:00 2001 From: Ricardo Koller Date: Fri, 2 Jul 2021 13:10:42 -0700 Subject: [PATCH 325/426] KVM: selftests: Address extra memslot parameters in vm_vaddr_alloc Commit a75a895e6457 ("KVM: selftests: Unconditionally use memslot 0 for vaddr allocations") removed the memslot parameters from vm_vaddr_alloc. It addressed all callers except one under lib/aarch64/, due to a race with commit e3db7579ef35 ("KVM: selftests: Add exception handling support for aarch64") Fix the vm_vaddr_alloc call in lib/aarch64/processor.c. Reported-by: Zenghui Yu Signed-off-by: Ricardo Koller Message-Id: <20210702201042.4036162-1-ricarkol@google.com> Reviewed-by: Eric Auger Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/lib/aarch64/processor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 9f49f6caafe5..632b74d6b3ca 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -401,7 +401,7 @@ unexpected_exception: void vm_init_descriptor_tables(struct kvm_vm *vm) { vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers), - vm->page_size, 0, 0); + vm->page_size); *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; } From f85d40160691881a17a397c448d799dfc90987ba Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 29 Jun 2021 01:26:32 +0800 Subject: [PATCH 326/426] KVM: X86: Disable hardware breakpoints unconditionally before kvm_x86->run() When the host is using debug registers but the guest is not using them nor is the guest in guest-debug state, the kvm code does not reset the host debug registers before kvm_x86->run(). Rather, it relies on the hardware vmentry instruction to automatically reset the dr7 registers which ensures that the host breakpoints do not affect the guest. This however violates the non-instrumentable nature around VM entry and exit; for example, when a host breakpoint is set on vcpu->arch.cr2, Another issue is consistency. When the guest debug registers are active, the host breakpoints are reset before kvm_x86->run(). But when the guest debug registers are inactive, the host breakpoints are delayed to be disabled. The host tracing tools may see different results depending on what the guest is doing. To fix the problems, we clear %db7 unconditionally before kvm_x86->run() if the host has set any breakpoints, no matter if the guest is using them or not. Signed-off-by: Lai Jiangshan Message-Id: <20210628172632.81029-1-jiangshanlai@gmail.com> Cc: stable@vger.kernel.org [Only clear %db7 instead of reloading all debug registers. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cf10d196ca65..c471b1375f36 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9597,6 +9597,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[3], 3); set_debugreg(vcpu->arch.dr6, 6); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; + } else if (unlikely(hw_breakpoint_active())) { + set_debugreg(0, 7); } for (;;) { From c0e1303ed4cc9e7ce39f106b471ad92ca559e3d3 Mon Sep 17 00:00:00 2001 From: Yu Zhang Date: Thu, 8 Jul 2021 07:57:02 +0800 Subject: [PATCH 327/426] KVM: VMX: Remove vmx_msr_index from vmx.h vmx_msr_index was used to record the list of MSRs which can be lazily restored when kvm returns to userspace. It is now reimplemented as kvm_uret_msrs_list, a common x86 list which is only used inside x86.c. So just remove the obsolete declaration in vmx.h. Signed-off-by: Yu Zhang Message-Id: <20210707235702.31595-1-yu.c.zhang@linux.intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 3979a947933a..db88ed4f2121 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -14,8 +14,6 @@ #include "vmx_ops.h" #include "cpuid.h" -extern const u32 vmx_msr_index[]; - #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 #define MSR_TYPE_RW 3 From 991afbbee8ac93b055a27477278a5fb556af1ff4 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Wed, 7 Jul 2021 15:50:58 +0300 Subject: [PATCH 328/426] KVM: SVM: #SMI interception must not skip the instruction Commit 5ff3a351f687 ("KVM: x86: Move trivial instruction-based exit handlers to common code"), unfortunately made a mistake of treating nop_on_interception and nop_interception in the same way. Former does truly nothing while the latter skips the instruction. SMI VM exit handler should do nothing. (SMI itself is handled by the host when we do STGI) Fixes: 5ff3a351f687 ("KVM: x86: Move trivial instruction-based exit handlers to common code") Signed-off-by: Maxim Levitsky Message-Id: <20210707125100.677203-2-mlevitsk@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index ca5614a48b21..80790faf6370 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2106,6 +2106,11 @@ static int nmi_interception(struct kvm_vcpu *vcpu) return 1; } +static int smi_interception(struct kvm_vcpu *vcpu) +{ + return 1; +} + static int intr_interception(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; @@ -3080,7 +3085,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_EXCP_BASE + GP_VECTOR] = gp_interception, [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, - [SVM_EXIT_SMI] = kvm_emulate_as_nop, + [SVM_EXIT_SMI] = smi_interception, [SVM_EXIT_INIT] = kvm_emulate_as_nop, [SVM_EXIT_VINTR] = interrupt_window_interception, [SVM_EXIT_RDPMC] = kvm_emulate_rdpmc, From 896707c212d440a6863ce0a3930c8a609e24497d Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Wed, 7 Jul 2021 15:50:59 +0300 Subject: [PATCH 329/426] KVM: SVM: remove INIT intercept handler Kernel never sends real INIT even to CPUs, other than on boot. Thus INIT interception is an error which should be caught by a check for an unknown VMexit reason. On top of that, the current INIT VM exit handler skips the current instruction which is wrong. That was added in commit 5ff3a351f687 ("KVM: x86: Move trivial instruction-based exit handlers to common code"). Fixes: 5ff3a351f687 ("KVM: x86: Move trivial instruction-based exit handlers to common code") Signed-off-by: Maxim Levitsky Message-Id: <20210707125100.677203-3-mlevitsk@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 80790faf6370..18aa4d45cc64 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3086,7 +3086,6 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, [SVM_EXIT_SMI] = smi_interception, - [SVM_EXIT_INIT] = kvm_emulate_as_nop, [SVM_EXIT_VINTR] = interrupt_window_interception, [SVM_EXIT_RDPMC] = kvm_emulate_rdpmc, [SVM_EXIT_CPUID] = kvm_emulate_cpuid, From 4b639a9f82fcf15497d1613a29aa1df798a24029 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Wed, 7 Jul 2021 15:51:00 +0300 Subject: [PATCH 330/426] KVM: SVM: add module param to control the #SMI interception In theory there are no side effects of not intercepting #SMI, because then #SMI becomes transparent to the OS and the KVM. Plus an observation on recent Zen2 CPUs reveals that these CPUs ignore #SMI interception and never deliver #SMI VMexits. This is also useful to test nested KVM to see that L1 handles #SMIs correctly in case when L1 doesn't intercept #SMI. Finally the default remains the same, the SMI are intercepted by default thus this patch doesn't have any effect unless non default module param value is used. Signed-off-by: Maxim Levitsky Message-Id: <20210707125100.677203-4-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 4 ++++ arch/x86/kvm/svm/svm.c | 10 +++++++++- arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 14 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 21d03e3a5dfd..2884c54a72bb 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -154,6 +154,10 @@ void recalc_intercepts(struct vcpu_svm *svm) for (i = 0; i < MAX_INTERCEPT; i++) c->intercepts[i] |= g->intercepts[i]; + + /* If SMI is not intercepted, ignore guest SMI intercept as well */ + if (!intercept_smi) + vmcb_clr_intercept(c, INTERCEPT_SMI); } static void copy_vmcb_control_area(struct vmcb_control_area *dst, diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 18aa4d45cc64..63488d3beb5b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -198,6 +198,11 @@ module_param(avic, bool, 0444); bool __read_mostly dump_invalid_vmcb; module_param(dump_invalid_vmcb, bool, 0644); + +bool intercept_smi = true; +module_param(intercept_smi, bool, 0444); + + static bool svm_gp_erratum_intercept = true; static u8 rsm_ins_bytes[] = "\x0f\xaa"; @@ -1185,7 +1190,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm_set_intercept(svm, INTERCEPT_INTR); svm_set_intercept(svm, INTERCEPT_NMI); - svm_set_intercept(svm, INTERCEPT_SMI); + + if (intercept_smi) + svm_set_intercept(svm, INTERCEPT_SMI); + svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0); svm_set_intercept(svm, INTERCEPT_RDPMC); svm_set_intercept(svm, INTERCEPT_CPUID); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f89b623bb591..8cb3bd59c5ea 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -31,6 +31,7 @@ #define MSRPM_OFFSETS 16 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; +extern bool intercept_smi; /* * Clean bits in VMCB. From b4a693924aab93f3747465b2261add46c82c3220 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 6 May 2021 10:58:25 -0700 Subject: [PATCH 331/426] KVM: SVM: Return -EFAULT if copy_to_user() for SEV mig packet header fails Return -EFAULT if copy_to_user() fails; if accessing user memory faults, copy_to_user() returns the number of bytes remaining, not an error code. Reported-by: Dan Carpenter Cc: Steve Rutherford Cc: Brijesh Singh Cc: Ashish Kalra Fixes: d3d1af85e2c7 ("KVM: SVM: Add KVM_SEND_UPDATE_DATA command") Signed-off-by: Sean Christopherson Message-Id: <20210506175826.2166383-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 8d36f0c73071..3dc3e2897804 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1309,8 +1309,9 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) } /* Copy packet header to userspace. */ - ret = copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr, - params.hdr_len); + if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr, + params.hdr_len)) + ret = -EFAULT; e_free_trans_data: kfree(trans_data); From c7a1b2b678c54ac19320daf525038d0e2e43ca7c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 6 May 2021 10:58:26 -0700 Subject: [PATCH 332/426] KVM: SVM: Fix sev_pin_memory() error checks in SEV migration utilities Use IS_ERR() instead of checking for a NULL pointer when querying for sev_pin_memory() failures. sev_pin_memory() always returns an error code cast to a pointer, or a valid pointer; it never returns NULL. Reported-by: Dan Carpenter Cc: Steve Rutherford Cc: Brijesh Singh Cc: Ashish Kalra Fixes: d3d1af85e2c7 ("KVM: SVM: Add KVM_SEND_UPDATE_DATA command") Fixes: 15fb7de1a7f5 ("KVM: SVM: Add KVM_SEV_RECEIVE_UPDATE_DATA command") Signed-off-by: Sean Christopherson Message-Id: <20210506175826.2166383-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 3dc3e2897804..02d60d7f903d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1271,8 +1271,8 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Pin guest memory */ guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, PAGE_SIZE, &n, 0); - if (!guest_page) - return -EFAULT; + if (IS_ERR(guest_page)) + return PTR_ERR(guest_page); /* allocate memory for header and transport buffer */ ret = -ENOMEM; @@ -1463,11 +1463,12 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) data.trans_len = params.trans_len; /* Pin guest memory */ - ret = -EFAULT; guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, PAGE_SIZE, &n, 0); - if (!guest_page) + if (IS_ERR(guest_page)) { + ret = PTR_ERR(guest_page); goto e_free_trans; + } /* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */ data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; From fce7e152ffc8f89d02a80617b16c7aa1527847c8 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:20 +0200 Subject: [PATCH 333/426] KVM: nSVM: Check the value written to MSR_VM_HSAVE_PA APM states that #GP is raised upon write to MSR_VM_HSAVE_PA when the supplied address is not page-aligned or is outside of "maximum supported physical address for this implementation". page_address_valid() check seems suitable. Also, forcefully page-align the address when it's written from VMM. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-2-vkuznets@redhat.com> Cc: stable@vger.kernel.org Reviewed-by: Maxim Levitsky [Add comment about behavior for host-provided values. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 63488d3beb5b..b6e91de891cb 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2954,7 +2954,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm_disable_lbrv(vcpu); break; case MSR_VM_HSAVE_PA: - svm->nested.hsave_msr = data; + /* + * Old kernels did not validate the value written to + * MSR_VM_HSAVE_PA. Allow KVM_SET_MSR to set an invalid + * value to allow live migrating buggy or malicious guests + * originating from those kernels. + */ + if (!msr->host_initiated && !page_address_valid(vcpu, data)) + return 1; + + svm->nested.hsave_msr = data & PAGE_MASK; break; case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); From fb79f566e4c99db8647cf0435e3732f12e856ab0 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:21 +0200 Subject: [PATCH 334/426] KVM: nSVM: Check that VM_HSAVE_PA MSR was set before VMRUN APM states that "The address written to the VM_HSAVE_PA MSR, which holds the address of the page used to save the host state on a VMRUN, must point to a hypervisor-owned page. If this check fails, the WRMSR will fail with a #GP(0) exception. Note that a value of 0 is not considered valid for the VM_HSAVE_PA MSR and a VMRUN that is attempted while the HSAVE_PA is 0 will fail with a #GP(0) exception." svm_set_msr() already checks that the supplied address is valid, so only check for '0' is missing. Add it to nested_svm_vmrun(). Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-3-vkuznets@redhat.com> Reviewed-by: Maxim Levitsky Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 2884c54a72bb..ec16a06f9aa8 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -622,6 +622,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) struct kvm_host_map map; u64 vmcb12_gpa; + if (!svm->nested.hsave_msr) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if (is_smm(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; From 0a758290762cf6fb69ad09712ac834cd4f07504f Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:22 +0200 Subject: [PATCH 335/426] KVM: nSVM: Introduce svm_copy_vmrun_state() Separate the code setting non-VMLOAD-VMSAVE state from svm_set_nested_state() into its own function. This is going to be re-used from svm_enter_smm()/svm_leave_smm(). Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-4-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 40 +++++++++++++++++++++------------------ arch/x86/kvm/svm/svm.h | 2 ++ 2 files changed, 24 insertions(+), 18 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index ec16a06f9aa8..c4296fb4b8be 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -701,6 +701,27 @@ out: return ret; } +/* Copy state save area fields which are handled by VMRUN */ +void svm_copy_vmrun_state(struct vmcb_save_area *from_save, + struct vmcb_save_area *to_save) +{ + to_save->es = from_save->es; + to_save->cs = from_save->cs; + to_save->ss = from_save->ss; + to_save->ds = from_save->ds; + to_save->gdtr = from_save->gdtr; + to_save->idtr = from_save->idtr; + to_save->rflags = from_save->rflags | X86_EFLAGS_FIXED; + to_save->efer = from_save->efer; + to_save->cr0 = from_save->cr0; + to_save->cr3 = from_save->cr3; + to_save->cr4 = from_save->cr4; + to_save->rax = from_save->rax; + to_save->rsp = from_save->rsp; + to_save->rip = from_save->rip; + to_save->cpl = 0; +} + void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) { to_vmcb->save.fs = from_vmcb->save.fs; @@ -1364,28 +1385,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; - svm->vmcb01.ptr->save.es = save->es; - svm->vmcb01.ptr->save.cs = save->cs; - svm->vmcb01.ptr->save.ss = save->ss; - svm->vmcb01.ptr->save.ds = save->ds; - svm->vmcb01.ptr->save.gdtr = save->gdtr; - svm->vmcb01.ptr->save.idtr = save->idtr; - svm->vmcb01.ptr->save.rflags = save->rflags | X86_EFLAGS_FIXED; - svm->vmcb01.ptr->save.efer = save->efer; - svm->vmcb01.ptr->save.cr0 = save->cr0; - svm->vmcb01.ptr->save.cr3 = save->cr3; - svm->vmcb01.ptr->save.cr4 = save->cr4; - svm->vmcb01.ptr->save.rax = save->rax; - svm->vmcb01.ptr->save.rsp = save->rsp; - svm->vmcb01.ptr->save.rip = save->rip; - svm->vmcb01.ptr->save.cpl = 0; - + svm_copy_vmrun_state(save, &svm->vmcb01.ptr->save); nested_load_control_from_vmcb12(svm, ctl); svm_switch_vmcb(svm, &svm->nested.vmcb02); - nested_vmcb02_prepare_control(svm); - kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); ret = 0; out_free: diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 8cb3bd59c5ea..fe87fd68b73b 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -464,6 +464,8 @@ void svm_leave_nested(struct vcpu_svm *svm); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct kvm_vcpu *vcpu); +void svm_copy_vmrun_state(struct vmcb_save_area *from_save, + struct vmcb_save_area *to_save); void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb); int nested_svm_vmexit(struct vcpu_svm *svm); From 37be407b2ce807179108eeac788805848fe048f1 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:23 +0200 Subject: [PATCH 336/426] KVM: nSVM: Fix L1 state corruption upon return from SMM VMCB split commit 4995a3685f1b ("KVM: SVM: Use a separate vmcb for the nested L2 guest") broke return from SMM when we entered there from guest (L2) mode. Gen2 WS2016/Hyper-V is known to do this on boot. The problem manifests itself like this: kvm_exit: reason EXIT_RSM rip 0x7ffbb280 info 0 0 kvm_emulate_insn: 0:7ffbb280: 0f aa kvm_smm_transition: vcpu 0: leaving SMM, smbase 0x7ffb3000 kvm_nested_vmrun: rip: 0x000000007ffbb280 vmcb: 0x0000000008224000 nrip: 0xffffffffffbbe119 int_ctl: 0x01020000 event_inj: 0x00000000 npt: on kvm_nested_intercepts: cr_read: 0000 cr_write: 0010 excp: 40060002 intercepts: fd44bfeb 0000217f 00000000 kvm_entry: vcpu 0, rip 0xffffffffffbbe119 kvm_exit: reason EXIT_NPF rip 0xffffffffffbbe119 info 200000006 1ab000 kvm_nested_vmexit: vcpu 0 reason npf rip 0xffffffffffbbe119 info1 0x0000000200000006 info2 0x00000000001ab000 intr_info 0x00000000 error_code 0x00000000 kvm_page_fault: address 1ab000 error_code 6 kvm_nested_vmexit_inject: reason EXIT_NPF info1 200000006 info2 1ab000 int_info 0 int_info_err 0 kvm_entry: vcpu 0, rip 0x7ffbb280 kvm_exit: reason EXIT_EXCP_GP rip 0x7ffbb280 info 0 0 kvm_emulate_insn: 0:7ffbb280: 0f aa kvm_inj_exception: #GP (0x0) Note: return to L2 succeeded but upon first exit to L1 its RIP points to 'RSM' instruction but we're not in SMM. The problem appears to be that VMCB01 gets irreversibly destroyed during SMM execution. Previously, we used to have 'hsave' VMCB where regular (pre-SMM) L1's state was saved upon nested_svm_vmexit() but now we just switch to VMCB01 from VMCB02. Pre-split (working) flow looked like: - SMM is triggered during L2's execution - L2's state is pushed to SMRAM - nested_svm_vmexit() restores L1's state from 'hsave' - SMM -> RSM - enter_svm_guest_mode() switches to L2 but keeps 'hsave' intact so we have pre-SMM (and pre L2 VMRUN) L1's state there - L2's state is restored from SMRAM - upon first exit L1's state is restored from L1. This was always broken with regards to svm_get_nested_state()/ svm_set_nested_state(): 'hsave' was never a part of what's being save and restored so migration happening during SMM triggered from L2 would never restore L1's state correctly. Post-split flow (broken) looks like: - SMM is triggered during L2's execution - L2's state is pushed to SMRAM - nested_svm_vmexit() switches to VMCB01 from VMCB02 - SMM -> RSM - enter_svm_guest_mode() switches from VMCB01 to VMCB02 but pre-SMM VMCB01 is already lost. - L2's state is restored from SMRAM - upon first exit L1's state is restored from VMCB01 but it is corrupted (reflects the state during 'RSM' execution). VMX doesn't have this problem because unlike VMCB, VMCS keeps both guest and host state so when we switch back to VMCS02 L1's state is intact there. To resolve the issue we need to save L1's state somewhere. We could've created a third VMCB for SMM but that would require us to modify saved state format. L1's architectural HSAVE area (pointed by MSR_VM_HSAVE_PA) seems appropriate: L0 is free to save any (or none) of L1's state there. Currently, KVM does 'none'. Note, for nested state migration to succeed, both source and destination hypervisors must have the fix. We, however, don't need to create a new flag indicating the fact that HSAVE area is now populated as migration during SMM triggered from L2 was always broken. Fixes: 4995a3685f1b ("KVM: SVM: Use a separate vmcb for the nested L2 guest") Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b6e91de891cb..cf8471890266 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4309,6 +4309,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_host_map map_save; int ret; if (is_guest_mode(vcpu)) { @@ -4324,6 +4325,29 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) ret = nested_svm_vmexit(svm); if (ret) return ret; + + /* + * KVM uses VMCB01 to store L1 host state while L2 runs but + * VMCB01 is going to be used during SMM and thus the state will + * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save + * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the + * format of the area is identical to guest save area offsetted + * by 0x400 (matches the offset of 'struct vmcb_save_area' + * within 'struct vmcb'). Note: HSAVE area may also be used by + * L1 hypervisor to save additional host context (e.g. KVM does + * that, see svm_prepare_guest_switch()) which must be + * preserved. + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; + + BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); + + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, + map_save.hva + 0x400); + + kvm_vcpu_unmap(vcpu, &map_save, true); } return 0; } @@ -4331,7 +4355,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_host_map map; + struct kvm_host_map map, map_save; int ret = 0; if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { @@ -4355,6 +4379,19 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, map.hva); kvm_vcpu_unmap(vcpu, &map, true); + + /* + * Restore L1 host state from L1 HSAVE area as VMCB01 was + * used during SMM (see svm_enter_smm()) + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; + + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); + + kvm_vcpu_unmap(vcpu, &map_save, true); } } From bb00bd9c0862558c6528e3ac97470aee222436ef Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:24 +0200 Subject: [PATCH 337/426] KVM: nSVM: Restore nested control upon leaving SMM If the VM was migrated while in SMM, no nested state was saved/restored, and therefore svm_leave_smm has to load both save and control area of the vmcb12. Save area is already loaded from HSAVE area, so now load the control area as well from the vmcb12. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-6-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 4 ++-- arch/x86/kvm/svm/svm.c | 7 ++++++- arch/x86/kvm/svm/svm.h | 2 ++ 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index c4296fb4b8be..3bd09c50c98b 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -308,8 +308,8 @@ static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu, return true; } -static void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control) +void nested_load_control_from_vmcb12(struct vcpu_svm *svm, + struct vmcb_control_area *control) { copy_vmcb_control_area(&svm->nested.ctl, control); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index cf8471890266..664d20f0689c 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4362,6 +4362,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); + struct vmcb *vmcb12; if (guest) { if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) @@ -4377,7 +4378,11 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) if (svm_allocate_nested(svm)) return 1; - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, map.hva); + vmcb12 = map.hva; + + nested_load_control_from_vmcb12(svm, &vmcb12->control); + + ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12); kvm_vcpu_unmap(vcpu, &map, true); /* diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index fe87fd68b73b..7e2090752d8f 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -482,6 +482,8 @@ int nested_svm_check_permissions(struct kvm_vcpu *vcpu); int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); +void nested_load_control_from_vmcb12(struct vcpu_svm *svm, + struct vmcb_control_area *control); void nested_sync_control_from_vmcb02(struct vcpu_svm *svm); void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm); void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); From d951b2210c1ad2dc08345bb8d97e5a172a15261e Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 28 Jun 2021 12:44:25 +0200 Subject: [PATCH 338/426] KVM: selftests: smm_test: Test SMM enter from L2 Two additional tests are added: - SMM triggered from L2 does not currupt L1 host state. - Save/restore during SMM triggered from L2 does not corrupt guest/host state. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210628104425.391276-7-vkuznets@redhat.com> Reviewed-by: Maxim Levitsky Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/x86_64/smm_test.c | 70 +++++++++++++++++-- 1 file changed, 64 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index c1f831803ad2..d0fe2fdce58c 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -53,15 +53,28 @@ static inline void sync_with_host(uint64_t phase) : "+a" (phase)); } -void self_smi(void) +static void self_smi(void) { x2apic_write_reg(APIC_ICR, APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI); } -void guest_code(void *arg) +static void l2_guest_code(void) { + sync_with_host(8); + + sync_with_host(10); + + vmcall(); +} + +static void guest_code(void *arg) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; uint64_t apicbase = rdmsr(MSR_IA32_APICBASE); + struct svm_test_data *svm = arg; + struct vmx_pages *vmx_pages = arg; sync_with_host(1); @@ -74,21 +87,50 @@ void guest_code(void *arg) sync_with_host(4); if (arg) { - if (cpu_has_svm()) - generic_svm_setup(arg, NULL, NULL); - else - GUEST_ASSERT(prepare_for_vmx_operation(arg)); + if (cpu_has_svm()) { + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + } else { + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + } sync_with_host(5); self_smi(); sync_with_host(7); + + if (cpu_has_svm()) { + run_guest(svm->vmcb, svm->vmcb_gpa); + svm->vmcb->save.rip += 3; + run_guest(svm->vmcb, svm->vmcb_gpa); + } else { + vmlaunch(); + vmresume(); + } + + /* Stages 8-11 are eaten by SMM (SMRAM_STAGE reported instead) */ + sync_with_host(12); } sync_with_host(DONE); } +void inject_smi(struct kvm_vm *vm) +{ + struct kvm_vcpu_events events; + + vcpu_events_get(vm, VCPU_ID, &events); + + events.smi.pending = 1; + events.flags |= KVM_VCPUEVENT_VALID_SMM; + + vcpu_events_set(vm, VCPU_ID, &events); +} + int main(int argc, char *argv[]) { vm_vaddr_t nested_gva = 0; @@ -147,6 +189,22 @@ int main(int argc, char *argv[]) "Unexpected stage: #%x, got %x", stage, stage_reported); + /* + * Enter SMM during L2 execution and check that we correctly + * return from it. Do not perform save/restore while in SMM yet. + */ + if (stage == 8) { + inject_smi(vm); + continue; + } + + /* + * Perform save/restore while the guest is in SMM triggered + * during L2 execution. + */ + if (stage == 10) + inject_smi(vm); + state = vcpu_save_state(vm, VCPU_ID); kvm_vm_release(vm); kvm_vm_restart(vm, O_RDWR); From e8917266ae0944385d50da5e691c89f64c5975a3 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 13 Jul 2021 13:34:53 -0600 Subject: [PATCH 339/426] dt-bindings: More dropping redundant minItems/maxItems Another round of removing redundant minItems/maxItems from new schema in the recent merge window. If a property has an 'items' list, then a 'minItems' or 'maxItems' with the same size as the list is redundant and can be dropped. Note that is DT schema specific behavior and not standard json-schema behavior. The tooling will fixup the final schema adding any unspecified minItems/maxItems. This condition is partially checked with the meta-schema already, but only if both 'minItems' and 'maxItems' are equal to the 'items' length. An improved meta-schema is pending. Cc: Stephen Boyd Cc: Joerg Roedel Cc: Will Deacon Cc: Krzysztof Kozlowski Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Cc: Alessandro Zummo Cc: Alexandre Belloni Cc: Greg Kroah-Hartman Cc: Sureshkumar Relli Cc: Brian Norris Cc: Kamal Dasu Cc: Linus Walleij Cc: Sebastian Siewior Cc: Laurent Pinchart Cc: linux-clk@vger.kernel.org Cc: iommu@lists.linux-foundation.org Cc: linux-mtd@lists.infradead.org Cc: linux-rtc@vger.kernel.org Cc: linux-usb@vger.kernel.org Signed-off-by: Rob Herring Reviewed-by: Greg Kroah-Hartman Acked-by: Alexandre Belloni Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20210713193453.690290-1-robh@kernel.org --- .../devicetree/bindings/clock/brcm,iproc-clocks.yaml | 1 - .../devicetree/bindings/iommu/rockchip,iommu.yaml | 2 -- .../bindings/memory-controllers/arm,pl353-smc.yaml | 1 - Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml | 8 -------- .../devicetree/bindings/rtc/faraday,ftrtc010.yaml | 1 - Documentation/devicetree/bindings/usb/nxp,isp1760.yaml | 2 -- 6 files changed, 15 deletions(-) diff --git a/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.yaml b/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.yaml index 8dc7b404ee12..1174c9aa9934 100644 --- a/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.yaml +++ b/Documentation/devicetree/bindings/clock/brcm,iproc-clocks.yaml @@ -50,7 +50,6 @@ properties: reg: minItems: 1 - maxItems: 3 items: - description: base register - description: power register diff --git a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml index d2e28a9e3545..ba9124f721f1 100644 --- a/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml +++ b/Documentation/devicetree/bindings/iommu/rockchip,iommu.yaml @@ -28,14 +28,12 @@ properties: - description: configuration registers for MMU instance 0 - description: configuration registers for MMU instance 1 minItems: 1 - maxItems: 2 interrupts: items: - description: interruption for MMU instance 0 - description: interruption for MMU instance 1 minItems: 1 - maxItems: 2 clocks: items: diff --git a/Documentation/devicetree/bindings/memory-controllers/arm,pl353-smc.yaml b/Documentation/devicetree/bindings/memory-controllers/arm,pl353-smc.yaml index 7a63c85ef8c5..01c9acf9275d 100644 --- a/Documentation/devicetree/bindings/memory-controllers/arm,pl353-smc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/arm,pl353-smc.yaml @@ -57,7 +57,6 @@ properties: ranges: minItems: 1 - maxItems: 3 description: | Memory bus areas for interacting with the devices. Reflects the memory layout with four integer values following: diff --git a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml index e5f1a33332a5..dd5a64969e37 100644 --- a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml +++ b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.yaml @@ -84,7 +84,6 @@ properties: interrupts: minItems: 1 - maxItems: 3 items: - description: NAND CTLRDY interrupt - description: FLASH_DMA_DONE if flash DMA is available @@ -92,7 +91,6 @@ properties: interrupt-names: minItems: 1 - maxItems: 3 items: - const: nand_ctlrdy - const: flash_dma_done @@ -148,8 +146,6 @@ allOf: then: properties: reg-names: - minItems: 2 - maxItems: 2 items: - const: nand - const: nand-int-base @@ -161,8 +157,6 @@ allOf: then: properties: reg-names: - minItems: 3 - maxItems: 3 items: - const: nand - const: nand-int-base @@ -175,8 +169,6 @@ allOf: then: properties: reg-names: - minItems: 3 - maxItems: 3 items: - const: nand - const: iproc-idm diff --git a/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml b/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml index 657c13b62b67..056d42daae06 100644 --- a/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml +++ b/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml @@ -30,7 +30,6 @@ properties: maxItems: 1 clocks: - minItems: 2 items: - description: PCLK clocks - description: EXTCLK clocks. Faraday calls it CLK1HZ and says the clock diff --git a/Documentation/devicetree/bindings/usb/nxp,isp1760.yaml b/Documentation/devicetree/bindings/usb/nxp,isp1760.yaml index a88f99adfe8e..f238848ad094 100644 --- a/Documentation/devicetree/bindings/usb/nxp,isp1760.yaml +++ b/Documentation/devicetree/bindings/usb/nxp,isp1760.yaml @@ -25,14 +25,12 @@ properties: interrupts: minItems: 1 - maxItems: 2 items: - description: Host controller interrupt - description: Device controller interrupt in isp1761 interrupt-names: minItems: 1 - maxItems: 2 items: - const: host - const: peripheral From f88321a3bf775649c685379a25fb9f3f79836bfd Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 13 Jul 2021 13:35:14 -0600 Subject: [PATCH 340/426] dt-bindings: Move fixed string 'patternProperties' to 'properties' There's no need for fixed strings to be under 'patternProperties', so move them under 'properties' instead. Cc: Jean Delvare Cc: Guenter Roeck Cc: Kishon Vijay Abraham I Cc: Vinod Koul Cc: Saravanan Sekar Cc: Mark Brown Cc: Jagan Teki Cc: Troy Kisky Cc: linux-hwmon@vger.kernel.org Cc: linux-phy@lists.infradead.org Cc: linux-spi@vger.kernel.org Signed-off-by: Rob Herring Acked-by: Mark Brown Acked-by: Guenter Roeck Link: https://lore.kernel.org/r/20210713193514.690894-1-robh@kernel.org --- .../devicetree/bindings/hwmon/adt7475.yaml | 22 ++++---- .../bindings/phy/ti,phy-j721e-wiz.yaml | 56 +++++++++---------- .../bindings/regulator/mps,mpq7920.yaml | 6 +- .../regulator/nxp,pf8x00-regulator.yaml | 3 +- .../bindings/spi/spi-controller.yaml | 32 +++++------ 5 files changed, 60 insertions(+), 59 deletions(-) diff --git a/Documentation/devicetree/bindings/hwmon/adt7475.yaml b/Documentation/devicetree/bindings/hwmon/adt7475.yaml index ad0ec9f35bd8..7d9c083632b9 100644 --- a/Documentation/devicetree/bindings/hwmon/adt7475.yaml +++ b/Documentation/devicetree/bindings/hwmon/adt7475.yaml @@ -39,17 +39,7 @@ properties: reg: maxItems: 1 -patternProperties: - "^adi,bypass-attenuator-in[0-4]$": - description: | - Configures bypassing the individual voltage input attenuator. If - set to 1 the attenuator is bypassed if set to 0 the attenuator is - not bypassed. If the property is absent then the attenuator - retains it's configuration from the bios/bootloader. - $ref: /schemas/types.yaml#/definitions/uint32 - enum: [0, 1] - - "^adi,pwm-active-state$": + adi,pwm-active-state: description: | Integer array, represents the active state of the pwm outputs If set to 0 the pwm uses a logic low output for 100% duty cycle. If set to 1 the pwm @@ -61,6 +51,16 @@ patternProperties: enum: [0, 1] default: 1 +patternProperties: + "^adi,bypass-attenuator-in[0-4]$": + description: | + Configures bypassing the individual voltage input attenuator. If + set to 1 the attenuator is bypassed if set to 0 the attenuator is + not bypassed. If the property is absent then the attenuator + retains it's configuration from the bios/bootloader. + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [0, 1] + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml index 5272b6f284ba..dcd63908aeae 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml @@ -77,6 +77,34 @@ properties: Type-C spec states minimum CC pin debounce of 100 ms and maximum of 200 ms. However, some solutions might need more than 200 ms. + refclk-dig: + type: object + description: | + WIZ node should have subnode for refclk_dig to select the reference + clock source for the reference clock used in the PHY and PMA digital + logic. + properties: + clocks: + minItems: 2 + maxItems: 4 + description: Phandle to two (Torrent) or four (Sierra) clock nodes representing + the inputs to refclk_dig + + "#clock-cells": + const: 0 + + assigned-clocks: + maxItems: 1 + + assigned-clock-parents: + maxItems: 1 + + required: + - clocks + - "#clock-cells" + - assigned-clocks + - assigned-clock-parents + patternProperties: "^pll[0|1]-refclk$": type: object @@ -121,34 +149,6 @@ patternProperties: - clocks - "#clock-cells" - "^refclk-dig$": - type: object - description: | - WIZ node should have subnode for refclk_dig to select the reference - clock source for the reference clock used in the PHY and PMA digital - logic. - properties: - clocks: - minItems: 2 - maxItems: 4 - description: Phandle to two (Torrent) or four (Sierra) clock nodes representing - the inputs to refclk_dig - - "#clock-cells": - const: 0 - - assigned-clocks: - maxItems: 1 - - assigned-clock-parents: - maxItems: 1 - - required: - - clocks - - "#clock-cells" - - assigned-clocks - - assigned-clock-parents - "^serdes@[0-9a-f]+$": type: object description: | diff --git a/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml b/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml index 12b8963615c3..c2e8c54e5311 100644 --- a/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml +++ b/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml @@ -36,12 +36,12 @@ properties: switching frequency must be one of following corresponding value 1.1MHz, 1.65MHz, 2.2MHz, 2.75MHz - patternProperties: - "^ldo[1-4]$": + ldortc: type: object $ref: regulator.yaml# - "^ldortc$": + patternProperties: + "^ldo[1-4]$": type: object $ref: regulator.yaml# diff --git a/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml b/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml index 8761437ed8ad..aabf50f5b39e 100644 --- a/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml @@ -83,7 +83,8 @@ properties: unevaluatedProperties: false - "^vsnvs$": + properties: + vsnvs: type: object $ref: regulator.yaml# description: diff --git a/Documentation/devicetree/bindings/spi/spi-controller.yaml b/Documentation/devicetree/bindings/spi/spi-controller.yaml index faef4f6f55b8..8246891602e7 100644 --- a/Documentation/devicetree/bindings/spi/spi-controller.yaml +++ b/Documentation/devicetree/bindings/spi/spi-controller.yaml @@ -79,22 +79,7 @@ properties: description: The SPI controller acts as a slave, instead of a master. -allOf: - - if: - not: - required: - - spi-slave - then: - properties: - "#address-cells": - const: 1 - else: - properties: - "#address-cells": - const: 0 - -patternProperties: - "^slave$": + slave: type: object properties: @@ -105,6 +90,7 @@ patternProperties: required: - compatible +patternProperties: "^.*@[0-9a-f]+$": type: object @@ -180,6 +166,20 @@ patternProperties: - compatible - reg +allOf: + - if: + not: + required: + - spi-slave + then: + properties: + "#address-cells": + const: 1 + else: + properties: + "#address-cells": + const: 0 + additionalProperties: true examples: From 58b63e0f556c2debb8c942abcc9e6beadc4a07f0 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Tue, 6 Jul 2021 09:07:34 +0800 Subject: [PATCH 341/426] pd: fix order of cleaning up the queue and freeing the tagset We must release the queue before freeing the tagset. Fixes: 262d431f9000 ("pd: use blk_mq_alloc_disk and blk_cleanup_disk") Signed-off-by: Guoqing Jiang Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210706010734.1356066-1-guoqing.jiang@linux.dev Signed-off-by: Jens Axboe --- drivers/block/paride/pd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 3b2b8e872beb..9b3298926356 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -1014,8 +1014,8 @@ static void __exit pd_exit(void) if (p) { disk->gd = NULL; del_gendisk(p); - blk_mq_free_tag_set(&disk->tag_set); blk_cleanup_disk(p); + blk_mq_free_tag_set(&disk->tag_set); pi_release(disk->pi); } } From 16ad3db3b24cd9f70aa24e93cef0d4a83dece7ac Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Tue, 6 Jul 2021 12:00:16 +0800 Subject: [PATCH 342/426] nbd: fix order of cleaning up the queue and freeing the tagset We must release the queue before freeing the tagset. Fixes: 4af5f2e03013 ("nbd: use blk_mq_alloc_disk and blk_cleanup_disk") Reported-and-tested-by: syzbot+9ca43ff47167c0ee3466@syzkaller.appspotmail.com Signed-off-by: Wang Qing Signed-off-by: Guoqing Jiang Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210706040016.1360412-1-guoqing.jiang@linux.dev Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index b7d663736d35..c38317979f74 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -239,8 +239,8 @@ static void nbd_dev_remove(struct nbd_device *nbd) if (disk) { del_gendisk(disk); - blk_mq_free_tag_set(&nbd->tag_set); blk_cleanup_disk(disk); + blk_mq_free_tag_set(&nbd->tag_set); } /* From 05d69d950d9d84218fc9beafd02dea1f6a70e09e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Jul 2021 16:17:11 +0200 Subject: [PATCH 343/426] xen-blkfront: sanitize the removal state machine xen-blkfront has a weird protocol where close message from the remote side can be delayed, and where hot removals are treated somewhat differently from regular removals, all leading to potential NULL pointer removals, and a del_gendisk from the block device release method, which will deadlock. Fix this by just performing normal hot removals even when the device is opened like all other Linux block drivers. Fixes: c76f48eb5c08 ("block: take bd_mutex around delete_partitions in del_gendisk") Reported-by: Vitaly Kuznetsov Signed-off-by: Christoph Hellwig Tested-by: Vitaly Kuznetsov Link: https://lore.kernel.org/r/20210715141711.1257293-1-hch@lst.de Signed-off-by: Jens Axboe --- drivers/block/xen-blkfront.c | 230 +++++------------------------------ 1 file changed, 29 insertions(+), 201 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 8d49f8fa98bb..d83fee21f6c5 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -502,34 +502,21 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg) static int blkif_ioctl(struct block_device *bdev, fmode_t mode, unsigned command, unsigned long argument) { - struct blkfront_info *info = bdev->bd_disk->private_data; int i; - dev_dbg(&info->xbdev->dev, "command: 0x%x, argument: 0x%lx\n", - command, (long)argument); - switch (command) { case CDROMMULTISESSION: - dev_dbg(&info->xbdev->dev, "FIXME: support multisession CDs later\n"); for (i = 0; i < sizeof(struct cdrom_multisession); i++) if (put_user(0, (char __user *)(argument + i))) return -EFAULT; return 0; - - case CDROM_GET_CAPABILITY: { - struct gendisk *gd = info->gd; - if (gd->flags & GENHD_FL_CD) + case CDROM_GET_CAPABILITY: + if (bdev->bd_disk->flags & GENHD_FL_CD) return 0; return -EINVAL; - } - default: - /*printk(KERN_ALERT "ioctl %08x not supported by Xen blkdev\n", - command);*/ - return -EINVAL; /* same return as native Linux */ + return -EINVAL; } - - return 0; } static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo, @@ -1177,36 +1164,6 @@ out_release_minors: return err; } -static void xlvbd_release_gendisk(struct blkfront_info *info) -{ - unsigned int minor, nr_minors, i; - struct blkfront_ring_info *rinfo; - - if (info->rq == NULL) - return; - - /* No more blkif_request(). */ - blk_mq_stop_hw_queues(info->rq); - - for_each_rinfo(info, rinfo, i) { - /* No more gnttab callback work. */ - gnttab_cancel_free_callback(&rinfo->callback); - - /* Flush gnttab callback work. Must be done with no locks held. */ - flush_work(&rinfo->work); - } - - del_gendisk(info->gd); - - minor = info->gd->first_minor; - nr_minors = info->gd->minors; - xlbd_release_minors(minor, nr_minors); - - blk_cleanup_disk(info->gd); - info->gd = NULL; - blk_mq_free_tag_set(&info->tag_set); -} - /* Already hold rinfo->ring_lock. */ static inline void kick_pending_request_queues_locked(struct blkfront_ring_info *rinfo) { @@ -1756,12 +1713,6 @@ abort_transaction: return err; } -static void free_info(struct blkfront_info *info) -{ - list_del(&info->info_list); - kfree(info); -} - /* Common code used when first setting up, and when resuming. */ static int talk_to_blkback(struct xenbus_device *dev, struct blkfront_info *info) @@ -1880,13 +1831,6 @@ again: xenbus_dev_fatal(dev, err, "%s", message); destroy_blkring: blkif_free(info, 0); - - mutex_lock(&blkfront_mutex); - free_info(info); - mutex_unlock(&blkfront_mutex); - - dev_set_drvdata(&dev->dev, NULL); - return err; } @@ -2126,38 +2070,26 @@ static int blkfront_resume(struct xenbus_device *dev) static void blkfront_closing(struct blkfront_info *info) { struct xenbus_device *xbdev = info->xbdev; - struct block_device *bdev = NULL; + struct blkfront_ring_info *rinfo; + unsigned int i; - mutex_lock(&info->mutex); - - if (xbdev->state == XenbusStateClosing) { - mutex_unlock(&info->mutex); + if (xbdev->state == XenbusStateClosing) return; + + /* No more blkif_request(). */ + blk_mq_stop_hw_queues(info->rq); + blk_set_queue_dying(info->rq); + set_capacity(info->gd, 0); + + for_each_rinfo(info, rinfo, i) { + /* No more gnttab callback work. */ + gnttab_cancel_free_callback(&rinfo->callback); + + /* Flush gnttab callback work. Must be done with no locks held. */ + flush_work(&rinfo->work); } - if (info->gd) - bdev = bdgrab(info->gd->part0); - - mutex_unlock(&info->mutex); - - if (!bdev) { - xenbus_frontend_closed(xbdev); - return; - } - - mutex_lock(&bdev->bd_disk->open_mutex); - - if (bdev->bd_openers) { - xenbus_dev_error(xbdev, -EBUSY, - "Device in use; refusing to close"); - xenbus_switch_state(xbdev, XenbusStateClosing); - } else { - xlvbd_release_gendisk(info); - xenbus_frontend_closed(xbdev); - } - - mutex_unlock(&bdev->bd_disk->open_mutex); - bdput(bdev); + xenbus_frontend_closed(xbdev); } static void blkfront_setup_discard(struct blkfront_info *info) @@ -2472,8 +2404,7 @@ static void blkback_changed(struct xenbus_device *dev, break; fallthrough; case XenbusStateClosing: - if (info) - blkfront_closing(info); + blkfront_closing(info); break; } } @@ -2481,56 +2412,21 @@ static void blkback_changed(struct xenbus_device *dev, static int blkfront_remove(struct xenbus_device *xbdev) { struct blkfront_info *info = dev_get_drvdata(&xbdev->dev); - struct block_device *bdev = NULL; - struct gendisk *disk; dev_dbg(&xbdev->dev, "%s removed", xbdev->nodename); - if (!info) - return 0; + del_gendisk(info->gd); + + mutex_lock(&blkfront_mutex); + list_del(&info->info_list); + mutex_unlock(&blkfront_mutex); blkif_free(info, 0); + xlbd_release_minors(info->gd->first_minor, info->gd->minors); + blk_cleanup_disk(info->gd); + blk_mq_free_tag_set(&info->tag_set); - mutex_lock(&info->mutex); - - disk = info->gd; - if (disk) - bdev = bdgrab(disk->part0); - - info->xbdev = NULL; - mutex_unlock(&info->mutex); - - if (!bdev) { - mutex_lock(&blkfront_mutex); - free_info(info); - mutex_unlock(&blkfront_mutex); - return 0; - } - - /* - * The xbdev was removed before we reached the Closed - * state. See if it's safe to remove the disk. If the bdev - * isn't closed yet, we let release take care of it. - */ - - mutex_lock(&disk->open_mutex); - info = disk->private_data; - - dev_warn(disk_to_dev(disk), - "%s was hot-unplugged, %d stale handles\n", - xbdev->nodename, bdev->bd_openers); - - if (info && !bdev->bd_openers) { - xlvbd_release_gendisk(info); - disk->private_data = NULL; - mutex_lock(&blkfront_mutex); - free_info(info); - mutex_unlock(&blkfront_mutex); - } - - mutex_unlock(&disk->open_mutex); - bdput(bdev); - + kfree(info); return 0; } @@ -2541,77 +2437,9 @@ static int blkfront_is_ready(struct xenbus_device *dev) return info->is_ready && info->xbdev; } -static int blkif_open(struct block_device *bdev, fmode_t mode) -{ - struct gendisk *disk = bdev->bd_disk; - struct blkfront_info *info; - int err = 0; - - mutex_lock(&blkfront_mutex); - - info = disk->private_data; - if (!info) { - /* xbdev gone */ - err = -ERESTARTSYS; - goto out; - } - - mutex_lock(&info->mutex); - - if (!info->gd) - /* xbdev is closed */ - err = -ERESTARTSYS; - - mutex_unlock(&info->mutex); - -out: - mutex_unlock(&blkfront_mutex); - return err; -} - -static void blkif_release(struct gendisk *disk, fmode_t mode) -{ - struct blkfront_info *info = disk->private_data; - struct xenbus_device *xbdev; - - mutex_lock(&blkfront_mutex); - if (disk->part0->bd_openers) - goto out_mutex; - - /* - * Check if we have been instructed to close. We will have - * deferred this request, because the bdev was still open. - */ - - mutex_lock(&info->mutex); - xbdev = info->xbdev; - - if (xbdev && xbdev->state == XenbusStateClosing) { - /* pending switch to state closed */ - dev_info(disk_to_dev(disk), "releasing disk\n"); - xlvbd_release_gendisk(info); - xenbus_frontend_closed(info->xbdev); - } - - mutex_unlock(&info->mutex); - - if (!xbdev) { - /* sudden device removal */ - dev_info(disk_to_dev(disk), "releasing disk\n"); - xlvbd_release_gendisk(info); - disk->private_data = NULL; - free_info(info); - } - -out_mutex: - mutex_unlock(&blkfront_mutex); -} - static const struct block_device_operations xlvbd_block_fops = { .owner = THIS_MODULE, - .open = blkif_open, - .release = blkif_release, .getgeo = blkif_getgeo, .ioctl = blkif_ioctl, .compat_ioctl = blkdev_compat_ptr_ioctl, From 295cf156231ca3f9e3a66bde7fab5e09c41835e0 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 12 Jul 2021 15:27:46 +0100 Subject: [PATCH 344/426] arm64: Avoid premature usercopy failure Al reminds us that the usercopy API must only return complete failure if absolutely nothing could be copied. Currently, if userspace does something silly like giving us an unaligned pointer to Device memory, or a size which overruns MTE tag bounds, we may fail to honour that requirement when faulting on a multi-byte access even though a smaller access could have succeeded. Add a mitigation to the fixup routines to fall back to a single-byte copy if we faulted on a larger access before anything has been written to the destination, to guarantee making *some* forward progress. We needn't be too concerned about the overall performance since this should only occur when callers are doing something a bit dodgy in the first place. Particularly broken userspace might still be able to trick generic_perform_write() into an infinite loop by targeting write() at an mmap() of some read-only device register where the fault-in load succeeds but any store synchronously aborts such that copy_to_user() is genuinely unable to make progress, but, well, don't do that... CC: stable@vger.kernel.org Reported-by: Chen Huang Suggested-by: Al Viro Reviewed-by: Catalin Marinas Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/dc03d5c675731a1f24a62417dba5429ad744234e.1626098433.git.robin.murphy@arm.com Signed-off-by: Will Deacon --- arch/arm64/lib/copy_from_user.S | 13 ++++++++++--- arch/arm64/lib/copy_in_user.S | 21 ++++++++++++++------- arch/arm64/lib/copy_to_user.S | 14 +++++++++++--- 3 files changed, 35 insertions(+), 13 deletions(-) diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 95cd62d67371..2cf999e41d30 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -29,7 +29,7 @@ .endm .macro ldrh1 reg, ptr, val - user_ldst 9998f, ldtrh, \reg, \ptr, \val + user_ldst 9997f, ldtrh, \reg, \ptr, \val .endm .macro strh1 reg, ptr, val @@ -37,7 +37,7 @@ .endm .macro ldr1 reg, ptr, val - user_ldst 9998f, ldtr, \reg, \ptr, \val + user_ldst 9997f, ldtr, \reg, \ptr, \val .endm .macro str1 reg, ptr, val @@ -45,7 +45,7 @@ .endm .macro ldp1 reg1, reg2, ptr, val - user_ldp 9998f, \reg1, \reg2, \ptr, \val + user_ldp 9997f, \reg1, \reg2, \ptr, \val .endm .macro stp1 reg1, reg2, ptr, val @@ -53,8 +53,10 @@ .endm end .req x5 +srcin .req x15 SYM_FUNC_START(__arch_copy_from_user) add end, x0, x2 + mov srcin, x1 #include "copy_template.S" mov x0, #0 // Nothing to copy ret @@ -63,6 +65,11 @@ EXPORT_SYMBOL(__arch_copy_from_user) .section .fixup,"ax" .align 2 +9997: cmp dst, dstin + b.ne 9998f + // Before being absolutely sure we couldn't copy anything, try harder +USER(9998f, ldtrb tmp1w, [srcin]) + strb tmp1w, [dst], #1 9998: sub x0, end, dst // bytes not copied ret .previous diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 1f61cd0df062..dbea3799c3ef 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -30,33 +30,34 @@ .endm .macro ldrh1 reg, ptr, val - user_ldst 9998f, ldtrh, \reg, \ptr, \val + user_ldst 9997f, ldtrh, \reg, \ptr, \val .endm .macro strh1 reg, ptr, val - user_ldst 9998f, sttrh, \reg, \ptr, \val + user_ldst 9997f, sttrh, \reg, \ptr, \val .endm .macro ldr1 reg, ptr, val - user_ldst 9998f, ldtr, \reg, \ptr, \val + user_ldst 9997f, ldtr, \reg, \ptr, \val .endm .macro str1 reg, ptr, val - user_ldst 9998f, sttr, \reg, \ptr, \val + user_ldst 9997f, sttr, \reg, \ptr, \val .endm .macro ldp1 reg1, reg2, ptr, val - user_ldp 9998f, \reg1, \reg2, \ptr, \val + user_ldp 9997f, \reg1, \reg2, \ptr, \val .endm .macro stp1 reg1, reg2, ptr, val - user_stp 9998f, \reg1, \reg2, \ptr, \val + user_stp 9997f, \reg1, \reg2, \ptr, \val .endm end .req x5 - +srcin .req x15 SYM_FUNC_START(__arch_copy_in_user) add end, x0, x2 + mov srcin, x1 #include "copy_template.S" mov x0, #0 ret @@ -65,6 +66,12 @@ EXPORT_SYMBOL(__arch_copy_in_user) .section .fixup,"ax" .align 2 +9997: cmp dst, dstin + b.ne 9998f + // Before being absolutely sure we couldn't copy anything, try harder +USER(9998f, ldtrb tmp1w, [srcin]) +USER(9998f, sttrb tmp1w, [dst]) + add dst, dst, #1 9998: sub x0, end, dst // bytes not copied ret .previous diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 043da90f5dd7..9f380eecf653 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -32,7 +32,7 @@ .endm .macro strh1 reg, ptr, val - user_ldst 9998f, sttrh, \reg, \ptr, \val + user_ldst 9997f, sttrh, \reg, \ptr, \val .endm .macro ldr1 reg, ptr, val @@ -40,7 +40,7 @@ .endm .macro str1 reg, ptr, val - user_ldst 9998f, sttr, \reg, \ptr, \val + user_ldst 9997f, sttr, \reg, \ptr, \val .endm .macro ldp1 reg1, reg2, ptr, val @@ -48,12 +48,14 @@ .endm .macro stp1 reg1, reg2, ptr, val - user_stp 9998f, \reg1, \reg2, \ptr, \val + user_stp 9997f, \reg1, \reg2, \ptr, \val .endm end .req x5 +srcin .req x15 SYM_FUNC_START(__arch_copy_to_user) add end, x0, x2 + mov srcin, x1 #include "copy_template.S" mov x0, #0 ret @@ -62,6 +64,12 @@ EXPORT_SYMBOL(__arch_copy_to_user) .section .fixup,"ax" .align 2 +9997: cmp dst, dstin + b.ne 9998f + // Before being absolutely sure we couldn't copy anything, try harder + ldrb tmp1w, [srcin] +USER(9998f, sttrb tmp1w, [dst]) + add dst, dst, #1 9998: sub x0, end, dst // bytes not copied ret .previous From 59f44069e0527523f27948da7b77599a73dab157 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 14 Jul 2021 15:38:41 +0100 Subject: [PATCH 345/426] arm64: mte: fix restoration of GCR_EL1 from suspend Since commit: bad1e1c663e0a72f ("arm64: mte: switch GCR_EL1 in kernel entry and exit") we saved/restored the user GCR_EL1 value at exception boundaries, and update_gcr_el1_excl() is no longer used for this. However it is used to restore the kernel's GCR_EL1 value when returning from a suspend state. Thus, the comment is misleading (and an ISB is necessary). When restoring the kernel's GCR value, we need an ISB to ensure this is used by subsequent instructions. We don't necessarily get an ISB by other means (e.g. if the kernel is built without support for pointer authentication). As __cpu_setup() initialised GCR_EL1.Exclude to 0xffff, until a context synchronization event, allocation tag 0 may be used rather than the desired set of tags. This patch drops the misleading comment, adds the missing ISB, and for clarity folds update_gcr_el1_excl() into its only user. Fixes: bad1e1c663e0 ("arm64: mte: switch GCR_EL1 in kernel entry and exit") Signed-off-by: Mark Rutland Cc: Andrey Konovalov Cc: Catalin Marinas Cc: Vincenzo Frascino Cc: Will Deacon Link: https://lore.kernel.org/r/20210714143843.56537-2-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/mte.c | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 69b3fde8759e..36f51b0e438a 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -193,18 +193,6 @@ void mte_check_tfsr_el1(void) } #endif -static void update_gcr_el1_excl(u64 excl) -{ - - /* - * Note that the mask controlled by the user via prctl() is an - * include while GCR_EL1 accepts an exclude mask. - * No need for ISB since this only affects EL0 currently, implicit - * with ERET. - */ - sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl); -} - static void set_gcr_el1_excl(u64 excl) { current->thread.gcr_user_excl = excl; @@ -265,7 +253,8 @@ void mte_suspend_exit(void) if (!system_supports_mte()) return; - update_gcr_el1_excl(gcr_kernel_excl); + sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, gcr_kernel_excl); + isb(); } long set_mte_ctrl(struct task_struct *task, unsigned long arg) From 31a7f0f6c8f392f002c937f34f372943cf8be5a9 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 14 Jul 2021 18:28:01 +0100 Subject: [PATCH 346/426] arm64: entry: add missing noinstr We intend that all the early exception handling code is marked as `noinstr`, but we forgot this for __el0_error_handler_common(), which is called before we have completed entry from user mode. If it were instrumented, we could run into problems with RCU, lockdep, etc. Mark it as `noinstr` to prevent this. The few other functions in entry-common.c which do not have `noinstr` are called once we've completed entry, and are safe to instrument. Fixes: bb8e93a287a5 ("arm64: entry: convert SError handlers to C") Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: Marc Zyngier Cc: Joey Gouly Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20210714172801.16475-1-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/entry-common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 12ce14a98b7c..db8b2e2d02c2 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -604,7 +604,7 @@ asmlinkage void noinstr el0t_64_fiq_handler(struct pt_regs *regs) __el0_fiq_handler_common(regs); } -static void __el0_error_handler_common(struct pt_regs *regs) +static void noinstr __el0_error_handler_common(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); From e6f85cbeb23bd74b8966cf1f15bf7d01399ff625 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 15 Jul 2021 13:30:49 +0100 Subject: [PATCH 347/426] arm64: entry: fix KCOV suppression We suppress KCOV for entry.o rather than entry-common.o. As entry.o is built from entry.S, this is pointless, and permits instrumentation of entry-common.o, which is built from entry-common.c. Fix the Makefile to suppress KCOV for entry-common.o, as we had intended to begin with. I've verified with objdump that this is working as expected. Fixes: bf6fa2c0dda7 ("arm64: entry: don't instrument entry code with KCOV") Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Marc Zyngier Cc: Will Deacon Link: https://lore.kernel.org/r/20210715123049.9990-1-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index cce308586fcc..3f1490bfb938 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -17,7 +17,7 @@ CFLAGS_syscall.o += -fno-stack-protector # It's not safe to invoke KCOV when portions of the kernel environment aren't # available or are out-of-sync with HW state. Since `noinstr` doesn't always # inhibit KCOV instrumentation, disable it for the entire compilation unit. -KCOV_INSTRUMENT_entry.o := n +KCOV_INSTRUMENT_entry-common.o := n KCOV_INSTRUMENT_idle.o := n # Object file lists. From 3ac1d426510f97ace05093ae9f2f710d9cbe6215 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Jul 2021 09:58:04 -0700 Subject: [PATCH 348/426] iomap: remove the length variable in iomap_seek_data The length variable is rather pointless given that it can be trivially deduced from offset and size. Also the initial calculation can lead to KASAN warnings. Signed-off-by: Christoph Hellwig Reported-by: Leizhen (ThunderTown) Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Matthew Wilcox (Oracle) --- fs/iomap/seek.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index dab1b02eba5b..50b8f1418f26 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -83,27 +83,23 @@ loff_t iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops) { loff_t size = i_size_read(inode); - loff_t length = size - offset; loff_t ret; /* Nothing to be found before or beyond the end of the file. */ if (offset < 0 || offset >= size) return -ENXIO; - while (length > 0) { - ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops, - &offset, iomap_seek_data_actor); + while (offset < size) { + ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT, + ops, &offset, iomap_seek_data_actor); if (ret < 0) return ret; if (ret == 0) - break; - + return offset; offset += ret; - length -= ret; } - if (length <= 0) - return -ENXIO; - return offset; + /* We've reached the end of the file without finding data */ + return -ENXIO; } EXPORT_SYMBOL_GPL(iomap_seek_data); From 49694d14ff68fa4b5f86019dbcfb44a8bd213e58 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Jul 2021 09:58:04 -0700 Subject: [PATCH 349/426] iomap: remove the length variable in iomap_seek_hole The length variable is rather pointless given that it can be trivially deduced from offset and size. Also the initial calculation can lead to KASAN warnings. Signed-off-by: Christoph Hellwig Reported-by: Leizhen (ThunderTown) Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Matthew Wilcox (Oracle) --- fs/iomap/seek.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index 50b8f1418f26..ce6fb810854f 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -35,23 +35,20 @@ loff_t iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops) { loff_t size = i_size_read(inode); - loff_t length = size - offset; loff_t ret; /* Nothing to be found before or beyond the end of the file. */ if (offset < 0 || offset >= size) return -ENXIO; - while (length > 0) { - ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops, - &offset, iomap_seek_hole_actor); + while (offset < size) { + ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT, + ops, &offset, iomap_seek_hole_actor); if (ret < 0) return ret; if (ret == 0) break; - offset += ret; - length -= ret; } return offset; From 8e1bcef8e18d0fec4afe527c074bb1fd6c2b140c Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 15 Jul 2021 09:58:05 -0700 Subject: [PATCH 350/426] iomap: Permit pages without an iop to enter writeback Create an iop in the writeback path if one doesn't exist. This allows us to avoid creating the iop in some cases. We'll initially do that for pages with inline data, but it can be extended to pages which are entirely within an extent. It also allows for an iop to be removed from pages in the future (eg page split). Co-developed-by: Matthew Wilcox (Oracle) Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andreas Gruenbacher Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 41da4f14c00b..ad976634d56b 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1304,14 +1304,13 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct inode *inode, struct page *page, u64 end_offset) { - struct iomap_page *iop = to_iomap_page(page); + struct iomap_page *iop = iomap_page_create(inode, page); struct iomap_ioend *ioend, *next; unsigned len = i_blocksize(inode); u64 file_offset; /* file offset of page */ int error = 0, count = 0, i; LIST_HEAD(submit_list); - WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop); WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0); /* From 637d3375953e052a62c0db409557e3b3354be88a Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 15 Jul 2021 09:58:05 -0700 Subject: [PATCH 351/426] iomap: Don't create iomap_page objects for inline files In iomap_readpage_actor, don't create iop objects for inline inodes. Otherwise, iomap_read_inline_data will set PageUptodate without setting iop->uptodate, and iomap_page_release will eventually complain. To prevent this kind of bug from occurring in the future, make sure the page doesn't have private data attached in iomap_read_inline_data. Signed-off-by: Andreas Gruenbacher Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index ad976634d56b..41076bab18cb 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -215,6 +215,7 @@ iomap_read_inline_data(struct inode *inode, struct page *page, if (PageUptodate(page)) return; + BUG_ON(page_has_private(page)); BUG_ON(page->index); BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data)); @@ -239,7 +240,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, { struct iomap_readpage_ctx *ctx = data; struct page *page = ctx->cur_page; - struct iomap_page *iop = iomap_page_create(inode, page); + struct iomap_page *iop; bool same_page = false, is_contig = false; loff_t orig_pos = pos; unsigned poff, plen; @@ -252,6 +253,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, } /* zero post-eof blocks as the page may be mapped */ + iop = iomap_page_create(inode, page); iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen); if (plen == 0) goto done; From 229adf3c64dbeae4e2f45fb561907ada9fcc0d0c Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 15 Jul 2021 09:58:06 -0700 Subject: [PATCH 352/426] iomap: Don't create iomap_page objects in iomap_page_mkwrite_actor Now that we create those objects in iomap_writepage_map when needed, there's no need to pre-create them in iomap_page_mkwrite_actor anymore. Signed-off-by: Andreas Gruenbacher Reviewed-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 41076bab18cb..87ccb3438bec 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -969,7 +969,6 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, block_commit_write(page, 0, length); } else { WARN_ON_ONCE(!PageUptodate(page)); - iomap_page_create(inode, page); set_page_dirty(page); } From da062d16a897c0759ae907e786bc0bea950c0c9d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:47 -0700 Subject: [PATCH 353/426] xfs: check for sparse inode clusters that cross new EOAG when shrinking While running xfs/168, I noticed occasional write verifier shutdowns involving inodes at the very end of the filesystem. Existing inode btree validation code checks that all inode clusters are fully contained within the filesystem. However, due to inadequate checking in the fs shrink code, it's possible that there could be a sparse inode cluster at the end of the filesystem where the upper inodes of the cluster are marked as holes and the corresponding blocks are free. In this case, the last blocks in the AG are listed in the bnobt. This enables the shrink to proceed but results in a filesystem that trips the inode verifiers. Fix this by disallowing the shrink. Signed-off-by: Darrick J. Wong Reviewed-by: Gao Xiang --- fs/xfs/libxfs/xfs_ag.c | 8 ++++++ fs/xfs/libxfs/xfs_ialloc.c | 55 ++++++++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_ialloc.h | 3 +++ 3 files changed, 66 insertions(+) diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 778ec52cce70..ee9ec0c50bec 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -803,6 +803,14 @@ xfs_ag_shrink_space( args.fsbno = XFS_AGB_TO_FSB(mp, agno, aglen - delta); + /* + * Make sure that the last inode cluster cannot overlap with the new + * end of the AG, even if it's sparse. + */ + error = xfs_ialloc_check_shrink(*tpp, agno, agibp, aglen - delta); + if (error) + return error; + /* * Disable perag reservations so it doesn't cause the allocation request * to fail. We'll reestablish reservation before we return. diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 57d9cb632983..aaf8805a82df 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -2928,3 +2928,58 @@ xfs_ialloc_calc_rootino( return XFS_AGINO_TO_INO(mp, 0, XFS_AGB_TO_AGINO(mp, first_bno)); } + +/* + * Ensure there are not sparse inode clusters that cross the new EOAG. + * + * This is a no-op for non-spinode filesystems since clusters are always fully + * allocated and checking the bnobt suffices. However, a spinode filesystem + * could have a record where the upper inodes are free blocks. If those blocks + * were removed from the filesystem, the inode record would extend beyond EOAG, + * which will be flagged as corruption. + */ +int +xfs_ialloc_check_shrink( + struct xfs_trans *tp, + xfs_agnumber_t agno, + struct xfs_buf *agibp, + xfs_agblock_t new_length) +{ + struct xfs_inobt_rec_incore rec; + struct xfs_btree_cur *cur; + struct xfs_mount *mp = tp->t_mountp; + struct xfs_perag *pag; + xfs_agino_t agino = XFS_AGB_TO_AGINO(mp, new_length); + int has; + int error; + + if (!xfs_sb_version_hassparseinodes(&mp->m_sb)) + return 0; + + pag = xfs_perag_get(mp, agno); + cur = xfs_inobt_init_cursor(mp, tp, agibp, pag, XFS_BTNUM_INO); + + /* Look up the inobt record that would correspond to the new EOFS. */ + error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has); + if (error || !has) + goto out; + + error = xfs_inobt_get_rec(cur, &rec, &has); + if (error) + goto out; + + if (!has) { + error = -EFSCORRUPTED; + goto out; + } + + /* If the record covers inodes that would be beyond EOFS, bail out. */ + if (rec.ir_startino + XFS_INODES_PER_CHUNK > agino) { + error = -ENOSPC; + goto out; + } +out: + xfs_btree_del_cursor(cur, error); + xfs_perag_put(pag); + return error; +} diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index 9df7c80408ff..9a2112b4ad5e 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -122,4 +122,7 @@ int xfs_ialloc_cluster_alignment(struct xfs_mount *mp); void xfs_ialloc_setup_geometry(struct xfs_mount *mp); xfs_ino_t xfs_ialloc_calc_rootino(struct xfs_mount *mp, int sunit); +int xfs_ialloc_check_shrink(struct xfs_trans *tp, xfs_agnumber_t agno, + struct xfs_buf *agibp, xfs_agblock_t new_length); + #endif /* __XFS_IALLOC_H__ */ From 5838d0356bb3c320867c393f12b169c01a870bda Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:48 -0700 Subject: [PATCH 354/426] xfs: reset child dir '..' entry when unlinking child While running xfs/168, I noticed a second source of post-shrink corruption errors causing shutdowns. Let's say that directory B has a low inode number and is a child of directory A, which has a high number. If B is empty but open, and unlinked from A, B's dotdot link continues to point to A. If A is then unlinked and the filesystem shrunk so that A is no longer a valid inode, a subsequent AIL push of B will trip the inode verifiers because the dotdot entry points outside of the filesystem. To avoid this problem, reset B's dotdot entry to the root directory when unlinking directories, since the root directory cannot be removed. Signed-off-by: Darrick J. Wong Reviewed-by: Gao Xiang --- fs/xfs/xfs_inode.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index a835ceb79ba5..990b72ae3635 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2763,6 +2763,19 @@ xfs_remove( error = xfs_droplink(tp, ip); if (error) goto out_trans_cancel; + + /* + * Point the unlinked child directory's ".." entry to the root + * directory to eliminate back-references to inodes that may + * get freed before the child directory is closed. If the fs + * gets shrunk, this can lead to dirent inode validation errors. + */ + if (dp->i_ino != tp->t_mountp->m_sb.sb_rootino) { + error = xfs_dir_replace(tp, ip, &xfs_name_dotdot, + tp->t_mountp->m_sb.sb_rootino, 0); + if (error) + return error; + } } else { /* * When removing a non-directory we need to log the parent From 83193e5ebb0164d612aa620ceab7d3746e80e2a4 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:50 -0700 Subject: [PATCH 355/426] xfs: correct the narrative around misaligned rtinherit/extszinherit dirs While auditing the realtime growfs code, I realized that the GROWFSRT ioctl (and by extension xfs_growfs) has always allowed sysadmins to change the realtime extent size when adding a realtime section to the filesystem. Since we also have always allowed sysadmins to set RTINHERIT and EXTSZINHERIT on directories even if there is no realtime device, this invalidates the premise laid out in the comments added in commit 603f000b15f2. In other words, this is not a case of inadequate metadata validation. This is a case of nearly forgotten (and apparently untested) but supported functionality. Update the comments to reflect what we've learned, and remove the log message about correcting the misalignment. Fixes: 603f000b15f2 ("xfs: validate extsz hints against rt extent size when rtinherit is set") Signed-off-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_inode_buf.c | 28 ++++++++++++++++------------ fs/xfs/libxfs/xfs_trans_inode.c | 10 ++++------ fs/xfs/xfs_ioctl.c | 8 ++++---- 3 files changed, 24 insertions(+), 22 deletions(-) diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 04ce361688f7..84ea2e0af9f0 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -592,23 +592,27 @@ xfs_inode_validate_extsize( /* * This comment describes a historic gap in this verifier function. * - * On older kernels, the extent size hint verifier doesn't check that - * the extent size hint is an integer multiple of the realtime extent - * size on a directory with both RTINHERIT and EXTSZINHERIT flags set. - * The verifier has always enforced the alignment rule for regular - * files with the REALTIME flag set. + * For a directory with both RTINHERIT and EXTSZINHERIT flags set, this + * function has never checked that the extent size hint is an integer + * multiple of the realtime extent size. Since we allow users to set + * this combination on non-rt filesystems /and/ to change the rt + * extent size when adding a rt device to a filesystem, the net effect + * is that users can configure a filesystem anticipating one rt + * geometry and change their minds later. Directories do not use the + * extent size hint, so this is harmless for them. * * If a directory with a misaligned extent size hint is allowed to * propagate that hint into a new regular realtime file, the result * is that the inode cluster buffer verifier will trigger a corruption - * shutdown the next time it is run. + * shutdown the next time it is run, because the verifier has always + * enforced the alignment rule for regular files. * - * Unfortunately, there could be filesystems with these misconfigured - * directories in the wild, so we cannot add a check to this verifier - * at this time because that will result a new source of directory - * corruption errors when reading an existing filesystem. Instead, we - * permit the misconfiguration to pass through the verifiers so that - * callers of this function can correct and mitigate externally. + * Because we allow administrators to set a new rt extent size when + * adding a rt section, we cannot add a check to this verifier because + * that will result a new source of directory corruption errors when + * reading an existing filesystem. Instead, we rely on callers to + * decide when alignment checks are appropriate, and fix things up as + * needed. */ if (rt_flag) diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 8d595a5c4abd..16f723ebe8dd 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -143,16 +143,14 @@ xfs_trans_log_inode( } /* - * Inode verifiers on older kernels don't check that the extent size - * hint is an integer multiple of the rt extent size on a directory - * with both rtinherit and extszinherit flags set. If we're logging a - * directory that is misconfigured in this way, clear the hint. + * Inode verifiers do not check that the extent size hint is an integer + * multiple of the rt extent size on a directory with both rtinherit + * and extszinherit flags set. If we're logging a directory that is + * misconfigured in this way, clear the hint. */ if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) && (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) { - xfs_info_once(ip->i_mount, - "Correcting misaligned extent size hint in inode 0x%llx.", ip->i_ino); ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT); ip->i_extsize = 0; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 65270e63c032..275d1c3123bd 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1292,10 +1292,10 @@ xfs_ioctl_setattr_check_extsize( new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); /* - * Inode verifiers on older kernels don't check that the extent size - * hint is an integer multiple of the rt extent size on a directory - * with both rtinherit and extszinherit flags set. Don't let sysadmins - * misconfigure directories. + * Inode verifiers do not check that the extent size hint is an integer + * multiple of the rt extent size on a directory with both rtinherit + * and extszinherit flags set. Don't let sysadmins misconfigure + * directories. */ if ((new_diflags & XFS_DIFLAG_RTINHERIT) && (new_diflags & XFS_DIFLAG_EXTSZINHERIT)) { From 5aa5b278237f356f86205c4b03d4cc64a293850a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:51 -0700 Subject: [PATCH 356/426] xfs: don't expose misaligned extszinherit hints to userspace Commit 603f000b15f2 changed xfs_ioctl_setattr_check_extsize to reject an attempt to set an EXTSZINHERIT extent size hint on a directory with RTINHERIT set if the hint isn't a multiple of the realtime extent size. However, I have recently discovered that it is possible to change the realtime extent size when adding a rt device to a filesystem, which means that the existence of directories with misaligned inherited hints is not an accident. As a result, it's possible that someone could have set a valid hint and added an rt volume with a different rt extent size, which invalidates the ondisk hints. After such a sequence, FSGETXATTR will report a misaligned hint, which FSSETXATTR will trip over, causing confusion if the user was doing the usual GET/SET sequence to change some other attribute. Change xfs_fill_fsxattr to omit the hint if it isn't aligned properly. Fixes: 603f000b15f2 ("xfs: validate extsz hints against rt extent size when rtinherit is set") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_ioctl.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 275d1c3123bd..16039ea10ac9 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1065,7 +1065,24 @@ xfs_fill_fsxattr( fileattr_fill_xflags(fa, xfs_ip2xflags(ip)); - fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize); + if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) { + fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize); + } else if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) { + /* + * Don't let a misaligned extent size hint on a directory + * escape to userspace if it won't pass the setattr checks + * later. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + ip->i_extsize % mp->m_sb.sb_rextsize > 0) { + fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | + FS_XFLAG_EXTSZINHERIT); + fa->fsx_extsize = 0; + } else { + fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize); + } + } + if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); fa->fsx_projid = ip->i_projid; From 0e2af9296f4f9c4c815ced2beb21093af7c38644 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:48 -0700 Subject: [PATCH 357/426] xfs: improve FSGROWFSRT precondition checking Improve the checking at the start of a realtime grow operation so that we avoid accidentally set a new extent size that is too large and avoid adding an rt volume to a filesystem with rmap or reflink because we don't support rt rmap or reflink yet. While we're at it, separate the checks so that we're only testing one aspect at a time. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_rtalloc.c | 39 ++++++++++++++++++++++++++++++++------- 1 file changed, 32 insertions(+), 7 deletions(-) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 4e7be6b4ca8e..8f6a05db4468 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -923,16 +923,41 @@ xfs_growfs_rt( uint8_t *rsum_cache; /* old summary cache */ sbp = &mp->m_sb; - /* - * Initial error checking. - */ + if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (mp->m_rtdev_targp == NULL || mp->m_rbmip == NULL || - (nrblocks = in->newblocks) <= sbp->sb_rblocks || - (sbp->sb_rblocks && (in->extsize != sbp->sb_rextsize))) + + /* Needs to have been mounted with an rt device. */ + if (!XFS_IS_REALTIME_MOUNT(mp)) return -EINVAL; - if ((error = xfs_sb_validate_fsb_count(sbp, nrblocks))) + /* + * Mount should fail if the rt bitmap/summary files don't load, but + * we'll check anyway. + */ + if (!mp->m_rbmip || !mp->m_rsumip) + return -EINVAL; + + /* Shrink not supported. */ + if (in->newblocks <= sbp->sb_rblocks) + return -EINVAL; + + /* Can only change rt extent size when adding rt volume. */ + if (sbp->sb_rblocks > 0 && in->extsize != sbp->sb_rextsize) + return -EINVAL; + + /* Range check the extent size. */ + if (XFS_FSB_TO_B(mp, in->extsize) > XFS_MAX_RTEXTSIZE || + XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE) + return -EINVAL; + + /* Unsupported realtime features. */ + if (xfs_sb_version_hasrmapbt(&mp->m_sb) || + xfs_sb_version_hasreflink(&mp->m_sb)) + return -EOPNOTSUPP; + + nrblocks = in->newblocks; + error = xfs_sb_validate_fsb_count(sbp, nrblocks); + if (error) return error; /* * Read in the last block of the device, make sure it exists. From 0925fecc557471b6f6a488c3590a275151210572 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 12 Jul 2021 12:58:49 -0700 Subject: [PATCH 358/426] xfs: fix an integer overflow error in xfs_growfs_rt During a realtime grow operation, we run a single transaction for each rt bitmap block added to the filesystem. This means that each step has to be careful to increase sb_rblocks appropriately. Fix the integer overflow error in this calculation that can happen when the extent size is very large. Found by running growfs to add a rt volume to a filesystem formatted with a 1g rt extent size. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_rtalloc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 8f6a05db4468..699066fb9052 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1021,7 +1021,8 @@ xfs_growfs_rt( ((sbp->sb_rextents & ((1 << mp->m_blkbit_log) - 1)) != 0); bmbno < nrbmblocks; bmbno++) { - xfs_trans_t *tp; + struct xfs_trans *tp; + xfs_rfsblock_t nrblocks_step; *nmp = *mp; nsbp = &nmp->m_sb; @@ -1030,10 +1031,9 @@ xfs_growfs_rt( */ nsbp->sb_rextsize = in->extsize; nsbp->sb_rbmblocks = bmbno + 1; - nsbp->sb_rblocks = - XFS_RTMIN(nrblocks, - nsbp->sb_rbmblocks * NBBY * - nsbp->sb_blocksize * nsbp->sb_rextsize); + nrblocks_step = (bmbno + 1) * NBBY * nsbp->sb_blocksize * + nsbp->sb_rextsize; + nsbp->sb_rblocks = min(nrblocks, nrblocks_step); nsbp->sb_rextents = nsbp->sb_rblocks; do_div(nsbp->sb_rextents, nsbp->sb_rextsize); ASSERT(nsbp->sb_rextents != 0); From b102a46ce16fd5550aed882c3c5b95f50da7992c Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 14 Jul 2021 09:03:41 -0700 Subject: [PATCH 359/426] xfs: detect misaligned rtinherit directory extent size hints If we encounter a directory that has been configured to pass on an extent size hint to a new realtime file and the hint isn't an integer multiple of the rt extent size, we should flag the hint for administrative review because that is a misconfiguration (that other parts of the kernel will fix automatically). Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Christoph Hellwig --- fs/xfs/scrub/inode.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 61f90b2c9430..76fbc7ca4cec 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -73,11 +73,25 @@ xchk_inode_extsize( uint16_t flags) { xfs_failaddr_t fa; + uint32_t value = be32_to_cpu(dip->di_extsize); - fa = xfs_inode_validate_extsize(sc->mp, be32_to_cpu(dip->di_extsize), - mode, flags); + fa = xfs_inode_validate_extsize(sc->mp, value, mode, flags); if (fa) xchk_ino_set_corrupt(sc, ino); + + /* + * XFS allows a sysadmin to change the rt extent size when adding a rt + * section to a filesystem after formatting. If there are any + * directories with extszinherit and rtinherit set, the hint could + * become misaligned with the new rextsize. The verifier doesn't check + * this, because we allow rtinherit directories even without an rt + * device. Flag this as an administrative warning since we will clean + * this up eventually. + */ + if ((flags & XFS_DIFLAG_RTINHERIT) && + (flags & XFS_DIFLAG_EXTSZINHERIT) && + value % sc->mp->m_sb.sb_rextsize > 0) + xchk_ino_set_warning(sc, ino); } /* From 0d4a062af2cea33c2000b28420e8e2eb58b4fd0b Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 14 Jul 2021 21:26:34 -0700 Subject: [PATCH 360/426] mm: move helper to check slub_debug_enabled Move the helper to check slub_debug_enabled, so that we can confine the use of #ifdef outside slub.c as well. Link: https://lkml.kernel.org/r/20210705103229.8505-2-yee.lee@mediatek.com Signed-off-by: Marco Elver Signed-off-by: Yee Lee Suggested-by: Matthew Wilcox Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Chinwen Chang Cc: Dmitry Vyukov Cc: Kuan-Ying Lee Cc: Nicholas Tang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.h | 15 +++++++++++---- mm/slub.c | 14 -------------- 2 files changed, 11 insertions(+), 18 deletions(-) diff --git a/mm/slab.h b/mm/slab.h index 67e06637ff2e..f997fd5e42c8 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -216,10 +216,18 @@ DECLARE_STATIC_KEY_FALSE(slub_debug_enabled); #endif extern void print_tracking(struct kmem_cache *s, void *object); long validate_slab_cache(struct kmem_cache *s); +static inline bool __slub_debug_enabled(void) +{ + return static_branch_unlikely(&slub_debug_enabled); +} #else static inline void print_tracking(struct kmem_cache *s, void *object) { } +static inline bool __slub_debug_enabled(void) +{ + return false; +} #endif /* @@ -229,11 +237,10 @@ static inline void print_tracking(struct kmem_cache *s, void *object) */ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags) { -#ifdef CONFIG_SLUB_DEBUG - VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS)); - if (static_branch_unlikely(&slub_debug_enabled)) + if (IS_ENABLED(CONFIG_SLUB_DEBUG)) + VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS)); + if (__slub_debug_enabled()) return s->flags & flags; -#endif return false; } diff --git a/mm/slub.c b/mm/slub.c index dc863c1ea324..e1644ac6ee7b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -120,25 +120,11 @@ */ #ifdef CONFIG_SLUB_DEBUG - #ifdef CONFIG_SLUB_DEBUG_ON DEFINE_STATIC_KEY_TRUE(slub_debug_enabled); #else DEFINE_STATIC_KEY_FALSE(slub_debug_enabled); #endif - -static inline bool __slub_debug_enabled(void) -{ - return static_branch_unlikely(&slub_debug_enabled); -} - -#else /* CONFIG_SLUB_DEBUG */ - -static inline bool __slub_debug_enabled(void) -{ - return false; -} - #endif /* CONFIG_SLUB_DEBUG */ static inline bool kmem_cache_debug(struct kmem_cache *s) From 77a63c69ec43f4dc28f4b2d1c933c39e55de6ad8 Mon Sep 17 00:00:00 2001 From: Yee Lee Date: Wed, 14 Jul 2021 21:26:37 -0700 Subject: [PATCH 361/426] kasan: add memzero init for unaligned size at DEBUG Issue: when SLUB debug is on, hwtag kasan_unpoison() would overwrite the redzone of object with unaligned size. An additional memzero_explicit() path is added to replacing init by hwtag instruction for those unaligned size at SLUB debug mode. The penalty is acceptable since they are only enabled in debug mode, not production builds. A block of comment is added for explanation. Link: https://lkml.kernel.org/r/20210705103229.8505-3-yee.lee@mediatek.com Signed-off-by: Yee Lee Suggested-by: Andrey Konovalov Suggested-by: Marco Elver Reviewed-by: Marco Elver Reviewed-by: Andrey Konovalov Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Nicholas Tang Cc: Kuan-Ying Lee Cc: Chinwen Chang Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/kasan.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 98e3059bfea4..d739cdd1621a 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -9,6 +9,7 @@ #ifdef CONFIG_KASAN_HW_TAGS #include +#include "../slab.h" DECLARE_STATIC_KEY_FALSE(kasan_flag_stacktrace); extern bool kasan_flag_async __ro_after_init; @@ -387,6 +388,17 @@ static inline void kasan_unpoison(const void *addr, size_t size, bool init) if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK)) return; + /* + * Explicitly initialize the memory with the precise object size to + * avoid overwriting the SLAB redzone. This disables initialization in + * the arch code and may thus lead to performance penalty. The penalty + * is accepted since SLAB redzones aren't enabled in production builds. + */ + if (__slub_debug_enabled() && + init && ((unsigned long)size & KASAN_GRANULE_MASK)) { + init = false; + memzero_explicit((void *)addr, size); + } size = round_up(size, KASAN_GRANULE_SIZE); hw_set_mem_tag_range((void *)addr, size, tag, init); From 2db710cc846d3321a4dc0977fa13769bddba2351 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 14 Jul 2021 21:26:40 -0700 Subject: [PATCH 362/426] kasan: fix build by including kernel.h The header relies on _RET_IP_ being defined, and had been receiving that definition via inclusion of bug.h which includes kernel.h. However, since f39650de687e ("kernel.h: split out panic and oops helpers") that is no longer the case and get the following build error when building CONFIG_KASAN_HW_TAGS on arm64: In file included from arch/arm64/mm/kasan_init.c:10: include/linux/kasan.h: In function 'kasan_slab_free': include/linux/kasan.h:230:39: error: '_RET_IP_' undeclared (first use in this function) 230 | return __kasan_slab_free(s, object, _RET_IP_, init); Fix it by including kernel.h from kasan.h. Link: https://lkml.kernel.org/r/20210705072716.2125074-1-elver@google.com Fixes: f39650de687e ("kernel.h: split out panic and oops helpers") Signed-off-by: Marco Elver Reviewed-by: Andy Shevchenko Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Peter Collingbourne Cc: Catalin Marinas Cc: Vincenzo Frascino Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 5310e217bd74..dd874a1ee862 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -3,6 +3,7 @@ #define _LINUX_KASAN_H #include +#include #include #include From 54aa386661fef92b5f092d7068bc6d4952b91a71 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Wed, 14 Jul 2021 21:26:43 -0700 Subject: [PATCH 363/426] Revert "mm/page_alloc: make should_fail_alloc_page() static" This reverts commit f7173090033c70886d925995e9dfdfb76dbb2441. Fix an unresolved symbol error when CONFIG_DEBUG_INFO_BTF=y: LD vmlinux BTFIDS vmlinux FAILED unresolved symbol should_fail_alloc_page make: *** [Makefile:1199: vmlinux] Error 255 make: *** Deleting file 'vmlinux' Link: https://lkml.kernel.org/r/20210708191128.153796-1-mcroce@linux.microsoft.com Fixes: f7173090033c ("mm/page_alloc: make should_fail_alloc_page() static") Signed-off-by: Matteo Croce Acked-by: Mel Gorman Tested-by: John Hubbard Cc: Michal Hocko Cc: David Hildenbrand Cc: Vlastimil Babka Cc: Dan Streetman Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3b97e17806be..bf3117bb1e16 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3820,7 +3820,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ -static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return __should_fail_alloc_page(gfp_mask, order); } From 187ad460b8413e863c951998cb321a117a717868 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 14 Jul 2021 21:26:46 -0700 Subject: [PATCH 364/426] mm/page_alloc: avoid page allocator recursion with pagesets.lock held Syzbot is reporting potential deadlocks due to pagesets.lock when PAGE_OWNER is enabled. One example from Desmond Cheong Zhi Xi is as follows __alloc_pages_bulk() local_lock_irqsave(&pagesets.lock, flags) <---- outer lock here prep_new_page(): post_alloc_hook(): set_page_owner(): __set_page_owner(): save_stack(): stack_depot_save(): alloc_pages(): alloc_page_interleave(): __alloc_pages(): get_page_from_freelist(): rm_queue(): rm_queue_pcplist(): local_lock_irqsave(&pagesets.lock, flags); *** DEADLOCK *** Zhang, Qiang also reported BUG: sleeping function called from invalid context at mm/page_alloc.c:5179 in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 1, name: swapper/0 ..... __dump_stack lib/dump_stack.c:79 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:96 ___might_sleep.cold+0x1f1/0x237 kernel/sched/core.c:9153 prepare_alloc_pages+0x3da/0x580 mm/page_alloc.c:5179 __alloc_pages+0x12f/0x500 mm/page_alloc.c:5375 alloc_page_interleave+0x1e/0x200 mm/mempolicy.c:2147 alloc_pages+0x238/0x2a0 mm/mempolicy.c:2270 stack_depot_save+0x39d/0x4e0 lib/stackdepot.c:303 save_stack+0x15e/0x1e0 mm/page_owner.c:120 __set_page_owner+0x50/0x290 mm/page_owner.c:181 prep_new_page mm/page_alloc.c:2445 [inline] __alloc_pages_bulk+0x8b9/0x1870 mm/page_alloc.c:5313 alloc_pages_bulk_array_node include/linux/gfp.h:557 [inline] vm_area_alloc_pages mm/vmalloc.c:2775 [inline] __vmalloc_area_node mm/vmalloc.c:2845 [inline] __vmalloc_node_range+0x39d/0x960 mm/vmalloc.c:2947 __vmalloc_node mm/vmalloc.c:2996 [inline] vzalloc+0x67/0x80 mm/vmalloc.c:3066 There are a number of ways it could be fixed. The page owner code could be audited to strip GFP flags that allow sleeping but it'll impair the functionality of PAGE_OWNER if allocations fail. The bulk allocator could add a special case to release/reacquire the lock for prep_new_page and lookup PCP after the lock is reacquired at the cost of performance. The pages requiring prep could be tracked using the least significant bit and looping through the array although it is more complicated for the list interface. The options are relatively complex and the second one still incurs a performance penalty when PAGE_OWNER is active so this patch takes the simple approach -- disable bulk allocation of PAGE_OWNER is active. The caller will be forced to allocate one page at a time incurring a performance penalty but PAGE_OWNER is already a performance penalty. Link: https://lkml.kernel.org/r/20210708081434.GV3840@techsingularity.net Fixes: dbbee9d5cd83 ("mm/page_alloc: convert per-cpu list protection to local_lock") Signed-off-by: Mel Gorman Reported-by: Desmond Cheong Zhi Xi Reported-by: "Zhang, Qiang" Reported-by: syzbot+127fd7828d6eeb611703@syzkaller.appspotmail.com Tested-by: syzbot+127fd7828d6eeb611703@syzkaller.appspotmail.com Acked-by: Rafael Aquini Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bf3117bb1e16..84609716bab5 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5239,6 +5239,18 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, if (nr_pages - nr_populated == 1) goto failed; +#ifdef CONFIG_PAGE_OWNER + /* + * PAGE_OWNER may recurse into the allocator to allocate space to + * save the stack with pagesets.lock held. Releasing/reacquiring + * removes much of the performance benefit of bulk allocation so + * force the caller to allocate one page at a time as it'll have + * similar performance to added complexity to the bulk allocator. + */ + if (static_branch_unlikely(&page_owner_inited)) + goto failed; +#endif + /* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */ gfp &= gfp_allowed_mask; alloc_gfp = gfp; From e5c15cea339115edf99dc92282865f173cf84510 Mon Sep 17 00:00:00 2001 From: Yanfei Xu Date: Wed, 14 Jul 2021 21:26:49 -0700 Subject: [PATCH 365/426] mm/page_alloc: correct return value when failing at preparing If the array passed in is already partially populated, we should return "nr_populated" even failing at preparing arguments stage. Link: https://lkml.kernel.org/r/20210713152100.10381-3-mgorman@techsingularity.net Signed-off-by: Yanfei Xu Signed-off-by: Mel Gorman Link: https://lore.kernel.org/r/20210709102855.55058-1-yanfei.xu@windriver.com Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 84609716bab5..4d79e357a4ba 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5255,7 +5255,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, gfp &= gfp_allowed_mask; alloc_gfp = gfp; if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags)) - return 0; + return nr_populated; gfp = alloc_gfp; /* Find an allowed local zone that meets the low watermark. */ From 061478438d04779181c2ce4d7ffeeca343a70a98 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 14 Jul 2021 21:26:52 -0700 Subject: [PATCH 366/426] mm/page_alloc: further fix __alloc_pages_bulk() return value The author of commit b3b64ebd3822 ("mm/page_alloc: do bulk array bounds check after checking populated elements") was possibly confused by the mixture of return values throughout the function. The API contract is clear that the function "Returns the number of pages on the list or array." It does not list zero as a unique return value with a special meaning. Therefore zero is a plausible return value only if @nr_pages is zero or less. Clean up the return logic to make it clear that the returned value is always the total number of pages in the array/list, not the number of pages that were allocated during this call. The only change in behavior with this patch is the value returned if prepare_alloc_pages() fails. To match the API contract, the number of pages currently in the array/list is returned in this case. The call site in __page_pool_alloc_pages_slow() also seems to be confused on this matter. It should be attended to by someone who is familiar with that code. [mel@techsingularity.net: Return nr_populated if 0 pages are requested] Link: https://lkml.kernel.org/r/20210713152100.10381-4-mgorman@techsingularity.net Signed-off-by: Chuck Lever Signed-off-by: Mel Gorman Acked-by: Jesper Dangaard Brouer Cc: Desmond Cheong Zhi Xi Cc: Zhang Qiang Cc: Yanfei Xu Cc: Matteo Croce Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4d79e357a4ba..3e97e68aef7a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5221,9 +5221,6 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, unsigned int alloc_flags = ALLOC_WMARK_LOW; int nr_populated = 0, nr_account = 0; - if (unlikely(nr_pages <= 0)) - return 0; - /* * Skip populated array elements to determine if any pages need * to be allocated before disabling IRQs. @@ -5231,9 +5228,13 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, while (page_array && nr_populated < nr_pages && page_array[nr_populated]) nr_populated++; + /* No pages requested? */ + if (unlikely(nr_pages <= 0)) + goto out; + /* Already populated array? */ if (unlikely(page_array && nr_pages - nr_populated == 0)) - return nr_populated; + goto out; /* Use the single page allocator for one page. */ if (nr_pages - nr_populated == 1) @@ -5255,7 +5256,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, gfp &= gfp_allowed_mask; alloc_gfp = gfp; if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags)) - return nr_populated; + goto out; gfp = alloc_gfp; /* Find an allowed local zone that meets the low watermark. */ @@ -5323,6 +5324,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); zone_statistics(ac.preferred_zoneref->zone, zone, nr_account); +out: return nr_populated; failed_irq: @@ -5338,7 +5340,7 @@ failed: nr_populated++; } - return nr_populated; + goto out; } EXPORT_SYMBOL_GPL(__alloc_pages_bulk); From ab7965de1725cd8514f0edbced5c2fb793846078 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jul 2021 21:26:55 -0700 Subject: [PATCH 367/426] mm: fix the try_to_unmap prototype for !CONFIG_MMU Adjust the nommu stub of try_to_unmap to match the changed protype for the full version. Turn it into an inline instead of a macro to generally improve the type checking. Link: https://lkml.kernel.org/r/20210705053944.885828-1-hch@lst.de Fixes: 1fb08ac63bee ("mm: rmap: make try_to_unmap() void function") Signed-off-by: Christoph Hellwig Reviewed-by: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 83fb86133fe1..c976cc6de257 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -291,7 +291,9 @@ static inline int page_referenced(struct page *page, int is_locked, return 0; } -#define try_to_unmap(page, refs) false +static inline void try_to_unmap(struct page *page, enum ttu_flags flags) +{ +} static inline int page_mkclean(struct page *page) { From c52114d9df6a193fba5317933c75bc9bb5f6cf8a Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 14 Jul 2021 21:26:58 -0700 Subject: [PATCH 368/426] lib/test_hmm: remove set but unused page variable The HMM selftests use atomic_check_access() to check atomic access to a page has been revoked. It doesn't matter if the page mapping has been removed from the mirrored page tables as that also implies atomic access has been revoked. Therefore remove the unused page variable to fix this compiler warning: lib/test_hmm.c:631:16: warning: variable `page' set but not used [-Wunused-but-set-variable] Link: https://lkml.kernel.org/r/20210706025603.4059-1-apopple@nvidia.com Fixes: b659baea7546 ("mm: selftests for exclusive device memory") Signed-off-by: Alistair Popple Reported-by: Hulk Robot Reported-by: kernel test robot Reported-by: Yang Yingliang Acked-by: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_hmm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 8c55c4723692..c259842f6d44 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -628,10 +628,8 @@ static int dmirror_check_atomic(struct dmirror *dmirror, unsigned long start, for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) { void *entry; - struct page *page; entry = xa_load(&dmirror->pt, pfn); - page = xa_untag_pointer(entry); if (xa_pointer_tag(entry) == DPT_XA_TAG_ATOMIC) return -EPERM; } From 16ee572eaf0d09daa4c8a755fdb71e40dbf8562d Mon Sep 17 00:00:00 2001 From: Desmond Cheong Zhi Xi Date: Wed, 14 Jul 2021 21:27:01 -0700 Subject: [PATCH 369/426] hfs: add missing clean-up in hfs_fill_super Patch series "hfs: fix various errors", v2. This series ultimately aims to address a lockdep warning in hfs_find_init reported by Syzbot [1]. The work done for this led to the discovery of another bug, and the Syzkaller repro test also reveals an invalid memory access error after clearing the lockdep warning. Hence, this series is broken up into three patches: 1. Add a missing call to hfs_find_exit for an error path in hfs_fill_super 2. Fix memory mapping in hfs_bnode_read by fixing calls to kmap 3. Add lock nesting notation to tell lockdep that the observed locking hierarchy is safe This patch (of 3): Before exiting hfs_fill_super, the struct hfs_find_data used in hfs_find_init should be passed to hfs_find_exit to be cleaned up, and to release the lock held on the btree. The call to hfs_find_exit is missing from an error path. We add it back in by consolidating calls to hfs_find_exit for error paths. Link: https://syzkaller.appspot.com/bug?id=f007ef1d7a31a469e3be7aeb0fde0769b18585db [1] Link: https://lkml.kernel.org/r/20210701030756.58760-1-desmondcheongzx@gmail.com Link: https://lkml.kernel.org/r/20210701030756.58760-2-desmondcheongzx@gmail.com Signed-off-by: Desmond Cheong Zhi Xi Reviewed-by: Viacheslav Dubeyko Cc: Gustavo A. R. Silva Cc: Al Viro Cc: Shuah Khan Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hfs/super.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 44d07c9e3a7f..12d9bae39363 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -420,14 +420,12 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) if (!res) { if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { res = -EIO; - goto bail; + goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); } - if (res) { - hfs_find_exit(&fd); - goto bail_no_root; - } + if (res) + goto bail_hfs_find; res = -EINVAL; root_inode = hfs_iget(sb, &fd.search_key->cat, &rec); hfs_find_exit(&fd); @@ -443,6 +441,8 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) /* everything's okay */ return 0; +bail_hfs_find: + hfs_find_exit(&fd); bail_no_root: pr_err("get root inode failed\n"); bail: From 54a5ead6f5e2b47131a7385d0c0af18e7b89cb02 Mon Sep 17 00:00:00 2001 From: Desmond Cheong Zhi Xi Date: Wed, 14 Jul 2021 21:27:05 -0700 Subject: [PATCH 370/426] hfs: fix high memory mapping in hfs_bnode_read Pages that we read in hfs_bnode_read need to be kmapped into kernel address space. However, currently only the 0th page is kmapped. If the given offset + length exceeds this 0th page, then we have an invalid memory access. To fix this, we kmap relevant pages one by one and copy their relevant portions of data. An example of invalid memory access occurring without this fix can be seen in the following crash report: ================================================================== BUG: KASAN: use-after-free in memcpy include/linux/fortify-string.h:191 [inline] BUG: KASAN: use-after-free in hfs_bnode_read+0xc4/0xe0 fs/hfs/bnode.c:26 Read of size 2 at addr ffff888125fdcffe by task syz-executor5/4634 CPU: 0 PID: 4634 Comm: syz-executor5 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x195/0x1f8 lib/dump_stack.c:120 print_address_description.constprop.0+0x1d/0x110 mm/kasan/report.c:233 __kasan_report mm/kasan/report.c:419 [inline] kasan_report.cold+0x7b/0xd4 mm/kasan/report.c:436 check_region_inline mm/kasan/generic.c:180 [inline] kasan_check_range+0x154/0x1b0 mm/kasan/generic.c:186 memcpy+0x24/0x60 mm/kasan/shadow.c:65 memcpy include/linux/fortify-string.h:191 [inline] hfs_bnode_read+0xc4/0xe0 fs/hfs/bnode.c:26 hfs_bnode_read_u16 fs/hfs/bnode.c:34 [inline] hfs_bnode_find+0x880/0xcc0 fs/hfs/bnode.c:365 hfs_brec_find+0x2d8/0x540 fs/hfs/bfind.c:126 hfs_brec_read+0x27/0x120 fs/hfs/bfind.c:165 hfs_cat_find_brec+0x19a/0x3b0 fs/hfs/catalog.c:194 hfs_fill_super+0xc13/0x1460 fs/hfs/super.c:419 mount_bdev+0x331/0x3f0 fs/super.c:1368 hfs_mount+0x35/0x40 fs/hfs/super.c:457 legacy_get_tree+0x10c/0x220 fs/fs_context.c:592 vfs_get_tree+0x93/0x300 fs/super.c:1498 do_new_mount fs/namespace.c:2905 [inline] path_mount+0x13f5/0x20e0 fs/namespace.c:3235 do_mount fs/namespace.c:3248 [inline] __do_sys_mount fs/namespace.c:3456 [inline] __se_sys_mount fs/namespace.c:3433 [inline] __x64_sys_mount+0x2b8/0x340 fs/namespace.c:3433 do_syscall_64+0x37/0xc0 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x45e63a Code: 48 c7 c2 bc ff ff ff f7 d8 64 89 02 b8 ff ff ff ff eb d2 e8 88 04 00 00 0f 1f 84 00 00 00 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f9404d410d8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000020000248 RCX: 000000000045e63a RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007f9404d41120 RBP: 00007f9404d41120 R08: 00000000200002c0 R09: 0000000020000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003 R13: 0000000000000003 R14: 00000000004ad5d8 R15: 0000000000000000 The buggy address belongs to the page: page:00000000dadbcf3e refcount:0 mapcount:0 mapping:0000000000000000 index:0x1 pfn:0x125fdc flags: 0x2fffc0000000000(node=0|zone=2|lastcpupid=0x3fff) raw: 02fffc0000000000 ffffea000497f748 ffffea000497f6c8 0000000000000000 raw: 0000000000000001 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888125fdce80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888125fdcf00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff888125fdcf80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff888125fdd000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888125fdd080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== Link: https://lkml.kernel.org/r/20210701030756.58760-3-desmondcheongzx@gmail.com Signed-off-by: Desmond Cheong Zhi Xi Reviewed-by: Viacheslav Dubeyko Cc: Al Viro Cc: Greg Kroah-Hartman Cc: Gustavo A. R. Silva Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hfs/bnode.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index b63a4df7327b..c0a73a6ffb28 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -15,16 +15,31 @@ #include "btree.h" -void hfs_bnode_read(struct hfs_bnode *node, void *buf, - int off, int len) +void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) { struct page *page; + int pagenum; + int bytes_read; + int bytes_to_read; + void *vaddr; off += node->page_offset; - page = node->page[0]; + pagenum = off >> PAGE_SHIFT; + off &= ~PAGE_MASK; /* compute page offset for the first page */ - memcpy(buf, kmap(page) + off, len); - kunmap(page); + for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) { + if (pagenum >= node->tree->pages_per_bnode) + break; + page = node->page[pagenum]; + bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off); + + vaddr = kmap_atomic(page); + memcpy(buf + bytes_read, vaddr + off, bytes_to_read); + kunmap_atomic(vaddr); + + pagenum++; + off = 0; /* page offset only applies to the first page */ + } } u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off) From b3b2177a2d795e35dc11597b2609eb1e7e57e570 Mon Sep 17 00:00:00 2001 From: Desmond Cheong Zhi Xi Date: Wed, 14 Jul 2021 21:27:08 -0700 Subject: [PATCH 371/426] hfs: add lock nesting notation to hfs_find_init Syzbot reports a possible recursive lock in [1]. This happens due to missing lock nesting information. From the logs, we see that a call to hfs_fill_super is made to mount the hfs filesystem. While searching for the root inode, the lock on the catalog btree is grabbed. Then, when the parent of the root isn't found, a call to __hfs_bnode_create is made to create the parent of the root. This eventually leads to a call to hfs_ext_read_extent which grabs a lock on the extents btree. Since the order of locking is catalog btree -> extents btree, this lock hierarchy does not lead to a deadlock. To tell lockdep that this locking is safe, we add nesting notation to distinguish between catalog btrees, extents btrees, and attributes btrees (for HFS+). This has already been done in hfsplus. Link: https://syzkaller.appspot.com/bug?id=f007ef1d7a31a469e3be7aeb0fde0769b18585db [1] Link: https://lkml.kernel.org/r/20210701030756.58760-4-desmondcheongzx@gmail.com Signed-off-by: Desmond Cheong Zhi Xi Reported-by: syzbot+b718ec84a87b7e73ade4@syzkaller.appspotmail.com Tested-by: syzbot+b718ec84a87b7e73ade4@syzkaller.appspotmail.com Reviewed-by: Viacheslav Dubeyko Cc: Al Viro Cc: Greg Kroah-Hartman Cc: Gustavo A. R. Silva Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hfs/bfind.c | 14 +++++++++++++- fs/hfs/btree.h | 7 +++++++ 2 files changed, 20 insertions(+), 1 deletion(-) diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index 4af318fbda77..ef9498a6e88a 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -25,7 +25,19 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) fd->key = ptr + tree->max_key_len + 2; hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); - mutex_lock(&tree->tree_lock); + switch (tree->cnid) { + case HFS_CAT_CNID: + mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX); + break; + case HFS_EXT_CNID: + mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX); + break; + case HFS_ATTR_CNID: + mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX); + break; + default: + return -EINVAL; + } return 0; } diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h index 4ba45caf5939..0e6baee93245 100644 --- a/fs/hfs/btree.h +++ b/fs/hfs/btree.h @@ -13,6 +13,13 @@ typedef int (*btree_keycmp)(const btree_key *, const btree_key *); #define NODE_HASH_SIZE 256 +/* B-tree mutex nested subclasses */ +enum hfs_btree_mutex_classes { + CATALOG_BTREE_MUTEX, + EXTENTS_BTREE_MUTEX, + ATTR_BTREE_MUTEX, +}; + /* A HFS BTree held in memory */ struct hfs_btree { struct super_block *sb; From d08af0a59684e18a51aa4bfd24c658994ea3fc5b Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Wed, 14 Jul 2021 21:27:11 -0700 Subject: [PATCH 372/426] mm/hugetlb: fix refs calculation from unaligned @vaddr Commit 82e5d378b0e47 ("mm/hugetlb: refactor subpage recording") refactored the count of subpages but missed an edge case when @vaddr is not aligned to PAGE_SIZE e.g. when close to vma->vm_end. It would then errousnly set @refs to 0 and record_subpages_vmas() wouldn't set the @pages array element to its value, consequently causing the reported null-deref by syzbot. Fix it by aligning down @vaddr by PAGE_SIZE in @refs calculation. Link: https://lkml.kernel.org/r/20210713152440.28650-1-joao.m.martins@oracle.com Fixes: 82e5d378b0e47 ("mm/hugetlb: refactor subpage recording") Reported-by: syzbot+a3fcd59df1b372066f5a@syzkaller.appspotmail.com Signed-off-by: Joao Martins Reviewed-by: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 924553aa8f78..dfc940d5221d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5440,8 +5440,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, continue; } - refs = min3(pages_per_huge_page(h) - pfn_offset, - (vma->vm_end - vaddr) >> PAGE_SHIFT, remainder); + /* vaddr may not be aligned to PAGE_SIZE */ + refs = min3(pages_per_huge_page(h) - pfn_offset, remainder, + (vma->vm_end - ALIGN_DOWN(vaddr, PAGE_SIZE)) >> PAGE_SHIFT); if (pages || vmas) record_subpages_vmas(mem_map_offset(page, pfn_offset), From a1c9ca5f65c9acfd7c02474b9d5cacbd7ea288df Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 15 Jul 2021 11:55:31 -0700 Subject: [PATCH 373/426] EDAC/igen6: fix core dependency AGAIN My previous patch had a typo/thinko which prevents this driver from being enabled: change X64_64 to X86_64. Fixes: 0a9ece9ba154 ("EDAC/igen6: fix core dependency") Signed-off-by: Randy Dunlap Cc: Qiuxu Zhuo Cc: Borislav Petkov Cc: Mauro Carvalho Chehab Cc: linux-edac@vger.kernel.org Cc: bowsingbetee Cc: stable@vger.kernel.org Signed-off-by: Tony Luck Signed-off-by: Linus Torvalds --- drivers/edac/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 91164c5f0757..2fc4c3f91fd5 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -271,7 +271,7 @@ config EDAC_PND2 config EDAC_IGEN6 tristate "Intel client SoC Integrated MC" depends on PCI && PCI_MMCONFIG && ARCH_HAVE_NMI_SAFE_CMPXCHG - depends on X64_64 && X86_MCE_INTEL + depends on X86_64 && X86_MCE_INTEL help Support for error detection and correction on the Intel client SoC Integrated Memory Controller using In-Band ECC IP. From 0967ebffe098157180a0bbd180ac90348c6e07d7 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:06 +0200 Subject: [PATCH 374/426] perf inject: Fix dso->nsinfo refcounting ASan reports a memory leak of nsinfo during the execution of: # perf test "31: Lookup mmap thread" The leak is caused by a refcounted variable being replaced without dropping the refcount. This patch makes sure that the refcnt of nsinfo is decreased when a refcounted variable is replaced with a new value. Signed-off-by: Riccardo Mancini Fixes: 27c9c3424fc217da ("perf inject: Add --buildid-all option") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/55223bc8821b34ccb01f92ef1401c02b6a32e61f.1626343282.git.rickyman7@gmail.com [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 5d6f583e2cd3..ffd2b25039e3 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -361,9 +361,10 @@ static struct dso *findnew_dso(int pid, int tid, const char *filename, dso = machine__findnew_dso_id(machine, filename, id); } - if (dso) + if (dso) { + nsinfo__put(dso->nsinfo); dso->nsinfo = nsi; - else + } else nsinfo__put(nsi); thread__put(thread); From 2d6b74baa7147251c30a46c4996e8cc224aa2dc5 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:06 +0200 Subject: [PATCH 375/426] perf map: Fix dso->nsinfo refcounting ASan reports a memory leak of nsinfo during the execution of # perf test "31: Lookup mmap thread" The leak is caused by a refcounted variable being replaced without dropping the refcount. This patch makes sure that the refcnt of nsinfo is decreased whenever a refcounted variable is replaced with a new value. Signed-off-by: Riccardo Mancini Fixes: bf2e710b3cb8445c ("perf maps: Lookup maps in both intitial mountns and inner mountns.") Cc: Ian Rogers Cc: Jiri Olsa Cc: Krister Johansen Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/55223bc8821b34ccb01f92ef1401c02b6a32e61f.1626343282.git.rickyman7@gmail.com [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8af693d9678c..72e7f3616157 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -192,6 +192,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (!(prot & PROT_EXEC)) dso__set_loaded(dso); } + + nsinfo__put(dso->nsinfo); dso->nsinfo = nsi; if (build_id__is_defined(bid)) From dedeb4be203b382ba7245d13079bc3b0f6d40c65 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:06 +0200 Subject: [PATCH 376/426] perf probe: Fix dso->nsinfo refcounting ASan reports a memory leak of nsinfo during the execution of: # perf test "31: Lookup mmap thread". The leak is caused by a refcounted variable being replaced without dropping the refcount. This patch makes sure that the refcnt of nsinfo is decreased whenever a refcounted variable is replaced with a new value. Signed-off-by: Riccardo Mancini Fixes: 544abd44c7064c8a ("perf probe: Allow placing uprobes in alternate namespaces.") Cc: Ian Rogers Cc: Jiri Olsa Cc: Krister Johansen Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/55223bc8821b34ccb01f92ef1401c02b6a32e61f.1626343282.git.rickyman7@gmail.com [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index c14e1d228e56..e05750cea34c 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -179,8 +179,10 @@ struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user) struct map *map; map = dso__new_map(target); - if (map && map->dso) + if (map && map->dso) { + nsinfo__put(map->dso->nsinfo); map->dso->nsinfo = nsinfo__get(nsi); + } return map; } else { return kernel_get_module_map(target); From 42db3d9ded555f7148b5695109a7dc8d66f0dde4 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:07 +0200 Subject: [PATCH 377/426] perf env: Fix sibling_dies memory leak ASan reports a memory leak in perf_env while running: # perf test "41: Session topology" Caused by sibling_dies not being freed. This patch adds the required free. Fixes: acae8b36cded0ee6 ("perf header: Add die information in CPU topology") Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/2140d0b57656e4eb9021ca9772250c24c032924b.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/env.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index ebc5e9ad35db..6c765946ef6f 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -186,6 +186,7 @@ void perf_env__exit(struct perf_env *env) zfree(&env->cpuid); zfree(&env->cmdline); zfree(&env->cmdline_argv); + zfree(&env->sibling_dies); zfree(&env->sibling_cores); zfree(&env->sibling_threads); zfree(&env->pmu_mappings); From 233f2dc1c284337286f9a64c0152236779a42f6c Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:08 +0200 Subject: [PATCH 378/426] perf test session_topology: Delete session->evlist ASan reports a memory leak related to session->evlist while running: # perf test "41: Session topology". When perf_data is in write mode, session->evlist is owned by the caller, which should also take care of deleting it. This patch adds the missing evlist__delete(). Signed-off-by: Riccardo Mancini Fixes: c84974ed9fb67293 ("perf test: Add entry to test cpu topology") Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/822f741f06eb25250fb60686cf30a35f447e9e91.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/topology.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index ec4e3b21b831..b5efe675b321 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -61,6 +61,7 @@ static int session_write_header(char *path) TEST_ASSERT_VAL("failed to write header", !perf_session__write_header(session, session->evlist, data.file.fd, true)); + evlist__delete(session->evlist); perf_session__delete(session); return 0; From fc56f54f6fcd5337634f4545af6459613129b432 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:09 +0200 Subject: [PATCH 379/426] perf test event_update: Fix memory leak of evlist ASan reports a memory leak when running: # perf test "49: Synthesize attr update" Caused by evlist not being deleted. This patch adds the missing evlist__delete and removes the perf_cpu_map__put since it's already being deleted by evlist__delete. Signed-off-by: Riccardo Mancini Fixes: a6e5281780d1da65 ("perf tools: Add event_update event unit type") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/f7994ad63d248f7645f901132d208fadf9f2b7e4.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/event_update.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 656218179222..932ab0740d11 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -118,6 +118,6 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to synthesize attr update cpus", !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus)); - perf_cpu_map__put(evsel->core.own_cpus); + evlist__delete(evlist); return 0; } From dccfca926c351ba0893af4c8b481477bdb2881a4 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:10 +0200 Subject: [PATCH 380/426] perf test event_update: Fix memory leak of unit ASan reports a memory leak while running: # perf test "49: Synthesize attr update" Caused by a string being duplicated but never freed. This patch adds the missing free(). Note that evsel->unit is not deallocated together with evsel since it is supposed to be a constant string. Signed-off-by: Riccardo Mancini Fixes: a6e5281780d1da65 ("perf tools: Add event_update event unit type") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/1fbc8158663fb0d4d5392e36bae564f6ad60be3c.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/event_update.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 932ab0740d11..44a50527f9d9 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -88,6 +88,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu struct evsel *evsel; struct event_name tmp; struct evlist *evlist = evlist__new_default(); + char *unit = strdup("KRAVA"); TEST_ASSERT_VAL("failed to get evlist", evlist); @@ -98,7 +99,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123); - evsel->unit = strdup("KRAVA"); + evsel->unit = unit; TEST_ASSERT_VAL("failed to synthesize attr update unit", !perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit)); @@ -118,6 +119,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to synthesize attr update cpus", !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus)); + free(unit); evlist__delete(evlist); return 0; } From 581e295a0f6b5c2931d280259fbbfff56959faa9 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:11 +0200 Subject: [PATCH 381/426] perf dso: Fix memory leak in dso__new_map() ASan reports a memory leak when running: # perf test "65: maps__merge_in". The causes of the leaks are two, this patch addresses only the first one, which is related to dso__new_map(). The bug is that dso__new_map() creates a new dso but never decreases the refcount it gets from creating it. This patch adds the missing dso__put(). Signed-off-by: Riccardo Mancini Fixes: d3a7c489c7fd2463 ("perf tools: Reference count struct dso") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/60bfe0cd06e89e2ca33646eb8468d7f5de2ee597.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index d786cf6b0cfa..ee15db2be2f4 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1154,8 +1154,10 @@ struct map *dso__new_map(const char *name) struct map *map = NULL; struct dso *dso = dso__new(name); - if (dso) + if (dso) { map = map__new2(0, dso); + dso__put(dso); + } return map; } From 244d1797c8c8e850b8de7992af713aa5c70d5650 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:12 +0200 Subject: [PATCH 382/426] perf test maps__merge_in: Fix memory leak of maps ASan reports a memory leak when running: # perf test "65: maps__merge_in" This is the second and final patch addressing these memory leaks. This time, the problem is simply that the maps object is never destructed. This patch adds the missing maps__exit call. Signed-off-by: Riccardo Mancini Fixes: 79b6bb73f888933c ("perf maps: Merge 'struct maps' with 'struct map_groups'") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/a1a29b97a58738987d150e94d4ebfad0282fb038.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/maps.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index edcbc70ff9d6..1ac72919fa35 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -116,5 +116,7 @@ int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unus ret = check_maps(merged3, ARRAY_SIZE(merged3), &maps); TEST_ASSERT_VAL("merge check failed", !ret); + + maps__exit(&maps); return TEST_OK; } From da6b7c6c0626901428245f65712385805e42eba6 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:13 +0200 Subject: [PATCH 383/426] perf env: Fix memory leak of cpu_pmu_caps ASan reports memory leaks while running: # perf test "83: Zstd perf.data compression/decompression" The first of the leaks is caused by env->cpu_pmu_caps not being freed. This patch adds the missing (z)free inside perf_env__exit. Signed-off-by: Riccardo Mancini Fixes: 6f91ea283a1ed23e ("perf header: Support CPU PMU capabilities") Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/6ba036a8220156ec1f3d6be3e5d25920f6145028.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/env.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 6c765946ef6f..cec2e6cad8aa 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -191,6 +191,7 @@ void perf_env__exit(struct perf_env *env) zfree(&env->sibling_threads); zfree(&env->pmu_mappings); zfree(&env->cpu); + zfree(&env->cpu_pmu_caps); zfree(&env->numa_map); for (i = 0; i < env->nr_numa_nodes; i++) From a37338aad8c4d8676173ead14e881d2ec308155c Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:14 +0200 Subject: [PATCH 384/426] perf report: Free generated help strings for sort option ASan reports the memory leak of the strings allocated by sort_help() when running perf report. This patch changes the returned pointer to char* (instead of const char*), saves it in a temporary variable, and finally deallocates it at function exit. Signed-off-by: Riccardo Mancini Fixes: 702fb9b415e7c99b ("perf report: Show all sort keys in help output") Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/a38b13f02812a8a6759200b9063c6191337f44d4.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 33 ++++++++++++++++++++++----------- tools/perf/util/sort.c | 2 +- tools/perf/util/sort.h | 2 +- 3 files changed, 24 insertions(+), 13 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 6386af6a2612..dc0364f671b9 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1175,6 +1175,8 @@ int cmd_report(int argc, const char **argv) .annotation_opts = annotation__default_options, .skip_empty = true, }; + char *sort_order_help = sort_help("sort by key(s):"); + char *field_order_help = sort_help("output field(s): overhead period sample "); const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -1209,9 +1211,9 @@ int cmd_report(int argc, const char **argv) OPT_BOOLEAN(0, "header-only", &report.header_only, "Show only data header."), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - sort_help("sort by key(s):")), + sort_order_help), OPT_STRING('F', "fields", &field_order, "key[,keys...]", - sort_help("output field(s): overhead period sample ")), + field_order_help), OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, @@ -1344,11 +1346,11 @@ int cmd_report(int argc, const char **argv) char sort_tmp[128]; if (ret < 0) - return ret; + goto exit; ret = perf_config(report__config, &report); if (ret) - return ret; + goto exit; argc = parse_options(argc, argv, options, report_usage, 0); if (argc) { @@ -1362,8 +1364,10 @@ int cmd_report(int argc, const char **argv) report.symbol_filter_str = argv[0]; } - if (annotate_check_args(&report.annotation_opts) < 0) - return -EINVAL; + if (annotate_check_args(&report.annotation_opts) < 0) { + ret = -EINVAL; + goto exit; + } if (report.mmaps_mode) report.tasks_mode = true; @@ -1377,12 +1381,14 @@ int cmd_report(int argc, const char **argv) if (symbol_conf.vmlinux_name && access(symbol_conf.vmlinux_name, R_OK)) { pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); - return -EINVAL; + ret = -EINVAL; + goto exit; } if (symbol_conf.kallsyms_name && access(symbol_conf.kallsyms_name, R_OK)) { pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name); - return -EINVAL; + ret = -EINVAL; + goto exit; } if (report.inverted_callchain) @@ -1406,12 +1412,14 @@ int cmd_report(int argc, const char **argv) repeat: session = perf_session__new(&data, false, &report.tool); - if (IS_ERR(session)) - return PTR_ERR(session); + if (IS_ERR(session)) { + ret = PTR_ERR(session); + goto exit; + } ret = evswitch__init(&report.evswitch, session->evlist, stderr); if (ret) - return ret; + goto exit; if (zstd_init(&(session->zstd_data), 0) < 0) pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); @@ -1646,5 +1654,8 @@ error: zstd_fini(&(session->zstd_data)); perf_session__delete(session); +exit: + free(sort_order_help); + free(field_order_help); return ret; } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 88ce47f2547e..568a88c001c6 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -3370,7 +3370,7 @@ static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int add_key(sb, s[i].name, llen); } -const char *sort_help(const char *prefix) +char *sort_help(const char *prefix) { struct strbuf sb; char *s; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 87a092645aa7..b67c469aba79 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -302,7 +302,7 @@ void reset_output_field(void); void sort__setup_elide(FILE *fp); void perf_hpp__set_elide(int idx, bool elide); -const char *sort_help(const char *prefix); +char *sort_help(const char *prefix); int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); From 02e6246f5364d5260a6ea6f92ab6f409058b162f Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:15 +0200 Subject: [PATCH 385/426] perf inject: Close inject.output on exit ASan reports a memory leak when running: # perf test "83: Zstd perf.data compression/decompression" which happens inside 'perf inject'. The bug is caused by inject.output never being closed. This patch adds the missing perf_data__close(). Signed-off-by: Riccardo Mancini Fixes: 6ef81c55a2b6584c ("perf session: Return error code for perf_session__new() function on failure") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mamatha Inamdar Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/c06f682afa964687367cf6e92a64ceb49aec76a5.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index ffd2b25039e3..c88c61e7f8cc 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -993,8 +993,10 @@ int cmd_inject(int argc, const char **argv) data.path = inject.input_name; inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool); - if (IS_ERR(inject.session)) - return PTR_ERR(inject.session); + if (IS_ERR(inject.session)) { + ret = PTR_ERR(inject.session); + goto out_close_output; + } if (zstd_init(&(inject.session->zstd_data), 0) < 0) pr_warning("Decompression initialization failed.\n"); @@ -1036,6 +1038,8 @@ int cmd_inject(int argc, const char **argv) out_delete: zstd_fini(&(inject.session->zstd_data)); perf_session__delete(inject.session); +out_close_output: + perf_data__close(&inject.output); free(inject.itrace_synth_opts.vm_tm_corr_args); return ret; } From 423b9174f5f71fd3d245f4da0feaf958976f66e7 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:16 +0200 Subject: [PATCH 386/426] perf session: Cleanup trace_event ASan reports several memory leaks when running: # perf test "82: Use vfs_getname probe to get syscall args filenames" many of which are related to session->tevent. This patch will solve this problem, then next patch will fix the remaining memory leaks in 'perf script'. This bug is due to a missing deallocation of the trace_event data strutures. This patch adds the missing trace_event__cleanup() in perf_session__delete(). Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/fa2a3f221d90e47ce4e5b7e2d6e64c3509ddc96a.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e9c929a39973..51f727402912 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -306,6 +306,7 @@ void perf_session__delete(struct perf_session *session) evlist__delete(session->evlist); perf_data__close(session->data); } + trace_event__cleanup(&session->tevent); free(session); } From 1b1f57cf9e4c8eb16c8f6b2ce12cc5dd3517fc61 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:17 +0200 Subject: [PATCH 387/426] perf script: Release zstd data ASan reports several memory leak while running: # perf test "82: Use vfs_getname probe to get syscall args filenames" One of the leaks is caused by zstd data not being released on exit in perf-script. This patch adds the missing zstd_fini(). Signed-off-by: Riccardo Mancini Fixes: b13b04d9382113f7 ("perf script: Initialize zstd_data") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/39388e8cc2f85ca219ea18697a17b7bd8f74b693.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8c03a9862872..bae0e5b72c0e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -4143,6 +4143,7 @@ out_delete: zfree(&script.ptime_range); } + zstd_fini(&(session->zstd_data)); evlist__free_stats(session->evlist); perf_session__delete(session); From faf3ac305d61341c74e5cdd9e41daecce7f67bfe Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:18 +0200 Subject: [PATCH 388/426] perf script: Fix memory 'threads' and 'cpus' leaks on exit ASan reports several memory leaks while running: # perf test "82: Use vfs_getname probe to get syscall args filenames" Two of these are caused by some refcounts not being decreased on perf-script exit, namely script.threads and script.cpus. This patch adds the missing __put calls in a new perf_script__exit function, which is called at the end of cmd_script. This patch concludes the fixes of all remaining memory leaks in perf test "82: Use vfs_getname probe to get syscall args filenames". Signed-off-by: Riccardo Mancini Fixes: cfc8874a48599249 ("perf script: Process cpu/threads maps") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/5ee73b19791c6fa9d24c4d57f4ac1a23609400d7.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index bae0e5b72c0e..064da7f3618d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2601,6 +2601,12 @@ static void perf_script__exit_per_event_dump_stats(struct perf_script *script) } } +static void perf_script__exit(struct perf_script *script) +{ + perf_thread_map__put(script->threads); + perf_cpu_map__put(script->cpus); +} + static int __cmd_script(struct perf_script *script) { int ret; @@ -4146,6 +4152,7 @@ out_delete: zstd_fini(&(session->zstd_data)); evlist__free_stats(session->evlist); perf_session__delete(session); + perf_script__exit(&script); if (script_started) cleanup_scripting(); From f8cbb0f926ae1e1fb5f9e51614e5437560ed4039 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:19 +0200 Subject: [PATCH 389/426] perf lzma: Close lzma stream on exit ASan reports memory leaks when running: # perf test "88: Check open filename arg using perf trace + vfs_getname" One of these is caused by the lzma stream never being closed inside lzma_decompress_to_file(). This patch adds the missing lzma_end(). Signed-off-by: Riccardo Mancini Fixes: 80a32e5b498a7547 ("perf tools: Add lzma decompression support for kernel module") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/aaf50bdce7afe996cfc06e1bbb36e4a2a9b9db93.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/lzma.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 39062df02629..51424cdc3b68 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -69,7 +69,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (ferror(infile)) { pr_err("lzma: read error: %s\n", strerror(errno)); - goto err_fclose; + goto err_lzma_end; } if (feof(infile)) @@ -83,7 +83,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (writen(output_fd, buf_out, write_size) != write_size) { pr_err("lzma: write error: %s\n", strerror(errno)); - goto err_fclose; + goto err_lzma_end; } strm.next_out = buf_out; @@ -95,11 +95,13 @@ int lzma_decompress_to_file(const char *input, int output_fd) break; pr_err("lzma: failed %s\n", lzma_strerror(ret)); - goto err_fclose; + goto err_lzma_end; } } err = 0; +err_lzma_end: + lzma_end(&strm); err_fclose: fclose(infile); return err; From 6c7f0ab04707c2882f08d5abb9dc41b54493b61c Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:20 +0200 Subject: [PATCH 390/426] perf trace: Free malloc'd trace fields on exit ASan reports several memory leaks running: # perf test "88: Check open filename arg using perf trace + vfs_getname" The first of these leaks is related to struct trace fields never being deallocated. This patch adds the function trace__exit, which is called at the end of cmd_trace, replacing the existing deallocation, which is now moved inside the new function. This function deallocates: - ev_qualifier - ev_qualifier_ids.entries - syscalls.table - sctbl - perfconfig_events Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/de5945ed5c0cb882cbfa3268567d0bff460ff016.1626343282.git.rickyman7@gmail.com [ Removed needless initialization to zero, missing named initializers are zeroed by the compiler ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 7ec18ff57fc4..e239e322e030 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -4701,6 +4701,15 @@ out: return err; } +static void trace__exit(struct trace *trace) +{ + strlist__delete(trace->ev_qualifier); + free(trace->ev_qualifier_ids.entries); + free(trace->syscalls.table); + syscalltbl__delete(trace->sctbl); + zfree(&trace->perfconfig_events); +} + int cmd_trace(int argc, const char **argv) { const char *trace_usage[] = { @@ -5135,6 +5144,6 @@ out_close: if (output_name != NULL) fclose(trace.output); out: - zfree(&trace.perfconfig_events); + trace__exit(&trace); return err; } From f2ebf8ffe7af10bff02d34addbebd9199de65ed2 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:21 +0200 Subject: [PATCH 391/426] perf trace: Free syscall->arg_fmt ASan reports several memory leaks running: # perf test "88: Check open filename arg using perf trace + vfs_getname" The second of these leaks is caused by the arg_fmt field of syscall not being deallocated. This patch adds a new function syscall__exit which is called on all syscalls.table entries in trace__exit, which will free the arg_fmt field. Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/d68f25c043d30464ac9fa79c3399e18f429bca82.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index e239e322e030..4039ff4c0788 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2266,6 +2266,14 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam return augmented_args; } +static void syscall__exit(struct syscall *sc) +{ + if (!sc) + return; + + free(sc->arg_fmt); +} + static int trace__sys_enter(struct trace *trace, struct evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) @@ -4703,9 +4711,15 @@ out: static void trace__exit(struct trace *trace) { + int i; + strlist__delete(trace->ev_qualifier); free(trace->ev_qualifier_ids.entries); - free(trace->syscalls.table); + if (trace->syscalls.table) { + for (i = 0; i <= trace->sctbl->syscalls.max_id; i++) + syscall__exit(&trace->syscalls.table[i]); + free(trace->syscalls.table); + } syscalltbl__delete(trace->sctbl); zfree(&trace->perfconfig_events); } From 3cb4d5e00e037c70f239173bdd399a7e6040830f Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:22 +0200 Subject: [PATCH 392/426] perf trace: Free syscall tp fields in evsel->priv ASan reports several memory leaks running: # perf test "88: Check open filename arg using perf trace + vfs_getname" The third of these leaks is related to evsel->priv fields of sycalls never being deallocated. This patch adds the function evlist__free_syscall_tp_fields which iterates over all evsels in evlist, matching syscalls, and calling the missing frees. This new function is called at the end of trace__run, right before calling evlist__delete. Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/46526611904ec5ff2768b59014e3afce8e0197d1.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 4039ff4c0788..0d9e58190f15 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3103,6 +3103,21 @@ static struct evsel *evsel__new_pgfault(u64 config) return evsel; } +static void evlist__free_syscall_tp_fields(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + struct evsel_trace *et = evsel->priv; + + if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls")) + continue; + + free(et->fmt); + free(et); + } +} + static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample) { const u32 type = event->header.type; @@ -4138,7 +4153,7 @@ out_disable: out_delete_evlist: trace__symbols__exit(trace); - + evlist__free_syscall_tp_fields(evlist); evlist__delete(evlist); cgroup__put(trace->cgroup); trace->evlist = NULL; From 659ede7d13f1cc37882088deecbc085da285b8f8 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:23 +0200 Subject: [PATCH 393/426] perf trace: Free strings in trace__parse_events_option() ASan reports several memory leaks running: # perf test "88: Check open filename arg using perf trace + vfs_getname" The fourth of these leaks is related to some strings never being freed in trace__parse_events_option. This patch adds the missing frees. Signed-off-by: Riccardo Mancini Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/34d08535b11124106b859790549991abff5a7de8.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 0d9e58190f15..9c265fa96011 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -4659,6 +4659,9 @@ do_concat: err = parse_events_option(&o, lists[0], 0); } out: + free(strace_groups_dir); + free(lists[0]); + free(lists[1]); if (sep) *sep = ','; From 704adfb5a9978462cd861f170201ae2b5e3d3a80 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 15 Jul 2021 00:02:06 -0400 Subject: [PATCH 394/426] tracing: Do not reference char * as a string in histograms The histogram logic was allowing events with char * pointers to be used as normal strings. But it was easy to crash the kernel with: # echo 'hist:keys=filename' > events/syscalls/sys_enter_openat/trigger And open some files, and boom! BUG: unable to handle page fault for address: 00007f2ced0c3280 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 1173fa067 P4D 1173fa067 PUD 1171b6067 PMD 1171dd067 PTE 0 Oops: 0000 [#1] PREEMPT SMP CPU: 6 PID: 1810 Comm: cat Not tainted 5.13.0-rc5-test+ #61 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v03.03 07/14/2016 RIP: 0010:strlen+0x0/0x20 Code: f6 82 80 2a 0b a9 20 74 11 0f b6 50 01 48 83 c0 01 f6 82 80 2a 0b a9 20 75 ef c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 <80> 3f 00 74 10 48 89 f8 48 83 c0 01 80 38 00 75 f7 48 29 f8 c3 RSP: 0018:ffffbdbf81567b50 EFLAGS: 00010246 RAX: 0000000000000003 RBX: ffff93815cdb3800 RCX: ffff9382401a22d0 RDX: 0000000000000100 RSI: 0000000000000000 RDI: 00007f2ced0c3280 RBP: 0000000000000100 R08: ffff9382409ff074 R09: ffffbdbf81567c98 R10: ffff9382409ff074 R11: 0000000000000000 R12: ffff9382409ff074 R13: 0000000000000001 R14: ffff93815a744f00 R15: 00007f2ced0c3280 FS: 00007f2ced0f8580(0000) GS:ffff93825a800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2ced0c3280 CR3: 0000000107069005 CR4: 00000000001706e0 Call Trace: event_hist_trigger+0x463/0x5f0 ? find_held_lock+0x32/0x90 ? sched_clock_cpu+0xe/0xd0 ? lock_release+0x155/0x440 ? kernel_init_free_pages+0x6d/0x90 ? preempt_count_sub+0x9b/0xd0 ? kernel_init_free_pages+0x6d/0x90 ? get_page_from_freelist+0x12c4/0x1680 ? __rb_reserve_next+0xe5/0x460 ? ring_buffer_lock_reserve+0x12a/0x3f0 event_triggers_call+0x52/0xe0 ftrace_syscall_enter+0x264/0x2c0 syscall_trace_enter.constprop.0+0x1ee/0x210 do_syscall_64+0x1c/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Where it triggered a fault on strlen(key) where key was the filename. The reason is that filename is a char * to user space, and the histogram code just blindly dereferenced it, with obvious bad results. I originally tried to use strncpy_from_user/kernel_nofault() but found that there's other places that its dereferenced and not worth the effort. Just do not allow "char *" to act like strings. Link: https://lkml.kernel.org/r/20210715000206.025df9d2@rorschach.local.home Cc: Ingo Molnar Cc: Andrew Morton Cc: Masami Hiramatsu Cc: Tzvetomir Stoyanov Cc: stable@vger.kernel.org Acked-by: Namhyung Kim Acked-by: Tom Zanussi Fixes: 79e577cbce4c4 ("tracing: Support string type key properly") Fixes: 5967bd5c4239 ("tracing: Let filter_assign_type() detect FILTER_PTR_STRING") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0207aeed31e6..16a9dfc9fffc 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1689,7 +1689,9 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (WARN_ON_ONCE(!field)) goto out; - if (is_string_field(field)) { + /* Pointers to strings are just pointers and dangerous to dereference */ + if (is_string_field(field) && + (field->filter_type != FILTER_PTR_STRING)) { flags |= HIST_FIELD_FL_STRING; hist_field->size = MAX_FILTER_STR_VAL; @@ -4495,8 +4497,6 @@ static inline void add_to_key(char *compound_key, void *key, field = key_field->field; if (field->filter_type == FILTER_DYN_STRING) size = *(u32 *)(rec + field->offset) >> 16; - else if (field->filter_type == FILTER_PTR_STRING) - size = strlen(key); else if (field->filter_type == FILTER_STATIC_STRING) size = field->size; From 507345b5ae6a57b7ecd7550ff39282ed20de7b8d Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Mon, 12 Jul 2021 12:38:24 -0300 Subject: [PATCH 395/426] cifs: handle reconnect of tcon when there is no cached dfs referral When there is no cached DFS referral of tcon->dfs_path, then reconnect to same share. Signed-off-by: Paulo Alcantara (SUSE) Cc: Signed-off-by: Steve French --- fs/cifs/connect.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index f1a7e63ab58f..d49c9e5c33fa 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4144,7 +4144,8 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru if (!tree) return -ENOMEM; - if (!tcon->dfs_path) { + /* If it is not dfs or there was no cached dfs referral, then reconnect to same share */ + if (!tcon->dfs_path || dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl)) { if (tcon->ipc) { scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); @@ -4154,9 +4155,6 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru goto out; } - rc = dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl); - if (rc) - goto out; isroot = ref.server_type == DFS_TYPE_ROOT; free_dfs_info_param(&ref); From 63f94e946fafcfc5080b4a4aec9770158268e4ee Mon Sep 17 00:00:00 2001 From: Steve French Date: Tue, 13 Jul 2021 19:40:33 -0500 Subject: [PATCH 396/426] cifs: fix missing null session check in mount Although it is unlikely to be have ended up with a null session pointer calling cifs_try_adding_channels in cifs_mount. Coverity correctly notes that we are already checking for it earlier (when we return from do_dfs_failover), so at a minimum to clarify the code we should make sure we also check for it when we exit the loop so we don't end up calling cifs_try_adding_channels or mount_setup_tlink with a null ses pointer. Addresses-Coverity: 1505608 ("Derefernce after null check") Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/connect.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index d49c9e5c33fa..a1e870232114 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3508,7 +3508,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) rc = -ELOOP; } while (rc == -EREMOTE); - if (rc || !tcon) + if (rc || !tcon || !ses) goto error; kfree(ref_path); From 16dd9b8c31aee7ae074fa3ee36a797e9ba9f7e4f Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Wed, 14 Jul 2021 23:00:00 -0500 Subject: [PATCH 397/426] cifs: added WARN_ON for all the count decrements We have a few ref counters srv_count, ses_count and tc_count which we use for ref counting. Added a WARN_ON during the decrement of each of these counters to make sure that they don't go below their minimum values. Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/cifs/connect.c | 9 +++++++++ fs/cifs/smb2ops.c | 2 ++ 2 files changed, 11 insertions(+) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a1e870232114..6b6c3e341b42 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1295,6 +1295,9 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) return; } + /* srv_count can never go negative */ + WARN_ON(server->srv_count < 0); + put_net(cifs_net_ns(server)); list_del_init(&server->tcp_ses_list); @@ -1654,6 +1657,9 @@ void cifs_put_smb_ses(struct cifs_ses *ses) } spin_unlock(&cifs_tcp_ses_lock); + /* ses_count can never go negative */ + WARN_ON(ses->ses_count < 0); + spin_lock(&GlobalMid_Lock); if (ses->status == CifsGood) ses->status = CifsExiting; @@ -2021,6 +2027,9 @@ cifs_put_tcon(struct cifs_tcon *tcon) return; } + /* tc_count can never go negative */ + WARN_ON(tcon->tc_count < 0); + if (tcon->use_witness) { int rc; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 232d528df230..ba3c58e1f725 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2910,6 +2910,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, /* ipc tcons are not refcounted */ spin_lock(&cifs_tcp_ses_lock); tcon->tc_count--; + /* tc_count can never go negative */ + WARN_ON(tcon->tc_count < 0); spin_unlock(&cifs_tcp_ses_lock); } kfree(utf16_path); From 4511d7c8f440ab13520601141d67d13cb074620a Mon Sep 17 00:00:00 2001 From: Steve French Date: Wed, 14 Jul 2021 23:32:09 -0500 Subject: [PATCH 398/426] SMB3.1.1: fix mount failure to some servers when compression enabled When sending the compression context to some servers, they rejected the SMB3.1.1 negotiate protocol because they expect the compression context to have a data length of a multiple of 8. Reviewed-by: Shyam Prasad N Signed-off-by: Steve French --- fs/cifs/smb2pdu.h | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 4b27cb9105fd..e9cac7970b66 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -394,6 +394,7 @@ struct smb2_compression_capabilities_context { __u16 Padding; __u32 Flags; __le16 CompressionAlgorithms[3]; + __u16 Pad; /* Some servers require pad to DataLen multiple of 8 */ /* Check if pad needed */ } __packed; From d936eb23874433caa3e3d841cfa16f5434b85dcf Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 15 Jul 2021 18:05:31 -0700 Subject: [PATCH 399/426] Revert "Makefile: Enable -Wimplicit-fallthrough for Clang" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit b7eb335e26a9c7f258c96b3962c283c379d3ede0. It turns out that the problem with the clang -Wimplicit-fallthrough warning is not about the kernel source code, but about clang itself, and that the warning is unusable until clang fixes its broken ways. In particular, when you enable this warning for clang, you not only get warnings about implicit fallthroughs. You also get this: warning: fallthrough annotation in unreachable code [-Wimplicit-fallthrough] which is completely broken becasue it (a) doesn't even tell you where the problem is (seriously: no line numbers, no filename, no nothing). (b) is fundamentally broken anyway, because there are perfectly valid reasons to have a fallthrough statement even if it turns out that it can perhaps not be reached. In the kernel, an example of that second case is code in the scheduler: switch (state) { case cpuset: if (IS_ENABLED(CONFIG_CPUSETS)) { cpuset_cpus_allowed_fallback(p); state = possible; break; } fallthrough; case possible: where if CONFIG_CPUSETS is enabled you actually never hit the fallthrough case at all. But that in no way makes the fallthrough wrong. So the warning is completely broken, and enabling it for clang is a very bad idea. In the meantime, we can keep the gcc option enabled, and make the gcc build use -Wimplicit-fallthrough=5 which means that we will at least continue to require a proper fallthrough statement, and that gcc won't silently accept the magic comment versions. Because gcc does this all correctly, and while the odd "=5" part is kind of obscure, it's documented in [1]: "-Wimplicit-fallthrough=5 doesn’t recognize any comments as fallthrough comments, only attributes disable the warning" so if clang ever fixes its bad behavior we can try enabling it there again. Link: https://gcc.gnu.org/onlinedocs/gcc/Warning-Options.html [1] Cc: Kees Cook Cc: Gustavo A. R. Silva Cc: Nathan Chancellor Cc: Nick Desaulniers Signed-off-by: Linus Torvalds --- Makefile | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/Makefile b/Makefile index eaa692976851..e97e7548315c 100644 --- a/Makefile +++ b/Makefile @@ -797,6 +797,12 @@ KBUILD_CFLAGS += -Wno-gnu # source of a reference will be _MergedGlobals and not on of the whitelisted names. # See modpost pattern 2 KBUILD_CFLAGS += -mno-global-merge +else + +# Warn about unmarked fall-throughs in switch statement. +# Disabled for clang while comment to attribute conversion happens and +# https://github.com/ClangBuiltLinux/linux/issues/636 is discussed. +KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=5,) endif # These warnings generated too much noise in a regular build. @@ -977,9 +983,6 @@ NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) # warn about C99 declaration after statement KBUILD_CFLAGS += -Wdeclaration-after-statement -# Warn about unmarked fall-throughs in switch statement. -KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=5,$(call cc-option,-Wimplicit-fallthrough,)) - # Variable Length Arrays (VLAs) should not be used anywhere in the kernel KBUILD_CFLAGS += -Wvla From 2f53d15cf95824ed320abed3c33759b8b21aca15 Mon Sep 17 00:00:00 2001 From: Xianting Tian Date: Wed, 30 Jun 2021 10:33:36 -0400 Subject: [PATCH 400/426] zonefs: remove redundant null bio check bio_alloc() with __GFP_DIRECT_RECLAIM, which is included in GFP_NOFS, never fails, see comments in bio_alloc_bioset(). Signed-off-by: Xianting Tian Signed-off-by: Damien Le Moal --- fs/zonefs/super.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index dbf03635869c..70055d486bf7 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -705,9 +705,6 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) return 0; bio = bio_alloc(GFP_NOFS, nr_pages); - if (!bio) - return -ENOMEM; - bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = zi->i_zsector; bio->bi_write_hint = iocb->ki_hint; From cdc3363065aba2711e51019b3d5787f044f8a133 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Thu, 15 Jul 2021 21:53:53 -0300 Subject: [PATCH 401/426] cifs: do not share tcp sessions of dfs connections Make sure that we do not share tcp sessions of dfs mounts when mounting regular shares that connect to same server. DFS connections rely on a single instance of tcp in order to do failover properly in cifs_reconnect(). Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/cifsglob.h | 3 +++ fs/cifs/connect.c | 38 +++++++++++++++++++++++++++++++++++--- 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index ade7080f7eaa..c0bfc2f01030 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -693,6 +693,9 @@ struct TCP_Server_Info { bool use_swn_dstaddr; struct sockaddr_storage swn_dstaddr; #endif +#ifdef CONFIG_CIFS_DFS_UPCALL + bool is_dfs_conn; /* if a dfs connection */ +#endif }; struct cifs_credits { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 6b6c3e341b42..1b04d6ec14dd 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1268,6 +1268,16 @@ cifs_find_tcp_session(struct smb3_fs_context *ctx) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { +#ifdef CONFIG_CIFS_DFS_UPCALL + /* + * DFS failover implementation in cifs_reconnect() requires unique tcp sessions for + * DFS connections to do failover properly, so avoid sharing them with regular + * shares or even links that may connect to same server but having completely + * different failover targets. + */ + if (server->is_dfs_conn) + continue; +#endif /* * Skip ses channels since they're only handled in lower layers * (e.g. cifs_send_recv). @@ -2968,6 +2978,23 @@ static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, } #ifdef CONFIG_CIFS_DFS_UPCALL +static int mount_get_dfs_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb, + unsigned int *xid, struct TCP_Server_Info **nserver, + struct cifs_ses **nses, struct cifs_tcon **ntcon) +{ + int rc; + + ctx->nosharesock = true; + rc = mount_get_conns(ctx, cifs_sb, xid, nserver, nses, ntcon); + if (*nserver) { + cifs_dbg(FYI, "%s: marking tcp session as a dfs connection\n", __func__); + spin_lock(&cifs_tcp_ses_lock); + (*nserver)->is_dfs_conn = true; + spin_unlock(&cifs_tcp_ses_lock); + } + return rc; +} + /* * cifs_build_path_to_root returns full path to root when we do not have an * existing connection (tcon) @@ -3163,7 +3190,7 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ tmp_ctx.prepath); mount_put_conns(cifs_sb, *xid, *server, *ses, *tcon); - rc = mount_get_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon); + rc = mount_get_dfs_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon); if (!rc || (*server && *ses)) { /* * We were able to connect to new target server. Update current context with @@ -3462,7 +3489,12 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) goto error; } - ctx->nosharesock = true; + mount_put_conns(cifs_sb, xid, server, ses, tcon); + /* + * Ignore error check here because we may failover to other targets from cached a + * referral. + */ + (void)mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); /* Get path of DFS root */ ref_path = build_unc_path_to_root(ctx, cifs_sb, false); @@ -3491,7 +3523,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) /* Connect to new DFS target only if we were redirected */ if (oldmnt != cifs_sb->ctx->mount_options) { mount_put_conns(cifs_sb, xid, server, ses, tcon); - rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); + rc = mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); } if (rc && !server && !ses) { /* Failed to connect. Try to connect to other targets in the referral. */ From 937654ce497fb6e977a8c52baee5f7d9616302d9 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:24 +0200 Subject: [PATCH 402/426] perf test bpf: Free obj_buf ASan reports some memory leaks when running: # perf test "42: BPF filter" The first of these leaks is caused by obj_buf never being deallocated in __test__bpf. This patch adds the missing free. Signed-off-by: Riccardo Mancini Fixes: ba1fae431e74bb42 ("perf test: Add 'perf test BPF'") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lore.kernel.org/lkml/60f3ca935fe6672e7e866276ce6264c9e26e4c87.1626343282.git.rickyman7@gmail.com [ Added missing stdlib.h include ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/bpf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 33bda9c26542..dbf5f5215abe 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include @@ -276,6 +277,7 @@ static int __test__bpf(int idx) } out: + free(obj_buf); bpf__clear(); return ret; } From 50d8d7e19c4398da74d028f367754e73547b078b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 14 Jul 2021 12:19:36 +0200 Subject: [PATCH 403/426] dt-bindings: display: renesas,du: Make resets optional on R-Car H1 The "resets" property is not present on R-Car Gen1 SoCs. Supporting it would require migrating from renesas,cpg-clocks to renesas,cpg-mssr. Reflect this in the DT bindings by removing the global "required: resets". All SoCs that do have "resets" properties already have SoC-specific rules making it required. Fixes: 99d66127fad25ebb ("dt-bindings: display: renesas,du: Convert binding to YAML") Signed-off-by: Geert Uytterhoeven Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/98575791b154d80347d5b78132c1d53f5315ee62.1626257936.git.geert+renesas@glider.be Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/display/renesas,du.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/devicetree/bindings/display/renesas,du.yaml b/Documentation/devicetree/bindings/display/renesas,du.yaml index 5f4345d43020..e3ca5389c17d 100644 --- a/Documentation/devicetree/bindings/display/renesas,du.yaml +++ b/Documentation/devicetree/bindings/display/renesas,du.yaml @@ -92,7 +92,6 @@ required: - reg - clocks - interrupts - - resets - ports allOf: From 5f291bfd33c8995c69f5a50f21445a4a93584ed2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 14 Jul 2021 11:33:43 +0200 Subject: [PATCH 404/426] arm: Typo s/PCI_IXP4XX_LEGACY/IXP4XX_PCI_LEGACY/ Kconfig symbol PCI_IXP4XX_LEGACY does not exist, but IXP4XX_PCI_LEGACY does. Fixes: d5d9f7ac58ea1041 ("ARM/ixp4xx: Make NEED_MACH_IO_H optional") Signed-off-by: Geert Uytterhoeven Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/82ce37c617293521f095a945a255456b9512769c.1626255077.git.geert+renesas@glider.be' Signed-off-by: Arnd Bergmann --- arch/arm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3ea1c417339f..82f908fa5676 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -395,7 +395,7 @@ config ARCH_IXP4XX select IXP4XX_IRQ select IXP4XX_TIMER # With the new PCI driver this is not needed - select NEED_MACH_IO_H if PCI_IXP4XX_LEGACY + select NEED_MACH_IO_H if IXP4XX_PCI_LEGACY select USB_EHCI_BIG_ENDIAN_DESC select USB_EHCI_BIG_ENDIAN_MMIO help From 2096d6feec8359203de406c424242dcb977fe1d1 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 14 Jul 2021 14:27:03 +0200 Subject: [PATCH 405/426] ARM: configs: Update Integrator defconfig This updates the Integrator defconfig for the changes in the v5.14-rc1 kernel: - The Framebuffer CONFIG_FB needs to be explicitly selected or we don't get any framebuffer anymore. DRM has stopped to select FB because of circular dependency. - Drop the unused Matrox FB drivers that are only used with specific PCI cards. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Reviewed-by: Kees Cook Cc: Kees Cook Link: https://lore.kernel.org/r/20210714122703.212609-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/integrator_defconfig | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig index b06e537d5149..4dfe321a79f6 100644 --- a/arch/arm/configs/integrator_defconfig +++ b/arch/arm/configs/integrator_defconfig @@ -57,10 +57,7 @@ CONFIG_DRM=y CONFIG_DRM_DISPLAY_CONNECTOR=y CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_PL111=y -CONFIG_FB_MODE_HELPERS=y -CONFIG_FB_MATROX=y -CONFIG_FB_MATROX_MILLENIUM=y -CONFIG_FB_MATROX_MYSTIQUE=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y # CONFIG_VGA_CONSOLE is not set CONFIG_LOGO=y From 56fa6e8a184489b47525488472e9bdcdcb59cd6f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 14 Jul 2021 11:00:40 +0200 Subject: [PATCH 406/426] ARM: configs: Update RealView defconfig This updates the RealView defconfig for the changes in the v5.14-rc1 kernel: - The Framebuffer CONFIG_FB needs to be explicitly selected or we don't get any framebuffer anymore. DRM has stopped to select FB because of circular dependency. - The CONFIG_FB_MODE_HELPERS are not needed when using DRM framebuffer emulation as DRM does. - Drop two unused penguin logos. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Reviewed-by: Kees Cook Cc: Kees Cook Link: https://lore.kernel.org/r/20210714090040.182381-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/realview_defconfig | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/configs/realview_defconfig b/arch/arm/configs/realview_defconfig index 483c400dd391..4c01e313099f 100644 --- a/arch/arm/configs/realview_defconfig +++ b/arch/arm/configs/realview_defconfig @@ -64,11 +64,9 @@ CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_DISPLAY_CONNECTOR=y CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_PL111=y -CONFIG_FB_MODE_HELPERS=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set CONFIG_SOUND=y CONFIG_SND=y # CONFIG_SND_DRIVERS is not set From 850d8ec92735b3d58b81363c4ae29932a2ebbabb Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 14 Jul 2021 10:18:19 +0200 Subject: [PATCH 407/426] ARM: configs: Update Versatile defconfig This updates the Versatile defconfig for the changes in the v5.14-rc1 kernel: - The Framebuffer CONFIG_FB needs to be explicitly selected or we don't get any framebuffer anymore. DRM has stopped to select FB because of circular dependency. - The CONFIG_FB_MODE_HELPERS are not needed when using DRM framebuffer emulation as DRM does. - The Acorn fonts are removed, the default framebuffer font works fine. I don't know why this was selected in the first place or how the Kconfig was altered so it was removed. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Reviewed-by: Kees Cook Cc: Kees Cook Link: https://lore.kernel.org/r/20210714081819.139210-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/versatile_defconfig | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/configs/versatile_defconfig b/arch/arm/configs/versatile_defconfig index e7ecfb365e91..b703f4757021 100644 --- a/arch/arm/configs/versatile_defconfig +++ b/arch/arm/configs/versatile_defconfig @@ -60,7 +60,7 @@ CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_DISPLAY_CONNECTOR=y CONFIG_DRM_SIMPLE_BRIDGE=y CONFIG_DRM_PL111=y -CONFIG_FB_MODE_HELPERS=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_LOGO=y CONFIG_SOUND=y @@ -88,8 +88,6 @@ CONFIG_NFSD=y CONFIG_NFSD_V3=y CONFIG_NLS_CODEPAGE_850=m CONFIG_NLS_ISO8859_1=m -CONFIG_FONTS=y -CONFIG_FONT_ACORN_8x8=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y From 49e7757a73d181b35851cb01b5d285888014f8b2 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 13 Jul 2021 15:37:08 +0200 Subject: [PATCH 408/426] ARM: configs: Update Vexpress defconfig This updates the Versatile Express defconfig for the changes in the v5.14-rc1 kernel: - The Framebuffer CONFIG_FB needs to be explicitly selected or we don't get any framebuffer anymore. DRM has stopped to select FB because of circular dependency. - CONFIG_CMA options were moved around. - CONFIG_MODULES options were moved around. - CONFIG_CRYPTO_HW was moved around. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Acked-by: Sudeep Holla Cc: Kees Cook Cc: Sudeep Holla Link: https://lore.kernel.org/r/20210713133708.94397-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/vexpress_defconfig | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/arch/arm/configs/vexpress_defconfig b/arch/arm/configs/vexpress_defconfig index 4479369540f2..b5e246dd23f4 100644 --- a/arch/arm/configs/vexpress_defconfig +++ b/arch/arm/configs/vexpress_defconfig @@ -11,9 +11,6 @@ CONFIG_CPUSETS=y # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_PROFILING=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set CONFIG_ARCH_VEXPRESS=y CONFIG_ARCH_VEXPRESS_DCSCB=y CONFIG_ARCH_VEXPRESS_TC2_PM=y @@ -23,14 +20,17 @@ CONFIG_MCPM=y CONFIG_VMSPLIT_2G=y CONFIG_NR_CPUS=8 CONFIG_ARM_PSCI=y -CONFIG_CMA=y CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_CMDLINE="console=ttyAMA0" CONFIG_CPU_IDLE=y CONFIG_VFP=y CONFIG_NEON=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_CMA=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -43,7 +43,6 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_NET_9P=y CONFIG_NET_9P_VIRTIO=y CONFIG_DEVTMPFS=y -CONFIG_DMA_CMA=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y @@ -59,7 +58,6 @@ CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_SD=y CONFIG_SCSI_VIRTIO=y CONFIG_ATA=y -# CONFIG_SATA_PMP is not set CONFIG_NETDEVICES=y CONFIG_VIRTIO_NET=y CONFIG_SMC91X=y @@ -81,11 +79,9 @@ CONFIG_DRM=y CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_SII902X=y CONFIG_DRM_PL111=y -CONFIG_FB_MODE_HELPERS=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set CONFIG_SOUND=y CONFIG_SND=y # CONFIG_SND_DRIVERS is not set @@ -136,10 +132,11 @@ CONFIG_ROOT_NFS=y CONFIG_9P_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y +# CONFIG_CRYPTO_HW is not set +CONFIG_DMA_CMA=y CONFIG_DEBUG_INFO=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_SCHED_DEBUG is not set CONFIG_DEBUG_USER=y -# CONFIG_CRYPTO_HW is not set From 042f2e107a2ea34605b3793a88b11761afc8e8e0 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 12 Jul 2021 10:55:22 +0200 Subject: [PATCH 409/426] ARM: configs: Update u8500_defconfig The platform lost the framebuffer due to a commit solving a circular dependency in v5.14-rc1, so add it back in by explicitly selecting the framebuffer. The U8500 has also gained a few systems using touchscreens from Cypress, Melfas and Zinitix so add these at the same time as we're updating the defconfig anyway. Fixes: f611b1e7624c ("drm: Avoid circular dependencies for CONFIG_FB") Signed-off-by: Linus Walleij Cc: phone-devel@vger.kernel.org Cc: Kees Cook Cc: Arnd Bergmann Cc: Stephan Gerhold Cc: newbyte@disroot.org Link: https://lore.kernel.org/r/20210712085522.672482-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann --- arch/arm/configs/u8500_defconfig | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index dbb1ef601762..3b30913d7d8d 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -61,6 +61,10 @@ CONFIG_INPUT_TOUCHSCREEN=y CONFIG_TOUCHSCREEN_ATMEL_MXT=y CONFIG_TOUCHSCREEN_BU21013=y CONFIG_TOUCHSCREEN_CY8CTMA140=y +CONFIG_TOUCHSCREEN_CYTTSP_CORE=y +CONFIG_TOUCHSCREEN_CYTTSP_SPI=y +CONFIG_TOUCHSCREEN_MMS114=y +CONFIG_TOUCHSCREEN_ZINITIX=y CONFIG_INPUT_MISC=y CONFIG_INPUT_AB8500_PONKEY=y CONFIG_INPUT_GPIO_VIBRA=y @@ -100,6 +104,7 @@ CONFIG_DRM_PANEL_SAMSUNG_S6E63M0_DSI=y CONFIG_DRM_PANEL_SONY_ACX424AKP=y CONFIG_DRM_LIMA=y CONFIG_DRM_MCDE=y +CONFIG_FB=y CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_BACKLIGHT_KTD253=y CONFIG_BACKLIGHT_GPIO=y From ab37a7a890c1176144a4c66ff3d51ef2c20ed486 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sat, 10 Jul 2021 13:04:55 +0200 Subject: [PATCH 410/426] ARM: multi_v7_defconfig: Make NOP_USB_XCEIV driver built-in The usage of usb-nop-xceiv PHY on Raspberry Pi boards with BCM283x has been a "regression source" a lot of times. The last case is breakage of USB mass storage boot has been commit e590474768f1 ("driver core: Set fw_devlink=on by default") for multi_v7_defconfig. As long as NOP_USB_XCEIV is configured as module, the dwc2 USB driver defer probing endlessly and prevent booting from USB mass storage device. So make the driver built-in as in bcm2835_defconfig and arm64/defconfig. Fixes: e590474768f1 ("driver core: Set fw_devlink=on by default") Reported-by: Ojaswin Mujoo Signed-off-by: Stefan Wahren Link: https://lore.kernel.org/r/1625915095-23077-1-git-send-email-stefan.wahren@i2se.com' Signed-off-by: Arnd Bergmann --- arch/arm/configs/multi_v7_defconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 52a0400fdd92..d9abaae118dd 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -821,7 +821,7 @@ CONFIG_USB_ISP1760=y CONFIG_USB_HSIC_USB3503=y CONFIG_AB8500_USB=y CONFIG_KEYSTONE_USB_PHY=m -CONFIG_NOP_USB_XCEIV=m +CONFIG_NOP_USB_XCEIV=y CONFIG_AM335X_PHY_USB=m CONFIG_TWL6030_USB=m CONFIG_USB_GPIO_VBUS=y From 82a1c67554dff610d6be4e1982c425717b3c6a23 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 1 Jul 2021 14:21:18 +0100 Subject: [PATCH 411/426] ARM: dts: versatile: Fix up interrupt controller node names Once the new schema interrupt-controller/arm,vic.yaml is added, we get the below warnings: arch/arm/boot/dts/versatile-ab.dt.yaml: intc@10140000: $nodename:0: 'intc@10140000' does not match '^interrupt-controller(@[0-9a-f,]+)*$' arch/arm/boot/dts/versatile-ab.dt.yaml: intc@10140000: 'clear-mask' does not match any of the regexes Fix the node names for the interrupt controller to conform to the standard node name interrupt-controller@.. Also drop invalid clear-mask property. Signed-off-by: Sudeep Holla Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20210701132118.759454-1-sudeep.holla@arm.com' Signed-off-by: Arnd Bergmann --- arch/arm/boot/dts/versatile-ab.dts | 5 ++--- arch/arm/boot/dts/versatile-pb.dts | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts index 37bd41ff8dff..151c0220047d 100644 --- a/arch/arm/boot/dts/versatile-ab.dts +++ b/arch/arm/boot/dts/versatile-ab.dts @@ -195,16 +195,15 @@ #size-cells = <1>; ranges; - vic: intc@10140000 { + vic: interrupt-controller@10140000 { compatible = "arm,versatile-vic"; interrupt-controller; #interrupt-cells = <1>; reg = <0x10140000 0x1000>; - clear-mask = <0xffffffff>; valid-mask = <0xffffffff>; }; - sic: intc@10003000 { + sic: interrupt-controller@10003000 { compatible = "arm,versatile-sic"; interrupt-controller; #interrupt-cells = <1>; diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index 06a0fdf24026..e7e751a858d8 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -7,7 +7,7 @@ amba { /* The Versatile PB is using more SIC IRQ lines than the AB */ - sic: intc@10003000 { + sic: interrupt-controller@10003000 { clear-mask = <0xffffffff>; /* * Valid interrupt lines mask according to From ae14c63a9f20d49dacfb6f3fa3fb11b3b4eb11bf Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 17 Jul 2021 13:27:00 -0700 Subject: [PATCH 412/426] Revert "mm/slub: use stackdepot to save stack trace in objects" This reverts commit 788691464c29455346dc613a3b43c2fb9e5757a4. It's not clear why, but it causes unexplained problems in entirely unrelated xfs code. The most likely explanation is some slab corruption, possibly triggered due to CONFIG_SLUB_DEBUG_ON. See [1]. It ends up having a few other problems too, like build errors on arch/arc, and Geert reporting it using much more memory on m68k [3] (it probably does so elsewhere too, but it is probably just more noticeable on m68k). The architecture issues (both build and memory use) are likely just because this change effectively force-enabled STACKDEPOT (along with a very bad default value for the stackdepot hash size). But together with the xfs issue, this all smells like "this commit was not ready" to me. Link: https://lore.kernel.org/linux-xfs/YPE3l82acwgI2OiV@infradead.org/ [1] Link: https://lore.kernel.org/lkml/202107150600.LkGNb4Vb-lkp@intel.com/ [2] Link: https://lore.kernel.org/lkml/CAMuHMdW=eoVzM1Re5FVoEN87nKfiLmM2+Ah7eNu2KXEhCvbZyA@mail.gmail.com/ [3] Reported-by: Christoph Hellwig Reported-by: kernel test robot Reported-by: Geert Uytterhoeven Cc: Andrew Morton Cc: Vlastimil Babka Cc: Randy Dunlap Signed-off-by: Linus Torvalds --- init/Kconfig | 1 - mm/slub.c | 79 ++++++++++++++++++++-------------------------------- 2 files changed, 30 insertions(+), 50 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index bb0d6e6262b1..55f9f7738ebb 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1847,7 +1847,6 @@ config SLUB_DEBUG default y bool "Enable SLUB debugging support" if EXPERT depends on SLUB && SYSFS - select STACKDEPOT if STACKTRACE_SUPPORT help SLUB has extensive debug support features. Disabling these can result in significant savings in code size. This also disables diff --git a/mm/slub.c b/mm/slub.c index e1644ac6ee7b..090fa14628f9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include @@ -207,8 +206,8 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s) #define TRACK_ADDRS_COUNT 16 struct track { unsigned long addr; /* Called from address */ -#ifdef CONFIG_STACKDEPOT - depot_stack_handle_t handle; +#ifdef CONFIG_STACKTRACE + unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */ #endif int cpu; /* Was running on cpu */ int pid; /* Pid context */ @@ -612,27 +611,22 @@ static struct track *get_track(struct kmem_cache *s, void *object, return kasan_reset_tag(p + alloc); } -#ifdef CONFIG_STACKDEPOT -static depot_stack_handle_t save_stack_depot_trace(gfp_t flags) -{ - unsigned long entries[TRACK_ADDRS_COUNT]; - depot_stack_handle_t handle; - unsigned int nr_entries; - - nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 4); - handle = stack_depot_save(entries, nr_entries, flags); - return handle; -} -#endif - static void set_track(struct kmem_cache *s, void *object, enum track_item alloc, unsigned long addr) { struct track *p = get_track(s, object, alloc); if (addr) { -#ifdef CONFIG_STACKDEPOT - p->handle = save_stack_depot_trace(GFP_NOWAIT); +#ifdef CONFIG_STACKTRACE + unsigned int nr_entries; + + metadata_access_enable(); + nr_entries = stack_trace_save(kasan_reset_tag(p->addrs), + TRACK_ADDRS_COUNT, 3); + metadata_access_disable(); + + if (nr_entries < TRACK_ADDRS_COUNT) + p->addrs[nr_entries] = 0; #endif p->addr = addr; p->cpu = smp_processor_id(); @@ -659,19 +653,14 @@ static void print_track(const char *s, struct track *t, unsigned long pr_time) pr_err("%s in %pS age=%lu cpu=%u pid=%d\n", s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid); -#ifdef CONFIG_STACKDEPOT +#ifdef CONFIG_STACKTRACE { - depot_stack_handle_t handle; - unsigned long *entries; - unsigned int nr_entries; - - handle = READ_ONCE(t->handle); - if (!handle) { - pr_err("object allocation/free stack trace missing\n"); - } else { - nr_entries = stack_depot_fetch(handle, &entries); - stack_trace_print(entries, nr_entries, 0); - } + int i; + for (i = 0; i < TRACK_ADDRS_COUNT; i++) + if (t->addrs[i]) + pr_err("\t%pS\n", (void *)t->addrs[i]); + else + break; } #endif } @@ -4045,26 +4034,18 @@ void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) objp = fixup_red_left(s, objp); trackp = get_track(s, objp, TRACK_ALLOC); kpp->kp_ret = (void *)trackp->addr; -#ifdef CONFIG_STACKDEPOT - { - depot_stack_handle_t handle; - unsigned long *entries; - unsigned int nr_entries; +#ifdef CONFIG_STACKTRACE + for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) { + kpp->kp_stack[i] = (void *)trackp->addrs[i]; + if (!kpp->kp_stack[i]) + break; + } - handle = READ_ONCE(trackp->handle); - if (handle) { - nr_entries = stack_depot_fetch(handle, &entries); - for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++) - kpp->kp_stack[i] = (void *)entries[i]; - } - - trackp = get_track(s, objp, TRACK_FREE); - handle = READ_ONCE(trackp->handle); - if (handle) { - nr_entries = stack_depot_fetch(handle, &entries); - for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++) - kpp->kp_free_stack[i] = (void *)entries[i]; - } + trackp = get_track(s, objp, TRACK_FREE); + for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) { + kpp->kp_free_stack[i] = (void *)trackp->addrs[i]; + if (!kpp->kp_free_stack[i]) + break; } #endif #endif From e0fa7ab42232e742dcb3de9f3c1f6127b5adc019 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Thu, 15 Jul 2021 18:07:25 +0200 Subject: [PATCH 413/426] perf probe-file: Delete namelist in del_events() on the error path ASan reports some memory leaks when running: # perf test "42: BPF filter" This second leak is caused by a strlist not being dellocated on error inside probe_file__del_events. This patch adds a goto label before the deallocation and makes the error path jump to it. Signed-off-by: Riccardo Mancini Fixes: e7895e422e4da63d ("perf probe: Split del_perf_probe_events()") Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/174963c587ae77fa108af794669998e4ae558338.1626343282.git.rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index f9a6cbcd6415..3d50de3217d5 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -377,11 +377,11 @@ int probe_file__del_events(int fd, struct strfilter *filter) ret = probe_file__get_events(fd, filter, namelist); if (ret < 0) - return ret; + goto out; ret = probe_file__del_strlist(fd, namelist); +out: strlist__delete(namelist); - return ret; } From d4b3eedce151e63932ce4a00f1d0baa340a8b907 Mon Sep 17 00:00:00 2001 From: Riccardo Mancini Date: Fri, 16 Jul 2021 16:11:20 +0200 Subject: [PATCH 414/426] perf data: Close all files in close_dir() When using 'perf report' in directory mode, the first file is not closed on exit, causing a memory leak. The problem is caused by the iterating variable never reaching 0. Fixes: 145520631130bd64 ("perf data: Add perf_data__(create_dir|close_dir) functions") Signed-off-by: Riccardo Mancini Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: Zhen Lei Link: http://lore.kernel.org/lkml/20210716141122.858082-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index a9c102e8e3c0..f5d260b1df4d 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -20,7 +20,7 @@ static void close_dir(struct perf_data_file *files, int nr) { - while (--nr >= 1) { + while (--nr >= 0) { close(files[nr].fd); zfree(&files[nr].path); } From 22a665513b34df458da1d3b7ee0b919c3f3d4653 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Thu, 15 Jul 2021 14:37:23 +0800 Subject: [PATCH 415/426] perf probe: Fix add event failure when running 32-bit perf in a 64-bit kernel The "address" member of "struct probe_trace_point" uses long data type. If kernel is 64-bit and perf program is 32-bit, size of "address" variable is 32 bits. As a result, upper 32 bits of address read from kernel are truncated, an error occurs during address comparison in kprobe_warn_out_range(). Before: # perf probe -a schedule schedule is out of .text, skip it. Error: Failed to add events. Solution: Change data type of "address" variable to u64 and change corresponding address printing and value assignment. After: # perf.new.new probe -a schedule Added new event: probe:schedule (on schedule) You can now use it in all perf tools, such as: perf record -e probe:schedule -aR sleep 1 # perf probe -l probe:schedule (on schedule@kernel/sched/core.c) # perf record -e probe:schedule -aR sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.156 MB perf.data (1366 samples) ] # perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 1K of event 'probe:schedule' # Event count (approx.): 1366 # # Overhead Command Shared Object Symbol # ........ ............... ................. ............ # 6.22% migration/0 [kernel.kallsyms] [k] schedule 6.22% migration/1 [kernel.kallsyms] [k] schedule 6.22% migration/2 [kernel.kallsyms] [k] schedule 6.22% migration/3 [kernel.kallsyms] [k] schedule 6.15% migration/10 [kernel.kallsyms] [k] schedule 6.15% migration/11 [kernel.kallsyms] [k] schedule 6.15% migration/12 [kernel.kallsyms] [k] schedule 6.15% migration/13 [kernel.kallsyms] [k] schedule 6.15% migration/14 [kernel.kallsyms] [k] schedule 6.15% migration/15 [kernel.kallsyms] [k] schedule 6.15% migration/4 [kernel.kallsyms] [k] schedule 6.15% migration/5 [kernel.kallsyms] [k] schedule 6.15% migration/6 [kernel.kallsyms] [k] schedule 6.15% migration/7 [kernel.kallsyms] [k] schedule 6.15% migration/8 [kernel.kallsyms] [k] schedule 6.15% migration/9 [kernel.kallsyms] [k] schedule 0.22% rcu_sched [kernel.kallsyms] [k] schedule ... # # (Cannot load tips.txt file, please install perf!) # Signed-off-by: Yang Jihong Acked-by: Masami Hiramatsu Cc: Alexander Shishkin Cc: Frank Ch. Eigler Cc: Ian Rogers Cc: Jianlin Lv Cc: Jin Yao Cc: Jiri Olsa Cc: Li Huafei Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Srikar Dronamraju Link: http://lore.kernel.org/lkml/20210715063723.11926-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dwarf-aux.c | 8 +++--- tools/perf/util/dwarf-aux.h | 2 +- tools/perf/util/probe-event.c | 49 ++++++++++++++++------------------ tools/perf/util/probe-event.h | 4 +-- tools/perf/util/probe-finder.c | 15 +++++------ tools/perf/util/probe-finder.h | 2 +- 6 files changed, 38 insertions(+), 42 deletions(-) diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 7d2ba8419b0c..609ca1671501 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -113,14 +113,14 @@ static Dwarf_Line *cu_getsrc_die(Dwarf_Die *cu_die, Dwarf_Addr addr) * * Find a line number and file name for @addr in @cu_die. */ -int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, - const char **fname, int *lineno) +int cu_find_lineinfo(Dwarf_Die *cu_die, Dwarf_Addr addr, + const char **fname, int *lineno) { Dwarf_Line *line; Dwarf_Die die_mem; Dwarf_Addr faddr; - if (die_find_realfunc(cu_die, (Dwarf_Addr)addr, &die_mem) + if (die_find_realfunc(cu_die, addr, &die_mem) && die_entrypc(&die_mem, &faddr) == 0 && faddr == addr) { *fname = dwarf_decl_file(&die_mem); @@ -128,7 +128,7 @@ int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, goto out; } - line = cu_getsrc_die(cu_die, (Dwarf_Addr)addr); + line = cu_getsrc_die(cu_die, addr); if (line && dwarf_lineno(line, lineno) == 0) { *fname = dwarf_linesrc(line, NULL, NULL); if (!*fname) diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index cb99646843a9..7ee0fa19b5c4 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -19,7 +19,7 @@ const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname); const char *cu_get_comp_dir(Dwarf_Die *cu_die); /* Get a line number and file name for given address */ -int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, +int cu_find_lineinfo(Dwarf_Die *cudie, Dwarf_Addr addr, const char **fname, int *lineno); /* Walk on functions at given address */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index e05750cea34c..b2a02c9ab8ea 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -239,8 +239,8 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) clear_probe_trace_event(tevs + i); } -static bool kprobe_blacklist__listed(unsigned long address); -static bool kprobe_warn_out_range(const char *symbol, unsigned long address) +static bool kprobe_blacklist__listed(u64 address); +static bool kprobe_warn_out_range(const char *symbol, u64 address) { struct map *map; bool ret = false; @@ -400,8 +400,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, pr_debug("Symbol %s address found : %" PRIx64 "\n", pp->function, address); - ret = debuginfo__find_probe_point(dinfo, (unsigned long)address, - result); + ret = debuginfo__find_probe_point(dinfo, address, result); if (ret <= 0) ret = (!ret) ? -ENOENT : ret; else { @@ -589,7 +588,7 @@ static void debuginfo_cache__exit(void) } -static int get_text_start_address(const char *exec, unsigned long *address, +static int get_text_start_address(const char *exec, u64 *address, struct nsinfo *nsi) { Elf *elf; @@ -634,7 +633,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, bool is_kprobe) { struct debuginfo *dinfo = NULL; - unsigned long stext = 0; + u64 stext = 0; u64 addr = tp->address; int ret = -ENOENT; @@ -662,8 +661,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, dinfo = debuginfo_cache__open(tp->module, verbose <= 0); if (dinfo) - ret = debuginfo__find_probe_point(dinfo, - (unsigned long)addr, pp); + ret = debuginfo__find_probe_point(dinfo, addr, pp); else ret = -ENOENT; @@ -678,7 +676,7 @@ error: /* Adjust symbol name and address */ static int post_process_probe_trace_point(struct probe_trace_point *tp, - struct map *map, unsigned long offs) + struct map *map, u64 offs) { struct symbol *sym; u64 addr = tp->address - offs; @@ -721,7 +719,7 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs, int ntevs, const char *pathname) { struct map *map; - unsigned long stext = 0; + u64 stext = 0; int i, ret = 0; /* Prepare a map for offline binary */ @@ -747,7 +745,7 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, struct nsinfo *nsi) { int i, ret = 0; - unsigned long stext = 0; + u64 stext = 0; if (!exec) return 0; @@ -792,7 +790,7 @@ post_process_module_probe_trace_events(struct probe_trace_event *tevs, mod_name = find_module_name(module); for (i = 0; i < ntevs; i++) { ret = post_process_probe_trace_point(&tevs[i].point, - map, (unsigned long)text_offs); + map, text_offs); if (ret < 0) break; tevs[i].point.module = @@ -1536,7 +1534,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) * so tmp[1] should always valid (but could be '\0'). */ if (tmp && !strncmp(tmp, "0x", 2)) { - pp->abs_address = strtoul(pp->function, &tmp, 0); + pp->abs_address = strtoull(pp->function, &tmp, 0); if (*tmp != '\0') { semantic_error("Invalid absolute address.\n"); return -EINVAL; @@ -1911,7 +1909,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev) argv[i] = NULL; argc -= 1; } else - tp->address = strtoul(fmt1_str, NULL, 0); + tp->address = strtoull(fmt1_str, NULL, 0); } else { /* Only the symbol-based probe has offset */ tp->symbol = strdup(fmt1_str); @@ -2157,7 +2155,7 @@ synthesize_uprobe_trace_def(struct probe_trace_point *tp, struct strbuf *buf) return -EINVAL; /* Use the tp->address for uprobes */ - err = strbuf_addf(buf, "%s:0x%lx", tp->module, tp->address); + err = strbuf_addf(buf, "%s:0x%" PRIx64, tp->module, tp->address); if (err >= 0 && tp->ref_ctr_offset) { if (!uprobe_ref_ctr_is_supported()) @@ -2172,7 +2170,7 @@ synthesize_kprobe_trace_def(struct probe_trace_point *tp, struct strbuf *buf) { if (!strncmp(tp->symbol, "0x", 2)) { /* Absolute address. See try_to_find_absolute_address() */ - return strbuf_addf(buf, "%s%s0x%lx", tp->module ?: "", + return strbuf_addf(buf, "%s%s0x%" PRIx64, tp->module ?: "", tp->module ? ":" : "", tp->address); } else { return strbuf_addf(buf, "%s%s%s+%lu", tp->module ?: "", @@ -2271,7 +2269,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp, pp->function = strdup(tp->symbol); pp->offset = tp->offset; } else { - ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address); + ret = e_snprintf(buf, 128, "0x%" PRIx64, tp->address); if (ret < 0) return ret; pp->function = strdup(buf); @@ -2452,8 +2450,8 @@ void clear_probe_trace_event(struct probe_trace_event *tev) struct kprobe_blacklist_node { struct list_head list; - unsigned long start; - unsigned long end; + u64 start; + u64 end; char *symbol; }; @@ -2498,7 +2496,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist) } INIT_LIST_HEAD(&node->list); list_add_tail(&node->list, blacklist); - if (sscanf(buf, "0x%lx-0x%lx", &node->start, &node->end) != 2) { + if (sscanf(buf, "0x%" PRIx64 "-0x%" PRIx64, &node->start, &node->end) != 2) { ret = -EINVAL; break; } @@ -2514,7 +2512,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist) ret = -ENOMEM; break; } - pr_debug2("Blacklist: 0x%lx-0x%lx, %s\n", + pr_debug2("Blacklist: 0x%" PRIx64 "-0x%" PRIx64 ", %s\n", node->start, node->end, node->symbol); ret++; } @@ -2526,8 +2524,7 @@ static int kprobe_blacklist__load(struct list_head *blacklist) } static struct kprobe_blacklist_node * -kprobe_blacklist__find_by_address(struct list_head *blacklist, - unsigned long address) +kprobe_blacklist__find_by_address(struct list_head *blacklist, u64 address) { struct kprobe_blacklist_node *node; @@ -2555,7 +2552,7 @@ static void kprobe_blacklist__release(void) kprobe_blacklist__delete(&kprobe_blacklist); } -static bool kprobe_blacklist__listed(unsigned long address) +static bool kprobe_blacklist__listed(u64 address) { return !!kprobe_blacklist__find_by_address(&kprobe_blacklist, address); } @@ -3223,7 +3220,7 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, * In __add_probe_trace_events, a NULL symbol is interpreted as * invalid. */ - if (asprintf(&tp->symbol, "0x%lx", tp->address) < 0) + if (asprintf(&tp->symbol, "0x%" PRIx64, tp->address) < 0) goto errout; /* For kprobe, check range */ @@ -3234,7 +3231,7 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, goto errout; } - if (asprintf(&tp->realname, "abs_%lx", tp->address) < 0) + if (asprintf(&tp->realname, "abs_%" PRIx64, tp->address) < 0) goto errout; if (pev->target) { diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 65769d7949a3..8ad5b1579f1d 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -33,7 +33,7 @@ struct probe_trace_point { char *module; /* Module name */ unsigned long offset; /* Offset from symbol */ unsigned long ref_ctr_offset; /* SDT reference counter offset */ - unsigned long address; /* Actual address of the trace point */ + u64 address; /* Actual address of the trace point */ bool retprobe; /* Return probe flag */ }; @@ -70,7 +70,7 @@ struct perf_probe_point { bool retprobe; /* Return probe flag */ char *lazy_line; /* Lazy matching pattern */ unsigned long offset; /* Offset from function entry */ - unsigned long abs_address; /* Absolute address of the point */ + u64 abs_address; /* Absolute address of the point */ }; /* Perf probe probing argument field chain */ diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 02ef0d78053b..50d861a80f57 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -668,7 +668,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, } tp->offset = (unsigned long)(paddr - eaddr); - tp->address = (unsigned long)paddr; + tp->address = paddr; tp->symbol = strdup(symbol); if (!tp->symbol) return -ENOMEM; @@ -1707,7 +1707,7 @@ int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, } /* Reverse search */ -int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, +int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr, struct perf_probe_point *ppt) { Dwarf_Die cudie, spdie, indie; @@ -1720,14 +1720,14 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, addr += baseaddr; /* Find cu die */ if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) { - pr_warning("Failed to find debug information for address %lx\n", + pr_warning("Failed to find debug information for address %" PRIx64 "\n", addr); ret = -EINVAL; goto end; } /* Find a corresponding line (filename and lineno) */ - cu_find_lineinfo(&cudie, addr, &fname, &lineno); + cu_find_lineinfo(&cudie, (Dwarf_Addr)addr, &fname, &lineno); /* Don't care whether it failed or not */ /* Find a corresponding function (name, baseline and baseaddr) */ @@ -1742,7 +1742,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, } fname = dwarf_decl_file(&spdie); - if (addr == (unsigned long)baseaddr) { + if (addr == baseaddr) { /* Function entry - Relative line number is 0 */ lineno = baseline; goto post; @@ -1788,7 +1788,7 @@ post: if (lineno) ppt->line = lineno - baseline; else if (basefunc) { - ppt->offset = addr - (unsigned long)baseaddr; + ppt->offset = addr - baseaddr; func = basefunc; } @@ -1828,8 +1828,7 @@ static int line_range_add_line(const char *src, unsigned int lineno, } static int line_range_walk_cb(const char *fname, int lineno, - Dwarf_Addr addr __maybe_unused, - void *data) + Dwarf_Addr addr, void *data) { struct line_finder *lf = data; const char *__fname; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 2febb5875678..8bc1c80d3c1c 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -46,7 +46,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, struct probe_trace_event **tevs); /* Find a perf_probe_point from debuginfo */ -int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, +int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr, struct perf_probe_point *ppt); int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, From b0f008551f0bf4d5f6db9b5f0e071b02790d6a2e Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 13 Jul 2021 19:23:58 +0800 Subject: [PATCH 416/426] perf sched: Fix record failure when CONFIG_SCHEDSTATS is not set The tracepoints trace_sched_stat_{wait, sleep, iowait} are not exposed to user if CONFIG_SCHEDSTATS is not set, "perf sched record" records the three events. As a result, the command fails. Before: #perf sched record sleep 1 event syntax error: 'sched:sched_stat_wait' \___ unknown tracepoint Error: File /sys/kernel/tracing/events/sched/sched_stat_wait not found. Hint: Perhaps this kernel misses some CONFIG_ setting to enable this feature?. Run 'perf list' for a list of valid events Usage: perf record [] [] or: perf record [] -- [] -e, --event event selector. use 'perf list' to list available events Solution: Check whether schedstat tracepoints are exposed. If no, these events are not recorded. After: # perf sched record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.163 MB perf.data (1091 samples) ] # perf sched report run measurement overhead: 4736 nsecs sleep measurement overhead: 9059979 nsecs the run test took 999854 nsecs the sleep test took 8945271 nsecs nr_run_events: 716 nr_sleep_events: 785 nr_wakeup_events: 0 ... ------------------------------------------------------------ Fixes: 2a09b5de235a6 ("sched/fair: do not expose some tracepoints to user if CONFIG_SCHEDSTATS is not set") Signed-off-by: Yang Jihong Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Cc: Yafang Shao Link: http://lore.kernel.org/lkml/20210713112358.194693-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index aaf1cde476c9..1ff10d4bccf3 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -3335,6 +3335,16 @@ static void setup_sorting(struct perf_sched *sched, const struct option *options sort_dimension__add("pid", &sched->cmp_pid); } +static bool schedstat_events_exposed(void) +{ + /* + * Select "sched:sched_stat_wait" event to check + * whether schedstat tracepoints are exposed. + */ + return IS_ERR(trace_event__tp_format("sched", "sched_stat_wait")) ? + false : true; +} + static int __cmd_record(int argc, const char **argv) { unsigned int rec_argc, i, j; @@ -3346,21 +3356,33 @@ static int __cmd_record(int argc, const char **argv) "-m", "1024", "-c", "1", "-e", "sched:sched_switch", - "-e", "sched:sched_stat_wait", - "-e", "sched:sched_stat_sleep", - "-e", "sched:sched_stat_iowait", "-e", "sched:sched_stat_runtime", "-e", "sched:sched_process_fork", "-e", "sched:sched_wakeup_new", "-e", "sched:sched_migrate_task", }; + + /* + * The tracepoints trace_sched_stat_{wait, sleep, iowait} + * are not exposed to user if CONFIG_SCHEDSTATS is not set, + * to prevent "perf sched record" execution failure, determine + * whether to record schedstat events according to actual situation. + */ + const char * const schedstat_args[] = { + "-e", "sched:sched_stat_wait", + "-e", "sched:sched_stat_sleep", + "-e", "sched:sched_stat_iowait", + }; + unsigned int schedstat_argc = schedstat_events_exposed() ? + ARRAY_SIZE(schedstat_args) : 0; + struct tep_event *waking_event; /* * +2 for either "-e", "sched:sched_wakeup" or * "-e", "sched:sched_waking" */ - rec_argc = ARRAY_SIZE(record_args) + 2 + argc - 1; + rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1; rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) @@ -3376,6 +3398,9 @@ static int __cmd_record(int argc, const char **argv) else rec_argv[i++] = strdup("sched:sched_wakeup"); + for (j = 0; j < schedstat_argc; j++) + rec_argv[i++] = strdup(schedstat_args[j]); + for (j = 1; j < (unsigned int)argc; j++, i++) rec_argv[i] = argv[j]; From 5df99bec210a2cf89dd91e52f0d0a714bf4cd96a Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 12 Jul 2021 15:35:46 -0400 Subject: [PATCH 417/426] scripts/setlocalversion: fix a bug when LOCALVERSION is empty The commit 042da426f8eb ("scripts/setlocalversion: simplify the short version part") reduces indentation. Unfortunately, it also changes behavior in a subtle way - if the user has empty "LOCALVERSION" variable, the plus sign is appended to the kernel version. It wasn't appended before. This patch reverts to the old behavior - we append the plus sign only if the LOCALVERSION variable is not set. Fixes: 042da426f8eb ("scripts/setlocalversion: simplify the short version part") Signed-off-by: Mikulas Patocka Signed-off-by: Masahiro Yamada --- scripts/setlocalversion | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 151f04971faa..6b54e46a0f12 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -131,11 +131,14 @@ res="${res}${CONFIG_LOCALVERSION}${LOCALVERSION}" if test "$CONFIG_LOCALVERSION_AUTO" = "y"; then # full scm version string res="$res$(scm_version)" -elif [ -z "${LOCALVERSION}" ]; then - # append a plus sign if the repository is not in a clean - # annotated or signed tagged state (as git describe only - # looks at signed or annotated tags - git tag -a/-s) and - # LOCALVERSION= is not specified +elif [ "${LOCALVERSION+set}" != "set" ]; then + # If the variable LOCALVERSION is not set, append a plus + # sign if the repository is not in a clean annotated or + # signed tagged state (as git describe only looks at signed + # or annotated tags - git tag -a/-s). + # + # If the variable LOCALVERSION is set (including being set + # to an empty string), we don't want to append a plus sign. scm=$(scm_version --short) res="$res${scm:++}" fi From d952cfaf0cffdbbb0433c67206b645131f17ca5f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 14 Jul 2021 13:23:49 +0900 Subject: [PATCH 418/426] kbuild: do not suppress Kconfig prompts for silent build When a new CONFIG option is available, Kbuild shows a prompt to get the user input. $ make [ snip ] Core Scheduling for SMT (SCHED_CORE) [N/y/?] (NEW) This is the only interactive place in the build process. Commit 174a1dcc9642 ("kbuild: sink stdout from cmd for silent build") suppressed Kconfig prompts as well because syncconfig is invoked by the 'cmd' macro. You cannot notice the fact that Kconfig is waiting for the user input. Use 'kecho' to show the equivalent short log without suppressing stdout from sub-make. Fixes: 174a1dcc9642 ("kbuild: sink stdout from cmd for silent build") Reported-by: Tetsuo Handa Signed-off-by: Masahiro Yamada Tested-by: Tetsuo Handa --- Makefile | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/Makefile b/Makefile index c3f9bd191b89..e264c5440f70 100644 --- a/Makefile +++ b/Makefile @@ -728,11 +728,12 @@ $(KCONFIG_CONFIG): # This exploits the 'multi-target pattern rule' trick. # The syncconfig should be executed only once to make all the targets. # (Note: use the grouped target '&:' when we bump to GNU Make 4.3) -quiet_cmd_syncconfig = SYNC $@ - cmd_syncconfig = $(MAKE) -f $(srctree)/Makefile syncconfig - +# +# Do not use $(call cmd,...) here. That would suppress prompts from syncconfig, +# so you cannot notice that Kconfig is waiting for the user input. %/config/auto.conf %/config/auto.conf.cmd %/generated/autoconf.h: $(KCONFIG_CONFIG) - +$(call cmd,syncconfig) + $(Q)$(kecho) " SYNC $@" + $(Q)$(MAKE) -f $(srctree)/Makefile syncconfig else # !may-sync-config # External modules and some install targets need include/generated/autoconf.h # and include/config/auto.conf but do not care if they are up-to-date. From 1d11053dc63094075bf9e4809fffd3bb5e72f9a6 Mon Sep 17 00:00:00 2001 From: Lecopzer Chen Date: Thu, 15 Jul 2021 15:37:16 +0800 Subject: [PATCH 419/426] Kbuild: lto: fix module versionings mismatch in GNU make 3.X When building modules(CONFIG_...=m), I found some of module versions are incorrect and set to 0. This can be found in build log for first clean build which shows WARNING: EXPORT symbol "XXXX" [drivers/XXX/XXX.ko] version generation failed, symbol will not be versioned. But in second build(incremental build), the WARNING disappeared and the module version becomes valid CRC and make someone who want to change modules without updating kernel image can't insert their modules. The problematic code is + $(foreach n, $(filter-out FORCE,$^), \ + $(if $(wildcard $(n).symversions), \ + ; cat $(n).symversions >> $@.symversions)) For example: rm -f fs/notify/built-in.a.symversions ; rm -f fs/notify/built-in.a; \ llvm-ar cDPrST fs/notify/built-in.a fs/notify/fsnotify.o \ fs/notify/notification.o fs/notify/group.o ... `foreach n` shows nothing to `cat` into $(n).symversions because `if $(wildcard $(n).symversions)` return nothing, but actually they do exist during this line was executed. -rw-r--r-- 1 root root 168580 Jun 13 19:10 fs/notify/fsnotify.o -rw-r--r-- 1 root root 111 Jun 13 19:10 fs/notify/fsnotify.o.symversions The reason is the $(n).symversions are generated at runtime, but Makefile wildcard function expends and checks the file exist or not during parsing the Makefile. Thus fix this by use `test` shell command to check the file existence in runtime. Rebase from both: 1. [https://lore.kernel.org/lkml/20210616080252.32046-1-lecopzer.chen@mediatek.com/] 2. [https://lore.kernel.org/lkml/20210702032943.7865-1-lecopzer.chen@mediatek.com/] Fixes: 38e891849003 ("kbuild: lto: fix module versioning") Co-developed-by: Sami Tolvanen Signed-off-by: Lecopzer Chen Signed-off-by: Masahiro Yamada --- scripts/Makefile.build | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 10b2f2380d6f..02197cb8e3a7 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -386,7 +386,7 @@ ifeq ($(CONFIG_LTO_CLANG) $(CONFIG_MODVERSIONS),y y) cmd_update_lto_symversions = \ rm -f $@.symversions \ $(foreach n, $(filter-out FORCE,$^), \ - $(if $(wildcard $(n).symversions), \ + $(if $(shell test -s $(n).symversions && echo y), \ ; cat $(n).symversions >> $@.symversions)) else cmd_update_lto_symversions = echo >/dev/null From 5e60f363b38fd40e4d8838b5d6f4d4ecee92c777 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Thu, 15 Jul 2021 11:26:02 +0200 Subject: [PATCH 420/426] Documentation: Fix intiramfs script name Documentation was not changed when renaming the script in commit 80e715a06c2d ("initramfs: rename gen_initramfs_list.sh to gen_initramfs.sh"). Fixing this. Basically does: $ sed -i -e s/gen_initramfs_list.sh/gen_initramfs.sh/g $(git grep -l gen_initramfs_list.sh) Fixes: 80e715a06c2d ("initramfs: rename gen_initramfs_list.sh to gen_initramfs.sh") Signed-off-by: Robert Richter Signed-off-by: Masahiro Yamada --- .../early-userspace/early_userspace_support.rst | 8 ++++---- Documentation/filesystems/ramfs-rootfs-initramfs.rst | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/driver-api/early-userspace/early_userspace_support.rst b/Documentation/driver-api/early-userspace/early_userspace_support.rst index 8a58c61932ff..61bdeac1bae5 100644 --- a/Documentation/driver-api/early-userspace/early_userspace_support.rst +++ b/Documentation/driver-api/early-userspace/early_userspace_support.rst @@ -69,17 +69,17 @@ early userspace image can be built by an unprivileged user. As a technical note, when directories and files are specified, the entire CONFIG_INITRAMFS_SOURCE is passed to -usr/gen_initramfs_list.sh. This means that CONFIG_INITRAMFS_SOURCE +usr/gen_initramfs.sh. This means that CONFIG_INITRAMFS_SOURCE can really be interpreted as any legal argument to -gen_initramfs_list.sh. If a directory is specified as an argument then +gen_initramfs.sh. If a directory is specified as an argument then the contents are scanned, uid/gid translation is performed, and usr/gen_init_cpio file directives are output. If a directory is -specified as an argument to usr/gen_initramfs_list.sh then the +specified as an argument to usr/gen_initramfs.sh then the contents of the file are simply copied to the output. All of the output directives from directory scanning and file contents copying are processed by usr/gen_init_cpio. -See also 'usr/gen_initramfs_list.sh -h'. +See also 'usr/gen_initramfs.sh -h'. Where's this all leading? ========================= diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.rst b/Documentation/filesystems/ramfs-rootfs-initramfs.rst index 4598b0d90b60..164960631925 100644 --- a/Documentation/filesystems/ramfs-rootfs-initramfs.rst +++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst @@ -170,7 +170,7 @@ Documentation/driver-api/early-userspace/early_userspace_support.rst for more de The kernel does not depend on external cpio tools. If you specify a directory instead of a configuration file, the kernel's build infrastructure creates a configuration file from that directory (usr/Makefile calls -usr/gen_initramfs_list.sh), and proceeds to package up that directory +usr/gen_initramfs.sh), and proceeds to package up that directory using the config file (by feeding it to usr/gen_init_cpio, which is created from usr/gen_init_cpio.c). The kernel's build-time cpio creation code is entirely self-contained, and the kernel's boot-time extractor is also From 2734d6c1b1a089fb593ef6a23d4b70903526fe0c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 18 Jul 2021 14:13:49 -0700 Subject: [PATCH 421/426] Linux 5.14-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 0517005d65fa..e4f5895badb5 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Opossums on Parade # *DOCUMENTATION* From dde0a31863d6a7b05ca7cb5d138586e71afc5e50 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 13 Jul 2021 21:35:18 +0200 Subject: [PATCH 422/426] PCI: endpoint: Make struct pci_epf_driver::remove return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of pci_epf_device_remove() (because there is only little it can do when a device disappears) and there are no pci_epf_drivers with a remove callback. So make it impossible for future drivers to return an unused error code by changing the remove prototype to return void. The real motivation for this change is the quest to make struct bus_type::remove return void, too. Acked-by: Kishon Vijay Abraham I Acked-by: Bjorn Helgaas Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210713193522.1770306-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/pci/endpoint/pci-epf-core.c | 5 ++--- include/linux/pci-epf.h | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index e9289d10f822..4b9ad96bf1b2 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -389,15 +389,14 @@ static int pci_epf_device_probe(struct device *dev) static int pci_epf_device_remove(struct device *dev) { - int ret = 0; struct pci_epf *epf = to_pci_epf(dev); struct pci_epf_driver *driver = to_pci_epf_driver(dev->driver); if (driver->remove) - ret = driver->remove(epf); + driver->remove(epf); epf->driver = NULL; - return ret; + return 0; } static struct bus_type pci_epf_bus_type = { diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 2debc27ba95e..8292420426f3 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -85,7 +85,7 @@ struct pci_epf_ops { */ struct pci_epf_driver { int (*probe)(struct pci_epf *epf); - int (*remove)(struct pci_epf *epf); + void (*remove)(struct pci_epf *epf); struct device_driver driver; struct pci_epf_ops *ops; From a7bdb9a9767360c2b4096bbb379e73022b274483 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 13 Jul 2021 21:35:19 +0200 Subject: [PATCH 423/426] s390/cio: Make struct css_driver::remove return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of css_remove() (because there is only little it can do when a device disappears) and all callbacks return 0 anyhow. So make it impossible for future drivers to return an unused error code by changing the remove prototype to return void. The real motivation for this change is the quest to make struct bus_type::remove return void, too. Reviewed-by: Cornelia Huck Acked-by: Vineeth Vijayan Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210713193522.1770306-3-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/s390/cio/chsc_sch.c | 3 +-- drivers/s390/cio/css.c | 7 ++++--- drivers/s390/cio/css.h | 2 +- drivers/s390/cio/device.c | 5 ++--- drivers/s390/cio/eadm_sch.c | 4 +--- drivers/s390/cio/vfio_ccw_drv.c | 3 +-- 6 files changed, 10 insertions(+), 14 deletions(-) diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c index c42405c620b5..684348d82f08 100644 --- a/drivers/s390/cio/chsc_sch.c +++ b/drivers/s390/cio/chsc_sch.c @@ -100,7 +100,7 @@ static int chsc_subchannel_probe(struct subchannel *sch) return ret; } -static int chsc_subchannel_remove(struct subchannel *sch) +static void chsc_subchannel_remove(struct subchannel *sch) { struct chsc_private *private; @@ -112,7 +112,6 @@ static int chsc_subchannel_remove(struct subchannel *sch) put_device(&sch->dev); } kfree(private); - return 0; } static void chsc_subchannel_shutdown(struct subchannel *sch) diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index a974943c27da..092fd1ea5799 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1374,12 +1374,13 @@ static int css_probe(struct device *dev) static int css_remove(struct device *dev) { struct subchannel *sch; - int ret; sch = to_subchannel(dev); - ret = sch->driver->remove ? sch->driver->remove(sch) : 0; + if (sch->driver->remove) + sch->driver->remove(sch); sch->driver = NULL; - return ret; + + return 0; } static void css_shutdown(struct device *dev) diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h index 2eddfc47f687..c98522cbe276 100644 --- a/drivers/s390/cio/css.h +++ b/drivers/s390/cio/css.h @@ -81,7 +81,7 @@ struct css_driver { int (*chp_event)(struct subchannel *, struct chp_link *, int); int (*sch_event)(struct subchannel *, int); int (*probe)(struct subchannel *); - int (*remove)(struct subchannel *); + void (*remove)(struct subchannel *); void (*shutdown)(struct subchannel *); int (*settle)(void); }; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 84f659cafe76..cd5d2d4d8e46 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -137,7 +137,7 @@ static int ccw_uevent(struct device *dev, struct kobj_uevent_env *env) static void io_subchannel_irq(struct subchannel *); static int io_subchannel_probe(struct subchannel *); -static int io_subchannel_remove(struct subchannel *); +static void io_subchannel_remove(struct subchannel *); static void io_subchannel_shutdown(struct subchannel *); static int io_subchannel_sch_event(struct subchannel *, int); static int io_subchannel_chp_event(struct subchannel *, struct chp_link *, @@ -1101,7 +1101,7 @@ out_schedule: return 0; } -static int io_subchannel_remove(struct subchannel *sch) +static void io_subchannel_remove(struct subchannel *sch) { struct io_subchannel_private *io_priv = to_io_private(sch); struct ccw_device *cdev; @@ -1120,7 +1120,6 @@ out_free: io_priv->dma_area, io_priv->dma_area_dma); kfree(io_priv); sysfs_remove_group(&sch->dev.kobj, &io_subchannel_attr_group); - return 0; } static void io_subchannel_verify(struct subchannel *sch) diff --git a/drivers/s390/cio/eadm_sch.c b/drivers/s390/cio/eadm_sch.c index c8964e0a23e7..15bdae5981ca 100644 --- a/drivers/s390/cio/eadm_sch.c +++ b/drivers/s390/cio/eadm_sch.c @@ -282,7 +282,7 @@ disable: spin_unlock_irq(sch->lock); } -static int eadm_subchannel_remove(struct subchannel *sch) +static void eadm_subchannel_remove(struct subchannel *sch) { struct eadm_private *private = get_eadm_private(sch); @@ -297,8 +297,6 @@ static int eadm_subchannel_remove(struct subchannel *sch) spin_unlock_irq(sch->lock); kfree(private); - - return 0; } static void eadm_subchannel_shutdown(struct subchannel *sch) diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 9b61e9b131ad..76099bcb765b 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -234,7 +234,7 @@ out_free: return ret; } -static int vfio_ccw_sch_remove(struct subchannel *sch) +static void vfio_ccw_sch_remove(struct subchannel *sch) { struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev); struct vfio_ccw_crw *crw, *temp; @@ -257,7 +257,6 @@ static int vfio_ccw_sch_remove(struct subchannel *sch) VFIO_CCW_MSG_EVENT(4, "unbound from subchannel %x.%x.%04x\n", sch->schid.cssid, sch->schid.ssid, sch->schid.sch_no); - return 0; } static void vfio_ccw_sch_shutdown(struct subchannel *sch) From 7a47c52142c18a9239c5afea2c9656c68d3f22e7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 13 Jul 2021 21:35:20 +0200 Subject: [PATCH 424/426] s390/ccwgroup: Drop if with an always false condition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core only calls a bus remove callback when there is a driver. So dev->driver is never NULL and the check can safely be removed. Reviewed-by: Cornelia Huck Acked-by: Vineeth Vijayan Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210713193522.1770306-4-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/s390/cio/ccwgroup.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index 9748165e08e9..a6aeab1ea0ae 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -444,8 +444,6 @@ static int ccwgroup_remove(struct device *dev) struct ccwgroup_device *gdev = to_ccwgroupdev(dev); struct ccwgroup_driver *gdrv = to_ccwgroupdrv(dev->driver); - if (!dev->driver) - return 0; if (gdrv->remove) gdrv->remove(gdev); From 15f83bb0191261adece5a26bfdf93c6eccdbc0bb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 13 Jul 2021 21:35:21 +0200 Subject: [PATCH 425/426] s390/scm: Make struct scm_driver::remove return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of scmdev_remove() (because there is only little it can do when a device disappears). So make it impossible for future drivers to return an unused error code by changing the remove prototype to return void. The real motivation for this change is the quest to make struct bus_type::remove return void, too. Reviewed-by: Cornelia Huck Acked-by: Vineeth Vijayan Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210713193522.1770306-5-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- arch/s390/include/asm/eadm.h | 2 +- drivers/s390/block/scm_drv.c | 4 +--- drivers/s390/cio/scm.c | 5 ++++- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h index bb63b2afdf6f..445fe4c8184a 100644 --- a/arch/s390/include/asm/eadm.h +++ b/arch/s390/include/asm/eadm.h @@ -105,7 +105,7 @@ enum scm_event {SCM_CHANGE, SCM_AVAIL}; struct scm_driver { struct device_driver drv; int (*probe) (struct scm_device *scmdev); - int (*remove) (struct scm_device *scmdev); + void (*remove) (struct scm_device *scmdev); void (*notify) (struct scm_device *scmdev, enum scm_event event); void (*handler) (struct scm_device *scmdev, void *data, blk_status_t error); diff --git a/drivers/s390/block/scm_drv.c b/drivers/s390/block/scm_drv.c index 3134fd6e058e..69a845eb8b1f 100644 --- a/drivers/s390/block/scm_drv.c +++ b/drivers/s390/block/scm_drv.c @@ -60,15 +60,13 @@ out: return ret; } -static int scm_remove(struct scm_device *scmdev) +static void scm_remove(struct scm_device *scmdev) { struct scm_blk_dev *bdev = dev_get_drvdata(&scmdev->dev); scm_blk_dev_cleanup(bdev); dev_set_drvdata(&scmdev->dev, NULL); kfree(bdev); - - return 0; } static struct scm_driver scm_drv = { diff --git a/drivers/s390/cio/scm.c b/drivers/s390/cio/scm.c index 9f26d4310bb3..b31711307e5a 100644 --- a/drivers/s390/cio/scm.c +++ b/drivers/s390/cio/scm.c @@ -33,7 +33,10 @@ static int scmdev_remove(struct device *dev) struct scm_device *scmdev = to_scm_dev(dev); struct scm_driver *scmdrv = to_scm_drv(dev->driver); - return scmdrv->remove ? scmdrv->remove(scmdev) : -ENODEV; + if (scmdrv->remove) + scmdrv->remove(scmdev); + + return 0; } static int scmdev_uevent(struct device *dev, struct kobj_uevent_env *env) From fc7a6209d5710618eb4f72a77cd81b8d694ecf89 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 13 Jul 2021 21:35:22 +0200 Subject: [PATCH 426/426] bus: Make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of this callback because there is only little it can do when a device disappears. This is the final bit of a long lasting cleanup quest where several buses were converted to also return void from their remove callback. Additionally some resource leaks were fixed that were caused by drivers returning an error code in the expectation that the driver won't go away. With struct bus_type::remove returning void it's prevented that newly implemented buses return an ignored error code and so don't anticipate wrong expectations for driver authors. Reviewed-by: Tom Rix (For fpga) Reviewed-by: Mathieu Poirier Reviewed-by: Cornelia Huck (For drivers/s390 and drivers/vfio) Acked-by: Russell King (Oracle) (For ARM, Amba and related parts) Acked-by: Mark Brown Acked-by: Chen-Yu Tsai (for sunxi-rsb) Acked-by: Pali Rohár Acked-by: Mauro Carvalho Chehab (for media) Acked-by: Hans de Goede (For drivers/platform) Acked-by: Alexandre Belloni Acked-By: Vinod Koul Acked-by: Juergen Gross (For xen) Acked-by: Lee Jones (For mfd) Acked-by: Johannes Thumshirn (For mcb) Acked-by: Johan Hovold Acked-by: Srinivas Kandagatla (For slimbus) Acked-by: Kirti Wankhede (For vfio) Acked-by: Maximilian Luz Acked-by: Heikki Krogerus (For ulpi and typec) Acked-by: Samuel Iglesias Gonsálvez (For ipack) Acked-by: Geoff Levand (For ps3) Acked-by: Yehezkel Bernat (For thunderbolt) Acked-by: Alexander Shishkin (For intel_th) Acked-by: Dominik Brodowski (For pcmcia) Acked-by: Rafael J. Wysocki (For ACPI) Acked-by: Bjorn Andersson (rpmsg and apr) Acked-by: Srinivas Pandruvada (For intel-ish-hid) Acked-by: Dan Williams (For CXL, DAX, and NVDIMM) Acked-by: William Breathitt Gray (For isa) Acked-by: Stefan Richter (For firewire) Acked-by: Benjamin Tissoires (For hid) Acked-by: Thorsten Scherer (For siox) Acked-by: Sven Van Asbroeck (For anybuss) Acked-by: Ulf Hansson (For MMC) Acked-by: Wolfram Sang # for I2C Acked-by: Sudeep Holla Acked-by: Geert Uytterhoeven Acked-by: Dmitry Torokhov Acked-by: Finn Thain Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210713193522.1770306-6-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- arch/arm/common/locomo.c | 3 +-- arch/arm/common/sa1111.c | 4 +--- arch/arm/mach-rpc/ecard.c | 4 +--- arch/mips/sgi-ip22/ip22-gio.c | 3 +-- arch/parisc/kernel/drivers.c | 5 ++--- arch/powerpc/platforms/ps3/system-bus.c | 3 +-- arch/powerpc/platforms/pseries/ibmebus.c | 3 +-- arch/powerpc/platforms/pseries/vio.c | 3 +-- arch/sparc/kernel/vio.c | 4 +--- drivers/acpi/bus.c | 3 +-- drivers/amba/bus.c | 4 +--- drivers/base/auxiliary.c | 4 +--- drivers/base/isa.c | 4 +--- drivers/base/platform.c | 4 +--- drivers/bcma/main.c | 6 ++---- drivers/bus/sunxi-rsb.c | 4 +--- drivers/cxl/core.c | 3 +-- drivers/dax/bus.c | 4 +--- drivers/dma/idxd/sysfs.c | 4 +--- drivers/firewire/core-device.c | 4 +--- drivers/firmware/arm_scmi/bus.c | 4 +--- drivers/firmware/google/coreboot_table.c | 4 +--- drivers/fpga/dfl.c | 4 +--- drivers/hid/hid-core.c | 4 +--- drivers/hid/intel-ish-hid/ishtp/bus.c | 4 +--- drivers/hv/vmbus_drv.c | 5 +---- drivers/hwtracing/intel_th/core.c | 4 +--- drivers/i2c/i2c-core-base.c | 5 +---- drivers/i3c/master.c | 4 +--- drivers/input/gameport/gameport.c | 3 +-- drivers/input/serio/serio.c | 3 +-- drivers/ipack/ipack.c | 4 +--- drivers/macintosh/macio_asic.c | 4 +--- drivers/mcb/mcb-core.c | 4 +--- drivers/media/pci/bt8xx/bttv-gpio.c | 3 +-- drivers/memstick/core/memstick.c | 3 +-- drivers/mfd/mcp-core.c | 3 +-- drivers/misc/mei/bus.c | 4 +--- drivers/misc/tifm_core.c | 3 +-- drivers/mmc/core/bus.c | 4 +--- drivers/mmc/core/sdio_bus.c | 4 +--- drivers/net/netdevsim/bus.c | 3 +-- drivers/ntb/core.c | 4 +--- drivers/ntb/ntb_transport.c | 4 +--- drivers/nubus/bus.c | 6 ++---- drivers/nvdimm/bus.c | 3 +-- drivers/pci/endpoint/pci-epf-core.c | 4 +--- drivers/pci/pci-driver.c | 3 +-- drivers/pcmcia/ds.c | 4 +--- drivers/platform/surface/aggregator/bus.c | 4 +--- drivers/platform/x86/wmi.c | 4 +--- drivers/pnp/driver.c | 3 +-- drivers/rapidio/rio-driver.c | 4 +--- drivers/rpmsg/rpmsg_core.c | 7 ++----- drivers/s390/cio/ccwgroup.c | 4 +--- drivers/s390/cio/css.c | 4 +--- drivers/s390/cio/device.c | 4 +--- drivers/s390/cio/scm.c | 4 +--- drivers/s390/crypto/ap_bus.c | 4 +--- drivers/scsi/scsi_debug.c | 3 +-- drivers/sh/superhyway/superhyway.c | 8 ++------ drivers/siox/siox-core.c | 4 +--- drivers/slimbus/core.c | 4 +--- drivers/soc/qcom/apr.c | 4 +--- drivers/spi/spi.c | 4 +--- drivers/spmi/spmi.c | 3 +-- drivers/ssb/main.c | 4 +--- drivers/staging/fieldbus/anybuss/host.c | 4 +--- drivers/staging/greybus/gbphy.c | 4 +--- drivers/target/loopback/tcm_loop.c | 5 ++--- drivers/thunderbolt/domain.c | 4 +--- drivers/tty/serdev/core.c | 4 +--- drivers/usb/common/ulpi.c | 4 +--- drivers/usb/serial/bus.c | 4 +--- drivers/usb/typec/bus.c | 4 +--- drivers/vdpa/vdpa.c | 4 +--- drivers/vfio/mdev/mdev_driver.c | 4 +--- drivers/virtio/virtio.c | 3 +-- drivers/vlynq/vlynq.c | 4 +--- drivers/vme/vme.c | 4 +--- drivers/xen/xenbus/xenbus.h | 2 +- drivers/xen/xenbus/xenbus_probe.c | 4 +--- drivers/zorro/zorro-driver.c | 3 +-- include/linux/device/bus.h | 2 +- sound/ac97/bus.c | 6 ++---- sound/aoa/soundbus/core.c | 4 +--- 86 files changed, 93 insertions(+), 243 deletions(-) diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c index e45f4e4e06b6..24d21ba63030 100644 --- a/arch/arm/common/locomo.c +++ b/arch/arm/common/locomo.c @@ -834,14 +834,13 @@ static int locomo_bus_probe(struct device *dev) return ret; } -static int locomo_bus_remove(struct device *dev) +static void locomo_bus_remove(struct device *dev) { struct locomo_dev *ldev = LOCOMO_DEV(dev); struct locomo_driver *drv = LOCOMO_DRV(dev->driver); if (drv->remove) drv->remove(ldev); - return 0; } struct bus_type locomo_bus_type = { diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index ff5e0d04cb89..092a2ebc0c28 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -1364,15 +1364,13 @@ static int sa1111_bus_probe(struct device *dev) return ret; } -static int sa1111_bus_remove(struct device *dev) +static void sa1111_bus_remove(struct device *dev) { struct sa1111_dev *sadev = to_sa1111_device(dev); struct sa1111_driver *drv = SA1111_DRV(dev->driver); if (drv->remove) drv->remove(sadev); - - return 0; } struct bus_type sa1111_bus_type = { diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index 827b50f1c73e..53813f9464a2 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -1052,7 +1052,7 @@ static int ecard_drv_probe(struct device *dev) return ret; } -static int ecard_drv_remove(struct device *dev) +static void ecard_drv_remove(struct device *dev) { struct expansion_card *ec = ECARD_DEV(dev); struct ecard_driver *drv = ECARD_DRV(dev->driver); @@ -1067,8 +1067,6 @@ static int ecard_drv_remove(struct device *dev) ec->ops = &ecard_default_ops; barrier(); ec->irq_data = NULL; - - return 0; } /* diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c index de0768a49ee8..dfc52f661ad0 100644 --- a/arch/mips/sgi-ip22/ip22-gio.c +++ b/arch/mips/sgi-ip22/ip22-gio.c @@ -143,14 +143,13 @@ static int gio_device_probe(struct device *dev) return error; } -static int gio_device_remove(struct device *dev) +static void gio_device_remove(struct device *dev) { struct gio_device *gio_dev = to_gio_device(dev); struct gio_driver *drv = to_gio_driver(dev->driver); if (dev->driver && drv->remove) drv->remove(gio_dev); - return 0; } static void gio_device_shutdown(struct device *dev) diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index 80fa0650736b..776d624a7207 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -133,14 +133,13 @@ static int parisc_driver_probe(struct device *dev) return rc; } -static int __exit parisc_driver_remove(struct device *dev) +static void __exit parisc_driver_remove(struct device *dev) { struct parisc_device *pa_dev = to_parisc_device(dev); struct parisc_driver *pa_drv = to_parisc_driver(dev->driver); + if (pa_drv->remove) pa_drv->remove(pa_dev); - - return 0; } diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 1a5665875165..cc5774c64fae 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -381,7 +381,7 @@ static int ps3_system_bus_probe(struct device *_dev) return result; } -static int ps3_system_bus_remove(struct device *_dev) +static void ps3_system_bus_remove(struct device *_dev) { struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev); struct ps3_system_bus_driver *drv; @@ -399,7 +399,6 @@ static int ps3_system_bus_remove(struct device *_dev) __func__, __LINE__, drv->core.name); pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core)); - return 0; } static void ps3_system_bus_shutdown(struct device *_dev) diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index c6c79ef55e13..7ee3ed7d6cc2 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -366,14 +366,13 @@ static int ibmebus_bus_device_probe(struct device *dev) return error; } -static int ibmebus_bus_device_remove(struct device *dev) +static void ibmebus_bus_device_remove(struct device *dev) { struct platform_device *of_dev = to_platform_device(dev); struct platform_driver *drv = to_platform_driver(dev->driver); if (dev->driver && drv->remove) drv->remove(of_dev); - return 0; } static void ibmebus_bus_device_shutdown(struct device *dev) diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index e00f3725ec96..58283cecbd52 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1257,7 +1257,7 @@ static int vio_bus_probe(struct device *dev) } /* convert from struct device to struct vio_dev and pass to driver. */ -static int vio_bus_remove(struct device *dev) +static void vio_bus_remove(struct device *dev) { struct vio_dev *viodev = to_vio_dev(dev); struct vio_driver *viodrv = to_vio_driver(dev->driver); @@ -1276,7 +1276,6 @@ static int vio_bus_remove(struct device *dev) vio_cmo_bus_remove(viodev); put_device(devptr); - return 0; } static void vio_bus_shutdown(struct device *dev) diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index 348a88691219..01122a208f94 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -93,7 +93,7 @@ static int vio_device_probe(struct device *dev) return drv->probe(vdev, id); } -static int vio_device_remove(struct device *dev) +static void vio_device_remove(struct device *dev) { struct vio_dev *vdev = to_vio_dev(dev); struct vio_driver *drv = to_vio_driver(dev->driver); @@ -107,8 +107,6 @@ static int vio_device_remove(struct device *dev) drv->remove(vdev); } - - return 0; } static ssize_t devspec_show(struct device *dev, diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index f854bcb8d010..b941555cb5e4 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1019,7 +1019,7 @@ static int acpi_device_probe(struct device *dev) return 0; } -static int acpi_device_remove(struct device *dev) +static void acpi_device_remove(struct device *dev) { struct acpi_device *acpi_dev = to_acpi_device(dev); struct acpi_driver *acpi_drv = acpi_dev->driver; @@ -1034,7 +1034,6 @@ static int acpi_device_remove(struct device *dev) acpi_dev->driver_data = NULL; put_device(dev); - return 0; } struct bus_type acpi_bus_type = { diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 939ca220bf78..962041148482 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -219,7 +219,7 @@ static int amba_probe(struct device *dev) return ret; } -static int amba_remove(struct device *dev) +static void amba_remove(struct device *dev) { struct amba_device *pcdev = to_amba_device(dev); struct amba_driver *drv = to_amba_driver(dev->driver); @@ -236,8 +236,6 @@ static int amba_remove(struct device *dev) amba_put_disable_pclk(pcdev); dev_pm_domain_detach(dev, true); - - return 0; } static void amba_shutdown(struct device *dev) diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c index adc199dfba3c..0c86f5bed9f4 100644 --- a/drivers/base/auxiliary.c +++ b/drivers/base/auxiliary.c @@ -79,7 +79,7 @@ static int auxiliary_bus_probe(struct device *dev) return ret; } -static int auxiliary_bus_remove(struct device *dev) +static void auxiliary_bus_remove(struct device *dev) { struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver); struct auxiliary_device *auxdev = to_auxiliary_dev(dev); @@ -87,8 +87,6 @@ static int auxiliary_bus_remove(struct device *dev) if (auxdrv->remove) auxdrv->remove(auxdev); dev_pm_domain_detach(dev, true); - - return 0; } static void auxiliary_bus_shutdown(struct device *dev) diff --git a/drivers/base/isa.c b/drivers/base/isa.c index aa4737667026..55e3ee2da98f 100644 --- a/drivers/base/isa.c +++ b/drivers/base/isa.c @@ -46,14 +46,12 @@ static int isa_bus_probe(struct device *dev) return 0; } -static int isa_bus_remove(struct device *dev) +static void isa_bus_remove(struct device *dev) { struct isa_driver *isa_driver = dev->platform_data; if (isa_driver && isa_driver->remove) isa_driver->remove(dev, to_isa_dev(dev)->id); - - return 0; } static void isa_bus_shutdown(struct device *dev) diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 8640578f45e9..a94b7f454881 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1438,7 +1438,7 @@ out: return ret; } -static int platform_remove(struct device *_dev) +static void platform_remove(struct device *_dev) { struct platform_driver *drv = to_platform_driver(_dev->driver); struct platform_device *dev = to_platform_device(_dev); @@ -1450,8 +1450,6 @@ static int platform_remove(struct device *_dev) dev_warn(_dev, "remove callback returned a non-zero value. This will be ignored.\n"); } dev_pm_domain_detach(_dev, true); - - return 0; } static void platform_shutdown(struct device *_dev) diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index 6535614a7dc1..e076630d17bd 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -27,7 +27,7 @@ static DEFINE_MUTEX(bcma_buses_mutex); static int bcma_bus_match(struct device *dev, struct device_driver *drv); static int bcma_device_probe(struct device *dev); -static int bcma_device_remove(struct device *dev); +static void bcma_device_remove(struct device *dev); static int bcma_device_uevent(struct device *dev, struct kobj_uevent_env *env); static ssize_t manuf_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -614,7 +614,7 @@ static int bcma_device_probe(struct device *dev) return err; } -static int bcma_device_remove(struct device *dev) +static void bcma_device_remove(struct device *dev) { struct bcma_device *core = container_of(dev, struct bcma_device, dev); struct bcma_driver *adrv = container_of(dev->driver, struct bcma_driver, @@ -623,8 +623,6 @@ static int bcma_device_remove(struct device *dev) if (adrv->remove) adrv->remove(core); put_device(dev); - - return 0; } static int bcma_device_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index d46db132d085..6f225dddc74f 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -169,13 +169,11 @@ static int sunxi_rsb_device_probe(struct device *dev) return drv->probe(rdev); } -static int sunxi_rsb_device_remove(struct device *dev) +static void sunxi_rsb_device_remove(struct device *dev) { const struct sunxi_rsb_driver *drv = to_sunxi_rsb_driver(dev->driver); drv->remove(to_sunxi_rsb_device(dev)); - - return 0; } static struct bus_type sunxi_rsb_bus = { diff --git a/drivers/cxl/core.c b/drivers/cxl/core.c index a2e4d54fc7bc..2b90b7c3b9d7 100644 --- a/drivers/cxl/core.c +++ b/drivers/cxl/core.c @@ -1034,13 +1034,12 @@ static int cxl_bus_probe(struct device *dev) return to_cxl_drv(dev->driver)->probe(dev); } -static int cxl_bus_remove(struct device *dev) +static void cxl_bus_remove(struct device *dev) { struct cxl_driver *cxl_drv = to_cxl_drv(dev->driver); if (cxl_drv->remove) cxl_drv->remove(dev); - return 0; } struct bus_type cxl_bus_type = { diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 5aee26e1bbd6..6cc4da4c713d 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -172,15 +172,13 @@ static int dax_bus_probe(struct device *dev) return 0; } -static int dax_bus_remove(struct device *dev) +static void dax_bus_remove(struct device *dev) { struct dax_device_driver *dax_drv = to_dax_drv(dev->driver); struct dev_dax *dev_dax = to_dev_dax(dev); if (dax_drv->remove) dax_drv->remove(dev_dax); - - return 0; } static struct bus_type dax_bus_type = { diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 0460d58e3941..5a017c62c752 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -260,7 +260,7 @@ static void disable_wq(struct idxd_wq *wq) dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev)); } -static int idxd_config_bus_remove(struct device *dev) +static void idxd_config_bus_remove(struct device *dev) { int rc; @@ -305,8 +305,6 @@ static int idxd_config_bus_remove(struct device *dev) dev_info(dev, "Device %s disabled\n", dev_name(dev)); } - - return 0; } static void idxd_config_bus_shutdown(struct device *dev) diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 68216988391f..90ed8fdaba75 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -187,14 +187,12 @@ static int fw_unit_probe(struct device *dev) return driver->probe(fw_unit(dev), unit_match(dev, dev->driver)); } -static int fw_unit_remove(struct device *dev) +static void fw_unit_remove(struct device *dev) { struct fw_driver *driver = container_of(dev->driver, struct fw_driver, driver); driver->remove(fw_unit(dev)); - - return 0; } static int get_modalias(struct fw_unit *unit, char *buffer, size_t buffer_size) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 6c7e24935eca..f6fe723ab869 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -111,15 +111,13 @@ static int scmi_dev_probe(struct device *dev) return scmi_drv->probe(scmi_dev); } -static int scmi_dev_remove(struct device *dev) +static void scmi_dev_remove(struct device *dev) { struct scmi_driver *scmi_drv = to_scmi_driver(dev->driver); struct scmi_device *scmi_dev = to_scmi_dev(dev); if (scmi_drv->remove) scmi_drv->remove(scmi_dev); - - return 0; } static struct bus_type scmi_bus_type = { diff --git a/drivers/firmware/google/coreboot_table.c b/drivers/firmware/google/coreboot_table.c index dc83ea118c67..c52bcaa9def6 100644 --- a/drivers/firmware/google/coreboot_table.c +++ b/drivers/firmware/google/coreboot_table.c @@ -44,15 +44,13 @@ static int coreboot_bus_probe(struct device *dev) return ret; } -static int coreboot_bus_remove(struct device *dev) +static void coreboot_bus_remove(struct device *dev) { struct coreboot_device *device = CB_DEV(dev); struct coreboot_driver *driver = CB_DRV(dev->driver); if (driver->remove) driver->remove(device); - - return 0; } static struct bus_type coreboot_bus_type = { diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index 511b20ff35a3..1ae6779a0dd6 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -284,15 +284,13 @@ static int dfl_bus_probe(struct device *dev) return ddrv->probe(ddev); } -static int dfl_bus_remove(struct device *dev) +static void dfl_bus_remove(struct device *dev) { struct dfl_driver *ddrv = to_dfl_drv(dev->driver); struct dfl_device *ddev = to_dfl_dev(dev); if (ddrv->remove) ddrv->remove(ddev); - - return 0; } static int dfl_bus_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 7db332139f7d..dbed2524fd47 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2302,7 +2302,7 @@ end: return ret; } -static int hid_device_remove(struct device *dev) +static void hid_device_remove(struct device *dev) { struct hid_device *hdev = to_hid_device(dev); struct hid_driver *hdrv; @@ -2322,8 +2322,6 @@ static int hid_device_remove(struct device *dev) if (!hdev->io_started) up(&hdev->driver_input_lock); - - return 0; } static ssize_t modalias_show(struct device *dev, struct device_attribute *a, diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index f0802b047ed8..8a51bd9cd093 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -255,7 +255,7 @@ static int ishtp_cl_bus_match(struct device *dev, struct device_driver *drv) * * Return: Return value from driver remove() call. */ -static int ishtp_cl_device_remove(struct device *dev) +static void ishtp_cl_device_remove(struct device *dev) { struct ishtp_cl_device *device = to_ishtp_cl_device(dev); struct ishtp_cl_driver *driver = to_ishtp_cl_driver(dev->driver); @@ -267,8 +267,6 @@ static int ishtp_cl_device_remove(struct device *dev) if (driver->remove) driver->remove(device); - - return 0; } /** diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 57bbbaa4e8f7..392c1ac4f819 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -922,7 +922,7 @@ static int vmbus_probe(struct device *child_device) /* * vmbus_remove - Remove a vmbus device */ -static int vmbus_remove(struct device *child_device) +static void vmbus_remove(struct device *child_device) { struct hv_driver *drv; struct hv_device *dev = device_to_hv_device(child_device); @@ -932,11 +932,8 @@ static int vmbus_remove(struct device *child_device) if (drv->remove) drv->remove(dev); } - - return 0; } - /* * vmbus_shutdown - Shutdown a vmbus device */ diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 66eed2dff818..7e753a75d23b 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -95,7 +95,7 @@ out_pm: static void intel_th_device_remove(struct intel_th_device *thdev); -static int intel_th_remove(struct device *dev) +static void intel_th_remove(struct device *dev) { struct intel_th_driver *thdrv = to_intel_th_driver(dev->driver); struct intel_th_device *thdev = to_intel_th_device(dev); @@ -164,8 +164,6 @@ static int intel_th_remove(struct device *dev) pm_runtime_disable(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); - - return 0; } static struct bus_type intel_th_bus = { diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 84f12bf90644..54964fbe3f03 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -601,7 +601,7 @@ put_sync_adapter: return status; } -static int i2c_device_remove(struct device *dev) +static void i2c_device_remove(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); struct i2c_adapter *adap; @@ -631,9 +631,6 @@ static int i2c_device_remove(struct device *dev) client->irq = 0; if (client->flags & I2C_CLIENT_HOST_NOTIFY) pm_runtime_put(&client->adapter->dev); - - /* return always 0 because there is WIP to make remove-functions void */ - return 0; } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index e2e12a5585e5..c3b4c677b442 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -322,7 +322,7 @@ static int i3c_device_probe(struct device *dev) return driver->probe(i3cdev); } -static int i3c_device_remove(struct device *dev) +static void i3c_device_remove(struct device *dev) { struct i3c_device *i3cdev = dev_to_i3cdev(dev); struct i3c_driver *driver = drv_to_i3cdrv(dev->driver); @@ -331,8 +331,6 @@ static int i3c_device_remove(struct device *dev) driver->remove(i3cdev); i3c_device_free_ibi(i3cdev); - - return 0; } struct bus_type i3c_bus_type = { diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c index 61fa7e724172..db58a01b23d3 100644 --- a/drivers/input/gameport/gameport.c +++ b/drivers/input/gameport/gameport.c @@ -697,13 +697,12 @@ static int gameport_driver_probe(struct device *dev) return gameport->drv ? 0 : -ENODEV; } -static int gameport_driver_remove(struct device *dev) +static void gameport_driver_remove(struct device *dev) { struct gameport *gameport = to_gameport_port(dev); struct gameport_driver *drv = to_gameport_driver(dev->driver); drv->disconnect(gameport); - return 0; } static void gameport_attach_driver(struct gameport_driver *drv) diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c index 29f491082926..ec117be3d8d8 100644 --- a/drivers/input/serio/serio.c +++ b/drivers/input/serio/serio.c @@ -778,12 +778,11 @@ static int serio_driver_probe(struct device *dev) return serio_connect_driver(serio, drv); } -static int serio_driver_remove(struct device *dev) +static void serio_driver_remove(struct device *dev) { struct serio *serio = to_serio_port(dev); serio_disconnect_driver(serio); - return 0; } static void serio_cleanup(struct serio *serio) diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c index 7de9605cac4f..b1c3198355e7 100644 --- a/drivers/ipack/ipack.c +++ b/drivers/ipack/ipack.c @@ -67,15 +67,13 @@ static int ipack_bus_probe(struct device *device) return drv->ops->probe(dev); } -static int ipack_bus_remove(struct device *device) +static void ipack_bus_remove(struct device *device) { struct ipack_device *dev = to_ipack_dev(device); struct ipack_driver *drv = to_ipack_driver(device->driver); if (drv->ops->remove) drv->ops->remove(dev); - - return 0; } static int ipack_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 49af60bdac92..c1fdf2896021 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -88,7 +88,7 @@ static int macio_device_probe(struct device *dev) return error; } -static int macio_device_remove(struct device *dev) +static void macio_device_remove(struct device *dev) { struct macio_dev * macio_dev = to_macio_device(dev); struct macio_driver * drv = to_macio_driver(dev->driver); @@ -96,8 +96,6 @@ static int macio_device_remove(struct device *dev) if (dev->driver && drv->remove) drv->remove(macio_dev); macio_dev_put(macio_dev); - - return 0; } static void macio_device_shutdown(struct device *dev) diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c index 38fbb3b59873..edf4ee6eff25 100644 --- a/drivers/mcb/mcb-core.c +++ b/drivers/mcb/mcb-core.c @@ -77,7 +77,7 @@ static int mcb_probe(struct device *dev) return ret; } -static int mcb_remove(struct device *dev) +static void mcb_remove(struct device *dev) { struct mcb_driver *mdrv = to_mcb_driver(dev->driver); struct mcb_device *mdev = to_mcb_device(dev); @@ -89,8 +89,6 @@ static int mcb_remove(struct device *dev) module_put(carrier_mod); put_device(&mdev->dev); - - return 0; } static void mcb_shutdown(struct device *dev) diff --git a/drivers/media/pci/bt8xx/bttv-gpio.c b/drivers/media/pci/bt8xx/bttv-gpio.c index b730225ca887..a2b18e2bed1b 100644 --- a/drivers/media/pci/bt8xx/bttv-gpio.c +++ b/drivers/media/pci/bt8xx/bttv-gpio.c @@ -46,14 +46,13 @@ static int bttv_sub_probe(struct device *dev) return sub->probe ? sub->probe(sdev) : -ENODEV; } -static int bttv_sub_remove(struct device *dev) +static void bttv_sub_remove(struct device *dev) { struct bttv_sub_device *sdev = to_bttv_sub_dev(dev); struct bttv_sub_driver *sub = to_bttv_sub_drv(dev->driver); if (sub->remove) sub->remove(sdev); - return 0; } struct bus_type bttv_sub_bus_type = { diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index bb1065990aeb..660df7d269fa 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -91,7 +91,7 @@ static int memstick_device_probe(struct device *dev) return rc; } -static int memstick_device_remove(struct device *dev) +static void memstick_device_remove(struct device *dev) { struct memstick_dev *card = container_of(dev, struct memstick_dev, dev); @@ -105,7 +105,6 @@ static int memstick_device_remove(struct device *dev) } put_device(dev); - return 0; } #ifdef CONFIG_PM diff --git a/drivers/mfd/mcp-core.c b/drivers/mfd/mcp-core.c index eff9423e90f5..2fa592c37c6f 100644 --- a/drivers/mfd/mcp-core.c +++ b/drivers/mfd/mcp-core.c @@ -33,13 +33,12 @@ static int mcp_bus_probe(struct device *dev) return drv->probe(mcp); } -static int mcp_bus_remove(struct device *dev) +static void mcp_bus_remove(struct device *dev) { struct mcp *mcp = to_mcp(dev); struct mcp_driver *drv = to_mcp_driver(dev->driver); drv->remove(mcp); - return 0; } static struct bus_type mcp_bus_type = { diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 935acc6bbf3c..3bf2bb4fd152 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -884,7 +884,7 @@ static int mei_cl_device_probe(struct device *dev) * * Return: 0 on success; < 0 otherwise */ -static int mei_cl_device_remove(struct device *dev) +static void mei_cl_device_remove(struct device *dev) { struct mei_cl_device *cldev = to_mei_cl_device(dev); struct mei_cl_driver *cldrv = to_mei_cl_driver(dev->driver); @@ -896,8 +896,6 @@ static int mei_cl_device_remove(struct device *dev) mei_cl_bus_module_put(cldev); module_put(THIS_MODULE); - - return 0; } static ssize_t name_show(struct device *dev, struct device_attribute *a, diff --git a/drivers/misc/tifm_core.c b/drivers/misc/tifm_core.c index 667e574a7df2..52656fc87e99 100644 --- a/drivers/misc/tifm_core.c +++ b/drivers/misc/tifm_core.c @@ -87,7 +87,7 @@ static void tifm_dummy_event(struct tifm_dev *sock) return; } -static int tifm_device_remove(struct device *dev) +static void tifm_device_remove(struct device *dev) { struct tifm_dev *sock = container_of(dev, struct tifm_dev, dev); struct tifm_driver *drv = container_of(dev->driver, struct tifm_driver, @@ -101,7 +101,6 @@ static int tifm_device_remove(struct device *dev) } put_device(dev); - return 0; } #ifdef CONFIG_PM diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c index 4383c262b3f5..f6b7a9c5bbff 100644 --- a/drivers/mmc/core/bus.c +++ b/drivers/mmc/core/bus.c @@ -140,14 +140,12 @@ static int mmc_bus_probe(struct device *dev) return drv->probe(card); } -static int mmc_bus_remove(struct device *dev) +static void mmc_bus_remove(struct device *dev) { struct mmc_driver *drv = to_mmc_driver(dev->driver); struct mmc_card *card = mmc_dev_to_card(dev); drv->remove(card); - - return 0; } static void mmc_bus_shutdown(struct device *dev) diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index 3d709029e07c..fda03b35c14a 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -203,7 +203,7 @@ disable_runtimepm: return ret; } -static int sdio_bus_remove(struct device *dev) +static void sdio_bus_remove(struct device *dev) { struct sdio_driver *drv = to_sdio_driver(dev->driver); struct sdio_func *func = dev_to_sdio_func(dev); @@ -232,8 +232,6 @@ static int sdio_bus_remove(struct device *dev) pm_runtime_put_sync(dev); dev_pm_domain_detach(dev, false); - - return 0; } static const struct dev_pm_ops sdio_bus_pm_ops = { diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index ccec29970d5b..14b154929533 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -370,12 +370,11 @@ static int nsim_bus_probe(struct device *dev) return nsim_dev_probe(nsim_bus_dev); } -static int nsim_bus_remove(struct device *dev) +static void nsim_bus_remove(struct device *dev) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); nsim_dev_remove(nsim_bus_dev); - return 0; } static int nsim_num_vf(struct device *dev) diff --git a/drivers/ntb/core.c b/drivers/ntb/core.c index f8f75a504a58..27dd93deff6e 100644 --- a/drivers/ntb/core.c +++ b/drivers/ntb/core.c @@ -271,7 +271,7 @@ static int ntb_probe(struct device *dev) return rc; } -static int ntb_remove(struct device *dev) +static void ntb_remove(struct device *dev) { struct ntb_dev *ntb; struct ntb_client *client; @@ -283,8 +283,6 @@ static int ntb_remove(struct device *dev) client->ops.remove(client, ntb); put_device(dev); } - - return 0; } static void ntb_dev_release(struct device *dev) diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 4a02561cfb96..a9b97ebc71ac 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -304,7 +304,7 @@ static int ntb_transport_bus_probe(struct device *dev) return rc; } -static int ntb_transport_bus_remove(struct device *dev) +static void ntb_transport_bus_remove(struct device *dev) { const struct ntb_transport_client *client; @@ -312,8 +312,6 @@ static int ntb_transport_bus_remove(struct device *dev) client->remove(dev); put_device(dev); - - return 0; } static struct bus_type ntb_transport_bus = { diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c index ad3d17c42e23..d9d04f27f89b 100644 --- a/drivers/nubus/bus.c +++ b/drivers/nubus/bus.c @@ -29,14 +29,12 @@ static int nubus_device_probe(struct device *dev) return err; } -static int nubus_device_remove(struct device *dev) +static void nubus_device_remove(struct device *dev) { struct nubus_driver *ndrv = to_nubus_driver(dev->driver); - int err = -ENODEV; if (dev->driver && ndrv->remove) - err = ndrv->remove(to_nubus_board(dev)); - return err; + ndrv->remove(to_nubus_board(dev)); } struct bus_type nubus_bus_type = { diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index e6aa87043a95..9dc7f3edd42b 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -108,7 +108,7 @@ static int nvdimm_bus_probe(struct device *dev) return rc; } -static int nvdimm_bus_remove(struct device *dev) +static void nvdimm_bus_remove(struct device *dev) { struct nd_device_driver *nd_drv = to_nd_device_driver(dev->driver); struct module *provider = to_bus_provider(dev); @@ -123,7 +123,6 @@ static int nvdimm_bus_remove(struct device *dev) dev_dbg(&nvdimm_bus->dev, "%s.remove(%s)\n", dev->driver->name, dev_name(dev)); module_put(provider); - return 0; } static void nvdimm_bus_shutdown(struct device *dev) diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 4b9ad96bf1b2..502eb79cd551 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -387,7 +387,7 @@ static int pci_epf_device_probe(struct device *dev) return driver->probe(epf); } -static int pci_epf_device_remove(struct device *dev) +static void pci_epf_device_remove(struct device *dev) { struct pci_epf *epf = to_pci_epf(dev); struct pci_epf_driver *driver = to_pci_epf_driver(dev->driver); @@ -395,8 +395,6 @@ static int pci_epf_device_remove(struct device *dev) if (driver->remove) driver->remove(epf); epf->driver = NULL; - - return 0; } static struct bus_type pci_epf_bus_type = { diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 3a72352aa5cf..a0615395500a 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -440,7 +440,7 @@ static int pci_device_probe(struct device *dev) return error; } -static int pci_device_remove(struct device *dev) +static void pci_device_remove(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct pci_driver *drv = pci_dev->driver; @@ -476,7 +476,6 @@ static int pci_device_remove(struct device *dev) */ pci_dev_put(pci_dev); - return 0; } static void pci_device_shutdown(struct device *dev) diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c index bd81aa64d011..5bd1b80424e7 100644 --- a/drivers/pcmcia/ds.c +++ b/drivers/pcmcia/ds.c @@ -350,7 +350,7 @@ static void pcmcia_card_remove(struct pcmcia_socket *s, struct pcmcia_device *le return; } -static int pcmcia_device_remove(struct device *dev) +static void pcmcia_device_remove(struct device *dev) { struct pcmcia_device *p_dev; struct pcmcia_driver *p_drv; @@ -389,8 +389,6 @@ static int pcmcia_device_remove(struct device *dev) /* references from pcmcia_device_probe */ pcmcia_put_dev(p_dev); module_put(p_drv->owner); - - return 0; } diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c index 0169677c243e..0a40dd9c94ed 100644 --- a/drivers/platform/surface/aggregator/bus.c +++ b/drivers/platform/surface/aggregator/bus.c @@ -316,14 +316,12 @@ static int ssam_bus_probe(struct device *dev) ->probe(to_ssam_device(dev)); } -static int ssam_bus_remove(struct device *dev) +static void ssam_bus_remove(struct device *dev) { struct ssam_device_driver *sdrv = to_ssam_device_driver(dev->driver); if (sdrv->remove) sdrv->remove(to_ssam_device(dev)); - - return 0; } struct bus_type ssam_bus_type = { diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 62e0d56a3332..a76313006bdc 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -980,7 +980,7 @@ probe_failure: return ret; } -static int wmi_dev_remove(struct device *dev) +static void wmi_dev_remove(struct device *dev) { struct wmi_block *wblock = dev_to_wblock(dev); struct wmi_driver *wdriver = @@ -997,8 +997,6 @@ static int wmi_dev_remove(struct device *dev) if (ACPI_FAILURE(wmi_method_enable(wblock, 0))) dev_warn(dev, "failed to disable device\n"); - - return 0; } static struct class wmi_bus_class = { diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c index c29d590c5e4f..cc6757dfa3f1 100644 --- a/drivers/pnp/driver.c +++ b/drivers/pnp/driver.c @@ -123,7 +123,7 @@ fail: return error; } -static int pnp_device_remove(struct device *dev) +static void pnp_device_remove(struct device *dev) { struct pnp_dev *pnp_dev = to_pnp_dev(dev); struct pnp_driver *drv = pnp_dev->driver; @@ -139,7 +139,6 @@ static int pnp_device_remove(struct device *dev) pnp_disable_dev(pnp_dev); pnp_device_detach(pnp_dev); - return 0; } static void pnp_device_shutdown(struct device *dev) diff --git a/drivers/rapidio/rio-driver.c b/drivers/rapidio/rio-driver.c index 72874153972e..a72bb0a40fcf 100644 --- a/drivers/rapidio/rio-driver.c +++ b/drivers/rapidio/rio-driver.c @@ -112,7 +112,7 @@ static int rio_device_probe(struct device *dev) * driver, then run the driver remove() method. Then update * the reference count. */ -static int rio_device_remove(struct device *dev) +static void rio_device_remove(struct device *dev) { struct rio_dev *rdev = to_rio_dev(dev); struct rio_driver *rdrv = rdev->driver; @@ -124,8 +124,6 @@ static int rio_device_remove(struct device *dev) } rio_dev_put(rdev); - - return 0; } static void rio_device_shutdown(struct device *dev) diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index c1404d3dae2c..9151836190ce 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -530,14 +530,13 @@ out: return err; } -static int rpmsg_dev_remove(struct device *dev) +static void rpmsg_dev_remove(struct device *dev) { struct rpmsg_device *rpdev = to_rpmsg_device(dev); struct rpmsg_driver *rpdrv = to_rpmsg_driver(rpdev->dev.driver); - int err = 0; if (rpdev->ops->announce_destroy) - err = rpdev->ops->announce_destroy(rpdev); + rpdev->ops->announce_destroy(rpdev); if (rpdrv->remove) rpdrv->remove(rpdev); @@ -546,8 +545,6 @@ static int rpmsg_dev_remove(struct device *dev) if (rpdev->ept) rpmsg_destroy_ept(rpdev->ept); - - return err; } static struct bus_type rpmsg_bus = { diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index a6aeab1ea0ae..382c5b5f8cd3 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -439,15 +439,13 @@ module_exit(cleanup_ccwgroup); /************************** driver stuff ******************************/ -static int ccwgroup_remove(struct device *dev) +static void ccwgroup_remove(struct device *dev) { struct ccwgroup_device *gdev = to_ccwgroupdev(dev); struct ccwgroup_driver *gdrv = to_ccwgroupdrv(dev->driver); if (gdrv->remove) gdrv->remove(gdev); - - return 0; } static void ccwgroup_shutdown(struct device *dev) diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 092fd1ea5799..ebc321edba51 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1371,7 +1371,7 @@ static int css_probe(struct device *dev) return ret; } -static int css_remove(struct device *dev) +static void css_remove(struct device *dev) { struct subchannel *sch; @@ -1379,8 +1379,6 @@ static int css_remove(struct device *dev) if (sch->driver->remove) sch->driver->remove(sch); sch->driver = NULL; - - return 0; } static void css_shutdown(struct device *dev) diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index cd5d2d4d8e46..adf33b653d87 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1741,7 +1741,7 @@ ccw_device_probe (struct device *dev) return 0; } -static int ccw_device_remove(struct device *dev) +static void ccw_device_remove(struct device *dev) { struct ccw_device *cdev = to_ccwdev(dev); struct ccw_driver *cdrv = cdev->drv; @@ -1775,8 +1775,6 @@ static int ccw_device_remove(struct device *dev) spin_unlock_irq(cdev->ccwlock); io_subchannel_quiesce(sch); __disable_cmf(cdev); - - return 0; } static void ccw_device_shutdown(struct device *dev) diff --git a/drivers/s390/cio/scm.c b/drivers/s390/cio/scm.c index b31711307e5a..b6b4589c70bd 100644 --- a/drivers/s390/cio/scm.c +++ b/drivers/s390/cio/scm.c @@ -28,15 +28,13 @@ static int scmdev_probe(struct device *dev) return scmdrv->probe ? scmdrv->probe(scmdev) : -ENODEV; } -static int scmdev_remove(struct device *dev) +static void scmdev_remove(struct device *dev) { struct scm_device *scmdev = to_scm_dev(dev); struct scm_driver *scmdrv = to_scm_drv(dev->driver); if (scmdrv->remove) scmdrv->remove(scmdev); - - return 0; } static int scmdev_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 8d3a1d84a757..0992edcaf1af 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -901,7 +901,7 @@ out: return rc; } -static int ap_device_remove(struct device *dev) +static void ap_device_remove(struct device *dev) { struct ap_device *ap_dev = to_ap_dev(dev); struct ap_driver *ap_drv = ap_dev->drv; @@ -926,8 +926,6 @@ static int ap_device_remove(struct device *dev) ap_dev->drv = NULL; put_device(dev); - - return 0; } struct ap_queue *ap_get_qdev(ap_qid_t qid) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 5b3a20a140f9..58f69366bdcc 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -7674,7 +7674,7 @@ static int sdebug_driver_probe(struct device *dev) return error; } -static int sdebug_driver_remove(struct device *dev) +static void sdebug_driver_remove(struct device *dev) { struct sdebug_host_info *sdbg_host; struct sdebug_dev_info *sdbg_devinfo, *tmp; @@ -7691,7 +7691,6 @@ static int sdebug_driver_remove(struct device *dev) } scsi_host_put(sdbg_host->shost); - return 0; } static int pseudo_lld_bus_match(struct device *dev, diff --git a/drivers/sh/superhyway/superhyway.c b/drivers/sh/superhyway/superhyway.c index 348836b90605..c0ab904c76ec 100644 --- a/drivers/sh/superhyway/superhyway.c +++ b/drivers/sh/superhyway/superhyway.c @@ -150,17 +150,13 @@ static int superhyway_device_probe(struct device *dev) return -ENODEV; } -static int superhyway_device_remove(struct device *dev) +static void superhyway_device_remove(struct device *dev) { struct superhyway_device *shyway_dev = to_superhyway_device(dev); struct superhyway_driver *shyway_drv = to_superhyway_driver(dev->driver); - if (shyway_drv && shyway_drv->remove) { + if (shyway_drv && shyway_drv->remove) shyway_drv->remove(shyway_dev); - return 0; - } - - return -ENODEV; } /** diff --git a/drivers/siox/siox-core.c b/drivers/siox/siox-core.c index 1794ff0106bc..7c4f32d76966 100644 --- a/drivers/siox/siox-core.c +++ b/drivers/siox/siox-core.c @@ -520,7 +520,7 @@ static int siox_probe(struct device *dev) return sdriver->probe(sdevice); } -static int siox_remove(struct device *dev) +static void siox_remove(struct device *dev) { struct siox_driver *sdriver = container_of(dev->driver, struct siox_driver, driver); @@ -528,8 +528,6 @@ static int siox_remove(struct device *dev) if (sdriver->remove) sdriver->remove(sdevice); - - return 0; } static void siox_shutdown(struct device *dev) diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index 1d2bc181da05..78480e332ab8 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -81,7 +81,7 @@ static int slim_device_probe(struct device *dev) return ret; } -static int slim_device_remove(struct device *dev) +static void slim_device_remove(struct device *dev) { struct slim_device *sbdev = to_slim_device(dev); struct slim_driver *sbdrv; @@ -91,8 +91,6 @@ static int slim_device_remove(struct device *dev) if (sbdrv->remove) sbdrv->remove(sbdev); } - - return 0; } static int slim_device_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index 7abfc8c4fdc7..475a57b435b2 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -217,7 +217,7 @@ static int apr_device_probe(struct device *dev) return adrv->probe(adev); } -static int apr_device_remove(struct device *dev) +static void apr_device_remove(struct device *dev) { struct apr_device *adev = to_apr_device(dev); struct apr_driver *adrv; @@ -231,8 +231,6 @@ static int apr_device_remove(struct device *dev) idr_remove(&apr->svcs_idr, adev->svc_id); spin_unlock(&apr->svcs_lock); } - - return 0; } static int apr_uevent(struct device *dev, struct kobj_uevent_env *env) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c99181165321..ad2b558dc9cb 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -405,7 +405,7 @@ static int spi_probe(struct device *dev) return ret; } -static int spi_remove(struct device *dev) +static void spi_remove(struct device *dev) { const struct spi_driver *sdrv = to_spi_driver(dev->driver); @@ -420,8 +420,6 @@ static int spi_remove(struct device *dev) } dev_pm_domain_detach(dev, true); - - return 0; } static void spi_shutdown(struct device *dev) diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c index 51f5aeb65b3b..b37ead9e2fad 100644 --- a/drivers/spmi/spmi.c +++ b/drivers/spmi/spmi.c @@ -345,7 +345,7 @@ fail_probe: return err; } -static int spmi_drv_remove(struct device *dev) +static void spmi_drv_remove(struct device *dev) { const struct spmi_driver *sdrv = to_spmi_driver(dev->driver); @@ -356,7 +356,6 @@ static int spmi_drv_remove(struct device *dev) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); pm_runtime_put_noidle(dev); - return 0; } static void spmi_drv_shutdown(struct device *dev) diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index 3a29b5570f9f..8a93c83cb6f8 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -283,7 +283,7 @@ static void ssb_device_shutdown(struct device *dev) ssb_drv->shutdown(ssb_dev); } -static int ssb_device_remove(struct device *dev) +static void ssb_device_remove(struct device *dev) { struct ssb_device *ssb_dev = dev_to_ssb_dev(dev); struct ssb_driver *ssb_drv = drv_to_ssb_drv(dev->driver); @@ -291,8 +291,6 @@ static int ssb_device_remove(struct device *dev) if (ssb_drv && ssb_drv->remove) ssb_drv->remove(ssb_dev); ssb_device_put(ssb_dev); - - return 0; } static int ssb_device_probe(struct device *dev) diff --git a/drivers/staging/fieldbus/anybuss/host.c b/drivers/staging/fieldbus/anybuss/host.c index 0f730efe9a6d..8a75f6642c78 100644 --- a/drivers/staging/fieldbus/anybuss/host.c +++ b/drivers/staging/fieldbus/anybuss/host.c @@ -1186,15 +1186,13 @@ static int anybus_bus_probe(struct device *dev) return adrv->probe(adev); } -static int anybus_bus_remove(struct device *dev) +static void anybus_bus_remove(struct device *dev) { struct anybuss_client_driver *adrv = to_anybuss_client_driver(dev->driver); if (adrv->remove) adrv->remove(to_anybuss_client(dev)); - - return 0; } static struct bus_type anybus_bus = { diff --git a/drivers/staging/greybus/gbphy.c b/drivers/staging/greybus/gbphy.c index 13d319860da5..5a5c17a4519b 100644 --- a/drivers/staging/greybus/gbphy.c +++ b/drivers/staging/greybus/gbphy.c @@ -169,7 +169,7 @@ static int gbphy_dev_probe(struct device *dev) return ret; } -static int gbphy_dev_remove(struct device *dev) +static void gbphy_dev_remove(struct device *dev) { struct gbphy_driver *gbphy_drv = to_gbphy_driver(dev->driver); struct gbphy_device *gbphy_dev = to_gbphy_dev(dev); @@ -180,8 +180,6 @@ static int gbphy_dev_remove(struct device *dev) pm_runtime_set_suspended(dev); pm_runtime_put_noidle(dev); pm_runtime_dont_use_autosuspend(dev); - - return 0; } static struct bus_type gbphy_bus_type = { diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 6d0b0e67e79e..cbb2118fb35e 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -81,7 +81,7 @@ static int tcm_loop_show_info(struct seq_file *m, struct Scsi_Host *host) } static int tcm_loop_driver_probe(struct device *); -static int tcm_loop_driver_remove(struct device *); +static void tcm_loop_driver_remove(struct device *); static int pseudo_lld_bus_match(struct device *dev, struct device_driver *dev_driver) @@ -363,7 +363,7 @@ static int tcm_loop_driver_probe(struct device *dev) return 0; } -static int tcm_loop_driver_remove(struct device *dev) +static void tcm_loop_driver_remove(struct device *dev) { struct tcm_loop_hba *tl_hba; struct Scsi_Host *sh; @@ -373,7 +373,6 @@ static int tcm_loop_driver_remove(struct device *dev) scsi_remove_host(sh); scsi_host_put(sh); - return 0; } static void tcm_loop_release_adapter(struct device *dev) diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c index a062befcb3b2..7018d959f775 100644 --- a/drivers/thunderbolt/domain.c +++ b/drivers/thunderbolt/domain.c @@ -86,7 +86,7 @@ static int tb_service_probe(struct device *dev) return driver->probe(svc, id); } -static int tb_service_remove(struct device *dev) +static void tb_service_remove(struct device *dev) { struct tb_service *svc = tb_to_service(dev); struct tb_service_driver *driver; @@ -94,8 +94,6 @@ static int tb_service_remove(struct device *dev) driver = container_of(dev->driver, struct tb_service_driver, driver); if (driver->remove) driver->remove(svc); - - return 0; } static void tb_service_shutdown(struct device *dev) diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index 9cdfcfe07e87..92498961fd92 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -421,15 +421,13 @@ static int serdev_drv_probe(struct device *dev) return ret; } -static int serdev_drv_remove(struct device *dev) +static void serdev_drv_remove(struct device *dev) { const struct serdev_device_driver *sdrv = to_serdev_device_driver(dev->driver); if (sdrv->remove) sdrv->remove(to_serdev_device(dev)); dev_pm_domain_detach(dev, true); - - return 0; } static struct bus_type serdev_bus_type = { diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 7e13b74e60e5..4169cf40a03b 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -78,14 +78,12 @@ static int ulpi_probe(struct device *dev) return drv->probe(to_ulpi_dev(dev)); } -static int ulpi_remove(struct device *dev) +static void ulpi_remove(struct device *dev) { struct ulpi_driver *drv = to_ulpi_driver(dev->driver); if (drv->remove) drv->remove(to_ulpi_dev(dev)); - - return 0; } static struct bus_type ulpi_bus = { diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c index 7133818a58b9..9e38142acd38 100644 --- a/drivers/usb/serial/bus.c +++ b/drivers/usb/serial/bus.c @@ -74,7 +74,7 @@ err_autopm_put: return retval; } -static int usb_serial_device_remove(struct device *dev) +static void usb_serial_device_remove(struct device *dev) { struct usb_serial_port *port = to_usb_serial_port(dev); struct usb_serial_driver *driver; @@ -101,8 +101,6 @@ static int usb_serial_device_remove(struct device *dev) if (!autopm_err) usb_autopm_put_interface(port->serial->interface); - - return 0; } static ssize_t new_id_store(struct device_driver *driver, diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index 7f3c9a8e2bf0..78e0e78954f2 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -382,7 +382,7 @@ static int typec_probe(struct device *dev) return ret; } -static int typec_remove(struct device *dev) +static void typec_remove(struct device *dev) { struct typec_altmode_driver *drv = to_altmode_driver(dev->driver); struct typec_altmode *adev = to_typec_altmode(dev); @@ -400,8 +400,6 @@ static int typec_remove(struct device *dev) adev->desc = NULL; adev->ops = NULL; - - return 0; } struct bus_type typec_bus = { diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index bb3f1d1f0422..3fc4525fc05c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -34,15 +34,13 @@ static int vdpa_dev_probe(struct device *d) return ret; } -static int vdpa_dev_remove(struct device *d) +static void vdpa_dev_remove(struct device *d) { struct vdpa_device *vdev = dev_to_vdpa(d); struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver); if (drv && drv->remove) drv->remove(vdev); - - return 0; } static struct bus_type vdpa_bus = { diff --git a/drivers/vfio/mdev/mdev_driver.c b/drivers/vfio/mdev/mdev_driver.c index c368ec824e2b..e2cb1ff56f6c 100644 --- a/drivers/vfio/mdev/mdev_driver.c +++ b/drivers/vfio/mdev/mdev_driver.c @@ -57,7 +57,7 @@ static int mdev_probe(struct device *dev) return ret; } -static int mdev_remove(struct device *dev) +static void mdev_remove(struct device *dev) { struct mdev_driver *drv = container_of(dev->driver, struct mdev_driver, driver); @@ -67,8 +67,6 @@ static int mdev_remove(struct device *dev) drv->remove(mdev); mdev_detach_iommu(mdev); - - return 0; } static int mdev_match(struct device *dev, struct device_driver *drv) diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 4b15c00c0a0a..2a6055c0d4d3 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -278,7 +278,7 @@ err: } -static int virtio_dev_remove(struct device *_d) +static void virtio_dev_remove(struct device *_d) { struct virtio_device *dev = dev_to_virtio(_d); struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); @@ -292,7 +292,6 @@ static int virtio_dev_remove(struct device *_d) /* Acknowledge the device's existence again. */ virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); - return 0; } static struct bus_type virtio_bus = { diff --git a/drivers/vlynq/vlynq.c b/drivers/vlynq/vlynq.c index e966981c0215..4af6615808cc 100644 --- a/drivers/vlynq/vlynq.c +++ b/drivers/vlynq/vlynq.c @@ -342,14 +342,12 @@ static int vlynq_device_probe(struct device *dev) return result; } -static int vlynq_device_remove(struct device *dev) +static void vlynq_device_remove(struct device *dev) { struct vlynq_driver *drv = to_vlynq_driver(dev->driver); if (drv->remove) drv->remove(to_vlynq_device(dev)); - - return 0; } int __vlynq_register_driver(struct vlynq_driver *driver, struct module *owner) diff --git a/drivers/vme/vme.c b/drivers/vme/vme.c index 1b15afea28ee..8dba20186be3 100644 --- a/drivers/vme/vme.c +++ b/drivers/vme/vme.c @@ -1990,7 +1990,7 @@ static int vme_bus_probe(struct device *dev) return -ENODEV; } -static int vme_bus_remove(struct device *dev) +static void vme_bus_remove(struct device *dev) { struct vme_driver *driver; struct vme_dev *vdev = dev_to_vme_dev(dev); @@ -1998,8 +1998,6 @@ static int vme_bus_remove(struct device *dev) driver = dev->platform_data; if (driver->remove) driver->remove(vdev); - - return 0; } struct bus_type vme_bus_type = { diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 2a93b7c9c159..2754bdfadcb8 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -106,7 +106,7 @@ void xs_request_exit(struct xb_req_data *req); int xenbus_match(struct device *_dev, struct device_driver *_drv); int xenbus_dev_probe(struct device *_dev); -int xenbus_dev_remove(struct device *_dev); +void xenbus_dev_remove(struct device *_dev); int xenbus_register_driver_common(struct xenbus_driver *drv, struct xen_bus_type *bus, struct module *owner, diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 33d09b3f6211..bd003ca8acbe 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -325,7 +325,7 @@ fail: } EXPORT_SYMBOL_GPL(xenbus_dev_probe); -int xenbus_dev_remove(struct device *_dev) +void xenbus_dev_remove(struct device *_dev) { struct xenbus_device *dev = to_xenbus_device(_dev); struct xenbus_driver *drv = to_xenbus_driver(_dev->driver); @@ -355,8 +355,6 @@ int xenbus_dev_remove(struct device *_dev) if (!drv->allow_rebind || xenbus_read_driver_state(dev->nodename) == XenbusStateClosing) xenbus_switch_state(dev, XenbusStateClosed); - - return 0; } EXPORT_SYMBOL_GPL(xenbus_dev_remove); diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c index 0dd7cbcec2b0..c18524bb8b2a 100644 --- a/drivers/zorro/zorro-driver.c +++ b/drivers/zorro/zorro-driver.c @@ -62,7 +62,7 @@ static int zorro_device_probe(struct device *dev) } -static int zorro_device_remove(struct device *dev) +static void zorro_device_remove(struct device *dev) { struct zorro_dev *z = to_zorro_dev(dev); struct zorro_driver *drv = to_zorro_driver(dev->driver); @@ -72,7 +72,6 @@ static int zorro_device_remove(struct device *dev) drv->remove(z); z->driver = NULL; } - return 0; } diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 1ea5e1d1545b..062777a45a74 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -91,7 +91,7 @@ struct bus_type { int (*uevent)(struct device *dev, struct kobj_uevent_env *env); int (*probe)(struct device *dev); void (*sync_state)(struct device *dev); - int (*remove)(struct device *dev); + void (*remove)(struct device *dev); void (*shutdown)(struct device *dev); int (*online)(struct device *dev); diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c index 6ddf646cda65..0d31a6d71468 100644 --- a/sound/ac97/bus.c +++ b/sound/ac97/bus.c @@ -514,7 +514,7 @@ static int ac97_bus_probe(struct device *dev) return ret; } -static int ac97_bus_remove(struct device *dev) +static void ac97_bus_remove(struct device *dev) { struct ac97_codec_device *adev = to_ac97_device(dev); struct ac97_codec_driver *adrv = to_ac97_driver(dev->driver); @@ -522,7 +522,7 @@ static int ac97_bus_remove(struct device *dev) ret = pm_runtime_resume_and_get(dev); if (ret < 0) - return ret; + return; ret = adrv->remove(adev); pm_runtime_put_noidle(dev); @@ -530,8 +530,6 @@ static int ac97_bus_remove(struct device *dev) ac97_put_disable_clk(adev); pm_runtime_disable(dev); - - return ret; } static struct bus_type ac97_bus_type = { diff --git a/sound/aoa/soundbus/core.c b/sound/aoa/soundbus/core.c index 002fb5bf220b..c9579d97fbab 100644 --- a/sound/aoa/soundbus/core.c +++ b/sound/aoa/soundbus/core.c @@ -104,7 +104,7 @@ static int soundbus_uevent(struct device *dev, struct kobj_uevent_env *env) return retval; } -static int soundbus_device_remove(struct device *dev) +static void soundbus_device_remove(struct device *dev) { struct soundbus_dev * soundbus_dev = to_soundbus_device(dev); struct soundbus_driver * drv = to_soundbus_driver(dev->driver); @@ -112,8 +112,6 @@ static int soundbus_device_remove(struct device *dev) if (dev->driver && drv->remove) drv->remove(soundbus_dev); soundbus_dev_put(soundbus_dev); - - return 0; } static void soundbus_device_shutdown(struct device *dev)