From 06e472acf964649a58b7de35fc9cdc3151acb970 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Fri, 28 Oct 2022 14:46:55 +0530 Subject: [PATCH 001/233] scsi: mpt3sas: Remove usage of dma_get_required_mask() API Remove the usage of dma_get_required_mask() API. Directly set the DMA mask to 63/64 if the system is a 64bit machine. Signed-off-by: Sreekanth Reddy Link: https://lore.kernel.org/r/20221028091655.17741-2-sreekanth.reddy@broadcom.com Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 4e981ccaac41..69061545d9d2 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2992,8 +2992,7 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) struct sysinfo s; u64 coherent_dma_mask, dma_mask; - if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 || - dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) { + if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4) { ioc->dma_mask = 32; coherent_dma_mask = dma_mask = DMA_BIT_MASK(32); /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */ From d347a951906b506c485ee9ffb76fe473b41f3e10 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Fri, 11 Nov 2022 15:52:46 +0530 Subject: [PATCH 002/233] scsi: mpi3mr: Remove usage of dma_get_required_mask() API Remove the usage of dma_get_required_mask() API. Directly set the DMA mask to 63/64 if the system is a 64bit machine. Signed-off-by: Sreekanth Reddy Link: https://lore.kernel.org/r/20221111102246.19995-2-sreekanth.reddy@broadcom.com Signed-off-by: Martin K. Petersen --- drivers/scsi/mpi3mr/mpi3mr_fw.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 0c4aabaefdcc..286a44506578 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -3633,8 +3633,7 @@ int mpi3mr_setup_resources(struct mpi3mr_ioc *mrioc) int i, retval = 0, capb = 0; u16 message_control; u64 dma_mask = mrioc->dma_mask ? mrioc->dma_mask : - (((dma_get_required_mask(&pdev->dev) > DMA_BIT_MASK(32)) && - (sizeof(dma_addr_t) > 4)) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32)); + ((sizeof(dma_addr_t) > 4) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32)); if (pci_enable_device_mem(pdev)) { ioc_err(mrioc, "pci_enable_device_mem: failed\n"); From 02228f6aa6a64d588bc31e3267d05ff184d772eb Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Sun, 27 Nov 2022 22:06:02 +0100 Subject: [PATCH 003/233] regulator: da9211: Use irq handler when ready If the system does not come from reset (like when it is kexec()), the regulator might have an IRQ waiting for us. If we enable the IRQ handler before its structures are ready, we crash. This patch fixes: [ 1.141839] Unable to handle kernel read from unreadable memory at virtual address 0000000000000078 [ 1.316096] Call trace: [ 1.316101] blocking_notifier_call_chain+0x20/0xa8 [ 1.322757] cpu cpu0: dummy supplies not allowed for exclusive requests [ 1.327823] regulator_notifier_call_chain+0x1c/0x2c [ 1.327825] da9211_irq_handler+0x68/0xf8 [ 1.327829] irq_thread+0x11c/0x234 [ 1.327833] kthread+0x13c/0x154 Signed-off-by: Ricardo Ribalda Reviewed-by: Adam Ward Link: https://lore.kernel.org/r/20221124-da9211-v2-0-1779e3c5d491@chromium.org Signed-off-by: Mark Brown --- drivers/regulator/da9211-regulator.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index e01b32d1fa17..00828f5baa97 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -498,6 +498,12 @@ static int da9211_i2c_probe(struct i2c_client *i2c) chip->chip_irq = i2c->irq; + ret = da9211_regulator_init(chip); + if (ret < 0) { + dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); + return ret; + } + if (chip->chip_irq != 0) { ret = devm_request_threaded_irq(chip->dev, chip->chip_irq, NULL, da9211_irq_handler, @@ -512,11 +518,6 @@ static int da9211_i2c_probe(struct i2c_client *i2c) dev_warn(chip->dev, "No IRQ configured\n"); } - ret = da9211_regulator_init(chip); - - if (ret < 0) - dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); - return ret; } From f728a5ea27c92133893590e731ce10f6561ced87 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 6 Dec 2022 14:07:49 +0100 Subject: [PATCH 004/233] dma-buf: fix dma_buf_export init order v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The init order and resulting error handling in dma_buf_export was pretty messy. Subordinate objects like the file and the sysfs kernel objects were initializing and wiring itself up with the object in the wrong order resulting not only in complicating and partially incorrect error handling, but also in publishing only halve initialized DMA-buf objects. Clean this up thoughtfully by allocating the file independent of the DMA-buf object. Then allocate and initialize the DMA-buf object itself, before publishing it through sysfs. If everything works as expected the file is then connected with the DMA-buf object and publish it through debugfs. Also adds the missing dma_resv_fini() into the error handling. v2: add some missing changes to dma_bug_getfile() and a missing NULL check in dma_buf_file_release() Signed-off-by: Christian König Reviewed-by: Michael J. Ruhl Reviewed-by: T.J. Mercier Acked-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20221209071535.933698-1-christian.koenig@amd.com --- drivers/dma-buf/dma-buf-sysfs-stats.c | 7 +- drivers/dma-buf/dma-buf-sysfs-stats.h | 4 +- drivers/dma-buf/dma-buf.c | 94 +++++++++++++-------------- 3 files changed, 48 insertions(+), 57 deletions(-) diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c index 2bba0babcb62..4b680e10c15a 100644 --- a/drivers/dma-buf/dma-buf-sysfs-stats.c +++ b/drivers/dma-buf/dma-buf-sysfs-stats.c @@ -168,14 +168,11 @@ void dma_buf_uninit_sysfs_statistics(void) kset_unregister(dma_buf_stats_kset); } -int dma_buf_stats_setup(struct dma_buf *dmabuf) +int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file) { struct dma_buf_sysfs_entry *sysfs_entry; int ret; - if (!dmabuf || !dmabuf->file) - return -EINVAL; - if (!dmabuf->exp_name) { pr_err("exporter name must not be empty if stats needed\n"); return -EINVAL; @@ -192,7 +189,7 @@ int dma_buf_stats_setup(struct dma_buf *dmabuf) /* create the directory for buffer stats */ ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL, - "%lu", file_inode(dmabuf->file)->i_ino); + "%lu", file_inode(file)->i_ino); if (ret) goto err_sysfs_dmabuf; diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.h b/drivers/dma-buf/dma-buf-sysfs-stats.h index a49c6e2650cc..7a8a995b75ba 100644 --- a/drivers/dma-buf/dma-buf-sysfs-stats.h +++ b/drivers/dma-buf/dma-buf-sysfs-stats.h @@ -13,7 +13,7 @@ int dma_buf_init_sysfs_statistics(void); void dma_buf_uninit_sysfs_statistics(void); -int dma_buf_stats_setup(struct dma_buf *dmabuf); +int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file); void dma_buf_stats_teardown(struct dma_buf *dmabuf); #else @@ -25,7 +25,7 @@ static inline int dma_buf_init_sysfs_statistics(void) static inline void dma_buf_uninit_sysfs_statistics(void) {} -static inline int dma_buf_stats_setup(struct dma_buf *dmabuf) +static inline int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file) { return 0; } diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index e6f36c014c4c..eb6b59363c4f 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -95,10 +95,11 @@ static int dma_buf_file_release(struct inode *inode, struct file *file) return -EINVAL; dmabuf = file->private_data; - - mutex_lock(&db_list.lock); - list_del(&dmabuf->list_node); - mutex_unlock(&db_list.lock); + if (dmabuf) { + mutex_lock(&db_list.lock); + list_del(&dmabuf->list_node); + mutex_unlock(&db_list.lock); + } return 0; } @@ -523,17 +524,17 @@ static inline int is_dma_buf_file(struct file *file) return file->f_op == &dma_buf_fops; } -static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) +static struct file *dma_buf_getfile(size_t size, int flags) { static atomic64_t dmabuf_inode = ATOMIC64_INIT(0); - struct file *file; struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb); + struct file *file; if (IS_ERR(inode)) return ERR_CAST(inode); - inode->i_size = dmabuf->size; - inode_set_bytes(inode, dmabuf->size); + inode->i_size = size; + inode_set_bytes(inode, size); /* * The ->i_ino acquired from get_next_ino() is not unique thus @@ -547,8 +548,6 @@ static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) flags, &dma_buf_fops); if (IS_ERR(file)) goto err_alloc_file; - file->private_data = dmabuf; - file->f_path.dentry->d_fsdata = dmabuf; return file; @@ -614,19 +613,11 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) size_t alloc_size = sizeof(struct dma_buf); int ret; - if (!exp_info->resv) - alloc_size += sizeof(struct dma_resv); - else - /* prevent &dma_buf[1] == dma_buf->resv */ - alloc_size += 1; - - if (WARN_ON(!exp_info->priv - || !exp_info->ops - || !exp_info->ops->map_dma_buf - || !exp_info->ops->unmap_dma_buf - || !exp_info->ops->release)) { + if (WARN_ON(!exp_info->priv || !exp_info->ops + || !exp_info->ops->map_dma_buf + || !exp_info->ops->unmap_dma_buf + || !exp_info->ops->release)) return ERR_PTR(-EINVAL); - } if (WARN_ON(exp_info->ops->cache_sgt_mapping && (exp_info->ops->pin || exp_info->ops->unpin))) @@ -638,10 +629,21 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) if (!try_module_get(exp_info->owner)) return ERR_PTR(-ENOENT); + file = dma_buf_getfile(exp_info->size, exp_info->flags); + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto err_module; + } + + if (!exp_info->resv) + alloc_size += sizeof(struct dma_resv); + else + /* prevent &dma_buf[1] == dma_buf->resv */ + alloc_size += 1; dmabuf = kzalloc(alloc_size, GFP_KERNEL); if (!dmabuf) { ret = -ENOMEM; - goto err_module; + goto err_file; } dmabuf->priv = exp_info->priv; @@ -653,44 +655,36 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) init_waitqueue_head(&dmabuf->poll); dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll; dmabuf->cb_in.active = dmabuf->cb_out.active = 0; - - if (!resv) { - resv = (struct dma_resv *)&dmabuf[1]; - dma_resv_init(resv); - } - dmabuf->resv = resv; - - file = dma_buf_getfile(dmabuf, exp_info->flags); - if (IS_ERR(file)) { - ret = PTR_ERR(file); - goto err_dmabuf; - } - - dmabuf->file = file; - mutex_init(&dmabuf->lock); INIT_LIST_HEAD(&dmabuf->attachments); + if (!resv) { + dmabuf->resv = (struct dma_resv *)&dmabuf[1]; + dma_resv_init(dmabuf->resv); + } else { + dmabuf->resv = resv; + } + + ret = dma_buf_stats_setup(dmabuf, file); + if (ret) + goto err_dmabuf; + + file->private_data = dmabuf; + file->f_path.dentry->d_fsdata = dmabuf; + dmabuf->file = file; + mutex_lock(&db_list.lock); list_add(&dmabuf->list_node, &db_list.head); mutex_unlock(&db_list.lock); - ret = dma_buf_stats_setup(dmabuf); - if (ret) - goto err_sysfs; - return dmabuf; -err_sysfs: - /* - * Set file->f_path.dentry->d_fsdata to NULL so that when - * dma_buf_release() gets invoked by dentry_ops, it exits - * early before calling the release() dma_buf op. - */ - file->f_path.dentry->d_fsdata = NULL; - fput(file); err_dmabuf: + if (!resv) + dma_resv_fini(dmabuf->resv); kfree(dmabuf); +err_file: + fput(file); err_module: module_put(exp_info->owner); return ERR_PTR(ret); From a3be19b91ea7121d388084e8c07f5b1b982eb40c Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Sat, 26 Nov 2022 09:07:52 +0800 Subject: [PATCH 005/233] scsi: iscsi: Fix multiple iSCSI session unbind events sent to userspace It was observed that the kernel would potentially send ISCSI_KEVENT_UNBIND_SESSION multiple times. Introduce 'target_state' in iscsi_cls_session() to make sure session will send only one unbind session event. This introduces a regression wrt. the issue fixed in commit 13e60d3ba287 ("scsi: iscsi: Report unbind session event when the target has been removed"). If iscsid dies for any reason after sending an unbind session to kernel, once iscsid is restarted, the kernel's ISCSI_KEVENT_UNBIND_SESSION event is lost and userspace is then unable to logout. However, the session is actually in invalid state (its target_id is INVALID) so iscsid should not sync this session during restart. Consequently we need to check the session's target state during iscsid restart. If session is in unbound state, do not sync this session and perform session teardown. This is OK because once a session is unbound, we can not recover it any more (mainly because its target id is INVALID). Signed-off-by: Wenchao Hao Link: https://lore.kernel.org/r/20221126010752.231917-1-haowenchao@huawei.com Reviewed-by: Mike Christie Reviewed-by: Wu Bo Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 50 ++++++++++++++++++++++++++--- include/scsi/scsi_transport_iscsi.h | 9 ++++++ 2 files changed, 54 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index c3fe5ecfee59..3eb58db1399d 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -1676,6 +1676,13 @@ static const char *iscsi_session_state_name(int state) return name; } +static char *iscsi_session_target_state_name[] = { + [ISCSI_SESSION_TARGET_UNBOUND] = "UNBOUND", + [ISCSI_SESSION_TARGET_ALLOCATED] = "ALLOCATED", + [ISCSI_SESSION_TARGET_SCANNED] = "SCANNED", + [ISCSI_SESSION_TARGET_UNBINDING] = "UNBINDING", +}; + int iscsi_session_chkready(struct iscsi_cls_session *session) { int err; @@ -1785,9 +1792,13 @@ static int iscsi_user_scan_session(struct device *dev, void *data) if ((scan_data->channel == SCAN_WILD_CARD || scan_data->channel == 0) && (scan_data->id == SCAN_WILD_CARD || - scan_data->id == id)) + scan_data->id == id)) { scsi_scan_target(&session->dev, 0, id, scan_data->lun, scan_data->rescan); + spin_lock_irqsave(&session->lock, flags); + session->target_state = ISCSI_SESSION_TARGET_SCANNED; + spin_unlock_irqrestore(&session->lock, flags); + } } user_scan_exit: @@ -1960,31 +1971,41 @@ static void __iscsi_unbind_session(struct work_struct *work) struct iscsi_cls_host *ihost = shost->shost_data; unsigned long flags; unsigned int target_id; + bool remove_target = true; ISCSI_DBG_TRANS_SESSION(session, "Unbinding session\n"); /* Prevent new scans and make sure scanning is not in progress */ mutex_lock(&ihost->mutex); spin_lock_irqsave(&session->lock, flags); - if (session->target_id == ISCSI_MAX_TARGET) { + if (session->target_state == ISCSI_SESSION_TARGET_ALLOCATED) { + remove_target = false; + } else if (session->target_state != ISCSI_SESSION_TARGET_SCANNED) { spin_unlock_irqrestore(&session->lock, flags); mutex_unlock(&ihost->mutex); - goto unbind_session_exit; + ISCSI_DBG_TRANS_SESSION(session, + "Skipping target unbinding: Session is unbound/unbinding.\n"); + return; } + session->target_state = ISCSI_SESSION_TARGET_UNBINDING; target_id = session->target_id; session->target_id = ISCSI_MAX_TARGET; spin_unlock_irqrestore(&session->lock, flags); mutex_unlock(&ihost->mutex); - scsi_remove_target(&session->dev); + if (remove_target) + scsi_remove_target(&session->dev); if (session->ida_used) ida_free(&iscsi_sess_ida, target_id); -unbind_session_exit: iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION); ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n"); + + spin_lock_irqsave(&session->lock, flags); + session->target_state = ISCSI_SESSION_TARGET_UNBOUND; + spin_unlock_irqrestore(&session->lock, flags); } static void __iscsi_destroy_session(struct work_struct *work) @@ -2061,6 +2082,9 @@ int iscsi_add_session(struct iscsi_cls_session *session, unsigned int target_id) session->ida_used = true; } else session->target_id = target_id; + spin_lock_irqsave(&session->lock, flags); + session->target_state = ISCSI_SESSION_TARGET_ALLOCATED; + spin_unlock_irqrestore(&session->lock, flags); dev_set_name(&session->dev, "session%u", session->sid); err = device_add(&session->dev); @@ -4368,6 +4392,19 @@ iscsi_session_attr(def_taskmgmt_tmo, ISCSI_PARAM_DEF_TASKMGMT_TMO, 0); iscsi_session_attr(discovery_parent_idx, ISCSI_PARAM_DISCOVERY_PARENT_IDX, 0); iscsi_session_attr(discovery_parent_type, ISCSI_PARAM_DISCOVERY_PARENT_TYPE, 0); +static ssize_t +show_priv_session_target_state(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct iscsi_cls_session *session = iscsi_dev_to_session(dev->parent); + + return sysfs_emit(buf, "%s\n", + iscsi_session_target_state_name[session->target_state]); +} + +static ISCSI_CLASS_ATTR(priv_sess, target_state, S_IRUGO, + show_priv_session_target_state, NULL); + static ssize_t show_priv_session_state(struct device *dev, struct device_attribute *attr, char *buf) @@ -4470,6 +4507,7 @@ static struct attribute *iscsi_session_attrs[] = { &dev_attr_sess_boot_target.attr, &dev_attr_priv_sess_recovery_tmo.attr, &dev_attr_priv_sess_state.attr, + &dev_attr_priv_sess_target_state.attr, &dev_attr_priv_sess_creator.attr, &dev_attr_sess_chap_out_idx.attr, &dev_attr_sess_chap_in_idx.attr, @@ -4583,6 +4621,8 @@ static umode_t iscsi_session_attr_is_visible(struct kobject *kobj, return S_IRUGO | S_IWUSR; else if (attr == &dev_attr_priv_sess_state.attr) return S_IRUGO; + else if (attr == &dev_attr_priv_sess_target_state.attr) + return S_IRUGO; else if (attr == &dev_attr_priv_sess_creator.attr) return S_IRUGO; else if (attr == &dev_attr_priv_sess_target_id.attr) diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index cab52b0f11d0..34c03707fb6e 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -236,6 +236,14 @@ enum { ISCSI_SESSION_FREE, }; +enum { + ISCSI_SESSION_TARGET_UNBOUND, + ISCSI_SESSION_TARGET_ALLOCATED, + ISCSI_SESSION_TARGET_SCANNED, + ISCSI_SESSION_TARGET_UNBINDING, + ISCSI_SESSION_TARGET_MAX, +}; + #define ISCSI_MAX_TARGET -1 struct iscsi_cls_session { @@ -264,6 +272,7 @@ struct iscsi_cls_session { */ pid_t creator; int state; + int target_state; /* session target bind state */ int sid; /* session id */ void *dd_data; /* LLD private data */ struct device dev; /* sysfs transport/container device */ From 67ff3d0a49f3d445c3922e30a54e03c161da561e Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 4 Dec 2022 11:52:44 -0800 Subject: [PATCH 006/233] scsi: storvsc: Fix swiotlb bounce buffer leak in confidential VM storvsc_queuecommand() maps the scatter/gather list using scsi_dma_map(), which in a confidential VM allocates swiotlb bounce buffers. If the I/O submission fails in storvsc_do_io(), the I/O is typically retried by higher level code, but the bounce buffer memory is never freed. The mostly like cause of I/O submission failure is a full VMBus channel ring buffer, which is not uncommon under high I/O loads. Eventually enough bounce buffer memory leaks that the confidential VM can't do any I/O. The same problem can arise in a non-confidential VM with kernel boot parameter swiotlb=force. Fix this by doing scsi_dma_unmap() in the case of an I/O submission error, which frees the bounce buffer memory. Fixes: 743b237c3a7b ("scsi: storvsc: Add Isolation VM support for storvsc driver") Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1670183564-76254-1-git-send-email-mikelley@microsoft.com Tested-by: Dexuan Cui Reviewed-by: Dexuan Cui Reviewed-by: Tianyu Lan Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index a84194d82347..0252ee2dd844 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1824,6 +1824,9 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) ret = storvsc_do_io(dev, cmd_request, get_cpu()); put_cpu(); + if (ret) + scsi_dma_unmap(scmnd); + if (ret == -EAGAIN) { /* no more space */ ret = SCSI_MLQUEUE_DEVICE_BUSY; From d0b9025540ef57cc4464ab2fc64ed8ddc49b5658 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 6 Dec 2022 14:13:45 +0100 Subject: [PATCH 007/233] scsi: core: scsi_error: Do not queue pointless abort workqueue functions If a host template doesn't implement the .eh_abort_handler() there is no point in queueing the abort workqueue function; all it does is invoking SCSI EH anyway. So return 'FAILED' from scsi_abort_command() if the .eh_abort_handler() is not implemented and save us from having to wait for the abort workqueue function to complete. Cc: Niklas Cassel Cc: Damien Le Moal Cc: John Garry Signed-off-by: Hannes Reinecke [niklas: moved the check to the top of scsi_abort_command()] Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20221206131346.2045375-1-niklas.cassel@wdc.com Reviewed-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_error.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 613d5aeb1e3c..955ee1bfde8f 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -231,6 +231,11 @@ scsi_abort_command(struct scsi_cmnd *scmd) struct Scsi_Host *shost = sdev->host; unsigned long flags; + if (!shost->hostt->eh_abort_handler) { + /* No abort handler, fail command directly */ + return FAILED; + } + if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) { /* * Retry after abort failed, escalate to next level. From f0a43ba6c66cc0688e2748d986a1459fdd3442ef Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Wed, 7 Dec 2022 11:36:59 +0900 Subject: [PATCH 008/233] scsi: mpi3mr: Refer CONFIG_SCSI_MPI3MR in Makefile When Kconfig item CONFIG_SCSI_MPI3MR was introduced for mpi3mr driver, the Makefile of the driver was not modified to refer the Kconfig item. As a result, mpi3mr.ko is built regardless of the Kconfig item value y or m. Also, if 'make localmodconfig' can not find the Kconfig item in the Makefile, then it does not generate CONFIG_SCSI_MPI3MR=m even when mpi3mr.ko is loaded on the system. Refer to the Kconfig item to avoid the issues. Fixes: c4f7ac64616e ("scsi: mpi3mr: Add mpi30 Rev-R headers and Kconfig") Signed-off-by: Shin'ichiro Kawasaki Link: https://lore.kernel.org/r/20221207023659.2411785-1-shinichiro.kawasaki@wdc.com Reviewed-by: Damien Le Moal Acked-by: Sathya Prakash Veerichetty Signed-off-by: Martin K. Petersen --- drivers/scsi/mpi3mr/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpi3mr/Makefile b/drivers/scsi/mpi3mr/Makefile index ef86ca46646b..3bf8cf34e1c3 100644 --- a/drivers/scsi/mpi3mr/Makefile +++ b/drivers/scsi/mpi3mr/Makefile @@ -1,5 +1,5 @@ # mpi3mr makefile -obj-m += mpi3mr.o +obj-$(CONFIG_SCSI_MPI3MR) += mpi3mr.o mpi3mr-y += mpi3mr_os.o \ mpi3mr_fw.o \ mpi3mr_app.o \ From c411a42fb91f452509c312e4dda713699a22a995 Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 13 Dec 2022 14:21:22 +0000 Subject: [PATCH 009/233] scsi: scsi_debug: Delete unreachable code in inquiry_vpd_b0() The 2nd return statement in inquiry_vpd_b0() is unreachable, so delete it. Signed-off-by: John Garry Link: https://lore.kernel.org/r/20221213142122.1011886-1-john.g.garry@oracle.com Reviewed-by: Jason Yan Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_debug.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index de3d3b1edaf5..6fa08857d6b9 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -1511,8 +1511,6 @@ static int inquiry_vpd_b0(unsigned char *arr) put_unaligned_be64(sdebug_write_same_length, &arr[32]); return 0x3c; /* Mandatory page length for Logical Block Provisioning */ - - return sizeof(vpdb0_data); } /* Block device characteristics VPD page (SBC-3) */ From 1a5665fc8d7a000671ebd3fe69c6f9acf1e0dcd9 Mon Sep 17 00:00:00 2001 From: Peter Wang Date: Thu, 8 Dec 2022 15:25:20 +0800 Subject: [PATCH 010/233] scsi: ufs: core: WLUN suspend SSU/enter hibern8 fail recovery When SSU/enter hibern8 fail in WLUN suspend flow, trigger the error handler and return busy to break the suspend. Otherwise the consumer will get stuck in runtime suspend status. Fixes: b294ff3e3449 ("scsi: ufs: core: Enable power management for wlun") Signed-off-by: Peter Wang Link: https://lore.kernel.org/r/20221208072520.26210-1-peter.wang@mediatek.com Reviewed-by: Stanley Chu Reviewed-by: Bart Van Assche Reviewed-by: Adrian Hunter Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 2dbe24977822..c63cd8bbe5c6 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -6056,6 +6056,14 @@ void ufshcd_schedule_eh_work(struct ufs_hba *hba) } } +static void ufshcd_force_error_recovery(struct ufs_hba *hba) +{ + spin_lock_irq(hba->host->host_lock); + hba->force_reset = true; + ufshcd_schedule_eh_work(hba); + spin_unlock_irq(hba->host->host_lock); +} + static void ufshcd_clk_scaling_allow(struct ufs_hba *hba, bool allow) { down_write(&hba->clk_scaling_lock); @@ -9083,6 +9091,15 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) if (!hba->dev_info.b_rpm_dev_flush_capable) { ret = ufshcd_set_dev_pwr_mode(hba, req_dev_pwr_mode); + if (ret && pm_op != UFS_SHUTDOWN_PM) { + /* + * If return err in suspend flow, IO will hang. + * Trigger error handler and break suspend for + * error recovery. + */ + ufshcd_force_error_recovery(hba); + ret = -EBUSY; + } if (ret) goto enable_scaling; } @@ -9094,6 +9111,15 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) */ check_for_bkops = !ufshcd_is_ufs_dev_deepsleep(hba); ret = ufshcd_link_state_transition(hba, req_link_state, check_for_bkops); + if (ret && pm_op != UFS_SHUTDOWN_PM) { + /* + * If return err in suspend flow, IO will hang. + * Trigger error handler and break suspend for + * error recovery. + */ + ufshcd_force_error_recovery(hba); + ret = -EBUSY; + } if (ret) goto set_dev_active; From 7cffcade57a429667447c4f41d8414bbcf1b3aaa Mon Sep 17 00:00:00 2001 From: Dawei Li Date: Tue, 13 Dec 2022 23:46:52 +0800 Subject: [PATCH 011/233] xen: make remove callback of xen driver void returned Since commit fc7a6209d571 ("bus: Make remove callback return void") forces bus_type::remove be void-returned, it doesn't make much sense for any bus based driver implementing remove callbalk to return non-void to its caller. This change is for xen bus based drivers. Acked-by: Juergen Gross Signed-off-by: Dawei Li Link: https://lore.kernel.org/r/TYCP286MB23238119AB4DF190997075C9CAE39@TYCP286MB2323.JPNP286.PROD.OUTLOOK.COM Signed-off-by: Juergen Gross --- drivers/block/xen-blkback/xenbus.c | 4 +--- drivers/block/xen-blkfront.c | 3 +-- drivers/char/tpm/xen-tpmfront.c | 3 +-- drivers/gpu/drm/xen/xen_drm_front.c | 3 +-- drivers/input/misc/xen-kbdfront.c | 5 ++--- drivers/net/xen-netback/xenbus.c | 3 +-- drivers/net/xen-netfront.c | 4 +--- drivers/pci/xen-pcifront.c | 4 +--- drivers/scsi/xen-scsifront.c | 4 +--- drivers/tty/hvc/hvc_xen.c | 4 ++-- drivers/usb/host/xen-hcd.c | 4 +--- drivers/video/fbdev/xen-fbfront.c | 6 ++---- drivers/xen/pvcalls-back.c | 3 +-- drivers/xen/pvcalls-front.c | 3 +-- drivers/xen/xen-pciback/xenbus.c | 4 +--- drivers/xen/xen-scsiback.c | 4 +--- include/xen/xenbus.h | 2 +- net/9p/trans_xen.c | 3 +-- sound/xen/xen_snd_front.c | 3 +-- 19 files changed, 22 insertions(+), 47 deletions(-) diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index c0227dfa4688..4807af1d5805 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -524,7 +524,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, return 0; } -static int xen_blkbk_remove(struct xenbus_device *dev) +static void xen_blkbk_remove(struct xenbus_device *dev) { struct backend_info *be = dev_get_drvdata(&dev->dev); @@ -547,8 +547,6 @@ static int xen_blkbk_remove(struct xenbus_device *dev) /* Put the reference we set in xen_blkif_alloc(). */ xen_blkif_put(be->blkif); } - - return 0; } int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt, diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 35b9bcad9db9..e68576ded7cb 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2468,7 +2468,7 @@ static void blkback_changed(struct xenbus_device *dev, } } -static int blkfront_remove(struct xenbus_device *xbdev) +static void blkfront_remove(struct xenbus_device *xbdev) { struct blkfront_info *info = dev_get_drvdata(&xbdev->dev); @@ -2489,7 +2489,6 @@ static int blkfront_remove(struct xenbus_device *xbdev) } kfree(info); - return 0; } static int blkfront_is_ready(struct xenbus_device *dev) diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c index 379291826261..80cca3b83b22 100644 --- a/drivers/char/tpm/xen-tpmfront.c +++ b/drivers/char/tpm/xen-tpmfront.c @@ -360,14 +360,13 @@ static int tpmfront_probe(struct xenbus_device *dev, return tpm_chip_register(priv->chip); } -static int tpmfront_remove(struct xenbus_device *dev) +static void tpmfront_remove(struct xenbus_device *dev) { struct tpm_chip *chip = dev_get_drvdata(&dev->dev); struct tpm_private *priv = dev_get_drvdata(&chip->dev); tpm_chip_unregister(chip); ring_free(priv); dev_set_drvdata(&chip->dev, NULL); - return 0; } static int tpmfront_resume(struct xenbus_device *dev) diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index 0d8e6bd1ccbf..90996c108146 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -717,7 +717,7 @@ static int xen_drv_probe(struct xenbus_device *xb_dev, return xenbus_switch_state(xb_dev, XenbusStateInitialising); } -static int xen_drv_remove(struct xenbus_device *dev) +static void xen_drv_remove(struct xenbus_device *dev) { struct xen_drm_front_info *front_info = dev_get_drvdata(&dev->dev); int to = 100; @@ -751,7 +751,6 @@ static int xen_drv_remove(struct xenbus_device *dev) xen_drm_drv_fini(front_info); xenbus_frontend_closed(dev); - return 0; } static const struct xenbus_device_id xen_driver_ids[] = { diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c index 8d8ebdc2039b..67f1c7364c95 100644 --- a/drivers/input/misc/xen-kbdfront.c +++ b/drivers/input/misc/xen-kbdfront.c @@ -51,7 +51,7 @@ module_param_array(ptr_size, int, NULL, 0444); MODULE_PARM_DESC(ptr_size, "Pointing device width, height in pixels (default 800,600)"); -static int xenkbd_remove(struct xenbus_device *); +static void xenkbd_remove(struct xenbus_device *); static int xenkbd_connect_backend(struct xenbus_device *, struct xenkbd_info *); static void xenkbd_disconnect_backend(struct xenkbd_info *); @@ -404,7 +404,7 @@ static int xenkbd_resume(struct xenbus_device *dev) return xenkbd_connect_backend(dev, info); } -static int xenkbd_remove(struct xenbus_device *dev) +static void xenkbd_remove(struct xenbus_device *dev) { struct xenkbd_info *info = dev_get_drvdata(&dev->dev); @@ -417,7 +417,6 @@ static int xenkbd_remove(struct xenbus_device *dev) input_unregister_device(info->mtouch); free_page((unsigned long)info->page); kfree(info); - return 0; } static int xenkbd_connect_backend(struct xenbus_device *dev, diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index c1ba4294f364..001636901dda 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -977,7 +977,7 @@ static int read_xenbus_vif_flags(struct backend_info *be) return 0; } -static int netback_remove(struct xenbus_device *dev) +static void netback_remove(struct xenbus_device *dev) { struct backend_info *be = dev_get_drvdata(&dev->dev); @@ -992,7 +992,6 @@ static int netback_remove(struct xenbus_device *dev) kfree(be->hotplug_script); kfree(be); dev_set_drvdata(&dev->dev, NULL); - return 0; } /* diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 9af2b027c19c..bc17f5391b1a 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -2640,7 +2640,7 @@ static void xennet_bus_close(struct xenbus_device *dev) } while (!ret); } -static int xennet_remove(struct xenbus_device *dev) +static void xennet_remove(struct xenbus_device *dev) { struct netfront_info *info = dev_get_drvdata(&dev->dev); @@ -2656,8 +2656,6 @@ static int xennet_remove(struct xenbus_device *dev) rtnl_unlock(); } xennet_free_netdev(info->netdev); - - return 0; } static const struct xenbus_device_id netfront_ids[] = { diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 7378e2f3e525..fcd029ca2eb1 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -1055,14 +1055,12 @@ out: return err; } -static int pcifront_xenbus_remove(struct xenbus_device *xdev) +static void pcifront_xenbus_remove(struct xenbus_device *xdev) { struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev); if (pdev) free_pdev(pdev); - - return 0; } static const struct xenbus_device_id xenpci_ids[] = { diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 66b316d173b0..71a3bb83984c 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -995,7 +995,7 @@ static int scsifront_suspend(struct xenbus_device *dev) return err; } -static int scsifront_remove(struct xenbus_device *dev) +static void scsifront_remove(struct xenbus_device *dev) { struct vscsifrnt_info *info = dev_get_drvdata(&dev->dev); @@ -1011,8 +1011,6 @@ static int scsifront_remove(struct xenbus_device *dev) scsifront_free_ring(info); scsi_host_put(info->host); - - return 0; } static void scsifront_disconnect(struct vscsifrnt_info *info) diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 7c23112dc923..c879f922c716 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -394,9 +394,9 @@ static int xen_console_remove(struct xencons_info *info) return 0; } -static int xencons_remove(struct xenbus_device *dev) +static void xencons_remove(struct xenbus_device *dev) { - return xen_console_remove(dev_get_drvdata(&dev->dev)); + xen_console_remove(dev_get_drvdata(&dev->dev)); } static int xencons_connect_backend(struct xenbus_device *dev, diff --git a/drivers/usb/host/xen-hcd.c b/drivers/usb/host/xen-hcd.c index de1b09158318..46fdab940092 100644 --- a/drivers/usb/host/xen-hcd.c +++ b/drivers/usb/host/xen-hcd.c @@ -1530,15 +1530,13 @@ static void xenhcd_backend_changed(struct xenbus_device *dev, } } -static int xenhcd_remove(struct xenbus_device *dev) +static void xenhcd_remove(struct xenbus_device *dev) { struct xenhcd_info *info = dev_get_drvdata(&dev->dev); struct usb_hcd *hcd = xenhcd_info_to_hcd(info); xenhcd_destroy_rings(info); usb_put_hcd(hcd); - - return 0; } static int xenhcd_probe(struct xenbus_device *dev, diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c index 4d2694d904aa..ae8a50ecdbd3 100644 --- a/drivers/video/fbdev/xen-fbfront.c +++ b/drivers/video/fbdev/xen-fbfront.c @@ -67,7 +67,7 @@ MODULE_PARM_DESC(video, "Video memory size in MB, width, height in pixels (default 2,800,600)"); static void xenfb_make_preferred_console(void); -static int xenfb_remove(struct xenbus_device *); +static void xenfb_remove(struct xenbus_device *); static void xenfb_init_shared_page(struct xenfb_info *, struct fb_info *); static int xenfb_connect_backend(struct xenbus_device *, struct xenfb_info *); static void xenfb_disconnect_backend(struct xenfb_info *); @@ -527,7 +527,7 @@ static int xenfb_resume(struct xenbus_device *dev) return xenfb_connect_backend(dev, info); } -static int xenfb_remove(struct xenbus_device *dev) +static void xenfb_remove(struct xenbus_device *dev) { struct xenfb_info *info = dev_get_drvdata(&dev->dev); @@ -542,8 +542,6 @@ static int xenfb_remove(struct xenbus_device *dev) vfree(info->gfns); vfree(info->fb); kfree(info); - - return 0; } static unsigned long vmalloc_to_gfn(void *address) diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index d6f945fd4147..ea52a2092bb8 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -1181,9 +1181,8 @@ static void pvcalls_back_changed(struct xenbus_device *dev, } } -static int pvcalls_back_remove(struct xenbus_device *dev) +static void pvcalls_back_remove(struct xenbus_device *dev) { - return 0; } static int pvcalls_back_uevent(struct xenbus_device *xdev, diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 1826e8e67125..5328f4d35f25 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -1085,7 +1085,7 @@ static const struct xenbus_device_id pvcalls_front_ids[] = { { "" } }; -static int pvcalls_front_remove(struct xenbus_device *dev) +static void pvcalls_front_remove(struct xenbus_device *dev) { struct pvcalls_bedata *bedata; struct sock_mapping *map = NULL, *n; @@ -1121,7 +1121,6 @@ static int pvcalls_front_remove(struct xenbus_device *dev) kfree(bedata->ring.sring); kfree(bedata); xenbus_switch_state(dev, XenbusStateClosed); - return 0; } static int pvcalls_front_probe(struct xenbus_device *dev, diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index d171091eec12..b11e401f1b1e 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -716,14 +716,12 @@ out: return err; } -static int xen_pcibk_xenbus_remove(struct xenbus_device *dev) +static void xen_pcibk_xenbus_remove(struct xenbus_device *dev) { struct xen_pcibk_device *pdev = dev_get_drvdata(&dev->dev); if (pdev != NULL) free_pdev(pdev); - - return 0; } static const struct xenbus_device_id xen_pcibk_ids[] = { diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 6106ed93817d..954188b0b858 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1249,7 +1249,7 @@ static void scsiback_release_translation_entry(struct vscsibk_info *info) spin_unlock_irqrestore(&info->v2p_lock, flags); } -static int scsiback_remove(struct xenbus_device *dev) +static void scsiback_remove(struct xenbus_device *dev) { struct vscsibk_info *info = dev_get_drvdata(&dev->dev); @@ -1261,8 +1261,6 @@ static int scsiback_remove(struct xenbus_device *dev) gnttab_page_cache_shrink(&info->free_pages, 0); dev_set_drvdata(&dev->dev, NULL); - - return 0; } static int scsiback_probe(struct xenbus_device *dev, diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index eaa932b99d8a..ad4fb4eab753 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -117,7 +117,7 @@ struct xenbus_driver { const struct xenbus_device_id *id); void (*otherend_changed)(struct xenbus_device *dev, enum xenbus_state backend_state); - int (*remove)(struct xenbus_device *dev); + void (*remove)(struct xenbus_device *dev); int (*suspend)(struct xenbus_device *dev); int (*resume)(struct xenbus_device *dev); int (*uevent)(struct xenbus_device *, struct kobj_uevent_env *); diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index aaa5fd364691..9950e1a5acb7 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -303,13 +303,12 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) kfree(priv); } -static int xen_9pfs_front_remove(struct xenbus_device *dev) +static void xen_9pfs_front_remove(struct xenbus_device *dev) { struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev); dev_set_drvdata(&dev->dev, NULL); xen_9pfs_front_free(priv); - return 0; } static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev, diff --git a/sound/xen/xen_snd_front.c b/sound/xen/xen_snd_front.c index 4041748c12e5..b66e037710d0 100644 --- a/sound/xen/xen_snd_front.c +++ b/sound/xen/xen_snd_front.c @@ -311,7 +311,7 @@ static int xen_drv_probe(struct xenbus_device *xb_dev, return xenbus_switch_state(xb_dev, XenbusStateInitialising); } -static int xen_drv_remove(struct xenbus_device *dev) +static void xen_drv_remove(struct xenbus_device *dev) { struct xen_snd_front_info *front_info = dev_get_drvdata(&dev->dev); int to = 100; @@ -345,7 +345,6 @@ static int xen_drv_remove(struct xenbus_device *dev) xen_snd_drv_fini(front_info); xenbus_frontend_closed(dev); - return 0; } static const struct xenbus_device_id xen_drv_ids[] = { From b18cba09e374637a0a3759d856a6bca94c133952 Mon Sep 17 00:00:00 2001 From: minoura makoto Date: Tue, 13 Dec 2022 13:14:31 +0900 Subject: [PATCH 012/233] SUNRPC: ensure the matching upcall is in-flight upon downcall Commit 9130b8dbc6ac ("SUNRPC: allow for upcalls for the same uid but different gss service") introduced `auth` argument to __gss_find_upcall(), but in gss_pipe_downcall() it was left as NULL since it (and auth->service) was not (yet) determined. When multiple upcalls with the same uid and different service are ongoing, it could happen that __gss_find_upcall(), which returns the first match found in the pipe->in_downcall list, could not find the correct gss_msg corresponding to the downcall we are looking for. Moreover, it might return a msg which is not sent to rpc.gssd yet. We could see mount.nfs process hung in D state with multiple mount.nfs are executed in parallel. The call trace below is of CentOS 7.9 kernel-3.10.0-1160.24.1.el7.x86_64 but we observed the same hang w/ elrepo kernel-ml-6.0.7-1.el7. PID: 71258 TASK: ffff91ebd4be0000 CPU: 36 COMMAND: "mount.nfs" #0 [ffff9203ca3234f8] __schedule at ffffffffa3b8899f #1 [ffff9203ca323580] schedule at ffffffffa3b88eb9 #2 [ffff9203ca323590] gss_cred_init at ffffffffc0355818 [auth_rpcgss] #3 [ffff9203ca323658] rpcauth_lookup_credcache at ffffffffc0421ebc [sunrpc] #4 [ffff9203ca3236d8] gss_lookup_cred at ffffffffc0353633 [auth_rpcgss] #5 [ffff9203ca3236e8] rpcauth_lookupcred at ffffffffc0421581 [sunrpc] #6 [ffff9203ca323740] rpcauth_refreshcred at ffffffffc04223d3 [sunrpc] #7 [ffff9203ca3237a0] call_refresh at ffffffffc04103dc [sunrpc] #8 [ffff9203ca3237b8] __rpc_execute at ffffffffc041e1c9 [sunrpc] #9 [ffff9203ca323820] rpc_execute at ffffffffc0420a48 [sunrpc] The scenario is like this. Let's say there are two upcalls for services A and B, A -> B in pipe->in_downcall, B -> A in pipe->pipe. When rpc.gssd reads pipe to get the upcall msg corresponding to service B from pipe->pipe and then writes the response, in gss_pipe_downcall the msg corresponding to service A will be picked because only uid is used to find the msg and it is before the one for B in pipe->in_downcall. And the process waiting for the msg corresponding to service A will be woken up. Actual scheduing of that process might be after rpc.gssd processes the next msg. In rpc_pipe_generic_upcall it clears msg->errno (for A). The process is scheduled to see gss_msg->ctx == NULL and gss_msg->msg.errno == 0, therefore it cannot break the loop in gss_create_upcall and is never woken up after that. This patch adds a simple check to ensure that a msg which is not sent to rpc.gssd yet is not chosen as the matching upcall upon receiving a downcall. Signed-off-by: minoura makoto Signed-off-by: Hiroshi Shimamoto Tested-by: Hiroshi Shimamoto Cc: Trond Myklebust Fixes: 9130b8dbc6ac ("SUNRPC: allow for upcalls for same uid but different gss service") Signed-off-by: Trond Myklebust --- include/linux/sunrpc/rpc_pipe_fs.h | 5 +++++ net/sunrpc/auth_gss/auth_gss.c | 19 +++++++++++++++++-- 2 files changed, 22 insertions(+), 2 deletions(-) diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index cd188a527d16..3b35b6f6533a 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -92,6 +92,11 @@ extern ssize_t rpc_pipe_generic_upcall(struct file *, struct rpc_pipe_msg *, char __user *, size_t); extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *); +/* returns true if the msg is in-flight, i.e., already eaten by the peer */ +static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) { + return (msg->copied != 0 && list_empty(&msg->list)); +} + struct rpc_clnt; extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *); extern int rpc_remove_client_dir(struct rpc_clnt *); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 7bb247c51e2f..2d7b1e03110a 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -302,7 +302,7 @@ __gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth list_for_each_entry(pos, &pipe->in_downcall, list) { if (!uid_eq(pos->uid, uid)) continue; - if (auth && pos->auth->service != auth->service) + if (pos->auth->service != auth->service) continue; refcount_inc(&pos->count); return pos; @@ -686,6 +686,21 @@ out: return err; } +static struct gss_upcall_msg * +gss_find_downcall(struct rpc_pipe *pipe, kuid_t uid) +{ + struct gss_upcall_msg *pos; + list_for_each_entry(pos, &pipe->in_downcall, list) { + if (!uid_eq(pos->uid, uid)) + continue; + if (!rpc_msg_is_inflight(&pos->msg)) + continue; + refcount_inc(&pos->count); + return pos; + } + return NULL; +} + #define MSG_BUF_MAXSIZE 1024 static ssize_t @@ -732,7 +747,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) err = -ENOENT; /* Find a matching upcall */ spin_lock(&pipe->lock); - gss_msg = __gss_find_upcall(pipe, uid, NULL); + gss_msg = gss_find_downcall(pipe, uid); if (gss_msg == NULL) { spin_unlock(&pipe->lock); goto err_put_ctx; From 4e699e34f923188175986ad8a74ab99f7034075e Mon Sep 17 00:00:00 2001 From: Ma Jun Date: Fri, 16 Dec 2022 11:05:26 +0800 Subject: [PATCH 013/233] drm/plane-helper: Add the missing declaration of drm_atomic_state Add the missing declaration of struct drm_atomic_state to fix the compile error below: error: 'struct drm_atomic_state' declared inside parameter list will not be visible outside of this definition or declaration [-Werror] Signed-off-by: Ma Jun Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Fixes: 8401bd361f59 ("drm/plane-helper: Add a drm_plane_helper_atomic_check() helper") Cc: Javier Martinez Canillas Cc: Thomas Zimmermann Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: David Airlie Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Cc: # v6.1+ Link: https://patchwork.freedesktop.org/patch/msgid/20221216030526.1335609-1-majun@amd.com --- include/drm/drm_plane_helper.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/drm/drm_plane_helper.h b/include/drm/drm_plane_helper.h index ff83d2621687..3a574e8cd22f 100644 --- a/include/drm/drm_plane_helper.h +++ b/include/drm/drm_plane_helper.h @@ -26,6 +26,7 @@ #include +struct drm_atomic_state; struct drm_crtc; struct drm_framebuffer; struct drm_modeset_acquire_ctx; From a6b9d2fa0024e7e399c26facd0fb466b7396e2b9 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 20 Dec 2022 12:31:29 -0500 Subject: [PATCH 014/233] pNFS/filelayout: Fix coalescing test for single DS When there is a single DS no striping constraints need to be placed on the IO. When such constraint is applied then buffered reads don't coalesce to the DS's rsize. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- fs/nfs/filelayout/filelayout.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index ad34a33b0737..4974cd18ca46 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -783,6 +783,12 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, return &fl->generic_hdr; } +static bool +filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg) +{ + return flseg->num_fh > 1; +} + /* * filelayout_pg_test(). Called by nfs_can_coalesce_requests() * @@ -803,6 +809,8 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, size = pnfs_generic_pg_test(pgio, prev, req); if (!size) return 0; + else if (!filelayout_lseg_is_striped(FILELAYOUT_LSEG(pgio->pg_lseg))) + return size; /* see if req and prev are in the same stripe */ if (prev) { From 4217c6ac817451d5116687f3cc6286220dc43d49 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 19 Dec 2022 14:01:30 +0000 Subject: [PATCH 015/233] drm/panfrost: Fix GEM handle creation ref-counting panfrost_gem_create_with_handle() previously returned a BO but with the only reference being from the handle, which user space could in theory guess and release, causing a use-after-free. Additionally if the call to panfrost_gem_mapping_get() in panfrost_ioctl_create_bo() failed then a(nother) reference on the BO was dropped. The _create_with_handle() is a problematic pattern, so ditch it and instead create the handle in panfrost_ioctl_create_bo(). If the call to panfrost_gem_mapping_get() fails then this means that user space has indeed gone behind our back and freed the handle. In which case just return an error code. Reported-by: Rob Clark Fixes: f3ba91228e8e ("drm/panfrost: Add initial panfrost driver") Signed-off-by: Steven Price Reviewed-by: Rob Clark Link: https://patchwork.freedesktop.org/patch/msgid/20221219140130.410578-1-steven.price@arm.com --- drivers/gpu/drm/panfrost/panfrost_drv.c | 27 ++++++++++++++++--------- drivers/gpu/drm/panfrost/panfrost_gem.c | 16 +-------------- drivers/gpu/drm/panfrost/panfrost_gem.h | 5 +---- 3 files changed, 20 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 2fa5afe21288..919e6cc04982 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -82,6 +82,7 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data, struct panfrost_gem_object *bo; struct drm_panfrost_create_bo *args = data; struct panfrost_gem_mapping *mapping; + int ret; if (!args->size || args->pad || (args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP))) @@ -92,21 +93,29 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data, !(args->flags & PANFROST_BO_NOEXEC)) return -EINVAL; - bo = panfrost_gem_create_with_handle(file, dev, args->size, args->flags, - &args->handle); + bo = panfrost_gem_create(dev, args->size, args->flags); if (IS_ERR(bo)) return PTR_ERR(bo); + ret = drm_gem_handle_create(file, &bo->base.base, &args->handle); + if (ret) + goto out; + mapping = panfrost_gem_mapping_get(bo, priv); - if (!mapping) { - drm_gem_object_put(&bo->base.base); - return -EINVAL; + if (mapping) { + args->offset = mapping->mmnode.start << PAGE_SHIFT; + panfrost_gem_mapping_put(mapping); + } else { + /* This can only happen if the handle from + * drm_gem_handle_create() has already been guessed and freed + * by user space + */ + ret = -EINVAL; } - args->offset = mapping->mmnode.start << PAGE_SHIFT; - panfrost_gem_mapping_put(mapping); - - return 0; +out: + drm_gem_object_put(&bo->base.base); + return ret; } /** diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index 293e799e2fe8..3c812fbd126f 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -235,12 +235,8 @@ struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t } struct panfrost_gem_object * -panfrost_gem_create_with_handle(struct drm_file *file_priv, - struct drm_device *dev, size_t size, - u32 flags, - uint32_t *handle) +panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags) { - int ret; struct drm_gem_shmem_object *shmem; struct panfrost_gem_object *bo; @@ -256,16 +252,6 @@ panfrost_gem_create_with_handle(struct drm_file *file_priv, bo->noexec = !!(flags & PANFROST_BO_NOEXEC); bo->is_heap = !!(flags & PANFROST_BO_HEAP); - /* - * Allocate an id of idr table where the obj is registered - * and handle has the id what user can see. - */ - ret = drm_gem_handle_create(file_priv, &shmem->base, handle); - /* drop reference from allocate - handle holds it now. */ - drm_gem_object_put(&shmem->base); - if (ret) - return ERR_PTR(ret); - return bo; } diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h index 8088d5fd8480..ad2877eeeccd 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.h +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h @@ -69,10 +69,7 @@ panfrost_gem_prime_import_sg_table(struct drm_device *dev, struct sg_table *sgt); struct panfrost_gem_object * -panfrost_gem_create_with_handle(struct drm_file *file_priv, - struct drm_device *dev, size_t size, - u32 flags, - uint32_t *handle); +panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags); int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv); void panfrost_gem_close(struct drm_gem_object *obj, From 523dfa96add75e60cfe6bf5a1c8f713635cd6b73 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 15 Dec 2022 17:34:49 +0100 Subject: [PATCH 016/233] drm/tests: reduce drm_mm_test stack usage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The check_reserve_boundaries function uses a lot of kernel stack, and it gets inlined by clang, which makes __drm_test_mm_reserve use even more of it, to the point of hitting the warning limit: drivers/gpu/drm/tests/drm_mm_test.c:344:12: error: stack frame size (1048) exceeds limit (1024) in '__drm_test_mm_reserve' [-Werror,-Wframe-larger-than] When building with gcc, this does not happen, but the structleak plugin can similarly increase the stack usage and needs to be disabled, as we do for all other kunit users. Signed-off-by: Arnd Bergmann Reviewed-by: Maíra Canal Reviewed-by: Nathan Chancellor Signed-off-by: Maíra Canal Link: https://patchwork.freedesktop.org/patch/msgid/20221215163511.266214-1-arnd@kernel.org --- drivers/gpu/drm/tests/Makefile | 2 ++ drivers/gpu/drm/tests/drm_mm_test.c | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/tests/Makefile b/drivers/gpu/drm/tests/Makefile index b29ef1085cad..f896ef85c2f2 100644 --- a/drivers/gpu/drm/tests/Makefile +++ b/drivers/gpu/drm/tests/Makefile @@ -12,3 +12,5 @@ obj-$(CONFIG_DRM_KUNIT_TEST) += \ drm_mm_test.o \ drm_plane_helper_test.o \ drm_rect_test.o + +CFLAGS_drm_mm_test.o := $(DISABLE_STRUCTLEAK_PLUGIN) diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c index 89f12d3b4a21..186b28dc7038 100644 --- a/drivers/gpu/drm/tests/drm_mm_test.c +++ b/drivers/gpu/drm/tests/drm_mm_test.c @@ -298,9 +298,9 @@ static bool expect_reserve_fail(struct kunit *test, struct drm_mm *mm, struct dr return false; } -static bool check_reserve_boundaries(struct kunit *test, struct drm_mm *mm, - unsigned int count, - u64 size) +static bool noinline_for_stack check_reserve_boundaries(struct kunit *test, struct drm_mm *mm, + unsigned int count, + u64 size) { const struct boundary { u64 start, size; From 26870c3f5b15187268bf183055c7b9f29fe66079 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 26 Dec 2022 10:11:17 -0800 Subject: [PATCH 017/233] xfs: don't assert if cmap covers imap after cycling lock In xfs_reflink_fill_cow_hole, there's a debugging assertion that trips if (after cycling the ILOCK to get a transaction) the requeried cow mapping overlaps the start of the area being written. IOWs, it trips if the hole in the cow fork that it's supposed to fill has been filled. This is trivially possible since we cycled ILOCK_EXCL. If we trip the assertion, then we know that cmap is a delalloc extent because @found is false. Fortunately, the bmapi_write call below will convert the delalloc extent to a real unwritten cow fork extent, so all we need to do here is remove the assertion. It turns out that generic/095 trips this pretty regularly with alwayscow mode enabled. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/xfs_reflink.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index fe46bce8cae6..5535778a98f9 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -416,8 +416,6 @@ xfs_reflink_fill_cow_hole( goto convert; } - ASSERT(cmap->br_startoff > imap->br_startoff); - /* Allocate the entire reservation as unwritten blocks. */ nimaps = 1; error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount, From d4542f314507015ac0e25c6e8102b88293826a51 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 26 Dec 2022 10:11:18 -0800 Subject: [PATCH 018/233] xfs: make xfs_iomap_page_ops static Shut up the sparse warnings about this variable that isn't referenced anywhere else. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/xfs_iomap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 669c1bc5c3a7..fc1946f80a4a 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -83,7 +83,7 @@ xfs_iomap_valid( return true; } -const struct iomap_page_ops xfs_iomap_page_ops = { +static const struct iomap_page_ops xfs_iomap_page_ops = { .iomap_valid = xfs_iomap_valid, }; From b24cded8c065d7cef8690b2c7b82b828cce57708 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Sun, 25 Dec 2022 09:37:12 +0100 Subject: [PATCH 019/233] spi: mediatek: Enable irq before the spi registration If the irq is enabled after the spi si registered, there can be a race with the initialization of the devices on the spi bus. Eg: mtk-spi 1100a000.spi: spi-mem transfer timeout spi-nor: probe of spi0.0 failed with error -110 Unable to handle kernel NULL pointer dereference at virtual address 0000000000000010 ... Call trace: mtk_spi_can_dma+0x0/0x2c Fixes: c6f7874687f7 ("spi: mediatek: Enable irq when pdata is ready") Reported-by: Daniel Golle Signed-off-by: Ricardo Ribalda Tested-by: Daniel Golle Link: https://lore.kernel.org/r/20221225-mtk-spi-fixes-v1-0-bb6c14c232f8@chromium.org Signed-off-by: Mark Brown --- drivers/spi/spi-mt65xx.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 6de8360e5c2a..9eab6c20dbc5 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -1253,6 +1253,11 @@ static int mtk_spi_probe(struct platform_device *pdev) dev_notice(dev, "SPI dma_set_mask(%d) failed, ret:%d\n", addr_bits, ret); + ret = devm_request_irq(dev, irq, mtk_spi_interrupt, + IRQF_TRIGGER_NONE, dev_name(dev), master); + if (ret) + return dev_err_probe(dev, ret, "failed to register irq\n"); + pm_runtime_enable(dev); ret = devm_spi_register_master(dev, master); @@ -1261,13 +1266,6 @@ static int mtk_spi_probe(struct platform_device *pdev) return dev_err_probe(dev, ret, "failed to register master\n"); } - ret = devm_request_irq(dev, irq, mtk_spi_interrupt, - IRQF_TRIGGER_NONE, dev_name(dev), master); - if (ret) { - pm_runtime_disable(dev); - return dev_err_probe(dev, ret, "failed to register irq\n"); - } - return 0; } From e8bb8f19e73a1e855e54788f8673b9b49e46b5cd Mon Sep 17 00:00:00 2001 From: Witold Sadowski Date: Mon, 19 Dec 2022 06:42:48 -0800 Subject: [PATCH 020/233] spi: cadence: Fix busy cycles calculation If xSPI is in x2/x4/x8 mode to calculate busy cycles, busy bits count must be divided by the number of lanes. If opcommand is using 8 busy bits, but SPI is in x4 mode, there will be only 2 busy cycles. Signed-off-by: Witold Sadowski Reviewed-by: Chandrakala Chavva Reviewed-by: Sunil Kovvuri Goutham Link: https://lore.kernel.org/r/20221219144254.20883-2-wsadowski@marvell.com Signed-off-by: Mark Brown --- drivers/spi/spi-cadence-xspi.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-cadence-xspi.c b/drivers/spi/spi-cadence-xspi.c index 520b4cc69cdc..91db3c973167 100644 --- a/drivers/spi/spi-cadence-xspi.c +++ b/drivers/spi/spi-cadence-xspi.c @@ -177,7 +177,10 @@ #define CDNS_XSPI_CMD_FLD_DSEQ_CMD_3(op) ( \ FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_DCNT_H, \ ((op)->data.nbytes >> 16) & 0xffff) | \ - FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, (op)->dummy.nbytes * 8)) + FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, \ + (op)->dummy.buswidth != 0 ? \ + (((op)->dummy.nbytes * 8) / (op)->dummy.buswidth) : \ + 0)) #define CDNS_XSPI_CMD_FLD_DSEQ_CMD_4(op, chipsel) ( \ FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R4_BANK, chipsel) | \ From b659b613cea2ae39746ca8bd2b69d1985dd9d770 Mon Sep 17 00:00:00 2001 From: Ferry Toth Date: Thu, 22 Dec 2022 21:53:02 +0100 Subject: [PATCH 021/233] Revert "usb: ulpi: defer ulpi_register on ulpi_read_id timeout" This reverts commit 8a7b31d545d3a15f0e6f5984ae16f0ca4fd76aac. This patch results in some qemu test failures, specifically xilinx-zynq-a9 machine and zynq-zc702 as well as zynq-zed devicetree files, when trying to boot from USB drive. Link: https://lore.kernel.org/lkml/20221220194334.GA942039@roeck-us.net/ Fixes: 8a7b31d545d3 ("usb: ulpi: defer ulpi_register on ulpi_read_id timeout") Cc: stable@vger.kernel.org Reported-by: Guenter Roeck Signed-off-by: Ferry Toth Link: https://lore.kernel.org/r/20221222205302.45761-1-ftoth@exalondelft.nl Signed-off-by: Greg Kroah-Hartman --- drivers/usb/common/ulpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 60e8174686a1..d7c8461976ce 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -207,7 +207,7 @@ static int ulpi_read_id(struct ulpi *ulpi) /* Test the interface */ ret = ulpi_write(ulpi, ULPI_SCRATCH, 0xaa); if (ret < 0) - return ret; + goto err; ret = ulpi_read(ulpi, ULPI_SCRATCH); if (ret < 0) From 2de5bba5890f6604a997c75e754df8082386c9f7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 15 Dec 2022 17:57:20 +0100 Subject: [PATCH 022/233] usb: fotg210: fix OTG-only build The fotg210 module combines the HCD and OTG drivers, which then fails to build when only the USB gadget support is enabled in the kernel but host support is not: aarch64-linux-ld: drivers/usb/fotg210/fotg210-core.o: in function `fotg210_init': fotg210-core.c:(.init.text+0xc): undefined reference to `usb_disabled' Move the check for usb_disabled() after the check for the HCD module, and let the OTG driver still be probed in this configuration. A nicer approach might be to have the common portion built as a library module, with the two platform other files registering their own platform_driver instances separately. Fixes: ddacd6ef44ca ("usb: fotg210: Fix Kconfig for USB host modules") Reviewed-by: Linus Walleij Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20221215165728.2062984-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/fotg210/fotg210-core.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/usb/fotg210/fotg210-core.c b/drivers/usb/fotg210/fotg210-core.c index 8a54edf921ac..ee740a6da463 100644 --- a/drivers/usb/fotg210/fotg210-core.c +++ b/drivers/usb/fotg210/fotg210-core.c @@ -144,10 +144,7 @@ static struct platform_driver fotg210_driver = { static int __init fotg210_init(void) { - if (usb_disabled()) - return -ENODEV; - - if (IS_ENABLED(CONFIG_USB_FOTG210_HCD)) + if (IS_ENABLED(CONFIG_USB_FOTG210_HCD) && !usb_disabled()) fotg210_hcd_init(); return platform_driver_register(&fotg210_driver); } From 56c5dab20a6391604df9521f812c01d1e3fe1bd0 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 12 Dec 2022 13:04:11 +0100 Subject: [PATCH 023/233] RDMA/srp: Move large values to a new enum for gcc13 Since gcc13, each member of an enum has the same type as the enum [1]. And that is inherited from its members. Provided these two: SRP_TAG_NO_REQ = ~0U, SRP_TAG_TSK_MGMT = 1U << 31 all other members are unsigned ints. Esp. with SRP_MAX_SGE and SRP_TSK_MGMT_SQ_SIZE and their use in min(), this results in the following warnings: include/linux/minmax.h:20:35: error: comparison of distinct pointer types lacks a cast drivers/infiniband/ulp/srp/ib_srp.c:563:42: note: in expansion of macro 'min' include/linux/minmax.h:20:35: error: comparison of distinct pointer types lacks a cast drivers/infiniband/ulp/srp/ib_srp.c:2369:27: note: in expansion of macro 'min' So move the large values away to a separate enum, so that they don't affect other members. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=36113 Link: https://lore.kernel.org/r/20221212120411.13750-1-jirislaby@kernel.org Signed-off-by: Jiri Slaby (SUSE) Reviewed-by: Bart Van Assche Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/srp/ib_srp.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index 00b0068fda20..5d94db453df3 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -62,9 +62,6 @@ enum { SRP_DEFAULT_CMD_SQ_SIZE = SRP_DEFAULT_QUEUE_SIZE - SRP_RSP_SQ_SIZE - SRP_TSK_MGMT_SQ_SIZE, - SRP_TAG_NO_REQ = ~0U, - SRP_TAG_TSK_MGMT = 1U << 31, - SRP_MAX_PAGES_PER_MR = 512, SRP_MAX_ADD_CDB_LEN = 16, @@ -79,6 +76,11 @@ enum { sizeof(struct srp_imm_buf), }; +enum { + SRP_TAG_NO_REQ = ~0U, + SRP_TAG_TSK_MGMT = BIT(31), +}; + enum srp_target_state { SRP_TARGET_SCANNING, SRP_TARGET_LIVE, From a23529989a8f56d23680c4f2d14011bc9c9457c9 Mon Sep 17 00:00:00 2001 From: Nikolaus Voss Date: Tue, 20 Dec 2022 09:17:50 +0100 Subject: [PATCH 024/233] crypto: caam - fix CAAM io mem access in blob_gen IO memory access has to be done with accessors defined in caam/regs.h as there are little-endian architectures with a big-endian CAAM unit. Fixes: 6a83830f649a ("crypto: caam - warn if blob_gen key is insecure") Signed-off-by: Nikolaus Voss Reviewed-by: Ahmad Fatoum Signed-off-by: Herbert Xu --- drivers/crypto/caam/blob_gen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/caam/blob_gen.c b/drivers/crypto/caam/blob_gen.c index 1f65df489847..f46b161d2cda 100644 --- a/drivers/crypto/caam/blob_gen.c +++ b/drivers/crypto/caam/blob_gen.c @@ -104,7 +104,7 @@ int caam_process_blob(struct caam_blob_priv *priv, } ctrlpriv = dev_get_drvdata(jrdev->parent); - moo = FIELD_GET(CSTA_MOO, ioread32(&ctrlpriv->ctrl->perfmon.status)); + moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->ctrl->perfmon.status)); if (moo != CSTA_MOO_SECURE && moo != CSTA_MOO_TRUSTED) dev_warn(jrdev, "using insecure test key, enable HAB to use unique device key!\n"); From 736f88689c6912f05d0116917910603a7ba97de7 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Wed, 21 Dec 2022 15:32:32 +0800 Subject: [PATCH 025/233] crypto: arm64/sm4 - fix possible crash with CFI enabled The SM4 CCM/GCM assembly functions for encryption and decryption is called via indirect function calls. Therefore they need to use SYM_TYPED_FUNC_START instead of SYM_FUNC_START to cause its type hash to be emitted when the kernel is built with CONFIG_CFI_CLANG=y. Otherwise, the code crashes with a CFI failure (if the compiler didn't happen to optimize out the indirect call). Fixes: 67fa3a7fdf80 ("crypto: arm64/sm4 - add CE implementation for CCM mode") Fixes: ae1b83c7d572 ("crypto: arm64/sm4 - add CE implementation for GCM mode") Signed-off-by: Tianjia Zhang Signed-off-by: Herbert Xu --- arch/arm64/crypto/sm4-ce-ccm-core.S | 5 +++-- arch/arm64/crypto/sm4-ce-gcm-core.S | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/arm64/crypto/sm4-ce-ccm-core.S b/arch/arm64/crypto/sm4-ce-ccm-core.S index 028207c4afd0..fa85856f33ce 100644 --- a/arch/arm64/crypto/sm4-ce-ccm-core.S +++ b/arch/arm64/crypto/sm4-ce-ccm-core.S @@ -8,6 +8,7 @@ */ #include +#include #include #include "sm4-ce-asm.h" @@ -104,7 +105,7 @@ SYM_FUNC_START(sm4_ce_ccm_final) SYM_FUNC_END(sm4_ce_ccm_final) .align 3 -SYM_FUNC_START(sm4_ce_ccm_enc) +SYM_TYPED_FUNC_START(sm4_ce_ccm_enc) /* input: * x0: round key array, CTX * x1: dst @@ -216,7 +217,7 @@ SYM_FUNC_START(sm4_ce_ccm_enc) SYM_FUNC_END(sm4_ce_ccm_enc) .align 3 -SYM_FUNC_START(sm4_ce_ccm_dec) +SYM_TYPED_FUNC_START(sm4_ce_ccm_dec) /* input: * x0: round key array, CTX * x1: dst diff --git a/arch/arm64/crypto/sm4-ce-gcm-core.S b/arch/arm64/crypto/sm4-ce-gcm-core.S index 7aa3ec18a289..347f25d75727 100644 --- a/arch/arm64/crypto/sm4-ce-gcm-core.S +++ b/arch/arm64/crypto/sm4-ce-gcm-core.S @@ -9,6 +9,7 @@ */ #include +#include #include #include "sm4-ce-asm.h" @@ -370,7 +371,7 @@ SYM_FUNC_START(pmull_ghash_update) SYM_FUNC_END(pmull_ghash_update) .align 3 -SYM_FUNC_START(sm4_ce_pmull_gcm_enc) +SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_enc) /* input: * x0: round key array, CTX * x1: dst @@ -581,7 +582,7 @@ SYM_FUNC_END(sm4_ce_pmull_gcm_enc) #define RH3 v20 .align 3 -SYM_FUNC_START(sm4_ce_pmull_gcm_dec) +SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_dec) /* input: * x0: round key array, CTX * x1: dst From b878d3ba9bb41cddb73ba4b56e5552f0a638daca Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 27 Dec 2022 16:10:05 -0800 Subject: [PATCH 026/233] thermal: int340x: Add missing attribute for data rate base Commit 473be51142ad ("thermal: int340x: processor_thermal: Add RFIM driver")' added rfi_restriction_data_rate_base string, mmio details and documentation, but missed adding attribute to sysfs. Add missing sysfs attribute. Fixes: 473be51142ad ("thermal: int340x: processor_thermal: Add RFIM driver") Cc: 5.11+ # v5.11+ Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- .../thermal/intel/int340x_thermal/processor_thermal_rfim.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c index 8c42e7662033..92ed1213fe37 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c @@ -172,6 +172,7 @@ static const struct attribute_group fivr_attribute_group = { RFIM_SHOW(rfi_restriction_run_busy, 1) RFIM_SHOW(rfi_restriction_err_code, 1) RFIM_SHOW(rfi_restriction_data_rate, 1) +RFIM_SHOW(rfi_restriction_data_rate_base, 1) RFIM_SHOW(ddr_data_rate_point_0, 1) RFIM_SHOW(ddr_data_rate_point_1, 1) RFIM_SHOW(ddr_data_rate_point_2, 1) @@ -181,11 +182,13 @@ RFIM_SHOW(rfi_disable, 1) RFIM_STORE(rfi_restriction_run_busy, 1) RFIM_STORE(rfi_restriction_err_code, 1) RFIM_STORE(rfi_restriction_data_rate, 1) +RFIM_STORE(rfi_restriction_data_rate_base, 1) RFIM_STORE(rfi_disable, 1) static DEVICE_ATTR_RW(rfi_restriction_run_busy); static DEVICE_ATTR_RW(rfi_restriction_err_code); static DEVICE_ATTR_RW(rfi_restriction_data_rate); +static DEVICE_ATTR_RW(rfi_restriction_data_rate_base); static DEVICE_ATTR_RO(ddr_data_rate_point_0); static DEVICE_ATTR_RO(ddr_data_rate_point_1); static DEVICE_ATTR_RO(ddr_data_rate_point_2); @@ -248,6 +251,7 @@ static struct attribute *dvfs_attrs[] = { &dev_attr_rfi_restriction_run_busy.attr, &dev_attr_rfi_restriction_err_code.attr, &dev_attr_rfi_restriction_data_rate.attr, + &dev_attr_rfi_restriction_data_rate_base.attr, &dev_attr_ddr_data_rate_point_0.attr, &dev_attr_ddr_data_rate_point_1.attr, &dev_attr_ddr_data_rate_point_2.attr, From 38b50aa44495d5eb4218f0b82fc2da76505cec53 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 28 Dec 2022 14:56:09 +0200 Subject: [PATCH 027/233] RDMA/mlx5: Fix mlx5_ib_get_hw_stats when used for device Currently, when mlx5_ib_get_hw_stats() is used for device (port_num = 0), there is a special handling in order to use the correct counters, but, port_num is being passed down the stack without any change. Also, some functions assume that port_num >=1. As a result, the following oops can occur. BUG: unable to handle page fault for address: ffff89510294f1a8 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP CPU: 8 PID: 1382 Comm: devlink Tainted: G W 6.1.0-rc4_for_upstream_base_2022_11_10_16_12 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:_raw_spin_lock+0xc/0x20 Call Trace: mlx5_ib_get_native_port_mdev+0x73/0xe0 [mlx5_ib] do_get_hw_stats.constprop.0+0x109/0x160 [mlx5_ib] mlx5_ib_get_hw_stats+0xad/0x180 [mlx5_ib] ib_setup_device_attrs+0xf0/0x290 [ib_core] ib_register_device+0x3bb/0x510 [ib_core] ? atomic_notifier_chain_register+0x67/0x80 __mlx5_ib_add+0x2b/0x80 [mlx5_ib] mlx5r_probe+0xb8/0x150 [mlx5_ib] ? auxiliary_match_id+0x6a/0x90 auxiliary_bus_probe+0x3c/0x70 ? driver_sysfs_add+0x6b/0x90 really_probe+0xcd/0x380 __driver_probe_device+0x80/0x170 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 ? driver_allows_async_probing+0x60/0x60 ? driver_allows_async_probing+0x60/0x60 bus_for_each_drv+0x7b/0xc0 __device_attach+0xbc/0x200 bus_probe_device+0x87/0xa0 device_add+0x404/0x940 ? dev_set_name+0x53/0x70 __auxiliary_device_add+0x43/0x60 add_adev+0x99/0xe0 [mlx5_core] mlx5_attach_device+0xc8/0x120 [mlx5_core] mlx5_load_one_devl_locked+0xb2/0xe0 [mlx5_core] devlink_reload+0x133/0x250 devlink_nl_cmd_reload+0x480/0x570 ? devlink_nl_pre_doit+0x44/0x2b0 genl_family_rcv_msg_doit.isra.0+0xc2/0x110 genl_rcv_msg+0x180/0x2b0 ? devlink_nl_cmd_region_read_dumpit+0x540/0x540 ? devlink_reload+0x250/0x250 ? devlink_put+0x50/0x50 ? genl_family_rcv_msg_doit.isra.0+0x110/0x110 netlink_rcv_skb+0x54/0x100 genl_rcv+0x24/0x40 netlink_unicast+0x1f6/0x2c0 netlink_sendmsg+0x237/0x490 sock_sendmsg+0x33/0x40 __sys_sendto+0x103/0x160 ? handle_mm_fault+0x10e/0x290 ? do_user_addr_fault+0x1c0/0x5f0 __x64_sys_sendto+0x25/0x30 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Fix it by setting port_num to 1 in order to get device status and remove unused variable. Fixes: aac4492ef23a ("IB/mlx5: Update counter implementation for dual port RoCE") Link: https://lore.kernel.org/r/98b82994c3cd3fa593b8a75ed3f3901e208beb0f.1672231736.git.leonro@nvidia.com Signed-off-by: Shay Drory Reviewed-by: Patrisious Haddad Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/counters.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c index 945758f39523..3e1272695d99 100644 --- a/drivers/infiniband/hw/mlx5/counters.c +++ b/drivers/infiniband/hw/mlx5/counters.c @@ -278,7 +278,6 @@ static int do_get_hw_stats(struct ib_device *ibdev, const struct mlx5_ib_counters *cnts = get_counters(dev, port_num - 1); struct mlx5_core_dev *mdev; int ret, num_counters; - u32 mdev_port_num; if (!stats) return -EINVAL; @@ -299,8 +298,9 @@ static int do_get_hw_stats(struct ib_device *ibdev, } if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) { - mdev = mlx5_ib_get_native_port_mdev(dev, port_num, - &mdev_port_num); + if (!port_num) + port_num = 1; + mdev = mlx5_ib_get_native_port_mdev(dev, port_num, NULL); if (!mdev) { /* If port is not affiliated yet, its in down state * which doesn't have any counters yet, so it would be From 8de8482fe5732fbef4f5af82bc0c0362c804cd1f Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 28 Dec 2022 14:56:10 +0200 Subject: [PATCH 028/233] RDMA/mlx5: Fix validation of max_rd_atomic caps for DC Currently, when modifying DC, we validate max_rd_atomic user attribute against the RC cap, validate against DC. RC and DC QP types have different device limitations. This can cause userspace created DC QPs to malfunction. Fixes: c32a4f296e1d ("IB/mlx5: Add support for DC Initiator QP") Link: https://lore.kernel.org/r/0c5aee72cea188c3bb770f4207cce7abc9b6fc74.1672231736.git.leonro@nvidia.com Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/qp.c | 49 +++++++++++++++++++++++---------- 1 file changed, 35 insertions(+), 14 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 40d9410ec303..cf953d23d18d 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4502,6 +4502,40 @@ static bool mlx5_ib_modify_qp_allowed(struct mlx5_ib_dev *dev, return false; } +static int validate_rd_atomic(struct mlx5_ib_dev *dev, struct ib_qp_attr *attr, + int attr_mask, enum ib_qp_type qp_type) +{ + int log_max_ra_res; + int log_max_ra_req; + + if (qp_type == MLX5_IB_QPT_DCI) { + log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev, + log_max_ra_res_dc); + log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev, + log_max_ra_req_dc); + } else { + log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev, + log_max_ra_res_qp); + log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev, + log_max_ra_req_qp); + } + + if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC && + attr->max_rd_atomic > log_max_ra_res) { + mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n", + attr->max_rd_atomic); + return false; + } + + if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC && + attr->max_dest_rd_atomic > log_max_ra_req) { + mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n", + attr->max_dest_rd_atomic); + return false; + } + return true; +} + int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { @@ -4589,21 +4623,8 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, goto out; } - if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC && - attr->max_rd_atomic > - (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_res_qp))) { - mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n", - attr->max_rd_atomic); + if (!validate_rd_atomic(dev, attr, attr_mask, qp_type)) goto out; - } - - if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC && - attr->max_dest_rd_atomic > - (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_req_qp))) { - mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n", - attr->max_dest_rd_atomic); - goto out; - } if (cur_state == new_state && cur_state == IB_QPS_RESET) { err = 0; From 029085b8949f5d269ae2bbd14915407dd0c7f902 Mon Sep 17 00:00:00 2001 From: Chengen Du Date: Fri, 30 Dec 2022 11:04:32 +0800 Subject: [PATCH 029/233] NFS: Judge the file access cache's timestamp in rcu path If the user's login time is newer than the cache's timestamp, we expect the cache may be stale and need to clear. The stale cache will remain in the list's tail if no other users operate on that inode. Once the user accesses the inode, the stale cache will be returned in rcu path. Signed-off-by: Chengen Du Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index ea1ceffa1d3a..d490d64a9ebd 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -3023,6 +3023,7 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre * but do it without locking. */ struct nfs_inode *nfsi = NFS_I(inode); + u64 login_time = nfs_access_login_time(current, cred); struct nfs_access_entry *cache; int err = -ECHILD; struct list_head *lh; @@ -3037,6 +3038,8 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre cache = NULL; if (cache == NULL) goto out; + if ((s64)(login_time - cache->timestamp) > 0) + goto out; if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) goto out; *mask = cache->mask; From 5e9a7b9c2ea18551759833146a181b14835bfe39 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 1 Jan 2023 20:17:23 -0500 Subject: [PATCH 030/233] NFS: Fix up a sparse warning sparse is warning about an incorrect RCU dereference. fs/nfs/dir.c:2965:56: warning: incorrect type in argument 1 (different address spaces) fs/nfs/dir.c:2965:56: expected struct cred const * fs/nfs/dir.c:2965:56: got struct cred const [noderef] __rcu *const cred Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index d490d64a9ebd..f7e4a88d5d92 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2957,12 +2957,14 @@ static u64 nfs_access_login_time(const struct task_struct *task, const struct cred *cred) { const struct task_struct *parent; + const struct cred *pcred; u64 ret; rcu_read_lock(); for (;;) { parent = rcu_dereference(task->real_parent); - if (parent == task || cred_fscmp(parent->cred, cred) != 0) + pcred = rcu_dereference(parent->cred); + if (parent == task || cred_fscmp(pcred, cred) != 0) break; task = parent; } From cdfb2fef522d0c3f9cf293db51de88e9b3d46846 Mon Sep 17 00:00:00 2001 From: Marios Makassikis Date: Fri, 23 Dec 2022 11:59:31 +0100 Subject: [PATCH 031/233] ksmbd: send proper error response in smb2_tree_connect() Currently, smb2_tree_connect doesn't send an error response packet on error. This causes libsmb2 to skip the specific error code and fail with the following: smb2_service failed with : Failed to parse fixed part of command payload. Unexpected size of Error reply. Expected 9, got 8 Signed-off-by: Marios Makassikis Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 14d7f3599c63..38fbda52e06f 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1928,13 +1928,13 @@ int smb2_tree_connect(struct ksmbd_work *work) if (conn->posix_ext_supported) status.tree_conn->posix_extensions = true; -out_err1: rsp->StructureSize = cpu_to_le16(16); + inc_rfc1001_len(work->response_buf, 16); +out_err1: rsp->Capabilities = 0; rsp->Reserved = 0; /* default manual caching */ rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING; - inc_rfc1001_len(work->response_buf, 16); if (!IS_ERR(treename)) kfree(treename); @@ -1967,6 +1967,9 @@ out_err1: rsp->hdr.Status = STATUS_ACCESS_DENIED; } + if (status.ret != KSMBD_TREE_CONN_STATUS_OK) + smb2_set_err_rsp(work); + return rc; } From 797805d81baa814f76cf7bdab35f86408a79d707 Mon Sep 17 00:00:00 2001 From: William Liu Date: Fri, 30 Dec 2022 13:03:15 +0900 Subject: [PATCH 032/233] ksmbd: check nt_len to be at least CIFS_ENCPWD_SIZE in ksmbd_decode_ntlmssp_auth_blob MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit "nt_len - CIFS_ENCPWD_SIZE" is passed directly from ksmbd_decode_ntlmssp_auth_blob to ksmbd_auth_ntlmv2. Malicious requests can set nt_len to less than CIFS_ENCPWD_SIZE, which results in a negative number (or large unsigned value) used for a subsequent memcpy in ksmbd_auth_ntlvm2 and can cause a panic. Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Cc: stable@vger.kernel.org Signed-off-by: William Liu Signed-off-by: Hrvoje Mišetić Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/auth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index 2a39ffb8423b..6e61b5bc7d86 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -322,7 +322,8 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, dn_off = le32_to_cpu(authblob->DomainName.BufferOffset); dn_len = le16_to_cpu(authblob->DomainName.Length); - if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len) + if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len || + nt_len < CIFS_ENCPWD_SIZE) return -EINVAL; /* TODO : use domain name that imported from configuration file */ From 83dcedd5540d4ac61376ddff5362f7d9f866a6ec Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 31 Dec 2022 17:32:31 +0900 Subject: [PATCH 033/233] ksmbd: fix infinite loop in ksmbd_conn_handler_loop() If kernel_recvmsg() return -EAGAIN in ksmbd_tcp_readv() and go round again, It will cause infinite loop issue. And all threads from next connections would be doing that. This patch add max retry count(2) to avoid it. kernel_recvmsg() will wait during 7sec timeout and try to retry two time if -EAGAIN is returned. And add flags of kvmalloc to __GFP_NOWARN and __GFP_NORETRY to disconnect immediately without retrying on memory alloation failure. Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers") Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-18259 Reviewed-by: Sergey Senozhatsky Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/connection.c | 7 +++++-- fs/ksmbd/transport_tcp.c | 5 ++++- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 12be8386446a..fd0a288af299 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -316,9 +316,12 @@ int ksmbd_conn_handler_loop(void *p) /* 4 for rfc1002 length field */ size = pdu_size + 4; - conn->request_buf = kvmalloc(size, GFP_KERNEL); + conn->request_buf = kvmalloc(size, + GFP_KERNEL | + __GFP_NOWARN | + __GFP_NORETRY); if (!conn->request_buf) - continue; + break; memcpy(conn->request_buf, hdr_buf, sizeof(hdr_buf)); if (!ksmbd_smb_request(conn)) diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index 63d55f543bd2..4c6bd0b69979 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -295,6 +295,7 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, struct msghdr ksmbd_msg; struct kvec *iov; struct ksmbd_conn *conn = KSMBD_TRANS(t)->conn; + int max_retry = 2; iov = get_conn_iovec(t, nr_segs); if (!iov) @@ -321,9 +322,11 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, } else if (conn->status == KSMBD_SESS_NEED_RECONNECT) { total_read = -EAGAIN; break; - } else if (length == -ERESTARTSYS || length == -EAGAIN) { + } else if ((length == -ERESTARTSYS || length == -EAGAIN) && + max_retry) { usleep_range(1000, 2000); length = 0; + max_retry--; continue; } else if (length <= 0) { total_read = -EAGAIN; From 3b754ed6d1cd90017e66e5cc16f3923e4a952ffc Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Mon, 19 Dec 2022 09:43:05 +0100 Subject: [PATCH 034/233] drm/meson: Reduce the FIFO lines held when AFBC is not used Having a bigger number of FIFO lines held after vsync is only useful to SoCs using AFBC to give time to the AFBC decoder to be reset, configured and enabled again. For SoCs not using AFBC this, on the contrary, is causing on some displays issues and a few pixels vertical offset in the displayed image. Conditionally increase the number of lines held after vsync only for SoCs using AFBC, leaving the default value for all the others. Fixes: 24e0d4058eff ("drm/meson: hold 32 lines after vsync to give time for AFBC start") Signed-off-by: Carlo Caione Acked-by: Martin Blumenstingl Acked-by: Neil Armstrong [narmstrong: added fixes tag] Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20221216-afbc_s905x-v1-0-033bebf780d9@baylibre.com --- drivers/gpu/drm/meson/meson_viu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c index d4b907889a21..cd399b0b7181 100644 --- a/drivers/gpu/drm/meson/meson_viu.c +++ b/drivers/gpu/drm/meson/meson_viu.c @@ -436,15 +436,14 @@ void meson_viu_init(struct meson_drm *priv) /* Initialize OSD1 fifo control register */ reg = VIU_OSD_DDR_PRIORITY_URGENT | - VIU_OSD_HOLD_FIFO_LINES(31) | VIU_OSD_FIFO_DEPTH_VAL(32) | /* fifo_depth_val: 32*8=256 */ VIU_OSD_WORDS_PER_BURST(4) | /* 4 words in 1 burst */ VIU_OSD_FIFO_LIMITS(2); /* fifo_lim: 2*16=32 */ if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) - reg |= VIU_OSD_BURST_LENGTH_32; + reg |= (VIU_OSD_BURST_LENGTH_32 | VIU_OSD_HOLD_FIFO_LINES(31)); else - reg |= VIU_OSD_BURST_LENGTH_64; + reg |= (VIU_OSD_BURST_LENGTH_64 | VIU_OSD_HOLD_FIFO_LINES(4)); writel_relaxed(reg, priv->io_base + _REG(VIU_OSD1_FIFO_CTRL_STAT)); writel_relaxed(reg, priv->io_base + _REG(VIU_OSD2_FIFO_CTRL_STAT)); From 7adde5ac25fa50dbb1fb237042316685cafe976c Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Thu, 8 Dec 2022 11:36:20 +0000 Subject: [PATCH 035/233] mtd: parsers: Fix potential memory leak in mtd_parser_tplink_safeloader_parse() The parts needs to be freed with all its elements, otherwise it will be leaked. Fixes: 00a3588084be ("mtd: parsers: add TP-Link SafeLoader partitions table parser") Signed-off-by: Yuan Can Reviewed-by: Dan Carpenter Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20221208113620.78855-1-yuancan@huawei.com --- drivers/mtd/parsers/tplink_safeloader.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/parsers/tplink_safeloader.c b/drivers/mtd/parsers/tplink_safeloader.c index f601e7bd8627..1c689dafca2a 100644 --- a/drivers/mtd/parsers/tplink_safeloader.c +++ b/drivers/mtd/parsers/tplink_safeloader.c @@ -91,7 +91,7 @@ static int mtd_parser_tplink_safeloader_parse(struct mtd_info *mtd, buf = mtd_parser_tplink_safeloader_read_table(mtd); if (!buf) { err = -ENOENT; - goto err_out; + goto err_free_parts; } for (idx = 0, offset = TPLINK_SAFELOADER_DATA_OFFSET; @@ -118,6 +118,8 @@ static int mtd_parser_tplink_safeloader_parse(struct mtd_info *mtd, err_free: for (idx -= 1; idx >= 0; idx--) kfree(parts[idx].name); +err_free_parts: + kfree(parts); err_out: return err; }; From 105c14b84d93168431abba5d55e6c26fa4b65abb Mon Sep 17 00:00:00 2001 From: Mikhail Zhilkin Date: Thu, 8 Dec 2022 23:28:29 +0300 Subject: [PATCH 036/233] mtd: parsers: scpart: fix __udivdi3 undefined on mips This fixes the following compile error on mips architecture with clang version 16.0.0 reported by the 0-DAY CI Kernel Test Service: ld.lld: error: undefined symbol: __udivdi3 referenced by scpart.c mtd/parsers/scpart.o:(scpart_parse) in archive drivers/built-in.a As a workaround this makes 'offs' a 32-bit type. This is enough, because the mtd containing partition table practically does not exceed 1 MB. We can revert this when the [Link] has been resolved. Link: https://github.com/ClangBuiltLinux/linux/issues/1635 Fixes: 9b78ef0c7997 ("mtd: parsers: add support for Sercomm partitions") Reported-by: kernel test robot Suggested-by: Arnd Bergmann Signed-off-by: Mikhail Zhilkin Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/805fe58e-690f-6a3f-5ebf-2f6f6e6e4599@gmail.com --- drivers/mtd/parsers/scpart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/parsers/scpart.c b/drivers/mtd/parsers/scpart.c index 02601bb33de4..6e5e11c37078 100644 --- a/drivers/mtd/parsers/scpart.c +++ b/drivers/mtd/parsers/scpart.c @@ -50,7 +50,7 @@ static int scpart_scan_partmap(struct mtd_info *master, loff_t partmap_offs, int cnt = 0; int res = 0; int res2; - loff_t offs; + uint32_t offs; size_t retlen; struct sc_part_desc *pdesc = NULL; struct sc_part_desc *tmpdesc; From d19ab1f785d0b6b9f709799f0938658903821ba1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 20 Dec 2022 15:13:34 +0100 Subject: [PATCH 037/233] mtd: cfi: allow building spi-intel standalone When MTD or MTD_CFI_GEOMETRY is disabled, the spi-intel driver fails to build, as it includes the shared CFI header: include/linux/mtd/cfi.h:62:2: error: #warning No CONFIG_MTD_CFI_Ix selected. No NOR chip support can work. [-Werror=cpp] 62 | #warning No CONFIG_MTD_CFI_Ix selected. No NOR chip support can work. linux/mtd/spi-nor.h does not actually need to include cfi.h, so remove the inclusion here to fix the warning. This uncovers a missing #include in spi-nor/core.c so add that there to prevent a different build issue. Fixes: e23e5a05d1fd ("mtd: spi-nor: intel-spi: Convert to SPI MEM") Signed-off-by: Arnd Bergmann Reviewed-by: Mika Westerberg Reviewed-by: Tokunori Ikegami Acked-by: Pratyush Yadav Reviewed-by: Tudor Ambarus Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20221220141352.1486360-1-arnd@kernel.org --- drivers/mtd/spi-nor/core.c | 1 + include/linux/mtd/spi-nor.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index d8703d7dfd0a..d67c926bca8b 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 25765556223a..a3f8cdca90c8 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -7,7 +7,6 @@ #define __LINUX_MTD_SPI_NOR_H #include -#include #include #include From 461ab10ef7e6ea9b41a0571a7fc6a72af9549a3c Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 17 Nov 2022 10:43:21 +0800 Subject: [PATCH 038/233] ceph: switch to vfs_inode_has_locks() to fix file lock bug For the POSIX locks they are using the same owner, which is the thread id. And multiple POSIX locks could be merged into single one, so when checking whether the 'file' has locks may fail. For a file where some openers use locking and others don't is a really odd usage pattern though. Locks are like stoplights -- they only work if everyone pays attention to them. Just switch ceph_get_caps() to check whether any locks are set on the inode. If there are POSIX/OFD/FLOCK locks on the file at the time, we should set CHECK_FILELOCK, regardless of what fd was used to set the lock. Fixes: ff5d913dfc71 ("ceph: return -EIO if read/write against filp that lost file locks") Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 2 +- fs/ceph/locks.c | 4 ---- fs/ceph/super.h | 1 - 3 files changed, 1 insertion(+), 6 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 4b159f97fe7b..f75ad432f375 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2913,7 +2913,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got while (true) { flags &= CEPH_FILE_MODE_MASK; - if (atomic_read(&fi->num_locks)) + if (vfs_inode_has_locks(inode)) flags |= CHECK_FILELOCK; _got = 0; ret = try_get_cap_refs(inode, need, want, endoff, diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index f3b461c708a8..6b3b8c299c17 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -32,18 +32,14 @@ void __init ceph_flock_init(void) static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src) { - struct ceph_file_info *fi = dst->fl_file->private_data; struct inode *inode = file_inode(dst->fl_file); atomic_inc(&ceph_inode(inode)->i_filelock_ref); - atomic_inc(&fi->num_locks); } static void ceph_fl_release_lock(struct file_lock *fl) { - struct ceph_file_info *fi = fl->fl_file->private_data; struct inode *inode = file_inode(fl->fl_file); struct ceph_inode_info *ci = ceph_inode(inode); - atomic_dec(&fi->num_locks); if (atomic_dec_and_test(&ci->i_filelock_ref)) { /* clear error when all locks are released */ spin_lock(&ci->i_ceph_lock); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 30bdb391a0dc..0ed3be75bb9a 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -790,7 +790,6 @@ struct ceph_file_info { struct list_head rw_contexts; u32 filp_gen; - atomic_t num_locks; }; struct ceph_dir_file_info { From 8e1858710d9a71d88acd922f2e95d1eddb90eea0 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 17 Nov 2022 10:57:53 +0800 Subject: [PATCH 039/233] ceph: avoid use-after-free in ceph_fl_release_lock() When ceph releasing the file_lock it will try to get the inode pointer from the fl->fl_file, which the memory could already be released by another thread in filp_close(). Because in VFS layer the fl->fl_file doesn't increase the file's reference counter. Will switch to use ceph dedicate lock info to track the inode. And in ceph_fl_release_lock() we should skip all the operations if the fl->fl_u.ceph.inode is not set, which should come from the request file_lock. And we will set fl->fl_u.ceph.inode when inserting it to the inode lock list, which is when copying the lock. Link: https://tracker.ceph.com/issues/57986 Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/locks.c | 20 ++++++++++++++++++-- include/linux/fs.h | 3 +++ 2 files changed, 21 insertions(+), 2 deletions(-) diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 6b3b8c299c17..9c8dc8a55e7e 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -34,18 +34,34 @@ static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src) { struct inode *inode = file_inode(dst->fl_file); atomic_inc(&ceph_inode(inode)->i_filelock_ref); + dst->fl_u.ceph.inode = igrab(inode); } +/* + * Do not use the 'fl->fl_file' in release function, which + * is possibly already released by another thread. + */ static void ceph_fl_release_lock(struct file_lock *fl) { - struct inode *inode = file_inode(fl->fl_file); - struct ceph_inode_info *ci = ceph_inode(inode); + struct inode *inode = fl->fl_u.ceph.inode; + struct ceph_inode_info *ci; + + /* + * If inode is NULL it should be a request file_lock, + * nothing we can do. + */ + if (!inode) + return; + + ci = ceph_inode(inode); if (atomic_dec_and_test(&ci->i_filelock_ref)) { /* clear error when all locks are released */ spin_lock(&ci->i_ceph_lock); ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK; spin_unlock(&ci->i_ceph_lock); } + fl->fl_u.ceph.inode = NULL; + iput(inode); } static const struct file_lock_operations ceph_fl_lock_ops = { diff --git a/include/linux/fs.h b/include/linux/fs.h index 066555ad1bf8..c1769a2c5d70 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1119,6 +1119,9 @@ struct file_lock { int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; + struct { + struct inode *inode; + } ceph; } fl_u; } __randomize_layout; From a764da46cd15f8b40292d2c0b29c4bf9a3e66c7e Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Wed, 9 Nov 2022 17:19:05 +0800 Subject: [PATCH 040/233] drm/virtio: Fix memory leak in virtio_gpu_object_create() The virtio_gpu_object_shmem_init() will alloc memory and save it in @ents, so when virtio_gpu_array_alloc() fails, this memory should be freed, this patch fixes it. Fixes: e7fef0923303 ("drm/virtio: Simplify error handling of virtio_gpu_object_create()") Signed-off-by: Xiu Jianfeng Reviewed-by: Dmitry Osipenko Signed-off-by: Dmitry Osipenko Link: https://patchwork.freedesktop.org/patch/msgid/20221109091905.55451-1-xiujianfeng@huawei.com --- drivers/gpu/drm/virtio/virtgpu_object.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 8d7728181de0..c7e74cf13022 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -184,7 +184,7 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev, struct virtio_gpu_object_array *objs = NULL; struct drm_gem_shmem_object *shmem_obj; struct virtio_gpu_object *bo; - struct virtio_gpu_mem_entry *ents; + struct virtio_gpu_mem_entry *ents = NULL; unsigned int nents; int ret; @@ -210,7 +210,7 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev, ret = -ENOMEM; objs = virtio_gpu_array_alloc(1); if (!objs) - goto err_put_id; + goto err_free_entry; virtio_gpu_array_add_obj(objs, &bo->base.base); ret = virtio_gpu_array_lock_resv(objs); @@ -239,6 +239,8 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev, err_put_objs: virtio_gpu_array_put_free(objs); +err_free_entry: + kvfree(ents); err_put_id: virtio_gpu_resource_id_put(vgdev, bo->hw_res_handle); err_free_gem: From 03dec92c4f788c54a7c01b40a018f601eb8a6c52 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 23 Nov 2022 03:13:03 +0300 Subject: [PATCH 041/233] drm/scheduler: Fix lockup in drm_sched_entity_kill() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The drm_sched_entity_kill() is invoked twice by drm_sched_entity_destroy() while userspace process is exiting or being killed. First time it's invoked when sched entity is flushed and second time when entity is released. This causes a lockup within wait_for_completion(entity_idle) due to how completion API works. Calling wait_for_completion() more times than complete() was invoked is a error condition that causes lockup because completion internally uses counter for complete/wait calls. The complete_all() must be used instead in such cases. This patch fixes lockup of Panfrost driver that is reproducible by killing any application in a middle of 3d drawing operation. Fixes: 2fdb8a8f07c2 ("drm/scheduler: rework entity flush, kill and fini") Signed-off-by: Dmitry Osipenko Reviewed-by: Christian König Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://patchwork.freedesktop.org/patch/msgid/20221123001303.533968-1-dmitry.osipenko@collabora.com --- drivers/gpu/drm/scheduler/sched_entity.c | 2 +- drivers/gpu/drm/scheduler/sched_main.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index fe09e5be79bd..15d04a0ec623 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -81,7 +81,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, init_completion(&entity->entity_idle); /* We start in an idle state. */ - complete(&entity->entity_idle); + complete_all(&entity->entity_idle); spin_lock_init(&entity->rq_lock); spsc_queue_init(&entity->job_queue); diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 31f3a1267be4..fd22d753b4ed 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -987,7 +987,7 @@ static int drm_sched_main(void *param) sched_job = drm_sched_entity_pop_job(entity); if (!sched_job) { - complete(&entity->entity_idle); + complete_all(&entity->entity_idle); continue; } @@ -998,7 +998,7 @@ static int drm_sched_main(void *param) trace_drm_run_job(sched_job, entity); fence = sched->ops->run_job(sched_job); - complete(&entity->entity_idle); + complete_all(&entity->entity_idle); drm_sched_fence_scheduled(s_fence); if (!IS_ERR_OR_NULL(fence)) { From 0a6564ebd953c4590663c9a3c99a3ea9920ade6f Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Thu, 29 Dec 2022 13:09:00 +0400 Subject: [PATCH 042/233] perf tools: Fix resources leak in perf_data__open_dir() In perf_data__open_dir(), opendir() opens the directory stream. Add missing closedir() to release it after use. Fixes: eb6176709b235b96 ("perf data: Add perf_data__open_dir_data function") Reviewed-by: Adrian Hunter Signed-off-by: Miaoqian Lin Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20221229090903.1402395-1-linmq006@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index a7f68c309545..fc16299c915f 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -132,6 +132,7 @@ int perf_data__open_dir(struct perf_data *data) file->size = st.st_size; } + closedir(dir); if (!files) return -EINVAL; @@ -140,6 +141,7 @@ int perf_data__open_dir(struct perf_data *data) return 0; out_err: + closedir(dir); close_dir(files, nr); return ret; } From a8f54d940196c8bd9aced9c82557fdc63baefb02 Mon Sep 17 00:00:00 2001 From: Eric Lin Date: Sat, 31 Dec 2022 05:27:31 +0000 Subject: [PATCH 043/233] perf tools riscv: Fix build error on riscv due to missing header for 'struct perf_sample' Since the definition of 'struct perf_sample' has been moved to sample.h, we need to include this header file to fix the build error as follows: arch/riscv/util/unwind-libdw.c: In function 'libdw__arch_set_initial_registers': arch/riscv/util/unwind-libdw.c:12:50: error: invalid use of undefined type 'struct perf_sample' 12 | struct regs_dump *user_regs = &ui->sample->user_regs; | ^~ Fixes: 9823147da6c893d9 ("perf tools: Move 'struct perf_sample' to a separate header file to disentangle headers") Signed-off-by: Eric Lin Cc: Alexander Shishkin Cc: greentime.hu@sifive.com Cc: Jiri Olsa Cc: linux-riscv@lists.infradead.org Cc: Namhyung Kim Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Vincent Chen Link: https://lore.kernel.org/r/20221231052731.24908-1-eric.lin@sifive.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/riscv/util/unwind-libdw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/riscv/util/unwind-libdw.c b/tools/perf/arch/riscv/util/unwind-libdw.c index 19536e172850..54a198714eb8 100644 --- a/tools/perf/arch/riscv/util/unwind-libdw.c +++ b/tools/perf/arch/riscv/util/unwind-libdw.c @@ -4,7 +4,7 @@ #include #include "../../util/unwind-libdw.h" #include "../../util/perf_regs.h" -#include "../../util/event.h" +#include "../../util/sample.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { From 55c41f2e4f7e81e48f3ecc9fba1e316e770213f2 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Mon, 26 Dec 2022 08:57:03 +0000 Subject: [PATCH 044/233] perf help: Use HAVE_LIBTRACEEVENT to filter out unsupported commands Commands such as kmem, kwork, lock, sched, trace and timechart depend on libtraceevent, these commands need to be isolated using HAVE_LIBTRACEEVENT macro when cmdlist generation. The output of the generate-cmdlist.sh script is as follows: # ./util/generate-cmdlist.sh /* Automatically generated by ./util/generate-cmdlist.sh */ struct cmdname_help { char name[16]; char help[80]; }; static struct cmdname_help common_cmds[] = { {"annotate", "Read perf.data (created by perf record) and display annotated code"}, {"archive", "Create archive with object files with build-ids found in perf.data file"}, {"bench", "General framework for benchmark suites"}, {"buildid-cache", "Manage build-id cache."}, {"buildid-list", "List the buildids in a perf.data file"}, {"c2c", "Shared Data C2C/HITM Analyzer."}, {"config", "Get and set variables in a configuration file."}, {"daemon", "Run record sessions on background"}, {"data", "Data file related processing"}, {"diff", "Read perf.data files and display the differential profile"}, {"evlist", "List the event names in a perf.data file"}, {"ftrace", "simple wrapper for kernel's ftrace functionality"}, {"inject", "Filter to augment the events stream with additional information"}, {"iostat", "Show I/O performance metrics"}, {"kallsyms", "Searches running kernel for symbols"}, {"kvm", "Tool to trace/measure kvm guest os"}, {"list", "List all symbolic event types"}, {"mem", "Profile memory accesses"}, {"record", "Run a command and record its profile into perf.data"}, {"report", "Read perf.data (created by perf record) and display the profile"}, {"script", "Read perf.data (created by perf record) and display trace output"}, {"stat", "Run a command and gather performance counter statistics"}, {"test", "Runs sanity tests."}, {"top", "System profiling tool."}, {"version", "display the version of perf binary"}, #ifdef HAVE_LIBELF_SUPPORT {"probe", "Define new dynamic tracepoints"}, #endif /* HAVE_LIBELF_SUPPORT */ #if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)) {"trace", "strace inspired tool"}, #endif /* HAVE_LIBTRACEEVENT && (HAVE_LIBAUDIT_SUPPORT || HAVE_SYSCALL_TABLE_SUPPORT) */ #ifdef HAVE_LIBTRACEEVENT {"kmem", "Tool to trace/measure kernel memory properties"}, {"kwork", "Tool to trace/measure kernel work properties (latencies)"}, {"lock", "Analyze lock events"}, {"sched", "Tool to trace/measure scheduler properties (latencies)"}, {"timechart", "Tool to visualize total system behavior during a workload"}, #endif /* HAVE_LIBTRACEEVENT */ }; Fixes: 378ef0f5d9d7f465 ("perf build: Use libtraceevent from the system") Signed-off-by: Yang Jihong Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20221226085703.95081-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/command-list.txt | 10 +++++----- tools/perf/util/generate-cmdlist.sh | 19 +++++++++++++++++-- 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index 8fcab5ad00c5..e8d2762adade 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -16,20 +16,20 @@ perf-ftrace mainporcelain common perf-inject mainporcelain common perf-iostat mainporcelain common perf-kallsyms mainporcelain common -perf-kmem mainporcelain common +perf-kmem mainporcelain traceevent perf-kvm mainporcelain common -perf-kwork mainporcelain common +perf-kwork mainporcelain traceevent perf-list mainporcelain common -perf-lock mainporcelain common +perf-lock mainporcelain traceevent perf-mem mainporcelain common perf-probe mainporcelain full perf-record mainporcelain common perf-report mainporcelain common -perf-sched mainporcelain common +perf-sched mainporcelain traceevent perf-script mainporcelain common perf-stat mainporcelain common perf-test mainporcelain common -perf-timechart mainporcelain common +perf-timechart mainporcelain traceevent perf-top mainporcelain common perf-trace mainporcelain audit perf-version mainporcelain common diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index c3cef36d4176..1b5140e5ce99 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -38,7 +38,7 @@ do done echo "#endif /* HAVE_LIBELF_SUPPORT */" -echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)" +echo "#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT))" sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt | sort | while read cmd @@ -51,5 +51,20 @@ do p }' "Documentation/perf-$cmd.txt" done -echo "#endif /* HAVE_LIBELF_SUPPORT */" +echo "#endif /* HAVE_LIBTRACEEVENT && (HAVE_LIBAUDIT_SUPPORT || HAVE_SYSCALL_TABLE_SUPPORT) */" + +echo "#ifdef HAVE_LIBTRACEEVENT" +sed -n -e 's/^perf-\([^ ]*\)[ ].* traceevent.*/\1/p' command-list.txt | +sort | +while read cmd +do + sed -n ' + /^NAME/,/perf-'"$cmd"'/H + ${ + x + s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ + p + }' "Documentation/perf-$cmd.txt" +done +echo "#endif /* HAVE_LIBTRACEEVENT */" echo "};" From 92d43bd3bc9728c1fb114d7011d46f5ea9489e28 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Tue, 8 Nov 2022 15:14:20 +0100 Subject: [PATCH 045/233] drm/imx: ipuv3-plane: Fix overlay plane width ipu_src_rect_width() was introduced to support odd screen resolutions such as 1366x768 by internally rounding up primary plane width to a multiple of 8 and compensating with reduced horizontal blanking. This also caused overlay plane width to be rounded up, which was not intended. Fix overlay plane width by limiting the rounding up to the primary plane. drm_rect_width(&new_state->src) >> 16 is the same value as drm_rect_width(dst) because there is no plane scaling support. Fixes: 94dfec48fca7 ("drm/imx: Add 8 pixel alignment fix") Reviewed-by: Lucas Stach Link: https://lore.kernel.org/r/20221108141420.176696-1-p.zabel@pengutronix.de Signed-off-by: Philipp Zabel Link: https://patchwork.freedesktop.org/patch/msgid/20221108141420.176696-1-p.zabel@pengutronix.de Tested-by: Ian Ray (cherry picked from commit 4333472f8d7befe62359fecb1083cd57a6e07bfc) Signed-off-by: Philipp Zabel --- drivers/gpu/drm/imx/ipuv3-plane.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index dba4f7d81d69..80142d9a4a55 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -614,6 +614,11 @@ static void ipu_plane_atomic_update(struct drm_plane *plane, break; } + if (ipu_plane->dp_flow == IPU_DP_FLOW_SYNC_BG) + width = ipu_src_rect_width(new_state); + else + width = drm_rect_width(&new_state->src) >> 16; + eba = drm_plane_state_to_eba(new_state, 0); /* @@ -622,8 +627,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane, */ if (ipu_state->use_pre) { axi_id = ipu_chan_assign_axi_id(ipu_plane->dma); - ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id, - ipu_src_rect_width(new_state), + ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id, width, drm_rect_height(&new_state->src) >> 16, fb->pitches[0], fb->format->format, fb->modifier, &eba); @@ -678,9 +682,8 @@ static void ipu_plane_atomic_update(struct drm_plane *plane, break; } - ipu_dmfc_config_wait4eot(ipu_plane->dmfc, ALIGN(drm_rect_width(dst), 8)); + ipu_dmfc_config_wait4eot(ipu_plane->dmfc, width); - width = ipu_src_rect_width(new_state); height = drm_rect_height(&new_state->src) >> 16; info = drm_format_info(fb->format->format); ipu_calculate_bursts(width, info->cpp[0], fb->pitches[0], @@ -744,8 +747,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane, ipu_cpmem_set_burstsize(ipu_plane->ipu_ch, 16); ipu_cpmem_zero(ipu_plane->alpha_ch); - ipu_cpmem_set_resolution(ipu_plane->alpha_ch, - ipu_src_rect_width(new_state), + ipu_cpmem_set_resolution(ipu_plane->alpha_ch, width, drm_rect_height(&new_state->src) >> 16); ipu_cpmem_set_format_passthrough(ipu_plane->alpha_ch, 8); ipu_cpmem_set_high_priority(ipu_plane->alpha_ch); From f24fb53984cfba42ff72a47466eabfd772da647b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ahelenia=20Ziemia=C5=84ska?= Date: Tue, 27 Dec 2022 21:58:00 +0100 Subject: [PATCH 046/233] perf tools: Don't include signature in version strings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This explodes the build if HEAD is signed, since the generated version is gpg: Signature made Mon 26 Dec 2022 20:34:48 CET, then a few more lines, then the SHA. Signed-off-by: Ahelenia Ziemiańska Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/7c9637711271f50ec2341fb8a7c29585335dab04.1672174189.git.nabijaczleweli@nabijaczleweli.xyz Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/Makefile | 2 +- tools/perf/util/PERF-VERSION-GEN | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 6e7b88917ca0..ba5d942e4c6a 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -267,7 +267,7 @@ $(OUTPUT)%.xml : %.txt $(ASCIIDOC) -b docbook -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \ -aperf_date=$(shell git log -1 --pretty="format:%cd" \ - --date=short $<) \ + --date=short --no-show-signature $<) \ -o $@+ $< && \ mv $@+ $@ diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 3cc42821d9b3..d7dc7c28508c 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -19,7 +19,7 @@ TAG= if test -d ../../.git -o -f ../../.git then TAG=$(MAKEFLAGS= make -sC ../.. kernelversion) - CID=$(git log -1 --abbrev=12 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID" + CID=$(git log -1 --abbrev=12 --pretty=format:"%h" --no-show-signature 2>/dev/null) && CID="-g$CID" elif test -f ../../PERF-VERSION-FILE then TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g') From 77fe30fed1c0cd282eadb0728999ea3d3350e0b0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 2 Jan 2023 13:06:45 -0300 Subject: [PATCH 047/233] perf tools: Fix segfault when trying to process tracepoints in perf.data and not linked with libtraceevent When we have a perf.data file with tracepoints, such as: # perf evlist -f probe_perf:lzma_decompress_to_file # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events # We end up segfaulting when using perf built with NO_LIBTRACEEVENT=1 by trying to find an evsel with a NULL 'event_name' variable: (gdb) run report --stdio -f Starting program: /root/bin/perf report --stdio -f Program received signal SIGSEGV, Segmentation fault. 0x000000000055219d in find_evsel (evlist=0xfda7b0, event_name=0x0) at util/sort.c:2830 warning: Source file is more recent than executable. 2830 if (event_name[0] == '%') { Missing separate debuginfos, use: dnf debuginfo-install bzip2-libs-1.0.8-11.fc36.x86_64 cyrus-sasl-lib-2.1.27-18.fc36.x86_64 elfutils-debuginfod-client-0.188-3.fc36.x86_64 elfutils-libelf-0.188-3.fc36.x86_64 elfutils-libs-0.188-3.fc36.x86_64 glibc-2.35-20.fc36.x86_64 keyutils-libs-1.6.1-4.fc36.x86_64 krb5-libs-1.19.2-12.fc36.x86_64 libbrotli-1.0.9-7.fc36.x86_64 libcap-2.48-4.fc36.x86_64 libcom_err-1.46.5-2.fc36.x86_64 libcurl-7.82.0-12.fc36.x86_64 libevent-2.1.12-6.fc36.x86_64 libgcc-12.2.1-4.fc36.x86_64 libidn2-2.3.4-1.fc36.x86_64 libnghttp2-1.51.0-1.fc36.x86_64 libpsl-0.21.1-5.fc36.x86_64 libselinux-3.3-4.fc36.x86_64 libssh-0.9.6-4.fc36.x86_64 libstdc++-12.2.1-4.fc36.x86_64 libunistring-1.0-1.fc36.x86_64 libunwind-1.6.2-2.fc36.x86_64 libxcrypt-4.4.33-4.fc36.x86_64 libzstd-1.5.2-2.fc36.x86_64 numactl-libs-2.0.14-5.fc36.x86_64 opencsd-1.2.0-1.fc36.x86_64 openldap-2.6.3-1.fc36.x86_64 openssl-libs-3.0.5-2.fc36.x86_64 slang-2.3.2-11.fc36.x86_64 xz-libs-5.2.5-9.fc36.x86_64 zlib-1.2.11-33.fc36.x86_64 (gdb) bt #0 0x000000000055219d in find_evsel (evlist=0xfda7b0, event_name=0x0) at util/sort.c:2830 #1 0x0000000000552416 in add_dynamic_entry (evlist=0xfda7b0, tok=0xffb6eb "trace", level=2) at util/sort.c:2976 #2 0x0000000000552d26 in sort_dimension__add (list=0xf93e00 , tok=0xffb6eb "trace", evlist=0xfda7b0, level=2) at util/sort.c:3193 #3 0x0000000000552e1c in setup_sort_list (list=0xf93e00 , str=0xffb6eb "trace", evlist=0xfda7b0) at util/sort.c:3227 #4 0x00000000005532fa in __setup_sorting (evlist=0xfda7b0) at util/sort.c:3381 #5 0x0000000000553cdc in setup_sorting (evlist=0xfda7b0) at util/sort.c:3608 #6 0x000000000042eb9f in cmd_report (argc=0, argv=0x7fffffffe470) at builtin-report.c:1596 #7 0x00000000004aee7e in run_builtin (p=0xf64ca0 , argc=3, argv=0x7fffffffe470) at perf.c:330 #8 0x00000000004af0f2 in handle_internal_command (argc=3, argv=0x7fffffffe470) at perf.c:384 #9 0x00000000004af241 in run_argv (argcp=0x7fffffffe29c, argv=0x7fffffffe290) at perf.c:428 #10 0x00000000004af5fc in main (argc=3, argv=0x7fffffffe470) at perf.c:562 (gdb) So check if we have tracepoint events in add_dynamic_entry() and bail out instead: # perf report --stdio -f This perf binary isn't linked with libtraceevent, can't process probe_perf:lzma_decompress_to_file Error: Unknown --sort key: `trace' # Fixes: 378ef0f5d9d7f465 ("perf build: Use libtraceevent from the system") Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lore.kernel.org/lkml/Y7MDb7kRaHZB6APC@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index e188f74698dd..37662cdec5ee 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2971,6 +2971,18 @@ static int add_dynamic_entry(struct evlist *evlist, const char *tok, ret = add_all_matching_fields(evlist, field_name, raw_trace, level); goto out; } +#else + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) { + pr_err("%s %s", ret ? "," : "This perf binary isn't linked with libtraceevent, can't process", evsel__name(evsel)); + ret = -ENOTSUP; + } + } + + if (ret) { + pr_err("\n"); + goto out; + } #endif evsel = find_evsel(evlist, event_name); From 5b24ac2dfd3eb3e36f794af3aa7f2828b19035bd Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Thu, 22 Dec 2022 23:28:21 -0800 Subject: [PATCH 048/233] kcsan: test: don't put the expect array on the stack Size of the 'expect' array in the __report_matches is 1536 bytes, which is exactly the default frame size warning limit of the xtensa architecture. As a result allmodconfig xtensa kernel builds with the gcc that does not support the compiler plugins (which otherwise would push the said warning limit to 2K) fail with the following message: kernel/kcsan/kcsan_test.c:257:1: error: the frame size of 1680 bytes is larger than 1536 bytes Fix it by dynamically allocating the 'expect' array. Signed-off-by: Max Filippov Reviewed-by: Marco Elver Tested-by: Marco Elver --- kernel/kcsan/kcsan_test.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index dcec1b743c69..a60c561724be 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -159,7 +159,7 @@ static bool __report_matches(const struct expect_report *r) const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT; bool ret = false; unsigned long flags; - typeof(observed.lines) expect; + typeof(*observed.lines) *expect; const char *end; char *cur; int i; @@ -168,6 +168,10 @@ static bool __report_matches(const struct expect_report *r) if (!report_available()) return false; + expect = kmalloc(sizeof(observed.lines), GFP_KERNEL); + if (WARN_ON(!expect)) + return false; + /* Generate expected report contents. */ /* Title */ @@ -253,6 +257,7 @@ static bool __report_matches(const struct expect_report *r) strstr(observed.lines[2], expect[1]))); out: spin_unlock_irqrestore(&observed.lock, flags); + kfree(expect); return ret; } From af82425c6a2d2f347c79b63ce74fca6dc6be157f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 2 Jan 2023 16:49:46 -0700 Subject: [PATCH 049/233] io_uring/io-wq: free worker if task_work creation is canceled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we cancel the task_work, the worker will never come into existance. As this is the last reference to it, ensure that we get it freed appropriately. Cc: stable@vger.kernel.org Reported-by: 진호 Signed-off-by: Jens Axboe --- io_uring/io-wq.c | 1 + 1 file changed, 1 insertion(+) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 6f1d0e5df23a..992dcd9f8c4c 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1230,6 +1230,7 @@ static void io_wq_cancel_tw_create(struct io_wq *wq) worker = container_of(cb, struct io_worker, create_work); io_worker_cancel_cb(worker); + kfree(worker); } } From f3cb80804b8295323919e031281768ba3bf5f8da Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 2 Jan 2023 19:28:49 -0800 Subject: [PATCH 050/233] time: Fix various kernel-doc problems Clean up kernel-doc complaints about function names and non-kernel-doc comments in kernel/time/. Fixes these warnings: kernel/time/time.c:479: warning: expecting prototype for set_normalized_timespec(). Prototype was for set_normalized_timespec64() instead kernel/time/time.c:553: warning: expecting prototype for msecs_to_jiffies(). Prototype was for __msecs_to_jiffies() instead kernel/time/timekeeping.c:1595: warning: contents before sections kernel/time/timekeeping.c:1705: warning: This comment starts with '/**', but isn't a kernel-doc comment. * We have three kinds of time sources to use for sleep time kernel/time/timekeeping.c:1726: warning: This comment starts with '/**', but isn't a kernel-doc comment. * 1) can be determined whether to use or not only when doing kernel/time/tick-oneshot.c:21: warning: missing initial short description on line: * tick_program_event kernel/time/tick-oneshot.c:107: warning: expecting prototype for tick_check_oneshot_mode(). Prototype was for tick_oneshot_mode_active() instead Signed-off-by: Randy Dunlap Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230103032849.12723-1-rdunlap@infradead.org --- kernel/time/tick-oneshot.c | 4 ++-- kernel/time/time.c | 8 ++++---- kernel/time/timekeeping.c | 8 ++++---- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 475ecceda768..5e2c2c26b3cc 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -18,7 +18,7 @@ #include "tick-internal.h" /** - * tick_program_event + * tick_program_event - program the CPU local timer device for the next event */ int tick_program_event(ktime_t expires, int force) { @@ -99,7 +99,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) } /** - * tick_check_oneshot_mode - check whether the system is in oneshot mode + * tick_oneshot_mode_active - check whether the system is in oneshot mode * * returns 1 when either nohz or highres are enabled. otherwise 0. */ diff --git a/kernel/time/time.c b/kernel/time/time.c index 526257b3727c..f4198af60fee 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -462,7 +462,7 @@ struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec) EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** - * set_normalized_timespec - set timespec sec and nsec parts and normalize + * set_normalized_timespec64 - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set @@ -526,7 +526,7 @@ struct timespec64 ns_to_timespec64(s64 nsec) EXPORT_SYMBOL(ns_to_timespec64); /** - * msecs_to_jiffies: - convert milliseconds to jiffies + * __msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: @@ -541,12 +541,12 @@ EXPORT_SYMBOL(ns_to_timespec64); * handling any 32-bit overflows. * for the details see __msecs_to_jiffies() * - * msecs_to_jiffies() checks for the passed in value being a constant + * __msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. - * the _msecs_to_jiffies helpers are the HZ dependent conversion + * The _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h */ unsigned long __msecs_to_jiffies(const unsigned int m) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index f72b9f1de178..5579ead449f2 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1590,10 +1590,10 @@ void __weak read_persistent_clock64(struct timespec64 *ts) /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. + * @wall_time: current time as returned by persistent clock + * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. - * @wall_time: - current time as returned by persistent clock - * @boot_offset: - offset that is defined as wall_time - boot_time * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't @@ -1701,7 +1701,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) -/** +/* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource @@ -1722,7 +1722,7 @@ bool timekeeping_rtc_skipresume(void) return !suspend_timing_needed; } -/** +/* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). From 69555549cfa42e10f2fdd2699ed4e34d9d4f392b Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 23 Nov 2022 03:13:03 +0300 Subject: [PATCH 051/233] drm/scheduler: Fix lockup in drm_sched_entity_kill() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The drm_sched_entity_kill() is invoked twice by drm_sched_entity_destroy() while userspace process is exiting or being killed. First time it's invoked when sched entity is flushed and second time when entity is released. This causes a lockup within wait_for_completion(entity_idle) due to how completion API works. Calling wait_for_completion() more times than complete() was invoked is a error condition that causes lockup because completion internally uses counter for complete/wait calls. The complete_all() must be used instead in such cases. This patch fixes lockup of Panfrost driver that is reproducible by killing any application in a middle of 3d drawing operation. Fixes: 2fdb8a8f07c2 ("drm/scheduler: rework entity flush, kill and fini") Signed-off-by: Dmitry Osipenko Reviewed-by: Christian König Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://patchwork.freedesktop.org/patch/msgid/20221123001303.533968-1-dmitry.osipenko@collabora.com --- drivers/gpu/drm/scheduler/sched_entity.c | 2 +- drivers/gpu/drm/scheduler/sched_main.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index fe09e5be79bd..15d04a0ec623 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -81,7 +81,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, init_completion(&entity->entity_idle); /* We start in an idle state. */ - complete(&entity->entity_idle); + complete_all(&entity->entity_idle); spin_lock_init(&entity->rq_lock); spsc_queue_init(&entity->job_queue); diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 31f3a1267be4..fd22d753b4ed 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -987,7 +987,7 @@ static int drm_sched_main(void *param) sched_job = drm_sched_entity_pop_job(entity); if (!sched_job) { - complete(&entity->entity_idle); + complete_all(&entity->entity_idle); continue; } @@ -998,7 +998,7 @@ static int drm_sched_main(void *param) trace_drm_run_job(sched_job, entity); fence = sched->ops->run_job(sched_job); - complete(&entity->entity_idle); + complete_all(&entity->entity_idle); drm_sched_fence_scheduled(s_fence); if (!IS_ERR_OR_NULL(fence)) { From b963c1d6261eb7fba1ba14074fb447521be84add Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 3 Jan 2023 10:21:01 -0300 Subject: [PATCH 052/233] perf test record_probe_libc_inet_pton: Fix failure due to extra inet_pton() backtrace in glibc >= 2.35 Starting with glibc 2.35 there are extra inet_pton() calls when doing a IPv6 ping as in one of the 'perf test' entry, which makes it fail: # perf test inet_pton 89: probe libc's inet_pton & backtrace it with ping : FAILED! # If we look at what this script is expecting (commenting out the removal of the temporary files in it): # cat /tmp/expected.aT6 ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\) .*inet_pton\+0x[[:xdigit:]]+[[:space:]]\(/usr/lib64/libc.so.6|inlined\)$ getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\(/usr/lib64/libc.so.6\)$ .*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$ # And looking at what we are getting out of 'perf script', to match with the above: # cat /tmp/perf.script.IUC ping 623883 [006] 265438.471610: probe_libc:inet_pton: (7f32bcf314c0) 1314c0 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6) 29510 __libc_start_call_main+0x80 (/usr/lib64/libc.so.6) ping 623883 [006] 265438.471664: probe_libc:inet_pton: (7f32bcf314c0) 1314c0 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6) fa6c6 getaddrinfo+0x126 (/usr/lib64/libc.so.6) 491e [unknown] (/usr/bin/ping) # We see that its just the first call to inet_pton() that didn't came thru getaddrinfo(), so if we ignore the first the script matches what it expects, testing that using 'perf probe' + 'perf record' + 'perf script' with callchains on userspace targets is producing the expected results. Since we don't have a 'perf script --skip' to help us here, use tac + grep to do that, resulting in a one liner that makes this script work on both older glibc versions as well as with 2.35. With it, on fedora 36, x86, glibc 2.35: # perf test inet_pton 90: probe libc's inet_pton & backtrace it with ping : Ok # perf test -v inet_pton 90: probe libc's inet_pton & backtrace it with ping : --- start --- test child forked, pid 627197 ping 627220 1 267956.962402: probe_libc:inet_pton_1: (7f488bf314c0) 1314c0 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6) fa6c6 getaddrinfo+0x126 (/usr/lib64/libc.so.6) 491e n (/usr/bin/ping) test child finished with 0 ---- end ---- probe libc's inet_pton & backtrace it with ping: Ok # And on Ubuntu 22.04.1 LTS on a Libre Computer ROC-RK3399-PC arm64 system: Before this patch it works (see that the script used has no 'tac' to remove the first event): root@roc-rk3399-pc:~# dpkg -l | grep libc-bin ii libc-bin 2.35-0ubuntu3.1 arm64 GNU C Library: Binaries root@roc-rk3399-pc:~# grep -w tac ~acme/libexec/perf-core/tests/shell/record+probe_libc_inet_pton.sh root@roc-rk3399-pc:~# perf test inet_pton 86: probe libc's inet_pton & backtrace it with ping : Ok root@roc-rk3399-pc:~# perf test -v inet_pton 86: probe libc's inet_pton & backtrace it with ping : --- start --- test child forked, pid 1375 ping 1399 [000] 4114.417450: probe_libc:inet_pton: (ffffb3e26120) 106120 inet_pton+0x0 (/usr/lib/aarch64-linux-gnu/libc.so.6) d18bc getaddrinfo+0xec (/usr/lib/aarch64-linux-gnu/libc.so.6) 2b68 [unknown] (/usr/bin/ping) test child finished with 0 ---- end ---- probe libc's inet_pton & backtrace it with ping: Ok root@roc-rk3399-pc:~# And after it continues to work: root@roc-rk3399-pc:~# grep -w tac ~acme/libexec/perf-core/tests/shell/record+probe_libc_inet_pton.sh perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script root@roc-rk3399-pc:~# perf test inet_pton 86: probe libc's inet_pton & backtrace it with ping : Ok root@roc-rk3399-pc:~# perf test -v inet_pton 86: probe libc's inet_pton & backtrace it with ping : --- start --- test child forked, pid 6995 ping 7019 [005] 4832.160741: probe_libc:inet_pton: (ffffa62e6120) 106120 inet_pton+0x0 (/usr/lib/aarch64-linux-gnu/libc.so.6) d18bc getaddrinfo+0xec (/usr/lib/aarch64-linux-gnu/libc.so.6) 2b68 [unknown] (/usr/bin/ping) test child finished with 0 ---- end ---- probe libc's inet_pton & backtrace it with ping: Ok root@roc-rk3399-pc:~# Reported-by: Thomas Richter Cc: Adrian Hunter Cc: Heiko Carstens Cc: Ian Rogers Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Vasily Gorbik Link: http://lore.kernel.org/lkml/Y7QyPkPlDYip3cZH@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 34c400ccbe04..216b6b64caa3 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -57,7 +57,7 @@ trace_libc_inet_pton_backtrace() { perf_data=`mktemp -u /tmp/perf.data.XXX` perf_script=`mktemp -u /tmp/perf.script.XXX` perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 - perf script -i $perf_data > $perf_script + perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script exec 3<$perf_script exec 4<$expected From 946c2923e76327343e4460e8bb7ec7b4d4589397 Mon Sep 17 00:00:00 2001 From: Tanmay Bhushan <007047221b@gmail.com> Date: Sat, 31 Dec 2022 16:05:01 +0100 Subject: [PATCH 053/233] btrfs: fix ASSERT em->len condition in btrfs_get_extent The em->len value is supposed to be verified in the assertion condition though we expect it to be same as the sectorsize. Fixes: a196a8944f77 ("btrfs: do not reset extent map members for inline extents read") Reviewed-by: Anand Jain Signed-off-by: Tanmay Bhushan <007047221b@gmail.com> Signed-off-by: David Sterba --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index bfcbe64eb8b3..940b404c8f28 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7092,7 +7092,7 @@ next: * Other members are not utilized for inline extents. */ ASSERT(em->block_start == EXTENT_MAP_INLINE); - ASSERT(em->len = fs_info->sectorsize); + ASSERT(em->len == fs_info->sectorsize); ret = read_inline_extent(inode, path, page); if (ret < 0) From 77177ed17d24ba060117bdb6efb8a01da7531676 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 29 Dec 2022 07:32:23 +0800 Subject: [PATCH 054/233] btrfs: add error message for metadata level mismatch From a recent regression report, we found that after commit 947a629988f1 ("btrfs: move tree block parentness check into validate_extent_buffer()") if we have a level mismatch (false alert though), there is no error message at all. This makes later debugging harder. This patch will add the proper error message for such case. Link: https://lore.kernel.org/linux-btrfs/CABXGCsNzVxo4iq-tJSGm_kO1UggHXgq6CdcHDL=z5FL4njYXSQ@mail.gmail.com/ Reviewed-by: Anand Jain Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0888d484df80..9940cc39dbc9 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -530,6 +530,9 @@ static int validate_extent_buffer(struct extent_buffer *eb, } if (found_level != check->level) { + btrfs_err(fs_info, + "level verify failed on logical %llu mirror %u wanted %u found %u", + eb->start, eb->read_mirror, check->level, found_level); ret = -EIO; goto out; } From 1d854e4fbabb0cb12ca4a7fcd784eb67a65de5f8 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 29 Dec 2022 07:32:24 +0800 Subject: [PATCH 055/233] btrfs: fix false alert on bad tree level check [BUG] There is a bug report that on a RAID0 NVMe btrfs system, under heavy write load the filesystem can flip RO randomly. With extra debugging, it shows some tree blocks failed to pass their level checks, and if that happens at critical path of a transaction, we abort the transaction: BTRFS error (device nvme0n1p3): level verify failed on logical 5446121209856 mirror 1 wanted 0 found 1 BTRFS error (device nvme0n1p3: state A): Transaction aborted (error -5) BTRFS: error (device nvme0n1p3: state A) in btrfs_finish_ordered_io:3343: errno=-5 IO failure BTRFS info (device nvme0n1p3: state EA): forced readonly [CAUSE] The reporter has already bisected to commit 947a629988f1 ("btrfs: move tree block parentness check into validate_extent_buffer()"). And with extra debugging, it shows we can have btrfs_tree_parent_check filled with all zeros in the following call trace: submit_one_bio+0xd4/0xe0 submit_extent_page+0x142/0x550 read_extent_buffer_pages+0x584/0x9c0 ? __pfx_end_bio_extent_readpage+0x10/0x10 ? folio_unlock+0x1d/0x50 btrfs_read_extent_buffer+0x98/0x150 read_tree_block+0x43/0xa0 read_block_for_search+0x266/0x370 btrfs_search_slot+0x351/0xd30 ? lock_is_held_type+0xe8/0x140 btrfs_lookup_csum+0x63/0x150 btrfs_csum_file_blocks+0x197/0x6c0 ? sched_clock_cpu+0x9f/0xc0 ? lock_release+0x14b/0x440 ? _raw_read_unlock+0x29/0x50 btrfs_finish_ordered_io+0x441/0x860 btrfs_work_helper+0xfe/0x400 ? lock_is_held_type+0xe8/0x140 process_one_work+0x294/0x5b0 worker_thread+0x4f/0x3a0 ? __pfx_worker_thread+0x10/0x10 kthread+0xf5/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2c/0x50 Currently we only copy the btrfs_tree_parent_check structure into bbio at read_extent_buffer_pages() after we have assembled the bbio. But as shown above, submit_extent_page() itself can already submit the bbio, leaving the bbio->parent_check uninitialized, and cause the false alert. [FIX] Instead of copying @check into bbio after bbio is assembled, we pass @check in btrfs_bio_ctrl::parent_check, and copy the content of parent_check in submit_one_bio() for metadata read. By this we should be able to pass the needed info for metadata endio verification, and fix the false alert. Reported-by: Mikhail Gavrilov Link: https://lore.kernel.org/linux-btrfs/CABXGCsNzVxo4iq-tJSGm_kO1UggHXgq6CdcHDL=z5FL4njYXSQ@mail.gmail.com/ Fixes: 947a629988f1 ("btrfs: move tree block parentness check into validate_extent_buffer()") Tested-by: Mikhail Gavrilov Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 83dd3aa59663..9bd32daa9b9a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -103,6 +103,15 @@ struct btrfs_bio_ctrl { u32 len_to_oe_boundary; btrfs_bio_end_io_t end_io_func; + /* + * This is for metadata read, to provide the extra needed verification + * info. This has to be provided for submit_one_bio(), as + * submit_one_bio() can submit a bio if it ends at stripe boundary. If + * no such parent_check is provided, the metadata can hit false alert at + * endio time. + */ + struct btrfs_tree_parent_check *parent_check; + /* * Tell writepage not to lock the state bits for this range, it still * does the unlocking. @@ -133,13 +142,24 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) btrfs_bio(bio)->file_offset = page_offset(bv->bv_page) + bv->bv_offset; - if (!is_data_inode(&inode->vfs_inode)) + if (!is_data_inode(&inode->vfs_inode)) { + if (btrfs_op(bio) != BTRFS_MAP_WRITE) { + /* + * For metadata read, we should have the parent_check, + * and copy it to bbio for metadata verification. + */ + ASSERT(bio_ctrl->parent_check); + memcpy(&btrfs_bio(bio)->parent_check, + bio_ctrl->parent_check, + sizeof(struct btrfs_tree_parent_check)); + } btrfs_submit_metadata_bio(inode, bio, mirror_num); - else if (btrfs_op(bio) == BTRFS_MAP_WRITE) + } else if (btrfs_op(bio) == BTRFS_MAP_WRITE) { btrfs_submit_data_write_bio(inode, bio, mirror_num); - else + } else { btrfs_submit_data_read_bio(inode, bio, mirror_num, bio_ctrl->compress_type); + } /* The bio is owned by the end_io handler now */ bio_ctrl->bio = NULL; @@ -4829,6 +4849,7 @@ static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait, struct extent_state *cached_state = NULL; struct btrfs_bio_ctrl bio_ctrl = { .mirror_num = mirror_num, + .parent_check = check, }; int ret = 0; @@ -4878,7 +4899,6 @@ static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait, */ atomic_dec(&eb->io_pages); } - memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check)); submit_one_bio(&bio_ctrl); if (ret || wait != WAIT_COMPLETE) { free_extent_state(cached_state); @@ -4905,6 +4925,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, unsigned long num_reads = 0; struct btrfs_bio_ctrl bio_ctrl = { .mirror_num = mirror_num, + .parent_check = check, }; if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) @@ -4996,7 +5017,6 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, } } - memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check)); submit_one_bio(&bio_ctrl); if (ret || wait != WAIT_COMPLETE) From 2f2e84ca60660402bd81d0859703567c59556e6a Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 23 Dec 2022 18:28:53 +0000 Subject: [PATCH 056/233] btrfs: fix off-by-one in delalloc search during lseek MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit During lseek, when searching for delalloc in a range that represents a hole and that range has a length of 1 byte, we end up not doing the actual delalloc search in the inode's io tree, resulting in not correctly reporting the offset with data or a hole. This actually only happens when the start offset is 0 because with any other start offset we round it down by sector size. Reproducer: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt/sdc $ xfs_io -f -c "pwrite -q 0 1" /mnt/sdc/foo $ xfs_io -c "seek -d 0" /mnt/sdc/foo Whence Result DATA EOF It should have reported an offset of 0 instead of EOF. Fix this by updating btrfs_find_delalloc_in_range() and count_range_bits() to deal with inclusive ranges properly. These functions are already supposed to work with inclusive end offsets, they just got it wrong in a couple places due to off-by-one mistakes. A test case for fstests will be added later. Reported-by: Joan Bruguera Micó Link: https://lore.kernel.org/linux-btrfs/20221223020509.457113-1-joanbrugueram@gmail.com/ Fixes: b6e833567ea1 ("btrfs: make hole and data seeking a lot more efficient") CC: stable@vger.kernel.org # 6.1 Tested-by: Joan Bruguera Micó Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/extent-io-tree.c | 2 +- fs/btrfs/file.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c index 9ae9cd1e7035..3c7766dfaa69 100644 --- a/fs/btrfs/extent-io-tree.c +++ b/fs/btrfs/extent-io-tree.c @@ -1551,7 +1551,7 @@ u64 count_range_bits(struct extent_io_tree *tree, u64 last = 0; int found = 0; - if (WARN_ON(search_end <= cur_start)) + if (WARN_ON(search_end < cur_start)) return 0; spin_lock(&tree->lock); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 91b00eb2440e..834bbcb91102 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3354,7 +3354,7 @@ bool btrfs_find_delalloc_in_range(struct btrfs_inode *inode, u64 start, u64 end, bool search_io_tree = true; bool ret = false; - while (cur_offset < end) { + while (cur_offset <= end) { u64 delalloc_start; u64 delalloc_end; bool delalloc; From d73a27b86fc722c28a26ec64002e3a7dc86d1c07 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Sun, 1 Jan 2023 09:02:21 +0800 Subject: [PATCH 057/233] btrfs: handle case when repair happens with dev-replace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [BUG] There is a bug report that a BUG_ON() in btrfs_repair_io_failure() (originally repair_io_failure() in v6.0 kernel) got triggered when replacing a unreliable disk: BTRFS warning (device sda1): csum failed root 257 ino 2397453 off 39624704 csum 0xb0d18c75 expected csum 0x4dae9c5e mirror 3 kernel BUG at fs/btrfs/extent_io.c:2380! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 9 PID: 3614331 Comm: kworker/u257:2 Tainted: G OE 6.0.0-5-amd64 #1 Debian 6.0.10-2 Hardware name: Micro-Star International Co., Ltd. MS-7C60/TRX40 PRO WIFI (MS-7C60), BIOS 2.70 07/01/2021 Workqueue: btrfs-endio btrfs_end_bio_work [btrfs] RIP: 0010:repair_io_failure+0x24a/0x260 [btrfs] Call Trace: clean_io_failure+0x14d/0x180 [btrfs] end_bio_extent_readpage+0x412/0x6e0 [btrfs] ? __switch_to+0x106/0x420 process_one_work+0x1c7/0x380 worker_thread+0x4d/0x380 ? rescuer_thread+0x3a0/0x3a0 kthread+0xe9/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 [CAUSE] Before the BUG_ON(), we got some read errors from the replace target first, note the mirror number (3, which is beyond RAID1 duplication, thus it's read from the replace target device). Then at the BUG_ON() location, we are trying to writeback the repaired sectors back the failed device. The check looks like this: ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical, &map_length, &bioc, mirror_num); if (ret) goto out_counter_dec; BUG_ON(mirror_num != bioc->mirror_num); But inside btrfs_map_block(), we can modify bioc->mirror_num especially for dev-replace: if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 && !need_full_stripe(op) && dev_replace->tgtdev != NULL) { ret = get_extra_mirror_from_replace(fs_info, logical, *length, dev_replace->srcdev->devid, &mirror_num, &physical_to_patch_in_first_stripe); patch_the_first_stripe_for_dev_replace = 1; } Thus if we're repairing the replace target device, we're going to trigger that BUG_ON(). But in reality, the read failure from the replace target device may be that, our replace hasn't reached the range we're reading, thus we're reading garbage, but with replace running, the range would be properly filled later. Thus in that case, we don't need to do anything but let the replace routine to handle it. [FIX] Instead of a BUG_ON(), just skip the repair if we're repairing the device replace target device. Reported-by: 小太 Link: https://lore.kernel.org/linux-btrfs/CACsxjPYyJGQZ+yvjzxA1Nn2LuqkYqTCcUH43S=+wXhyf8S00Ag@mail.gmail.com/ CC: stable@vger.kernel.org # 6.0+ Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/bio.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index b8fb7ef6b520..8affc88b0e0a 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -329,7 +329,16 @@ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, &map_length, &bioc, mirror_num); if (ret) goto out_counter_dec; - BUG_ON(mirror_num != bioc->mirror_num); + /* + * This happens when dev-replace is also running, and the + * mirror_num indicates the dev-replace target. + * + * In this case, we don't need to do anything, as the read + * error just means the replace progress hasn't reached our + * read range, and later replace routine would handle it well. + */ + if (mirror_num != bioc->mirror_num) + goto out_counter_dec; } sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9; From 39f501d68ec1ed5cd5c66ac6ec2a7131c517bb92 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 26 Dec 2022 09:00:40 +0800 Subject: [PATCH 058/233] btrfs: always report error in run_one_delayed_ref() Currently we have a btrfs_debug() for run_one_delayed_ref() failure, but if end users hit such problem, there will be no chance that btrfs_debug() is enabled. This can lead to very little useful info for debugging. This patch will: - Add extra info for error reporting Including: * logical bytenr * num_bytes * type * action * ref_mod - Replace the btrfs_debug() with btrfs_err() - Move the error reporting into run_one_delayed_ref() This is to avoid use-after-free, the @node can be freed in the caller. This error should only be triggered at most once. As if run_one_delayed_ref() failed, we trigger the error message, then causing the call chain to error out: btrfs_run_delayed_refs() `- btrfs_run_delayed_refs() `- btrfs_run_delayed_refs_for_head() `- run_one_delayed_ref() And we will abort the current transaction in btrfs_run_delayed_refs(). If we have to run delayed refs for the abort transaction, run_one_delayed_ref() will just cleanup the refs and do nothing, thus no new error messages would be output. Reviewed-by: Anand Jain Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 892d78c1853c..72ba13b027a9 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1713,6 +1713,11 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, BUG(); if (ret && insert_reserved) btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1); + if (ret < 0) + btrfs_err(trans->fs_info, +"failed to run delayed ref for logical %llu num_bytes %llu type %u action %u ref_mod %d: %d", + node->bytenr, node->num_bytes, node->type, + node->action, node->ref_mod, ret); return ret; } @@ -1954,8 +1959,6 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, if (ret) { unselect_delayed_ref_head(delayed_refs, locked_ref); btrfs_put_delayed_ref(ref); - btrfs_debug(fs_info, "run_one_delayed_ref returned %d", - ret); return ret; } From 2ba48b20049b5a76f34a85f853c9496d1b10533a Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 22 Dec 2022 07:59:17 +0800 Subject: [PATCH 059/233] btrfs: fix compat_ro checks against remount [BUG] Even with commit 81d5d61454c3 ("btrfs: enhance unsupported compat RO flags handling"), btrfs can still mount a fs with unsupported compat_ro flags read-only, then remount it RW: # btrfs ins dump-super /dev/loop0 | grep compat_ro_flags -A 3 compat_ro_flags 0x403 ( FREE_SPACE_TREE | FREE_SPACE_TREE_VALID | unknown flag: 0x400 ) # mount /dev/loop0 /mnt/btrfs mount: /mnt/btrfs: wrong fs type, bad option, bad superblock on /dev/loop0, missing codepage or helper program, or other error. dmesg(1) may have more information after failed mount system call. ^^^ RW mount failed as expected ^^^ # dmesg -t | tail -n5 loop0: detected capacity change from 0 to 1048576 BTRFS: device fsid cb5b82f5-0fdd-4d81-9b4b-78533c324afa devid 1 transid 7 /dev/loop0 scanned by mount (1146) BTRFS info (device loop0): using crc32c (crc32c-intel) checksum algorithm BTRFS info (device loop0): using free space tree BTRFS error (device loop0): cannot mount read-write because of unknown compat_ro features (0x403) BTRFS error (device loop0): open_ctree failed # mount /dev/loop0 -o ro /mnt/btrfs # mount -o remount,rw /mnt/btrfs ^^^ RW remount succeeded unexpectedly ^^^ [CAUSE] Currently we use btrfs_check_features() to check compat_ro flags against our current mount flags. That function get reused between open_ctree() and btrfs_remount(). But for btrfs_remount(), the super block we passed in still has the old mount flags, thus btrfs_check_features() still believes we're mounting read-only. [FIX] Replace the existing @sb argument with @is_rw_mount. As originally we only use @sb to determine if the mount is RW. Now it's callers' responsibility to determine if the mount is RW, and since there are only two callers, the check is pretty simple: - caller in open_ctree() Just pass !sb_rdonly(). - caller in btrfs_remount() Pass !(*flags & SB_RDONLY), as our check should be against the new flags. Now we can correctly reject the RW remount: # mount /dev/loop0 -o ro /mnt/btrfs # mount -o remount,rw /mnt/btrfs mount: /mnt/btrfs: mount point not mounted or bad option. dmesg(1) may have more information after failed mount system call. # dmesg -t | tail -n 1 BTRFS error (device loop0: state M): cannot mount read-write because of unknown compat_ro features (0x403) Reported-by: Chung-Chiang Cheng Fixes: 81d5d61454c3 ("btrfs: enhance unsupported compat RO flags handling") CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Anand Jain Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 8 +++++--- fs/btrfs/disk-io.h | 2 +- fs/btrfs/super.c | 2 +- 3 files changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9940cc39dbc9..8aeaada1fcae 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3384,6 +3384,8 @@ out: /* * Do various sanity and dependency checks of different features. * + * @is_rw_mount: If the mount is read-write. + * * This is the place for less strict checks (like for subpage or artificial * feature dependencies). * @@ -3394,7 +3396,7 @@ out: * (space cache related) can modify on-disk format like free space tree and * screw up certain feature dependencies. */ -int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb) +int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) { struct btrfs_super_block *disk_super = fs_info->super_copy; u64 incompat = btrfs_super_incompat_flags(disk_super); @@ -3433,7 +3435,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb) if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) incompat |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA; - if (compat_ro_unsupp && !sb_rdonly(sb)) { + if (compat_ro_unsupp && is_rw_mount) { btrfs_err(fs_info, "cannot mount read-write because of unknown compat_ro features (0x%llx)", compat_ro); @@ -3636,7 +3638,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_alloc; } - ret = btrfs_check_features(fs_info, sb); + ret = btrfs_check_features(fs_info, !sb_rdonly(sb)); if (ret < 0) { err = ret; goto fail_alloc; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 363935cfc084..f2f295eb6103 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -50,7 +50,7 @@ int __cold open_ctree(struct super_block *sb, void __cold close_ctree(struct btrfs_fs_info *fs_info); int btrfs_validate_super(struct btrfs_fs_info *fs_info, struct btrfs_super_block *sb, int mirror_num); -int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb); +int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount); int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors); struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev); struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index d5de18d6517e..433ce221dc5c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1705,7 +1705,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; - ret = btrfs_check_features(fs_info, sb); + ret = btrfs_check_features(fs_info, !(*flags & SB_RDONLY)); if (ret < 0) goto restore; From f528fe213a6ad21a6e8644dbd5de10dc264a89fd Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Mon, 2 Jan 2023 12:23:20 +0100 Subject: [PATCH 060/233] regulator: qcom-rpmh: PM8550 ldo11 regulator is an nldo This fixes the definition of the PM8550 ldo11 regulator matching it's capabilities since this LDO is designed to work between 1,2V and 1,5V. Fixes: e6e3776d682d ("regulator: qcom-rpmh: Add support for PM8550 regulators") Signed-off-by: Neil Armstrong Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230102-topic-sm8550-upstream-fixes-reg-l11b-nldo-v1-1-d97def246338@linaro.org Signed-off-by: Mark Brown --- drivers/regulator/qcom-rpmh-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c index 43b5b9377714..ae6021390143 100644 --- a/drivers/regulator/qcom-rpmh-regulator.c +++ b/drivers/regulator/qcom-rpmh-regulator.c @@ -1016,7 +1016,7 @@ static const struct rpmh_vreg_init_data pm8550_vreg_data[] = { RPMH_VREG("ldo8", "ldo%s8", &pmic5_pldo_lv, "vdd-l8-l9"), RPMH_VREG("ldo9", "ldo%s9", &pmic5_pldo, "vdd-l8-l9"), RPMH_VREG("ldo10", "ldo%s10", &pmic5_nldo, "vdd-l1-l4-l10"), - RPMH_VREG("ldo11", "ldo%s11", &pmic5_pldo, "vdd-l11"), + RPMH_VREG("ldo11", "ldo%s11", &pmic5_nldo, "vdd-l11"), RPMH_VREG("ldo12", "ldo%s12", &pmic5_pldo, "vdd-l12"), RPMH_VREG("ldo13", "ldo%s13", &pmic5_pldo, "vdd-l2-l13-l14"), RPMH_VREG("ldo14", "ldo%s14", &pmic5_pldo, "vdd-l2-l13-l14"), From c07311b5509f6035f1dd828db3e90ff4859cf3b9 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 28 Dec 2022 06:34:54 -0500 Subject: [PATCH 061/233] perf/x86/rapl: Treat Tigerlake like Icelake Since Tigerlake seems to have inherited its cstates and other RAPL power caps from Icelake, assume it also follows Icelake for its RAPL events. Signed-off-by: Chris Wilson Signed-off-by: Rodrigo Vivi Signed-off-by: Ingo Molnar Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Zhang Rui Link: https://lore.kernel.org/r/20221228113454.1199118-1-rodrigo.vivi@intel.com --- arch/x86/events/rapl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index a829492bca4c..ae5779ea4417 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -800,6 +800,8 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl), From c0f399ff51495ac8d30367418f4f6292ecd61fbe Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 26 Dec 2022 10:11:18 -0800 Subject: [PATCH 062/233] xfs: fix off-by-one error in xfs_btree_space_to_height Lately I've been stress-testing extreme-sized rmap btrees by using the (new) xfs_db bmap_inflate command to clone bmbt mappings billions of times and then using xfs_repair to build new rmap and refcount btrees. This of course is /much/ faster than actually FICLONEing a file billions of times. Unfortunately, xfs_repair fails in xfs_btree_bload_compute_geometry with EOVERFLOW, which indicates that xfs_mount.m_rmap_maxlevels is not sufficiently large for the test scenario. For a 1TB filesystem (~67 million AG blocks, 4 AGs) the btheight command reports: $ xfs_db -c 'btheight -n 4400801200 -w min rmapbt' /dev/sda rmapbt: worst case per 4096-byte block: 84 records (leaf) / 45 keyptrs (node) level 0: 4400801200 records, 52390491 blocks level 1: 52390491 records, 1164234 blocks level 2: 1164234 records, 25872 blocks level 3: 25872 records, 575 blocks level 4: 575 records, 13 blocks level 5: 13 records, 1 block 6 levels, 53581186 blocks total The AG is sufficiently large to build this rmap btree. Unfortunately, m_rmap_maxlevels is 5. Augmenting the loop in the space->height function to report height, node blocks, and blocks remaining produces this: ht 1 node_blocks 45 blockleft 67108863 ht 2 node_blocks 2025 blockleft 67108818 ht 3 node_blocks 91125 blockleft 67106793 ht 4 node_blocks 4100625 blockleft 67015668 final height: 5 The goal of this function is to compute the maximum height btree that can be stored in the given number of ondisk fsblocks. Starting with the top level of the tree, each iteration through the loop adds the fanout factor of the next level down until we run out of blocks. IOWs, maximum height is achieved by using the smallest fanout factor that can apply to that level. However, the loop setup is not correct. Top level btree blocks are allowed to contain fewer than minrecs items, so the computation is incorrect because the first time through the loop it should be using a fanout factor of 2. With this corrected, the above becomes: ht 1 node_blocks 2 blockleft 67108863 ht 2 node_blocks 90 blockleft 67108861 ht 3 node_blocks 4050 blockleft 67108771 ht 4 node_blocks 182250 blockleft 67104721 ht 5 node_blocks 8201250 blockleft 66922471 final height: 6 Fixes: 9ec691205e7d ("xfs: compute the maximum height of the rmap btree when reflink enabled") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_btree.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 4c16c8c31fcb..35f574421670 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4666,7 +4666,12 @@ xfs_btree_space_to_height( const unsigned int *limits, unsigned long long leaf_blocks) { - unsigned long long node_blocks = limits[1]; + /* + * The root btree block can have fewer than minrecs pointers in it + * because the tree might not be big enough to require that amount of + * fanout. Hence it has a minimum size of 2 pointers, not limits[1]. + */ + unsigned long long node_blocks = 2; unsigned long long blocks_left = leaf_blocks - 1; unsigned int height = 1; From 817644fa4525258992f17fecf4f1d6cdd2e1b731 Mon Sep 17 00:00:00 2001 From: Hironori Shiina Date: Mon, 26 Dec 2022 10:11:19 -0800 Subject: [PATCH 063/233] xfs: get root inode correctly at bulkstat The root inode number should be set to `breq->startino` for getting stat information of the root when XFS_BULK_IREQ_SPECIAL_ROOT is used. Otherwise, the inode search is started from 1 (XFS_BULK_IREQ_SPECIAL_ROOT) and the inode with the lowest number in a filesystem is returned. Fixes: bf3cb3944792 ("xfs: allow single bulkstat of special inodes") Signed-off-by: Hironori Shiina Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_ioctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 13f1b2add390..736510bc241b 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -754,7 +754,7 @@ xfs_bulkstat_fmt( static int xfs_bulk_ireq_setup( struct xfs_mount *mp, - struct xfs_bulk_ireq *hdr, + const struct xfs_bulk_ireq *hdr, struct xfs_ibulk *breq, void __user *ubuffer) { @@ -780,7 +780,7 @@ xfs_bulk_ireq_setup( switch (hdr->ino) { case XFS_BULK_IREQ_SPECIAL_ROOT: - hdr->ino = mp->m_sb.sb_rootino; + breq->startino = mp->m_sb.sb_rootino; break; default: return -EINVAL; From 4da112513c01d7d0acf1025b8764349d46e177d6 Mon Sep 17 00:00:00 2001 From: Wu Guanghao Date: Tue, 27 Dec 2022 09:41:30 -0800 Subject: [PATCH 064/233] xfs: Fix deadlock on xfs_inodegc_worker We are doing a test about deleting a large number of files when memory is low. A deadlock problem was found. [ 1240.279183] -> #1 (fs_reclaim){+.+.}-{0:0}: [ 1240.280450] lock_acquire+0x197/0x460 [ 1240.281548] fs_reclaim_acquire.part.0+0x20/0x30 [ 1240.282625] kmem_cache_alloc+0x2b/0x940 [ 1240.283816] xfs_trans_alloc+0x8a/0x8b0 [ 1240.284757] xfs_inactive_ifree+0xe4/0x4e0 [ 1240.285935] xfs_inactive+0x4e9/0x8a0 [ 1240.286836] xfs_inodegc_worker+0x160/0x5e0 [ 1240.287969] process_one_work+0xa19/0x16b0 [ 1240.289030] worker_thread+0x9e/0x1050 [ 1240.290131] kthread+0x34f/0x460 [ 1240.290999] ret_from_fork+0x22/0x30 [ 1240.291905] [ 1240.291905] -> #0 ((work_completion)(&gc->work)){+.+.}-{0:0}: [ 1240.293569] check_prev_add+0x160/0x2490 [ 1240.294473] __lock_acquire+0x2c4d/0x5160 [ 1240.295544] lock_acquire+0x197/0x460 [ 1240.296403] __flush_work+0x6bc/0xa20 [ 1240.297522] xfs_inode_mark_reclaimable+0x6f0/0xdc0 [ 1240.298649] destroy_inode+0xc6/0x1b0 [ 1240.299677] dispose_list+0xe1/0x1d0 [ 1240.300567] prune_icache_sb+0xec/0x150 [ 1240.301794] super_cache_scan+0x2c9/0x480 [ 1240.302776] do_shrink_slab+0x3f0/0xaa0 [ 1240.303671] shrink_slab+0x170/0x660 [ 1240.304601] shrink_node+0x7f7/0x1df0 [ 1240.305515] balance_pgdat+0x766/0xf50 [ 1240.306657] kswapd+0x5bd/0xd20 [ 1240.307551] kthread+0x34f/0x460 [ 1240.308346] ret_from_fork+0x22/0x30 [ 1240.309247] [ 1240.309247] other info that might help us debug this: [ 1240.309247] [ 1240.310944] Possible unsafe locking scenario: [ 1240.310944] [ 1240.312379] CPU0 CPU1 [ 1240.313363] ---- ---- [ 1240.314433] lock(fs_reclaim); [ 1240.315107] lock((work_completion)(&gc->work)); [ 1240.316828] lock(fs_reclaim); [ 1240.318088] lock((work_completion)(&gc->work)); [ 1240.319203] [ 1240.319203] *** DEADLOCK *** ... [ 2438.431081] Workqueue: xfs-inodegc/sda xfs_inodegc_worker [ 2438.432089] Call Trace: [ 2438.432562] __schedule+0xa94/0x1d20 [ 2438.435787] schedule+0xbf/0x270 [ 2438.436397] schedule_timeout+0x6f8/0x8b0 [ 2438.445126] wait_for_completion+0x163/0x260 [ 2438.448610] __flush_work+0x4c4/0xa40 [ 2438.455011] xfs_inode_mark_reclaimable+0x6ef/0xda0 [ 2438.456695] destroy_inode+0xc6/0x1b0 [ 2438.457375] dispose_list+0xe1/0x1d0 [ 2438.458834] prune_icache_sb+0xe8/0x150 [ 2438.461181] super_cache_scan+0x2b3/0x470 [ 2438.461950] do_shrink_slab+0x3cf/0xa50 [ 2438.462687] shrink_slab+0x17d/0x660 [ 2438.466392] shrink_node+0x87e/0x1d40 [ 2438.467894] do_try_to_free_pages+0x364/0x1300 [ 2438.471188] try_to_free_pages+0x26c/0x5b0 [ 2438.473567] __alloc_pages_slowpath.constprop.136+0x7aa/0x2100 [ 2438.482577] __alloc_pages+0x5db/0x710 [ 2438.485231] alloc_pages+0x100/0x200 [ 2438.485923] allocate_slab+0x2c0/0x380 [ 2438.486623] ___slab_alloc+0x41f/0x690 [ 2438.490254] __slab_alloc+0x54/0x70 [ 2438.491692] kmem_cache_alloc+0x23e/0x270 [ 2438.492437] xfs_trans_alloc+0x88/0x880 [ 2438.493168] xfs_inactive_ifree+0xe2/0x4e0 [ 2438.496419] xfs_inactive+0x4eb/0x8b0 [ 2438.497123] xfs_inodegc_worker+0x16b/0x5e0 [ 2438.497918] process_one_work+0xbf7/0x1a20 [ 2438.500316] worker_thread+0x8c/0x1060 [ 2438.504938] ret_from_fork+0x22/0x30 When the memory is insufficient, xfs_inonodegc_worker will trigger memory reclamation when memory is allocated, then flush_work() may be called to wait for the work to complete. This causes a deadlock. So use memalloc_nofs_save() to avoid triggering memory reclamation in xfs_inodegc_worker. Signed-off-by: Wu Guanghao Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_icache.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index f35e2cee5265..ddeaccc04aec 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1853,12 +1853,20 @@ xfs_inodegc_worker( struct xfs_inodegc, work); struct llist_node *node = llist_del_all(&gc->list); struct xfs_inode *ip, *n; + unsigned int nofs_flag; WRITE_ONCE(gc->items, 0); if (!node) return; + /* + * We can allocate memory here while doing writeback on behalf of + * memory reclaim. To avoid memory allocation deadlocks set the + * task-wide nofs context for the following operations. + */ + nofs_flag = memalloc_nofs_save(); + ip = llist_entry(node, struct xfs_inode, i_gclist); trace_xfs_inodegc_worker(ip->i_mount, READ_ONCE(gc->shrinker_hits)); @@ -1867,6 +1875,8 @@ xfs_inodegc_worker( xfs_iflags_set(ip, XFS_INACTIVATING); xfs_inodegc_inactivate(ip); } + + memalloc_nofs_restore(nofs_flag); } /* From e195605ed28b5581dc2d509283cfea2e8635a251 Mon Sep 17 00:00:00 2001 From: Li zeming Date: Tue, 3 Jan 2023 09:54:28 -0800 Subject: [PATCH 065/233] =?UTF-8?q?xfs:=20xfs=5Fqm:=20remove=20unnecessary?= =?UTF-8?q?=20=E2=80=980=E2=80=99=20values=20from=20error?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit error is assigned first, so it does not need to initialize the assignment. Signed-off-by: Li zeming Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_qm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index ff53d40a2dae..e2c542f6dcd4 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -68,7 +68,7 @@ restart: while (1) { struct xfs_dquot *batch[XFS_DQ_LOOKUP_BATCH]; - int error = 0; + int error; int i; mutex_lock(&qi->qi_tree_lock); From f89fb55714b620ff1352141a9f9315611f16573e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 2 Jan 2023 23:09:16 -0800 Subject: [PATCH 066/233] perf build: Don't propagate subdir to submakes for install_headers subdir is added to the OUTPUT which fails as part of building install_headers when passed from "make -C tools perf_install". Committer testing: The original reporter (see the Link: below) had trouble with this: $ make -C tools perf_install That ended up with errors like this: /var/home/acme/git/perf-urgent/tools/scripts/Makefile.include:17: *** output directory "/var/home/acme/git/perf-urgent/tools/perf/libperf/perf/" does not exist. Stop. With this patch applied we now get it installed at: INSTALL /var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h As expected: $ ls -la /var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h -rw-r--r--. 1 acme acme 1146 Jan 3 15:42 /var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h And if we clean tools with: $ make -C tools clean it gets cleaned up: $ ls -la /var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h ls: cannot access '/var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h': No such file or directory $ Fixes: 746bd29e348f99b4 ("perf build: Use tools/lib headers from install path") Reported-by: Torsten Hilbrich Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/fa4b3115-d555-3d7f-54d1-018002e99350@secunet.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 13e7d26e77f0..1e32c93b8042 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -819,7 +819,7 @@ $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) $(LIBAPI): FORCE | $(LIBAPI_OUTPUT) $(Q)$(MAKE) -C $(LIBAPI_DIR) O=$(LIBAPI_OUTPUT) \ - DESTDIR=$(LIBAPI_DESTDIR) prefix= \ + DESTDIR=$(LIBAPI_DESTDIR) prefix= subdir= \ $@ install_headers $(LIBAPI)-clean: @@ -828,7 +828,7 @@ $(LIBAPI)-clean: $(LIBBPF): FORCE | $(LIBBPF_OUTPUT) $(Q)$(MAKE) -C $(LIBBPF_DIR) FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) \ - O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \ + O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= subdir= \ $@ install_headers $(LIBBPF)-clean: @@ -837,7 +837,7 @@ $(LIBBPF)-clean: $(LIBPERF): FORCE | $(LIBPERF_OUTPUT) $(Q)$(MAKE) -C $(LIBPERF_DIR) O=$(LIBPERF_OUTPUT) \ - DESTDIR=$(LIBPERF_DESTDIR) prefix= \ + DESTDIR=$(LIBPERF_DESTDIR) prefix= subdir= \ $@ install_headers $(LIBPERF)-clean: @@ -846,7 +846,7 @@ $(LIBPERF)-clean: $(LIBSUBCMD): FORCE | $(LIBSUBCMD_OUTPUT) $(Q)$(MAKE) -C $(LIBSUBCMD_DIR) O=$(LIBSUBCMD_OUTPUT) \ - DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= \ + DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= subdir= \ $@ install_headers $(LIBSUBCMD)-clean: @@ -855,7 +855,7 @@ $(LIBSUBCMD)-clean: $(LIBSYMBOL): FORCE | $(LIBSYMBOL_OUTPUT) $(Q)$(MAKE) -C $(LIBSYMBOL_DIR) O=$(LIBSYMBOL_OUTPUT) \ - DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= \ + DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= subdir= \ $@ install_headers $(LIBSYMBOL)-clean: From d8d85ce86dc82de4f88b821a78f533b9d5b22a45 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 30 Dec 2022 11:26:27 +0100 Subject: [PATCH 067/233] perf lock contention: Fix core dump related to not finding the "__sched_text_end" symbol on s/390 The test case perf lock contention dumps core on s390. Run the following commands: # ./perf lock record -- ./perf bench sched messaging # Running 'sched/messaging' benchmark: # 20 sender and receiver processes per group # 10 groups == 400 processes run Total time: 2.799 [sec] [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.073 MB perf.data (100 samples) ] # # ./perf lock contention Segmentation fault (core dumped) # The function call stack is lengthy, here are the top 5 functions: # gdb ./perf core.24048 GNU gdb (GDB) Fedora Linux 12.1-6.fc37 Core was generated by `./perf lock contention'. Program terminated with signal SIGSEGV, Segmentation fault. #0 0x00000000011dd25c in machine__is_lock_function (machine=0x3029e28, addr=1789230) at util/machine.c:3356 3356 machine->sched.text_end = kmap->unmap_ip(kmap, sym->start); (gdb) where #0 0x00000000011dd25c in machine__is_lock_function (machine=0x3029e28, addr=1789230) at util/machine.c:3356 #1 0x000000000109f244 in callchain_id (evsel=0x30313e0, sample=0x3ffea4f77d0) at builtin-lock.c:957 #2 0x000000000109e094 in get_key_by_aggr_mode (key=0x3ffea4f7290, addr=27758136, evsel=0x30313e0, sample=0x3ffea4f77d0) at builtin-lock.c:586 #3 0x000000000109f4d0 in report_lock_contention_begin_event (evsel=0x30313e0, sample=0x3ffea4f77d0) at builtin-lock.c:1004 #4 0x00000000010a00ae in evsel__process_contention_begin (evsel=0x30313e0, sample=0x3ffea4f77d0) at builtin-lock.c:1254 #5 0x00000000010a0e14 in process_sample_event (tool=0x3ffea4f8480, event=0x3ff85601ef8, sample=0x3ffea4f77d0, evsel=0x30313e0, machine=0x3029e28) at builtin-lock.c:1464 ..... The issue is in function machine__is_lock_function() in file ./util/machine.c lines 3355: /* should not fail from here */ sym = machine__find_kernel_symbol_by_name(machine, "__sched_text_end", &kmap); machine->sched.text_end = kmap->unmap_ip(kmap, sym->start) On s390 the symbol __sched_text_end is *NOT* in the symbol list and the resulting pointer sym is set to NULL. The sym->start is then a NULL pointer access and generates the core dump. The reason why __sched_text_end is not in the symbol list on s390 is simple: When the symbol list is created at perf start up with function calls dso__load +--> dso__load_vmlinux_path +--> dso__load_vmlinux +--> dso__load_sym +--> dso__load_sym_internal (reads kernel symbols) +--> symbols__fixup_end +--> symbols__fixup_duplicate The issue is in function symbols__fixup_duplicate(). It deletes all symbols with have the same address. On s390: # nm -g ~/linux/vmlinux| fgrep c68390 0000000000c68390 T __cpuidle_text_start 0000000000c68390 T __sched_text_end # two symbols have identical addresses and __sched_text_end is considered duplicate (in ascending sort order) and removed from the symbol list. Therefore it is missing and an invalid pointer reference occurs. The code checks for symbol __sched_text_start and when it exists assumes symbol __sched_text_end is also in the symbol table. However this is not the case on s390. Same situation exists for symbol __lock_text_start: 0000000000c68770 T __cpuidle_text_end 0000000000c68770 T __lock_text_start This symbol is also removed from the symbol table but used in function machine__is_lock_function(). To fix this and keep duplicate symbols in the symbol table, set symbol_conf.allow_aliases to true. This prevents the removal of duplicate symbols in function symbols__fixup_duplicate(). Output After: # ./perf lock contention contended total wait max wait avg wait type caller 48 124.39 ms 123.99 ms 2.59 ms rwsem:W unlink_anon_vmas+0x24a 47 83.68 ms 83.26 ms 1.78 ms rwsem:W free_pgtables+0x132 5 41.22 us 10.55 us 8.24 us rwsem:W free_pgtables+0x140 4 40.12 us 20.55 us 10.03 us rwsem:W copy_process+0x1ac8 # Fixes: 0d2997f750d1de39 ("perf lock: Look up callchain for the contended locks") Signed-off-by: Thomas Richter Acked-by: Namhyung Kim Cc: Heiko Carstens Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20221230102627.2410847-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 718b82bfcdff..506c2fe42d52 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1670,6 +1670,7 @@ static int __cmd_report(bool display_info) /* for lock function check */ symbol_conf.sort_by_name = true; + symbol_conf.allow_aliases = true; symbol__init(&session->header.env); if (!data.is_pipe) { @@ -1757,6 +1758,7 @@ static int __cmd_contention(int argc, const char **argv) /* for lock function check */ symbol_conf.sort_by_name = true; + symbol_conf.allow_aliases = true; symbol__init(&session->header.env); if (use_bpf) { From cf97eb7e47d4671084c7e114c5d88a3d0540ecbd Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Tue, 20 Dec 2022 17:11:24 -0500 Subject: [PATCH 068/233] drm/amdkfd: Fix kernel warning during topology setup This patch fixes the following kernel warning seen during driver load by correctly initializing the p2plink attr before creating the sysfs file: [ +0.002865] ------------[ cut here ]------------ [ +0.002327] kobject: '(null)' (0000000056260cfb): is not initialized, yet kobject_put() is being called. [ +0.004780] WARNING: CPU: 32 PID: 1006 at lib/kobject.c:718 kobject_put+0xaa/0x1c0 [ +0.001361] Call Trace: [ +0.001234] [ +0.001067] kfd_remove_sysfs_node_entry+0x24a/0x2d0 [amdgpu] [ +0.003147] kfd_topology_update_sysfs+0x3d/0x750 [amdgpu] [ +0.002890] kfd_topology_add_device+0xbd7/0xc70 [amdgpu] [ +0.002844] ? lock_release+0x13c/0x2e0 [ +0.001936] ? smu_cmn_send_smc_msg_with_param+0x1e8/0x2d0 [amdgpu] [ +0.003313] ? amdgpu_dpm_get_mclk+0x54/0x60 [amdgpu] [ +0.002703] kgd2kfd_device_init.cold+0x39f/0x4ed [amdgpu] [ +0.002930] amdgpu_amdkfd_device_init+0x13d/0x1f0 [amdgpu] [ +0.002944] amdgpu_device_init.cold+0x1464/0x17b4 [amdgpu] [ +0.002970] ? pci_bus_read_config_word+0x43/0x80 [ +0.002380] amdgpu_driver_load_kms+0x15/0x100 [amdgpu] [ +0.002744] amdgpu_pci_probe+0x147/0x370 [amdgpu] [ +0.002522] local_pci_probe+0x40/0x80 [ +0.001896] work_for_cpu_fn+0x10/0x20 [ +0.001892] process_one_work+0x26e/0x5a0 [ +0.002029] worker_thread+0x1fd/0x3e0 [ +0.001890] ? process_one_work+0x5a0/0x5a0 [ +0.002115] kthread+0xea/0x110 [ +0.001618] ? kthread_complete_and_exit+0x20/0x20 [ +0.002422] ret_from_fork+0x1f/0x30 [ +0.001808] [ +0.001103] irq event stamp: 59837 [ +0.001718] hardirqs last enabled at (59849): [] __up_console_sem+0x52/0x60 [ +0.004414] hardirqs last disabled at (59860): [] __up_console_sem+0x37/0x60 [ +0.004414] softirqs last enabled at (59654): [] irq_exit_rcu+0xd7/0x130 [ +0.004205] softirqs last disabled at (59649): [] irq_exit_rcu+0xd7/0x130 [ +0.004203] ---[ end trace 0000000000000000 ]--- Fixes: 0f28cca87e9a ("drm/amdkfd: Extend KFD device topology to surface peer-to-peer links") Signed-off-by: Mukul Joshi Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index bceb1a5b2518..3fdaba56be6f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -801,7 +801,7 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev, p2plink->attr.name = "properties"; p2plink->attr.mode = KFD_SYSFS_FILE_MODE; - sysfs_attr_init(&iolink->attr); + sysfs_attr_init(&p2plink->attr); ret = sysfs_create_file(p2plink->kobj, &p2plink->attr); if (ret < 0) return ret; From f3c23bea598ab7e8e4b8c5ca66598921310f718e Mon Sep 17 00:00:00 2001 From: Samson Tam Date: Mon, 5 Dec 2022 11:08:40 -0500 Subject: [PATCH 069/233] drm/amd/display: Uninitialized variables causing 4k60 UCLK to stay at DPM1 and not DPM0 [Why] SwathSizePerSurfaceY[] and SwathSizePerSurfaceC[] values are uninitialized because we are using += instead of = operator. [How] Assign values in loop with = operator. Acked-by: Aurabindo Pillai Signed-off-by: Samson Tam Reviewed-by: Aric Cyr Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0.x, 6.1.x --- .../drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 5af601cff1a0..b53feeaf5cf1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -6257,12 +6257,12 @@ bool dml32_CalculateDETSwathFillLatencyHiding(unsigned int NumberOfActiveSurface double SwathSizePerSurfaceC[DC__NUM_DPP__MAX]; bool NotEnoughDETSwathFillLatencyHiding = false; - /* calculate sum of single swath size for all pipes in bytes*/ + /* calculate sum of single swath size for all pipes in bytes */ for (k = 0; k < NumberOfActiveSurfaces; k++) { - SwathSizePerSurfaceY[k] += SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k]; + SwathSizePerSurfaceY[k] = SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k]; if (SwathHeightC[k] != 0) - SwathSizePerSurfaceC[k] += SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k]; + SwathSizePerSurfaceC[k] = SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k]; else SwathSizePerSurfaceC[k] = 0; From 2a12187d5853d9fd5102278cecef7dac7c8ce7ea Mon Sep 17 00:00:00 2001 From: Andreas Rammhold Date: Fri, 23 Dec 2022 12:27:47 +0100 Subject: [PATCH 070/233] of/fdt: run soc memory setup when early_init_dt_scan_memory fails If memory has been found early_init_dt_scan_memory now returns 1. If it hasn't found any memory it will return 0, allowing other memory setup mechanisms to carry on. Previously early_init_dt_scan_memory always returned 0 without distinguishing between any kind of memory setup being done or not. Any code path after the early_init_dt_scan memory call in the ramips plat_mem_setup code wouldn't be executed anymore. Making early_init_dt_scan_memory the only way to initialize the memory. Some boards, including my mt7621 based Cudy X6 board, depend on memory initialization being done via the soc_info.mem_detect function pointer. Those wouldn't be able to obtain memory and panic the kernel during early bootup with the message "early_init_dt_alloc_memory_arch: Failed to allocate 12416 bytes align=0x40". Fixes: 1f012283e936 ("of/fdt: Rework early_init_dt_scan_memory() to call directly") Cc: stable@vger.kernel.org Signed-off-by: Andreas Rammhold Link: https://lore.kernel.org/r/20221223112748.2935235-1-andreas@rammhold.de Signed-off-by: Rob Herring --- arch/mips/ralink/of.c | 2 +- drivers/of/fdt.c | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 01c132bc33d5..4d06de77d92a 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -64,7 +64,7 @@ void __init plat_mem_setup(void) dtb = get_fdt(); __dt_setup_arch(dtb); - if (!early_init_dt_scan_memory()) + if (early_init_dt_scan_memory()) return; if (soc_info.mem_detect) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index b2272bccf85c..02cc4a285cb9 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1099,7 +1099,7 @@ u64 __init dt_mem_next_cell(int s, const __be32 **cellp) */ int __init early_init_dt_scan_memory(void) { - int node; + int node, found_memory = 0; const void *fdt = initial_boot_params; fdt_for_each_subnode(node, fdt, 0) { @@ -1139,6 +1139,8 @@ int __init early_init_dt_scan_memory(void) early_init_dt_add_memory_arch(base, size); + found_memory = 1; + if (!hotpluggable) continue; @@ -1147,7 +1149,7 @@ int __init early_init_dt_scan_memory(void) base, base + size); } } - return 0; + return found_memory; } int __init early_init_dt_scan_chosen(char *cmdline) From 1d7a4a40bf76e2305c8beed4a019bf58af6121ac Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 23 Dec 2022 14:21:59 +0100 Subject: [PATCH 071/233] dt-bindings: soundwire: qcom,soundwire: correct sizes related to number of ports There are several properties depending on number of ports. Some of them had maximum limit of 5 and some of 8. SM8450 AudioReach comes with 8 ports, so fix the limits: sm8450-sony-xperia-nagara-pdx224.dtb: soundwire-controller@3250000: qcom,ports-word-length: 'oneOf' conditional failed, one must be fixed: [[255, 255, 255, 255, 255, 255, 255, 255]] is too short [255, 255, 255, 255, 255, 255, 255, 255] is too long Fixes: febc50b82bc9 ("dt-bindings: soundwire: Convert text bindings to DT Schema") Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20221223132159.81211-1-krzysztof.kozlowski@linaro.org Signed-off-by: Rob Herring --- .../devicetree/bindings/soundwire/qcom,soundwire.yaml | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/devicetree/bindings/soundwire/qcom,soundwire.yaml b/Documentation/devicetree/bindings/soundwire/qcom,soundwire.yaml index bcbfa71536cd..3efdc192ab01 100644 --- a/Documentation/devicetree/bindings/soundwire/qcom,soundwire.yaml +++ b/Documentation/devicetree/bindings/soundwire/qcom,soundwire.yaml @@ -80,7 +80,7 @@ properties: or applicable for the respective data port. More info in MIPI Alliance SoundWire 1.0 Specifications. minItems: 3 - maxItems: 5 + maxItems: 8 qcom,ports-sinterval-low: $ref: /schemas/types.yaml#/definitions/uint8-array @@ -124,7 +124,7 @@ properties: or applicable for the respective data port. More info in MIPI Alliance SoundWire 1.0 Specifications. minItems: 3 - maxItems: 5 + maxItems: 8 qcom,ports-block-pack-mode: $ref: /schemas/types.yaml#/definitions/uint8-array @@ -154,7 +154,7 @@ properties: or applicable for the respective data port. More info in MIPI Alliance SoundWire 1.0 Specifications. minItems: 3 - maxItems: 5 + maxItems: 8 items: oneOf: - minimum: 0 @@ -171,7 +171,7 @@ properties: or applicable for the respective data port. More info in MIPI Alliance SoundWire 1.0 Specifications. minItems: 3 - maxItems: 5 + maxItems: 8 items: oneOf: - minimum: 0 @@ -187,7 +187,7 @@ properties: or applicable for the respective data port. More info in MIPI Alliance SoundWire 1.0 Specifications. minItems: 3 - maxItems: 5 + maxItems: 8 items: oneOf: - minimum: 0 From 9ffa13ff78a0a55df968a72d6f0ebffccee5c9f4 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 4 Jan 2023 01:34:02 +0000 Subject: [PATCH 072/233] io_uring: pin context while queueing deferred tw Unlike normal tw, nothing prevents deferred tw to be executed right after an tw item added to ->work_llist in io_req_local_work_add(). For instance, the waiting task may get waken up by CQ posting or a normal tw. Thus we need to pin the ring for the rest of io_req_local_work_add() Cc: stable@vger.kernel.org Fixes: c0e0d6ba25f18 ("io_uring: add IORING_SETUP_DEFER_TASKRUN") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/1a79362b9c10b8523ef70b061d96523650a23344.1672795998.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 58ac13b69dc8..6bed44855679 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1236,13 +1236,18 @@ static void io_req_local_work_add(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - if (!llist_add(&req->io_task_work.node, &ctx->work_llist)) + percpu_ref_get(&ctx->refs); + + if (!llist_add(&req->io_task_work.node, &ctx->work_llist)) { + percpu_ref_put(&ctx->refs); return; + } /* need it for the following io_cqring_wake() */ smp_mb__after_atomic(); if (unlikely(atomic_read(&req->task->io_uring->in_idle))) { io_move_task_work_from_local(ctx); + percpu_ref_put(&ctx->refs); return; } @@ -1252,6 +1257,7 @@ static void io_req_local_work_add(struct io_kiocb *req) if (ctx->has_evfd) io_eventfd_signal(ctx); __io_cqring_wake(ctx); + percpu_ref_put(&ctx->refs); } void __io_req_task_work_add(struct io_kiocb *req, bool allow_local) From f26cc9593581bd734c846bf827401350b36dc3c9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 4 Jan 2023 01:34:57 +0000 Subject: [PATCH 073/233] io_uring: lockdep annotate CQ locking Locking around CQE posting is complex and depends on options the ring is created with, add more thorough lockdep annotations checking all invariants. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/aa3770b4eacae3915d782cc2ab2f395a99b4b232.1672795976.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 5 ++--- io_uring/io_uring.h | 15 +++++++++++++++ 2 files changed, 17 insertions(+), 3 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 6bed44855679..472574192dd6 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -731,6 +731,8 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, size_t ocq_size = sizeof(struct io_overflow_cqe); bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32); + lockdep_assert_held(&ctx->completion_lock); + if (is_cqe32) ocq_size += sizeof(struct io_uring_cqe); @@ -820,9 +822,6 @@ static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res, { struct io_uring_cqe *cqe; - if (!ctx->task_complete) - lockdep_assert_held(&ctx->completion_lock); - ctx->cq_extra++; /* diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index e9f0d41ebb99..ab4b2a1c3b7e 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -79,6 +79,19 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx); bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all); +#define io_lockdep_assert_cq_locked(ctx) \ + do { \ + if (ctx->flags & IORING_SETUP_IOPOLL) { \ + lockdep_assert_held(&ctx->uring_lock); \ + } else if (!ctx->task_complete) { \ + lockdep_assert_held(&ctx->completion_lock); \ + } else if (ctx->submitter_task->flags & PF_EXITING) { \ + lockdep_assert(current_work()); \ + } else { \ + lockdep_assert(current == ctx->submitter_task); \ + } \ + } while (0) + static inline void io_req_task_work_add(struct io_kiocb *req) { __io_req_task_work_add(req, true); @@ -92,6 +105,8 @@ void io_cq_unlock_post(struct io_ring_ctx *ctx); static inline struct io_uring_cqe *io_get_cqe_overflow(struct io_ring_ctx *ctx, bool overflow) { + io_lockdep_assert_cq_locked(ctx); + if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) { struct io_uring_cqe *cqe = ctx->cqe_cached; From 67fcb2c598bc7643f694e8194d5c300a52af5aa9 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 29 Dec 2022 14:04:46 -0800 Subject: [PATCH 074/233] cifs: Fix kmap_local_page() unmapping kmap_local_page() requires kunmap_local() to unmap the mapping. In addition memcpy_page() is provided to perform this common memcpy pattern. Replace the kmap_local_page() and broken kunmap() with memcpy_page() Fixes: d406d26745ab ("cifs: skip alloc when request has no pages") Reviewed-by: Paulo Alcantara Reviewed-by: "Fabio M. De Francesco" Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Signed-off-by: Ira Weiny Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index dc160de7a6de..0d7e9bcd9f34 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -4488,17 +4488,12 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst, /* copy pages form the old */ for (j = 0; j < npages; j++) { - char *dst, *src; unsigned int offset, len; rqst_page_get_length(new, j, &len, &offset); - dst = kmap_local_page(new->rq_pages[j]) + offset; - src = kmap_local_page(old->rq_pages[j]) + offset; - - memcpy(dst, src, len); - kunmap(new->rq_pages[j]); - kunmap(old->rq_pages[j]); + memcpy_page(new->rq_pages[j], offset, + old->rq_pages[j], offset, len); } } From 9e6002c8738a9d5675ba706fcdbc0a544f814974 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Thu, 29 Dec 2022 12:33:55 -0300 Subject: [PATCH 075/233] cifs: ignore ipc reconnect failures during dfs failover If it failed to reconnect ipc used for getting referrals, we can just ignore it as it is not required for reconnecting the share. The worst case would be not being able to detect or chase nested links as long as dfs root server is unreachable. Before patch: $ mount.cifs //root/dfs/link /mnt -o echo_interval=10,... -> target share: /fs0/share disconnect root & fs0 $ ls /mnt ls: cannot access '/mnt': Host is down connect fs0 $ ls /mnt ls: cannot access '/mnt': Resource temporarily unavailable After patch: $ mount.cifs //root/dfs/link /mnt -o echo_interval=10,... -> target share: /fs0/share disconnect root & fs0 $ ls /mnt ls: cannot access '/mnt': Host is down connect fs0 $ ls /mnt bar.rtf dir1 foo Signed-off-by: Paulo Alcantara (SUSE) Reviewed-by: Enzo Matsumiya Signed-off-by: Steve French --- fs/cifs/dfs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/cifs/dfs.c b/fs/cifs/dfs.c index b541e68378f6..30086f2060a1 100644 --- a/fs/cifs/dfs.c +++ b/fs/cifs/dfs.c @@ -401,8 +401,7 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t if (ipc->need_reconnect) { scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); rc = ops->tree_connect(xid, ipc->ses, tree, ipc, cifs_sb->local_nls); - if (rc) - break; + cifs_dbg(FYI, "%s: reconnect ipc: %d\n", __func__, rc); } scnprintf(tree, MAX_TREE_SIZE, "\\%s", share); From 775e44d6d86dca400d614cbda5dab4def4951fe7 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Thu, 29 Dec 2022 12:33:56 -0300 Subject: [PATCH 076/233] cifs: fix race in assemble_neg_contexts() Serialise access of TCP_Server_Info::hostname in assemble_neg_contexts() by holding the server's mutex otherwise it might end up accessing an already-freed hostname pointer from cifs_reconnect() or cifs_resolve_server(). Signed-off-by: Paulo Alcantara (SUSE) Reviewed-by: Enzo Matsumiya Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index a5695748a89b..2c484d47c592 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -541,9 +541,10 @@ static void assemble_neg_contexts(struct smb2_negotiate_req *req, struct TCP_Server_Info *server, unsigned int *total_len) { - char *pneg_ctxt; - char *hostname = NULL; unsigned int ctxt_len, neg_context_count; + struct TCP_Server_Info *pserver; + char *pneg_ctxt; + char *hostname; if (*total_len > 200) { /* In case length corrupted don't want to overrun smb buffer */ @@ -574,8 +575,9 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, * secondary channels don't have the hostname field populated * use the hostname field in the primary channel instead */ - hostname = CIFS_SERVER_IS_CHAN(server) ? - server->primary_server->hostname : server->hostname; + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + cifs_server_lock(pserver); + hostname = pserver->hostname; if (hostname && (hostname[0] != 0)) { ctxt_len = build_netname_ctxt((struct smb2_netname_neg_context *)pneg_ctxt, hostname); @@ -584,6 +586,7 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, neg_context_count = 3; } else neg_context_count = 2; + cifs_server_unlock(pserver); build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt); *total_len += sizeof(struct smb2_posix_neg_context); From 340726747336716350eb5a928b860a29db955f05 Mon Sep 17 00:00:00 2001 From: Aaron Thompson Date: Wed, 4 Jan 2023 10:07:37 +0000 Subject: [PATCH 077/233] memblock tests: Fix compilation error. Commit cf4694be2b2cf ("tools: Add atomic_test_and_set_bit()") changed tools/arch/x86/include/asm/atomic.h to include , which causes 'make -C tools/testing/memblock' to fail with: In file included from ../../include/asm/atomic.h:6, from ../../include/linux/atomic.h:5, from ./linux/mmzone.h:5, from ../../include/linux/mm.h:5, from ../../include/linux/pfn.h:5, from ./linux/memory_hotplug.h:6, from ./linux/init.h:7, from ./linux/memblock.h:11, from tests/common.h:8, from tests/basic_api.h:5, from main.c:2: ../../include/asm/../../arch/x86/include/asm/atomic.h:11:10: fatal error: asm/asm.h: No such file or directory 11 | #include | ^~~~~~~~~~~ Create a symlink to asm/asm.h in the same manner as the existing one to asm/cmpxchg.h. Signed-off-by: Aaron Thompson Link: https://lore.kernel.org/r/010101857c402765-96e2dbc6-b82b-47e2-a437-4834dbe0b96b-000000@us-west-2.amazonses.com Signed-off-by: Mike Rapoport (IBM) --- tools/testing/memblock/.gitignore | 1 + tools/testing/memblock/Makefile | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/memblock/.gitignore b/tools/testing/memblock/.gitignore index 654338e0be52..4cc7cd5aac2b 100644 --- a/tools/testing/memblock/.gitignore +++ b/tools/testing/memblock/.gitignore @@ -1,4 +1,5 @@ main memblock.c linux/memblock.h +asm/asm.h asm/cmpxchg.h diff --git a/tools/testing/memblock/Makefile b/tools/testing/memblock/Makefile index 2310ac4d080e..7a1ca694a982 100644 --- a/tools/testing/memblock/Makefile +++ b/tools/testing/memblock/Makefile @@ -29,13 +29,14 @@ include: ../../../include/linux/memblock.h ../../include/linux/*.h \ @mkdir -p linux test -L linux/memblock.h || ln -s ../../../../include/linux/memblock.h linux/memblock.h + test -L asm/asm.h || ln -s ../../../arch/x86/include/asm/asm.h asm/asm.h test -L asm/cmpxchg.h || ln -s ../../../arch/x86/include/asm/cmpxchg.h asm/cmpxchg.h memblock.c: $(EXTR_SRC) test -L memblock.c || ln -s $(EXTR_SRC) memblock.c clean: - $(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/cmpxchg.h + $(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/asm.h asm/cmpxchg.h help: @echo 'Memblock simulator' From fa81ab49bbe4e1ce756581c970486de0ddb14309 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Fri, 16 Dec 2022 14:03:03 +0400 Subject: [PATCH 078/233] memblock: Fix doc for memblock_phys_free memblock_phys_free() is the counterpart to memblock_phys_alloc. Change memblock_alloc_xx() with memblock_phys_alloc_xx() to keep consistency. Signed-off-by: Miaoqian Lin Link: https://lore.kernel.org/r/20221216100304.688209-1-linmq006@gmail.com Signed-off-by: Mike Rapoport (IBM) --- mm/memblock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memblock.c b/mm/memblock.c index 511d4783dcf1..d036c7861310 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -836,7 +836,7 @@ void __init_memblock memblock_free(void *ptr, size_t size) * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * - * Free boot memory block previously allocated by memblock_alloc_xx() API. + * Free boot memory block previously allocated by memblock_phys_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) From fb710ddee75fb96f50ee6d004ef777a0cf7ad5a3 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 28 Dec 2022 15:57:03 +0100 Subject: [PATCH 079/233] perf test record_probe_libc_inet_pton: Fix test on s/390 where 'text_to_binary_address' now appears on the backtrace perf test '84: probe libc's inet_pton & backtrace it with ping' fails on s390. Debugging revealed a changed stack trace for the ping command using probes: ping 35729 [002] 8006.365063: probe_libc:inet_pton: (3ff9603e7c0) 13e7c0 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6) ---> 104371 text_to_binary_address+0xef1 (inlined) 104371 gaih_inet+0xef1 (inlined) 104371 __GI_getaddrinfo+0xef1 (inlined) 5d4b main+0x139b (/usr/bin/ping) The line "---> text_to_binary_address ..." is new. It was introduced with glibc version 2.36.7.2 released with Fedora 37 for s390. Output before # perf test inet_pton 84: probe libc's inet_pton & backtrace it with ping : FAILED! # Output after: # perf test inet_pton 84: probe libc's inet_pton & backtrace it with ping : Ok # Signed-off-by: Thomas Richter Cc: Heiko Carstens Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20221228145704.2702487-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 216b6b64caa3..57e7a6a470c9 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -37,6 +37,7 @@ trace_libc_inet_pton_backtrace() { case "$(uname -m)" in s390x) eventattr='call-graph=dwarf,max-stack=4' + echo "text_to_binary_address.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected From 2d656b0f81b22101db0447f890e39fdd736b745e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 3 Jan 2023 22:44:01 -0800 Subject: [PATCH 080/233] perf stat: Fix handling of unsupported cgroup events when using BPF counters When --for-each-cgroup option is used, it fails when any of events is not supported and exits immediately. This is not how 'perf stat' handles unsupported events. Let's ignore the failure and proceed with others so that the output is similar to when BPF counters are not used: Before: $ sudo ./perf stat -a --bpf-counters -e L1-icache-loads,L1-dcache-loads --for-each-cgroup system.slice,user.slice sleep 1 Failed to open first cgroup events $ After it shows output similat to when --bpf-counters isn't specified: $ sudo ./perf stat -a --bpf-counters -e L1-icache-loads,L1-dcache-loads --for-each-cgroup system.slice,user.slice sleep 1 Performance counter stats for 'system wide': L1-icache-loads system.slice 29,892,418 L1-dcache-loads system.slice L1-icache-loads user.slice 52,497,220 L1-dcache-loads user.slice $ Fixes: 944138f048f7d759 ("perf stat: Enable BPF counter with --for-each-cgroup") Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Song Liu Link: https://lore.kernel.org/r/20230104064402.1551516-4-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_counter_cgroup.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 3c2df7522f6f..1c82377ed78b 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -116,27 +116,19 @@ static int bperf_load_program(struct evlist *evlist) /* open single copy of the events w/o cgroup */ err = evsel__open_per_cpu(evsel, evsel->core.cpus, -1); - if (err) { - pr_err("Failed to open first cgroup events\n"); - goto out; - } + if (err == 0) + evsel->supported = true; map_fd = bpf_map__fd(skel->maps.events); perf_cpu_map__for_each_cpu(cpu, j, evsel->core.cpus) { int fd = FD(evsel, j); __u32 idx = evsel->core.idx * total_cpus + cpu.cpu; - err = bpf_map_update_elem(map_fd, &idx, &fd, - BPF_ANY); - if (err < 0) { - pr_err("Failed to update perf_event fd\n"); - goto out; - } + bpf_map_update_elem(map_fd, &idx, &fd, BPF_ANY); } evsel->cgrp = leader_cgrp; } - evsel->supported = true; if (evsel->cgrp == cgrp) continue; From 54b353a20c7e8be98414754f5aff98c8a68fcc1f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 3 Jan 2023 22:44:02 -0800 Subject: [PATCH 081/233] perf stat: Fix handling of --for-each-cgroup with --bpf-counters to match non BPF mode The --for-each-cgroup can have the same cgroup multiple times, but this confuses BPF counters (since they have the same cgroup id), making only the last cgroup events to be counted. Let's check the cgroup name before adding a new entry to the cgroups list. Before: $ sudo ./perf stat -a --bpf-counters --for-each-cgroup /,/ sleep 1 Performance counter stats for 'system wide': msec cpu-clock / context-switches / cpu-migrations / page-faults / cycles / instructions / branches / branch-misses / 8,016.04 msec cpu-clock / # 7.998 CPUs utilized 6,152 context-switches / # 767.461 /sec 250 cpu-migrations / # 31.187 /sec 442 page-faults / # 55.139 /sec 613,111,487 cycles / # 0.076 GHz 280,599,604 instructions / # 0.46 insn per cycle 57,692,724 branches / # 7.197 M/sec 3,385,168 branch-misses / # 5.87% of all branches 1.002220125 seconds time elapsed After it becomes similar to the non-BPF mode: $ sudo ./perf stat -a --bpf-counters --for-each-cgroup /,/ sleep 1 Performance counter stats for 'system wide': 8,013.38 msec cpu-clock / # 7.998 CPUs utilized 6,859 context-switches / # 855.944 /sec 334 cpu-migrations / # 41.680 /sec 345 page-faults / # 43.053 /sec 782,326,119 cycles / # 0.098 GHz 471,645,724 instructions / # 0.60 insn per cycle 94,963,430 branches / # 11.851 M/sec 3,685,511 branch-misses / # 3.88% of all branches 1.001864539 seconds time elapsed Committer notes: As a reminder, to test with BPF counters one has to use BUILD_BPF_SKEL=1 in the make command line and have clang/llvm installed when building perf, otherwise the --bpf-counters option will not be available: # perf stat -a --bpf-counters --for-each-cgroup /,/ sleep 1 Error: unknown option `bpf-counters' Usage: perf stat [] [] -a, --all-cpus system-wide collection from all CPUs # Fixes: bb1c15b60b981d10 ("perf stat: Support regex pattern in --for-each-cgroup") Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: bpf@vger.kernel.org Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Link: https://lore.kernel.org/r/20230104064402.1551516-5-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cgroup.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index e99b41f9be45..cd978c240e0d 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -224,6 +224,19 @@ static int add_cgroup_name(const char *fpath, const struct stat *sb __maybe_unus return 0; } +static int check_and_add_cgroup_name(const char *fpath) +{ + struct cgroup_name *cn; + + list_for_each_entry(cn, &cgroup_list, list) { + if (!strcmp(cn->name, fpath)) + return 0; + } + + /* pretend if it's added by ftw() */ + return add_cgroup_name(fpath, NULL, FTW_D, NULL); +} + static void release_cgroup_list(void) { struct cgroup_name *cn; @@ -242,7 +255,7 @@ static int list_cgroups(const char *str) struct cgroup_name *cn; char *s; - /* use given name as is - for testing purpose */ + /* use given name as is when no regex is given */ for (;;) { p = strchr(str, ','); e = p ? p : eos; @@ -253,13 +266,13 @@ static int list_cgroups(const char *str) s = strndup(str, e - str); if (!s) return -1; - /* pretend if it's added by ftw() */ - ret = add_cgroup_name(s, NULL, FTW_D, NULL); + + ret = check_and_add_cgroup_name(s); free(s); - if (ret) + if (ret < 0) return -1; } else { - if (add_cgroup_name("", NULL, FTW_D, NULL) < 0) + if (check_and_add_cgroup_name("/") < 0) return -1; } From 191f8453fc99a537ea78b727acea739782378b0d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 4 Jan 2023 07:48:37 -0700 Subject: [PATCH 082/233] ARM: renumber bits related to _TIF_WORK_MASK We want to ensure that the mask related to calling do_work_pending() is within the first 16 bits. Move bits unrelated to that outside of that range, to avoid spuriously calling do_work_pending() when we don't need to. Cc: stable@vger.kernel.org Fixes: 32d59773da38 ("arm: add support for TIF_NOTIFY_SIGNAL") Reported-and-tested-by: Hui Tang Suggested-by: Russell King (Oracle) Link: https://lore.kernel.org/lkml/7ecb8f3c-2aeb-a905-0d4a-aa768b9649b5@huawei.com/ Signed-off-by: Jens Axboe --- arch/arm/include/asm/thread_info.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index aecc403b2880..7f092cb55a41 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -128,15 +128,16 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define TIF_NEED_RESCHED 1 /* rescheduling necessary */ #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ #define TIF_UPROBE 3 /* breakpointed or singlestepping */ -#define TIF_SYSCALL_TRACE 4 /* syscall trace active */ -#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ -#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ -#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ -#define TIF_NOTIFY_SIGNAL 8 /* signal notifications exist */ +#define TIF_NOTIFY_SIGNAL 4 /* signal notifications exist */ #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ -#define TIF_RESTORE_SIGMASK 20 +#define TIF_RESTORE_SIGMASK 19 +#define TIF_SYSCALL_TRACE 20 /* syscall trace active */ +#define TIF_SYSCALL_AUDIT 21 /* syscall auditing active */ +#define TIF_SYSCALL_TRACEPOINT 22 /* syscall tracepoint instrumentation */ +#define TIF_SECCOMP 23 /* seccomp syscall filtering active */ + #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) From 39a154fc2d172a3a5865e5a9fa2a2983eb7a99ac Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Thu, 29 Dec 2022 18:43:46 -0300 Subject: [PATCH 083/233] cifs: protect access of TCP_Server_Info::{dstaddr,hostname} Use the appropriate locks to protect access of hostname and dstaddr fields in cifs_tree_connect() as they might get changed by other tasks. Signed-off-by: Paulo Alcantara (SUSE) Reviewed-by: Enzo Matsumiya Signed-off-by: Steve French --- fs/cifs/dfs.c | 22 +++++++++++----------- fs/cifs/misc.c | 2 ++ 2 files changed, 13 insertions(+), 11 deletions(-) diff --git a/fs/cifs/dfs.c b/fs/cifs/dfs.c index 30086f2060a1..b64d20374b9c 100644 --- a/fs/cifs/dfs.c +++ b/fs/cifs/dfs.c @@ -327,8 +327,8 @@ static int update_server_fullpath(struct TCP_Server_Info *server, struct cifs_sb return rc; } -static int target_share_matches_server(struct TCP_Server_Info *server, const char *tcp_host, - size_t tcp_host_len, char *share, bool *target_match) +static int target_share_matches_server(struct TCP_Server_Info *server, char *share, + bool *target_match) { int rc = 0; const char *dfs_host; @@ -338,13 +338,16 @@ static int target_share_matches_server(struct TCP_Server_Info *server, const cha extract_unc_hostname(share, &dfs_host, &dfs_host_len); /* Check if hostnames or addresses match */ - if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) { - cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len, - dfs_host, (int)tcp_host_len, tcp_host); + cifs_server_lock(server); + if (dfs_host_len != strlen(server->hostname) || + strncasecmp(dfs_host, server->hostname, dfs_host_len)) { + cifs_dbg(FYI, "%s: %.*s doesn't match %s\n", __func__, + (int)dfs_host_len, dfs_host, server->hostname); rc = match_target_ip(server, dfs_host, dfs_host_len, target_match); if (rc) cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc); } + cifs_server_unlock(server); return rc; } @@ -358,13 +361,9 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t struct cifs_ses *root_ses = CIFS_DFS_ROOT_SES(tcon->ses); struct cifs_tcon *ipc = root_ses->tcon_ipc; char *share = NULL, *prefix = NULL; - const char *tcp_host; - size_t tcp_host_len; struct dfs_cache_tgt_iterator *tit; bool target_match; - extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len); - tit = dfs_cache_get_tgt_iterator(tl); if (!tit) { rc = -ENOENT; @@ -387,8 +386,7 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t break; } - rc = target_share_matches_server(server, tcp_host, tcp_host_len, share, - &target_match); + rc = target_share_matches_server(server, share, &target_match); if (rc) break; if (!target_match) { @@ -497,7 +495,9 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru } if (tcon->ipc) { + cifs_server_lock(server); scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); + cifs_server_unlock(server); rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); goto out; } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 4d3c586785a5..2a19c7987c5b 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1277,7 +1277,9 @@ int match_target_ip(struct TCP_Server_Info *server, if (rc < 0) return rc; + spin_lock(&server->srv_lock); *result = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, (struct sockaddr *)&ss); + spin_unlock(&server->srv_lock); cifs_dbg(FYI, "%s: ip addresses match: %u\n", __func__, *result); return 0; } From 3792fc508c095abd84b10ceae12bd773e61fdc36 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 15 Nov 2022 16:15:18 +0300 Subject: [PATCH 084/233] drm/i915: unpin on error in intel_vgpu_shadow_mm_pin() Call intel_vgpu_unpin_mm() on this error path. Fixes: 418741480809 ("drm/i915/gvt: Adding ppgtt to GVT GEM context after shadow pdps settled.") Signed-off-by: Dan Carpenter Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/Y3OQ5tgZIVxyQ/WV@kili Reviewed-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/scheduler.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 9cd8fcbf7cad..8009239935f7 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -695,6 +695,7 @@ intel_vgpu_shadow_mm_pin(struct intel_vgpu_workload *workload) if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT || !workload->shadow_mm->ppgtt_mm.shadowed) { + intel_vgpu_unpin_mm(workload->shadow_mm); gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); return -EINVAL; } From c4b850d1f448a901fbf4f7f36dec38c84009b489 Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Mon, 19 Dec 2022 22:03:56 +0800 Subject: [PATCH 085/233] drm/i915/gvt: fix gvt debugfs destroy When gvt debug fs is destroyed, need to have a sane check if drm minor's debugfs root is still available or not, otherwise in case like device remove through unbinding, drm minor's debugfs directory has already been removed, then intel_gvt_debugfs_clean() would act upon dangling pointer like below oops. i915 0000:00:02.0: Direct firmware load for i915/gvt/vid_0x8086_did_0x1926_rid_0x0a.golden_hw_state failed with error -2 i915 0000:00:02.0: MDEV: Registered Console: switching to colour dummy device 80x25 i915 0000:00:02.0: MDEV: Unregistering BUG: kernel NULL pointer dereference, address: 00000000000000a0 PGD 0 P4D 0 Oops: 0002 [#1] PREEMPT SMP PTI CPU: 2 PID: 2486 Comm: gfx-unbind.sh Tainted: G I 6.1.0-rc8+ #15 Hardware name: Dell Inc. XPS 13 9350/0JXC1H, BIOS 1.13.0 02/10/2020 RIP: 0010:down_write+0x1f/0x90 Code: 1d ff ff 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 53 48 89 fb e8 62 c0 ff ff bf 01 00 00 00 e8 28 5e 31 ff 31 c0 ba 01 00 00 00 48 0f b1 13 75 33 65 48 8b 04 25 c0 bd 01 00 48 89 43 08 bf 01 RSP: 0018:ffff9eb3036ffcc8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 00000000000000a0 RCX: ffffff8100000000 RDX: 0000000000000001 RSI: 0000000000000064 RDI: ffffffffa48787a8 RBP: ffff9eb3036ffd30 R08: ffffeb1fc45a0608 R09: ffffeb1fc45a05c0 R10: 0000000000000002 R11: 0000000000000000 R12: 0000000000000000 R13: ffff91acc33fa328 R14: ffff91acc033f080 R15: ffff91acced533e0 FS: 00007f6947bba740(0000) GS:ffff91ae36d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000a0 CR3: 00000001133a2002 CR4: 00000000003706e0 Call Trace: simple_recursive_removal+0x9f/0x2a0 ? start_creating.part.0+0x120/0x120 ? _raw_spin_lock+0x13/0x40 debugfs_remove+0x40/0x60 intel_gvt_debugfs_clean+0x15/0x30 [kvmgt] intel_gvt_clean_device+0x49/0xe0 [kvmgt] intel_gvt_driver_remove+0x2f/0xb0 i915_driver_remove+0xa4/0xf0 i915_pci_remove+0x1a/0x30 pci_device_remove+0x33/0xa0 device_release_driver_internal+0x1b2/0x230 unbind_store+0xe0/0x110 kernfs_fop_write_iter+0x11b/0x1f0 vfs_write+0x203/0x3d0 ksys_write+0x63/0xe0 do_syscall_64+0x37/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f6947cb5190 Code: 40 00 48 8b 15 71 9c 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 80 3d 51 24 0e 00 00 74 17 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 48 89 RSP: 002b:00007ffcbac45a28 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f6947cb5190 RDX: 000000000000000d RSI: 0000555e35c866a0 RDI: 0000000000000001 RBP: 0000555e35c866a0 R08: 0000000000000002 R09: 0000555e358cb97c R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000001 R13: 000000000000000d R14: 0000000000000000 R15: 0000555e358cb8e0 Modules linked in: kvmgt CR2: 00000000000000a0 ---[ end trace 0000000000000000 ]--- Cc: Wang, Zhi Cc: He, Yu Cc: stable@vger.kernel.org Reviewed-by: Zhi Wang Fixes: bc7b0be316ae ("drm/i915/gvt: Add basic debugfs infrastructure") Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20221219140357.769557-1-zhenyuw@linux.intel.com --- drivers/gpu/drm/i915/gvt/debugfs.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c index 9f1c209d9251..d7df27feee8c 100644 --- a/drivers/gpu/drm/i915/gvt/debugfs.c +++ b/drivers/gpu/drm/i915/gvt/debugfs.c @@ -199,6 +199,10 @@ void intel_gvt_debugfs_init(struct intel_gvt *gvt) */ void intel_gvt_debugfs_clean(struct intel_gvt *gvt) { - debugfs_remove_recursive(gvt->debugfs_root); - gvt->debugfs_root = NULL; + struct drm_minor *minor = gvt->gt->i915->drm.primary; + + if (minor->debugfs_root) { + debugfs_remove_recursive(gvt->debugfs_root); + gvt->debugfs_root = NULL; + } } From 704f3384f322b40ba24d958473edfb1c9750c8fd Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Mon, 19 Dec 2022 22:03:57 +0800 Subject: [PATCH 086/233] drm/i915/gvt: fix vgpu debugfs clean in remove Check carefully on root debugfs available when destroying vgpu, e.g in remove case drm minor's debugfs root might already be destroyed, which led to kernel oops like below. Console: switching to colour dummy device 80x25 i915 0000:00:02.0: MDEV: Unregistering intel_vgpu_mdev b1338b2d-a709-4c23-b766-cc436c36cdf0: Removing from iommu group 14 BUG: kernel NULL pointer dereference, address: 0000000000000150 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP CPU: 3 PID: 1046 Comm: driverctl Not tainted 6.1.0-rc2+ #6 Hardware name: HP HP ProDesk 600 G3 MT/829D, BIOS P02 Ver. 02.44 09/13/2022 RIP: 0010:__lock_acquire+0x5e2/0x1f90 Code: 87 ad 09 00 00 39 05 e1 1e cc 02 0f 82 f1 09 00 00 ba 01 00 00 00 48 83 c4 48 89 d0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 45 31 ff <48> 81 3f 60 9e c2 b6 45 0f 45 f8 83 fe 01 0f 87 55 fa ff ff 89 f0 RSP: 0018:ffff9f770274f948 EFLAGS: 00010046 RAX: 0000000000000003 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000150 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: ffff8895d1173300 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000150 R14: 0000000000000000 R15: 0000000000000000 FS: 00007fc9b2ba0740(0000) GS:ffff889cdfcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000150 CR3: 000000010fd93005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: lock_acquire+0xbf/0x2b0 ? simple_recursive_removal+0xa5/0x2b0 ? lock_release+0x13d/0x2d0 down_write+0x2a/0xd0 ? simple_recursive_removal+0xa5/0x2b0 simple_recursive_removal+0xa5/0x2b0 ? start_creating.part.0+0x110/0x110 ? _raw_spin_unlock+0x29/0x40 debugfs_remove+0x40/0x60 intel_gvt_debugfs_remove_vgpu+0x15/0x30 [kvmgt] intel_gvt_destroy_vgpu+0x60/0x100 [kvmgt] intel_vgpu_release_dev+0xe/0x20 [kvmgt] device_release+0x30/0x80 kobject_put+0x79/0x1b0 device_release_driver_internal+0x1b8/0x230 bus_remove_device+0xec/0x160 device_del+0x189/0x400 ? up_write+0x9c/0x1b0 ? mdev_device_remove_common+0x60/0x60 [mdev] mdev_device_remove_common+0x22/0x60 [mdev] mdev_device_remove_cb+0x17/0x20 [mdev] device_for_each_child+0x56/0x80 mdev_unregister_parent+0x5a/0x81 [mdev] intel_gvt_clean_device+0x2d/0xe0 [kvmgt] intel_gvt_driver_remove+0x2e/0xb0 [i915] i915_driver_remove+0xac/0x100 [i915] i915_pci_remove+0x1a/0x30 [i915] pci_device_remove+0x31/0xa0 device_release_driver_internal+0x1b8/0x230 unbind_store+0xd8/0x100 kernfs_fop_write_iter+0x156/0x210 vfs_write+0x236/0x4a0 ksys_write+0x61/0xd0 do_syscall_64+0x55/0x80 ? find_held_lock+0x2b/0x80 ? lock_release+0x13d/0x2d0 ? up_read+0x17/0x20 ? lock_is_held_type+0xe3/0x140 ? asm_exc_page_fault+0x22/0x30 ? lockdep_hardirqs_on+0x7d/0x100 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fc9b2c9e0c4 Code: 15 71 7d 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 80 3d 3d 05 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 48 89 54 24 18 48 RSP: 002b:00007ffec29c81c8 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007fc9b2c9e0c4 RDX: 000000000000000d RSI: 0000559f8b5f48a0 RDI: 0000000000000001 RBP: 0000559f8b5f48a0 R08: 0000559f8b5f3540 R09: 00007fc9b2d76d30 R10: 0000000000000000 R11: 0000000000000202 R12: 000000000000000d R13: 00007fc9b2d77780 R14: 000000000000000d R15: 00007fc9b2d72a00 Modules linked in: sunrpc intel_rapl_msr intel_rapl_common intel_pmc_core_pltdrv intel_pmc_core intel_tcc_cooling x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel ee1004 igbvf rapl vfat fat intel_cstate intel_uncore pktcdvd i2c_i801 pcspkr wmi_bmof i2c_smbus acpi_pad vfio_pci vfio_pci_core vfio_virqfd zram fuse dm_multipath kvmgt mdev vfio_iommu_type1 vfio kvm irqbypass i915 nvme e1000e igb nvme_core crct10dif_pclmul crc32_pclmul crc32c_intel polyval_clmulni polyval_generic serio_raw ghash_clmulni_intel sha512_ssse3 dca drm_buddy intel_gtt video wmi drm_display_helper ttm CR2: 0000000000000150 ---[ end trace 0000000000000000 ]--- Cc: Wang Zhi Cc: He Yu Cc: Alex Williamson Cc: stable@vger.kernel.org Reviewed-by: Zhi Wang Tested-by: Yu He Fixes: bc7b0be316ae ("drm/i915/gvt: Add basic debugfs infrastructure") Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20221219140357.769557-2-zhenyuw@linux.intel.com --- drivers/gpu/drm/i915/gvt/debugfs.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c index d7df27feee8c..e08ed0e9f165 100644 --- a/drivers/gpu/drm/i915/gvt/debugfs.c +++ b/drivers/gpu/drm/i915/gvt/debugfs.c @@ -175,8 +175,13 @@ void intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu) */ void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu) { - debugfs_remove_recursive(vgpu->debugfs); - vgpu->debugfs = NULL; + struct intel_gvt *gvt = vgpu->gvt; + struct drm_minor *minor = gvt->gt->i915->drm.primary; + + if (minor->debugfs_root && gvt->debugfs_root) { + debugfs_remove_recursive(vgpu->debugfs); + vgpu->debugfs = NULL; + } } /** From a06d4b9e15c0ea4e05b200cfb1f1050e785a5e87 Mon Sep 17 00:00:00 2001 From: Zhi Wang Date: Thu, 10 Nov 2022 12:20:34 +0000 Subject: [PATCH 087/233] drm/i915/gvt: use atomic operations to change the vGPU status Several vGPU status are used to decide the availability of GVT-g core logics when creating a vGPU. Use atomic operations on changing the vGPU status to avoid the racing. Cc: Zhenyu Wang Cc: Kevin Tian Cc: Jason Gunthorpe Cc: intel-gvt-dev@lists.freedesktop.org Suggested-by: Alex Williamson Signed-off-by: Zhi Wang Reviewed-by: Zhenyu Wang Reviewed-by: Kevin Tian Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20221110122034.3382-2-zhi.a.wang@intel.com --- drivers/gpu/drm/i915/gvt/debugfs.c | 19 ++++++++++++++- drivers/gpu/drm/i915/gvt/dmabuf.c | 3 ++- drivers/gpu/drm/i915/gvt/gtt.c | 4 ++-- drivers/gpu/drm/i915/gvt/gvt.h | 15 ++++++++---- drivers/gpu/drm/i915/gvt/interrupt.c | 2 +- drivers/gpu/drm/i915/gvt/kvmgt.c | 35 +++++++++++----------------- drivers/gpu/drm/i915/gvt/scheduler.c | 3 ++- drivers/gpu/drm/i915/gvt/vgpu.c | 12 ++++------ 8 files changed, 53 insertions(+), 40 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c index e08ed0e9f165..0616b73175f3 100644 --- a/drivers/gpu/drm/i915/gvt/debugfs.c +++ b/drivers/gpu/drm/i915/gvt/debugfs.c @@ -151,6 +151,22 @@ DEFINE_SIMPLE_ATTRIBUTE(vgpu_scan_nonprivbb_fops, vgpu_scan_nonprivbb_get, vgpu_scan_nonprivbb_set, "0x%llx\n"); +static int vgpu_status_get(void *data, u64 *val) +{ + struct intel_vgpu *vgpu = (struct intel_vgpu *)data; + + *val = 0; + + if (test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) + *val |= (1 << INTEL_VGPU_STATUS_ATTACHED); + if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status)) + *val |= (1 << INTEL_VGPU_STATUS_ACTIVE); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(vgpu_status_fops, vgpu_status_get, NULL, "0x%llx\n"); + /** * intel_gvt_debugfs_add_vgpu - register debugfs entries for a vGPU * @vgpu: a vGPU @@ -162,11 +178,12 @@ void intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu) snprintf(name, 16, "vgpu%d", vgpu->id); vgpu->debugfs = debugfs_create_dir(name, vgpu->gvt->debugfs_root); - debugfs_create_bool("active", 0444, vgpu->debugfs, &vgpu->active); debugfs_create_file("mmio_diff", 0444, vgpu->debugfs, vgpu, &vgpu_mmio_diff_fops); debugfs_create_file("scan_nonprivbb", 0644, vgpu->debugfs, vgpu, &vgpu_scan_nonprivbb_fops); + debugfs_create_file("status", 0644, vgpu->debugfs, vgpu, + &vgpu_status_fops); } /** diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 355f1c0e8664..ffe41e9be04f 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -134,7 +134,8 @@ static void dmabuf_gem_object_free(struct kref *kref) struct list_head *pos; struct intel_vgpu_dmabuf_obj *dmabuf_obj; - if (vgpu && vgpu->active && !list_empty(&vgpu->dmabuf_obj_list_head)) { + if (vgpu && test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status) && + !list_empty(&vgpu->dmabuf_obj_list_head)) { list_for_each(pos, &vgpu->dmabuf_obj_list_head) { dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list); if (dmabuf_obj == obj) { diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 51e5e8fb505b..6b4039010cae 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -55,7 +55,7 @@ static bool intel_gvt_is_valid_gfn(struct intel_vgpu *vgpu, unsigned long gfn) int idx; bool ret; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return false; idx = srcu_read_lock(&kvm->srcu); @@ -1178,7 +1178,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu, if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M)) return 0; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -EINVAL; pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry)); if (is_error_noslot_pfn(pfn)) diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 62823c0e13ab..2d65800d8e93 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -172,13 +172,18 @@ struct intel_vgpu_submission { #define KVMGT_DEBUGFS_FILENAME "kvmgt_nr_cache_entries" +enum { + INTEL_VGPU_STATUS_ATTACHED = 0, + INTEL_VGPU_STATUS_ACTIVE, + INTEL_VGPU_STATUS_NR_BITS, +}; + struct intel_vgpu { struct vfio_device vfio_device; struct intel_gvt *gvt; struct mutex vgpu_lock; int id; - bool active; - bool attached; + DECLARE_BITMAP(status, INTEL_VGPU_STATUS_NR_BITS); bool pv_notified; bool failsafe; unsigned int resetting_eng; @@ -467,7 +472,7 @@ void intel_vgpu_write_fence(struct intel_vgpu *vgpu, #define for_each_active_vgpu(gvt, vgpu, id) \ idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) \ - for_each_if(vgpu->active) + for_each_if(test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status)) static inline void intel_vgpu_write_pci_bar(struct intel_vgpu *vgpu, u32 offset, u32 val, bool low) @@ -725,7 +730,7 @@ static inline bool intel_gvt_mmio_is_cmd_write_patch( static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa, void *buf, unsigned long len) { - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -ESRCH; return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, false); } @@ -743,7 +748,7 @@ static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa, static inline int intel_gvt_write_gpa(struct intel_vgpu *vgpu, unsigned long gpa, void *buf, unsigned long len) { - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -ESRCH; return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, true); } diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c index a6b2021b665f..68eca023bbc6 100644 --- a/drivers/gpu/drm/i915/gvt/interrupt.c +++ b/drivers/gpu/drm/i915/gvt/interrupt.c @@ -433,7 +433,7 @@ static int inject_virtual_interrupt(struct intel_vgpu *vgpu) * enabled by guest. so if msi_trigger is null, success is still * returned and don't inject interrupt into guest. */ - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -ESRCH; if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1) return -EFAULT; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index f5451adcd489..8ae7039b3683 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -638,7 +638,7 @@ static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu) mutex_lock(&vgpu->gvt->lock); for_each_active_vgpu(vgpu->gvt, itr, id) { - if (!itr->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, itr->status)) continue; if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) { @@ -655,9 +655,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) { struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); - if (vgpu->attached) - return -EEXIST; - if (!vgpu->vfio_device.kvm || vgpu->vfio_device.kvm->mm != current->mm) { gvt_vgpu_err("KVM is required to use Intel vGPU\n"); @@ -667,14 +664,14 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) if (__kvmgt_vgpu_exist(vgpu)) return -EEXIST; - vgpu->attached = true; - vgpu->track_node.track_write = kvmgt_page_track_write; vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot; kvm_get_kvm(vgpu->vfio_device.kvm); kvm_page_track_register_notifier(vgpu->vfio_device.kvm, &vgpu->track_node); + set_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status); + debugfs_create_ulong(KVMGT_DEBUGFS_FILENAME, 0444, vgpu->debugfs, &vgpu->nr_cache_entries); @@ -698,11 +695,10 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev) { struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); - if (!vgpu->attached) - return; - intel_gvt_release_vgpu(vgpu); + clear_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status); + debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs)); kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm, @@ -718,8 +714,6 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev) vgpu->dma_addr_cache = RB_ROOT; intel_vgpu_release_msi_eventfd_ctx(vgpu); - - vgpu->attached = false; } static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar) @@ -1512,9 +1506,6 @@ static void intel_vgpu_remove(struct mdev_device *mdev) { struct intel_vgpu *vgpu = dev_get_drvdata(&mdev->dev); - if (WARN_ON_ONCE(vgpu->attached)) - return; - vfio_unregister_group_dev(&vgpu->vfio_device); vfio_put_device(&vgpu->vfio_device); } @@ -1559,7 +1550,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn) struct kvm_memory_slot *slot; int idx; - if (!info->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status)) return -ESRCH; idx = srcu_read_lock(&kvm->srcu); @@ -1589,8 +1580,8 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn) struct kvm_memory_slot *slot; int idx; - if (!info->attached) - return 0; + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status)) + return -ESRCH; idx = srcu_read_lock(&kvm->srcu); slot = gfn_to_memslot(kvm, gfn); @@ -1668,7 +1659,7 @@ int intel_gvt_dma_map_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, struct gvt_dma *entry; int ret; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return -EINVAL; mutex_lock(&vgpu->cache_lock); @@ -1714,8 +1705,8 @@ int intel_gvt_dma_pin_guest_page(struct intel_vgpu *vgpu, dma_addr_t dma_addr) struct gvt_dma *entry; int ret = 0; - if (!vgpu->attached) - return -ENODEV; + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) + return -EINVAL; mutex_lock(&vgpu->cache_lock); entry = __gvt_cache_find_dma_addr(vgpu, dma_addr); @@ -1742,7 +1733,7 @@ void intel_gvt_dma_unmap_guest_page(struct intel_vgpu *vgpu, { struct gvt_dma *entry; - if (!vgpu->attached) + if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) return; mutex_lock(&vgpu->cache_lock); @@ -1778,7 +1769,7 @@ static void intel_gvt_test_and_emulate_vblank(struct intel_gvt *gvt) idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) { if (test_and_clear_bit(INTEL_GVT_REQUEST_EMULATE_VBLANK + id, (void *)&gvt->service_request)) { - if (vgpu->active) + if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status)) intel_vgpu_emulate_vblank(vgpu); } } diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 8009239935f7..f4055804aad1 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -866,7 +866,8 @@ pick_next_workload(struct intel_gvt *gvt, struct intel_engine_cs *engine) goto out; } - if (!scheduler->current_vgpu->active || + if (!test_bit(INTEL_VGPU_STATUS_ACTIVE, + scheduler->current_vgpu->status) || list_empty(workload_q_head(scheduler->current_vgpu, engine))) goto out; diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 3c529c2705dd..a5497440484f 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -166,9 +166,7 @@ void intel_gvt_clean_vgpu_types(struct intel_gvt *gvt) */ void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu) { - mutex_lock(&vgpu->vgpu_lock); - vgpu->active = true; - mutex_unlock(&vgpu->vgpu_lock); + set_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status); } /** @@ -183,7 +181,7 @@ void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu) { mutex_lock(&vgpu->vgpu_lock); - vgpu->active = false; + clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status); if (atomic_read(&vgpu->submission.running_workload_num)) { mutex_unlock(&vgpu->vgpu_lock); @@ -228,7 +226,8 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) struct intel_gvt *gvt = vgpu->gvt; struct drm_i915_private *i915 = gvt->gt->i915; - drm_WARN(&i915->drm, vgpu->active, "vGPU is still active!\n"); + drm_WARN(&i915->drm, test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status), + "vGPU is still active!\n"); /* * remove idr first so later clean can judge if need to stop @@ -285,8 +284,7 @@ struct intel_vgpu *intel_gvt_create_idle_vgpu(struct intel_gvt *gvt) if (ret) goto out_free_vgpu; - vgpu->active = false; - + clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status); return vgpu; out_free_vgpu: From 4a61648af68f5ba4884f0e3b494ee1cabc4b6620 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Fri, 30 Dec 2022 00:56:41 +0800 Subject: [PATCH 088/233] drm/i915/gvt: fix double free bug in split_2MB_gtt_entry If intel_gvt_dma_map_guest_page failed, it will call ppgtt_invalidate_spt, which will finally free the spt. But the caller function ppgtt_populate_spt_by_guest_entry does not notice that, it will free spt again in its error path. Fix this by canceling the mapping of DMA address and freeing sub_spt. Besides, leave the handle of spt destroy to caller function instead of callee function when error occurs. Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support") Signed-off-by: Zheng Wang Reviewed-by: Zhenyu Wang Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20221229165641.1192455-1-zyytlz.wz@163.com --- drivers/gpu/drm/i915/gvt/gtt.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 6b4039010cae..4ec85308379a 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1209,10 +1209,8 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, for_each_shadow_entry(sub_spt, &sub_se, sub_index) { ret = intel_gvt_dma_map_guest_page(vgpu, start_gfn + sub_index, PAGE_SIZE, &dma_addr); - if (ret) { - ppgtt_invalidate_spt(spt); - return ret; - } + if (ret) + goto err; sub_se.val64 = se->val64; /* Copy the PAT field from PDE. */ @@ -1231,6 +1229,17 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, ops->set_pfn(se, sub_spt->shadow_page.mfn); ppgtt_set_shadow_entry(spt, se, index); return 0; +err: + /* Cancel the existing addess mappings of DMA addr. */ + for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) { + gvt_vdbg_mm("invalidate 4K entry\n"); + ppgtt_invalidate_pte(sub_spt, &sub_se); + } + /* Release the new allocated spt. */ + trace_spt_change(sub_spt->vgpu->id, "release", sub_spt, + sub_spt->guest_page.gfn, sub_spt->shadow_page.type); + ppgtt_free_spt(sub_spt); + return ret; } static int split_64KB_gtt_entry(struct intel_vgpu *vgpu, From 613b14884b8595e20b9fac4126bf627313827fbe Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 4 Jan 2023 08:51:19 -0700 Subject: [PATCH 089/233] block: handle bio_split_to_limits() NULL return This can't happen right now, but in preparation for allowing bio_split_to_limits() returning NULL if it ended the bio, check for it in all the callers. Signed-off-by: Jens Axboe --- block/blk-merge.c | 4 +++- block/blk-mq.c | 5 ++++- drivers/block/drbd/drbd_req.c | 2 ++ drivers/block/ps3vram.c | 2 ++ drivers/md/dm.c | 2 ++ drivers/md/md.c | 2 ++ drivers/nvme/host/multipath.c | 2 ++ drivers/s390/block/dcssblk.c | 2 ++ 8 files changed, 19 insertions(+), 2 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index 35a8f75cc45d..071c5f8cf0cf 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -358,11 +358,13 @@ struct bio *__bio_split_to_limits(struct bio *bio, default: split = bio_split_rw(bio, lim, nr_segs, bs, get_max_io_size(bio, lim) << SECTOR_SHIFT); + if (IS_ERR(split)) + return NULL; break; } if (split) { - /* there isn't chance to merge the splitted bio */ + /* there isn't chance to merge the split bio */ split->bi_opf |= REQ_NOMERGE; blkcg_bio_issue_init(split); diff --git a/block/blk-mq.c b/block/blk-mq.c index c5cf0dbca1db..2c49b4151da1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2951,8 +2951,11 @@ void blk_mq_submit_bio(struct bio *bio) blk_status_t ret; bio = blk_queue_bounce(bio, q); - if (bio_may_exceed_limits(bio, &q->limits)) + if (bio_may_exceed_limits(bio, &q->limits)) { bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); + if (!bio) + return; + } if (!bio_integrity_prep(bio)) return; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index eb14ec8ec04c..e36216d50753 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -1607,6 +1607,8 @@ void drbd_submit_bio(struct bio *bio) struct drbd_device *device = bio->bi_bdev->bd_disk->private_data; bio = bio_split_to_limits(bio); + if (!bio) + return; /* * what we "blindly" assume: diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index c76e0148eada..574e470b220b 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -587,6 +587,8 @@ static void ps3vram_submit_bio(struct bio *bio) dev_dbg(&dev->core, "%s\n", __func__); bio = bio_split_to_limits(bio); + if (!bio) + return; spin_lock_irq(&priv->lock); busy = !bio_list_empty(&priv->list); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index e1ea3a7bd9d9..b424a6ee27ba 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1742,6 +1742,8 @@ static void dm_split_and_process_bio(struct mapped_device *md, * otherwise associated queue_limits won't be imposed. */ bio = bio_split_to_limits(bio); + if (!bio) + return; } init_clone_info(&ci, md, map, bio, is_abnormal); diff --git a/drivers/md/md.c b/drivers/md/md.c index 775f1dde190a..8af639296b3c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -455,6 +455,8 @@ static void md_submit_bio(struct bio *bio) } bio = bio_split_to_limits(bio); + if (!bio) + return; if (mddev->ro == MD_RDONLY && unlikely(rw == WRITE)) { if (bio_sectors(bio) != 0) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index c03093b6813c..fc39d01e7b63 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -376,6 +376,8 @@ static void nvme_ns_head_submit_bio(struct bio *bio) * pool from the original queue to allocate the bvecs from. */ bio = bio_split_to_limits(bio); + if (!bio) + return; srcu_idx = srcu_read_lock(&head->srcu); ns = nvme_find_path(head); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index b392b9f5482e..c0f85ffb2b62 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -865,6 +865,8 @@ dcssblk_submit_bio(struct bio *bio) unsigned long bytes_done; bio = bio_split_to_limits(bio); + if (!bio) + return; bytes_done = 0; dev_info = bio->bi_bdev->bd_disk->private_data; From 481028dbf1daa2808e1be06f6a865b5fe5939efc Mon Sep 17 00:00:00 2001 From: Jesus Sanchez-Palencia Date: Wed, 4 Jan 2023 11:34:14 -0800 Subject: [PATCH 090/233] perf tools: Fix build on uClibc systems by adding missing sys/types.h include Not all libc implementations define ssize_t as part of stdio.h like glibc does since the standard only requires this type to be defined by unistd.h and sys/types.h. For this reason the perf build is currently broken for toolchains based on uClibc, for instance. Include sys/types.h explicitly to fix that. Committer notes: In addition, in the past this worked in uClibc test systems as there was another way to get to sys/types.h that got removed in that cset: tools/perf/util/trace-event.h /usr/include/traceevent/event_parse.h # This got removed from util/trace-event.h in 378ef0f5d9d7f465 /usr/include/regex.h /usr/include/sys/types.h typedef __ssize_t ssize_t; So the size_t that is used in tools/perf/util/trace-event.h was being obtained indirectly, by chance. Fixes: 378ef0f5d9d7f465 ("perf build: Use libtraceevent from the system") Signed-off-by: Jesus Sanchez-Palencia Cc: Alexander Shishkin Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Link: http://lore.kernel.org/lkml/20230104193414.606905-1-jesussanp@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/trace-event.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index add6c5d9531c..9b3cd79cca12 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -4,6 +4,7 @@ #include #include +#include #include struct evlist; From f52853a668bfeddd79f319d536a506f68cc2b478 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 4 Jan 2023 22:58:30 +0800 Subject: [PATCH 091/233] perf/x86/rapl: Add support for Intel Meteor Lake Meteor Lake RAPL support is the same as previous Sky Lake. Add Meteor Lake model for RAPL. Signed-off-by: Zhang Rui Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230104145831.25498-1-rui.zhang@intel.com --- arch/x86/events/rapl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index ae5779ea4417..589c6885560d 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -809,6 +809,8 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); From 57512b57dcfaf63c52d8ad2fb35321328cde31b0 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 4 Jan 2023 22:58:31 +0800 Subject: [PATCH 092/233] perf/x86/rapl: Add support for Intel Emerald Rapids Emerald Rapids RAPL support is the same as previous Sapphire Rapids. Add Emerald Rapids model for RAPL. Signed-off-by: Zhang Rui Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230104145831.25498-2-rui.zhang@intel.com --- arch/x86/events/rapl.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 589c6885560d..52e6e7ed4f78 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -806,6 +806,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &model_spr), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl), From 9cea62b2cbabff8ed46f2df17778b624ad9dd25a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 4 Jan 2023 08:52:06 -0700 Subject: [PATCH 093/233] block: don't allow splitting of a REQ_NOWAIT bio If we split a bio marked with REQ_NOWAIT, then we can trigger spurious EAGAIN if constituent parts of that split bio end up failing request allocations. Parts will complete just fine, but just a single failure in one of the chained bios will yield an EAGAIN final result for the parent bio. Return EAGAIN early if we end up needing to split such a bio, which allows for saner recovery handling. Cc: stable@vger.kernel.org # 5.15+ Link: https://github.com/axboe/liburing/issues/766 Reported-by: Michael Kelley Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- block/blk-merge.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/block/blk-merge.c b/block/blk-merge.c index 071c5f8cf0cf..b7c193d67185 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -309,6 +309,16 @@ static struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, *segs = nsegs; return NULL; split: + /* + * We can't sanely support splitting for a REQ_NOWAIT bio. End it + * with EAGAIN if splitting is required and return an error pointer. + */ + if (bio->bi_opf & REQ_NOWAIT) { + bio->bi_status = BLK_STS_AGAIN; + bio_endio(bio); + return ERR_PTR(-EAGAIN); + } + *segs = nsegs; /* From fa8e442e832a3647cdd90f3e606c473a51bc1b26 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 4 Jan 2023 21:32:35 +0800 Subject: [PATCH 094/233] ublk: honor IO_URING_F_NONBLOCK for handling control command Most of control command handlers may sleep, so return -EAGAIN in case of IO_URING_F_NONBLOCK to defer the handling into io wq context. Fixes: 71f28f3136af ("ublk_drv: add io_uring based userspace block driver") Reported-by: Jens Axboe Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230104133235.836536-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index e9de9d846b73..17b677b5d3b2 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1992,6 +1992,9 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; int ret = -EINVAL; + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + ublk_ctrl_cmd_dump(cmd); if (!(issue_flags & IO_URING_F_SQE128)) From 59b745bb4e0bd445366c45b8df6b51b69134f4f5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 4 Jan 2023 13:49:54 -0700 Subject: [PATCH 095/233] io_uring: move 'poll_multi_queue' bool in io_ring_ctx The cacheline section holding this variable has two gaps, where one is caused by this bool not packing well with structs. This causes it to blow into the next cacheline. Move the variable, shrinking io_ring_ctx by a full cacheline in size. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index dcd8a563ab52..128a67a40065 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -292,6 +292,8 @@ struct io_ring_ctx { struct { spinlock_t completion_lock; + bool poll_multi_queue; + /* * ->iopoll_list is protected by the ctx->uring_lock for * io_uring instances that don't use IORING_SETUP_SQPOLL. @@ -300,7 +302,6 @@ struct io_ring_ctx { */ struct io_wq_work_list iopoll_list; struct io_hash_table cancel_table; - bool poll_multi_queue; struct llist_head work_llist; From ee4b4e2248565babfba807d82c0f3e00c392a4c0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 4 Jan 2023 14:43:27 -0700 Subject: [PATCH 096/233] Revert "block: bio_copy_data_iter" This reverts commit db1c7d77976775483a8ef240b4c705f113e13ea1. We're reinstating the pktcdvd driver, which needs this API. Signed-off-by: Jens Axboe --- block/bio.c | 37 ++++++++++++++++++++++--------------- include/linux/bio.h | 2 ++ 2 files changed, 24 insertions(+), 15 deletions(-) diff --git a/block/bio.c b/block/bio.c index 5f96fcae3f75..ab59a491a883 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1401,6 +1401,27 @@ void __bio_advance(struct bio *bio, unsigned bytes) } EXPORT_SYMBOL(__bio_advance); +void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, + struct bio *src, struct bvec_iter *src_iter) +{ + while (src_iter->bi_size && dst_iter->bi_size) { + struct bio_vec src_bv = bio_iter_iovec(src, *src_iter); + struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter); + unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len); + void *src_buf = bvec_kmap_local(&src_bv); + void *dst_buf = bvec_kmap_local(&dst_bv); + + memcpy(dst_buf, src_buf, bytes); + + kunmap_local(dst_buf); + kunmap_local(src_buf); + + bio_advance_iter_single(src, src_iter, bytes); + bio_advance_iter_single(dst, dst_iter, bytes); + } +} +EXPORT_SYMBOL(bio_copy_data_iter); + /** * bio_copy_data - copy contents of data buffers from one bio to another * @src: source bio @@ -1414,21 +1435,7 @@ void bio_copy_data(struct bio *dst, struct bio *src) struct bvec_iter src_iter = src->bi_iter; struct bvec_iter dst_iter = dst->bi_iter; - while (src_iter.bi_size && dst_iter.bi_size) { - struct bio_vec src_bv = bio_iter_iovec(src, src_iter); - struct bio_vec dst_bv = bio_iter_iovec(dst, dst_iter); - unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len); - void *src_buf = bvec_kmap_local(&src_bv); - void *dst_buf = bvec_kmap_local(&dst_bv); - - memcpy(dst_buf, src_buf, bytes); - - kunmap_local(dst_buf); - kunmap_local(src_buf); - - bio_advance_iter_single(src, &src_iter, bytes); - bio_advance_iter_single(dst, &dst_iter, bytes); - } + bio_copy_data_iter(dst, &dst_iter, src, &src_iter); } EXPORT_SYMBOL(bio_copy_data); diff --git a/include/linux/bio.h b/include/linux/bio.h index 22078a28d7cb..c1da63f6c808 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -475,6 +475,8 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); +extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, + struct bio *src, struct bvec_iter *src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); extern void bio_free_pages(struct bio *bio); void guard_bio_eod(struct bio *bio); From 050a4f341f35bf51db321c7f68700f9e0b1a7552 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 4 Jan 2023 14:44:02 -0700 Subject: [PATCH 097/233] Revert "block: remove devnode callback from struct block_device_operations" This reverts commit 85d6ce58e493ac8b7122e2fbe3f41b94d6ebdc11. We're reinstating the pktcdvd driver, which needs this API. Signed-off-by: Jens Axboe --- block/genhd.c | 11 +++++++++++ include/linux/blkdev.h | 1 + 2 files changed, 12 insertions(+) diff --git a/block/genhd.c b/block/genhd.c index 08f76135a637..14329dc278b2 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1201,10 +1201,21 @@ struct class block_class = { .dev_uevent = block_uevent, }; +static char *block_devnode(struct device *dev, umode_t *mode, + kuid_t *uid, kgid_t *gid) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (disk->fops->devnode) + return disk->fops->devnode(disk, mode); + return NULL; +} + const struct device_type disk_type = { .name = "disk", .groups = disk_attr_groups, .release = disk_release, + .devnode = block_devnode, }; #ifdef CONFIG_PROC_FS diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 301cf1cf4f2f..43d4e073b111 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1395,6 +1395,7 @@ struct block_device_operations { void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); + char *(*devnode)(struct gendisk *disk, umode_t *mode); /* returns the length of the identifier or a negative errno: */ int (*get_unique_id)(struct gendisk *disk, u8 id[16], enum blk_unique_id id_type); From 4b83e99ee7092df37a5cf292fde976ebc475ea63 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 4 Jan 2023 14:44:13 -0700 Subject: [PATCH 098/233] Revert "pktcdvd: remove driver." MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit f40eb99897af665f11858dd7b56edcb62c3f3c67. There are apparently still users out there of this driver. While we'd love to remove it to ease the maintenance burden, let's reinstate it for now until better (userspace) solutions can be developed. Link: https://lore.kernel.org/lkml/20230104190115.ceglfefco475ev6c@pali/ Reported-by: Pali Rohár Signed-off-by: Jens Axboe --- Documentation/ABI/testing/debugfs-pktcdvd | 18 + Documentation/ABI/testing/sysfs-class-pktcdvd | 97 + MAINTAINERS | 7 + drivers/block/Kconfig | 43 + drivers/block/Makefile | 1 + drivers/block/pktcdvd.c | 2944 +++++++++++++++++ include/linux/pktcdvd.h | 197 ++ include/uapi/linux/pktcdvd.h | 112 + 8 files changed, 3419 insertions(+) create mode 100644 Documentation/ABI/testing/debugfs-pktcdvd create mode 100644 Documentation/ABI/testing/sysfs-class-pktcdvd create mode 100644 drivers/block/pktcdvd.c create mode 100644 include/linux/pktcdvd.h create mode 100644 include/uapi/linux/pktcdvd.h diff --git a/Documentation/ABI/testing/debugfs-pktcdvd b/Documentation/ABI/testing/debugfs-pktcdvd new file mode 100644 index 000000000000..f6f65a4faea0 --- /dev/null +++ b/Documentation/ABI/testing/debugfs-pktcdvd @@ -0,0 +1,18 @@ +What: /sys/kernel/debug/pktcdvd/pktcdvd[0-7] +Date: Oct. 2006 +KernelVersion: 2.6.20 +Contact: Thomas Maier +Description: + +The pktcdvd module (packet writing driver) creates +these files in debugfs: + +/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/ + + ==== ====== ==================================== + info 0444 Lots of driver statistics and infos. + ==== ====== ==================================== + +Example:: + + cat /sys/kernel/debug/pktcdvd/pktcdvd0/info diff --git a/Documentation/ABI/testing/sysfs-class-pktcdvd b/Documentation/ABI/testing/sysfs-class-pktcdvd new file mode 100644 index 000000000000..ba1ce626591d --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-pktcdvd @@ -0,0 +1,97 @@ +sysfs interface +--------------- +The pktcdvd module (packet writing driver) creates the following files in the +sysfs: ( is in the format major:minor) + +What: /sys/class/pktcdvd/add +What: /sys/class/pktcdvd/remove +What: /sys/class/pktcdvd/device_map +Date: Oct. 2006 +KernelVersion: 2.6.20 +Contact: Thomas Maier +Description: + + ========== ============================================== + add (WO) Write a block device id (major:minor) to + create a new pktcdvd device and map it to the + block device. + + remove (WO) Write the pktcdvd device id (major:minor) + to remove the pktcdvd device. + + device_map (RO) Shows the device mapping in format: + pktcdvd[0-7] + ========== ============================================== + + +What: /sys/class/pktcdvd/pktcdvd[0-7]/dev +What: /sys/class/pktcdvd/pktcdvd[0-7]/uevent +Date: Oct. 2006 +KernelVersion: 2.6.20 +Contact: Thomas Maier +Description: + dev: (RO) Device id + + uevent: (WO) To send a uevent + + +What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_started +What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_finished +What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_written +What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read +What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read_gather +What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/reset +Date: Oct. 2006 +KernelVersion: 2.6.20 +Contact: Thomas Maier +Description: + packets_started: (RO) Number of started packets. + + packets_finished: (RO) Number of finished packets. + + kb_written: (RO) kBytes written. + + kb_read: (RO) kBytes read. + + kb_read_gather: (RO) kBytes read to fill write packets. + + reset: (WO) Write any value to it to reset + pktcdvd device statistic values, like + bytes read/written. + + +What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/size +What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_off +What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_on +Date: Oct. 2006 +KernelVersion: 2.6.20 +Contact: Thomas Maier +Description: + ============== ================================================ + size (RO) Contains the size of the bio write queue. + + congestion_off (RW) If bio write queue size is below this mark, + accept new bio requests from the block layer. + + congestion_on (RW) If bio write queue size is higher as this + mark, do no longer accept bio write requests + from the block layer and wait till the pktcdvd + device has processed enough bio's so that bio + write queue size is below congestion off mark. + A value of <= 0 disables congestion control. + ============== ================================================ + + +Example: +-------- +To use the pktcdvd sysfs interface directly, you can do:: + + # create a new pktcdvd device mapped to /dev/hdc + echo "22:0" >/sys/class/pktcdvd/add + cat /sys/class/pktcdvd/device_map + # assuming device pktcdvd0 was created, look at stat's + cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written + # print the device id of the mapped block device + fgrep pktcdvd0 /sys/class/pktcdvd/device_map + # remove device, using pktcdvd0 device id 253:0 + echo "253:0" >/sys/class/pktcdvd/remove diff --git a/MAINTAINERS b/MAINTAINERS index d53b3a6cdc67..3ef137fea4f6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16520,6 +16520,13 @@ S: Supported F: Documentation/devicetree/bindings/input/pine64,pinephone-keyboard.yaml F: drivers/input/keyboard/pinephone-keyboard.c +PKTCDVD DRIVER +M: linux-block@vger.kernel.org +S: Orphan +F: drivers/block/pktcdvd.c +F: include/linux/pktcdvd.h +F: include/uapi/linux/pktcdvd.h + PLANTOWER PMS7003 AIR POLLUTION SENSOR DRIVER M: Tomasz Duszynski S: Maintained diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index a2184b428493..a41145d52de9 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -285,6 +285,49 @@ config BLK_DEV_RAM_SIZE The default value is 4096 kilobytes. Only change this if you know what you are doing. +config CDROM_PKTCDVD + tristate "Packet writing on CD/DVD media (DEPRECATED)" + depends on !UML + depends on SCSI + select CDROM + help + Note: This driver is deprecated and will be removed from the + kernel in the near future! + + If you have a CDROM/DVD drive that supports packet writing, say + Y to include support. It should work with any MMC/Mt Fuji + compliant ATAPI or SCSI drive, which is just about any newer + DVD/CD writer. + + Currently only writing to CD-RW, DVD-RW, DVD+RW and DVDRAM discs + is possible. + DVD-RW disks must be in restricted overwrite mode. + + See the file + for further information on the use of this driver. + + To compile this driver as a module, choose M here: the + module will be called pktcdvd. + +config CDROM_PKTCDVD_BUFFERS + int "Free buffers for data gathering" + depends on CDROM_PKTCDVD + default "8" + help + This controls the maximum number of active concurrent packets. More + concurrent packets can increase write performance, but also require + more memory. Each concurrent packet will require approximately 64Kb + of non-swappable kernel memory, memory which will be allocated when + a disc is opened for writing. + +config CDROM_PKTCDVD_WCACHE + bool "Enable write caching" + depends on CDROM_PKTCDVD + help + If enabled, write caching will be set for the CD-R/W device. For now + this option is dangerous unless the CD-RW media is known good, as we + don't do deferred write error handling yet. + config ATA_OVER_ETH tristate "ATA over Ethernet support" depends on NET diff --git a/drivers/block/Makefile b/drivers/block/Makefile index 962ee65d8ca3..101612cba303 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_AMIGA_Z2RAM) += z2ram.o obj-$(CONFIG_N64CART) += n64cart.o obj-$(CONFIG_BLK_DEV_RAM) += brd.o obj-$(CONFIG_BLK_DEV_LOOP) += loop.o +obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o obj-$(CONFIG_SUNVDC) += sunvdc.o obj-$(CONFIG_BLK_DEV_NBD) += nbd.o diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c new file mode 100644 index 000000000000..4cea3b08087e --- /dev/null +++ b/drivers/block/pktcdvd.c @@ -0,0 +1,2944 @@ +/* + * Copyright (C) 2000 Jens Axboe + * Copyright (C) 2001-2004 Peter Osterlund + * Copyright (C) 2006 Thomas Maier + * + * May be copied or modified under the terms of the GNU General Public + * License. See linux/COPYING for more information. + * + * Packet writing layer for ATAPI and SCSI CD-RW, DVD+RW, DVD-RW and + * DVD-RAM devices. + * + * Theory of operation: + * + * At the lowest level, there is the standard driver for the CD/DVD device, + * such as drivers/scsi/sr.c. This driver can handle read and write requests, + * but it doesn't know anything about the special restrictions that apply to + * packet writing. One restriction is that write requests must be aligned to + * packet boundaries on the physical media, and the size of a write request + * must be equal to the packet size. Another restriction is that a + * GPCMD_FLUSH_CACHE command has to be issued to the drive before a read + * command, if the previous command was a write. + * + * The purpose of the packet writing driver is to hide these restrictions from + * higher layers, such as file systems, and present a block device that can be + * randomly read and written using 2kB-sized blocks. + * + * The lowest layer in the packet writing driver is the packet I/O scheduler. + * Its data is defined by the struct packet_iosched and includes two bio + * queues with pending read and write requests. These queues are processed + * by the pkt_iosched_process_queue() function. The write requests in this + * queue are already properly aligned and sized. This layer is responsible for + * issuing the flush cache commands and scheduling the I/O in a good order. + * + * The next layer transforms unaligned write requests to aligned writes. This + * transformation requires reading missing pieces of data from the underlying + * block device, assembling the pieces to full packets and queuing them to the + * packet I/O scheduler. + * + * At the top layer there is a custom ->submit_bio function that forwards + * read requests directly to the iosched queue and puts write requests in the + * unaligned write queue. A kernel thread performs the necessary read + * gathering to convert the unaligned writes to aligned writes and then feeds + * them to the packet I/O scheduler. + * + *************************************************************************/ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRIVER_NAME "pktcdvd" + +#define pkt_err(pd, fmt, ...) \ + pr_err("%s: " fmt, pd->name, ##__VA_ARGS__) +#define pkt_notice(pd, fmt, ...) \ + pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__) +#define pkt_info(pd, fmt, ...) \ + pr_info("%s: " fmt, pd->name, ##__VA_ARGS__) + +#define pkt_dbg(level, pd, fmt, ...) \ +do { \ + if (level == 2 && PACKET_DEBUG >= 2) \ + pr_notice("%s: %s():" fmt, \ + pd->name, __func__, ##__VA_ARGS__); \ + else if (level == 1 && PACKET_DEBUG >= 1) \ + pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__); \ +} while (0) + +#define MAX_SPEED 0xffff + +static DEFINE_MUTEX(pktcdvd_mutex); +static struct pktcdvd_device *pkt_devs[MAX_WRITERS]; +static struct proc_dir_entry *pkt_proc; +static int pktdev_major; +static int write_congestion_on = PKT_WRITE_CONGESTION_ON; +static int write_congestion_off = PKT_WRITE_CONGESTION_OFF; +static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */ +static mempool_t psd_pool; +static struct bio_set pkt_bio_set; + +static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */ +static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */ + +/* forward declaration */ +static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev); +static int pkt_remove_dev(dev_t pkt_dev); +static int pkt_seq_show(struct seq_file *m, void *p); + +static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd) +{ + return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1); +} + +/********************************************************** + * sysfs interface for pktcdvd + * by (C) 2006 Thomas Maier + + /sys/class/pktcdvd/pktcdvd[0-7]/ + stat/reset + stat/packets_started + stat/packets_finished + stat/kb_written + stat/kb_read + stat/kb_read_gather + write_queue/size + write_queue/congestion_off + write_queue/congestion_on + **********************************************************/ + +static ssize_t packets_started_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%lu\n", pd->stats.pkt_started); +} +static DEVICE_ATTR_RO(packets_started); + +static ssize_t packets_finished_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%lu\n", pd->stats.pkt_ended); +} +static DEVICE_ATTR_RO(packets_finished); + +static ssize_t kb_written_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%lu\n", pd->stats.secs_w >> 1); +} +static DEVICE_ATTR_RO(kb_written); + +static ssize_t kb_read_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%lu\n", pd->stats.secs_r >> 1); +} +static DEVICE_ATTR_RO(kb_read); + +static ssize_t kb_read_gather_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%lu\n", pd->stats.secs_rg >> 1); +} +static DEVICE_ATTR_RO(kb_read_gather); + +static ssize_t reset_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + + if (len > 0) { + pd->stats.pkt_started = 0; + pd->stats.pkt_ended = 0; + pd->stats.secs_w = 0; + pd->stats.secs_rg = 0; + pd->stats.secs_r = 0; + } + return len; +} +static DEVICE_ATTR_WO(reset); + +static struct attribute *pkt_stat_attrs[] = { + &dev_attr_packets_finished.attr, + &dev_attr_packets_started.attr, + &dev_attr_kb_read.attr, + &dev_attr_kb_written.attr, + &dev_attr_kb_read_gather.attr, + &dev_attr_reset.attr, + NULL, +}; + +static const struct attribute_group pkt_stat_group = { + .name = "stat", + .attrs = pkt_stat_attrs, +}; + +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int n; + + spin_lock(&pd->lock); + n = sysfs_emit(buf, "%d\n", pd->bio_queue_size); + spin_unlock(&pd->lock); + return n; +} +static DEVICE_ATTR_RO(size); + +static void init_write_congestion_marks(int* lo, int* hi) +{ + if (*hi > 0) { + *hi = max(*hi, 500); + *hi = min(*hi, 1000000); + if (*lo <= 0) + *lo = *hi - 100; + else { + *lo = min(*lo, *hi - 100); + *lo = max(*lo, 100); + } + } else { + *hi = -1; + *lo = -1; + } +} + +static ssize_t congestion_off_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int n; + + spin_lock(&pd->lock); + n = sysfs_emit(buf, "%d\n", pd->write_congestion_off); + spin_unlock(&pd->lock); + return n; +} + +static ssize_t congestion_off_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int val; + + if (sscanf(buf, "%d", &val) == 1) { + spin_lock(&pd->lock); + pd->write_congestion_off = val; + init_write_congestion_marks(&pd->write_congestion_off, + &pd->write_congestion_on); + spin_unlock(&pd->lock); + } + return len; +} +static DEVICE_ATTR_RW(congestion_off); + +static ssize_t congestion_on_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int n; + + spin_lock(&pd->lock); + n = sysfs_emit(buf, "%d\n", pd->write_congestion_on); + spin_unlock(&pd->lock); + return n; +} + +static ssize_t congestion_on_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int val; + + if (sscanf(buf, "%d", &val) == 1) { + spin_lock(&pd->lock); + pd->write_congestion_on = val; + init_write_congestion_marks(&pd->write_congestion_off, + &pd->write_congestion_on); + spin_unlock(&pd->lock); + } + return len; +} +static DEVICE_ATTR_RW(congestion_on); + +static struct attribute *pkt_wq_attrs[] = { + &dev_attr_congestion_on.attr, + &dev_attr_congestion_off.attr, + &dev_attr_size.attr, + NULL, +}; + +static const struct attribute_group pkt_wq_group = { + .name = "write_queue", + .attrs = pkt_wq_attrs, +}; + +static const struct attribute_group *pkt_groups[] = { + &pkt_stat_group, + &pkt_wq_group, + NULL, +}; + +static void pkt_sysfs_dev_new(struct pktcdvd_device *pd) +{ + if (class_pktcdvd) { + pd->dev = device_create_with_groups(class_pktcdvd, NULL, + MKDEV(0, 0), pd, pkt_groups, + "%s", pd->name); + if (IS_ERR(pd->dev)) + pd->dev = NULL; + } +} + +static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd) +{ + if (class_pktcdvd) + device_unregister(pd->dev); +} + + +/******************************************************************** + /sys/class/pktcdvd/ + add map block device + remove unmap packet dev + device_map show mappings + *******************************************************************/ + +static void class_pktcdvd_release(struct class *cls) +{ + kfree(cls); +} + +static ssize_t device_map_show(struct class *c, struct class_attribute *attr, + char *data) +{ + int n = 0; + int idx; + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + for (idx = 0; idx < MAX_WRITERS; idx++) { + struct pktcdvd_device *pd = pkt_devs[idx]; + if (!pd) + continue; + n += sprintf(data+n, "%s %u:%u %u:%u\n", + pd->name, + MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev), + MAJOR(pd->bdev->bd_dev), + MINOR(pd->bdev->bd_dev)); + } + mutex_unlock(&ctl_mutex); + return n; +} +static CLASS_ATTR_RO(device_map); + +static ssize_t add_store(struct class *c, struct class_attribute *attr, + const char *buf, size_t count) +{ + unsigned int major, minor; + + if (sscanf(buf, "%u:%u", &major, &minor) == 2) { + /* pkt_setup_dev() expects caller to hold reference to self */ + if (!try_module_get(THIS_MODULE)) + return -ENODEV; + + pkt_setup_dev(MKDEV(major, minor), NULL); + + module_put(THIS_MODULE); + + return count; + } + + return -EINVAL; +} +static CLASS_ATTR_WO(add); + +static ssize_t remove_store(struct class *c, struct class_attribute *attr, + const char *buf, size_t count) +{ + unsigned int major, minor; + if (sscanf(buf, "%u:%u", &major, &minor) == 2) { + pkt_remove_dev(MKDEV(major, minor)); + return count; + } + return -EINVAL; +} +static CLASS_ATTR_WO(remove); + +static struct attribute *class_pktcdvd_attrs[] = { + &class_attr_add.attr, + &class_attr_remove.attr, + &class_attr_device_map.attr, + NULL, +}; +ATTRIBUTE_GROUPS(class_pktcdvd); + +static int pkt_sysfs_init(void) +{ + int ret = 0; + + /* + * create control files in sysfs + * /sys/class/pktcdvd/... + */ + class_pktcdvd = kzalloc(sizeof(*class_pktcdvd), GFP_KERNEL); + if (!class_pktcdvd) + return -ENOMEM; + class_pktcdvd->name = DRIVER_NAME; + class_pktcdvd->owner = THIS_MODULE; + class_pktcdvd->class_release = class_pktcdvd_release; + class_pktcdvd->class_groups = class_pktcdvd_groups; + ret = class_register(class_pktcdvd); + if (ret) { + kfree(class_pktcdvd); + class_pktcdvd = NULL; + pr_err("failed to create class pktcdvd\n"); + return ret; + } + return 0; +} + +static void pkt_sysfs_cleanup(void) +{ + if (class_pktcdvd) + class_destroy(class_pktcdvd); + class_pktcdvd = NULL; +} + +/******************************************************************** + entries in debugfs + + /sys/kernel/debug/pktcdvd[0-7]/ + info + + *******************************************************************/ + +static int pkt_debugfs_seq_show(struct seq_file *m, void *p) +{ + return pkt_seq_show(m, p); +} + +static int pkt_debugfs_fops_open(struct inode *inode, struct file *file) +{ + return single_open(file, pkt_debugfs_seq_show, inode->i_private); +} + +static const struct file_operations debug_fops = { + .open = pkt_debugfs_fops_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .owner = THIS_MODULE, +}; + +static void pkt_debugfs_dev_new(struct pktcdvd_device *pd) +{ + if (!pkt_debugfs_root) + return; + pd->dfs_d_root = debugfs_create_dir(pd->name, pkt_debugfs_root); + if (!pd->dfs_d_root) + return; + + pd->dfs_f_info = debugfs_create_file("info", 0444, + pd->dfs_d_root, pd, &debug_fops); +} + +static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd) +{ + if (!pkt_debugfs_root) + return; + debugfs_remove(pd->dfs_f_info); + debugfs_remove(pd->dfs_d_root); + pd->dfs_f_info = NULL; + pd->dfs_d_root = NULL; +} + +static void pkt_debugfs_init(void) +{ + pkt_debugfs_root = debugfs_create_dir(DRIVER_NAME, NULL); +} + +static void pkt_debugfs_cleanup(void) +{ + debugfs_remove(pkt_debugfs_root); + pkt_debugfs_root = NULL; +} + +/* ----------------------------------------------------------*/ + + +static void pkt_bio_finished(struct pktcdvd_device *pd) +{ + BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0); + if (atomic_dec_and_test(&pd->cdrw.pending_bios)) { + pkt_dbg(2, pd, "queue empty\n"); + atomic_set(&pd->iosched.attention, 1); + wake_up(&pd->wqueue); + } +} + +/* + * Allocate a packet_data struct + */ +static struct packet_data *pkt_alloc_packet_data(int frames) +{ + int i; + struct packet_data *pkt; + + pkt = kzalloc(sizeof(struct packet_data), GFP_KERNEL); + if (!pkt) + goto no_pkt; + + pkt->frames = frames; + pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL); + if (!pkt->w_bio) + goto no_bio; + + for (i = 0; i < frames / FRAMES_PER_PAGE; i++) { + pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO); + if (!pkt->pages[i]) + goto no_page; + } + + spin_lock_init(&pkt->lock); + bio_list_init(&pkt->orig_bios); + + for (i = 0; i < frames; i++) { + pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL); + if (!pkt->r_bios[i]) + goto no_rd_bio; + } + + return pkt; + +no_rd_bio: + for (i = 0; i < frames; i++) + kfree(pkt->r_bios[i]); +no_page: + for (i = 0; i < frames / FRAMES_PER_PAGE; i++) + if (pkt->pages[i]) + __free_page(pkt->pages[i]); + kfree(pkt->w_bio); +no_bio: + kfree(pkt); +no_pkt: + return NULL; +} + +/* + * Free a packet_data struct + */ +static void pkt_free_packet_data(struct packet_data *pkt) +{ + int i; + + for (i = 0; i < pkt->frames; i++) + kfree(pkt->r_bios[i]); + for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++) + __free_page(pkt->pages[i]); + kfree(pkt->w_bio); + kfree(pkt); +} + +static void pkt_shrink_pktlist(struct pktcdvd_device *pd) +{ + struct packet_data *pkt, *next; + + BUG_ON(!list_empty(&pd->cdrw.pkt_active_list)); + + list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_free_list, list) { + pkt_free_packet_data(pkt); + } + INIT_LIST_HEAD(&pd->cdrw.pkt_free_list); +} + +static int pkt_grow_pktlist(struct pktcdvd_device *pd, int nr_packets) +{ + struct packet_data *pkt; + + BUG_ON(!list_empty(&pd->cdrw.pkt_free_list)); + + while (nr_packets > 0) { + pkt = pkt_alloc_packet_data(pd->settings.size >> 2); + if (!pkt) { + pkt_shrink_pktlist(pd); + return 0; + } + pkt->id = nr_packets; + pkt->pd = pd; + list_add(&pkt->list, &pd->cdrw.pkt_free_list); + nr_packets--; + } + return 1; +} + +static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node) +{ + struct rb_node *n = rb_next(&node->rb_node); + if (!n) + return NULL; + return rb_entry(n, struct pkt_rb_node, rb_node); +} + +static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node) +{ + rb_erase(&node->rb_node, &pd->bio_queue); + mempool_free(node, &pd->rb_pool); + pd->bio_queue_size--; + BUG_ON(pd->bio_queue_size < 0); +} + +/* + * Find the first node in the pd->bio_queue rb tree with a starting sector >= s. + */ +static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s) +{ + struct rb_node *n = pd->bio_queue.rb_node; + struct rb_node *next; + struct pkt_rb_node *tmp; + + if (!n) { + BUG_ON(pd->bio_queue_size > 0); + return NULL; + } + + for (;;) { + tmp = rb_entry(n, struct pkt_rb_node, rb_node); + if (s <= tmp->bio->bi_iter.bi_sector) + next = n->rb_left; + else + next = n->rb_right; + if (!next) + break; + n = next; + } + + if (s > tmp->bio->bi_iter.bi_sector) { + tmp = pkt_rbtree_next(tmp); + if (!tmp) + return NULL; + } + BUG_ON(s > tmp->bio->bi_iter.bi_sector); + return tmp; +} + +/* + * Insert a node into the pd->bio_queue rb tree. + */ +static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *node) +{ + struct rb_node **p = &pd->bio_queue.rb_node; + struct rb_node *parent = NULL; + sector_t s = node->bio->bi_iter.bi_sector; + struct pkt_rb_node *tmp; + + while (*p) { + parent = *p; + tmp = rb_entry(parent, struct pkt_rb_node, rb_node); + if (s < tmp->bio->bi_iter.bi_sector) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&node->rb_node, parent, p); + rb_insert_color(&node->rb_node, &pd->bio_queue); + pd->bio_queue_size++; +} + +/* + * Send a packet_command to the underlying block device and + * wait for completion. + */ +static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc) +{ + struct request_queue *q = bdev_get_queue(pd->bdev); + struct scsi_cmnd *scmd; + struct request *rq; + int ret = 0; + + rq = scsi_alloc_request(q, (cgc->data_direction == CGC_DATA_WRITE) ? + REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); + if (IS_ERR(rq)) + return PTR_ERR(rq); + scmd = blk_mq_rq_to_pdu(rq); + + if (cgc->buflen) { + ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen, + GFP_NOIO); + if (ret) + goto out; + } + + scmd->cmd_len = COMMAND_SIZE(cgc->cmd[0]); + memcpy(scmd->cmnd, cgc->cmd, CDROM_PACKET_SIZE); + + rq->timeout = 60*HZ; + if (cgc->quiet) + rq->rq_flags |= RQF_QUIET; + + blk_execute_rq(rq, false); + if (scmd->result) + ret = -EIO; +out: + blk_mq_free_request(rq); + return ret; +} + +static const char *sense_key_string(__u8 index) +{ + static const char * const info[] = { + "No sense", "Recovered error", "Not ready", + "Medium error", "Hardware error", "Illegal request", + "Unit attention", "Data protect", "Blank check", + }; + + return index < ARRAY_SIZE(info) ? info[index] : "INVALID"; +} + +/* + * A generic sense dump / resolve mechanism should be implemented across + * all ATAPI + SCSI devices. + */ +static void pkt_dump_sense(struct pktcdvd_device *pd, + struct packet_command *cgc) +{ + struct scsi_sense_hdr *sshdr = cgc->sshdr; + + if (sshdr) + pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n", + CDROM_PACKET_SIZE, cgc->cmd, + sshdr->sense_key, sshdr->asc, sshdr->ascq, + sense_key_string(sshdr->sense_key)); + else + pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd); +} + +/* + * flush the drive cache to media + */ +static int pkt_flush_cache(struct pktcdvd_device *pd) +{ + struct packet_command cgc; + + init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); + cgc.cmd[0] = GPCMD_FLUSH_CACHE; + cgc.quiet = 1; + + /* + * the IMMED bit -- we default to not setting it, although that + * would allow a much faster close, this is safer + */ +#if 0 + cgc.cmd[1] = 1 << 1; +#endif + return pkt_generic_packet(pd, &cgc); +} + +/* + * speed is given as the normal factor, e.g. 4 for 4x + */ +static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd, + unsigned write_speed, unsigned read_speed) +{ + struct packet_command cgc; + struct scsi_sense_hdr sshdr; + int ret; + + init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); + cgc.sshdr = &sshdr; + cgc.cmd[0] = GPCMD_SET_SPEED; + cgc.cmd[2] = (read_speed >> 8) & 0xff; + cgc.cmd[3] = read_speed & 0xff; + cgc.cmd[4] = (write_speed >> 8) & 0xff; + cgc.cmd[5] = write_speed & 0xff; + + ret = pkt_generic_packet(pd, &cgc); + if (ret) + pkt_dump_sense(pd, &cgc); + + return ret; +} + +/* + * Queue a bio for processing by the low-level CD device. Must be called + * from process context. + */ +static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio) +{ + spin_lock(&pd->iosched.lock); + if (bio_data_dir(bio) == READ) + bio_list_add(&pd->iosched.read_queue, bio); + else + bio_list_add(&pd->iosched.write_queue, bio); + spin_unlock(&pd->iosched.lock); + + atomic_set(&pd->iosched.attention, 1); + wake_up(&pd->wqueue); +} + +/* + * Process the queued read/write requests. This function handles special + * requirements for CDRW drives: + * - A cache flush command must be inserted before a read request if the + * previous request was a write. + * - Switching between reading and writing is slow, so don't do it more often + * than necessary. + * - Optimize for throughput at the expense of latency. This means that streaming + * writes will never be interrupted by a read, but if the drive has to seek + * before the next write, switch to reading instead if there are any pending + * read requests. + * - Set the read speed according to current usage pattern. When only reading + * from the device, it's best to use the highest possible read speed, but + * when switching often between reading and writing, it's better to have the + * same read and write speeds. + */ +static void pkt_iosched_process_queue(struct pktcdvd_device *pd) +{ + + if (atomic_read(&pd->iosched.attention) == 0) + return; + atomic_set(&pd->iosched.attention, 0); + + for (;;) { + struct bio *bio; + int reads_queued, writes_queued; + + spin_lock(&pd->iosched.lock); + reads_queued = !bio_list_empty(&pd->iosched.read_queue); + writes_queued = !bio_list_empty(&pd->iosched.write_queue); + spin_unlock(&pd->iosched.lock); + + if (!reads_queued && !writes_queued) + break; + + if (pd->iosched.writing) { + int need_write_seek = 1; + spin_lock(&pd->iosched.lock); + bio = bio_list_peek(&pd->iosched.write_queue); + spin_unlock(&pd->iosched.lock); + if (bio && (bio->bi_iter.bi_sector == + pd->iosched.last_write)) + need_write_seek = 0; + if (need_write_seek && reads_queued) { + if (atomic_read(&pd->cdrw.pending_bios) > 0) { + pkt_dbg(2, pd, "write, waiting\n"); + break; + } + pkt_flush_cache(pd); + pd->iosched.writing = 0; + } + } else { + if (!reads_queued && writes_queued) { + if (atomic_read(&pd->cdrw.pending_bios) > 0) { + pkt_dbg(2, pd, "read, waiting\n"); + break; + } + pd->iosched.writing = 1; + } + } + + spin_lock(&pd->iosched.lock); + if (pd->iosched.writing) + bio = bio_list_pop(&pd->iosched.write_queue); + else + bio = bio_list_pop(&pd->iosched.read_queue); + spin_unlock(&pd->iosched.lock); + + if (!bio) + continue; + + if (bio_data_dir(bio) == READ) + pd->iosched.successive_reads += + bio->bi_iter.bi_size >> 10; + else { + pd->iosched.successive_reads = 0; + pd->iosched.last_write = bio_end_sector(bio); + } + if (pd->iosched.successive_reads >= HI_SPEED_SWITCH) { + if (pd->read_speed == pd->write_speed) { + pd->read_speed = MAX_SPEED; + pkt_set_speed(pd, pd->write_speed, pd->read_speed); + } + } else { + if (pd->read_speed != pd->write_speed) { + pd->read_speed = pd->write_speed; + pkt_set_speed(pd, pd->write_speed, pd->read_speed); + } + } + + atomic_inc(&pd->cdrw.pending_bios); + submit_bio_noacct(bio); + } +} + +/* + * Special care is needed if the underlying block device has a small + * max_phys_segments value. + */ +static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q) +{ + if ((pd->settings.size << 9) / CD_FRAMESIZE + <= queue_max_segments(q)) { + /* + * The cdrom device can handle one segment/frame + */ + clear_bit(PACKET_MERGE_SEGS, &pd->flags); + return 0; + } else if ((pd->settings.size << 9) / PAGE_SIZE + <= queue_max_segments(q)) { + /* + * We can handle this case at the expense of some extra memory + * copies during write operations + */ + set_bit(PACKET_MERGE_SEGS, &pd->flags); + return 0; + } else { + pkt_err(pd, "cdrom max_phys_segments too small\n"); + return -EIO; + } +} + +static void pkt_end_io_read(struct bio *bio) +{ + struct packet_data *pkt = bio->bi_private; + struct pktcdvd_device *pd = pkt->pd; + BUG_ON(!pd); + + pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n", + bio, (unsigned long long)pkt->sector, + (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status); + + if (bio->bi_status) + atomic_inc(&pkt->io_errors); + bio_uninit(bio); + if (atomic_dec_and_test(&pkt->io_wait)) { + atomic_inc(&pkt->run_sm); + wake_up(&pd->wqueue); + } + pkt_bio_finished(pd); +} + +static void pkt_end_io_packet_write(struct bio *bio) +{ + struct packet_data *pkt = bio->bi_private; + struct pktcdvd_device *pd = pkt->pd; + BUG_ON(!pd); + + pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status); + + pd->stats.pkt_ended++; + + bio_uninit(bio); + pkt_bio_finished(pd); + atomic_dec(&pkt->io_wait); + atomic_inc(&pkt->run_sm); + wake_up(&pd->wqueue); +} + +/* + * Schedule reads for the holes in a packet + */ +static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) +{ + int frames_read = 0; + struct bio *bio; + int f; + char written[PACKET_MAX_SIZE]; + + BUG_ON(bio_list_empty(&pkt->orig_bios)); + + atomic_set(&pkt->io_wait, 0); + atomic_set(&pkt->io_errors, 0); + + /* + * Figure out which frames we need to read before we can write. + */ + memset(written, 0, sizeof(written)); + spin_lock(&pkt->lock); + bio_list_for_each(bio, &pkt->orig_bios) { + int first_frame = (bio->bi_iter.bi_sector - pkt->sector) / + (CD_FRAMESIZE >> 9); + int num_frames = bio->bi_iter.bi_size / CD_FRAMESIZE; + pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9); + BUG_ON(first_frame < 0); + BUG_ON(first_frame + num_frames > pkt->frames); + for (f = first_frame; f < first_frame + num_frames; f++) + written[f] = 1; + } + spin_unlock(&pkt->lock); + + if (pkt->cache_valid) { + pkt_dbg(2, pd, "zone %llx cached\n", + (unsigned long long)pkt->sector); + goto out_account; + } + + /* + * Schedule reads for missing parts of the packet. + */ + for (f = 0; f < pkt->frames; f++) { + int p, offset; + + if (written[f]) + continue; + + bio = pkt->r_bios[f]; + bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ); + bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9); + bio->bi_end_io = pkt_end_io_read; + bio->bi_private = pkt; + + p = (f * CD_FRAMESIZE) / PAGE_SIZE; + offset = (f * CD_FRAMESIZE) % PAGE_SIZE; + pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n", + f, pkt->pages[p], offset); + if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset)) + BUG(); + + atomic_inc(&pkt->io_wait); + pkt_queue_bio(pd, bio); + frames_read++; + } + +out_account: + pkt_dbg(2, pd, "need %d frames for zone %llx\n", + frames_read, (unsigned long long)pkt->sector); + pd->stats.pkt_started++; + pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9); +} + +/* + * Find a packet matching zone, or the least recently used packet if + * there is no match. + */ +static struct packet_data *pkt_get_packet_data(struct pktcdvd_device *pd, int zone) +{ + struct packet_data *pkt; + + list_for_each_entry(pkt, &pd->cdrw.pkt_free_list, list) { + if (pkt->sector == zone || pkt->list.next == &pd->cdrw.pkt_free_list) { + list_del_init(&pkt->list); + if (pkt->sector != zone) + pkt->cache_valid = 0; + return pkt; + } + } + BUG(); + return NULL; +} + +static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *pkt) +{ + if (pkt->cache_valid) { + list_add(&pkt->list, &pd->cdrw.pkt_free_list); + } else { + list_add_tail(&pkt->list, &pd->cdrw.pkt_free_list); + } +} + +static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state state) +{ +#if PACKET_DEBUG > 1 + static const char *state_name[] = { + "IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED" + }; + enum packet_data_state old_state = pkt->state; + pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n", + pkt->id, (unsigned long long)pkt->sector, + state_name[old_state], state_name[state]); +#endif + pkt->state = state; +} + +/* + * Scan the work queue to see if we can start a new packet. + * returns non-zero if any work was done. + */ +static int pkt_handle_queue(struct pktcdvd_device *pd) +{ + struct packet_data *pkt, *p; + struct bio *bio = NULL; + sector_t zone = 0; /* Suppress gcc warning */ + struct pkt_rb_node *node, *first_node; + struct rb_node *n; + + atomic_set(&pd->scan_queue, 0); + + if (list_empty(&pd->cdrw.pkt_free_list)) { + pkt_dbg(2, pd, "no pkt\n"); + return 0; + } + + /* + * Try to find a zone we are not already working on. + */ + spin_lock(&pd->lock); + first_node = pkt_rbtree_find(pd, pd->current_sector); + if (!first_node) { + n = rb_first(&pd->bio_queue); + if (n) + first_node = rb_entry(n, struct pkt_rb_node, rb_node); + } + node = first_node; + while (node) { + bio = node->bio; + zone = get_zone(bio->bi_iter.bi_sector, pd); + list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) { + if (p->sector == zone) { + bio = NULL; + goto try_next_bio; + } + } + break; +try_next_bio: + node = pkt_rbtree_next(node); + if (!node) { + n = rb_first(&pd->bio_queue); + if (n) + node = rb_entry(n, struct pkt_rb_node, rb_node); + } + if (node == first_node) + node = NULL; + } + spin_unlock(&pd->lock); + if (!bio) { + pkt_dbg(2, pd, "no bio\n"); + return 0; + } + + pkt = pkt_get_packet_data(pd, zone); + + pd->current_sector = zone + pd->settings.size; + pkt->sector = zone; + BUG_ON(pkt->frames != pd->settings.size >> 2); + pkt->write_size = 0; + + /* + * Scan work queue for bios in the same zone and link them + * to this packet. + */ + spin_lock(&pd->lock); + pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone); + while ((node = pkt_rbtree_find(pd, zone)) != NULL) { + bio = node->bio; + pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long) + get_zone(bio->bi_iter.bi_sector, pd)); + if (get_zone(bio->bi_iter.bi_sector, pd) != zone) + break; + pkt_rbtree_erase(pd, node); + spin_lock(&pkt->lock); + bio_list_add(&pkt->orig_bios, bio); + pkt->write_size += bio->bi_iter.bi_size / CD_FRAMESIZE; + spin_unlock(&pkt->lock); + } + /* check write congestion marks, and if bio_queue_size is + * below, wake up any waiters + */ + if (pd->congested && + pd->bio_queue_size <= pd->write_congestion_off) { + pd->congested = false; + wake_up_var(&pd->congested); + } + spin_unlock(&pd->lock); + + pkt->sleep_time = max(PACKET_WAIT_TIME, 1); + pkt_set_state(pkt, PACKET_WAITING_STATE); + atomic_set(&pkt->run_sm, 1); + + spin_lock(&pd->cdrw.active_list_lock); + list_add(&pkt->list, &pd->cdrw.pkt_active_list); + spin_unlock(&pd->cdrw.active_list_lock); + + return 1; +} + +/** + * bio_list_copy_data - copy contents of data buffers from one chain of bios to + * another + * @src: source bio list + * @dst: destination bio list + * + * Stops when it reaches the end of either the @src list or @dst list - that is, + * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of + * bios). + */ +static void bio_list_copy_data(struct bio *dst, struct bio *src) +{ + struct bvec_iter src_iter = src->bi_iter; + struct bvec_iter dst_iter = dst->bi_iter; + + while (1) { + if (!src_iter.bi_size) { + src = src->bi_next; + if (!src) + break; + + src_iter = src->bi_iter; + } + + if (!dst_iter.bi_size) { + dst = dst->bi_next; + if (!dst) + break; + + dst_iter = dst->bi_iter; + } + + bio_copy_data_iter(dst, &dst_iter, src, &src_iter); + } +} + +/* + * Assemble a bio to write one packet and queue the bio for processing + * by the underlying block device. + */ +static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) +{ + int f; + + bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames, + REQ_OP_WRITE); + pkt->w_bio->bi_iter.bi_sector = pkt->sector; + pkt->w_bio->bi_end_io = pkt_end_io_packet_write; + pkt->w_bio->bi_private = pkt; + + /* XXX: locking? */ + for (f = 0; f < pkt->frames; f++) { + struct page *page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE]; + unsigned offset = (f * CD_FRAMESIZE) % PAGE_SIZE; + + if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset)) + BUG(); + } + pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt); + + /* + * Fill-in bvec with data from orig_bios. + */ + spin_lock(&pkt->lock); + bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head); + + pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE); + spin_unlock(&pkt->lock); + + pkt_dbg(2, pd, "Writing %d frames for zone %llx\n", + pkt->write_size, (unsigned long long)pkt->sector); + + if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames)) + pkt->cache_valid = 1; + else + pkt->cache_valid = 0; + + /* Start the write request */ + atomic_set(&pkt->io_wait, 1); + pkt_queue_bio(pd, pkt->w_bio); +} + +static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status) +{ + struct bio *bio; + + if (status) + pkt->cache_valid = 0; + + /* Finish all bios corresponding to this packet */ + while ((bio = bio_list_pop(&pkt->orig_bios))) { + bio->bi_status = status; + bio_endio(bio); + } +} + +static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt) +{ + pkt_dbg(2, pd, "pkt %d\n", pkt->id); + + for (;;) { + switch (pkt->state) { + case PACKET_WAITING_STATE: + if ((pkt->write_size < pkt->frames) && (pkt->sleep_time > 0)) + return; + + pkt->sleep_time = 0; + pkt_gather_data(pd, pkt); + pkt_set_state(pkt, PACKET_READ_WAIT_STATE); + break; + + case PACKET_READ_WAIT_STATE: + if (atomic_read(&pkt->io_wait) > 0) + return; + + if (atomic_read(&pkt->io_errors) > 0) { + pkt_set_state(pkt, PACKET_RECOVERY_STATE); + } else { + pkt_start_write(pd, pkt); + } + break; + + case PACKET_WRITE_WAIT_STATE: + if (atomic_read(&pkt->io_wait) > 0) + return; + + if (!pkt->w_bio->bi_status) { + pkt_set_state(pkt, PACKET_FINISHED_STATE); + } else { + pkt_set_state(pkt, PACKET_RECOVERY_STATE); + } + break; + + case PACKET_RECOVERY_STATE: + pkt_dbg(2, pd, "No recovery possible\n"); + pkt_set_state(pkt, PACKET_FINISHED_STATE); + break; + + case PACKET_FINISHED_STATE: + pkt_finish_packet(pkt, pkt->w_bio->bi_status); + return; + + default: + BUG(); + break; + } + } +} + +static void pkt_handle_packets(struct pktcdvd_device *pd) +{ + struct packet_data *pkt, *next; + + /* + * Run state machine for active packets + */ + list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { + if (atomic_read(&pkt->run_sm) > 0) { + atomic_set(&pkt->run_sm, 0); + pkt_run_state_machine(pd, pkt); + } + } + + /* + * Move no longer active packets to the free list + */ + spin_lock(&pd->cdrw.active_list_lock); + list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_active_list, list) { + if (pkt->state == PACKET_FINISHED_STATE) { + list_del(&pkt->list); + pkt_put_packet_data(pd, pkt); + pkt_set_state(pkt, PACKET_IDLE_STATE); + atomic_set(&pd->scan_queue, 1); + } + } + spin_unlock(&pd->cdrw.active_list_lock); +} + +static void pkt_count_states(struct pktcdvd_device *pd, int *states) +{ + struct packet_data *pkt; + int i; + + for (i = 0; i < PACKET_NUM_STATES; i++) + states[i] = 0; + + spin_lock(&pd->cdrw.active_list_lock); + list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { + states[pkt->state]++; + } + spin_unlock(&pd->cdrw.active_list_lock); +} + +/* + * kcdrwd is woken up when writes have been queued for one of our + * registered devices + */ +static int kcdrwd(void *foobar) +{ + struct pktcdvd_device *pd = foobar; + struct packet_data *pkt; + long min_sleep_time, residue; + + set_user_nice(current, MIN_NICE); + set_freezable(); + + for (;;) { + DECLARE_WAITQUEUE(wait, current); + + /* + * Wait until there is something to do + */ + add_wait_queue(&pd->wqueue, &wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + /* Check if we need to run pkt_handle_queue */ + if (atomic_read(&pd->scan_queue) > 0) + goto work_to_do; + + /* Check if we need to run the state machine for some packet */ + list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { + if (atomic_read(&pkt->run_sm) > 0) + goto work_to_do; + } + + /* Check if we need to process the iosched queues */ + if (atomic_read(&pd->iosched.attention) != 0) + goto work_to_do; + + /* Otherwise, go to sleep */ + if (PACKET_DEBUG > 1) { + int states[PACKET_NUM_STATES]; + pkt_count_states(pd, states); + pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", + states[0], states[1], states[2], + states[3], states[4], states[5]); + } + + min_sleep_time = MAX_SCHEDULE_TIMEOUT; + list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { + if (pkt->sleep_time && pkt->sleep_time < min_sleep_time) + min_sleep_time = pkt->sleep_time; + } + + pkt_dbg(2, pd, "sleeping\n"); + residue = schedule_timeout(min_sleep_time); + pkt_dbg(2, pd, "wake up\n"); + + /* make swsusp happy with our thread */ + try_to_freeze(); + + list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { + if (!pkt->sleep_time) + continue; + pkt->sleep_time -= min_sleep_time - residue; + if (pkt->sleep_time <= 0) { + pkt->sleep_time = 0; + atomic_inc(&pkt->run_sm); + } + } + + if (kthread_should_stop()) + break; + } +work_to_do: + set_current_state(TASK_RUNNING); + remove_wait_queue(&pd->wqueue, &wait); + + if (kthread_should_stop()) + break; + + /* + * if pkt_handle_queue returns true, we can queue + * another request. + */ + while (pkt_handle_queue(pd)) + ; + + /* + * Handle packet state machine + */ + pkt_handle_packets(pd); + + /* + * Handle iosched queues + */ + pkt_iosched_process_queue(pd); + } + + return 0; +} + +static void pkt_print_settings(struct pktcdvd_device *pd) +{ + pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n", + pd->settings.fp ? "Fixed" : "Variable", + pd->settings.size >> 2, + pd->settings.block_mode == 8 ? '1' : '2'); +} + +static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control) +{ + memset(cgc->cmd, 0, sizeof(cgc->cmd)); + + cgc->cmd[0] = GPCMD_MODE_SENSE_10; + cgc->cmd[2] = page_code | (page_control << 6); + cgc->cmd[7] = cgc->buflen >> 8; + cgc->cmd[8] = cgc->buflen & 0xff; + cgc->data_direction = CGC_DATA_READ; + return pkt_generic_packet(pd, cgc); +} + +static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc) +{ + memset(cgc->cmd, 0, sizeof(cgc->cmd)); + memset(cgc->buffer, 0, 2); + cgc->cmd[0] = GPCMD_MODE_SELECT_10; + cgc->cmd[1] = 0x10; /* PF */ + cgc->cmd[7] = cgc->buflen >> 8; + cgc->cmd[8] = cgc->buflen & 0xff; + cgc->data_direction = CGC_DATA_WRITE; + return pkt_generic_packet(pd, cgc); +} + +static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di) +{ + struct packet_command cgc; + int ret; + + /* set up command and get the disc info */ + init_cdrom_command(&cgc, di, sizeof(*di), CGC_DATA_READ); + cgc.cmd[0] = GPCMD_READ_DISC_INFO; + cgc.cmd[8] = cgc.buflen = 2; + cgc.quiet = 1; + + ret = pkt_generic_packet(pd, &cgc); + if (ret) + return ret; + + /* not all drives have the same disc_info length, so requeue + * packet with the length the drive tells us it can supply + */ + cgc.buflen = be16_to_cpu(di->disc_information_length) + + sizeof(di->disc_information_length); + + if (cgc.buflen > sizeof(disc_information)) + cgc.buflen = sizeof(disc_information); + + cgc.cmd[8] = cgc.buflen; + return pkt_generic_packet(pd, &cgc); +} + +static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, track_information *ti) +{ + struct packet_command cgc; + int ret; + + init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ); + cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO; + cgc.cmd[1] = type & 3; + cgc.cmd[4] = (track & 0xff00) >> 8; + cgc.cmd[5] = track & 0xff; + cgc.cmd[8] = 8; + cgc.quiet = 1; + + ret = pkt_generic_packet(pd, &cgc); + if (ret) + return ret; + + cgc.buflen = be16_to_cpu(ti->track_information_length) + + sizeof(ti->track_information_length); + + if (cgc.buflen > sizeof(track_information)) + cgc.buflen = sizeof(track_information); + + cgc.cmd[8] = cgc.buflen; + return pkt_generic_packet(pd, &cgc); +} + +static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd, + long *last_written) +{ + disc_information di; + track_information ti; + __u32 last_track; + int ret; + + ret = pkt_get_disc_info(pd, &di); + if (ret) + return ret; + + last_track = (di.last_track_msb << 8) | di.last_track_lsb; + ret = pkt_get_track_info(pd, last_track, 1, &ti); + if (ret) + return ret; + + /* if this track is blank, try the previous. */ + if (ti.blank) { + last_track--; + ret = pkt_get_track_info(pd, last_track, 1, &ti); + if (ret) + return ret; + } + + /* if last recorded field is valid, return it. */ + if (ti.lra_v) { + *last_written = be32_to_cpu(ti.last_rec_address); + } else { + /* make it up instead */ + *last_written = be32_to_cpu(ti.track_start) + + be32_to_cpu(ti.track_size); + if (ti.free_blocks) + *last_written -= (be32_to_cpu(ti.free_blocks) + 7); + } + return 0; +} + +/* + * write mode select package based on pd->settings + */ +static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) +{ + struct packet_command cgc; + struct scsi_sense_hdr sshdr; + write_param_page *wp; + char buffer[128]; + int ret, size; + + /* doesn't apply to DVD+RW or DVD-RAM */ + if ((pd->mmc3_profile == 0x1a) || (pd->mmc3_profile == 0x12)) + return 0; + + memset(buffer, 0, sizeof(buffer)); + init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ); + cgc.sshdr = &sshdr; + ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0); + if (ret) { + pkt_dump_sense(pd, &cgc); + return ret; + } + + size = 2 + ((buffer[0] << 8) | (buffer[1] & 0xff)); + pd->mode_offset = (buffer[6] << 8) | (buffer[7] & 0xff); + if (size > sizeof(buffer)) + size = sizeof(buffer); + + /* + * now get it all + */ + init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ); + cgc.sshdr = &sshdr; + ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0); + if (ret) { + pkt_dump_sense(pd, &cgc); + return ret; + } + + /* + * write page is offset header + block descriptor length + */ + wp = (write_param_page *) &buffer[sizeof(struct mode_page_header) + pd->mode_offset]; + + wp->fp = pd->settings.fp; + wp->track_mode = pd->settings.track_mode; + wp->write_type = pd->settings.write_type; + wp->data_block_type = pd->settings.block_mode; + + wp->multi_session = 0; + +#ifdef PACKET_USE_LS + wp->link_size = 7; + wp->ls_v = 1; +#endif + + if (wp->data_block_type == PACKET_BLOCK_MODE1) { + wp->session_format = 0; + wp->subhdr2 = 0x20; + } else if (wp->data_block_type == PACKET_BLOCK_MODE2) { + wp->session_format = 0x20; + wp->subhdr2 = 8; +#if 0 + wp->mcn[0] = 0x80; + memcpy(&wp->mcn[1], PACKET_MCN, sizeof(wp->mcn) - 1); +#endif + } else { + /* + * paranoia + */ + pkt_err(pd, "write mode wrong %d\n", wp->data_block_type); + return 1; + } + wp->packet_size = cpu_to_be32(pd->settings.size >> 2); + + cgc.buflen = cgc.cmd[8] = size; + ret = pkt_mode_select(pd, &cgc); + if (ret) { + pkt_dump_sense(pd, &cgc); + return ret; + } + + pkt_print_settings(pd); + return 0; +} + +/* + * 1 -- we can write to this track, 0 -- we can't + */ +static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) +{ + switch (pd->mmc3_profile) { + case 0x1a: /* DVD+RW */ + case 0x12: /* DVD-RAM */ + /* The track is always writable on DVD+RW/DVD-RAM */ + return 1; + default: + break; + } + + if (!ti->packet || !ti->fp) + return 0; + + /* + * "good" settings as per Mt Fuji. + */ + if (ti->rt == 0 && ti->blank == 0) + return 1; + + if (ti->rt == 0 && ti->blank == 1) + return 1; + + if (ti->rt == 1 && ti->blank == 0) + return 1; + + pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet); + return 0; +} + +/* + * 1 -- we can write to this disc, 0 -- we can't + */ +static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) +{ + switch (pd->mmc3_profile) { + case 0x0a: /* CD-RW */ + case 0xffff: /* MMC3 not supported */ + break; + case 0x1a: /* DVD+RW */ + case 0x13: /* DVD-RW */ + case 0x12: /* DVD-RAM */ + return 1; + default: + pkt_dbg(2, pd, "Wrong disc profile (%x)\n", + pd->mmc3_profile); + return 0; + } + + /* + * for disc type 0xff we should probably reserve a new track. + * but i'm not sure, should we leave this to user apps? probably. + */ + if (di->disc_type == 0xff) { + pkt_notice(pd, "unknown disc - no track?\n"); + return 0; + } + + if (di->disc_type != 0x20 && di->disc_type != 0) { + pkt_err(pd, "wrong disc type (%x)\n", di->disc_type); + return 0; + } + + if (di->erasable == 0) { + pkt_notice(pd, "disc not erasable\n"); + return 0; + } + + if (di->border_status == PACKET_SESSION_RESERVED) { + pkt_err(pd, "can't write to last track (reserved)\n"); + return 0; + } + + return 1; +} + +static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) +{ + struct packet_command cgc; + unsigned char buf[12]; + disc_information di; + track_information ti; + int ret, track; + + init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ); + cgc.cmd[0] = GPCMD_GET_CONFIGURATION; + cgc.cmd[8] = 8; + ret = pkt_generic_packet(pd, &cgc); + pd->mmc3_profile = ret ? 0xffff : buf[6] << 8 | buf[7]; + + memset(&di, 0, sizeof(disc_information)); + memset(&ti, 0, sizeof(track_information)); + + ret = pkt_get_disc_info(pd, &di); + if (ret) { + pkt_err(pd, "failed get_disc\n"); + return ret; + } + + if (!pkt_writable_disc(pd, &di)) + return -EROFS; + + pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR; + + track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */ + ret = pkt_get_track_info(pd, track, 1, &ti); + if (ret) { + pkt_err(pd, "failed get_track\n"); + return ret; + } + + if (!pkt_writable_track(pd, &ti)) { + pkt_err(pd, "can't write to this track\n"); + return -EROFS; + } + + /* + * we keep packet size in 512 byte units, makes it easier to + * deal with request calculations. + */ + pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2; + if (pd->settings.size == 0) { + pkt_notice(pd, "detected zero packet size!\n"); + return -ENXIO; + } + if (pd->settings.size > PACKET_MAX_SECTORS) { + pkt_err(pd, "packet size is too big\n"); + return -EROFS; + } + pd->settings.fp = ti.fp; + pd->offset = (be32_to_cpu(ti.track_start) << 2) & (pd->settings.size - 1); + + if (ti.nwa_v) { + pd->nwa = be32_to_cpu(ti.next_writable); + set_bit(PACKET_NWA_VALID, &pd->flags); + } + + /* + * in theory we could use lra on -RW media as well and just zero + * blocks that haven't been written yet, but in practice that + * is just a no-go. we'll use that for -R, naturally. + */ + if (ti.lra_v) { + pd->lra = be32_to_cpu(ti.last_rec_address); + set_bit(PACKET_LRA_VALID, &pd->flags); + } else { + pd->lra = 0xffffffff; + set_bit(PACKET_LRA_VALID, &pd->flags); + } + + /* + * fine for now + */ + pd->settings.link_loss = 7; + pd->settings.write_type = 0; /* packet */ + pd->settings.track_mode = ti.track_mode; + + /* + * mode1 or mode2 disc + */ + switch (ti.data_mode) { + case PACKET_MODE1: + pd->settings.block_mode = PACKET_BLOCK_MODE1; + break; + case PACKET_MODE2: + pd->settings.block_mode = PACKET_BLOCK_MODE2; + break; + default: + pkt_err(pd, "unknown data mode\n"); + return -EROFS; + } + return 0; +} + +/* + * enable/disable write caching on drive + */ +static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd, + int set) +{ + struct packet_command cgc; + struct scsi_sense_hdr sshdr; + unsigned char buf[64]; + int ret; + + init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ); + cgc.sshdr = &sshdr; + cgc.buflen = pd->mode_offset + 12; + + /* + * caching mode page might not be there, so quiet this command + */ + cgc.quiet = 1; + + ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0); + if (ret) + return ret; + + buf[pd->mode_offset + 10] |= (!!set << 2); + + cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff)); + ret = pkt_mode_select(pd, &cgc); + if (ret) { + pkt_err(pd, "write caching control failed\n"); + pkt_dump_sense(pd, &cgc); + } else if (!ret && set) + pkt_notice(pd, "enabled write caching\n"); + return ret; +} + +static int pkt_lock_door(struct pktcdvd_device *pd, int lockflag) +{ + struct packet_command cgc; + + init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); + cgc.cmd[0] = GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL; + cgc.cmd[4] = lockflag ? 1 : 0; + return pkt_generic_packet(pd, &cgc); +} + +/* + * Returns drive maximum write speed + */ +static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd, + unsigned *write_speed) +{ + struct packet_command cgc; + struct scsi_sense_hdr sshdr; + unsigned char buf[256+18]; + unsigned char *cap_buf; + int ret, offset; + + cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset]; + init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN); + cgc.sshdr = &sshdr; + + ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0); + if (ret) { + cgc.buflen = pd->mode_offset + cap_buf[1] + 2 + + sizeof(struct mode_page_header); + ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0); + if (ret) { + pkt_dump_sense(pd, &cgc); + return ret; + } + } + + offset = 20; /* Obsoleted field, used by older drives */ + if (cap_buf[1] >= 28) + offset = 28; /* Current write speed selected */ + if (cap_buf[1] >= 30) { + /* If the drive reports at least one "Logical Unit Write + * Speed Performance Descriptor Block", use the information + * in the first block. (contains the highest speed) + */ + int num_spdb = (cap_buf[30] << 8) + cap_buf[31]; + if (num_spdb > 0) + offset = 34; + } + + *write_speed = (cap_buf[offset] << 8) | cap_buf[offset + 1]; + return 0; +} + +/* These tables from cdrecord - I don't have orange book */ +/* standard speed CD-RW (1-4x) */ +static char clv_to_speed[16] = { + /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */ + 0, 2, 4, 6, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 +}; +/* high speed CD-RW (-10x) */ +static char hs_clv_to_speed[16] = { + /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */ + 0, 2, 4, 6, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 +}; +/* ultra high speed CD-RW */ +static char us_clv_to_speed[16] = { + /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */ + 0, 2, 4, 8, 0, 0,16, 0,24,32,40,48, 0, 0, 0, 0 +}; + +/* + * reads the maximum media speed from ATIP + */ +static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, + unsigned *speed) +{ + struct packet_command cgc; + struct scsi_sense_hdr sshdr; + unsigned char buf[64]; + unsigned int size, st, sp; + int ret; + + init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ); + cgc.sshdr = &sshdr; + cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP; + cgc.cmd[1] = 2; + cgc.cmd[2] = 4; /* READ ATIP */ + cgc.cmd[8] = 2; + ret = pkt_generic_packet(pd, &cgc); + if (ret) { + pkt_dump_sense(pd, &cgc); + return ret; + } + size = ((unsigned int) buf[0]<<8) + buf[1] + 2; + if (size > sizeof(buf)) + size = sizeof(buf); + + init_cdrom_command(&cgc, buf, size, CGC_DATA_READ); + cgc.sshdr = &sshdr; + cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP; + cgc.cmd[1] = 2; + cgc.cmd[2] = 4; + cgc.cmd[8] = size; + ret = pkt_generic_packet(pd, &cgc); + if (ret) { + pkt_dump_sense(pd, &cgc); + return ret; + } + + if (!(buf[6] & 0x40)) { + pkt_notice(pd, "disc type is not CD-RW\n"); + return 1; + } + if (!(buf[6] & 0x4)) { + pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n"); + return 1; + } + + st = (buf[6] >> 3) & 0x7; /* disc sub-type */ + + sp = buf[16] & 0xf; /* max speed from ATIP A1 field */ + + /* Info from cdrecord */ + switch (st) { + case 0: /* standard speed */ + *speed = clv_to_speed[sp]; + break; + case 1: /* high speed */ + *speed = hs_clv_to_speed[sp]; + break; + case 2: /* ultra high speed */ + *speed = us_clv_to_speed[sp]; + break; + default: + pkt_notice(pd, "unknown disc sub-type %d\n", st); + return 1; + } + if (*speed) { + pkt_info(pd, "maximum media speed: %d\n", *speed); + return 0; + } else { + pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st); + return 1; + } +} + +static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd) +{ + struct packet_command cgc; + struct scsi_sense_hdr sshdr; + int ret; + + pkt_dbg(2, pd, "Performing OPC\n"); + + init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); + cgc.sshdr = &sshdr; + cgc.timeout = 60*HZ; + cgc.cmd[0] = GPCMD_SEND_OPC; + cgc.cmd[1] = 1; + ret = pkt_generic_packet(pd, &cgc); + if (ret) + pkt_dump_sense(pd, &cgc); + return ret; +} + +static int pkt_open_write(struct pktcdvd_device *pd) +{ + int ret; + unsigned int write_speed, media_write_speed, read_speed; + + ret = pkt_probe_settings(pd); + if (ret) { + pkt_dbg(2, pd, "failed probe\n"); + return ret; + } + + ret = pkt_set_write_settings(pd); + if (ret) { + pkt_dbg(1, pd, "failed saving write settings\n"); + return -EIO; + } + + pkt_write_caching(pd, USE_WCACHING); + + ret = pkt_get_max_speed(pd, &write_speed); + if (ret) + write_speed = 16 * 177; + switch (pd->mmc3_profile) { + case 0x13: /* DVD-RW */ + case 0x1a: /* DVD+RW */ + case 0x12: /* DVD-RAM */ + pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed); + break; + default: + ret = pkt_media_speed(pd, &media_write_speed); + if (ret) + media_write_speed = 16; + write_speed = min(write_speed, media_write_speed * 177); + pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176); + break; + } + read_speed = write_speed; + + ret = pkt_set_speed(pd, write_speed, read_speed); + if (ret) { + pkt_dbg(1, pd, "couldn't set write speed\n"); + return -EIO; + } + pd->write_speed = write_speed; + pd->read_speed = read_speed; + + ret = pkt_perform_opc(pd); + if (ret) { + pkt_dbg(1, pd, "Optimum Power Calibration failed\n"); + } + + return 0; +} + +/* + * called at open time. + */ +static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) +{ + int ret; + long lba; + struct request_queue *q; + struct block_device *bdev; + + /* + * We need to re-open the cdrom device without O_NONBLOCK to be able + * to read/write from/to it. It is already opened in O_NONBLOCK mode + * so open should not fail. + */ + bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd); + if (IS_ERR(bdev)) { + ret = PTR_ERR(bdev); + goto out; + } + + ret = pkt_get_last_written(pd, &lba); + if (ret) { + pkt_err(pd, "pkt_get_last_written failed\n"); + goto out_putdev; + } + + set_capacity(pd->disk, lba << 2); + set_capacity_and_notify(pd->bdev->bd_disk, lba << 2); + + q = bdev_get_queue(pd->bdev); + if (write) { + ret = pkt_open_write(pd); + if (ret) + goto out_putdev; + /* + * Some CDRW drives can not handle writes larger than one packet, + * even if the size is a multiple of the packet size. + */ + blk_queue_max_hw_sectors(q, pd->settings.size); + set_bit(PACKET_WRITABLE, &pd->flags); + } else { + pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); + clear_bit(PACKET_WRITABLE, &pd->flags); + } + + ret = pkt_set_segment_merging(pd, q); + if (ret) + goto out_putdev; + + if (write) { + if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) { + pkt_err(pd, "not enough memory for buffers\n"); + ret = -ENOMEM; + goto out_putdev; + } + pkt_info(pd, "%lukB available on disc\n", lba << 1); + } + + return 0; + +out_putdev: + blkdev_put(bdev, FMODE_READ | FMODE_EXCL); +out: + return ret; +} + +/* + * called when the device is closed. makes sure that the device flushes + * the internal cache before we close. + */ +static void pkt_release_dev(struct pktcdvd_device *pd, int flush) +{ + if (flush && pkt_flush_cache(pd)) + pkt_dbg(1, pd, "not flushing cache\n"); + + pkt_lock_door(pd, 0); + + pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); + blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL); + + pkt_shrink_pktlist(pd); +} + +static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor) +{ + if (dev_minor >= MAX_WRITERS) + return NULL; + + dev_minor = array_index_nospec(dev_minor, MAX_WRITERS); + return pkt_devs[dev_minor]; +} + +static int pkt_open(struct block_device *bdev, fmode_t mode) +{ + struct pktcdvd_device *pd = NULL; + int ret; + + mutex_lock(&pktcdvd_mutex); + mutex_lock(&ctl_mutex); + pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev)); + if (!pd) { + ret = -ENODEV; + goto out; + } + BUG_ON(pd->refcnt < 0); + + pd->refcnt++; + if (pd->refcnt > 1) { + if ((mode & FMODE_WRITE) && + !test_bit(PACKET_WRITABLE, &pd->flags)) { + ret = -EBUSY; + goto out_dec; + } + } else { + ret = pkt_open_dev(pd, mode & FMODE_WRITE); + if (ret) + goto out_dec; + /* + * needed here as well, since ext2 (among others) may change + * the blocksize at mount time + */ + set_blocksize(bdev, CD_FRAMESIZE); + } + + mutex_unlock(&ctl_mutex); + mutex_unlock(&pktcdvd_mutex); + return 0; + +out_dec: + pd->refcnt--; +out: + mutex_unlock(&ctl_mutex); + mutex_unlock(&pktcdvd_mutex); + return ret; +} + +static void pkt_close(struct gendisk *disk, fmode_t mode) +{ + struct pktcdvd_device *pd = disk->private_data; + + mutex_lock(&pktcdvd_mutex); + mutex_lock(&ctl_mutex); + pd->refcnt--; + BUG_ON(pd->refcnt < 0); + if (pd->refcnt == 0) { + int flush = test_bit(PACKET_WRITABLE, &pd->flags); + pkt_release_dev(pd, flush); + } + mutex_unlock(&ctl_mutex); + mutex_unlock(&pktcdvd_mutex); +} + + +static void pkt_end_io_read_cloned(struct bio *bio) +{ + struct packet_stacked_data *psd = bio->bi_private; + struct pktcdvd_device *pd = psd->pd; + + psd->bio->bi_status = bio->bi_status; + bio_put(bio); + bio_endio(psd->bio); + mempool_free(psd, &psd_pool); + pkt_bio_finished(pd); +} + +static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio) +{ + struct bio *cloned_bio = + bio_alloc_clone(pd->bdev, bio, GFP_NOIO, &pkt_bio_set); + struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO); + + psd->pd = pd; + psd->bio = bio; + cloned_bio->bi_private = psd; + cloned_bio->bi_end_io = pkt_end_io_read_cloned; + pd->stats.secs_r += bio_sectors(bio); + pkt_queue_bio(pd, cloned_bio); +} + +static void pkt_make_request_write(struct request_queue *q, struct bio *bio) +{ + struct pktcdvd_device *pd = q->queuedata; + sector_t zone; + struct packet_data *pkt; + int was_empty, blocked_bio; + struct pkt_rb_node *node; + + zone = get_zone(bio->bi_iter.bi_sector, pd); + + /* + * If we find a matching packet in state WAITING or READ_WAIT, we can + * just append this bio to that packet. + */ + spin_lock(&pd->cdrw.active_list_lock); + blocked_bio = 0; + list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { + if (pkt->sector == zone) { + spin_lock(&pkt->lock); + if ((pkt->state == PACKET_WAITING_STATE) || + (pkt->state == PACKET_READ_WAIT_STATE)) { + bio_list_add(&pkt->orig_bios, bio); + pkt->write_size += + bio->bi_iter.bi_size / CD_FRAMESIZE; + if ((pkt->write_size >= pkt->frames) && + (pkt->state == PACKET_WAITING_STATE)) { + atomic_inc(&pkt->run_sm); + wake_up(&pd->wqueue); + } + spin_unlock(&pkt->lock); + spin_unlock(&pd->cdrw.active_list_lock); + return; + } else { + blocked_bio = 1; + } + spin_unlock(&pkt->lock); + } + } + spin_unlock(&pd->cdrw.active_list_lock); + + /* + * Test if there is enough room left in the bio work queue + * (queue size >= congestion on mark). + * If not, wait till the work queue size is below the congestion off mark. + */ + spin_lock(&pd->lock); + if (pd->write_congestion_on > 0 + && pd->bio_queue_size >= pd->write_congestion_on) { + struct wait_bit_queue_entry wqe; + + init_wait_var_entry(&wqe, &pd->congested, 0); + for (;;) { + prepare_to_wait_event(__var_waitqueue(&pd->congested), + &wqe.wq_entry, + TASK_UNINTERRUPTIBLE); + if (pd->bio_queue_size <= pd->write_congestion_off) + break; + pd->congested = true; + spin_unlock(&pd->lock); + schedule(); + spin_lock(&pd->lock); + } + } + spin_unlock(&pd->lock); + + /* + * No matching packet found. Store the bio in the work queue. + */ + node = mempool_alloc(&pd->rb_pool, GFP_NOIO); + node->bio = bio; + spin_lock(&pd->lock); + BUG_ON(pd->bio_queue_size < 0); + was_empty = (pd->bio_queue_size == 0); + pkt_rbtree_insert(pd, node); + spin_unlock(&pd->lock); + + /* + * Wake up the worker thread. + */ + atomic_set(&pd->scan_queue, 1); + if (was_empty) { + /* This wake_up is required for correct operation */ + wake_up(&pd->wqueue); + } else if (!list_empty(&pd->cdrw.pkt_free_list) && !blocked_bio) { + /* + * This wake up is not required for correct operation, + * but improves performance in some cases. + */ + wake_up(&pd->wqueue); + } +} + +static void pkt_submit_bio(struct bio *bio) +{ + struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata; + struct bio *split; + + bio = bio_split_to_limits(bio); + + pkt_dbg(2, pd, "start = %6llx stop = %6llx\n", + (unsigned long long)bio->bi_iter.bi_sector, + (unsigned long long)bio_end_sector(bio)); + + /* + * Clone READ bios so we can have our own bi_end_io callback. + */ + if (bio_data_dir(bio) == READ) { + pkt_make_request_read(pd, bio); + return; + } + + if (!test_bit(PACKET_WRITABLE, &pd->flags)) { + pkt_notice(pd, "WRITE for ro device (%llu)\n", + (unsigned long long)bio->bi_iter.bi_sector); + goto end_io; + } + + if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) { + pkt_err(pd, "wrong bio size\n"); + goto end_io; + } + + do { + sector_t zone = get_zone(bio->bi_iter.bi_sector, pd); + sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd); + + if (last_zone != zone) { + BUG_ON(last_zone != zone + pd->settings.size); + + split = bio_split(bio, last_zone - + bio->bi_iter.bi_sector, + GFP_NOIO, &pkt_bio_set); + bio_chain(split, bio); + } else { + split = bio; + } + + pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split); + } while (split != bio); + + return; +end_io: + bio_io_error(bio); +} + +static void pkt_init_queue(struct pktcdvd_device *pd) +{ + struct request_queue *q = pd->disk->queue; + + blk_queue_logical_block_size(q, CD_FRAMESIZE); + blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS); + q->queuedata = pd; +} + +static int pkt_seq_show(struct seq_file *m, void *p) +{ + struct pktcdvd_device *pd = m->private; + char *msg; + int states[PACKET_NUM_STATES]; + + seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev); + + seq_printf(m, "\nSettings:\n"); + seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2); + + if (pd->settings.write_type == 0) + msg = "Packet"; + else + msg = "Unknown"; + seq_printf(m, "\twrite type:\t\t%s\n", msg); + + seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable"); + seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss); + + seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode); + + if (pd->settings.block_mode == PACKET_BLOCK_MODE1) + msg = "Mode 1"; + else if (pd->settings.block_mode == PACKET_BLOCK_MODE2) + msg = "Mode 2"; + else + msg = "Unknown"; + seq_printf(m, "\tblock mode:\t\t%s\n", msg); + + seq_printf(m, "\nStatistics:\n"); + seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started); + seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended); + seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1); + seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1); + seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1); + + seq_printf(m, "\nMisc:\n"); + seq_printf(m, "\treference count:\t%d\n", pd->refcnt); + seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags); + seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed); + seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed); + seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset); + seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset); + + seq_printf(m, "\nQueue state:\n"); + seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size); + seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios)); + seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", (unsigned long long)pd->current_sector); + + pkt_count_states(pd, states); + seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", + states[0], states[1], states[2], states[3], states[4], states[5]); + + seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n", + pd->write_congestion_off, + pd->write_congestion_on); + return 0; +} + +static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) +{ + int i; + struct block_device *bdev; + struct scsi_device *sdev; + + if (pd->pkt_dev == dev) { + pkt_err(pd, "recursive setup not allowed\n"); + return -EBUSY; + } + for (i = 0; i < MAX_WRITERS; i++) { + struct pktcdvd_device *pd2 = pkt_devs[i]; + if (!pd2) + continue; + if (pd2->bdev->bd_dev == dev) { + pkt_err(pd, "%pg already setup\n", pd2->bdev); + return -EBUSY; + } + if (pd2->pkt_dev == dev) { + pkt_err(pd, "can't chain pktcdvd devices\n"); + return -EBUSY; + } + } + + bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL); + if (IS_ERR(bdev)) + return PTR_ERR(bdev); + sdev = scsi_device_from_queue(bdev->bd_disk->queue); + if (!sdev) { + blkdev_put(bdev, FMODE_READ | FMODE_NDELAY); + return -EINVAL; + } + put_device(&sdev->sdev_gendev); + + /* This is safe, since we have a reference from open(). */ + __module_get(THIS_MODULE); + + pd->bdev = bdev; + set_blocksize(bdev, CD_FRAMESIZE); + + pkt_init_queue(pd); + + atomic_set(&pd->cdrw.pending_bios, 0); + pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name); + if (IS_ERR(pd->cdrw.thread)) { + pkt_err(pd, "can't start kernel thread\n"); + goto out_mem; + } + + proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd); + pkt_dbg(1, pd, "writer mapped to %pg\n", bdev); + return 0; + +out_mem: + blkdev_put(bdev, FMODE_READ | FMODE_NDELAY); + /* This is safe: open() is still holding a reference. */ + module_put(THIS_MODULE); + return -ENOMEM; +} + +static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) +{ + struct pktcdvd_device *pd = bdev->bd_disk->private_data; + int ret; + + pkt_dbg(2, pd, "cmd %x, dev %d:%d\n", + cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); + + mutex_lock(&pktcdvd_mutex); + switch (cmd) { + case CDROMEJECT: + /* + * The door gets locked when the device is opened, so we + * have to unlock it or else the eject command fails. + */ + if (pd->refcnt == 1) + pkt_lock_door(pd, 0); + fallthrough; + /* + * forward selected CDROM ioctls to CD-ROM, for UDF + */ + case CDROMMULTISESSION: + case CDROMREADTOCENTRY: + case CDROM_LAST_WRITTEN: + case CDROM_SEND_PACKET: + case SCSI_IOCTL_SEND_COMMAND: + if (!bdev->bd_disk->fops->ioctl) + ret = -ENOTTY; + else + ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); + break; + default: + pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd); + ret = -ENOTTY; + } + mutex_unlock(&pktcdvd_mutex); + + return ret; +} + +static unsigned int pkt_check_events(struct gendisk *disk, + unsigned int clearing) +{ + struct pktcdvd_device *pd = disk->private_data; + struct gendisk *attached_disk; + + if (!pd) + return 0; + if (!pd->bdev) + return 0; + attached_disk = pd->bdev->bd_disk; + if (!attached_disk || !attached_disk->fops->check_events) + return 0; + return attached_disk->fops->check_events(attached_disk, clearing); +} + +static char *pkt_devnode(struct gendisk *disk, umode_t *mode) +{ + return kasprintf(GFP_KERNEL, "pktcdvd/%s", disk->disk_name); +} + +static const struct block_device_operations pktcdvd_ops = { + .owner = THIS_MODULE, + .submit_bio = pkt_submit_bio, + .open = pkt_open, + .release = pkt_close, + .ioctl = pkt_ioctl, + .compat_ioctl = blkdev_compat_ptr_ioctl, + .check_events = pkt_check_events, + .devnode = pkt_devnode, +}; + +/* + * Set up mapping from pktcdvd device to CD-ROM device. + */ +static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) +{ + int idx; + int ret = -ENOMEM; + struct pktcdvd_device *pd; + struct gendisk *disk; + + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + + for (idx = 0; idx < MAX_WRITERS; idx++) + if (!pkt_devs[idx]) + break; + if (idx == MAX_WRITERS) { + pr_err("max %d writers supported\n", MAX_WRITERS); + ret = -EBUSY; + goto out_mutex; + } + + pd = kzalloc(sizeof(struct pktcdvd_device), GFP_KERNEL); + if (!pd) + goto out_mutex; + + ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE, + sizeof(struct pkt_rb_node)); + if (ret) + goto out_mem; + + INIT_LIST_HEAD(&pd->cdrw.pkt_free_list); + INIT_LIST_HEAD(&pd->cdrw.pkt_active_list); + spin_lock_init(&pd->cdrw.active_list_lock); + + spin_lock_init(&pd->lock); + spin_lock_init(&pd->iosched.lock); + bio_list_init(&pd->iosched.read_queue); + bio_list_init(&pd->iosched.write_queue); + sprintf(pd->name, DRIVER_NAME"%d", idx); + init_waitqueue_head(&pd->wqueue); + pd->bio_queue = RB_ROOT; + + pd->write_congestion_on = write_congestion_on; + pd->write_congestion_off = write_congestion_off; + + ret = -ENOMEM; + disk = blk_alloc_disk(NUMA_NO_NODE); + if (!disk) + goto out_mem; + pd->disk = disk; + disk->major = pktdev_major; + disk->first_minor = idx; + disk->minors = 1; + disk->fops = &pktcdvd_ops; + disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART; + strcpy(disk->disk_name, pd->name); + disk->private_data = pd; + + pd->pkt_dev = MKDEV(pktdev_major, idx); + ret = pkt_new_dev(pd, dev); + if (ret) + goto out_mem2; + + /* inherit events of the host device */ + disk->events = pd->bdev->bd_disk->events; + + ret = add_disk(disk); + if (ret) + goto out_mem2; + + pkt_sysfs_dev_new(pd); + pkt_debugfs_dev_new(pd); + + pkt_devs[idx] = pd; + if (pkt_dev) + *pkt_dev = pd->pkt_dev; + + mutex_unlock(&ctl_mutex); + return 0; + +out_mem2: + put_disk(disk); +out_mem: + mempool_exit(&pd->rb_pool); + kfree(pd); +out_mutex: + mutex_unlock(&ctl_mutex); + pr_err("setup of pktcdvd device failed\n"); + return ret; +} + +/* + * Tear down mapping from pktcdvd device to CD-ROM device. + */ +static int pkt_remove_dev(dev_t pkt_dev) +{ + struct pktcdvd_device *pd; + int idx; + int ret = 0; + + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + + for (idx = 0; idx < MAX_WRITERS; idx++) { + pd = pkt_devs[idx]; + if (pd && (pd->pkt_dev == pkt_dev)) + break; + } + if (idx == MAX_WRITERS) { + pr_debug("dev not setup\n"); + ret = -ENXIO; + goto out; + } + + if (pd->refcnt > 0) { + ret = -EBUSY; + goto out; + } + if (!IS_ERR(pd->cdrw.thread)) + kthread_stop(pd->cdrw.thread); + + pkt_devs[idx] = NULL; + + pkt_debugfs_dev_remove(pd); + pkt_sysfs_dev_remove(pd); + + blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY); + + remove_proc_entry(pd->name, pkt_proc); + pkt_dbg(1, pd, "writer unmapped\n"); + + del_gendisk(pd->disk); + put_disk(pd->disk); + + mempool_exit(&pd->rb_pool); + kfree(pd); + + /* This is safe: open() is still holding a reference. */ + module_put(THIS_MODULE); + +out: + mutex_unlock(&ctl_mutex); + return ret; +} + +static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd) +{ + struct pktcdvd_device *pd; + + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + + pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index); + if (pd) { + ctrl_cmd->dev = new_encode_dev(pd->bdev->bd_dev); + ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev); + } else { + ctrl_cmd->dev = 0; + ctrl_cmd->pkt_dev = 0; + } + ctrl_cmd->num_devices = MAX_WRITERS; + + mutex_unlock(&ctl_mutex); +} + +static long pkt_ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct pkt_ctrl_command ctrl_cmd; + int ret = 0; + dev_t pkt_dev = 0; + + if (cmd != PACKET_CTRL_CMD) + return -ENOTTY; + + if (copy_from_user(&ctrl_cmd, argp, sizeof(struct pkt_ctrl_command))) + return -EFAULT; + + switch (ctrl_cmd.command) { + case PKT_CTRL_CMD_SETUP: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev); + ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev); + break; + case PKT_CTRL_CMD_TEARDOWN: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev)); + break; + case PKT_CTRL_CMD_STATUS: + pkt_get_status(&ctrl_cmd); + break; + default: + return -ENOTTY; + } + + if (copy_to_user(argp, &ctrl_cmd, sizeof(struct pkt_ctrl_command))) + return -EFAULT; + return ret; +} + +#ifdef CONFIG_COMPAT +static long pkt_ctl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return pkt_ctl_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); +} +#endif + +static const struct file_operations pkt_ctl_fops = { + .open = nonseekable_open, + .unlocked_ioctl = pkt_ctl_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pkt_ctl_compat_ioctl, +#endif + .owner = THIS_MODULE, + .llseek = no_llseek, +}; + +static struct miscdevice pkt_misc = { + .minor = MISC_DYNAMIC_MINOR, + .name = DRIVER_NAME, + .nodename = "pktcdvd/control", + .fops = &pkt_ctl_fops +}; + +static int __init pkt_init(void) +{ + int ret; + + mutex_init(&ctl_mutex); + + ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE, + sizeof(struct packet_stacked_data)); + if (ret) + return ret; + ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0); + if (ret) { + mempool_exit(&psd_pool); + return ret; + } + + ret = register_blkdev(pktdev_major, DRIVER_NAME); + if (ret < 0) { + pr_err("unable to register block device\n"); + goto out2; + } + if (!pktdev_major) + pktdev_major = ret; + + ret = pkt_sysfs_init(); + if (ret) + goto out; + + pkt_debugfs_init(); + + ret = misc_register(&pkt_misc); + if (ret) { + pr_err("unable to register misc device\n"); + goto out_misc; + } + + pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL); + + return 0; + +out_misc: + pkt_debugfs_cleanup(); + pkt_sysfs_cleanup(); +out: + unregister_blkdev(pktdev_major, DRIVER_NAME); +out2: + mempool_exit(&psd_pool); + bioset_exit(&pkt_bio_set); + return ret; +} + +static void __exit pkt_exit(void) +{ + remove_proc_entry("driver/"DRIVER_NAME, NULL); + misc_deregister(&pkt_misc); + + pkt_debugfs_cleanup(); + pkt_sysfs_cleanup(); + + unregister_blkdev(pktdev_major, DRIVER_NAME); + mempool_exit(&psd_pool); + bioset_exit(&pkt_bio_set); +} + +MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives"); +MODULE_AUTHOR("Jens Axboe "); +MODULE_LICENSE("GPL"); + +module_init(pkt_init); +module_exit(pkt_exit); diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h new file mode 100644 index 000000000000..f9c5ac80d59b --- /dev/null +++ b/include/linux/pktcdvd.h @@ -0,0 +1,197 @@ +/* + * Copyright (C) 2000 Jens Axboe + * Copyright (C) 2001-2004 Peter Osterlund + * + * May be copied or modified under the terms of the GNU General Public + * License. See linux/COPYING for more information. + * + * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and + * DVD-RW devices. + * + */ +#ifndef __PKTCDVD_H +#define __PKTCDVD_H + +#include +#include +#include +#include +#include +#include +#include + +/* default bio write queue congestion marks */ +#define PKT_WRITE_CONGESTION_ON 10000 +#define PKT_WRITE_CONGESTION_OFF 9000 + + +struct packet_settings +{ + __u32 size; /* packet size in (512 byte) sectors */ + __u8 fp; /* fixed packets */ + __u8 link_loss; /* the rest is specified + * as per Mt Fuji */ + __u8 write_type; + __u8 track_mode; + __u8 block_mode; +}; + +/* + * Very crude stats for now + */ +struct packet_stats +{ + unsigned long pkt_started; + unsigned long pkt_ended; + unsigned long secs_w; + unsigned long secs_rg; + unsigned long secs_r; +}; + +struct packet_cdrw +{ + struct list_head pkt_free_list; + struct list_head pkt_active_list; + spinlock_t active_list_lock; /* Serialize access to pkt_active_list */ + struct task_struct *thread; + atomic_t pending_bios; +}; + +/* + * Switch to high speed reading after reading this many kilobytes + * with no interspersed writes. + */ +#define HI_SPEED_SWITCH 512 + +struct packet_iosched +{ + atomic_t attention; /* Set to non-zero when queue processing is needed */ + int writing; /* Non-zero when writing, zero when reading */ + spinlock_t lock; /* Protecting read/write queue manipulations */ + struct bio_list read_queue; + struct bio_list write_queue; + sector_t last_write; /* The sector where the last write ended */ + int successive_reads; +}; + +/* + * 32 buffers of 2048 bytes + */ +#if (PAGE_SIZE % CD_FRAMESIZE) != 0 +#error "PAGE_SIZE must be a multiple of CD_FRAMESIZE" +#endif +#define PACKET_MAX_SIZE 128 +#define FRAMES_PER_PAGE (PAGE_SIZE / CD_FRAMESIZE) +#define PACKET_MAX_SECTORS (PACKET_MAX_SIZE * CD_FRAMESIZE >> 9) + +enum packet_data_state { + PACKET_IDLE_STATE, /* Not used at the moment */ + PACKET_WAITING_STATE, /* Waiting for more bios to arrive, so */ + /* we don't have to do as much */ + /* data gathering */ + PACKET_READ_WAIT_STATE, /* Waiting for reads to fill in holes */ + PACKET_WRITE_WAIT_STATE, /* Waiting for the write to complete */ + PACKET_RECOVERY_STATE, /* Recover after read/write errors */ + PACKET_FINISHED_STATE, /* After write has finished */ + + PACKET_NUM_STATES /* Number of possible states */ +}; + +/* + * Information needed for writing a single packet + */ +struct pktcdvd_device; + +struct packet_data +{ + struct list_head list; + + spinlock_t lock; /* Lock protecting state transitions and */ + /* orig_bios list */ + + struct bio_list orig_bios; /* Original bios passed to pkt_make_request */ + /* that will be handled by this packet */ + int write_size; /* Total size of all bios in the orig_bios */ + /* list, measured in number of frames */ + + struct bio *w_bio; /* The bio we will send to the real CD */ + /* device once we have all data for the */ + /* packet we are going to write */ + sector_t sector; /* First sector in this packet */ + int frames; /* Number of frames in this packet */ + + enum packet_data_state state; /* Current state */ + atomic_t run_sm; /* Incremented whenever the state */ + /* machine needs to be run */ + long sleep_time; /* Set this to non-zero to make the state */ + /* machine run after this many jiffies. */ + + atomic_t io_wait; /* Number of pending IO operations */ + atomic_t io_errors; /* Number of read/write errors during IO */ + + struct bio *r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */ + struct page *pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE]; + + int cache_valid; /* If non-zero, the data for the zone defined */ + /* by the sector variable is completely cached */ + /* in the pages[] vector. */ + + int id; /* ID number for debugging */ + struct pktcdvd_device *pd; +}; + +struct pkt_rb_node { + struct rb_node rb_node; + struct bio *bio; +}; + +struct packet_stacked_data +{ + struct bio *bio; /* Original read request bio */ + struct pktcdvd_device *pd; +}; +#define PSD_POOL_SIZE 64 + +struct pktcdvd_device +{ + struct block_device *bdev; /* dev attached */ + dev_t pkt_dev; /* our dev */ + char name[20]; + struct packet_settings settings; + struct packet_stats stats; + int refcnt; /* Open count */ + int write_speed; /* current write speed, kB/s */ + int read_speed; /* current read speed, kB/s */ + unsigned long offset; /* start offset */ + __u8 mode_offset; /* 0 / 8 */ + __u8 type; + unsigned long flags; + __u16 mmc3_profile; + __u32 nwa; /* next writable address */ + __u32 lra; /* last recorded address */ + struct packet_cdrw cdrw; + wait_queue_head_t wqueue; + + spinlock_t lock; /* Serialize access to bio_queue */ + struct rb_root bio_queue; /* Work queue of bios we need to handle */ + int bio_queue_size; /* Number of nodes in bio_queue */ + bool congested; /* Someone is waiting for bio_queue_size + * to drop. */ + sector_t current_sector; /* Keep track of where the elevator is */ + atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */ + /* needs to be run. */ + mempool_t rb_pool; /* mempool for pkt_rb_node allocations */ + + struct packet_iosched iosched; + struct gendisk *disk; + + int write_congestion_off; + int write_congestion_on; + + struct device *dev; /* sysfs pktcdvd[0-7] dev */ + + struct dentry *dfs_d_root; /* debugfs: devname directory */ + struct dentry *dfs_f_info; /* debugfs: info file */ +}; + +#endif /* __PKTCDVD_H */ diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h new file mode 100644 index 000000000000..9cbb55d21c94 --- /dev/null +++ b/include/uapi/linux/pktcdvd.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2000 Jens Axboe + * Copyright (C) 2001-2004 Peter Osterlund + * + * May be copied or modified under the terms of the GNU General Public + * License. See linux/COPYING for more information. + * + * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and + * DVD-RW devices. + * + */ +#ifndef _UAPI__PKTCDVD_H +#define _UAPI__PKTCDVD_H + +#include + +/* + * 1 for normal debug messages, 2 is very verbose. 0 to turn it off. + */ +#define PACKET_DEBUG 1 + +#define MAX_WRITERS 8 + +#define PKT_RB_POOL_SIZE 512 + +/* + * How long we should hold a non-full packet before starting data gathering. + */ +#define PACKET_WAIT_TIME (HZ * 5 / 1000) + +/* + * use drive write caching -- we need deferred error handling to be + * able to successfully recover with this option (drive will return good + * status as soon as the cdb is validated). + */ +#if defined(CONFIG_CDROM_PKTCDVD_WCACHE) +#define USE_WCACHING 1 +#else +#define USE_WCACHING 0 +#endif + +/* + * No user-servicable parts beyond this point -> + */ + +/* + * device types + */ +#define PACKET_CDR 1 +#define PACKET_CDRW 2 +#define PACKET_DVDR 3 +#define PACKET_DVDRW 4 + +/* + * flags + */ +#define PACKET_WRITABLE 1 /* pd is writable */ +#define PACKET_NWA_VALID 2 /* next writable address valid */ +#define PACKET_LRA_VALID 3 /* last recorded address valid */ +#define PACKET_MERGE_SEGS 4 /* perform segment merging to keep */ + /* underlying cdrom device happy */ + +/* + * Disc status -- from READ_DISC_INFO + */ +#define PACKET_DISC_EMPTY 0 +#define PACKET_DISC_INCOMPLETE 1 +#define PACKET_DISC_COMPLETE 2 +#define PACKET_DISC_OTHER 3 + +/* + * write type, and corresponding data block type + */ +#define PACKET_MODE1 1 +#define PACKET_MODE2 2 +#define PACKET_BLOCK_MODE1 8 +#define PACKET_BLOCK_MODE2 10 + +/* + * Last session/border status + */ +#define PACKET_SESSION_EMPTY 0 +#define PACKET_SESSION_INCOMPLETE 1 +#define PACKET_SESSION_RESERVED 2 +#define PACKET_SESSION_COMPLETE 3 + +#define PACKET_MCN "4a656e734178626f65323030300000" + +#undef PACKET_USE_LS + +#define PKT_CTRL_CMD_SETUP 0 +#define PKT_CTRL_CMD_TEARDOWN 1 +#define PKT_CTRL_CMD_STATUS 2 + +struct pkt_ctrl_command { + __u32 command; /* in: Setup, teardown, status */ + __u32 dev_index; /* in/out: Device index */ + __u32 dev; /* in/out: Device nr for cdrw device */ + __u32 pkt_dev; /* in/out: Device nr for packet device */ + __u32 num_devices; /* out: Largest device index + 1 */ + __u32 padding; /* Not used */ +}; + +/* + * packet ioctls + */ +#define PACKET_IOCTL_MAGIC ('X') +#define PACKET_CTRL_CMD _IOWR(PACKET_IOCTL_MAGIC, 1, struct pkt_ctrl_command) + + +#endif /* _UAPI__PKTCDVD_H */ From 6fe6ece398f7431784847e922a2c8c385dc58a35 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Wed, 21 Dec 2022 16:24:13 +0100 Subject: [PATCH 099/233] Revert "drm/amd/display: Enable Freesync Video Mode by default" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit de05abe6b9d0fe08f65d744f7f75a4cba4df27ad. The bug referenced below was bisected to this commit. There has been no activity toward fixing it in 3 months, so let's revert for now. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2162 Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 27 +++++++++++++++++++ .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +++++---- 3 files changed, 35 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 6b74df446694..e3e2e6e3b485 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -195,6 +195,7 @@ extern int amdgpu_emu_mode; extern uint amdgpu_smu_memory_pool_size; extern int amdgpu_smu_pptable_id; extern uint amdgpu_dc_feature_mask; +extern uint amdgpu_freesync_vid_mode; extern uint amdgpu_dc_debug_mask; extern uint amdgpu_dc_visual_confirm; extern uint amdgpu_dm_abm_level; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b4f2d61ea0d5..1353ffd08988 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -181,6 +181,7 @@ int amdgpu_mes_kiq; int amdgpu_noretry = -1; int amdgpu_force_asic_type = -1; int amdgpu_tmz = -1; /* auto */ +uint amdgpu_freesync_vid_mode; int amdgpu_reset_method = -1; /* auto */ int amdgpu_num_kcq = -1; int amdgpu_smartshift_bias; @@ -879,6 +880,32 @@ module_param_named(backlight, amdgpu_backlight, bint, 0444); MODULE_PARM_DESC(tmz, "Enable TMZ feature (-1 = auto (default), 0 = off, 1 = on)"); module_param_named(tmz, amdgpu_tmz, int, 0444); +/** + * DOC: freesync_video (uint) + * Enable the optimization to adjust front porch timing to achieve seamless + * mode change experience when setting a freesync supported mode for which full + * modeset is not needed. + * + * The Display Core will add a set of modes derived from the base FreeSync + * video mode into the corresponding connector's mode list based on commonly + * used refresh rates and VRR range of the connected display, when users enable + * this feature. From the userspace perspective, they can see a seamless mode + * change experience when the change between different refresh rates under the + * same resolution. Additionally, userspace applications such as Video playback + * can read this modeset list and change the refresh rate based on the video + * frame rate. Finally, the userspace can also derive an appropriate mode for a + * particular refresh rate based on the FreeSync Mode and add it to the + * connector's mode list. + * + * Note: This is an experimental feature. + * + * The default value: 0 (off). + */ +MODULE_PARM_DESC( + freesync_video, + "Enable freesync modesetting optimization feature (0 = off (default), 1 = on)"); +module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444); + /** * DOC: reset_method (int) * GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco) 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 86bc23a67d97..1b7f20a9d4ae 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5835,7 +5835,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, */ DRM_DEBUG_DRIVER("No preferred mode found\n"); } else { - recalculate_timing = is_freesync_video_mode(&mode, aconnector); + recalculate_timing = amdgpu_freesync_vid_mode && + is_freesync_video_mode(&mode, aconnector); if (recalculate_timing) { freesync_mode = get_highest_refresh_rate_mode(aconnector, false); drm_mode_copy(&saved_mode, &mode); @@ -6986,7 +6987,7 @@ static void amdgpu_dm_connector_add_freesync_modes(struct drm_connector *connect struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); - if (!edid) + if (!(amdgpu_freesync_vid_mode && edid)) return; if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10) @@ -8850,7 +8851,8 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, * TODO: Refactor this function to allow this check to work * in all conditions. */ - if (dm_new_crtc_state->stream && + if (amdgpu_freesync_vid_mode && + dm_new_crtc_state->stream && is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state)) goto skip_modeset; @@ -8885,7 +8887,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, if (!dm_old_crtc_state->stream) goto skip_modeset; - if (dm_new_crtc_state->stream && + if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream && is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state)) { new_crtc_state->mode_changed = false; @@ -8897,7 +8899,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, set_freesync_fixed_config(dm_new_crtc_state); goto skip_modeset; - } else if (aconnector && + } else if (amdgpu_freesync_vid_mode && aconnector && is_freesync_video_mode(&new_crtc_state->mode, aconnector)) { struct drm_display_mode *high_mode; From bd0ddcfc83d85bc30c868f2c3457312c7f1ccee2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 3 Jan 2023 12:00:31 -0600 Subject: [PATCH 100/233] Revert "of: fdt: Honor CONFIG_CMDLINE* even without /chosen node" This reverts commit a7d550f82b445cf218b47a2c1a9c56e97ecb8c7a. Some arches (PPC at least) don't call early_init_dt_scan_nodes(), so moving the cmdline processing there breaks them. Reported-by: Geoff Levand Cc: Alexander Sverdlin Tested-by: Geoff Levand Reviewed-by: Alexander Sverdlin Link: https://lore.kernel.org/r/20230103-dt-cmdline-fix-v1-1-7038e88b18b6@kernel.org Signed-off-by: Rob Herring --- drivers/of/fdt.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 02cc4a285cb9..4f88e8bbdd27 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1175,6 +1175,26 @@ int __init early_init_dt_scan_chosen(char *cmdline) if (p != NULL && l > 0) strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE)); + /* + * CONFIG_CMDLINE is meant to be a default in case nothing else + * managed to set the command line, unless CONFIG_CMDLINE_FORCE + * is set in which case we override whatever was found earlier. + */ +#ifdef CONFIG_CMDLINE +#if defined(CONFIG_CMDLINE_EXTEND) + strlcat(cmdline, " ", COMMAND_LINE_SIZE); + strlcat(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE); +#elif defined(CONFIG_CMDLINE_FORCE) + strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE); +#else + /* No arguments from boot loader, use kernel's cmdl*/ + if (!((char *)cmdline)[0]) + strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE); +#endif +#endif /* CONFIG_CMDLINE */ + + pr_debug("Command line is: %s\n", (char *)cmdline); + rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l); if (rng_seed && l > 0) { add_bootloader_randomness(rng_seed, l); @@ -1279,26 +1299,6 @@ void __init early_init_dt_scan_nodes(void) if (rc) pr_warn("No chosen node found, continuing without\n"); - /* - * CONFIG_CMDLINE is meant to be a default in case nothing else - * managed to set the command line, unless CONFIG_CMDLINE_FORCE - * is set in which case we override whatever was found earlier. - */ -#ifdef CONFIG_CMDLINE -#if defined(CONFIG_CMDLINE_EXTEND) - strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); - strlcat(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#elif defined(CONFIG_CMDLINE_FORCE) - strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#else - /* No arguments from boot loader, use kernel's cmdl */ - if (!boot_command_line[0]) - strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#endif -#endif /* CONFIG_CMDLINE */ - - pr_debug("Command line is: %s\n", boot_command_line); - /* Setup memory, calling early_init_dt_add_memory_arch */ early_init_dt_scan_memory(); From 064e32dc5b03114d0767893fecdaf7b5dfd8c286 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 3 Jan 2023 12:00:32 -0600 Subject: [PATCH 101/233] of: fdt: Honor CONFIG_CMDLINE* even without /chosen node, take 2 I do not read a strict requirement on /chosen node in either ePAPR or in Documentation/devicetree. Help text for CONFIG_CMDLINE and CONFIG_CMDLINE_EXTEND doesn't make their behavior explicitly dependent on the presence of /chosen or the presense of /chosen/bootargs. However the early check for /chosen and bailing out in early_init_dt_scan_chosen() skips CONFIG_CMDLINE handling which is not really related to /chosen node or the particular method of passing cmdline from bootloader. This leads to counterintuitive combinations (assuming CONFIG_CMDLINE_EXTEND=y): a) bootargs="foo", CONFIG_CMDLINE="bar" => cmdline=="foo bar" b) /chosen missing, CONFIG_CMDLINE="bar" => cmdline=="" c) bootargs="", CONFIG_CMDLINE="bar" => cmdline==" bar" Rework early_init_dt_scan_chosen() so that the cmdline config options are always handled. [commit msg written by Alexander Sverdlin] Cc: Alexander Sverdlin Cc: Linus Walleij Cc: Arnd Bergmann Tested-by: Geoff Levand Reviewed-by: Alexander Sverdlin Link: https://lore.kernel.org/r/20230103-dt-cmdline-fix-v1-2-7038e88b18b6@kernel.org Signed-off-by: Rob Herring --- drivers/of/fdt.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 4f88e8bbdd27..f08b25195ae7 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1163,18 +1163,32 @@ int __init early_init_dt_scan_chosen(char *cmdline) if (node < 0) node = fdt_path_offset(fdt, "/chosen@0"); if (node < 0) - return -ENOENT; + /* Handle the cmdline config options even if no /chosen node */ + goto handle_cmdline; chosen_node_offset = node; early_init_dt_check_for_initrd(node); early_init_dt_check_for_elfcorehdr(node); + rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l); + if (rng_seed && l > 0) { + add_bootloader_randomness(rng_seed, l); + + /* try to clear seed so it won't be found. */ + fdt_nop_property(initial_boot_params, node, "rng-seed"); + + /* update CRC check value */ + of_fdt_crc32 = crc32_be(~0, initial_boot_params, + fdt_totalsize(initial_boot_params)); + } + /* Retrieve command line */ p = of_get_flat_dt_prop(node, "bootargs", &l); if (p != NULL && l > 0) strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE)); +handle_cmdline: /* * CONFIG_CMDLINE is meant to be a default in case nothing else * managed to set the command line, unless CONFIG_CMDLINE_FORCE @@ -1195,18 +1209,6 @@ int __init early_init_dt_scan_chosen(char *cmdline) pr_debug("Command line is: %s\n", (char *)cmdline); - rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l); - if (rng_seed && l > 0) { - add_bootloader_randomness(rng_seed, l); - - /* try to clear seed so it won't be found. */ - fdt_nop_property(initial_boot_params, node, "rng-seed"); - - /* update CRC check value */ - of_fdt_crc32 = crc32_be(~0, initial_boot_params, - fdt_totalsize(initial_boot_params)); - } - return 0; } From 7246210ecdd0cda97fa3e3bb15c32c6c2d9a23b5 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Tue, 27 Dec 2022 11:29:28 +0000 Subject: [PATCH 102/233] cifs: refcount only the selected iface during interface update When the server interface for a channel is not active anymore, we have the logic to select an alternative interface. However this was not breaking out of the loop as soon as a new alternative was found. As a result, some interfaces may get refcounted unintentionally. There was also a bug in checking if we found an alternate iface. Fixed that too. Fixes: b54034a73baf ("cifs: during reconnect, update interface if necessary") Cc: stable@vger.kernel.org # 5.19+ Signed-off-by: Shyam Prasad N Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/sess.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 9e7d9f0baa18..0b842a07e157 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -292,9 +292,10 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) continue; } kref_get(&iface->refcount); + break; } - if (!list_entry_is_head(iface, &ses->iface_list, iface_head)) { + if (list_entry_is_head(iface, &ses->iface_list, iface_head)) { rc = 1; iface = NULL; cifs_dbg(FYI, "unable to find a suitable iface\n"); From cc7d79d4fad6a4eab3f88c4bb237de72be4478f1 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Thu, 22 Dec 2022 12:54:44 +0000 Subject: [PATCH 103/233] cifs: fix interface count calculation during refresh The last fix to iface_count did fix the overcounting issue. However, during each refresh, we could end up undercounting the iface_count, if a match was found. Fixing this by doing increments and decrements instead of setting it to 0 before each parsing of server interfaces. Fixes: 096bbeec7bd6 ("smb3: interface count displayed incorrectly") Cc: stable@vger.kernel.org # 6.1 Signed-off-by: Shyam Prasad N Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 0d7e9bcd9f34..e6bcd2baf446 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -530,7 +530,6 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, p = buf; spin_lock(&ses->iface_lock); - ses->iface_count = 0; /* * Go through iface_list and do kref_put to remove * any unused ifaces. ifaces in use will be removed @@ -540,6 +539,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, iface_head) { iface->is_active = 0; kref_put(&iface->refcount, release_iface); + ses->iface_count--; } spin_unlock(&ses->iface_lock); @@ -618,6 +618,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, /* just get a ref so that it doesn't get picked/freed */ iface->is_active = 1; kref_get(&iface->refcount); + ses->iface_count++; spin_unlock(&ses->iface_lock); goto next_iface; } else if (ret < 0) { From a53da43decaa3936998fa7dce2346855a6942166 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 1 Jan 2023 15:07:09 +0900 Subject: [PATCH 104/233] kbuild: fix single *.ko build The single *.ko build is broken since commit f65a486821cf ("kbuild: change module.order to list *.o instead of *.ko"). Fixes: f65a486821cf ("kbuild: change module.order to list *.o instead of *.ko") Reported-by: Marc Kleine-Budde Signed-off-by: Masahiro Yamada Tested-by: Marc Kleine-Budde --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index c05b4fb7121e..dfba294ae790 100644 --- a/Makefile +++ b/Makefile @@ -1986,7 +1986,7 @@ $(single-no-ko): $(build-dir) # Remove MODORDER when done because it is not the real one. PHONY += single_modules single_modules: $(single-no-ko) modules_prepare - $(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$m;) } > $(MODORDER) + $(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$(m:%.ko=%.o);) } > $(MODORDER) $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost ifneq ($(KBUILD_MODPOST_NOFINAL),1) $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal From 735aec59afb18c3e2da0a637037e69ad62dbda6a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 4 Jan 2023 23:04:59 +0900 Subject: [PATCH 105/233] kbuild: readd -w option when vmlinux.o or Module.symver is missing Commit 63ffe00d8c93 ("kbuild: Fix running modpost with musl libc") accidentally turned the unresolved symbol warnings into errors when vmlinux.o (for in-tree builds) or Module.symver (for external module builds) is missing. In those cases, unresolved symbols are expected, but the -w option is not set because 'missing-input' is referenced before set. Move $(missing-input) back to the original place. This should be fine for musl libc because vmlinux.o and -w are not added at the same time. With this change, -w may be passed twice, but it is not a big deal. Link: https://lore.kernel.org/all/b56a03b8-2a2a-f833-a5d2-cdc50a7ca2bb@cschramm.eu/ Fixes: 63ffe00d8c93 ("kbuild: Fix running modpost with musl libc") Reported-by: Christopher Schramm Signed-off-by: Masahiro Yamada Tested-by: Samuel Holland --- scripts/Makefile.modpost | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 0ee296cf520c..43343e13c542 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -44,6 +44,7 @@ modpost-args = \ $(if $(CONFIG_MODVERSIONS),-m) \ $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \ $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ + $(if $(KBUILD_MODPOST_WARN),-w) \ $(if $(KBUILD_NSDEPS),-d $(MODULES_NSDEPS)) \ $(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N) \ -o $@ @@ -55,10 +56,6 @@ ifneq ($(findstring i,$(filter-out --%,$(MAKEFLAGS))),) modpost-args += -n endif -ifneq ($(KBUILD_MODPOST_WARN)$(missing-input),) -modpost-args += -w -endif - # Read out modules.order to pass in modpost. # Otherwise, allmodconfig would fail with "Argument list too long". ifdef KBUILD_MODULES @@ -124,6 +121,10 @@ modpost-args += -e $(addprefix -i , $(KBUILD_EXTRA_SYMBOLS)) endif # ($(KBUILD_EXTMOD),) +ifneq ($(missing-input),) +modpost-args += -w +endif + quiet_cmd_modpost = MODPOST $@ cmd_modpost = \ $(if $(missing-input), \ From 4b9880dbf3bdba3a7c56445137c3d0e30aaa0a40 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 5 Jan 2023 22:05:04 +1100 Subject: [PATCH 106/233] powerpc/vmlinux.lds: Define RUNTIME_DISCARD_EXIT The powerpc linker script explicitly includes .exit.text, because otherwise the link fails due to references from __bug_table and __ex_table. The code is freed (discarded) at runtime along with .init.text and data. That has worked in the past despite powerpc not defining RUNTIME_DISCARD_EXIT because DISCARDS appears late in the powerpc linker script (line 410), and the explicit inclusion of .exit.text earlier (line 280) supersedes the discard. However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") introduced an earlier use of DISCARD as part of the RO_DATA macro (line 136). With binutils < 2.36 that causes the DISCARD directives later in the script to be applied earlier [1], causing .exit.text to actually be discarded at link time, leading to build errors: '.exit.text' referenced in section '__bug_table' of crypto/algboss.o: defined in discarded section '.exit.text' of crypto/algboss.o '.exit.text' referenced in section '__ex_table' of drivers/nvdimm/core.o: defined in discarded section '.exit.text' of drivers/nvdimm/core.o Fix it by defining RUNTIME_DISCARD_EXIT, which causes the generic DISCARDS macro to not include .exit.text at all. 1: https://lore.kernel.org/lkml/87fscp2v7k.fsf@igel.home/ Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230105132349.384666-1-mpe@ellerman.id.au --- arch/powerpc/kernel/vmlinux.lds.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8c3862b4c259..c5ea7d03d539 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -8,6 +8,7 @@ #define BSS_FIRST_SECTIONS *(.bss.prominit) #define EMITS_PT_NOTE #define RO_EXCEPTION_TABLE_ALIGN 0 +#define RUNTIME_DISCARD_EXIT #define SOFT_MASK_TABLE(align) \ . = ALIGN(align); \ From 07b050f9290ee012a407a0f64151db902a1520f5 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 5 Jan 2023 22:28:36 +1100 Subject: [PATCH 107/233] powerpc/vmlinux.lds: Don't discard .rela* for relocatable builds Relocatable kernels must not discard relocations, they need to be processed at runtime. As such they are included for CONFIG_RELOCATABLE builds in the powerpc linker script (line 340). However they are also unconditionally discarded later in the script (line 414). Previously that worked because the earlier inclusion superseded the discard. However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") introduced an earlier use of DISCARD as part of the RO_DATA macro (line 137). With binutils < 2.36 that causes the DISCARD directives later in the script to be applied earlier, causing .rela* to actually be discarded at link time, leading to build warnings and a kernel that doesn't boot: ld: warning: discarding dynamic section .rela.init.rodata Fix it by conditionally discarding .rela* only when CONFIG_RELOCATABLE is disabled. Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230105132349.384666-2-mpe@ellerman.id.au --- arch/powerpc/kernel/vmlinux.lds.S | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index c5ea7d03d539..a4c6efadc90c 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -411,9 +411,12 @@ SECTIONS DISCARDS /DISCARD/ : { *(*.EMB.apuinfo) - *(.glink .iplt .plt .rela* .comment) + *(.glink .iplt .plt .comment) *(.gnu.version*) *(.gnu.attributes) *(.eh_frame) +#ifndef CONFIG_RELOCATABLE + *(.rela*) +#endif } } From be5f95c8779e19779dd81927c8574fec5aaba36c Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 5 Jan 2023 22:42:59 +1100 Subject: [PATCH 108/233] powerpc/vmlinux.lds: Don't discard .comment Although the powerpc linker script mentions .comment in the DISCARD section, that has never actually caused it to be discarded, because the earlier ELF_DETAILS macro (previously STABS_DEBUG) explicitly includes .comment. However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") introduced an earlier use of DISCARD as part of the RO_DATA macro. With binutils < 2.36 that causes the DISCARD directives later in the script to be applied earlier, causing .comment to actually be discarded. It's confusing to explicitly include and discard .comment, and even more so if the behaviour depends on the toolchain version. So don't discard .comment in order to maintain the existing behaviour in all cases. Fixes: 83a092cf95f2 ("powerpc: Link warning for orphan sections") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230105132349.384666-3-mpe@ellerman.id.au --- arch/powerpc/kernel/vmlinux.lds.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index a4c6efadc90c..958e77a24f85 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -411,7 +411,7 @@ SECTIONS DISCARDS /DISCARD/ : { *(*.EMB.apuinfo) - *(.glink .iplt .plt .comment) + *(.glink .iplt .plt) *(.gnu.version*) *(.gnu.attributes) *(.eh_frame) From 12521a5d5cb7ff0ad43eadfc9c135d86e1131fa8 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 5 Jan 2023 10:49:15 +0000 Subject: [PATCH 109/233] io_uring: fix CQ waiting timeout handling Jiffy to ktime CQ waiting conversion broke how we treat timeouts, in particular we rearm it anew every time we get into io_cqring_wait_schedule() without adjusting the timeout. Waiting for 2 CQEs and getting a task_work in the middle may double the timeout value, or even worse in some cases task may wait indefinitely. Cc: stable@vger.kernel.org Fixes: 228339662b398 ("io_uring: don't convert to jiffies for waiting on timeouts") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/f7bffddd71b08f28a877d44d37ac953ddb01590d.1672915663.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 472574192dd6..2ac1cd8d23ea 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2470,7 +2470,7 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx) /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, - ktime_t timeout) + ktime_t *timeout) { int ret; unsigned long check_cq; @@ -2488,7 +2488,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)) return -EBADR; } - if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) + if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) return -ETIME; /* @@ -2564,7 +2564,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, } prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); - ret = io_cqring_wait_schedule(ctx, &iowq, timeout); + ret = io_cqring_wait_schedule(ctx, &iowq, &timeout); if (__io_cqring_events_user(ctx) >= min_events) break; cond_resched(); From 601a27ea09a317d0fe2895df7d875381fb393041 Mon Sep 17 00:00:00 2001 From: Wengang Wang Date: Wed, 4 Jan 2023 10:05:43 -0800 Subject: [PATCH 110/233] xfs: fix extent busy updating In xfs_extent_busy_update_extent() case 6 and 7, whenever bno is modified on extent busy, the relavent length has to be modified accordingly. Signed-off-by: Wengang Wang Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_extent_busy.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index ad22a003f959..f3d328e4a440 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -236,6 +236,7 @@ xfs_extent_busy_update_extent( * */ busyp->bno = fend; + busyp->length = bend - fend; } else if (bbno < fbno) { /* * Case 8: From b2b50d572135c5c6e10c2ff79cd828d5a8141ef6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 4 Jan 2023 16:37:53 -0800 Subject: [PATCH 111/233] block: Remove "select SRCU" Now that the SRCU Kconfig option is unconditionally selected, there is no longer any point in selecting it. Therefore, remove the "select SRCU" Kconfig statements. Signed-off-by: Paul E. McKenney Cc: Jens Axboe Cc: linux-block@vger.kernel.org Signed-off-by: Jens Axboe --- block/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/block/Kconfig b/block/Kconfig index 444c5ab3b67e..5d9d9c84d516 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -6,7 +6,6 @@ menuconfig BLOCK bool "Enable the block layer" if EXPERT default y select SBITMAP - select SRCU help Provide block layer support for the kernel. From 38892ea4cefbb6ed3a91e76d3af84a1f8077d2d4 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Wed, 4 Jan 2023 18:36:27 +0900 Subject: [PATCH 112/233] spi: dt-bindings: Rename spi-cs-setup-ns to spi-cs-setup-delay-ns Other delay values follow the delay-ns naming convention, so unify the newly introduced spi-cs-setup-ns property for consistency. Also fix a typo while we're here. Fixes: f6c911f3308c ("spi: dt-bindings: Introduce spi-cs-setup-ns property") Signed-off-by: Hector Martin Link: https://lore.kernel.org/r/20230104093631.15611-2-marcan@marcan.st Signed-off-by: Mark Brown --- .../devicetree/bindings/spi/spi-peripheral-props.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml index ead2cccf658f..9a60c0664bbe 100644 --- a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml +++ b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml @@ -44,9 +44,9 @@ properties: description: Maximum SPI clocking speed of the device in Hz. - spi-cs-setup-ns: + spi-cs-setup-delay-ns: description: - Delay in nanosecods to be introduced by the controller after CS is + Delay in nanoseconds to be introduced by the controller after CS is asserted. spi-rx-bus-width: From e0fe6a31cac84735939c29d1e05055d58325c6c0 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Wed, 4 Jan 2023 18:36:28 +0900 Subject: [PATCH 113/233] spi: Rename spi-cs-setup-ns property to spi-cs-setup-delay-ns As mentioned in the corresponding DT binding commit, the naming scheme for delay properties includes "delay" in the name, so let's keep that consistent. Fixes: 33a2fde5f77b ("spi: Introduce spi-cs-setup-ns property") Signed-off-by: Hector Martin Link: https://lore.kernel.org/r/20230104093631.15611-3-marcan@marcan.st Signed-off-by: Mark Brown --- drivers/spi/spi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 3cc7bb4d03de..15f174f4e056 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2310,7 +2310,7 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, if (!of_property_read_u32(nc, "spi-max-frequency", &value)) spi->max_speed_hz = value; - if (!of_property_read_u16(nc, "spi-cs-setup-ns", &cs_setup)) { + if (!of_property_read_u16(nc, "spi-cs-setup-delay-ns", &cs_setup)) { spi->cs_setup.value = cs_setup; spi->cs_setup.unit = SPI_DELAY_UNIT_NSECS; } From e95d50d74b93a767a026f588e8de0b9718a0105e Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 5 Jan 2023 13:23:39 +0200 Subject: [PATCH 114/233] lib/scatterlist: Fix to merge contiguous pages into the last SG properly When sg_alloc_append_table_from_pages() calls to pages_are_mergeable() in its 'sgt_append->prv' flow to check whether it can merge contiguous pages into the last SG, it passes the page arguments in the wrong order. The first parameter should be the next candidate page to be merged to the last page and not the opposite. The current code leads to a corrupted SG which resulted in OOPs and unexpected errors when non-contiguous pages are merged wrongly. Fix to pass the page parameters in the right order. Fixes: 1567b49d1a40 ("lib/scatterlist: add check when merging zone device pages") Link: https://lore.kernel.org/r/20230105112339.107969-1-yishaih@nvidia.com Signed-off-by: Yishai Hadas Reviewed-by: Jason Gunthorpe Reviewed-by: Logan Gunthorpe Signed-off-by: Jason Gunthorpe --- lib/scatterlist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/scatterlist.c b/lib/scatterlist.c index a0ad2a7959b5..f72aa50c6654 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -476,7 +476,7 @@ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append, /* Merge contiguous pages into the last SG */ prv_len = sgt_append->prv->length; last_pg = sg_page(sgt_append->prv); - while (n_pages && pages_are_mergeable(last_pg, pages[0])) { + while (n_pages && pages_are_mergeable(pages[0], last_pg)) { if (sgt_append->prv->length + PAGE_SIZE > max_segment) break; sgt_append->prv->length += PAGE_SIZE; From b2d473a6019ef9a54b0156ecdb2e0398c9fa6a24 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Mon, 2 Jan 2023 17:07:48 +0100 Subject: [PATCH 115/233] riscv, kprobes: Stricter c.jr/c.jalr decoding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the compressed instruction extension, c.jr, c.jalr, c.mv, and c.add is encoded the following way (each instruction is 16b): ---+-+-----------+-----------+-- 100 0 rs1[4:0]!=0 00000 10 : c.jr 100 1 rs1[4:0]!=0 00000 10 : c.jalr 100 0 rd[4:0]!=0 rs2[4:0]!=0 10 : c.mv 100 1 rd[4:0]!=0 rs2[4:0]!=0 10 : c.add The following logic is used to decode c.jr and c.jalr: insn & 0xf007 == 0x8002 => instruction is an c.jr insn & 0xf007 == 0x9002 => instruction is an c.jalr When 0xf007 is used to mask the instruction, c.mv can be incorrectly decoded as c.jr, and c.add as c.jalr. Correct the decoding by changing the mask from 0xf007 to 0xf07f. Fixes: c22b0bcb1dd0 ("riscv: Add kprobes supported") Signed-off-by: Björn Töpel Reviewed-by: Conor Dooley Reviewed-by: Guo Ren Link: https://lore.kernel.org/r/20230102160748.1307289-1-bjorn@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/probes/simulate-insn.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h index cb6ff7dccb92..de8474146a9b 100644 --- a/arch/riscv/kernel/probes/simulate-insn.h +++ b/arch/riscv/kernel/probes/simulate-insn.h @@ -31,9 +31,9 @@ __RISCV_INSN_FUNCS(fence, 0x7f, 0x0f); } while (0) __RISCV_INSN_FUNCS(c_j, 0xe003, 0xa001); -__RISCV_INSN_FUNCS(c_jr, 0xf007, 0x8002); +__RISCV_INSN_FUNCS(c_jr, 0xf07f, 0x8002); __RISCV_INSN_FUNCS(c_jal, 0xe003, 0x2001); -__RISCV_INSN_FUNCS(c_jalr, 0xf007, 0x9002); +__RISCV_INSN_FUNCS(c_jalr, 0xf07f, 0x9002); __RISCV_INSN_FUNCS(c_beqz, 0xe003, 0xc001); __RISCV_INSN_FUNCS(c_bnez, 0xe003, 0xe001); __RISCV_INSN_FUNCS(c_ebreak, 0xffff, 0x9002); From b9b916aee6715cd7f3318af6dc360c4729417b94 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Thu, 29 Dec 2022 17:05:45 +0000 Subject: [PATCH 116/233] riscv: uaccess: fix type of 0 variable on error in get_user() If the get_user(x, ptr) has x as a pointer, then the setting of (x) = 0 is going to produce the following sparse warning, so fix this by forcing the type of 'x' when access_ok() fails. fs/aio.c:2073:21: warning: Using plain integer as NULL pointer Signed-off-by: Ben Dooks Reviewed-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20221229170545.718264-1-ben-linux@fluff.org Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 855450bed9f5..ec0cab9fbddd 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -165,7 +165,7 @@ do { \ might_fault(); \ access_ok(__p, sizeof(*__p)) ? \ __get_user((x), __p) : \ - ((x) = 0, -EFAULT); \ + ((x) = (__force __typeof__(x))0, -EFAULT); \ }) #define __put_user_asm(insn, x, ptr, err) \ From c26de7507d1f5ffa5daf6a4980ef7896889691a9 Mon Sep 17 00:00:00 2001 From: Biao Huang Date: Thu, 5 Jan 2023 09:07:11 +0800 Subject: [PATCH 117/233] stmmac: dwmac-mediatek: remove the dwmac_fix_mac_speed In current driver, MAC will always enable 2ns delay in RGMII mode, but that's not the correct usage. Remove the dwmac_fix_mac_speed() in driver, and recommend "rgmii-id" for phy-mode in device tree. Fixes: f2d356a6ab71 ("stmmac: dwmac-mediatek: add support for mt8195") Reviewed-by: Andrew Lunn Signed-off-by: Biao Huang Signed-off-by: Jakub Kicinski --- .../ethernet/stmicro/stmmac/dwmac-mediatek.c | 26 ------------------- 1 file changed, 26 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index d42e1afb6521..2f7d8e4561d9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -90,7 +90,6 @@ struct mediatek_dwmac_plat_data { struct mediatek_dwmac_variant { int (*dwmac_set_phy_interface)(struct mediatek_dwmac_plat_data *plat); int (*dwmac_set_delay)(struct mediatek_dwmac_plat_data *plat); - void (*dwmac_fix_mac_speed)(void *priv, unsigned int speed); /* clock ids to be requested */ const char * const *clk_list; @@ -443,32 +442,9 @@ static int mt8195_set_delay(struct mediatek_dwmac_plat_data *plat) return 0; } -static void mt8195_fix_mac_speed(void *priv, unsigned int speed) -{ - struct mediatek_dwmac_plat_data *priv_plat = priv; - - if ((phy_interface_mode_is_rgmii(priv_plat->phy_mode))) { - /* prefer 2ns fixed delay which is controlled by TXC_PHASE_CTRL, - * when link speed is 1Gbps with RGMII interface, - * Fall back to delay macro circuit for 10/100Mbps link speed. - */ - if (speed == SPEED_1000) - regmap_update_bits(priv_plat->peri_regmap, - MT8195_PERI_ETH_CTRL0, - MT8195_RGMII_TXC_PHASE_CTRL | - MT8195_DLY_GTXC_ENABLE | - MT8195_DLY_GTXC_INV | - MT8195_DLY_GTXC_STAGES, - MT8195_RGMII_TXC_PHASE_CTRL); - else - mt8195_set_delay(priv_plat); - } -} - static const struct mediatek_dwmac_variant mt8195_gmac_variant = { .dwmac_set_phy_interface = mt8195_set_interface, .dwmac_set_delay = mt8195_set_delay, - .dwmac_fix_mac_speed = mt8195_fix_mac_speed, .clk_list = mt8195_dwmac_clk_l, .num_clks = ARRAY_SIZE(mt8195_dwmac_clk_l), .dma_bit_mask = 35, @@ -619,8 +595,6 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, plat->bsp_priv = priv_plat; plat->init = mediatek_dwmac_init; plat->clks_config = mediatek_dwmac_clks_config; - if (priv_plat->variant->dwmac_fix_mac_speed) - plat->fix_mac_speed = priv_plat->variant->dwmac_fix_mac_speed; plat->safety_feat_cfg = devm_kzalloc(&pdev->dev, sizeof(*plat->safety_feat_cfg), From eea8ce81fbb544e3caad1a1c876ba1af467b3d3c Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Thu, 5 Jan 2023 11:42:49 +0800 Subject: [PATCH 118/233] net: usb: cdc_ether: add support for Thales Cinterion PLS62-W modem This modem has 7 interfaces, 5 of them are serial interfaces and are driven by cdc_acm, while 2 of them are wwan interfaces and are driven by cdc_ether: If 0: Abstract (modem) If 1: Abstract (modem) If 2: Abstract (modem) If 3: Abstract (modem) If 4: Abstract (modem) If 5: Ethernet Networking If 6: Ethernet Networking Without this change, the 2 network interfaces will be named to usb0 and usb1, our QA think the names are confusing and filed a bug on it. After applying this change, the name will be wwan0 and wwan1, and they could work well with modem manager. Signed-off-by: Hui Wang Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230105034249.10433-1-hui.wang@canonical.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/cdc_ether.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 8911cd2ed534..c140edb4b648 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -1007,6 +1007,12 @@ static const struct usb_device_id products[] = { USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&wwan_info, +}, { + /* Cinterion PLS62-W modem by GEMALTO/THALES */ + USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x005b, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, }, { /* Cinterion PLS83/PLS63 modem by GEMALTO/THALES */ USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0069, USB_CLASS_COMM, From 1a5a23b9bdf6bde0e5185ca834ff6e806cc2aaaf Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 30 Dec 2022 14:54:27 +0800 Subject: [PATCH 119/233] usb: fotg210-udc: fix error return code in fotg210_udc_probe() After commit 5f217ccd520f ("fotg210-udc: Support optional external PHY"), the error code is re-assigned to 0 in fotg210_udc_probe(), if allocate or map memory fails after the assignment, it can't return an error code. Set the error code to -ENOMEM to fix this problem. Fixes: 5f217ccd520f ("fotg210-udc: Support optional external PHY") Signed-off-by: Yang Yingliang Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20221230065427.944586-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/fotg210/fotg210-udc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/fotg210/fotg210-udc.c b/drivers/usb/fotg210/fotg210-udc.c index 66e1b7ee3346..87cca81bf4ac 100644 --- a/drivers/usb/fotg210/fotg210-udc.c +++ b/drivers/usb/fotg210/fotg210-udc.c @@ -1201,6 +1201,8 @@ int fotg210_udc_probe(struct platform_device *pdev) dev_info(dev, "found and initialized PHY\n"); } + ret = -ENOMEM; + for (i = 0; i < FOTG210_MAX_NUM_EP; i++) { fotg210->ep[i] = kzalloc(sizeof(struct fotg210_ep), GFP_KERNEL); if (!fotg210->ep[i]) From 8a758d98dba380a7d32a98b0840ad707e3036233 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 23:17:06 +0100 Subject: [PATCH 120/233] rxrpc: Stash the network namespace pointer in rxrpc_local Stash the network namespace pointer in the rxrpc_local struct in addition to a pointer to the rxrpc-specific net namespace info. Use this to remove some places where the socket is passed as a parameter. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- net/rxrpc/ar-internal.h | 10 +++++----- net/rxrpc/call_accept.c | 2 +- net/rxrpc/conn_client.c | 2 +- net/rxrpc/local_object.c | 7 ++++--- net/rxrpc/peer_object.c | 23 ++++++++++------------- 5 files changed, 21 insertions(+), 23 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 18092526d3c8..9cf763c338bc 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -283,7 +283,8 @@ struct rxrpc_local { struct rcu_head rcu; atomic_t active_users; /* Number of users of the local endpoint */ refcount_t ref; /* Number of references to the structure */ - struct rxrpc_net *rxnet; /* The network ns in which this resides */ + struct net *net; /* The network namespace */ + struct rxrpc_net *rxnet; /* Our bits in the network namespace */ struct hlist_node link; struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; @@ -1063,12 +1064,11 @@ void rxrpc_peer_keepalive_worker(struct work_struct *); */ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); -struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *, - struct sockaddr_rxrpc *, gfp_t); +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, + struct sockaddr_rxrpc *srx, gfp_t gfp); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t, enum rxrpc_peer_trace); -void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *, - struct rxrpc_peer *); +void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer); void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *, enum rxrpc_peer_trace); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index c02401656fa9..c957e4415cdc 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -280,7 +280,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, (peer_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); - rxrpc_new_incoming_peer(rx, local, peer); + rxrpc_new_incoming_peer(local, peer); } /* Now allocate and set up the connection */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 87efa0373aed..e4063c4f4bb2 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -378,7 +378,7 @@ static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx, _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp); + cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp); if (!cp->peer) goto error; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 270b63d8f37a..c0ac2fe07ec4 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -85,7 +85,7 @@ static long rxrpc_local_cmp_key(const struct rxrpc_local *local, /* * Allocate a new local endpoint. */ -static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, +static struct rxrpc_local *rxrpc_alloc_local(struct net *net, const struct sockaddr_rxrpc *srx) { struct rxrpc_local *local; @@ -94,7 +94,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, if (local) { refcount_set(&local->ref, 1); atomic_set(&local->active_users, 1); - local->rxnet = rxnet; + local->net = net; + local->rxnet = rxrpc_net(net); INIT_HLIST_NODE(&local->link); init_rwsem(&local->defrag_sem); init_completion(&local->io_thread_ready); @@ -248,7 +249,7 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, goto found; } - local = rxrpc_alloc_local(rxnet, srx); + local = rxrpc_alloc_local(net, srx); if (!local) goto nomem; diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 4eecea2be307..8d7a715a0bb1 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -147,10 +147,10 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, * assess the MTU size for the network interface through which this peer is * reached */ -static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx, +static void rxrpc_assess_MTU_size(struct rxrpc_local *local, struct rxrpc_peer *peer) { - struct net *net = sock_net(&rx->sk); + struct net *net = local->net; struct dst_entry *dst; struct rtable *rt; struct flowi fl; @@ -236,11 +236,11 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp, /* * Initialise peer record. */ -static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer, +static void rxrpc_init_peer(struct rxrpc_local *local, struct rxrpc_peer *peer, unsigned long hash_key) { peer->hash_key = hash_key; - rxrpc_assess_MTU_size(rx, peer); + rxrpc_assess_MTU_size(local, peer); peer->mtu = peer->if_mtu; peer->rtt_last_req = ktime_get_real(); @@ -272,8 +272,7 @@ static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer, /* * Set up a new peer. */ -static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, - struct rxrpc_local *local, +static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, unsigned long hash_key, gfp_t gfp) @@ -285,7 +284,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, peer = rxrpc_alloc_peer(local, gfp, rxrpc_peer_new_client); if (peer) { memcpy(&peer->srx, srx, sizeof(*srx)); - rxrpc_init_peer(rx, peer, hash_key); + rxrpc_init_peer(local, peer, hash_key); } _leave(" = %p", peer); @@ -304,14 +303,13 @@ static void rxrpc_free_peer(struct rxrpc_peer *peer) * since we've already done a search in the list from the non-reentrant context * (the data_ready handler) that is the only place we can add new peers. */ -void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, - struct rxrpc_peer *peer) +void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) { struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key; hash_key = rxrpc_peer_hash_key(local, &peer->srx); - rxrpc_init_peer(rx, peer, hash_key); + rxrpc_init_peer(local, peer, hash_key); spin_lock(&rxnet->peer_hash_lock); hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); @@ -322,8 +320,7 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, /* * obtain a remote transport endpoint for the specified address */ -struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, - struct rxrpc_local *local, +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp) { struct rxrpc_peer *peer, *candidate; @@ -343,7 +340,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, /* The peer is not yet present in hash - create a candidate * for a new record and then redo the search. */ - candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp); + candidate = rxrpc_create_peer(local, srx, hash_key, gfp); if (!candidate) { _leave(" = NULL [nomem]"); return NULL; From 5040011d073d3acdeb58af2b64f84e33bb03abd2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Nov 2022 10:24:29 +0000 Subject: [PATCH 121/233] rxrpc: Make the local endpoint hold a ref on a connected call Make the local endpoint and it's I/O thread hold a reference on a connected call until that call is disconnected. Without this, we're reliant on either the AF_RXRPC socket to hold a ref (which is dropped when the call is released) or a queued work item to hold a ref (the work item is being replaced with the I/O thread). Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 3 +++ net/rxrpc/call_object.c | 2 ++ net/rxrpc/conn_client.c | 6 +++--- net/rxrpc/conn_object.c | 25 +++++++++++++++---------- 4 files changed, 23 insertions(+), 13 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 5f9dd7389536..b526d982da7e 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -148,6 +148,7 @@ E_(rxrpc_client_to_idle, "->Idle") #define rxrpc_call_traces \ + EM(rxrpc_call_get_io_thread, "GET iothread") \ EM(rxrpc_call_get_input, "GET input ") \ EM(rxrpc_call_get_kernel_service, "GET krnl-srv") \ EM(rxrpc_call_get_notify_socket, "GET notify ") \ @@ -160,6 +161,7 @@ EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ EM(rxrpc_call_put_discard_error, "PUT disc-err") \ + EM(rxrpc_call_put_io_thread, "PUT iothread") \ EM(rxrpc_call_put_input, "PUT input ") \ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ @@ -173,6 +175,7 @@ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ EM(rxrpc_call_see_connected, "SEE connect ") \ + EM(rxrpc_call_see_disconnected, "SEE disconn ") \ EM(rxrpc_call_see_distribute_error, "SEE dist-err") \ EM(rxrpc_call_see_input, "SEE input ") \ EM(rxrpc_call_see_release, "SEE release ") \ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 89dcf60b1158..239fc3c75079 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -453,6 +453,8 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, BUG(); } + rxrpc_get_call(call, rxrpc_call_get_io_thread); + /* Set the channel for this call. We don't get channel_lock as we're * only defending against the data_ready handler (which we're called * from) and the RESPONSE packet parser (which is only really diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index e4063c4f4bb2..1edd65883c55 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -725,8 +725,11 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper); + rxrpc_get_call(call, rxrpc_call_get_io_thread); + bundle = rxrpc_prep_call(rx, call, cp, srx, gfp); if (IS_ERR(bundle)) { + rxrpc_put_call(call, rxrpc_call_get_io_thread); ret = PTR_ERR(bundle); goto out; } @@ -820,7 +823,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call _enter("c=%x", call->debug_id); spin_lock(&bundle->channel_lock); - set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); /* Calls that have never actually been assigned a channel can simply be * discarded. @@ -912,8 +914,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call out: spin_unlock(&bundle->channel_lock); - _leave(""); - return; } /* diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 3c8f83dacb2b..2bd3f6288895 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -178,6 +178,9 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + rxrpc_see_call(call, rxrpc_call_see_disconnected); + call->peer->cong_ssthresh = call->cong_ssthresh; if (!hlist_unhashed(&call->error_link)) { @@ -186,18 +189,20 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) spin_unlock(&call->peer->lock); } - if (rxrpc_is_client_call(call)) - return rxrpc_disconnect_client_call(conn->bundle, call); + if (rxrpc_is_client_call(call)) { + rxrpc_disconnect_client_call(conn->bundle, call); + } else { + spin_lock(&conn->bundle->channel_lock); + __rxrpc_disconnect_call(conn, call); + spin_unlock(&conn->bundle->channel_lock); - spin_lock(&conn->bundle->channel_lock); - __rxrpc_disconnect_call(conn, call); - spin_unlock(&conn->bundle->channel_lock); + conn->idle_timestamp = jiffies; + if (atomic_dec_and_test(&conn->active)) + rxrpc_set_service_reap_timer(conn->rxnet, + jiffies + rxrpc_connection_expiry); + } - set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); - conn->idle_timestamp = jiffies; - if (atomic_dec_and_test(&conn->active)) - rxrpc_set_service_reap_timer(conn->rxnet, - jiffies + rxrpc_connection_expiry); + rxrpc_put_call(call, rxrpc_call_put_io_thread); } /* From 30df927b936b2ef21eb07dce9c141c7897609643 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 8 Oct 2022 14:33:50 +0100 Subject: [PATCH 122/233] rxrpc: Separate call retransmission from other conn events Call the rxrpc_conn_retransmit_call() directly from rxrpc_input_packet() rather than calling it via connection event handling. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- net/rxrpc/ar-internal.h | 2 ++ net/rxrpc/conn_event.c | 34 +++++----------------------------- net/rxrpc/io_thread.c | 2 +- 3 files changed, 8 insertions(+), 30 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 9cf763c338bc..f3b8806e7241 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -897,6 +897,8 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *); /* * conn_event.c */ +void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb, + unsigned int channel); void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 480364bcbf85..dfd29882126f 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -19,9 +19,9 @@ /* * Retransmit terminal ACK or ABORT of the previous call. */ -static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, - struct sk_buff *skb, - unsigned int channel) +void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, + struct sk_buff *skb, + unsigned int channel) { struct rxrpc_skb_priv *sp = skb ? rxrpc_skb(skb) : NULL; struct rxrpc_channel *chan; @@ -292,24 +292,6 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); switch (sp->hdr.type) { - case RXRPC_PACKET_TYPE_DATA: - case RXRPC_PACKET_TYPE_ACK: - rxrpc_conn_retransmit_call(conn, skb, - sp->hdr.cid & RXRPC_CHANNELMASK); - return 0; - - case RXRPC_PACKET_TYPE_BUSY: - /* Just ignore BUSY packets for now. */ - return 0; - - case RXRPC_PACKET_TYPE_ABORT: - conn->error = -ECONNABORTED; - conn->abort_code = skb->priority; - conn->state = RXRPC_CONN_REMOTELY_ABORTED; - set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); - return -ECONNABORTED; - case RXRPC_PACKET_TYPE_CHALLENGE: return conn->security->respond_to_challenge(conn, skb, _abort_code); @@ -504,18 +486,12 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { _leave(" = -ECONNABORTED [%u]", conn->state); - return -ECONNABORTED; + return 0; } _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); switch (sp->hdr.type) { - case RXRPC_PACKET_TYPE_DATA: - case RXRPC_PACKET_TYPE_ACK: - rxrpc_conn_retransmit_call(conn, skb, - sp->hdr.cid & RXRPC_CHANNELMASK); - return 0; - case RXRPC_PACKET_TYPE_BUSY: /* Just ignore BUSY packets for now. */ return 0; @@ -526,7 +502,7 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) conn->state = RXRPC_CONN_REMOTELY_ABORTED; set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); - return -ECONNABORTED; + return 0; case RXRPC_PACKET_TYPE_CHALLENGE: case RXRPC_PACKET_TYPE_RESPONSE: diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 1ad067d66fb6..0e1a548d35f8 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -358,7 +358,7 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, sp->hdr.seq, sp->hdr.serial, sp->hdr.flags); - rxrpc_input_conn_packet(conn, skb); + rxrpc_conn_retransmit_call(conn, skb, channel); return 0; } From a343b174b4bdde851033996960bca5ad1394d04b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 Oct 2022 22:17:56 +0100 Subject: [PATCH 123/233] rxrpc: Only set/transmit aborts in the I/O thread Only set the abort call completion state in the I/O thread and only transmit ABORT packets from there. rxrpc_abort_call() can then be made to actually send the packet. Further, ABORT packets should only be sent if the call has been exposed to the network (ie. at least one attempted DATA transmission has occurred for it). Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 1 + net/rxrpc/ar-internal.h | 7 ++++++- net/rxrpc/call_event.c | 16 +++++++++++++--- net/rxrpc/call_object.c | 7 ++++--- net/rxrpc/input.c | 6 ++---- net/rxrpc/recvmsg.c | 2 ++ net/rxrpc/sendmsg.c | 29 ++++++++++++++++++++++------- 7 files changed, 50 insertions(+), 18 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index b526d982da7e..c44cc01de750 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -17,6 +17,7 @@ * Declare tracing information enums and their string mappings for display. */ #define rxrpc_call_poke_traces \ + EM(rxrpc_call_poke_abort, "Abort") \ EM(rxrpc_call_poke_error, "Error") \ EM(rxrpc_call_poke_idle, "Idle") \ EM(rxrpc_call_poke_start, "Start") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index f3b8806e7241..0cf28a56aec5 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -625,7 +625,10 @@ struct rxrpc_call { unsigned long events; spinlock_t notify_lock; /* Kernel notification lock */ rwlock_t state_lock; /* lock for state transition */ - u32 abort_code; /* Local/remote abort code */ + const char *send_abort_why; /* String indicating why the abort was sent */ + s32 send_abort; /* Abort code to be sent */ + short send_abort_err; /* Error to be associated with the abort */ + s32 abort_code; /* Local/remote abort code */ int error; /* Local error incurred */ enum rxrpc_call_state state; /* current state of call */ enum rxrpc_call_completion completion; /* Call completion condition */ @@ -1146,6 +1149,8 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *, /* * sendmsg.c */ +bool rxrpc_propose_abort(struct rxrpc_call *call, + u32 abort_code, int error, const char *why); int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); /* diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index b2cf448fb02c..b7efecf5ccfc 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -270,9 +270,11 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) { struct rxrpc_txbuf *txb; - if (rxrpc_is_client_call(call) && - !test_bit(RXRPC_CALL_EXPOSED, &call->flags)) + if (!test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { + if (list_empty(&call->tx_sendmsg)) + return; rxrpc_expose_client_call(call); + } while ((txb = list_first_entry_or_null(&call->tx_sendmsg, struct rxrpc_txbuf, call_link))) { @@ -336,6 +338,7 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) unsigned long now, next, t; rxrpc_serial_t ackr_serial; bool resend = false, expired = false; + s32 abort_code; rxrpc_see_call(call, rxrpc_call_see_input); @@ -346,6 +349,14 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) if (call->state == RXRPC_CALL_COMPLETE) goto out; + /* Handle abort request locklessly, vs rxrpc_propose_abort(). */ + abort_code = smp_load_acquire(&call->send_abort); + if (abort_code) { + rxrpc_abort_call(call->send_abort_why, call, 0, call->send_abort, + call->send_abort_err); + goto out; + } + if (skb && skb->mark == RXRPC_SKB_MARK_ERROR) goto out; @@ -433,7 +444,6 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) } else { rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME); } - rxrpc_send_abort_packet(call); goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 239fc3c75079..298b7c465d7e 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -430,6 +430,8 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, call->state = RXRPC_CALL_SERVER_SECURING; call->cong_tstamp = skb->tstamp; + __set_bit(RXRPC_CALL_EXPOSED, &call->flags); + spin_lock(&conn->state_lock); switch (conn->state) { @@ -590,7 +592,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) call = list_entry(rx->to_be_accepted.next, struct rxrpc_call, accept_link); list_del(&call->accept_link); - rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET); + rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, "SKR"); rxrpc_put_call(call, rxrpc_call_put_release_sock_tba); } @@ -598,8 +600,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) call = list_entry(rx->sock_calls.next, struct rxrpc_call, sock_link); rxrpc_get_call(call, rxrpc_call_get_release_sock); - rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET); - rxrpc_send_abort_packet(call); + rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, "SKT"); rxrpc_release_call(rx, call); rxrpc_put_call(call, rxrpc_call_put_release_sock); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index d0e20e946e48..1f03a286620d 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -12,8 +12,7 @@ static void rxrpc_proto_abort(const char *why, struct rxrpc_call *call, rxrpc_seq_t seq) { - if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) - rxrpc_send_abort_packet(call); + rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG); } /* @@ -1007,8 +1006,7 @@ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_CALL_COMPLETE: break; default: - if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) - rxrpc_send_abort_packet(call); + rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN); trace_rxrpc_improper_term(call); break; } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 6ebd6440a2b7..a4ccdc006d0f 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -134,6 +134,8 @@ bool rxrpc_abort_call(const char *why, struct rxrpc_call *call, write_lock(&call->state_lock); ret = __rxrpc_abort_call(why, call, seq, abort_code, error); write_unlock(&call->state_lock); + if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags)) + rxrpc_send_abort_packet(call); return ret; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index cde1e65f16b4..dc3c2a834fc8 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -17,6 +17,26 @@ #include #include "ar-internal.h" +/* + * Propose an abort to be made in the I/O thread. + */ +bool rxrpc_propose_abort(struct rxrpc_call *call, + u32 abort_code, int error, const char *why) +{ + _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why); + + if (!call->send_abort && call->state < RXRPC_CALL_COMPLETE) { + call->send_abort_why = why; + call->send_abort_err = error; + /* Request abort locklessly vs rxrpc_input_call_event(). */ + smp_store_release(&call->send_abort, abort_code); + rxrpc_poke_call(call, rxrpc_call_poke_abort); + return true; + } + + return false; +} + /* * Return true if there's sufficient Tx queue space. */ @@ -663,9 +683,8 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) /* it's too late for this call */ ret = -ESHUTDOWN; } else if (p.command == RXRPC_CMD_SEND_ABORT) { + rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED, "CMD"); ret = 0; - if (rxrpc_abort_call("CMD", call, 0, p.abort_code, -ECONNABORTED)) - ret = rxrpc_send_abort_packet(call); } else if (p.command != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; } else { @@ -760,11 +779,7 @@ bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why); mutex_lock(&call->user_mutex); - - aborted = rxrpc_abort_call(why, call, 0, abort_code, error); - if (aborted) - rxrpc_send_abort_packet(call); - + aborted = rxrpc_propose_abort(call, abort_code, error, why); mutex_unlock(&call->user_mutex); return aborted; } From 03fc55adf8761c546d72798264b019c9f672c578 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 Oct 2022 17:01:25 +0100 Subject: [PATCH 124/233] rxrpc: Only disconnect calls in the I/O thread Only perform call disconnection in the I/O thread to reduce the locking requirement. This is the first part of a fix for a race that exists between call connection and call disconnection whereby the data transmission code adds the call to the peer error distribution list after the call has been disconnected (say by the rxrpc socket getting closed). The fix is to complete the process of moving call connection, data transmission and call disconnection into the I/O thread and thus forcibly serialising them. Note that the issue may predate the overhaul to an I/O thread model that were included in the merge window for v6.2, but the timing is very much changed by the change given below. Fixes: cf37b5987508 ("rxrpc: Move DATA transmission into call processor work item") Reported-by: syzbot+c22650d2844392afdcfd@syzkaller.appspotmail.com Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 1 + net/rxrpc/call_event.c | 7 ++++++- net/rxrpc/call_object.c | 9 +-------- net/rxrpc/input.c | 6 ------ net/rxrpc/recvmsg.c | 1 + 5 files changed, 9 insertions(+), 15 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index c44cc01de750..eac513668e33 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -18,6 +18,7 @@ */ #define rxrpc_call_poke_traces \ EM(rxrpc_call_poke_abort, "Abort") \ + EM(rxrpc_call_poke_complete, "Compl") \ EM(rxrpc_call_poke_error, "Error") \ EM(rxrpc_call_poke_idle, "Idle") \ EM(rxrpc_call_poke_start, "Start") \ diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index b7efecf5ccfc..b2fc3fa686ec 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -484,8 +484,13 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) } out: - if (call->state == RXRPC_CALL_COMPLETE) + if (call->state == RXRPC_CALL_COMPLETE) { del_timer_sync(&call->timer); + if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) + rxrpc_disconnect_call(call); + if (call->security) + call->security->free_call_crypto(call); + } if (call->acks_hard_ack != call->tx_bottom) rxrpc_shrink_call_tx_buffer(call); _leave(""); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 298b7c465d7e..13aac3ca03a0 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -50,7 +50,7 @@ void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) struct rxrpc_local *local = call->local; bool busy; - if (call->state < RXRPC_CALL_COMPLETE) { + if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) { spin_lock_bh(&local->lock); busy = !list_empty(&call->attend_link); trace_rxrpc_poke_call(call, busy, what); @@ -533,13 +533,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), call->flags, rxrpc_call_see_release); - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); - if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags)) BUG(); rxrpc_put_call_slot(call); - del_timer_sync(&call->timer); /* Make sure we don't get any more notifications */ write_lock(&rx->recvmsg_lock); @@ -572,10 +569,6 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); - if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) - rxrpc_disconnect_call(call); - if (call->security) - call->security->free_call_crypto(call); _leave(""); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 1f03a286620d..bb4beb445325 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -997,8 +997,6 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) */ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) { - struct rxrpc_connection *conn = call->conn; - switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); @@ -1012,8 +1010,4 @@ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) } rxrpc_input_call_event(call, skb); - - spin_lock(&conn->bundle->channel_lock); - __rxrpc_disconnect_call(conn, call); - spin_unlock(&conn->bundle->channel_lock); } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index a4ccdc006d0f..8d5fe65f5951 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -201,6 +201,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) case RXRPC_CALL_CLIENT_RECV_REPLY: __rxrpc_call_completed(call); write_unlock(&call->state_lock); + rxrpc_poke_call(call, rxrpc_call_poke_complete); break; case RXRPC_CALL_SERVER_RECV_REQUEST: From f2cce89a074e6d2991dddc94f6b6ebe1576b8459 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 09:08:34 +0100 Subject: [PATCH 125/233] rxrpc: Implement a mechanism to send an event notification to a connection Provide a means by which an event notification can be sent to a connection through such that the I/O thread can pick it up and handle it rather than doing it in a separate workqueue. This is then used to move the deferred final ACK of a call into the I/O thread rather than a separate work queue as part of the drive to do all transmission from the I/O thread. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 5 ++--- net/rxrpc/ar-internal.h | 5 +++++ net/rxrpc/conn_event.c | 14 ++++++++++---- net/rxrpc/conn_object.c | 20 +++++++++++++++++++- net/rxrpc/io_thread.c | 19 ++++++++++++++++++- net/rxrpc/local_object.c | 1 + 6 files changed, 55 insertions(+), 9 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index eac513668e33..b969756f97fc 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -111,7 +111,7 @@ EM(rxrpc_conn_get_call_input, "GET inp-call") \ EM(rxrpc_conn_get_conn_input, "GET inp-conn") \ EM(rxrpc_conn_get_idle, "GET idle ") \ - EM(rxrpc_conn_get_poke, "GET poke ") \ + EM(rxrpc_conn_get_poke_timer, "GET poke ") \ EM(rxrpc_conn_get_service_conn, "GET svc-conn") \ EM(rxrpc_conn_new_client, "NEW client ") \ EM(rxrpc_conn_new_service, "NEW service ") \ @@ -126,10 +126,9 @@ EM(rxrpc_conn_put_service_reaped, "PUT svc-reap") \ EM(rxrpc_conn_put_unbundle, "PUT unbundle") \ EM(rxrpc_conn_put_unidle, "PUT unidle ") \ + EM(rxrpc_conn_put_work, "PUT work ") \ EM(rxrpc_conn_queue_challenge, "QUE chall ") \ - EM(rxrpc_conn_queue_retry_work, "QUE retry-wk") \ EM(rxrpc_conn_queue_rx_work, "QUE rx-work ") \ - EM(rxrpc_conn_queue_timer, "QUE timer ") \ EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \ EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \ E_(rxrpc_conn_see_work, "SEE work ") diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 0cf28a56aec5..d82d7f36cdaa 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -202,6 +202,7 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { + struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ u16 offset; /* Offset of data */ u16 len; /* Length of data */ u8 flags; @@ -292,6 +293,7 @@ struct rxrpc_local { struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head rx_queue; /* Received packets */ + struct list_head conn_attend_q; /* Conns requiring immediate attention */ struct list_head call_attend_q; /* Calls requiring immediate attention */ struct rb_root client_bundles; /* Client connection bundles by socket params */ spinlock_t client_bundles_lock; /* Lock for client_bundles */ @@ -441,6 +443,7 @@ struct rxrpc_connection { struct rxrpc_peer *peer; /* Remote endpoint */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ struct key *key; /* Security details */ + struct list_head attend_link; /* Link in local->conn_attend_q */ refcount_t ref; atomic_t active; /* Active count for service conns */ @@ -905,6 +908,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *s void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); +void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb); /* * conn_object.c @@ -912,6 +916,7 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); extern unsigned int rxrpc_connection_expiry; extern unsigned int rxrpc_closed_conn_expiry; +void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why); struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t); struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *, struct sockaddr_rxrpc *, diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index dfd29882126f..7a980a32344f 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -412,10 +412,6 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn) if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events)) rxrpc_secure_connection(conn); - /* Process delayed ACKs whose time has come. */ - if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) - rxrpc_process_delayed_final_acks(conn, false); - /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { @@ -515,3 +511,13 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) return -EPROTO; } } + +/* + * Input a connection event. + */ +void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb) +{ + /* Process delayed ACKs whose time has come. */ + if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) + rxrpc_process_delayed_final_acks(conn, false); +} diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 2bd3f6288895..281f59e356f5 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -23,12 +23,30 @@ static void rxrpc_clean_up_connection(struct work_struct *work); static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, unsigned long reap_at); +void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) +{ + struct rxrpc_local *local = conn->local; + bool busy; + + if (WARN_ON_ONCE(!local)) + return; + + spin_lock_bh(&local->lock); + busy = !list_empty(&conn->attend_link); + if (!busy) { + rxrpc_get_connection(conn, why); + list_add_tail(&conn->attend_link, &local->conn_attend_q); + } + spin_unlock_bh(&local->lock); + rxrpc_wake_up_io_thread(local); +} + static void rxrpc_connection_timer(struct timer_list *timer) { struct rxrpc_connection *conn = container_of(timer, struct rxrpc_connection, timer); - rxrpc_queue_conn(conn, rxrpc_conn_queue_timer); + rxrpc_poke_conn(conn, rxrpc_conn_get_poke_timer); } /* diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 0e1a548d35f8..46e58cf5bc96 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -421,6 +421,7 @@ reject_packet: */ int rxrpc_io_thread(void *data) { + struct rxrpc_connection *conn; struct sk_buff_head rx_queue; struct rxrpc_local *local = data; struct rxrpc_call *call; @@ -436,6 +437,20 @@ int rxrpc_io_thread(void *data) for (;;) { rxrpc_inc_stat(local->rxnet, stat_io_loop); + /* Deal with connections that want immediate attention. */ + conn = list_first_entry_or_null(&local->conn_attend_q, + struct rxrpc_connection, + attend_link); + if (conn) { + spin_lock_bh(&local->lock); + list_del_init(&conn->attend_link); + spin_unlock_bh(&local->lock); + + rxrpc_input_conn_event(conn, NULL); + rxrpc_put_connection(conn, rxrpc_conn_put_poke); + continue; + } + /* Deal with calls that want immediate attention. */ if ((call = list_first_entry_or_null(&local->call_attend_q, struct rxrpc_call, @@ -463,6 +478,7 @@ int rxrpc_io_thread(void *data) rxrpc_input_error(local, skb); rxrpc_free_skb(skb, rxrpc_skb_put_error_report); break; + break; default: WARN_ON_ONCE(1); rxrpc_free_skb(skb, rxrpc_skb_put_unknown); @@ -481,7 +497,8 @@ int rxrpc_io_thread(void *data) set_current_state(TASK_INTERRUPTIBLE); should_stop = kthread_should_stop(); if (!skb_queue_empty(&local->rx_queue) || - !list_empty(&local->call_attend_q)) { + !list_empty(&local->call_attend_q) || + !list_empty(&local->conn_attend_q)) { __set_current_state(TASK_RUNNING); continue; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index c0ac2fe07ec4..8ef6cd8defa4 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -100,6 +100,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net, init_rwsem(&local->defrag_sem); init_completion(&local->io_thread_ready); skb_queue_head_init(&local->rx_queue); + INIT_LIST_HEAD(&local->conn_attend_q); INIT_LIST_HEAD(&local->call_attend_q); local->client_bundles = RB_ROOT; spin_lock_init(&local->client_bundles_lock); From a00ce28b1778fa3576575b43bdb17f60ded38b66 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 09:56:36 +0100 Subject: [PATCH 126/233] rxrpc: Clean up connection abort Clean up connection abort, using the connection state_lock to gate access to change that state, and use an rxrpc_call_completion value to indicate the difference between local and remote aborts as these can be pasted directly into the call state. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 2 + net/rxrpc/ar-internal.h | 46 ++++--- net/rxrpc/call_object.c | 8 +- net/rxrpc/conn_event.c | 233 ++++++++++++----------------------- net/rxrpc/insecure.c | 18 +-- net/rxrpc/output.c | 56 +++++++++ net/rxrpc/proc.c | 10 +- net/rxrpc/rxkad.c | 28 ++--- 8 files changed, 188 insertions(+), 213 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index b969756f97fc..222d0498d23f 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -111,6 +111,7 @@ EM(rxrpc_conn_get_call_input, "GET inp-call") \ EM(rxrpc_conn_get_conn_input, "GET inp-conn") \ EM(rxrpc_conn_get_idle, "GET idle ") \ + EM(rxrpc_conn_get_poke_abort, "GET pk-abort") \ EM(rxrpc_conn_get_poke_timer, "GET poke ") \ EM(rxrpc_conn_get_service_conn, "GET svc-conn") \ EM(rxrpc_conn_new_client, "NEW client ") \ @@ -128,6 +129,7 @@ EM(rxrpc_conn_put_unidle, "PUT unidle ") \ EM(rxrpc_conn_put_work, "PUT work ") \ EM(rxrpc_conn_queue_challenge, "QUE chall ") \ + EM(rxrpc_conn_queue_retry_work, "QUE retry-wk") \ EM(rxrpc_conn_queue_rx_work, "QUE rx-work ") \ EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \ EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index d82d7f36cdaa..78bd6fb0bc15 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -263,13 +263,11 @@ struct rxrpc_security { /* respond to a challenge */ int (*respond_to_challenge)(struct rxrpc_connection *, - struct sk_buff *, - u32 *); + struct sk_buff *); /* verify a response */ int (*verify_response)(struct rxrpc_connection *, - struct sk_buff *, - u32 *); + struct sk_buff *); /* clear connection security */ void (*clear)(struct rxrpc_connection *); @@ -367,6 +365,18 @@ struct rxrpc_conn_parameters { u32 security_level; /* Security level selected */ }; +/* + * Call completion condition (state == RXRPC_CALL_COMPLETE). + */ +enum rxrpc_call_completion { + RXRPC_CALL_SUCCEEDED, /* - Normal termination */ + RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ + RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ + RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ + RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ + NR__RXRPC_CALL_COMPLETIONS +}; + /* * Bits in the connection flags. */ @@ -391,6 +401,7 @@ enum rxrpc_conn_flag { */ enum rxrpc_conn_event { RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */ + RXRPC_CONN_EV_ABORT_CALLS, /* Abort attached calls */ }; /* @@ -403,8 +414,7 @@ enum rxrpc_conn_proto_state { RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */ RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */ RXRPC_CONN_SERVICE, /* Service secured connection */ - RXRPC_CONN_REMOTELY_ABORTED, /* Conn aborted by peer */ - RXRPC_CONN_LOCALLY_ABORTED, /* Conn aborted locally */ + RXRPC_CONN_ABORTED, /* Conn aborted */ RXRPC_CONN__NR_STATES }; @@ -487,7 +497,8 @@ struct rxrpc_connection { unsigned long idle_timestamp; /* Time at which last became idle */ spinlock_t state_lock; /* state-change lock */ enum rxrpc_conn_proto_state state; /* current state of connection */ - u32 abort_code; /* Abort code of connection abort */ + enum rxrpc_call_completion completion; /* Completion condition */ + s32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ atomic_t serial; /* packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ @@ -561,18 +572,6 @@ enum rxrpc_call_state { NR__RXRPC_CALL_STATES }; -/* - * Call completion condition (state == RXRPC_CALL_COMPLETE). - */ -enum rxrpc_call_completion { - RXRPC_CALL_SUCCEEDED, /* - Normal termination */ - RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ - RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ - RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ - RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ - NR__RXRPC_CALL_COMPLETIONS -}; - /* * Call Tx congestion management modes. */ @@ -905,11 +904,19 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *); */ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb, unsigned int channel); +int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, + s32 abort_code, int err, const char *why); void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb); +static inline bool rxrpc_is_conn_aborted(const struct rxrpc_connection *conn) +{ + /* Order reading the abort info after the state check. */ + return smp_load_acquire(&conn->state) == RXRPC_CONN_ABORTED; +} + /* * conn_object.c */ @@ -1059,6 +1066,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); +void rxrpc_send_conn_abort(struct rxrpc_connection *conn); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 13aac3ca03a0..666430182dfd 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -443,14 +443,10 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, call->state = RXRPC_CALL_SERVER_RECV_REQUEST; break; - case RXRPC_CONN_REMOTELY_ABORTED: - __rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, + case RXRPC_CONN_ABORTED: + __rxrpc_set_call_completion(call, conn->completion, conn->abort_code, conn->error); break; - case RXRPC_CONN_LOCALLY_ABORTED: - __rxrpc_abort_call("CON", call, 1, - conn->abort_code, conn->error); - break; default: BUG(); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 7a980a32344f..753d91a9646f 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -16,6 +16,60 @@ #include #include "ar-internal.h" +/* + * Set the completion state on an aborted connection. + */ +static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff *skb, + s32 abort_code, int err, + enum rxrpc_call_completion compl) +{ + bool aborted = false; + + if (conn->state != RXRPC_CONN_ABORTED) { + spin_lock(&conn->state_lock); + if (conn->state != RXRPC_CONN_ABORTED) { + conn->abort_code = abort_code; + conn->error = err; + conn->completion = compl; + /* Order the abort info before the state change. */ + smp_store_release(&conn->state, RXRPC_CONN_ABORTED); + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); + set_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events); + aborted = true; + } + spin_unlock(&conn->state_lock); + } + + return aborted; +} + +/* + * Mark a socket buffer to indicate that the connection it's on should be aborted. + */ +int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, + s32 abort_code, int err, const char *why) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + if (rxrpc_set_conn_aborted(conn, skb, abort_code, err, + RXRPC_CALL_LOCALLY_ABORTED)) { + trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber, + sp->hdr.seq, abort_code, err); + rxrpc_poke_conn(conn, rxrpc_conn_get_poke_abort); + } + return -EPROTO; +} + +/* + * Mark a connection as being remotely aborted. + */ +static bool rxrpc_input_conn_abort(struct rxrpc_connection *conn, + struct sk_buff *skb) +{ + return rxrpc_set_conn_aborted(conn, skb, skb->priority, -ECONNABORTED, + RXRPC_CALL_REMOTELY_ABORTED); +} + /* * Retransmit terminal ACK or ABORT of the previous call. */ @@ -146,9 +200,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, /* * pass a connection-level abort onto all calls on that connection */ -static void rxrpc_abort_calls(struct rxrpc_connection *conn, - enum rxrpc_call_completion compl, - rxrpc_serial_t serial) +static void rxrpc_abort_calls(struct rxrpc_connection *conn) { struct rxrpc_call *call; int i; @@ -161,102 +213,17 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, call = rcu_dereference_protected( conn->channels[i].call, lockdep_is_held(&conn->bundle->channel_lock)); - if (call) { - if (compl == RXRPC_CALL_LOCALLY_ABORTED) - trace_rxrpc_abort(call->debug_id, - "CON", call->cid, - call->call_id, 0, + if (call) + rxrpc_set_call_completion(call, + conn->completion, conn->abort_code, conn->error); - else - trace_rxrpc_rx_abort(call, serial, - conn->abort_code); - rxrpc_set_call_completion(call, compl, - conn->abort_code, - conn->error); - } } spin_unlock(&conn->bundle->channel_lock); _leave(""); } -/* - * generate a connection-level abort - */ -static int rxrpc_abort_connection(struct rxrpc_connection *conn, - int error, u32 abort_code) -{ - struct rxrpc_wire_header whdr; - struct msghdr msg; - struct kvec iov[2]; - __be32 word; - size_t len; - u32 serial; - int ret; - - _enter("%d,,%u,%u", conn->debug_id, error, abort_code); - - /* generate a connection-level abort */ - spin_lock(&conn->state_lock); - if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { - spin_unlock(&conn->state_lock); - _leave(" = 0 [already dead]"); - return 0; - } - - conn->error = error; - conn->abort_code = abort_code; - conn->state = RXRPC_CONN_LOCALLY_ABORTED; - set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - spin_unlock(&conn->state_lock); - - msg.msg_name = &conn->peer->srx.transport; - msg.msg_namelen = conn->peer->srx.transport_len; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; - - whdr.epoch = htonl(conn->proto.epoch); - whdr.cid = htonl(conn->proto.cid); - whdr.callNumber = 0; - whdr.seq = 0; - whdr.type = RXRPC_PACKET_TYPE_ABORT; - whdr.flags = conn->out_clientflag; - whdr.userStatus = 0; - whdr.securityIndex = conn->security_ix; - whdr._rsvd = 0; - whdr.serviceId = htons(conn->service_id); - - word = htonl(conn->abort_code); - - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); - iov[1].iov_base = &word; - iov[1].iov_len = sizeof(word); - - len = iov[0].iov_len + iov[1].iov_len; - - serial = atomic_inc_return(&conn->serial); - rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial); - whdr.serial = htonl(serial); - - ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len); - if (ret < 0) { - trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_point_conn_abort); - _debug("sendmsg failed: %d", ret); - return -EAGAIN; - } - - trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort); - - conn->peer->last_tx_at = ktime_get_seconds(); - - _leave(" = 0"); - return 0; -} - /* * mark a call as being on a now-secured channel * - must be called with BH's disabled. @@ -278,26 +245,22 @@ static void rxrpc_call_is_secure(struct rxrpc_call *call) * connection-level Rx packet processor */ static int rxrpc_process_event(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); int loop, ret; - if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { - _leave(" = -ECONNABORTED [%u]", conn->state); + if (conn->state == RXRPC_CONN_ABORTED) return -ECONNABORTED; - } _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_CHALLENGE: - return conn->security->respond_to_challenge(conn, skb, - _abort_code); + return conn->security->respond_to_challenge(conn, skb); case RXRPC_PACKET_TYPE_RESPONSE: - ret = conn->security->verify_response(conn, skb, _abort_code); + ret = conn->security->verify_response(conn, skb); if (ret < 0) return ret; @@ -336,26 +299,8 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, */ static void rxrpc_secure_connection(struct rxrpc_connection *conn) { - u32 abort_code; - int ret; - - _enter("{%d}", conn->debug_id); - - ASSERT(conn->security_ix != 0); - - if (conn->security->issue_challenge(conn) < 0) { - abort_code = RX_CALL_DEAD; - ret = -ENOMEM; - goto abort; - } - - _leave(""); - return; - -abort: - _debug("abort %d, %d", ret, abort_code); - rxrpc_abort_connection(conn, ret, abort_code); - _leave(" [aborted]"); + if (conn->security->issue_challenge(conn) < 0) + rxrpc_abort_conn(conn, NULL, RX_CALL_DEAD, -ENOMEM, "OOM"); } /* @@ -406,7 +351,6 @@ again: static void rxrpc_do_process_connection(struct rxrpc_connection *conn) { struct sk_buff *skb; - u32 abort_code = RX_PROTOCOL_ERROR; int ret; if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events)) @@ -416,33 +360,18 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn) * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { rxrpc_see_skb(skb, rxrpc_skb_see_conn_work); - ret = rxrpc_process_event(conn, skb, &abort_code); + ret = rxrpc_process_event(conn, skb); switch (ret) { - case -EPROTO: - case -EKEYEXPIRED: - case -EKEYREJECTED: - goto protocol_error; case -ENOMEM: case -EAGAIN: - goto requeue_and_leave; - case -ECONNABORTED: + skb_queue_head(&conn->rx_queue, skb); + rxrpc_queue_conn(conn, rxrpc_conn_queue_retry_work); + break; default: rxrpc_free_skb(skb, rxrpc_skb_put_conn_work); break; } } - - return; - -requeue_and_leave: - skb_queue_head(&conn->rx_queue, skb); - return; - -protocol_error: - if (rxrpc_abort_connection(conn, ret, abort_code) < 0) - goto requeue_and_leave; - rxrpc_free_skb(skb, rxrpc_skb_put_conn_work); - return; } void rxrpc_process_connection(struct work_struct *work) @@ -480,28 +409,25 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { - _leave(" = -ECONNABORTED [%u]", conn->state); - return 0; - } - - _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); - switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_BUSY: /* Just ignore BUSY packets for now. */ return 0; case RXRPC_PACKET_TYPE_ABORT: - conn->error = -ECONNABORTED; - conn->abort_code = skb->priority; - conn->state = RXRPC_CONN_REMOTELY_ABORTED; - set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); - return 0; + if (rxrpc_is_conn_aborted(conn)) + return true; + rxrpc_input_conn_abort(conn, skb); + rxrpc_abort_calls(conn); + return true; case RXRPC_PACKET_TYPE_CHALLENGE: case RXRPC_PACKET_TYPE_RESPONSE: + if (rxrpc_is_conn_aborted(conn)) { + if (conn->completion == RXRPC_CALL_LOCALLY_ABORTED) + rxrpc_send_conn_abort(conn); + return true; + } rxrpc_post_packet_to_conn(conn, skb); return 0; @@ -517,6 +443,9 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) */ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb) { + if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events)) + rxrpc_abort_calls(conn); + /* Process delayed ACKs whose time has come. */ if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) rxrpc_process_delayed_final_acks(conn, false); diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 0eb8471bfc53..29dcc7d3f51a 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -43,25 +43,15 @@ static void none_free_call_crypto(struct rxrpc_call *call) } static int none_respond_to_challenge(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("chall_none")); - return -EPROTO; + return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, "RXN"); } static int none_verify_response(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("resp_none")); - return -EPROTO; + return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, "RXN"); } static void none_clear(struct rxrpc_connection *conn) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 3d8c9f830ee0..8a5ff2c9e061 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -544,6 +544,62 @@ send_fragmentable: goto done; } +/* + * Transmit a connection-level abort. + */ +void rxrpc_send_conn_abort(struct rxrpc_connection *conn) +{ + struct rxrpc_wire_header whdr; + struct msghdr msg; + struct kvec iov[2]; + __be32 word; + size_t len; + u32 serial; + int ret; + + msg.msg_name = &conn->peer->srx.transport; + msg.msg_namelen = conn->peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + whdr.epoch = htonl(conn->proto.epoch); + whdr.cid = htonl(conn->proto.cid); + whdr.callNumber = 0; + whdr.seq = 0; + whdr.type = RXRPC_PACKET_TYPE_ABORT; + whdr.flags = conn->out_clientflag; + whdr.userStatus = 0; + whdr.securityIndex = conn->security_ix; + whdr._rsvd = 0; + whdr.serviceId = htons(conn->service_id); + + word = htonl(conn->abort_code); + + iov[0].iov_base = &whdr; + iov[0].iov_len = sizeof(whdr); + iov[1].iov_base = &word; + iov[1].iov_len = sizeof(word); + + len = iov[0].iov_len + iov[1].iov_len; + + serial = atomic_inc_return(&conn->serial); + whdr.serial = htonl(serial); + + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); + ret = do_udp_sendmsg(conn->local->socket, &msg, len); + if (ret < 0) { + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_point_conn_abort); + _debug("sendmsg failed: %d", ret); + return; + } + + trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort); + + conn->peer->last_tx_at = ktime_get_seconds(); +} + /* * Reject a packet through the local endpoint. */ diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 3a59591ec061..63947cce4048 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -17,8 +17,7 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { [RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ", [RXRPC_CONN_SERVICE_CHALLENGING] = "SvChall ", [RXRPC_CONN_SERVICE] = "SvSecure", - [RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort", - [RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort", + [RXRPC_CONN_ABORTED] = "Aborted ", }; /* @@ -143,6 +142,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) { struct rxrpc_connection *conn; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + const char *state; char lbuff[50], rbuff[50]; if (v == &rxnet->conn_proc_list) { @@ -163,9 +163,11 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) } sprintf(lbuff, "%pISpc", &conn->local->srx.transport); - sprintf(rbuff, "%pISpc", &conn->peer->srx.transport); print: + state = rxrpc_is_conn_aborted(conn) ? + rxrpc_call_completions[conn->completion] : + rxrpc_conn_states[conn->state]; seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %s %3u %3d" " %s %08x %08x %08x %08x %08x %08x %08x\n", @@ -176,7 +178,7 @@ print: rxrpc_conn_is_service(conn) ? "Svc" : "Clt", refcount_read(&conn->ref), atomic_read(&conn->active), - rxrpc_conn_states[conn->state], + state, key_serial(conn->key), atomic_read(&conn->serial), conn->hi_serial, diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index d1233720e05f..5d2fbc6ec3cf 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -821,8 +821,7 @@ static int rxkad_encrypt_response(struct rxrpc_connection *conn, * respond to a challenge packet */ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { const struct rxrpc_key_token *token; struct rxkad_challenge challenge; @@ -898,7 +897,7 @@ protocol_error: trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); ret = -EPROTO; other_error: - *_abort_code = abort_code; + rxrpc_abort_conn(conn, skb, abort_code, ret, "RXK"); return ret; } @@ -910,8 +909,7 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, void *ticket, size_t ticket_len, struct rxrpc_crypt *_session_key, - time64_t *_expiry, - u32 *_abort_code) + time64_t *_expiry) { struct skcipher_request *req; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -1042,8 +1040,7 @@ bad_ticket: abort_code = RXKADBADTICKET; ret = -EPROTO; other_error: - *_abort_code = abort_code; - return ret; + return rxrpc_abort_conn(conn, skb, abort_code, ret, "RXK"); temporary_error: return ret; } @@ -1086,8 +1083,7 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn, * verify a response */ static int rxkad_verify_response(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { struct rxkad_response *response; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -1115,11 +1111,8 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, abort_code = RXKADNOAUTH; break; } - trace_rxrpc_abort(0, "SVK", - sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - abort_code, PTR_ERR(server_key)); - *_abort_code = abort_code; - return -EPROTO; + return rxrpc_abort_conn(conn, skb, abort_code, + PTR_ERR(server_key), "RXK"); } ret = -ENOMEM; @@ -1168,7 +1161,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, goto temporary_error_free_ticket; ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len, - &session_key, &expiry, _abort_code); + &session_key, &expiry); if (ret < 0) goto temporary_error_free_ticket; @@ -1246,10 +1239,9 @@ protocol_error_free: kfree(ticket); protocol_error: kfree(response); - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); key_put(server_key); - *_abort_code = abort_code; - return -EPROTO; + trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); + return rxrpc_abort_conn(conn, skb, abort_code, -EPROTO, "RXK"); temporary_error_free_ticket: kfree(ticket); From 57af281e5389b6fefedb3685f86847cbb0055f75 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2022 21:45:42 +0100 Subject: [PATCH 127/233] rxrpc: Tidy up abort generation infrastructure Tidy up the abort generation infrastructure in the following ways: (1) Create an enum and string mapping table to list the reasons an abort might be generated in tracing. (2) Replace the 3-char string with the values from (1) in the places that use that to log the abort source. This gets rid of a memcpy() in the tracepoint. (3) Subsume the rxrpc_rx_eproto tracepoint with the rxrpc_abort tracepoint and use values from (1) to indicate the trace reason. (4) Always make a call to an abort function at the point of the abort rather than stashing the values into variables and using goto to get to a place where it reported. The C optimiser will collapse the calls together as appropriate. The abort functions return a value that can be returned directly if appropriate. Note that this extends into afs also at the points where that generates an abort. To aid with this, the afs sources need to #define RXRPC_TRACE_ONLY_DEFINE_ENUMS before including the rxrpc tracing header because they don't have access to the rxrpc internal structures that some of the tracepoints make use of. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- fs/afs/cmservice.c | 6 +- fs/afs/rxrpc.c | 23 ++- include/net/af_rxrpc.h | 3 +- include/trace/events/rxrpc.h | 140 +++++++++++---- net/rxrpc/ar-internal.h | 51 +++--- net/rxrpc/call_accept.c | 43 +++-- net/rxrpc/call_event.c | 13 +- net/rxrpc/call_object.c | 6 +- net/rxrpc/conn_event.c | 19 +-- net/rxrpc/input.c | 65 ++++--- net/rxrpc/insecure.c | 6 +- net/rxrpc/io_thread.c | 163 ++++++++---------- net/rxrpc/recvmsg.c | 18 +- net/rxrpc/rxkad.c | 321 +++++++++++++++-------------------- net/rxrpc/rxperf.c | 17 +- net/rxrpc/security.c | 14 +- net/rxrpc/sendmsg.c | 20 ++- 17 files changed, 484 insertions(+), 444 deletions(-) diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 7dcd59693a0c..d4ddb20d6732 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -13,6 +13,8 @@ #include "internal.h" #include "afs_cm.h" #include "protocol_yfs.h" +#define RXRPC_TRACE_ONLY_DEFINE_ENUMS +#include static int afs_deliver_cb_init_call_back_state(struct afs_call *); static int afs_deliver_cb_init_call_back_state3(struct afs_call *); @@ -191,7 +193,7 @@ static void afs_cm_destructor(struct afs_call *call) * Abort a service call from within an action function. */ static void afs_abort_service_call(struct afs_call *call, u32 abort_code, int error, - const char *why) + enum rxrpc_abort_reason why) { rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, error, why); @@ -469,7 +471,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0) afs_send_empty_reply(call); else - afs_abort_service_call(call, 1, 1, "K-1"); + afs_abort_service_call(call, 1, 1, afs_abort_probeuuid_negative); afs_put_call(call); _leave(""); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index c62939e5ea1f..bd3830bc6700 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -13,6 +13,8 @@ #include "internal.h" #include "afs_cm.h" #include "protocol_yfs.h" +#define RXRPC_TRACE_ONLY_DEFINE_ENUMS +#include struct workqueue_struct *afs_async_calls; @@ -397,7 +399,8 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) error_do_abort: if (ret != -ECONNABORTED) { rxrpc_kernel_abort_call(call->net->socket, rxcall, - RX_USER_ABORT, ret, "KSD"); + RX_USER_ABORT, ret, + afs_abort_send_data_error); } else { len = 0; iov_iter_kvec(&msg.msg_iter, ITER_DEST, NULL, 0, 0); @@ -527,7 +530,8 @@ static void afs_deliver_to_call(struct afs_call *call) case -ENOTSUPP: abort_code = RXGEN_OPCODE; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - abort_code, ret, "KIV"); + abort_code, ret, + afs_abort_op_not_supported); goto local_abort; case -EIO: pr_err("kAFS: Call %u in bad state %u\n", @@ -542,12 +546,14 @@ static void afs_deliver_to_call(struct afs_call *call) if (state != AFS_CALL_CL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - abort_code, ret, "KUM"); + abort_code, ret, + afs_abort_unmarshal_error); goto local_abort; default: abort_code = RX_CALL_DEAD; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - abort_code, ret, "KER"); + abort_code, ret, + afs_abort_general_error); goto local_abort; } } @@ -619,7 +625,8 @@ long afs_wait_for_call_to_complete(struct afs_call *call, /* Kill off the call if it's still live. */ _debug("call interrupted"); if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - RX_USER_ABORT, -EINTR, "KWI")) + RX_USER_ABORT, -EINTR, + afs_abort_interrupted)) afs_set_call_complete(call, -EINTR, 0); } } @@ -836,7 +843,8 @@ void afs_send_empty_reply(struct afs_call *call) case -ENOMEM: _debug("oom"); rxrpc_kernel_abort_call(net->socket, call->rxcall, - RXGEN_SS_MARSHAL, -ENOMEM, "KOO"); + RXGEN_SS_MARSHAL, -ENOMEM, + afs_abort_oom); fallthrough; default: _leave(" [error]"); @@ -878,7 +886,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) if (n == -ENOMEM) { _debug("oom"); rxrpc_kernel_abort_call(net->socket, call->rxcall, - RXGEN_SS_MARSHAL, -ENOMEM, "KOO"); + RXGEN_SS_MARSHAL, -ENOMEM, + afs_abort_oom); } _leave(" [error]"); } diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index d5a5ae926380..ba717eac0229 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -15,6 +15,7 @@ struct key; struct sock; struct socket; struct rxrpc_call; +enum rxrpc_abort_reason; enum rxrpc_interruptibility { RXRPC_INTERRUPTIBLE, /* Call is interruptible */ @@ -55,7 +56,7 @@ int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *, int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *, struct iov_iter *, size_t *, bool, u32 *, u16 *); bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, - u32, int, const char *); + u32, int, enum rxrpc_abort_reason); void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 222d0498d23f..caeabd50e049 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -16,6 +16,104 @@ /* * Declare tracing information enums and their string mappings for display. */ +#define rxrpc_abort_reasons \ + /* AFS errors */ \ + EM(afs_abort_general_error, "afs-error") \ + EM(afs_abort_interrupted, "afs-intr") \ + EM(afs_abort_oom, "afs-oom") \ + EM(afs_abort_op_not_supported, "afs-op-notsupp") \ + EM(afs_abort_probeuuid_negative, "afs-probeuuid-neg") \ + EM(afs_abort_send_data_error, "afs-send-data") \ + EM(afs_abort_unmarshal_error, "afs-unmarshal") \ + /* rxperf errors */ \ + EM(rxperf_abort_general_error, "rxperf-error") \ + EM(rxperf_abort_oom, "rxperf-oom") \ + EM(rxperf_abort_op_not_supported, "rxperf-op-notsupp") \ + EM(rxperf_abort_unmarshal_error, "rxperf-unmarshal") \ + /* RxKAD security errors */ \ + EM(rxkad_abort_1_short_check, "rxkad1-short-check") \ + EM(rxkad_abort_1_short_data, "rxkad1-short-data") \ + EM(rxkad_abort_1_short_encdata, "rxkad1-short-encdata") \ + EM(rxkad_abort_1_short_header, "rxkad1-short-hdr") \ + EM(rxkad_abort_2_short_check, "rxkad2-short-check") \ + EM(rxkad_abort_2_short_data, "rxkad2-short-data") \ + EM(rxkad_abort_2_short_header, "rxkad2-short-hdr") \ + EM(rxkad_abort_2_short_len, "rxkad2-short-len") \ + EM(rxkad_abort_bad_checksum, "rxkad2-bad-cksum") \ + EM(rxkad_abort_chall_key_expired, "rxkad-chall-key-exp") \ + EM(rxkad_abort_chall_level, "rxkad-chall-level") \ + EM(rxkad_abort_chall_no_key, "rxkad-chall-nokey") \ + EM(rxkad_abort_chall_short, "rxkad-chall-short") \ + EM(rxkad_abort_chall_version, "rxkad-chall-version") \ + EM(rxkad_abort_resp_bad_callid, "rxkad-resp-bad-callid") \ + EM(rxkad_abort_resp_bad_checksum, "rxkad-resp-bad-cksum") \ + EM(rxkad_abort_resp_bad_param, "rxkad-resp-bad-param") \ + EM(rxkad_abort_resp_call_ctr, "rxkad-resp-call-ctr") \ + EM(rxkad_abort_resp_call_state, "rxkad-resp-call-state") \ + EM(rxkad_abort_resp_key_expired, "rxkad-resp-key-exp") \ + EM(rxkad_abort_resp_key_rejected, "rxkad-resp-key-rej") \ + EM(rxkad_abort_resp_level, "rxkad-resp-level") \ + EM(rxkad_abort_resp_nokey, "rxkad-resp-nokey") \ + EM(rxkad_abort_resp_ooseq, "rxkad-resp-ooseq") \ + EM(rxkad_abort_resp_short, "rxkad-resp-short") \ + EM(rxkad_abort_resp_short_tkt, "rxkad-resp-short-tkt") \ + EM(rxkad_abort_resp_tkt_aname, "rxkad-resp-tk-aname") \ + EM(rxkad_abort_resp_tkt_expired, "rxkad-resp-tk-exp") \ + EM(rxkad_abort_resp_tkt_future, "rxkad-resp-tk-future") \ + EM(rxkad_abort_resp_tkt_inst, "rxkad-resp-tk-inst") \ + EM(rxkad_abort_resp_tkt_len, "rxkad-resp-tk-len") \ + EM(rxkad_abort_resp_tkt_realm, "rxkad-resp-tk-realm") \ + EM(rxkad_abort_resp_tkt_short, "rxkad-resp-tk-short") \ + EM(rxkad_abort_resp_tkt_sinst, "rxkad-resp-tk-sinst") \ + EM(rxkad_abort_resp_tkt_sname, "rxkad-resp-tk-sname") \ + EM(rxkad_abort_resp_unknown_tkt, "rxkad-resp-unknown-tkt") \ + EM(rxkad_abort_resp_version, "rxkad-resp-version") \ + /* rxrpc errors */ \ + EM(rxrpc_abort_call_improper_term, "call-improper-term") \ + EM(rxrpc_abort_call_reset, "call-reset") \ + EM(rxrpc_abort_call_sendmsg, "call-sendmsg") \ + EM(rxrpc_abort_call_sock_release, "call-sock-rel") \ + EM(rxrpc_abort_call_sock_release_tba, "call-sock-rel-tba") \ + EM(rxrpc_abort_call_timeout, "call-timeout") \ + EM(rxrpc_abort_no_service_key, "no-serv-key") \ + EM(rxrpc_abort_nomem, "nomem") \ + EM(rxrpc_abort_service_not_offered, "serv-not-offered") \ + EM(rxrpc_abort_shut_down, "shut-down") \ + EM(rxrpc_abort_unsupported_security, "unsup-sec") \ + EM(rxrpc_badmsg_bad_abort, "bad-abort") \ + EM(rxrpc_badmsg_bad_jumbo, "bad-jumbo") \ + EM(rxrpc_badmsg_short_ack, "short-ack") \ + EM(rxrpc_badmsg_short_ack_info, "short-ack-info") \ + EM(rxrpc_badmsg_short_hdr, "short-hdr") \ + EM(rxrpc_badmsg_unsupported_packet, "unsup-pkt") \ + EM(rxrpc_badmsg_zero_call, "zero-call") \ + EM(rxrpc_badmsg_zero_seq, "zero-seq") \ + EM(rxrpc_badmsg_zero_service, "zero-service") \ + EM(rxrpc_eproto_ackr_outside_window, "ackr-out-win") \ + EM(rxrpc_eproto_ackr_sack_overflow, "ackr-sack-over") \ + EM(rxrpc_eproto_ackr_short_sack, "ackr-short-sack") \ + EM(rxrpc_eproto_ackr_zero, "ackr-zero") \ + EM(rxrpc_eproto_bad_upgrade, "bad-upgrade") \ + EM(rxrpc_eproto_data_after_last, "data-after-last") \ + EM(rxrpc_eproto_different_last, "diff-last") \ + EM(rxrpc_eproto_early_reply, "early-reply") \ + EM(rxrpc_eproto_improper_term, "improper-term") \ + EM(rxrpc_eproto_no_client_call, "no-cl-call") \ + EM(rxrpc_eproto_no_client_conn, "no-cl-conn") \ + EM(rxrpc_eproto_no_service_call, "no-sv-call") \ + EM(rxrpc_eproto_reupgrade, "re-upgrade") \ + EM(rxrpc_eproto_rxnull_challenge, "rxnull-chall") \ + EM(rxrpc_eproto_rxnull_response, "rxnull-resp") \ + EM(rxrpc_eproto_tx_rot_last, "tx-rot-last") \ + EM(rxrpc_eproto_unexpected_ack, "unex-ack") \ + EM(rxrpc_eproto_unexpected_ackall, "unex-ackall") \ + EM(rxrpc_eproto_unexpected_implicit_end, "unex-impl-end") \ + EM(rxrpc_eproto_unexpected_reply, "unex-reply") \ + EM(rxrpc_eproto_wrong_security, "wrong-sec") \ + EM(rxrpc_recvmsg_excess_data, "recvmsg-excess") \ + EM(rxrpc_recvmsg_short_data, "recvmsg-short") \ + E_(rxrpc_sendmsg_late_send, "sendmsg-late") + #define rxrpc_call_poke_traces \ EM(rxrpc_call_poke_abort, "Abort") \ EM(rxrpc_call_poke_complete, "Compl") \ @@ -382,6 +480,7 @@ #define EM(a, b) a, #define E_(a, b) a +enum rxrpc_abort_reason { rxrpc_abort_reasons } __mode(byte); enum rxrpc_bundle_trace { rxrpc_bundle_traces } __mode(byte); enum rxrpc_call_poke_trace { rxrpc_call_poke_traces } __mode(byte); enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte); @@ -410,9 +509,13 @@ enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); */ #undef EM #undef E_ + +#ifndef RXRPC_TRACE_ONLY_DEFINE_ENUMS + #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a); +rxrpc_abort_reasons; rxrpc_bundle_traces; rxrpc_call_poke_traces; rxrpc_call_traces; @@ -663,14 +766,14 @@ TRACE_EVENT(rxrpc_rx_done, ); TRACE_EVENT(rxrpc_abort, - TP_PROTO(unsigned int call_nr, const char *why, u32 cid, u32 call_id, - rxrpc_seq_t seq, int abort_code, int error), + TP_PROTO(unsigned int call_nr, enum rxrpc_abort_reason why, + u32 cid, u32 call_id, rxrpc_seq_t seq, int abort_code, int error), TP_ARGS(call_nr, why, cid, call_id, seq, abort_code, error), TP_STRUCT__entry( __field(unsigned int, call_nr ) - __array(char, why, 4 ) + __field(enum rxrpc_abort_reason, why ) __field(u32, cid ) __field(u32, call_id ) __field(rxrpc_seq_t, seq ) @@ -679,8 +782,8 @@ TRACE_EVENT(rxrpc_abort, ), TP_fast_assign( - memcpy(__entry->why, why, 4); __entry->call_nr = call_nr; + __entry->why = why; __entry->cid = cid; __entry->call_id = call_id; __entry->abort_code = abort_code; @@ -691,7 +794,8 @@ TRACE_EVENT(rxrpc_abort, TP_printk("c=%08x %08x:%08x s=%u a=%d e=%d %s", __entry->call_nr, __entry->cid, __entry->call_id, __entry->seq, - __entry->abort_code, __entry->error, __entry->why) + __entry->abort_code, __entry->error, + __print_symbolic(__entry->why, rxrpc_abort_reasons)) ); TRACE_EVENT(rxrpc_call_complete, @@ -1527,30 +1631,6 @@ TRACE_EVENT(rxrpc_improper_term, __entry->abort_code) ); -TRACE_EVENT(rxrpc_rx_eproto, - TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial, - const char *why), - - TP_ARGS(call, serial, why), - - TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_serial_t, serial ) - __field(const char *, why ) - ), - - TP_fast_assign( - __entry->call = call ? call->debug_id : 0; - __entry->serial = serial; - __entry->why = why; - ), - - TP_printk("c=%08x EPROTO %08x %s", - __entry->call, - __entry->serial, - __entry->why) - ); - TRACE_EVENT(rxrpc_connect_call, TP_PROTO(struct rxrpc_call *call), @@ -1848,6 +1928,8 @@ TRACE_EVENT(rxrpc_call_poked, #undef EM #undef E_ + +#endif /* RXRPC_TRACE_ONLY_DEFINE_ENUMS */ #endif /* _TRACE_RXRPC_H */ /* This part must be outside protection */ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 78bd6fb0bc15..120ce3ccbb22 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -627,9 +627,10 @@ struct rxrpc_call { unsigned long events; spinlock_t notify_lock; /* Kernel notification lock */ rwlock_t state_lock; /* lock for state transition */ - const char *send_abort_why; /* String indicating why the abort was sent */ + unsigned int send_abort_why; /* Why the abort [enum rxrpc_abort_reason] */ s32 send_abort; /* Abort code to be sent */ short send_abort_err; /* Error to be associated with the abort */ + rxrpc_seq_t send_abort_seq; /* DATA packet that incurred the abort (or 0) */ s32 abort_code; /* Local/remote abort code */ int error; /* Local error incurred */ enum rxrpc_call_state state; /* current state of call */ @@ -818,9 +819,11 @@ extern struct workqueue_struct *rxrpc_workqueue; */ int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); -int rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_peer *, - struct rxrpc_connection *, struct sockaddr_rxrpc *, - struct sk_buff *); +bool rxrpc_new_incoming_call(struct rxrpc_local *local, + struct rxrpc_peer *peer, + struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb); void rxrpc_accept_incoming_calls(struct rxrpc_local *); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); @@ -840,7 +843,7 @@ void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long now, enum rxrpc_timer_trace why); -void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); +bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); /* * call_object.c @@ -905,10 +908,10 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *); void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb, unsigned int channel); int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, - s32 abort_code, int err, const char *why); + s32 abort_code, int err, enum rxrpc_abort_reason why); void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); -int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); +bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb); static inline bool rxrpc_is_conn_aborted(const struct rxrpc_connection *conn) @@ -979,12 +982,19 @@ void rxrpc_implicit_end_call(struct rxrpc_call *, struct sk_buff *); */ int rxrpc_encap_rcv(struct sock *, struct sk_buff *); void rxrpc_error_report(struct sock *); +bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, + s32 abort_code, int err); int rxrpc_io_thread(void *data); static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local) { wake_up_process(local->io_thread); } +static inline bool rxrpc_protocol_error(struct sk_buff *skb, enum rxrpc_abort_reason why) +{ + return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EPROTO); +} + /* * insecure.c */ @@ -1108,29 +1118,26 @@ bool __rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion bool rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int); bool __rxrpc_call_completed(struct rxrpc_call *); bool rxrpc_call_completed(struct rxrpc_call *); -bool __rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int); -bool rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int); +bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why); +bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why); int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* * Abort a call due to a protocol error. */ -static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call, - struct sk_buff *skb, - const char *eproto_why, - const char *why, - u32 abort_code) +static inline int rxrpc_abort_eproto(struct rxrpc_call *call, + struct sk_buff *skb, + s32 abort_code, + enum rxrpc_abort_reason why) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why); - return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO); + rxrpc_abort_call(call, sp->hdr.seq, abort_code, -EPROTO, why); + return -EPROTO; } -#define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \ - __rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \ - (abort_why), (abort_code)) - /* * rtt.c */ @@ -1162,8 +1169,8 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *, /* * sendmsg.c */ -bool rxrpc_propose_abort(struct rxrpc_call *call, - u32 abort_code, int error, const char *why); +bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, + enum rxrpc_abort_reason why); int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); /* diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index c957e4415cdc..a132d486dea0 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -326,11 +326,11 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, * If we want to report an error, we mark the skb with the packet type and * abort code and return false. */ -int rxrpc_new_incoming_call(struct rxrpc_local *local, - struct rxrpc_peer *peer, - struct rxrpc_connection *conn, - struct sockaddr_rxrpc *peer_srx, - struct sk_buff *skb) +bool rxrpc_new_incoming_call(struct rxrpc_local *local, + struct rxrpc_peer *peer, + struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb) { const struct rxrpc_security *sec = NULL; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -339,10 +339,9 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local, _enter(""); - /* Don't set up a call for anything other than the first DATA packet. */ - if (sp->hdr.seq != 1 || - sp->hdr.type != RXRPC_PACKET_TYPE_DATA) - return 0; /* Just discard */ + /* Don't set up a call for anything other than a DATA packet. */ + if (sp->hdr.type != RXRPC_PACKET_TYPE_DATA) + return rxrpc_protocol_error(skb, rxrpc_eproto_no_service_call); rcu_read_lock(); @@ -363,16 +362,14 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local, if (!conn) { sec = rxrpc_get_incoming_security(rx, skb); if (!sec) - goto reject; + goto unsupported_security; } spin_lock(&rx->incoming_lock); if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED || rx->sk.sk_state == RXRPC_CLOSE) { - trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber, - sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN); - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; - skb->priority = RX_INVALID_OPERATION; + rxrpc_direct_abort(skb, rxrpc_abort_shut_down, + RX_INVALID_OPERATION, -ESHUTDOWN); goto no_call; } @@ -413,22 +410,24 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local, _leave(" = %p{%d}", call, call->debug_id); rxrpc_input_call_event(call, skb); rxrpc_put_call(call, rxrpc_call_put_input); - return 0; + return true; unsupported_service: - trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EOPNOTSUPP); - skb->priority = RX_INVALID_OPERATION; - goto reject; + rcu_read_unlock(); + return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, + RX_INVALID_OPERATION, -EOPNOTSUPP); +unsupported_security: + rcu_read_unlock(); + return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, + RX_INVALID_OPERATION, -EKEYREJECTED); no_call: spin_unlock(&rx->incoming_lock); -reject: rcu_read_unlock(); _leave(" = f [%u]", skb->mark); - return -EPROTO; + return false; discard: rcu_read_unlock(); - return 0; + return true; } /* diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index b2fc3fa686ec..695aeb70d1a6 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -333,7 +333,7 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call) /* * Handle retransmission and deferred ACK/abort generation. */ -void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) +bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { unsigned long now, next, t; rxrpc_serial_t ackr_serial; @@ -352,8 +352,8 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) /* Handle abort request locklessly, vs rxrpc_propose_abort(). */ abort_code = smp_load_acquire(&call->send_abort); if (abort_code) { - rxrpc_abort_call(call->send_abort_why, call, 0, call->send_abort, - call->send_abort_err); + rxrpc_abort_call(call, 0, call->send_abort, call->send_abort_err, + call->send_abort_why); goto out; } @@ -440,9 +440,11 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && (int)call->conn->hi_serial - (int)call->rx_serial > 0) { trace_rxrpc_call_reset(call); - rxrpc_abort_call("EXP", call, 0, RX_CALL_DEAD, -ECONNRESET); + rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET, + rxrpc_abort_call_reset); } else { - rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME); + rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME, + rxrpc_abort_call_timeout); } goto out; } @@ -494,4 +496,5 @@ out: if (call->acks_hard_ack != call->tx_bottom) rxrpc_shrink_call_tx_buffer(call); _leave(""); + return true; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 666430182dfd..705f6e26cc75 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -581,7 +581,8 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) call = list_entry(rx->to_be_accepted.next, struct rxrpc_call, accept_link); list_del(&call->accept_link); - rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, "SKR"); + rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, + rxrpc_abort_call_sock_release_tba); rxrpc_put_call(call, rxrpc_call_put_release_sock_tba); } @@ -589,7 +590,8 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) call = list_entry(rx->sock_calls.next, struct rxrpc_call, sock_link); rxrpc_get_call(call, rxrpc_call_get_release_sock); - rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, "SKT"); + rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, + rxrpc_abort_call_sock_release); rxrpc_release_call(rx, call); rxrpc_put_call(call, rxrpc_call_put_release_sock); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 753d91a9646f..485d7f0fed2c 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -47,7 +47,7 @@ static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff * Mark a socket buffer to indicate that the connection it's on should be aborted. */ int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, - s32 abort_code, int err, const char *why) + s32 abort_code, int err, enum rxrpc_abort_reason why) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -288,8 +288,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return 0; default: - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("bad_conn_pkt")); + WARN_ON_ONCE(1); return -EPROTO; } } @@ -300,7 +299,8 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, static void rxrpc_secure_connection(struct rxrpc_connection *conn) { if (conn->security->issue_challenge(conn) < 0) - rxrpc_abort_conn(conn, NULL, RX_CALL_DEAD, -ENOMEM, "OOM"); + rxrpc_abort_conn(conn, NULL, RX_CALL_DEAD, -ENOMEM, + rxrpc_abort_nomem); } /* @@ -405,14 +405,14 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, /* * Input a connection-level packet. */ -int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) +bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_BUSY: /* Just ignore BUSY packets for now. */ - return 0; + return true; case RXRPC_PACKET_TYPE_ABORT: if (rxrpc_is_conn_aborted(conn)) @@ -429,12 +429,11 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) return true; } rxrpc_post_packet_to_conn(conn, skb); - return 0; + return true; default: - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("bad_conn_pkt")); - return -EPROTO; + WARN_ON_ONCE(1); + return true; } } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index bb4beb445325..bd69ff2d9082 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -9,10 +9,10 @@ #include "ar-internal.h" -static void rxrpc_proto_abort(const char *why, - struct rxrpc_call *call, rxrpc_seq_t seq) +static void rxrpc_proto_abort(struct rxrpc_call *call, rxrpc_seq_t seq, + enum rxrpc_abort_reason why) { - rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG); + rxrpc_abort_call(call, seq, RX_PROTOCOL_ERROR, -EBADMSG, why); } /* @@ -249,8 +249,8 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, * This occurs when we get an ACKALL packet, the first DATA packet of a reply, * or a final ACK packet. */ -static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, - const char *abort_why) +static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, + enum rxrpc_abort_reason abort_why) { unsigned int state; @@ -283,13 +283,12 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, else trace_rxrpc_txqueue(call, rxrpc_txqueue_end); _leave(" = ok"); - return true; + return; bad_state: write_unlock(&call->state_lock); kdebug("end_tx %s", rxrpc_call_states[call->state]); - rxrpc_proto_abort(abort_why, call, call->tx_top); - return false; + rxrpc_proto_abort(call, call->tx_top, abort_why); } /* @@ -311,11 +310,13 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { if (!rxrpc_rotate_tx_window(call, top, &summary)) { - rxrpc_proto_abort("TXL", call, top); + rxrpc_proto_abort(call, top, rxrpc_eproto_early_reply); return false; } } - return rxrpc_end_tx_phase(call, true, "ETD"); + + rxrpc_end_tx_phase(call, true, rxrpc_eproto_unexpected_reply); + return true; } static void rxrpc_input_update_ack_window(struct rxrpc_call *call, @@ -365,17 +366,14 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, if (last) { if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq + 1 != wtop) { - rxrpc_proto_abort("LSN", call, seq); - return; - } + seq + 1 != wtop) + return rxrpc_proto_abort(call, seq, rxrpc_eproto_different_last); } else { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && after_eq(seq, wtop)) { pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n", call->debug_id, seq, window, wtop, wlimit); - rxrpc_proto_abort("LSA", call, seq); - return; + return rxrpc_proto_abort(call, seq, rxrpc_eproto_data_after_last); } } @@ -583,7 +581,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) goto out_notify; if (!rxrpc_input_split_jumbo(call, skb)) { - rxrpc_proto_abort("VLD", call, sp->hdr.seq); + rxrpc_proto_abort(call, sp->hdr.seq, rxrpc_badmsg_bad_jumbo); goto out_notify; } skb = NULL; @@ -764,7 +762,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) offset = sizeof(struct rxrpc_wire_header); if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) - return rxrpc_proto_abort("XAK", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack); offset += sizeof(ack); ack_serial = sp->hdr.serial; @@ -844,7 +842,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) ioffset = offset + nr_acks + 3; if (skb->len >= ioffset + sizeof(info) && skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) - return rxrpc_proto_abort("XAI", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info); if (nr_acks > 0) skb_condense(skb); @@ -867,7 +865,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_input_ackinfo(call, skb, &info); if (first_soft_ack == 0) - return rxrpc_proto_abort("AK0", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero); /* Ignore ACKs unless we are or have just been transmitting. */ switch (READ_ONCE(call->state)) { @@ -882,20 +880,20 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (before(hard_ack, call->acks_hard_ack) || after(hard_ack, call->tx_top)) - return rxrpc_proto_abort("AKW", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_outside_window); if (nr_acks > call->tx_top - hard_ack) - return rxrpc_proto_abort("AKN", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_sack_overflow); if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { - rxrpc_end_tx_phase(call, false, "ETA"); + rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack); return; } } if (nr_acks > 0) { if (offset > (int)skb->len - nr_acks) - return rxrpc_proto_abort("XSA", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack); rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, nr_acks, &summary); } @@ -917,7 +915,7 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ack_summary summary = { 0 }; if (rxrpc_rotate_tx_window(call, call->tx_top, &summary)) - rxrpc_end_tx_phase(call, false, "ETL"); + rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ackall); } /* @@ -962,27 +960,23 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: - rxrpc_input_data(call, skb); - break; + return rxrpc_input_data(call, skb); case RXRPC_PACKET_TYPE_ACK: - rxrpc_input_ack(call, skb); - break; + return rxrpc_input_ack(call, skb); case RXRPC_PACKET_TYPE_BUSY: /* Just ignore BUSY packets from the server; the retry and * lifespan timers will take care of business. BUSY packets * from the client don't make sense. */ - break; + return; case RXRPC_PACKET_TYPE_ABORT: - rxrpc_input_abort(call, skb); - break; + return rxrpc_input_abort(call, skb); case RXRPC_PACKET_TYPE_ACKALL: - rxrpc_input_ackall(call, skb); - break; + return rxrpc_input_ackall(call, skb); default: break; @@ -1004,7 +998,8 @@ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_CALL_COMPLETE: break; default: - rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN); + rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ESHUTDOWN, + rxrpc_eproto_improper_term); trace_rxrpc_improper_term(call); break; } diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 29dcc7d3f51a..34353b6e584b 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -45,13 +45,15 @@ static void none_free_call_crypto(struct rxrpc_call *call) static int none_respond_to_challenge(struct rxrpc_connection *conn, struct sk_buff *skb) { - return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, "RXN"); + return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, + rxrpc_eproto_rxnull_challenge); } static int none_verify_response(struct rxrpc_connection *conn, struct sk_buff *skb) { - return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, "RXN"); + return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, + rxrpc_eproto_rxnull_response); } static void none_clear(struct rxrpc_connection *conn) diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 46e58cf5bc96..33fd2394c8b3 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -66,10 +66,32 @@ void rxrpc_error_report(struct sock *sk) rcu_read_unlock(); } +/* + * Directly produce an abort from a packet. + */ +bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, + s32 abort_code, int err) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + abort_code, err); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = abort_code; + return false; +} + +static bool rxrpc_bad_message(struct sk_buff *skb, enum rxrpc_abort_reason why) +{ + return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EBADMSG); +} + +#define just_discard true + /* * Process event packets targeted at a local endpoint. */ -static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb) +static bool rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); char v; @@ -81,22 +103,21 @@ static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb) if (v == 0) rxrpc_send_version_request(local, &sp->hdr, skb); } + + return true; } /* * Extract the wire header from a packet and translate the byte order. */ -static noinline -int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) +static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp, + struct sk_buff *skb) { struct rxrpc_wire_header whdr; /* dig out the RxRPC connection details */ - if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) { - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("bad_hdr")); - return -EBADMSG; - } + if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) + return rxrpc_bad_message(skb, rxrpc_badmsg_short_hdr); memset(sp, 0, sizeof(*sp)); sp->hdr.epoch = ntohl(whdr.epoch); @@ -110,7 +131,7 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) sp->hdr.securityIndex = whdr.securityIndex; sp->hdr._rsvd = ntohs(whdr._rsvd); sp->hdr.serviceId = ntohs(whdr.serviceId); - return 0; + return true; } /* @@ -130,28 +151,28 @@ static bool rxrpc_extract_abort(struct sk_buff *skb) /* * Process packets received on the local endpoint */ -static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) +static bool rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) { struct rxrpc_connection *conn; struct sockaddr_rxrpc peer_srx; struct rxrpc_skb_priv *sp; struct rxrpc_peer *peer = NULL; struct sk_buff *skb = *_skb; - int ret = 0; + bool ret = false; skb_pull(skb, sizeof(struct udphdr)); sp = rxrpc_skb(skb); /* dig out the RxRPC connection details */ - if (rxrpc_extract_header(sp, skb) < 0) - goto bad_message; + if (!rxrpc_extract_header(sp, skb)) + return just_discard; if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - return 0; + return just_discard; } } @@ -160,28 +181,28 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: if (rxrpc_to_client(sp)) - return 0; - rxrpc_input_version(local, skb); - return 0; + return just_discard; + return rxrpc_input_version(local, skb); case RXRPC_PACKET_TYPE_BUSY: if (rxrpc_to_server(sp)) - return 0; + return just_discard; fallthrough; case RXRPC_PACKET_TYPE_ACK: case RXRPC_PACKET_TYPE_ACKALL: if (sp->hdr.callNumber == 0) - goto bad_message; + return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call); break; case RXRPC_PACKET_TYPE_ABORT: if (!rxrpc_extract_abort(skb)) - return 0; /* Just discard if malformed */ + return just_discard; /* Just discard if malformed */ break; case RXRPC_PACKET_TYPE_DATA: - if (sp->hdr.callNumber == 0 || - sp->hdr.seq == 0) - goto bad_message; + if (sp->hdr.callNumber == 0) + return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call); + if (sp->hdr.seq == 0) + return rxrpc_bad_message(skb, rxrpc_badmsg_zero_seq); /* Unshare the packet so that it can be modified for in-place * decryption. @@ -191,7 +212,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) if (!skb) { rxrpc_eaten_skb(*_skb, rxrpc_skb_eaten_by_unshare_nomem); *_skb = NULL; - return 0; + return just_discard; } if (skb != *_skb) { @@ -205,28 +226,28 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) case RXRPC_PACKET_TYPE_CHALLENGE: if (rxrpc_to_server(sp)) - return 0; + return just_discard; break; case RXRPC_PACKET_TYPE_RESPONSE: if (rxrpc_to_client(sp)) - return 0; + return just_discard; break; /* Packet types 9-11 should just be ignored. */ case RXRPC_PACKET_TYPE_PARAMS: case RXRPC_PACKET_TYPE_10: case RXRPC_PACKET_TYPE_11: - return 0; + return just_discard; default: - goto bad_message; + return rxrpc_bad_message(skb, rxrpc_badmsg_unsupported_packet); } if (sp->hdr.serviceId == 0) - goto bad_message; + return rxrpc_bad_message(skb, rxrpc_badmsg_zero_service); if (WARN_ON_ONCE(rxrpc_extract_addr_from_skb(&peer_srx, skb) < 0)) - return true; /* Unsupported address type - discard. */ + return just_discard; /* Unsupported address type. */ if (peer_srx.transport.family != local->srx.transport.family && (peer_srx.transport.family == AF_INET && @@ -234,7 +255,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n", peer_srx.transport.family, local->srx.transport.family); - return true; /* Wrong address type - discard. */ + return just_discard; /* Wrong address type. */ } if (rxrpc_to_client(sp)) { @@ -242,12 +263,8 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) conn = rxrpc_find_client_connection_rcu(local, &peer_srx, skb); conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input); rcu_read_unlock(); - if (!conn) { - trace_rxrpc_abort(0, "NCC", sp->hdr.cid, - sp->hdr.callNumber, sp->hdr.seq, - RXKADINCONSISTENCY, EBADMSG); - goto protocol_error; - } + if (!conn) + return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_conn); ret = rxrpc_input_packet_on_conn(conn, &peer_srx, skb); rxrpc_put_connection(conn, rxrpc_conn_put_call_input); @@ -280,19 +297,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) ret = rxrpc_new_incoming_call(local, peer, NULL, &peer_srx, skb); rxrpc_put_peer(peer, rxrpc_peer_put_input); - if (ret < 0) - goto reject_packet; - return 0; - -bad_message: - trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_PROTOCOL_ERROR, EBADMSG); -protocol_error: - skb->priority = RX_PROTOCOL_ERROR; - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; -reject_packet: - rxrpc_reject_packet(local, skb); - return 0; + return ret; } /* @@ -306,21 +311,23 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, struct rxrpc_channel *chan; struct rxrpc_call *call = NULL; unsigned int channel; + bool ret; if (sp->hdr.securityIndex != conn->security_ix) - goto wrong_security; + return rxrpc_direct_abort(skb, rxrpc_eproto_wrong_security, + RXKADINCONSISTENCY, -EBADMSG); if (sp->hdr.serviceId != conn->service_id) { int old_id; if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) - goto reupgrade; + return rxrpc_protocol_error(skb, rxrpc_eproto_reupgrade); + old_id = cmpxchg(&conn->service_id, conn->orig_service_id, sp->hdr.serviceId); - if (old_id != conn->orig_service_id && old_id != sp->hdr.serviceId) - goto reupgrade; + return rxrpc_protocol_error(skb, rxrpc_eproto_bad_upgrade); } if (after(sp->hdr.serial, conn->hi_serial)) @@ -336,19 +343,19 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, /* Ignore really old calls */ if (sp->hdr.callNumber < chan->last_call) - return 0; + return just_discard; if (sp->hdr.callNumber == chan->last_call) { if (chan->call || sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) - return 0; + return just_discard; /* For the previous service call, if completed successfully, we * discard all further packets. */ if (rxrpc_conn_is_service(conn) && chan->last_type == RXRPC_PACKET_TYPE_ACK) - return 0; + return just_discard; /* But otherwise we need to retransmit the final packet from * data cached in the connection record. @@ -359,7 +366,7 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, sp->hdr.serial, sp->hdr.flags); rxrpc_conn_retransmit_call(conn, skb, channel); - return 0; + return just_discard; } rcu_read_lock(); @@ -370,7 +377,8 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, if (sp->hdr.callNumber > chan->call_id) { if (rxrpc_to_client(sp)) { rxrpc_put_call(call, rxrpc_call_put_input); - goto reject_packet; + return rxrpc_protocol_error(skb, + rxrpc_eproto_unexpected_implicit_end); } if (call) { @@ -382,38 +390,14 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, if (!call) { if (rxrpc_to_client(sp)) - goto bad_message; - if (rxrpc_new_incoming_call(conn->local, conn->peer, conn, - peer_srx, skb) == 0) - return 0; - goto reject_packet; + return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_call); + return rxrpc_new_incoming_call(conn->local, conn->peer, conn, + peer_srx, skb); } - rxrpc_input_call_event(call, skb); + ret = rxrpc_input_call_event(call, skb); rxrpc_put_call(call, rxrpc_call_put_input); - return 0; - -wrong_security: - trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RXKADINCONSISTENCY, EBADMSG); - skb->priority = RXKADINCONSISTENCY; - goto post_abort; - -reupgrade: - trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_PROTOCOL_ERROR, EBADMSG); - goto protocol_error; - -bad_message: - trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_PROTOCOL_ERROR, EBADMSG); -protocol_error: - skb->priority = RX_PROTOCOL_ERROR; -post_abort: - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; -reject_packet: - rxrpc_reject_packet(conn->local, skb); - return 0; + return ret; } /* @@ -470,7 +454,8 @@ int rxrpc_io_thread(void *data) switch (skb->mark) { case RXRPC_SKB_MARK_PACKET: skb->priority = 0; - rxrpc_input_packet(local, &skb); + if (!rxrpc_input_packet(local, &skb)) + rxrpc_reject_packet(local, skb); trace_rxrpc_rx_done(skb->mark, skb->priority); rxrpc_free_skb(skb, rxrpc_skb_put_input); break; diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 8d5fe65f5951..59b521b82aec 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -117,8 +117,8 @@ bool rxrpc_call_completed(struct rxrpc_call *call) /* * Record that a call is locally aborted. */ -bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call, - rxrpc_seq_t seq, u32 abort_code, int error) +bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why) { trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq, abort_code, error); @@ -126,13 +126,13 @@ bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call, abort_code, error); } -bool rxrpc_abort_call(const char *why, struct rxrpc_call *call, - rxrpc_seq_t seq, u32 abort_code, int error) +bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why) { bool ret; write_lock(&call->state_lock); - ret = __rxrpc_abort_call(why, call, seq, abort_code, error); + ret = __rxrpc_abort_call(call, seq, abort_code, error, why); write_unlock(&call->state_lock); if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags)) rxrpc_send_abort_packet(call); @@ -642,11 +642,15 @@ out: return ret; short_data: - trace_rxrpc_rx_eproto(call, 0, tracepoint_string("short_data")); + trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_short_data, + call->cid, call->call_id, call->rx_consumed, + 0, -EBADMSG); ret = -EBADMSG; goto out; excess_data: - trace_rxrpc_rx_eproto(call, 0, tracepoint_string("excess_data")); + trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_excess_data, + call->cid, call->call_id, call->rx_consumed, + 0, -EMSGSIZE); ret = -EMSGSIZE; goto out; call_complete: diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 5d2fbc6ec3cf..e52cb8058156 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -411,18 +411,15 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist sg[16]; - bool aborted; u32 data_size, buf; u16 check; int ret; _enter(""); - if (sp->len < 8) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H", - RXKADSEALEDINCON); - goto protocol_error; - } + if (sp->len < 8) + return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_1_short_header); /* Decrypt the skbuff in-place. TODO: We really want to decrypt * directly into the target buffer. @@ -442,11 +439,9 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_zero(req); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1", - RXKADDATALEN); - goto protocol_error; - } + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) + return rxrpc_abort_eproto(call, skb, RXKADDATALEN, + rxkad_abort_1_short_encdata); sp->offset += sizeof(sechdr); sp->len -= sizeof(sechdr); @@ -456,26 +451,16 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, check = buf >> 16; check ^= seq ^ call->call_id; check &= 0xffff; - if (check != 0) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_check", "V1C", - RXKADSEALEDINCON); - goto protocol_error; - } - - if (data_size > sp->len) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L", - RXKADDATALEN); - goto protocol_error; - } + if (check != 0) + return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_1_short_check); + if (data_size > sp->len) + return rxrpc_abort_eproto(call, skb, RXKADDATALEN, + rxkad_abort_1_short_data); sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; - -protocol_error: - if (aborted) - rxrpc_send_abort_packet(call); - return -EPROTO; } /* @@ -490,18 +475,15 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; - bool aborted; u32 data_size, buf; u16 check; int nsg, ret; _enter(",{%d}", sp->len); - if (sp->len < 8) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H", - RXKADSEALEDINCON); - goto protocol_error; - } + if (sp->len < 8) + return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_2_short_header); /* Decrypt the skbuff in-place. TODO: We really want to decrypt * directly into the target buffer. @@ -513,7 +495,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, } else { sg = kmalloc_array(nsg, sizeof(*sg), GFP_NOIO); if (!sg) - goto nomem; + return -ENOMEM; } sg_init_table(sg, nsg); @@ -537,11 +519,9 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, kfree(sg); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2", - RXKADDATALEN); - goto protocol_error; - } + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) + return rxrpc_abort_eproto(call, skb, RXKADDATALEN, + rxkad_abort_2_short_len); sp->offset += sizeof(sechdr); sp->len -= sizeof(sechdr); @@ -551,30 +531,17 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, check = buf >> 16; check ^= seq ^ call->call_id; check &= 0xffff; - if (check != 0) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_check", "V2C", - RXKADSEALEDINCON); - goto protocol_error; - } + if (check != 0) + return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_2_short_check); - if (data_size > sp->len) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L", - RXKADDATALEN); - goto protocol_error; - } + if (data_size > sp->len) + return rxrpc_abort_eproto(call, skb, RXKADDATALEN, + rxkad_abort_2_short_data); sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; - -protocol_error: - if (aborted) - rxrpc_send_abort_packet(call); - return -EPROTO; - -nomem: - _leave(" = -ENOMEM"); - return -ENOMEM; } /* @@ -590,7 +557,6 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) __be32 buf[2]; } crypto __aligned(8); rxrpc_seq_t seq = sp->hdr.seq; - bool aborted; int ret; u16 cksum; u32 x, y; @@ -627,9 +593,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) cksum = 1; /* zero checksums are not permitted */ if (cksum != sp->hdr.cksum) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK", - RXKADSEALEDINCON); - goto protocol_error; + ret = rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_bad_checksum); + goto out; } switch (call->conn->security_level) { @@ -647,13 +613,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) break; } +out: skcipher_request_free(req); return ret; - -protocol_error: - if (aborted) - rxrpc_send_abort_packet(call); - return -EPROTO; } /* @@ -827,27 +789,24 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, struct rxkad_challenge challenge; struct rxkad_response *resp; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - const char *eproto; - u32 version, nonce, min_level, abort_code; - int ret; + u32 version, nonce, min_level; + int ret = -EPROTO; _enter("{%d,%x}", conn->debug_id, key_serial(conn->key)); - eproto = tracepoint_string("chall_no_key"); - abort_code = RX_PROTOCOL_ERROR; if (!conn->key) - goto protocol_error; + return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, + rxkad_abort_chall_no_key); - abort_code = RXKADEXPIRED; ret = key_validate(conn->key); if (ret < 0) - goto other_error; + return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret, + rxkad_abort_chall_key_expired); - eproto = tracepoint_string("chall_short"); - abort_code = RXKADPACKETSHORT; if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), &challenge, sizeof(challenge)) < 0) - goto protocol_error; + return rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, + rxkad_abort_chall_short); version = ntohl(challenge.version); nonce = ntohl(challenge.nonce); @@ -855,15 +814,13 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, nonce, min_level); - eproto = tracepoint_string("chall_ver"); - abort_code = RXKADINCONSISTENCY; if (version != RXKAD_VERSION) - goto protocol_error; + return rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO, + rxkad_abort_chall_version); - abort_code = RXKADLEVELFAIL; - ret = -EACCES; if (conn->security_level < min_level) - goto other_error; + return rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EACCES, + rxkad_abort_chall_level); token = conn->key->payload.data[0]; @@ -892,13 +849,6 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad); kfree(resp); return ret; - -protocol_error: - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); - ret = -EPROTO; -other_error: - rxrpc_abort_conn(conn, skb, abort_code, ret, "RXK"); - return ret; } /* @@ -912,16 +862,12 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, time64_t *_expiry) { struct skcipher_request *req; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv, key; struct scatterlist sg[1]; struct in_addr addr; unsigned int life; - const char *eproto; time64_t issue, now; bool little_endian; - int ret; - u32 abort_code; u8 *p, *q, *name, *end; _enter("{%d},{%x}", conn->debug_id, key_serial(server_key)); @@ -933,10 +879,9 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, memcpy(&iv, &server_key->payload.data[2], sizeof(iv)); - ret = -ENOMEM; req = skcipher_request_alloc(server_key->payload.data[0], GFP_NOFS); if (!req) - goto temporary_error; + return -ENOMEM; sg_init_one(&sg[0], ticket, ticket_len); skcipher_request_set_callback(req, 0, NULL, NULL); @@ -947,18 +892,21 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, p = ticket; end = p + ticket_len; -#define Z(field) \ - ({ \ - u8 *__str = p; \ - eproto = tracepoint_string("rxkad_bad_"#field); \ - q = memchr(p, 0, end - p); \ - if (!q || q - p > (field##_SZ)) \ - goto bad_ticket; \ - for (; p < q; p++) \ - if (!isprint(*p)) \ - goto bad_ticket; \ - p++; \ - __str; \ +#define Z(field, fieldl) \ + ({ \ + u8 *__str = p; \ + q = memchr(p, 0, end - p); \ + if (!q || q - p > field##_SZ) \ + return rxrpc_abort_conn( \ + conn, skb, RXKADBADTICKET, -EPROTO, \ + rxkad_abort_resp_tkt_##fieldl); \ + for (; p < q; p++) \ + if (!isprint(*p)) \ + return rxrpc_abort_conn( \ + conn, skb, RXKADBADTICKET, -EPROTO, \ + rxkad_abort_resp_tkt_##fieldl); \ + p++; \ + __str; \ }) /* extract the ticket flags */ @@ -967,20 +915,20 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, p++; /* extract the authentication name */ - name = Z(ANAME); + name = Z(ANAME, aname); _debug("KIV ANAME: %s", name); /* extract the principal's instance */ - name = Z(INST); + name = Z(INST, inst); _debug("KIV INST : %s", name); /* extract the principal's authentication domain */ - name = Z(REALM); + name = Z(REALM, realm); _debug("KIV REALM: %s", name); - eproto = tracepoint_string("rxkad_bad_len"); if (end - p < 4 + 8 + 4 + 2) - goto bad_ticket; + return rxrpc_abort_conn(conn, skb, RXKADBADTICKET, -EPROTO, + rxkad_abort_resp_tkt_short); /* get the IPv4 address of the entity that requested the ticket */ memcpy(&addr, p, sizeof(addr)); @@ -1012,37 +960,23 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, _debug("KIV ISSUE: %llx [%llx]", issue, now); /* check the ticket is in date */ - if (issue > now) { - abort_code = RXKADNOAUTH; - ret = -EKEYREJECTED; - goto other_error; - } - - if (issue < now - life) { - abort_code = RXKADEXPIRED; - ret = -EKEYEXPIRED; - goto other_error; - } + if (issue > now) + return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, -EKEYREJECTED, + rxkad_abort_resp_tkt_future); + if (issue < now - life) + return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, -EKEYEXPIRED, + rxkad_abort_resp_tkt_expired); *_expiry = issue + life; /* get the service name */ - name = Z(SNAME); + name = Z(SNAME, sname); _debug("KIV SNAME: %s", name); /* get the service instance name */ - name = Z(INST); + name = Z(INST, sinst); _debug("KIV SINST: %s", name); return 0; - -bad_ticket: - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); - abort_code = RXKADBADTICKET; - ret = -EPROTO; -other_error: - return rxrpc_abort_conn(conn, skb, abort_code, ret, "RXK"); -temporary_error: - return ret; } /* @@ -1089,10 +1023,9 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt session_key; struct key *server_key; - const char *eproto; time64_t expiry; void *ticket; - u32 abort_code, version, kvno, ticket_len, level; + u32 version, kvno, ticket_len, level; __be32 csum; int ret, i; @@ -1100,19 +1033,18 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, server_key = rxrpc_look_up_server_security(conn, skb, 0, 0); if (IS_ERR(server_key)) { - switch (PTR_ERR(server_key)) { + ret = PTR_ERR(server_key); + switch (ret) { case -ENOKEY: - abort_code = RXKADUNKNOWNKEY; - break; + return rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, ret, + rxkad_abort_resp_nokey); case -EKEYEXPIRED: - abort_code = RXKADEXPIRED; - break; + return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret, + rxkad_abort_resp_key_expired); default: - abort_code = RXKADNOAUTH; - break; + return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, ret, + rxkad_abort_resp_key_rejected); } - return rxrpc_abort_conn(conn, skb, abort_code, - PTR_ERR(server_key), "RXK"); } ret = -ENOMEM; @@ -1120,11 +1052,12 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, if (!response) goto temporary_error; - eproto = tracepoint_string("rxkad_rsp_short"); - abort_code = RXKADPACKETSHORT; if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), - response, sizeof(*response)) < 0) + response, sizeof(*response)) < 0) { + rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, + rxkad_abort_resp_short); goto protocol_error; + } version = ntohl(response->version); ticket_len = ntohl(response->ticket_len); @@ -1132,20 +1065,23 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, trace_rxrpc_rx_response(conn, sp->hdr.serial, version, kvno, ticket_len); - eproto = tracepoint_string("rxkad_rsp_ver"); - abort_code = RXKADINCONSISTENCY; - if (version != RXKAD_VERSION) + if (version != RXKAD_VERSION) { + rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO, + rxkad_abort_resp_version); goto protocol_error; + } - eproto = tracepoint_string("rxkad_rsp_tktlen"); - abort_code = RXKADTICKETLEN; - if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN) + if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN) { + rxrpc_abort_conn(conn, skb, RXKADTICKETLEN, -EPROTO, + rxkad_abort_resp_tkt_len); goto protocol_error; + } - eproto = tracepoint_string("rxkad_rsp_unkkey"); - abort_code = RXKADUNKNOWNKEY; - if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5) + if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5) { + rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, -EPROTO, + rxkad_abort_resp_unknown_tkt); goto protocol_error; + } /* extract the kerberos ticket and decrypt and decode it */ ret = -ENOMEM; @@ -1153,12 +1089,12 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, if (!ticket) goto temporary_error_free_resp; - eproto = tracepoint_string("rxkad_tkt_short"); - abort_code = RXKADPACKETSHORT; - ret = skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), - ticket, ticket_len); - if (ret < 0) - goto temporary_error_free_ticket; + if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), + ticket, ticket_len) < 0) { + rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, + rxkad_abort_resp_short_tkt); + goto protocol_error; + } ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len, &session_key, &expiry); @@ -1169,56 +1105,66 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, * response */ rxkad_decrypt_response(conn, response, &session_key); - eproto = tracepoint_string("rxkad_rsp_param"); - abort_code = RXKADSEALEDINCON; - if (ntohl(response->encrypted.epoch) != conn->proto.epoch) - goto protocol_error_free; - if (ntohl(response->encrypted.cid) != conn->proto.cid) - goto protocol_error_free; - if (ntohl(response->encrypted.securityIndex) != conn->security_ix) + if (ntohl(response->encrypted.epoch) != conn->proto.epoch || + ntohl(response->encrypted.cid) != conn->proto.cid || + ntohl(response->encrypted.securityIndex) != conn->security_ix) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_bad_param); goto protocol_error_free; + } + csum = response->encrypted.checksum; response->encrypted.checksum = 0; rxkad_calc_response_checksum(response); - eproto = tracepoint_string("rxkad_rsp_csum"); - if (response->encrypted.checksum != csum) + if (response->encrypted.checksum != csum) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_bad_checksum); goto protocol_error_free; + } spin_lock(&conn->bundle->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { struct rxrpc_call *call; u32 call_id = ntohl(response->encrypted.call_id[i]); - eproto = tracepoint_string("rxkad_rsp_callid"); - if (call_id > INT_MAX) + if (call_id > INT_MAX) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_bad_callid); goto protocol_error_unlock; + } - eproto = tracepoint_string("rxkad_rsp_callctr"); - if (call_id < conn->channels[i].call_counter) + if (call_id < conn->channels[i].call_counter) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_call_ctr); goto protocol_error_unlock; + } - eproto = tracepoint_string("rxkad_rsp_callst"); if (call_id > conn->channels[i].call_counter) { call = rcu_dereference_protected( conn->channels[i].call, lockdep_is_held(&conn->bundle->channel_lock)); - if (call && call->state < RXRPC_CALL_COMPLETE) + if (call && call->state < RXRPC_CALL_COMPLETE) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_call_state); goto protocol_error_unlock; + } conn->channels[i].call_counter = call_id; } } spin_unlock(&conn->bundle->channel_lock); - eproto = tracepoint_string("rxkad_rsp_seq"); - abort_code = RXKADOUTOFSEQUENCE; - if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1) + if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1) { + rxrpc_abort_conn(conn, skb, RXKADOUTOFSEQUENCE, -EPROTO, + rxkad_abort_resp_ooseq); goto protocol_error_free; + } - eproto = tracepoint_string("rxkad_rsp_level"); - abort_code = RXKADLEVELFAIL; level = ntohl(response->encrypted.level); - if (level > RXRPC_SECURITY_ENCRYPT) + if (level > RXRPC_SECURITY_ENCRYPT) { + rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EPROTO, + rxkad_abort_resp_level); goto protocol_error_free; + } conn->security_level = level; /* create a key to hold the security data and expiration time - after @@ -1240,8 +1186,7 @@ protocol_error_free: protocol_error: kfree(response); key_put(server_key); - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); - return rxrpc_abort_conn(conn, skb, abort_code, -EPROTO, "RXK"); + return -EPROTO; temporary_error_free_ticket: kfree(ticket); diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c index d33a109e846c..16dcabb71ebe 100644 --- a/net/rxrpc/rxperf.c +++ b/net/rxrpc/rxperf.c @@ -10,6 +10,8 @@ #include #include #include +#define RXRPC_TRACE_ONLY_DEFINE_ENUMS +#include MODULE_DESCRIPTION("rxperf test server (afs)"); MODULE_AUTHOR("Red Hat, Inc."); @@ -307,12 +309,14 @@ static void rxperf_deliver_to_call(struct work_struct *work) case -EOPNOTSUPP: abort_code = RXGEN_OPCODE; rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - abort_code, ret, "GOP"); + abort_code, ret, + rxperf_abort_op_not_supported); goto call_complete; case -ENOTSUPP: abort_code = RX_USER_ABORT; rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - abort_code, ret, "GUA"); + abort_code, ret, + rxperf_abort_op_not_supported); goto call_complete; case -EIO: pr_err("Call %u in bad state %u\n", @@ -324,11 +328,13 @@ static void rxperf_deliver_to_call(struct work_struct *work) case -ENOMEM: case -EFAULT: rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - RXGEN_SS_UNMARSHAL, ret, "GUM"); + RXGEN_SS_UNMARSHAL, ret, + rxperf_abort_unmarshal_error); goto call_complete; default: rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - RX_CALL_DEAD, ret, "GER"); + RX_CALL_DEAD, ret, + rxperf_abort_general_error); goto call_complete; } } @@ -523,7 +529,8 @@ static int rxperf_process_call(struct rxperf_call *call) if (n == -ENOMEM) rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - RXGEN_SS_MARSHAL, -ENOMEM, "GOM"); + RXGEN_SS_MARSHAL, -ENOMEM, + rxperf_abort_oom); return n; } diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index ab968f65a490..78af14694618 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -144,21 +144,15 @@ const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *rx, sec = rxrpc_security_lookup(sp->hdr.securityIndex); if (!sec) { - trace_rxrpc_abort(0, "SVS", - sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EKEYREJECTED); - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; - skb->priority = RX_INVALID_OPERATION; + rxrpc_direct_abort(skb, rxrpc_abort_unsupported_security, + RX_INVALID_OPERATION, -EKEYREJECTED); return NULL; } if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE && !rx->securities) { - trace_rxrpc_abort(0, "SVR", - sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EKEYREJECTED); - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; - skb->priority = sec->no_key_abort; + rxrpc_direct_abort(skb, rxrpc_abort_no_service_key, + sec->no_key_abort, -EKEYREJECTED); return NULL; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index dc3c2a834fc8..d67808b659f1 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -20,14 +20,15 @@ /* * Propose an abort to be made in the I/O thread. */ -bool rxrpc_propose_abort(struct rxrpc_call *call, - u32 abort_code, int error, const char *why) +bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, + enum rxrpc_abort_reason why) { - _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why); + _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why); if (!call->send_abort && call->state < RXRPC_CALL_COMPLETE) { call->send_abort_why = why; call->send_abort_err = error; + call->send_abort_seq = 0; /* Request abort locklessly vs rxrpc_input_call_event(). */ smp_store_release(&call->send_abort, abort_code); rxrpc_poke_call(call, rxrpc_call_poke_abort); @@ -683,7 +684,8 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) /* it's too late for this call */ ret = -ESHUTDOWN; } else if (p.command == RXRPC_CMD_SEND_ABORT) { - rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED, "CMD"); + rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED, + rxrpc_abort_call_sendmsg); ret = 0; } else if (p.command != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; @@ -748,7 +750,9 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, break; default: /* Request phase complete for this client call */ - trace_rxrpc_rx_eproto(call, 0, tracepoint_string("late_send")); + trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send, + call->cid, call->call_id, call->rx_consumed, + 0, -EPROTO); ret = -EPROTO; break; } @@ -766,17 +770,17 @@ EXPORT_SYMBOL(rxrpc_kernel_send_data); * @call: The call to be aborted * @abort_code: The abort code to stick into the ABORT packet * @error: Local error value - * @why: 3-char string indicating why. + * @why: Indication as to why. * * Allow a kernel service to abort a call, if it's still in an abortable state * and return true if the call was aborted, false if it was already complete. */ bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, - u32 abort_code, int error, const char *why) + u32 abort_code, int error, enum rxrpc_abort_reason why) { bool aborted; - _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why); + _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why); mutex_lock(&call->user_mutex); aborted = rxrpc_propose_abort(call, abort_code, error, why); From f06cb29189361353e9ed12df936c8e1d7f69b730 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 22:58:56 +0100 Subject: [PATCH 128/233] rxrpc: Make the set of connection IDs per local endpoint Make the set of connection IDs per local endpoint so that endpoints don't cause each other's connections to get dismissed. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- net/rxrpc/af_rxrpc.c | 8 -------- net/rxrpc/ar-internal.h | 5 +++-- net/rxrpc/conn_client.c | 44 +++++++++++++++++----------------------- net/rxrpc/conn_object.c | 6 +++--- net/rxrpc/local_object.c | 10 +++++++++ 5 files changed, 35 insertions(+), 38 deletions(-) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 7ea576f6ba4b..6f6a6b77ee84 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -957,16 +957,9 @@ static const struct net_proto_family rxrpc_family_ops = { static int __init af_rxrpc_init(void) { int ret = -1; - unsigned int tmp; BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); - get_random_bytes(&tmp, sizeof(tmp)); - tmp &= 0x3fffffff; - if (tmp == 0) - tmp = 1; - idr_set_cursor(&rxrpc_client_conn_ids, tmp); - ret = -ENOMEM; rxrpc_call_jar = kmem_cache_create( "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, @@ -1062,7 +1055,6 @@ static void __exit af_rxrpc_exit(void) * are released. */ rcu_barrier(); - rxrpc_destroy_client_conn_ids(); destroy_workqueue(rxrpc_workqueue); rxrpc_exit_security(); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 120ce3ccbb22..e9ab06100a21 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -300,6 +300,8 @@ struct rxrpc_local { int debug_id; /* debug ID for printks */ bool dead; bool service_closed; /* Service socket closed */ + struct idr conn_ids; /* List of connection IDs */ + spinlock_t conn_lock; /* Lock for client connection pool */ struct sockaddr_rxrpc srx; /* local address */ }; @@ -887,9 +889,8 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) extern unsigned int rxrpc_reap_client_connections; extern unsigned long rxrpc_conn_idle_client_expiry; extern unsigned long rxrpc_conn_idle_client_fast_expiry; -extern struct idr rxrpc_client_conn_ids; -void rxrpc_destroy_client_conn_ids(void); +void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local); struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 1edd65883c55..59ce5c08cf57 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -34,12 +34,6 @@ __read_mostly unsigned int rxrpc_reap_client_connections = 900; __read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ; __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; -/* - * We use machine-unique IDs for our client connections. - */ -DEFINE_IDR(rxrpc_client_conn_ids); -static DEFINE_SPINLOCK(rxrpc_conn_id_lock); - static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); /* @@ -51,65 +45,65 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, gfp_t gfp) { - struct rxrpc_net *rxnet = conn->rxnet; + struct rxrpc_local *local = conn->local; int id; _enter(""); idr_preload(gfp); - spin_lock(&rxrpc_conn_id_lock); + spin_lock(&local->conn_lock); - id = idr_alloc_cyclic(&rxrpc_client_conn_ids, conn, + id = idr_alloc_cyclic(&local->conn_ids, conn, 1, 0x40000000, GFP_NOWAIT); if (id < 0) goto error; - spin_unlock(&rxrpc_conn_id_lock); + spin_unlock(&local->conn_lock); idr_preload_end(); - conn->proto.epoch = rxnet->epoch; + conn->proto.epoch = local->rxnet->epoch; conn->proto.cid = id << RXRPC_CIDSHIFT; set_bit(RXRPC_CONN_HAS_IDR, &conn->flags); _leave(" [CID %x]", conn->proto.cid); return 0; error: - spin_unlock(&rxrpc_conn_id_lock); + spin_unlock(&local->conn_lock); idr_preload_end(); _leave(" = %d", id); return id; } /* - * Release a connection ID for a client connection from the global pool. + * Release a connection ID for a client connection. */ -static void rxrpc_put_client_connection_id(struct rxrpc_connection *conn) +static void rxrpc_put_client_connection_id(struct rxrpc_local *local, + struct rxrpc_connection *conn) { if (test_bit(RXRPC_CONN_HAS_IDR, &conn->flags)) { - spin_lock(&rxrpc_conn_id_lock); - idr_remove(&rxrpc_client_conn_ids, - conn->proto.cid >> RXRPC_CIDSHIFT); - spin_unlock(&rxrpc_conn_id_lock); + spin_lock(&local->conn_lock); + idr_remove(&local->conn_ids, conn->proto.cid >> RXRPC_CIDSHIFT); + spin_unlock(&local->conn_lock); } } /* * Destroy the client connection ID tree. */ -void rxrpc_destroy_client_conn_ids(void) +void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local) { struct rxrpc_connection *conn; int id; - if (!idr_is_empty(&rxrpc_client_conn_ids)) { - idr_for_each_entry(&rxrpc_client_conn_ids, conn, id) { + if (!idr_is_empty(&local->conn_ids)) { + idr_for_each_entry(&local->conn_ids, conn, id) { pr_err("AF_RXRPC: Leaked client conn %p {%d}\n", conn, refcount_read(&conn->ref)); } BUG(); } - idr_destroy(&rxrpc_client_conn_ids); + idr_destroy(&local->conn_ids); } /* @@ -225,7 +219,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) return conn; error_1: - rxrpc_put_client_connection_id(conn); + rxrpc_put_client_connection_id(bundle->local, conn); error_0: kfree(conn); _leave(" = %d", ret); @@ -257,7 +251,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) * times the maximum number of client conns away from the current * allocation point to try and keep the IDs concentrated. */ - id_cursor = idr_get_cursor(&rxrpc_client_conn_ids); + id_cursor = idr_get_cursor(&conn->local->conn_ids); id = conn->proto.cid >> RXRPC_CIDSHIFT; distance = id - id_cursor; if (distance < 0) @@ -982,7 +976,7 @@ void rxrpc_kill_client_conn(struct rxrpc_connection *conn) trace_rxrpc_client(conn, -1, rxrpc_client_cleanup); atomic_dec(&rxnet->nr_client_conns); - rxrpc_put_client_connection_id(conn); + rxrpc_put_client_connection_id(local, conn); } /* diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 281f59e356f5..2e3f0a222e1b 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -100,10 +100,10 @@ struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *lo _enter(",%x", sp->hdr.cid & RXRPC_CIDMASK); - /* Look up client connections by connection ID alone as their IDs are - * unique for this machine. + /* Look up client connections by connection ID alone as their + * IDs are unique for this machine. */ - conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); + conn = idr_find(&local->conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); if (!conn || refcount_read(&conn->ref) == 0) { _debug("no conn"); goto not_found; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 8ef6cd8defa4..ca8b3ee68b59 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -89,6 +89,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net, const struct sockaddr_rxrpc *srx) { struct rxrpc_local *local; + u32 tmp; local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); if (local) { @@ -109,6 +110,14 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net, local->debug_id = atomic_inc_return(&rxrpc_debug_id); memcpy(&local->srx, srx, sizeof(*srx)); local->srx.srx_service = 0; + idr_init(&local->conn_ids); + get_random_bytes(&tmp, sizeof(tmp)); + tmp &= 0x3fffffff; + if (tmp == 0) + tmp = 1; + idr_set_cursor(&local->conn_ids, tmp); + spin_lock_init(&local->conn_lock); + trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, 1); } @@ -409,6 +418,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local) * local endpoint. */ rxrpc_purge_queue(&local->rx_queue); + rxrpc_destroy_client_conn_ids(local); } /* From 2953d3b8d8fd1188034c54862b74402b0b846695 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 08:54:03 +0100 Subject: [PATCH 129/233] rxrpc: Offload the completion of service conn security to the I/O thread Offload the completion of the challenge/response cycle on a service connection to the I/O thread. After the RESPONSE packet has been successfully decrypted and verified by the work queue, offloading the changing of the call states to the I/O thread makes iteration over the conn's channel list simpler. Do this by marking the RESPONSE skbuff and putting it onto the receive queue for the I/O thread to collect. We put it on the front of the queue as we've already received the packet for it. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 2 ++ net/rxrpc/ar-internal.h | 1 + net/rxrpc/conn_event.c | 46 +++++++++++++++++++++++++----------- net/rxrpc/io_thread.c | 5 ++++ 4 files changed, 40 insertions(+), 14 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index caeabd50e049..85671f4a77de 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -126,6 +126,7 @@ #define rxrpc_skb_traces \ EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \ EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ + EM(rxrpc_skb_get_conn_secured, "GET conn-secd") \ EM(rxrpc_skb_get_conn_work, "GET conn-work") \ EM(rxrpc_skb_get_local_work, "GET locl-work") \ EM(rxrpc_skb_get_reject_work, "GET rej-work ") \ @@ -135,6 +136,7 @@ EM(rxrpc_skb_new_error_report, "NEW error-rpt") \ EM(rxrpc_skb_new_jumbo_subpacket, "NEW jumbo-sub") \ EM(rxrpc_skb_new_unshared, "NEW unshared ") \ + EM(rxrpc_skb_put_conn_secured, "PUT conn-secd") \ EM(rxrpc_skb_put_conn_work, "PUT conn-work") \ EM(rxrpc_skb_put_error_report, "PUT error-rep") \ EM(rxrpc_skb_put_input, "PUT input ") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index e9ab06100a21..e508ec221b75 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -38,6 +38,7 @@ struct rxrpc_txbuf; enum rxrpc_skb_mark { RXRPC_SKB_MARK_PACKET, /* Received packet */ RXRPC_SKB_MARK_ERROR, /* Error notification */ + RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */ RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ }; diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 485d7f0fed2c..b2042702ca9a 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -248,7 +248,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - int loop, ret; + int ret; if (conn->state == RXRPC_CONN_ABORTED) return -ECONNABORTED; @@ -269,22 +269,21 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, if (ret < 0) return ret; - spin_lock(&conn->bundle->channel_lock); spin_lock(&conn->state_lock); - - if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { + if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) conn->state = RXRPC_CONN_SERVICE; - spin_unlock(&conn->state_lock); - for (loop = 0; loop < RXRPC_MAXCALLS; loop++) - rxrpc_call_is_secure( - rcu_dereference_protected( - conn->channels[loop].call, - lockdep_is_held(&conn->bundle->channel_lock))); - } else { - spin_unlock(&conn->state_lock); - } + spin_unlock(&conn->state_lock); - spin_unlock(&conn->bundle->channel_lock); + if (conn->state == RXRPC_CONN_SERVICE) { + /* Offload call state flipping to the I/O thread. As + * we've already received the packet, put it on the + * front of the queue. + */ + skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED; + rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured); + skb_queue_head(&conn->local->rx_queue, skb); + rxrpc_wake_up_io_thread(conn->local); + } return 0; default: @@ -442,9 +441,28 @@ bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) */ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb) { + unsigned int loop; + if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events)) rxrpc_abort_calls(conn); + switch (skb->mark) { + case RXRPC_SKB_MARK_SERVICE_CONN_SECURED: + if (conn->state != RXRPC_CONN_SERVICE) + break; + + spin_lock(&conn->bundle->channel_lock); + + for (loop = 0; loop < RXRPC_MAXCALLS; loop++) + rxrpc_call_is_secure( + rcu_dereference_protected( + conn->channels[loop].call, + lockdep_is_held(&conn->bundle->channel_lock))); + + spin_unlock(&conn->bundle->channel_lock); + break; + } + /* Process delayed ACKs whose time has come. */ if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) rxrpc_process_delayed_final_acks(conn, false); diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 33fd2394c8b3..751139b3c1ac 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -451,6 +451,7 @@ int rxrpc_io_thread(void *data) /* Process received packets and errors. */ if ((skb = __skb_dequeue(&rx_queue))) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); switch (skb->mark) { case RXRPC_SKB_MARK_PACKET: skb->priority = 0; @@ -463,6 +464,10 @@ int rxrpc_io_thread(void *data) rxrpc_input_error(local, skb); rxrpc_free_skb(skb, rxrpc_skb_put_error_report); break; + case RXRPC_SKB_MARK_SERVICE_CONN_SECURED: + rxrpc_input_conn_event(sp->conn, skb); + rxrpc_put_connection(sp->conn, rxrpc_conn_put_poke); + rxrpc_free_skb(skb, rxrpc_skb_put_conn_secured); break; default: WARN_ON_ONCE(1); From 1bab27af6b88b5c811f99de4812b5590f20d1cb7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 09:30:23 +0100 Subject: [PATCH 130/233] rxrpc: Set up a connection bundle from a call, not rxrpc_conn_parameters Use the information now stored in struct rxrpc_call to configure the connection bundle and thence the connection, rather than using the rxrpc_conn_parameters struct. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 3 +- net/rxrpc/af_rxrpc.c | 1 - net/rxrpc/ar-internal.h | 8 +-- net/rxrpc/call_object.c | 4 +- net/rxrpc/conn_client.c | 132 ++++++++++++++++++----------------- net/rxrpc/conn_object.c | 2 +- net/rxrpc/sendmsg.c | 1 - 7 files changed, 76 insertions(+), 75 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 85671f4a77de..e2f6b79d5517 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -178,7 +178,6 @@ #define rxrpc_peer_traces \ EM(rxrpc_peer_free, "FREE ") \ EM(rxrpc_peer_get_accept, "GET accept ") \ - EM(rxrpc_peer_get_activate_call, "GET act-call") \ EM(rxrpc_peer_get_bundle, "GET bundle ") \ EM(rxrpc_peer_get_client_conn, "GET cln-conn") \ EM(rxrpc_peer_get_input, "GET input ") \ @@ -191,7 +190,6 @@ EM(rxrpc_peer_put_bundle, "PUT bundle ") \ EM(rxrpc_peer_put_call, "PUT call ") \ EM(rxrpc_peer_put_conn, "PUT conn ") \ - EM(rxrpc_peer_put_discard_tmp, "PUT disc-tmp") \ EM(rxrpc_peer_put_input, "PUT input ") \ EM(rxrpc_peer_put_input_error, "PUT inpt-err") \ E_(rxrpc_peer_put_keepalive, "PUT keepaliv") @@ -201,6 +199,7 @@ EM(rxrpc_bundle_get_client_call, "GET clt-call") \ EM(rxrpc_bundle_get_client_conn, "GET clt-conn") \ EM(rxrpc_bundle_get_service_conn, "GET svc-conn") \ + EM(rxrpc_bundle_put_call, "PUT call ") \ EM(rxrpc_bundle_put_conn, "PUT conn ") \ EM(rxrpc_bundle_put_discard, "PUT discard ") \ E_(rxrpc_bundle_new, "NEW ") diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 6f6a6b77ee84..f4e1ffff2ba4 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -328,7 +328,6 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, mutex_unlock(&call->user_mutex); } - rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp); _leave(" = %p", call); return call; } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index e508ec221b75..2740c6333114 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -360,7 +360,6 @@ struct rxrpc_conn_proto { struct rxrpc_conn_parameters { struct rxrpc_local *local; /* Representation of local endpoint */ - struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* Security details */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ @@ -428,6 +427,7 @@ struct rxrpc_bundle { struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* Security details */ + const struct rxrpc_security *security; /* applied security module */ refcount_t ref; atomic_t active; /* Number of active users */ unsigned int debug_id; @@ -593,6 +593,7 @@ enum rxrpc_congest_mode { struct rxrpc_call { struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ + struct rxrpc_bundle *bundle; /* Connection bundle to use */ struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_sock __rcu *socket; /* socket responsible */ @@ -894,11 +895,10 @@ extern unsigned long rxrpc_conn_idle_client_fast_expiry; void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local); struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); -int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, - struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, - gfp_t); +int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); +void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_discard_expired_client_conns(struct work_struct *); void rxrpc_destroy_all_client_connections(struct rxrpc_net *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 705f6e26cc75..835e9781afc6 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -365,7 +365,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, /* Set up or get a connection record and set the protocol parameters, * including channel number and call ID. */ - ret = rxrpc_connect_call(rx, call, cp, srx, gfp); + ret = rxrpc_connect_call(call, gfp); if (ret < 0) goto error_attached_to_socket; @@ -663,6 +663,8 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); rxrpc_put_connection(call->conn, rxrpc_conn_put_call); + rxrpc_deactivate_bundle(call->bundle); + rxrpc_put_bundle(call->bundle, rxrpc_bundle_put_call); rxrpc_put_peer(call->peer, rxrpc_peer_put_call); rxrpc_put_local(call->local, rxrpc_local_put_call); call_rcu(&call->rcu, rxrpc_rcu_free_call); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 59ce5c08cf57..c0db7722571e 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -34,7 +34,10 @@ __read_mostly unsigned int rxrpc_reap_client_connections = 900; __read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ; __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; -static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); +static void rxrpc_activate_bundle(struct rxrpc_bundle *bundle) +{ + atomic_inc(&bundle->active); +} /* * Get a connection ID and epoch for a client connection from the global pool. @@ -109,20 +112,21 @@ void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local) /* * Allocate a connection bundle. */ -static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, +static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call, gfp_t gfp) { struct rxrpc_bundle *bundle; bundle = kzalloc(sizeof(*bundle), gfp); if (bundle) { - bundle->local = cp->local; - bundle->peer = rxrpc_get_peer(cp->peer, rxrpc_peer_get_bundle); - bundle->key = cp->key; - bundle->exclusive = cp->exclusive; - bundle->upgrade = cp->upgrade; - bundle->service_id = cp->service_id; - bundle->security_level = cp->security_level; + bundle->local = call->local; + bundle->peer = rxrpc_get_peer(call->peer, rxrpc_peer_get_bundle); + bundle->key = key_get(call->key); + bundle->security = call->security; + bundle->exclusive = test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags); + bundle->upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags); + bundle->service_id = call->dest_srx.srx_service; + bundle->security_level = call->security_level; refcount_set(&bundle->ref, 1); atomic_set(&bundle->active, 1); spin_lock_init(&bundle->channel_lock); @@ -146,19 +150,23 @@ static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) { trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free); rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle); + key_put(bundle->key); kfree(bundle); } void rxrpc_put_bundle(struct rxrpc_bundle *bundle, enum rxrpc_bundle_trace why) { - unsigned int id = bundle->debug_id; + unsigned int id; bool dead; int r; - dead = __refcount_dec_and_test(&bundle->ref, &r); - trace_rxrpc_bundle(id, r - 1, why); - if (dead) - rxrpc_free_bundle(bundle); + if (bundle) { + id = bundle->debug_id; + dead = __refcount_dec_and_test(&bundle->ref, &r); + trace_rxrpc_bundle(id, r - 1, why); + if (dead) + rxrpc_free_bundle(bundle); + } } /* @@ -272,20 +280,23 @@ dont_reuse: * Look up the conn bundle that matches the connection parameters, adding it if * it doesn't yet exist. */ -static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *cp, - gfp_t gfp) +static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp) { static atomic_t rxrpc_bundle_id; struct rxrpc_bundle *bundle, *candidate; - struct rxrpc_local *local = cp->local; + struct rxrpc_local *local = call->local; struct rb_node *p, **pp, *parent; long diff; + bool upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags); _enter("{%px,%x,%u,%u}", - cp->peer, key_serial(cp->key), cp->security_level, cp->upgrade); + call->peer, key_serial(call->key), call->security_level, + upgrade); - if (cp->exclusive) - return rxrpc_alloc_bundle(cp, gfp); + if (test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags)) { + call->bundle = rxrpc_alloc_bundle(call, gfp); + return call->bundle; + } /* First, see if the bundle is already there. */ _debug("search 1"); @@ -294,11 +305,11 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c while (p) { bundle = rb_entry(p, struct rxrpc_bundle, local_node); -#define cmp(X) ((long)bundle->X - (long)cp->X) - diff = (cmp(peer) ?: - cmp(key) ?: - cmp(security_level) ?: - cmp(upgrade)); +#define cmp(X, Y) ((long)(X) - (long)(Y)) + diff = (cmp(bundle->peer, call->peer) ?: + cmp(bundle->key, call->key) ?: + cmp(bundle->security_level, call->security_level) ?: + cmp(bundle->upgrade, upgrade)); #undef cmp if (diff < 0) p = p->rb_left; @@ -311,9 +322,9 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c _debug("not found"); /* It wasn't. We need to add one. */ - candidate = rxrpc_alloc_bundle(cp, gfp); + candidate = rxrpc_alloc_bundle(call, gfp); if (!candidate) - return NULL; + return ERR_PTR(-ENOMEM); _debug("search 2"); spin_lock(&local->client_bundles_lock); @@ -323,11 +334,11 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c parent = *pp; bundle = rb_entry(parent, struct rxrpc_bundle, local_node); -#define cmp(X) ((long)bundle->X - (long)cp->X) - diff = (cmp(peer) ?: - cmp(key) ?: - cmp(security_level) ?: - cmp(upgrade)); +#define cmp(X, Y) ((long)(X) - (long)(Y)) + diff = (cmp(bundle->peer, call->peer) ?: + cmp(bundle->key, call->key) ?: + cmp(bundle->security_level, call->security_level) ?: + cmp(bundle->upgrade, upgrade)); #undef cmp if (diff < 0) pp = &(*pp)->rb_left; @@ -341,19 +352,19 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id); rb_link_node(&candidate->local_node, parent, pp); rb_insert_color(&candidate->local_node, &local->client_bundles); - rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call); + call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call); spin_unlock(&local->client_bundles_lock); - _leave(" = %u [new]", candidate->debug_id); - return candidate; + _leave(" = B=%u [new]", call->bundle->debug_id); + return call->bundle; found_bundle_free: rxrpc_free_bundle(candidate); found_bundle: - rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call); - atomic_inc(&bundle->active); + call->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call); + rxrpc_activate_bundle(bundle); spin_unlock(&local->client_bundles_lock); - _leave(" = %u [found]", bundle->debug_id); - return bundle; + _leave(" = B=%u [found]", call->bundle->debug_id); + return call->bundle; } /* @@ -362,31 +373,25 @@ found_bundle: * If we return with a connection, the call will be on its waiting list. It's * left to the caller to assign a channel and wake up the call. */ -static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) +static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_call *call, gfp_t gfp) { struct rxrpc_bundle *bundle; _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp); - if (!cp->peer) + call->peer = rxrpc_lookup_peer(call->local, &call->dest_srx, gfp); + if (!call->peer) goto error; call->tx_last_sent = ktime_get_real(); - call->cong_ssthresh = cp->peer->cong_ssthresh; + call->cong_ssthresh = call->peer->cong_ssthresh; if (call->cong_cwnd >= call->cong_ssthresh) call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; else call->cong_mode = RXRPC_CALL_SLOW_START; - if (cp->upgrade) - __set_bit(RXRPC_CALL_UPGRADE, &call->flags); /* Find the client connection bundle. */ - bundle = rxrpc_look_up_bundle(cp, gfp); + bundle = rxrpc_look_up_bundle(call, gfp); if (!bundle) goto error; @@ -449,7 +454,7 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) if (old) trace_rxrpc_client(old, -1, rxrpc_client_replace); candidate->bundle_shift = shift; - atomic_inc(&bundle->active); + rxrpc_activate_bundle(bundle); bundle->conns[i] = candidate; for (j = 0; j < RXRPC_MAXCALLS; j++) set_bit(shift + j, &bundle->avail_chans); @@ -541,7 +546,6 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, rxrpc_see_call(call, rxrpc_call_see_activate_client); list_del_init(&call->chan_wait_link); - call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call); call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call); call->cid = conn->proto.cid | channel; call->call_id = call_id; @@ -705,14 +709,11 @@ out: * find a connection for a call * - called in process context with IRQs enabled */ -int rxrpc_connect_call(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) +int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp) { struct rxrpc_bundle *bundle; - struct rxrpc_net *rxnet = cp->local->rxnet; + struct rxrpc_local *local = call->local; + struct rxrpc_net *rxnet = local->rxnet; int ret = 0; _enter("{%d,%lx},", call->debug_id, call->user_call_ID); @@ -721,7 +722,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, rxrpc_get_call(call, rxrpc_call_get_io_thread); - bundle = rxrpc_prep_call(rx, call, cp, srx, gfp); + bundle = rxrpc_prep_call(call, gfp); if (IS_ERR(bundle)) { rxrpc_put_call(call, rxrpc_call_get_io_thread); ret = PTR_ERR(bundle); @@ -738,9 +739,6 @@ granted_channel: /* Paired with the write barrier in rxrpc_activate_one_channel(). */ smp_rmb(); -out_put_bundle: - rxrpc_deactivate_bundle(bundle); - rxrpc_put_bundle(bundle, rxrpc_bundle_get_client_call); out: _leave(" = %d", ret); return ret; @@ -758,7 +756,7 @@ wait_failed: trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed); rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); rxrpc_disconnect_client_call(bundle, call); - goto out_put_bundle; + goto out; } /* @@ -945,11 +943,15 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) /* * Drop the active count on a bundle. */ -static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) +void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) { - struct rxrpc_local *local = bundle->local; + struct rxrpc_local *local; bool need_put = false; + if (!bundle) + return; + + local = bundle->local; if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) { if (!bundle->exclusive) { _debug("erase bundle"); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 2e3f0a222e1b..2a7d5378300c 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -208,7 +208,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) } if (rxrpc_is_client_call(call)) { - rxrpc_disconnect_client_call(conn->bundle, call); + rxrpc_disconnect_client_call(call->bundle, call); } else { spin_lock(&conn->bundle->channel_lock); __rxrpc_disconnect_call(conn, call); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index d67808b659f1..2a003c3a9897 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -564,7 +564,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, atomic_inc_return(&rxrpc_debug_id)); /* The socket is now unlocked */ - rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp); _leave(" = %p\n", call); return call; } From 0b9bb322f13d486d5b8630264ccbfb4794bb43a9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Oct 2022 00:16:55 +0100 Subject: [PATCH 131/233] rxrpc: Split out the call state changing functions into their own file Split out the functions that change the state of an rxrpc call into their own file. The idea being to remove anything to do with changing the state of a call directly from the rxrpc sendmsg() and recvmsg() paths and have all that done in the I/O thread only, with the ultimate aim of removing the state lock entirely. Moving the code out of sendmsg.c and recvmsg.c makes that easier to manage. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- net/rxrpc/Makefile | 1 + net/rxrpc/ar-internal.h | 26 ++++++++---- net/rxrpc/call_state.c | 89 +++++++++++++++++++++++++++++++++++++++++ net/rxrpc/recvmsg.c | 81 ------------------------------------- 4 files changed, 108 insertions(+), 89 deletions(-) create mode 100644 net/rxrpc/call_state.c diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index e76d3459d78e..ac5caf5a48e1 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -10,6 +10,7 @@ rxrpc-y := \ call_accept.o \ call_event.o \ call_object.o \ + call_state.o \ conn_client.o \ conn_event.o \ conn_object.o \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 2740c6333114..203e0354d86b 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -885,6 +885,24 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) return !rxrpc_is_service_call(call); } +/* + * call_state.c + */ +bool __rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error); +bool rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error); +bool __rxrpc_call_completed(struct rxrpc_call *call); +bool rxrpc_call_completed(struct rxrpc_call *call); +bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why); +bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why); + /* * conn_client.c */ @@ -1116,14 +1134,6 @@ extern const struct seq_operations rxrpc_local_seq_ops; * recvmsg.c */ void rxrpc_notify_socket(struct rxrpc_call *); -bool __rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int); -bool rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int); -bool __rxrpc_call_completed(struct rxrpc_call *); -bool rxrpc_call_completed(struct rxrpc_call *); -bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, - u32 abort_code, int error, enum rxrpc_abort_reason why); -bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, - u32 abort_code, int error, enum rxrpc_abort_reason why); int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* diff --git a/net/rxrpc/call_state.c b/net/rxrpc/call_state.c new file mode 100644 index 000000000000..8fbb2112ed7e --- /dev/null +++ b/net/rxrpc/call_state.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Call state changing functions. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include "ar-internal.h" + +/* + * Transition a call to the complete state. + */ +bool __rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error) +{ + if (call->state < RXRPC_CALL_COMPLETE) { + call->abort_code = abort_code; + call->error = error; + call->completion = compl; + call->state = RXRPC_CALL_COMPLETE; + trace_rxrpc_call_complete(call); + wake_up(&call->waitq); + rxrpc_notify_socket(call); + return true; + } + return false; +} + +bool rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error) +{ + bool ret = false; + + if (call->state < RXRPC_CALL_COMPLETE) { + write_lock(&call->state_lock); + ret = __rxrpc_set_call_completion(call, compl, abort_code, error); + write_unlock(&call->state_lock); + } + return ret; +} + +/* + * Record that a call successfully completed. + */ +bool __rxrpc_call_completed(struct rxrpc_call *call) +{ + return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); +} + +bool rxrpc_call_completed(struct rxrpc_call *call) +{ + bool ret = false; + + if (call->state < RXRPC_CALL_COMPLETE) { + write_lock(&call->state_lock); + ret = __rxrpc_call_completed(call); + write_unlock(&call->state_lock); + } + return ret; +} + +/* + * Record that a call is locally aborted. + */ +bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why) +{ + trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq, + abort_code, error); + return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED, + abort_code, error); +} + +bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why) +{ + bool ret; + + write_lock(&call->state_lock); + ret = __rxrpc_abort_call(call, seq, abort_code, error, why); + write_unlock(&call->state_lock); + if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags)) + rxrpc_send_abort_packet(call); + return ret; +} diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 59b521b82aec..ff08f917ecda 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -58,87 +58,6 @@ void rxrpc_notify_socket(struct rxrpc_call *call) _leave(""); } -/* - * Transition a call to the complete state. - */ -bool __rxrpc_set_call_completion(struct rxrpc_call *call, - enum rxrpc_call_completion compl, - u32 abort_code, - int error) -{ - if (call->state < RXRPC_CALL_COMPLETE) { - call->abort_code = abort_code; - call->error = error; - call->completion = compl; - call->state = RXRPC_CALL_COMPLETE; - trace_rxrpc_call_complete(call); - wake_up(&call->waitq); - rxrpc_notify_socket(call); - return true; - } - return false; -} - -bool rxrpc_set_call_completion(struct rxrpc_call *call, - enum rxrpc_call_completion compl, - u32 abort_code, - int error) -{ - bool ret = false; - - if (call->state < RXRPC_CALL_COMPLETE) { - write_lock(&call->state_lock); - ret = __rxrpc_set_call_completion(call, compl, abort_code, error); - write_unlock(&call->state_lock); - } - return ret; -} - -/* - * Record that a call successfully completed. - */ -bool __rxrpc_call_completed(struct rxrpc_call *call) -{ - return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); -} - -bool rxrpc_call_completed(struct rxrpc_call *call) -{ - bool ret = false; - - if (call->state < RXRPC_CALL_COMPLETE) { - write_lock(&call->state_lock); - ret = __rxrpc_call_completed(call); - write_unlock(&call->state_lock); - } - return ret; -} - -/* - * Record that a call is locally aborted. - */ -bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, - u32 abort_code, int error, enum rxrpc_abort_reason why) -{ - trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq, - abort_code, error); - return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED, - abort_code, error); -} - -bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, - u32 abort_code, int error, enum rxrpc_abort_reason why) -{ - bool ret; - - write_lock(&call->state_lock); - ret = __rxrpc_abort_call(call, seq, abort_code, error, why); - write_unlock(&call->state_lock); - if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags)) - rxrpc_send_abort_packet(call); - return ret; -} - /* * Pass a call terminating message to userspace. */ From d41b3f5b96881809c73f86e3ca436c9426610b7a Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 19 Dec 2022 15:32:32 +0000 Subject: [PATCH 132/233] rxrpc: Wrap accesses to get call state to put the barrier in one place Wrap accesses to get the state of a call from outside of the I/O thread in a single place so that the barrier needed to order wrt the error code and abort code is in just that place. Also use a barrier when setting the call state and again when reading the call state such that the auxiliary completion info (error code, abort code) can be read without taking a read lock on the call state lock. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- net/rxrpc/af_rxrpc.c | 2 +- net/rxrpc/ar-internal.h | 16 ++++++++++++++++ net/rxrpc/call_state.c | 3 ++- net/rxrpc/recvmsg.c | 12 ++++++------ net/rxrpc/sendmsg.c | 29 +++++++++++++---------------- 5 files changed, 38 insertions(+), 24 deletions(-) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index f4e1ffff2ba4..61c30d0f6735 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -379,7 +379,7 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call); bool rxrpc_kernel_check_life(const struct socket *sock, const struct rxrpc_call *call) { - return call->state != RXRPC_CALL_COMPLETE; + return !rxrpc_call_is_complete(call); } EXPORT_SYMBOL(rxrpc_kernel_check_life); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 203e0354d86b..9e992487649c 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -903,6 +903,22 @@ bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, u32 abort_code, int error, enum rxrpc_abort_reason why); +static inline enum rxrpc_call_state rxrpc_call_state(const struct rxrpc_call *call) +{ + /* Order read ->state before read ->error. */ + return smp_load_acquire(&call->state); +} + +static inline bool rxrpc_call_is_complete(const struct rxrpc_call *call) +{ + return rxrpc_call_state(call) == RXRPC_CALL_COMPLETE; +} + +static inline bool rxrpc_call_has_failed(const struct rxrpc_call *call) +{ + return rxrpc_call_is_complete(call) && call->completion != RXRPC_CALL_SUCCEEDED; +} + /* * conn_client.c */ diff --git a/net/rxrpc/call_state.c b/net/rxrpc/call_state.c index 8fbb2112ed7e..649fb9e5d1af 100644 --- a/net/rxrpc/call_state.c +++ b/net/rxrpc/call_state.c @@ -19,7 +19,8 @@ bool __rxrpc_set_call_completion(struct rxrpc_call *call, call->abort_code = abort_code; call->error = error; call->completion = compl; - call->state = RXRPC_CALL_COMPLETE; + /* Allow reader of completion state to operate locklessly */ + smp_store_release(&call->state, RXRPC_CALL_COMPLETE); trace_rxrpc_call_complete(call); wake_up(&call->waitq); rxrpc_notify_socket(call); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index ff08f917ecda..7bf36a8839ec 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -89,7 +89,7 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, &tmp); break; default: - pr_err("Invalid terminal call state %u\n", call->state); + pr_err("Invalid terminal call state %u\n", call->completion); BUG(); break; } @@ -111,7 +111,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); - if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) + if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_RECV_REPLY) rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); write_lock(&call->state_lock); @@ -210,7 +210,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; - if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { + if (rxrpc_call_state(call) >= RXRPC_CALL_SERVER_ACK_REQUEST) { seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; ret = 1; goto done; @@ -416,7 +416,7 @@ try_again: msg->msg_namelen = len; } - switch (READ_ONCE(call->state)) { + switch (rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_RECV_REPLY: case RXRPC_CALL_SERVER_RECV_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: @@ -436,7 +436,7 @@ try_again: if (ret < 0) goto error_unlock_call; - if (call->state == RXRPC_CALL_COMPLETE) { + if (rxrpc_call_is_complete(call)) { ret = rxrpc_recvmsg_term(call, msg); if (ret < 0) goto error_unlock_call; @@ -516,7 +516,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, mutex_lock(&call->user_mutex); - switch (READ_ONCE(call->state)) { + switch (rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_RECV_REPLY: case RXRPC_CALL_SERVER_RECV_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 2a003c3a9897..f0b5822f3e04 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -25,7 +25,7 @@ bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, { _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why); - if (!call->send_abort && call->state < RXRPC_CALL_COMPLETE) { + if (!call->send_abort && !rxrpc_call_is_complete(call)) { call->send_abort_why = why; call->send_abort_err = error; call->send_abort_seq = 0; @@ -60,7 +60,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, if (rxrpc_check_tx_space(call, NULL)) return 0; - if (call->state >= RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) return call->error; if (signal_pending(current)) @@ -95,7 +95,7 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, if (rxrpc_check_tx_space(call, &tx_win)) return 0; - if (call->state >= RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) return call->error; if (timeout == 0 && @@ -124,7 +124,7 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, if (rxrpc_check_tx_space(call, NULL)) return 0; - if (call->state >= RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) return call->error; trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); @@ -273,7 +273,7 @@ reload: ret = -EPIPE; if (sk->sk_shutdown & SEND_SHUTDOWN) goto maybe_error; - state = READ_ONCE(call->state); + state = rxrpc_call_state(call); ret = -ESHUTDOWN; if (state >= RXRPC_CALL_COMPLETE) goto maybe_error; @@ -350,7 +350,7 @@ reload: /* check for the far side aborting the call or a network error * occurring */ - if (call->state == RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) goto call_terminated; /* add the packet to the send queue if it's now full */ @@ -375,12 +375,9 @@ reload: success: ret = copied; - if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) { - read_lock(&call->state_lock); - if (call->error < 0) - ret = call->error; - read_unlock(&call->state_lock); - } + if (rxrpc_call_is_complete(call) && + call->error < 0) + ret = call->error; out: call->tx_pending = txb; _leave(" = %d", ret); @@ -618,10 +615,10 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) return PTR_ERR(call); /* ... and we have the call lock. */ ret = 0; - if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) goto out_put_unlock; } else { - switch (READ_ONCE(call->state)) { + switch (rxrpc_call_state(call)) { case RXRPC_CALL_UNINITIALISED: case RXRPC_CALL_CLIENT_AWAIT_CONN: case RXRPC_CALL_SERVER_PREALLOC: @@ -675,7 +672,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) break; } - state = READ_ONCE(call->state); + state = rxrpc_call_state(call); _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, state, call->conn); @@ -735,7 +732,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, call->state, call->conn); - switch (READ_ONCE(call->state)) { + switch (rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: case RXRPC_CALL_SERVER_SEND_REPLY: From 2d689424b6184535890c251f937ccf815fde9cd2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Nov 2022 08:35:36 +0000 Subject: [PATCH 133/233] rxrpc: Move call state changes from sendmsg to I/O thread Move all the call state changes that are made in rxrpc_sendmsg() to the I/O thread. This is a step towards removing the call state lock. This requires the switch to the RXRPC_CALL_CLIENT_AWAIT_REPLY and RXRPC_CALL_SERVER_SEND_REPLY states to be done when the last packet is decanted from ->tx_sendmsg to ->tx_buffer in the I/O thread, not when it is added to ->tx_sendmsg by sendmsg(). Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- Documentation/networking/rxrpc.rst | 4 +- net/rxrpc/call_event.c | 50 +++++++++++++++++++++- net/rxrpc/sendmsg.c | 69 ++++++------------------------ 3 files changed, 63 insertions(+), 60 deletions(-) diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst index 39494a6ea739..e1af54424192 100644 --- a/Documentation/networking/rxrpc.rst +++ b/Documentation/networking/rxrpc.rst @@ -880,8 +880,8 @@ The kernel interface functions are as follows: notify_end_rx can be NULL or it can be used to specify a function to be called when the call changes state to end the Tx phase. This function is - called with the call-state spinlock held to prevent any reply or final ACK - from being delivered first. + called with a spinlock held to prevent the last DATA packet from being + transmitted until the function returns. (#) Receive data from a call:: diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 695aeb70d1a6..2e3c01060d59 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -251,6 +251,50 @@ out: _leave(""); } +/* + * Start transmitting the reply to a service. This cancels the need to ACK the + * request if we haven't yet done so. + */ +static void rxrpc_begin_service_reply(struct rxrpc_call *call) +{ + unsigned long now; + + write_lock(&call->state_lock); + + if (call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { + now = jiffies; + call->state = RXRPC_CALL_SERVER_SEND_REPLY; + WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); + if (call->ackr_reason == RXRPC_ACK_DELAY) + call->ackr_reason = 0; + trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); + } + + write_unlock(&call->state_lock); +} + +/* + * Close the transmission phase. After this point there is no more data to be + * transmitted in the call. + */ +static void rxrpc_close_tx_phase(struct rxrpc_call *call) +{ + _debug("________awaiting reply/ACK__________"); + + write_lock(&call->state_lock); + switch (call->state) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + break; + case RXRPC_CALL_SERVER_SEND_REPLY: + call->state = RXRPC_CALL_SERVER_AWAIT_ACK; + break; + default: + break; + } + write_unlock(&call->state_lock); +} + static bool rxrpc_tx_window_has_space(struct rxrpc_call *call) { unsigned int winsize = min_t(unsigned int, call->tx_winsize, @@ -285,6 +329,9 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) call->tx_top = txb->seq; list_add_tail(&txb->call_link, &call->tx_buffer); + if (txb->wire.flags & RXRPC_LAST_PACKET) + rxrpc_close_tx_phase(call); + rxrpc_transmit_one(call, txb); if (!rxrpc_tx_window_has_space(call)) @@ -298,12 +345,11 @@ static void rxrpc_transmit_some_data(struct rxrpc_call *call) case RXRPC_CALL_SERVER_ACK_REQUEST: if (list_empty(&call->tx_sendmsg)) return; + rxrpc_begin_service_reply(call); fallthrough; case RXRPC_CALL_SERVER_SEND_REPLY: - case RXRPC_CALL_SERVER_AWAIT_ACK: case RXRPC_CALL_CLIENT_SEND_REQUEST: - case RXRPC_CALL_CLIENT_AWAIT_REPLY: if (!rxrpc_tx_window_has_space(call)) return; if (list_empty(&call->tx_sendmsg)) { diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index f0b5822f3e04..0428528abbf4 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -189,7 +189,6 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, struct rxrpc_txbuf *txb, rxrpc_notify_end_tx_t notify_end_tx) { - unsigned long now; rxrpc_seq_t seq = txb->seq; bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke; @@ -212,36 +211,10 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, poke = list_empty(&call->tx_sendmsg); list_add_tail(&txb->call_link, &call->tx_sendmsg); call->tx_prepared = seq; + if (last) + rxrpc_notify_end_tx(rx, call, notify_end_tx); spin_unlock(&call->tx_lock); - if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { - _debug("________awaiting reply/ACK__________"); - write_lock(&call->state_lock); - switch (call->state) { - case RXRPC_CALL_CLIENT_SEND_REQUEST: - call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; - rxrpc_notify_end_tx(rx, call, notify_end_tx); - break; - case RXRPC_CALL_SERVER_ACK_REQUEST: - call->state = RXRPC_CALL_SERVER_SEND_REPLY; - now = jiffies; - WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); - if (call->ackr_reason == RXRPC_ACK_DELAY) - call->ackr_reason = 0; - trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); - if (!last) - break; - fallthrough; - case RXRPC_CALL_SERVER_SEND_REPLY: - call->state = RXRPC_CALL_SERVER_AWAIT_ACK; - rxrpc_notify_end_tx(rx, call, notify_end_tx); - break; - default: - break; - } - write_unlock(&call->state_lock); - } - if (poke) rxrpc_poke_call(call, rxrpc_call_poke_start); } @@ -280,8 +253,13 @@ reload: ret = -EPROTO; if (state != RXRPC_CALL_CLIENT_SEND_REQUEST && state != RXRPC_CALL_SERVER_ACK_REQUEST && - state != RXRPC_CALL_SERVER_SEND_REPLY) + state != RXRPC_CALL_SERVER_SEND_REPLY) { + /* Request phase complete for this client call */ + trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send, + call->cid, call->call_id, call->rx_consumed, + 0, -EPROTO); goto maybe_error; + } ret = -EMSGSIZE; if (call->tx_total_len != -1) { @@ -573,7 +551,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) { - enum rxrpc_call_state state; struct rxrpc_call *call; unsigned long now, j; bool dropped_lock = false; @@ -672,11 +649,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) break; } - state = rxrpc_call_state(call); - _debug("CALL %d USR %lx ST %d on CONN %p", - call->debug_id, call->user_call_ID, state, call->conn); - - if (state >= RXRPC_CALL_COMPLETE) { + if (rxrpc_call_is_complete(call)) { /* it's too late for this call */ ret = -ESHUTDOWN; } else if (p.command == RXRPC_CMD_SEND_ABORT) { @@ -722,7 +695,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, bool dropped_lock = false; int ret; - _enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]); + _enter("{%d},", call->debug_id); ASSERTCMP(msg->msg_name, ==, NULL); ASSERTCMP(msg->msg_control, ==, NULL); @@ -732,26 +705,10 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, call->state, call->conn); - switch (rxrpc_call_state(call)) { - case RXRPC_CALL_CLIENT_SEND_REQUEST: - case RXRPC_CALL_SERVER_ACK_REQUEST: - case RXRPC_CALL_SERVER_SEND_REPLY: - ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len, - notify_end_tx, &dropped_lock); - break; - case RXRPC_CALL_COMPLETE: - read_lock(&call->state_lock); + ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len, + notify_end_tx, &dropped_lock); + if (ret == -ESHUTDOWN) ret = call->error; - read_unlock(&call->state_lock); - break; - default: - /* Request phase complete for this client call */ - trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send, - call->cid, call->call_id, call->rx_consumed, - 0, -EPROTO); - ret = -EPROTO; - break; - } if (!dropped_lock) mutex_unlock(&call->user_mutex); From 93368b6bd58ac49d804fdc9ab041a6dc89ebf1cc Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 26 Oct 2022 23:43:00 +0100 Subject: [PATCH 134/233] rxrpc: Move call state changes from recvmsg to I/O thread Move the call state changes that are made in rxrpc_recvmsg() to the I/O thread. This means that, thenceforth, only the I/O thread does this and the call state lock can be removed. This requires the Rx phase to be ended when the last packet is received, not when it is processed. Since this now changes the rxrpc call state to SUCCEEDED before we've consumed all the data from it, rxrpc_kernel_check_life() mustn't say the call is dead until the recvmsg queue is empty (unless the call has failed). Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- fs/afs/rxrpc.c | 1 + net/rxrpc/af_rxrpc.c | 10 ++- net/rxrpc/ar-internal.h | 3 +- net/rxrpc/input.c | 38 ++++++++- net/rxrpc/recvmsg.c | 168 +++++++++++++++------------------------- 5 files changed, 109 insertions(+), 111 deletions(-) diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index bd3830bc6700..7817e2b860e5 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -909,6 +909,7 @@ int afs_extract_data(struct afs_call *call, bool want_more) ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, iter, &call->iov_len, want_more, &remote_abort, &call->service_id); + trace_afs_receive_data(call, call->iter, want_more, ret); if (ret == 0 || ret == -EAGAIN) return ret; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 61c30d0f6735..cf200e4e0eae 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -373,13 +373,17 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call); * @sock: The socket the call is on * @call: The call to check * - * Allow a kernel service to find out whether a call is still alive - - * ie. whether it has completed. + * Allow a kernel service to find out whether a call is still alive - whether + * it has completed successfully and all received data has been consumed. */ bool rxrpc_kernel_check_life(const struct socket *sock, const struct rxrpc_call *call) { - return !rxrpc_call_is_complete(call); + if (!rxrpc_call_is_complete(call)) + return true; + if (call->completion != RXRPC_CALL_SUCCEEDED) + return false; + return !skb_queue_empty(&call->recvmsg_queue); } EXPORT_SYMBOL(rxrpc_kernel_check_life); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 9e992487649c..861273439736 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -545,7 +545,8 @@ enum rxrpc_call_flag { RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */ - RXRPC_CALL_RX_IS_IDLE, /* Reception is idle - send an ACK */ + RXRPC_CALL_RX_IS_IDLE, /* recvmsg() is idle - send an ACK */ + RXRPC_CALL_RECVMSG_READ_ALL, /* recvmsg() read all of the received data */ }; /* diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index bd69ff2d9082..6eb21425f41f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -319,6 +319,41 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) return true; } +/* + * End the packet reception phase. + */ +static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) +{ + rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); + + _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]); + + trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); + + if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_RECV_REPLY) + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); + + write_lock(&call->state_lock); + + switch (call->state) { + case RXRPC_CALL_CLIENT_RECV_REPLY: + __rxrpc_call_completed(call); + write_unlock(&call->state_lock); + break; + + case RXRPC_CALL_SERVER_RECV_REQUEST: + call->state = RXRPC_CALL_SERVER_ACK_REQUEST; + call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; + write_unlock(&call->state_lock); + rxrpc_propose_delay_ACK(call, serial, + rxrpc_propose_ack_processing_op); + break; + default: + write_unlock(&call->state_lock); + break; + } +} + static void rxrpc_input_update_ack_window(struct rxrpc_call *call, rxrpc_seq_t window, rxrpc_seq_t wtop) { @@ -337,8 +372,9 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, __skb_queue_tail(&call->recvmsg_queue, skb); rxrpc_input_update_ack_window(call, window, wtop); - trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq); + if (last) + rxrpc_end_rx_phase(call, sp->hdr.serial); } /* diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 7bf36a8839ec..dd54ceee7bcc 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -100,42 +100,6 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) return ret; } -/* - * End the packet reception phase. - */ -static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) -{ - rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); - - _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]); - - trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); - - if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_RECV_REPLY) - rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); - - write_lock(&call->state_lock); - - switch (call->state) { - case RXRPC_CALL_CLIENT_RECV_REPLY: - __rxrpc_call_completed(call); - write_unlock(&call->state_lock); - rxrpc_poke_call(call, rxrpc_call_poke_complete); - break; - - case RXRPC_CALL_SERVER_RECV_REQUEST: - call->state = RXRPC_CALL_SERVER_ACK_REQUEST; - call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; - write_unlock(&call->state_lock); - rxrpc_propose_delay_ACK(call, serial, - rxrpc_propose_ack_processing_op); - break; - default: - write_unlock(&call->state_lock); - break; - } -} - /* * Discard a packet we've used up and advance the Rx window by one. */ @@ -166,10 +130,9 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate, serial, call->rx_consumed); - if (last) { - rxrpc_end_rx_phase(call, serial); - return; - } + + if (last) + set_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags); /* Check to see if there's an ACK that needs sending. */ acked = atomic_add_return(call->rx_consumed - old_consumed, @@ -194,7 +157,8 @@ static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb) /* * Deliver messages to a call. This keeps processing packets until the buffer * is filled and we find either more DATA (returns 0) or the end of the DATA - * (returns 1). If more packets are required, it returns -EAGAIN. + * (returns 1). If more packets are required, it returns -EAGAIN and if the + * call has failed it returns -EIO. */ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, struct msghdr *msg, struct iov_iter *iter, @@ -210,7 +174,13 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; - if (rxrpc_call_state(call) >= RXRPC_CALL_SERVER_ACK_REQUEST) { + if (rxrpc_call_has_failed(call)) { + seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; + ret = -EIO; + goto done; + } + + if (test_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags)) { seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; ret = 1; goto done; @@ -234,14 +204,15 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (rx_pkt_offset == 0) { ret2 = rxrpc_verify_data(call, skb); - rx_pkt_offset = sp->offset; - rx_pkt_len = sp->len; trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, - rx_pkt_offset, rx_pkt_len, ret2); + sp->offset, sp->len, ret2); if (ret2 < 0) { + kdebug("verify = %d", ret2); ret = ret2; goto out; } + rx_pkt_offset = sp->offset; + rx_pkt_len = sp->len; } else { trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, rx_pkt_offset, rx_pkt_len, 0); @@ -416,36 +387,36 @@ try_again: msg->msg_namelen = len; } - switch (rxrpc_call_state(call)) { - case RXRPC_CALL_CLIENT_RECV_REPLY: - case RXRPC_CALL_SERVER_RECV_REQUEST: - case RXRPC_CALL_SERVER_ACK_REQUEST: - ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len, - flags, &copied); - if (ret == -EAGAIN) - ret = 0; - - if (!skb_queue_empty(&call->recvmsg_queue)) - rxrpc_notify_socket(call); - break; - default: + ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len, + flags, &copied); + if (ret == -EAGAIN) ret = 0; - break; - } - + if (ret == -EIO) + goto call_failed; if (ret < 0) goto error_unlock_call; - if (rxrpc_call_is_complete(call)) { - ret = rxrpc_recvmsg_term(call, msg); - if (ret < 0) - goto error_unlock_call; - if (!(flags & MSG_PEEK)) - rxrpc_release_call(rx, call); - msg->msg_flags |= MSG_EOR; - ret = 1; - } + if (rxrpc_call_is_complete(call) && + skb_queue_empty(&call->recvmsg_queue)) + goto call_complete; + if (rxrpc_call_has_failed(call)) + goto call_failed; + rxrpc_notify_socket(call); + goto not_yet_complete; + +call_failed: + rxrpc_purge_queue(&call->recvmsg_queue); +call_complete: + ret = rxrpc_recvmsg_term(call, msg); + if (ret < 0) + goto error_unlock_call; + if (!(flags & MSG_PEEK)) + rxrpc_release_call(rx, call); + msg->msg_flags |= MSG_EOR; + ret = 1; + +not_yet_complete: if (ret == 0) msg->msg_flags |= MSG_MORE; else @@ -508,49 +479,34 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, size_t offset = 0; int ret; - _enter("{%d,%s},%zu,%d", - call->debug_id, rxrpc_call_states[call->state], - *_len, want_more); - - ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_SECURING); + _enter("{%d},%zu,%d", call->debug_id, *_len, want_more); mutex_lock(&call->user_mutex); - switch (rxrpc_call_state(call)) { - case RXRPC_CALL_CLIENT_RECV_REPLY: - case RXRPC_CALL_SERVER_RECV_REQUEST: - case RXRPC_CALL_SERVER_ACK_REQUEST: - ret = rxrpc_recvmsg_data(sock, call, NULL, iter, - *_len, 0, &offset); - *_len -= offset; - if (ret < 0) - goto out; - - /* We can only reach here with a partially full buffer if we - * have reached the end of the data. We must otherwise have a - * full buffer or have been given -EAGAIN. - */ - if (ret == 1) { - if (iov_iter_count(iter) > 0) - goto short_data; - if (!want_more) - goto read_phase_complete; - ret = 0; - goto out; - } - - if (!want_more) - goto excess_data; + ret = rxrpc_recvmsg_data(sock, call, NULL, iter, *_len, 0, &offset); + *_len -= offset; + if (ret == -EIO) + goto call_failed; + if (ret < 0) goto out; - case RXRPC_CALL_COMPLETE: - goto call_complete; - - default: - ret = -EINPROGRESS; + /* We can only reach here with a partially full buffer if we have + * reached the end of the data. We must otherwise have a full buffer + * or have been given -EAGAIN. + */ + if (ret == 1) { + if (iov_iter_count(iter) > 0) + goto short_data; + if (!want_more) + goto read_phase_complete; + ret = 0; goto out; } + if (!want_more) + goto excess_data; + goto out; + read_phase_complete: ret = 1; out: @@ -572,7 +528,7 @@ excess_data: 0, -EMSGSIZE); ret = -EMSGSIZE; goto out; -call_complete: +call_failed: *_abort = call->abort_code; ret = call->error; if (call->completion == RXRPC_CALL_SUCCEEDED) { From 96b4059f43ce69e9c590f77d6ce3e99888d5cfe6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Oct 2022 11:25:55 +0100 Subject: [PATCH 135/233] rxrpc: Remove call->state_lock All the setters of call->state are now in the I/O thread and thus the state lock is now unnecessary. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- net/rxrpc/ar-internal.h | 33 +++++++++----- net/rxrpc/call_accept.c | 2 +- net/rxrpc/call_event.c | 42 ++++++++---------- net/rxrpc/call_object.c | 30 ++++++------- net/rxrpc/call_state.c | 91 +++++++++++++++----------------------- net/rxrpc/conn_client.c | 10 ++--- net/rxrpc/conn_event.c | 11 ++--- net/rxrpc/input.c | 96 ++++++++++++++++++----------------------- net/rxrpc/output.c | 4 +- net/rxrpc/proc.c | 6 ++- net/rxrpc/rxkad.c | 2 +- net/rxrpc/sendmsg.c | 3 -- 12 files changed, 144 insertions(+), 186 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 861273439736..751b1903fd6e 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -631,14 +631,13 @@ struct rxrpc_call { unsigned long flags; unsigned long events; spinlock_t notify_lock; /* Kernel notification lock */ - rwlock_t state_lock; /* lock for state transition */ unsigned int send_abort_why; /* Why the abort [enum rxrpc_abort_reason] */ s32 send_abort; /* Abort code to be sent */ short send_abort_err; /* Error to be associated with the abort */ rxrpc_seq_t send_abort_seq; /* DATA packet that incurred the abort (or 0) */ s32 abort_code; /* Local/remote abort code */ int error; /* Local error incurred */ - enum rxrpc_call_state state; /* current state of call */ + enum rxrpc_call_state _state; /* Current state of call (needs barrier) */ enum rxrpc_call_completion completion; /* Call completion condition */ refcount_t ref; u8 security_ix; /* Security type */ @@ -889,25 +888,37 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) /* * call_state.c */ -bool __rxrpc_set_call_completion(struct rxrpc_call *call, - enum rxrpc_call_completion compl, - u32 abort_code, - int error); bool rxrpc_set_call_completion(struct rxrpc_call *call, enum rxrpc_call_completion compl, u32 abort_code, int error); -bool __rxrpc_call_completed(struct rxrpc_call *call); bool rxrpc_call_completed(struct rxrpc_call *call); -bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, - u32 abort_code, int error, enum rxrpc_abort_reason why); bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, u32 abort_code, int error, enum rxrpc_abort_reason why); +void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl, + int error); + +static inline void rxrpc_set_call_state(struct rxrpc_call *call, + enum rxrpc_call_state state) +{ + /* Order write of completion info before write of ->state. */ + smp_store_release(&call->_state, state); +} + +static inline enum rxrpc_call_state __rxrpc_call_state(const struct rxrpc_call *call) +{ + return call->_state; /* Only inside I/O thread */ +} + +static inline bool __rxrpc_call_is_complete(const struct rxrpc_call *call) +{ + return __rxrpc_call_state(call) == RXRPC_CALL_COMPLETE; +} static inline enum rxrpc_call_state rxrpc_call_state(const struct rxrpc_call *call) { - /* Order read ->state before read ->error. */ - return smp_load_acquire(&call->state); + /* Order read ->state before read of completion info. */ + return smp_load_acquire(&call->_state); } static inline bool rxrpc_call_is_complete(const struct rxrpc_call *call) diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index a132d486dea0..3fbf2fcaaf9e 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -99,7 +99,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, if (!call) return -ENOMEM; call->flags |= (1 << RXRPC_CALL_IS_SERVICE); - call->state = RXRPC_CALL_SERVER_PREALLOC; + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_PREALLOC); __set_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events); trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 2e3c01060d59..1abdef15debc 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -257,20 +257,13 @@ out: */ static void rxrpc_begin_service_reply(struct rxrpc_call *call) { - unsigned long now; + unsigned long now = jiffies; - write_lock(&call->state_lock); - - if (call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { - now = jiffies; - call->state = RXRPC_CALL_SERVER_SEND_REPLY; - WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); - if (call->ackr_reason == RXRPC_ACK_DELAY) - call->ackr_reason = 0; - trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); - } - - write_unlock(&call->state_lock); + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SEND_REPLY); + WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); + if (call->ackr_reason == RXRPC_ACK_DELAY) + call->ackr_reason = 0; + trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); } /* @@ -281,18 +274,16 @@ static void rxrpc_close_tx_phase(struct rxrpc_call *call) { _debug("________awaiting reply/ACK__________"); - write_lock(&call->state_lock); - switch (call->state) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: - call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY); break; case RXRPC_CALL_SERVER_SEND_REPLY: - call->state = RXRPC_CALL_SERVER_AWAIT_ACK; + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_AWAIT_ACK); break; default: break; } - write_unlock(&call->state_lock); } static bool rxrpc_tx_window_has_space(struct rxrpc_call *call) @@ -341,7 +332,7 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) static void rxrpc_transmit_some_data(struct rxrpc_call *call) { - switch (call->state) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_SERVER_ACK_REQUEST: if (list_empty(&call->tx_sendmsg)) return; @@ -390,9 +381,10 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) //printk("\n--------------------\n"); _enter("{%d,%s,%lx}", - call->debug_id, rxrpc_call_states[call->state], call->events); + call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)], + call->events); - if (call->state == RXRPC_CALL_COMPLETE) + if (__rxrpc_call_is_complete(call)) goto out; /* Handle abort request locklessly, vs rxrpc_propose_abort(). */ @@ -415,7 +407,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) } t = READ_ONCE(call->expect_req_by); - if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST && + if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST && time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now); expired = true; @@ -499,7 +491,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_lost_ack); - if (resend && call->state != RXRPC_CALL_CLIENT_RECV_REPLY) + if (resend && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY) rxrpc_resend(call, NULL); if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) @@ -511,7 +503,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_propose_ack_input_data); /* Make sure the timer is restarted */ - if (call->state != RXRPC_CALL_COMPLETE) { + if (!__rxrpc_call_is_complete(call)) { next = call->expect_rx_by; #define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; } @@ -532,7 +524,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) } out: - if (call->state == RXRPC_CALL_COMPLETE) { + if (__rxrpc_call_is_complete(call)) { del_timer_sync(&call->timer); if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) rxrpc_disconnect_call(call); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 835e9781afc6..c94161acf3c4 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -69,7 +69,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) _enter("%d", call->debug_id); - if (call->state < RXRPC_CALL_COMPLETE) { + if (!__rxrpc_call_is_complete(call)) { trace_rxrpc_timer_expired(call, jiffies); rxrpc_poke_call(call, rxrpc_call_poke_timer); } @@ -162,7 +162,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, init_waitqueue_head(&call->waitq); spin_lock_init(&call->notify_lock); spin_lock_init(&call->tx_lock); - rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; call->tx_total_len = -1; @@ -211,7 +210,6 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, now = ktime_get_real(); call->acks_latest_ts = now; call->cong_tstamp = now; - call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; call->dest_srx = *srx; call->interruptibility = p->interruptibility; call->tx_total_len = p->tx_total_len; @@ -227,11 +225,13 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, ret = rxrpc_init_client_call_security(call); if (ret < 0) { - __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret); rxrpc_put_call(call, rxrpc_call_put_discard_error); return ERR_PTR(ret); } + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_CONN); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), p->user_call_ID, rxrpc_call_new_client); @@ -384,8 +384,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, error_dup_user_ID: write_unlock(&rx->call_lock); release_sock(&rx->sk); - __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, -EEXIST); + rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EEXIST); trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0, rxrpc_call_see_userid_exists); rxrpc_release_call(rx, call); @@ -403,8 +402,7 @@ error_attached_to_socket: trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret, rxrpc_call_see_connect_failed); set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); - __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); + rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret); _leave(" = c=%08x [err]", call->debug_id); return call; } @@ -427,25 +425,25 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, call->call_id = sp->hdr.callNumber; call->dest_srx.srx_service = sp->hdr.serviceId; call->cid = sp->hdr.cid; - call->state = RXRPC_CALL_SERVER_SECURING; call->cong_tstamp = skb->tstamp; __set_bit(RXRPC_CALL_EXPOSED, &call->flags); + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING); spin_lock(&conn->state_lock); switch (conn->state) { case RXRPC_CONN_SERVICE_UNSECURED: case RXRPC_CONN_SERVICE_CHALLENGING: - call->state = RXRPC_CALL_SERVER_SECURING; + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING); break; case RXRPC_CONN_SERVICE: - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST); break; case RXRPC_CONN_ABORTED: - __rxrpc_set_call_completion(call, conn->completion, - conn->abort_code, conn->error); + rxrpc_set_call_completion(call, conn->completion, + conn->abort_code, conn->error); break; default: BUG(); @@ -614,7 +612,7 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why) dead = __refcount_dec_and_test(&call->ref, &r); trace_rxrpc_call(debug_id, r - 1, 0, why); if (dead) { - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); + ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE); if (!list_empty(&call->link)) { spin_lock(&rxnet->call_lock); @@ -677,7 +675,7 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) { memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); + ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE); ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); del_timer(&call->timer); @@ -715,7 +713,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", call, refcount_read(&call->ref), - rxrpc_call_states[call->state], + rxrpc_call_states[__rxrpc_call_state(call)], call->flags, call->events); spin_unlock(&rxnet->call_lock); diff --git a/net/rxrpc/call_state.c b/net/rxrpc/call_state.c index 649fb9e5d1af..27dc1242b712 100644 --- a/net/rxrpc/call_state.c +++ b/net/rxrpc/call_state.c @@ -10,81 +10,60 @@ /* * Transition a call to the complete state. */ -bool __rxrpc_set_call_completion(struct rxrpc_call *call, +bool rxrpc_set_call_completion(struct rxrpc_call *call, enum rxrpc_call_completion compl, u32 abort_code, int error) { - if (call->state < RXRPC_CALL_COMPLETE) { - call->abort_code = abort_code; - call->error = error; - call->completion = compl; - /* Allow reader of completion state to operate locklessly */ - smp_store_release(&call->state, RXRPC_CALL_COMPLETE); - trace_rxrpc_call_complete(call); - wake_up(&call->waitq); - rxrpc_notify_socket(call); - return true; - } - return false; -} + if (__rxrpc_call_state(call) == RXRPC_CALL_COMPLETE) + return false; -bool rxrpc_set_call_completion(struct rxrpc_call *call, - enum rxrpc_call_completion compl, - u32 abort_code, - int error) -{ - bool ret = false; - - if (call->state < RXRPC_CALL_COMPLETE) { - write_lock(&call->state_lock); - ret = __rxrpc_set_call_completion(call, compl, abort_code, error); - write_unlock(&call->state_lock); - } - return ret; + call->abort_code = abort_code; + call->error = error; + call->completion = compl; + /* Allow reader of completion state to operate locklessly */ + rxrpc_set_call_state(call, RXRPC_CALL_COMPLETE); + trace_rxrpc_call_complete(call); + wake_up(&call->waitq); + rxrpc_notify_socket(call); + return true; } /* * Record that a call successfully completed. */ -bool __rxrpc_call_completed(struct rxrpc_call *call) -{ - return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); -} - bool rxrpc_call_completed(struct rxrpc_call *call) { - bool ret = false; - - if (call->state < RXRPC_CALL_COMPLETE) { - write_lock(&call->state_lock); - ret = __rxrpc_call_completed(call); - write_unlock(&call->state_lock); - } - return ret; + return rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); } /* * Record that a call is locally aborted. */ -bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, - u32 abort_code, int error, enum rxrpc_abort_reason why) -{ - trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq, - abort_code, error); - return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED, - abort_code, error); -} - bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, u32 abort_code, int error, enum rxrpc_abort_reason why) { - bool ret; - - write_lock(&call->state_lock); - ret = __rxrpc_abort_call(call, seq, abort_code, error, why); - write_unlock(&call->state_lock); - if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags)) + trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq, + abort_code, error); + if (!rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED, + abort_code, error)) + return false; + if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) rxrpc_send_abort_packet(call); - return ret; + return true; +} + +/* + * Record that a call errored out before even getting off the ground, thereby + * setting the state to allow it to be destroyed. + */ +void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl, + int error) +{ + call->abort_code = RX_CALL_DEAD; + call->error = error; + call->completion = compl; + call->_state = RXRPC_CALL_COMPLETE; + trace_rxrpc_call_complete(call); + __set_bit(RXRPC_CALL_RELEASED, &call->flags); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index c0db7722571e..8b5ea68dc47e 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -553,9 +553,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, trace_rxrpc_connect_call(call); - write_lock(&call->state_lock); - call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; - write_unlock(&call->state_lock); + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST); /* Paired with the read barrier in rxrpc_connect_call(). This orders * cid and epoch in the connection wrt to call_id without the need to @@ -687,7 +685,7 @@ static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle, set_current_state(TASK_UNINTERRUPTIBLE); break; } - if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_AWAIT_CONN) + if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) break; if ((call->interruptibility == RXRPC_INTERRUPTIBLE || call->interruptibility == RXRPC_PREINTERRUPTIBLE) && @@ -729,7 +727,7 @@ int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp) goto out; } - if (call->state == RXRPC_CALL_CLIENT_AWAIT_CONN) { + if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_CONN) { ret = rxrpc_wait_for_channel(bundle, call, gfp); if (ret < 0) goto wait_failed; @@ -748,7 +746,7 @@ wait_failed: list_del_init(&call->chan_wait_link); spin_unlock(&bundle->channel_lock); - if (call->state != RXRPC_CALL_CLIENT_AWAIT_CONN) { + if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) { ret = 0; goto granted_channel; } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index b2042702ca9a..8d0b9ff0a5e1 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -230,14 +230,9 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn) */ static void rxrpc_call_is_secure(struct rxrpc_call *call) { - _enter("%p", call); - if (call) { - write_lock(&call->state_lock); - if (call->state == RXRPC_CALL_SERVER_SECURING) { - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - rxrpc_notify_socket(call); - } - write_unlock(&call->state_lock); + if (call && __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SECURING) { + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST); + rxrpc_notify_socket(call); } } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 6eb21425f41f..367927a99881 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -184,7 +184,7 @@ void rxrpc_congestion_degrade(struct rxrpc_call *call) if (call->cong_mode != RXRPC_CALL_SLOW_START && call->cong_mode != RXRPC_CALL_CONGEST_AVOIDANCE) return; - if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) + if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_REPLY) return; rtt = ns_to_ktime(call->peer->srtt_us * (1000 / 8)); @@ -252,43 +252,31 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, enum rxrpc_abort_reason abort_why) { - unsigned int state; - ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); - write_lock(&call->state_lock); - - state = call->state; - switch (state) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: - if (reply_begun) - call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY; - else - call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + if (reply_begun) { + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_RECV_REPLY); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); + break; + } + + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY); + trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply); break; case RXRPC_CALL_SERVER_AWAIT_ACK: - __rxrpc_call_completed(call); - state = call->state; + rxrpc_call_completed(call); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); break; default: - goto bad_state; + kdebug("end_tx %s", rxrpc_call_states[__rxrpc_call_state(call)]); + rxrpc_proto_abort(call, call->tx_top, abort_why); + break; } - - write_unlock(&call->state_lock); - if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY) - trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply); - else - trace_rxrpc_txqueue(call, rxrpc_txqueue_end); - _leave(" = ok"); - return; - -bad_state: - write_unlock(&call->state_lock); - kdebug("end_tx %s", rxrpc_call_states[call->state]); - rxrpc_proto_abort(call, call->tx_top, abort_why); } /* @@ -303,7 +291,7 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) if (call->ackr_reason) { now = jiffies; timo = now + MAX_JIFFY_OFFSET; - WRITE_ONCE(call->resend_at, timo); + WRITE_ONCE(call->delay_ack_at, timo); trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); } @@ -326,30 +314,23 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) { rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); - _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]); + _enter("%d,%s", call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)]); trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); - if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_RECV_REPLY) - rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); - - write_lock(&call->state_lock); - - switch (call->state) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_RECV_REPLY: - __rxrpc_call_completed(call); - write_unlock(&call->state_lock); + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); + rxrpc_call_completed(call); break; case RXRPC_CALL_SERVER_RECV_REQUEST: - call->state = RXRPC_CALL_SERVER_ACK_REQUEST; + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST); call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; - write_unlock(&call->state_lock); - rxrpc_propose_delay_ACK(call, serial, - rxrpc_propose_ack_processing_op); + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op); break; + default: - write_unlock(&call->state_lock); break; } } @@ -583,7 +564,6 @@ protocol_error: static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - enum rxrpc_call_state state; rxrpc_serial_t serial = sp->hdr.serial; rxrpc_seq_t seq0 = sp->hdr.seq; @@ -591,11 +571,20 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) atomic64_read(&call->ackr_window), call->rx_highest_seq, skb->len, seq0); - state = READ_ONCE(call->state); - if (state >= RXRPC_CALL_COMPLETE) + if (__rxrpc_call_is_complete(call)) return; - if (state == RXRPC_CALL_SERVER_RECV_REQUEST) { + switch (__rxrpc_call_state(call)) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + /* Received data implicitly ACKs all of the request + * packets we sent when we're acting as a client. + */ + if (!rxrpc_receiving_reply(call)) + goto out_notify; + break; + + case RXRPC_CALL_SERVER_RECV_REQUEST: { unsigned long timo = READ_ONCE(call->next_req_timo); unsigned long now, expect_req_by; @@ -606,15 +595,12 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_reduce_call_timer(call, expect_req_by, now, rxrpc_timer_set_for_idle); } + break; } - /* Received data implicitly ACKs all of the request packets we sent - * when we're acting as a client. - */ - if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || - state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && - !rxrpc_receiving_reply(call)) - goto out_notify; + default: + break; + } if (!rxrpc_input_split_jumbo(call, skb)) { rxrpc_proto_abort(call, sp->hdr.seq, rxrpc_badmsg_bad_jumbo); @@ -904,7 +890,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero); /* Ignore ACKs unless we are or have just been transmitting. */ - switch (READ_ONCE(call->state)) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: case RXRPC_CALL_SERVER_SEND_REPLY: @@ -1027,7 +1013,7 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) */ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) { - switch (READ_ONCE(call->state)) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); fallthrough; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 8a5ff2c9e061..a9746be29634 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -261,7 +261,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_tx_point_call_ack); rxrpc_tx_backoff(call, ret); - if (call->state < RXRPC_CALL_COMPLETE) { + if (!__rxrpc_call_is_complete(call)) { if (ret < 0) rxrpc_cancel_rtt_probe(call, serial, rtt_slot); rxrpc_set_keepalive(call); @@ -723,7 +723,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) static inline void rxrpc_instant_resend(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { - if (call->state < RXRPC_CALL_COMPLETE) + if (!__rxrpc_call_is_complete(call)) kdebug("resend"); } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 63947cce4048..c39ef94602ed 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -50,6 +50,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_local *local; struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + enum rxrpc_call_state state; unsigned long timeout = 0; rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; @@ -74,7 +75,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) sprintf(rbuff, "%pISpc", &call->dest_srx.transport); - if (call->state != RXRPC_CALL_SERVER_PREALLOC) { + state = rxrpc_call_state(call); + if (state != RXRPC_CALL_SERVER_PREALLOC) { timeout = READ_ONCE(call->expect_rx_by); timeout -= jiffies; } @@ -91,7 +93,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call->call_id, rxrpc_is_service_call(call) ? "Svc" : "Clt", refcount_read(&call->ref), - rxrpc_call_states[call->state], + rxrpc_call_states[state], call->abort_code, call->debug_id, acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack, diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index e52cb8058156..dfb01e7b90fb 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -1143,7 +1143,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, call = rcu_dereference_protected( conn->channels[i].call, lockdep_is_held(&conn->bundle->channel_lock)); - if (call && call->state < RXRPC_CALL_COMPLETE) { + if (call && !__rxrpc_call_is_complete(call)) { rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, rxkad_abort_resp_call_state); goto protocol_error_unlock; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 0428528abbf4..a5d0005b7ce5 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -702,9 +702,6 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, mutex_lock(&call->user_mutex); - _debug("CALL %d USR %lx ST %d on CONN %p", - call->debug_id, call->user_call_ID, call->state, call->conn); - ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len, notify_end_tx, &dropped_lock); if (ret == -ESHUTDOWN) From 0d6bf319bc5aba4535bb46e1b607973688a2248a Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Nov 2022 16:46:13 +0000 Subject: [PATCH 136/233] rxrpc: Move the client conn cache management to the I/O thread Move the management of the client connection cache to the I/O thread rather than managing it from the namespace as an aggregate across all the local endpoints within the namespace. This will allow a load of locking to be got rid of in a future patch as only the I/O thread will be looking at the this. The downside is that the total number of cached connections on the system can get higher because the limit is now per-local rather than per-netns. We can, however, keep the number of client conns in use across the entire netfs and use that to reduce the expiration time of idle connection. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- net/rxrpc/ar-internal.h | 17 ++++---- net/rxrpc/conn_client.c | 92 ++++++++++++++-------------------------- net/rxrpc/conn_object.c | 1 - net/rxrpc/io_thread.c | 4 ++ net/rxrpc/local_object.c | 17 ++++++++ net/rxrpc/net_ns.c | 17 -------- 6 files changed, 62 insertions(+), 86 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 751b1903fd6e..de84061a5447 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -76,13 +76,7 @@ struct rxrpc_net { bool live; - bool kill_all_client_conns; atomic_t nr_client_conns; - spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ - struct mutex client_conn_discard_lock; /* Prevent multiple discarders */ - struct list_head idle_client_conns; - struct work_struct client_conn_reaper; - struct timer_list client_conn_reap_timer; struct hlist_head local_endpoints; struct mutex local_mutex; /* Lock for ->local_endpoints */ @@ -294,8 +288,16 @@ struct rxrpc_local { struct sk_buff_head rx_queue; /* Received packets */ struct list_head conn_attend_q; /* Conns requiring immediate attention */ struct list_head call_attend_q; /* Calls requiring immediate attention */ + struct rb_root client_bundles; /* Client connection bundles by socket params */ spinlock_t client_bundles_lock; /* Lock for client_bundles */ + bool kill_all_client_conns; + spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ + struct list_head idle_client_conns; + struct timer_list client_conn_reap_timer; + unsigned long client_conn_flags; +#define RXRPC_CLIENT_CONN_REAP_TIMER 0 /* The client conn reap timer expired */ + spinlock_t lock; /* access lock */ rwlock_t services_lock; /* lock for services list */ int debug_id; /* debug ID for printks */ @@ -946,8 +948,7 @@ void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); -void rxrpc_discard_expired_client_conns(struct work_struct *); -void rxrpc_destroy_all_client_connections(struct rxrpc_net *); +void rxrpc_discard_expired_client_conns(struct rxrpc_local *local); void rxrpc_clean_up_local_conns(struct rxrpc_local *); /* diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 8b5ea68dc47e..ebb43f65ebc5 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -578,17 +578,17 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, */ static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn) { - struct rxrpc_net *rxnet = bundle->local->rxnet; + struct rxrpc_local *local = bundle->local; bool drop_ref; if (!list_empty(&conn->cache_link)) { drop_ref = false; - spin_lock(&rxnet->client_conn_cache_lock); + spin_lock(&local->client_conn_cache_lock); if (!list_empty(&conn->cache_link)) { list_del_init(&conn->cache_link); drop_ref = true; } - spin_unlock(&rxnet->client_conn_cache_lock); + spin_unlock(&local->client_conn_cache_lock); if (drop_ref) rxrpc_put_connection(conn, rxrpc_conn_put_unidle); } @@ -710,14 +710,10 @@ out: int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp) { struct rxrpc_bundle *bundle; - struct rxrpc_local *local = call->local; - struct rxrpc_net *rxnet = local->rxnet; int ret = 0; _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper); - rxrpc_get_call(call, rxrpc_call_get_io_thread); bundle = rxrpc_prep_call(call, gfp); @@ -787,14 +783,14 @@ void rxrpc_expose_client_call(struct rxrpc_call *call) /* * Set the reap timer. */ -static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet) +static void rxrpc_set_client_reap_timer(struct rxrpc_local *local) { - if (!rxnet->kill_all_client_conns) { + if (!local->kill_all_client_conns) { unsigned long now = jiffies; unsigned long reap_at = now + rxrpc_conn_idle_client_expiry; - if (rxnet->live) - timer_reduce(&rxnet->client_conn_reap_timer, reap_at); + if (local->rxnet->live) + timer_reduce(&local->client_conn_reap_timer, reap_at); } } @@ -805,7 +801,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call { struct rxrpc_connection *conn; struct rxrpc_channel *chan = NULL; - struct rxrpc_net *rxnet = bundle->local->rxnet; + struct rxrpc_local *local = bundle->local; unsigned int channel; bool may_reuse; u32 cid; @@ -895,11 +891,11 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call conn->idle_timestamp = jiffies; rxrpc_get_connection(conn, rxrpc_conn_get_idle); - spin_lock(&rxnet->client_conn_cache_lock); - list_move_tail(&conn->cache_link, &rxnet->idle_client_conns); - spin_unlock(&rxnet->client_conn_cache_lock); + spin_lock(&local->client_conn_cache_lock); + list_move_tail(&conn->cache_link, &local->idle_client_conns); + spin_unlock(&local->client_conn_cache_lock); - rxrpc_set_client_reap_timer(rxnet); + rxrpc_set_client_reap_timer(local); } out: @@ -986,42 +982,34 @@ void rxrpc_kill_client_conn(struct rxrpc_connection *conn) * This may be called from conn setup or from a work item so cannot be * considered non-reentrant. */ -void rxrpc_discard_expired_client_conns(struct work_struct *work) +void rxrpc_discard_expired_client_conns(struct rxrpc_local *local) { struct rxrpc_connection *conn; - struct rxrpc_net *rxnet = - container_of(work, struct rxrpc_net, client_conn_reaper); unsigned long expiry, conn_expires_at, now; unsigned int nr_conns; _enter(""); - if (list_empty(&rxnet->idle_client_conns)) { + if (list_empty(&local->idle_client_conns)) { _leave(" [empty]"); return; } - /* Don't double up on the discarding */ - if (!mutex_trylock(&rxnet->client_conn_discard_lock)) { - _leave(" [already]"); - return; - } - /* We keep an estimate of what the number of conns ought to be after * we've discarded some so that we don't overdo the discarding. */ - nr_conns = atomic_read(&rxnet->nr_client_conns); + nr_conns = atomic_read(&local->rxnet->nr_client_conns); next: - spin_lock(&rxnet->client_conn_cache_lock); + spin_lock(&local->client_conn_cache_lock); - if (list_empty(&rxnet->idle_client_conns)) + if (list_empty(&local->idle_client_conns)) goto out; - conn = list_entry(rxnet->idle_client_conns.next, + conn = list_entry(local->idle_client_conns.next, struct rxrpc_connection, cache_link); - if (!rxnet->kill_all_client_conns) { + if (!local->kill_all_client_conns) { /* If the number of connections is over the reap limit, we * expedite discard by reducing the expiry timeout. We must, * however, have at least a short grace period to be able to do @@ -1044,7 +1032,7 @@ next: trace_rxrpc_client(conn, -1, rxrpc_client_discard); list_del_init(&conn->cache_link); - spin_unlock(&rxnet->client_conn_cache_lock); + spin_unlock(&local->client_conn_cache_lock); rxrpc_unbundle_conn(conn); /* Drop the ->cache_link ref */ @@ -1062,32 +1050,11 @@ not_yet_expired: * then things get messier. */ _debug("not yet"); - if (!rxnet->kill_all_client_conns) - timer_reduce(&rxnet->client_conn_reap_timer, conn_expires_at); + if (!local->kill_all_client_conns) + timer_reduce(&local->client_conn_reap_timer, conn_expires_at); out: - spin_unlock(&rxnet->client_conn_cache_lock); - mutex_unlock(&rxnet->client_conn_discard_lock); - _leave(""); -} - -/* - * Preemptively destroy all the client connection records rather than waiting - * for them to time out - */ -void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet) -{ - _enter(""); - - spin_lock(&rxnet->client_conn_cache_lock); - rxnet->kill_all_client_conns = true; - spin_unlock(&rxnet->client_conn_cache_lock); - - del_timer_sync(&rxnet->client_conn_reap_timer); - - if (!rxrpc_queue_work(&rxnet->client_conn_reaper)) - _debug("destroy: queue failed"); - + spin_unlock(&local->client_conn_cache_lock); _leave(""); } @@ -1097,14 +1064,19 @@ void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet) void rxrpc_clean_up_local_conns(struct rxrpc_local *local) { struct rxrpc_connection *conn, *tmp; - struct rxrpc_net *rxnet = local->rxnet; LIST_HEAD(graveyard); _enter(""); - spin_lock(&rxnet->client_conn_cache_lock); + spin_lock(&local->client_conn_cache_lock); + local->kill_all_client_conns = true; + spin_unlock(&local->client_conn_cache_lock); - list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns, + del_timer_sync(&local->client_conn_reap_timer); + + spin_lock(&local->client_conn_cache_lock); + + list_for_each_entry_safe(conn, tmp, &local->idle_client_conns, cache_link) { if (conn->local == local) { atomic_dec(&conn->active); @@ -1113,7 +1085,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local) } } - spin_unlock(&rxnet->client_conn_cache_lock); + spin_unlock(&local->client_conn_cache_lock); while (!list_empty(&graveyard)) { conn = list_entry(graveyard.next, diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 2a7d5378300c..3d8c1dc6a82a 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -470,7 +470,6 @@ void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet) _enter(""); atomic_dec(&rxnet->nr_conns); - rxrpc_destroy_all_client_connections(rxnet); del_timer_sync(&rxnet->service_conn_reap_timer); rxrpc_queue_work(&rxnet->service_conn_reaper); diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 751139b3c1ac..a299cc34c140 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -435,6 +435,10 @@ int rxrpc_io_thread(void *data) continue; } + if (test_and_clear_bit(RXRPC_CLIENT_CONN_REAP_TIMER, + &local->client_conn_flags)) + rxrpc_discard_expired_client_conns(local); + /* Deal with calls that want immediate attention. */ if ((call = list_first_entry_or_null(&local->call_attend_q, struct rxrpc_call, diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index ca8b3ee68b59..9bc8d08ca12c 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -82,6 +82,16 @@ static long rxrpc_local_cmp_key(const struct rxrpc_local *local, } } +static void rxrpc_client_conn_reap_timeout(struct timer_list *timer) +{ + struct rxrpc_local *local = + container_of(timer, struct rxrpc_local, client_conn_reap_timer); + + if (local->kill_all_client_conns && + test_and_set_bit(RXRPC_CLIENT_CONN_REAP_TIMER, &local->client_conn_flags)) + rxrpc_wake_up_io_thread(local); +} + /* * Allocate a new local endpoint. */ @@ -103,8 +113,15 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net, skb_queue_head_init(&local->rx_queue); INIT_LIST_HEAD(&local->conn_attend_q); INIT_LIST_HEAD(&local->call_attend_q); + local->client_bundles = RB_ROOT; spin_lock_init(&local->client_bundles_lock); + local->kill_all_client_conns = false; + spin_lock_init(&local->client_conn_cache_lock); + INIT_LIST_HEAD(&local->idle_client_conns); + timer_setup(&local->client_conn_reap_timer, + rxrpc_client_conn_reap_timeout, 0); + spin_lock_init(&local->lock); rwlock_init(&local->services_lock); local->debug_id = atomic_inc_return(&rxrpc_debug_id); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 5905530e2f33..a0319c040c25 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -10,15 +10,6 @@ unsigned int rxrpc_net_id; -static void rxrpc_client_conn_reap_timeout(struct timer_list *timer) -{ - struct rxrpc_net *rxnet = - container_of(timer, struct rxrpc_net, client_conn_reap_timer); - - if (rxnet->live) - rxrpc_queue_work(&rxnet->client_conn_reaper); -} - static void rxrpc_service_conn_reap_timeout(struct timer_list *timer) { struct rxrpc_net *rxnet = @@ -63,14 +54,6 @@ static __net_init int rxrpc_init_net(struct net *net) rxrpc_service_conn_reap_timeout, 0); atomic_set(&rxnet->nr_client_conns, 0); - rxnet->kill_all_client_conns = false; - spin_lock_init(&rxnet->client_conn_cache_lock); - mutex_init(&rxnet->client_conn_discard_lock); - INIT_LIST_HEAD(&rxnet->idle_client_conns); - INIT_WORK(&rxnet->client_conn_reaper, - rxrpc_discard_expired_client_conns); - timer_setup(&rxnet->client_conn_reap_timer, - rxrpc_client_conn_reap_timeout, 0); INIT_HLIST_HEAD(&rxnet->local_endpoints); mutex_init(&rxnet->local_mutex); From 9d35d880e0e4a3ab32d8c12f9e4d76198aadd42d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 19 Oct 2022 09:45:43 +0100 Subject: [PATCH 137/233] rxrpc: Move client call connection to the I/O thread Move the connection setup of client calls to the I/O thread so that a whole load of locking and barrierage can be eliminated. This necessitates the app thread waiting for connection to complete before it can begin encrypting data. This also completes the fix for a race that exists between call connection and call disconnection whereby the data transmission code adds the call to the peer error distribution list after the call has been disconnected (say by the rxrpc socket getting closed). The fix is to complete the process of moving call connection, data transmission and call disconnection into the I/O thread and thus forcibly serialising them. Note that the issue may predate the overhaul to an I/O thread model that were included in the merge window for v6.2, but the timing is very much changed by the change given below. Fixes: cf37b5987508 ("rxrpc: Move DATA transmission into call processor work item") Reported-by: syzbot+c22650d2844392afdcfd@syzkaller.appspotmail.com Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 5 +- net/rxrpc/ar-internal.h | 22 +- net/rxrpc/call_object.c | 58 +++- net/rxrpc/call_state.c | 2 +- net/rxrpc/conn_client.c | 533 ++++++++--------------------------- net/rxrpc/conn_event.c | 49 +--- net/rxrpc/conn_object.c | 19 +- net/rxrpc/conn_service.c | 1 - net/rxrpc/io_thread.c | 13 +- net/rxrpc/local_object.c | 6 +- net/rxrpc/proc.c | 1 + net/rxrpc/rxkad.c | 21 +- net/rxrpc/security.c | 33 +-- net/rxrpc/sendmsg.c | 64 +++++ 14 files changed, 297 insertions(+), 530 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index e2f6b79d5517..283db0ea3db4 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -218,7 +218,6 @@ EM(rxrpc_conn_put_call, "PUT call ") \ EM(rxrpc_conn_put_call_input, "PUT inp-call") \ EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \ - EM(rxrpc_conn_put_discard, "PUT discard ") \ EM(rxrpc_conn_put_discard_idle, "PUT disc-idl") \ EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \ EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \ @@ -240,12 +239,11 @@ EM(rxrpc_client_chan_activate, "ChActv") \ EM(rxrpc_client_chan_disconnect, "ChDisc") \ EM(rxrpc_client_chan_pass, "ChPass") \ - EM(rxrpc_client_chan_wait_failed, "ChWtFl") \ EM(rxrpc_client_cleanup, "Clean ") \ EM(rxrpc_client_discard, "Discar") \ - EM(rxrpc_client_duplicate, "Duplic") \ EM(rxrpc_client_exposed, "Expose") \ EM(rxrpc_client_replace, "Replac") \ + EM(rxrpc_client_queue_new_call, "Q-Call") \ EM(rxrpc_client_to_active, "->Actv") \ E_(rxrpc_client_to_idle, "->Idle") @@ -273,6 +271,7 @@ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ + EM(rxrpc_call_put_userid, "PUT user-id ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index de84061a5447..007258538bee 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -292,7 +292,6 @@ struct rxrpc_local { struct rb_root client_bundles; /* Client connection bundles by socket params */ spinlock_t client_bundles_lock; /* Lock for client_bundles */ bool kill_all_client_conns; - spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ struct list_head idle_client_conns; struct timer_list client_conn_reap_timer; unsigned long client_conn_flags; @@ -304,7 +303,8 @@ struct rxrpc_local { bool dead; bool service_closed; /* Service socket closed */ struct idr conn_ids; /* List of connection IDs */ - spinlock_t conn_lock; /* Lock for client connection pool */ + struct list_head new_client_calls; /* Newly created client calls need connection */ + spinlock_t client_call_lock; /* Lock for ->new_client_calls */ struct sockaddr_rxrpc srx; /* local address */ }; @@ -385,7 +385,6 @@ enum rxrpc_call_completion { * Bits in the connection flags. */ enum rxrpc_conn_flag { - RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */ RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */ RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */ RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */ @@ -413,6 +412,7 @@ enum rxrpc_conn_event { */ enum rxrpc_conn_proto_state { RXRPC_CONN_UNUSED, /* Connection not yet attempted */ + RXRPC_CONN_CLIENT_UNSECURED, /* Client connection needs security init */ RXRPC_CONN_CLIENT, /* Client connection */ RXRPC_CONN_SERVICE_PREALLOC, /* Service connection preallocation */ RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */ @@ -436,11 +436,9 @@ struct rxrpc_bundle { u32 security_level; /* Security level selected */ u16 service_id; /* Service ID for this connection */ bool try_upgrade; /* True if the bundle is attempting upgrade */ - bool alloc_conn; /* True if someone's getting a conn */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ - short alloc_error; /* Error from last conn allocation */ - spinlock_t channel_lock; + unsigned short alloc_error; /* Error from last conn allocation */ struct rb_node local_node; /* Node in local->client_conns */ struct list_head waiting_calls; /* Calls waiting for channels */ unsigned long avail_chans; /* Mask of available channels */ @@ -468,7 +466,7 @@ struct rxrpc_connection { unsigned char act_chans; /* Mask of active channels */ struct rxrpc_channel { unsigned long final_ack_at; /* Time at which to issue final ACK */ - struct rxrpc_call __rcu *call; /* Active call */ + struct rxrpc_call *call; /* Active call */ unsigned int call_debug_id; /* call->debug_id */ u32 call_id; /* ID of current call */ u32 call_counter; /* Call ID counter */ @@ -489,6 +487,7 @@ struct rxrpc_connection { struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ + struct mutex security_lock; /* Lock for security management */ const struct rxrpc_security *security; /* applied security module */ union { struct { @@ -619,7 +618,7 @@ struct rxrpc_call { struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ - struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */ + struct list_head wait_link; /* Link in local->new_client_calls */ struct hlist_node error_link; /* link in error distribution list */ struct list_head accept_link; /* Link in rx->acceptq */ struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ @@ -866,6 +865,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct sockaddr_rxrpc *, struct rxrpc_call_params *, gfp_t, unsigned int); +void rxrpc_start_call_timer(struct rxrpc_call *call); void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); @@ -905,6 +905,7 @@ static inline void rxrpc_set_call_state(struct rxrpc_call *call, { /* Order write of completion info before write of ->state. */ smp_store_release(&call->_state, state); + wake_up(&call->waitq); } static inline enum rxrpc_call_state __rxrpc_call_state(const struct rxrpc_call *call) @@ -940,10 +941,11 @@ extern unsigned int rxrpc_reap_client_connections; extern unsigned long rxrpc_conn_idle_client_expiry; extern unsigned long rxrpc_conn_idle_client_fast_expiry; -void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local); +void rxrpc_purge_client_connections(struct rxrpc_local *local); struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); -int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp); +int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp); +void rxrpc_connect_client_calls(struct rxrpc_local *local); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index c94161acf3c4..3ded5a24627c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -150,7 +150,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, timer_setup(&call->timer, rxrpc_call_timer_expired, 0); INIT_WORK(&call->destroyer, rxrpc_destroy_call); INIT_LIST_HEAD(&call->link); - INIT_LIST_HEAD(&call->chan_wait_link); + INIT_LIST_HEAD(&call->wait_link); INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); @@ -242,7 +242,7 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, /* * Initiate the call ack/resend/expiry timer. */ -static void rxrpc_start_call_timer(struct rxrpc_call *call) +void rxrpc_start_call_timer(struct rxrpc_call *call) { unsigned long now = jiffies; unsigned long j = now + MAX_JIFFY_OFFSET; @@ -286,6 +286,39 @@ static void rxrpc_put_call_slot(struct rxrpc_call *call) up(limiter); } +/* + * Start the process of connecting a call. We obtain a peer and a connection + * bundle, but the actual association of a call with a connection is offloaded + * to the I/O thread to simplify locking. + */ +static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp) +{ + struct rxrpc_local *local = call->local; + int ret = 0; + + _enter("{%d,%lx},", call->debug_id, call->user_call_ID); + + call->peer = rxrpc_lookup_peer(local, &call->dest_srx, gfp); + if (!call->peer) + goto error; + + ret = rxrpc_look_up_bundle(call, gfp); + if (ret < 0) + goto error; + + trace_rxrpc_client(NULL, -1, rxrpc_client_queue_new_call); + rxrpc_get_call(call, rxrpc_call_get_io_thread); + spin_lock(&local->client_call_lock); + list_add_tail(&call->wait_link, &local->new_client_calls); + spin_unlock(&local->client_call_lock); + rxrpc_wake_up_io_thread(local); + return 0; + +error: + __set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + return ret; +} + /* * Set up a call for the given parameters. * - Called with the socket lock held, which it must release. @@ -369,10 +402,6 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, if (ret < 0) goto error_attached_to_socket; - rxrpc_see_call(call, rxrpc_call_see_connected); - - rxrpc_start_call_timer(call); - _leave(" = %p [new]", call); return call; @@ -387,22 +416,20 @@ error_dup_user_ID: rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EEXIST); trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0, rxrpc_call_see_userid_exists); - rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put_userid_exists); _leave(" = -EEXIST"); return ERR_PTR(-EEXIST); /* We got an error, but the call is attached to the socket and is in - * need of release. However, we might now race with recvmsg() when - * completing the call queues it. Return 0 from sys_sendmsg() and + * need of release. However, we might now race with recvmsg() when it + * completion notifies the socket. Return 0 from sys_sendmsg() and * leave the error to recvmsg() to deal with. */ error_attached_to_socket: trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret, rxrpc_call_see_connect_failed); - set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); - rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret); + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); _leave(" = c=%08x [err]", call->debug_id); return call; } @@ -460,7 +487,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, chan = sp->hdr.cid & RXRPC_CHANNELMASK; conn->channels[chan].call_counter = call->call_id; conn->channels[chan].call_id = call->call_id; - rcu_assign_pointer(conn->channels[chan].call, call); + conn->channels[chan].call = call; spin_unlock(&conn->state_lock); spin_lock(&conn->peer->lock); @@ -520,7 +547,7 @@ static void rxrpc_cleanup_ring(struct rxrpc_call *call) void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; - bool put = false; + bool put = false, putu = false; _enter("{%d,%d}", call->debug_id, refcount_read(&call->ref)); @@ -555,7 +582,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) if (test_and_clear_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { rb_erase(&call->sock_node, &rx->calls); memset(&call->sock_node, 0xdd, sizeof(call->sock_node)); - rxrpc_put_call(call, rxrpc_call_put_userid_exists); + putu = true; } list_del(&call->sock_link); @@ -563,6 +590,9 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); + if (putu) + rxrpc_put_call(call, rxrpc_call_put_userid); + _leave(""); } diff --git a/net/rxrpc/call_state.c b/net/rxrpc/call_state.c index 27dc1242b712..6afb54373ebb 100644 --- a/net/rxrpc/call_state.c +++ b/net/rxrpc/call_state.c @@ -65,5 +65,5 @@ void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion comp call->completion = compl; call->_state = RXRPC_CALL_COMPLETE; trace_rxrpc_call_complete(call); - __set_bit(RXRPC_CALL_RELEASED, &call->flags); + WARN_ON_ONCE(__test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags)); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index ebb43f65ebc5..981ca5b98bcb 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -39,61 +39,19 @@ static void rxrpc_activate_bundle(struct rxrpc_bundle *bundle) atomic_inc(&bundle->active); } -/* - * Get a connection ID and epoch for a client connection from the global pool. - * The connection struct pointer is then recorded in the idr radix tree. The - * epoch doesn't change until the client is rebooted (or, at least, unless the - * module is unloaded). - */ -static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, - gfp_t gfp) -{ - struct rxrpc_local *local = conn->local; - int id; - - _enter(""); - - idr_preload(gfp); - spin_lock(&local->conn_lock); - - id = idr_alloc_cyclic(&local->conn_ids, conn, - 1, 0x40000000, GFP_NOWAIT); - if (id < 0) - goto error; - - spin_unlock(&local->conn_lock); - idr_preload_end(); - - conn->proto.epoch = local->rxnet->epoch; - conn->proto.cid = id << RXRPC_CIDSHIFT; - set_bit(RXRPC_CONN_HAS_IDR, &conn->flags); - _leave(" [CID %x]", conn->proto.cid); - return 0; - -error: - spin_unlock(&local->conn_lock); - idr_preload_end(); - _leave(" = %d", id); - return id; -} - /* * Release a connection ID for a client connection. */ static void rxrpc_put_client_connection_id(struct rxrpc_local *local, struct rxrpc_connection *conn) { - if (test_bit(RXRPC_CONN_HAS_IDR, &conn->flags)) { - spin_lock(&local->conn_lock); - idr_remove(&local->conn_ids, conn->proto.cid >> RXRPC_CIDSHIFT); - spin_unlock(&local->conn_lock); - } + idr_remove(&local->conn_ids, conn->proto.cid >> RXRPC_CIDSHIFT); } /* * Destroy the client connection ID tree. */ -void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local) +static void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local) { struct rxrpc_connection *conn; int id; @@ -129,7 +87,6 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call, bundle->security_level = call->security_level; refcount_set(&bundle->ref, 1); atomic_set(&bundle->active, 1); - spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_new); } @@ -169,69 +126,68 @@ void rxrpc_put_bundle(struct rxrpc_bundle *bundle, enum rxrpc_bundle_trace why) } } +/* + * Get rid of outstanding client connection preallocations when a local + * endpoint is destroyed. + */ +void rxrpc_purge_client_connections(struct rxrpc_local *local) +{ + rxrpc_destroy_client_conn_ids(local); +} + /* * Allocate a client connection. */ static struct rxrpc_connection * -rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) +rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle) { struct rxrpc_connection *conn; - struct rxrpc_net *rxnet = bundle->local->rxnet; - int ret; + struct rxrpc_local *local = bundle->local; + struct rxrpc_net *rxnet = local->rxnet; + int id; _enter(""); - conn = rxrpc_alloc_connection(rxnet, gfp); - if (!conn) { - _leave(" = -ENOMEM"); + conn = rxrpc_alloc_connection(rxnet, GFP_ATOMIC | __GFP_NOWARN); + if (!conn) return ERR_PTR(-ENOMEM); + + id = idr_alloc_cyclic(&local->conn_ids, conn, 1, 0x40000000, + GFP_ATOMIC | __GFP_NOWARN); + if (id < 0) { + kfree(conn); + return ERR_PTR(id); } refcount_set(&conn->ref, 1); - conn->bundle = bundle; - conn->local = bundle->local; - conn->peer = bundle->peer; - conn->key = bundle->key; + conn->proto.cid = id << RXRPC_CIDSHIFT; + conn->proto.epoch = local->rxnet->epoch; + conn->out_clientflag = RXRPC_CLIENT_INITIATED; + conn->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn); + conn->local = rxrpc_get_local(bundle->local, rxrpc_local_get_client_conn); + conn->peer = rxrpc_get_peer(bundle->peer, rxrpc_peer_get_client_conn); + conn->key = key_get(bundle->key); + conn->security = bundle->security; conn->exclusive = bundle->exclusive; conn->upgrade = bundle->upgrade; conn->orig_service_id = bundle->service_id; conn->security_level = bundle->security_level; - conn->out_clientflag = RXRPC_CLIENT_INITIATED; - conn->state = RXRPC_CONN_CLIENT; + conn->state = RXRPC_CONN_CLIENT_UNSECURED; conn->service_id = conn->orig_service_id; - ret = rxrpc_get_client_connection_id(conn, gfp); - if (ret < 0) - goto error_0; - - ret = rxrpc_init_client_conn_security(conn); - if (ret < 0) - goto error_1; + if (conn->security == &rxrpc_no_security) + conn->state = RXRPC_CONN_CLIENT; atomic_inc(&rxnet->nr_conns); write_lock(&rxnet->conn_lock); list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn); - rxrpc_get_peer(conn->peer, rxrpc_peer_get_client_conn); - rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); - key_get(conn->key); - - trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), - rxrpc_conn_new_client); + rxrpc_see_connection(conn, rxrpc_conn_new_client); atomic_inc(&rxnet->nr_client_conns); trace_rxrpc_client(conn, -1, rxrpc_client_alloc); - _leave(" = %p", conn); return conn; - -error_1: - rxrpc_put_client_connection_id(bundle->local, conn); -error_0: - kfree(conn); - _leave(" = %d", ret); - return ERR_PTR(ret); } /* @@ -249,7 +205,8 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags)) goto dont_reuse; - if (conn->state != RXRPC_CONN_CLIENT || + if ((conn->state != RXRPC_CONN_CLIENT_UNSECURED && + conn->state != RXRPC_CONN_CLIENT) || conn->proto.epoch != rxnet->epoch) goto mark_dont_reuse; @@ -280,7 +237,7 @@ dont_reuse: * Look up the conn bundle that matches the connection parameters, adding it if * it doesn't yet exist. */ -static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp) +int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp) { static atomic_t rxrpc_bundle_id; struct rxrpc_bundle *bundle, *candidate; @@ -295,7 +252,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t if (test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags)) { call->bundle = rxrpc_alloc_bundle(call, gfp); - return call->bundle; + return call->bundle ? 0 : -ENOMEM; } /* First, see if the bundle is already there. */ @@ -324,7 +281,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t /* It wasn't. We need to add one. */ candidate = rxrpc_alloc_bundle(call, gfp); if (!candidate) - return ERR_PTR(-ENOMEM); + return -ENOMEM; _debug("search 2"); spin_lock(&local->client_bundles_lock); @@ -355,7 +312,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call); spin_unlock(&local->client_bundles_lock); _leave(" = B=%u [new]", call->bundle->debug_id); - return call->bundle; + return 0; found_bundle_free: rxrpc_free_bundle(candidate); @@ -364,160 +321,77 @@ found_bundle: rxrpc_activate_bundle(bundle); spin_unlock(&local->client_bundles_lock); _leave(" = B=%u [found]", call->bundle->debug_id); - return call->bundle; -} - -/* - * Create or find a client bundle to use for a call. - * - * If we return with a connection, the call will be on its waiting list. It's - * left to the caller to assign a channel and wake up the call. - */ -static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_call *call, gfp_t gfp) -{ - struct rxrpc_bundle *bundle; - - _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - - call->peer = rxrpc_lookup_peer(call->local, &call->dest_srx, gfp); - if (!call->peer) - goto error; - - call->tx_last_sent = ktime_get_real(); - call->cong_ssthresh = call->peer->cong_ssthresh; - if (call->cong_cwnd >= call->cong_ssthresh) - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; - else - call->cong_mode = RXRPC_CALL_SLOW_START; - - /* Find the client connection bundle. */ - bundle = rxrpc_look_up_bundle(call, gfp); - if (!bundle) - goto error; - - /* Get this call queued. Someone else may activate it whilst we're - * lining up a new connection, but that's fine. - */ - spin_lock(&bundle->channel_lock); - list_add_tail(&call->chan_wait_link, &bundle->waiting_calls); - spin_unlock(&bundle->channel_lock); - - _leave(" = [B=%x]", bundle->debug_id); - return bundle; - -error: - _leave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); + return 0; } /* * Allocate a new connection and add it into a bundle. */ -static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) - __releases(bundle->channel_lock) +static bool rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, + unsigned int slot) { - struct rxrpc_connection *candidate = NULL, *old = NULL; - bool conflict; - int i; + struct rxrpc_connection *conn, *old; + unsigned int shift = slot * RXRPC_MAXCALLS; + unsigned int i; - _enter(""); - - conflict = bundle->alloc_conn; - if (!conflict) - bundle->alloc_conn = true; - spin_unlock(&bundle->channel_lock); - if (conflict) { - _leave(" [conf]"); - return; + old = bundle->conns[slot]; + if (old) { + bundle->conns[slot] = NULL; + trace_rxrpc_client(old, -1, rxrpc_client_replace); + rxrpc_put_connection(old, rxrpc_conn_put_noreuse); } - candidate = rxrpc_alloc_client_connection(bundle, gfp); - - spin_lock(&bundle->channel_lock); - bundle->alloc_conn = false; - - if (IS_ERR(candidate)) { - bundle->alloc_error = PTR_ERR(candidate); - spin_unlock(&bundle->channel_lock); - _leave(" [err %ld]", PTR_ERR(candidate)); - return; + conn = rxrpc_alloc_client_connection(bundle); + if (IS_ERR(conn)) { + bundle->alloc_error = PTR_ERR(conn); + return false; } - bundle->alloc_error = 0; - - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) { - unsigned int shift = i * RXRPC_MAXCALLS; - int j; - - old = bundle->conns[i]; - if (!rxrpc_may_reuse_conn(old)) { - if (old) - trace_rxrpc_client(old, -1, rxrpc_client_replace); - candidate->bundle_shift = shift; - rxrpc_activate_bundle(bundle); - bundle->conns[i] = candidate; - for (j = 0; j < RXRPC_MAXCALLS; j++) - set_bit(shift + j, &bundle->avail_chans); - candidate = NULL; - break; - } - - old = NULL; - } - - spin_unlock(&bundle->channel_lock); - - if (candidate) { - _debug("discard C=%x", candidate->debug_id); - trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate); - rxrpc_put_connection(candidate, rxrpc_conn_put_discard); - } - - rxrpc_put_connection(old, rxrpc_conn_put_noreuse); - _leave(""); + rxrpc_activate_bundle(bundle); + conn->bundle_shift = shift; + bundle->conns[slot] = conn; + for (i = 0; i < RXRPC_MAXCALLS; i++) + set_bit(shift + i, &bundle->avail_chans); + return true; } /* * Add a connection to a bundle if there are no usable connections or we have * connections waiting for extra capacity. */ -static void rxrpc_maybe_add_conn(struct rxrpc_bundle *bundle, gfp_t gfp) +static bool rxrpc_bundle_has_space(struct rxrpc_bundle *bundle) { - struct rxrpc_call *call; - int i, usable; + int slot = -1, i, usable; _enter(""); - spin_lock(&bundle->channel_lock); + bundle->alloc_error = 0; /* See if there are any usable connections. */ usable = 0; - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) + for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) { if (rxrpc_may_reuse_conn(bundle->conns[i])) usable++; - - if (!usable && !list_empty(&bundle->waiting_calls)) { - call = list_first_entry(&bundle->waiting_calls, - struct rxrpc_call, chan_wait_link); - if (test_bit(RXRPC_CALL_UPGRADE, &call->flags)) - bundle->try_upgrade = true; + else if (slot == -1) + slot = i; } + if (!usable && bundle->upgrade) + bundle->try_upgrade = true; + if (!usable) goto alloc_conn; if (!bundle->avail_chans && !bundle->try_upgrade && - !list_empty(&bundle->waiting_calls) && usable < ARRAY_SIZE(bundle->conns)) goto alloc_conn; - spin_unlock(&bundle->channel_lock); _leave(""); - return; + return usable; alloc_conn: - return rxrpc_add_conn_to_bundle(bundle, gfp); + return slot >= 0 ? rxrpc_add_conn_to_bundle(bundle, slot) : false; } /* @@ -531,11 +405,13 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, struct rxrpc_channel *chan = &conn->channels[channel]; struct rxrpc_bundle *bundle = conn->bundle; struct rxrpc_call *call = list_entry(bundle->waiting_calls.next, - struct rxrpc_call, chan_wait_link); + struct rxrpc_call, wait_link); u32 call_id = chan->call_counter + 1; _enter("C=%x,%u", conn->debug_id, channel); + list_del_init(&call->wait_link); + trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate); /* Cancel the final ACK on the previous call if it hasn't been sent yet @@ -545,65 +421,50 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, clear_bit(conn->bundle_shift + channel, &bundle->avail_chans); rxrpc_see_call(call, rxrpc_call_see_activate_client); - list_del_init(&call->chan_wait_link); call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call); call->cid = conn->proto.cid | channel; call->call_id = call_id; call->dest_srx.srx_service = conn->service_id; - - trace_rxrpc_connect_call(call); - - rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST); - - /* Paired with the read barrier in rxrpc_connect_call(). This orders - * cid and epoch in the connection wrt to call_id without the need to - * take the channel_lock. - * - * We provisionally assign a callNumber at this point, but we don't - * confirm it until the call is about to be exposed. - * - * TODO: Pair with a barrier in the data_ready handler when that looks - * at the call ID through a connection channel. - */ - smp_wmb(); + call->cong_ssthresh = call->peer->cong_ssthresh; + if (call->cong_cwnd >= call->cong_ssthresh) + call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + else + call->cong_mode = RXRPC_CALL_SLOW_START; chan->call_id = call_id; chan->call_debug_id = call->debug_id; - rcu_assign_pointer(chan->call, call); + chan->call = call; + + rxrpc_see_call(call, rxrpc_call_see_connected); + trace_rxrpc_connect_call(call); + call->tx_last_sent = ktime_get_real(); + rxrpc_start_call_timer(call); + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST); wake_up(&call->waitq); } /* * Remove a connection from the idle list if it's on it. */ -static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn) +static void rxrpc_unidle_conn(struct rxrpc_connection *conn) { - struct rxrpc_local *local = bundle->local; - bool drop_ref; - if (!list_empty(&conn->cache_link)) { - drop_ref = false; - spin_lock(&local->client_conn_cache_lock); - if (!list_empty(&conn->cache_link)) { - list_del_init(&conn->cache_link); - drop_ref = true; - } - spin_unlock(&local->client_conn_cache_lock); - if (drop_ref) - rxrpc_put_connection(conn, rxrpc_conn_put_unidle); + list_del_init(&conn->cache_link); + rxrpc_put_connection(conn, rxrpc_conn_put_unidle); } } /* - * Assign channels and callNumbers to waiting calls with channel_lock - * held by caller. + * Assign channels and callNumbers to waiting calls. */ -static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle) +static void rxrpc_activate_channels(struct rxrpc_bundle *bundle) { struct rxrpc_connection *conn; unsigned long avail, mask; unsigned int channel, slot; + trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans); + if (bundle->try_upgrade) mask = 1; else @@ -623,7 +484,7 @@ static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle) if (bundle->try_upgrade) set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); - rxrpc_unidle_conn(bundle, conn); + rxrpc_unidle_conn(conn); channel &= (RXRPC_MAXCALLS - 1); conn->act_chans |= 1 << channel; @@ -632,125 +493,24 @@ static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle) } /* - * Assign channels and callNumbers to waiting calls. + * Connect waiting channels (called from the I/O thread). */ -static void rxrpc_activate_channels(struct rxrpc_bundle *bundle) +void rxrpc_connect_client_calls(struct rxrpc_local *local) { - _enter("B=%x", bundle->debug_id); + struct rxrpc_call *call; - trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans); + while ((call = list_first_entry_or_null(&local->new_client_calls, + struct rxrpc_call, wait_link)) + ) { + struct rxrpc_bundle *bundle = call->bundle; - if (!bundle->avail_chans) - return; + spin_lock(&local->client_call_lock); + list_move_tail(&call->wait_link, &bundle->waiting_calls); + spin_unlock(&local->client_call_lock); - spin_lock(&bundle->channel_lock); - rxrpc_activate_channels_locked(bundle); - spin_unlock(&bundle->channel_lock); - _leave(""); -} - -/* - * Wait for a callNumber and a channel to be granted to a call. - */ -static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle, - struct rxrpc_call *call, gfp_t gfp) -{ - DECLARE_WAITQUEUE(myself, current); - int ret = 0; - - _enter("%d", call->debug_id); - - if (!gfpflags_allow_blocking(gfp)) { - rxrpc_maybe_add_conn(bundle, gfp); - rxrpc_activate_channels(bundle); - ret = bundle->alloc_error ?: -EAGAIN; - goto out; + if (rxrpc_bundle_has_space(bundle)) + rxrpc_activate_channels(bundle); } - - add_wait_queue_exclusive(&call->waitq, &myself); - for (;;) { - rxrpc_maybe_add_conn(bundle, gfp); - rxrpc_activate_channels(bundle); - ret = bundle->alloc_error; - if (ret < 0) - break; - - switch (call->interruptibility) { - case RXRPC_INTERRUPTIBLE: - case RXRPC_PREINTERRUPTIBLE: - set_current_state(TASK_INTERRUPTIBLE); - break; - case RXRPC_UNINTERRUPTIBLE: - default: - set_current_state(TASK_UNINTERRUPTIBLE); - break; - } - if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) - break; - if ((call->interruptibility == RXRPC_INTERRUPTIBLE || - call->interruptibility == RXRPC_PREINTERRUPTIBLE) && - signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } - schedule(); - } - remove_wait_queue(&call->waitq, &myself); - __set_current_state(TASK_RUNNING); - -out: - _leave(" = %d", ret); - return ret; -} - -/* - * find a connection for a call - * - called in process context with IRQs enabled - */ -int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp) -{ - struct rxrpc_bundle *bundle; - int ret = 0; - - _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - - rxrpc_get_call(call, rxrpc_call_get_io_thread); - - bundle = rxrpc_prep_call(call, gfp); - if (IS_ERR(bundle)) { - rxrpc_put_call(call, rxrpc_call_get_io_thread); - ret = PTR_ERR(bundle); - goto out; - } - - if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_CONN) { - ret = rxrpc_wait_for_channel(bundle, call, gfp); - if (ret < 0) - goto wait_failed; - } - -granted_channel: - /* Paired with the write barrier in rxrpc_activate_one_channel(). */ - smp_rmb(); - -out: - _leave(" = %d", ret); - return ret; - -wait_failed: - spin_lock(&bundle->channel_lock); - list_del_init(&call->chan_wait_link); - spin_unlock(&bundle->channel_lock); - - if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) { - ret = 0; - goto granted_channel; - } - - trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed); - rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); - rxrpc_disconnect_client_call(bundle, call); - goto out; } /* @@ -808,8 +568,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call _enter("c=%x", call->debug_id); - spin_lock(&bundle->channel_lock); - /* Calls that have never actually been assigned a channel can simply be * discarded. */ @@ -818,8 +576,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call _debug("call is waiting"); ASSERTCMP(call->call_id, ==, 0); ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags)); - list_del_init(&call->chan_wait_link); - goto out; + list_del_init(&call->wait_link); + return; } cid = call->cid; @@ -827,10 +585,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call chan = &conn->channels[channel]; trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); - if (rcu_access_pointer(chan->call) != call) { - spin_unlock(&bundle->channel_lock); - BUG(); - } + if (WARN_ON(chan->call != call)) + return; may_reuse = rxrpc_may_reuse_conn(conn); @@ -851,16 +607,15 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call trace_rxrpc_client(conn, channel, rxrpc_client_to_active); bundle->try_upgrade = false; if (may_reuse) - rxrpc_activate_channels_locked(bundle); + rxrpc_activate_channels(bundle); } - } /* See if we can pass the channel directly to another call. */ if (may_reuse && !list_empty(&bundle->waiting_calls)) { trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass); rxrpc_activate_one_channel(conn, channel); - goto out; + return; } /* Schedule the final ACK to be transmitted in a short while so that it @@ -878,7 +633,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call } /* Deactivate the channel. */ - rcu_assign_pointer(chan->call, NULL); + chan->call = NULL; set_bit(conn->bundle_shift + channel, &conn->bundle->avail_chans); conn->act_chans &= ~(1 << channel); @@ -891,15 +646,10 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call conn->idle_timestamp = jiffies; rxrpc_get_connection(conn, rxrpc_conn_get_idle); - spin_lock(&local->client_conn_cache_lock); list_move_tail(&conn->cache_link, &local->idle_client_conns); - spin_unlock(&local->client_conn_cache_lock); rxrpc_set_client_reap_timer(local); } - -out: - spin_unlock(&bundle->channel_lock); } /* @@ -909,7 +659,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) { struct rxrpc_bundle *bundle = conn->bundle; unsigned int bindex; - bool need_drop = false; int i; _enter("C=%x", conn->debug_id); @@ -917,18 +666,13 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) rxrpc_process_delayed_final_acks(conn, true); - spin_lock(&bundle->channel_lock); bindex = conn->bundle_shift / RXRPC_MAXCALLS; if (bundle->conns[bindex] == conn) { _debug("clear slot %u", bindex); bundle->conns[bindex] = NULL; for (i = 0; i < RXRPC_MAXCALLS; i++) clear_bit(conn->bundle_shift + i, &bundle->avail_chans); - need_drop = true; - } - spin_unlock(&bundle->channel_lock); - - if (need_drop) { + rxrpc_put_client_connection_id(bundle->local, conn); rxrpc_deactivate_bundle(bundle); rxrpc_put_connection(conn, rxrpc_conn_put_unbundle); } @@ -990,24 +734,16 @@ void rxrpc_discard_expired_client_conns(struct rxrpc_local *local) _enter(""); - if (list_empty(&local->idle_client_conns)) { - _leave(" [empty]"); - return; - } - /* We keep an estimate of what the number of conns ought to be after * we've discarded some so that we don't overdo the discarding. */ nr_conns = atomic_read(&local->rxnet->nr_client_conns); next: - spin_lock(&local->client_conn_cache_lock); - - if (list_empty(&local->idle_client_conns)) - goto out; - - conn = list_entry(local->idle_client_conns.next, - struct rxrpc_connection, cache_link); + conn = list_first_entry_or_null(&local->idle_client_conns, + struct rxrpc_connection, cache_link); + if (!conn) + return; if (!local->kill_all_client_conns) { /* If the number of connections is over the reap limit, we @@ -1032,8 +768,6 @@ next: trace_rxrpc_client(conn, -1, rxrpc_client_discard); list_del_init(&conn->cache_link); - spin_unlock(&local->client_conn_cache_lock); - rxrpc_unbundle_conn(conn); /* Drop the ->cache_link ref */ rxrpc_put_connection(conn, rxrpc_conn_put_discard_idle); @@ -1053,8 +787,6 @@ not_yet_expired: if (!local->kill_all_client_conns) timer_reduce(&local->client_conn_reap_timer, conn_expires_at); -out: - spin_unlock(&local->client_conn_cache_lock); _leave(""); } @@ -1063,34 +795,19 @@ out: */ void rxrpc_clean_up_local_conns(struct rxrpc_local *local) { - struct rxrpc_connection *conn, *tmp; - LIST_HEAD(graveyard); + struct rxrpc_connection *conn; _enter(""); - spin_lock(&local->client_conn_cache_lock); local->kill_all_client_conns = true; - spin_unlock(&local->client_conn_cache_lock); del_timer_sync(&local->client_conn_reap_timer); - spin_lock(&local->client_conn_cache_lock); - - list_for_each_entry_safe(conn, tmp, &local->idle_client_conns, - cache_link) { - if (conn->local == local) { - atomic_dec(&conn->active); - trace_rxrpc_client(conn, -1, rxrpc_client_discard); - list_move(&conn->cache_link, &graveyard); - } - } - - spin_unlock(&local->client_conn_cache_lock); - - while (!list_empty(&graveyard)) { - conn = list_entry(graveyard.next, - struct rxrpc_connection, cache_link); + while ((conn = list_first_entry_or_null(&local->idle_client_conns, + struct rxrpc_connection, cache_link))) { list_del_init(&conn->cache_link); + atomic_dec(&conn->active); + trace_rxrpc_client(conn, -1, rxrpc_client_discard); rxrpc_unbundle_conn(conn); rxrpc_put_connection(conn, rxrpc_conn_put_local_dead); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 8d0b9ff0a5e1..44414e724415 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -100,9 +100,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, /* If the last call got moved on whilst we were waiting to run, just * ignore this packet. */ - call_id = READ_ONCE(chan->last_call); - /* Sync with __rxrpc_disconnect_call() */ - smp_rmb(); + call_id = chan->last_call; if (skb && call_id != sp->hdr.callNumber) return; @@ -119,9 +117,12 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[2].iov_base = &ack_info; iov[2].iov_len = sizeof(ack_info); + serial = atomic_inc_return(&conn->serial); + pkt.whdr.epoch = htonl(conn->proto.epoch); pkt.whdr.cid = htonl(conn->proto.cid | channel); pkt.whdr.callNumber = htonl(call_id); + pkt.whdr.serial = htonl(serial); pkt.whdr.seq = 0; pkt.whdr.type = chan->last_type; pkt.whdr.flags = conn->out_clientflag; @@ -158,31 +159,15 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[0].iov_len += sizeof(pkt.ack); len += sizeof(pkt.ack) + 3 + sizeof(ack_info); ioc = 3; - break; - default: - return; - } - - /* Resync with __rxrpc_disconnect_call() and check that the last call - * didn't get advanced whilst we were filling out the packets. - */ - smp_rmb(); - if (READ_ONCE(chan->last_call) != call_id) - return; - - serial = atomic_inc_return(&conn->serial); - pkt.whdr.serial = htonl(serial); - - switch (chan->last_type) { - case RXRPC_PACKET_TYPE_ABORT: - break; - case RXRPC_PACKET_TYPE_ACK: trace_rxrpc_tx_ack(chan->call_debug_id, serial, ntohl(pkt.ack.firstPacket), ntohl(pkt.ack.serial), pkt.ack.reason, 0); break; + + default: + return; } ret = kernel_sendmsg(conn->local->socket, &msg, iov, ioc, len); @@ -207,12 +192,8 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn) _enter("{%d},%x", conn->debug_id, conn->abort_code); - spin_lock(&conn->bundle->channel_lock); - for (i = 0; i < RXRPC_MAXCALLS; i++) { - call = rcu_dereference_protected( - conn->channels[i].call, - lockdep_is_held(&conn->bundle->channel_lock)); + call = conn->channels[i].call; if (call) rxrpc_set_call_completion(call, conn->completion, @@ -220,7 +201,6 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn) conn->error); } - spin_unlock(&conn->bundle->channel_lock); _leave(""); } @@ -316,9 +296,7 @@ again: if (!test_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags)) continue; - smp_rmb(); /* vs rxrpc_disconnect_client_call */ - ack_at = READ_ONCE(chan->final_ack_at); - + ack_at = chan->final_ack_at; if (time_before(j, ack_at) && !force) { if (time_before(ack_at, next_j)) { next_j = ack_at; @@ -446,15 +424,8 @@ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb) if (conn->state != RXRPC_CONN_SERVICE) break; - spin_lock(&conn->bundle->channel_lock); - for (loop = 0; loop < RXRPC_MAXCALLS; loop++) - rxrpc_call_is_secure( - rcu_dereference_protected( - conn->channels[loop].call, - lockdep_is_held(&conn->bundle->channel_lock))); - - spin_unlock(&conn->bundle->channel_lock); + rxrpc_call_is_secure(conn->channels[loop].call); break; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 3d8c1dc6a82a..ac85d4644a3c 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -67,6 +67,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, INIT_WORK(&conn->destructor, rxrpc_clean_up_connection); INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); + mutex_init(&conn->security_lock); skb_queue_head_init(&conn->rx_queue); conn->rxnet = rxnet; conn->security = &rxrpc_no_security; @@ -157,7 +158,7 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, _enter("%d,%x", conn->debug_id, call->cid); - if (rcu_access_pointer(chan->call) == call) { + if (chan->call == call) { /* Save the result of the call so that we can repeat it if necessary * through the channel, whilst disposing of the actual call record. */ @@ -177,12 +178,9 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, break; } - /* Sync with rxrpc_conn_retransmit(). */ - smp_wmb(); chan->last_call = chan->call_id; chan->call_id = chan->call_counter; - - rcu_assign_pointer(chan->call, NULL); + chan->call = NULL; } _leave(""); @@ -210,10 +208,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) if (rxrpc_is_client_call(call)) { rxrpc_disconnect_client_call(call->bundle, call); } else { - spin_lock(&conn->bundle->channel_lock); __rxrpc_disconnect_call(conn, call); - spin_unlock(&conn->bundle->channel_lock); - conn->idle_timestamp = jiffies; if (atomic_dec_and_test(&conn->active)) rxrpc_set_service_reap_timer(conn->rxnet, @@ -316,10 +311,10 @@ static void rxrpc_clean_up_connection(struct work_struct *work) container_of(work, struct rxrpc_connection, destructor); struct rxrpc_net *rxnet = conn->rxnet; - ASSERT(!rcu_access_pointer(conn->channels[0].call) && - !rcu_access_pointer(conn->channels[1].call) && - !rcu_access_pointer(conn->channels[2].call) && - !rcu_access_pointer(conn->channels[3].call)); + ASSERT(!conn->channels[0].call && + !conn->channels[1].call && + !conn->channels[2].call && + !conn->channels[3].call); ASSERT(list_empty(&conn->cache_link)); del_timer_sync(&conn->timer); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 2a55a88b2a5b..f30323de82bd 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -11,7 +11,6 @@ static struct rxrpc_bundle rxrpc_service_dummy_bundle = { .ref = REFCOUNT_INIT(1), .debug_id = UINT_MAX, - .channel_lock = __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock), }; /* diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index a299cc34c140..9e9dfb2fc559 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -369,10 +369,7 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, return just_discard; } - rcu_read_lock(); - call = rxrpc_try_get_call(rcu_dereference(chan->call), - rxrpc_call_get_input); - rcu_read_unlock(); + call = rxrpc_try_get_call(chan->call, rxrpc_call_get_input); if (sp->hdr.callNumber > chan->call_id) { if (rxrpc_to_client(sp)) { @@ -453,6 +450,9 @@ int rxrpc_io_thread(void *data) continue; } + if (!list_empty(&local->new_client_calls)) + rxrpc_connect_client_calls(local); + /* Process received packets and errors. */ if ((skb = __skb_dequeue(&rx_queue))) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -492,7 +492,10 @@ int rxrpc_io_thread(void *data) should_stop = kthread_should_stop(); if (!skb_queue_empty(&local->rx_queue) || !list_empty(&local->call_attend_q) || - !list_empty(&local->conn_attend_q)) { + !list_empty(&local->conn_attend_q) || + !list_empty(&local->new_client_calls) || + test_bit(RXRPC_CLIENT_CONN_REAP_TIMER, + &local->client_conn_flags)) { __set_current_state(TASK_RUNNING); continue; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 9bc8d08ca12c..b8eaca5d9f22 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -117,7 +117,6 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net, local->client_bundles = RB_ROOT; spin_lock_init(&local->client_bundles_lock); local->kill_all_client_conns = false; - spin_lock_init(&local->client_conn_cache_lock); INIT_LIST_HEAD(&local->idle_client_conns); timer_setup(&local->client_conn_reap_timer, rxrpc_client_conn_reap_timeout, 0); @@ -133,7 +132,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net, if (tmp == 0) tmp = 1; idr_set_cursor(&local->conn_ids, tmp); - spin_lock_init(&local->conn_lock); + INIT_LIST_HEAD(&local->new_client_calls); + spin_lock_init(&local->client_call_lock); trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, 1); } @@ -435,7 +435,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local) * local endpoint. */ rxrpc_purge_queue(&local->rx_queue); - rxrpc_destroy_client_conn_ids(local); + rxrpc_purge_client_connections(local); } /* diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index c39ef94602ed..750158a085cd 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -12,6 +12,7 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { [RXRPC_CONN_UNUSED] = "Unused ", + [RXRPC_CONN_CLIENT_UNSECURED] = "ClUnsec ", [RXRPC_CONN_CLIENT] = "Client ", [RXRPC_CONN_SERVICE_PREALLOC] = "SvPrealc", [RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ", diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index dfb01e7b90fb..1bf571a66e02 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -1122,36 +1122,31 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, goto protocol_error_free; } - spin_lock(&conn->bundle->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { - struct rxrpc_call *call; u32 call_id = ntohl(response->encrypted.call_id[i]); + u32 counter = READ_ONCE(conn->channels[i].call_counter); if (call_id > INT_MAX) { rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, rxkad_abort_resp_bad_callid); - goto protocol_error_unlock; + goto protocol_error_free; } - if (call_id < conn->channels[i].call_counter) { + if (call_id < counter) { rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, rxkad_abort_resp_call_ctr); - goto protocol_error_unlock; + goto protocol_error_free; } - if (call_id > conn->channels[i].call_counter) { - call = rcu_dereference_protected( - conn->channels[i].call, - lockdep_is_held(&conn->bundle->channel_lock)); - if (call && !__rxrpc_call_is_complete(call)) { + if (call_id > counter) { + if (conn->channels[i].call) { rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, rxkad_abort_resp_call_state); - goto protocol_error_unlock; + goto protocol_error_free; } conn->channels[i].call_counter = call_id; } } - spin_unlock(&conn->bundle->channel_lock); if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1) { rxrpc_abort_conn(conn, skb, RXKADOUTOFSEQUENCE, -EPROTO, @@ -1179,8 +1174,6 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, _leave(" = 0"); return 0; -protocol_error_unlock: - spin_unlock(&conn->bundle->channel_lock); protocol_error_free: kfree(ticket); protocol_error: diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index 78af14694618..cd66634dffe6 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -97,38 +97,31 @@ found: */ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) { - const struct rxrpc_security *sec; struct rxrpc_key_token *token; struct key *key = conn->key; - int ret; + int ret = 0; _enter("{%d},{%x}", conn->debug_id, key_serial(key)); - if (!key) - return 0; - - ret = key_validate(key); - if (ret < 0) - return ret; - for (token = key->payload.data[0]; token; token = token->next) { - sec = rxrpc_security_lookup(token->security_index); - if (sec) + if (token->security_index == conn->security->security_index) goto found; } return -EKEYREJECTED; found: - conn->security = sec; - - ret = conn->security->init_connection_security(conn, token); - if (ret < 0) { - conn->security = &rxrpc_no_security; - return ret; + mutex_lock(&conn->security_lock); + if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) { + ret = conn->security->init_connection_security(conn, token); + if (ret == 0) { + spin_lock(&conn->state_lock); + if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) + conn->state = RXRPC_CONN_CLIENT; + spin_unlock(&conn->state_lock); + } } - - _leave(" = 0"); - return 0; + mutex_unlock(&conn->security_lock); + return ret; } /* diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index a5d0005b7ce5..da49fcf1c456 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -38,6 +38,60 @@ bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, return false; } +/* + * Wait for a call to become connected. Interruption here doesn't cause the + * call to be aborted. + */ +static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo) +{ + DECLARE_WAITQUEUE(myself, current); + int ret = 0; + + _enter("%d", call->debug_id); + + if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) + return call->error; + + add_wait_queue_exclusive(&call->waitq, &myself); + + for (;;) { + ret = call->error; + if (ret < 0) + break; + + switch (call->interruptibility) { + case RXRPC_INTERRUPTIBLE: + case RXRPC_PREINTERRUPTIBLE: + set_current_state(TASK_INTERRUPTIBLE); + break; + case RXRPC_UNINTERRUPTIBLE: + default: + set_current_state(TASK_UNINTERRUPTIBLE); + break; + } + if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) { + ret = call->error; + break; + } + if ((call->interruptibility == RXRPC_INTERRUPTIBLE || + call->interruptibility == RXRPC_PREINTERRUPTIBLE) && + signal_pending(current)) { + ret = sock_intr_errno(*timeo); + break; + } + *timeo = schedule_timeout(*timeo); + } + + remove_wait_queue(&call->waitq, &myself); + __set_current_state(TASK_RUNNING); + + if (ret == 0 && rxrpc_call_is_complete(call)) + ret = call->error; + + _leave(" = %d", ret); + return ret; +} + /* * Return true if there's sufficient Tx queue space. */ @@ -239,6 +293,16 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + ret = rxrpc_wait_to_be_connected(call, &timeo); + if (ret < 0) + return ret; + + if (call->conn->state == RXRPC_CONN_CLIENT_UNSECURED) { + ret = rxrpc_init_client_conn_security(call->conn); + if (ret < 0) + return ret; + } + /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); From c244c092f1ed2acfb5af3d3da81e22367d3dd733 Mon Sep 17 00:00:00 2001 From: Tung Nguyen Date: Thu, 5 Jan 2023 06:02:51 +0000 Subject: [PATCH 138/233] tipc: fix unexpected link reset due to discovery messages This unexpected behavior is observed: node 1 | node 2 ------ | ------ link is established | link is established reboot | link is reset up | send discovery message receive discovery message | link is established | link is established send discovery message | | receive discovery message | link is reset (unexpected) | send reset message link is reset | It is due to delayed re-discovery as described in function tipc_node_check_dest(): "this link endpoint has already reset and re-established contact with the peer, before receiving a discovery message from that node." However, commit 598411d70f85 has changed the condition for calling tipc_node_link_down() which was the acceptance of new media address. This commit fixes this by restoring the old and correct behavior. Fixes: 598411d70f85 ("tipc: make resetting of links non-atomic") Acked-by: Jon Maloy Signed-off-by: Tung Nguyen Signed-off-by: David S. Miller --- net/tipc/node.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/tipc/node.c b/net/tipc/node.c index 49ddc484c4fe..5e000fde8067 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1179,8 +1179,9 @@ void tipc_node_check_dest(struct net *net, u32 addr, bool addr_match = false; bool sign_match = false; bool link_up = false; + bool link_is_reset = false; bool accept_addr = false; - bool reset = true; + bool reset = false; char *if_name; unsigned long intv; u16 session; @@ -1200,14 +1201,14 @@ void tipc_node_check_dest(struct net *net, u32 addr, /* Prepare to validate requesting node's signature and media address */ l = le->link; link_up = l && tipc_link_is_up(l); + link_is_reset = l && tipc_link_is_reset(l); addr_match = l && !memcmp(&le->maddr, maddr, sizeof(*maddr)); sign_match = (signature == n->signature); /* These three flags give us eight permutations: */ if (sign_match && addr_match && link_up) { - /* All is fine. Do nothing. */ - reset = false; + /* All is fine. Ignore requests. */ /* Peer node is not a container/local namespace */ if (!n->peer_hash_mix) n->peer_hash_mix = hash_mixes; @@ -1232,6 +1233,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, */ accept_addr = true; *respond = true; + reset = true; } else if (!sign_match && addr_match && link_up) { /* Peer node rebooted. Two possibilities: * - Delayed re-discovery; this link endpoint has already @@ -1263,6 +1265,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, n->signature = signature; accept_addr = true; *respond = true; + reset = true; } if (!accept_addr) @@ -1291,6 +1294,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, tipc_link_fsm_evt(l, LINK_RESET_EVT); if (n->state == NODE_FAILINGOVER) tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT); + link_is_reset = tipc_link_is_reset(l); le->link = l; n->link_cnt++; tipc_node_calculate_timer(n, l); @@ -1303,7 +1307,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, memcpy(&le->maddr, maddr, sizeof(*maddr)); exit: tipc_node_write_unlock(n); - if (reset && l && !tipc_link_is_reset(l)) + if (reset && !link_is_reset) tipc_node_link_down(n, b->identity, false); tipc_node_put(n); } From 83c7423d1eb6806d13c521d1002cc1a012111719 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 21 Dec 2022 17:45:51 +0100 Subject: [PATCH 139/233] udf: Fix extension of the last extent in the file When extending the last extent in the file within the last block, we wrongly computed the length of the last extent. This is mostly a cosmetical problem since the extent does not contain any data and the length will be fixed up by following operations but still. Fixes: 1f3868f06855 ("udf: Fix extending file within last block") Signed-off-by: Jan Kara --- fs/udf/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 1d7c2a812fc1..f3e988928d1d 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -595,7 +595,7 @@ static void udf_do_extend_final_block(struct inode *inode, */ if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK)) return; - added_bytes = (last_ext->extLength & UDF_EXTENT_LENGTH_MASK) - new_elen; + added_bytes = new_elen - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); last_ext->extLength += added_bytes; UDF_I(inode)->i_lenExtents += added_bytes; From 23970a1c9475b305770fd37bebfec7a10f263787 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 30 Dec 2022 12:53:41 -0500 Subject: [PATCH 140/233] udf: initialize newblock to 0 The clang build reports this error fs/udf/inode.c:805:6: error: variable 'newblock' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized] if (*err < 0) ^~~~~~~~ newblock is never set before error handling jump. Initialize newblock to 0 and remove redundant settings. Fixes: d8b39db5fab8 ("udf: Handle error when adding extent to a file") Reported-by: Nathan Chancellor Signed-off-by: Tom Rix Signed-off-by: Jan Kara Message-Id: <20221230175341.1629734-1-trix@redhat.com> --- fs/udf/inode.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index f3e988928d1d..34e416327dd4 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -684,7 +684,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, struct kernel_lb_addr eloc, tmpeloc; int c = 1; loff_t lbcount = 0, b_off = 0; - udf_pblk_t newblocknum, newblock; + udf_pblk_t newblocknum, newblock = 0; sector_t offset = 0; int8_t etype; struct udf_inode_info *iinfo = UDF_I(inode); @@ -787,7 +787,6 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len); if (ret < 0) { *err = ret; - newblock = 0; goto out_free; } c = 0; @@ -852,7 +851,6 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, goal, err); if (!newblocknum) { *err = -ENOSPC; - newblock = 0; goto out_free; } if (isBeyondEOF) From e498a04443240c15c3c857165f7b652b87f4fd96 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 3 Jan 2023 13:17:46 +0100 Subject: [PATCH 141/233] usb: dwc3: xilinx: include linux/gpio/consumer.h The newly added gpio consumer calls cause a build failure in configurations that fail to include the right header implicitly: drivers/usb/dwc3/dwc3-xilinx.c: In function 'dwc3_xlnx_init_zynqmp': drivers/usb/dwc3/dwc3-xilinx.c:207:22: error: implicit declaration of function 'devm_gpiod_get_optional'; did you mean 'devm_clk_get_optional'? [-Werror=implicit-function-declaration] 207 | reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); | ^~~~~~~~~~~~~~~~~~~~~~~ | devm_clk_get_optional Fixes: ca05b38252d7 ("usb: dwc3: xilinx: Add gpio-reset support") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230103121755.956027-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/dwc3-xilinx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c index 8607d4c23283..0745e9f11b2e 100644 --- a/drivers/usb/dwc3/dwc3-xilinx.c +++ b/drivers/usb/dwc3/dwc3-xilinx.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include From c4e3ef5685393c5051b52cf1e94b8891d49793ab Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Thu, 8 Dec 2022 16:50:35 -0800 Subject: [PATCH 142/233] usb: dwc3: gadget: Ignore End Transfer delay on teardown If we delay sending End Transfer for Setup TRB to be prepared, we need to check if the End Transfer was in preparation for a driver teardown/soft-disconnect. In those cases, just send the End Transfer command without delay. In the case of soft-disconnect, there's a very small chance the command may not go through immediately. But should it happen, the Setup TRB will be prepared during the polling of the controller halted state, allowing the command to go through then. In the case of disabling endpoint due to reconfiguration (e.g. set_interface(alt-setting) or usb reset), then it's driven by the host. Typically the host wouldn't immediately cancel the control request and send another control transfer to trigger the End Transfer command timeout. Fixes: 4db0fbb60136 ("usb: dwc3: gadget: Don't delay End Transfer on delayed_status") Cc: stable@vger.kernel.org Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/f1617a323e190b9cc408fb8b65456e32b5814113.1670546756.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 789976567f9f..89dcfac01235 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1727,6 +1727,7 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int else if (!ret) dep->flags |= DWC3_EP_END_TRANSFER_PENDING; + dep->flags &= ~DWC3_EP_DELAY_STOP; return ret; } @@ -3732,8 +3733,10 @@ void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, if (dep->number <= 1 && dwc->ep0state != EP0_DATA_PHASE) return; + if (interrupt && (dep->flags & DWC3_EP_DELAY_STOP)) + return; + if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) || - (dep->flags & DWC3_EP_DELAY_STOP) || (dep->flags & DWC3_EP_END_TRANSFER_PENDING)) return; From 0d4d52361b6c29bf771acd4fa461f06d78fb2fac Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 3 Jan 2023 15:11:07 +0100 Subject: [PATCH 143/233] s390/debug: add _ASM_S390_ prefix to header guard Using DEBUG_H without a prefix is very generic and inconsistent with other header guards in arch/s390/include/asm. In fact it collides with the same name in the ath9k wireless driver though that depends on !S390 via disabled wireless support. Let's just use a consistent header guard name and prevent possible future trouble. Signed-off-by: Niklas Schnelle Signed-off-by: Heiko Carstens --- arch/s390/include/asm/debug.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 77f24262c25c..ac665b9670c5 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -4,8 +4,8 @@ * * Copyright IBM Corp. 1999, 2020 */ -#ifndef DEBUG_H -#define DEBUG_H +#ifndef _ASM_S390_DEBUG_H +#define _ASM_S390_DEBUG_H #include #include @@ -487,4 +487,4 @@ void debug_register_static(debug_info_t *id, int pages_per_area, int nr_areas); #endif /* MODULE */ -#endif /* DEBUG_H */ +#endif /* _ASM_S390_DEBUG_H */ From 45d619bdaf799196d702a9ae464b07066d6db2f9 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 7 Dec 2022 17:15:19 +0100 Subject: [PATCH 144/233] s390: expicitly align _edata and _end symbols on page boundary Symbols _edata and _end in the linker script are the only unaligned expicitly on page boundary. Although _end is aligned implicitly by BSS_SECTION macro that is still inconsistent and could lead to a bug if a tool or function would assume that _edata is as aligned as others. For example, vmem_map_init() function does not align symbols _etext, _einittext etc. Should these symbols be unaligned as well, the size of ranges to update were short on one page. Instead of fixing every occurrence of this kind in the code and external tools just force the alignment on these two symbols. Reviewed-by: Heiko Carstens Signed-off-by: Alexander Gordeev Signed-off-by: Heiko Carstens --- arch/s390/kernel/vmlinux.lds.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 5ea3830af0cc..f81d96710595 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -79,6 +79,7 @@ SECTIONS _end_amode31_refs = .; } + . = ALIGN(PAGE_SIZE); _edata = .; /* End of data section */ /* will be freed after init */ @@ -193,6 +194,7 @@ SECTIONS BSS_SECTION(PAGE_SIZE, 4 * PAGE_SIZE, PAGE_SIZE) + . = ALIGN(PAGE_SIZE); _end = . ; /* From a494398bde273143c2352dd373cad8211f7d94b2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 5 Jan 2023 12:13:06 +0900 Subject: [PATCH 145/233] s390: define RUNTIME_DISCARD_EXIT to fix link error with GNU ld < 2.36 Nathan Chancellor reports that the s390 vmlinux fails to link with GNU ld < 2.36 since commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv"). It happens for defconfig, or more specifically for CONFIG_EXPOLINE=y. $ s390x-linux-gnu-ld --version | head -n1 GNU ld (GNU Binutils for Debian) 2.35.2 $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- allnoconfig $ ./scripts/config -e CONFIG_EXPOLINE $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- olddefconfig $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- `.exit.text' referenced in section `.s390_return_reg' of drivers/base/dd.o: defined in discarded section `.exit.text' of drivers/base/dd.o make[1]: *** [scripts/Makefile.vmlinux:34: vmlinux] Error 1 make: *** [Makefile:1252: vmlinux] Error 2 arch/s390/kernel/vmlinux.lds.S wants to keep EXIT_TEXT: .exit.text : { EXIT_TEXT } But, at the same time, EXIT_TEXT is thrown away by DISCARD because s390 does not define RUNTIME_DISCARD_EXIT. I still do not understand why the latter wins after 99cb0d917ffa, but defining RUNTIME_DISCARD_EXIT seems correct because the comment line in arch/s390/kernel/vmlinux.lds.S says: /* * .exit.text is discarded at runtime, not link time, * to deal with references from __bug_table */ Nathan also found that binutils commit 21401fc7bf67 ("Duplicate output sections in scripts") cured this issue, so we cannot reproduce it with binutils 2.36+, but it is better to not rely on it. Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Link: https://lore.kernel.org/all/Y7Jal56f6UBh1abE@dev-arch.thelio-3990X/ Reported-by: Nathan Chancellor Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20230105031306.1455409-1-masahiroy@kernel.org Signed-off-by: Heiko Carstens --- arch/s390/kernel/vmlinux.lds.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index f81d96710595..cbf9c1b0beda 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -17,6 +17,8 @@ /* Handle ro_after_init data on our own. */ #define RO_AFTER_INIT_DATA +#define RUNTIME_DISCARD_EXIT + #define EMITS_PT_NOTE #include From 0b3a551fa58b4da941efeb209b3770868e2eddd7 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 5 Jan 2023 14:55:56 -0500 Subject: [PATCH 146/233] nfsd: fix handling of cached open files in nfsd4_open codepath Commit fb70bf124b05 ("NFSD: Instantiate a struct file when creating a regular NFSv4 file") added the ability to cache an open fd over a compound. There are a couple of problems with the way this currently works: It's racy, as a newly-created nfsd_file can end up with its PENDING bit cleared while the nf is hashed, and the nf_file pointer is still zeroed out. Other tasks can find it in this state and they expect to see a valid nf_file, and can oops if nf_file is NULL. Also, there is no guarantee that we'll end up creating a new nfsd_file if one is already in the hash. If an extant entry is in the hash with a valid nf_file, nfs4_get_vfs_file will clobber its nf_file pointer with the value of op_file and the old nf_file will leak. Fix both issues by making a new nfsd_file_acquirei_opened variant that takes an optional file pointer. If one is present when this is called, we'll take a new reference to it instead of trying to open the file. If the nfsd_file already has a valid nf_file, we'll just ignore the optional file and pass the nfsd_file back as-is. Also rework the tracepoints a bit to allow for an "opened" variant and don't try to avoid counting acquisitions in the case where we already have a cached open file. Fixes: fb70bf124b05 ("NFSD: Instantiate a struct file when creating a regular NFSv4 file") Cc: Trond Myklebust Reported-by: Stanislav Saner Reported-and-Tested-by: Ruben Vestergaard Reported-and-Tested-by: Torkil Svensgaard Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 40 ++++++++++++++++++---------------- fs/nfsd/filecache.h | 5 +++-- fs/nfsd/nfs4state.c | 16 ++++---------- fs/nfsd/trace.h | 52 ++++++++++++--------------------------------- 4 files changed, 42 insertions(+), 71 deletions(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 45b2c9e3f636..0ef070349014 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1071,8 +1071,8 @@ nfsd_file_is_cached(struct inode *inode) static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **pnf, - bool open, bool want_gc) + unsigned int may_flags, struct file *file, + struct nfsd_file **pnf, bool want_gc) { struct nfsd_file_lookup_key key = { .type = NFSD_FILE_KEY_FULL, @@ -1147,8 +1147,7 @@ wait_for_construction: status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); out: if (status == nfs_ok) { - if (open) - this_cpu_inc(nfsd_file_acquisitions); + this_cpu_inc(nfsd_file_acquisitions); *pnf = nf; } else { if (refcount_dec_and_test(&nf->nf_ref)) @@ -1158,20 +1157,23 @@ out: out_status: put_cred(key.cred); - if (open) - trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); + trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); return status; open_file: trace_nfsd_file_alloc(nf); nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode); if (nf->nf_mark) { - if (open) { + if (file) { + get_file(file); + nf->nf_file = file; + status = nfs_ok; + trace_nfsd_file_opened(nf, status); + } else { status = nfsd_open_verified(rqstp, fhp, may_flags, &nf->nf_file); trace_nfsd_file_open(nf, status); - } else - status = nfs_ok; + } } else status = nfserr_jukebox; /* @@ -1207,7 +1209,7 @@ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, true); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true); } /** @@ -1228,28 +1230,30 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, false); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false); } /** - * nfsd_file_create - Get a struct nfsd_file, do not open + * nfsd_file_acquire_opened - Get a struct nfsd_file using existing open file * @rqstp: the RPC transaction being executed * @fhp: the NFS filehandle of the file just created * @may_flags: NFSD_MAY_ settings for the file + * @file: cached, already-open file (may be NULL) * @pnf: OUT: new or found "struct nfsd_file" object * - * The nfsd_file_object returned by this API is reference-counted - * but not garbage-collected. The object is released immediately - * one RCU grace period after the final nfsd_file_put(). + * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist, + * and @file is non-NULL, use it to instantiate a new nfsd_file instead of + * opening a new one. * * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in * network byte order is returned. */ __be32 -nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **pnf) +nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct file *file, + struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false, false); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false); } /* diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index b7efb2c3ddb1..41516a4263ea 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -60,7 +60,8 @@ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **nfp); __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **nfp); -__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **nfp); +__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct file *file, + struct nfsd_file **nfp); int nfsd_file_cache_stats_show(struct seq_file *m, void *v); #endif /* _FS_NFSD_FILECACHE_H */ diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index e1e85c21f12b..313f666d5357 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5262,18 +5262,10 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, if (!fp->fi_fds[oflag]) { spin_unlock(&fp->fi_lock); - if (!open->op_filp) { - status = nfsd_file_acquire(rqstp, cur_fh, access, &nf); - if (status != nfs_ok) - goto out_put_access; - } else { - status = nfsd_file_create(rqstp, cur_fh, access, &nf); - if (status != nfs_ok) - goto out_put_access; - nf->nf_file = open->op_filp; - open->op_filp = NULL; - trace_nfsd_file_create(rqstp, access, nf); - } + status = nfsd_file_acquire_opened(rqstp, cur_fh, access, + open->op_filp, &nf); + if (status != nfs_ok) + goto out_put_access; spin_lock(&fp->fi_lock); if (!fp->fi_fds[oflag]) { diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index c852ae8eaf37..8f9c82d9e075 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -981,43 +981,6 @@ TRACE_EVENT(nfsd_file_acquire, ) ); -TRACE_EVENT(nfsd_file_create, - TP_PROTO( - const struct svc_rqst *rqstp, - unsigned int may_flags, - const struct nfsd_file *nf - ), - - TP_ARGS(rqstp, may_flags, nf), - - TP_STRUCT__entry( - __field(const void *, nf_inode) - __field(const void *, nf_file) - __field(unsigned long, may_flags) - __field(unsigned long, nf_flags) - __field(unsigned long, nf_may) - __field(unsigned int, nf_ref) - __field(u32, xid) - ), - - TP_fast_assign( - __entry->nf_inode = nf->nf_inode; - __entry->nf_file = nf->nf_file; - __entry->may_flags = may_flags; - __entry->nf_flags = nf->nf_flags; - __entry->nf_may = nf->nf_may; - __entry->nf_ref = refcount_read(&nf->nf_ref); - __entry->xid = be32_to_cpu(rqstp->rq_xid); - ), - - TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p", - __entry->xid, __entry->nf_inode, - show_nfsd_may_flags(__entry->may_flags), - __entry->nf_ref, show_nf_flags(__entry->nf_flags), - show_nfsd_may_flags(__entry->nf_may), __entry->nf_file - ) -); - TRACE_EVENT(nfsd_file_insert_err, TP_PROTO( const struct svc_rqst *rqstp, @@ -1079,8 +1042,8 @@ TRACE_EVENT(nfsd_file_cons_err, ) ); -TRACE_EVENT(nfsd_file_open, - TP_PROTO(struct nfsd_file *nf, __be32 status), +DECLARE_EVENT_CLASS(nfsd_file_open_class, + TP_PROTO(const struct nfsd_file *nf, __be32 status), TP_ARGS(nf, status), TP_STRUCT__entry( __field(void *, nf_inode) /* cannot be dereferenced */ @@ -1104,6 +1067,17 @@ TRACE_EVENT(nfsd_file_open, __entry->nf_file) ) +#define DEFINE_NFSD_FILE_OPEN_EVENT(name) \ +DEFINE_EVENT(nfsd_file_open_class, name, \ + TP_PROTO( \ + const struct nfsd_file *nf, \ + __be32 status \ + ), \ + TP_ARGS(nf, status)) + +DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_open); +DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_opened); + TRACE_EVENT(nfsd_file_is_cached, TP_PROTO( const struct inode *inode, From 7827c81f0248e3c2f40d438b020f3d222f002171 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 6 Jan 2023 12:43:37 -0500 Subject: [PATCH 147/233] Revert "SUNRPC: Use RMW bitops in single-threaded hot paths" The premise that "Once an svc thread is scheduled and executing an RPC, no other processes will touch svc_rqst::rq_flags" is false. svc_xprt_enqueue() examines the RQ_BUSY flag in scheduled nfsd threads when determining which thread to wake up next. Found via KCSAN. Fixes: 28df0988815f ("SUNRPC: Use RMW bitops in single-threaded hot paths") Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/nfs4proc.c | 7 +++---- fs/nfsd/nfs4xdr.c | 2 +- net/sunrpc/auth_gss/svcauth_gss.c | 4 ++-- net/sunrpc/svc.c | 6 +++--- net/sunrpc/svc_xprt.c | 2 +- net/sunrpc/svcsock.c | 8 ++++---- net/sunrpc/xprtrdma/svc_rdma_transport.c | 2 +- 7 files changed, 15 insertions(+), 16 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index bd880d55f565..9b81d012666e 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -937,7 +937,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * the client wants us to do more in this compound: */ if (!nfsd4_last_compound_op(rqstp)) - __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* check stateid */ status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, @@ -2607,12 +2607,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) cstate->minorversion = args->minorversion; fh_init(current_fh, NFS4_FHSIZE); fh_init(save_fh, NFS4_FHSIZE); - /* * Don't use the deferral mechanism for NFSv4; compounds make it * too hard to avoid non-idempotency problems. */ - __clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); /* * According to RFC3010, this takes precedence over all other errors. @@ -2734,7 +2733,7 @@ encode_op: out: cstate->status = status; /* Reset deferral mechanism for RPC deferrals */ - __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); return rpc_success; } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index ebb4d02a42ce..97edb32be77f 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2523,7 +2523,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE; if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) - __clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); return true; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 148bb0a7fa5b..acb822b23af1 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -923,7 +923,7 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g * rejecting the server-computed MIC in this somewhat rare case, * do not use splice with the GSS integrity service. */ - __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* Did we already verify the signature on the original pass through? */ if (rqstp->rq_deferred) @@ -990,7 +990,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs int pad, remaining_len, offset; u32 rseqno; - __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); priv_len = svc_getnl(&buf->head[0]); if (rqstp->rq_deferred) { diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 8f1b596db33f..b1da586c4476 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1243,10 +1243,10 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) goto err_short_len; /* Will be turned off by GSS integrity and privacy services */ - __set_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + set_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* Will be turned off only when NFSv4 Sessions are used */ - __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); - __clear_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + clear_bit(RQ_DROPME, &rqstp->rq_flags); svc_putu32(resv, rqstp->rq_xid); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 2106003645a7..c2ce12538008 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1238,7 +1238,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; - __set_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_DROPME, &rqstp->rq_flags); dr->handle.revisit = svc_revisit; return &dr->handle; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 2fc98fea59b4..e833103f4629 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -298,9 +298,9 @@ static void svc_sock_setbufsize(struct svc_sock *svsk, unsigned int nreqs) static void svc_sock_secure_port(struct svc_rqst *rqstp) { if (svc_port_is_privileged(svc_addr(rqstp))) - __set_bit(RQ_SECURE, &rqstp->rq_flags); + set_bit(RQ_SECURE, &rqstp->rq_flags); else - __clear_bit(RQ_SECURE, &rqstp->rq_flags); + clear_bit(RQ_SECURE, &rqstp->rq_flags); } /* @@ -1008,9 +1008,9 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; rqstp->rq_prot = IPPROTO_TCP; if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags)) - __set_bit(RQ_LOCAL, &rqstp->rq_flags); + set_bit(RQ_LOCAL, &rqstp->rq_flags); else - __clear_bit(RQ_LOCAL, &rqstp->rq_flags); + clear_bit(RQ_LOCAL, &rqstp->rq_flags); p = (__be32 *)rqstp->rq_arg.head[0].iov_base; calldir = p[1]; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 199fa012f18a..94b20fb47135 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -602,7 +602,7 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt) static void svc_rdma_secure_port(struct svc_rqst *rqstp) { - __set_bit(RQ_SECURE, &rqstp->rq_flags); + set_bit(RQ_SECURE, &rqstp->rq_flags); } static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt) From cb7a95af78d29442b8294683eca4897544b8ef46 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 4 Jan 2023 11:06:28 -0800 Subject: [PATCH 148/233] hfs/hfsplus: avoid WARN_ON() for sanity check, use proper error handling Commit 55d1cbbbb29e ("hfs/hfsplus: use WARN_ON for sanity check") fixed a build warning by turning a comment into a WARN_ON(), but it turns out that syzbot then complains because it can trigger said warning with a corrupted hfs image. The warning actually does warn about a bad situation, but we are much better off just handling it as the error it is. So rather than warn about us doing bad things, stop doing the bad things and return -EIO. While at it, also fix a memory leak that was introduced by an earlier fix for a similar syzbot warning situation, and add a check for one case that historically wasn't handled at all (ie neither comment nor subsequent WARN_ON). Reported-by: syzbot+7bb7cd3595533513a9e7@syzkaller.appspotmail.com Fixes: 55d1cbbbb29e ("hfs/hfsplus: use WARN_ON for sanity check") Fixes: 8d824e69d9f3 ("hfs: fix OOB Read in __hfs_brec_find") Link: https://lore.kernel.org/lkml/000000000000dbce4e05f170f289@google.com/ Tested-by: Michael Schmitz Cc: Arnd Bergmann Cc: Matthew Wilcox Cc: Viacheslav Dubeyko Signed-off-by: Linus Torvalds --- fs/hfs/inode.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 9c329a365e75..3a155c1d810e 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -458,15 +458,16 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) /* panic? */ return -EIO; + res = -EIO; if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN) - return -EIO; + goto out; fd.search_key->cat = HFS_I(main_inode)->cat_key; if (hfs_brec_find(&fd)) - /* panic? */ goto out; if (S_ISDIR(main_inode->i_mode)) { - WARN_ON(fd.entrylength < sizeof(struct hfs_cat_dir)); + if (fd.entrylength < sizeof(struct hfs_cat_dir)) + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_dir)); if (rec.type != HFS_CDR_DIR || @@ -479,6 +480,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_dir)); } else if (HFS_IS_RSRC(inode)) { + if (fd.entrylength < sizeof(struct hfs_cat_file)) + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); hfs_inode_write_fork(inode, rec.file.RExtRec, @@ -486,7 +489,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); } else { - WARN_ON(fd.entrylength < sizeof(struct hfs_cat_file)); + if (fd.entrylength < sizeof(struct hfs_cat_file)) + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); if (rec.type != HFS_CDR_FIL || @@ -503,9 +507,10 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); } + res = 0; out: hfs_find_exit(&fd); - return 0; + return res; } static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, From 1382999aa0548a171a272ca817f6c38e797c458c Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 6 Jan 2023 04:01:56 +0100 Subject: [PATCH 149/233] tpm: Allow system suspend to continue when TPM suspend fails TPM 1 is sometimes broken across system suspends, due to races or locking issues or something else that haven't been diagnosed or fixed yet, most likely having to do with concurrent reads from the TPM's hardware random number generator driver. These issues prevent the system from actually suspending, with errors like: tpm tpm0: A TPM error (28) occurred continue selftest ... tpm tpm0: A TPM error (28) occurred attempting get random ... tpm tpm0: Error (28) sending savestate before suspend tpm_tis 00:08: PM: __pnp_bus_suspend(): tpm_pm_suspend+0x0/0x80 returns 28 tpm_tis 00:08: PM: dpm_run_callback(): pnp_bus_suspend+0x0/0x10 returns 28 tpm_tis 00:08: PM: failed to suspend: error 28 PM: Some devices failed to suspend, or early wake event detected This issue was partially fixed by 23393c646142 ("char: tpm: Protect tpm_pm_suspend with locks"), in a last minute 6.1 commit that Linus took directly because the TPM maintainers weren't available. However, it seems like this just addresses the most common cases of the bug, rather than addressing it entirely. So there are more things to fix still, apparently. In lieu of actually fixing the underlying bug, just allow system suspend to continue, so that laptops still go to sleep fine. Later, this can be reverted when the real bug is fixed. Link: https://lore.kernel.org/lkml/7cbe96cf-e0b5-ba63-d1b4-f63d2e826efa@suse.cz/ Cc: stable@vger.kernel.org # 6.1+ Reported-by: Vlastimil Babka Suggested-by: Linus Torvalds Acked-by: Luigi Semenzato Cc: Peter Huewe Cc: Jarkko Sakkinen Cc: James Bottomley Cc: Johannes Altmanninger Signed-off-by: Jason A. Donenfeld Signed-off-by: Linus Torvalds --- drivers/char/tpm/tpm-interface.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index d69905233aff..7e513b771832 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -412,7 +412,9 @@ int tpm_pm_suspend(struct device *dev) } suspended: - return rc; + if (rc) + dev_err(dev, "Ignoring error %d while suspending\n", rc); + return 0; } EXPORT_SYMBOL_GPL(tpm_pm_suspend); From b4e9b8763e417db31c7088103cc557d55cb7a8f5 Mon Sep 17 00:00:00 2001 From: Angela Czubak Date: Thu, 5 Jan 2023 21:31:07 +0530 Subject: [PATCH 150/233] octeontx2-af: Fix LMAC config in cgx_lmac_rx_tx_enable PF netdev can request AF to enable or disable reception and transmission on assigned CGX::LMAC. The current code instead of disabling or enabling 'reception and transmission' also disables/enable the LMAC. This patch fixes this issue. Fixes: 1435f66a28b4 ("octeontx2-af: CGX Rx/Tx enable/disable mbox handlers") Signed-off-by: Angela Czubak Signed-off-by: Hariprasad Kelam Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230105160107.17638-1-hkelam@marvell.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 4 ++-- drivers/net/ethernet/marvell/octeontx2/af/cgx.h | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index b2b71fe80d61..724df6398bbe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -774,9 +774,9 @@ int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable) cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_CFG); if (enable) - cfg |= CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN; + cfg |= DATA_PKT_RX_EN | DATA_PKT_TX_EN; else - cfg &= ~(CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN); + cfg &= ~(DATA_PKT_RX_EN | DATA_PKT_TX_EN); cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index fb2d37676d84..5a20d93004c7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -26,7 +26,6 @@ #define CMR_P2X_SEL_SHIFT 59ULL #define CMR_P2X_SEL_NIX0 1ULL #define CMR_P2X_SEL_NIX1 2ULL -#define CMR_EN BIT_ULL(55) #define DATA_PKT_TX_EN BIT_ULL(53) #define DATA_PKT_RX_EN BIT_ULL(54) #define CGX_LMAC_TYPE_SHIFT 40 From 4414c1f5c7a375eaa108676a56e12cc8234eb647 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Fri, 6 Jan 2023 23:30:57 -0800 Subject: [PATCH 151/233] xtensa: drop unused members of struct thread_struct bad_vaddr, bad_uaddr and error_code fields are set but never read by the xtensa arch-specific code. Drop them. Also drop the commented out info field. Signed-off-by: Max Filippov --- arch/xtensa/include/asm/processor.h | 9 --------- arch/xtensa/kernel/traps.c | 2 -- arch/xtensa/mm/fault.c | 4 ---- 3 files changed, 15 deletions(-) diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 228e4dff5fb2..a6d09fe04831 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -154,11 +154,6 @@ struct thread_struct { unsigned long ra; /* kernel's a0: return address and window call size */ unsigned long sp; /* kernel's a1: stack pointer */ - /* struct xtensa_cpuinfo info; */ - - unsigned long bad_vaddr; /* last user fault */ - unsigned long bad_uaddr; /* last kernel fault accessing user space */ - unsigned long error_code; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK]; struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK]; @@ -176,10 +171,6 @@ struct thread_struct { { \ ra: 0, \ sp: sizeof(init_stack) + (long) &init_stack, \ - /*info: {0}, */ \ - bad_vaddr: 0, \ - bad_uaddr: 0, \ - error_code: 0, \ } diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 0c25e035ff10..cd98366a9b23 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -362,8 +362,6 @@ static void do_unaligned_user(struct pt_regs *regs) __die_if_kernel("Unhandled unaligned exception in kernel", regs, SIGKILL); - current->thread.bad_vaddr = regs->excvaddr; - current->thread.error_code = -3; pr_info_ratelimited("Unaligned memory access to %08lx in '%s' " "(pid = %d, pc = %#010lx)\n", regs->excvaddr, current->comm, diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 8c781b05c0bd..faf7cf35a0ee 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -206,8 +206,6 @@ good_area: bad_area: mmap_read_unlock(mm); if (user_mode(regs)) { - current->thread.bad_vaddr = address; - current->thread.error_code = is_write; force_sig_fault(SIGSEGV, code, (void *) address); return; } @@ -232,7 +230,6 @@ do_sigbus: /* Send a sigbus, regardless of whether we were in kernel * or user mode. */ - current->thread.bad_vaddr = address; force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address); /* Kernel mode? Handle exceptions or die */ @@ -252,7 +249,6 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) if ((entry = search_exception_tables(regs->pc)) != NULL) { pr_debug("%s: Exception at pc=%#010lx (%lx)\n", current->comm, regs->pc, entry->fixup); - current->thread.bad_uaddr = address; regs->pc = entry->fixup; return; } From 42f229c350f57a8e825f7591e17cbc5c87e50235 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 6 Jan 2023 13:03:18 +0000 Subject: [PATCH 152/233] rxrpc: Fix incoming call setup race An incoming call can race with rxrpc socket destruction, leading to a leaked call. This may result in an oops when the call timer eventually expires: BUG: kernel NULL pointer dereference, address: 0000000000000874 RIP: 0010:_raw_spin_lock_irqsave+0x2a/0x50 Call Trace: try_to_wake_up+0x59/0x550 ? __local_bh_enable_ip+0x37/0x80 ? rxrpc_poke_call+0x52/0x110 [rxrpc] ? rxrpc_poke_call+0x110/0x110 [rxrpc] ? rxrpc_poke_call+0x110/0x110 [rxrpc] call_timer_fn+0x24/0x120 with a warning in the kernel log looking something like: rxrpc: Call 00000000ba5e571a still in use (1,SvAwtACK,1061d,0)! incurred during rmmod of rxrpc. The 1061d is the call flags: RECVMSG_READ_ALL, RX_HEARD, BEGAN_RX_TIMER, RX_LAST, EXPOSED, IS_SERVICE, RELEASED but no DISCONNECTED flag (0x800), so it's an incoming (service) call and it's still connected. The race appears to be that: (1) rxrpc_new_incoming_call() consults the service struct, checks sk_state and allocates a call - then pauses, possibly for an interrupt. (2) rxrpc_release_sock() sets RXRPC_CLOSE, nulls the service pointer, discards the prealloc and releases all calls attached to the socket. (3) rxrpc_new_incoming_call() resumes, launching the new call, including its timer and attaching it to the socket. Fix this by read-locking local->services_lock to access the AF_RXRPC socket providing the service rather than RCU in rxrpc_new_incoming_call(). There's no real need to use RCU here as local->services_lock is only write-locked by the socket side in two places: when binding and when shutting down. Fixes: 5e6ef4f1017c ("rxrpc: Make the I/O thread take over the call and local processor work") Reported-by: Marc Dionne Signed-off-by: David Howells cc: linux-afs@lists.infradead.org --- net/rxrpc/af_rxrpc.c | 8 ++++---- net/rxrpc/ar-internal.h | 2 +- net/rxrpc/call_accept.c | 14 +++++++------- net/rxrpc/security.c | 6 +++--- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index cf200e4e0eae..ebbd4a1c3f86 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -155,10 +155,10 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) if (service_id) { write_lock(&local->services_lock); - if (rcu_access_pointer(local->service)) + if (local->service) goto service_in_use; rx->local = local; - rcu_assign_pointer(local->service, rx); + local->service = rx; write_unlock(&local->services_lock); rx->sk.sk_state = RXRPC_SERVER_BOUND; @@ -875,9 +875,9 @@ static int rxrpc_release_sock(struct sock *sk) sk->sk_state = RXRPC_CLOSE; - if (rx->local && rcu_access_pointer(rx->local->service) == rx) { + if (rx->local && rx->local->service == rx) { write_lock(&rx->local->services_lock); - rcu_assign_pointer(rx->local->service, NULL); + rx->local->service = NULL; write_unlock(&rx->local->services_lock); } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 007258538bee..433060cade03 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -283,7 +283,7 @@ struct rxrpc_local { struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; struct completion io_thread_ready; /* Indication that the I/O thread started */ - struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ + struct rxrpc_sock *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head rx_queue; /* Received packets */ struct list_head conn_attend_q; /* Conns requiring immediate attention */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 3fbf2fcaaf9e..3e8689fdc437 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -343,13 +343,13 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, if (sp->hdr.type != RXRPC_PACKET_TYPE_DATA) return rxrpc_protocol_error(skb, rxrpc_eproto_no_service_call); - rcu_read_lock(); + read_lock(&local->services_lock); /* Weed out packets to services we're not offering. Packets that would * begin a call are explicitly rejected and the rest are just * discarded. */ - rx = rcu_dereference(local->service); + rx = local->service; if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && sp->hdr.serviceId != rx->second_service) ) { @@ -399,7 +399,7 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, spin_unlock(&conn->state_lock); spin_unlock(&rx->incoming_lock); - rcu_read_unlock(); + read_unlock(&local->services_lock); if (hlist_unhashed(&call->error_link)) { spin_lock(&call->peer->lock); @@ -413,20 +413,20 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, return true; unsupported_service: - rcu_read_unlock(); + read_unlock(&local->services_lock); return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, RX_INVALID_OPERATION, -EOPNOTSUPP); unsupported_security: - rcu_read_unlock(); + read_unlock(&local->services_lock); return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, RX_INVALID_OPERATION, -EKEYREJECTED); no_call: spin_unlock(&rx->incoming_lock); - rcu_read_unlock(); + read_unlock(&local->services_lock); _leave(" = f [%u]", skb->mark); return false; discard: - rcu_read_unlock(); + read_unlock(&local->services_lock); return true; } diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index cd66634dffe6..cb8dd1d3b1d4 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -178,9 +178,9 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn, sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex); - rcu_read_lock(); + read_lock(&conn->local->services_lock); - rx = rcu_dereference(conn->local->service); + rx = conn->local->service; if (!rx) goto out; @@ -202,6 +202,6 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn, } out: - rcu_read_unlock(); + read_unlock(&conn->local->services_lock); return key; } From ea44242bbfcde2993fb27ec7c3ad5ab5cc39e438 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Thu, 15 Dec 2022 12:09:25 +0800 Subject: [PATCH 153/233] scsi: hisi_sas: Fix tag freeing for reserved tags The reserved tags were put in the lower region of the tagset in commit f7d190a94e35 ("scsi: hisi_sas: Put reserved tags in lower region of tagset"). However, only the allocate function was changed, freeing was not handled. This resulted in a failure to boot: [ 33.467345] hisi_sas_v3_hw 0000:b4:02.0: task exec: failed[-132]! [ 33.473413] sas: Executing internal abort failed 5000000000000603 (-132) [ 33.480088] hisi_sas_v3_hw 0000:b4:02.0: I_T nexus reset: internal abort (-132) [ 33.657336] hisi_sas_v3_hw 0000:b4:02.0: task exec: failed[-132]! [ 33.663403] ata7.00: failed to IDENTIFY (I/O error, err_mask=0x40) [ 35.787344] hisi_sas_v3_hw 0000:b4:04.0: task exec: failed[-132]! [ 35.793411] sas: Executing internal abort failed 5000000000000703 (-132) [ 35.800084] hisi_sas_v3_hw 0000:b4:04.0: I_T nexus reset: internal abort (-132) [ 35.977335] hisi_sas_v3_hw 0000:b4:04.0: task exec: failed[-132]! [ 35.983403] ata10.00: failed to IDENTIFY (I/O error, err_mask=0x40) [ 35.989643] ata10.00: revalidation failed (errno=-5) Fixes: f7d190a94e35 ("scsi: hisi_sas: Put reserved tags in lower region of tagset") Cc: John Garry Cc: Xiang Chen Signed-off-by: Jason Yan Reviewed-by: John Garry Acked-by: Xiang Chen Signed-off-by: Martin K. Petersen --- drivers/scsi/hisi_sas/hisi_sas_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 41ba22f6c7f0..e9c2d306ed87 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -162,7 +162,7 @@ static void hisi_sas_slot_index_clear(struct hisi_hba *hisi_hba, int slot_idx) static void hisi_sas_slot_index_free(struct hisi_hba *hisi_hba, int slot_idx) { if (hisi_hba->hw->slot_index_alloc || - slot_idx >= HISI_SAS_UNRESERVED_IPTT) { + slot_idx < HISI_SAS_RESERVED_IPTT) { spin_lock(&hisi_hba->lock); hisi_sas_slot_index_clear(hisi_hba, slot_idx); spin_unlock(&hisi_hba->lock); From a67aad57d9aee41180aff36e54cb72fe4b8d5a5a Mon Sep 17 00:00:00 2001 From: Xingui Yang Date: Wed, 21 Dec 2022 01:52:03 +0000 Subject: [PATCH 154/233] scsi: libsas: Grab the ATA port lock in sas_ata_device_link_abort() Grab the ATA port lock in sas_ata_device_link_abort() before calling ata_link_abort() as outlined in this function's locking requirements. Fixes: 44112922674b ("scsi: libsas: Add sas_ata_device_link_abort()") Signed-off-by: Xingui Yang Reviewed-by: John Garry Reviewed-by: Jason Yan Signed-off-by: Martin K. Petersen --- drivers/scsi/libsas/sas_ata.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 1ccce706167a..5e80225b5308 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -889,7 +889,9 @@ void sas_ata_device_link_abort(struct domain_device *device, bool force_reset) { struct ata_port *ap = device->sata_dev.ap; struct ata_link *link = &ap->link; + unsigned long flags; + spin_lock_irqsave(ap->lock, flags); device->sata_dev.fis[2] = ATA_ERR | ATA_DRDY; /* tf status */ device->sata_dev.fis[3] = ATA_ABORTED; /* tf error */ @@ -897,6 +899,7 @@ void sas_ata_device_link_abort(struct domain_device *device, bool force_reset) if (force_reset) link->eh_info.action |= ATA_EH_RESET; ata_link_abort(link); + spin_unlock_irqrestore(ap->lock, flags); } EXPORT_SYMBOL_GPL(sas_ata_device_link_abort); From 7fb3ff22ad8772bbf0e3ce1ef3eb7b09f431807f Mon Sep 17 00:00:00 2001 From: Yair Podemsky Date: Wed, 30 Nov 2022 14:51:21 +0200 Subject: [PATCH 155/233] sched/core: Fix arch_scale_freq_tick() on tickless systems In order for the scheduler to be frequency invariant we measure the ratio between the maximum CPU frequency and the actual CPU frequency. During long tickless periods of time the calculations that keep track of that might overflow, in the function scale_freq_tick(): if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) goto error; eventually forcing the kernel to disable the feature for all CPUs, and show the warning message: "Scheduler frequency invariance went wobbly, disabling!". Let's avoid that by limiting the frequency invariant calculations to CPUs with regular tick. Fixes: e2b0d619b400 ("x86, sched: check for counters overflow in frequency invariant accounting") Suggested-by: "Peter Zijlstra (Intel)" Signed-off-by: Yair Podemsky Signed-off-by: Ingo Molnar Reviewed-by: Valentin Schneider Acked-by: Giovanni Gherdovich Link: https://lore.kernel.org/r/20221130125121.34407-1-ypodemsk@redhat.com --- kernel/sched/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 25b582b6ee5f..965d813c28ad 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5504,7 +5504,9 @@ void scheduler_tick(void) unsigned long thermal_pressure; u64 resched_latency; - arch_scale_freq_tick(); + if (housekeeping_cpu(cpu, HK_TYPE_TICK)) + arch_scale_freq_tick(); + sched_clock_tick(); rq_lock(rq, &rf); From c0f7ae27539fbac267384a7bfc58296ea7550d52 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Mon, 26 Dec 2022 16:40:43 +0200 Subject: [PATCH 156/233] MAINTAINERS: Update email of Tudor Ambarus My professional email will change and the microchip one will bounce after mid-november of 2022. Update the MAINTAINERS file, the YAML bindings, MODULE_AUTHOR entries and author mentions, and add an entry in the .mailmap file. Signed-off-by: Tudor Ambarus Acked-by: Rob Herring Acked-by: Pratyush Yadav Acked-by: Mark Brown Acked-by: Nicolas Ferre Acked-by: Herbert Xu Acked-by: Krzysztof Kozlowski Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20221226144043.367706-1-tudor.ambarus@linaro.org --- .mailmap | 1 + .../bindings/crypto/atmel,at91sam9g46-aes.yaml | 2 +- .../bindings/crypto/atmel,at91sam9g46-sha.yaml | 2 +- .../bindings/crypto/atmel,at91sam9g46-tdes.yaml | 2 +- .../devicetree/bindings/spi/atmel,at91rm9200-spi.yaml | 2 +- .../devicetree/bindings/spi/atmel,quadspi.yaml | 2 +- MAINTAINERS | 10 +++++----- drivers/crypto/atmel-ecc.c | 4 ++-- drivers/crypto/atmel-i2c.c | 4 ++-- drivers/crypto/atmel-i2c.h | 2 +- 10 files changed, 16 insertions(+), 15 deletions(-) diff --git a/.mailmap b/.mailmap index ccba4cf0d893..562f70d3b6a5 100644 --- a/.mailmap +++ b/.mailmap @@ -422,6 +422,7 @@ Tony Luck TripleX Chung TripleX Chung Tsuneo Yoshioka +Tudor Ambarus Tycho Andersen Tzung-Bi Shih Uwe Kleine-König diff --git a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml index 0ccaab16dc61..0b7383b3106b 100644 --- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml +++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel Advanced Encryption Standard (AES) HW cryptographic accelerator maintainers: - - Tudor Ambarus + - Tudor Ambarus properties: compatible: diff --git a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml index 5163c51b4547..ee2ffb034325 100644 --- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml +++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel Secure Hash Algorithm (SHA) HW cryptographic accelerator maintainers: - - Tudor Ambarus + - Tudor Ambarus properties: compatible: diff --git a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml index fcc5adf03cad..3d6ed24b1b00 100644 --- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml +++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel Triple Data Encryption Standard (TDES) HW cryptographic accelerator maintainers: - - Tudor Ambarus + - Tudor Ambarus properties: compatible: diff --git a/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml b/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml index 4dd973e341e6..6c57dd6c3a36 100644 --- a/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml +++ b/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel SPI device maintainers: - - Tudor Ambarus + - Tudor Ambarus allOf: - $ref: spi-controller.yaml# diff --git a/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml b/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml index 1d493add4053..b0d99bc10535 100644 --- a/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml +++ b/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel Quad Serial Peripheral Interface (QSPI) maintainers: - - Tudor Ambarus + - Tudor Ambarus allOf: - $ref: spi-controller.yaml# diff --git a/MAINTAINERS b/MAINTAINERS index 7f86d02cb427..36c500e34508 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13620,7 +13620,7 @@ F: arch/microblaze/ MICROCHIP AT91 DMA DRIVERS M: Ludovic Desroches -M: Tudor Ambarus +M: Tudor Ambarus L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: dmaengine@vger.kernel.org S: Supported @@ -13665,7 +13665,7 @@ F: Documentation/devicetree/bindings/media/microchip,csi2dc.yaml F: drivers/media/platform/microchip/microchip-csi2dc.c MICROCHIP ECC DRIVER -M: Tudor Ambarus +M: Tudor Ambarus L: linux-crypto@vger.kernel.org S: Maintained F: drivers/crypto/atmel-ecc.* @@ -13762,7 +13762,7 @@ S: Maintained F: drivers/mmc/host/atmel-mci.c MICROCHIP NAND DRIVER -M: Tudor Ambarus +M: Tudor Ambarus L: linux-mtd@lists.infradead.org S: Supported F: Documentation/devicetree/bindings/mtd/atmel-nand.txt @@ -13814,7 +13814,7 @@ S: Supported F: drivers/power/reset/at91-sama5d2_shdwc.c MICROCHIP SPI DRIVER -M: Tudor Ambarus +M: Tudor Ambarus S: Supported F: drivers/spi/spi-atmel.* @@ -19665,7 +19665,7 @@ F: drivers/clk/spear/ F: drivers/pinctrl/spear/ SPI NOR SUBSYSTEM -M: Tudor Ambarus +M: Tudor Ambarus M: Pratyush Yadav R: Michael Walle L: linux-mtd@lists.infradead.org diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c index 53100fb9b07b..12205e2b53b4 100644 --- a/drivers/crypto/atmel-ecc.c +++ b/drivers/crypto/atmel-ecc.c @@ -3,7 +3,7 @@ * Microchip / Atmel ECC (I2C) driver. * * Copyright (c) 2017, Microchip Technology Inc. - * Author: Tudor Ambarus + * Author: Tudor Ambarus */ #include @@ -411,6 +411,6 @@ static void __exit atmel_ecc_exit(void) module_init(atmel_ecc_init); module_exit(atmel_ecc_exit); -MODULE_AUTHOR("Tudor Ambarus "); +MODULE_AUTHOR("Tudor Ambarus"); MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/crypto/atmel-i2c.c b/drivers/crypto/atmel-i2c.c index 81ce09bedda8..55bff1e13142 100644 --- a/drivers/crypto/atmel-i2c.c +++ b/drivers/crypto/atmel-i2c.c @@ -3,7 +3,7 @@ * Microchip / Atmel ECC (I2C) driver. * * Copyright (c) 2017, Microchip Technology Inc. - * Author: Tudor Ambarus + * Author: Tudor Ambarus */ #include @@ -390,6 +390,6 @@ static void __exit atmel_i2c_exit(void) module_init(atmel_i2c_init); module_exit(atmel_i2c_exit); -MODULE_AUTHOR("Tudor Ambarus "); +MODULE_AUTHOR("Tudor Ambarus"); MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/crypto/atmel-i2c.h b/drivers/crypto/atmel-i2c.h index 48929efe2a5b..35f7857a7f7c 100644 --- a/drivers/crypto/atmel-i2c.h +++ b/drivers/crypto/atmel-i2c.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2017, Microchip Technology Inc. - * Author: Tudor Ambarus + * Author: Tudor Ambarus */ #ifndef __ATMEL_I2C_H__ From 5304930dbae82d259bcf7e5611db7c81e7a42eff Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 7 Jan 2023 10:15:35 -0500 Subject: [PATCH 157/233] NFSD: Use set_bit(RQ_DROPME) The premise that "Once an svc thread is scheduled and executing an RPC, no other processes will touch svc_rqst::rq_flags" is false. svc_xprt_enqueue() examines the RQ_BUSY flag in scheduled nfsd threads when determining which thread to wake up next. Fixes: 9315564747cb ("NFSD: Use only RQ_DROPME to signal the need to drop a reply") Signed-off-by: Chuck Lever --- fs/nfsd/nfsproc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index a5570cf75f3f..9744443c3965 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -211,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - __set_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -246,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - __set_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } From b7bfaa761d760e72a969d116517eaa12e404c262 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 8 Jan 2023 11:49:43 -0600 Subject: [PATCH 158/233] Linux 6.2-rc3 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index dfba294ae790..460716314fb3 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* From 37c1785609833e626d344047a84e272b7879b2c3 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Thu, 5 Jan 2023 17:01:41 +0800 Subject: [PATCH 159/233] x86/xen: Remove the unused function p2m_index() The function p2m_index is defined in the p2m.c file, but not called elsewhere, so remove this unused function. arch/x86/xen/p2m.c:137:24: warning: unused function 'p2m_index'. Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=3557 Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20230105090141.36248-1-jiapeng.chong@linux.alibaba.com Signed-off-by: Juergen Gross --- arch/x86/xen/p2m.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58db86f7b384..9bdc3b656b2c 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -134,11 +134,6 @@ static inline unsigned p2m_mid_index(unsigned long pfn) return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE; } -static inline unsigned p2m_index(unsigned long pfn) -{ - return pfn % P2M_PER_PAGE; -} - static void p2m_top_mfn_init(unsigned long *top) { unsigned i; From c0dccad87cf68fc6012aec7567e354353097ec1a Mon Sep 17 00:00:00 2001 From: Roger Pau Monne Date: Wed, 30 Nov 2022 17:36:02 +0100 Subject: [PATCH 160/233] hvc/xen: lock console list traversal MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The currently lockless access to the xen console list in vtermno_to_xencons() is incorrect, as additions and removals from the list can happen anytime, and as such the traversal of the list to get the private console data for a given termno needs to happen with the lock held. Note users that modify the list already do so with the lock taken. Adjust current lock takers to use the _irq{save,restore} helpers, since the context in which vtermno_to_xencons() is called can have interrupts disabled. Use the _irq{save,restore} set of helpers to switch the current callers to disable interrupts in the locked region. I haven't checked if existing users could instead use the _irq variant, as I think it's safer to use _irq{save,restore} upfront. While there switch from using list_for_each_entry_safe to list_for_each_entry: the current entry cursor won't be removed as part of the code in the loop body, so using the _safe variant is pointless. Fixes: 02e19f9c7cac ('hvc_xen: implement multiconsole support') Signed-off-by: Roger Pau Monné Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/20221130163611.14686-1-roger.pau@citrix.com Signed-off-by: Juergen Gross --- drivers/tty/hvc/hvc_xen.c | 46 ++++++++++++++++++++++++--------------- 1 file changed, 29 insertions(+), 17 deletions(-) diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index c879f922c716..5bddb2f5e931 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -52,17 +52,22 @@ static DEFINE_SPINLOCK(xencons_lock); static struct xencons_info *vtermno_to_xencons(int vtermno) { - struct xencons_info *entry, *n, *ret = NULL; + struct xencons_info *entry, *ret = NULL; + unsigned long flags; - if (list_empty(&xenconsoles)) - return NULL; + spin_lock_irqsave(&xencons_lock, flags); + if (list_empty(&xenconsoles)) { + spin_unlock_irqrestore(&xencons_lock, flags); + return NULL; + } - list_for_each_entry_safe(entry, n, &xenconsoles, list) { + list_for_each_entry(entry, &xenconsoles, list) { if (entry->vtermno == vtermno) { ret = entry; break; } } + spin_unlock_irqrestore(&xencons_lock, flags); return ret; } @@ -223,7 +228,7 @@ static int xen_hvm_console_init(void) { int r; uint64_t v = 0; - unsigned long gfn; + unsigned long gfn, flags; struct xencons_info *info; if (!xen_hvm_domain()) @@ -258,9 +263,9 @@ static int xen_hvm_console_init(void) goto err; info->vtermno = HVC_COOKIE; - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_add_tail(&info->list, &xenconsoles); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; err: @@ -283,6 +288,7 @@ static int xencons_info_pv_init(struct xencons_info *info, int vtermno) static int xen_pv_console_init(void) { struct xencons_info *info; + unsigned long flags; if (!xen_pv_domain()) return -ENODEV; @@ -299,9 +305,9 @@ static int xen_pv_console_init(void) /* already configured */ return 0; } - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); xencons_info_pv_init(info, HVC_COOKIE); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; } @@ -309,6 +315,7 @@ static int xen_pv_console_init(void) static int xen_initial_domain_console_init(void) { struct xencons_info *info; + unsigned long flags; if (!xen_initial_domain()) return -ENODEV; @@ -323,9 +330,9 @@ static int xen_initial_domain_console_init(void) info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false); info->vtermno = HVC_COOKIE; - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_add_tail(&info->list, &xenconsoles); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; } @@ -380,10 +387,12 @@ static void xencons_free(struct xencons_info *info) static int xen_console_remove(struct xencons_info *info) { + unsigned long flags; + xencons_disconnect_backend(info); - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_del(&info->list); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); if (info->xbdev != NULL) xencons_free(info); else { @@ -464,6 +473,7 @@ static int xencons_probe(struct xenbus_device *dev, { int ret, devid; struct xencons_info *info; + unsigned long flags; devid = dev->nodename[strlen(dev->nodename) - 1] - '0'; if (devid == 0) @@ -482,9 +492,9 @@ static int xencons_probe(struct xenbus_device *dev, ret = xencons_connect_backend(dev, info); if (ret < 0) goto error; - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_add_tail(&info->list, &xenconsoles); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; @@ -584,10 +594,12 @@ static int __init xen_hvc_init(void) info->hvc = hvc_alloc(HVC_COOKIE, info->irq, ops, 256); if (IS_ERR(info->hvc)) { + unsigned long flags; + r = PTR_ERR(info->hvc); - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_del(&info->list); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); if (info->irq) unbind_from_irqhandler(info->irq, NULL); kfree(info); From f57034cedeb6e00256313a2a6ee67f974d709b0b Mon Sep 17 00:00:00 2001 From: Oleksii Moisieiev Date: Tue, 20 Dec 2022 14:50:13 +0000 Subject: [PATCH 161/233] xen/pvcalls: free active map buffer on pvcalls_front_free_map Data buffer for active map is allocated in alloc_active_ring and freed in free_active_ring function, which is used only for the error cleanup. pvcalls_front_release is calling pvcalls_front_free_map which ends foreign access for this buffer, but doesn't free allocated pages. Call free_active_ring to clean all allocated resources. Signed-off-by: Oleksii Moisieiev Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/6a762ee32dd655cbb09a4aa0e2307e8919761311.1671531297.git.oleksii_moisieiev@epam.com Signed-off-by: Juergen Gross --- drivers/xen/pvcalls-front.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 5328f4d35f25..d5d589bda243 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -225,6 +225,8 @@ again: return IRQ_HANDLED; } +static void free_active_ring(struct sock_mapping *map); + static void pvcalls_front_free_map(struct pvcalls_bedata *bedata, struct sock_mapping *map) { @@ -240,7 +242,7 @@ static void pvcalls_front_free_map(struct pvcalls_bedata *bedata, for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++) gnttab_end_foreign_access(map->active.ring->ref[i], NULL); gnttab_end_foreign_access(map->active.ref, NULL); - free_page((unsigned long)map->active.ring); + free_active_ring(map); kfree(map); } From a5a36720c3f650f859f5e9535dd62d06f13f4f3b Mon Sep 17 00:00:00 2001 From: "Ivan T. Ivanov" Date: Fri, 6 Jan 2023 15:19:05 +0200 Subject: [PATCH 162/233] brcmfmac: Prefer DT board type over DMI board type The introduction of support for Apple board types inadvertently changed the precedence order, causing hybrid SMBIOS+DT platforms to look up the firmware using the DMI information instead of the device tree compatible to generate the board type. Revert back to the old behavior, as affected platforms use firmwares named after the DT compatible. Fixes: 7682de8b3351 ("wifi: brcmfmac: of: Fetch Apple properties") [1] https://bugzilla.opensuse.org/show_bug.cgi?id=1206697#c13 Cc: stable@vger.kernel.org Signed-off-by: Ivan T. Ivanov Reviewed-by: Hector Martin Reviewed-by: Arend van Spriel Tested-by: Peter Robinson Signed-off-by: David S. Miller --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c index a83699de01ec..fdd0c9abc1a1 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c @@ -79,7 +79,8 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type, /* Apple ARM64 platforms have their own idea of board type, passed in * via the device tree. They also have an antenna SKU parameter */ - if (!of_property_read_string(np, "brcm,board-type", &prop)) + err = of_property_read_string(np, "brcm,board-type", &prop); + if (!err) settings->board_type = prop; if (!of_property_read_string(np, "apple,antenna-sku", &prop)) @@ -87,7 +88,7 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type, /* Set board-type to the first string of the machine compatible prop */ root = of_find_node_by_path("/"); - if (root && !settings->board_type) { + if (root && err) { char *board_type; const char *tmp; From 60ea6f00c57dae5e7ba2c52ed407cb24fdb11ebe Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 6 Jan 2023 07:25:01 -0600 Subject: [PATCH 163/233] net: ipa: correct IPA v4.7 IMEM offset Commit b310de784bacd ("net: ipa: add IPA v4.7 support") was merged despite an unresolved comment made by Konrad Dybcio. Konrad observed that the IMEM region specified for IPA v4.7 did not match that used downstream for the SM7225 SoC. In "lagoon.dtsi" present in a Sony Xperia source tree, a ipa_smmu_ap node was defined with a "qcom,additional-mapping" property that defined the IPA IMEM area starting at offset 0x146a8000 (not 0x146a9000 that was committed). The IPA v4.7 target system used for testing uses the SM7225 SoC, so we'll adhere what the downstream code specifies is the address of the IMEM region used for IPA. Link: https://lore.kernel.org/linux-arm-msm/20221208211529.757669-1-elder@linaro.org Fixes: b310de784bac ("net: ipa: add IPA v4.7 support") Tested-by: Luca Weiss Signed-off-by: Alex Elder Reviewed-by: Konrad Dybcio Signed-off-by: David S. Miller --- drivers/net/ipa/data/ipa_data-v4.7.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c index 7552c400961e..b83390c48615 100644 --- a/drivers/net/ipa/data/ipa_data-v4.7.c +++ b/drivers/net/ipa/data/ipa_data-v4.7.c @@ -357,7 +357,7 @@ static const struct ipa_mem ipa_mem_local_data[] = { static const struct ipa_mem_data ipa_mem_data = { .local_count = ARRAY_SIZE(ipa_mem_local_data), .local = ipa_mem_local_data, - .imem_addr = 0x146a9000, + .imem_addr = 0x146a8000, .imem_size = 0x00002000, .smem_id = 497, .smem_size = 0x00009000, From 2ab6478d1266b522a0a6ce3697914d63529f9e7a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 5 Jan 2023 15:22:29 -0800 Subject: [PATCH 164/233] mlxsw: spectrum_router: Replace 0-length array with flexible array Zero-length arrays are deprecated[1]. Replace struct mlxsw_sp_nexthop_group_info's "nexthops" 0-length array with a flexible array. Detected with GCC 13, using -fstrict-flex-arrays=3: drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c: In function 'mlxsw_sp_nexthop_group_hash_obj': drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3278:38: warning: array subscript i is outside array bounds of 'struct mlxsw_sp_nexthop[0]' [-Warray-bounds=] 3278 | val ^= jhash(&nh->ifindex, sizeof(nh->ifindex), seed); | ^~~~~~~~~~~~ drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:2954:33: note: while referencing 'nexthops' 2954 | struct mlxsw_sp_nexthop nexthops[0]; | ^~~~~~~~ [1] https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays Cc: Ido Schimmel Cc: Petr Machata Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: "Gustavo A. R. Silva" Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Ido Schimmel Reviewed-by: Gustavo A. R. Silva Tested-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index c22c3ac4e2a1..09e32778b012 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2951,7 +2951,7 @@ struct mlxsw_sp_nexthop_group_info { gateway:1, /* routes using the group use a gateway */ is_resilient:1; struct list_head list; /* member in nh_res_grp_list */ - struct mlxsw_sp_nexthop nexthops[0]; + struct mlxsw_sp_nexthop nexthops[]; #define nh_rif nexthops[0].rif }; From 9dab880d675b9d0dd56c6428e4e8352a3339371d Mon Sep 17 00:00:00 2001 From: Minsuk Kang Date: Fri, 6 Jan 2023 17:23:44 +0900 Subject: [PATCH 165/233] nfc: pn533: Wait for out_urb's completion in pn533_usb_send_frame() Fix a use-after-free that occurs in hcd when in_urb sent from pn533_usb_send_frame() is completed earlier than out_urb. Its callback frees the skb data in pn533_send_async_complete() that is used as a transfer buffer of out_urb. Wait before sending in_urb until the callback of out_urb is called. To modify the callback of out_urb alone, separate the complete function of out_urb and ack_urb. Found by a modified version of syzkaller. BUG: KASAN: use-after-free in dummy_timer Call Trace: memcpy (mm/kasan/shadow.c:65) dummy_perform_transfer (drivers/usb/gadget/udc/dummy_hcd.c:1352) transfer (drivers/usb/gadget/udc/dummy_hcd.c:1453) dummy_timer (drivers/usb/gadget/udc/dummy_hcd.c:1972) arch_static_branch (arch/x86/include/asm/jump_label.h:27) static_key_false (include/linux/jump_label.h:207) timer_expire_exit (include/trace/events/timer.h:127) call_timer_fn (kernel/time/timer.c:1475) expire_timers (kernel/time/timer.c:1519) __run_timers (kernel/time/timer.c:1790) run_timer_softirq (kernel/time/timer.c:1803) Fixes: c46ee38620a2 ("NFC: pn533: add NXP pn533 nfc device driver") Signed-off-by: Minsuk Kang Signed-off-by: David S. Miller --- drivers/nfc/pn533/usb.c | 44 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 41 insertions(+), 3 deletions(-) diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index 6f71ac72012e..ed9c5e2cf3ad 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -153,10 +153,17 @@ static int pn533_usb_send_ack(struct pn533 *dev, gfp_t flags) return usb_submit_urb(phy->ack_urb, flags); } +struct pn533_out_arg { + struct pn533_usb_phy *phy; + struct completion done; +}; + static int pn533_usb_send_frame(struct pn533 *dev, struct sk_buff *out) { struct pn533_usb_phy *phy = dev->phy; + struct pn533_out_arg arg; + void *cntx; int rc; if (phy->priv == NULL) @@ -168,10 +175,17 @@ static int pn533_usb_send_frame(struct pn533 *dev, print_hex_dump_debug("PN533 TX: ", DUMP_PREFIX_NONE, 16, 1, out->data, out->len, false); + init_completion(&arg.done); + cntx = phy->out_urb->context; + phy->out_urb->context = &arg; + rc = usb_submit_urb(phy->out_urb, GFP_KERNEL); if (rc) return rc; + wait_for_completion(&arg.done); + phy->out_urb->context = cntx; + if (dev->protocol_type == PN533_PROTO_REQ_RESP) { /* request for response for sent packet directly */ rc = pn533_submit_urb_for_response(phy, GFP_KERNEL); @@ -408,7 +422,31 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy) return arg.rc; } -static void pn533_send_complete(struct urb *urb) +static void pn533_out_complete(struct urb *urb) +{ + struct pn533_out_arg *arg = urb->context; + struct pn533_usb_phy *phy = arg->phy; + + switch (urb->status) { + case 0: + break; /* success */ + case -ECONNRESET: + case -ENOENT: + dev_dbg(&phy->udev->dev, + "The urb has been stopped (status %d)\n", + urb->status); + break; + case -ESHUTDOWN: + default: + nfc_err(&phy->udev->dev, + "Urb failure (status %d)\n", + urb->status); + } + + complete(&arg->done); +} + +static void pn533_ack_complete(struct urb *urb) { struct pn533_usb_phy *phy = urb->context; @@ -496,10 +534,10 @@ static int pn533_usb_probe(struct usb_interface *interface, usb_fill_bulk_urb(phy->out_urb, phy->udev, usb_sndbulkpipe(phy->udev, out_endpoint), - NULL, 0, pn533_send_complete, phy); + NULL, 0, pn533_out_complete, phy); usb_fill_bulk_urb(phy->ack_urb, phy->udev, usb_sndbulkpipe(phy->udev, out_endpoint), - NULL, 0, pn533_send_complete, phy); + NULL, 0, pn533_ack_complete, phy); switch (id->driver_info) { case PN533_DEVICE_STD: From 7871f54e3deed68a27111dda162c4fe9b9c65f8f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 6 Jan 2023 14:25:23 +0000 Subject: [PATCH 166/233] gro: take care of DODGY packets Jaroslav reported a recent throughput regression with virtio_net caused by blamed commit. It is unclear if DODGY GSO packets coming from user space can be accepted by GRO engine in the future with minimal changes, and if there is any expected gain from it. In the meantime, make sure to detect and flush DODGY packets. Fixes: 5eddb24901ee ("gro: add support of (hw)gro packets to gro stack") Signed-off-by: Eric Dumazet Reported-and-bisected-by: Jaroslav Pulchart Cc: Coco Li Cc: Paolo Abeni Signed-off-by: David S. Miller --- net/core/gro.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/core/gro.c b/net/core/gro.c index fd8c6a7e8d3e..506f83d715f8 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -505,8 +505,9 @@ found_ptype: NAPI_GRO_CB(skb)->count = 1; if (unlikely(skb_is_gso(skb))) { NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs; - /* Only support TCP at the moment. */ - if (!skb_is_gso_tcp(skb)) + /* Only support TCP and non DODGY users. */ + if (!skb_is_gso_tcp(skb) || + (skb_shinfo(skb)->gso_type & SKB_GSO_DODGY)) NAPI_GRO_CB(skb)->flush = 1; } From 76761babaa984fce8ecd87d87a68d920f24df438 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Fri, 6 Jan 2023 21:15:07 +0100 Subject: [PATCH 167/233] net: lan966x: Allow to add rules in TCAM even if not enabled The blamed commit implemented the vcap_operations to allow to add an entry in the TCAM. One of the callbacks is to validate the supported keysets. If the TCAM lookup was not enabled, then this will return failure so no entries could be added. This doesn't make much sense, as you can enable at a later point the TCAM. Therefore change it such to allow entries in TCAM even it is not enabled. Fixes: 4426b78c626d ("net: lan966x: Add port keyset config and callback interface") Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c index d8dc9fbb81e1..a54c0426a35f 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c @@ -95,10 +95,7 @@ lan966x_vcap_is2_get_port_keysets(struct net_device *dev, int lookup, bool found = false; u32 val; - /* Check if the port keyset selection is enabled */ val = lan_rd(lan966x, ANA_VCAP_S2_CFG(port->chip_port)); - if (!ANA_VCAP_S2_CFG_ENA_GET(val)) - return -ENOENT; /* Collect all keysets for the port in a list */ if (l3_proto == ETH_P_ALL) From 7d6ceeb1875cc08dc3d1e558e191434d94840cd5 Mon Sep 17 00:00:00 2001 From: Mirsad Goran Todorovac Date: Sat, 7 Jan 2023 04:40:20 +0100 Subject: [PATCH 168/233] af_unix: selftest: Fix the size of the parameter to connect() Adjust size parameter in connect() to match the type of the parameter, to fix "No such file or directory" error in selftests/net/af_unix/ test_oob_unix.c:127. The existing code happens to work provided that the autogenerated pathname is shorter than sizeof (struct sockaddr), which is why it hasn't been noticed earlier. Visible from the trace excerpt: bind(3, {sa_family=AF_UNIX, sun_path="unix_oob_453059"}, 110) = 0 clone(child_stack=NULL, flags=CLONE_CHILD_CLEARTID|CLONE_CHILD_SETTID|SIGCHLD, child_tidptr=0x7fa6a6577a10) = 453060 [pid ] connect(6, {sa_family=AF_UNIX, sun_path="unix_oob_45305"}, 16) = -1 ENOENT (No such file or directory) BUG: The filename is trimmed to sizeof (struct sockaddr). Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Shuah Khan Cc: Kuniyuki Iwashima Cc: Florian Westphal Reviewed-by: Florian Westphal Fixes: 314001f0bf92 ("af_unix: Add OOB support") Signed-off-by: Mirsad Goran Todorovac Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- tools/testing/selftests/net/af_unix/test_unix_oob.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c index b57e91e1c3f2..532459a15067 100644 --- a/tools/testing/selftests/net/af_unix/test_unix_oob.c +++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c @@ -124,7 +124,7 @@ void producer(struct sockaddr_un *consumer_addr) wait_for_signal(pipefd[0]); if (connect(cfd, (struct sockaddr *)consumer_addr, - sizeof(struct sockaddr)) != 0) { + sizeof(*consumer_addr)) != 0) { perror("Connect failed"); kill(0, SIGTERM); exit(1); From 87ca4f9efbd7cc649ff43b87970888f2812945b8 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 30 Dec 2022 23:11:19 -0500 Subject: [PATCH 169/233] sched/core: Fix use-after-free bug in dup_user_cpus_ptr() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 07ec77a1d4e8 ("sched: Allow task CPU affinity to be restricted on asymmetric systems"), the setting and clearing of user_cpus_ptr are done under pi_lock for arm64 architecture. However, dup_user_cpus_ptr() accesses user_cpus_ptr without any lock protection. Since sched_setaffinity() can be invoked from another process, the process being modified may be undergoing fork() at the same time. When racing with the clearing of user_cpus_ptr in __set_cpus_allowed_ptr_locked(), it can lead to user-after-free and possibly double-free in arm64 kernel. Commit 8f9ea86fdf99 ("sched: Always preserve the user requested cpumask") fixes this problem as user_cpus_ptr, once set, will never be cleared in a task's lifetime. However, this bug was re-introduced in commit 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()") which allows the clearing of user_cpus_ptr in do_set_cpus_allowed(). This time, it will affect all arches. Fix this bug by always clearing the user_cpus_ptr of the newly cloned/forked task before the copying process starts and check the user_cpus_ptr state of the source task under pi_lock. Note to stable, this patch won't be applicable to stable releases. Just copy the new dup_user_cpus_ptr() function over. Fixes: 07ec77a1d4e8 ("sched: Allow task CPU affinity to be restricted on asymmetric systems") Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()") Reported-by: David Wang 王标 Signed-off-by: Waiman Long Signed-off-by: Ingo Molnar Reviewed-by: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221231041120.440785-2-longman@redhat.com --- kernel/sched/core.c | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 965d813c28ad..f9f6e5413dcf 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2612,19 +2612,43 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { + cpumask_t *user_mask; unsigned long flags; - if (!src->user_cpus_ptr) + /* + * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's + * may differ by now due to racing. + */ + dst->user_cpus_ptr = NULL; + + /* + * This check is racy and losing the race is a valid situation. + * It is not worth the extra overhead of taking the pi_lock on + * every fork/clone. + */ + if (data_race(!src->user_cpus_ptr)) return 0; - dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node); - if (!dst->user_cpus_ptr) + user_mask = kmalloc_node(cpumask_size(), GFP_KERNEL, node); + if (!user_mask) return -ENOMEM; - /* Use pi_lock to protect content of user_cpus_ptr */ + /* + * Use pi_lock to protect content of user_cpus_ptr + * + * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent + * do_set_cpus_allowed(). + */ raw_spin_lock_irqsave(&src->pi_lock, flags); - cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr); + if (src->user_cpus_ptr) { + swap(dst->user_cpus_ptr, user_mask); + cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr); + } raw_spin_unlock_irqrestore(&src->pi_lock, flags); + + if (unlikely(user_mask)) + kfree(user_mask); + return 0; } From 9a5418bc48babb313d2a62df29ebe21ce8c06c59 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 30 Dec 2022 23:11:20 -0500 Subject: [PATCH 170/233] sched/core: Use kfree_rcu() in do_set_cpus_allowed() Commit 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()") may call kfree() if user_cpus_ptr was previously set. Unfortunately, some of the callers of do_set_cpus_allowed() may have pi_lock held when calling it. So the following splats may be printed especially when running with a PREEMPT_RT kernel: WARNING: possible circular locking dependency detected BUG: sleeping function called from invalid context To avoid these problems, kfree_rcu() is used instead. An internal cpumask_rcuhead union is created for the sole purpose of facilitating the use of kfree_rcu() to free the cpumask. Since user_cpus_ptr is not being used in non-SMP configs, the newly introduced alloc_user_cpus_ptr() helper will return NULL in this case and sched_setaffinity() is modified to handle this special case. Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()") Suggested-by: Peter Zijlstra Signed-off-by: Waiman Long Signed-off-by: Ingo Molnar Reviewed-by: Peter Zijlstra Link: https://lore.kernel.org/r/20221231041120.440785-3-longman@redhat.com --- kernel/sched/core.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f9f6e5413dcf..bb1ee6d7bdde 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2604,9 +2604,29 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) .user_mask = NULL, .flags = SCA_USER, /* clear the user requested mask */ }; + union cpumask_rcuhead { + cpumask_t cpumask; + struct rcu_head rcu; + }; __do_set_cpus_allowed(p, &ac); - kfree(ac.user_mask); + + /* + * Because this is called with p->pi_lock held, it is not possible + * to use kfree() here (when PREEMPT_RT=y), therefore punt to using + * kfree_rcu(). + */ + kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu); +} + +static cpumask_t *alloc_user_cpus_ptr(int node) +{ + /* + * See do_set_cpus_allowed() above for the rcu_head usage. + */ + int size = max_t(int, cpumask_size(), sizeof(struct rcu_head)); + + return kmalloc_node(size, GFP_KERNEL, node); } int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, @@ -2629,7 +2649,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, if (data_race(!src->user_cpus_ptr)) return 0; - user_mask = kmalloc_node(cpumask_size(), GFP_KERNEL, node); + user_mask = alloc_user_cpus_ptr(node); if (!user_mask) return -ENOMEM; @@ -3605,6 +3625,11 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) return false; } +static inline cpumask_t *alloc_user_cpus_ptr(int node) +{ + return NULL; +} + #endif /* !CONFIG_SMP */ static void @@ -8265,8 +8290,8 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) if (retval) goto out_put_task; - user_mask = kmalloc(cpumask_size(), GFP_KERNEL); - if (!user_mask) { + user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE); + if (IS_ENABLED(CONFIG_SMP) && !user_mask) { retval = -ENOMEM; goto out_put_task; } From 01f2ea5bcf89dbd7a6530dbce7f2fb4e327e7006 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 4 Jan 2023 12:13:46 -0800 Subject: [PATCH 171/233] perf/x86/cstate: Add Meteor Lake support Meteor Lake is Intel's successor to Raptor lake. From the perspective of Intel cstate residency counters, there is nothing changed compared with Raptor lake. Share adl_cstates with Raptor lake. Update the comments for Meteor Lake. Signed-off-by: Kan Liang Signed-off-by: Ingo Molnar Reviewed-by: Andi Kleen Link: https://lore.kernel.org/r/20230104201349.1451191-6-kan.liang@linux.intel.com --- arch/x86/events/intel/cstate.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index a2834bc93149..3019fb1926e3 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -41,6 +41,7 @@ * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL + * MTL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,50 +52,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR + * TGL,TNT,RKL,ADL,RPL,SPR,MTL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL,RPL + * ICL,TGL,RKL,ADL,RPL,MTL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, - * RPL,SPR + * RPL,SPR,MTL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR + * TGL,TNT,RKL,ADL,RPL,SPR,MTL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL,RPL + * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL,RPL + * TNT,RKL,ADL,RPL,MTL * Scope: Package (physical package) * */ @@ -686,6 +687,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); From 6887a4d3aede084bf08b70fbc9736c69fce05d7f Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 4 Jan 2023 12:13:47 -0800 Subject: [PATCH 172/233] perf/x86/msr: Add Meteor Lake support Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs are also supported. Signed-off-by: Kan Liang Signed-off-by: Ingo Molnar Reviewed-by: Andi Kleen Link: https://lore.kernel.org/r/20230104201349.1451191-7-kan.liang@linux.intel.com --- arch/x86/events/msr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index ecced3a52668..074150d28fa8 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -107,6 +107,8 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: case INTEL_FAM6_RAPTORLAKE_S: + case INTEL_FAM6_METEORLAKE: + case INTEL_FAM6_METEORLAKE_L: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; From 69ced4160969025821f2999ff92163ed26568f1c Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 6 Jan 2023 08:04:48 -0800 Subject: [PATCH 173/233] perf/x86/msr: Add Emerald Rapids The same as Sapphire Rapids, the SMI_COUNT MSR is also supported on Emerald Rapids. Add Emerald Rapids model. Signed-off-by: Kan Liang Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230106160449.3566477-3-kan.liang@linux.intel.com --- arch/x86/events/msr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 074150d28fa8..c65d8906cbcf 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -69,6 +69,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: From 5268a2842066c227e6ccd94bac562f1e1000244f Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 6 Jan 2023 08:04:49 -0800 Subject: [PATCH 174/233] perf/x86/intel/uncore: Add Emerald Rapids From the perspective of the uncore PMU, the new Emerald Rapids is the same as the Sapphire Rapids. The only difference is the event list, which will be supported in the perf tool later. Signed-off-by: Kan Liang Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230106160449.3566477-4-kan.liang@linux.intel.com --- arch/x86/events/intel/uncore.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 6f1ccc57a692..459b1aafd4d4 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1833,6 +1833,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, }; From f993d24a948d22710148dae2c48b8a87155f6cb9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 7 Jan 2023 01:10:23 +0900 Subject: [PATCH 175/233] s390: fix -Wundef warning for CONFIG_KERNEL_ZSTD Since commit 80b6093b55e3 ("kbuild: add -Wundef to KBUILD_CPPFLAGS for W=1 builds"), building with W=1 detects misuse of #(el)if. $ make W=1 ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- [snip] arch/s390/boot/decompressor.c:28:7: warning: "CONFIG_KERNEL_ZSTD" is not defined, evaluates to 0 [-Wundef] 28 | #elif CONFIG_KERNEL_ZSTD | ^~~~~~~~~~~~~~~~~~ This issue has been hidden because arch/s390/boot/Makefile overwrites KBUILD_CFLAGS, dropping -Wundef. CONFIG_KERNEL_ZSTD is a bool option. #elif defined() should be used. The line #ifdef CONFIG_KERNEL_BZIP2 is fine, but I changed it for consistency. Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20230106161024.2373602-1-masahiroy@kernel.org Signed-off-by: Heiko Carstens --- arch/s390/boot/decompressor.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c index e27c2140d620..8dcd7af2911a 100644 --- a/arch/s390/boot/decompressor.c +++ b/arch/s390/boot/decompressor.c @@ -23,9 +23,9 @@ #define memmove memmove #define memzero(s, n) memset((s), 0, (n)) -#ifdef CONFIG_KERNEL_BZIP2 +#if defined(CONFIG_KERNEL_BZIP2) #define BOOT_HEAP_SIZE 0x400000 -#elif CONFIG_KERNEL_ZSTD +#elif defined(CONFIG_KERNEL_ZSTD) #define BOOT_HEAP_SIZE 0x30000 #else #define BOOT_HEAP_SIZE 0x10000 From 6f9aba7f0d74e8dd085f9ac11fe8f3fdd7fde4ca Mon Sep 17 00:00:00 2001 From: Athira Rajeev Date: Thu, 5 Jan 2023 17:34:36 +0530 Subject: [PATCH 176/233] perf tests bpf prologue: Fix bpf-script-test-prologue test compile issue with clang MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While running 'perf test' for bpf, observed that "BPF prologue generation" test case fails to compile with clang. Logs below from powerpc: :33:2: error: use of undeclared identifier 'fmode_t' fmode_t f_mode = (fmode_t)_f_mode; ^ :37:6: error: use of undeclared identifier 'f_mode'; did you mean '_f_mode'? if (f_mode & FMODE_WRITE) ^~~~~~ _f_mode :30:60: note: '_f_mode' declared here int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode, ^ 2 errors generated. The test code tests/bpf-script-test-prologue.c uses fmode_t. And the error above is for "fmode_t" which is defined in include/linux/types.h as part of kernel build directory: "/lib/modules//build" that comes from kernel devel [ soft link to /usr/src/ ]. Clang picks this header file from "-working-directory" build option that specifies this build folder. But the commit 14e4b9f4289aed2c ("perf trace: Raw augmented syscalls fix libbpf 1.0+ compatibility") changed the include directory to use: "/usr/include". Post this change, types.h from /usr/include/ is getting picked upwhich doesn’t contain definition of "fmode_t" and hence fails to compile. Compilation command before this commit: /usr/bin/clang -D__KERNEL__ -D__NR_CPUS__=72 -DLINUX_VERSION_CODE=0x50e00 -xc -I/root/lib/perf/include/bpf -nostdinc -I./arch/powerpc/include -I./arch/powerpc/include/generated -I./include -I./arch/powerpc/include/uapi -I./arch/powerpc/include/generated/uapi -I./include/uapi -I./include/generated/uapi -include ./include/linux/compiler-version.h -include ./include/linux/kconfig.h -Wno-unused-value -Wno-pointer-sign -working-directory /lib/modules//build -c - -target bpf -g -O2 -o - Compilation command after this commit: /usr/bin/clang -D__KERNEL__ -D__NR_CPUS__=72 -DLINUX_VERSION_CODE=0x50e00 -xc -I/usr/include/ -nostdinc -I./arch/powerpc/include -I./arch/powerpc/include/generated -I./include -I./arch/powerpc/include/uapi -I./arch/powerpc/include/generated/uapi -I./include/uapi -I./include/generated/uapi -include ./include/linux/compiler-version.h -include ./include/linux/kconfig.h -Wno-unused-value -Wno-pointer-sign -working-directory /lib/modules//build -c - -target bpf -g -O2 -o - The difference is addition of -I/usr/include/ in the first line which is causing the error. Fix this by adding typedef for "fmode_t" in the testcase to solve the compile issue. Fixes: 14e4b9f4289aed2c ("perf trace: Raw augmented syscalls fix libbpf 1.0+ compatibility") Signed-off-by: Athira Jajeev Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Disha Goel Cc: Ian Rogers Cc: James Clark Cc: Jiri Olsa Cc: Kajol Jain Cc: linuxppc-dev@lists.ozlabs.org Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Nageswara R Sastry Cc: Namhyung Kim Link: https://lore.kernel.org/linux-perf-users/20230105120436.92051-1-atrajeev@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/bpf-script-test-prologue.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c index bd83d364cf30..91778b5c6125 100644 --- a/tools/perf/tests/bpf-script-test-prologue.c +++ b/tools/perf/tests/bpf-script-test-prologue.c @@ -20,6 +20,8 @@ # undef if #endif +typedef unsigned int __bitwise fmode_t; + #define FMODE_READ 0x1 #define FMODE_WRITE 0x2 From cad90e5381d840cf2296aaac9b3eff71a30b7c5b Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 20 Dec 2022 20:13:23 +1000 Subject: [PATCH 177/233] objtool: Tolerate STT_NOTYPE symbols at end of section Hand-written asm often contains non-function symbols in executable sections. _end symbols for finding the size of instruction blocks for runtime processing is one such usage. optprobe_template_end is one example that causes the warning: objtool: optprobe_template_end(): can't find starting instruction This is because the symbol happens to be at the end of the file (and therefore end of a section in the object file). So ignore end-of-section STT_NOTYPE symbols instead of bailing out because an instruction can't be found. While we're here, add a more descriptive warning for STT_FUNC symbols found at the end of a section. [ This also solves a PowerPC regression reported by Sathvika Vasireddy. ] Reported-by: Naveen N. Rao Reported-by: Sathvika Vasireddy Signed-off-by: Nicholas Piggin Signed-off-by: Ingo Molnar Acked-by: Sathvika Vasireddy Link: https://lore.kernel.org/r/20221220101323.3119939-1-npiggin@gmail.com --- tools/objtool/check.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4350be739f4f..4b7c8b33069e 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -427,6 +427,15 @@ static int decode_instructions(struct objtool_file *file) if (func->type != STT_NOTYPE && func->type != STT_FUNC) continue; + if (func->offset == sec->sh.sh_size) { + /* Heuristic: likely an "end" symbol */ + if (func->type == STT_NOTYPE) + continue; + WARN("%s(): STT_FUNC at end of section", + func->name); + return -1; + } + if (func->return_thunk || func->alias != func) continue; From feaf75658783a919410f8c2039dbc24b6a29603d Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Mon, 9 Jan 2023 08:54:37 +0100 Subject: [PATCH 178/233] nolibc: fix fd_set type The kernel uses unsigned long for the fd_set bitmap, but nolibc use u32. This works fine on little endian machines, but fails on big endian. Convert to unsigned long to fix this. Signed-off-by: Sven Schnelle Signed-off-by: Willy Tarreau Signed-off-by: Paul E. McKenney --- tools/include/nolibc/types.h | 53 ++++++++++++++++++++---------------- 1 file changed, 30 insertions(+), 23 deletions(-) diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h index 959997034e55..300e0ff1cd58 100644 --- a/tools/include/nolibc/types.h +++ b/tools/include/nolibc/types.h @@ -89,39 +89,46 @@ #define EXIT_SUCCESS 0 #define EXIT_FAILURE 1 +#define FD_SETIDXMASK (8 * sizeof(unsigned long)) +#define FD_SETBITMASK (8 * sizeof(unsigned long)-1) + /* for select() */ typedef struct { - uint32_t fd32[(FD_SETSIZE + 31) / 32]; + unsigned long fds[(FD_SETSIZE + FD_SETBITMASK) / FD_SETIDXMASK]; } fd_set; -#define FD_CLR(fd, set) do { \ - fd_set *__set = (set); \ - int __fd = (fd); \ - if (__fd >= 0) \ - __set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \ +#define FD_CLR(fd, set) do { \ + fd_set *__set = (set); \ + int __fd = (fd); \ + if (__fd >= 0) \ + __set->fds[__fd / FD_SETIDXMASK] &= \ + ~(1U << (__fd & FX_SETBITMASK)); \ } while (0) -#define FD_SET(fd, set) do { \ - fd_set *__set = (set); \ - int __fd = (fd); \ - if (__fd >= 0) \ - __set->fd32[__fd / 32] |= 1U << (__fd & 31); \ +#define FD_SET(fd, set) do { \ + fd_set *__set = (set); \ + int __fd = (fd); \ + if (__fd >= 0) \ + __set->fds[__fd / FD_SETIDXMASK] |= \ + 1 << (__fd & FD_SETBITMASK); \ } while (0) -#define FD_ISSET(fd, set) ({ \ - fd_set *__set = (set); \ - int __fd = (fd); \ - int __r = 0; \ - if (__fd >= 0) \ - __r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \ - __r; \ +#define FD_ISSET(fd, set) ({ \ + fd_set *__set = (set); \ + int __fd = (fd); \ + int __r = 0; \ + if (__fd >= 0) \ + __r = !!(__set->fds[__fd / FD_SETIDXMASK] & \ +1U << (__fd & FD_SET_BITMASK)); \ + __r; \ }) -#define FD_ZERO(set) do { \ - fd_set *__set = (set); \ - int __idx; \ - for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \ - __set->fd32[__idx] = 0; \ +#define FD_ZERO(set) do { \ + fd_set *__set = (set); \ + int __idx; \ + int __size = (FD_SETSIZE+FD_SETBITMASK) / FD_SETIDXMASK;\ + for (__idx = 0; __idx < __size; __idx++) \ + __set->fds[__idx] = 0; \ } while (0) /* for poll() */ From 16f5cea74179b5795af7ce359971f5128d10f80e Mon Sep 17 00:00:00 2001 From: Warner Losh Date: Mon, 9 Jan 2023 08:54:38 +0100 Subject: [PATCH 179/233] tools/nolibc: Fix S_ISxxx macros The mode field has the type encoded as an value in a field, not as a bit mask. Mask the mode with S_IFMT instead of each type to test. Otherwise, false positives are possible: eg S_ISDIR will return true for block devices because S_IFDIR = 0040000 and S_IFBLK = 0060000 since mode is masked with S_IFDIR instead of S_IFMT. These macros now match the similar definitions in tools/include/uapi/linux/stat.h. Signed-off-by: Warner Losh Signed-off-by: Willy Tarreau Signed-off-by: Paul E. McKenney --- tools/include/nolibc/types.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h index 300e0ff1cd58..f1d64fca7cf0 100644 --- a/tools/include/nolibc/types.h +++ b/tools/include/nolibc/types.h @@ -26,13 +26,13 @@ #define S_IFSOCK 0140000 #define S_IFMT 0170000 -#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR) -#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR) -#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK) -#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG) -#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO) -#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK) -#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK) +#define S_ISDIR(mode) (((mode) & S_IFMT) == S_IFDIR) +#define S_ISCHR(mode) (((mode) & S_IFMT) == S_IFCHR) +#define S_ISBLK(mode) (((mode) & S_IFMT) == S_IFBLK) +#define S_ISREG(mode) (((mode) & S_IFMT) == S_IFREG) +#define S_ISFIFO(mode) (((mode) & S_IFMT) == S_IFIFO) +#define S_ISLNK(mode) (((mode) & S_IFMT) == S_IFLNK) +#define S_ISSOCK(mode) (((mode) & S_IFMT) == S_IFSOCK) /* dirent types */ #define DT_UNKNOWN 0x0 From 184177c3d6e023da934761e198c281344d7dd65b Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 9 Jan 2023 08:54:39 +0100 Subject: [PATCH 180/233] tools/nolibc: restore mips branch ordering in the _start block Depending on the compiler used and the optimization options, the sbrk() test was crashing, both on real hardware (mips-24kc) and in qemu. One such example is kernel.org toolchain in version 11.3 optimizing at -Os. Inspecting the sys_brk() call shows the following code: 0040047c : 40047c: 24020fcd li v0,4045 400480: 27bdffe0 addiu sp,sp,-32 400484: 0000000c syscall 400488: 27bd0020 addiu sp,sp,32 40048c: 10e00001 beqz a3,400494 400490: 00021023 negu v0,v0 400494: 03e00008 jr ra It is obviously wrong, the "negu" instruction is placed in beqz's delayed slot, and worse, there's no nop nor instruction after the return, so the next function's first instruction (addiu sip,sip,-32) will also be executed as part of the delayed slot that follows the return. This is caused by the ".set noreorder" directive in the _start block, that applies to the whole program. The compiler emits code without the delayed slots and relies on the compiler to swap instructions when this option is not set. Removing the option would require to change the startup code in a way that wouldn't make it look like the resulting code, which would not be easy to debug. Instead let's just save the default ordering before changing it, and restore it at the end of the _start block. Now the code is correct: 0040047c : 40047c: 24020fcd li v0,4045 400480: 27bdffe0 addiu sp,sp,-32 400484: 0000000c syscall 400488: 10e00002 beqz a3,400494 40048c: 27bd0020 addiu sp,sp,32 400490: 00021023 negu v0,v0 400494: 03e00008 jr ra 400498: 00000000 nop Fixes: 66b6f755ad45 ("rcutorture: Import a copy of nolibc") #5.0 Signed-off-by: Willy Tarreau Signed-off-by: Paul E. McKenney --- tools/include/nolibc/arch-mips.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h index 5fc5b8029bff..7380093ba9e7 100644 --- a/tools/include/nolibc/arch-mips.h +++ b/tools/include/nolibc/arch-mips.h @@ -192,6 +192,7 @@ struct sys_stat_struct { __asm__ (".section .text\n" ".weak __start\n" ".set nomips16\n" + ".set push\n" ".set noreorder\n" ".option pic0\n" ".ent __start\n" @@ -210,6 +211,7 @@ __asm__ (".section .text\n" "li $v0, 4001\n" // NR_exit == 4001 "syscall\n" ".end __start\n" + ".set pop\n" ""); #endif // _NOLIBC_ARCH_MIPS_H From 55abdd1f5e1e07418bf4a46c233a92f83cb5ae97 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 9 Jan 2023 08:54:40 +0100 Subject: [PATCH 181/233] tools/nolibc: fix missing includes causing build issues at -O0 After the nolibc includes were split to facilitate portability from standard libcs, programs that include only what they need may miss some symbols which are needed by libgcc. This is the case for raise() which is needed by the divide by zero code in some architectures for example. Regardless, being able to include only the apparently needed files is convenient. Instead of trying to move all exported definitions to a single file, since this can change over time, this patch takes another approach consisting in including the nolibc header at the end of all standard include files. This way their types and functions are already known at the moment of inclusion, and including any single one of them is sufficient to bring all the required ones. Signed-off-by: Willy Tarreau Signed-off-by: Paul E. McKenney --- tools/include/nolibc/ctype.h | 3 +++ tools/include/nolibc/errno.h | 3 +++ tools/include/nolibc/signal.h | 3 +++ tools/include/nolibc/stdio.h | 3 +++ tools/include/nolibc/stdlib.h | 3 +++ tools/include/nolibc/string.h | 3 +++ tools/include/nolibc/sys.h | 2 ++ tools/include/nolibc/time.h | 3 +++ tools/include/nolibc/types.h | 3 +++ tools/include/nolibc/unistd.h | 3 +++ 10 files changed, 29 insertions(+) diff --git a/tools/include/nolibc/ctype.h b/tools/include/nolibc/ctype.h index e3000b2992d7..6f90706d0644 100644 --- a/tools/include/nolibc/ctype.h +++ b/tools/include/nolibc/ctype.h @@ -96,4 +96,7 @@ int ispunct(int c) return isgraph(c) && !isalnum(c); } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_CTYPE_H */ diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h index 06893d6dfb7a..9dc4919c769b 100644 --- a/tools/include/nolibc/errno.h +++ b/tools/include/nolibc/errno.h @@ -24,4 +24,7 @@ static int errno; */ #define MAX_ERRNO 4095 +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_ERRNO_H */ diff --git a/tools/include/nolibc/signal.h b/tools/include/nolibc/signal.h index ef47e71e2be3..137552216e46 100644 --- a/tools/include/nolibc/signal.h +++ b/tools/include/nolibc/signal.h @@ -19,4 +19,7 @@ int raise(int signal) return sys_kill(sys_getpid(), signal); } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_SIGNAL_H */ diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index a3cebc4bc3ac..96ac8afc5aee 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -303,4 +303,7 @@ void perror(const char *msg) fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno); } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_STDIO_H */ diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index 92378c4b9660..a24000d1e822 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -419,4 +419,7 @@ char *u64toa(uint64_t in) return itoa_buffer; } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_STDLIB_H */ diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index ad97c0d522b8..0932db3817d2 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -285,4 +285,7 @@ char *strrchr(const char *s, int c) return (char *)ret; } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_STRING_H */ diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index ce3ee03aa679..78473d34e27c 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -1243,5 +1243,7 @@ ssize_t write(int fd, const void *buf, size_t count) return ret; } +/* make sure to include all global symbols */ +#include "nolibc.h" #endif /* _NOLIBC_SYS_H */ diff --git a/tools/include/nolibc/time.h b/tools/include/nolibc/time.h index d18b7661fdd7..84655361b9ad 100644 --- a/tools/include/nolibc/time.h +++ b/tools/include/nolibc/time.h @@ -25,4 +25,7 @@ time_t time(time_t *tptr) return tv.tv_sec; } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_TIME_H */ diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h index f1d64fca7cf0..fbbc0e68c001 100644 --- a/tools/include/nolibc/types.h +++ b/tools/include/nolibc/types.h @@ -209,4 +209,7 @@ struct stat { }) #endif +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_TYPES_H */ diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h index 1c25e20ee360..1cfcd52106a4 100644 --- a/tools/include/nolibc/unistd.h +++ b/tools/include/nolibc/unistd.h @@ -51,4 +51,7 @@ int tcsetpgrp(int fd, pid_t pid) return ioctl(fd, TIOCSPGRP, &pid); } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_UNISTD_H */ From 1bfbe1f3e96720daf185f03d101f072d69753f88 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 9 Jan 2023 08:54:41 +0100 Subject: [PATCH 182/233] tools/nolibc: prevent gcc from making memset() loop over itself When building on ARM in thumb mode with gcc-11.3 at -O2 or -O3, nolibc-test segfaults during the select() tests. It turns out that at this level, gcc recognizes an opportunity for using memset() to zero the fd_set, but it miscompiles it because it also recognizes a memset pattern as well, and decides to call memset() from the memset() code: 000122bc : 122bc: b510 push {r4, lr} 122be: 0004 movs r4, r0 122c0: 2a00 cmp r2, #0 122c2: d003 beq.n 122cc 122c4: 23ff movs r3, #255 ; 0xff 122c6: 4019 ands r1, r3 122c8: f7ff fff8 bl 122bc 122cc: 0020 movs r0, r4 122ce: bd10 pop {r4, pc} Simply placing an empty asm() statement inside the loop suffices to avoid this. Signed-off-by: Willy Tarreau Signed-off-by: Paul E. McKenney --- tools/include/nolibc/string.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index 0932db3817d2..fffdaf6ff467 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -88,8 +88,11 @@ void *memset(void *dst, int b, size_t len) { char *p = dst; - while (len--) + while (len--) { + /* prevent gcc from recognizing memset() here */ + asm volatile(""); *(p++) = b; + } return dst; } From 00b18da4089330196906b9fe075c581c17eb726c Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 9 Jan 2023 08:54:42 +0100 Subject: [PATCH 183/233] tools/nolibc: fix the O_* fcntl/open macro definitions for riscv When RISCV port was imported in 5.2, the O_* macros were taken with their octal value and written as-is in hex, resulting in the getdents64() to fail in nolibc-test. Fixes: 582e84f7b779 ("tool headers nolibc: add RISCV support") #5.2 Signed-off-by: Willy Tarreau Signed-off-by: Paul E. McKenney --- tools/include/nolibc/arch-riscv.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h index ba04771cb3a3..a3bdd9803f8c 100644 --- a/tools/include/nolibc/arch-riscv.h +++ b/tools/include/nolibc/arch-riscv.h @@ -11,13 +11,13 @@ #define O_RDONLY 0 #define O_WRONLY 1 #define O_RDWR 2 -#define O_CREAT 0x100 -#define O_EXCL 0x200 -#define O_NOCTTY 0x400 -#define O_TRUNC 0x1000 -#define O_APPEND 0x2000 -#define O_NONBLOCK 0x4000 -#define O_DIRECTORY 0x200000 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x10000 struct sys_stat_struct { unsigned long st_dev; /* Device. */ From f58985620f55580a07d40062c4115d8c9cf6ae27 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Wed, 7 Dec 2022 08:55:02 +0000 Subject: [PATCH 184/233] ice: Fix potential memory leak in ice_gnss_tty_write() The ice_gnss_tty_write() return directly if the write_buf alloc failed, leaking the cmd_buf. Fix by free cmd_buf if write_buf alloc failed. Fixes: d6b98c8d242a ("ice: add write functionality for GNSS TTY") Signed-off-by: Yuan Can Reviewed-by: Leon Romanovsky Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_gnss.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index b5a7f246d230..a1915551c69a 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -363,6 +363,7 @@ ice_gnss_tty_write(struct tty_struct *tty, const unsigned char *buf, int count) /* Send the data out to a hardware port */ write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL); if (!write_buf) { + kfree(cmd_buf); err = -ENOMEM; goto exit; } From 40543b3d9d2c13227ecd3aa90a713c201d1d7f09 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Thu, 8 Dec 2022 21:35:52 +0800 Subject: [PATCH 185/233] ice: Add check for kzalloc Add the check for the return value of kzalloc in order to avoid NULL pointer dereference. Moreover, use the goto-label to share the clean code. Fixes: d6b98c8d242a ("ice: add write functionality for GNSS TTY") Signed-off-by: Jiasheng Jiang Reviewed-by: Jiri Pirko Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_gnss.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index a1915551c69a..43e199b5b513 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -461,6 +461,9 @@ static struct tty_driver *ice_gnss_create_tty_driver(struct ice_pf *pf) for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) { pf->gnss_tty_port[i] = kzalloc(sizeof(*pf->gnss_tty_port[i]), GFP_KERNEL); + if (!pf->gnss_tty_port[i]) + goto err_out; + pf->gnss_serial[i] = NULL; tty_port_init(pf->gnss_tty_port[i]); @@ -470,21 +473,23 @@ static struct tty_driver *ice_gnss_create_tty_driver(struct ice_pf *pf) err = tty_register_driver(tty_driver); if (err) { dev_err(dev, "Failed to register TTY driver err=%d\n", err); - - for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) { - tty_port_destroy(pf->gnss_tty_port[i]); - kfree(pf->gnss_tty_port[i]); - } - kfree(ttydrv_name); - tty_driver_kref_put(pf->ice_gnss_tty_driver); - - return NULL; + goto err_out; } for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) dev_info(dev, "%s%d registered\n", ttydrv_name, i); return tty_driver; + +err_out: + while (i--) { + tty_port_destroy(pf->gnss_tty_port[i]); + kfree(pf->gnss_tty_port[i]); + } + kfree(ttydrv_name); + tty_driver_kref_put(pf->ice_gnss_tty_driver); + + return NULL; } /** From 5a41237ad1d4b62008f93163af1d9b1da90729d8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 9 Jan 2023 17:04:49 -0600 Subject: [PATCH 186/233] gcc: disable -Warray-bounds for gcc-11 too We had already disabled this warning for gcc-12 due to bugs in the value range analysis, but it turns out we end up having some similar problems with gcc-11.3 too, so let's disable it there too. Older gcc versions end up being increasingly less relevant, and hopefully clang and newer version of gcc (ie gcc-13) end up working reliably enough that we still get the build coverage even when we disable this for some versions. Link: https://lore.kernel.org/all/20221227002941.GA2691687@roeck-us.net/ Link: https://lore.kernel.org/all/D8BDBF66-E44C-45D4-9758-BAAA4F0C1998@kernel.org/ Cc: Kees Cook Cc: Vlastimil Babka Cc: Guenter Roeck Signed-off-by: Linus Torvalds --- init/Kconfig | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/init/Kconfig b/init/Kconfig index 7e5c3ddc341d..0958846b005e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -894,13 +894,17 @@ config CC_IMPLICIT_FALLTHROUGH default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5) default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough) -# Currently, disable gcc-12 array-bounds globally. +# Currently, disable gcc-11,12 array-bounds globally. # We may want to target only particular configurations some day. +config GCC11_NO_ARRAY_BOUNDS + def_bool y + config GCC12_NO_ARRAY_BOUNDS def_bool y config CC_NO_ARRAY_BOUNDS bool + default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_ARRAY_BOUNDS default y if CC_IS_GCC && GCC_VERSION >= 120000 && GCC_VERSION < 130000 && GCC12_NO_ARRAY_BOUNDS # From 9e17f99220d111ea031b44153fdfe364b0024ff2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 7 Jan 2023 19:10:04 +0200 Subject: [PATCH 187/233] net/sched: act_mpls: Fix warning during failed attribute validation The 'TCA_MPLS_LABEL' attribute is of 'NLA_U32' type, but has a validation type of 'NLA_VALIDATE_FUNCTION'. This is an invalid combination according to the comment above 'struct nla_policy': " Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: NLA_BINARY Validation function called for the attribute. All other Unused - but note that it's a union " This can trigger the warning [1] in nla_get_range_unsigned() when validation of the attribute fails. Despite being of 'NLA_U32' type, the associated 'min'/'max' fields in the policy are negative as they are aliased by the 'validate' field. Fix by changing the attribute type to 'NLA_BINARY' which is consistent with the above comment and all other users of NLA_POLICY_VALIDATE_FN(). As a result, move the length validation to the validation function. No regressions in MPLS tests: # ./tdc.py -f tc-tests/actions/mpls.json [...] # echo $? 0 [1] WARNING: CPU: 0 PID: 17743 at lib/nlattr.c:118 nla_get_range_unsigned+0x1d8/0x1e0 lib/nlattr.c:117 Modules linked in: CPU: 0 PID: 17743 Comm: syz-executor.0 Not tainted 6.1.0-rc8 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:nla_get_range_unsigned+0x1d8/0x1e0 lib/nlattr.c:117 [...] Call Trace: __netlink_policy_dump_write_attr+0x23d/0x990 net/netlink/policy.c:310 netlink_policy_dump_write_attr+0x22/0x30 net/netlink/policy.c:411 netlink_ack_tlv_fill net/netlink/af_netlink.c:2454 [inline] netlink_ack+0x546/0x760 net/netlink/af_netlink.c:2506 netlink_rcv_skb+0x1b7/0x240 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:6109 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2482 ___sys_sendmsg net/socket.c:2536 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2565 __do_sys_sendmsg net/socket.c:2574 [inline] __se_sys_sendmsg net/socket.c:2572 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2572 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Link: https://lore.kernel.org/netdev/CAO4mrfdmjvRUNbDyP0R03_DrD_eFCLCguz6OxZ2TYRSv0K9gxA@mail.gmail.com/ Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC") Reported-by: Wei Chen Tested-by: Wei Chen Signed-off-by: Ido Schimmel Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/20230107171004.608436-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/sched/act_mpls.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index ff47ce4d3968..6b26bdb999d7 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -134,6 +134,11 @@ static int valid_label(const struct nlattr *attr, { const u32 *label = nla_data(attr); + if (nla_len(attr) != sizeof(*label)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length"); + return -EINVAL; + } + if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) { NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range"); return -EINVAL; @@ -145,7 +150,8 @@ static int valid_label(const struct nlattr *attr, static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = { [TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)), [TCA_MPLS_PROTO] = { .type = NLA_U16 }, - [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_U32, valid_label), + [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, + valid_label), [TCA_MPLS_TC] = NLA_POLICY_RANGE(NLA_U8, 0, 7), [TCA_MPLS_TTL] = NLA_POLICY_MIN(NLA_U8, 1), [TCA_MPLS_BOS] = NLA_POLICY_RANGE(NLA_U8, 0, 1), From 2ea26b4de6f42b74a5f1701de41efa6bc9f12666 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 8 Jan 2023 20:37:53 +0100 Subject: [PATCH 188/233] Revert "r8169: disable detection of chip version 36" This reverts commit 42666b2c452ce87894786aae05e3fad3cfc6cb59. This chip version seems to be very rare, but it exits in consumer devices, see linked report. Link: https://stackoverflow.com/questions/75049473/cant-setup-a-wired-network-in-archlinux-fresh-install Fixes: 42666b2c452c ("r8169: disable detection of chip version 36") Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/42e9674c-d5d0-a65a-f578-e5c74f244739@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/realtek/r8169_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 24592d972523..dadd61bccfe7 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1996,10 +1996,7 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) /* 8168F family. */ { 0x7c8, 0x488, RTL_GIGA_MAC_VER_38 }, - /* It seems this chip version never made it to - * the wild. Let's disable detection. - * { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 }, - */ + { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 }, { 0x7cf, 0x480, RTL_GIGA_MAC_VER_35 }, /* 8168E family. */ From 17b3222e943701c408d6e03357967829aaea0550 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Sun, 13 Nov 2022 00:04:17 +0200 Subject: [PATCH 189/233] net/mlx5: DR, Fix 'stack frame size exceeds limit' error in dr_rule If the kernel configuration asks the compiler to check frame limit of 1K, dr_rule_create_rule_nic exceed this limit: "stack frame size (1184) exceeds limit (1024)" Fixing this issue by checking configured frame limit and using the optimization STE array only for cases with the usual 2K (or larger) stack size warning. Fixes: b9b81e1e9382 ("net/mlx5: DR, For short chains of STEs, avoid allocating ste_arr dynamically") Reported-by: kernel test robot Signed-off-by: Yevgeny Kliteynik --- .../ethernet/mellanox/mlx5/core/steering/dr_rule.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index 74cbe53ee9db..b851141e03de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -3,7 +3,12 @@ #include "dr_types.h" +#if defined(CONFIG_FRAME_WARN) && (CONFIG_FRAME_WARN < 2048) +/* don't try to optimize STE allocation if the stack is too constaraining */ +#define DR_RULE_MAX_STES_OPTIMIZED 0 +#else #define DR_RULE_MAX_STES_OPTIMIZED 5 +#endif #define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES) static int dr_rule_append_to_miss_list(struct mlx5dr_domain *dmn, @@ -1218,10 +1223,7 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, mlx5dr_domain_nic_unlock(nic_dmn); - if (unlikely(!hw_ste_arr_is_opt)) - kfree(hw_ste_arr); - - return 0; + goto out; free_rule: dr_rule_clean_rule_members(rule, nic_rule); @@ -1238,6 +1240,7 @@ remove_from_nic_tbl: free_hw_ste: mlx5dr_domain_nic_unlock(nic_dmn); +out: if (unlikely(!hw_ste_arr_is_opt)) kfree(hw_ste_arr); From e0bf81bf0d3d4747c146e0bf44774d3d881d7137 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Tue, 16 Aug 2022 23:19:11 +0300 Subject: [PATCH 190/233] net/mlx5: check attr pointer validity before dereferencing it Fix attr pointer validity checks after it was already dereferenced. Fixes: cb0d54cbf948 ("net/mlx5e: Fix wrong source vport matching on tunnel rule") Signed-off-by: Ariel Levkovich Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index e455b215c708..75b77dd2392b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -143,7 +143,7 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, if (mlx5_esw_indir_table_decap_vport(attr)) vport = mlx5_esw_indir_table_decap_vport(attr); - if (attr && !attr->chain && esw_attr->int_port) + if (!attr->chain && esw_attr && esw_attr->int_port) metadata = mlx5e_tc_int_port_get_metadata_for_match(esw_attr->int_port); else From 5e72f3f1c558019082cfeedeed73748f35d780c6 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Tue, 30 Aug 2022 00:32:30 +0300 Subject: [PATCH 191/233] net/mlx5e: TC, Keep mod hdr actions after mod hdr alloc When offloading TC NIC rule which has mod_hdr action, the mod_hdr actions list is freed upon mod_hdr allocation. In the new format of handling multi table actions and CT in particular, the mod_hdr actions list is still relevant when setting the pre and post rules and therefore, freeing the list may cause adding rules which don't set the FTE_ID. Therefore, the mod_hdr actions list needs to be kept for the pre/post flows as well and should be left for these handler to be freed. Fixes: 8300f225268b ("net/mlx5e: Create new flow attr for multi table actions") Signed-off-by: Ariel Levkovich Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9af2aa2922f5..dbadaf166487 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1301,7 +1301,6 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); - mlx5e_mod_hdr_dealloc(&parse_attr->mod_hdr_acts); if (err) return err; } @@ -1359,8 +1358,10 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, } mutex_unlock(&tc->t_lock); - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts); mlx5e_detach_mod_hdr(priv, flow); + } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) mlx5_fc_destroy(priv->mdev, attr->counter); From da2e552b469a0cd130ff70a88ccc4139da428a65 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Mon, 28 Nov 2022 19:05:47 +0200 Subject: [PATCH 192/233] net/mlx5: Fix command stats access after free Command may fail while driver is reloading and can't accept FW commands till command interface is reinitialized. Such command failure is being logged to command stats. This results in NULL pointer access as command stats structure is being freed and reallocated during mlx5 devlink reload (see kernel log below). Fix it by making command stats statically allocated on driver probe. Kernel log: [ 2394.808802] BUG: unable to handle kernel paging request at 000000000002a9c0 [ 2394.810610] PGD 0 P4D 0 [ 2394.811811] Oops: 0002 [#1] SMP NOPTI ... [ 2394.815482] RIP: 0010:native_queued_spin_lock_slowpath+0x183/0x1d0 ... [ 2394.829505] Call Trace: [ 2394.830667] _raw_spin_lock_irq+0x23/0x26 [ 2394.831858] cmd_status_err+0x55/0x110 [mlx5_core] [ 2394.833020] mlx5_access_reg+0xe7/0x150 [mlx5_core] [ 2394.834175] mlx5_query_port_ptys+0x78/0xa0 [mlx5_core] [ 2394.835337] mlx5e_ethtool_get_link_ksettings+0x74/0x590 [mlx5_core] [ 2394.836454] ? kmem_cache_alloc_trace+0x140/0x1c0 [ 2394.837562] __rh_call_get_link_ksettings+0x33/0x100 [ 2394.838663] ? __rtnl_unlock+0x25/0x50 [ 2394.839755] __ethtool_get_link_ksettings+0x72/0x150 [ 2394.840862] duplex_show+0x6e/0xc0 [ 2394.841963] dev_attr_show+0x1c/0x40 [ 2394.843048] sysfs_kf_seq_show+0x9b/0x100 [ 2394.844123] seq_read+0x153/0x410 [ 2394.845187] vfs_read+0x91/0x140 [ 2394.846226] ksys_read+0x4f/0xb0 [ 2394.847234] do_syscall_64+0x5b/0x1a0 [ 2394.848228] entry_SYSCALL_64_after_hwframe+0x65/0xca Fixes: 34f46ae0d4b3 ("net/mlx5: Add command failures data to debugfs") Signed-off-by: Moshe Shemesh Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 13 ++----------- include/linux/mlx5/driver.h | 2 +- 2 files changed, 3 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index d3ca745d107d..c837103a9ee3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -2176,15 +2176,9 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) return -EINVAL; } - cmd->stats = kvcalloc(MLX5_CMD_OP_MAX, sizeof(*cmd->stats), GFP_KERNEL); - if (!cmd->stats) - return -ENOMEM; - cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0); - if (!cmd->pool) { - err = -ENOMEM; - goto dma_pool_err; - } + if (!cmd->pool) + return -ENOMEM; err = alloc_cmd_page(dev, cmd); if (err) @@ -2268,8 +2262,6 @@ err_free_page: err_free_pool: dma_pool_destroy(cmd->pool); -dma_pool_err: - kvfree(cmd->stats); return err; } @@ -2282,7 +2274,6 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev) destroy_msg_cache(dev); free_cmd_page(dev, cmd); dma_pool_destroy(cmd->pool); - kvfree(cmd->stats); } void mlx5_cmd_set_state(struct mlx5_core_dev *dev, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d476255c9a3f..76ef2e4fde38 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -315,7 +315,7 @@ struct mlx5_cmd { struct mlx5_cmd_debug dbg; struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; - struct mlx5_cmd_stats *stats; + struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX]; }; struct mlx5_cmd_mailbox { From ab4b01bfdaa69492fb36484026b0a0f0af02d75a Mon Sep 17 00:00:00 2001 From: Roy Novich Date: Wed, 4 Jan 2023 11:16:21 +0200 Subject: [PATCH 193/233] net/mlx5e: Verify dev is present for fix features ndo The native NIC port net device instance is being used as Uplink representor. While changing profiles private resources are not available, fix features ndo does not check if the netdev is present. Add driver protection to verify private resources are ready. Fixes: 7a9fb35e8c3a ("net/mlx5e: Do not reload ethernet ports when changing eswitch mode") Signed-off-by: Roy Novich Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cff5f2e29e1e..abcc614b6191 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4084,6 +4084,9 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, struct mlx5e_vlan_table *vlan; struct mlx5e_params *params; + if (!netif_device_present(netdev)) + return features; + vlan = mlx5e_fs_get_vlan(priv->fs); mutex_lock(&priv->state_lock); params = &priv->channels.params; From 806a8df7126a8c05d60411eeb81057c2a8bbe7a7 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 15 Dec 2022 13:02:38 +0200 Subject: [PATCH 194/233] net/mlx5e: IPoIB, Block queue count configuration when sub interfaces are present PKEY sub interfaces share the receive queues with the parent interface. While setting the sub interface queue count is not supported, it is currently possible to change the number of queues of the parent interface. Thus we can end up with inconsistent queue sizes between the parent and its sub interfaces. This change disallows setting the queue count on the parent interface when sub interfaces are present. This is achieved by introducing an explicit reference to the parent netdev in the mlx5i_priv of the child interface. An additional counter is also required on the parent side to detect when sub interfaces are attached and for proper cleanup. The rtnl lock is taken during the ethtool op and the sub interface ndo_init/uninit ops. There is no race here around counting the sub interfaces, reading the sub interfaces and setting the number of channels. The ASSERT_RTNL was added to document that. Fixes: be98737a4faa ("net/mlx5e: Use dynamic per-channel allocations in stats") Signed-off-by: Dragos Tatulea Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/ipoib/ethtool.c | 16 +++++++- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 38 +++++++++++++++++++ .../ethernet/mellanox/mlx5/core/ipoib/ipoib.h | 6 +++ .../mellanox/mlx5/core/ipoib/ipoib_vlan.c | 9 ++--- 4 files changed, 62 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index c247cca154e9..eff92dc0927c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -90,9 +90,21 @@ static void mlx5i_get_ringparam(struct net_device *dev, static int mlx5i_set_channels(struct net_device *dev, struct ethtool_channels *ch) { - struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct mlx5i_priv *ipriv = netdev_priv(dev); + struct mlx5e_priv *epriv = mlx5i_epriv(dev); - return mlx5e_ethtool_set_channels(priv, ch); + /* rtnl lock protects from race between this ethtool op and sub + * interface ndo_init/uninit. + */ + ASSERT_RTNL(); + if (ipriv->num_sub_interfaces > 0) { + mlx5_core_warn(epriv->mdev, + "can't change number of channels for interfaces with sub interfaces (%u)\n", + ipriv->num_sub_interfaces); + return -EINVAL; + } + + return mlx5e_ethtool_set_channels(epriv, ch); } static void mlx5i_get_channels(struct net_device *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 2c73c8445e63..911cf4d23964 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -160,6 +160,44 @@ void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_dropped = sstats->tx_queue_dropped; } +struct net_device *mlx5i_parent_get(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv, *parent_ipriv; + struct net_device *parent_dev; + int parent_ifindex; + + ipriv = priv->ppriv; + + parent_ifindex = netdev->netdev_ops->ndo_get_iflink(netdev); + parent_dev = dev_get_by_index(dev_net(netdev), parent_ifindex); + if (!parent_dev) + return NULL; + + parent_ipriv = netdev_priv(parent_dev); + + ASSERT_RTNL(); + parent_ipriv->num_sub_interfaces++; + + ipriv->parent_dev = parent_dev; + + return parent_dev; +} + +void mlx5i_parent_put(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv, *parent_ipriv; + + ipriv = priv->ppriv; + parent_ipriv = netdev_priv(ipriv->parent_dev); + + ASSERT_RTNL(); + parent_ipriv->num_sub_interfaces--; + + dev_put(ipriv->parent_dev); +} + int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index 99d46fda9f82..f3f2af972020 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -54,9 +54,11 @@ struct mlx5i_priv { struct rdma_netdev rn; /* keep this first */ u32 qpn; bool sub_interface; + u32 num_sub_interfaces; u32 qkey; u16 pkey_index; struct mlx5i_pkey_qpn_ht *qpn_htbl; + struct net_device *parent_dev; char *mlx5e_priv[]; }; @@ -117,5 +119,9 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more); void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); +/* Reference management for child to parent interfaces. */ +struct net_device *mlx5i_parent_get(struct net_device *netdev); +void mlx5i_parent_put(struct net_device *netdev); + #endif /* CONFIG_MLX5_CORE_IPOIB */ #endif /* __MLX5E_IPOB_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 4d9c9e49645c..28795fb6bccc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -158,21 +158,19 @@ static int mlx5i_pkey_dev_init(struct net_device *dev) struct mlx5e_priv *priv = mlx5i_epriv(dev); struct mlx5i_priv *ipriv, *parent_ipriv; struct net_device *parent_dev; - int parent_ifindex; ipriv = priv->ppriv; - /* Get QPN to netdevice hash table from parent */ - parent_ifindex = dev->netdev_ops->ndo_get_iflink(dev); - parent_dev = dev_get_by_index(dev_net(dev), parent_ifindex); + /* Link to parent */ + parent_dev = mlx5i_parent_get(dev); if (!parent_dev) { mlx5_core_warn(priv->mdev, "failed to get parent device\n"); return -EINVAL; } + /* Get QPN to netdevice hash table from parent */ parent_ipriv = netdev_priv(parent_dev); ipriv->qpn_htbl = parent_ipriv->qpn_htbl; - dev_put(parent_dev); return mlx5i_dev_init(dev); } @@ -184,6 +182,7 @@ static int mlx5i_pkey_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void mlx5i_pkey_dev_cleanup(struct net_device *netdev) { + mlx5i_parent_put(netdev); return mlx5i_dev_cleanup(netdev); } From 31c70bfe58ef09fe36327ddcced9143a16e9e83d Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Fri, 25 Nov 2022 17:51:19 +0200 Subject: [PATCH 195/233] net/mlx5e: IPoIB, Block PKEY interfaces with less rx queues than parent A user is able to configure an arbitrary number of rx queues when creating an interface via netlink. This doesn't work for child PKEY interfaces because the child interface uses the parent receive channels. Although the child shares the parent's receive channels, the number of rx queues is important for the channel_stats array: the parent's rx channel index is used to access the child's channel_stats. So the array has to be at least as large as the parent's rx queue size for the counting to work correctly and to prevent out of bound accesses. This patch checks for the mentioned scenario and returns an error when trying to create the interface. The error is propagated to the user. Fixes: be98737a4faa ("net/mlx5e: Use dynamic per-channel allocations in stats") Signed-off-by: Dragos Tatulea Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 28795fb6bccc..03e681297937 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -168,6 +168,15 @@ static int mlx5i_pkey_dev_init(struct net_device *dev) return -EINVAL; } + if (dev->num_rx_queues < parent_dev->real_num_rx_queues) { + mlx5_core_warn(priv->mdev, + "failed to create child device with rx queues [%d] less than parent's [%d]\n", + dev->num_rx_queues, + parent_dev->real_num_rx_queues); + mlx5i_parent_put(dev); + return -EINVAL; + } + /* Get QPN to netdevice hash table from parent */ parent_ipriv = netdev_priv(parent_dev); ipriv->qpn_htbl = parent_ipriv->qpn_htbl; From b5e23931c45a2f99f60a2f2b98a9e4d5a62a5b13 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Wed, 23 Nov 2022 16:59:13 +0200 Subject: [PATCH 196/233] net/mlx5e: IPoIB, Fix child PKEY interface stats on rx path The current code always does the accounting using the stats from the parent interface (linked in the rq). This doesn't work when there are child interfaces configured. Fix this behavior by always using the stats from the child interface priv. This will also work for parent only interfaces: the child (netdev) and parent netdev (rq->netdev) will point to the same thing. Fixes: be98737a4faa ("net/mlx5e: Use dynamic per-channel allocations in stats") Signed-off-by: Dragos Tatulea Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index c8820ab22169..3df455f6b168 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -2419,7 +2419,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, priv = mlx5i_epriv(netdev); tstamp = &priv->tstamp; - stats = rq->stats; + stats = &priv->channel_stats[rq->ix]->rq; flags_rqpn = be32_to_cpu(cqe->flags_rqpn); g = (flags_rqpn >> 28) & 3; From 2414c9b7a29d237c9c40abd62853dbc08b4ba7df Mon Sep 17 00:00:00 2001 From: Oz Shlomo Date: Wed, 7 Dec 2022 11:05:02 +0000 Subject: [PATCH 197/233] net/mlx5e: TC, ignore match level for post meter rules The post meter table only matches on reg_c5. As such, the inner/outer match levels are irrelevant for the match critieria. The cited patch only sets the outer criteria to none, thus setting the inner match level for encapsulated packets. This caused rules with police action on tunnel devices to not find an existing flow group for the match criteria, thus failing to offload the rule. Set both the inner and outer match levels to none for post_meter rules. Fixes: 0d8c38d44f33 ("net/mlx5e: TC, init post meter rules with branching attributes") Signed-off-by: Oz Shlomo Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c index 8d7d761482d2..50b60fd00946 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c @@ -127,6 +127,7 @@ mlx5e_post_meter_add_rule(struct mlx5e_priv *priv, attr->counter = act_counter; attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT; + attr->inner_match_level = MLX5_MATCH_NONE; attr->outer_match_level = MLX5_MATCH_NONE; attr->chain = 0; attr->prio = 0; From c09502d54dc109530ccb9a8910ab286d0745f119 Mon Sep 17 00:00:00 2001 From: Oz Shlomo Date: Thu, 8 Dec 2022 08:31:48 +0000 Subject: [PATCH 198/233] net/mlx5e: TC, Restore pkt rate policing support The offending commit removed the support for all packet rate metering. Restore the pkt rate metering support by removing the restriction. Fixes: 3603f26633e7 ("net/mlx5e: TC, allow meter jump control action") Signed-off-by: Oz Shlomo Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c index 512d43148922..c4378afdec09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c @@ -34,12 +34,6 @@ static int police_act_validate(const struct flow_action_entry *act, return -EOPNOTSUPP; } - if (act->police.rate_pkt_ps) { - NL_SET_ERR_MSG_MOD(extack, - "QoS offload not support packets per second"); - return -EOPNOTSUPP; - } - return 0; } From 3099d2e62f9061ed57798e68e285d35837be686f Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Sun, 8 Jan 2023 12:53:02 +0200 Subject: [PATCH 199/233] net/mlx5e: Fix memory leak on updating vport counters When updating statistics driver queries the vport's counters. On fail, add error path releasing the allocated buffer avoiding memory leak. Fixes: 64b68e369649 ("net/mlx5: Refactor and expand rep vport stat group") Signed-off-by: Aya Levin Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 75b9e1528fd2..7d90e5b72854 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -191,7 +191,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep) if (err) { netdev_warn(priv->netdev, "vport %d error %d reading stats\n", rep->vport, err); - return; + goto out; } #define MLX5_GET_CTR(p, x) \ @@ -241,6 +241,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep) rep_stats->tx_vport_rdma_multicast_bytes = MLX5_GET_CTR(out, received_ib_multicast.octets); +out: kvfree(out); } From fe91d57277eef8bb4aca05acfa337b4a51d0bba4 Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Mon, 5 Dec 2022 14:26:09 -0800 Subject: [PATCH 200/233] net/mlx5: Fix ptp max frequency adjustment range .max_adj of ptp_clock_info acts as an absolute value for the amount in ppb that can be set for a single call of .adjfine. This means that a single call to .getfine cannot be greater than .max_adj or less than -(.max_adj). Provides correct value for max frequency adjustment value supported by devices. Fixes: 3d8c38af1493 ("net/mlx5e: Add PTP Hardware Clock (PHC) support") Signed-off-by: Rahul Rameshbabu Reviewed-by: Gal Pressman Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 69cfe60c558a..69318b143268 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -681,7 +681,7 @@ static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, static const struct ptp_clock_info mlx5_ptp_clock_info = { .owner = THIS_MODULE, .name = "mlx5_ptp", - .max_adj = 100000000, + .max_adj = 50000000, .n_alarm = 0, .n_ext_ts = 0, .n_per_out = 0, From d515d63cae2cd186acf40deaa8ef33067bb7f637 Mon Sep 17 00:00:00 2001 From: Gavin Li Date: Tue, 27 Dec 2022 04:54:09 +0200 Subject: [PATCH 201/233] net/mlx5e: Don't support encap rules with gbp option Previously, encap rules with gbp option would be offloaded by mistake but driver does not support gbp option offload. To fix this issue, check if the encap rule has gbp option and don't offload the rule Fixes: d8f9dfae49ce ("net: sched: allow flower to match vxlan options") Signed-off-by: Gavin Li Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index fd07c4cbfd1d..1f62c702b625 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -88,6 +88,8 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[], struct udphdr *udp = (struct udphdr *)(buf); struct vxlanhdr *vxh; + if (tun_key->tun_flags & TUNNEL_VXLAN_OPT) + return -EOPNOTSUPP; vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr)); *ip_proto = IPPROTO_UDP; From cd4f186dc110a0f0b3484048b8ecd42ee006ca6d Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 15 Dec 2022 15:33:38 +0200 Subject: [PATCH 202/233] net/mlx5: E-switch, Coverity: overlapping copy When a capability is set via port function caps callbacks, a memcpy() is performed in which the source and the target are the same address, e.g.: the copy is redundant. Hence, Remove it. Discovered by Coverity. Fixes: 7db98396ef45 ("net/mlx5: E-Switch, Implement devlink port function cmds to control RoCE") Fixes: e5b9642a33be ("net/mlx5: E-Switch, Implement devlink port function cmds to control migratable") Signed-off-by: Shay Drory Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 75b77dd2392b..c981fa77f439 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -4143,8 +4143,6 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable, } hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); - memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability), - MLX5_UN_SZ_BYTES(hca_cap_union)); MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1); err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport, @@ -4236,8 +4234,6 @@ int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable, } hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); - memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability), - MLX5_UN_SZ_BYTES(hca_cap_union)); MLX5_SET(cmd_hca_cap, hca_caps, roce, enable); err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport_num, From f5e1ed04aa2ea665a796f0109091ca3f2b01024a Mon Sep 17 00:00:00 2001 From: Emeel Hakim Date: Wed, 14 Dec 2022 16:34:13 +0200 Subject: [PATCH 203/233] net/mlx5e: Fix macsec ssci attribute handling in offload path Currently when macsec offload is set with extended packet number (epn) enabled, the driver wrongly deduce the short secure channel identifier (ssci) from the salt instead of the stand alone ssci attribute as it should, consequently creating a mismatch between the kernel and driver's ssci values. Fix by using the ssci value from the relevant attribute. Fixes: 4411a6c0abd3 ("net/mlx5e: Support MACsec offload extended packet number (EPN)") Signed-off-by: Emeel Hakim Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_accel/macsec.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 9369a580743e..cf7b3bb54c86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -62,6 +62,7 @@ struct mlx5e_macsec_sa { u32 enc_key_id; u32 next_pn; sci_t sci; + ssci_t ssci; salt_t salt; struct rhash_head hash; @@ -499,10 +500,11 @@ mlx5e_macsec_get_macsec_device_context(const struct mlx5e_macsec *macsec, } static void update_macsec_epn(struct mlx5e_macsec_sa *sa, const struct macsec_key *key, - const pn_t *next_pn_halves) + const pn_t *next_pn_halves, ssci_t ssci) { struct mlx5e_macsec_epn_state *epn_state = &sa->epn_state; + sa->ssci = ssci; sa->salt = key->salt; epn_state->epn_enabled = 1; epn_state->epn_msb = next_pn_halves->upper; @@ -550,7 +552,8 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx) tx_sa->assoc_num = assoc_num; if (secy->xpn) - update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves); + update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves, + ctx_tx_sa->ssci); err = mlx5_create_encryption_key(mdev, ctx->sa.key, secy->key_len, MLX5_ACCEL_OBJ_MACSEC_KEY, @@ -945,7 +948,8 @@ static int mlx5e_macsec_add_rxsa(struct macsec_context *ctx) rx_sa->fs_id = rx_sc->sc_xarray_element->fs_id; if (ctx->secy->xpn) - update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves); + update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves, + ctx_rx_sa->ssci); err = mlx5_create_encryption_key(mdev, ctx->sa.key, ctx->secy->key_len, MLX5_ACCEL_OBJ_MACSEC_KEY, From 9828994ac492e8e7de47fe66097b7e665328f348 Mon Sep 17 00:00:00 2001 From: Emeel Hakim Date: Sun, 11 Dec 2022 13:22:23 +0200 Subject: [PATCH 204/233] net/mlx5e: Fix macsec possible null dereference when updating MAC security entity (SecY) Upon updating MAC security entity (SecY) in hw offload path, the macsec security association (SA) initialization routine is called. In case of extended packet number (epn) is enabled the salt and ssci attributes are retrieved using the MACsec driver rx_sa context which is unavailable when updating a SecY property such as encoding-sa hence the null dereference. Fix by using the provided SA to set those attributes. Fixes: 4411a6c0abd3 ("net/mlx5e: Support MACsec offload extended packet number (EPN)") Signed-off-by: Emeel Hakim Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_accel/macsec.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index cf7b3bb54c86..7f6b940830b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -359,7 +359,6 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_macsec_obj_attrs obj_attrs; union mlx5e_macsec_rule *macsec_rule; - struct macsec_key *key; int err; obj_attrs.next_pn = sa->next_pn; @@ -369,13 +368,9 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, obj_attrs.aso_pdn = macsec->aso.pdn; obj_attrs.epn_state = sa->epn_state; - key = (is_tx) ? &ctx->sa.tx_sa->key : &ctx->sa.rx_sa->key; - if (sa->epn_state.epn_enabled) { - obj_attrs.ssci = (is_tx) ? cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci) : - cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci); - - memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt)); + obj_attrs.ssci = cpu_to_be32((__force u32)sa->ssci); + memcpy(&obj_attrs.salt, &sa->salt, sizeof(sa->salt)); } obj_attrs.replay_window = ctx->secy->replay_window; From e59370b2e96eb8e7e057a2a16e999ff385a3f2fb Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Sun, 8 Jan 2023 16:45:41 +0100 Subject: [PATCH 205/233] selftests/net: l2_tos_ttl_inherit.sh: Set IPv6 addresses with "nodad". The ping command can run before DAD completes. In that case, ping may fail and break the selftest. We don't need DAD here since we're working on isolated device pairs. Fixes: b690842d12fd ("selftests/net: test l2 tunnel TOS/TTL inheriting") Signed-off-by: Guillaume Nault Signed-off-by: Paolo Abeni --- tools/testing/selftests/net/l2_tos_ttl_inherit.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh index dca1e6f777a8..e2574b08eabc 100755 --- a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh +++ b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh @@ -137,8 +137,8 @@ setup() { if [ "$type" = "gre" ]; then type="ip6gretap" fi - ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0 - $ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1 + ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0 nodad + $ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1 nodad ip link add name tep0 type $type $local_addr1 \ remote fdd1:ced0:5d88:3fce::2 tos $test_tos ttl $test_ttl \ $vxlan $geneve @@ -170,8 +170,8 @@ setup() { ip addr add 198.19.0.1/24 brd + dev ${parent}0 $ns ip addr add 198.19.0.2/24 brd + dev ${parent}1 elif [ "$inner" = "6" ]; then - ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0 - $ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1 + ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0 nodad + $ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1 nodad fi } From c53cb00f7983a5474f2d36967f84908b85af9159 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Sun, 8 Jan 2023 16:45:46 +0100 Subject: [PATCH 206/233] selftests/net: l2_tos_ttl_inherit.sh: Run tests in their own netns. This selftest currently runs half in the current namespace and half in a netns of its own. Therefore, the test can fail if the current namespace is already configured with incompatible parameters (for example if it already has a veth0 interface). Adapt the script to put both ends of the veth pair in their own netns. Now veth0 is created in NS0 instead of the current namespace, while veth1 is set up in NS1 (instead of the 'testing' netns). The user visible netns names are randomised to minimise the risk of conflicts with already existing namespaces. The cleanup() function doesn't need to remove the virtual interface anymore: deleting NS0 and NS1 automatically removes the virtual interfaces they contained. We can remove $ns, which was only used to run ip commands in the 'testing' netns (let's use the builtin "-netns" option instead). However, we still need a similar functionality as ping and tcpdump now need to run in NS0. So we now have $RUN_NS0 for that. Fixes: b690842d12fd ("selftests/net: test l2 tunnel TOS/TTL inheriting") Reported-by: Mirsad Goran Todorovac Tested-by: Mirsad Goran Todorovac Signed-off-by: Guillaume Nault Signed-off-by: Paolo Abeni --- .../selftests/net/l2_tos_ttl_inherit.sh | 162 ++++++++++-------- 1 file changed, 93 insertions(+), 69 deletions(-) diff --git a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh index e2574b08eabc..cf56680d598f 100755 --- a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh +++ b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh @@ -25,6 +25,11 @@ expected_tos="0x00" expected_ttl="0" failed=false +readonly NS0=$(mktemp -u ns0-XXXXXXXX) +readonly NS1=$(mktemp -u ns1-XXXXXXXX) + +RUN_NS0="ip netns exec ${NS0}" + get_random_tos() { # Get a random hex tos value between 0x00 and 0xfc, a multiple of 4 echo "0x$(tr -dc '0-9a-f' < /dev/urandom | head -c 1)\ @@ -61,7 +66,6 @@ setup() { local vlan="$5" local test_tos="0x00" local test_ttl="0" - local ns="ip netns exec testing" # We don't want a test-tos of 0x00, # because this is the value that we get when no tos is set. @@ -94,14 +98,15 @@ setup() { printf "│%7s │%6s │%6s │%13s │%13s │%6s │" \ "$type" "$outer" "$inner" "$tos" "$ttl" "$vlan" - # Create 'testing' netns, veth pair and connect main ns with testing ns - ip netns add testing - ip link add type veth - ip link set veth1 netns testing - ip link set veth0 up - $ns ip link set veth1 up - ip addr flush dev veth0 - $ns ip addr flush dev veth1 + # Create netns NS0 and NS1 and connect them with a veth pair + ip netns add "${NS0}" + ip netns add "${NS1}" + ip link add name veth0 netns "${NS0}" type veth \ + peer name veth1 netns "${NS1}" + ip -netns "${NS0}" link set dev veth0 up + ip -netns "${NS1}" link set dev veth1 up + ip -netns "${NS0}" address flush dev veth0 + ip -netns "${NS1}" address flush dev veth1 local local_addr1="" local local_addr2="" @@ -127,51 +132,59 @@ setup() { if [ "$type" = "gre" ]; then type="gretap" fi - ip addr add 198.18.0.1/24 dev veth0 - $ns ip addr add 198.18.0.2/24 dev veth1 - ip link add name tep0 type $type $local_addr1 remote \ - 198.18.0.2 tos $test_tos ttl $test_ttl $vxlan $geneve - $ns ip link add name tep1 type $type $local_addr2 remote \ - 198.18.0.1 tos $test_tos ttl $test_ttl $vxlan $geneve + ip -netns "${NS0}" address add 198.18.0.1/24 dev veth0 + ip -netns "${NS1}" address add 198.18.0.2/24 dev veth1 + ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \ + remote 198.18.0.2 tos $test_tos ttl $test_ttl \ + $vxlan $geneve + ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \ + remote 198.18.0.1 tos $test_tos ttl $test_ttl \ + $vxlan $geneve elif [ "$outer" = "6" ]; then if [ "$type" = "gre" ]; then type="ip6gretap" fi - ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0 nodad - $ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1 nodad - ip link add name tep0 type $type $local_addr1 \ - remote fdd1:ced0:5d88:3fce::2 tos $test_tos ttl $test_ttl \ - $vxlan $geneve - $ns ip link add name tep1 type $type $local_addr2 \ - remote fdd1:ced0:5d88:3fce::1 tos $test_tos ttl $test_ttl \ - $vxlan $geneve + ip -netns "${NS0}" address add fdd1:ced0:5d88:3fce::1/64 \ + dev veth0 nodad + ip -netns "${NS1}" address add fdd1:ced0:5d88:3fce::2/64 \ + dev veth1 nodad + ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \ + remote fdd1:ced0:5d88:3fce::2 tos $test_tos \ + ttl $test_ttl $vxlan $geneve + ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \ + remote fdd1:ced0:5d88:3fce::1 tos $test_tos \ + ttl $test_ttl $vxlan $geneve fi # Bring L2-tunnel link up and create VLAN on top - ip link set tep0 up - $ns ip link set tep1 up - ip addr flush dev tep0 - $ns ip addr flush dev tep1 + ip -netns "${NS0}" link set tep0 up + ip -netns "${NS1}" link set tep1 up + ip -netns "${NS0}" address flush dev tep0 + ip -netns "${NS1}" address flush dev tep1 local parent if $vlan; then parent="vlan99-" - ip link add link tep0 name ${parent}0 type vlan id 99 - $ns ip link add link tep1 name ${parent}1 type vlan id 99 - ip link set ${parent}0 up - $ns ip link set ${parent}1 up - ip addr flush dev ${parent}0 - $ns ip addr flush dev ${parent}1 + ip -netns "${NS0}" link add link tep0 name ${parent}0 \ + type vlan id 99 + ip -netns "${NS1}" link add link tep1 name ${parent}1 \ + type vlan id 99 + ip -netns "${NS0}" link set dev ${parent}0 up + ip -netns "${NS1}" link set dev ${parent}1 up + ip -netns "${NS0}" address flush dev ${parent}0 + ip -netns "${NS1}" address flush dev ${parent}1 else parent="tep" fi # Assign inner IPv4/IPv6 addresses if [ "$inner" = "4" ] || [ "$inner" = "other" ]; then - ip addr add 198.19.0.1/24 brd + dev ${parent}0 - $ns ip addr add 198.19.0.2/24 brd + dev ${parent}1 + ip -netns "${NS0}" address add 198.19.0.1/24 brd + dev ${parent}0 + ip -netns "${NS1}" address add 198.19.0.2/24 brd + dev ${parent}1 elif [ "$inner" = "6" ]; then - ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0 nodad - $ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1 nodad + ip -netns "${NS0}" address add fdd4:96cf:4eae:443b::1/64 \ + dev ${parent}0 nodad + ip -netns "${NS1}" address add fdd4:96cf:4eae:443b::2/64 \ + dev ${parent}1 nodad fi } @@ -192,10 +205,10 @@ verify() { ping_dst="198.19.0.3" # Generates ARPs which are not IPv4/IPv6 fi if [ "$tos_ttl" = "inherit" ]; then - ping -i 0.1 $ping_dst -Q "$expected_tos" -t "$expected_ttl" \ - 2>/dev/null 1>&2 & ping_pid="$!" + ${RUN_NS0} ping -i 0.1 $ping_dst -Q "$expected_tos" \ + -t "$expected_ttl" 2>/dev/null 1>&2 & ping_pid="$!" else - ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!" + ${RUN_NS0} ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!" fi local tunnel_type_offset tunnel_type_proto req_proto_offset req_offset if [ "$type" = "gre" ]; then @@ -216,10 +229,12 @@ verify() { req_proto_offset="$((req_proto_offset + 4))" req_offset="$((req_offset + 4))" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip[$tunnel_type_offset] = $tunnel_type_proto and \ - ip[$req_proto_offset] = 0x01 and \ - ip[$req_offset] = 0x08 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip[$tunnel_type_offset] = $tunnel_type_proto and \ + ip[$req_proto_offset] = 0x01 and \ + ip[$req_offset] = 0x08 2>/dev/null \ + | head -n 1)" elif [ "$inner" = "6" ]; then req_proto_offset="44" req_offset="78" @@ -231,10 +246,12 @@ verify() { req_proto_offset="$((req_proto_offset + 4))" req_offset="$((req_offset + 4))" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip[$tunnel_type_offset] = $tunnel_type_proto and \ - ip[$req_proto_offset] = 0x3a and \ - ip[$req_offset] = 0x80 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip[$tunnel_type_offset] = $tunnel_type_proto and \ + ip[$req_proto_offset] = 0x3a and \ + ip[$req_offset] = 0x80 2>/dev/null \ + | head -n 1)" elif [ "$inner" = "other" ]; then req_proto_offset="36" req_offset="45" @@ -250,11 +267,13 @@ verify() { expected_tos="0x00" expected_ttl="64" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip[$tunnel_type_offset] = $tunnel_type_proto and \ - ip[$req_proto_offset] = 0x08 and \ - ip[$((req_proto_offset + 1))] = 0x06 and \ - ip[$req_offset] = 0x01 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip[$tunnel_type_offset] = $tunnel_type_proto and \ + ip[$req_proto_offset] = 0x08 and \ + ip[$((req_proto_offset + 1))] = 0x06 and \ + ip[$req_offset] = 0x01 2>/dev/null \ + | head -n 1)" fi elif [ "$outer" = "6" ]; then if [ "$type" = "gre" ]; then @@ -273,10 +292,12 @@ verify() { req_proto_offset="$((req_proto_offset + 4))" req_offset="$((req_offset + 4))" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip6[$tunnel_type_offset] = $tunnel_type_proto and \ - ip6[$req_proto_offset] = 0x01 and \ - ip6[$req_offset] = 0x08 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip6[$tunnel_type_offset] = $tunnel_type_proto and \ + ip6[$req_proto_offset] = 0x01 and \ + ip6[$req_offset] = 0x08 2>/dev/null \ + | head -n 1)" elif [ "$inner" = "6" ]; then local req_proto_offset="72" local req_offset="106" @@ -288,10 +309,12 @@ verify() { req_proto_offset="$((req_proto_offset + 4))" req_offset="$((req_offset + 4))" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip6[$tunnel_type_offset] = $tunnel_type_proto and \ - ip6[$req_proto_offset] = 0x3a and \ - ip6[$req_offset] = 0x80 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip6[$tunnel_type_offset] = $tunnel_type_proto and \ + ip6[$req_proto_offset] = 0x3a and \ + ip6[$req_offset] = 0x80 2>/dev/null \ + | head -n 1)" elif [ "$inner" = "other" ]; then local req_proto_offset="64" local req_offset="73" @@ -307,11 +330,13 @@ verify() { expected_tos="0x00" expected_ttl="64" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip6[$tunnel_type_offset] = $tunnel_type_proto and \ - ip6[$req_proto_offset] = 0x08 and \ - ip6[$((req_proto_offset + 1))] = 0x06 and \ - ip6[$req_offset] = 0x01 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip6[$tunnel_type_offset] = $tunnel_type_proto and \ + ip6[$req_proto_offset] = 0x08 and \ + ip6[$((req_proto_offset + 1))] = 0x06 and \ + ip6[$req_offset] = 0x01 2>/dev/null \ + | head -n 1)" fi fi kill -9 $ping_pid @@ -351,9 +376,8 @@ verify() { } cleanup() { - ip link del veth0 2>/dev/null - ip netns del testing 2>/dev/null - ip link del tep0 2>/dev/null + ip netns del "${NS0}" 2>/dev/null + ip netns del "${NS1}" 2>/dev/null } printf "┌────────┬───────┬───────┬──────────────┬" From d68ff8ad3351b8fc8d6f14b9a4f5cc8ba3e8bd13 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Sun, 8 Jan 2023 16:45:50 +0100 Subject: [PATCH 207/233] selftests/net: l2_tos_ttl_inherit.sh: Ensure environment cleanup on failure. Use 'set -e' and an exit handler to stop the script if a command fails and ensure the test environment is cleaned up in any case. Also, handle the case where the script is interrupted by SIGINT. The only command that's expected to fail is 'wait $ping_pid', since it's killed by the script. Handle this case with '|| true' to make it play well with 'set -e'. Finally, return the Kselftest SKIP code (4) when the script breaks because of an environment problem or a command line failure. The 0 and 1 return codes should now reliably indicate that all tests have been run (0: all tests run and passed, 1: all tests run but at least one failed, 4: test script didn't run completely). Fixes: b690842d12fd ("selftests/net: test l2 tunnel TOS/TTL inheriting") Reported-by: Mirsad Goran Todorovac Tested-by: Mirsad Goran Todorovac Signed-off-by: Guillaume Nault Signed-off-by: Paolo Abeni --- .../selftests/net/l2_tos_ttl_inherit.sh | 40 +++++++++++++++++-- 1 file changed, 36 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh index cf56680d598f..f11756e7df2f 100755 --- a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh +++ b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh @@ -12,13 +12,16 @@ # In addition this script also checks if forcing a specific field in the # outer header is working. +# Return 4 by default (Kselftest SKIP code) +ERR=4 + if [ "$(id -u)" != "0" ]; then echo "Please run as root." - exit 0 + exit $ERR fi if ! which tcpdump > /dev/null 2>&1; then echo "No tcpdump found. Required for this test." - exit 0 + exit $ERR fi expected_tos="0x00" @@ -340,7 +343,7 @@ verify() { fi fi kill -9 $ping_pid - wait $ping_pid 2>/dev/null + wait $ping_pid 2>/dev/null || true result="FAIL" if [ "$outer" = "4" ]; then captured_ttl="$(get_field "ttl" "$out")" @@ -380,6 +383,31 @@ cleanup() { ip netns del "${NS1}" 2>/dev/null } +exit_handler() { + # Don't exit immediately if one of the intermediate commands fails. + # We might be called at the end of the script, when the network + # namespaces have already been deleted. So cleanup() may fail, but we + # still need to run until 'exit $ERR' or the script won't return the + # correct error code. + set +e + + cleanup + + exit $ERR +} + +# Restore the default SIGINT handler (just in case) and exit. +# The exit handler will take care of cleaning everything up. +interrupted() { + trap - INT + + exit $ERR +} + +set -e +trap exit_handler EXIT +trap interrupted INT + printf "┌────────┬───────┬───────┬──────────────┬" printf "──────────────┬───────┬────────┐\n" for type in gre vxlan geneve; do @@ -409,6 +437,10 @@ done printf "└────────┴───────┴───────┴──────────────┴" printf "──────────────┴───────┴────────┘\n" +# All tests done. +# Set ERR appropriately: it will be returned by the exit handler. if $failed; then - exit 1 + ERR=1 +else + ERR=0 fi From 53da7aec32982f5ee775b69dce06d63992ce4af3 Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Mon, 9 Jan 2023 11:43:25 +0530 Subject: [PATCH 208/233] octeontx2-pf: Fix resource leakage in VF driver unbind resources allocated like mcam entries to support the Ntuple feature and hash tables for the tc feature are not getting freed in driver unbind. This patch fixes the issue. Fixes: 2da489432747 ("octeontx2-pf: devlink params support to set mcam entry count") Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Kovvuri Goutham Link: https://lore.kernel.org/r/20230109061325.21395-1-hkelam@marvell.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 86653bb8e403..7f8ffbf79cf7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -758,6 +758,8 @@ static void otx2vf_remove(struct pci_dev *pdev) if (vf->otx2_wq) destroy_workqueue(vf->otx2_wq); otx2_ptp_destroy(vf); + otx2_mcam_flow_del(vf); + otx2_shutdown_tc(vf); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); if (test_bit(CN10K_LMTST, &vf->hw.cap_flag)) From 526970be53d5dd60122141540142fb0eeb0b22d8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 10 Jan 2023 11:44:51 +0100 Subject: [PATCH 209/233] sh/mm: Fix pmd_t for real Because typing is hard... Fixes: 0862ff059c9e ("sh/mm: Make pmd_t similar to pte_t") Reported-by: Guenter Roeck Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Linus Torvalds --- arch/sh/include/asm/pgtable-3level.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index a889a3a938ba..d1ce73f3bd85 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -28,7 +28,7 @@ #define pmd_ERROR(e) \ printk("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) -typedef struct { +typedef union { struct { unsigned long pmd_low; unsigned long pmd_high; From c2337a40e04dde1692b5b0a46ecc59f89aaba8a1 Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Mon, 14 Nov 2022 11:40:08 +0100 Subject: [PATCH 210/233] s390/kexec: fix ipl report address for kdump This commit addresses the following erroneous situation with file-based kdump executed on a system with a valid IPL report. On s390, a kdump kernel, its initrd and IPL report if present are loaded into a special and reserved on boot memory region - crashkernel. When a system crashes and kdump was activated before, the purgatory code is entered first which swaps the crashkernel and [0 - crashkernel size] memory regions. Only after that the kdump kernel is entered. For this reason, the pointer to an IPL report in lowcore must point to the IPL report after the swap and not to the address of the IPL report that was located in crashkernel memory region before the swap. Failing to do so, makes the kdump's decompressor try to read memory from the crashkernel memory region which already contains the production's kernel memory. The situation described above caused spontaneous kdump failures/hangs on systems where the Secure IPL is activated because on such systems an IPL report is always present. In that case kdump's decompressor tried to parse an IPL report which frequently lead to illegal memory accesses because an IPL report contains addresses to various data. Cc: Fixes: 99feaa717e55 ("s390/kexec_file: Create ipl report and pass to next kernel") Reviewed-by: Vasily Gorbik Signed-off-by: Alexander Egorenkov Signed-off-by: Heiko Carstens --- arch/s390/kernel/machine_kexec_file.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index fc6d5f58debe..2df94d32140c 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -187,8 +187,6 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->memsz = ALIGN(data->memsz, PAGE_SIZE); buf.mem = data->memsz; - if (image->type == KEXEC_TYPE_CRASH) - buf.mem += crashk_res.start; ptr = (void *)ipl_cert_list_addr; end = ptr + ipl_cert_list_size; @@ -225,6 +223,9 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr); *lc_ipl_parmblock_ptr = (__u32)buf.mem; + if (image->type == KEXEC_TYPE_CRASH) + buf.mem += crashk_res.start; + ret = kexec_add_buffer(&buf); out: return ret; From d891f2b724b39a2a41e3ad7b57110193993242ff Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 6 Jan 2023 07:13:19 -0800 Subject: [PATCH 211/233] perf build: Properly guard libbpf includes Including libbpf header files should be guarded by HAVE_LIBBPF_SUPPORT. In bpf_counter.h, move the skeleton utilities under HAVE_BPF_SKEL. Fixes: d6a735ef3277c45f ("perf bpf_counter: Move common functions to bpf_counter.h") Reported-by: Mike Leach Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Tested-by: Jiri Olsa Tested-by: Mike Leach Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20230105172243.7238-1-mike.leach@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 2 ++ tools/perf/util/bpf_counter.h | 6 ++++++ 2 files changed, 8 insertions(+) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 86e06f136f40..d21fe0f32a6d 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -16,7 +16,9 @@ #include "util/record.h" #include +#ifdef HAVE_LIBBPF_SUPPORT #include +#endif #include "util/bpf_map.h" #include "util/rlimit.h" #include "builtin.h" diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h index 4dbf26408b69..c6d21c07b14c 100644 --- a/tools/perf/util/bpf_counter.h +++ b/tools/perf/util/bpf_counter.h @@ -4,9 +4,12 @@ #include #include + +#ifdef HAVE_LIBBPF_SUPPORT #include #include #include +#endif struct evsel; struct target; @@ -87,6 +90,8 @@ static inline void set_max_rlimit(void) setrlimit(RLIMIT_MEMLOCK, &rinf); } +#ifdef HAVE_BPF_SKEL + static inline __u32 bpf_link_get_id(int fd) { struct bpf_link_info link_info = { .id = 0, }; @@ -127,5 +132,6 @@ static inline int bperf_trigger_reading(int prog_fd, int cpu) return bpf_prog_test_run_opts(prog_fd, &opts); } +#endif /* HAVE_BPF_SKEL */ #endif /* __PERF_BPF_COUNTER_H */ From b3719108ae60169eda5c941ca5e1be1faa371c57 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Sun, 8 Jan 2023 14:23:59 +0800 Subject: [PATCH 212/233] perf kmem: Support legacy tracepoints Commit 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of tracepoints") removed tracepoints 'kmalloc_node' and 'kmem_cache_alloc_node', we need to consider the tool should be backward compatible. If it detect the tracepoint "kmem:kmalloc_node", this patch enables the legacy tracepoints, otherwise, it will ignore them. Fixes: 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of tracepoints") Reported-by: Ravi Bangoria Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Alexander Shishkin Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Vlastimil Babka Link: https://lore.kernel.org/r/20230108062400.250690-1-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kmem.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index e20656c431a4..50a3df5dc18a 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1824,6 +1824,19 @@ static int parse_line_opt(const struct option *opt __maybe_unused, return 0; } +static bool slab_legacy_tp_is_exposed(void) +{ + /* + * The tracepoints "kmem:kmalloc_node" and + * "kmem:kmem_cache_alloc_node" have been removed on the latest + * kernel, if the tracepoint "kmem:kmalloc_node" is existed it + * means the tool is running on an old kernel, we need to + * rollback to support these legacy tracepoints. + */ + return IS_ERR(trace_event__tp_format("kmem", "kmalloc_node")) ? + false : true; +} + static int __cmd_record(int argc, const char **argv) { const char * const record_args[] = { @@ -1831,22 +1844,28 @@ static int __cmd_record(int argc, const char **argv) }; const char * const slab_events[] = { "-e", "kmem:kmalloc", - "-e", "kmem:kmalloc_node", "-e", "kmem:kfree", "-e", "kmem:kmem_cache_alloc", - "-e", "kmem:kmem_cache_alloc_node", "-e", "kmem:kmem_cache_free", }; + const char * const slab_legacy_events[] = { + "-e", "kmem:kmalloc_node", + "-e", "kmem:kmem_cache_alloc_node", + }; const char * const page_events[] = { "-e", "kmem:mm_page_alloc", "-e", "kmem:mm_page_free", }; unsigned int rec_argc, i, j; const char **rec_argv; + unsigned int slab_legacy_tp_exposed = slab_legacy_tp_is_exposed(); rec_argc = ARRAY_SIZE(record_args) + argc - 1; - if (kmem_slab) + if (kmem_slab) { rec_argc += ARRAY_SIZE(slab_events); + if (slab_legacy_tp_exposed) + rec_argc += ARRAY_SIZE(slab_legacy_events); + } if (kmem_page) rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */ @@ -1861,6 +1880,10 @@ static int __cmd_record(int argc, const char **argv) if (kmem_slab) { for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++) rec_argv[i] = strdup(slab_events[j]); + if (slab_legacy_tp_exposed) { + for (j = 0; j < ARRAY_SIZE(slab_legacy_events); j++, i++) + rec_argv[i] = strdup(slab_legacy_events[j]); + } } if (kmem_page) { rec_argv[i++] = strdup("-g"); From dce088ab0d51ae3b14fb2bd608e9c649aadfe5dc Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Sun, 8 Jan 2023 14:24:00 +0800 Subject: [PATCH 213/233] perf kmem: Support field "node" in evsel__process_alloc_event() coping with recent tracepoint restructuring Commit 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of tracepoints") adds the field "node" into the tracepoints 'kmalloc' and 'kmem_cache_alloc', so this patch modifies the event process function to support the field "node". If field "node" is detected by checking function evsel__field(), it stats the cross allocation. When the "node" value is NUMA_NO_NODE (-1), it means the memory can be allocated from any memory node, in this case, we don't account it as a cross allocation. Fixes: 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of tracepoints") Reported-by: Ravi Bangoria Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Alexander Shishkin Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Vlastimil Babka Link: https://lore.kernel.org/r/20230108062400.250690-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kmem.c | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 50a3df5dc18a..8ae0a1535293 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -26,6 +26,7 @@ #include "util/string2.h" #include +#include #include #include #include @@ -185,22 +186,33 @@ static int evsel__process_alloc_event(struct evsel *evsel, struct perf_sample *s total_allocated += bytes_alloc; nr_allocs++; - return 0; -} -static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_sample *sample) -{ - int ret = evsel__process_alloc_event(evsel, sample); + /* + * Commit 11e9734bcb6a ("mm/slab_common: unify NUMA and UMA + * version of tracepoints") adds the field "node" into the + * tracepoints 'kmalloc' and 'kmem_cache_alloc'. + * + * The legacy tracepoints 'kmalloc_node' and 'kmem_cache_alloc_node' + * also contain the field "node". + * + * If the tracepoint contains the field "node" the tool stats the + * cross allocation. + */ + if (evsel__field(evsel, "node")) { + int node1, node2; - if (!ret) { - int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}), - node2 = evsel__intval(evsel, sample, "node"); + node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}); + node2 = evsel__intval(evsel, sample, "node"); - if (node1 != node2) + /* + * If the field "node" is NUMA_NO_NODE (-1), we don't take it + * as a cross allocation. + */ + if ((node2 != NUMA_NO_NODE) && (node1 != node2)) nr_cross_allocs++; } - return ret; + return 0; } static int ptr_cmp(void *, void *); @@ -1369,8 +1381,8 @@ static int __cmd_kmem(struct perf_session *session) /* slab allocator */ { "kmem:kmalloc", evsel__process_alloc_event, }, { "kmem:kmem_cache_alloc", evsel__process_alloc_event, }, - { "kmem:kmalloc_node", evsel__process_alloc_node_event, }, - { "kmem:kmem_cache_alloc_node", evsel__process_alloc_node_event, }, + { "kmem:kmalloc_node", evsel__process_alloc_event, }, + { "kmem:kmem_cache_alloc_node", evsel__process_alloc_event, }, { "kmem:kfree", evsel__process_free_event, }, { "kmem:kmem_cache_free", evsel__process_free_event, }, /* page allocator */ From 213b760fbc69f2d6aed8f64f006a17869f0d8da4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 9 Jan 2023 11:59:30 -0300 Subject: [PATCH 214/233] perf tools: Don't install libtraceevent plugins as its not anymore in the kernel sources While doing 'make -C tools/perf build-test' one can notice error messages while trying to install libtraceevent plugins, stop doing that as libtraceevent isn't anymore a homie. These are the warnings dealt with: make_install_prefix_slash_O: make install prefix=/tmp/krava/ failed to find: /tmp/krava/etc/bash_completion.d/perf failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_cfg80211.so failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_scsi.so failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_xen.so failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_function.so failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_sched_switch.so failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_mac80211.so failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_kvm.so failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_kmem.so failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_hrtimer.so failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_jbd2.so Fixes: 4171925aa9f3f7bf ("tools lib traceevent: Remove libtraceevent") Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Cc: Steven Rostedt Link: http://lore.kernel.org/lkml/Y7xXz+TSpiCbQGjw@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 8 -------- tools/perf/tests/make | 12 ------------ 2 files changed, 20 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index c2504c39bdcb..156440ea0191 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1314,14 +1314,6 @@ tip_instdir_SQ = $(subst ','\'',$(tip_instdir)) export perfexec_instdir_SQ -# If we install to $(HOME) we keep the traceevent default: -# $(HOME)/.traceevent/plugins -# Otherwise we install plugins into the global $(libdir). -ifdef DESTDIR -plugindir=$(libdir)/traceevent/plugins -plugindir_SQ= $(subst ','\'',$(plugindir)) -endif - print_var = $(eval $(print_var_code)) $(info $(MSG)) define print_var_code MSG = $(shell printf '...%40s: %s' $(1) $($(1))) diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 05e818a8bbad..009d6efb673c 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -222,19 +222,7 @@ installed_files_bin := bin/perf installed_files_bin += etc/bash_completion.d/perf installed_files_bin += libexec/perf-core/perf-archive -installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so - installed_files_all := $(installed_files_bin) -installed_files_all += $(installed_files_plugins) test_make_install := $(call test_dest_files,$(installed_files_all)) test_make_install_O := $(call test_dest_files,$(installed_files_all)) From f00eccb447762c99675f3f5b0311a1216135af95 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 6 Jan 2023 07:13:20 -0800 Subject: [PATCH 215/233] perf build: Fix build error when NO_LIBBPF=1 The $(LIBBPF) target should only be a dependency of prepare if the static version of libbpf is needed. Add a new LIBBPF_STATIC variable that is set by Makefile.config. Use LIBBPF_STATIC to determine whether the CFLAGS, etc. need updating and for adding $(LIBBPF) as a prepare dependency. As Makefile.config isn't loaded for "clean" as a target, always set LIBBPF_OUTPUT regardless of whether it is needed for $(LIBBPF). This is done to minimize conditional logic for $(LIBBPF)-clean. This issue and an original fix was reported by Mike Leach in: https://lore.kernel.org/lkml/20230105172243.7238-1-mike.leach@linaro.org/ Fixes: 746bd29e348f99b4 ("perf build: Use tools/lib headers from install path") Reported-by: Mike Leach Signed-off-by: Ian Rogers Tested-by: Jiri Olsa Cc: Alexander Shishkin Cc: bpf@vger.kernel.org Cc: Ian Rogers Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20230106151320.619514-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 2 ++ tools/perf/Makefile.perf | 21 ++++++++++++--------- 2 files changed, 14 insertions(+), 9 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 156440ea0191..9962ae23ab8c 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -602,6 +602,8 @@ ifndef NO_LIBELF dummy := $(error Error: No libbpf devel library found, please install libbpf-devel); endif else + # Libbpf will be built as a static library from tools/lib/bpf. + LIBBPF_STATIC := 1 CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 1e32c93b8042..b7d9c4206230 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -303,10 +303,12 @@ ifneq ($(OUTPUT),) else LIBBPF_OUTPUT = $(CURDIR)/libbpf endif -LIBBPF_DESTDIR = $(LIBBPF_OUTPUT) -LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include -LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a -CFLAGS += -I$(LIBBPF_OUTPUT)/include +ifdef LIBBPF_STATIC + LIBBPF_DESTDIR = $(LIBBPF_OUTPUT) + LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include + LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a + CFLAGS += -I$(LIBBPF_OUTPUT)/include +endif ifneq ($(OUTPUT),) LIBSUBCMD_OUTPUT = $(abspath $(OUTPUT))/libsubcmd @@ -393,10 +395,8 @@ endif export PERL_PATH PERFLIBS = $(LIBAPI) $(LIBPERF) $(LIBSUBCMD) $(LIBSYMBOL) -ifndef NO_LIBBPF - ifndef LIBBPF_DYNAMIC - PERFLIBS += $(LIBBPF) - endif +ifdef LIBBPF_STATIC + PERFLIBS += $(LIBBPF) endif # We choose to avoid "if .. else if .. else .. endif endif" @@ -756,12 +756,15 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(arch_errno_name_array) \ $(sync_file_range_arrays) \ $(LIBAPI) \ - $(LIBBPF) \ $(LIBPERF) \ $(LIBSUBCMD) \ $(LIBSYMBOL) \ bpf-skel +ifdef LIBBPF_STATIC +prepare: $(LIBBPF) +endif + $(OUTPUT)%.o: %.c prepare FORCE $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ From 14292a4ae1a37a7c97fda59b85cd625c77165ddf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 10 Jan 2023 11:46:37 -0300 Subject: [PATCH 216/233] perf bpf: Avoid build breakage with libbpf < 0.8.0 + LIBBPF_DYNAMIC=1 In 746bd29e348f99b4 ("perf build: Use tools/lib headers from install path") we stopped having the tools/lib/ directory from the kernel sources in the header include path unconditionally, which breaks the build on systems with older versions of libbpf-devel, in this case 0.7.0 as some of the structures and function declarations present in the newer version of libbpf included in the kernel sources (tools/lib/bpf) are not anymore used, just the ones in the system libbpf. So instead of trying to provide alternative functions when the libbpf-bpf_program__set_insns feature test fails, fail a LIBBPF_DYNAMIC=1 build (requesting the use of the system's libbpf) and emit this build error message: $ make LIBBPF_DYNAMIC=1 -C tools/perf Makefile.config:593: *** Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources. Stop. $ For v6.3 these tests will be revamped and we'll require libbpf 1.0 as a minimal version for using LIBBPF_DYNAMIC=1, most distros should have it by now or at v6.3 time. Fixes: 746bd29e348f99b4 ("perf build: Use tools/lib headers from install path") Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/CAP-5=fVa51_URGsdDFVTzpyGmdDRj_Dj2EKPuDHNQ0BYgMSzUA@mail.gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 9962ae23ab8c..5b8784675903 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -589,6 +589,8 @@ ifndef NO_LIBELF $(call feature_check,libbpf-bpf_program__set_insns) ifeq ($(feature-libbpf-bpf_program__set_insns), 1) CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS + else + dummy := $(error Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources); endif $(call feature_check,libbpf-btf__raw_data) ifeq ($(feature-libbpf-btf__raw_data), 1) From b93fb4405fcb5112c5739c5349afb52ec7f15c07 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 29 Nov 2022 09:57:48 +0800 Subject: [PATCH 217/233] ixgbe: fix pci device refcount leak As the comment of pci_get_domain_bus_and_slot() says, it returns a PCI device with refcount incremented, when finish using it, the caller must decrement the reference count by calling pci_dev_put(). In ixgbe_get_first_secondary_devfn() and ixgbe_x550em_a_has_mii(), pci_dev_put() is called to avoid leak. Fixes: 8fa10ef01260 ("ixgbe: register a mdiobus") Signed-off-by: Yang Yingliang Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 24aa97f993ca..123dca9ce468 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -855,9 +855,11 @@ static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn) rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn); if (rp_pdev && rp_pdev->subordinate) { bus = rp_pdev->subordinate->number; + pci_dev_put(rp_pdev); return pci_get_domain_bus_and_slot(0, bus, 0); } + pci_dev_put(rp_pdev); return NULL; } @@ -874,6 +876,7 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) struct ixgbe_adapter *adapter = hw->back; struct pci_dev *pdev = adapter->pdev; struct pci_dev *func0_pdev; + bool has_mii = false; /* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices * are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0 @@ -884,15 +887,16 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0)); if (func0_pdev) { if (func0_pdev == pdev) - return true; - else - return false; + has_mii = true; + goto out; } func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0)); if (func0_pdev == pdev) - return true; + has_mii = true; - return false; +out: + pci_dev_put(func0_pdev); + return has_mii; } /** From 5e91c72e560cc85f7163bbe3d14197268de31383 Mon Sep 17 00:00:00 2001 From: Christopher S Hall Date: Wed, 14 Dec 2022 16:10:38 +0800 Subject: [PATCH 218/233] igc: Fix PPS delta between two synchronized end-points This patch fix the pulse per second output delta between two synchronized end-points. Based on Intel Discrete I225 Software User Manual Section 4.2.15 TimeSync Auxiliary Control Register, ST0[Bit 4] and ST1[Bit 7] must be set to ensure that clock output will be toggles based on frequency value defined. This is to ensure that output of the PPS is aligned with the clock. How to test: 1) Running time synchronization on both end points. Ex: ptp4l --step_threshold=1 -m -f gPTP.cfg -i 2) Configure PPS output using below command for both end-points Ex: SDP0 on I225 REV4 SKU variant ./testptp -d /dev/ptp0 -L 0,2 ./testptp -d /dev/ptp0 -p 1000000000 3) Measure the output using analyzer for both end-points Fixes: 87938851b6ef ("igc: enable auxiliary PHC functions for the i225") Signed-off-by: Christopher S Hall Signed-off-by: Muhammad Husaini Zulkifli Acked-by: Sasha Neftin Tested-by: Naama Meir Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_defines.h | 2 ++ drivers/net/ethernet/intel/igc/igc_ptp.c | 10 ++++++---- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index a7b22639cfcd..e9747ec5ac0b 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -475,7 +475,9 @@ #define IGC_TSAUXC_EN_TT0 BIT(0) /* Enable target time 0. */ #define IGC_TSAUXC_EN_TT1 BIT(1) /* Enable target time 1. */ #define IGC_TSAUXC_EN_CLK0 BIT(2) /* Enable Configurable Frequency Clock 0. */ +#define IGC_TSAUXC_ST0 BIT(4) /* Start Clock 0 Toggle on Target Time 0. */ #define IGC_TSAUXC_EN_CLK1 BIT(5) /* Enable Configurable Frequency Clock 1. */ +#define IGC_TSAUXC_ST1 BIT(7) /* Start Clock 1 Toggle on Target Time 1. */ #define IGC_TSAUXC_EN_TS0 BIT(8) /* Enable hardware timestamp 0. */ #define IGC_TSAUXC_AUTT0 BIT(9) /* Auxiliary Timestamp Taken. */ #define IGC_TSAUXC_EN_TS1 BIT(10) /* Enable hardware timestamp 0. */ diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 8dbb9f903ca7..c34734d432e0 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -322,7 +322,7 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, ts = ns_to_timespec64(ns); if (rq->perout.index == 1) { if (use_freq) { - tsauxc_mask = IGC_TSAUXC_EN_CLK1; + tsauxc_mask = IGC_TSAUXC_EN_CLK1 | IGC_TSAUXC_ST1; tsim_mask = 0; } else { tsauxc_mask = IGC_TSAUXC_EN_TT1; @@ -333,7 +333,7 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, freqout = IGC_FREQOUT1; } else { if (use_freq) { - tsauxc_mask = IGC_TSAUXC_EN_CLK0; + tsauxc_mask = IGC_TSAUXC_EN_CLK0 | IGC_TSAUXC_ST0; tsim_mask = 0; } else { tsauxc_mask = IGC_TSAUXC_EN_TT0; @@ -347,10 +347,12 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, tsauxc = rd32(IGC_TSAUXC); tsim = rd32(IGC_TSIM); if (rq->perout.index == 1) { - tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1); + tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1 | + IGC_TSAUXC_ST1); tsim &= ~IGC_TSICR_TT1; } else { - tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0); + tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0 | + IGC_TSAUXC_ST0); tsim &= ~IGC_TSICR_TT0; } if (on) { From 6650c8e906ce58404bfdfceceeba7bd10d397d40 Mon Sep 17 00:00:00 2001 From: Daniil Tatianin Date: Tue, 20 Dec 2022 09:32:46 +0300 Subject: [PATCH 219/233] iavf/iavf_main: actually log ->src mask when talking about it This fixes a copy-paste issue where dev_err would log the dst mask even though it is clearly talking about src. Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Fixes: 0075fa0fadd0 ("i40evf: Add support to apply cloud filters") Signed-off-by: Daniil Tatianin Reviewed-by: Michal Swiatkowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index c4e451ef7942..adc02adef83a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3850,7 +3850,7 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", - be32_to_cpu(match.mask->dst)); + be32_to_cpu(match.mask->src)); return -EINVAL; } } From 96398560f26aa07e8f2969d73c8197e6a6d10407 Mon Sep 17 00:00:00 2001 From: Frederick Lawler Date: Mon, 9 Jan 2023 10:39:06 -0600 Subject: [PATCH 220/233] net: sched: disallow noqueue for qdisc classes While experimenting with applying noqueue to a classful queue discipline, we discovered a NULL pointer dereference in the __dev_queue_xmit() path that generates a kernel OOPS: # dev=enp0s5 # tc qdisc replace dev $dev root handle 1: htb default 1 # tc class add dev $dev parent 1: classid 1:1 htb rate 10mbit # tc qdisc add dev $dev parent 1:1 handle 10: noqueue # ping -I $dev -w 1 -c 1 1.1.1.1 [ 2.172856] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 2.173217] #PF: supervisor instruction fetch in kernel mode ... [ 2.178451] Call Trace: [ 2.178577] [ 2.178686] htb_enqueue+0x1c8/0x370 [ 2.178880] dev_qdisc_enqueue+0x15/0x90 [ 2.179093] __dev_queue_xmit+0x798/0xd00 [ 2.179305] ? _raw_write_lock_bh+0xe/0x30 [ 2.179522] ? __local_bh_enable_ip+0x32/0x70 [ 2.179759] ? ___neigh_create+0x610/0x840 [ 2.179968] ? eth_header+0x21/0xc0 [ 2.180144] ip_finish_output2+0x15e/0x4f0 [ 2.180348] ? dst_output+0x30/0x30 [ 2.180525] ip_push_pending_frames+0x9d/0xb0 [ 2.180739] raw_sendmsg+0x601/0xcb0 [ 2.180916] ? _raw_spin_trylock+0xe/0x50 [ 2.181112] ? _raw_spin_unlock_irqrestore+0x16/0x30 [ 2.181354] ? get_page_from_freelist+0xcd6/0xdf0 [ 2.181594] ? sock_sendmsg+0x56/0x60 [ 2.181781] sock_sendmsg+0x56/0x60 [ 2.181958] __sys_sendto+0xf7/0x160 [ 2.182139] ? handle_mm_fault+0x6e/0x1d0 [ 2.182366] ? do_user_addr_fault+0x1e1/0x660 [ 2.182627] __x64_sys_sendto+0x1b/0x30 [ 2.182881] do_syscall_64+0x38/0x90 [ 2.183085] entry_SYSCALL_64_after_hwframe+0x63/0xcd ... [ 2.187402] Previously in commit d66d6c3152e8 ("net: sched: register noqueue qdisc"), NULL was set for the noqueue discipline on noqueue init so that __dev_queue_xmit() falls through for the noqueue case. This also sets a bypass of the enqueue NULL check in the register_qdisc() function for the struct noqueue_disc_ops. Classful queue disciplines make it past the NULL check in __dev_queue_xmit() because the discipline is set to htb (in this case), and then in the call to __dev_xmit_skb(), it calls into htb_enqueue() which grabs a leaf node for a class and then calls qdisc_enqueue() by passing in a queue discipline which assumes ->enqueue() is not set to NULL. Fix this by not allowing classes to be assigned to the noqueue discipline. Linux TC Notes states that classes cannot be set to the noqueue discipline. [1] Let's enforce that here. Links: 1. https://linux-tc-notes.sourceforge.net/tc/doc/sch_noqueue.txt Fixes: d66d6c3152e8 ("net: sched: register noqueue qdisc") Cc: stable@vger.kernel.org Signed-off-by: Frederick Lawler Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20230109163906.706000-1-fred@cloudflare.com Signed-off-by: Jakub Kicinski --- net/sched/sch_api.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 2317db02c764..72d2c204d5f3 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1133,6 +1133,11 @@ skip: return -ENOENT; } + if (new && new->ops == &noqueue_qdisc_ops) { + NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class"); + return -EINVAL; + } + err = cops->graft(parent, cl, new, &old, extack); if (err) return err; From b0e380b5d4275299adf43e249f18309331b6f54f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Mon, 9 Jan 2023 16:32:23 +0100 Subject: [PATCH 221/233] net: lan966x: check for ptp to be enabled in lan966x_ptp_deinit() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If ptp was not enabled due to missing IRQ for instance, lan966x_ptp_deinit() will dereference NULL pointers. Fixes: d096459494a8 ("net: lan966x: Add support for ptp clocks") Signed-off-by: Clément Léger Reviewed-by: Horatiu Vultur Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c index f9ebfaafbebc..a8348437dd87 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c @@ -1073,6 +1073,9 @@ void lan966x_ptp_deinit(struct lan966x *lan966x) struct lan966x_port *port; int i; + if (!lan966x->ptp) + return; + for (i = 0; i < lan966x->num_phys_ports; i++) { port = lan966x->ports[i]; if (!port) From cb3e9864cdbe35ff6378966660edbcbac955fe17 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 10 Jan 2023 08:59:06 +0800 Subject: [PATCH 222/233] ipv6: raw: Deduct extension header length in rawv6_push_pending_frames The total cork length created by ip6_append_data includes extension headers, so we must exclude them when comparing them against the IPV6_CHECKSUM offset which does not include extension headers. Reported-by: Kyle Zeng Fixes: 357b40a18b04 ("[IPV6]: IPV6_CHECKSUM socket option can corrupt kernel memory") Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- net/ipv6/raw.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a06a9f847db5..ada087b50541 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -505,6 +505,7 @@ csum_copy_err: static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { + struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; @@ -522,6 +523,9 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; + opt = inet6_sk(sk)->cork.opt; + total_len -= opt ? opt->opt_flen : 0; + if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); From a720416d94634068951773cb9e9d6f1b73769e5b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 6 Jan 2023 11:07:18 +0100 Subject: [PATCH 223/233] spi: spidev: fix a race condition when accessing spidev->spi There's a spinlock in place that is taken in file_operations callbacks whenever we check if spidev->spi is still alive (not null). It's also taken when spidev->spi is set to NULL in remove(). This however doesn't protect the code against driver unbind event while one of the syscalls is still in progress. To that end we need a lock taken continuously as long as we may still access spidev->spi. As both the file ops and the remove callback are never called from interrupt context, we can replace the spinlock with a mutex. Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20230106100719.196243-1-brgl@bgdev.pl Signed-off-by: Mark Brown --- drivers/spi/spidev.c | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 6313e7d0cdf8..42aaaca67265 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -68,7 +68,7 @@ static_assert(N_SPI_MINORS > 0 && N_SPI_MINORS <= 256); struct spidev_data { dev_t devt; - spinlock_t spi_lock; + struct mutex spi_lock; struct spi_device *spi; struct list_head device_entry; @@ -95,9 +95,8 @@ spidev_sync(struct spidev_data *spidev, struct spi_message *message) int status; struct spi_device *spi; - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); spi = spidev->spi; - spin_unlock_irq(&spidev->spi_lock); if (spi == NULL) status = -ESHUTDOWN; @@ -107,6 +106,7 @@ spidev_sync(struct spidev_data *spidev, struct spi_message *message) if (status == 0) status = message->actual_length; + mutex_unlock(&spidev->spi_lock); return status; } @@ -359,12 +359,12 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) * we issue this ioctl. */ spidev = filp->private_data; - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); spi = spi_dev_get(spidev->spi); - spin_unlock_irq(&spidev->spi_lock); - - if (spi == NULL) + if (spi == NULL) { + mutex_unlock(&spidev->spi_lock); return -ESHUTDOWN; + } /* use the buffer lock here for triple duty: * - prevent I/O (from us) so calling spi_setup() is safe; @@ -508,6 +508,7 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) mutex_unlock(&spidev->buf_lock); spi_dev_put(spi); + mutex_unlock(&spidev->spi_lock); return retval; } @@ -529,12 +530,12 @@ spidev_compat_ioc_message(struct file *filp, unsigned int cmd, * we issue this ioctl. */ spidev = filp->private_data; - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); spi = spi_dev_get(spidev->spi); - spin_unlock_irq(&spidev->spi_lock); - - if (spi == NULL) + if (spi == NULL) { + mutex_unlock(&spidev->spi_lock); return -ESHUTDOWN; + } /* SPI_IOC_MESSAGE needs the buffer locked "normally" */ mutex_lock(&spidev->buf_lock); @@ -561,6 +562,7 @@ spidev_compat_ioc_message(struct file *filp, unsigned int cmd, done: mutex_unlock(&spidev->buf_lock); spi_dev_put(spi); + mutex_unlock(&spidev->spi_lock); return retval; } @@ -640,10 +642,10 @@ static int spidev_release(struct inode *inode, struct file *filp) spidev = filp->private_data; filp->private_data = NULL; - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); /* ... after we unbound from the underlying device? */ dofree = (spidev->spi == NULL); - spin_unlock_irq(&spidev->spi_lock); + mutex_unlock(&spidev->spi_lock); /* last close? */ spidev->users--; @@ -776,7 +778,7 @@ static int spidev_probe(struct spi_device *spi) /* Initialize the driver data */ spidev->spi = spi; - spin_lock_init(&spidev->spi_lock); + mutex_init(&spidev->spi_lock); mutex_init(&spidev->buf_lock); INIT_LIST_HEAD(&spidev->device_entry); @@ -821,9 +823,9 @@ static void spidev_remove(struct spi_device *spi) /* prevent new opens */ mutex_lock(&device_list_lock); /* make sure ops on existing fds can abort cleanly */ - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); spidev->spi = NULL; - spin_unlock_irq(&spidev->spi_lock); + mutex_unlock(&spidev->spi_lock); list_del(&spidev->device_entry); device_destroy(spidev_class, spidev->devt); From 6b35b173dbc1711f8d272e3f322d2ad697015919 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 6 Jan 2023 11:07:19 +0100 Subject: [PATCH 224/233] spi: spidev: remove debug messages that access spidev->spi without locking The two debug messages in spidev_open() dereference spidev->spi without taking the lock and without checking if it's not null. This can lead to a crash. Drop the messages as they're not needed - the user-space will get informed about ENOMEM with the syscall return value. Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20230106100719.196243-2-brgl@bgdev.pl Signed-off-by: Mark Brown --- drivers/spi/spidev.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 42aaaca67265..1935ca613447 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -603,7 +603,6 @@ static int spidev_open(struct inode *inode, struct file *filp) if (!spidev->tx_buffer) { spidev->tx_buffer = kmalloc(bufsiz, GFP_KERNEL); if (!spidev->tx_buffer) { - dev_dbg(&spidev->spi->dev, "open/ENOMEM\n"); status = -ENOMEM; goto err_find_dev; } @@ -612,7 +611,6 @@ static int spidev_open(struct inode *inode, struct file *filp) if (!spidev->rx_buffer) { spidev->rx_buffer = kmalloc(bufsiz, GFP_KERNEL); if (!spidev->rx_buffer) { - dev_dbg(&spidev->spi->dev, "open/ENOMEM\n"); status = -ENOMEM; goto err_alloc_rx_buf; } From 82d3edb50a11bf3c5ef63294d5358ba230181413 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 5 Jan 2023 15:44:20 +0100 Subject: [PATCH 225/233] s390/cpum_sf: add READ_ONCE() semantics to compare and swap loops The current cmpxchg_double() loops within the perf hw sampling code do not have READ_ONCE() semantics to read the old value from memory. This allows the compiler to generate code which reads the "old" value several times from memory, which again allows for inconsistencies. For example: /* Reset trailer (using compare-double-and-swap) */ do { te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; te_flags |= SDB_TE_ALERT_REQ_MASK; } while (!cmpxchg_double(&te->flags, &te->overflow, te->flags, te->overflow, te_flags, 0ULL)); The compiler could generate code where te->flags used within the cmpxchg_double() call may be refetched from memory and which is not necessarily identical to the previous read version which was used to generate te_flags. Which in turn means that an incorrect update could happen. Fix this by adding READ_ONCE() semantics to all cmpxchg_double() loops. Given that READ_ONCE() cannot generate code on s390 which atomically reads 16 bytes, use a private compare-and-swap-double implementation to achieve that. Also replace cmpxchg_double() with the private implementation to be able to re-use the old value within the loops. As a side effect this converts the whole code to only use bit fields to read and modify bits within the hws trailer header. Reported-by: Alexander Gordeev Acked-by: Alexander Gordeev Acked-by: Hendrik Brueckner Reviewed-by: Thomas Richter Cc: Link: https://lore.kernel.org/linux-s390/Y71QJBhNTIatvxUT@osiris/T/#ma14e2a5f7aa8ed4b94b6f9576799b3ad9c60f333 Signed-off-by: Heiko Carstens --- arch/s390/include/asm/cpu_mf.h | 31 +++++----- arch/s390/kernel/perf_cpum_sf.c | 101 ++++++++++++++++++++------------ 2 files changed, 77 insertions(+), 55 deletions(-) diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index feaba12dbecb..efa103b52a1a 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -131,19 +131,21 @@ struct hws_combined_entry { struct hws_diag_entry diag; /* Diagnostic-sampling data entry */ } __packed; -struct hws_trailer_entry { - union { - struct { - unsigned int f:1; /* 0 - Block Full Indicator */ - unsigned int a:1; /* 1 - Alert request control */ - unsigned int t:1; /* 2 - Timestamp format */ - unsigned int :29; /* 3 - 31: Reserved */ - unsigned int bsdes:16; /* 32-47: size of basic SDE */ - unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ - }; - unsigned long long flags; /* 0 - 63: All indicators */ +union hws_trailer_header { + struct { + unsigned int f:1; /* 0 - Block Full Indicator */ + unsigned int a:1; /* 1 - Alert request control */ + unsigned int t:1; /* 2 - Timestamp format */ + unsigned int :29; /* 3 - 31: Reserved */ + unsigned int bsdes:16; /* 32-47: size of basic SDE */ + unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ + unsigned long long overflow; /* 64 - Overflow Count */ }; - unsigned long long overflow; /* 64 - sample Overflow count */ + __uint128_t val; +}; + +struct hws_trailer_entry { + union hws_trailer_header header; /* 0 - 15 Flags + Overflow Count */ unsigned char timestamp[16]; /* 16 - 31 timestamp */ unsigned long long reserved1; /* 32 -Reserved */ unsigned long long reserved2; /* */ @@ -290,14 +292,11 @@ static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi, return USEC_PER_SEC * qsi->cpu_speed / rate; } -#define SDB_TE_ALERT_REQ_MASK 0x4000000000000000UL -#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL - /* Return TOD timestamp contained in an trailer entry */ static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te) { /* TOD in STCKE format */ - if (te->t) + if (te->header.t) return *((unsigned long long *) &te->timestamp[1]); /* TOD in STCK format */ diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 332a49965130..ce886a03545a 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -163,14 +163,15 @@ static void free_sampling_buffer(struct sf_buffer *sfb) static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags) { - unsigned long sdb, *trailer; + struct hws_trailer_entry *te; + unsigned long sdb; /* Allocate and initialize sample-data-block */ sdb = get_zeroed_page(gfp_flags); if (!sdb) return -ENOMEM; - trailer = trailer_entry_ptr(sdb); - *trailer = SDB_TE_ALERT_REQ_MASK; + te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb); + te->header.a = 1; /* Link SDB into the sample-data-block-table */ *sdbt = sdb; @@ -1206,7 +1207,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, "%s: Found unknown" " sampling data entry: te->f %i" " basic.def %#4x (%p)\n", __func__, - te->f, sample->def, sample); + te->header.f, sample->def, sample); /* Sample slot is not yet written or other record. * * This condition can occur if the buffer was reused @@ -1217,7 +1218,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, * that are not full. Stop processing if the first * invalid format was detected. */ - if (!te->f) + if (!te->header.f) break; } @@ -1227,6 +1228,16 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, } } +static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t new) +{ + asm volatile( + " cdsg %[old],%[new],%[ptr]\n" + : [old] "+d" (old), [ptr] "+QS" (*ptr) + : [new] "d" (new) + : "memory", "cc"); + return old; +} + /* hw_perf_event_update() - Process sampling buffer * @event: The perf event * @flush_all: Flag to also flush partially filled sample-data-blocks @@ -1243,10 +1254,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, */ static void hw_perf_event_update(struct perf_event *event, int flush_all) { + unsigned long long event_overflow, sampl_overflow, num_sdb; + union hws_trailer_header old, prev, new; struct hw_perf_event *hwc = &event->hw; struct hws_trailer_entry *te; unsigned long *sdbt; - unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags; int done; /* @@ -1266,25 +1278,25 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt); /* Leave loop if no more work to do (block full indicator) */ - if (!te->f) { + if (!te->header.f) { done = 1; if (!flush_all) break; } /* Check the sample overflow count */ - if (te->overflow) + if (te->header.overflow) /* Account sample overflows and, if a particular limit * is reached, extend the sampling buffer. * For details, see sfb_account_overflows(). */ - sampl_overflow += te->overflow; + sampl_overflow += te->header.overflow; /* Timestamps are valid for full sample-data-blocks only */ debug_sprintf_event(sfdbg, 6, "%s: sdbt %#lx " "overflow %llu timestamp %#llx\n", - __func__, (unsigned long)sdbt, te->overflow, - (te->f) ? trailer_timestamp(te) : 0ULL); + __func__, (unsigned long)sdbt, te->header.overflow, + (te->header.f) ? trailer_timestamp(te) : 0ULL); /* Collect all samples from a single sample-data-block and * flag if an (perf) event overflow happened. If so, the PMU @@ -1294,12 +1306,16 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) num_sdb++; /* Reset trailer (using compare-double-and-swap) */ + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te_flags |= SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - te->flags, te->overflow, - te_flags, 0ULL)); + old.val = prev.val; + new.val = prev.val; + new.f = 0; + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); /* Advance to next sample-data-block */ sdbt++; @@ -1384,7 +1400,7 @@ static void aux_output_end(struct perf_output_handle *handle) range_scan = AUX_SDB_NUM_ALERT(aux); for (i = 0, idx = aux->head; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - if (!(te->flags & SDB_TE_BUFFER_FULL_MASK)) + if (!te->header.f) break; } /* i is num of SDBs which are full */ @@ -1392,7 +1408,7 @@ static void aux_output_end(struct perf_output_handle *handle) /* Remove alert indicators in the buffer */ te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags &= ~SDB_TE_ALERT_REQ_MASK; + te->header.a = 0; debug_sprintf_event(sfdbg, 6, "%s: SDBs %ld range %ld head %ld\n", __func__, i, range_scan, aux->head); @@ -1437,9 +1453,9 @@ static int aux_output_begin(struct perf_output_handle *handle, idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | - SDB_TE_ALERT_REQ_MASK); - te->overflow = 0; + te->header.f = 0; + te->header.a = 0; + te->header.overflow = 0; } /* Save the position of empty SDBs */ aux->empty_mark = aux->head + range - 1; @@ -1448,7 +1464,7 @@ static int aux_output_begin(struct perf_output_handle *handle, /* Set alert indicator */ aux->alert_mark = aux->head + range/2 - 1; te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags = te->flags | SDB_TE_ALERT_REQ_MASK; + te->header.a = 1; /* Reset hardware buffer head */ head = AUX_SDB_INDEX(aux, aux->head); @@ -1475,14 +1491,17 @@ static int aux_output_begin(struct perf_output_handle *handle, static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; + union hws_trailer_header old, prev, new; struct hws_trailer_entry *te; te = aux_sdb_trailer(aux, alert_index); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - *overflow = orig_overflow = te->overflow; - if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { + old.val = prev.val; + new.val = prev.val; + *overflow = old.overflow; + if (old.f) { /* * SDB is already set by hardware. * Abort and try to set somewhere @@ -1490,10 +1509,10 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, */ return false; } - new_flags = orig_flags | SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); return true; } @@ -1522,8 +1541,9 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; unsigned long i, range_scan, idx, idx_old; + union hws_trailer_header old, prev, new; + unsigned long long orig_overflow; struct hws_trailer_entry *te; debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld " @@ -1554,17 +1574,20 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, idx_old = idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - orig_overflow = te->overflow; - new_flags = orig_flags & ~SDB_TE_BUFFER_FULL_MASK; + old.val = prev.val; + new.val = prev.val; + orig_overflow = old.overflow; + new.f = 0; + new.overflow = 0; if (idx == aux->alert_mark) - new_flags |= SDB_TE_ALERT_REQ_MASK; + new.a = 1; else - new_flags &= ~SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); *overflow += orig_overflow; } From e3f360db08d55a14112bd27454e616a24296a8b0 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 9 Jan 2023 11:51:20 +0100 Subject: [PATCH 226/233] s390/percpu: add READ_ONCE() to arch_this_cpu_to_op_simple() Make sure that *ptr__ within arch_this_cpu_to_op_simple() is only dereferenced once by using READ_ONCE(). Otherwise the compiler could generate incorrect code. Cc: Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens --- arch/s390/include/asm/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index cb5fc0690435..081837b391e3 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -31,7 +31,7 @@ pcp_op_T__ *ptr__; \ preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ - prev__ = *ptr__; \ + prev__ = READ_ONCE(*ptr__); \ do { \ old__ = prev__; \ new__ = old__ op (val); \ From 42400d99e9f0728c17240edb9645637ead40f6b9 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 9 Jan 2023 15:54:56 +0100 Subject: [PATCH 227/233] KVM: s390: interrupt: use READ_ONCE() before cmpxchg() Use READ_ONCE() before cmpxchg() to prevent that the compiler generates code that fetches the to be compared old value several times from memory. Reviewed-by: Christian Borntraeger Acked-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20230109145456.2895385-1-hca@linux.ibm.com Signed-off-by: Heiko Carstens --- arch/s390/kvm/interrupt.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 1dae78deddf2..ab26aa53ee37 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -83,8 +83,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union esca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -95,8 +96,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union bsca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -126,16 +128,18 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl old = *sigp_ctrl; + union esca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } else { struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl old = *sigp_ctrl; + union bsca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } From cf129830ee820f7fc90b98df193cd49d49344d09 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 10 Jan 2023 20:56:59 +0200 Subject: [PATCH 228/233] perf auxtrace: Fix address filter duplicate symbol selection When a match has been made to the nth duplicate symbol, return success not error. Example: Before: $ cat file.c cat: file.c: No such file or directory $ cat file1.c #include static void func(void) { printf("First func\n"); } void other(void); int main() { func(); other(); return 0; } $ cat file2.c #include static void func(void) { printf("Second func\n"); } void other(void) { func(); } $ gcc -Wall -Wextra -o test file1.c file2.c $ perf record -e intel_pt//u --filter 'filter func @ ./test' -- ./test Multiple symbols with name 'func' #1 0x1149 l func which is near main #2 0x1179 l func which is near other Disambiguate symbol name by inserting #n after the name e.g. func #2 Or select a global symbol by inserting #0 or #g or #G Failed to parse address filter: 'filter func @ ./test' Filter format is: filter|start|stop|tracestop [/ ] [@] Where multiple filters are separated by space or comma. $ perf record -e intel_pt//u --filter 'filter func #2 @ ./test' -- ./test Failed to parse address filter: 'filter func #2 @ ./test' Filter format is: filter|start|stop|tracestop [/ ] [@] Where multiple filters are separated by space or comma. After: $ perf record -e intel_pt//u --filter 'filter func #2 @ ./test' -- ./test First func Second func [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data ] $ perf script --itrace=b -Ftime,flags,ip,sym,addr --ns 1231062.526977619: tr strt 0 [unknown] => 558495708179 func 1231062.526977619: tr end call 558495708188 func => 558495708050 _init 1231062.526979286: tr strt 0 [unknown] => 55849570818d func 1231062.526979286: tr end return 55849570818f func => 55849570819d other Fixes: 1b36c03e356936d6 ("perf record: Add support for using symbols in address filters") Reported-by: Dmitrii Dolgov <9erthalion6@gmail.com> Signed-off-by: Adrian Hunter Tested-by: Dmitry Dolgov <9erthalion6@gmail.com> Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230110185659.15979-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/auxtrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 265d20cc126b..c2e323cd7d49 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -2611,7 +2611,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start, *size = sym->start - *start; if (idx > 0) { if (*size) - return 1; + return 0; } else if (dso_sym_match(sym, sym_name, &cnt, idx)) { print_duplicate_syms(dso, sym_name); return -EINVAL; From 1ecf7bd9c267ab85aff3c4a17fe56bc9754a13be Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 11 Jan 2023 15:04:47 +0100 Subject: [PATCH 229/233] s390: update defconfigs Signed-off-by: Heiko Carstens --- arch/s390/configs/debug_defconfig | 7 ++++--- arch/s390/configs/defconfig | 6 ++++-- arch/s390/configs/zfcpdump_defconfig | 2 +- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index a7b4e1d82758..74b35ec2ad28 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -190,7 +190,6 @@ CONFIG_NFT_CT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m -CONFIG_NFT_OBJREF=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m @@ -569,6 +568,7 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +# CONFIG_LEGACY_TIOCSTI is not set CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HANGCHECK_TIMER=m @@ -660,6 +660,7 @@ CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y @@ -705,6 +706,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_INTEGRITY_PLATFORM_KEYRING=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y @@ -781,6 +783,7 @@ CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CORDIC=m CONFIG_CRYPTO_LIB_CURVE25519=m CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m @@ -848,7 +851,6 @@ CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_FTRACE_STARTUP_TEST=y # CONFIG_EVENT_TRACE_STARTUP_TEST is not set @@ -870,7 +872,6 @@ CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y -CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_MIN_HEAP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 2bc2d0fe5774..cec71268e3bc 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -181,7 +181,6 @@ CONFIG_NFT_CT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m -CONFIG_NFT_OBJREF=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m @@ -559,6 +558,7 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +# CONFIG_LEGACY_TIOCSTI is not set CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HANGCHECK_TIMER=m @@ -645,6 +645,7 @@ CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y @@ -688,6 +689,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_INTEGRITY_PLATFORM_KEYRING=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y @@ -766,6 +768,7 @@ CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m CONFIG_CRYPTO_LIB_CURVE25519=m @@ -798,7 +801,6 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index ae14ab0b864d..a9c0c81d1de9 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -13,7 +13,6 @@ CONFIG_TUNE_ZEC12=y # CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 CONFIG_HZ_100=y -# CONFIG_RELOCATABLE is not set # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y @@ -50,6 +49,7 @@ CONFIG_ZFCP=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set +# CONFIG_LEGACY_TIOCSTI is not set # CONFIG_HVC_IUCV is not set # CONFIG_HW_RANDOM_S390 is not set # CONFIG_HMC_DRV is not set From ae9f29fdfd827ad06c1ae8155c042245a9d00757 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Tue, 10 Jan 2023 19:53:59 +0800 Subject: [PATCH 230/233] net: hns3: fix wrong use of rss size during VF rss config Currently, it used old rss size to get current tc mode. As a result, the rss size is updated, but the tc mode is still configured based on the old rss size. So this patch fixes it by using the new rss size in both process. Fixes: 93969dc14fcd ("net: hns3: refactor VF rss init APIs with new common rss init APIs") Signed-off-by: Jie Wang Signed-off-by: Hao Lan Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/20230110115359.10163-1-lanhao@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 081bd2c3f289..e84e5be8e59e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -3130,7 +3130,7 @@ static int hclgevf_set_channels(struct hnae3_handle *handle, u32 new_tqps_num, hclgevf_update_rss_size(handle, new_tqps_num); - hclge_comm_get_rss_tc_info(cur_rss_size, hdev->hw_tc_map, + hclge_comm_get_rss_tc_info(kinfo->rss_size, hdev->hw_tc_map, tc_offset, tc_valid, tc_size); ret = hclge_comm_set_rss_tc_mode(&hdev->hw.hw, tc_offset, tc_valid, tc_size); From 97f5e03a4a27d27ee4fed0cdb1658c81cf2784db Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Jan 2023 20:25:47 -0800 Subject: [PATCH 231/233] bnxt: make sure we return pages to the pool Before the commit under Fixes the page would have been released from the pool before the napi_alloc_skb() call, so normal page freeing was fine (released page == no longer in the pool). After the change we just mark the page for recycling so it's still in the pool if the skb alloc fails, we need to recycle. Same commit added the same bug in the new bnxt_rx_multi_page_skb(). Fixes: 1dc4c557bfed ("bnxt: adding bnxt_xdp_build_skb to build skb from multibuffer xdp_buff") Reviewed-by: Andy Gospodarek Link: https://lore.kernel.org/r/20230111042547.987749-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 16ce7a90610c..240a7e8a7652 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -993,7 +993,7 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp, DMA_ATTR_WEAK_ORDERING); skb = build_skb(page_address(page), PAGE_SIZE); if (!skb) { - __free_page(page); + page_pool_recycle_direct(rxr->page_pool, page); return NULL; } skb_mark_for_recycle(skb); @@ -1031,7 +1031,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, skb = napi_alloc_skb(&rxr->bnapi->napi, payload); if (!skb) { - __free_page(page); + page_pool_recycle_direct(rxr->page_pool, page); return NULL; } From ae9dcb91c6069e20b3b9505d79cbc89fd6e086f5 Mon Sep 17 00:00:00 2001 From: Noor Azura Ahmad Tarmizi Date: Wed, 11 Jan 2023 13:02:00 +0800 Subject: [PATCH 232/233] net: stmmac: add aux timestamps fifo clearance wait Add timeout polling wait for auxiliary timestamps snapshot FIFO clear bit (ATSFC) to clear. This is to ensure no residue fifo value is being read erroneously. Fixes: f4da56529da6 ("net: stmmac: Add support for external trigger timestamping") Cc: # 5.10.x Signed-off-by: Noor Azura Ahmad Tarmizi Link: https://lore.kernel.org/r/20230111050200.2130-1-noor.azura.ahmad.tarmizi@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index fc06ddeac0d5..b4388ca8d211 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -210,7 +210,10 @@ static int stmmac_enable(struct ptp_clock_info *ptp, } writel(acr_value, ptpaddr + PTP_ACR); mutex_unlock(&priv->aux_ts_lock); - ret = 0; + /* wait for auxts fifo clear to finish */ + ret = readl_poll_timeout(ptpaddr + PTP_ACR, acr_value, + !(acr_value & PTP_ACR_ATSFC), + 10, 10000); break; default: From be53771c87f4e322a9835d3faa9cd73a4ecdec5b Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Wed, 11 Jan 2023 13:32:28 +0000 Subject: [PATCH 233/233] r8152: add vendor/device ID pair for Microsoft Devkit The Microsoft Devkit 2023 is a an ARM64 based machine featuring a Realtek 8153 USB3.0-to-GBit Ethernet adapter. As in their other machines, Microsoft uses a custom USB device ID. Add the respective ID values to the driver. This makes Ethernet work on the MS Devkit device. The chip has been visually confirmed to be a RTL8153. Signed-off-by: Andre Przywara Link: https://lore.kernel.org/r/20230111133228.190801-1-andre.przywara@arm.com Signed-off-by: Paolo Abeni --- drivers/net/usb/r8152.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index a481a1d831e2..23da1d9dafd1 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9836,6 +9836,7 @@ static const struct usb_device_id rtl8152_table[] = { REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab), REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6), REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927), + REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0c5e), REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101), REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f), REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3054),