From 5adf349439d29f92467e864f728dfc23180f3ef9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 3 Mar 2022 12:23:23 +0100 Subject: [PATCH 01/12] x86/module: Fix the paravirt vs alternative order Ever since commit 4e6292114c74 ("x86/paravirt: Add new features for paravirt patching") there is an ordering dependency between patching paravirt ops and patching alternatives, the module loader still violates this. Fixes: 4e6292114c74 ("x86/paravirt: Add new features for paravirt patching") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Reviewed-by: Miroslav Benes Cc: Link: https://lore.kernel.org/r/20220303112825.068773913@infradead.org --- arch/x86/kernel/module.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 95fa745e310a..96d7c27b7093 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -273,6 +273,14 @@ int module_finalize(const Elf_Ehdr *hdr, retpolines = s; } + /* + * See alternative_instructions() for the ordering rules between the + * various patching types. + */ + if (para) { + void *pseg = (void *)para->sh_addr; + apply_paravirt(pseg, pseg + para->sh_size); + } if (retpolines) { void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); @@ -290,11 +298,6 @@ int module_finalize(const Elf_Ehdr *hdr, tseg, tseg + text->sh_size); } - if (para) { - void *pseg = (void *)para->sh_addr; - apply_paravirt(pseg, pseg + para->sh_size); - } - /* make jump label nops */ jump_label_apply_nops(me); From 7228918b34615ef6317edcd9a058a057bc54aa32 Mon Sep 17 00:00:00 2001 From: Ross Philipson Date: Wed, 23 Feb 2022 21:07:35 -0500 Subject: [PATCH 02/12] x86/boot: Fix memremap of setup_indirect structures As documented, the setup_indirect structure is nested inside the setup_data structures in the setup_data list. The code currently accesses the fields inside the setup_indirect structure but only the sizeof(struct setup_data) is being memremapped. No crash occurred but this is just due to how the area is remapped under the covers. Properly memremap both the setup_data and setup_indirect structures in these cases before accessing them. Fixes: b3c72fc9a78e ("x86/boot: Introduce setup_indirect") Signed-off-by: Ross Philipson Signed-off-by: Borislav Petkov Reviewed-by: Daniel Kiper Cc: Link: https://lore.kernel.org/r/1645668456-22036-2-git-send-email-ross.philipson@oracle.com --- arch/x86/kernel/e820.c | 41 ++++++++++++++------ arch/x86/kernel/kdebugfs.c | 35 +++++++++++++---- arch/x86/kernel/ksysfs.c | 77 ++++++++++++++++++++++++++++++-------- arch/x86/kernel/setup.c | 34 +++++++++++++---- arch/x86/mm/ioremap.c | 24 ++++++++++-- 5 files changed, 165 insertions(+), 46 deletions(-) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index bc0657f0deed..f267205f2d5a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -995,8 +995,10 @@ early_param("memmap", parse_memmap_opt); */ void __init e820__reserve_setup_data(void) { + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; + u32 len; pa_data = boot_params.hdr.setup_data; if (!pa_data) @@ -1004,6 +1006,14 @@ void __init e820__reserve_setup_data(void) while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); + if (!data) { + pr_warn("e820: failed to memremap setup_data entry\n"); + return; + } + + len = sizeof(*data); + pa_next = data->next; + e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* @@ -1015,18 +1025,27 @@ void __init e820__reserve_setup_data(void) sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - e820__range_update(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - e820__range_update_kexec(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + if (data->type == SETUP_INDIRECT) { + len += data->len; + early_memunmap(data, sizeof(*data)); + data = early_memremap(pa_data, len); + if (!data) { + pr_warn("e820: failed to memremap indirect setup_data\n"); + return; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + e820__range_update(indirect->addr, indirect->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + e820__range_update_kexec(indirect->addr, indirect->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + } } - pa_data = data->next; - early_memunmap(data, sizeof(*data)); + pa_data = pa_next; + early_memunmap(data, len); } e820__update_table(e820_table); diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 64b6da95af98..e2e89bebcbc3 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -88,11 +88,13 @@ create_setup_data_node(struct dentry *parent, int no, static int __init create_setup_data_nodes(struct dentry *parent) { + struct setup_indirect *indirect; struct setup_data_node *node; struct setup_data *data; - int error; + u64 pa_data, pa_next; struct dentry *d; - u64 pa_data; + int error; + u32 len; int no = 0; d = debugfs_create_dir("setup_data", parent); @@ -112,12 +114,29 @@ static int __init create_setup_data_nodes(struct dentry *parent) error = -ENOMEM; goto err_dir; } + pa_next = data->next; - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - node->paddr = ((struct setup_indirect *)data->data)->addr; - node->type = ((struct setup_indirect *)data->data)->type; - node->len = ((struct setup_indirect *)data->data)->len; + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(pa_data, len, MEMREMAP_WB); + if (!data) { + kfree(node); + error = -ENOMEM; + goto err_dir; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + node->paddr = indirect->addr; + node->type = indirect->type; + node->len = indirect->len; + } else { + node->paddr = pa_data; + node->type = data->type; + node->len = data->len; + } } else { node->paddr = pa_data; node->type = data->type; @@ -125,7 +144,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) } create_setup_data_node(d, no, node); - pa_data = data->next; + pa_data = pa_next; memunmap(data); no++; diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index d0a19121c6a4..257892fcefa7 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -91,26 +91,41 @@ static int get_setup_data_paddr(int nr, u64 *paddr) static int __init get_setup_data_size(int nr, size_t *size) { - int i = 0; + u64 pa_data = boot_params.hdr.setup_data, pa_next; + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data = boot_params.hdr.setup_data; + int i = 0; + u32 len; while (pa_data) { data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; + pa_next = data->next; + if (nr == i) { - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) - *size = ((struct setup_indirect *)data->data)->len; - else + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(pa_data, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) + *size = indirect->len; + else + *size = data->len; + } else { *size = data->len; + } memunmap(data); return 0; } - pa_data = data->next; + pa_data = pa_next; memunmap(data); i++; } @@ -120,9 +135,11 @@ static int __init get_setup_data_size(int nr, size_t *size) static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { + struct setup_indirect *indirect; + struct setup_data *data; int nr, ret; u64 paddr; - struct setup_data *data; + u32 len; ret = kobj_to_setup_data_nr(kobj, &nr); if (ret) @@ -135,10 +152,20 @@ static ssize_t type_show(struct kobject *kobj, if (!data) return -ENOMEM; - if (data->type == SETUP_INDIRECT) - ret = sprintf(buf, "0x%x\n", ((struct setup_indirect *)data->data)->type); - else + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(paddr, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + ret = sprintf(buf, "0x%x\n", indirect->type); + } else { ret = sprintf(buf, "0x%x\n", data->type); + } + memunmap(data); return ret; } @@ -149,9 +176,10 @@ static ssize_t setup_data_data_read(struct file *fp, char *buf, loff_t off, size_t count) { + struct setup_indirect *indirect; + struct setup_data *data; int nr, ret = 0; u64 paddr, len; - struct setup_data *data; void *p; ret = kobj_to_setup_data_nr(kobj, &nr); @@ -165,10 +193,27 @@ static ssize_t setup_data_data_read(struct file *fp, if (!data) return -ENOMEM; - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - paddr = ((struct setup_indirect *)data->data)->addr; - len = ((struct setup_indirect *)data->data)->len; + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(paddr, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } else { + /* + * Even though this is technically undefined, return + * the data as though it is a normal setup_data struct. + * This will at least allow it to be inspected. + */ + paddr += sizeof(*data); + len = data->len; + } } else { paddr += sizeof(*data); len = data->len; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f7a132eb794d..90d7e1788c91 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -369,21 +369,41 @@ static void __init parse_setup_data(void) static void __init memblock_x86_reserve_range_setup_data(void) { + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; + u32 len; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); + if (!data) { + pr_warn("setup: failed to memremap setup_data entry\n"); + return; + } + + len = sizeof(*data); + pa_next = data->next; + memblock_reserve(pa_data, sizeof(*data) + data->len); - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) - memblock_reserve(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len); + if (data->type == SETUP_INDIRECT) { + len += data->len; + early_memunmap(data, sizeof(*data)); + data = early_memremap(pa_data, len); + if (!data) { + pr_warn("setup: failed to memremap indirect setup_data\n"); + return; + } - pa_data = data->next; - early_memunmap(data, sizeof(*data)); + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) + memblock_reserve(indirect->addr, indirect->len); + } + + pa_data = pa_next; + early_memunmap(data, len); } } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 026031b3b782..ab666c4cd357 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -615,6 +615,7 @@ static bool memremap_is_efi_data(resource_size_t phys_addr, static bool memremap_is_setup_data(resource_size_t phys_addr, unsigned long size) { + struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; @@ -627,6 +628,10 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, data = memremap(paddr, sizeof(*data), MEMREMAP_WB | MEMREMAP_DEC); + if (!data) { + pr_warn("failed to memremap setup_data entry\n"); + return false; + } paddr_next = data->next; len = data->len; @@ -636,10 +641,21 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, return true; } - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - paddr = ((struct setup_indirect *)data->data)->addr; - len = ((struct setup_indirect *)data->data)->len; + if (data->type == SETUP_INDIRECT) { + memunmap(data); + data = memremap(paddr, sizeof(*data) + len, + MEMREMAP_WB | MEMREMAP_DEC); + if (!data) { + pr_warn("failed to memremap indirect setup_data\n"); + return false; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } } memunmap(data); From 445c1470b6ef96440e7cfc42dfc160f5004fd149 Mon Sep 17 00:00:00 2001 From: Ross Philipson Date: Wed, 23 Feb 2022 21:07:36 -0500 Subject: [PATCH 03/12] x86/boot: Add setup_indirect support in early_memremap_is_setup_data() The x86 boot documentation describes the setup_indirect structures and how they are used. Only one of the two functions in ioremap.c that needed to be modified to be aware of the introduction of setup_indirect functionality was updated. Adds comparable support to the other function where it was missing. Fixes: b3c72fc9a78e ("x86/boot: Introduce setup_indirect") Signed-off-by: Ross Philipson Signed-off-by: Borislav Petkov Reviewed-by: Daniel Kiper Cc: Link: https://lore.kernel.org/r/1645668456-22036-3-git-send-email-ross.philipson@oracle.com --- arch/x86/mm/ioremap.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index ab666c4cd357..17a492c27306 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -676,22 +676,51 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, unsigned long size) { + struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; paddr = boot_params.hdr.setup_data; while (paddr) { - unsigned int len; + unsigned int len, size; if (phys_addr == paddr) return true; data = early_memremap_decrypted(paddr, sizeof(*data)); + if (!data) { + pr_warn("failed to early memremap setup_data entry\n"); + return false; + } + + size = sizeof(*data); paddr_next = data->next; len = data->len; - early_memunmap(data, sizeof(*data)); + if ((phys_addr > paddr) && (phys_addr < (paddr + len))) { + early_memunmap(data, sizeof(*data)); + return true; + } + + if (data->type == SETUP_INDIRECT) { + size += len; + early_memunmap(data, sizeof(*data)); + data = early_memremap_decrypted(paddr, size); + if (!data) { + pr_warn("failed to early memremap indirect setup_data\n"); + return false; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } + } + + early_memunmap(data, size); if ((phys_addr > paddr) && (phys_addr < (paddr + len))) return true; From a365a65f9ca1ceb9cf1ac29db4a4f51df7c507ad Mon Sep 17 00:00:00 2001 From: Li Huafei Date: Thu, 10 Mar 2022 20:09:15 +0800 Subject: [PATCH 04/12] x86/traps: Mark do_int3() NOKPROBE_SYMBOL Since kprobe_int3_handler() is called in do_int3(), probing do_int3() can cause a breakpoint recursion and crash the kernel. Therefore, do_int3() should be marked as NOKPROBE_SYMBOL. Fixes: 21e28290b317 ("x86/traps: Split int3 handler up") Signed-off-by: Li Huafei Signed-off-by: Borislav Petkov Acked-by: Masami Hiramatsu Cc: Link: https://lore.kernel.org/r/20220310120915.63349-1-lihuafei1@huawei.com --- arch/x86/kernel/traps.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c9d566dcf89a..8143693a7ea6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -659,6 +659,7 @@ static bool do_int3(struct pt_regs *regs) return res == NOTIFY_STOP; } +NOKPROBE_SYMBOL(do_int3); static void do_int3_user(struct pt_regs *regs) { From 08999b2489b4c9b939d7483dbd03702ee4576d96 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Fri, 4 Mar 2022 00:38:58 +0200 Subject: [PATCH 05/12] x86/sgx: Free backing memory after faulting the enclave page There is a limited amount of SGX memory (EPC) on each system. When that memory is used up, SGX has its own swapping mechanism which is similar in concept but totally separate from the core mm/* code. Instead of swapping to disk, SGX swaps from EPC to normal RAM. That normal RAM comes from a shared memory pseudo-file and can itself be swapped by the core mm code. There is a hierarchy like this: EPC <-> shmem <-> disk After data is swapped back in from shmem to EPC, the shmem backing storage needs to be freed. Currently, the backing shmem is not freed. This effectively wastes the shmem while the enclave is running. The memory is recovered when the enclave is destroyed and the backing storage freed. Sort this out by freeing memory with shmem_truncate_range(), as soon as a page is faulted back to the EPC. In addition, free the memory for PCMD pages as soon as all PCMD's in a page have been marked as unused by zeroing its contents. Cc: stable@vger.kernel.org Fixes: 1728ab54b4be ("x86/sgx: Add a page reclaimer") Reported-by: Dave Hansen Signed-off-by: Jarkko Sakkinen Signed-off-by: Dave Hansen Link: https://lkml.kernel.org/r/20220303223859.273187-1-jarkko@kernel.org --- arch/x86/kernel/cpu/sgx/encl.c | 57 ++++++++++++++++++++++++++++------ 1 file changed, 48 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 48afe96ae0f0..7c63a1911fae 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -12,6 +12,30 @@ #include "encls.h" #include "sgx.h" +/* + * Calculate byte offset of a PCMD struct associated with an enclave page. PCMD's + * follow right after the EPC data in the backing storage. In addition to the + * visible enclave pages, there's one extra page slot for SECS, before PCMD + * structs. + */ +static inline pgoff_t sgx_encl_get_backing_page_pcmd_offset(struct sgx_encl *encl, + unsigned long page_index) +{ + pgoff_t epc_end_off = encl->size + sizeof(struct sgx_secs); + + return epc_end_off + page_index * sizeof(struct sgx_pcmd); +} + +/* + * Free a page from the backing storage in the given page index. + */ +static inline void sgx_encl_truncate_backing_page(struct sgx_encl *encl, unsigned long page_index) +{ + struct inode *inode = file_inode(encl->backing); + + shmem_truncate_range(inode, PFN_PHYS(page_index), PFN_PHYS(page_index) + PAGE_SIZE - 1); +} + /* * ELDU: Load an EPC page as unblocked. For more info, see "OS Management of EPC * Pages" in the SDM. @@ -22,9 +46,11 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, { unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK; struct sgx_encl *encl = encl_page->encl; + pgoff_t page_index, page_pcmd_off; struct sgx_pageinfo pginfo; struct sgx_backing b; - pgoff_t page_index; + bool pcmd_page_empty; + u8 *pcmd_page; int ret; if (secs_page) @@ -32,14 +58,16 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, else page_index = PFN_DOWN(encl->size); + page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); + ret = sgx_encl_get_backing(encl, page_index, &b); if (ret) return ret; pginfo.addr = encl_page->desc & PAGE_MASK; pginfo.contents = (unsigned long)kmap_atomic(b.contents); - pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) + - b.pcmd_offset; + pcmd_page = kmap_atomic(b.pcmd); + pginfo.metadata = (unsigned long)pcmd_page + b.pcmd_offset; if (secs_page) pginfo.secs = (u64)sgx_get_epc_virt_addr(secs_page); @@ -55,11 +83,24 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, ret = -EFAULT; } - kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset)); + memset(pcmd_page + b.pcmd_offset, 0, sizeof(struct sgx_pcmd)); + + /* + * The area for the PCMD in the page was zeroed above. Check if the + * whole page is now empty meaning that all PCMD's have been zeroed: + */ + pcmd_page_empty = !memchr_inv(pcmd_page, 0, PAGE_SIZE); + + kunmap_atomic(pcmd_page); kunmap_atomic((void *)(unsigned long)pginfo.contents); sgx_encl_put_backing(&b, false); + sgx_encl_truncate_backing_page(encl, page_index); + + if (pcmd_page_empty) + sgx_encl_truncate_backing_page(encl, PFN_DOWN(page_pcmd_off)); + return ret; } @@ -579,7 +620,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { - pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5); + pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); struct page *contents; struct page *pcmd; @@ -587,7 +628,7 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, if (IS_ERR(contents)) return PTR_ERR(contents); - pcmd = sgx_encl_get_backing_page(encl, pcmd_index); + pcmd = sgx_encl_get_backing_page(encl, PFN_DOWN(page_pcmd_off)); if (IS_ERR(pcmd)) { put_page(contents); return PTR_ERR(pcmd); @@ -596,9 +637,7 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, backing->page_index = page_index; backing->contents = contents; backing->pcmd = pcmd; - backing->pcmd_offset = - (page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) * - sizeof(struct sgx_pcmd); + backing->pcmd_offset = page_pcmd_off & (PAGE_SIZE - 1); return 0; } From 3755d35ee1d2454b20b8a1e20d790e56201678a4 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 3 Feb 2022 10:39:22 +0100 Subject: [PATCH 06/12] drm/panel: Select DRM_DP_HELPER for DRM_PANEL_EDP As reported in [1], DRM_PANEL_EDP depends on DRM_DP_HELPER. Select the option to fix the build failure. The error message is shown below. arm-linux-gnueabihf-ld: drivers/gpu/drm/panel/panel-edp.o: in function `panel_edp_probe': panel-edp.c:(.text+0xb74): undefined reference to `drm_panel_dp_aux_backlight' make[1]: *** [/builds/linux/Makefile:1222: vmlinux] Error 1 The issue has been reported before, when DisplayPort helpers were hidden behind the option CONFIG_DRM_KMS_HELPER. [2] v2: * fix and expand commit description (Arnd) Signed-off-by: Thomas Zimmermann Fixes: 9d6366e743f3 ("drm: fb_helper: improve CONFIG_FB dependency") Reported-by: Naresh Kamboju Reported-by: Linux Kernel Functional Testing Reviewed-by: Lyude Paul Acked-by: Sam Ravnborg Link: https://lore.kernel.org/dri-devel/CA+G9fYvN0NyaVkRQmA1O6rX7H8PPaZrUAD7=RDy33QY9rUU-9g@mail.gmail.com/ # [1] Link: https://lore.kernel.org/all/20211117062704.14671-1-rdunlap@infradead.org/ # [2] Cc: Thomas Zimmermann Cc: Lyude Paul Cc: Daniel Vetter Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: dri-devel@lists.freedesktop.org Link: https://patchwork.freedesktop.org/patch/msgid/20220203093922.20754-1-tzimmermann@suse.de Signed-off-by: Dave Airlie --- drivers/gpu/drm/panel/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index 434c2861bb40..0aec5a10b064 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -106,6 +106,7 @@ config DRM_PANEL_EDP depends on PM select VIDEOMODE_HELPERS select DRM_DP_AUX_BUS + select DRM_DP_HELPER help DRM panel driver for dumb eDP panels that need at most a regulator and a GPIO to be powered up. Optionally a backlight can be attached so From 3ec94eeaff9ad58a76be2232068b4a2546b2f6bb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 21 Dec 2020 12:53:44 -0300 Subject: [PATCH 07/12] tools kvm headers arm64: Update KVM headers from the kernel sources To pick the changes from: a5905d6af492ee6a ("KVM: arm64: Allow SMCCC_ARCH_WORKAROUND_3 to be discovered and migrated") That don't causes any changes in tooling (when built on x86), only addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Cc: James Morse Link: https://lore.kernel.org/lkml/YiyhAK6sVPc83FaI@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/kvm.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index b3edde68bc3e..323e251ed37b 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -281,6 +281,11 @@ struct kvm_arm_copy_mte_tags { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 KVM_REG_ARM_FW_REG(3) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED 2 + /* SVE registers */ #define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) From ec9d50ace39925f7fd0302bf0fad640e2c9826ea Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 1 Jul 2021 13:39:15 -0300 Subject: [PATCH 08/12] tools headers cpufeatures: Sync with the kernel sources To pick the changes from: d45476d983240937 ("x86/speculation: Rename RETPOLINE_AMD to RETPOLINE_LFENCE") Its just a comment fixup. This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Cc: Borislav Petkov Cc: Peter Zijlstra (Intel) Link: https://lore.kernel.org/lkml/YiyiHatGaJQM7l/Y@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index ab4e53715d8a..65d147974f8d 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -204,7 +204,7 @@ /* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCEs for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ From a7a72631f62445e3671b7cab5ad01f856c1aa90d Mon Sep 17 00:00:00 2001 From: Weiguo Li Date: Fri, 11 Mar 2022 21:06:57 +0800 Subject: [PATCH 09/12] perf parse-events: Fix NULL check against wrong variable We did a null check after "tmp->symbol = strdup(...)", but we checked "list->symbol" other than "tmp->symbol". Reviewed-by: John Garry Signed-off-by: Weiguo Li Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/tencent_DF39269807EC9425E24787E6DB632441A405@qq.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9739b05b999e..dfb50a5f83d0 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2193,7 +2193,7 @@ int perf_pmu__test_parse_init(void) for (i = 0; i < ARRAY_SIZE(symbols); i++, tmp++) { tmp->type = symbols[i].type; tmp->symbol = strdup(symbols[i].symbol); - if (!list->symbol) + if (!tmp->symbol) goto err_free; } From 073a15c3512f6b8d36c0c05992cf31e845f4dfe0 Mon Sep 17 00:00:00 2001 From: Weiguo Li Date: Fri, 11 Mar 2022 21:07:16 +0800 Subject: [PATCH 10/12] perf bench: Fix NULL check against wrong variable We did a NULL check after "epollfdp = calloc(...)", but we checked "epollfd" instead of "epollfdp". Signed-off-by: Weiguo Li Acked-by: Davidlohr Bueso Cc: Alexander Shishkin Cc: Davidlohr Bueso Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/tencent_B5D64530EB9C7DBB8D2C88A0C790F1489D0A@qq.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/epoll-ctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 740ae764537e..134612bde0cb 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -106,7 +106,7 @@ static void nest_epollfd(void) printinfo("Nesting level(s): %d\n", nested); epollfdp = calloc(nested, sizeof(int)); - if (!epollfd) + if (!epollfdp) err(EXIT_FAILURE, "calloc"); for (i = 0; i < nested; i++) { From 91c9923a473a694eb1c5c01ab778a77114969707 Mon Sep 17 00:00:00 2001 From: Zhengjun Xing Date: Mon, 7 Mar 2022 23:16:27 +0800 Subject: [PATCH 11/12] perf parse: Fix event parser error for hybrid systems This bug happened on hybrid systems when both cpu_core and cpu_atom have the same event name such as "UOPS_RETIRED.MS" while their event terms are different, then during perf stat, the event for cpu_atom will parse fail and then no output for cpu_atom. UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/ UOPS_RETIRED.MS -> cpu_atom/period=0x1e8483,umask=0x1,event=0xc2/ It is because event terms in the "head" of parse_events_multi_pmu_add will be changed to event terms for cpu_core after parsing UOPS_RETIRED.MS for cpu_core, then when parsing the same event for cpu_atom, it still uses the event terms for cpu_core, but event terms for cpu_atom are different with cpu_core, the event parses for cpu_atom will fail. This patch fixes it, the event terms should be parsed from the original event. This patch can work for the hybrid systems that have the same event in more than 2 PMUs. It also can work in non-hybrid systems. Before: # perf stat -v -e UOPS_RETIRED.MS -a sleep 1 Using CPUID GenuineIntel-6-97-1 UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/ Control descriptor is not initialized UOPS_RETIRED.MS: 2737845 16068518485 16068518485 Performance counter stats for 'system wide': 2,737,845 cpu_core/UOPS_RETIRED.MS/ 1.002553850 seconds time elapsed After: # perf stat -v -e UOPS_RETIRED.MS -a sleep 1 Using CPUID GenuineIntel-6-97-1 UOPS_RETIRED.MS -> cpu_core/period=0x1e8483,umask=0x4,event=0xc2,frontend=0x8/ UOPS_RETIRED.MS -> cpu_atom/period=0x1e8483,umask=0x1,event=0xc2/ Control descriptor is not initialized UOPS_RETIRED.MS: 1977555 16076950711 16076950711 UOPS_RETIRED.MS: 568684 8038694234 8038694234 Performance counter stats for 'system wide': 1,977,555 cpu_core/UOPS_RETIRED.MS/ 568,684 cpu_atom/UOPS_RETIRED.MS/ 1.004758259 seconds time elapsed Fixes: fb0811535e92c6c1 ("perf parse-events: Allow config on kernel PMU events") Reviewed-by: Kan Liang Signed-off-by: Zhengjun Xing Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220307151627.30049-1-zhengjun.xing@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index dfb50a5f83d0..24997925ae00 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1648,6 +1648,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, { struct parse_events_term *term; struct list_head *list = NULL; + struct list_head *orig_head = NULL; struct perf_pmu *pmu = NULL; int ok = 0; char *config; @@ -1674,7 +1675,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, } list_add_tail(&term->list, head); - /* Add it for all PMUs that support the alias */ list = malloc(sizeof(struct list_head)); if (!list) @@ -1687,13 +1687,15 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, str)) { + parse_events_copy_term_list(head, &orig_head); if (!parse_events_add_pmu(parse_state, list, - pmu->name, head, + pmu->name, orig_head, true, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; } + parse_events_terms__delete(orig_head); } } } From 09688c0166e76ce2fb85e86b9d99be8b0084cdf9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Mar 2022 13:23:37 -0700 Subject: [PATCH 12/12] Linux 5.17-rc8 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 87f672473523..55a30ca69350 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Superb Owl # *DOCUMENTATION*