- Linux-stable-mirror - lists.linaro.org

[PATCH 1/1] iommu/vt-d: Optimize iotlb_sync_map for non-caching/non-RWBF modes

by Lu Baolu

The iotlb_sync_map iommu ops allows drivers to perform necessary cache flushes when new mappings are established. For the Intel iommu driver, this callback specifically serves two purposes: - To flush caches when a second-stage page table is attached to a device whose iommu is operating in caching mode (CAP_REG.CM==1). - To explicitly flush internal write buffers to ensure updates to memory- resident remapping structures are visible to hardware (CAP_REG.RWBF==1). However, in scenarios where neither caching mode nor the RWBF flag is active, the cache_tag_flush_range_np() helper, which is called in the iotlb_sync_map path, effectively becomes a no-op. Despite being a no-op, cache_tag_flush_range_np() involves iterating through all cache tags of the iommu's attached to the domain, protected by a spinlock. This unnecessary execution path introduces overhead, leading to a measurable I/O performance regression. On systems with NVMes under the same bridge, performance was observed to drop from approximately ~6150 MiB/s down to ~4985 MiB/s. Introduce a flag in the dmar_domain structure. This flag will only be set when iotlb_sync_map is required (i.e., when CM or RWBF is set). The cache_tag_flush_range_np() is called only for domains where this flag is set. Reported-by: Ioanna Alifieraki <ioanna-maria.alifieraki(a)canonical.com> Closes: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2115738 Link: https://lore.kernel.org/r/20250701171154.52435-1-ioanna-maria.alifieraki@ca… Fixes: 129dab6e1286 ("iommu/vt-d: Use cache_tag_flush_range_np() in iotlb_sync_map") Cc: stable(a)vger.kernel.org Signed-off-by: Lu Baolu <baolu.lu(a)linux.intel.com> --- drivers/iommu/intel/iommu.c | 19 ++++++++++++++++++- drivers/iommu/intel/iommu.h | 3 +++ 2 files changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7aa3932251b2..f60201ee4be0 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1796,6 +1796,18 @@ static int domain_setup_first_level(struct intel_iommu *iommu, (pgd_t *)pgd, flags, old); } +static bool domain_need_iotlb_sync_map(struct dmar_domain *domain, + struct intel_iommu *iommu) +{ + if (cap_caching_mode(iommu->cap) && !domain->use_first_level) + return true; + + if (rwbf_quirk || cap_rwbf(iommu->cap)) + return true; + + return false; +} + static int dmar_domain_attach_device(struct dmar_domain *domain, struct device *dev) { @@ -1833,6 +1845,8 @@ static int dmar_domain_attach_device(struct dmar_domain *domain, if (ret) goto out_block_translation; + domain->iotlb_sync_map |= domain_need_iotlb_sync_map(domain, iommu); + return 0; out_block_translation: @@ -3945,7 +3959,10 @@ static bool risky_device(struct pci_dev *pdev) static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain, unsigned long iova, size_t size) { - cache_tag_flush_range_np(to_dmar_domain(domain), iova, iova + size - 1); + struct dmar_domain *dmar_domain = to_dmar_domain(domain); + + if (dmar_domain->iotlb_sync_map) + cache_tag_flush_range_np(dmar_domain, iova, iova + size - 1); return 0; } diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 3ddbcc603de2..7ab2c34a5ecc 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -614,6 +614,9 @@ struct dmar_domain { u8 has_mappings:1; /* Has mappings configured through * iommu_map() interface. */ + u8 iotlb_sync_map:1; /* Need to flush IOTLB cache or write + * buffer when creating mappings. + */ spinlock_t lock; /* Protect device tracking lists */ struct list_head devices; /* all devices' list */ -- 2.43.0

1 week, 2 days

3
2
0 0

+ mm-damon-fix-divide-by-zero-in-damon_get_intervals_score.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon: fix divide by zero in damon_get_intervals_score() has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-fix-divide-by-zero-in-damon_get_intervals_score.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Honggyu Kim <honggyu.kim(a)sk.com> Subject: mm/damon: fix divide by zero in damon_get_intervals_score() Date: Wed, 2 Jul 2025 09:02:04 +0900 The current implementation allows having zero size regions with no special reasons, but damon_get_intervals_score() gets crashed by divide by zero when the region size is zero. [ 29.403950] Oops: divide error: 0000 [#1] SMP NOPTI This patch fixes the bug, but does not disallow zero size regions to keep the backward compatibility since disallowing zero size regions might be a breaking change for some users. In addition, the same crash can happen when intervals_goal.access_bp is zero so this should be fixed in stable trees as well. Link: https://lkml.kernel.org/r/20250702000205.1921-5-honggyu.kim@sk.com Fixes: f04b0fedbe71 ("mm/damon/core: implement intervals auto-tuning") Signed-off-by: Honggyu Kim <honggyu.kim(a)sk.com> Reviewed-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/core.c | 1 + 1 file changed, 1 insertion(+) --- a/mm/damon/core.c~mm-damon-fix-divide-by-zero-in-damon_get_intervals_score +++ a/mm/damon/core.c @@ -1449,6 +1449,7 @@ static unsigned long damon_get_intervals } } target_access_events = max_access_events * goal_bp / 10000; + target_access_events = target_access_events ? : 1; return access_events * 10000 / target_access_events; } _ Patches currently in -mm which might be from honggyu.kim(a)sk.com are samples-damon-fix-damon-sample-prcl-for-start-failure.patch samples-damon-fix-damon-sample-wsse-for-start-failure.patch samples-damon-fix-damon-sample-mtier-for-start-failure.patch mm-damon-fix-divide-by-zero-in-damon_get_intervals_score.patch

1 week, 2 days

1
0
0 0

+ samples-damon-fix-damon-sample-mtier-for-start-failure.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: samples/damon: fix damon sample mtier for start failure has been added to the -mm mm-hotfixes-unstable branch. Its filename is samples-damon-fix-damon-sample-mtier-for-start-failure.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Honggyu Kim <honggyu.kim(a)sk.com> Subject: samples/damon: fix damon sample mtier for start failure Date: Wed, 2 Jul 2025 09:02:03 +0900 The damon_sample_mtier_start() can fail so we must reset the "enable" parameter to "false" again for proper rollback. In such cases, setting Y to "enable" then N triggers the similar crash with mtier because damon sample start failed but the "enable" stays as Y. Link: https://lkml.kernel.org/r/20250702000205.1921-4-honggyu.kim@sk.com Fixes: 82a08bde3cf7 ("samples/damon: implement a DAMON module for memory tiering") Signed-off-by: Honggyu Kim <honggyu.kim(a)sk.com> Reviewed-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- samples/damon/mtier.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) --- a/samples/damon/mtier.c~samples-damon-fix-damon-sample-mtier-for-start-failure +++ a/samples/damon/mtier.c @@ -164,8 +164,12 @@ static int damon_sample_mtier_enable_sto if (enable == enabled) return 0; - if (enable) - return damon_sample_mtier_start(); + if (enable) { + err = damon_sample_mtier_start(); + if (err) + enable = false; + return err; + } damon_sample_mtier_stop(); return 0; } _ Patches currently in -mm which might be from honggyu.kim(a)sk.com are samples-damon-fix-damon-sample-prcl-for-start-failure.patch samples-damon-fix-damon-sample-wsse-for-start-failure.patch samples-damon-fix-damon-sample-mtier-for-start-failure.patch mm-damon-fix-divide-by-zero-in-damon_get_intervals_score.patch

1 week, 2 days

1
0
0 0

+ samples-damon-fix-damon-sample-wsse-for-start-failure.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: samples/damon: fix damon sample wsse for start failure has been added to the -mm mm-hotfixes-unstable branch. Its filename is samples-damon-fix-damon-sample-wsse-for-start-failure.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Honggyu Kim <honggyu.kim(a)sk.com> Subject: samples/damon: fix damon sample wsse for start failure Date: Wed, 2 Jul 2025 09:02:02 +0900 The damon_sample_wsse_start() can fail so we must reset the "enable" parameter to "false" again for proper rollback. In such cases, setting Y to "enable" then N triggers the similar crash with wsse because damon sample start failed but the "enable" stays as Y. Link: https://lkml.kernel.org/r/20250702000205.1921-3-honggyu.kim@sk.com Fixes: b757c6cfc696 ("samples/damon/wsse: start and stop DAMON as the user requests") Signed-off-by: Honggyu Kim <honggyu.kim(a)sk.com> Reviewed-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- samples/damon/wsse.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) --- a/samples/damon/wsse.c~samples-damon-fix-damon-sample-wsse-for-start-failure +++ a/samples/damon/wsse.c @@ -102,8 +102,12 @@ static int damon_sample_wsse_enable_stor if (enable == enabled) return 0; - if (enable) - return damon_sample_wsse_start(); + if (enable) { + err = damon_sample_wsse_start(); + if (err) + enable = false; + return err; + } damon_sample_wsse_stop(); return 0; } _ Patches currently in -mm which might be from honggyu.kim(a)sk.com are samples-damon-fix-damon-sample-prcl-for-start-failure.patch samples-damon-fix-damon-sample-wsse-for-start-failure.patch samples-damon-fix-damon-sample-mtier-for-start-failure.patch mm-damon-fix-divide-by-zero-in-damon_get_intervals_score.patch

1 week, 2 days

1
0
0 0

+ samples-damon-fix-damon-sample-prcl-for-start-failure.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: samples/damon: fix damon sample prcl for start failure has been added to the -mm mm-hotfixes-unstable branch. Its filename is samples-damon-fix-damon-sample-prcl-for-start-failure.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Honggyu Kim <honggyu.kim(a)sk.com> Subject: samples/damon: fix damon sample prcl for start failure Date: Wed, 2 Jul 2025 09:02:01 +0900 Patch series "mm/damon: fix divide by zero and its samples", v3. This series includes fixes against damon and its samples to make it safer when damon sample starting fails. It includes the following changes. - fix unexpected divide by zero crash for zero size regions - fix bugs for damon samples in case of start failures This patch (of 4): The damon_sample_prcl_start() can fail so we must reset the "enable" parameter to "false" again for proper rollback. In such cases, setting Y to "enable" then N triggers the following crash because damon sample start failed but the "enable" stays as Y. [ 2441.419649] damon_sample_prcl: start [ 2454.146817] damon_sample_prcl: stop [ 2454.146862] ------------[ cut here ]------------ [ 2454.146865] kernel BUG at mm/slub.c:546! [ 2454.148183] Oops: invalid opcode: 0000 [#1] SMP NOPTI ... [ 2454.167555] Call Trace: [ 2454.167822] <TASK> [ 2454.168061] damon_destroy_ctx+0x78/0x140 [ 2454.168454] damon_sample_prcl_enable_store+0x8d/0xd0 [ 2454.168932] param_attr_store+0xa1/0x120 [ 2454.169315] module_attr_store+0x20/0x50 [ 2454.169695] sysfs_kf_write+0x72/0x90 [ 2454.170065] kernfs_fop_write_iter+0x150/0x1e0 [ 2454.170491] vfs_write+0x315/0x440 [ 2454.170833] ksys_write+0x69/0xf0 [ 2454.171162] __x64_sys_write+0x19/0x30 [ 2454.171525] x64_sys_call+0x18b2/0x2700 [ 2454.171900] do_syscall_64+0x7f/0x680 [ 2454.172258] ? exit_to_user_mode_loop+0xf6/0x180 [ 2454.172694] ? clear_bhb_loop+0x30/0x80 [ 2454.173067] ? clear_bhb_loop+0x30/0x80 [ 2454.173439] entry_SYSCALL_64_after_hwframe+0x76/0x7e Link: https://lkml.kernel.org/r/20250702000205.1921-1-honggyu.kim@sk.com Link: https://lkml.kernel.org/r/20250702000205.1921-2-honggyu.kim@sk.com Fixes: 2aca254620a8 ("samples/damon: introduce a skeleton of a smaple DAMON module for proactive reclamation") Signed-off-by: Honggyu Kim <honggyu.kim(a)sk.com> Reviewed-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- samples/damon/prcl.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) --- a/samples/damon/prcl.c~samples-damon-fix-damon-sample-prcl-for-start-failure +++ a/samples/damon/prcl.c @@ -122,8 +122,12 @@ static int damon_sample_prcl_enable_stor if (enable == enabled) return 0; - if (enable) - return damon_sample_prcl_start(); + if (enable) { + err = damon_sample_prcl_start(); + if (err) + enable = false; + return err; + } damon_sample_prcl_stop(); return 0; } _ Patches currently in -mm which might be from honggyu.kim(a)sk.com are samples-damon-fix-damon-sample-prcl-for-start-failure.patch samples-damon-fix-damon-sample-wsse-for-start-failure.patch samples-damon-fix-damon-sample-mtier-for-start-failure.patch mm-damon-fix-divide-by-zero-in-damon_get_intervals_score.patch

1 week, 2 days

1
0
0 0

[PATCH] drm/nouveau: Do not fail module init on debugfs errors

by Aaron Thompson

From: Aaron Thompson <dev(a)aaront.org> If CONFIG_DEBUG_FS is enabled, nouveau_drm_init() returns an error if it fails to create the "nouveau" directory in debugfs. One case where that will happen is when debugfs access is restricted by CONFIG_DEBUG_FS_ALLOW_NONE or by the boot parameter debugfs=off, which cause the debugfs APIs to return -EPERM. So just ignore errors from debugfs. Note that nouveau_debugfs_root may be an error now, but that is a standard pattern for debugfs. From include/linux/debugfs.h: "NOTE: it's expected that most callers should _ignore_ the errors returned by this function. Other debugfs functions handle the fact that the "dentry" passed to them could be an error and they don't crash in that case. Drivers should generally work fine even if debugfs fails to init anyway." Fixes: 97118a1816d2 ("drm/nouveau: create module debugfs root") Cc: stable(a)vger.kernel.org Signed-off-by: Aaron Thompson <dev(a)aaront.org> --- drivers/gpu/drm/nouveau/nouveau_debugfs.c | 6 +----- drivers/gpu/drm/nouveau/nouveau_debugfs.h | 5 ++--- drivers/gpu/drm/nouveau/nouveau_drm.c | 4 +--- 3 files changed, 4 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c index 200e65a7cefc..c7869a639bef 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c @@ -314,14 +314,10 @@ nouveau_debugfs_fini(struct nouveau_drm *drm) drm->debugfs = NULL; } -int +void nouveau_module_debugfs_init(void) { nouveau_debugfs_root = debugfs_create_dir("nouveau", NULL); - if (IS_ERR(nouveau_debugfs_root)) - return PTR_ERR(nouveau_debugfs_root); - - return 0; } void diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.h b/drivers/gpu/drm/nouveau/nouveau_debugfs.h index b7617b344ee2..d05ed0e641c4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.h +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.h @@ -24,7 +24,7 @@ extern void nouveau_debugfs_fini(struct nouveau_drm *); extern struct dentry *nouveau_debugfs_root; -int nouveau_module_debugfs_init(void); +void nouveau_module_debugfs_init(void); void nouveau_module_debugfs_fini(void); #else static inline void @@ -42,10 +42,9 @@ nouveau_debugfs_fini(struct nouveau_drm *drm) { } -static inline int +static inline void nouveau_module_debugfs_init(void) { - return 0; } static inline void diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 0c82a63cd49d..1527b801f013 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1461,9 +1461,7 @@ nouveau_drm_init(void) if (!nouveau_modeset) return 0; - ret = nouveau_module_debugfs_init(); - if (ret) - return ret; + nouveau_module_debugfs_init(); #ifdef CONFIG_NOUVEAU_PLATFORM_DRIVER platform_driver_register(&nouveau_platform_driver); base-commit: d0b3b7b22dfa1f4b515fd3a295b3fd958f9e81af -- 2.39.5

1 week, 2 days

3
2
0 0

[PATCH v6 01/12] platform/x86/intel/pmt: fix a crashlog NULL pointer access

by Michael J. Ruhl

Usage of the intel_pmt_read() for binary sysfs, requires a pcidev. The current use of the endpoint value is only valid for telemetry endpoint usage. Without the ep, the crashlog usage causes the following NULL pointer exception: BUG: kernel NULL pointer dereference, address: 0000000000000000 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:intel_pmt_read+0x3b/0x70 [pmt_class] Code: Call Trace: <TASK> ? sysfs_kf_bin_read+0xc0/0xe0 kernfs_fop_read_iter+0xac/0x1a0 vfs_read+0x26d/0x350 ksys_read+0x6b/0xe0 __x64_sys_read+0x1d/0x30 x64_sys_call+0x1bc8/0x1d70 do_syscall_64+0x6d/0x110 Augment struct intel_pmt_entry with a pointer to the pcidev to avoid the NULL pointer exception. Reviewed-by: Tejas Upadhyay <tejas.upadhyay(a)intel.com> Fixes: 045a513040cc ("platform/x86/intel/pmt: Use PMT callbacks") Cc: <stable(a)vger.kernel.org> Signed-off-by: Michael J. Ruhl <michael.j.ruhl(a)intel.com> --- drivers/platform/x86/intel/pmt/class.c | 3 ++- drivers/platform/x86/intel/pmt/class.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c index 7233b654bbad..d046e8752173 100644 --- a/drivers/platform/x86/intel/pmt/class.c +++ b/drivers/platform/x86/intel/pmt/class.c @@ -97,7 +97,7 @@ intel_pmt_read(struct file *filp, struct kobject *kobj, if (count > entry->size - off) count = entry->size - off; - count = pmt_telem_read_mmio(entry->ep->pcidev, entry->cb, entry->header.guid, buf, + count = pmt_telem_read_mmio(entry->pcidev, entry->cb, entry->header.guid, buf, entry->base, off, count); return count; @@ -252,6 +252,7 @@ static int intel_pmt_populate_entry(struct intel_pmt_entry *entry, return -EINVAL; } + entry->pcidev = pci_dev; entry->guid = header->guid; entry->size = header->size; entry->cb = ivdev->priv_data; diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h index b2006d57779d..f6ce80c4e051 100644 --- a/drivers/platform/x86/intel/pmt/class.h +++ b/drivers/platform/x86/intel/pmt/class.h @@ -39,6 +39,7 @@ struct intel_pmt_header { struct intel_pmt_entry { struct telem_endpoint *ep; + struct pci_dev *pcidev; struct intel_pmt_header header; struct bin_attribute pmt_bin_attr; struct kobject *kobj; -- 2.49.0

1 week, 2 days

1
0
0 0

+ kasan-remove-kasan_find_vm_area-to-prevent-possible-deadlock.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: kasan: remove kasan_find_vm_area() to prevent possible deadlock has been added to the -mm mm-hotfixes-unstable branch. Its filename is kasan-remove-kasan_find_vm_area-to-prevent-possible-deadlock.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Yeoreum Yun <yeoreum.yun(a)arm.com> Subject: kasan: remove kasan_find_vm_area() to prevent possible deadlock Date: Thu, 3 Jul 2025 19:10:18 +0100 find_vm_area() couldn't be called in atomic_context. If find_vm_area() is called to reports vm area information, kasan can trigger deadlock like: CPU0 CPU1 vmalloc(); alloc_vmap_area(); spin_lock(&vn->busy.lock) spin_lock_bh(&some_lock); <interrupt occurs> <in softirq> spin_lock(&some_lock); <access invalid address> kasan_report(); print_report(); print_address_description(); kasan_find_vm_area(); find_vm_area(); spin_lock(&vn->busy.lock) // deadlock! To prevent possible deadlock while kasan reports, remove kasan_find_vm_area(). Link: https://lkml.kernel.org/r/20250703181018.580833-1-yeoreum.yun@arm.com Fixes: c056a364e954 ("kasan: print virtual mapping info in reports") Signed-off-by: Yeoreum Yun <yeoreum.yun(a)arm.com> Reported-by: Yunseong Kim <ysk(a)kzalloc.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Andrey Konovalov <andreyknvl(a)gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Cc: Byungchul Park <byungchul(a)sk.com> Cc: Dmitriy Vyukov <dvyukov(a)google.com> Cc: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kasan/report.c | 45 +------------------------------------------- 1 file changed, 2 insertions(+), 43 deletions(-) --- a/mm/kasan/report.c~kasan-remove-kasan_find_vm_area-to-prevent-possible-deadlock +++ a/mm/kasan/report.c @@ -370,36 +370,6 @@ static inline bool init_task_stack_addr( sizeof(init_thread_union.stack)); } -/* - * This function is invoked with report_lock (a raw_spinlock) held. A - * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping - * rt_spinlock. - * - * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a - * lockdep warning for this raw_spinlock -> spinlock dependency. This config - * option is enabled by default to ensure better test coverage to expose this - * kind of RT kernel problem. This lockdep splat, however, can be suppressed - * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the - * invalid PREEMPT_RT case has been taken care of. - */ -static inline struct vm_struct *kasan_find_vm_area(void *addr) -{ - static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP); - struct vm_struct *va; - - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - return NULL; - - /* - * Suppress lockdep warning and fetch vmalloc area of the - * offending address. - */ - lock_map_acquire_try(&vmalloc_map); - va = find_vm_area(addr); - lock_map_release(&vmalloc_map); - return va; -} - static void print_address_description(void *addr, u8 tag, struct kasan_report_info *info) { @@ -429,19 +399,8 @@ static void print_address_description(vo } if (is_vmalloc_addr(addr)) { - struct vm_struct *va = kasan_find_vm_area(addr); - - if (va) { - pr_err("The buggy address belongs to the virtual mapping at\n" - " [%px, %px) created by:\n" - " %pS\n", - va->addr, va->addr + va->size, va->caller); - pr_err("\n"); - - page = vmalloc_to_page(addr); - } else { - pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); - } + pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); + page = vmalloc_to_page(addr); } if (page) { _ Patches currently in -mm which might be from yeoreum.yun(a)arm.com are kasan-remove-kasan_find_vm_area-to-prevent-possible-deadlock.patch

1 week, 2 days

1
0
0 0

[PATCH 6.12.y 0/3] r8169: add support for RTL8125D

by mathieu.tortuyaux＠gmail.com

From: Mathieu Tortuyaux <mtortuyaux(a)microsoft.com> Hi, This backports support for Realtek device 0x688 on Kernel 6.12.y: * Tested in Flatcar CI w/ Kernel 6.12.35 on qemu (for regression): https://github.com/flatcar/scripts/pull/3006 * The user requesting this support has confirmed correct behavior: https://github.com/flatcar/Flatcar/issues/1749#issuecomment-3005483988 The two other commits ("net: phy: realtek: merge the drivers for internal NBase-T PHY's" and "net: phy: realtek: add RTL8125D-internal PHY") are required to add support here as well, otherwise it fails with: ``` $ dmesg ... r8169 ... : no dedicated PHY driver found for PHY ID 0x001cc841 ... ``` Thanks and have a great day, Mathieu (@tormath1) Heiner Kallweit (3): r8169: add support for RTL8125D net: phy: realtek: merge the drivers for internal NBase-T PHY's net: phy: realtek: add RTL8125D-internal PHY drivers/net/ethernet/realtek/r8169.h | 1 + drivers/net/ethernet/realtek/r8169_main.c | 23 +++++--- .../net/ethernet/realtek/r8169_phy_config.c | 10 ++++ drivers/net/phy/realtek.c | 54 +++++++++++++++---- 4 files changed, 71 insertions(+), 17 deletions(-) -- 2.49.0

1 week, 2 days

3
14
0 0

[PATCH 6.12.y] mm/vmalloc: fix data race in show_numa_info()

by Jeongjun Park

commit 5c5f0468d172ddec2e333d738d2a1f85402cf0bc upstream. The following data-race was found in show_numa_info(): ================================================================== BUG: KCSAN: data-race in vmalloc_info_show / vmalloc_info_show read to 0xffff88800971fe30 of 4 bytes by task 8289 on cpu 0: show_numa_info mm/vmalloc.c:4936 [inline] vmalloc_info_show+0x5a8/0x7e0 mm/vmalloc.c:5016 seq_read_iter+0x373/0xb40 fs/seq_file.c:230 proc_reg_read_iter+0x11e/0x170 fs/proc/inode.c:299 .... write to 0xffff88800971fe30 of 4 bytes by task 8287 on cpu 1: show_numa_info mm/vmalloc.c:4934 [inline] vmalloc_info_show+0x38f/0x7e0 mm/vmalloc.c:5016 seq_read_iter+0x373/0xb40 fs/seq_file.c:230 proc_reg_read_iter+0x11e/0x170 fs/proc/inode.c:299 .... value changed: 0x0000008f -> 0x00000000 ================================================================== According to this report,there is a read/write data-race because m->private is accessible to multiple CPUs. To fix this, instead of allocating the heap in proc_vmalloc_init() and passing the heap address to m->private, vmalloc_info_show() should allocate the heap. Link: https://lkml.kernel.org/r/20250508165620.15321-1-aha310510@gmail.com Fixes: 8e1d743 ("mm: vmalloc: support multiple nodes in vmallocinfo") Signed-off-by: Jeongjun Park <aha310510(a)gmail.com> Suggested-by: Eric Dumazet <edumazet(a)google.com> Suggested-by: Andrew Morton <akpm(a)linux-foundation.org> Reviewed-by: "Uladzislau Rezki (Sony)" <urezki(a)gmail.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmalloc.c | 63 +++++++++++++++++++++++++++++----------------------- 1 file changed, 35 insertions(+), 28 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index cc04e501b1c5..7888600b6a79 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3095,7 +3095,7 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm) /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. - * Pair with smp_rmb() in show_numa_info(). + * Pair with smp_rmb() in vread_iter() and vmalloc_info_show(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; @@ -4938,28 +4938,29 @@ bool vmalloc_dump_obj(void *object) #endif #ifdef CONFIG_PROC_FS -static void show_numa_info(struct seq_file *m, struct vm_struct *v) -{ - if (IS_ENABLED(CONFIG_NUMA)) { - unsigned int nr, *counters = m->private; - unsigned int step = 1U << vm_area_page_order(v); - if (!counters) - return; +/* + * Print number of pages allocated on each memory node. + * + * This function can only be called if CONFIG_NUMA is enabled + * and VM_UNINITIALIZED bit in v->flags is disabled. + */ +static void show_numa_info(struct seq_file *m, struct vm_struct *v, + unsigned int *counters) +{ + unsigned int nr; + unsigned int step = 1U << vm_area_page_order(v); - if (v->flags & VM_UNINITIALIZED) - return; - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ - smp_rmb(); + if (!counters) + return; - memset(counters, 0, nr_node_ids * sizeof(unsigned int)); + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); - for (nr = 0; nr < v->nr_pages; nr += step) - counters[page_to_nid(v->pages[nr])] += step; - for_each_node_state(nr, N_HIGH_MEMORY) - if (counters[nr]) - seq_printf(m, " N%u=%u", nr, counters[nr]); - } + for (nr = 0; nr < v->nr_pages; nr += step) + counters[page_to_nid(v->pages[nr])] += step; + for_each_node_state(nr, N_HIGH_MEMORY) + if (counters[nr]) + seq_printf(m, " N%u=%u", nr, counters[nr]); } static void show_purge_info(struct seq_file *m) @@ -4987,6 +4988,10 @@ static int vmalloc_info_show(struct seq_file *m, void *p) struct vmap_area *va; struct vm_struct *v; int i; + unsigned int *counters; + + if (IS_ENABLED(CONFIG_NUMA)) + counters = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; @@ -5003,6 +5008,11 @@ static int vmalloc_info_show(struct seq_file *m, void *p) } v = va->vm; + if (v->flags & VM_UNINITIALIZED) + continue; + + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); @@ -5037,7 +5047,9 @@ static int vmalloc_info_show(struct seq_file *m, void *p) if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); - show_numa_info(m, v); + if (IS_ENABLED(CONFIG_NUMA)) + show_numa_info(m, v, counters); + seq_putc(m, '\n'); } spin_unlock(&vn->busy.lock); @@ -5047,19 +5059,14 @@ static int vmalloc_info_show(struct seq_file *m, void *p) * As a final step, dump "unpurged" areas. */ show_purge_info(m); + if (IS_ENABLED(CONFIG_NUMA)) + kfree(counters); return 0; } static int __init proc_vmalloc_init(void) { - void *priv_data = NULL; - - if (IS_ENABLED(CONFIG_NUMA)) - priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); - - proc_create_single_data("vmallocinfo", - 0400, NULL, vmalloc_info_show, priv_data); - + proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); return 0; } module_init(proc_vmalloc_init); --

1 week, 2 days

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror