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

[PATCH V3] mm/slab: introduce kvfree_rcu_barrier_on_cache() for cache destruction

by Harry Yoo

Currently, kvfree_rcu_barrier() flushes RCU sheaves across all slab caches when a cache is destroyed. This is unnecessary; only the RCU sheaves belonging to the cache being destroyed need to be flushed. As suggested by Vlastimil Babka, introduce a weaker form of kvfree_rcu_barrier() that operates on a specific slab cache. Factor out flush_rcu_sheaves_on_cache() from flush_all_rcu_sheaves() and call it from flush_all_rcu_sheaves() and kvfree_rcu_barrier_on_cache(). Call kvfree_rcu_barrier_on_cache() instead of kvfree_rcu_barrier() on cache destruction. The performance benefit is evaluated on a 12 core 24 threads AMD Ryzen 5900X machine (1 socket), by loading slub_kunit module. Before: Total calls: 19 Average latency (us): 18127 Total time (us): 344414 After: Total calls: 19 Average latency (us): 10066 Total time (us): 191264 Two performance regression have been reported: - stress module loader test's runtime increases by 50-60% (Daniel) - internal graphics test's runtime on Tegra23 increases by 35% (Jon) They are fixed by this change. Suggested-by: Vlastimil Babka <vbabka(a)suse.cz> Fixes: ec66e0d59952 ("slab: add sheaf support for batching kfree_rcu() operations") Cc: <stable(a)vger.kernel.org> Link: https://lore.kernel.org/linux-mm/1bda09da-93be-4737-aef0-d47f8c5c9301@suse.… Reported-and-tested-by: Daniel Gomez <da.gomez(a)samsung.com> Closes: https://lore.kernel.org/linux-mm/0406562e-2066-4cf8-9902-b2b0616dd742@kerne… Reported-and-tested-by: Jon Hunter <jonathanh(a)nvidia.com> Closes: https://lore.kernel.org/linux-mm/e988eff6-1287-425e-a06c-805af5bbf262@nvidi… Signed-off-by: Harry Yoo <harry.yoo(a)oracle.com> --- v2 -> v3: - Addressed Suren's comment [1], thanks! [1] https://lore.kernel.org/linux-mm/CAJuCfpE+g65Dm8-r=psDJQf_O1rfBG62DOzx4mE1m… include/linux/slab.h | 7 ++++++ mm/slab.h | 1 + mm/slab_common.c | 52 +++++++++++++++++++++++++++++------------ mm/slub.c | 55 ++++++++++++++++++++++++-------------------- 4 files changed, 75 insertions(+), 40 deletions(-) diff --git a/include/linux/slab.h b/include/linux/slab.h index cf443f064a66..2482992248dc 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -1150,10 +1150,17 @@ static inline void kvfree_rcu_barrier(void) rcu_barrier(); } +static inline void kvfree_rcu_barrier_on_cache(struct kmem_cache *s) +{ + rcu_barrier(); +} + static inline void kfree_rcu_scheduler_running(void) { } #else void kvfree_rcu_barrier(void); +void kvfree_rcu_barrier_on_cache(struct kmem_cache *s); + void kfree_rcu_scheduler_running(void); #endif diff --git a/mm/slab.h b/mm/slab.h index f730e012553c..e767aa7e91b0 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -422,6 +422,7 @@ static inline bool is_kmalloc_normal(struct kmem_cache *s) bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj); void flush_all_rcu_sheaves(void); +void flush_rcu_sheaves_on_cache(struct kmem_cache *s); #define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \ SLAB_CACHE_DMA32 | SLAB_PANIC | \ diff --git a/mm/slab_common.c b/mm/slab_common.c index 84dfff4f7b1f..dd8a49d6f9cc 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -492,7 +492,7 @@ void kmem_cache_destroy(struct kmem_cache *s) return; /* in-flight kfree_rcu()'s may include objects from our cache */ - kvfree_rcu_barrier(); + kvfree_rcu_barrier_on_cache(s); if (IS_ENABLED(CONFIG_SLUB_RCU_DEBUG) && (s->flags & SLAB_TYPESAFE_BY_RCU)) { @@ -2038,25 +2038,13 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr) } EXPORT_SYMBOL_GPL(kvfree_call_rcu); -/** - * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete. - * - * Note that a single argument of kvfree_rcu() call has a slow path that - * triggers synchronize_rcu() following by freeing a pointer. It is done - * before the return from the function. Therefore for any single-argument - * call that will result in a kfree() to a cache that is to be destroyed - * during module exit, it is developer's responsibility to ensure that all - * such calls have returned before the call to kmem_cache_destroy(). - */ -void kvfree_rcu_barrier(void) +static inline void __kvfree_rcu_barrier(void) { struct kfree_rcu_cpu_work *krwp; struct kfree_rcu_cpu *krcp; bool queued; int i, cpu; - flush_all_rcu_sheaves(); - /* * Firstly we detach objects and queue them over an RCU-batch * for all CPUs. Finally queued works are flushed for each CPU. @@ -2118,8 +2106,43 @@ void kvfree_rcu_barrier(void) } } } + +/** + * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete. + * + * Note that a single argument of kvfree_rcu() call has a slow path that + * triggers synchronize_rcu() following by freeing a pointer. It is done + * before the return from the function. Therefore for any single-argument + * call that will result in a kfree() to a cache that is to be destroyed + * during module exit, it is developer's responsibility to ensure that all + * such calls have returned before the call to kmem_cache_destroy(). + */ +void kvfree_rcu_barrier(void) +{ + flush_all_rcu_sheaves(); + __kvfree_rcu_barrier(); +} EXPORT_SYMBOL_GPL(kvfree_rcu_barrier); +/** + * kvfree_rcu_barrier_on_cache - Wait for in-flight kvfree_rcu() calls on a + * specific slab cache. + * @s: slab cache to wait for + * + * See the description of kvfree_rcu_barrier() for details. + */ +void kvfree_rcu_barrier_on_cache(struct kmem_cache *s) +{ + if (s->cpu_sheaves) + flush_rcu_sheaves_on_cache(s); + /* + * TODO: Introduce a version of __kvfree_rcu_barrier() that works + * on a specific slab cache. + */ + __kvfree_rcu_barrier(); +} +EXPORT_SYMBOL_GPL(kvfree_rcu_barrier_on_cache); + static unsigned long kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { @@ -2215,4 +2238,3 @@ void __init kvfree_rcu_init(void) } #endif /* CONFIG_KVFREE_RCU_BATCHED */ - diff --git a/mm/slub.c b/mm/slub.c index 785e25a14999..7cec2220712b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4118,42 +4118,47 @@ static void flush_rcu_sheaf(struct work_struct *w) /* needed for kvfree_rcu_barrier() */ -void flush_all_rcu_sheaves(void) +void flush_rcu_sheaves_on_cache(struct kmem_cache *s) { struct slub_flush_work *sfw; - struct kmem_cache *s; unsigned int cpu; - cpus_read_lock(); - mutex_lock(&slab_mutex); + mutex_lock(&flush_lock); - list_for_each_entry(s, &slab_caches, list) { - if (!s->cpu_sheaves) - continue; + for_each_online_cpu(cpu) { + sfw = &per_cpu(slub_flush, cpu); - mutex_lock(&flush_lock); + /* + * we don't check if rcu_free sheaf exists - racing + * __kfree_rcu_sheaf() might have just removed it. + * by executing flush_rcu_sheaf() on the cpu we make + * sure the __kfree_rcu_sheaf() finished its call_rcu() + */ - for_each_online_cpu(cpu) { - sfw = &per_cpu(slub_flush, cpu); + INIT_WORK(&sfw->work, flush_rcu_sheaf); + sfw->s = s; + queue_work_on(cpu, flushwq, &sfw->work); + } - /* - * we don't check if rcu_free sheaf exists - racing - * __kfree_rcu_sheaf() might have just removed it. - * by executing flush_rcu_sheaf() on the cpu we make - * sure the __kfree_rcu_sheaf() finished its call_rcu() - */ + for_each_online_cpu(cpu) { + sfw = &per_cpu(slub_flush, cpu); + flush_work(&sfw->work); + } - INIT_WORK(&sfw->work, flush_rcu_sheaf); - sfw->s = s; - queue_work_on(cpu, flushwq, &sfw->work); - } + mutex_unlock(&flush_lock); +} - for_each_online_cpu(cpu) { - sfw = &per_cpu(slub_flush, cpu); - flush_work(&sfw->work); - } +void flush_all_rcu_sheaves(void) +{ + struct kmem_cache *s; + + cpus_read_lock(); + mutex_lock(&slab_mutex); - mutex_unlock(&flush_lock); + list_for_each_entry(s, &slab_caches, list) { + if (!s->cpu_sheaves) + continue; + flush_rcu_sheaves_on_cache(s); } mutex_unlock(&slab_mutex); -- 2.43.0

2 days, 7 hours

2
1
0 0

[PATCH] ceph: Drop the string reference in __ceph_pool_perm_get()

by Haoxiang Li

After calling ceph_get_string(), ceph_put_string() is required to drop the reference in error paths. Fixes: 779fe0fb8e18 ("ceph: rados pool namespace support") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <lihaoxiang(a)isrc.iscas.ac.cn> --- fs/ceph/addr.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 322ed268f14a..690a54b4c316 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -2440,13 +2440,13 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, err = ceph_osdc_alloc_messages(rd_req, GFP_NOFS); if (err) - goto out_unlock; + goto put_string; wr_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL, 1, false, GFP_NOFS); if (!wr_req) { err = -ENOMEM; - goto out_unlock; + goto put_string; } wr_req->r_flags = CEPH_OSD_FLAG_WRITE; @@ -2456,13 +2456,13 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, err = ceph_osdc_alloc_messages(wr_req, GFP_NOFS); if (err) - goto out_unlock; + goto put_string; /* one page should be large enough for STAT data */ pages = ceph_alloc_page_vector(1, GFP_KERNEL); if (IS_ERR(pages)) { err = PTR_ERR(pages); - goto out_unlock; + goto put_string; } osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE, @@ -2480,7 +2480,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, else if (err != -EPERM) { if (err == -EBLOCKLISTED) fsc->blocklisted = true; - goto out_unlock; + goto put_string; } if (err2 == 0 || err2 == -EEXIST) @@ -2489,14 +2489,14 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, if (err2 == -EBLOCKLISTED) fsc->blocklisted = true; err = err2; - goto out_unlock; + goto put_string; } pool_ns_len = pool_ns ? pool_ns->len : 0; perm = kmalloc(struct_size(perm, pool_ns, pool_ns_len + 1), GFP_NOFS); if (!perm) { err = -ENOMEM; - goto out_unlock; + goto put_string; } perm->pool = pool; @@ -2509,6 +2509,8 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, rb_link_node(&perm->node, parent, p); rb_insert_color(&perm->node, &mdsc->pool_perm_tree); err = 0; +put_string: + ceph_put_string(rd_req->r_base_oloc.pool_ns); out_unlock: up_write(&mdsc->pool_perm_rwsem); -- 2.25.1

2 days, 7 hours

2
1
0 0

[PATCH] nfsd: Drop the client reference in client_states_open()

by Haoxiang Li

In error path, call drop_client() to drop the reference obtained by get_nfsdfs_clp(). Fixes: a204f25e372d ("nfsd: create get_nfsdfs_clp helper") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <lihaoxiang(a)isrc.iscas.ac.cn> --- fs/nfsd/nfs4state.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8a6960500217..caa0756b6914 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3097,8 +3097,10 @@ static int client_states_open(struct inode *inode, struct file *file) return -ENXIO; ret = seq_open(file, &states_seq_ops); - if (ret) + if (ret) { + drop_client(clp); return ret; + } s = file->private_data; s->private = clp; return 0; -- 2.25.1

2 days, 8 hours

3
4
0 0

[PATCH] iio: adc: PAC1934: Fix clamped value in pac1934_reg_snapshot

by Thorsten Blum

The local variable 'curr_energy' was never clamped to PAC_193X_MIN_POWER_ACC or PAC_193X_MAX_POWER_ACC because the return value of clamp() was not used. Fix this by assigning the clamped value back to 'curr_energy'. Cc: stable(a)vger.kernel.org Fixes: 0fb528c8255b ("iio: adc: adding support for PAC193x") Signed-off-by: Thorsten Blum <thorsten.blum(a)linux.dev> --- drivers/iio/adc/pac1934.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iio/adc/pac1934.c b/drivers/iio/adc/pac1934.c index 48df16509260..256488d3936b 100644 --- a/drivers/iio/adc/pac1934.c +++ b/drivers/iio/adc/pac1934.c @@ -665,7 +665,8 @@ static int pac1934_reg_snapshot(struct pac1934_chip_info *info, /* add the power_acc field */ curr_energy += inc; - clamp(curr_energy, PAC_193X_MIN_POWER_ACC, PAC_193X_MAX_POWER_ACC); + curr_energy = clamp(curr_energy, PAC_193X_MIN_POWER_ACC, + PAC_193X_MAX_POWER_ACC); reg_data->energy_sec_acc[cnt] = curr_energy; } -- Thorsten Blum <thorsten.blum(a)linux.dev> GPG: 1D60 735E 8AEF 3BE4 73B6 9D84 7336 78FD 8DFE EAD4

2 days, 10 hours

3
2
0 0

[PATCH v1 4/4] mm/hugetlb: fix excessive IPI broadcasts when unsharing PMD tables using mmu_gather

by David Hildenbrand (Red Hat)

As reported, ever since commit 1013af4f585f ("mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race") we can end up in some situations where we perform so many IPI broadcasts when unsharing hugetlb PMD page tables that it severely regresses some workloads. In particular, when we fork()+exit(), or when we munmap() a large area backed by many shared PMD tables, we perform one IPI broadcast per unshared PMD table. There are two optimizations to be had: (1) When we process (unshare) multiple such PMD tables, such as during exit(), it is sufficient to send a single IPI broadcast (as long as we respect locking rules) instead of one per PMD table. Locking prevents that any of these PMD tables could get reuse before we drop the lock. (2) When we are not the last sharer (> 2 users including us), there is no need to send the IPI broadcast. The shared PMD tables cannot become exclusive (fully unshared) before an IPI will be broadcasted by the last sharer. Concurrent GUP-fast could walk into a PMD table just before we unshared it. It could then succeed in grabbing a page from the shared page table even after munmap() etc succeeded (and supressed an IPI). But there is not difference compared to GUP-fast just sleeping for a while after grabbing the page and re-enabling IRQs. Most importantly, GUP-fast will never walk into page tables that are no-longer shared, because the last sharer will issue an IPI broadcast. (if ever required, checking whether the PUD changed in GUP-fast after grabbing the page like we do in the PTE case could handle this) So let's rework PMD sharing TLB flushing + IPI sync to use the mmu_gather infrastructure so we can implement these optimizations and demystify the code at least a bit. Extend the mmu_gather infrastructure to be able to deal with our special hugetlb PMD table sharing implementation. We'll consolidate the handling for (full) unsharing of PMD tables in tlb_unshare_pmd_ptdesc() and tlb_flush_unshared_tables(), and track in "struct mmu_gather" whether we had (full) unsharing of PMD tables. Because locking is very special (concurrent unsharing+reuse must be prevented), we disallow deferring flushing to tlb_finish_mmu() and instead require an explicit earlier call to tlb_flush_unshared_tables(). From hugetlb code, we call huge_pmd_unshare_flush() where we make sure that the expected lock protecting us from concurrent unsharing+reuse is still held. Check with a VM_WARN_ON_ONCE() in tlb_finish_mmu() that tlb_flush_unshared_tables() was properly called earlier. Document it all properly. Notes about tlb_remove_table_sync_one() interaction with unsharing: There are two fairly tricky things: (1) tlb_remove_table_sync_one() is a NOP on architectures without CONFIG_MMU_GATHER_RCU_TABLE_FREE. Here, the assumption is that the previous TLB flush would send an IPI to all relevant CPUs. Careful: some architectures like x86 only send IPIs to all relevant CPUs when tlb->freed_tables is set. The relevant architectures should be selecting MMU_GATHER_RCU_TABLE_FREE, but x86 might not do that in stable kernels and it might have been problematic before this patch. Also, the arch flushing behavior (independent of IPIs) is different when tlb->freed_tables is set. Do we have to enlighten them to also take care of tlb->unshared_tables? So far we didn't care, so hopefully we are fine. Of course, we could be setting tlb->freed_tables as well, but that might then unnecessarily flush too much, because the semantics of tlb->freed_tables are a bit fuzzy. This patch changes nothing in this regard. (2) tlb_remove_table_sync_one() is not a NOP on architectures with CONFIG_MMU_GATHER_RCU_TABLE_FREE that actually don't need a sync. Take x86 as an example: in the common case (!pv, !X86_FEATURE_INVLPGB) we still issue IPIs during TLB flushes and don't actually need the second tlb_remove_table_sync_one(). This optimized can be implemented on top of this, by checking e.g., in tlb_remove_table_sync_one() whether we really need IPIs. But as described in (1), it really must honor tlb->freed_tables then to send IPIs to all relevant CPUs. Further note that the ptdesc_pmd_pts_dec() in huge_pmd_share() is not a concern, as we are holding the i_mmap_lock the whole time, preventing concurrent unsharing. That ptdesc_pmd_pts_dec() usage will be removed separately as a cleanup later. There are plenty more cleanups to be had, but they have to wait until this is fixed. Fixes: 1013af4f585f ("mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race") Reported-by: Uschakow, Stanislav" <suschako(a)amazon.de> Closes: https://lore.kernel.org/all/4d3878531c76479d9f8ca9789dc6485d@amazon.de/ Cc: <stable(a)vger.kernel.org> Signed-off-by: David Hildenbrand (Red Hat) <david(a)kernel.org> --- include/asm-generic/tlb.h | 69 +++++++++++++++++++++- include/linux/hugetlb.h | 19 +++--- mm/hugetlb.c | 121 ++++++++++++++++++++++---------------- mm/mmu_gather.c | 6 ++ mm/mprotect.c | 2 +- mm/rmap.c | 25 +++++--- 6 files changed, 173 insertions(+), 69 deletions(-) diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 1fff717cae510..324a21f53b644 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -364,6 +364,17 @@ struct mmu_gather { unsigned int vma_huge : 1; unsigned int vma_pfn : 1; + /* + * Did we unshare (unmap) any shared page tables? + */ + unsigned int unshared_tables : 1; + + /* + * Did we unshare any page tables such that they are now exclusive + * and could get reused+modified by the new owner? + */ + unsigned int fully_unshared_tables : 1; + unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER @@ -400,6 +411,7 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; + tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an @@ -484,7 +496,7 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || - tlb->cleared_puds || tlb->cleared_p4ds)) + tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables)) return; tlb_flush(tlb); @@ -773,6 +785,61 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) } #endif +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt, + unsigned long addr) +{ + /* + * The caller must make sure that concurrent unsharing + exclusive + * reuse is impossible until tlb_flush_unshared_tables() was called. + */ + VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt)); + ptdesc_pmd_pts_dec(pt); + + /* Clearing a PUD pointing at a PMD table with PMD leaves. */ + tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE); + + /* + * If the page table is now exclusively owned, we fully unshared + * a page table. + */ + if (!ptdesc_pmd_is_shared(pt)) + tlb->fully_unshared_tables = true; + tlb->unshared_tables = true; +} + +static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb) +{ + /* + * As soon as the caller drops locks to allow for reuse of + * previously-shared tables, these tables could get modified and + * even reused outside of hugetlb context. So flush the TLB now. + * + * Note that we cannot defer the flush to a later point even if we are + * not the last sharer of the page table. + */ + if (tlb->unshared_tables) + tlb_flush_mmu_tlbonly(tlb); + + /* + * Similarly, we must make sure that concurrent GUP-fast will not + * walk previously-shared page tables that are getting modified+reused + * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast. + * + * We only perform this when we are the last sharer of a page table, + * as the IPI will reach all CPUs: any GUP-fast. + * + * Note that on configs where tlb_remove_table_sync_one() is a NOP, + * the expectation is that the tlb_flush_mmu_tlbonly() would have issued + * required IPIs already for us. + */ + if (tlb->fully_unshared_tables) { + tlb_remove_table_sync_one(); + tlb->fully_unshared_tables = false; + } +} +#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 03c8725efa289..63b248c6bfd47 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -240,8 +240,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); @@ -271,7 +272,7 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); -long hugetlb_change_protection(struct vm_area_struct *vma, +long hugetlb_change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); @@ -300,13 +301,17 @@ static inline struct address_space *hugetlb_folio_mapping_lock_write( return NULL; } -static inline int huge_pmd_unshare(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline int huge_pmd_unshare(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } +static inline void huge_pmd_unshare_flush(struct mmu_gather *tlb, + struct vm_area_struct *vma) +{ +} + static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) @@ -432,7 +437,7 @@ static inline void move_hugetlb_state(struct folio *old_folio, { } -static inline long hugetlb_change_protection( +static inline long hugetlb_change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3c77cdef12a32..3db94693a06fc 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5096,8 +5096,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; - bool shared_pmd = false; + struct mmu_gather tlb; + tlb_gather_mmu(&tlb, vma->vm_mm); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); @@ -5122,12 +5123,12 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; - if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { - shared_pmd = true; + if (huge_pmd_unshare(&tlb, vma, old_addr, src_pte)) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } + tlb_remove_huge_tlb_entry(h, &tlb, src_pte, old_addr); dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); if (!dst_pte) @@ -5136,13 +5137,13 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); } - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, old_end - len, old_end); + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); + mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); return len + old_addr - old_end; } @@ -5161,7 +5162,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); bool adjust_reservation; unsigned long last_addr_mask; - bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -5184,10 +5184,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(tlb, vma, address, ptep)) { spin_unlock(ptl); - tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); - force_flush = true; address |= last_addr_mask; continue; } @@ -5303,14 +5301,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } tlb_end_vma(tlb, vma); - /* - * There is nothing protecting a previously-shared page table that we - * unshared through huge_pmd_unshare() from getting freed after we - * release i_mmap_rwsem, so flush the TLB now. If huge_pmd_unshare() - * succeeded, flush the range corresponding to the pud. - */ - if (force_flush) - tlb_flush_mmu_tlbonly(tlb); + huge_pmd_unshare_flush(tlb, vma); } void __hugetlb_zap_begin(struct vm_area_struct *vma, @@ -6399,7 +6390,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, } #endif /* CONFIG_USERFAULTFD */ -long hugetlb_change_protection(struct vm_area_struct *vma, +long hugetlb_change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { @@ -6409,7 +6400,6 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); - bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; @@ -6452,7 +6442,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, } } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(tlb, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it @@ -6461,7 +6451,6 @@ long hugetlb_change_protection(struct vm_area_struct *vma, WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); - shared_pmd = true; address |= last_addr_mask; continue; } @@ -6522,22 +6511,16 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; + tlb_remove_huge_tlb_entry(h, tlb, ptep, address); } next: spin_unlock(ptl); cond_resched(); } - /* - * There is nothing protecting a previously-shared page table that we - * unshared through huge_pmd_unshare() from getting freed after we - * release i_mmap_rwsem, so flush the TLB now. If huge_pmd_unshare() - * succeeded, flush the range corresponding to the pud. - */ - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, start, end); + + tlb_flush_mmu_tlbonly(tlb); + huge_pmd_unshare_flush(tlb, vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new @@ -6904,18 +6887,27 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return pte; } -/* - * unmap huge page backed by shared pte. +/** + * huge_pmd_unshare - Unmap a pmd table if it is shared by multiple users + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * @addr: the address we are trying to unshare. + * @ptep: pointer into the (pmd) page table. + * + * Called with the page table lock held, the i_mmap_rwsem held in write mode + * and the hugetlb vma lock held in write mode. * - * Called with page table lock held. + * Note: The caller must call huge_pmd_unshare_flush() before dropping the + * i_mmap_rwsem. * - * returns: 1 successfully unmapped a shared pte page - * 0 the underlying pte page is not shared, or it is the last user + * Returns: 1 if it was a shared PMD table and it got unmapped, or 0 if it + * was not a shared PMD table. */ -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); + struct mm_struct *mm = vma->vm_mm; pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); @@ -6927,18 +6919,36 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); pud_clear(pud); - /* - * Once our caller drops the rmap lock, some other process might be - * using this page table as a normal, non-hugetlb page table. - * Wait for pending gup_fast() in other threads to finish before letting - * that happen. - */ - tlb_remove_table_sync_one(); - ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); + + tlb_unshare_pmd_ptdesc(tlb, virt_to_ptdesc(ptep), addr); + mm_dec_nr_pmds(mm); return 1; } +/* + * huge_pmd_unshare_flush - Complete a sequence of huge_pmd_unshare() calls + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * + * Perform necessary TLB flushes or IPI broadcasts to synchronize PMD table + * unsharing with concurrent page table walkers (TLB, GUP-fast, etc.). + * + * This function must be called after a sequence of huge_pmd_unshare() + * calls while still holding the i_mmap_rwsem. + */ +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + /* + * We must synchronize page table unsharing such that nobody will + * try reusing a previously-shared page table while it might still + * be in use by previous sharers (TLB, GUP_fast). + */ + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + + tlb_flush_unshared_tables(tlb); +} + #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, @@ -6947,12 +6957,16 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return NULL; } -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { return 0; } +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ +} + void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { @@ -7219,6 +7233,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; + struct mmu_gather tlb; unsigned long address; spinlock_t *ptl; pte_t *ptep; @@ -7229,6 +7244,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, if (start >= end) return; + tlb_gather_mmu(&tlb, mm); flush_cache_range(vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because @@ -7248,10 +7264,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - huge_pmd_unshare(mm, vma, address, ptep); + huge_pmd_unshare(&tlb, vma, address, ptep); spin_unlock(ptl); } - flush_hugetlb_tlb_range(vma, start, end); + huge_pmd_unshare_flush(&tlb, vma); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); @@ -7261,6 +7277,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); } /* diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 247e3f9db6c7a..822a790127375 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -468,6 +468,12 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) */ void tlb_finish_mmu(struct mmu_gather *tlb) { + /* + * We expect an earlier huge_pmd_unshare_flush() call to sort this out, + * due to complicated locking requirements with page table unsharing. + */ + VM_WARN_ON_ONCE(tlb->fully_unshared_tables); + /* * If there are parallel threads are doing PTE changes on same range * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB diff --git a/mm/mprotect.c b/mm/mprotect.c index 283889e4f1cec..5c330e817129e 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -652,7 +652,7 @@ long change_protection(struct mmu_gather *tlb, #endif if (is_vm_hugetlb_page(vma)) - pages = hugetlb_change_protection(vma, start, end, newprot, + pages = hugetlb_change_protection(tlb, vma, start, end, newprot, cp_flags); else pages = change_protection_range(tlb, vma, start, end, newprot, diff --git a/mm/rmap.c b/mm/rmap.c index 748f48727a162..d6799afe11147 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -76,7 +76,7 @@ #include <linux/mm_inline.h> #include <linux/oom.h> -#include <asm/tlbflush.h> +#include <asm/tlb.h> #define CREATE_TRACE_POINTS #include <trace/events/migrate.h> @@ -2008,13 +2008,17 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { + + tlb_gather_mmu(&tlb, mm); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. @@ -2022,6 +2026,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, goto walk_done; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) @@ -2398,17 +2403,20 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, * fail if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { - hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + tlb_gather_mmu(&tlb, mm); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { + hugetlb_vma_unlock_write(vma); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. @@ -2417,6 +2425,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, break; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); -- 2.52.0

2 days, 11 hours

2
3
0 0

[PATCH] nfs/localio: fix regression due to out-of-order __put_cred

by Trond Myklebust

From: Mike Snitzer <snitzer(a)kernel.org> commit 3af870aedbff10bfed220e280b57a405e972229f upstream. Commit f2060bdc21d7 ("nfs/localio: add refcounting for each iocb IO associated with NFS pgio header") inadvertantly reintroduced the same potential for __put_cred() triggering BUG_ON(cred == current->cred) that commit 992203a1fba5 ("nfs/localio: restore creds before releasing pageio data") fixed. Fix this by saving and restoring the cred around each {read,write}_iter call within the respective for loop of nfs_local_call_{read,write}. Reported-by: Zorro Lang <zlang(a)redhat.com> Fixes: f2060bdc21d7 ("nfs/localio: add refcounting for each iocb IO associated with NFS pgio header") Cc: <stable(a)vger.kernel.org> # 6.18.x Signed-off-by: Mike Snitzer <snitzer(a)kernel.org> Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> --- fs/nfs/localio.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index 656976b4f42c..ee635172d68a 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -625,8 +625,6 @@ static void nfs_local_call_read(struct work_struct *work) ssize_t status; int n_iters; - save_cred = override_creds(filp->f_cred); - n_iters = atomic_read(&iocb->n_iters); for (int i = 0; i < n_iters ; i++) { if (iocb->iter_is_dio_aligned[i]) { @@ -639,7 +637,10 @@ static void nfs_local_call_read(struct work_struct *work) } else iocb->kiocb.ki_flags &= ~IOCB_DIRECT; + save_cred = override_creds(filp->f_cred); status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]); + revert_creds(save_cred); + if (status != -EIOCBQUEUED) { if (unlikely(status >= 0 && status < iocb->iters[i].count)) force_done = true; /* Partial read */ @@ -649,8 +650,6 @@ static void nfs_local_call_read(struct work_struct *work) } } } - - revert_creds(save_cred); } static int @@ -832,7 +831,6 @@ static void nfs_local_call_write(struct work_struct *work) int n_iters; current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; - save_cred = override_creds(filp->f_cred); file_start_write(filp); n_iters = atomic_read(&iocb->n_iters); @@ -847,7 +845,10 @@ static void nfs_local_call_write(struct work_struct *work) } else iocb->kiocb.ki_flags &= ~IOCB_DIRECT; + save_cred = override_creds(filp->f_cred); status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]); + revert_creds(save_cred); + if (status != -EIOCBQUEUED) { if (unlikely(status >= 0 && status < iocb->iters[i].count)) force_done = true; /* Partial write */ @@ -859,7 +860,6 @@ static void nfs_local_call_write(struct work_struct *work) } file_end_write(filp); - revert_creds(save_cred); current->flags = old_flags; } -- 2.52.0

2 days, 18 hours

2
2
0 0

Please apply 5b1e38c0792cc7a44997328de37d393f81b2501a to 5.15

by Nathan Chancellor

Hi stable folks, Please apply commit 5b1e38c0792c ("dpaa2-mac: bail if the dpmacs fwnode is not found") to 5.15, where it addresses an instance of -Wsometimes-uninitialized with clang-21 and newer, introduced by commit 3264f599c1a8 ("net: dpaa2-mac: Add ACPI support for DPAA2 MAC driver") in 5.14. drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c:54:13: error: variable 'parent' is used uninitialized whenever 'if' condition is false [-Werror,-Wsometimes-uninitialized] 54 | } else if (is_acpi_node(fwnode)) { | ^~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c:58:29: note: uninitialized use occurs here 58 | fwnode_for_each_child_node(parent, child) { | ^~~~~~ drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c:54:9: note: remove the 'if' if its condition is always true 54 | } else if (is_acpi_node(fwnode)) { | ^~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c:43:39: note: initialize the variable 'parent' to silence this warning 43 | struct fwnode_handle *fwnode, *parent, *child = NULL; | ^ | = NULL It applies and builds cleanly for me. If there are any issues, please let me know. Cheers, Nathan

2 days, 23 hours

2
1
0 0

Apply fc7bf4c0d65a342b29fe38c332db3fe900b481b9 to 5.15

by Nathan Chancellor

Hi stable folks, Please apply commit fc7bf4c0d65a ("drm/i915/selftests: Fix inconsistent IS_ERR and PTR_ERR") to 5.15, where it resolves a couple of instances of -Wuninitialized with clang-21 or newer that were introduced by commit cdb35d1ed6d2 ("drm/i915/gem: Migrate to system at dma-buf attach time (v7)") in 5.15. In file included from drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c:329: drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:105:18: error: variable 'dmabuf' is uninitialized when used here [-Werror,-Wuninitialized] 105 | PTR_ERR(dmabuf)); | ^~~~~~ drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:94:24: note: initialize the variable 'dmabuf' to silence this warning 94 | struct dma_buf *dmabuf; | ^ | = NULL drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:161:18: error: variable 'dmabuf' is uninitialized when used here [-Werror,-Wuninitialized] 161 | PTR_ERR(dmabuf)); | ^~~~~~ drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:149:24: note: initialize the variable 'dmabuf' to silence this warning 149 | struct dma_buf *dmabuf; | ^ | = NULL It applies and builds cleanly for me. If there are any issues, please let me know. Cheers, Nathan

2 days, 23 hours

2
1
0 0

Apply ccc35ff2fd2911986b716a87fe65e03fac2312c9 to 5.15, 6.1, and 6.6

by Nathan Chancellor

Hi stable folks, Please apply commit ccc35ff2fd29 ("leds: spi-byte: Use devm_led_classdev_register_ext()") to 5.15, 6.1, and 6.6. It inadvertently addresses an instance of -Wuninitialized visible with clang-21 and newer: drivers/leds/leds-spi-byte.c:99:26: error: variable 'child' is uninitialized when used here [-Werror,-Wuninitialized] 99 | of_property_read_string(child, "label", &name); | ^~~~~ drivers/leds/leds-spi-byte.c:83:27: note: initialize the variable 'child' to silence this warning 83 | struct device_node *child; | ^ | = NULL It applies cleanly to 6.6. I have attached a backport for 6.1 and 5.15, which can be generated locally with: $ git format-patch -1 --stdout ccc35ff2fd2911986b716a87fe65e03fac2312c9 | sed 's;strscpy;strlcpy;' | patch -p1 This change seems safe to me but if I am missing a massive dependency chain, an alternative would be moving child's initialization up in these stable branches. Cheers, Nathan diff --git a/drivers/leds/leds-spi-byte.c b/drivers/leds/leds-spi-byte.c index 82696e0607a5..7dd876df8b36 100644 --- a/drivers/leds/leds-spi-byte.c +++ b/drivers/leds/leds-spi-byte.c @@ -96,6 +96,7 @@ static int spi_byte_probe(struct spi_device *spi) if (!led) return -ENOMEM; + child = of_get_next_available_child(dev_of_node(dev), NULL); of_property_read_string(child, "label", &name); strlcpy(led->name, name, sizeof(led->name)); led->spi = spi; @@ -106,7 +107,6 @@ static int spi_byte_probe(struct spi_device *spi) led->ldev.max_brightness = led->cdef->max_value - led->cdef->off_value; led->ldev.brightness_set_blocking = spi_byte_brightness_set_blocking; - child = of_get_next_available_child(dev_of_node(dev), NULL); state = of_get_property(child, "default-state", NULL); if (state) { if (!strcmp(state, "on")) {

2 days, 23 hours

2
1
0 0

[PATCH AUTOSEL 6.18-6.1] ksmbd: fix use-after-free in ksmbd_tree_connect_put under concurrency

by Sasha Levin

From: Namjae Jeon <linkinjeon(a)kernel.org> [ Upstream commit b39a1833cc4a2755b02603eec3a71a85e9dff926 ] Under high concurrency, A tree-connection object (tcon) is freed on a disconnect path while another path still holds a reference and later executes *_put()/write on it. Reported-by: Qianchang Zhao <pioooooooooip(a)gmail.com> Reported-by: Zhitong Liu <liuzhitong1993(a)gmail.com> Signed-off-by: Namjae Jeon <linkinjeon(a)kernel.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- LLM Generated explanations, may be completely bogus: fs/smb/server/mgmt/tree_connect.c | 18 ++++-------------- fs/smb/server/mgmt/tree_connect.h | 1 - fs/smb/server/smb2pdu.c | 3 --- 3 files changed, 4 insertions(+), 18 deletions(-) diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index ecfc575086712..d3483d9c757c7 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -78,7 +78,6 @@ ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) tree_conn->t_state = TREE_NEW; status.tree_conn = tree_conn; atomic_set(&tree_conn->refcount, 1); - init_waitqueue_head(&tree_conn->refcount_q); ret = xa_err(xa_store(&sess->tree_conns, tree_conn->id, tree_conn, KSMBD_DEFAULT_GFP)); @@ -100,14 +99,8 @@ ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon) { - /* - * Checking waitqueue to releasing tree connect on - * tree disconnect. waitqueue_active is safe because it - * uses atomic operation for condition. - */ - if (!atomic_dec_return(&tcon->refcount) && - waitqueue_active(&tcon->refcount_q)) - wake_up(&tcon->refcount_q); + if (atomic_dec_and_test(&tcon->refcount)) + kfree(tcon); } int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, @@ -119,14 +112,11 @@ int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, xa_erase(&sess->tree_conns, tree_conn->id); write_unlock(&sess->tree_conns_lock); - if (!atomic_dec_and_test(&tree_conn->refcount)) - wait_event(tree_conn->refcount_q, - atomic_read(&tree_conn->refcount) == 0); - ret = ksmbd_ipc_tree_disconnect_request(sess->id, tree_conn->id); ksmbd_release_tree_conn_id(sess, tree_conn->id); ksmbd_share_config_put(tree_conn->share_conf); - kfree(tree_conn); + if (atomic_dec_and_test(&tree_conn->refcount)) + kfree(tree_conn); return ret; } diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index a42cdd0510411..f0023d86716f2 100644 --- a/fs/smb/server/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h @@ -33,7 +33,6 @@ struct ksmbd_tree_connect { int maximal_access; bool posix_extensions; atomic_t refcount; - wait_queue_head_t refcount_q; unsigned int t_state; }; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index a2830ec67e782..dba29881debdc 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2200,7 +2200,6 @@ int smb2_tree_disconnect(struct ksmbd_work *work) goto err_out; } - WARN_ON_ONCE(atomic_dec_and_test(&tcon->refcount)); tcon->t_state = TREE_DISCONNECTED; write_unlock(&sess->tree_conns_lock); @@ -2210,8 +2209,6 @@ int smb2_tree_disconnect(struct ksmbd_work *work) goto err_out; } - work->tcon = NULL; - rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_tree_disconnect_rsp)); -- 2.51.0

3 days, 1 hour

2
28
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror