From: Christoph Hellwig hch@lst.de

[ Upstream commit 9a208ba5c9afa62c7b1e9c6f5e783066e84e2d3c ]

There is no clear benefit in having this helper vs just open coding it.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Chaitanya Kulkarni kch@nvidia.com Link: https://lore.kernel.org/r/20211019062530.2174626-2-hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/sync.c | 38 +++++++++++++++++--------------------- 1 file changed, 17 insertions(+), 21 deletions(-)

diff --git a/fs/sync.c b/fs/sync.c index 1373a610dc78..0d6cdc507cb9 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -21,25 +21,6 @@ #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \ SYNC_FILE_RANGE_WAIT_AFTER)

-/* - * Do the filesystem syncing work. For simple filesystems - * writeback_inodes_sb(sb) just dirties buffers with inodes so we have to - * submit IO for these buffers via __sync_blockdev(). This also speeds up the - * wait == 1 case since in that case write_inode() functions do - * sync_dirty_buffer() and thus effectively write one block at a time. - */ -static int __sync_filesystem(struct super_block *sb, int wait) -{ - if (wait) - sync_inodes_sb(sb); - else - writeback_inodes_sb(sb, WB_REASON_SYNC); - - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, wait); - return __sync_blockdev(sb->s_bdev, wait); -} - /* * Write out and wait upon all dirty data associated with this * superblock. Filesystem data as well as the underlying block @@ -61,10 +42,25 @@ int sync_filesystem(struct super_block *sb) if (sb_rdonly(sb)) return 0;

- ret = __sync_filesystem(sb, 0); + /* + * Do the filesystem syncing work. For simple filesystems + * writeback_inodes_sb(sb) just dirties buffers with inodes so we have + * to submit I/O for these buffers via __sync_blockdev(). This also + * speeds up the wait == 1 case since in that case write_inode() + * methods call sync_dirty_buffer() and thus effectively write one block + * at a time. + */ + writeback_inodes_sb(sb, WB_REASON_SYNC); + if (sb->s_op->sync_fs) + sb->s_op->sync_fs(sb, 0); + ret = __sync_blockdev(sb->s_bdev, 0); if (ret < 0) return ret; - return __sync_filesystem(sb, 1); + + sync_inodes_sb(sb); + if (sb->s_op->sync_fs) + sb->s_op->sync_fs(sb, 1); + return __sync_blockdev(sb->s_bdev, 1); } EXPORT_SYMBOL(sync_filesystem);

From: Christoph Hellwig hch@lst.de

[ Upstream commit 1e03a36bdff4709c1bbf0f57f60ae3f776d51adf ]

Get rid of the indirections and just provide a sync_bdevs helper for the generic sync code.

Signed-off-by: Christoph Hellwig hch@lst.de Link: https://lore.kernel.org/r/20211019062530.2174626-8-hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/bdev.c | 17 ++++++++++++++--- fs/internal.h | 6 ------ fs/sync.c | 23 ++++------------------- include/linux/blkdev.h | 4 ++++ 4 files changed, 22 insertions(+), 28 deletions(-)

diff --git a/block/bdev.c b/block/bdev.c index 33cac289302e..18abafb135e0 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -1017,7 +1017,7 @@ int __invalidate_device(struct block_device *bdev, bool kill_dirty) } EXPORT_SYMBOL(__invalidate_device);

-void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) +void sync_bdevs(bool wait) { struct inode *inode, *old_inode = NULL;

@@ -1048,8 +1048,19 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) bdev = I_BDEV(inode);

mutex_lock(&bdev->bd_disk->open_mutex); - if (bdev->bd_openers) - func(bdev, arg); + if (!bdev->bd_openers) { + ; /* skip */ + } else if (wait) { + /* + * We keep the error status of individual mapping so + * that applications can catch the writeback error using + * fsync(2). See filemap_fdatawait_keep_errors() for + * details. + */ + filemap_fdatawait_keep_errors(inode->i_mapping); + } else { + filemap_fdatawrite(inode->i_mapping); + } mutex_unlock(&bdev->bd_disk->open_mutex);

spin_lock(&blockdev_superblock->s_inode_list_lock); diff --git a/fs/internal.h b/fs/internal.h index b5caa16f4645..cdd83d4899bb 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -23,17 +23,11 @@ struct pipe_inode_info; #ifdef CONFIG_BLOCK extern void __init bdev_cache_init(void);

-void iterate_bdevs(void (*)(struct block_device *, void *), void *); void emergency_thaw_bdev(struct super_block *sb); #else static inline void bdev_cache_init(void) { } - -static inline void iterate_bdevs(void (*f)(struct block_device *, void *), - void *arg) -{ -} static inline int emergency_thaw_bdev(struct super_block *sb) { return 0; diff --git a/fs/sync.c b/fs/sync.c index a621089eb07e..3ce8e2137f31 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -78,21 +78,6 @@ static void sync_fs_one_sb(struct super_block *sb, void *arg) sb->s_op->sync_fs(sb, *(int *)arg); }

-static void fdatawrite_one_bdev(struct block_device *bdev, void *arg) -{ - filemap_fdatawrite(bdev->bd_inode->i_mapping); -} - -static void fdatawait_one_bdev(struct block_device *bdev, void *arg) -{ - /* - * We keep the error status of individual mapping so that - * applications can catch the writeback error using fsync(2). - * See filemap_fdatawait_keep_errors() for details. - */ - filemap_fdatawait_keep_errors(bdev->bd_inode->i_mapping); -} - /* * Sync everything. We start by waking flusher threads so that most of * writeback runs on all devices in parallel. Then we sync all inodes reliably @@ -111,8 +96,8 @@ void ksys_sync(void) iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &wait); - iterate_bdevs(fdatawrite_one_bdev, NULL); - iterate_bdevs(fdatawait_one_bdev, NULL); + sync_bdevs(false); + sync_bdevs(true); if (unlikely(laptop_mode)) laptop_sync_completion(); } @@ -133,10 +118,10 @@ static void do_sync_work(struct work_struct *work) */ iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); - iterate_bdevs(fdatawrite_one_bdev, NULL); + sync_bdevs(false); iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); - iterate_bdevs(fdatawrite_one_bdev, NULL); + sync_bdevs(false); printk("Emergency Sync complete\n"); kfree(work); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6bbd393e6bcc..aebe67ed7a73 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -2000,6 +2000,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); int sync_blockdev_nowait(struct block_device *bdev); +void sync_bdevs(bool wait); #else static inline void invalidate_bdev(struct block_device *bdev) { @@ -2012,6 +2013,9 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) { return 0; } +static inline void sync_bdevs(bool wait) +{ +} #endif int fsync_bdev(struct block_device *bdev);

From: Darrick J. Wong djwong@kernel.org

[ Upstream commit 2d86293c70750e4331e9616aded33ab6b47c299d ]

Now that the VFS will do something with the return values from ->sync_fs, make ours pass on error codes.

Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Christoph Hellwig hch@lst.de Acked-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/xfs/xfs_super.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -729,6 +729,7 @@ xfs_fs_sync_fs( int wait) { struct xfs_mount *mp = XFS_M(sb); + int error;

trace_xfs_fs_sync_fs(mp, __return_address);

@@ -738,7 +739,10 @@ xfs_fs_sync_fs( if (!wait) return 0;

- xfs_log_force(mp, XFS_LOG_SYNC); + error = xfs_log_force(mp, XFS_LOG_SYNC); + if (error) + return error; + if (laptop_mode) { /* * The disk must be active because we're syncing.

From: Anshuman Khandual anshuman.khandual@arm.com

commit 3de360c3fdb34fbdbaf6da3af94367d3fded95d3 upstream.

CONFIG_SPARSEMEM_VMEMMAP is now the only available memory model on arm64 platforms and free_unused_memmap() would just return without creating any holes in the memmap mapping. There is no need for any special handling in pfn_valid() and HAVE_ARCH_PFN_VALID can just be dropped. This also moves the pfn upper bits sanity check into generic pfn_valid().

[rppt: rebased on v5.15-rc3]

Link: https://lkml.kernel.org/r/1621947349-25421-1-git-send-email-anshuman.khandua... Signed-off-by: Anshuman Khandual anshuman.khandual@arm.com Acked-by: David Hildenbrand david@redhat.com Acked-by: Mike Rapoport rppt@linux.ibm.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: Will Deacon will@kernel.org Cc: David Hildenbrand david@redhat.com Cc: Mike Rapoport rppt@kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Mike Rapoport rppt@linux.ibm.com Link: https://lore.kernel.org/r/20210930013039.11260-3-rppt@kernel.org Signed-off-by: Will Deacon will@kernel.org Fixes: 859a85ddf90e ("mm: remove pfn_valid_within() and CONFIG_HOLES_IN_ZONE") Link: https://lore.kernel.org/r/Yl0IZWT2nsiYtqBT@linux.ibm.com Signed-off-by: Georgi Djakov quic_c_gdjako@quicinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/Kconfig | 1 - arch/arm64/include/asm/page.h | 1 - arch/arm64/mm/init.c | 37 ------------------------------------- 3 files changed, 39 deletions(-)

--- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -154,7 +154,6 @@ config ARM64 select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT - select HAVE_ARCH_PFN_VALID select HAVE_ARCH_PREL32_RELOCATIONS select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET select HAVE_ARCH_SECCOMP_FILTER --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -41,7 +41,6 @@ void tag_clear_highpage(struct page *to)

typedef struct page *pgtable_t;

-int pfn_valid(unsigned long pfn); int pfn_is_map_memory(unsigned long pfn);

#include <asm/memory.h> --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -184,43 +184,6 @@ static void __init zone_sizes_init(unsig free_area_init(max_zone_pfns); }

-int pfn_valid(unsigned long pfn) -{ - phys_addr_t addr = PFN_PHYS(pfn); - struct mem_section *ms; - - /* - * Ensure the upper PAGE_SHIFT bits are clear in the - * pfn. Else it might lead to false positives when - * some of the upper bits are set, but the lower bits - * match a valid pfn. - */ - if (PHYS_PFN(addr) != pfn) - return 0; - - if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) - return 0; - - ms = __pfn_to_section(pfn); - if (!valid_section(ms)) - return 0; - - /* - * ZONE_DEVICE memory does not have the memblock entries. - * memblock_is_map_memory() check for ZONE_DEVICE based - * addresses will always fail. Even the normal hotplugged - * memory will never have MEMBLOCK_NOMAP flag set in their - * memblock entries. Skip memblock search for all non early - * memory sections covering all of hotplug memory including - * both normal and ZONE_DEVICE based. - */ - if (!early_section(ms)) - return pfn_section_valid(ms, pfn); - - return memblock_is_memory(addr); -} -EXPORT_SYMBOL(pfn_valid); - int pfn_is_map_memory(unsigned long pfn) { phys_addr_t addr = PFN_PHYS(pfn);

From: Xiongwei Song sxwjean@gmail.com

commit ca831f29f8f25c97182e726429b38c0802200c8f upstream.

Arthur Marsh reported we would hit the error below when building kernel with gcc-12:

CC mm/page_alloc.o mm/page_alloc.c: In function `mem_init_print_info': mm/page_alloc.c:8173:27: error: comparison between two arrays [-Werror=array-compare] 8173 | if (start <= pos && pos < end && size > adj) \ |

In C++20, the comparision between arrays should be warned.

Link: https://lkml.kernel.org/r/20211125130928.32465-1-sxwjean@me.com Signed-off-by: Xiongwei Song sxwjean@gmail.com Reported-by: Arthur Marsh arthur.marsh@internode.on.net Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Cc: Khem Raj raj.khem@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8169,7 +8169,7 @@ void __init mem_init_print_info(void) */ #define adj_init_size(start, end, size, pos, adj) \ do { \ - if (start <= pos && pos < end && size > adj) \ + if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ size -= adj; \ } while (0)

From: Marco Elver elver@google.com

commit 2dfe63e61cc31ee59ce951672b0850b5229cd5b0 upstream.

Calling kmem_obj_info() via kmem_dump_obj() on KFENCE objects has been producing garbage data due to the object not actually being maintained by SLAB or SLUB.

Fix this by implementing __kfence_obj_info() that copies relevant information to struct kmem_obj_info when the object was allocated by KFENCE; this is called by a common kmem_obj_info(), which also calls the slab/slub/slob specific variant now called __kmem_obj_info().

For completeness, kmem_dump_obj() now displays if the object was allocated by KFENCE.

Link: https://lore.kernel.org/all/20220323090520.GG16885@xsang-OptiPlex-9020/ Link: https://lkml.kernel.org/r/20220406131558.3558585-1-elver@google.com Fixes: b89fb5ef0ce6 ("mm, kfence: insert KFENCE hooks for SLUB") Fixes: d3fb45f370d9 ("mm, kfence: insert KFENCE hooks for SLAB") Signed-off-by: Marco Elver elver@google.com Reviewed-by: Hyeonggon Yoo 42.hyeyoo@gmail.com Reported-by: kernel test robot oliver.sang@intel.com Acked-by: Vlastimil Babka vbabka@suse.cz [slab] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/kfence.h | 24 ++++++++++++++++++++++++ mm/kfence/core.c | 21 --------------------- mm/kfence/kfence.h | 21 +++++++++++++++++++++ mm/kfence/report.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++ mm/slab.c | 2 +- mm/slab.h | 2 +- mm/slab_common.c | 9 +++++++++ mm/slob.c | 2 +- mm/slub.c | 2 +- 9 files changed, 105 insertions(+), 25 deletions(-)

--- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -202,6 +202,22 @@ static __always_inline __must_check bool */ bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs);

+#ifdef CONFIG_PRINTK +struct kmem_obj_info; +/** + * __kfence_obj_info() - fill kmem_obj_info struct + * @kpp: kmem_obj_info to be filled + * @object: the object + * + * Return: + * * false - not a KFENCE object + * * true - a KFENCE object, filled @kpp + * + * Copies information to @kpp for KFENCE objects. + */ +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page); +#endif + #else /* CONFIG_KFENCE */

static inline bool is_kfence_address(const void *addr) { return false; } @@ -219,6 +235,14 @@ static inline bool __must_check kfence_h return false; }

+#ifdef CONFIG_PRINTK +struct kmem_obj_info; +static inline bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) +{ + return false; +} +#endif + #endif

#endif /* _LINUX_KFENCE_H */ --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -221,27 +221,6 @@ static bool kfence_unprotect(unsigned lo return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false)); }

-static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) -{ - long index; - - /* The checks do not affect performance; only called from slow-paths. */ - - if (!is_kfence_address((void *)addr)) - return NULL; - - /* - * May be an invalid index if called with an address at the edge of - * __kfence_pool, in which case we would report an "invalid access" - * error. - */ - index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; - if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) - return NULL; - - return &kfence_metadata[index]; -} - static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta) { unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2; --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -93,6 +93,27 @@ struct kfence_metadata {

extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS];

+static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) +{ + long index; + + /* The checks do not affect performance; only called from slow-paths. */ + + if (!is_kfence_address((void *)addr)) + return NULL; + + /* + * May be an invalid index if called with an address at the edge of + * __kfence_pool, in which case we would report an "invalid access" + * error. + */ + index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; + if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) + return NULL; + + return &kfence_metadata[index]; +} + /* KFENCE error types for report generation. */ enum kfence_error_type { KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */ --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -273,3 +273,50 @@ void kfence_report_error(unsigned long a /* We encountered a memory safety error, taint the kernel! */ add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK); } + +#ifdef CONFIG_PRINTK +static void kfence_to_kp_stack(const struct kfence_track *track, void **kp_stack) +{ + int i, j; + + i = get_stack_skipnr(track->stack_entries, track->num_stack_entries, NULL); + for (j = 0; i < track->num_stack_entries && j < KS_ADDRS_COUNT; ++i, ++j) + kp_stack[j] = (void *)track->stack_entries[i]; + if (j < KS_ADDRS_COUNT) + kp_stack[j] = NULL; +} + +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) +{ + struct kfence_metadata *meta = addr_to_metadata((unsigned long)object); + unsigned long flags; + + if (!meta) + return false; + + /* + * If state is UNUSED at least show the pointer requested; the rest + * would be garbage data. + */ + kpp->kp_ptr = object; + + /* Requesting info an a never-used object is almost certainly a bug. */ + if (WARN_ON(meta->state == KFENCE_OBJECT_UNUSED)) + return true; + + raw_spin_lock_irqsave(&meta->lock, flags); + + kpp->kp_page = page; + kpp->kp_slab_cache = meta->cache; + kpp->kp_objp = (void *)meta->addr; + kfence_to_kp_stack(&meta->alloc_track, kpp->kp_stack); + if (meta->state == KFENCE_OBJECT_FREED) + kfence_to_kp_stack(&meta->free_track, kpp->kp_free_stack); + /* get_stack_skipnr() ensures the first entry is outside allocator. */ + kpp->kp_ret = kpp->kp_stack[0]; + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + return true; +} +#endif --- a/mm/slab.c +++ b/mm/slab.c @@ -3658,7 +3658,7 @@ EXPORT_SYMBOL(__kmalloc_node_track_calle #endif /* CONFIG_NUMA */

#ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) { struct kmem_cache *cachep; unsigned int objnr; --- a/mm/slab.h +++ b/mm/slab.h @@ -643,7 +643,7 @@ struct kmem_obj_info { void *kp_stack[KS_ADDRS_COUNT]; void *kp_free_stack[KS_ADDRS_COUNT]; }; -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page); +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page); #endif

#endif /* MM_SLAB_H */ --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -568,6 +568,13 @@ bool kmem_valid_obj(void *object) } EXPORT_SYMBOL_GPL(kmem_valid_obj);

+static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) +{ + if (__kfence_obj_info(kpp, object, page)) + return; + __kmem_obj_info(kpp, object, page); +} + /** * kmem_dump_obj - Print available slab provenance information * @object: slab object for which to find provenance information. @@ -603,6 +610,8 @@ void kmem_dump_obj(void *object) pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name); else pr_cont(" slab%s", cp); + if (is_kfence_address(object)) + pr_cont(" (kfence)"); if (kp.kp_objp) pr_cont(" start %px", kp.kp_objp); if (kp.kp_data_offset) --- a/mm/slob.c +++ b/mm/slob.c @@ -462,7 +462,7 @@ out: }

#ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) { kpp->kp_ptr = object; kpp->kp_page = page; --- a/mm/slub.c +++ b/mm/slub.c @@ -4299,7 +4299,7 @@ int __kmem_cache_shutdown(struct kmem_ca }

#ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) { void *base; int __maybe_unused i;

From: Peter Wang peter.wang@mediatek.com

commit 2bd3b6b75946db2ace06e145d53988e10ed7e99a upstream.

When ufs initializes without scmd->device->sector_size set, scsi_get_lba() will get a wrong shift number and trigger an ubsan error. The shift exponent 4294967286 is too large for the 64-bit type 'sector_t' (aka 'unsigned long long').

Call scsi_get_lba() only when opcode is READ_10/WRITE_10/UNMAP.

Link: https://lore.kernel.org/r/20220307111752.10465-1-peter.wang@mediatek.com Reviewed-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Peter Wang peter.wang@mediatek.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/ufs/ufshcd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -358,7 +358,7 @@ static void ufshcd_add_uic_command_trace static void ufshcd_add_command_trace(struct ufs_hba *hba, unsigned int tag, enum ufs_trace_str_t str_t) { - u64 lba; + u64 lba = 0; u8 opcode = 0, group_id = 0; u32 intr, doorbell; struct ufshcd_lrb *lrbp = &hba->lrb[tag]; @@ -375,7 +375,6 @@ static void ufshcd_add_command_trace(str return;

opcode = cmd->cmnd[0]; - lba = scsi_get_lba(cmd);

if (opcode == READ_10 || opcode == WRITE_10) { /* @@ -383,6 +382,7 @@ static void ufshcd_add_command_trace(str */ transfer_len = be32_to_cpu(lrbp->ucd_req_ptr->sc.exp_data_transfer_len); + lba = scsi_get_lba(cmd); if (opcode == WRITE_10) group_id = lrbp->cmd->cmnd[6]; } else if (opcode == UNMAP) { @@ -390,6 +390,7 @@ static void ufshcd_add_command_trace(str * The number of Bytes to be unmapped beginning with the lba. */ transfer_len = blk_rq_bytes(rq); + lba = scsi_get_lba(cmd); }

intr = ufshcd_readl(hba, REG_INTERRUPT_STATUS);

From: Takashi Iwai tiwai@suse.de

commit 0665886ad1392e6b5bae85d7a6ccbed48dca1522 upstream.

When a rawmidi output stream is closed, it calls the drain at first, then does trigger-off only when the drain returns -ERESTARTSYS as a fallback. It implies that each driver should turn off the stream properly after the drain. Meanwhile, USB-audio MIDI interface didn't change the port->active flag after the drain. This may leave the output work picking up the port that is closed right now, which eventually leads to a use-after-free for the already released rawmidi object.

This patch fixes the bug by properly clearing the port->active flag after the output drain.

Reported-by: syzbot+70e777a39907d6d5fd0a@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/00000000000011555605dceaff03@google.com Link: https://lore.kernel.org/r/20220420130247.22062-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/midi.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -1194,6 +1194,7 @@ static void snd_usbmidi_output_drain(str } while (drain_urbs && timeout); finish_wait(&ep->drain_wait, &wait); } + port->active = 0; spin_unlock_irq(&ep->buffer_lock); }

From: Mark Brown broonie@kernel.org

[ Upstream commit c775cbf62ed4911e4f0f23880f01815753123690 ]

The MCLK of the WM8731 on the AT91SAM9G20-EK board is connected to the PCK0 output of the SoC, intended in the reference software to be supplied using PLLB and programmed to 12MHz. As originally written for use with a board file the audio driver was responsible for configuring the entire tree but in the conversion to the common clock framework the registration of the named pck0 and pllb clocks was removed so the driver has failed to instantiate ever since.

Since the WM8731 driver has had support for managing a MCLK provided via the common clock framework for some time we can simply drop all the clock management code from the machine driver other than configuration of the sysclk rate, the CODEC driver still respects that configuration from the machine driver.

Fixes: ff78a189b0ae55f ("ARM: at91: remove old at91-specific clock driver") Signed-off-by: Mark Brown broonie@kernel.org Reviewed-by: Codrin Ciubotariu codrin.ciubotariu@microchip.com Link: https://lore.kernel.org/r/20220325154241.1600757-2-broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/atmel/sam9g20_wm8731.c | 61 -------------------------------- 1 file changed, 61 deletions(-)

diff --git a/sound/soc/atmel/sam9g20_wm8731.c b/sound/soc/atmel/sam9g20_wm8731.c index 8a55d59a6c2a..d243de5f23dc 100644 --- a/sound/soc/atmel/sam9g20_wm8731.c +++ b/sound/soc/atmel/sam9g20_wm8731.c @@ -46,35 +46,6 @@ */ #undef ENABLE_MIC_INPUT

-static struct clk *mclk; - -static int at91sam9g20ek_set_bias_level(struct snd_soc_card *card, - struct snd_soc_dapm_context *dapm, - enum snd_soc_bias_level level) -{ - static int mclk_on; - int ret = 0; - - switch (level) { - case SND_SOC_BIAS_ON: - case SND_SOC_BIAS_PREPARE: - if (!mclk_on) - ret = clk_enable(mclk); - if (ret == 0) - mclk_on = 1; - break; - - case SND_SOC_BIAS_OFF: - case SND_SOC_BIAS_STANDBY: - if (mclk_on) - clk_disable(mclk); - mclk_on = 0; - break; - } - - return ret; -} - static const struct snd_soc_dapm_widget at91sam9g20ek_dapm_widgets[] = { SND_SOC_DAPM_MIC("Int Mic", NULL), SND_SOC_DAPM_SPK("Ext Spk", NULL), @@ -135,7 +106,6 @@ static struct snd_soc_card snd_soc_at91sam9g20ek = { .owner = THIS_MODULE, .dai_link = &at91sam9g20ek_dai, .num_links = 1, - .set_bias_level = at91sam9g20ek_set_bias_level,

.dapm_widgets = at91sam9g20ek_dapm_widgets, .num_dapm_widgets = ARRAY_SIZE(at91sam9g20ek_dapm_widgets), @@ -148,7 +118,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct device_node *codec_np, *cpu_np; - struct clk *pllb; struct snd_soc_card *card = &snd_soc_at91sam9g20ek; int ret;

@@ -162,31 +131,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) return -EINVAL; }

- /* - * Codec MCLK is supplied by PCK0 - set it up. - */ - mclk = clk_get(NULL, "pck0"); - if (IS_ERR(mclk)) { - dev_err(&pdev->dev, "Failed to get MCLK\n"); - ret = PTR_ERR(mclk); - goto err; - } - - pllb = clk_get(NULL, "pllb"); - if (IS_ERR(pllb)) { - dev_err(&pdev->dev, "Failed to get PLLB\n"); - ret = PTR_ERR(pllb); - goto err_mclk; - } - ret = clk_set_parent(mclk, pllb); - clk_put(pllb); - if (ret != 0) { - dev_err(&pdev->dev, "Failed to set MCLK parent\n"); - goto err_mclk; - } - - clk_set_rate(mclk, MCLK_RATE); - card->dev = &pdev->dev;

/* Parse device node info */ @@ -230,9 +174,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev)

return ret;

-err_mclk: - clk_put(mclk); - mclk = NULL; err: atmel_ssc_put_audio(0); return ret; @@ -242,8 +183,6 @@ static int at91sam9g20ek_audio_remove(struct platform_device *pdev) { struct snd_soc_card *card = platform_get_drvdata(pdev);

- clk_disable(mclk); - mclk = NULL; snd_soc_unregister_card(card); atmel_ssc_put_audio(0);

From: Miaoqian Lin linmq006@gmail.com

[ Upstream commit 8ba08d3a367a70f707b7c5d53ad92b98b960ee88 ]

We need to call clk_put() to undo clk_get() in the error path. Use devm_clk_get() to obtain a reference to the clock, It has the benefit that clk_put() is no longer required.

Fixes: 0d6a04da9b25 ("ASoC: Add Rockchip rk817 audio CODEC support") Signed-off-by: Miaoqian Lin linmq006@gmail.com Link: https://lore.kernel.org/r/20220404090753.17940-1-linmq006@gmail.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/rk817_codec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/rk817_codec.c b/sound/soc/codecs/rk817_codec.c index 8fffe378618d..cce6f4e7992f 100644 --- a/sound/soc/codecs/rk817_codec.c +++ b/sound/soc/codecs/rk817_codec.c @@ -489,7 +489,7 @@ static int rk817_platform_probe(struct platform_device *pdev)

rk817_codec_parse_dt_property(&pdev->dev, rk817_codec_data);

- rk817_codec_data->mclk = clk_get(pdev->dev.parent, "mclk"); + rk817_codec_data->mclk = devm_clk_get(pdev->dev.parent, "mclk"); if (IS_ERR(rk817_codec_data->mclk)) { dev_dbg(&pdev->dev, "Unable to get mclk\n"); ret = -ENXIO;

From: Srinivas Kandagatla srinivas.kandagatla@linaro.org

[ Upstream commit db6dd1bee63d1d88fbddfe07af800af5948ac28e ]

SIDO(Single-Inductor Dual-Ouput) Buck powers up both analog and digital circuits along with internal memory, powering off this is the last thing that codec should do when going to very low power.

Current code was powering off this Buck if there are no users of sysclk, which is not correct. Powering off this buck will result in no register access. This code path was never tested until recently after adding pm support in SoundWire controller. Fix this by removing the buck poweroff when the codec is active and also the code that is not used.

Without this patch all the read/write transactions will never complete and results in SLIMBus Errors like:

qcom,slim-ngd qcom,slim-ngd.1: Tx:MT:0x0, MC:0x60, LA:0xcf failed:-110 wcd934x-codec wcd934x-codec.1.auto: ASoC: error at soc_component_read_no_lock on wcd934x-codec.1.auto for register: [0x00000d05] -110 qcom,slim-ngd-ctrl 171c0000.slim: Error Interrupt received 0x82000000

Reported-by: Amit Pundir amit.pundir@linaro.org Fixes: a61f3b4f476e ("ASoC: wcd934x: add support to wcd9340/wcd9341 codec") Signed-off-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Tested-by: Amit Pundir amit.pundir@linaro.org Link: https://lore.kernel.org/r/20220407094313.2880-1-srinivas.kandagatla@linaro.o... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/wcd934x.c | 26 +------------------------- 1 file changed, 1 insertion(+), 25 deletions(-)

diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c index 7b99318070cf..144046864d15 100644 --- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -1274,29 +1274,7 @@ static int wcd934x_set_sido_input_src(struct wcd934x_codec *wcd, int sido_src) if (sido_src == wcd->sido_input_src) return 0;

- if (sido_src == SIDO_SOURCE_INTERNAL) { - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_EN_MASK, 0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_PRE_ENX_MASK, 0x0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_RCO, - WCD934X_ANA_RCO_BG_EN_MASK, 0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_PRE_EN1_MASK, - WCD934X_ANA_BUCK_PRE_EN1_ENABLE); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_PRE_EN2_MASK, - WCD934X_ANA_BUCK_PRE_EN2_ENABLE); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_EN_MASK, - WCD934X_ANA_BUCK_HI_ACCU_ENABLE); - usleep_range(100, 110); - } else if (sido_src == SIDO_SOURCE_RCO_BG) { + if (sido_src == SIDO_SOURCE_RCO_BG) { regmap_update_bits(wcd->regmap, WCD934X_ANA_RCO, WCD934X_ANA_RCO_BG_EN_MASK, WCD934X_ANA_RCO_BG_ENABLE); @@ -1382,8 +1360,6 @@ static int wcd934x_disable_ana_bias_and_syclk(struct wcd934x_codec *wcd) regmap_update_bits(wcd->regmap, WCD934X_CLK_SYS_MCLK_PRG, WCD934X_EXT_CLK_BUF_EN_MASK | WCD934X_MCLK_EN_MASK, 0x0); - wcd934x_set_sido_input_src(wcd, SIDO_SOURCE_INTERNAL); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BIAS, WCD934X_ANA_BIAS_EN_MASK, 0); regmap_update_bits(wcd->regmap, WCD934X_ANA_BIAS,

From: Miaoqian Lin linmq006@gmail.com

[ Upstream commit 7104b9cb35a33ad803a1adbbfa50569b008faf15 ]

of_parse_phandle() returns NULL on errors, rather than error pointers. Using NULL check on grp_np to fix this.

Fixes: d078cd1b4185 ("dmaengine: imx-sdma: Add imx6sx platform support") Signed-off-by: Miaoqian Lin linmq006@gmail.com Link: https://lore.kernel.org/r/20220308064952.15743-1-linmq006@gmail.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/imx-sdma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index cacc725ca545..263f0466b1b8 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1869,7 +1869,7 @@ static int sdma_event_remap(struct sdma_engine *sdma) u32 reg, val, shift, num_map, i; int ret = 0;

- if (IS_ERR(np) || IS_ERR(gpr_np)) + if (IS_ERR(np) || !gpr_np) goto out;

event_remap = of_find_property(np, propname, NULL); @@ -1917,7 +1917,7 @@ static int sdma_event_remap(struct sdma_engine *sdma) }

out: - if (!IS_ERR(gpr_np)) + if (gpr_np) of_node_put(gpr_np);

return ret;

From: Herve Codina herve.codina@bootlin.com

[ Upstream commit 8fc5133d6d4da65cad6b73152fc714ad3d7f91c1 ]

On some arch (ie aarch64 iMX8MM) unaligned PCIe accesses are not allowed and lead to a kernel Oops. [ 1911.668835] Unable to handle kernel paging request at virtual address ffff80001bc00a8c [ 1911.668841] Mem abort info: [ 1911.668844] ESR = 0x96000061 [ 1911.668847] EC = 0x25: DABT (current EL), IL = 32 bits [ 1911.668850] SET = 0, FnV = 0 [ 1911.668852] EA = 0, S1PTW = 0 [ 1911.668853] Data abort info: [ 1911.668855] ISV = 0, ISS = 0x00000061 [ 1911.668857] CM = 0, WnR = 1 [ 1911.668861] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000040ff4000 [ 1911.668864] [ffff80001bc00a8c] pgd=00000000bffff003, pud=00000000bfffe003, pmd=0068000018400705 [ 1911.668872] Internal error: Oops: 96000061 [#1] PREEMPT SMP ...

The llp register present in the channel group registers is not aligned on 64bit.

Fix unaligned 64bit access using two 32bit accesses

Fixes: 04e0a39fc10f ("dmaengine: dw-edma: Add writeq() and readq() for 64 bits architectures") Signed-off-by: Herve Codina herve.codina@bootlin.com Link: https://lore.kernel.org/r/20220225120252.309404-1-herve.codina@bootlin.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/dw-edma/dw-edma-v0-core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index 329fc2e57b70..b5b8f8181e77 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -415,8 +415,11 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) (DW_EDMA_V0_CCS | DW_EDMA_V0_LLE)); /* Linked list */ #ifdef CONFIG_64BIT - SET_CH_64(dw, chan->dir, chan->id, llp.reg, - chunk->ll_region.paddr); + /* llp is not aligned on 64bit -> keep 32bit accesses */ + SET_CH_32(dw, chan->dir, chan->id, llp.lsb, + lower_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.msb, + upper_32_bits(chunk->ll_region.paddr)); #else /* CONFIG_64BIT */ SET_CH_32(dw, chan->dir, chan->id, llp.lsb, lower_32_bits(chunk->ll_region.paddr));

From: Sabrina Dubroca sd@queasysnail.net

[ Upstream commit 5bd8baab087dff657e05387aee802e70304cc813 ]

Commit ebe48d368e97 ("esp: Fix possible buffer overflow in ESP transformation") tried to fix skb_page_frag_refill usage in ESP by capping allocsize to 32k, but that doesn't completely solve the issue, as skb_page_frag_refill may return a single page. If that happens, we will write out of bounds, despite the check introduced in the previous patch.

This patch forces COW in cases where we would end up calling skb_page_frag_refill with a size larger than a page (first in esp_output_head with tailen, then in esp_output_tail with skb->data_len).

Fixes: cac2661c53f3 ("esp4: Avoid skb_cow_data whenever possible") Fixes: 03e2a30f6a27 ("esp6: Avoid skb_cow_data whenever possible") Signed-off-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/esp.h | 2 -- net/ipv4/esp4.c | 5 ++--- net/ipv6/esp6.c | 5 ++--- 3 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/include/net/esp.h b/include/net/esp.h index 90cd02ff77ef..9c5637d41d95 100644 --- a/include/net/esp.h +++ b/include/net/esp.h @@ -4,8 +4,6 @@

#include <linux/skbuff.h>

-#define ESP_SKB_FRAG_MAXSIZE (PAGE_SIZE << SKB_FRAG_PAGE_ORDER) - struct ip_esp_hdr;

static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 70e6c87fbe3d..d747166bb291 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -446,7 +446,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz;

/* this is non-NULL only with TCP/UDP Encapsulation */ if (x->encap) { @@ -456,8 +455,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * return err; }

- allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow;

if (!skb_cloned(skb)) { diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 5023f59a5b96..6219d97cac7a 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -483,7 +483,6 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz;

if (x->encap) { int err = esp6_output_encap(x, skb, esp); @@ -492,8 +491,8 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info return err; }

- allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow;

if (!skb_cloned(skb)) {

From: Sasha Neftin sasha.neftin@intel.com

[ Upstream commit 907862e9aef75bf89e2b265efcc58870be06081e ]

An infinite loop may occur if we fail to acquire the HW semaphore, which is needed for resource release. This will typically happen if the hardware is surprise-removed. At this stage there is nothing to do, except log an error and quit.

Fixes: c0071c7aa5fe ("igc: Add HW initialization code") Suggested-by: Dima Ruinskiy dima.ruinskiy@intel.com Signed-off-by: Sasha Neftin sasha.neftin@intel.com Tested-by: Naama Meir naamax.meir@linux.intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igc/igc_i225.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index b6807e16eea9..a0e2a404d535 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -156,8 +156,15 @@ void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask) { u32 swfw_sync;

- while (igc_get_hw_semaphore_i225(hw)) - ; /* Empty */ + /* Releasing the resource requires first getting the HW semaphore. + * If we fail to get the semaphore, there is nothing we can do, + * except log an error and quit. We are not allowed to hang here + * indefinitely, as it may cause denial of service or system crash. + */ + if (igc_get_hw_semaphore_i225(hw)) { + hw_dbg("Failed to release SW_FW_SYNC.\n"); + return; + }

swfw_sync = rd32(IGC_SW_FW_SYNC); swfw_sync &= ~mask;

From: Vinicius Costa Gomes vinicius.gomes@intel.com

[ Upstream commit 822f52e7efdc88fccffb9fbf6250a4b7666a0b0f ]

Some mainboard/CPU combinations, in particular, Alder Lake-S with a W680 mainboard, have shown problems (system hangs usually, no kernel logs) with suspend/resume when PCIe PTM is enabled and active. In some cases, it could be reproduced when removing the igc module.

The best we can do is to stop PTM dialogs from the downstream/device side before the interface is brought down. PCIe PTM will be re-enabled when the interface is being brought up.

Fixes: a90ec8483732 ("igc: Add support for PTP getcrosststamp()") Signed-off-by: Vinicius Costa Gomes vinicius.gomes@intel.com Tested-by: Naama Meir naamax.meir@linux.intel.com Acked-by: Paul Menzel pmenzel@molgen.mpg.de Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igc/igc_ptp.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 4f9245aa79a1..8e521f99b80a 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -996,6 +996,17 @@ static void igc_ptp_time_restore(struct igc_adapter *adapter) igc_ptp_write_i225(adapter, &ts); }

+static void igc_ptm_stop(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 ctrl; + + ctrl = rd32(IGC_PTM_CTRL); + ctrl &= ~IGC_PTM_CTRL_EN; + + wr32(IGC_PTM_CTRL, ctrl); +} + /** * igc_ptp_suspend - Disable PTP work items and prepare for suspend * @adapter: Board private structure @@ -1013,8 +1024,10 @@ void igc_ptp_suspend(struct igc_adapter *adapter) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);

- if (pci_device_is_present(adapter->pdev)) + if (pci_device_is_present(adapter->pdev)) { igc_ptp_time_save(adapter); + igc_ptm_stop(adapter); + } }

/**

From: David Howells dhowells@redhat.com

[ Upstream commit ee3b0826b4764f6c13ad6db67495c5a1c38e9025 ]

A recent patch[1] from Eric Dumazet flipped the order in which the keepalive timer and the keepalive worker were cancelled in order to fix a syzbot reported issue[2]. Unfortunately, this enables the mirror image bug whereby the timer races with rxrpc_exit_net(), restarting the worker after it has been cancelled:

CPU 1 CPU 2 =============== ===================== if (rxnet->live) <INTERRUPT> rxnet->live = false; cancel_work_sync(&rxnet->peer_keepalive_work); rxrpc_queue_work(&rxnet->peer_keepalive_work); del_timer_sync(&rxnet->peer_keepalive_timer);

Fix this by restoring the removed del_timer_sync() so that we try to remove the timer twice. If the timer runs again, it should see ->live == false and not restart the worker.

Fixes: 1946014ca3b1 ("rxrpc: fix a race in rxrpc_exit_net()") Signed-off-by: David Howells dhowells@redhat.com cc: Eric Dumazet edumazet@google.com cc: Marc Dionne marc.dionne@auristor.com cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/20220404183439.3537837-1-eric.dumazet@gmail.com/ [1] Link: https://syzkaller.appspot.com/bug?extid=724378c4bb58f703b09a [2] Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/rxrpc/net_ns.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index f15d6942da45..cc7e30733feb 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -113,7 +113,9 @@ static __net_exit void rxrpc_exit_net(struct net *net) struct rxrpc_net *rxnet = rxrpc_net(net);

rxnet->live = false; + del_timer_sync(&rxnet->peer_keepalive_timer); cancel_work_sync(&rxnet->peer_keepalive_work); + /* Remove the timer again as the worker may have restarted it. */ del_timer_sync(&rxnet->peer_keepalive_timer); rxrpc_destroy_all_calls(rxnet); rxrpc_destroy_all_connections(rxnet);

From: Hangbin Liu liuhangbin@gmail.com

[ Upstream commit 29e8e659f984be00d75ec5fef4e37c88def72712 ]

packet_sock xmit could be dev_queue_xmit, which also returns negative errors. So only checking positive errors is not enough, or userspace sendmsg may return success while packet is not send out.

Move the net_xmit_errno() assignment in the braces as checkpatch.pl said do not use assignment in if condition.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Flavio Leitner fbl@redhat.com Signed-off-by: Hangbin Liu liuhangbin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/packet/af_packet.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c0d4a65931de..88c3b5cf8d94 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2820,8 +2820,9 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)

status = TP_STATUS_SEND_REQUEST; err = po->xmit(skb); - if (unlikely(err > 0)) { - err = net_xmit_errno(err); + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ @@ -3022,8 +3023,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->no_fcs = 1;

err = po->xmit(skb); - if (err > 0 && (err = net_xmit_errno(err)) != 0) - goto out_unlock; + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); + if (err) + goto out_unlock; + }

dev_put(dev);

From: Peilin Ye peilin.ye@bytedance.com

[ Upstream commit ab198e1d0dd8dc4bc7575fb50758e2cbd51e14e1 ]

Feng reported an skb_under_panic BUG triggered by running test_ip6gretap() in tools/testing/selftests/bpf/test_tunnel.sh:

[ 82.492551] skbuff: skb_under_panic: text:ffffffffb268bb8e len:403 put:12 head:ffff9997c5480000 data:ffff9997c547fff8 tail:0x18b end:0x2c0 dev:ip6gretap11 <...> [ 82.607380] Call Trace: [ 82.609389] <TASK> [ 82.611136] skb_push.cold.109+0x10/0x10 [ 82.614289] __gre6_xmit+0x41e/0x590 [ 82.617169] ip6gre_tunnel_xmit+0x344/0x3f0 [ 82.620526] dev_hard_start_xmit+0xf1/0x330 [ 82.623882] sch_direct_xmit+0xe4/0x250 [ 82.626961] __dev_queue_xmit+0x720/0xfe0 <...> [ 82.633431] packet_sendmsg+0x96a/0x1cb0 [ 82.636568] sock_sendmsg+0x30/0x40 <...>

The following sequence of events caused the BUG:

1. During ip6gretap device initialization, tunnel->tun_hlen (e.g. 4) is calculated based on old flags (see ip6gre_calc_hlen()); 2. packet_snd() reserves header room for skb A, assuming tunnel->tun_hlen is 4; 3. Later (in clsact Qdisc), the eBPF program sets a new tunnel key for skb A using bpf_skb_set_tunnel_key() (see _ip6gretap_set_tunnel()); 4. __gre6_xmit() detects the new tunnel key, and recalculates "tun_hlen" (e.g. 12) based on new flags (e.g. TUNNEL_KEY and TUNNEL_SEQ); 5. gre_build_header() calls skb_push() with insufficient reserved header room, triggering the BUG.

As sugguested by Cong, fix it by moving the call to skb_cow_head() after the recalculation of tun_hlen.

Reproducer:

OBJ=$LINUX/tools/testing/selftests/bpf/test_tunnel_kern.o

ip netns add at_ns0 ip link add veth0 type veth peer name veth1 ip link set veth0 netns at_ns0 ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 ip netns exec at_ns0 ip link set dev veth0 up ip link set dev veth1 up mtu 1500 ip addr add dev veth1 172.16.1.200/24

ip netns exec at_ns0 ip addr add ::11/96 dev veth0 ip netns exec at_ns0 ip link set dev veth0 up ip addr add dev veth1 ::22/96 ip link set dev veth1 up

ip netns exec at_ns0 \ ip link add dev ip6gretap00 type ip6gretap seq flowlabel 0xbcdef key 2 \ local ::11 remote ::22

ip netns exec at_ns0 ip addr add dev ip6gretap00 10.1.1.100/24 ip netns exec at_ns0 ip addr add dev ip6gretap00 fc80::100/96 ip netns exec at_ns0 ip link set dev ip6gretap00 up

ip link add dev ip6gretap11 type ip6gretap external ip addr add dev ip6gretap11 10.1.1.200/24 ip addr add dev ip6gretap11 fc80::200/24 ip link set dev ip6gretap11 up

tc qdisc add dev ip6gretap11 clsact tc filter add dev ip6gretap11 egress bpf da obj $OBJ sec ip6gretap_set_tunnel tc filter add dev ip6gretap11 ingress bpf da obj $OBJ sec ip6gretap_get_tunnel

ping6 -c 3 -w 10 -q ::11

Fixes: 6712abc168eb ("ip6_gre: add ip6 gre and gretap collect_md mode") Reported-by: Feng Zhou zhoufeng.zf@bytedance.com Co-developed-by: Cong Wang cong.wang@bytedance.com Signed-off-by: Cong Wang cong.wang@bytedance.com Signed-off-by: Peilin Ye peilin.ye@bytedance.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_gre.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 288720838329..869c3337e319 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -733,9 +733,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, else fl6->daddr = tunnel->parms.raddr;

- if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) - return -ENOMEM; - /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;

@@ -763,6 +760,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); tun_hlen = gre_calc_hlen(flags);

+ if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) + return -ENOMEM; + gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), @@ -773,6 +773,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, if (tunnel->parms.o_flags & TUNNEL_SEQ) tunnel->o_seqno++;

+ if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) + return -ENOMEM; + gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno));

From: Eric Dumazet edumazet@google.com

[ Upstream commit ec5b0f605b105457f257f2870acad4a5d463984b ]

While investigating a related syzbot report, I found that whenever call to tcf_exts_init() from u32_init_knode() is failing, we end up with an elevated refcount on ht->refcnt

To avoid that, only increase the refcount after all possible errors have been evaluated.

Fixes: b9a24bb76bf6 ("net_sched: properly handle failure case of tcf_exts_init()") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Cong Wang xiyou.wangcong@gmail.com Cc: Jiri Pirko jiri@resnulli.us Acked-by: Jamal Hadi Salim jhs@mojatatu.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/cls_u32.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 81f933ebee05..5d30db0d7157 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -814,10 +814,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht);

- /* bump reference count as long as we hold pointer to structure */ - if (ht) - ht->refcnt++; - #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update * so we must keep them in tact. When the node is later destroyed @@ -839,6 +835,10 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, return NULL; }

+ /* bump reference count as long as we hold pointer to structure */ + if (ht) + ht->refcnt++; + return new; }

From: Eric Dumazet edumazet@google.com

[ Upstream commit 9cb7c013420f98fa6fd12fc6a5dc055170c108db ]

Reads and Writes to ip6_rt_gc_expire always have been racy, as syzbot reported lately [1]

There is a possible risk of under-flow, leading to unexpected high value passed to fib6_run_gc(), although I have not observed this in the field.

Hosts hitting ip6_dst_gc() very hard are under pretty bad state anyway.

[1] BUG: KCSAN: data-race in ip6_dst_gc / ip6_dst_gc

read-write to 0xffff888102110744 of 4 bytes by task 13165 on cpu 1: ip6_dst_gc+0x1f3/0x220 net/ipv6/route.c:3311 dst_alloc+0x9b/0x160 net/core/dst.c:86 ip6_dst_alloc net/ipv6/route.c:344 [inline] icmp6_dst_alloc+0xb2/0x360 net/ipv6/route.c:3261 mld_sendpack+0x2b9/0x580 net/ipv6/mcast.c:1807 mld_send_cr net/ipv6/mcast.c:2119 [inline] mld_ifc_work+0x576/0x800 net/ipv6/mcast.c:2651 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289 worker_thread+0x618/0xa70 kernel/workqueue.c:2436 kthread+0x1a9/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30

read-write to 0xffff888102110744 of 4 bytes by task 11607 on cpu 0: ip6_dst_gc+0x1f3/0x220 net/ipv6/route.c:3311 dst_alloc+0x9b/0x160 net/core/dst.c:86 ip6_dst_alloc net/ipv6/route.c:344 [inline] icmp6_dst_alloc+0xb2/0x360 net/ipv6/route.c:3261 mld_sendpack+0x2b9/0x580 net/ipv6/mcast.c:1807 mld_send_cr net/ipv6/mcast.c:2119 [inline] mld_ifc_work+0x576/0x800 net/ipv6/mcast.c:2651 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289 worker_thread+0x618/0xa70 kernel/workqueue.c:2436 kthread+0x1a9/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30

value changed: 0x00000bb3 -> 0x00000ba9

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 11607 Comm: kworker/0:21 Not tainted 5.18.0-rc1-syzkaller-00037-g42e7a03d3bad-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: mld mld_ifc_work

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Reviewed-by: David Ahern dsahern@kernel.org Link: https://lore.kernel.org/r/20220413181333.649424-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/netns/ipv6.h | 4 ++-- net/ipv6/route.c | 11 ++++++----- 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 6bd7e5a85ce7..ff82983b7ab4 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -75,8 +75,8 @@ struct netns_ipv6 { struct list_head fib6_walkers; rwlock_t fib6_walker_lock; spinlock_t fib6_gc_lock; - unsigned int ip6_rt_gc_expire; - unsigned long ip6_rt_last_gc; + atomic_t ip6_rt_gc_expire; + unsigned long ip6_rt_last_gc; unsigned char flowlabel_has_excl; #ifdef CONFIG_IPV6_MULTIPLE_TABLES bool fib6_has_custom_rules; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6b269595efaa..0ca7c780d97a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3303,6 +3303,7 @@ static int ip6_dst_gc(struct dst_ops *ops) int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + unsigned int val; int entries;

entries = dst_entries_get_fast(ops); @@ -3313,13 +3314,13 @@ static int ip6_dst_gc(struct dst_ops *ops) entries <= rt_max_size) goto out;

- net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); + fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) - net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; + atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: - net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; + val = atomic_read(&net->ipv6.ip6_rt_gc_expire); + atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); return entries > rt_max_size; }

@@ -6528,7 +6529,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0;

- net->ipv6.ip6_rt_gc_expire = 30*HZ; + atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ);

ret = 0; out:

From: Kurt Kanzenbach kurt@linutronix.de

[ Upstream commit 0763120b090418a5257402754e22a34227ae5f12 ]

In case the checksum calculation is offloaded to the DSA master network interface, it will include the switch trailing tag. As soon as the switch strips that tag on egress, the calculated checksum is wrong.

Therefore, add the checksum calculation to the tagger (if required) before adding the switch tag. This way, the hellcreek code works with all DSA master interfaces regardless of their declared feature set.

Fixes: 01ef09caad66 ("net: dsa: Add tag handling for Hirschmann Hellcreek switches") Signed-off-by: Kurt Kanzenbach kurt@linutronix.de Reviewed-by: Florian Fainelli f.fainelli@gmail.com Link: https://lore.kernel.org/r/20220415103320.90657-1-kurt@linutronix.de Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/dsa/tag_hellcreek.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index f64b805303cd..eb204ad36eee 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -21,6 +21,14 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, struct dsa_port *dp = dsa_slave_to_port(dev); u8 *tag;

+ /* Calculate checksums (if required) before adding the trailer tag to + * avoid including it in calculations. That would lead to wrong + * checksums after the switch strips the tag. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, HELLCREEK_TAG_LEN); *tag = BIT(dp->index);

From: Eric Dumazet edumazet@google.com

[ Upstream commit 99c07327ae11e24886d552dddbe4537bfca2765d ]

netlink_dump() is allocating an skb, reserves space in it but forgets to reset network header.

This allows a BPF program, invoked later from sk_filter() to access uninitialized kernel memory from the reserved space.

Theorically mac header reset could be omitted, because it is set to a special initial value. bpf_internal_load_pointer_neg_helper calls skb_mac_header() without checking skb_mac_header_was_set(). Relying on skb->len not being too big seems fragile. We also could add a sanity check in bpf_internal_load_pointer_neg_helper() to avoid surprises in the future.

syzbot report was:

BUG: KMSAN: uninit-value in ___bpf_prog_run+0xa22b/0xb420 kernel/bpf/core.c:1637 ___bpf_prog_run+0xa22b/0xb420 kernel/bpf/core.c:1637 __bpf_prog_run32+0x121/0x180 kernel/bpf/core.c:1796 bpf_dispatcher_nop_func include/linux/bpf.h:784 [inline] __bpf_prog_run include/linux/filter.h:626 [inline] bpf_prog_run include/linux/filter.h:633 [inline] __bpf_prog_run_save_cb+0x168/0x580 include/linux/filter.h:756 bpf_prog_run_save_cb include/linux/filter.h:770 [inline] sk_filter_trim_cap+0x3bc/0x8c0 net/core/filter.c:150 sk_filter include/linux/filter.h:905 [inline] netlink_dump+0xe0c/0x16c0 net/netlink/af_netlink.c:2276 netlink_recvmsg+0x1129/0x1c80 net/netlink/af_netlink.c:2002 sock_recvmsg_nosec net/socket.c:948 [inline] sock_recvmsg net/socket.c:966 [inline] sock_read_iter+0x5a9/0x630 net/socket.c:1039 do_iter_readv_writev+0xa7f/0xc70 do_iter_read+0x52c/0x14c0 fs/read_write.c:786 vfs_readv fs/read_write.c:906 [inline] do_readv+0x432/0x800 fs/read_write.c:943 __do_sys_readv fs/read_write.c:1034 [inline] __se_sys_readv fs/read_write.c:1031 [inline] __x64_sys_readv+0xe5/0x120 fs/read_write.c:1031 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x44/0xae

Uninit was stored to memory at: ___bpf_prog_run+0x96c/0xb420 kernel/bpf/core.c:1558 __bpf_prog_run32+0x121/0x180 kernel/bpf/core.c:1796 bpf_dispatcher_nop_func include/linux/bpf.h:784 [inline] __bpf_prog_run include/linux/filter.h:626 [inline] bpf_prog_run include/linux/filter.h:633 [inline] __bpf_prog_run_save_cb+0x168/0x580 include/linux/filter.h:756 bpf_prog_run_save_cb include/linux/filter.h:770 [inline] sk_filter_trim_cap+0x3bc/0x8c0 net/core/filter.c:150 sk_filter include/linux/filter.h:905 [inline] netlink_dump+0xe0c/0x16c0 net/netlink/af_netlink.c:2276 netlink_recvmsg+0x1129/0x1c80 net/netlink/af_netlink.c:2002 sock_recvmsg_nosec net/socket.c:948 [inline] sock_recvmsg net/socket.c:966 [inline] sock_read_iter+0x5a9/0x630 net/socket.c:1039 do_iter_readv_writev+0xa7f/0xc70 do_iter_read+0x52c/0x14c0 fs/read_write.c:786 vfs_readv fs/read_write.c:906 [inline] do_readv+0x432/0x800 fs/read_write.c:943 __do_sys_readv fs/read_write.c:1034 [inline] __se_sys_readv fs/read_write.c:1031 [inline] __x64_sys_readv+0xe5/0x120 fs/read_write.c:1031 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x44/0xae

Uninit was created at: slab_post_alloc_hook mm/slab.h:737 [inline] slab_alloc_node mm/slub.c:3244 [inline] __kmalloc_node_track_caller+0xde3/0x14f0 mm/slub.c:4972 kmalloc_reserve net/core/skbuff.c:354 [inline] __alloc_skb+0x545/0xf90 net/core/skbuff.c:426 alloc_skb include/linux/skbuff.h:1158 [inline] netlink_dump+0x30f/0x16c0 net/netlink/af_netlink.c:2242 netlink_recvmsg+0x1129/0x1c80 net/netlink/af_netlink.c:2002 sock_recvmsg_nosec net/socket.c:948 [inline] sock_recvmsg net/socket.c:966 [inline] sock_read_iter+0x5a9/0x630 net/socket.c:1039 do_iter_readv_writev+0xa7f/0xc70 do_iter_read+0x52c/0x14c0 fs/read_write.c:786 vfs_readv fs/read_write.c:906 [inline] do_readv+0x432/0x800 fs/read_write.c:943 __do_sys_readv fs/read_write.c:1034 [inline] __se_sys_readv fs/read_write.c:1031 [inline] __x64_sys_readv+0xe5/0x120 fs/read_write.c:1031 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x44/0xae

CPU: 0 PID: 3470 Comm: syz-executor751 Not tainted 5.17.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: db65a3aaf29e ("netlink: Trim skb to alloc size to avoid MSG_TRUNC") Fixes: 9063e21fb026 ("netlink: autosize skb lengthes") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Link: https://lore.kernel.org/r/20220415181442.551228-1-eric.dumazet@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/netlink/af_netlink.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 83ca93b32f5f..fb7f7b17c78c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2284,6 +2284,13 @@ static int netlink_dump(struct sock *sk) * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); + + /* Make sure malicious BPF programs can not read unitialized memory + * from skb->head -> skb->data + */ + skb_reset_network_header(skb); + skb_reset_mac_header(skb); + netlink_skb_set_owner_r(skb, sk);

if (nlk->dump_done_errno > 0) {

From: Kevin Hao haokexin@gmail.com

[ Upstream commit 234901de2bc6847eaa0aeb4aba62c31ffb8d3ad6 ]

The init_systime() may be invoked in atomic state. We have observed the following call trace when running "phc_ctl /dev/ptp0 set" on a Intel Agilex board. BUG: sleeping function called from invalid context at drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c:74 in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 381, name: phc_ctl preempt_count: 1, expected: 0 RCU nest depth: 0, expected: 0 Preemption disabled at: [<ffff80000892ef78>] stmmac_set_time+0x34/0x8c CPU: 2 PID: 381 Comm: phc_ctl Not tainted 5.18.0-rc2-next-20220414-yocto-standard+ #567 Hardware name: SoCFPGA Agilex SoCDK (DT) Call trace: dump_backtrace.part.0+0xc4/0xd0 show_stack+0x24/0x40 dump_stack_lvl+0x7c/0xa0 dump_stack+0x18/0x34 __might_resched+0x154/0x1c0 __might_sleep+0x58/0x90 init_systime+0x78/0x120 stmmac_set_time+0x64/0x8c ptp_clock_settime+0x60/0x9c pc_clock_settime+0x6c/0xc0 __arm64_sys_clock_settime+0x88/0xf0 invoke_syscall+0x5c/0x130 el0_svc_common.constprop.0+0x4c/0x100 do_el0_svc+0x7c/0xa0 el0_svc+0x58/0xcc el0t_64_sync_handler+0xa4/0x130 el0t_64_sync+0x18c/0x190

So we should use readl_poll_timeout_atomic() here instead of readl_poll_timeout().

Also adjust the delay time to 10us to fix a "__bad_udelay" build error reported by "kernel test robot lkp@intel.com". I have tested this on Intel Agilex and NXP S32G boards, there is no delay needed at all. So the 10us delay should be long enough for most cases.

Fixes: ff8ed737860e ("net: stmmac: use readl_poll_timeout() function in init_systime()") Signed-off-by: Kevin Hao haokexin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index a7ec9f4d46ce..d68ef72dcdde 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -71,9 +71,9 @@ static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) writel(value, ioaddr + PTP_TCR);

/* wait for present system time initialize to complete */ - return readl_poll_timeout(ioaddr + PTP_TCR, value, + return readl_poll_timeout_atomic(ioaddr + PTP_TCR, value, !(value & PTP_TCR_TSINIT), - 10000, 100000); + 10, 100000); }

static int config_addend(void __iomem *ioaddr, u32 addend)

From: Dave Jiang dave.jiang@intel.com

[ Upstream commit 505a2d1032ae656b0a8c736be110255503941cde ]

Block wq_max_transfer_size_store() when the device is configured as read-only and not configurable.

Fixes: d7aad5550eca ("dmaengine: idxd: add support for configurable max wq xfer size") Reported-by: Bernice Zhang bernice.zhang@intel.com Tested-by: Bernice Zhang bernice.zhang@intel.com Signed-off-by: Dave Jiang dave.jiang@intel.com Link: https://lore.kernel.org/r/164971488154.2200913.10706665404118545941.stgit@dj... Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/idxd/sysfs.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index f7ab5c077a2b..33d94c67fedb 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -842,6 +842,9 @@ static ssize_t wq_max_transfer_size_store(struct device *dev, struct device_attr u64 xfer_size; int rc;

+ if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + if (wq->state != IDXD_WQ_DISABLED) return -EPERM;

From: Ido Schimmel idosch@nvidia.com

[ Upstream commit 044011fdf162c5dd61c02841930c8f438a9adadb ]

The test verifies that packets are correctly flooded by the bridge and the VXLAN device by matching on the encapsulated packets at the other end. However, if packets other than those generated by the test also ingress the bridge (e.g., MLD packets), they will be flooded as well and interfere with the expected count.

Make the test more robust by making sure that only the packets generated by the test can ingress the bridge. Drop all the rest using tc filters on the egress of 'br0' and 'h1'.

In the software data path, the problem can be solved by matching on the inner destination MAC or dropping unwanted packets at the egress of the VXLAN device, but this is not currently supported by mlxsw.

Fixes: 94d302deae25 ("selftests: mlxsw: Add a test for VxLAN flooding") Signed-off-by: Ido Schimmel idosch@nvidia.com Reviewed-by: Amit Cohen amcohen@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../drivers/net/mlxsw/vxlan_flooding.sh | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh index fedcb7b35af9..af5ea50ed5c0 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh @@ -172,6 +172,17 @@ flooding_filters_add() local lsb local i

+ # Prevent unwanted packets from entering the bridge and interfering + # with the test. + tc qdisc add dev br0 clsact + tc filter add dev br0 egress protocol all pref 1 handle 1 \ + matchall skip_hw action drop + tc qdisc add dev $h1 clsact + tc filter add dev $h1 egress protocol all pref 1 handle 1 \ + flower skip_hw dst_mac de:ad:be:ef:13:37 action pass + tc filter add dev $h1 egress protocol all pref 2 handle 2 \ + matchall skip_hw action drop + tc qdisc add dev $rp2 clsact

for i in $(eval echo {1..$num_remotes}); do @@ -194,6 +205,12 @@ flooding_filters_del() done

tc qdisc del dev $rp2 clsact + + tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall + tc filter del dev $h1 egress protocol all pref 1 handle 1 flower + tc qdisc del dev $h1 clsact + tc filter del dev br0 egress protocol all pref 1 handle 1 matchall + tc qdisc del dev br0 clsact }

flooding_check_packets()

From: Kees Cook keescook@chromium.org

[ Upstream commit b3f1dd52c991d79118f35e6d1bf4d7cb09882e38 ]

When building multi_v7_defconfig+CONFIG_SMP=n, -Warray-bounds exposes a couple negative array index accesses:

arch/arm/mach-vexpress/spc.c: In function 've_spc_clk_init': arch/arm/mach-vexpress/spc.c:583:21: warning: array subscript -1 is below array bounds of 'bool[2]' {aka '_Bool[2]'} [-Warray-bounds] 583 | if (init_opp_table[cluster]) | ~~~~~~~~~~~~~~^~~~~~~~~ arch/arm/mach-vexpress/spc.c:556:7: note: while referencing 'init_opp_table' 556 | bool init_opp_table[MAX_CLUSTERS] = { false }; | ^~~~~~~~~~~~~~ arch/arm/mach-vexpress/spc.c:592:18: warning: array subscript -1 is below array bounds of 'bool[2]' {aka '_Bool[2]'} [-Warray-bounds] 592 | init_opp_table[cluster] = true; | ~~~~~~~~~~~~~~^~~~~~~~~ arch/arm/mach-vexpress/spc.c:556:7: note: while referencing 'init_opp_table' 556 | bool init_opp_table[MAX_CLUSTERS] = { false }; | ^~~~~~~~~~~~~~

Skip this logic when built !SMP.

Link: https://lore.kernel.org/r/20220331190443.851661-1-keescook@chromium.org Cc: Liviu Dudau liviu.dudau@arm.com Cc: Sudeep Holla sudeep.holla@arm.com Cc: Lorenzo Pieralisi lorenzo.pieralisi@arm.com Cc: Russell King linux@armlinux.org.uk Cc: linux-arm-kernel@lists.infradead.org Acked-by: Liviu Dudau liviu.dudau@arm.com Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Sudeep Holla sudeep.holla@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-vexpress/spc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index 1da11bdb1dfb..1c6500c4e6a1 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -580,7 +580,7 @@ static int __init ve_spc_clk_init(void) }

cluster = topology_physical_package_id(cpu_dev->id); - if (init_opp_table[cluster]) + if (cluster < 0 || init_opp_table[cluster]) continue;

if (ve_init_opp_table(cpu_dev))

From: Sameer Pujar spujar@nvidia.com

[ Upstream commit d1da1052ffad63aa5181b69f20a6952e31f339c2 ]

This reverts following commit 69125b4b9440 ("reset: tegra-bpmp: Revert Handle errors in BPMP response").

The Tegra194 HDA reset failure is fixed by commit d278dc9151a0 ("ALSA: hda/tegra: Fix Tegra194 HDA reset failure"). The temporary revert of original commit c045ceb5a145 ("reset: tegra-bpmp: Handle errors in BPMP response") can be removed now.

Signed-off-by: Sameer Pujar spujar@nvidia.com Tested-by: Jon Hunter jonathanh@nvidia.com Reviewed-by: Jon Hunter jonathanh@nvidia.com Acked-by: Thierry Reding treding@nvidia.com Signed-off-by: Philipp Zabel p.zabel@pengutronix.de Link: https://lore.kernel.org/r/1641995806-15245-1-git-send-email-spujar@nvidia.co... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/reset/tegra/reset-bpmp.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c index 24d3395964cc..4c5bba52b105 100644 --- a/drivers/reset/tegra/reset-bpmp.c +++ b/drivers/reset/tegra/reset-bpmp.c @@ -20,6 +20,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc); struct mrq_reset_request request; struct tegra_bpmp_message msg; + int err;

memset(&request, 0, sizeof(request)); request.cmd = command; @@ -30,7 +31,13 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, msg.tx.data = &request; msg.tx.size = sizeof(request);

- return tegra_bpmp_transfer(bpmp, &msg); + err = tegra_bpmp_transfer(bpmp, &msg); + if (err) + return err; + if (msg.rx.ret) + return -EINVAL; + + return 0; }

static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc,

From: Borislav Petkov bp@suse.de

[ Upstream commit 1ef8715975de8bd481abbd0839ed4f49d9e5b0ff ]

Fix:

sound/usb/midi.c: In function ‘snd_usbmidi_out_endpoint_create’: sound/usb/midi.c:1389:2: error: case label does not reduce to an integer constant case USB_ID(0xfc08, 0x0101): /* Unknown vendor Cable */ ^~~~

See https://lore.kernel.org/r/YkwQ6%2BtIH8GQpuct@zn.tnic for the gory details as to why it triggers with older gccs only.

[ A slight correction with parentheses around the argument by tiwai ]

Signed-off-by: Borislav Petkov bp@suse.de Link: https://lore.kernel.org/r/20220405151517.29753-3-bp@alien8.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/usb/usbaudio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index 167834133b9b..b8359a0aa008 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -8,7 +8,7 @@ */

/* handling of USB vendor/product ID pairs as 32-bit numbers */ -#define USB_ID(vendor, product) (((vendor) << 16) | (product)) +#define USB_ID(vendor, product) (((unsigned int)(vendor) << 16) | (product)) #define USB_ID_VENDOR(id) ((id) >> 16) #define USB_ID_PRODUCT(id) ((u16)(id))

From: Rob Herring robh@kernel.org

[ Upstream commit 1bc12d301594eafde0a8529d28d459af81053b3a ]

The common touchscreen properties are all 32-bit, not 16-bit. These properties must not be too important as they are all ignored in case of an error reading them.

Signed-off-by: Rob Herring robh@kernel.org Link: https://lore.kernel.org/r/Yk3moe6Hz8ELM0iS@robh.at.kernel.org' Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi | 8 ++++---- arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi index 1dc9d187601c..a0bd540f27d3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi @@ -89,12 +89,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>;

ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index b16c7caf34c1..87b5e23c766f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -70,12 +70,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>;

ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>;

From: David Howells dhowells@redhat.com

[ Upstream commit 994fd530a512597ffcd713b0f6d5bc916c5698f0 ]

Use the IOCB_DIRECT indicator flag on the I/O context rather than checking to see if the file was opened O_DIRECT.

Signed-off-by: David Howells dhowells@redhat.com cc: Steve French sfrench@samba.org cc: Shyam Prasad N nspmangalore@gmail.com cc: Rohith Surabattula rohiths.msft@gmail.com cc: linux-cifs@vger.kernel.org Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/cifsfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 29a019cf1d5f..8f8d281e3151 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -936,7 +936,7 @@ cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) ssize_t rc; struct inode *inode = file_inode(iocb->ki_filp);

- if (iocb->ki_filp->f_flags & O_DIRECT) + if (iocb->ki_flags & IOCB_DIRECT) return cifs_user_readv(iocb, iter);

rc = cifs_revalidate_mapping(inode);

From: Borislav Petkov bp@suse.de

[ Upstream commit dbc2b1764734857d68425468ffa8486e97ab89df ]

Fix:

drivers/net/wireless/mediatek/mt76/mt76x2/pci.c: In function ‘mt76x2e_probe’: ././include/linux/compiler_types.h:352:38: error: call to ‘__compiletime_assert_946’ \ declared with attribute error: FIELD_PREP: mask is not constant _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)

See https://lore.kernel.org/r/YkwQ6%2BtIH8GQpuct@zn.tnic for the gory details as to why it triggers with older gccs only.

Signed-off-by: Borislav Petkov bp@suse.de Cc: Felix Fietkau nbd@nbd.name Cc: Lorenzo Bianconi lorenzo.bianconi83@gmail.com Cc: Ryder Lee ryder.lee@mediatek.com Cc: Shayne Chen shayne.chen@mediatek.com Cc: Sean Wang sean.wang@mediatek.com Cc: Kalle Valo kvalo@kernel.org Cc: "David S. Miller" davem@davemloft.net Cc: Jakub Kicinski kuba@kernel.org Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/20220405151517.29753-9-bp@alien8.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/mediatek/mt76/mt76x2/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c index adf288e50e21..5cd0379d86de 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c @@ -80,7 +80,7 @@ mt76x2e_probe(struct pci_dev *pdev, const struct pci_device_id *id) mt76_rmw_field(dev, 0x15a10, 0x1f << 16, 0x9);

/* RG_SSUSB_G1_CDR_BIC_LTR = 0xf */ - mt76_rmw_field(dev, 0x15a0c, 0xf << 28, 0xf); + mt76_rmw_field(dev, 0x15a0c, 0xfU << 28, 0xf);

/* RG_SSUSB_CDR_BR_PE1D = 0x3 */ mt76_rmw_field(dev, 0x15c58, 0x3 << 6, 0x3);

From: Lv Ruyi lv.ruyi@zte.com.cn

[ Upstream commit 1a7eb80d170c28be2928433702256fe2a0bd1e0f ]

Both of of_get_parent() and of_parse_phandle() return node pointer with refcount incremented, use of_node_put() on it to decrease refcount when done.

Reported-by: Zeal Robot zealci@zte.com.cn Signed-off-by: Lv Ruyi lv.ruyi@zte.com.cn Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 763d2c7b5fb1..5750f9a56393 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -489,11 +489,15 @@ static int dpaa_get_ts_info(struct net_device *net_dev, info->phc_index = -1;

fman_node = of_get_parent(mac_node); - if (fman_node) + if (fman_node) { ptp_node = of_parse_phandle(fman_node, "ptimer-handle", 0); + of_node_put(fman_node); + }

- if (ptp_node) + if (ptp_node) { ptp_dev = of_find_device_by_node(ptp_node); + of_node_put(ptp_node); + }

if (ptp_dev) ptp = platform_get_drvdata(ptp_dev);

From: Tomas Melin tomas.melin@vaisala.com

[ Upstream commit 5ad7f18cd82cee8e773d40cc7a1465a526f2615c ]

commit 4298388574da ("net: macb: restart tx after tx used bit read") added support for restarting transmission. Restarting tx does not work in case controller asserts TXUBR interrupt and TQBP is already at the end of the tx queue. In that situation, restarting tx will immediately cause assertion of another TXUBR interrupt. The driver will end up in an infinite interrupt loop which it cannot break out of.

For cases where TQBP is at the end of the tx queue, instead only clear TX_USED interrupt. As more data gets pushed to the queue, transmission will resume.

This issue was observed on a Xilinx Zynq-7000 based board. During stress test of the network interface, driver would get stuck on interrupt loop within seconds or minutes causing CPU to stall.

Signed-off-by: Tomas Melin tomas.melin@vaisala.com Tested-by: Claudiu Beznea claudiu.beznea@microchip.com Reviewed-by: Claudiu Beznea claudiu.beznea@microchip.com Link: https://lore.kernel.org/r/20220407161659.14532-1-tomas.melin@vaisala.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/cadence/macb_main.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 9705c49655ad..217c1a0f8940 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1689,6 +1689,7 @@ static void macb_tx_restart(struct macb_queue *queue) unsigned int head = queue->tx_head; unsigned int tail = queue->tx_tail; struct macb *bp = queue->bp; + unsigned int head_idx, tbqp;

if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, MACB_BIT(TXUBR)); @@ -1696,6 +1697,13 @@ static void macb_tx_restart(struct macb_queue *queue) if (head == tail) return;

+ tbqp = queue_readl(queue, TBQP) / macb_dma_desc_get_size(bp); + tbqp = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, tbqp)); + head_idx = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, head)); + + if (tbqp == head_idx) + return; + macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); }

From: Mike Christie michael.christie@oracle.com

[ Upstream commit 5bd856256f8c03e329f8ff36d8c8efcb111fe6df ]

Move the tx and rx suspend fields into one flags field.

Link: https://lore.kernel.org/r/20220408001314.5014-8-michael.christie@oracle.com Tested-by: Manish Rangankar mrangankar@marvell.com Reviewed-by: Lee Duncan lduncan@suse.com Reviewed-by: Chris Leech cleech@redhat.com Signed-off-by: Mike Christie michael.christie@oracle.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/bnx2i/bnx2i_hwi.c | 2 +- drivers/scsi/bnx2i/bnx2i_iscsi.c | 2 +- drivers/scsi/cxgbi/libcxgbi.c | 6 +++--- drivers/scsi/libiscsi.c | 20 ++++++++++---------- drivers/scsi/libiscsi_tcp.c | 2 +- include/scsi/libiscsi.h | 9 +++++---- 6 files changed, 21 insertions(+), 20 deletions(-)

diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index 5521469ce678..e16327a4b4c9 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -1977,7 +1977,7 @@ static int bnx2i_process_new_cqes(struct bnx2i_conn *bnx2i_conn) if (nopin->cq_req_sn != qp->cqe_exp_seq_sn) break;

- if (unlikely(test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx))) { + if (unlikely(test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { if (nopin->op_code == ISCSI_OP_NOOP_IN && nopin->itt == (u16) RESERVED_ITT) { printk(KERN_ALERT "bnx2i: Unsolicited " diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c index 1b5f3e143f07..2e5241d12dc3 100644 --- a/drivers/scsi/bnx2i/bnx2i_iscsi.c +++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c @@ -1721,7 +1721,7 @@ static int bnx2i_tear_down_conn(struct bnx2i_hba *hba, struct iscsi_conn *conn = ep->conn->cls_conn->dd_data;

/* Must suspend all rx queue activity for this ep */ - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); } /* CONN_DISCONNECT timeout may or may not be an issue depending * on what transcribed in TCP layer, different targets behave diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 8c7d4dda4cf2..4365d52c6430 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -1634,11 +1634,11 @@ void cxgbi_conn_pdu_ready(struct cxgbi_sock *csk) log_debug(1 << CXGBI_DBG_PDU_RX, "csk 0x%p, conn 0x%p.\n", csk, conn);

- if (unlikely(!conn || conn->suspend_rx)) { + if (unlikely(!conn || test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { log_debug(1 << CXGBI_DBG_PDU_RX, - "csk 0x%p, conn 0x%p, id %d, suspend_rx %lu!\n", + "csk 0x%p, conn 0x%p, id %d, conn flags 0x%lx!\n", csk, conn, conn ? conn->id : 0xFF, - conn ? conn->suspend_rx : 0xFF); + conn ? conn->flags : 0xFF); return; }

diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index cbc263ec9d66..a4f26431b033 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -1392,8 +1392,8 @@ static bool iscsi_set_conn_failed(struct iscsi_conn *conn) if (conn->stop_stage == 0) session->state = ISCSI_STATE_FAILED;

- set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); return true; }

@@ -1454,7 +1454,7 @@ static int iscsi_xmit_task(struct iscsi_conn *conn, struct iscsi_task *task, * Do this after dropping the extra ref because if this was a requeue * it's removed from that list and cleanup_queued_task would miss it. */ - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { /* * Save the task and ref in case we weren't cleaning up this * task and get woken up again. @@ -1532,7 +1532,7 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) int rc = 0;

spin_lock_bh(&conn->session->frwd_lock); - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { ISCSI_DBG_SESSION(conn->session, "Tx suspended!\n"); spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; @@ -1746,7 +1746,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) goto fault; }

- if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { reason = FAILURE_SESSION_IN_RECOVERY; sc->result = DID_REQUEUE << 16; goto fault; @@ -1935,7 +1935,7 @@ static void fail_scsi_tasks(struct iscsi_conn *conn, u64 lun, int error) void iscsi_suspend_queue(struct iscsi_conn *conn) { spin_lock_bh(&conn->session->frwd_lock); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); spin_unlock_bh(&conn->session->frwd_lock); } EXPORT_SYMBOL_GPL(iscsi_suspend_queue); @@ -1953,7 +1953,7 @@ void iscsi_suspend_tx(struct iscsi_conn *conn) struct Scsi_Host *shost = conn->session->host; struct iscsi_host *ihost = shost_priv(shost);

- set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); if (ihost->workq) flush_workqueue(ihost->workq); } @@ -1961,7 +1961,7 @@ EXPORT_SYMBOL_GPL(iscsi_suspend_tx);

static void iscsi_start_tx(struct iscsi_conn *conn) { - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); iscsi_conn_queue_work(conn); }

@@ -3324,8 +3324,8 @@ int iscsi_conn_bind(struct iscsi_cls_session *cls_session, /* * Unblock xmitworker(), Login Phase will pass through. */ - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); return 0; } EXPORT_SYMBOL_GPL(iscsi_conn_bind); diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 2e9ffe3d1a55..883005757ddb 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -927,7 +927,7 @@ int iscsi_tcp_recv_skb(struct iscsi_conn *conn, struct sk_buff *skb, */ conn->last_recv = jiffies;

- if (unlikely(conn->suspend_rx)) { + if (unlikely(test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { ISCSI_DBG_TCP(conn, "Rx suspended!\n"); *status = ISCSI_TCP_SUSPENDED; return 0; diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index 4ee233e5a6ff..bdb0ae11682d 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -52,8 +52,10 @@ enum {

#define ISID_SIZE 6

-/* Connection suspend "bit" */ -#define ISCSI_SUSPEND_BIT 1 +/* Connection flags */ +#define ISCSI_CONN_FLAG_SUSPEND_TX BIT(0) +#define ISCSI_CONN_FLAG_SUSPEND_RX BIT(1) +

#define ISCSI_ITT_MASK 0x1fff #define ISCSI_TOTAL_CMDS_MAX 4096 @@ -199,8 +201,7 @@ struct iscsi_conn { struct list_head cmdqueue; /* data-path cmd queue */ struct list_head requeue; /* tasks needing another run */ struct work_struct xmitwork; /* per-conn. xmit workqueue */ - unsigned long suspend_tx; /* suspend Tx */ - unsigned long suspend_rx; /* suspend Rx */ + unsigned long flags; /* ISCSI_CONN_FLAGs */

/* negotiated params */ unsigned max_recv_dlength; /* initiator_max_recv_dsl*/

From: Mike Christie michael.christie@oracle.com

[ Upstream commit 857b06527f707f5df634b854898a191b5c1d0272 ]

We set the qedi_ep state to EP_STATE_OFLDCONN_START when the ep is created. Then in qedi_set_path we kick off the offload work. If userspace times out the connection and calls ep_disconnect, qedi will only flush the offload work if the qedi_ep state has transitioned away from EP_STATE_OFLDCONN_START. If we can't connect we will not have transitioned state and will leave the offload work running, and we will free the qedi_ep from under it.

This patch just has us init the work when we create the ep, then always flush it.

Link: https://lore.kernel.org/r/20220408001314.5014-10-michael.christie@oracle.com Tested-by: Manish Rangankar mrangankar@marvell.com Reviewed-by: Lee Duncan lduncan@suse.com Reviewed-by: Chris Leech cleech@redhat.com Acked-by: Manish Rangankar mrangankar@marvell.com Signed-off-by: Mike Christie michael.christie@oracle.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qedi/qedi_iscsi.c | 69 +++++++++++++++++----------------- 1 file changed, 34 insertions(+), 35 deletions(-)

diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index c5260429c637..04b40a6c1aff 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -859,6 +859,37 @@ static int qedi_task_xmit(struct iscsi_task *task) return qedi_iscsi_send_ioreq(task); }

+static void qedi_offload_work(struct work_struct *work) +{ + struct qedi_endpoint *qedi_ep = + container_of(work, struct qedi_endpoint, offload_work); + struct qedi_ctx *qedi; + int wait_delay = 5 * HZ; + int ret; + + qedi = qedi_ep->qedi; + + ret = qedi_iscsi_offload_conn(qedi_ep); + if (ret) { + QEDI_ERR(&qedi->dbg_ctx, + "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n", + qedi_ep->iscsi_cid, qedi_ep, ret); + qedi_ep->state = EP_STATE_OFLDCONN_FAILED; + return; + } + + ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait, + (qedi_ep->state == + EP_STATE_OFLDCONN_COMPL), + wait_delay); + if (ret <= 0 || qedi_ep->state != EP_STATE_OFLDCONN_COMPL) { + qedi_ep->state = EP_STATE_OFLDCONN_FAILED; + QEDI_ERR(&qedi->dbg_ctx, + "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n", + qedi_ep->iscsi_cid, qedi_ep); + } +} + static struct iscsi_endpoint * qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr, int non_blocking) @@ -907,6 +938,7 @@ qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr, } qedi_ep = ep->dd_data; memset(qedi_ep, 0, sizeof(struct qedi_endpoint)); + INIT_WORK(&qedi_ep->offload_work, qedi_offload_work); qedi_ep->state = EP_STATE_IDLE; qedi_ep->iscsi_cid = (u32)-1; qedi_ep->qedi = qedi; @@ -1055,12 +1087,11 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep) qedi_ep = ep->dd_data; qedi = qedi_ep->qedi;

+ flush_work(&qedi_ep->offload_work); + if (qedi_ep->state == EP_STATE_OFLDCONN_START) goto ep_exit_recover;

- if (qedi_ep->state != EP_STATE_OFLDCONN_NONE) - flush_work(&qedi_ep->offload_work); - if (qedi_ep->conn) { qedi_conn = qedi_ep->conn; abrt_conn = qedi_conn->abrt_conn; @@ -1234,37 +1265,6 @@ static int qedi_data_avail(struct qedi_ctx *qedi, u16 vlanid) return rc; }

-static void qedi_offload_work(struct work_struct *work) -{ - struct qedi_endpoint *qedi_ep = - container_of(work, struct qedi_endpoint, offload_work); - struct qedi_ctx *qedi; - int wait_delay = 5 * HZ; - int ret; - - qedi = qedi_ep->qedi; - - ret = qedi_iscsi_offload_conn(qedi_ep); - if (ret) { - QEDI_ERR(&qedi->dbg_ctx, - "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n", - qedi_ep->iscsi_cid, qedi_ep, ret); - qedi_ep->state = EP_STATE_OFLDCONN_FAILED; - return; - } - - ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait, - (qedi_ep->state == - EP_STATE_OFLDCONN_COMPL), - wait_delay); - if ((ret <= 0) || (qedi_ep->state != EP_STATE_OFLDCONN_COMPL)) { - qedi_ep->state = EP_STATE_OFLDCONN_FAILED; - QEDI_ERR(&qedi->dbg_ctx, - "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n", - qedi_ep->iscsi_cid, qedi_ep); - } -} - static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data) { struct qedi_ctx *qedi; @@ -1380,7 +1380,6 @@ static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data) qedi_ep->dst_addr, qedi_ep->dst_port); }

- INIT_WORK(&qedi_ep->offload_work, qedi_offload_work); queue_work(qedi->offload_thread, &qedi_ep->offload_work);

ret = 0;

From: NeilBrown neilb@suse.de

[ Upstream commit b3d4650d82c71b9c9a8184de9e8bb656012b289e ]

When asked to create a path ending '/', but which is not to be a directory (LOOKUP_DIRECTORY not set), filename_create() will never try to create the file. If it doesn't exist, -ENOENT is reported.

However, it still passes LOOKUP_CREATE|LOOKUP_EXCL to the filesystems ->lookup() function, even though there is no intent to create. This is misleading and can cause incorrect behaviour.

If you try

ln -s foo /path/dir/

where 'dir' is a directory on an NFS filesystem which is not currently known in the dcache, this will fail with ENOENT.

But as the name is not in the dcache, nfs_lookup gets called with LOOKUP_CREATE|LOOKUP_EXCL and so it returns NULL without performing any lookup, with the expectation that a subsequent call to create the target will be made, and the lookup can be combined with the creation. In the case with a trailing '/' and no LOOKUP_DIRECTORY, that call is never made. Instead filename_create() sees that the dentry is not (yet) positive and returns -ENOENT - even though the directory actually exists.

So only set LOOKUP_CREATE|LOOKUP_EXCL if there really is an intent to create, and use the absence of these flags to decide if -ENOENT should be returned.

Note that filename_parentat() is only interested in LOOKUP_REVAL, so we split that out and store it in 'reval_flag'. __lookup_hash() then gets reval_flag combined with whatever create flags were determined to be needed.

Reviewed-by: David Disseldorp ddiss@suse.de Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: NeilBrown neilb@suse.de Cc: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/namei.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c index 3bb65f48fe1d..8882a70dc119 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3625,18 +3625,14 @@ static struct dentry *filename_create(int dfd, struct filename *name, { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; + bool want_dir = lookup_flags & LOOKUP_DIRECTORY; + unsigned int reval_flag = lookup_flags & LOOKUP_REVAL; + unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL; int type; int err2; int error; - bool is_dir = (lookup_flags & LOOKUP_DIRECTORY);

- /* - * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any - * other flags passed in are ignored! - */ - lookup_flags &= LOOKUP_REVAL; - - error = filename_parentat(dfd, name, lookup_flags, path, &last, &type); + error = filename_parentat(dfd, name, reval_flag, path, &last, &type); if (error) return ERR_PTR(error);

@@ -3650,11 +3646,13 @@ static struct dentry *filename_create(int dfd, struct filename *name, /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* - * Do the final lookup. + * Do the final lookup. Suppress 'create' if there is a trailing + * '/', and a directory wasn't requested. */ - lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; + if (last.name[last.len] && !want_dir) + create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path->dentry, lookup_flags); + dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock;

@@ -3668,7 +3666,7 @@ static struct dentry *filename_create(int dfd, struct filename *name, * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ - if (unlikely(!is_dir && last.name[last.len])) { + if (unlikely(!create_flags)) { error = -ENOENT; goto fail; }

From: Christoph Hellwig hch@lst.de

[ Upstream commit a98a945b80f8684121d477ae68ebc01da953da1f ]

The MAXIO MAP1002/1202 controllers reports completely bogus Namespace identifiers that even change after suspend cycles. Disable using the Identifiers entirely.

Reported-by: 金韬 me@kingtous.cn Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Keith Busch kbusch@kernel.org Tested-by: 金韬 me@kingtous.cn Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/pci.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b925a5f4afc3..61f01f5afdc1 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3352,6 +3352,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x1e4B, 0x1002), /* MAXIO MAP1002 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4B, 0x1202), /* MAXIO MAP1202 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065),

From: Shubhrajyoti Datta shubhrajyoti.datta@xilinx.com

commit e2932d1f6f055b2af2114c7e64a26dc1b5593d0c upstream.

Currently, the error count is read wrongly from the status register. Read the count from the proper error count register (ERRCNT).

[ bp: Massage. ]

Fixes: b500b4a029d5 ("EDAC, synopsys: Add ECC support for ZynqMP DDR controller") Signed-off-by: Shubhrajyoti Datta shubhrajyoti.datta@xilinx.com Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Michal Simek michal.simek@xilinx.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220414102813.4468-1-shubhrajyoti.datta@xilinx.co... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/edac/synopsys_edac.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)

--- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -163,6 +163,11 @@ #define ECC_STAT_CECNT_SHIFT 8 #define ECC_STAT_BITNUM_MASK 0x7F

+/* ECC error count register definitions */ +#define ECC_ERRCNT_UECNT_MASK 0xFFFF0000 +#define ECC_ERRCNT_UECNT_SHIFT 16 +#define ECC_ERRCNT_CECNT_MASK 0xFFFF + /* DDR QOS Interrupt register definitions */ #define DDR_QOS_IRQ_STAT_OFST 0x20200 #define DDR_QOSUE_MASK 0x4 @@ -418,15 +423,16 @@ static int zynqmp_get_error_info(struct base = priv->baseaddr; p = &priv->stat;

+ regval = readl(base + ECC_ERRCNT_OFST); + p->ce_cnt = regval & ECC_ERRCNT_CECNT_MASK; + p->ue_cnt = (regval & ECC_ERRCNT_UECNT_MASK) >> ECC_ERRCNT_UECNT_SHIFT; + if (!p->ce_cnt) + goto ue_err; + regval = readl(base + ECC_STAT_OFST); if (!regval) return 1;

- p->ce_cnt = (regval & ECC_STAT_CECNT_MASK) >> ECC_STAT_CECNT_SHIFT; - p->ue_cnt = (regval & ECC_STAT_UECNT_MASK) >> ECC_STAT_UECNT_SHIFT; - if (!p->ce_cnt) - goto ue_err; - p->ceinfo.bitpos = (regval & ECC_STAT_BITNUM_MASK);

regval = readl(base + ECC_CEADDR0_OFST);

From: Shakeel Butt shakeelb@google.com

commit 9b3016154c913b2e7ec5ae5c9a42eb9e732d86aa upstream.

Daniel Dao has reported [1] a regression on workloads that may trigger a lot of refaults (anon and file). The underlying issue is that flushing rstat is expensive. Although rstat flush are batched with (nr_cpus * MEMCG_BATCH) stat updates, it seems like there are workloads which genuinely do stat updates larger than batch value within short amount of time. Since the rstat flush can happen in the performance critical codepaths like page faults, such workload can suffer greatly.

This patch fixes this regression by making the rstat flushing conditional in the performance critical codepaths. More specifically, the kernel relies on the async periodic rstat flusher to flush the stats and only if the periodic flusher is delayed by more than twice the amount of its normal time window then the kernel allows rstat flushing from the performance critical codepaths.

Now the question: what are the side-effects of this change? The worst that can happen is the refault codepath will see 4sec old lruvec stats and may cause false (or missed) activations of the refaulted page which may under-or-overestimate the workingset size. Though that is not very concerning as the kernel can already miss or do false activations.

There are two more codepaths whose flushing behavior is not changed by this patch and we may need to come to them in future. One is the writeback stats used by dirty throttling and second is the deactivation heuristic in the reclaim. For now keeping an eye on them and if there is report of regression due to these codepaths, we will reevaluate then.

Link: https://lore.kernel.org/all/CA+wXwBSyO87ZX5PVwdHm-=dBjZYECGmfnydUicUyrQqndgX... [1] Link: https://lkml.kernel.org/r/20220304184040.1304781-1-shakeelb@google.com Fixes: 1f828223b799 ("memcg: flush lruvec stats in the refault") Signed-off-by: Shakeel Butt shakeelb@google.com Reported-by: Daniel Dao dqminh@cloudflare.com Tested-by: Ivan Babrou ivan@cloudflare.com Cc: Michal Hocko mhocko@suse.com Cc: Roman Gushchin roman.gushchin@linux.dev Cc: Johannes Weiner hannes@cmpxchg.org Cc: Michal Koutný mkoutny@suse.com Cc: Frank Hofmann fhofmann@cloudflare.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/memcontrol.h | 5 +++++ mm/memcontrol.c | 12 +++++++++++- mm/workingset.c | 2 +- 3 files changed, 17 insertions(+), 2 deletions(-)

--- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1002,6 +1002,7 @@ static inline unsigned long lruvec_page_ }

void mem_cgroup_flush_stats(void); +void mem_cgroup_flush_stats_delayed(void);

void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1422,6 +1423,10 @@ static inline void mem_cgroup_flush_stat { }

+static inline void mem_cgroup_flush_stats_delayed(void) +{ +} + static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -650,6 +650,9 @@ static DECLARE_DEFERRABLE_WORK(stats_flu static DEFINE_SPINLOCK(stats_flush_lock); static DEFINE_PER_CPU(unsigned int, stats_updates); static atomic_t stats_flush_threshold = ATOMIC_INIT(0); +static u64 flush_next_time; + +#define FLUSH_TIME (2UL*HZ)

static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) { @@ -671,6 +674,7 @@ static void __mem_cgroup_flush_stats(voi if (!spin_trylock_irqsave(&stats_flush_lock, flag)) return;

+ flush_next_time = jiffies_64 + 2*FLUSH_TIME; cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); atomic_set(&stats_flush_threshold, 0); spin_unlock_irqrestore(&stats_flush_lock, flag); @@ -682,10 +686,16 @@ void mem_cgroup_flush_stats(void) __mem_cgroup_flush_stats(); }

+void mem_cgroup_flush_stats_delayed(void) +{ + if (time_after64(jiffies_64, flush_next_time)) + mem_cgroup_flush_stats(); +} + static void flush_memcg_stats_dwork(struct work_struct *w) { __mem_cgroup_flush_stats(); - queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ); + queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME); }

/** --- a/mm/workingset.c +++ b/mm/workingset.c @@ -352,7 +352,7 @@ void workingset_refault(struct page *pag

inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file);

- mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_delayed(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if

From: Nico Pache npache@redhat.com

commit e4a38402c36e42df28eb1a5394be87e6571fb48a upstream.

The pthread struct is allocated on PRIVATE|ANONYMOUS memory [1] which can be targeted by the oom reaper. This mapping is used to store the futex robust list head; the kernel does not keep a copy of the robust list and instead references a userspace address to maintain the robustness during a process death.

A race can occur between exit_mm and the oom reaper that allows the oom reaper to free the memory of the futex robust list before the exit path has handled the futex death:

CPU1 CPU2 -------------------------------------------------------------------- page_fault do_exit "signal" wake_oom_reaper oom_reaper oom_reap_task_mm (invalidates mm) exit_mm exit_mm_release futex_exit_release futex_cleanup exit_robust_list get_user (EFAULT- can't access memory)

If the get_user EFAULT's, the kernel will be unable to recover the waiters on the robust_list, leaving userspace mutexes hung indefinitely.

Delay the OOM reaper, allowing more time for the exit path to perform the futex cleanup.

Reproducer: https://gitlab.com/jsavitz/oom_futex_reproducer

Based on a patch by Michal Hocko.

Link: https://elixir.bootlin.com/glibc/glibc-2.35/source/nptl/allocatestack.c#L370 [1] Link: https://lkml.kernel.org/r/20220414144042.677008-1-npache@redhat.com Fixes: 212925802454 ("mm: oom: let oom_reap_task and exit_mmap run concurrently") Signed-off-by: Joel Savitz jsavitz@redhat.com Signed-off-by: Nico Pache npache@redhat.com Co-developed-by: Joel Savitz jsavitz@redhat.com Suggested-by: Thomas Gleixner tglx@linutronix.de Acked-by: Thomas Gleixner tglx@linutronix.de Acked-by: Michal Hocko mhocko@suse.com Cc: Rafael Aquini aquini@redhat.com Cc: Waiman Long longman@redhat.com Cc: Herton R. Krzesinski herton@redhat.com Cc: Juri Lelli juri.lelli@redhat.com Cc: Vincent Guittot vincent.guittot@linaro.org Cc: Dietmar Eggemann dietmar.eggemann@arm.com Cc: Steven Rostedt rostedt@goodmis.org Cc: Ben Segall bsegall@google.com Cc: Mel Gorman mgorman@suse.de Cc: Daniel Bristot de Oliveira bristot@redhat.com Cc: David Rientjes rientjes@google.com Cc: Andrea Arcangeli aarcange@redhat.com Cc: Davidlohr Bueso dave@stgolabs.net Cc: Peter Zijlstra peterz@infradead.org Cc: Ingo Molnar mingo@redhat.com Cc: Joel Savitz jsavitz@redhat.com Cc: Darren Hart dvhart@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/sched.h | 1 mm/oom_kill.c | 54 +++++++++++++++++++++++++++++++++++++------------- 2 files changed, 41 insertions(+), 14 deletions(-)

--- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1436,6 +1436,7 @@ struct task_struct { int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; + struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -635,7 +635,7 @@ done: */ set_bit(MMF_OOM_SKIP, &mm->flags);

- /* Drop a reference taken by wake_oom_reaper */ + /* Drop a reference taken by queue_oom_reaper */ put_task_struct(tsk); }

@@ -645,12 +645,12 @@ static int oom_reaper(void *unused) struct task_struct *tsk = NULL;

wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL); - spin_lock(&oom_reaper_lock); + spin_lock_irq(&oom_reaper_lock); if (oom_reaper_list != NULL) { tsk = oom_reaper_list; oom_reaper_list = tsk->oom_reaper_list; } - spin_unlock(&oom_reaper_lock); + spin_unlock_irq(&oom_reaper_lock);

if (tsk) oom_reap_task(tsk); @@ -659,22 +659,48 @@ static int oom_reaper(void *unused) return 0; }

-static void wake_oom_reaper(struct task_struct *tsk) +static void wake_oom_reaper(struct timer_list *timer) { - /* mm is already queued? */ - if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) + struct task_struct *tsk = container_of(timer, struct task_struct, + oom_reaper_timer); + struct mm_struct *mm = tsk->signal->oom_mm; + unsigned long flags; + + /* The victim managed to terminate on its own - see exit_mmap */ + if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + put_task_struct(tsk); return; + }

- get_task_struct(tsk); - - spin_lock(&oom_reaper_lock); + spin_lock_irqsave(&oom_reaper_lock, flags); tsk->oom_reaper_list = oom_reaper_list; oom_reaper_list = tsk; - spin_unlock(&oom_reaper_lock); + spin_unlock_irqrestore(&oom_reaper_lock, flags); trace_wake_reaper(tsk->pid); wake_up(&oom_reaper_wait); }

+/* + * Give the OOM victim time to exit naturally before invoking the oom_reaping. + * The timers timeout is arbitrary... the longer it is, the longer the worst + * case scenario for the OOM can take. If it is too small, the oom_reaper can + * get in the way and release resources needed by the process exit path. + * e.g. The futex robust list can sit in Anon|Private memory that gets reaped + * before the exit path is able to wake the futex waiters. + */ +#define OOM_REAPER_DELAY (2*HZ) +static void queue_oom_reaper(struct task_struct *tsk) +{ + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) + return; + + get_task_struct(tsk); + timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0); + tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY; + add_timer(&tsk->oom_reaper_timer); +} + static int __init oom_init(void) { oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); @@ -682,7 +708,7 @@ static int __init oom_init(void) } subsys_initcall(oom_init) #else -static inline void wake_oom_reaper(struct task_struct *tsk) +static inline void queue_oom_reaper(struct task_struct *tsk) { } #endif /* CONFIG_MMU */ @@ -933,7 +959,7 @@ static void __oom_kill_process(struct ta rcu_read_unlock();

if (can_oom_reap) - wake_oom_reaper(victim); + queue_oom_reaper(victim);

mmdrop(mm); put_task_struct(victim); @@ -969,7 +995,7 @@ static void oom_kill_process(struct oom_ task_lock(victim); if (task_will_free_mem(victim)) { mark_oom_victim(victim); - wake_oom_reaper(victim); + queue_oom_reaper(victim); task_unlock(victim); put_task_struct(victim); return; @@ -1067,7 +1093,7 @@ bool out_of_memory(struct oom_control *o */ if (task_will_free_mem(current)) { mark_oom_victim(current); - wake_oom_reaper(current); + queue_oom_reaper(current); return true; }

From: Zheyu Ma zheyuma97@gmail.com

commit aafa9f958342db36c17ac2a7f1b841032c96feb4 upstream.

Before detecting the cable type on the dma bar, the driver should check whether the 'bmdma_addr' is zero, which means the adapter does not support DMA, otherwise we will get the following error:

[ 5.146634] Bad IO access at port 0x1 (return inb(port)) [ 5.147206] WARNING: CPU: 2 PID: 303 at lib/iomap.c:44 ioread8+0x4a/0x60 [ 5.150856] RIP: 0010:ioread8+0x4a/0x60 [ 5.160238] Call Trace: [ 5.160470] <TASK> [ 5.160674] marvell_cable_detect+0x6e/0xc0 [pata_marvell] [ 5.161728] ata_eh_recover+0x3520/0x6cc0 [ 5.168075] ata_do_eh+0x49/0x3c0

Signed-off-by: Zheyu Ma zheyuma97@gmail.com Signed-off-by: Damien Le Moal damien.lemoal@opensource.wdc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/ata/pata_marvell.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/ata/pata_marvell.c +++ b/drivers/ata/pata_marvell.c @@ -83,6 +83,8 @@ static int marvell_cable_detect(struct a switch(ap->port_no) { case 0: + if (!ap->ioaddr.bmdma_addr) + return ATA_CBL_PATA_UNK; if (ioread8(ap->ioaddr.bmdma_addr + 1) & 1) return ATA_CBL_PATA40; return ATA_CBL_PATA80;

From: Kevin Groeneveld kgroeneveld@lenbrook.com

commit a3ae97f4c87d9570e7e9a3e3324c443757f6e29a upstream.

Commit b98ce2f4e32b ("dmaengine: imx-sdma: add uart rom script") broke uart rx on imx5 when using sdma firmware from older Freescale 2.6.35 kernel. In this case reading addr->uartXX_2_mcu_addr was going out of bounds of the firmware memory and corrupting the uart script addresses.

Simply adding a bounds check before accessing addr->uartXX_2_mcu_addr does not work as the uartXX_2_mcu_addr members are now beyond the size of the older firmware and the uart addresses would never be populated in that case. There are other ways to fix this but overall the logic seems clearer to me to revert the uartXX_2_mcu_ram_addr structure entries back to uartXX_2_mcu_addr, change the newer entries to uartXX_2_mcu_rom_addr and update the logic accordingly.

I have tested this patch on: 1. An i.MX53 system with sdma firmware from Freescale 2.6.35 kernel. Without this patch uart rx is broken in this scenario, with the patch uart rx is restored. 2. An i.MX6D system with no external sdma firmware. uart is okay with or without this patch. 3. An i.MX8MM system using current sdma-imx7d.bin firmware from linux-firmware. uart is okay with or without this patch and I confirmed the rom version of the uart script is being used which was the intention and reason for commit b98ce2f4e32b ("dmaengine: imx-sdma: add uart rom script") in the first place.

Fixes: b98ce2f4e32b ("dmaengine: imx-sdma: add uart rom script") Cc: stable@vger.kernel.org Signed-off-by: Kevin Groeneveld kgroeneveld@lenbrook.com Reviewed-by: Lucas Stach l.stach@pengutronix.de Reviewed-by: Fabio Estevam festevam@gmail.com Acked-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Link: https://lore.kernel.org/r/20220410223118.15086-1-kgroeneveld@lenbrook.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/dma/imx-sdma.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-)

--- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -198,12 +198,12 @@ struct sdma_script_start_addrs { s32 per_2_firi_addr; s32 mcu_2_firi_addr; s32 uart_2_per_addr; - s32 uart_2_mcu_ram_addr; + s32 uart_2_mcu_addr; s32 per_2_app_addr; s32 mcu_2_app_addr; s32 per_2_per_addr; s32 uartsh_2_per_addr; - s32 uartsh_2_mcu_ram_addr; + s32 uartsh_2_mcu_addr; s32 per_2_shp_addr; s32 mcu_2_shp_addr; s32 ata_2_mcu_addr; @@ -232,8 +232,8 @@ struct sdma_script_start_addrs { s32 mcu_2_ecspi_addr; s32 mcu_2_sai_addr; s32 sai_2_mcu_addr; - s32 uart_2_mcu_addr; - s32 uartsh_2_mcu_addr; + s32 uart_2_mcu_rom_addr; + s32 uartsh_2_mcu_rom_addr; /* End of v3 array */ s32 mcu_2_zqspi_addr; /* End of v4 array */ @@ -1780,17 +1780,17 @@ static void sdma_add_scripts(struct sdma saddr_arr[i] = addr_arr[i];

/* - * get uart_2_mcu_addr/uartsh_2_mcu_addr rom script specially because - * they are now replaced by uart_2_mcu_ram_addr/uartsh_2_mcu_ram_addr - * to be compatible with legacy freescale/nxp sdma firmware, and they - * are located in the bottom part of sdma_script_start_addrs which are - * beyond the SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1. + * For compatibility with NXP internal legacy kernel before 4.19 which + * is based on uart ram script and mainline kernel based on uart rom + * script, both uart ram/rom scripts are present in newer sdma + * firmware. Use the rom versions if they are present (V3 or newer). */ - if (addr->uart_2_mcu_addr) - sdma->script_addrs->uart_2_mcu_addr = addr->uart_2_mcu_addr; - if (addr->uartsh_2_mcu_addr) - sdma->script_addrs->uartsh_2_mcu_addr = addr->uartsh_2_mcu_addr; - + if (sdma->script_number >= SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V3) { + if (addr->uart_2_mcu_rom_addr) + sdma->script_addrs->uart_2_mcu_addr = addr->uart_2_mcu_rom_addr; + if (addr->uartsh_2_mcu_rom_addr) + sdma->script_addrs->uartsh_2_mcu_addr = addr->uartsh_2_mcu_rom_addr; + } }

static void sdma_load_firmware(const struct firmware *fw, void *context)

From: Miaoqian Lin linmq006@gmail.com

[ Upstream commit 81022a170462d38ea10612cb67e8e2c529d58abe ]

If the device is already in a runtime PM enabled state pm_runtime_get_sync() will return 1, so a test for negative value should be used to check for errors.

Fixes: f77621cc640a ("Input: omap-keypad - dynamically handle register offsets") Signed-off-by: Miaoqian Lin linmq006@gmail.com Link: https://lore.kernel.org/r/20220412070131.19848-1-linmq006@gmail.com Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/input/keyboard/omap4-keypad.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c index 43375b38ee59..8a7ce41b8c56 100644 --- a/drivers/input/keyboard/omap4-keypad.c +++ b/drivers/input/keyboard/omap4-keypad.c @@ -393,7 +393,7 @@ static int omap4_keypad_probe(struct platform_device *pdev) * revision register. */ error = pm_runtime_get_sync(dev); - if (error) { + if (error < 0) { dev_err(dev, "pm_runtime_get_sync() failed\n"); pm_runtime_put_noidle(dev); return error;

From: kuyo chang kuyo.chang@mediatek.com

[ Upstream commit 40f5aa4c5eaebfeaca4566217cb9c468e28ed682 ]

The warning in cfs_rq_is_decayed() triggered:

SCHED_WARN_ON(cfs_rq->avg.load_avg || cfs_rq->avg.util_avg || cfs_rq->avg.runnable_avg)

There exists a corner case in attach_entity_load_avg() which will cause load_sum to be zero while load_avg will not be.

Consider se_weight is 88761 as per the sched_prio_to_weight[] table. Further assume the get_pelt_divider() is 47742, this gives: se->avg.load_avg is 1.

However, calculating load_sum:

se->avg.load_sum = div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se)); se->avg.load_sum = 1*47742/88761 = 0.

Then enqueue_load_avg() adds this to the cfs_rq totals:

cfs_rq->avg.load_avg += se->avg.load_avg; cfs_rq->avg.load_sum += se_weight(se) * se->avg.load_sum;

Resulting in load_avg being 1 with load_sum is 0, which will trigger the WARN.

Fixes: f207934fb79d ("sched/fair: Align PELT windows between cfs_rq and its se") Signed-off-by: kuyo chang kuyo.chang@mediatek.com [peterz: massage changelog] Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Vincent Guittot vincent.guittot@linaro.org Tested-by: Dietmar Eggemann dietmar.eggemann@arm.com Link: https://lkml.kernel.org/r/20220414090229.342-1-kuyo.chang@mediatek.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/fair.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 02766f3fe206..9a4fa22a69ed 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3794,11 +3794,11 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s

se->avg.runnable_sum = se->avg.runnable_avg * divider;

- se->avg.load_sum = divider; - if (se_weight(se)) { - se->avg.load_sum = - div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se)); - } + se->avg.load_sum = se->avg.load_avg * divider; + if (se_weight(se) < se->avg.load_sum) + se->avg.load_sum = div_u64(se->avg.load_sum, se_weight(se)); + else + se->avg.load_sum = 1;

enqueue_load_avg(cfs_rq, se); cfs_rq->avg.util_avg += se->avg.util_avg;

From: Dave Stevenson dave.stevenson@raspberrypi.com

[ Upstream commit f92055ae0acb035891e988ce345d6b81a0316423 ]

If a call to rpi_touchscreen_i2c_write from rpi_touchscreen_probe fails before mipi_dsi_device_register_full is called, then in trying to log the error message if uses ts->dsi->dev when it is still NULL.

Use ts->i2c->dev instead, which is initialised earlier in probe.

Fixes: 2f733d6194bd ("drm/panel: Add support for the Raspberry Pi 7" Touchscreen.") Signed-off-by: Dave Stevenson dave.stevenson@raspberrypi.com Signed-off-by: Stefan Wahren stefan.wahren@i2se.com Signed-off-by: Maxime Ripard maxime@cerno.tech Link: https://patchwork.freedesktop.org/patch/msgid/20220415162513.42190-2-stefan.... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c index 46029c5610c8..1f805eb8fdb5 100644 --- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c +++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c @@ -229,7 +229,7 @@ static void rpi_touchscreen_i2c_write(struct rpi_touchscreen *ts,

ret = i2c_smbus_write_byte_data(ts->i2c, reg, val); if (ret) - dev_err(&ts->dsi->dev, "I2C write failed: %d\n", ret); + dev_err(&ts->i2c->dev, "I2C write failed: %d\n", ret); }

static int rpi_touchscreen_write(struct rpi_touchscreen *ts, u16 reg, u32 val)

From: Alexey Kardashevskiy aik@ozlabs.ru

[ Upstream commit 26a62b750a4e6364b0393562f66759b1494c3a01 ]

The LoPAPR spec defines a guest visible IOMMU with a variable page size. Currently QEMU advertises 4K, 64K, 2M, 16MB pages, a Linux VM picks the biggest (16MB). In the case of a passed though PCI device, there is a hardware IOMMU which does not support all pages sizes from the above - P8 cannot do 2MB and P9 cannot do 16MB. So for each emulated 16M IOMMU page we may create several smaller mappings ("TCEs") in the hardware IOMMU.

The code wrongly uses the emulated TCE index instead of hardware TCE index in error handling. The problem is easier to see on POWER8 with multi-level TCE tables (when only the first level is preallocated) as hash mode uses real mode TCE hypercalls handlers. The kernel starts using indirect tables when VMs get bigger than 128GB (depends on the max page order). The very first real mode hcall is going to fail with H_TOO_HARD as in the real mode we cannot allocate memory for TCEs (we can in the virtual mode) but on the way out the code attempts to clear hardware TCEs using emulated TCE indexes which corrupts random kernel memory because it_offset==1<<59 is subtracted from those indexes and the resulting index is out of the TCE table bounds.

This fixes kvmppc_clear_tce() to use the correct TCE indexes.

While at it, this fixes TCE cache invalidation which uses emulated TCE indexes instead of the hardware ones. This went unnoticed as 64bit DMA is used these days and VMs map all RAM in one go and only then do DMA and this is when the TCE cache gets populated.

Potentially this could slow down mapping, however normally 16MB emulated pages are backed by 64K hardware pages so it is one write to the "TCE Kill" per 256 updates which is not that bad considering the size of the cache (1024 TCEs or so).

Fixes: ca1fc489cfa0 ("KVM: PPC: Book3S: Allow backing bigger guest IOMMU pages with smaller physical pages")

Signed-off-by: Alexey Kardashevskiy aik@ozlabs.ru Tested-by: David Gibson david@gibson.dropbear.id.au Reviewed-by: Frederic Barrat fbarrat@linux.ibm.com Reviewed-by: David Gibson david@gibson.dropbear.id.au Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20220420050840.328223-1-aik@ozlabs.ru Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kvm/book3s_64_vio.c | 45 +++++++++++++++-------------- arch/powerpc/kvm/book3s_64_vio_hv.c | 44 ++++++++++++++-------------- 2 files changed, 45 insertions(+), 44 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 6365087f3160..3cb2e05a7ee8 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -421,13 +421,19 @@ static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt, tbl[idx % TCES_PER_PAGE] = tce; }

-static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_clear_tce(struct mm_struct *mm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE;

- iommu_tce_xchg_no_kill(mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill(mm, tbl, io_entry + i, &hpa, &dir); + } }

static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm, @@ -486,6 +492,8 @@ static long kvmppc_tce_iommu_unmap(struct kvm *kvm, break; }

+ iommu_tce_kill(tbl, io_entry, subpages); + return ret; }

@@ -545,6 +553,8 @@ static long kvmppc_tce_iommu_map(struct kvm *kvm, break; }

+ iommu_tce_kill(tbl, io_entry, subpages); + return ret; }

@@ -591,10 +601,9 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir);

- iommu_tce_kill(stit->tbl, entry, 1);

if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry); goto unlock_exit; } } @@ -670,13 +679,13 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, */ if (get_user(tce, tces + i)) { ret = H_TOO_HARD; - goto invalidate_exit; + goto unlock_exit; } tce = be64_to_cpu(tce);

if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; }

list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -685,19 +694,15 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce));

if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, + entry + i); + goto unlock_exit; } }

kvmppc_tce_put(stt, entry + i, tce); }

-invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, entry, npages); - unlock_exit: srcu_read_unlock(&vcpu->kvm->srcu, idx);

@@ -736,20 +741,16 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, continue;

if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret;

WARN_ON_ONCE(1); - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry + i); } }

for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);

-invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, ioba >> stt->page_shift, npages); - return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 870b7f0c7ea5..fdeda6a9cff4 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -247,13 +247,19 @@ static void iommu_tce_kill_rm(struct iommu_table *tbl, tbl->it_ops->tce_kill(tbl, entry, pages, true); }

-static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_rm_clear_tce(struct kvm *kvm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE;

- iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, io_entry + i, &hpa, &dir); + } }

static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -316,6 +322,8 @@ static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm, break; }

+ iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; }

@@ -379,6 +387,8 @@ static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, break; }

+ iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; }

@@ -420,10 +430,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir);

- iommu_tce_kill_rm(stit->tbl, entry, 1); - if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry); return ret; } } @@ -561,7 +569,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, ua = 0; if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; }

list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -570,19 +578,15 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce));

if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, + entry + i); + goto unlock_exit; } }

kvmppc_rm_tce_put(stt, entry + i, tce); }

-invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, entry, npages); - unlock_exit: if (!prereg) arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock); @@ -620,20 +624,16 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, continue;

if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret;

WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry + i); } }

for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value);

-invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages); - return ret; }

From: Athira Rajeev atrajeev@linux.vnet.ibm.com

[ Upstream commit 0dcad700bb2776e3886fe0a645a4bf13b1e747cd ]

When scheduling a group of events, there are constraint checks done to make sure all events can go in a group. Example, one of the criteria is that events in a group cannot use the same PMC. But platform specific PMU supports alternative event for some of the event codes. During perf_event_open(), if any event group doesn't match constraint check criteria, further lookup is done to find alternative event.

By current design, the array of alternatives events in PMU code is expected to be sorted by column 0. This is because in find_alternative() the return criteria is based on event code comparison. ie. "event < ev_alt[i][0])". This optimisation is there since find_alternative() can be called multiple times. In power9 PMU code, the alternative event array is not sorted properly and hence there is breakage in finding alternative events.

To work with existing logic, fix the alternative event array to be sorted by column 0 for power9-pmu.c

Results:

With alternative events, multiplexing can be avoided. That is, for example, in power9 PM_LD_MISS_L1 (0x3e054) has alternative event, PM_LD_MISS_L1_ALT (0x400f0). This is an identical event which can be programmed in a different PMC.

Before:

# perf stat -e r3e054,r300fc

Performance counter stats for 'system wide':

1057860 r3e054 (50.21%) 379 r300fc (49.79%)

0.944329741 seconds time elapsed

Since both the events are using PMC3 in this case, they are multiplexed here.

After:

# perf stat -e r3e054,r300fc

Performance counter stats for 'system wide':

1006948 r3e054 182 r300fc

Fixes: 91e0bd1e6251 ("powerpc/perf: Add PM_LD_MISS_L1 and PM_BR_2PATH to power9 event list") Signed-off-by: Athira Rajeev atrajeev@linux.vnet.ibm.com Reviewed-by: Madhavan Srinivasan maddy@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20220419114828.89843-1-atrajeev@linux.vnet.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/perf/power9-pmu.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index ff3382140d7e..cbdd074ee2a7 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -133,11 +133,11 @@ int p9_dd22_bl_ev[] = {

/* Table of alternatives, sorted by column 0 */ static const unsigned int power9_event_alternatives[][MAX_ALT] = { - { PM_INST_DISP, PM_INST_DISP_ALT }, - { PM_RUN_CYC_ALT, PM_RUN_CYC }, - { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, - { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, { PM_BR_2PATH, PM_BR_2PATH_ALT }, + { PM_INST_DISP, PM_INST_DISP_ALT }, + { PM_RUN_CYC_ALT, PM_RUN_CYC }, + { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, + { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, };

static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[])

From: Leo Yan leo.yan@linaro.org

[ Upstream commit c6d8df01064333dcf140eda996abdb60a60e24b3 ]

If use command 'perf script -F,+data_src' to dump memory samples with Arm SPE trace data, it reports error:

# perf script -F,+data_src Samples for 'dummy:u' event do not have DATA_SRC attribute set. Cannot print 'data_src' field.

This is because the 'dummy:u' event is absent DATA_SRC bit in its sample type, so if a file contains AUX area tracing data then always allow field 'data_src' to be selected as an option for perf script.

Fixes: e55ed3423c1bb29f ("perf arm-spe: Synthesize memory event") Signed-off-by: Leo Yan leo.yan@linaro.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: German Gomez german.gomez@arm.com Cc: Ingo Molnar mingo@redhat.com Cc: James Clark james.clark@arm.com Cc: Jiri Olsa jolsa@kernel.org Cc: Leo Yan leo.yan@linaro.org Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: https://lore.kernel.org/r/20220417114837.839896-1-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 18b56256bb6f..cb3d81adf5ca 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -455,7 +455,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL;

if (PRINT_FIELD(DATA_SRC) && - evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC)) + evsel__do_check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC, allow_user_set)) return -EINVAL;

if (PRINT_FIELD(WEIGHT) &&

From: Guo Ren guoren@linux.alibaba.com

commit ee69d4be8fd064cd08270b4808d2dfece3614ee0 upstream.

These patch_text implementations are using stop_machine_cpuslocked infrastructure with atomic cpu_count. The original idea: When the master CPU patch_text, the others should wait for it. But current implementation is using the first CPU as master, which couldn't guarantee the remaining CPUs are waiting. This patch changes the last CPU as the master to solve the potential risk.

Fixes: 64711f9a47d4 ("xtensa: implement jump_label support") Signed-off-by: Guo Ren guoren@linux.alibaba.com Signed-off-by: Guo Ren guoren@kernel.org Reviewed-by: Max Filippov jcmvbkbc@gmail.com Reviewed-by: Masami Hiramatsu mhiramat@kernel.org Cc: stable@vger.kernel.org Message-Id: 20220407073323.743224-4-guoren@kernel.org Signed-off-by: Max Filippov jcmvbkbc@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/xtensa/kernel/jump_label.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/xtensa/kernel/jump_label.c +++ b/arch/xtensa/kernel/jump_label.c @@ -40,7 +40,7 @@ static int patch_text_stop_machine(void { struct patch *patch = data;

- if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { local_patch_text(patch->addr, patch->data, patch->sz); atomic_inc(&patch->cpu_count); } else {

From: Paolo Valerio pvalerio@redhat.com

commit cefa91b2332d7009bc0be5d951d6cbbf349f90f8 upstream.

Given a sufficiently large number of actions, while copying and reserving memory for a new action of a new flow, if next_offset is greater than MAX_ACTIONS_BUFSIZE, the function reserve_sfa_size() does not return -EMSGSIZE as expected, but it allocates MAX_ACTIONS_BUFSIZE bytes increasing actions_len by req_size. This can then lead to an OOB write access, especially when further actions need to be copied.

Fix it by rearranging the flow action size check.

KASAN splat below:

================================================================== BUG: KASAN: slab-out-of-bounds in reserve_sfa_size+0x1ba/0x380 [openvswitch] Write of size 65360 at addr ffff888147e4001c by task handler15/836

CPU: 1 PID: 836 Comm: handler15 Not tainted 5.18.0-rc1+ #27 ... Call Trace: <TASK> dump_stack_lvl+0x45/0x5a print_report.cold+0x5e/0x5db ? __lock_text_start+0x8/0x8 ? reserve_sfa_size+0x1ba/0x380 [openvswitch] kasan_report+0xb5/0x130 ? reserve_sfa_size+0x1ba/0x380 [openvswitch] kasan_check_range+0xf5/0x1d0 memcpy+0x39/0x60 reserve_sfa_size+0x1ba/0x380 [openvswitch] __add_action+0x24/0x120 [openvswitch] ovs_nla_add_action+0xe/0x20 [openvswitch] ovs_ct_copy_action+0x29d/0x1130 [openvswitch] ? __kernel_text_address+0xe/0x30 ? unwind_get_return_address+0x56/0xa0 ? create_prof_cpu_mask+0x20/0x20 ? ovs_ct_verify+0xf0/0xf0 [openvswitch] ? prep_compound_page+0x198/0x2a0 ? __kasan_check_byte+0x10/0x40 ? kasan_unpoison+0x40/0x70 ? ksize+0x44/0x60 ? reserve_sfa_size+0x75/0x380 [openvswitch] __ovs_nla_copy_actions+0xc26/0x2070 [openvswitch] ? __zone_watermark_ok+0x420/0x420 ? validate_set.constprop.0+0xc90/0xc90 [openvswitch] ? __alloc_pages+0x1a9/0x3e0 ? __alloc_pages_slowpath.constprop.0+0x1da0/0x1da0 ? unwind_next_frame+0x991/0x1e40 ? __mod_node_page_state+0x99/0x120 ? __mod_lruvec_page_state+0x2e3/0x470 ? __kasan_kmalloc_large+0x90/0xe0 ovs_nla_copy_actions+0x1b4/0x2c0 [openvswitch] ovs_flow_cmd_new+0x3cd/0xb10 [openvswitch] ...

Cc: stable@vger.kernel.org Fixes: f28cd2af22a0 ("openvswitch: fix flow actions reallocation") Signed-off-by: Paolo Valerio pvalerio@redhat.com Acked-by: Eelco Chaudron echaudro@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/openvswitch/flow_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2436,7 +2436,7 @@ static struct nlattr *reserve_sfa_size(s new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);

if (new_acts_size > MAX_ACTIONS_BUFSIZE) { - if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { + if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) { OVS_NLERR(log, "Flow action size exceeds max %u", MAX_ACTIONS_BUFSIZE); return ERR_PTR(-EMSGSIZE);

From: Xiaomeng Tong xiam0nd.tong@gmail.com

commit f730a46b931d894816af34a0ff8e4ad51565b39f upstream.

These two bug are here: list_for_each_entry_safe_continue(w, n, list, power_list); list_for_each_entry_safe_continue(w, n, list, power_list);

After the list_for_each_entry_safe_continue() exits, the list iterator will always be a bogus pointer which point to an invalid struct objdect containing HEAD member. The funciton poniter 'w->event' will be a invalid value which can lead to a control-flow hijack if the 'w' can be controlled.

The original intention was to continue the outer list_for_each_entry_safe() loop with the same entry if w->event is NULL, but misunderstanding the meaning of list_for_each_entry_safe_continue().

So just add a 'continue;' to fix the bug.

Cc: stable@vger.kernel.org Fixes: 163cac061c973 ("ASoC: Factor out DAPM sequence execution") Signed-off-by: Xiaomeng Tong xiam0nd.tong@gmail.com Link: https://lore.kernel.org/r/20220329012134.9375-1-xiam0nd.tong@gmail.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/soc-dapm.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

--- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1685,8 +1685,7 @@ static void dapm_seq_run(struct snd_soc_ switch (w->id) { case snd_soc_dapm_pre: if (!w->event) - list_for_each_entry_safe_continue(w, n, list, - power_list); + continue;

if (event == SND_SOC_DAPM_STREAM_START) ret = w->event(w, @@ -1698,8 +1697,7 @@ static void dapm_seq_run(struct snd_soc_

case snd_soc_dapm_post: if (!w->event) - list_for_each_entry_safe_continue(w, n, list, - power_list); + continue;

if (event == SND_SOC_DAPM_STREAM_START) ret = w->event(w,

From: Sergey Matyukevich sergey.matyukevich@synopsys.com

commit b1c6ecfdd06907554518ec384ce8e99889d15193 upstream.

Function syscall_trace_exit expects pointer to pt_regs. However r0 is also used to keep syscall return value. Restore pointer to pt_regs before calling syscall_trace_exit.

Cc: stable@vger.kernel.org Signed-off-by: Sergey Matyukevich sergey.matyukevich@synopsys.com Signed-off-by: Vineet Gupta vgupta@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arc/kernel/entry.S | 1 + 1 file changed, 1 insertion(+)

--- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -196,6 +196,7 @@ tracesys_exit: st r0, [sp, PT_r0] ; sys call return value in pt_regs

;POST Sys Call Ptrace Hook + mov r0, sp ; pt_regs needed bl @syscall_trace_exit b ret_from_exception ; NOT ret_from_system_call at is saves r0 which ; we'd done before calling post hook above

From: Like Xu likexu@tencent.com

commit 75189d1de1b377e580ebd2d2c55914631eac9c64 upstream.

NMI-watchdog is one of the favorite features of kernel developers, but it does not work in AMD guest even with vPMU enabled and worse, the system misrepresents this capability via /proc.

This is a PMC emulation error. KVM does not pass the latest valid value to perf_event in time when guest NMI-watchdog is running, thus the perf_event corresponding to the watchdog counter will enter the old state at some point after the first guest NMI injection, forcing the hardware register PMC0 to be constantly written to 0x800000000001.

Meanwhile, the running counter should accurately reflect its new value based on the latest coordinated pmc->counter (from vPMC's point of view) rather than the value written directly by the guest.

Fixes: 168d918f2643 ("KVM: x86: Adjust counter sample period after a wrmsr") Reported-by: Dongli Cao caodongli@kingsoft.com Signed-off-by: Like Xu likexu@tencent.com Reviewed-by: Yanan Wang wangyanan55@huawei.com Tested-by: Yanan Wang wangyanan55@huawei.com Reviewed-by: Jim Mattson jmattson@google.com Message-Id: 20220409015226.38619-1-likexu@tencent.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/pmu.h | 9 +++++++++ arch/x86/kvm/svm/pmu.c | 1 + arch/x86/kvm/vmx/pmu_intel.c | 8 ++------ 3 files changed, 12 insertions(+), 6 deletions(-)

--- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -141,6 +141,15 @@ static inline u64 get_sample_period(stru return sample_period; }

+static inline void pmc_update_sample_period(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event || pmc->is_paused) + return; + + perf_event_period(pmc->perf_event, + get_sample_period(pmc, pmc->counter)); +} + void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -256,6 +256,7 @@ static int amd_pmu_set_msr(struct kvm_vc pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { pmc->counter += data - pmc_read_counter(pmc); + pmc_update_sample_period(pmc); return 0; } /* MSR_EVNTSELn */ --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -439,15 +439,11 @@ static int intel_pmu_set_msr(struct kvm_ !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel)

From: Sean Christopherson seanjc@google.com

commit 7c69661e225cc484fbf44a0b99b56714a5241ae3 upstream.

Defer APICv updates that occur while L2 is active until nested VM-Exit, i.e. until L1 regains control. vmx_refresh_apicv_exec_ctrl() assumes L1 is active and (a) stomps all over vmcs02 and (b) neglects to ever updated vmcs01. E.g. if vmcs12 doesn't enable the TPR shadow for L2 (and thus no APICv controls), L1 performs nested VM-Enter APICv inhibited, and APICv becomes unhibited while L2 is active, KVM will set various APICv controls in vmcs02 and trigger a failed VM-Entry. The kicker is that, unless running with nested_early_check=1, KVM blames L1 and chaos ensues.

In all cases, ignoring vmcs02 and always deferring the inhibition change to vmcs01 is correct (or at least acceptable). The ABSENT and DISABLE inhibitions cannot truly change while L2 is active (see below).

IRQ_BLOCKING can change, but it is firmly a best effort debug feature. Furthermore, only L2's APIC is accelerated/virtualized to the full extent possible, e.g. even if L1 passes through its APIC to L2, normal MMIO/MSR interception will apply to the virtual APIC managed by KVM. The exception is the SELF_IPI register when x2APIC is enabled, but that's an acceptable hole.

Lastly, Hyper-V's Auto EOI can technically be toggled if L1 exposes the MSRs to L2, but for that to work in any sane capacity, L1 would need to pass through IRQs to L2 as well, and IRQs must be intercepted to enable virtual interrupt delivery. I.e. exposing Auto EOI to L2 and enabling VID for L2 are, for all intents and purposes, mutually exclusive.

Lack of dynamic toggling is also why this scenario is all but impossible to encounter in KVM's current form. But a future patch will pend an APICv update request _during_ vCPU creation to plug a race where a vCPU that's being created doesn't get included in the "all vCPUs request" because it's not yet visible to other vCPUs. If userspaces restores L2 after VM creation (hello, KVM selftests), the first KVM_RUN will occur while L2 is active and thus service the APICv update request made during VM creation.

Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20220420013732.3308816-3-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx/nested.c | 5 +++++ arch/x86/kvm/vmx/vmx.c | 5 +++++ arch/x86/kvm/vmx/vmx.h | 1 + 3 files changed, 11 insertions(+)

--- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4601,6 +4601,11 @@ void nested_vmx_vmexit(struct kvm_vcpu * kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); }

+ if (vmx->nested.update_vmcs01_apicv_status) { + vmx->nested.update_vmcs01_apicv_status = false; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } + if ((vm_exit_reason != -1) && (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) vmx->nested.need_vmcs12_to_shadow_sync = true; --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4098,6 +4098,11 @@ static void vmx_refresh_apicv_exec_ctrl( { struct vcpu_vmx *vmx = to_vmx(vcpu);

+ if (is_guest_mode(vcpu)) { + vmx->nested.update_vmcs01_apicv_status = true; + return; + } + pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); if (cpu_has_secondary_exec_ctrls()) { if (kvm_vcpu_apicv_active(vcpu)) --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -164,6 +164,7 @@ struct nested_vmx { bool change_vmcs01_virtual_apic_mode; bool reload_vmcs01_apic_access_page; bool update_vmcs01_cpu_dirty_logging; + bool update_vmcs01_apicv_status;

/* * Enlightened VMCS has been enabled. It does not mean that L1 has to

From: Florian Westphal fw@strlen.de

commit 719774377622bc4025d2a74f551b5dc2158c6c30 upstream.

Convert nf_conn reference counting from atomic_t to refcount_t based api. refcount_t api provides more runtime sanity checks and will warn on certain constructs, e.g. refcount_inc() on a zero reference count, which usually indicates use-after-free.

For this reason template allocation is changed to init the refcount to 1, the subsequenct add operations are removed.

Likewise, init_conntrack() is changed to set the initial refcount to 1 instead refcount_inc().

This is safe because the new entry is not (yet) visible to other cpus.

Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/netfilter/nf_conntrack_common.h | 8 ++++---- net/netfilter/nf_conntrack_core.c | 26 +++++++++++++------------- net/netfilter/nf_conntrack_expect.c | 4 ++-- net/netfilter/nf_conntrack_netlink.c | 6 +++--- net/netfilter/nf_conntrack_standalone.c | 4 ++-- net/netfilter/nf_flow_table_core.c | 2 +- net/netfilter/nf_synproxy_core.c | 1 - net/netfilter/nft_ct.c | 4 +--- net/netfilter/xt_CT.c | 3 +-- net/openvswitch/conntrack.c | 1 - net/sched/act_ct.c | 1 - 11 files changed, 27 insertions(+), 33 deletions(-)

--- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -2,7 +2,7 @@ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H

-#include <linux/atomic.h> +#include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h>

struct ip_conntrack_stat { @@ -25,19 +25,19 @@ struct ip_conntrack_stat { #define NFCT_PTRMASK ~(NFCT_INFOMASK)

struct nf_conntrack { - atomic_t use; + refcount_t use; };

void nf_conntrack_destroy(struct nf_conntrack *nfct); static inline void nf_conntrack_put(struct nf_conntrack *nfct) { - if (nfct && atomic_dec_and_test(&nfct->use)) + if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) - atomic_inc(&nfct->use); + refcount_inc(&nfct->use); }

#endif /* _NF_CONNTRACK_COMMON_H */ --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -598,7 +598,7 @@ struct nf_conn *nf_ct_tmpl_alloc(struct tmpl->status = IPS_TEMPLATE; write_pnet(&tmpl->ct_net, net); nf_ct_zone_add(tmpl, zone); - atomic_set(&tmpl->ct_general.use, 0); + refcount_set(&tmpl->ct_general.use, 1);

return tmpl; } @@ -631,7 +631,7 @@ destroy_conntrack(struct nf_conntrack *n struct nf_conn *ct = (struct nf_conn *)nfct;

pr_debug("destroy_conntrack(%p)\n", ct); - WARN_ON(atomic_read(&nfct->use) != 0); + WARN_ON(refcount_read(&nfct->use) != 0);

if (unlikely(nf_ct_is_template(ct))) { nf_ct_tmpl_free(ct); @@ -755,7 +755,7 @@ nf_ct_match(const struct nf_conn *ct1, c /* caller must hold rcu readlock and none of the nf_conntrack_locks */ static void nf_ct_gc_expired(struct nf_conn *ct) { - if (!atomic_inc_not_zero(&ct->ct_general.use)) + if (!refcount_inc_not_zero(&ct->ct_general.use)) return;

if (nf_ct_should_gc(ct)) @@ -823,7 +823,7 @@ __nf_conntrack_find_get(struct net *net, * in, try to obtain a reference and re-check tuple */ ct = nf_ct_tuplehash_to_ctrack(h); - if (likely(atomic_inc_not_zero(&ct->ct_general.use))) { + if (likely(refcount_inc_not_zero(&ct->ct_general.use))) { if (likely(nf_ct_key_equal(h, tuple, zone, net))) goto found;

@@ -920,7 +920,7 @@ nf_conntrack_hash_check_insert(struct nf

smp_wmb(); /* The caller holds a reference to this object */ - atomic_set(&ct->ct_general.use, 2); + refcount_set(&ct->ct_general.use, 2); __nf_conntrack_hash_insert(ct, hash, reply_hash); nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert); @@ -971,7 +971,7 @@ static void __nf_conntrack_insert_prepar { struct nf_conn_tstamp *tstamp;

- atomic_inc(&ct->ct_general.use); + refcount_inc(&ct->ct_general.use); ct->status |= IPS_CONFIRMED;

/* set conntrack timestamp, if enabled. */ @@ -1364,7 +1364,7 @@ static unsigned int early_drop_list(stru nf_ct_is_dying(tmp)) continue;

- if (!atomic_inc_not_zero(&tmp->ct_general.use)) + if (!refcount_inc_not_zero(&tmp->ct_general.use)) continue;

/* kill only if still in same netns -- might have moved due to @@ -1513,7 +1513,7 @@ static void gc_worker(struct work_struct continue;

/* need to take reference to avoid possible races */ - if (!atomic_inc_not_zero(&tmp->ct_general.use)) + if (!refcount_inc_not_zero(&tmp->ct_general.use)) continue;

if (gc_worker_skip_ct(tmp)) { @@ -1622,7 +1622,7 @@ __nf_conntrack_alloc(struct net *net, /* Because we use RCU lookups, we set ct_general.use to zero before * this is inserted in any list. */ - atomic_set(&ct->ct_general.use, 0); + refcount_set(&ct->ct_general.use, 0); return ct; out: atomic_dec(&cnet->count); @@ -1647,7 +1647,7 @@ void nf_conntrack_free(struct nf_conn *c /* A freed object has refcnt == 0, that's * the golden rule for SLAB_TYPESAFE_BY_RCU */ - WARN_ON(atomic_read(&ct->ct_general.use) != 0); + WARN_ON(refcount_read(&ct->ct_general.use) != 0);

nf_ct_ext_destroy(ct); kmem_cache_free(nf_conntrack_cachep, ct); @@ -1739,8 +1739,8 @@ init_conntrack(struct net *net, struct n if (!exp) __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);

- /* Now it is inserted into the unconfirmed list, bump refcount */ - nf_conntrack_get(&ct->ct_general); + /* Now it is inserted into the unconfirmed list, set refcount to 1. */ + refcount_set(&ct->ct_general.use, 1); nf_ct_add_to_unconfirmed_list(ct);

local_bh_enable(); @@ -2352,7 +2352,7 @@ get_next_corpse(int (*iter)(struct nf_co

return NULL; found: - atomic_inc(&ct->ct_general.use); + refcount_inc(&ct->ct_general.use); spin_unlock(lockp); local_bh_enable(); return ct; --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -203,12 +203,12 @@ nf_ct_find_expectation(struct net *net, * about to invoke ->destroy(), or nf_ct_delete() via timeout * or early_drop(). * - * The atomic_inc_not_zero() check tells: If that fails, we + * The refcount_inc_not_zero() check tells: If that fails, we * know that the ct is being destroyed. If it succeeds, we * can be sure the ct cannot disappear underneath. */ if (unlikely(nf_ct_is_dying(exp->master) || - !atomic_inc_not_zero(&exp->master->ct_general.use))) + !refcount_inc_not_zero(&exp->master->ct_general.use))) return NULL;

if (exp->flags & NF_CT_EXPECT_PERMANENT) { --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -508,7 +508,7 @@ nla_put_failure:

static int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct) { - if (nla_put_be32(skb, CTA_USE, htonl(atomic_read(&ct->ct_general.use)))) + if (nla_put_be32(skb, CTA_USE, htonl(refcount_read(&ct->ct_general.use)))) goto nla_put_failure; return 0;

@@ -1200,7 +1200,7 @@ restart: ct = nf_ct_tuplehash_to_ctrack(h); if (nf_ct_is_expired(ct)) { if (i < ARRAY_SIZE(nf_ct_evict) && - atomic_inc_not_zero(&ct->ct_general.use)) + refcount_inc_not_zero(&ct->ct_general.use)) nf_ct_evict[i++] = ct; continue; } @@ -1748,7 +1748,7 @@ restart: NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, dying ? true : false, 0); if (res < 0) { - if (!atomic_inc_not_zero(&ct->ct_general.use)) + if (!refcount_inc_not_zero(&ct->ct_general.use)) continue; cb->args[0] = cpu; cb->args[1] = (unsigned long)ct; --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -303,7 +303,7 @@ static int ct_seq_show(struct seq_file * int ret = 0;

WARN_ON(!ct); - if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) + if (unlikely(!refcount_inc_not_zero(&ct->ct_general.use))) return 0;

if (nf_ct_should_gc(ct)) { @@ -370,7 +370,7 @@ static int ct_seq_show(struct seq_file * ct_show_zone(s, ct, NF_CT_DEFAULT_ZONE_DIR); ct_show_delta_time(s, ct);

- seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)); + seq_printf(s, "use=%u\n", refcount_read(&ct->ct_general.use));

if (seq_has_overflowed(s)) goto release; --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -48,7 +48,7 @@ struct flow_offload *flow_offload_alloc( struct flow_offload *flow;

if (unlikely(nf_ct_is_dying(ct) || - !atomic_inc_not_zero(&ct->ct_general.use))) + !refcount_inc_not_zero(&ct->ct_general.use))) return NULL;

flow = kzalloc(sizeof(*flow), GFP_ATOMIC); --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -349,7 +349,6 @@ static int __net_init synproxy_net_init( goto err2;

__set_bit(IPS_CONFIRMED_BIT, &ct->status); - nf_conntrack_get(&ct->ct_general); snet->tmpl = ct;

snet->stats = alloc_percpu(struct synproxy_stats); --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -259,7 +259,7 @@ static void nft_ct_set_zone_eval(const s

ct = this_cpu_read(nft_ct_pcpu_template);

- if (likely(atomic_read(&ct->ct_general.use) == 1)) { + if (likely(refcount_read(&ct->ct_general.use) == 1)) { nf_ct_zone_add(ct, &zone); } else { /* previous skb got queued to userspace */ @@ -270,7 +270,6 @@ static void nft_ct_set_zone_eval(const s } }

- atomic_inc(&ct->ct_general.use); nf_ct_set(skb, ct, IP_CT_NEW); } #endif @@ -375,7 +374,6 @@ static bool nft_ct_tmpl_alloc_pcpu(void) return false; }

- atomic_set(&tmp->ct_general.use, 1); per_cpu(nft_ct_pcpu_template, cpu) = tmp; }

--- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -24,7 +24,7 @@ static inline int xt_ct_target(struct sk return XT_CONTINUE;

if (ct) { - atomic_inc(&ct->ct_general.use); + refcount_inc(&ct->ct_general.use); nf_ct_set(skb, ct, IP_CT_NEW); } else { nf_ct_set(skb, ct, IP_CT_UNTRACKED); @@ -201,7 +201,6 @@ static int xt_ct_tg_check(const struct x goto err4; } __set_bit(IPS_CONFIRMED_BIT, &ct->status); - nf_conntrack_get(&ct->ct_general); out: info->ct = ct; return 0; --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1722,7 +1722,6 @@ int ovs_ct_copy_action(struct net *net, goto err_free_ct;

__set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); - nf_conntrack_get(&ct_info.ct->ct_general); return 0; err_free_ct: __ovs_ct_free_action(&ct_info); --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1232,7 +1232,6 @@ static int tcf_ct_fill_params(struct net return -ENOMEM; } __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); - nf_conntrack_get(&tmpl->ct_general); p->tmpl = tmpl;

return 0;

From: Darrick J. Wong djwong@kernel.org

commit ad5cd4f4ee4d5fcdb1bfb7a0c073072961e70783 upstream.

Since the initial introduction of (posix) fallocate back at the turn of the century, it has been possible to use this syscall to change the user-visible contents of files. This can happen by extending the file size during a preallocation, or through any of the newer modes (punch, zero, collapse, insert range). Because the call can be used to change file contents, we should treat it like we do any other modification to a file -- update the mtime, and drop set[ug]id privileges/capabilities.

The VFS function file_modified() does all this for us if pass it a locked inode, so let's make fallocate drop permissions correctly.

Signed-off-by: Darrick J. Wong djwong@kernel.org Link: https://lore.kernel.org/r/20220308185043.GA117678@magnolia Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/ext4.h | 2 +- fs/ext4/extents.c | 32 +++++++++++++++++++++++++------- fs/ext4/inode.c | 7 ++++++- 3 files changed, 32 insertions(+), 9 deletions(-)

--- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3027,7 +3027,7 @@ extern int ext4_inode_attach_jinode(stru extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); -extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length); +extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length); extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4504,9 +4504,9 @@ retry: return ret > 0 ? ret2 : ret; }

-static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len);

-static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len);

static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) @@ -4578,6 +4578,10 @@ static long ext4_zero_range(struct file /* Wait all existing dio workers, newcomers will block on i_mutex */ inode_dio_wait(inode);

+ ret = file_modified(file); + if (ret) + goto out_mutex; + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4696,7 +4700,7 @@ long ext4_fallocate(struct file *file, i ext4_fc_start_update(inode);

if (mode & FALLOC_FL_PUNCH_HOLE) { - ret = ext4_punch_hole(inode, offset, len); + ret = ext4_punch_hole(file, offset, len); goto exit; }

@@ -4705,12 +4709,12 @@ long ext4_fallocate(struct file *file, i goto exit;

if (mode & FALLOC_FL_COLLAPSE_RANGE) { - ret = ext4_collapse_range(inode, offset, len); + ret = ext4_collapse_range(file, offset, len); goto exit; }

if (mode & FALLOC_FL_INSERT_RANGE) { - ret = ext4_insert_range(inode, offset, len); + ret = ext4_insert_range(file, offset, len); goto exit; }

@@ -4746,6 +4750,10 @@ long ext4_fallocate(struct file *file, i /* Wait all existing dio workers, newcomers will block on i_mutex */ inode_dio_wait(inode);

+ ret = file_modified(file); + if (ret) + goto out; + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); if (ret) goto out; @@ -5248,8 +5256,9 @@ out: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; ext4_lblk_t punch_start, punch_stop; @@ -5301,6 +5310,10 @@ static int ext4_collapse_range(struct in /* Wait for existing dio to complete */ inode_dio_wait(inode);

+ ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. @@ -5394,8 +5407,9 @@ out_mutex: * by len bytes. * Returns 0 on success, error otherwise. */ -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; handle_t *handle; @@ -5452,6 +5466,10 @@ static int ext4_insert_range(struct inod /* Wait for existing dio to complete */ inode_dio_wait(inode);

+ ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3939,8 +3939,9 @@ int ext4_break_layouts(struct inode *ino * Returns: 0 on success or negative on failure */

-int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) +int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; ext4_lblk_t first_block, stop_block; struct address_space *mapping = inode->i_mapping; @@ -4002,6 +4003,10 @@ int ext4_punch_hole(struct inode *inode, /* Wait all existing dio workers, newcomers will block on i_mutex */ inode_dio_wait(inode);

+ ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache.

From: Ye Bin yebin10@huawei.com

commit c186f0887fe7061a35cebef024550ec33ef8fbd8 upstream.

We got issue as follows: EXT4-fs (loop0): mounted filesystem without journal. Opts: ,errors=continue ================================================================== BUG: KASAN: use-after-free in ext4_search_dir fs/ext4/namei.c:1394 [inline] BUG: KASAN: use-after-free in search_dirblock fs/ext4/namei.c:1199 [inline] BUG: KASAN: use-after-free in __ext4_find_entry+0xdca/0x1210 fs/ext4/namei.c:1553 Read of size 1 at addr ffff8881317c3005 by task syz-executor117/2331

CPU: 1 PID: 2331 Comm: syz-executor117 Not tainted 5.10.0+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:83 [inline] dump_stack+0x144/0x187 lib/dump_stack.c:124 print_address_description+0x7d/0x630 mm/kasan/report.c:387 __kasan_report+0x132/0x190 mm/kasan/report.c:547 kasan_report+0x47/0x60 mm/kasan/report.c:564 ext4_search_dir fs/ext4/namei.c:1394 [inline] search_dirblock fs/ext4/namei.c:1199 [inline] __ext4_find_entry+0xdca/0x1210 fs/ext4/namei.c:1553 ext4_lookup_entry fs/ext4/namei.c:1622 [inline] ext4_lookup+0xb8/0x3a0 fs/ext4/namei.c:1690 __lookup_hash+0xc5/0x190 fs/namei.c:1451 do_rmdir+0x19e/0x310 fs/namei.c:3760 do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x445e59 Code: 4d c7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 1b c7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fff2277fac8 EFLAGS: 00000246 ORIG_RAX: 0000000000000054 RAX: ffffffffffffffda RBX: 0000000000400280 RCX: 0000000000445e59 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00000000200000c0 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000002 R10: 00007fff2277f990 R11: 0000000000000246 R12: 0000000000000000 R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000

The buggy address belongs to the page: page:0000000048cd3304 refcount:0 mapcount:0 mapping:0000000000000000 index:0x1 pfn:0x1317c3 flags: 0x200000000000000() raw: 0200000000000000 ffffea0004526588 ffffea0004528088 0000000000000000 raw: 0000000000000001 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff8881317c2f00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff8881317c2f80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

ffff8881317c3000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

^ ffff8881317c3080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff8881317c3100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ==================================================================

ext4_search_dir: ... de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; while ((char *) de < dlimit) { ... if ((char *) de + de->name_len <= dlimit && ext4_match(dir, fname, de)) { ... } ... de_len = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); if (de_len <= 0) return -1; offset += de_len; de = (struct ext4_dir_entry_2 *) ((char *) de + de_len); }

Assume: de=0xffff8881317c2fff dlimit=0x0xffff8881317c3000

If read 'de->name_len' which address is 0xffff8881317c3005, obviously is out of range, then will trigger use-after-free. To solve this issue, 'dlimit' must reserve 8 bytes, as we will read 'de->name_len' to judge if '(char *) de + de->name_len' out of range.

Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20220324064816.1209985-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/ext4.h | 4 ++++ fs/ext4/namei.c | 4 ++-- 2 files changed, 6 insertions(+), 2 deletions(-)

--- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2267,6 +2267,10 @@ static inline int ext4_forced_shutdown(s * Structure of a directory entry */ #define EXT4_NAME_LEN 255 +/* + * Base length of the ext4 directory entry excluding the name length + */ +#define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN)

struct ext4_dir_entry { __le32 inode; /* Inode number */ --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1466,10 +1466,10 @@ int ext4_search_dir(struct buffer_head *

de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; - while ((char *) de < dlimit) { + while ((char *) de < dlimit - EXT4_BASE_DIR_LEN) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ - if ((char *) de + de->name_len <= dlimit && + if (de->name + de->name_len <= dlimit && ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */

From: wangjianjian (C) wangjianjian3@huawei.com

commit 7102ffe4c166ca0f5e35137e9f9de83768c2d27d upstream.

According to document and code, ext4_xattr_header's size is 32 bytes, so h_reserved size should be 3.

Signed-off-by: Wang Jianjian wangjianjian3@huawei.com Link: https://lore.kernel.org/r/92fcc3a6-7d77-8c09-4126-377fcb4c46a5@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/filesystems/ext4/attributes.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/Documentation/filesystems/ext4/attributes.rst +++ b/Documentation/filesystems/ext4/attributes.rst @@ -76,7 +76,7 @@ The beginning of an extended attribute b - Checksum of the extended attribute block. * - 0x14 - __u32 - - h_reserved[2] + - h_reserved[3] - Zero.

The checksum is calculated against the FS UUID, the 64-bit block number

From: Theodore Ts'o tytso@mit.edu

commit 85d825dbf4899a69407338bae462a59aa9a37326 upstream.

If the file system does not use bigalloc, calculating the overhead is cheap, so force the recalculation of the overhead so we don't have to trust the precalculated overhead in the superblock.

Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/super.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)

--- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4788,9 +4788,18 @@ no_journal: * Get the # of file system overhead blocks from the * superblock if present. */ - if (es->s_overhead_clusters) - sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); - else { + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + /* ignore the precalculated value if it is ridiculous */ + if (sbi->s_overhead > ext4_blocks_count(es)) + sbi->s_overhead = 0; + /* + * If the bigalloc feature is not enabled recalculating the + * overhead doesn't take long, so we might as well just redo + * it to make sure we are using the correct value. + */ + if (!ext4_has_feature_bigalloc(sb)) + sbi->s_overhead = 0; + if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq;

From: Ye Bin yebin10@huawei.com

commit 23e3d7f7061f8682c751c46512718f47580ad8f0 upstream.

we got issue as follows: [ 72.796117] EXT4-fs error (device sda): ext4_journal_check_start:83: comm fallocate: Detected aborted journal [ 72.826847] EXT4-fs (sda): Remounting filesystem read-only fallocate: fallocate failed: Read-only file system [ 74.791830] jbd2_journal_commit_transaction: jh=0xffff9cfefe725d90 bh=0x0000000000000000 end delay [ 74.793597] ------------[ cut here ]------------ [ 74.794203] kernel BUG at fs/jbd2/transaction.c:2063! [ 74.794886] invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 74.795533] CPU: 4 PID: 2260 Comm: jbd2/sda-8 Not tainted 5.17.0-rc8-next-20220315-dirty #150 [ 74.798327] RIP: 0010:__jbd2_journal_unfile_buffer+0x3e/0x60 [ 74.801971] RSP: 0018:ffffa828c24a3cb8 EFLAGS: 00010202 [ 74.802694] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 74.803601] RDX: 0000000000000001 RSI: ffff9cfefe725d90 RDI: ffff9cfefe725d90 [ 74.804554] RBP: ffff9cfefe725d90 R08: 0000000000000000 R09: ffffa828c24a3b20 [ 74.805471] R10: 0000000000000001 R11: 0000000000000001 R12: ffff9cfefe725d90 [ 74.806385] R13: ffff9cfefe725d98 R14: 0000000000000000 R15: ffff9cfe833a4d00 [ 74.807301] FS: 0000000000000000(0000) GS:ffff9d01afb00000(0000) knlGS:0000000000000000 [ 74.808338] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 74.809084] CR2: 00007f2b81bf4000 CR3: 0000000100056000 CR4: 00000000000006e0 [ 74.810047] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 74.810981] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 74.811897] Call Trace: [ 74.812241] <TASK> [ 74.812566] __jbd2_journal_refile_buffer+0x12f/0x180 [ 74.813246] jbd2_journal_refile_buffer+0x4c/0xa0 [ 74.813869] jbd2_journal_commit_transaction.cold+0xa1/0x148 [ 74.817550] kjournald2+0xf8/0x3e0 [ 74.819056] kthread+0x153/0x1c0 [ 74.819963] ret_from_fork+0x22/0x30

Above issue may happen as follows: write truncate kjournald2 generic_perform_write ext4_write_begin ext4_walk_page_buffers do_journal_get_write_access ->add BJ_Reserved list ext4_journalled_write_end ext4_walk_page_buffers write_end_fn ext4_handle_dirty_metadata ***************JBD2 ABORT************** jbd2_journal_dirty_metadata -> return -EROFS, jh in reserved_list jbd2_journal_commit_transaction while (commit_transaction->t_reserved_list) jh = commit_transaction->t_reserved_list; truncate_pagecache_range do_invalidatepage ext4_journalled_invalidatepage jbd2_journal_invalidatepage journal_unmap_buffer __dispose_buffer __jbd2_journal_unfile_buffer jbd2_journal_put_journal_head ->put last ref_count __journal_remove_journal_head bh->b_private = NULL; jh->b_bh = NULL; jbd2_journal_refile_buffer(journal, jh); bh = jh2bh(jh); ->bh is NULL, later will trigger null-ptr-deref journal_free_journal_head(jh);

After commit 96f1e0974575, we no longer hold the j_state_lock while iterating over the list of reserved handles in jbd2_journal_commit_transaction(). This potentially allows the journal_head to be freed by journal_unmap_buffer while the commit codepath is also trying to free the BJ_Reserved buffers. Keeping j_state_lock held while trying extends hold time of the lock minimally, and solves this issue.

Fixes: 96f1e0974575("jbd2: avoid long hold times of j_state_lock while committing a transaction") Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20220317142137.1821590-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/jbd2/commit.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -501,7 +501,6 @@ void jbd2_journal_commit_transaction(jou } spin_unlock(&commit_transaction->t_handle_lock); commit_transaction->t_state = T_SWITCH; - write_unlock(&journal->j_state_lock);

J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <= journal->j_max_transaction_buffers); @@ -521,6 +520,8 @@ void jbd2_journal_commit_transaction(jou * has reserved. This is consistent with the existing behaviour * that multiple jbd2_journal_get_write_access() calls to the same * buffer are perfectly permissible. + * We use journal->j_state_lock here to serialize processing of + * t_reserved_list with eviction of buffers from journal_unmap_buffer(). */ while (commit_transaction->t_reserved_list) { jh = commit_transaction->t_reserved_list; @@ -540,6 +541,7 @@ void jbd2_journal_commit_transaction(jou jbd2_journal_refile_buffer(journal, jh); }

+ write_unlock(&journal->j_state_lock); /* * Now try to drop any written-back buffers from the journal's * checkpoint lists. We do this *before* commit because it potentially

From: Khazhismel Kumykov khazhy@google.com

commit ccf16413e520164eb718cf8b22a30438da80ff23 upstream.

kernel ulong and compat_ulong_t may not be same width. Use type directly to eliminate mismatches.

This would result in truncation rather than EFBIG for 32bit mode for large disks.

Reviewed-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Khazhismel Kumykov khazhy@google.com Reviewed-by: Chaitanya Kulkarni kch@nvidia.com Link: https://lore.kernel.org/r/20220414224056.2875681-1-khazhy@google.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- block/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/block/ioctl.c +++ b/block/ioctl.c @@ -645,7 +645,7 @@ long compat_blkdev_ioctl(struct file *fi (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: size = i_size_read(bdev->bd_inode); - if ((size >> 9) > ~0UL) + if ((size >> 9) > ~(compat_ulong_t)0) return -EFBIG; return compat_put_ulong(argp, size >> 9);