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

[merged mm-hotfixes-stable] mm-zswap-move-allocations-during-cpu-init-outside-the-lock.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: zswap: move allocations during CPU init outside the lock has been removed from the -mm tree. Its filename was mm-zswap-move-allocations-during-cpu-init-outside-the-lock.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yosry Ahmed <yosryahmed(a)google.com> Subject: mm: zswap: move allocations during CPU init outside the lock Date: Mon, 13 Jan 2025 21:44:58 +0000 In zswap_cpu_comp_prepare(), allocations are made and assigned to various members of acomp_ctx under acomp_ctx->mutex. However, allocations may recurse into zswap through reclaim, trying to acquire the same mutex and deadlocking. Move the allocations before the mutex critical section. Only the initialization of acomp_ctx needs to be done with the mutex held. Link: https://lkml.kernel.org/r/20250113214458.2123410-1-yosryahmed@google.com Fixes: 12dcb0ef5406 ("mm: zswap: properly synchronize freeing resources during CPU hotunplug") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/zswap.c | 42 ++++++++++++++++++++++++------------------ 1 file changed, 24 insertions(+), 18 deletions(-) --- a/mm/zswap.c~mm-zswap-move-allocations-during-cpu-init-outside-the-lock +++ a/mm/zswap.c @@ -820,15 +820,15 @@ static int zswap_cpu_comp_prepare(unsign { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); - struct crypto_acomp *acomp; - struct acomp_req *req; + struct crypto_acomp *acomp = NULL; + struct acomp_req *req = NULL; + u8 *buffer = NULL; int ret; - mutex_lock(&acomp_ctx->mutex); - acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) { + buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); + if (!buffer) { ret = -ENOMEM; - goto buffer_fail; + goto fail; } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); @@ -836,21 +836,25 @@ static int zswap_cpu_comp_prepare(unsign pr_err("could not alloc crypto acomp %s : %ld\n", pool->tfm_name, PTR_ERR(acomp)); ret = PTR_ERR(acomp); - goto acomp_fail; + goto fail; } - acomp_ctx->acomp = acomp; - acomp_ctx->is_sleepable = acomp_is_async(acomp); - req = acomp_request_alloc(acomp_ctx->acomp); + req = acomp_request_alloc(acomp); if (!req) { pr_err("could not alloc crypto acomp_request %s\n", pool->tfm_name); ret = -ENOMEM; - goto req_fail; + goto fail; } - acomp_ctx->req = req; + /* + * Only hold the mutex after completing allocations, otherwise we may + * recurse into zswap through reclaim and attempt to hold the mutex + * again resulting in a deadlock. + */ + mutex_lock(&acomp_ctx->mutex); crypto_init_wait(&acomp_ctx->wait); + /* * if the backend of acomp is async zip, crypto_req_done() will wakeup * crypto_wait_req(); if the backend of acomp is scomp, the callback @@ -859,15 +863,17 @@ static int zswap_cpu_comp_prepare(unsign acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + acomp_ctx->buffer = buffer; + acomp_ctx->acomp = acomp; + acomp_ctx->is_sleepable = acomp_is_async(acomp); + acomp_ctx->req = req; mutex_unlock(&acomp_ctx->mutex); return 0; -req_fail: - crypto_free_acomp(acomp_ctx->acomp); -acomp_fail: - kfree(acomp_ctx->buffer); -buffer_fail: - mutex_unlock(&acomp_ctx->mutex); +fail: + if (acomp) + crypto_free_acomp(acomp); + kfree(buffer); return ret; } _ Patches currently in -mm which might be from yosryahmed(a)google.com are

10 months

1
0
0 0

[merged mm-hotfixes-stable] alloc_tag-skip-pgalloc_tag_swap-if-profiling-is-disabled.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: alloc_tag: skip pgalloc_tag_swap if profiling is disabled has been removed from the -mm tree. Its filename was alloc_tag-skip-pgalloc_tag_swap-if-profiling-is-disabled.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Suren Baghdasaryan <surenb(a)google.com> Subject: alloc_tag: skip pgalloc_tag_swap if profiling is disabled Date: Thu, 26 Dec 2024 13:16:39 -0800 When memory allocation profiling is disabled, there is no need to swap allocation tags during migration. Skip it to avoid unnecessary overhead. Once I added these checks, the overhead of the mode when memory profiling is enabled but turned off went down by about 50%. Link: https://lkml.kernel.org/r/20241226211639.1357704-2-surenb@google.com Fixes: e0a955bf7f61 ("mm/codetag: add pgalloc_tag_copy()") Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Cc: David Wang <00107082(a)163.com> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: Yu Zhao <yuzhao(a)google.com> Cc: Zhenhua Huang <quic_zhenhuah(a)quicinc.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- lib/alloc_tag.c | 3 +++ 1 file changed, 3 insertions(+) --- a/lib/alloc_tag.c~alloc_tag-skip-pgalloc_tag_swap-if-profiling-is-disabled +++ a/lib/alloc_tag.c @@ -195,6 +195,9 @@ void pgalloc_tag_swap(struct folio *new, union codetag_ref ref_old, ref_new; struct alloc_tag *tag_old, *tag_new; + if (!mem_alloc_profiling_enabled()) + return; + tag_old = pgalloc_tag_get(&old->page); if (!tag_old) return; _ Patches currently in -mm which might be from surenb(a)google.com are alloc_tag-avoid-current-alloc_tag-manipulations-when-profiling-is-disabled.patch

10 months

1
0
0 0

[PATCH v2] xfs: fix online repair probing when CONFIG_XFS_ONLINE_REPAIR=n

by Darrick J. Wong

From: Darrick J. Wong <djwong(a)kernel.org> I received a report from the release engineering side of the house that xfs_scrub without the -n flag (aka fix it mode) would try to fix a broken filesystem even on a kernel that doesn't have online repair built into it: # xfs_scrub -dTvn /mnt/test EXPERIMENTAL xfs_scrub program in use! Use at your own risk! Phase 1: Find filesystem geometry. /mnt/test: using 1 threads to scrub. Phase 1: Memory used: 132k/0k (108k/25k), time: 0.00/ 0.00/ 0.00s <snip> Phase 4: Repair filesystem. <snip> Info: /mnt/test/some/victimdir directory entries: Attempting repair. (repair.c line 351) Corruption: /mnt/test/some/victimdir directory entries: Repair unsuccessful; offline repair required. (repair.c line 204) Source: https://blogs.oracle.com/linux/post/xfs-online-filesystem-repair It is strange that xfs_scrub doesn't refuse to run, because the kernel is supposed to return EOPNOTSUPP if we actually needed to run a repair, and xfs_io's repair subcommand will perror that. And yet: # xfs_io -x -c 'repair probe' /mnt/test # The first problem is commit dcb660f9222fd9 (4.15) which should have had xchk_probe set the CORRUPT OFLAG so that any of the repair machinery will get called at all. It turns out that some refactoring that happened in the 6.6-6.8 era broke the operation of this corner case. What we *really* want to happen is that all the predicates that would steer xfs_scrub_metadata() towards calling xrep_attempt() should function the same way that they do when repair is compiled in; and then xrep_attempt gets to return the fatal EOPNOTSUPP error code that causes the probe to fail. Instead, commit 8336a64eb75cba (6.6) started the failwhale swimming by hoisting OFLAG checking logic into a helper whose non-repair stub always returns false, causing scrub to return "repair not needed" when in fact the repair is not supported. Prior to that commit, the oflag checking that was open-coded in scrub.c worked correctly. Similarly, in commit 4bdfd7d15747b1 (6.8) we hoisted the IFLAG_REPAIR and ALREADY_FIXED logic into a helper whose non-repair stub always returns false, so we never enter the if test body that would have called xrep_attempt, let alone fail to decode the OFLAGs correctly. The final insult (yes, we're doing The Naked Gun now) is commit 48a72f60861f79 (6.8) in which we hoisted the "are we going to try a repair?" predicate into yet another function with a non-repair stub always returns false. Fix xchk_probe to trigger xrep_probe if repair is enabled, or return EOPNOTSUPP directly if it is not. For all the other scrub types, we need to fix the header predicates so that the ->repair functions (which are all xrep_notsupported) get called to return EOPNOTSUPP. Commit 48a72 is tagged here because the scrub code prior to LTS 6.12 are incomplete and not worth patching. Reported-by: David Flynn <david.flynn(a)oracle.com> Cc: <stable(a)vger.kernel.org> # v6.8 Fixes: 48a72f60861f79 ("xfs: don't complain about unfixed metadata when repairs were injected") Signed-off-by: "Darrick J. Wong" <djwong(a)kernel.org> Reviewed-by: Christoph Hellwig <hch(a)lst.de> --- fs/xfs/scrub/common.h | 5 ----- fs/xfs/scrub/repair.h | 11 ++++++++++- fs/xfs/scrub/scrub.c | 12 ++++++++++++ 3 files changed, 22 insertions(+), 6 deletions(-) diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 546be550b221b6..4722cb51fd1522 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -225,7 +225,6 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm) bool xchk_dir_looks_zapped(struct xfs_inode *dp); bool xchk_pptr_looks_zapped(struct xfs_inode *ip); -#ifdef CONFIG_XFS_ONLINE_REPAIR /* Decide if a repair is required. */ static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm) { @@ -245,10 +244,6 @@ static inline bool xchk_could_repair(const struct xfs_scrub *sc) return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) && !(sc->flags & XREP_ALREADY_FIXED); } -#else -# define xchk_needs_repair(sc) (false) -# define xchk_could_repair(sc) (false) -#endif /* CONFIG_XFS_ONLINE_REPAIR */ int xchk_metadata_inode_forks(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index 823c00d1a50262..af0a3a9e5ed978 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -191,7 +191,16 @@ int xrep_reset_metafile_resv(struct xfs_scrub *sc); #else #define xrep_ino_dqattach(sc) (0) -#define xrep_will_attempt(sc) (false) + +/* + * When online repair is not built into the kernel, we still want to attempt + * the repair so that the stub xrep_attempt below will return EOPNOTSUPP. + */ +static inline bool xrep_will_attempt(const struct xfs_scrub *sc) +{ + return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) || + xchk_needs_repair(sc->sm); +} static inline int xrep_attempt( diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index d3a4ddd918f621..01fdbbc7adf30e 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -149,6 +149,18 @@ xchk_probe( if (xchk_should_terminate(sc, &error)) return error; + /* + * If the caller is probing to see if repair works but repair isn't + * built into the kernel, return EOPNOTSUPP because that's the signal + * that userspace expects. If online repair is built in, set the + * CORRUPT flag (without any of the usual tracing/logging) to force us + * into xrep_probe. + */ + if (xchk_could_repair(sc)) { + if (!IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)) + return -EOPNOTSUPP; + sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; + } return 0; }

10 months

1
0
0 0

FAILED: patch "[PATCH] iio: adc: rockchip_saradc: fix information leak in triggered" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 38724591364e1e3b278b4053f102b49ea06ee17c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025011310-ruckus-ceramics-7ebc@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 38724591364e1e3b278b4053f102b49ea06ee17c Mon Sep 17 00:00:00 2001 From: Javier Carrasco <javier.carrasco.cruz(a)gmail.com> Date: Mon, 25 Nov 2024 22:16:12 +0100 Subject: [PATCH] iio: adc: rockchip_saradc: fix information leak in triggered buffer The 'data' local struct is used to push data to user space from a triggered buffer, but it does not set values for inactive channels, as it only uses iio_for_each_active_channel() to assign new values. Initialize the struct to zero before using it to avoid pushing uninitialized information to userspace. Cc: stable(a)vger.kernel.org Fixes: 4e130dc7b413 ("iio: adc: rockchip_saradc: Add support iio buffers") Signed-off-by: Javier Carrasco <javier.carrasco.cruz(a)gmail.com> Link: https://patch.msgid.link/20241125-iio_memset_scan_holes-v1-4-0cb6e98d895c@g… Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c index 240cfa391674..dfd47a6e1f4a 100644 --- a/drivers/iio/adc/rockchip_saradc.c +++ b/drivers/iio/adc/rockchip_saradc.c @@ -368,6 +368,8 @@ static irqreturn_t rockchip_saradc_trigger_handler(int irq, void *p) int ret; int i, j = 0; + memset(&data, 0, sizeof(data)); + mutex_lock(&info->lock); iio_for_each_active_channel(i_dev, i) {

10 months

3
2
0 0

[PATCH 6.1.y 1/2] erofs: tidy up EROFS on-disk naming

by Gao Xiang

commit 1c7f49a76773bcf95d3c840cff6cd449114ddf56 upstream. - Get rid of all "vle" (variable-length extents) expressions since they only expand overall name lengths unnecessarily; - Rename COMPRESSION_LEGACY to COMPRESSED_FULL; - Move on-disk directory definitions ahead of compression; - Drop unused extended attribute definitions; - Move inode ondisk union `i_u` out as `union erofs_inode_i_u`. No actual logical change. Reviewed-by: Yue Hu <huyue2(a)coolpad.com> Reviewed-by: Chao Yu <chao(a)kernel.org> Link: https://lore.kernel.org/r/20230331063149.25611-1-hsiangkao@linux.alibaba.com [ A backport dependency to resolve minor conflicts to fix CVE-2024-53234. ] Signed-off-by: Gao Xiang <hsiangkao(a)linux.alibaba.com> --- fs/erofs/erofs_fs.h | 145 +++++++++++++++++++------------------------- fs/erofs/zmap.c | 116 +++++++++++++++++------------------ 2 files changed, 119 insertions(+), 142 deletions(-) diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index 44876a97cabd..1a4a614895c6 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -82,32 +82,27 @@ struct erofs_super_block { }; /* - * erofs inode datalayout (i_format in on-disk inode): + * EROFS inode datalayout (i_format in on-disk inode): * 0 - uncompressed flat inode without tail-packing inline data: - * inode, [xattrs], ... | ... | no-holed data * 1 - compressed inode with non-compact indexes: - * inode, [xattrs], [map_header], extents ... | ... * 2 - uncompressed flat inode with tail-packing inline data: - * inode, [xattrs], tailpacking data, ... | ... | no-holed data * 3 - compressed inode with compact indexes: - * inode, [xattrs], map_header, extents ... | ... * 4 - chunk-based inode with (optional) multi-device support: - * inode, [xattrs], chunk indexes ... | ... * 5~7 - reserved */ enum { EROFS_INODE_FLAT_PLAIN = 0, - EROFS_INODE_FLAT_COMPRESSION_LEGACY = 1, + EROFS_INODE_COMPRESSED_FULL = 1, EROFS_INODE_FLAT_INLINE = 2, - EROFS_INODE_FLAT_COMPRESSION = 3, + EROFS_INODE_COMPRESSED_COMPACT = 3, EROFS_INODE_CHUNK_BASED = 4, EROFS_INODE_DATALAYOUT_MAX }; static inline bool erofs_inode_is_data_compressed(unsigned int datamode) { - return datamode == EROFS_INODE_FLAT_COMPRESSION || - datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY; + return datamode == EROFS_INODE_COMPRESSED_COMPACT || + datamode == EROFS_INODE_COMPRESSED_FULL; } /* bit definitions of inode i_format */ @@ -128,11 +123,30 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode) #define EROFS_CHUNK_FORMAT_ALL \ (EROFS_CHUNK_FORMAT_BLKBITS_MASK | EROFS_CHUNK_FORMAT_INDEXES) +/* 32-byte on-disk inode */ +#define EROFS_INODE_LAYOUT_COMPACT 0 +/* 64-byte on-disk inode */ +#define EROFS_INODE_LAYOUT_EXTENDED 1 + struct erofs_inode_chunk_info { __le16 format; /* chunk blkbits, etc. */ __le16 reserved; }; +union erofs_inode_i_u { + /* total compressed blocks for compressed inodes */ + __le32 compressed_blocks; + + /* block address for uncompressed flat inodes */ + __le32 raw_blkaddr; + + /* for device files, used to indicate old/new device # */ + __le32 rdev; + + /* for chunk-based files, it contains the summary info */ + struct erofs_inode_chunk_info c; +}; + /* 32-byte reduced form of an ondisk inode */ struct erofs_inode_compact { __le16 i_format; /* inode format hints */ @@ -143,29 +157,14 @@ struct erofs_inode_compact { __le16 i_nlink; __le32 i_size; __le32 i_reserved; - union { - /* total compressed blocks for compressed inodes */ - __le32 compressed_blocks; - /* block address for uncompressed flat inodes */ - __le32 raw_blkaddr; - - /* for device files, used to indicate old/new device # */ - __le32 rdev; - - /* for chunk-based files, it contains the summary info */ - struct erofs_inode_chunk_info c; - } i_u; - __le32 i_ino; /* only used for 32-bit stat compatibility */ + union erofs_inode_i_u i_u; + + __le32 i_ino; /* only used for 32-bit stat compatibility */ __le16 i_uid; __le16 i_gid; __le32 i_reserved2; }; -/* 32-byte on-disk inode */ -#define EROFS_INODE_LAYOUT_COMPACT 0 -/* 64-byte on-disk inode */ -#define EROFS_INODE_LAYOUT_EXTENDED 1 - /* 64-byte complete form of an ondisk inode */ struct erofs_inode_extended { __le16 i_format; /* inode format hints */ @@ -175,22 +174,9 @@ struct erofs_inode_extended { __le16 i_mode; __le16 i_reserved; __le64 i_size; - union { - /* total compressed blocks for compressed inodes */ - __le32 compressed_blocks; - /* block address for uncompressed flat inodes */ - __le32 raw_blkaddr; - - /* for device files, used to indicate old/new device # */ - __le32 rdev; - - /* for chunk-based files, it contains the summary info */ - struct erofs_inode_chunk_info c; - } i_u; - - /* only used for 32-bit stat compatibility */ - __le32 i_ino; + union erofs_inode_i_u i_u; + __le32 i_ino; /* only used for 32-bit stat compatibility */ __le32 i_uid; __le32 i_gid; __le64 i_mtime; @@ -199,10 +185,6 @@ struct erofs_inode_extended { __u8 i_reserved2[16]; }; -#define EROFS_MAX_SHARED_XATTRS (128) -/* h_shared_count between 129 ... 255 are special # */ -#define EROFS_SHARED_XATTR_EXTENT (255) - /* * inline xattrs (n == i_xattr_icount): * erofs_xattr_ibody_header(1) + (n - 1) * 4 bytes @@ -268,6 +250,22 @@ struct erofs_inode_chunk_index { __le32 blkaddr; /* start block address of this inode chunk */ }; +/* dirent sorts in alphabet order, thus we can do binary search */ +struct erofs_dirent { + __le64 nid; /* node number */ + __le16 nameoff; /* start offset of file name */ + __u8 file_type; /* file type */ + __u8 reserved; /* reserved */ +} __packed; + +/* + * EROFS file types should match generic FT_* types and + * it seems no need to add BUILD_BUG_ONs since potential + * unmatchness will break other fses as well... + */ + +#define EROFS_NAME_LEN 255 + /* maximum supported size of a physical compression cluster */ #define Z_EROFS_PCLUSTER_MAX_SIZE (1024 * 1024) @@ -337,10 +335,8 @@ struct z_erofs_map_header { __u8 h_clusterbits; }; -#define Z_EROFS_VLE_LEGACY_HEADER_PADDING 8 - /* - * Fixed-sized output compression on-disk logical cluster type: + * On-disk logical cluster type: * 0 - literal (uncompressed) lcluster * 1,3 - compressed lcluster (for HEAD lclusters) * 2 - compressed lcluster (for NONHEAD lclusters) @@ -364,27 +360,27 @@ struct z_erofs_map_header { * di_u.delta[1] = distance to the next HEAD lcluster */ enum { - Z_EROFS_VLE_CLUSTER_TYPE_PLAIN = 0, - Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 = 1, - Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD = 2, - Z_EROFS_VLE_CLUSTER_TYPE_HEAD2 = 3, - Z_EROFS_VLE_CLUSTER_TYPE_MAX + Z_EROFS_LCLUSTER_TYPE_PLAIN = 0, + Z_EROFS_LCLUSTER_TYPE_HEAD1 = 1, + Z_EROFS_LCLUSTER_TYPE_NONHEAD = 2, + Z_EROFS_LCLUSTER_TYPE_HEAD2 = 3, + Z_EROFS_LCLUSTER_TYPE_MAX }; -#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS 2 -#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT 0 +#define Z_EROFS_LI_LCLUSTER_TYPE_BITS 2 +#define Z_EROFS_LI_LCLUSTER_TYPE_BIT 0 /* (noncompact only, HEAD) This pcluster refers to partial decompressed data */ -#define Z_EROFS_VLE_DI_PARTIAL_REF (1 << 15) +#define Z_EROFS_LI_PARTIAL_REF (1 << 15) /* * D0_CBLKCNT will be marked _only_ at the 1st non-head lcluster to store the * compressed block count of a compressed extent (in logical clusters, aka. * block count of a pcluster). */ -#define Z_EROFS_VLE_DI_D0_CBLKCNT (1 << 11) +#define Z_EROFS_LI_D0_CBLKCNT (1 << 11) -struct z_erofs_vle_decompressed_index { +struct z_erofs_lcluster_index { __le16 di_advise; /* where to decompress in the head lcluster */ __le16 di_clusterofs; @@ -401,25 +397,8 @@ struct z_erofs_vle_decompressed_index { } di_u; }; -#define Z_EROFS_VLE_LEGACY_INDEX_ALIGN(size) \ - (round_up(size, sizeof(struct z_erofs_vle_decompressed_index)) + \ - sizeof(struct z_erofs_map_header) + Z_EROFS_VLE_LEGACY_HEADER_PADDING) - -/* dirent sorts in alphabet order, thus we can do binary search */ -struct erofs_dirent { - __le64 nid; /* node number */ - __le16 nameoff; /* start offset of file name */ - __u8 file_type; /* file type */ - __u8 reserved; /* reserved */ -} __packed; - -/* - * EROFS file types should match generic FT_* types and - * it seems no need to add BUILD_BUG_ONs since potential - * unmatchness will break other fses as well... - */ - -#define EROFS_NAME_LEN 255 +#define Z_EROFS_FULL_INDEX_ALIGN(end) \ + (ALIGN(end, 8) + sizeof(struct z_erofs_map_header) + 8) /* check the EROFS on-disk layout strictly at compile time */ static inline void erofs_check_ondisk_layout_definitions(void) @@ -436,15 +415,15 @@ static inline void erofs_check_ondisk_layout_definitions(void) BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_info) != 4); BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) != 8); BUILD_BUG_ON(sizeof(struct z_erofs_map_header) != 8); - BUILD_BUG_ON(sizeof(struct z_erofs_vle_decompressed_index) != 8); + BUILD_BUG_ON(sizeof(struct z_erofs_lcluster_index) != 8); BUILD_BUG_ON(sizeof(struct erofs_dirent) != 12); /* keep in sync between 2 index structures for better extendibility */ BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) != - sizeof(struct z_erofs_vle_decompressed_index)); + sizeof(struct z_erofs_lcluster_index)); BUILD_BUG_ON(sizeof(struct erofs_deviceslot) != 128); - BUILD_BUG_ON(BIT(Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) < - Z_EROFS_VLE_CLUSTER_TYPE_MAX - 1); + BUILD_BUG_ON(BIT(Z_EROFS_LI_LCLUSTER_TYPE_BITS) < + Z_EROFS_LCLUSTER_TYPE_MAX - 1); /* exclude old compiler versions like gcc 7.5.0 */ BUILD_BUG_ON(__builtin_constant_p(fmh) ? fmh != cpu_to_le64(1ULL << 63) : 0); diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 183e7a4b8259..046eaaf16dad 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -14,7 +14,7 @@ int z_erofs_fill_inode(struct inode *inode) if (!erofs_sb_has_big_pcluster(sbi) && !erofs_sb_has_ztailpacking(sbi) && !erofs_sb_has_fragments(sbi) && - vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) { + vi->datalayout == EROFS_INODE_COMPRESSED_FULL) { vi->z_advise = 0; vi->z_algorithmtype[0] = 0; vi->z_algorithmtype[1] = 0; @@ -45,11 +45,10 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); - const erofs_off_t pos = - Z_EROFS_VLE_LEGACY_INDEX_ALIGN(erofs_iloc(inode) + - vi->inode_isize + vi->xattr_isize) + - lcn * sizeof(struct z_erofs_vle_decompressed_index); - struct z_erofs_vle_decompressed_index *di; + const erofs_off_t pos = Z_EROFS_FULL_INDEX_ALIGN(erofs_iloc(inode) + + vi->inode_isize + vi->xattr_isize) + + lcn * sizeof(struct z_erofs_lcluster_index); + struct z_erofs_lcluster_index *di; unsigned int advise, type; m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb, @@ -57,33 +56,33 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, if (IS_ERR(m->kaddr)) return PTR_ERR(m->kaddr); - m->nextpackoff = pos + sizeof(struct z_erofs_vle_decompressed_index); + m->nextpackoff = pos + sizeof(struct z_erofs_lcluster_index); m->lcn = lcn; di = m->kaddr + erofs_blkoff(inode->i_sb, pos); advise = le16_to_cpu(di->di_advise); - type = (advise >> Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT) & - ((1 << Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) - 1); + type = (advise >> Z_EROFS_LI_LCLUSTER_TYPE_BIT) & + ((1 << Z_EROFS_LI_LCLUSTER_TYPE_BITS) - 1); switch (type) { - case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + case Z_EROFS_LCLUSTER_TYPE_NONHEAD: m->clusterofs = 1 << vi->z_logical_clusterbits; m->delta[0] = le16_to_cpu(di->di_u.delta[0]); - if (m->delta[0] & Z_EROFS_VLE_DI_D0_CBLKCNT) { + if (m->delta[0] & Z_EROFS_LI_D0_CBLKCNT) { if (!(vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | Z_EROFS_ADVISE_BIG_PCLUSTER_2))) { DBG_BUGON(1); return -EFSCORRUPTED; } m->compressedblks = m->delta[0] & - ~Z_EROFS_VLE_DI_D0_CBLKCNT; + ~Z_EROFS_LI_D0_CBLKCNT; m->delta[0] = 1; } m->delta[1] = le16_to_cpu(di->di_u.delta[1]); break; - case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: - if (advise & Z_EROFS_VLE_DI_PARTIAL_REF) + case Z_EROFS_LCLUSTER_TYPE_PLAIN: + case Z_EROFS_LCLUSTER_TYPE_HEAD1: + case Z_EROFS_LCLUSTER_TYPE_HEAD2: + if (advise & Z_EROFS_LI_PARTIAL_REF) m->partialref = true; m->clusterofs = le16_to_cpu(di->di_clusterofs); if (m->clusterofs >= 1 << vi->z_logical_clusterbits) { @@ -125,13 +124,13 @@ static int get_compacted_la_distance(unsigned int lclusterbits, lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * i, &type); - if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) + if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD) return d1; ++d1; } while (++i < vcnt); - /* vcnt - 1 (Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) item */ - if (!(lo & Z_EROFS_VLE_DI_D0_CBLKCNT)) + /* vcnt - 1 (Z_EROFS_LCLUSTER_TYPE_NONHEAD) item */ + if (!(lo & Z_EROFS_LI_D0_CBLKCNT)) d1 += lo - 1; return d1; } @@ -169,19 +168,19 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * i, &type); m->type = type; - if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) { + if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { m->clusterofs = 1 << lclusterbits; /* figure out lookahead_distance: delta[1] if needed */ if (lookahead) m->delta[1] = get_compacted_la_distance(lclusterbits, encodebits, vcnt, in, i); - if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) { + if (lo & Z_EROFS_LI_D0_CBLKCNT) { if (!big_pcluster) { DBG_BUGON(1); return -EFSCORRUPTED; } - m->compressedblks = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; + m->compressedblks = lo & ~Z_EROFS_LI_D0_CBLKCNT; m->delta[0] = 1; return 0; } else if (i + 1 != (int)vcnt) { @@ -195,9 +194,9 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, */ lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * (i - 1), &type); - if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) + if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD) lo = 0; - else if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) + else if (lo & Z_EROFS_LI_D0_CBLKCNT) lo = 1; m->delta[0] = lo + 1; return 0; @@ -211,7 +210,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, --i; lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * i, &type); - if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) + if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) i -= lo; if (i >= 0) @@ -223,10 +222,10 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, --i; lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * i, &type); - if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) { - if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) { + if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { + if (lo & Z_EROFS_LI_D0_CBLKCNT) { --i; - nblk += lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; + nblk += lo & ~Z_EROFS_LI_D0_CBLKCNT; continue; } /* bigpcluster shouldn't have plain d0 == 1 */ @@ -301,10 +300,10 @@ static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m, { const unsigned int datamode = EROFS_I(m->inode)->datalayout; - if (datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY) + if (datamode == EROFS_INODE_COMPRESSED_FULL) return legacy_load_cluster_from_disk(m, lcn); - if (datamode == EROFS_INODE_FLAT_COMPRESSION) + if (datamode == EROFS_INODE_COMPRESSED_COMPACT) return compacted_load_cluster_from_disk(m, lcn, lookahead); return -EINVAL; @@ -326,7 +325,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, return err; switch (m->type) { - case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + case Z_EROFS_LCLUSTER_TYPE_NONHEAD: if (!m->delta[0]) { erofs_err(m->inode->i_sb, "invalid lookback distance 0 @ nid %llu", @@ -336,9 +335,9 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, } lookback_distance = m->delta[0]; continue; - case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: + case Z_EROFS_LCLUSTER_TYPE_PLAIN: + case Z_EROFS_LCLUSTER_TYPE_HEAD1: + case Z_EROFS_LCLUSTER_TYPE_HEAD2: m->headtype = m->type; m->map->m_la = (lcn << lclusterbits) | m->clusterofs; return 0; @@ -367,15 +366,15 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, unsigned long lcn; int err; - DBG_BUGON(m->type != Z_EROFS_VLE_CLUSTER_TYPE_PLAIN && - m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 && - m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD2); + DBG_BUGON(m->type != Z_EROFS_LCLUSTER_TYPE_PLAIN && + m->type != Z_EROFS_LCLUSTER_TYPE_HEAD1 && + m->type != Z_EROFS_LCLUSTER_TYPE_HEAD2); DBG_BUGON(m->type != m->headtype); - if (m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN || - ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1) && + if (m->headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN || + ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD1) && !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) || - ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) && + ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) && !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2))) { map->m_plen = 1ULL << lclusterbits; return 0; @@ -397,19 +396,19 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, * BUG_ON in the debugging mode only for developers to notice that. */ DBG_BUGON(lcn == initial_lcn && - m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD); + m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD); switch (m->type) { - case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: + case Z_EROFS_LCLUSTER_TYPE_PLAIN: + case Z_EROFS_LCLUSTER_TYPE_HEAD1: + case Z_EROFS_LCLUSTER_TYPE_HEAD2: /* * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type * rather than CBLKCNT, it's a 1 lcluster-sized pcluster. */ m->compressedblks = 1 << (lclusterbits - sb->s_blocksize_bits); break; - case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + case Z_EROFS_LCLUSTER_TYPE_NONHEAD: if (m->delta[0] != 1) goto err_bonus_cblkcnt; if (m->compressedblks) @@ -453,12 +452,12 @@ static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m) if (err) return err; - if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) { + if (m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { DBG_BUGON(!m->delta[1] && m->clusterofs != 1 << lclusterbits); - } else if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN || - m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 || - m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) { + } else if (m->type == Z_EROFS_LCLUSTER_TYPE_PLAIN || + m->type == Z_EROFS_LCLUSTER_TYPE_HEAD1 || + m->type == Z_EROFS_LCLUSTER_TYPE_HEAD2) { /* go on until the next HEAD lcluster */ if (lcn != headlcn) break; @@ -477,8 +476,7 @@ static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m) } static int z_erofs_do_map_blocks(struct inode *inode, - struct erofs_map_blocks *map, - int flags) + struct erofs_map_blocks *map, int flags) { struct erofs_inode *const vi = EROFS_I(inode); bool ztailpacking = vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER; @@ -508,9 +506,9 @@ static int z_erofs_do_map_blocks(struct inode *inode, end = (m.lcn + 1ULL) << lclusterbits; switch (m.type) { - case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: + case Z_EROFS_LCLUSTER_TYPE_PLAIN: + case Z_EROFS_LCLUSTER_TYPE_HEAD1: + case Z_EROFS_LCLUSTER_TYPE_HEAD2: if (endoff >= m.clusterofs) { m.headtype = m.type; map->m_la = (m.lcn << lclusterbits) | m.clusterofs; @@ -535,7 +533,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, map->m_flags |= EROFS_MAP_FULL_MAPPED; m.delta[0] = 1; fallthrough; - case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + case Z_EROFS_LCLUSTER_TYPE_NONHEAD: /* get the corresponding first chunk */ err = z_erofs_extent_lookback(&m, m.delta[0]); if (err) @@ -556,7 +554,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, vi->z_tailextent_headlcn = m.lcn; /* for non-compact indexes, fragmentoff is 64 bits */ if (fragment && - vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) + vi->datalayout == EROFS_INODE_COMPRESSED_FULL) vi->z_fragmentoff |= (u64)m.pblk << 32; } if (ztailpacking && m.lcn == vi->z_tailextent_headlcn) { @@ -572,7 +570,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, goto unmap_out; } - if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN) { + if (m.headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN) { if (map->m_llen > map->m_plen) { DBG_BUGON(1); err = -EFSCORRUPTED; @@ -582,7 +580,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, Z_EROFS_COMPRESSION_INTERLACED : Z_EROFS_COMPRESSION_SHIFTED; } else { - afmt = m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2 ? + afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ? vi->z_algorithmtype[1] : vi->z_algorithmtype[0]; if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) { erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu", @@ -676,7 +674,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) err = -EFSCORRUPTED; goto out_put_metabuf; } - if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION && + if (vi->datalayout == EROFS_INODE_COMPRESSED_COMPACT && !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu", -- 2.43.5

10 months

2
3
0 0

[PATCH 5.10] net: defer final 'struct net' free in netns dismantle

by Vasiliy Kovalev

From: Eric Dumazet <edumazet(a)google.com> commit 0f6ede9fbc747e2553612271bce108f7517e7a45 upstream. Ilya reported a slab-use-after-free in dst_destroy [1] Issue is in xfrm6_net_init() and xfrm4_net_init() : They copy xfrm[46]_dst_ops_template into net->xfrm.xfrm[46]_dst_ops. But net structure might be freed before all the dst callbacks are called. So when dst_destroy() calls later : if (dst->ops->destroy) dst->ops->destroy(dst); dst->ops points to the old net->xfrm.xfrm[46]_dst_ops, which has been freed. See a relevant issue fixed in : ac888d58869b ("net: do not delay dst_entries_add() in dst_release()") A fix is to queue the 'struct net' to be freed after one another cleanup_net() round (and existing rcu_barrier()) [1] BUG: KASAN: slab-use-after-free in dst_destroy (net/core/dst.c:112) Read of size 8 at addr ffff8882137ccab0 by task swapper/37/0 Dec 03 05:46:18 kernel: CPU: 37 UID: 0 PID: 0 Comm: swapper/37 Kdump: loaded Not tainted 6.12.0 #67 Hardware name: Red Hat KVM/RHEL, BIOS 1.16.1-1.el9 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:124) print_address_description.constprop.0 (mm/kasan/report.c:378) ? dst_destroy (net/core/dst.c:112) print_report (mm/kasan/report.c:489) ? dst_destroy (net/core/dst.c:112) ? kasan_addr_to_slab (mm/kasan/common.c:37) kasan_report (mm/kasan/report.c:603) ? dst_destroy (net/core/dst.c:112) ? rcu_do_batch (kernel/rcu/tree.c:2567) dst_destroy (net/core/dst.c:112) rcu_do_batch (kernel/rcu/tree.c:2567) ? __pfx_rcu_do_batch (kernel/rcu/tree.c:2491) ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4339 kernel/locking/lockdep.c:4406) rcu_core (kernel/rcu/tree.c:2825) handle_softirqs (kernel/softirq.c:554) __irq_exit_rcu (kernel/softirq.c:589 kernel/softirq.c:428 kernel/softirq.c:637) irq_exit_rcu (kernel/softirq.c:651) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1049 arch/x86/kernel/apic/apic.c:1049) </IRQ> <TASK> asm_sysvec_apic_timer_interrupt (./arch/x86/include/asm/idtentry.h:702) RIP: 0010:default_idle (./arch/x86/include/asm/irqflags.h:37 ./arch/x86/include/asm/irqflags.h:92 arch/x86/kernel/process.c:743) Code: 00 4d 29 c8 4c 01 c7 4c 29 c2 e9 6e ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 90 0f 00 2d c7 c9 27 00 fb f4 <fa> c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 90 RSP: 0018:ffff888100d2fe00 EFLAGS: 00000246 RAX: 00000000001870ed RBX: 1ffff110201a5fc2 RCX: ffffffffb61a3e46 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffffb3d4d123 RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed11c7e1835d R10: ffff888e3f0c1aeb R11: 0000000000000000 R12: 0000000000000000 R13: ffff888100d20000 R14: dffffc0000000000 R15: 0000000000000000 ? ct_kernel_exit.constprop.0 (kernel/context_tracking.c:148) ? cpuidle_idle_call (kernel/sched/idle.c:186) default_idle_call (./include/linux/cpuidle.h:143 kernel/sched/idle.c:118) cpuidle_idle_call (kernel/sched/idle.c:186) ? __pfx_cpuidle_idle_call (kernel/sched/idle.c:168) ? lock_release (kernel/locking/lockdep.c:467 kernel/locking/lockdep.c:5848) ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4347 kernel/locking/lockdep.c:4406) ? tsc_verify_tsc_adjust (arch/x86/kernel/tsc_sync.c:59) do_idle (kernel/sched/idle.c:326) cpu_startup_entry (kernel/sched/idle.c:423 (discriminator 1)) start_secondary (arch/x86/kernel/smpboot.c:202 arch/x86/kernel/smpboot.c:282) ? __pfx_start_secondary (arch/x86/kernel/smpboot.c:232) ? soft_restart_cpu (arch/x86/kernel/head_64.S:452) common_startup_64 (arch/x86/kernel/head_64.S:414) </TASK> Dec 03 05:46:18 kernel: Allocated by task 12184: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (./arch/x86/include/asm/current.h:49 mm/kasan/common.c:60 mm/kasan/common.c:69) __kasan_slab_alloc (mm/kasan/common.c:319 mm/kasan/common.c:345) kmem_cache_alloc_noprof (mm/slub.c:4085 mm/slub.c:4134 mm/slub.c:4141) copy_net_ns (net/core/net_namespace.c:421 net/core/net_namespace.c:480) create_new_namespaces (kernel/nsproxy.c:110) unshare_nsproxy_namespaces (kernel/nsproxy.c:228 (discriminator 4)) ksys_unshare (kernel/fork.c:3313) __x64_sys_unshare (kernel/fork.c:3382) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Dec 03 05:46:18 kernel: Freed by task 11: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (./arch/x86/include/asm/current.h:49 mm/kasan/common.c:60 mm/kasan/common.c:69) kasan_save_free_info (mm/kasan/generic.c:582) __kasan_slab_free (mm/kasan/common.c:271) kmem_cache_free (mm/slub.c:4579 mm/slub.c:4681) cleanup_net (net/core/net_namespace.c:456 net/core/net_namespace.c:446 net/core/net_namespace.c:647) process_one_work (kernel/workqueue.c:3229) worker_thread (kernel/workqueue.c:3304 kernel/workqueue.c:3391) kthread (kernel/kthread.c:389) ret_from_fork (arch/x86/kernel/process.c:147) ret_from_fork_asm (arch/x86/entry/entry_64.S:257) Dec 03 05:46:18 kernel: Last potentially related work creation: kasan_save_stack (mm/kasan/common.c:48) __kasan_record_aux_stack (mm/kasan/generic.c:541) insert_work (./include/linux/instrumented.h:68 ./include/asm-generic/bitops/instrumented-non-atomic.h:141 kernel/workqueue.c:788 kernel/workqueue.c:795 kernel/workqueue.c:2186) __queue_work (kernel/workqueue.c:2340) queue_work_on (kernel/workqueue.c:2391) xfrm_policy_insert (net/xfrm/xfrm_policy.c:1610) xfrm_add_policy (net/xfrm/xfrm_user.c:2116) xfrm_user_rcv_msg (net/xfrm/xfrm_user.c:3321) netlink_rcv_skb (net/netlink/af_netlink.c:2536) xfrm_netlink_rcv (net/xfrm/xfrm_user.c:3344) netlink_unicast (net/netlink/af_netlink.c:1316 net/netlink/af_netlink.c:1342) netlink_sendmsg (net/netlink/af_netlink.c:1886) sock_write_iter (net/socket.c:729 net/socket.c:744 net/socket.c:1165) vfs_write (fs/read_write.c:590 fs/read_write.c:683) ksys_write (fs/read_write.c:736) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Dec 03 05:46:18 kernel: Second to last potentially related work creation: kasan_save_stack (mm/kasan/common.c:48) __kasan_record_aux_stack (mm/kasan/generic.c:541) insert_work (./include/linux/instrumented.h:68 ./include/asm-generic/bitops/instrumented-non-atomic.h:141 kernel/workqueue.c:788 kernel/workqueue.c:795 kernel/workqueue.c:2186) __queue_work (kernel/workqueue.c:2340) queue_work_on (kernel/workqueue.c:2391) __xfrm_state_insert (./include/linux/workqueue.h:723 net/xfrm/xfrm_state.c:1150 net/xfrm/xfrm_state.c:1145 net/xfrm/xfrm_state.c:1513) xfrm_state_update (./include/linux/spinlock.h:396 net/xfrm/xfrm_state.c:1940) xfrm_add_sa (net/xfrm/xfrm_user.c:912) xfrm_user_rcv_msg (net/xfrm/xfrm_user.c:3321) netlink_rcv_skb (net/netlink/af_netlink.c:2536) xfrm_netlink_rcv (net/xfrm/xfrm_user.c:3344) netlink_unicast (net/netlink/af_netlink.c:1316 net/netlink/af_netlink.c:1342) netlink_sendmsg (net/netlink/af_netlink.c:1886) sock_write_iter (net/socket.c:729 net/socket.c:744 net/socket.c:1165) vfs_write (fs/read_write.c:590 fs/read_write.c:683) ksys_write (fs/read_write.c:736) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Fixes: a8a572a6b5f2 ("xfrm: dst_entries_init() per-net dst_ops") Reported-by: Ilya Maximets <i.maximets(a)ovn.org> Closes: https://lore.kernel.org/netdev/CANn89iKKYDVpB=MtmfH7nyv2p=rJWSLedO5k7wSZgtY… Signed-off-by: Eric Dumazet <edumazet(a)google.com> Acked-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Link: https://patch.msgid.link/20241204125455.3871859-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Vasiliy Kovalev <kovalev(a)altlinux.org> --- Backport to fix CVE-2024-56658 Link: https://www.cve.org/CVERecord/?id=CVE-2024-56658 --- include/net/net_namespace.h | 1 + net/core/net_namespace.c | 25 +++++++++++++++++++++++-- 2 files changed, 24 insertions(+), 2 deletions(-) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index eb0e7731f3b1c8..df95d553923937 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -80,6 +80,7 @@ struct net { * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ + struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ #ifdef CONFIG_KEYS diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6192a05ebcce2c..232c5afc1f777d 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -452,10 +452,29 @@ static struct net *net_alloc(void) goto out; } +static LLIST_HEAD(defer_free_list); + +static void net_complete_free(void) +{ + struct llist_node *kill_list; + struct net *net, *next; + + /* Get the list of namespaces to free from last round. */ + kill_list = llist_del_all(&defer_free_list); + + llist_for_each_entry_safe(net, next, kill_list, defer_free_list) + kmem_cache_free(net_cachep, net); + +} + static void net_free(struct net *net) { - kfree(rcu_access_pointer(net->gen)); - kmem_cache_free(net_cachep, net); + if (refcount_dec_and_test(&net->passive)) { + kfree(rcu_access_pointer(net->gen)); + + /* Wait for an extra rcu_barrier() before final free. */ + llist_add(&net->defer_free_list, &defer_free_list); + } } void net_drop_ns(void *p) @@ -628,6 +647,8 @@ static void cleanup_net(struct work_struct *work) */ rcu_barrier(); + net_complete_free(); + /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); -- 2.33.8

10 months

2
1
0 0

[PATCH 5.15.y] regmap: fix wrong backport

by Tzung-Bi Shih

f373a1898175 ("regmap: detach regmap from dev on regmap_exit") wrongly backported upstream commit 3061e170381a. It should patch regmap_exit() instead of regmap_reinit_cache(). Fixes: f373a1898175 ("regmap: detach regmap from dev on regmap_exit") Signed-off-by: Tzung-Bi Shih <tzungbi(a)kernel.org> --- drivers/base/regmap/regmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 00437ed9d5e0..6d94ad8bf1eb 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1508,7 +1508,6 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) { int ret; - regmap_detach_dev(map->dev, map); regcache_exit(map); regmap_debugfs_exit(map); @@ -1543,6 +1542,7 @@ void regmap_exit(struct regmap *map) { struct regmap_async *async; + regmap_detach_dev(map->dev, map); regcache_exit(map); regmap_debugfs_exit(map); regmap_range_exit(map); -- 2.48.0.rc2.279.g1de40edade-goog

10 months

2
1
0 0

[PATCH 5.10] xsk: fix OOB map writes when deleting elements

by Vasiliy Kovalev

From: Maciej Fijalkowski <maciej.fijalkowski(a)intel.com> commit 32cd3db7de97c0c7a018756ce66244342fd583f0 upstream. Jordy says: " In the xsk_map_delete_elem function an unsigned integer (map->max_entries) is compared with a user-controlled signed integer (k). Due to implicit type conversion, a large unsigned value for map->max_entries can bypass the intended bounds check: if (k >= map->max_entries) return -EINVAL; This allows k to hold a negative value (between -2147483648 and -2), which is then used as an array index in m->xsk_map[k], which results in an out-of-bounds access. spin_lock_bh(&m->lock); map_entry = &m->xsk_map[k]; // Out-of-bounds map_entry old_xs = unrcu_pointer(xchg(map_entry, NULL)); // Oob write if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); The xchg operation can then be used to cause an out-of-bounds write. Moreover, the invalid map_entry passed to xsk_map_sock_delete can lead to further memory corruption. " It indeed results in following splat: [76612.897343] BUG: unable to handle page fault for address: ffffc8fc2e461108 [76612.904330] #PF: supervisor write access in kernel mode [76612.909639] #PF: error_code(0x0002) - not-present page [76612.914855] PGD 0 P4D 0 [76612.917431] Oops: Oops: 0002 [#1] PREEMPT SMP [76612.921859] CPU: 11 UID: 0 PID: 10318 Comm: a.out Not tainted 6.12.0-rc1+ #470 [76612.929189] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [76612.939781] RIP: 0010:xsk_map_delete_elem+0x2d/0x60 [76612.944738] Code: 00 00 41 54 55 53 48 63 2e 3b 6f 24 73 38 4c 8d a7 f8 00 00 00 48 89 fb 4c 89 e7 e8 2d bf 05 00 48 8d b4 eb 00 01 00 00 31 ff <48> 87 3e 48 85 ff 74 05 e8 16 ff ff ff 4c 89 e7 e8 3e bc 05 00 31 [76612.963774] RSP: 0018:ffffc9002e407df8 EFLAGS: 00010246 [76612.969079] RAX: 0000000000000000 RBX: ffffc9002e461000 RCX: 0000000000000000 [76612.976323] RDX: 0000000000000001 RSI: ffffc8fc2e461108 RDI: 0000000000000000 [76612.983569] RBP: ffffffff80000001 R08: 0000000000000000 R09: 0000000000000007 [76612.990812] R10: ffffc9002e407e18 R11: ffff888108a38858 R12: ffffc9002e4610f8 [76612.998060] R13: ffff888108a38858 R14: 00007ffd1ae0ac78 R15: ffffc9002e4610c0 [76613.005303] FS: 00007f80b6f59740(0000) GS:ffff8897e0ec0000(0000) knlGS:0000000000000000 [76613.013517] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [76613.019349] CR2: ffffc8fc2e461108 CR3: 000000011e3ef001 CR4: 00000000007726f0 [76613.026595] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [76613.033841] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [76613.041086] PKRU: 55555554 [76613.043842] Call Trace: [76613.046331] <TASK> [76613.048468] ? __die+0x20/0x60 [76613.051581] ? page_fault_oops+0x15a/0x450 [76613.055747] ? search_extable+0x22/0x30 [76613.059649] ? search_bpf_extables+0x5f/0x80 [76613.063988] ? exc_page_fault+0xa9/0x140 [76613.067975] ? asm_exc_page_fault+0x22/0x30 [76613.072229] ? xsk_map_delete_elem+0x2d/0x60 [76613.076573] ? xsk_map_delete_elem+0x23/0x60 [76613.080914] __sys_bpf+0x19b7/0x23c0 [76613.084555] __x64_sys_bpf+0x1a/0x20 [76613.088194] do_syscall_64+0x37/0xb0 [76613.091832] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [76613.096962] RIP: 0033:0x7f80b6d1e88d [76613.100592] Code: 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 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 73 01 c3 48 8b 0d 73 b5 0f 00 f7 d8 64 89 01 48 [76613.119631] RSP: 002b:00007ffd1ae0ac68 EFLAGS: 00000206 ORIG_RAX: 0000000000000141 [76613.131330] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f80b6d1e88d [76613.142632] RDX: 0000000000000098 RSI: 00007ffd1ae0ad20 RDI: 0000000000000003 [76613.153967] RBP: 00007ffd1ae0adc0 R08: 0000000000000000 R09: 0000000000000000 [76613.166030] R10: 00007f80b6f77040 R11: 0000000000000206 R12: 00007ffd1ae0aed8 [76613.177130] R13: 000055ddf42ce1e9 R14: 000055ddf42d0d98 R15: 00007f80b6fab040 [76613.188129] </TASK> Fix this by simply changing key type from int to u32. Fixes: fbfc504a24f5 ("bpf: introduce new bpf AF_XDP map type BPF_MAP_TYPE_XSKMAP") CC: stable(a)vger.kernel.org Reported-by: Jordy Zomer <jordyzomer(a)google.com> Suggested-by: Jordy Zomer <jordyzomer(a)google.com> Reviewed-by: Toke Høiland-Jørgensen <toke(a)redhat.com> Acked-by: John Fastabend <john.fastabend(a)gmail.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski(a)intel.com> Link: https://lore.kernel.org/r/20241122121030.716788-2-maciej.fijalkowski@intel.… Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Vasiliy Kovalev <kovalev(a)altlinux.org> --- Backport to fix CVE-2024-56614 Link: https://www.cve.org/CVERecord/?id=CVE-2024-56614 --- net/xdp/xskmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 49da2b8ace8b7d..bb356e892128c8 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -223,7 +223,7 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) { struct xsk_map *m = container_of(map, struct xsk_map, map); struct xdp_sock *old_xs, **map_entry; - int k = *(u32 *)key; + u32 k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; -- 2.33.8

10 months

2
1
0 0

[PATCH 5.10/5.15] can: hi311x: hi3110_can_ist(): fix potential use-after-free

by Vasiliy Kovalev

From: Dario Binacchi <dario.binacchi(a)amarulasolutions.com> [ Upstream commit 9ad86d377ef4a19c75a9c639964879a5b25a433b ] The commit a22bd630cfff ("can: hi311x: do not report txerr and rxerr during bus-off") removed the reporting of rxerr and txerr even in case of correct operation (i. e. not bus-off). The error count information added to the CAN frame after netif_rx() is a potential use after free, since there is no guarantee that the skb is in the same state. It might be freed or reused. Fix the issue by postponing the netif_rx() call in case of txerr and rxerr reporting. Fixes: a22bd630cfff ("can: hi311x: do not report txerr and rxerr during bus-off") Signed-off-by: Dario Binacchi <dario.binacchi(a)amarulasolutions.com> Link: https://patch.msgid.link/20241122221650.633981-5-dario.binacchi@amarulasolu… Signed-off-by: Marc Kleine-Budde <mkl(a)pengutronix.de> [kovalev: changed the call order of netif_rx_ni() according to netif_rx() of the upstream patch] Signed-off-by: Vasiliy Kovalev <kovalev(a)altlinux.org> --- Backport to fix CVE-2024-56651 Link: https://www.cve.org/CVERecord/?id=CVE-2024-56651 --- drivers/net/can/spi/hi311x.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index 28273e84171a25..1cdc05475cda61 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -673,9 +673,9 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id) tx_state = txerr >= rxerr ? new_state : 0; rx_state = txerr <= rxerr ? new_state : 0; can_change_state(net, cf, tx_state, rx_state); - netif_rx_ni(skb); if (new_state == CAN_STATE_BUS_OFF) { + netif_rx_ni(skb); can_bus_off(net); if (priv->can.restart_ms == 0) { priv->force_quit = 1; @@ -685,6 +685,7 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id) } else { cf->data[6] = txerr; cf->data[7] = rxerr; + netif_rx_ni(skb); } } -- 2.33.8

10 months

2
1
0 0

[PATCH 5.10 1/1] tcp/dccp: Don't use timer_pending() in reqsk_queue_unlink().

by d.privalov

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> commit e8c526f2bdf1845bedaf6a478816a3d06fa78b8f upstream. Martin KaFai Lau reported use-after-free [0] in reqsk_timer_handler(). """ We are seeing a use-after-free from a bpf prog attached to trace_tcp_retransmit_synack. The program passes the req->sk to the bpf_sk_storage_get_tracing kernel helper which does check for null before using it. """ The commit 83fccfc3940c ("inet: fix potential deadlock in reqsk_queue_unlink()") added timer_pending() in reqsk_queue_unlink() not to call del_timer_sync() from reqsk_timer_handler(), but it introduced a small race window. Before the timer is called, expire_timers() calls detach_timer(timer, true) to clear timer->entry.pprev and marks it as not pending. If reqsk_queue_unlink() checks timer_pending() just after expire_timers() calls detach_timer(), TCP will miss del_timer_sync(); the reqsk timer will continue running and send multiple SYN+ACKs until it expires. The reported UAF could happen if req->sk is close()d earlier than the timer expiration, which is 63s by default. The scenario would be 1. inet_csk_complete_hashdance() calls inet_csk_reqsk_queue_drop(), but del_timer_sync() is missed 2. reqsk timer is executed and scheduled again 3. req->sk is accept()ed and reqsk_put() decrements rsk_refcnt, but reqsk timer still has another one, and inet_csk_accept() does not clear req->sk for non-TFO sockets 4. sk is close()d 5. reqsk timer is executed again, and BPF touches req->sk Let's not use timer_pending() by passing the caller context to __inet_csk_reqsk_queue_drop(). Note that reqsk timer is pinned, so the issue does not happen in most use cases. [1] [0] BUG: KFENCE: use-after-free read in bpf_sk_storage_get_tracing+0x2e/0x1b0 Use-after-free read at 0x00000000a891fb3a (in kfence-#1): bpf_sk_storage_get_tracing+0x2e/0x1b0 bpf_prog_5ea3e95db6da0438_tcp_retransmit_synack+0x1d20/0x1dda bpf_trace_run2+0x4c/0xc0 tcp_rtx_synack+0xf9/0x100 reqsk_timer_handler+0xda/0x3d0 run_timer_softirq+0x292/0x8a0 irq_exit_rcu+0xf5/0x320 sysvec_apic_timer_interrupt+0x6d/0x80 asm_sysvec_apic_timer_interrupt+0x16/0x20 intel_idle_irq+0x5a/0xa0 cpuidle_enter_state+0x94/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb kfence-#1: 0x00000000a72cc7b6-0x00000000d97616d9, size=2376, cache=TCPv6 allocated by task 0 on cpu 9 at 260507.901592s: sk_prot_alloc+0x35/0x140 sk_clone_lock+0x1f/0x3f0 inet_csk_clone_lock+0x15/0x160 tcp_create_openreq_child+0x1f/0x410 tcp_v6_syn_recv_sock+0x1da/0x700 tcp_check_req+0x1fb/0x510 tcp_v6_rcv+0x98b/0x1420 ipv6_list_rcv+0x2258/0x26e0 napi_complete_done+0x5b1/0x2990 mlx5e_napi_poll+0x2ae/0x8d0 net_rx_action+0x13e/0x590 irq_exit_rcu+0xf5/0x320 common_interrupt+0x80/0x90 asm_common_interrupt+0x22/0x40 cpuidle_enter_state+0xfb/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb freed by task 0 on cpu 9 at 260507.927527s: rcu_core_si+0x4ff/0xf10 irq_exit_rcu+0xf5/0x320 sysvec_apic_timer_interrupt+0x6d/0x80 asm_sysvec_apic_timer_interrupt+0x16/0x20 cpuidle_enter_state+0xfb/0x273 cpu_startup_entry+0x15e/0x260 start_secondary+0x8a/0x90 secondary_startup_64_no_verify+0xfa/0xfb Fixes: 83fccfc3940c ("inet: fix potential deadlock in reqsk_queue_unlink()") Reported-by: Martin KaFai Lau <martin.lau(a)kernel.org> Closes: https://lore.kernel.org/netdev/eb6684d0-ffd9-4bdc-9196-33f690c25824@linux.d… Link: https://lore.kernel.org/netdev/b55e2ca0-42f2-4b7c-b445-6ffd87ca74a0@linux.d… [1] Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Martin KaFai Lau <martin.lau(a)kernel.org> Link: https://patch.msgid.link/20241014223312.4254-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> [d.privalov: adapt calling __inet_csk_reqsk_queue_drop()] Signed-off-by: Dmitriy Privalov <d.privalov(a)omp.ru> --- Backport fix for CVE-2024-50154 Link: https://nvd.nist.gov/vuln/detail/CVE-2024-50154 --- net/ipv4/inet_connection_sock.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6ebe43b4d28f..332133aae3e1 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -722,21 +722,31 @@ static bool reqsk_queue_unlink(struct request_sock *req) found = __sk_nulls_del_node_init_rcu(req_to_sk(req)); spin_unlock(lock); } - if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer)) - reqsk_put(req); + return found; } -bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +static bool __inet_csk_reqsk_queue_drop(struct sock *sk, + struct request_sock *req, + bool from_timer) { bool unlinked = reqsk_queue_unlink(req); + if (!from_timer && del_timer_sync(&req->rsk_timer)) + reqsk_put(req); + if (unlinked) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } + return unlinked; } + +bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +{ + return __inet_csk_reqsk_queue_drop(sk, req, false); +} EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req) @@ -804,7 +814,8 @@ static void reqsk_timer_handler(struct timer_list *t) return; } drop: - inet_csk_reqsk_queue_drop_and_put(sk_listener, req);` + __inet_csk_reqsk_queue_drop(sk_listener, req, true); + reqsk_put(req); } static void reqsk_queue_hash_req(struct request_sock *req, -- 2.34.1

10 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror