September 2024 - Linux-stable-mirror

[PATCH] drbd: Add NULL check for net_conf to prevent dereference in state validation

by Mikhail Lobanov

If the net_conf pointer is NULL and the code attempts to access its fields without a check, it will lead to a null pointer dereference. Add a NULL check before dereferencing the pointer. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 44ed167da748 ("drbd: rcu_read_lock() and rcu_dereference() for tconn->net_conf") Cc: stable(a)vger.kernel.org Signed-off-by: Mikhail Lobanov <m.lobanov(a)rosalinux.ru> --- drivers/block/drbd/drbd_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 287a8d1d3f70..87cf5883078f 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -876,7 +876,7 @@ is_valid_state(struct drbd_device *device, union drbd_state ns) ns.disk == D_OUTDATED) rv = SS_CONNECTED_OUTDATES; - else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && + else if (nc && (ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && (nc->verify_alg[0] == 0)) rv = SS_NO_VERIFY_ALG; -- 2.43.0

1 month, 1 week

2
1
0 0

[PATCH net v2] net: drop bad gso csum_start and offset in virtio_net_hdr

by Willem de Bruijn

From: Willem de Bruijn <willemb(a)google.com> Tighten csum_start and csum_offset checks in virtio_net_hdr_to_skb for GSO packets. The function already checks that a checksum requested with VIRTIO_NET_HDR_F_NEEDS_CSUM is in skb linear. But for GSO packets this might not hold for segs after segmentation. Syzkaller demonstrated to reach this warning in skb_checksum_help offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (WARN_ON_ONCE(offset >= skb_headlen(skb))) By injecting a TSO packet: WARNING: CPU: 1 PID: 3539 at net/core/dev.c:3284 skb_checksum_help+0x3d0/0x5b0 ip_do_fragment+0x209/0x1b20 net/ipv4/ip_output.c:774 ip_finish_output_gso net/ipv4/ip_output.c:279 [inline] __ip_finish_output+0x2bd/0x4b0 net/ipv4/ip_output.c:301 iptunnel_xmit+0x50c/0x930 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x2296/0x2c70 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x759/0xa60 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4850 [inline] netdev_start_xmit include/linux/netdevice.h:4864 [inline] xmit_one net/core/dev.c:3595 [inline] dev_hard_start_xmit+0x261/0x8c0 net/core/dev.c:3611 __dev_queue_xmit+0x1b97/0x3c90 net/core/dev.c:4261 packet_snd net/packet/af_packet.c:3073 [inline] The geometry of the bad input packet at tcp_gso_segment: [ 52.003050][ T8403] skb len=12202 headroom=244 headlen=12093 tailroom=0 [ 52.003050][ T8403] mac=(168,24) mac_len=24 net=(192,52) trans=244 [ 52.003050][ T8403] shinfo(txflags=0 nr_frags=1 gso(size=1552 type=3 segs=0)) [ 52.003050][ T8403] csum(0x60000c7 start=199 offset=1536 ip_summed=3 complete_sw=0 valid=0 level=0) Mitigate with stricter input validation. csum_offset: for GSO packets, deduce the correct value from gso_type. This is already done for USO. Extend it to TSO. Let UFO be: udp[46]_ufo_fragment ignores these fields and always computes the checksum in software. csum_start: finding the real offset requires parsing to the transport header. Do not add a parser, use existing segmentation parsing. Thanks to SKB_GSO_DODGY, that also catches bad packets that are hw offloaded. Again test both TSO and USO. Do not test UFO for the above reason, and do not test UDP tunnel offload. GSO packet are almost always CHECKSUM_PARTIAL. USO packets may be CHECKSUM_NONE since commit 10154dbded6d6 ("udp: Allow GSO transmit from devices with no checksum offload"), but then still these fields are initialized correctly in udp4_hwcsum/udp6_hwcsum_outgoing. So no need to test for ip_summed == CHECKSUM_PARTIAL first. This revises an existing fix mentioned in the Fixes tag, which broke small packets with GSO offload, as detected by kselftests. Link: https://syzkaller.appspot.com/bug?extid=e1db31216c789f552871 Link: https://lore.kernel.org/netdev/20240723223109.2196886-1-kuba@kernel.org Fixes: e269d79c7d35 ("net: missing check virtio") Cc: stable(a)vger.kernel.org Signed-off-by: Willem de Bruijn <willemb(a)google.com> --- v1->v2 - skb_transport_header instead of skb->transport_header (edumazet@) - typo: migitate -> mitigate --- include/linux/virtio_net.h | 16 +++++----------- net/ipv4/tcp_offload.c | 3 +++ net/ipv4/udp_offload.c | 4 ++++ 3 files changed, 12 insertions(+), 11 deletions(-) diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index d1d7825318c32..6c395a2600e8d 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -56,7 +56,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; - u64 ret, remainder, gso_size; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -99,16 +98,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); - if (hdr->gso_size) { - gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); - ret = div64_u64_rem(skb->len, gso_size, &remainder); - if (!(ret && (hdr->gso_size > needed) && - ((remainder > needed) || (remainder == 0)))) { - return -EINVAL; - } - skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG; - } - if (!pskb_may_pull(skb, needed)) return -EINVAL; @@ -182,6 +171,11 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; + case SKB_GSO_TCPV4: + case SKB_GSO_TCPV6: + if (skb->csum_offset != offsetof(struct tcphdr, check)) + return -EINVAL; + break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 4b791e74529e1..e4ad3311e1489 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (thlen < sizeof(*th)) goto out; + if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb))) + goto out; + if (!pskb_may_pull(skb, thlen)) goto out; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index aa2e0a28ca613..bc8a9da750fed 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -278,6 +278,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(skb_checksum_start(gso_skb) != + skb_transport_header(gso_skb))) + return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), -- 2.46.0.rc1.232.g9752f9e123-goog

1 month, 1 week

9
18
0 0

[merged mm-stable] mm-codetag-add-pgalloc_tag_copy.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/codetag: add pgalloc_tag_copy() has been removed from the -mm tree. Its filename was mm-codetag-add-pgalloc_tag_copy.patch This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yu Zhao <yuzhao(a)google.com> Subject: mm/codetag: add pgalloc_tag_copy() Date: Thu, 5 Sep 2024 22:21:08 -0600 Add pgalloc_tag_copy() to transfer the codetag from the old folio to the new one during migration. This makes original allocation sites persist cross migration rather than lump into the get_new_folio callbacks passed into migrate_pages(), e.g., compaction_alloc(): # echo 1 >/proc/sys/vm/compact_memory # grep compaction_alloc /proc/allocinfo Before this patch: 132968448 32463 mm/compaction.c:1880 func:compaction_alloc After this patch: 0 0 mm/compaction.c:1880 func:compaction_alloc Link: https://lkml.kernel.org/r/20240906042108.1150526-3-yuzhao@google.com Fixes: dcfe378c81f7 ("lib: introduce support for page allocation tagging") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Acked-by: Suren Baghdasaryan <surenb(a)google.com> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/alloc_tag.h | 24 ++++++++++-------------- include/linux/mm.h | 27 +++++++++++++++++++++++++++ mm/migrate.c | 1 + 3 files changed, 38 insertions(+), 14 deletions(-) --- a/include/linux/alloc_tag.h~mm-codetag-add-pgalloc_tag_copy +++ a/include/linux/alloc_tag.h @@ -137,7 +137,16 @@ static inline void alloc_tag_sub_check(u /* Caller should verify both ref and tag to be valid */ static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return; + ref->ct = &tag->ct; +} + +static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + __alloc_tag_ref_set(ref, tag); /* * We need in increment the call counter every time we have a new * allocation or when we split a large allocation into smaller ones. @@ -147,22 +156,9 @@ static inline void __alloc_tag_ref_set(u this_cpu_inc(tag->counters->calls); } -static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) -{ - alloc_tag_add_check(ref, tag); - if (!ref || !tag) - return; - - __alloc_tag_ref_set(ref, tag); -} - static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) { - alloc_tag_add_check(ref, tag); - if (!ref || !tag) - return; - - __alloc_tag_ref_set(ref, tag); + alloc_tag_ref_set(ref, tag); this_cpu_add(tag->counters->bytes, bytes); } --- a/include/linux/mm.h~mm-codetag-add-pgalloc_tag_copy +++ a/include/linux/mm.h @@ -4108,10 +4108,37 @@ static inline void pgalloc_tag_split(str } } } + +static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) +{ + struct alloc_tag *tag; + union codetag_ref *ref; + + tag = pgalloc_tag_get(&old->page); + if (!tag) + return; + + ref = get_page_tag_ref(&new->page); + if (!ref) + return; + + /* Clear the old ref to the original allocation tag. */ + clear_page_tag_ref(&old->page); + /* Decrement the counters of the tag on get_new_folio. */ + alloc_tag_sub(ref, folio_nr_pages(new)); + + __alloc_tag_ref_set(ref, tag); + + put_page_tag_ref(ref); +} #else /* !CONFIG_MEM_ALLOC_PROFILING */ static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) { } + +static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) +{ +} #endif /* CONFIG_MEM_ALLOC_PROFILING */ #endif /* _LINUX_MM_H */ --- a/mm/migrate.c~mm-codetag-add-pgalloc_tag_copy +++ a/mm/migrate.c @@ -743,6 +743,7 @@ void folio_migrate_flags(struct folio *n folio_set_readahead(newfolio); folio_copy_owner(newfolio, folio); + pgalloc_tag_copy(newfolio, folio); mem_cgroup_migrate(folio, newfolio); } _ Patches currently in -mm which might be from yuzhao(a)google.com are

1 month, 1 week

1
0
0 0

[merged mm-stable] mm-codetag-fix-pgalloc_tag_split.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/codetag: fix pgalloc_tag_split() has been removed from the -mm tree. Its filename was mm-codetag-fix-pgalloc_tag_split.patch This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yu Zhao <yuzhao(a)google.com> Subject: mm/codetag: fix pgalloc_tag_split() Date: Thu, 5 Sep 2024 22:21:07 -0600 The current assumption is that a large folio can only be split into order-0 folios. That is not the case for hugeTLB demotion, nor for THP split: see commit c010d47f107f ("mm: thp: split huge page to any lower order pages"). When a large folio is split into ones of a lower non-zero order, only the new head pages should be tagged. Tagging tail pages can cause imbalanced "calls" counters, since only head pages are untagged by pgalloc_tag_sub() and the "calls" counts on tail pages are leaked, e.g., # echo 2048kB >/sys/kernel/mm/hugepages/hugepages-1048576kB/demote_size # echo 700 >/sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages # time echo 700 >/sys/kernel/mm/hugepages/hugepages-1048576kB/demote # echo 0 >/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages # grep alloc_gigantic_folio /proc/allocinfo Before this patch: 0 549427200 mm/hugetlb.c:1549 func:alloc_gigantic_folio real 0m2.057s user 0m0.000s sys 0m2.051s After this patch: 0 0 mm/hugetlb.c:1549 func:alloc_gigantic_folio real 0m1.711s user 0m0.000s sys 0m1.704s Not tagging tail pages also improves the splitting time, e.g., by about 15% when demoting 1GB hugeTLB folios to 2MB ones, as shown above. Link: https://lkml.kernel.org/r/20240906042108.1150526-2-yuzhao@google.com Fixes: be25d1d4e822 ("mm: create new codetag references during page splitting") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Acked-by: Suren Baghdasaryan <surenb(a)google.com> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mm.h | 30 ++++++++++++++++++++++++++++++ include/linux/pgalloc_tag.h | 31 ------------------------------- mm/huge_memory.c | 2 +- mm/hugetlb.c | 2 +- mm/page_alloc.c | 4 ++-- 5 files changed, 34 insertions(+), 35 deletions(-) --- a/include/linux/mm.h~mm-codetag-fix-pgalloc_tag_split +++ a/include/linux/mm.h @@ -4084,4 +4084,34 @@ void vma_pgtable_walk_end(struct vm_area int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); +#ifdef CONFIG_MEM_ALLOC_PROFILING +static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) +{ + int i; + struct alloc_tag *tag; + unsigned int nr_pages = 1 << new_order; + + if (!mem_alloc_profiling_enabled()) + return; + + tag = pgalloc_tag_get(&folio->page); + if (!tag) + return; + + for (i = nr_pages; i < (1 << old_order); i += nr_pages) { + union codetag_ref *ref = get_page_tag_ref(folio_page(folio, i)); + + if (ref) { + /* Set new reference to point to the original tag */ + alloc_tag_ref_set(ref, tag); + put_page_tag_ref(ref); + } + } +} +#else /* !CONFIG_MEM_ALLOC_PROFILING */ +static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) +{ +} +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + #endif /* _LINUX_MM_H */ --- a/include/linux/pgalloc_tag.h~mm-codetag-fix-pgalloc_tag_split +++ a/include/linux/pgalloc_tag.h @@ -80,36 +80,6 @@ static inline void pgalloc_tag_sub(struc } } -static inline void pgalloc_tag_split(struct page *page, unsigned int nr) -{ - int i; - struct page_ext *first_page_ext; - struct page_ext *page_ext; - union codetag_ref *ref; - struct alloc_tag *tag; - - if (!mem_alloc_profiling_enabled()) - return; - - first_page_ext = page_ext = page_ext_get(page); - if (unlikely(!page_ext)) - return; - - ref = codetag_ref_from_page_ext(page_ext); - if (!ref->ct) - goto out; - - tag = ct_to_alloc_tag(ref->ct); - page_ext = page_ext_next(page_ext); - for (i = 1; i < nr; i++) { - /* Set new reference to point to the original tag */ - alloc_tag_ref_set(codetag_ref_from_page_ext(page_ext), tag); - page_ext = page_ext_next(page_ext); - } -out: - page_ext_put(first_page_ext); -} - static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { struct alloc_tag *tag = NULL; @@ -142,7 +112,6 @@ static inline void clear_page_tag_ref(st static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} -static inline void pgalloc_tag_split(struct page *page, unsigned int nr) {} static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} --- a/mm/huge_memory.c~mm-codetag-fix-pgalloc_tag_split +++ a/mm/huge_memory.c @@ -3226,7 +3226,7 @@ static void __split_huge_page(struct pag /* Caller disabled irqs, so they are still disabled here */ split_page_owner(head, order, new_order); - pgalloc_tag_split(head, 1 << order); + pgalloc_tag_split(folio, order, new_order); /* See comment in __split_huge_page_tail() */ if (folio_test_anon(folio)) { --- a/mm/hugetlb.c~mm-codetag-fix-pgalloc_tag_split +++ a/mm/hugetlb.c @@ -3778,7 +3778,7 @@ static long demote_free_hugetlb_folios(s list_del(&folio->lru); split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst)); - pgalloc_tag_split(&folio->page, 1 << huge_page_order(src)); + pgalloc_tag_split(folio, huge_page_order(src), huge_page_order(dst)); for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { struct page *page = folio_page(folio, i); --- a/mm/page_alloc.c~mm-codetag-fix-pgalloc_tag_split +++ a/mm/page_alloc.c @@ -2776,7 +2776,7 @@ void split_page(struct page *page, unsig for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); split_page_owner(page, order, 0); - pgalloc_tag_split(page, 1 << order); + pgalloc_tag_split(page_folio(page), order, 0); split_page_memcg(page, order, 0); } EXPORT_SYMBOL_GPL(split_page); @@ -4974,7 +4974,7 @@ static void *make_alloc_exact(unsigned l struct page *last = page + nr; split_page_owner(page, order, 0); - pgalloc_tag_split(page, 1 << order); + pgalloc_tag_split(page_folio(page), order, 0); split_page_memcg(page, order, 0); while (page < --last) set_page_refcounted(last); _ Patches currently in -mm which might be from yuzhao(a)google.com are

1 month, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-damon-vaddr-protect-vma-traversal-in-__damon_va_thre_regions-with-rcu-read-lock.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/damon/vaddr: protect vma traversal in __damon_va_thre_regions() with rcu read lock has been removed from the -mm tree. Its filename was mm-damon-vaddr-protect-vma-traversal-in-__damon_va_thre_regions-with-rcu-read-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: "Liam R. Howlett" <Liam.Howlett(a)oracle.com> Subject: mm/damon/vaddr: protect vma traversal in __damon_va_thre_regions() with rcu read lock Date: Wed, 4 Sep 2024 17:12:04 -0700 Traversing VMAs of a given maple tree should be protected by rcu read lock. However, __damon_va_three_regions() is not doing the protection. Hold the lock. Link: https://lkml.kernel.org/r/20240905001204.1481-1-sj@kernel.org Fixes: d0cf3dd47f0d ("damon: convert __damon_va_three_regions to use the VMA iterator") Signed-off-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Signed-off-by: SeongJae Park <sj(a)kernel.org> Reported-by: Guenter Roeck <linux(a)roeck-us.net> Closes: https://lore.kernel.org/b83651a0-5b24-4206-b860-cb54ffdf209b@roeck-us.net Tested-by: Guenter Roeck <linux(a)roeck-us.net> Cc: David Hildenbrand <david(a)redhat.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/vaddr.c | 2 ++ 1 file changed, 2 insertions(+) --- a/mm/damon/vaddr.c~mm-damon-vaddr-protect-vma-traversal-in-__damon_va_thre_regions-with-rcu-read-lock +++ a/mm/damon/vaddr.c @@ -126,6 +126,7 @@ static int __damon_va_three_regions(stru * If this is too slow, it can be optimised to examine the maple * tree gaps. */ + rcu_read_lock(); for_each_vma(vmi, vma) { unsigned long gap; @@ -146,6 +147,7 @@ static int __damon_va_three_regions(stru next: prev = vma; } + rcu_read_unlock(); if (!sz_range(&second_gap) || !sz_range(&first_gap)) return -EINVAL; _ Patches currently in -mm which might be from Liam.Howlett(a)oracle.com are maple_tree-mark-three-functions-as-__maybe_unused.patch

1 month, 1 week

1
0
0 0

[merged mm-hotfixes-stable] ocfs2-cancel-dqi_sync_work-before-freeing-oinfo.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: ocfs2: cancel dqi_sync_work before freeing oinfo has been removed from the -mm tree. Its filename was ocfs2-cancel-dqi_sync_work-before-freeing-oinfo.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: Joseph Qi <joseph.qi(a)linux.alibaba.com> Subject: ocfs2: cancel dqi_sync_work before freeing oinfo Date: Wed, 4 Sep 2024 15:10:03 +0800 ocfs2_global_read_info() will initialize and schedule dqi_sync_work at the end, if error occurs after successfully reading global quota, it will trigger the following warning with CONFIG_DEBUG_OBJECTS_* enabled: ODEBUG: free active (active state 0) object: 00000000d8b0ce28 object type: timer_list hint: qsync_work_fn+0x0/0x16c This reports that there is an active delayed work when freeing oinfo in error handling, so cancel dqi_sync_work first. BTW, return status instead of -1 when .read_file_info fails. Link: https://syzkaller.appspot.com/bug?extid=f7af59df5d6b25f0febd Link: https://lkml.kernel.org/r/20240904071004.2067695-1-joseph.qi@linux.alibaba.… Fixes: 171bf93ce11f ("ocfs2: Periodic quota syncing") Signed-off-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Reviewed-by: Heming Zhao <heming.zhao(a)suse.com> Reported-by: syzbot+f7af59df5d6b25f0febd(a)syzkaller.appspotmail.com Tested-by: syzbot+f7af59df5d6b25f0febd(a)syzkaller.appspotmail.com Cc: Mark Fasheh <mark(a)fasheh.com> Cc: Joel Becker <jlbec(a)evilplan.org> Cc: Junxiao Bi <junxiao.bi(a)oracle.com> Cc: Changwei Ge <gechangwei(a)live.cn> Cc: Gang He <ghe(a)suse.com> Cc: Jun Piao <piaojun(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/ocfs2/quota_local.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) --- a/fs/ocfs2/quota_local.c~ocfs2-cancel-dqi_sync_work-before-freeing-oinfo +++ a/fs/ocfs2/quota_local.c @@ -692,7 +692,7 @@ static int ocfs2_local_read_info(struct int status; struct buffer_head *bh = NULL; struct ocfs2_quota_recovery *rec; - int locked = 0; + int locked = 0, global_read = 0; info->dqi_max_spc_limit = 0x7fffffffffffffffLL; info->dqi_max_ino_limit = 0x7fffffffffffffffLL; @@ -700,6 +700,7 @@ static int ocfs2_local_read_info(struct if (!oinfo) { mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota" " info."); + status = -ENOMEM; goto out_err; } info->dqi_priv = oinfo; @@ -712,6 +713,7 @@ static int ocfs2_local_read_info(struct status = ocfs2_global_read_info(sb, type); if (status < 0) goto out_err; + global_read = 1; status = ocfs2_inode_lock(lqinode, &oinfo->dqi_lqi_bh, 1); if (status < 0) { @@ -782,10 +784,12 @@ out_err: if (locked) ocfs2_inode_unlock(lqinode, 1); ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk); + if (global_read) + cancel_delayed_work_sync(&oinfo->dqi_sync_work); kfree(oinfo); } brelse(bh); - return -1; + return status; } /* Write local info to quota file */ _ Patches currently in -mm which might be from joseph.qi(a)linux.alibaba.com are ocfs2-cleanup-return-value-and-mlog-in-ocfs2_global_read_info.patch

1 month, 1 week

1
0
0 0

[merged mm-hotfixes-stable] ocfs2-fix-possible-null-ptr-deref-in-ocfs2_set_buffer_uptodate.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: ocfs2: fix possible null-ptr-deref in ocfs2_set_buffer_uptodate has been removed from the -mm tree. Its filename was ocfs2-fix-possible-null-ptr-deref-in-ocfs2_set_buffer_uptodate.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: Lizhi Xu <lizhi.xu(a)windriver.com> Subject: ocfs2: fix possible null-ptr-deref in ocfs2_set_buffer_uptodate Date: Mon, 2 Sep 2024 10:36:36 +0800 When doing cleanup, if flags without OCFS2_BH_READAHEAD, it may trigger NULL pointer dereference in the following ocfs2_set_buffer_uptodate() if bh is NULL. Link: https://lkml.kernel.org/r/20240902023636.1843422-3-joseph.qi@linux.alibaba.… Fixes: cf76c78595ca ("ocfs2: don't put and assigning null to bh allocated outside") Signed-off-by: Lizhi Xu <lizhi.xu(a)windriver.com> Signed-off-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Reviewed-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Reported-by: Heming Zhao <heming.zhao(a)suse.com> Suggested-by: Heming Zhao <heming.zhao(a)suse.com> Cc: <stable(a)vger.kernel.org> [4.20+] Cc: Changwei Ge <gechangwei(a)live.cn> Cc: Gang He <ghe(a)suse.com> Cc: Joel Becker <jlbec(a)evilplan.org> Cc: Jun Piao <piaojun(a)huawei.com> Cc: Junxiao Bi <junxiao.bi(a)oracle.com> Cc: Mark Fasheh <mark(a)fasheh.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/ocfs2/buffer_head_io.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) --- a/fs/ocfs2/buffer_head_io.c~ocfs2-fix-possible-null-ptr-deref-in-ocfs2_set_buffer_uptodate +++ a/fs/ocfs2/buffer_head_io.c @@ -388,7 +388,8 @@ read_failure: /* Always set the buffer in the cache, even if it was * a forced read, or read-ahead which hasn't yet * completed. */ - ocfs2_set_buffer_uptodate(ci, bh); + if (bh) + ocfs2_set_buffer_uptodate(ci, bh); } ocfs2_metadata_cache_io_unlock(ci); _ Patches currently in -mm which might be from lizhi.xu(a)windriver.com are

1 month, 1 week

1
0
0 0

[merged mm-hotfixes-stable] ocfs2-remove-unreasonable-unlock-in-ocfs2_read_blocks.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: ocfs2: remove unreasonable unlock in ocfs2_read_blocks has been removed from the -mm tree. Its filename was ocfs2-remove-unreasonable-unlock-in-ocfs2_read_blocks.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: Lizhi Xu <lizhi.xu(a)windriver.com> Subject: ocfs2: remove unreasonable unlock in ocfs2_read_blocks Date: Mon, 2 Sep 2024 10:36:35 +0800 Patch series "Misc fixes for ocfs2_read_blocks", v5. This series contains 2 fixes for ocfs2_read_blocks(). The first patch fix the issue reported by syzbot, which detects bad unlock balance in ocfs2_read_blocks(). The second patch fixes an issue reported by Heming Zhao when reviewing above fix. This patch (of 2): There was a lock release before exiting, so remove the unreasonable unlock. Link: https://lkml.kernel.org/r/20240902023636.1843422-1-joseph.qi@linux.alibaba.… Link: https://lkml.kernel.org/r/20240902023636.1843422-2-joseph.qi@linux.alibaba.… Fixes: cf76c78595ca ("ocfs2: don't put and assigning null to bh allocated outside") Signed-off-by: Lizhi Xu <lizhi.xu(a)windriver.com> Signed-off-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Reviewed-by: Heming Zhao <heming.zhao(a)suse.com> Reviewed-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Reported-by: syzbot+ab134185af9ef88dfed5(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ab134185af9ef88dfed5 Tested-by: syzbot+ab134185af9ef88dfed5(a)syzkaller.appspotmail.com Cc: Mark Fasheh <mark(a)fasheh.com> Cc: Joel Becker <jlbec(a)evilplan.org> Cc: Junxiao Bi <junxiao.bi(a)oracle.com> Cc: Changwei Ge <gechangwei(a)live.cn> Cc: Gang He <ghe(a)suse.com> Cc: Jun Piao <piaojun(a)huawei.com> Cc: <stable(a)vger.kernel.org> [4.20+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/ocfs2/buffer_head_io.c | 1 - 1 file changed, 1 deletion(-) --- a/fs/ocfs2/buffer_head_io.c~ocfs2-remove-unreasonable-unlock-in-ocfs2_read_blocks +++ a/fs/ocfs2/buffer_head_io.c @@ -235,7 +235,6 @@ int ocfs2_read_blocks(struct ocfs2_cachi if (bhs[i] == NULL) { bhs[i] = sb_getblk(sb, block++); if (bhs[i] == NULL) { - ocfs2_metadata_cache_io_unlock(ci); status = -ENOMEM; mlog_errno(status); /* Don't forget to put previous bh! */ _ Patches currently in -mm which might be from lizhi.xu(a)windriver.com are

1 month, 1 week

1
0
0 0

[merged mm-hotfixes-stable] ocfs2-fix-null-ptr-deref-when-journal-load-failed.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: ocfs2: fix null-ptr-deref when journal load failed. has been removed from the -mm tree. Its filename was ocfs2-fix-null-ptr-deref-when-journal-load-failed.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: Julian Sun <sunjunchao2870(a)gmail.com> Subject: ocfs2: fix null-ptr-deref when journal load failed. Date: Mon, 2 Sep 2024 11:08:44 +0800 During the mounting process, if journal_reset() fails because of too short journal, then lead to jbd2_journal_load() fails with NULL j_sb_buffer. Subsequently, ocfs2_journal_shutdown() calls jbd2_journal_flush()->jbd2_cleanup_journal_tail()-> __jbd2_update_log_tail()->jbd2_journal_update_sb_log_tail() ->lock_buffer(journal->j_sb_buffer), resulting in a null-pointer dereference error. To resolve this issue, we should check the JBD2_LOADED flag to ensure the journal was properly loaded. Additionally, use journal instead of osb->journal directly to simplify the code. Link: https://syzkaller.appspot.com/bug?extid=05b9b39d8bdfe1a0861f Link: https://lkml.kernel.org/r/20240902030844.422725-1-sunjunchao2870@gmail.com Fixes: f6f50e28f0cb ("jbd2: Fail to load a journal if it is too short") Signed-off-by: Julian Sun <sunjunchao2870(a)gmail.com> Reported-by: syzbot+05b9b39d8bdfe1a0861f(a)syzkaller.appspotmail.com Suggested-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Reviewed-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Cc: Mark Fasheh <mark(a)fasheh.com> Cc: Joel Becker <jlbec(a)evilplan.org> Cc: Junxiao Bi <junxiao.bi(a)oracle.com> Cc: Changwei Ge <gechangwei(a)live.cn> Cc: Gang He <ghe(a)suse.com> Cc: Jun Piao <piaojun(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/ocfs2/journal.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) --- a/fs/ocfs2/journal.c~ocfs2-fix-null-ptr-deref-when-journal-load-failed +++ a/fs/ocfs2/journal.c @@ -1055,7 +1055,7 @@ void ocfs2_journal_shutdown(struct ocfs2 if (!igrab(inode)) BUG(); - num_running_trans = atomic_read(&(osb->journal->j_num_trans)); + num_running_trans = atomic_read(&(journal->j_num_trans)); trace_ocfs2_journal_shutdown(num_running_trans); /* Do a commit_cache here. It will flush our journal, *and* @@ -1074,9 +1074,10 @@ void ocfs2_journal_shutdown(struct ocfs2 osb->commit_task = NULL; } - BUG_ON(atomic_read(&(osb->journal->j_num_trans)) != 0); + BUG_ON(atomic_read(&(journal->j_num_trans)) != 0); - if (ocfs2_mount_local(osb)) { + if (ocfs2_mount_local(osb) && + (journal->j_journal->j_flags & JBD2_LOADED)) { jbd2_journal_lock_updates(journal->j_journal); status = jbd2_journal_flush(journal->j_journal, 0); jbd2_journal_unlock_updates(journal->j_journal); _ Patches currently in -mm which might be from sunjunchao2870(a)gmail.com are

1 month, 1 week

1
0
0 0

[PATCH net-next v3 5/6] idpf: fix netdev Tx queue stop/wake

by Tony Nguyen

From: Michal Kubiak <michal.kubiak(a)intel.com> netif_txq_maybe_stop() returns -1, 0, or 1, while idpf_tx_maybe_stop_common() says it returns 0 or -EBUSY. As a result, there sometimes are Tx queue timeout warnings despite that the queue is empty or there is at least enough space to restart it. Make idpf_tx_maybe_stop_common() inline and returning true or false, handling the return of netif_txq_maybe_stop() properly. Use a correct goto in idpf_tx_maybe_stop_splitq() to avoid stopping the queue or incrementing the stops counter twice. Fixes: 6818c4d5b3c2 ("idpf: add splitq start_xmit") Fixes: a5ab9ee0df0b ("idpf: add singleq start_xmit and napi poll") Cc: stable(a)vger.kernel.org # 6.7+ Signed-off-by: Michal Kubiak <michal.kubiak(a)intel.com> Reviewed-by: Przemek Kitszel <przemyslaw.kitszel(a)intel.com> Signed-off-by: Alexander Lobakin <aleksander.lobakin(a)intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com> --- .../ethernet/intel/idpf/idpf_singleq_txrx.c | 4 +++ drivers/net/ethernet/intel/idpf/idpf_txrx.c | 35 +++++-------------- drivers/net/ethernet/intel/idpf/idpf_txrx.h | 9 ++++- 3 files changed, 21 insertions(+), 27 deletions(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index 947d3ff9677c..5ba360abbe66 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -375,6 +375,10 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb, IDPF_TX_DESCS_FOR_CTX)) { idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false); + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_inc(&tx_q->q_stats.q_busy); + u64_stats_update_end(&tx_q->stats_sync); + return NETDEV_TX_BUSY; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 9844d01eaedb..5d74f324bcd4 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -2132,29 +2132,6 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc, desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag); } -/** - * idpf_tx_maybe_stop_common - 1st level check for common Tx stop conditions - * @tx_q: the queue to be checked - * @size: number of descriptors we want to assure is available - * - * Returns 0 if stop is not needed - */ -int idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q, unsigned int size) -{ - struct netdev_queue *nq; - - if (likely(IDPF_DESC_UNUSED(tx_q) >= size)) - return 0; - - u64_stats_update_begin(&tx_q->stats_sync); - u64_stats_inc(&tx_q->q_stats.q_busy); - u64_stats_update_end(&tx_q->stats_sync); - - nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx); - - return netif_txq_maybe_stop(nq, IDPF_DESC_UNUSED(tx_q), size, size); -} - /** * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions * @tx_q: the queue to be checked @@ -2166,7 +2143,7 @@ static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q, unsigned int descs_needed) { if (idpf_tx_maybe_stop_common(tx_q, descs_needed)) - goto splitq_stop; + goto out; /* If there are too many outstanding completions expected on the * completion queue, stop the TX queue to give the device some time to @@ -2185,10 +2162,12 @@ static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q, return 0; splitq_stop: + netif_stop_subqueue(tx_q->netdev, tx_q->idx); + +out: u64_stats_update_begin(&tx_q->stats_sync); u64_stats_inc(&tx_q->q_stats.q_busy); u64_stats_update_end(&tx_q->stats_sync); - netif_stop_subqueue(tx_q->netdev, tx_q->idx); return -EBUSY; } @@ -2211,7 +2190,11 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val, nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx); tx_q->next_to_use = val; - idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED); + if (idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED)) { + u64_stats_update_begin(&tx_q->stats_sync); + u64_stats_inc(&tx_q->q_stats.q_busy); + u64_stats_update_end(&tx_q->stats_sync); + } /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 3a2a92e79e60..33305de06975 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -1018,7 +1018,6 @@ void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb, struct idpf_tx_buf *first, u16 ring_idx); unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq, struct sk_buff *skb); -int idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q, unsigned int size); void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue); netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb, struct idpf_tx_queue *tx_q); @@ -1027,4 +1026,12 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rxq, u16 cleaned_count); int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off); +static inline bool idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q, + u32 needed) +{ + return !netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx, + IDPF_DESC_UNUSED(tx_q), + needed, needed); +} + #endif /* !_IDPF_TXRX_H_ */ -- 2.42.0

1 month, 1 week

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2024