December 2025 - Linux-stable-mirror

[merged mm-hotfixes-stable] kernel-kexec-fix-ima-when-allocation-happens-in-cma-area.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: kernel/kexec: fix IMA when allocation happens in CMA area has been removed from the -mm tree. Its filename was kernel-kexec-fix-ima-when-allocation-happens-in-cma-area.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: Pingfan Liu <piliu(a)redhat.com> Subject: kernel/kexec: fix IMA when allocation happens in CMA area Date: Tue, 16 Dec 2025 09:48:52 +0800 *** Bug description *** When I tested kexec with the latest kernel, I ran into the following warning: [ 40.712410] ------------[ cut here ]------------ [ 40.712576] WARNING: CPU: 2 PID: 1562 at kernel/kexec_core.c:1001 kimage_map_segment+0x144/0x198 [...] [ 40.816047] Call trace: [ 40.818498] kimage_map_segment+0x144/0x198 (P) [ 40.823221] ima_kexec_post_load+0x58/0xc0 [ 40.827246] __do_sys_kexec_file_load+0x29c/0x368 [...] [ 40.855423] ---[ end trace 0000000000000000 ]--- *** How to reproduce *** This bug is only triggered when the kexec target address is allocated in the CMA area. If no CMA area is reserved in the kernel, use the "cma=" option in the kernel command line to reserve one. *** Root cause *** The commit 07d24902977e ("kexec: enable CMA based contiguous allocation") allocates the kexec target address directly on the CMA area to avoid copying during the jump. In this case, there is no IND_SOURCE for the kexec segment. But the current implementation of kimage_map_segment() assumes that IND_SOURCE pages exist and map them into a contiguous virtual address by vmap(). *** Solution *** If IMA segment is allocated in the CMA area, use its page_address() directly. Link: https://lkml.kernel.org/r/20251216014852.8737-2-piliu@redhat.com Fixes: 07d24902977e ("kexec: enable CMA based contiguous allocation") Signed-off-by: Pingfan Liu <piliu(a)redhat.com> Acked-by: Baoquan He <bhe(a)redhat.com> Cc: Alexander Graf <graf(a)amazon.com> Cc: Steven Chen <chenste(a)linux.microsoft.com> Cc: Mimi Zohar <zohar(a)linux.ibm.com> Cc: Roberto Sassu <roberto.sassu(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- kernel/kexec_core.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) --- a/kernel/kexec_core.c~kernel-kexec-fix-ima-when-allocation-happens-in-cma-area +++ a/kernel/kexec_core.c @@ -960,13 +960,17 @@ void *kimage_map_segment(struct kimage * kimage_entry_t *ptr, entry; struct page **src_pages; unsigned int npages; + struct page *cma; void *vaddr = NULL; int i; + cma = image->segment_cma[idx]; + if (cma) + return page_address(cma); + addr = image->segment[idx].mem; size = image->segment[idx].memsz; eaddr = addr + size; - /* * Collect the source pages and map them in a contiguous VA range. */ @@ -1007,7 +1011,8 @@ void *kimage_map_segment(struct kimage * void kimage_unmap_segment(void *segment_buffer) { - vunmap(segment_buffer); + if (is_vmalloc_addr(segment_buffer)) + vunmap(segment_buffer); } struct kexec_load_limit { _ Patches currently in -mm which might be from piliu(a)redhat.com are

21 hours, 50 minutes

1
0
0 0

[merged mm-hotfixes-stable] kernel-kexec-change-the-prototype-of-kimage_map_segment.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: kernel/kexec: change the prototype of kimage_map_segment() has been removed from the -mm tree. Its filename was kernel-kexec-change-the-prototype-of-kimage_map_segment.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: Pingfan Liu <piliu(a)redhat.com> Subject: kernel/kexec: change the prototype of kimage_map_segment() Date: Tue, 16 Dec 2025 09:48:51 +0800 The kexec segment index will be required to extract the corresponding information for that segment in kimage_map_segment(). Additionally, kexec_segment already holds the kexec relocation destination address and size. Therefore, the prototype of kimage_map_segment() can be changed. Link: https://lkml.kernel.org/r/20251216014852.8737-1-piliu@redhat.com Fixes: 07d24902977e ("kexec: enable CMA based contiguous allocation") Signed-off-by: Pingfan Liu <piliu(a)redhat.com> Acked-by: Baoquan He <bhe(a)redhat.com> Cc: Mimi Zohar <zohar(a)linux.ibm.com> Cc: Roberto Sassu <roberto.sassu(a)huawei.com> Cc: Alexander Graf <graf(a)amazon.com> Cc: Steven Chen <chenste(a)linux.microsoft.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/kexec.h | 4 ++-- kernel/kexec_core.c | 9 ++++++--- security/integrity/ima/ima_kexec.c | 4 +--- 3 files changed, 9 insertions(+), 8 deletions(-) --- a/include/linux/kexec.h~kernel-kexec-change-the-prototype-of-kimage_map_segment +++ a/include/linux/kexec.h @@ -530,7 +530,7 @@ extern bool kexec_file_dbg_print; #define kexec_dprintk(fmt, arg...) \ do { if (kexec_file_dbg_print) pr_info(fmt, ##arg); } while (0) -extern void *kimage_map_segment(struct kimage *image, unsigned long addr, unsigned long size); +extern void *kimage_map_segment(struct kimage *image, int idx); extern void kimage_unmap_segment(void *buffer); #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; @@ -540,7 +540,7 @@ static inline void __crash_kexec(struct static inline void crash_kexec(struct pt_regs *regs) { } static inline int kexec_should_crash(struct task_struct *p) { return 0; } static inline int kexec_crash_loaded(void) { return 0; } -static inline void *kimage_map_segment(struct kimage *image, unsigned long addr, unsigned long size) +static inline void *kimage_map_segment(struct kimage *image, int idx) { return NULL; } static inline void kimage_unmap_segment(void *buffer) { } #define kexec_in_progress false --- a/kernel/kexec_core.c~kernel-kexec-change-the-prototype-of-kimage_map_segment +++ a/kernel/kexec_core.c @@ -953,17 +953,20 @@ int kimage_load_segment(struct kimage *i return result; } -void *kimage_map_segment(struct kimage *image, - unsigned long addr, unsigned long size) +void *kimage_map_segment(struct kimage *image, int idx) { + unsigned long addr, size, eaddr; unsigned long src_page_addr, dest_page_addr = 0; - unsigned long eaddr = addr + size; kimage_entry_t *ptr, entry; struct page **src_pages; unsigned int npages; void *vaddr = NULL; int i; + addr = image->segment[idx].mem; + size = image->segment[idx].memsz; + eaddr = addr + size; + /* * Collect the source pages and map them in a contiguous VA range. */ --- a/security/integrity/ima/ima_kexec.c~kernel-kexec-change-the-prototype-of-kimage_map_segment +++ a/security/integrity/ima/ima_kexec.c @@ -250,9 +250,7 @@ void ima_kexec_post_load(struct kimage * if (!image->ima_buffer_addr) return; - ima_kexec_buffer = kimage_map_segment(image, - image->ima_buffer_addr, - image->ima_buffer_size); + ima_kexec_buffer = kimage_map_segment(image, image->ima_segment_index); if (!ima_kexec_buffer) { pr_err("Could not map measurements buffer.\n"); return; _ Patches currently in -mm which might be from piliu(a)redhat.com are

21 hours, 50 minutes

1
0
0 0

[merged mm-hotfixes-stable] mm-page_alloc-change-all-pageblocks-migrate-type-on-coalescing.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/page_alloc: change all pageblocks migrate type on coalescing has been removed from the -mm tree. Its filename was mm-page_alloc-change-all-pageblocks-migrate-type-on-coalescing.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: Alexander Gordeev <agordeev(a)linux.ibm.com> Subject: mm/page_alloc: change all pageblocks migrate type on coalescing Date: Fri, 12 Dec 2025 16:14:57 +0100 When a page is freed it coalesces with a buddy into a higher order page while possible. When the buddy page migrate type differs, it is expected to be updated to match the one of the page being freed. However, only the first pageblock of the buddy page is updated, while the rest of the pageblocks are left unchanged. That causes warnings in later expand() and other code paths (like below), since an inconsistency between migration type of the list containing the page and the page-owned pageblocks migration types is introduced. [ 308.986589] ------------[ cut here ]------------ [ 308.987227] page type is 0, passed migratetype is 1 (nr=256) [ 308.987275] WARNING: CPU: 1 PID: 5224 at mm/page_alloc.c:812 expand+0x23c/0x270 [ 308.987293] Modules linked in: algif_hash(E) af_alg(E) nft_fib_inet(E) nft_fib_ipv4(E) nft_fib_ipv6(E) nft_fib(E) nft_reject_inet(E) nf_reject_ipv4(E) nf_reject_ipv6(E) nft_reject(E) nft_ct(E) nft_chain_nat(E) nf_nat(E) nf_conntrack(E) nf_defrag_ipv6(E) nf_defrag_ipv4(E) nf_tables(E) s390_trng(E) vfio_ccw(E) mdev(E) vfio_iommu_type1(E) vfio(E) sch_fq_codel(E) drm(E) i2c_core(E) drm_panel_orientation_quirks(E) loop(E) nfnetlink(E) vsock_loopback(E) vmw_vsock_virtio_transport_common(E) vsock(E) ctcm(E) fsm(E) diag288_wdt(E) watchdog(E) zfcp(E) scsi_transport_fc(E) ghash_s390(E) prng(E) aes_s390(E) des_generic(E) des_s390(E) libdes(E) sha3_512_s390(E) sha3_256_s390(E) sha_common(E) paes_s390(E) crypto_engine(E) pkey_cca(E) pkey_ep11(E) zcrypt(E) rng_core(E) pkey_pckmo(E) pkey(E) autofs4(E) [ 308.987439] Unloaded tainted modules: hmac_s390(E):2 [ 308.987650] CPU: 1 UID: 0 PID: 5224 Comm: mempig_verify Kdump: loaded Tainted: G E 6.18.0-gcc-bpf-debug #431 PREEMPT [ 308.987657] Tainted: [E]=UNSIGNED_MODULE [ 308.987661] Hardware name: IBM 3906 M04 704 (z/VM 7.3.0) [ 308.987666] Krnl PSW : 0404f00180000000 00000349976fa600 (expand+0x240/0x270) [ 308.987676] R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:3 PM:0 RI:0 EA:3 [ 308.987682] Krnl GPRS: 0000034980000004 0000000000000005 0000000000000030 000003499a0e6d88 [ 308.987688] 0000000000000005 0000034980000005 000002be803ac000 0000023efe6c8300 [ 308.987692] 0000000000000008 0000034998d57290 000002be00000100 0000023e00000008 [ 308.987696] 0000000000000000 0000000000000000 00000349976fa5fc 000002c99b1eb6f0 [ 308.987708] Krnl Code: 00000349976fa5f0: c020008a02f2 larl %r2,000003499883abd4 00000349976fa5f6: c0e5ffe3f4b5 brasl %r14,0000034997378f60 #00000349976fa5fc: af000000 mc 0,0 >00000349976fa600: a7f4ff4c brc 15,00000349976fa498 00000349976fa604: b9040026 lgr %r2,%r6 00000349976fa608: c0300088317f larl %r3,0000034998800906 00000349976fa60e: c0e5fffdb6e1 brasl %r14,00000349976b13d0 00000349976fa614: af000000 mc 0,0 [ 308.987734] Call Trace: [ 308.987738] [<00000349976fa600>] expand+0x240/0x270 [ 308.987744] ([<00000349976fa5fc>] expand+0x23c/0x270) [ 308.987749] [<00000349976ff95e>] rmqueue_bulk+0x71e/0x940 [ 308.987754] [<00000349976ffd7e>] __rmqueue_pcplist+0x1fe/0x2a0 [ 308.987759] [<0000034997700966>] rmqueue.isra.0+0xb46/0xf40 [ 308.987763] [<0000034997703ec8>] get_page_from_freelist+0x198/0x8d0 [ 308.987768] [<0000034997706fa8>] __alloc_frozen_pages_noprof+0x198/0x400 [ 308.987774] [<00000349977536f8>] alloc_pages_mpol+0xb8/0x220 [ 308.987781] [<0000034997753bf6>] folio_alloc_mpol_noprof+0x26/0xc0 [ 308.987786] [<0000034997753e4c>] vma_alloc_folio_noprof+0x6c/0xa0 [ 308.987791] [<0000034997775b22>] vma_alloc_anon_folio_pmd+0x42/0x240 [ 308.987799] [<000003499777bfea>] __do_huge_pmd_anonymous_page+0x3a/0x210 [ 308.987804] [<00000349976cb08e>] __handle_mm_fault+0x4de/0x500 [ 308.987809] [<00000349976cb14c>] handle_mm_fault+0x9c/0x3a0 [ 308.987813] [<000003499734d70e>] do_exception+0x1de/0x540 [ 308.987822] [<0000034998387390>] __do_pgm_check+0x130/0x220 [ 308.987830] [<000003499839a934>] pgm_check_handler+0x114/0x160 [ 308.987838] 3 locks held by mempig_verify/5224: [ 308.987842] #0: 0000023ea44c1e08 (vm_lock){++++}-{0:0}, at: lock_vma_under_rcu+0xb2/0x2a0 [ 308.987859] #1: 0000023ee4d41b18 (&pcp->lock){+.+.}-{2:2}, at: rmqueue.isra.0+0xad6/0xf40 [ 308.987871] #2: 0000023efe6c8998 (&zone->lock){..-.}-{2:2}, at: rmqueue_bulk+0x5a/0x940 [ 308.987886] Last Breaking-Event-Address: [ 308.987890] [<0000034997379096>] __warn_printk+0x136/0x140 [ 308.987897] irq event stamp: 52330356 [ 308.987901] hardirqs last enabled at (52330355): [<000003499838742e>] __do_pgm_check+0x1ce/0x220 [ 308.987907] hardirqs last disabled at (52330356): [<000003499839932e>] _raw_spin_lock_irqsave+0x9e/0xe0 [ 308.987913] softirqs last enabled at (52329882): [<0000034997383786>] handle_softirqs+0x2c6/0x530 [ 308.987922] softirqs last disabled at (52329859): [<0000034997382f86>] __irq_exit_rcu+0x126/0x140 [ 308.987929] ---[ end trace 0000000000000000 ]--- [ 308.987936] ------------[ cut here ]------------ [ 308.987940] page type is 0, passed migratetype is 1 (nr=256) [ 308.987951] WARNING: CPU: 1 PID: 5224 at mm/page_alloc.c:860 __del_page_from_free_list+0x1be/0x1e0 [ 308.987960] Modules linked in: algif_hash(E) af_alg(E) nft_fib_inet(E) nft_fib_ipv4(E) nft_fib_ipv6(E) nft_fib(E) nft_reject_inet(E) nf_reject_ipv4(E) nf_reject_ipv6(E) nft_reject(E) nft_ct(E) nft_chain_nat(E) nf_nat(E) nf_conntrack(E) nf_defrag_ipv6(E) nf_defrag_ipv4(E) nf_tables(E) s390_trng(E) vfio_ccw(E) mdev(E) vfio_iommu_type1(E) vfio(E) sch_fq_codel(E) drm(E) i2c_core(E) drm_panel_orientation_quirks(E) loop(E) nfnetlink(E) vsock_loopback(E) vmw_vsock_virtio_transport_common(E) vsock(E) ctcm(E) fsm(E) diag288_wdt(E) watchdog(E) zfcp(E) scsi_transport_fc(E) ghash_s390(E) prng(E) aes_s390(E) des_generic(E) des_s390(E) libdes(E) sha3_512_s390(E) sha3_256_s390(E) sha_common(E) paes_s390(E) crypto_engine(E) pkey_cca(E) pkey_ep11(E) zcrypt(E) rng_core(E) pkey_pckmo(E) pkey(E) autofs4(E) [ 308.988070] Unloaded tainted modules: hmac_s390(E):2 [ 308.988087] CPU: 1 UID: 0 PID: 5224 Comm: mempig_verify Kdump: loaded Tainted: G W E 6.18.0-gcc-bpf-debug #431 PREEMPT [ 308.988095] Tainted: [W]=WARN, [E]=UNSIGNED_MODULE [ 308.988100] Hardware name: IBM 3906 M04 704 (z/VM 7.3.0) [ 308.988105] Krnl PSW : 0404f00180000000 00000349976f9e32 (__del_page_from_free_list+0x1c2/0x1e0) [ 308.988118] R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:3 PM:0 RI:0 EA:3 [ 308.988127] Krnl GPRS: 0000034980000004 0000000000000005 0000000000000030 000003499a0e6d88 [ 308.988133] 0000000000000005 0000034980000005 0000034998d57290 0000023efe6c8300 [ 308.988139] 0000000000000001 0000000000000008 000002be00000100 000002be803ac000 [ 308.988144] 0000000000000000 0000000000000001 00000349976f9e2e 000002c99b1eb728 [ 308.988153] Krnl Code: 00000349976f9e22: c020008a06d9 larl %r2,000003499883abd4 00000349976f9e28: c0e5ffe3f89c brasl %r14,0000034997378f60 #00000349976f9e2e: af000000 mc 0,0 >00000349976f9e32: a7f4ff4e brc 15,00000349976f9cce 00000349976f9e36: b904002b lgr %r2,%r11 00000349976f9e3a: c030008a06e7 larl %r3,000003499883ac08 00000349976f9e40: c0e5fffdbac8 brasl %r14,00000349976b13d0 00000349976f9e46: af000000 mc 0,0 [ 308.988184] Call Trace: [ 308.988188] [<00000349976f9e32>] __del_page_from_free_list+0x1c2/0x1e0 [ 308.988195] ([<00000349976f9e2e>] __del_page_from_free_list+0x1be/0x1e0) [ 308.988202] [<00000349976ff946>] rmqueue_bulk+0x706/0x940 [ 308.988208] [<00000349976ffd7e>] __rmqueue_pcplist+0x1fe/0x2a0 [ 308.988214] [<0000034997700966>] rmqueue.isra.0+0xb46/0xf40 [ 308.988221] [<0000034997703ec8>] get_page_from_freelist+0x198/0x8d0 [ 308.988227] [<0000034997706fa8>] __alloc_frozen_pages_noprof+0x198/0x400 [ 308.988233] [<00000349977536f8>] alloc_pages_mpol+0xb8/0x220 [ 308.988240] [<0000034997753bf6>] folio_alloc_mpol_noprof+0x26/0xc0 [ 308.988247] [<0000034997753e4c>] vma_alloc_folio_noprof+0x6c/0xa0 [ 308.988253] [<0000034997775b22>] vma_alloc_anon_folio_pmd+0x42/0x240 [ 308.988260] [<000003499777bfea>] __do_huge_pmd_anonymous_page+0x3a/0x210 [ 308.988267] [<00000349976cb08e>] __handle_mm_fault+0x4de/0x500 [ 308.988273] [<00000349976cb14c>] handle_mm_fault+0x9c/0x3a0 [ 308.988279] [<000003499734d70e>] do_exception+0x1de/0x540 [ 308.988286] [<0000034998387390>] __do_pgm_check+0x130/0x220 [ 308.988293] [<000003499839a934>] pgm_check_handler+0x114/0x160 [ 308.988300] 3 locks held by mempig_verify/5224: [ 308.988305] #0: 0000023ea44c1e08 (vm_lock){++++}-{0:0}, at: lock_vma_under_rcu+0xb2/0x2a0 [ 308.988322] #1: 0000023ee4d41b18 (&pcp->lock){+.+.}-{2:2}, at: rmqueue.isra.0+0xad6/0xf40 [ 308.988334] #2: 0000023efe6c8998 (&zone->lock){..-.}-{2:2}, at: rmqueue_bulk+0x5a/0x940 [ 308.988346] Last Breaking-Event-Address: [ 308.988350] [<0000034997379096>] __warn_printk+0x136/0x140 [ 308.988356] irq event stamp: 52330356 [ 308.988360] hardirqs last enabled at (52330355): [<000003499838742e>] __do_pgm_check+0x1ce/0x220 [ 308.988366] hardirqs last disabled at (52330356): [<000003499839932e>] _raw_spin_lock_irqsave+0x9e/0xe0 [ 308.988373] softirqs last enabled at (52329882): [<0000034997383786>] handle_softirqs+0x2c6/0x530 [ 308.988380] softirqs last disabled at (52329859): [<0000034997382f86>] __irq_exit_rcu+0x126/0x140 [ 308.988388] ---[ end trace 0000000000000000 ]--- Link: https://lkml.kernel.org/r/20251215081002.3353900A9c-agordeev@linux.ibm.com Link: https://lkml.kernel.org/r/20251212151457.3898073Add-agordeev@linux.ibm.com Fixes: e6cf9e1c4cde ("mm: page_alloc: fix up block types when merging compatible blocks") Signed-off-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Reported-by: Marc Hartmayer <mhartmay(a)linux.ibm.com> Closes: https://lore.kernel.org/linux-mm/87wmalyktd.fsf@linux.ibm.com/ Acked-by: Vlastimil Babka <vbabka(a)suse.cz> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Reviewed-by: Wei Yang <richard.weiyang(a)gmail.com> Cc: Marc Hartmayer <mhartmay(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_alloc.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) --- a/mm/page_alloc.c~mm-page_alloc-change-all-pageblocks-migrate-type-on-coalescing +++ a/mm/page_alloc.c @@ -914,6 +914,17 @@ buddy_merge_likely(unsigned long pfn, un NULL) != NULL; } +static void change_pageblock_range(struct page *pageblock_page, + int start_order, int migratetype) +{ + int nr_pageblocks = 1 << (start_order - pageblock_order); + + while (nr_pageblocks--) { + set_pageblock_migratetype(pageblock_page, migratetype); + pageblock_page += pageblock_nr_pages; + } +} + /* * Freeing function for a buddy system allocator. * @@ -1000,7 +1011,7 @@ static inline void __free_one_page(struc * expand() down the line puts the sub-blocks * on the right freelists. */ - set_pageblock_migratetype(buddy, migratetype); + change_pageblock_range(buddy, order, migratetype); } combined_pfn = buddy_pfn & pfn; @@ -2147,17 +2158,6 @@ bool pageblock_unisolate_and_move_free_p #endif /* CONFIG_MEMORY_ISOLATION */ -static void change_pageblock_range(struct page *pageblock_page, - int start_order, int migratetype) -{ - int nr_pageblocks = 1 << (start_order - pageblock_order); - - while (nr_pageblocks--) { - set_pageblock_migratetype(pageblock_page, migratetype); - pageblock_page += pageblock_nr_pages; - } -} - static inline bool boost_watermark(struct zone *zone) { unsigned long max_boost; _ Patches currently in -mm which might be from agordeev(a)linux.ibm.com are powerpc-64s-do-not-re-activate-batched-tlb-flush.patch

21 hours, 50 minutes

1
0
0 0

[merged mm-hotfixes-stable] kasan-unpoison-vms-addresses-with-a-common-tag.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: kasan: unpoison vms[area] addresses with a common tag has been removed from the -mm tree. Its filename was kasan-unpoison-vms-addresses-with-a-common-tag.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: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> Subject: kasan: unpoison vms[area] addresses with a common tag Date: Thu, 04 Dec 2025 19:00:11 +0000 A KASAN tag mismatch, possibly causing a kernel panic, can be observed on systems with a tag-based KASAN enabled and with multiple NUMA nodes. It was reported on arm64 and reproduced on x86. It can be explained in the following points: 1. There can be more than one virtual memory chunk. 2. Chunk's base address has a tag. 3. The base address points at the first chunk and thus inherits the tag of the first chunk. 4. The subsequent chunks will be accessed with the tag from the first chunk. 5. Thus, the subsequent chunks need to have their tag set to match that of the first chunk. Use the new vmalloc flag that disables random tag assignment in __kasan_unpoison_vmalloc() - pass the same random tag to all the vm_structs by tagging the pointers before they go inside __kasan_unpoison_vmalloc(). Assigning a common tag resolves the pcpu chunk address mismatch. [akpm(a)linux-foundation.org: use WARN_ON_ONCE(), per Andrey] Link: https://lkml.kernel.org/r/CA+fCnZeuGdKSEm11oGT6FS71_vGq1vjq-xY36kxVdFvwmag2… [maciej.wieczor-retman(a)intel.com: remove unneeded pr_warn()] Link: https://lkml.kernel.org/r/919897daaaa3c982a27762a2ee038769ad033991.17649453… Link: https://lkml.kernel.org/r/873821114a9f722ffb5d6702b94782e902883fdf.17648745… Fixes: 1d96320f8d53 ("kasan, vmalloc: add vmalloc tagging for SW_TAGS") Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> Reviewed-by: Andrey Konovalov <andreyknvl(a)gmail.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Cc: Danilo Krummrich <dakr(a)kernel.org> Cc: Dmitriy Vyukov <dvyukov(a)google.com> Cc: Jiayuan Chen <jiayuan.chen(a)linux.dev> Cc: Kees Cook <kees(a)kernel.org> Cc: Marco Elver <elver(a)google.com> Cc: "Uladzislau Rezki (Sony)" <urezki(a)gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Cc: <stable(a)vger.kernel.org> [6.1+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kasan/common.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) --- a/mm/kasan/common.c~kasan-unpoison-vms-addresses-with-a-common-tag +++ a/mm/kasan/common.c @@ -584,11 +584,26 @@ void __kasan_unpoison_vmap_areas(struct unsigned long size; void *addr; int area; + u8 tag; - for (area = 0 ; area < nr_vms ; area++) { + /* + * If KASAN_VMALLOC_KEEP_TAG was set at this point, all vms[] pointers + * would be unpoisoned with the KASAN_TAG_KERNEL which would disable + * KASAN checks down the line. + */ + if (WARN_ON_ONCE(flags & KASAN_VMALLOC_KEEP_TAG)) + return; + + size = vms[0]->size; + addr = vms[0]->addr; + vms[0]->addr = __kasan_unpoison_vmalloc(addr, size, flags); + tag = get_tag(vms[0]->addr); + + for (area = 1 ; area < nr_vms ; area++) { size = vms[area]->size; - addr = vms[area]->addr; - vms[area]->addr = __kasan_unpoison_vmalloc(addr, size, flags); + addr = set_tag(vms[area]->addr, tag); + vms[area]->addr = + __kasan_unpoison_vmalloc(addr, size, flags | KASAN_VMALLOC_KEEP_TAG); } } #endif _ Patches currently in -mm which might be from maciej.wieczor-retman(a)intel.com are

21 hours, 50 minutes

1
0
0 0

[merged mm-hotfixes-stable] kasan-refactor-pcpu-kasan-vmalloc-unpoison.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: kasan: refactor pcpu kasan vmalloc unpoison has been removed from the -mm tree. Its filename was kasan-refactor-pcpu-kasan-vmalloc-unpoison.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: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> Subject: kasan: refactor pcpu kasan vmalloc unpoison Date: Thu, 04 Dec 2025 19:00:04 +0000 A KASAN tag mismatch, possibly causing a kernel panic, can be observed on systems with a tag-based KASAN enabled and with multiple NUMA nodes. It was reported on arm64 and reproduced on x86. It can be explained in the following points: 1. There can be more than one virtual memory chunk. 2. Chunk's base address has a tag. 3. The base address points at the first chunk and thus inherits the tag of the first chunk. 4. The subsequent chunks will be accessed with the tag from the first chunk. 5. Thus, the subsequent chunks need to have their tag set to match that of the first chunk. Refactor code by reusing __kasan_unpoison_vmalloc in a new helper in preparation for the actual fix. Link: https://lkml.kernel.org/r/eb61d93b907e262eefcaa130261a08bcb6c5ce51.17648745… Fixes: 1d96320f8d53 ("kasan, vmalloc: add vmalloc tagging for SW_TAGS") Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> Reviewed-by: Andrey Konovalov <andreyknvl(a)gmail.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Cc: Danilo Krummrich <dakr(a)kernel.org> Cc: Dmitriy Vyukov <dvyukov(a)google.com> Cc: Jiayuan Chen <jiayuan.chen(a)linux.dev> Cc: Kees Cook <kees(a)kernel.org> Cc: Marco Elver <elver(a)google.com> Cc: "Uladzislau Rezki (Sony)" <urezki(a)gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Cc: <stable(a)vger.kernel.org> [6.1+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/kasan.h | 15 +++++++++++++++ mm/kasan/common.c | 17 +++++++++++++++++ mm/vmalloc.c | 4 +--- 3 files changed, 33 insertions(+), 3 deletions(-) --- a/include/linux/kasan.h~kasan-refactor-pcpu-kasan-vmalloc-unpoison +++ a/include/linux/kasan.h @@ -631,6 +631,16 @@ static __always_inline void kasan_poison __kasan_poison_vmalloc(start, size); } +void __kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags); +static __always_inline void +kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ + if (kasan_enabled()) + __kasan_unpoison_vmap_areas(vms, nr_vms, flags); +} + #else /* CONFIG_KASAN_VMALLOC */ static inline void kasan_populate_early_vm_area_shadow(void *start, @@ -655,6 +665,11 @@ static inline void *kasan_unpoison_vmall static inline void kasan_poison_vmalloc(const void *start, unsigned long size) { } +static __always_inline void +kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ } + #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ --- a/mm/kasan/common.c~kasan-refactor-pcpu-kasan-vmalloc-unpoison +++ a/mm/kasan/common.c @@ -28,6 +28,7 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/bug.h> +#include <linux/vmalloc.h> #include "kasan.h" #include "../slab.h" @@ -575,3 +576,19 @@ bool __kasan_check_byte(const void *addr } return true; } + +#ifdef CONFIG_KASAN_VMALLOC +void __kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ + unsigned long size; + void *addr; + int area; + + for (area = 0 ; area < nr_vms ; area++) { + size = vms[area]->size; + addr = vms[area]->addr; + vms[area]->addr = __kasan_unpoison_vmalloc(addr, size, flags); + } +} +#endif --- a/mm/vmalloc.c~kasan-refactor-pcpu-kasan-vmalloc-unpoison +++ a/mm/vmalloc.c @@ -5027,9 +5027,7 @@ retry: * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ - for (area = 0; area < nr_vms; area++) - vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr, - vms[area]->size, KASAN_VMALLOC_PROT_NORMAL); + kasan_unpoison_vmap_areas(vms, nr_vms, KASAN_VMALLOC_PROT_NORMAL); kfree(vas); return vms; _ Patches currently in -mm which might be from maciej.wieczor-retman(a)intel.com are

21 hours, 50 minutes

1
0
0 0

[merged mm-hotfixes-stable] mm-kasan-fix-incorrect-unpoisoning-in-vrealloc-for-kasan.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/kasan: fix incorrect unpoisoning in vrealloc for KASAN has been removed from the -mm tree. Its filename was mm-kasan-fix-incorrect-unpoisoning-in-vrealloc-for-kasan.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: Jiayuan Chen <jiayuan.chen(a)linux.dev> Subject: mm/kasan: fix incorrect unpoisoning in vrealloc for KASAN Date: Thu, 04 Dec 2025 18:59:55 +0000 Patch series "kasan: vmalloc: Fixes for the percpu allocator and vrealloc", v3. Patches fix two issues related to KASAN and vmalloc. The first one, a KASAN tag mismatch, possibly resulting in a kernel panic, can be observed on systems with a tag-based KASAN enabled and with multiple NUMA nodes. Initially it was only noticed on x86 [1] but later a similar issue was also reported on arm64 [2]. Specifically the problem is related to how vm_structs interact with pcpu_chunks - both when they are allocated, assigned and when pcpu_chunk addresses are derived. When vm_structs are allocated they are unpoisoned, each with a different random tag, if vmalloc support is enabled along the KASAN mode. Later when first pcpu chunk is allocated it gets its 'base_addr' field set to the first allocated vm_struct. With that it inherits that vm_struct's tag. When pcpu_chunk addresses are later derived (by pcpu_chunk_addr(), for example in pcpu_alloc_noprof()) the base_addr field is used and offsets are added to it. If the initial conditions are satisfied then some of the offsets will point into memory allocated with a different vm_struct. So while the lower bits will get accurately derived the tag bits in the top of the pointer won't match the shadow memory contents. The solution (proposed at v2 of the x86 KASAN series [3]) is to unpoison the vm_structs with the same tag when allocating them for the per cpu allocator (in pcpu_get_vm_areas()). The second one reported by syzkaller [4] is related to vrealloc and happens because of random tag generation when unpoisoning memory without allocating new pages. This breaks shadow memory tracking and needs to reuse the existing tag instead of generating a new one. At the same time an inconsistency in used flags is corrected. This patch (of 3): Syzkaller reported a memory out-of-bounds bug [4]. This patch fixes two issues: 1. In vrealloc the KASAN_VMALLOC_VM_ALLOC flag is missing when unpoisoning the extended region. This flag is required to correctly associate the allocation with KASAN's vmalloc tracking. Note: In contrast, vzalloc (via __vmalloc_node_range_noprof) explicitly sets KASAN_VMALLOC_VM_ALLOC and calls kasan_unpoison_vmalloc() with it. vrealloc must behave consistently -- especially when reusing existing vmalloc regions -- to ensure KASAN can track allocations correctly. 2. When vrealloc reuses an existing vmalloc region (without allocating new pages) KASAN generates a new tag, which breaks tag-based memory access tracking. Introduce KASAN_VMALLOC_KEEP_TAG, a new KASAN flag that allows reusing the tag already attached to the pointer, ensuring consistent tag behavior during reallocation. Pass KASAN_VMALLOC_KEEP_TAG and KASAN_VMALLOC_VM_ALLOC to the kasan_unpoison_vmalloc inside vrealloc_node_align_noprof(). Link: https://lkml.kernel.org/r/cover.1765978969.git.m.wieczorretman@pm.me Link: https://lkml.kernel.org/r/38dece0a4074c43e48150d1e242f8242c73bf1a5.17648745… Link: https://lore.kernel.org/all/e7e04692866d02e6d3b32bb43b998e5d17092ba4.173868… [1] Link: https://lore.kernel.org/all/aMUrW1Znp1GEj7St@MiWiFi-R3L-srv/ [2] Link: https://lore.kernel.org/all/CAPAsAGxDRv_uFeMYu9TwhBVWHCCtkSxoWY4xmFB_vowMbi… [3] Link: https://syzkaller.appspot.com/bug?extid=997752115a851cb0cf36 [4] Fixes: a0309faf1cb0 ("mm: vmalloc: support more granular vrealloc() sizing") Signed-off-by: Jiayuan Chen <jiayuan.chen(a)linux.dev> Co-developed-by: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> Reported-by: syzbot+997752115a851cb0cf36(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/68e243a2.050a0220.1696c6.007d.GAE@google.com/T/ Reviewed-by: Andrey Konovalov <andreyknvl(a)gmail.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Cc: Danilo Krummrich <dakr(a)kernel.org> Cc: Dmitriy Vyukov <dvyukov(a)google.com> Cc: Kees Cook <kees(a)kernel.org> Cc: Marco Elver <elver(a)google.com> Cc: "Uladzislau Rezki (Sony)" <urezki(a)gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/kasan.h | 1 + mm/kasan/hw_tags.c | 2 +- mm/kasan/shadow.c | 4 +++- mm/vmalloc.c | 4 +++- 4 files changed, 8 insertions(+), 3 deletions(-) --- a/include/linux/kasan.h~mm-kasan-fix-incorrect-unpoisoning-in-vrealloc-for-kasan +++ a/include/linux/kasan.h @@ -28,6 +28,7 @@ typedef unsigned int __bitwise kasan_vma #define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u) #define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) #define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) +#define KASAN_VMALLOC_KEEP_TAG ((__force kasan_vmalloc_flags_t)0x08u) #define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */ #define KASAN_VMALLOC_TLB_FLUSH 0x2 /* TLB flush */ --- a/mm/kasan/hw_tags.c~mm-kasan-fix-incorrect-unpoisoning-in-vrealloc-for-kasan +++ a/mm/kasan/hw_tags.c @@ -361,7 +361,7 @@ void *__kasan_unpoison_vmalloc(const voi return (void *)start; } - tag = kasan_random_tag(); + tag = (flags & KASAN_VMALLOC_KEEP_TAG) ? get_tag(start) : kasan_random_tag(); start = set_tag(start, tag); /* Unpoison and initialize memory up to size. */ --- a/mm/kasan/shadow.c~mm-kasan-fix-incorrect-unpoisoning-in-vrealloc-for-kasan +++ a/mm/kasan/shadow.c @@ -631,7 +631,9 @@ void *__kasan_unpoison_vmalloc(const voi !(flags & KASAN_VMALLOC_PROT_NORMAL)) return (void *)start; - start = set_tag(start, kasan_random_tag()); + if (unlikely(!(flags & KASAN_VMALLOC_KEEP_TAG))) + start = set_tag(start, kasan_random_tag()); + kasan_unpoison(start, size, false); return (void *)start; } --- a/mm/vmalloc.c~mm-kasan-fix-incorrect-unpoisoning-in-vrealloc-for-kasan +++ a/mm/vmalloc.c @@ -4331,7 +4331,9 @@ void *vrealloc_node_align_noprof(const v */ if (size <= alloced_size) { kasan_unpoison_vmalloc(p + old_size, size - old_size, - KASAN_VMALLOC_PROT_NORMAL); + KASAN_VMALLOC_PROT_NORMAL | + KASAN_VMALLOC_VM_ALLOC | + KASAN_VMALLOC_KEEP_TAG); /* * No need to zero memory here, as unused memory will have * already been zeroed at initial allocation time or during _ Patches currently in -mm which might be from jiayuan.chen(a)linux.dev are

21 hours, 50 minutes

1
0
0 0

[merged mm-hotfixes-stable] idr-fix-idr_alloc-returning-an-id-out-of-range.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: idr: fix idr_alloc() returning an ID out of range has been removed from the -mm tree. Its filename was idr-fix-idr_alloc-returning-an-id-out-of-range.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: "Matthew Wilcox (Oracle)" <willy(a)infradead.org> Subject: idr: fix idr_alloc() returning an ID out of range Date: Fri, 28 Nov 2025 16:18:32 +0000 If you use an IDR with a non-zero base, and specify a range that lies entirely below the base, 'max - base' becomes very large and idr_get_free() can return an ID that lies outside of the requested range. Link: https://lkml.kernel.org/r/20251128161853.3200058-1-willy@infradead.org Fixes: 6ce711f27500 ("idr: Make 1-based IDRs more efficient") Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> Reported-by: Jan Sokolowski <jan.sokolowski(a)intel.com> Reported-by: Koen Koning <koen.koning(a)intel.com> Reported-by: Peter Senna Tschudin <peter.senna(a)linux.intel.com> Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/6449 Reviewed-by: Christian K��nig <christian.koenig(a)amd.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- lib/idr.c | 2 ++ tools/testing/radix-tree/idr-test.c | 21 +++++++++++++++++++++ 2 files changed, 23 insertions(+) --- a/lib/idr.c~idr-fix-idr_alloc-returning-an-id-out-of-range +++ a/lib/idr.c @@ -40,6 +40,8 @@ int idr_alloc_u32(struct idr *idr, void if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR))) idr->idr_rt.xa_flags |= IDR_RT_MARKER; + if (max < base) + return -ENOSPC; id = (id < base) ? 0 : id - base; radix_tree_iter_init(&iter, id); --- a/tools/testing/radix-tree/idr-test.c~idr-fix-idr_alloc-returning-an-id-out-of-range +++ a/tools/testing/radix-tree/idr-test.c @@ -57,6 +57,26 @@ void idr_alloc_test(void) idr_destroy(&idr); } +void idr_alloc2_test(void) +{ + int id; + struct idr idr = IDR_INIT_BASE(idr, 1); + + id = idr_alloc(&idr, idr_alloc2_test, 0, 1, GFP_KERNEL); + assert(id == -ENOSPC); + + id = idr_alloc(&idr, idr_alloc2_test, 1, 2, GFP_KERNEL); + assert(id == 1); + + id = idr_alloc(&idr, idr_alloc2_test, 0, 1, GFP_KERNEL); + assert(id == -ENOSPC); + + id = idr_alloc(&idr, idr_alloc2_test, 0, 2, GFP_KERNEL); + assert(id == -ENOSPC); + + idr_destroy(&idr); +} + void idr_replace_test(void) { DEFINE_IDR(idr); @@ -409,6 +429,7 @@ void idr_checks(void) idr_replace_test(); idr_alloc_test(); + idr_alloc2_test(); idr_null_test(); idr_nowait_test(); idr_get_next_test(0); _ Patches currently in -mm which might be from willy(a)infradead.org are

21 hours, 50 minutes

1
0
0 0

[PATCH 5.10.y 5.15.y RESEND] ipv6: Fix potential uninit-value access in __ip6_make_skb()

by skulkarni＠mvista.com

From: Shigeru Yoshida <syoshida(a)redhat.com> commit 4e13d3a9c25b7080f8a619f961e943fe08c2672c upstream. As it was done in commit fc1092f51567 ("ipv4: Fix uninit-value access in __ip_make_skb()") for IPv4, check FLOWI_FLAG_KNOWN_NH on fl6->flowi6_flags instead of testing HDRINCL on the socket to avoid a race condition which causes uninit-value access. Fixes: ea30388baebc ("ipv6: Fix an uninit variable access bug in __ip6_make_skb()") Signed-off-by: Shigeru Yoshida <syoshida(a)redhat.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Shubham Kulkarni <skulkarni(a)mvista.com> --- Referred stable v6.1.y version of the patch to generate this one [ v6.1 link: https://github.com/gregkh/linux/commit/a05c1ede50e9656f0752e523c7b54f3a3489… ] --- net/ipv6/ip6_output.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 426330b8dfa4..99ee18b3a953 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1917,7 +1917,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; - if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_socket->type == SOCK_RAW && + !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; -- 2.25.1

22 hours, 20 minutes

1
0
0 0

[PATCH] ipv6: Fix potential uninit-value access in __ip6_make_skb()

by skulkarni＠mvista.com

From: Shigeru Yoshida <syoshida(a)redhat.com> commit 4e13d3a9c25b7080f8a619f961e943fe08c2672c upstream. As it was done in commit fc1092f51567 ("ipv4: Fix uninit-value access in __ip_make_skb()") for IPv4, check FLOWI_FLAG_KNOWN_NH on fl6->flowi6_flags instead of testing HDRINCL on the socket to avoid a race condition which causes uninit-value access. Fixes: ea30388baebc ("ipv6: Fix an uninit variable access bug in __ip6_make_skb()") Signed-off-by: Shigeru Yoshida <syoshida(a)redhat.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Shubham Kulkarni <skulkarni(a)mvista.com> --- Referred stable v6.1.y version of the patch to generate this one [ v6.1 link: https://github.com/gregkh/linux/commit/a05c1ede50e9656f0752e523c7b54f3a3489… ] --- net/ipv6/ip6_output.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 426330b8dfa4..99ee18b3a953 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1917,7 +1917,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; - if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_socket->type == SOCK_RAW && + !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; -- 2.25.1

22 hours, 39 minutes

1
1
0 0

[PATCH v3 1/2] mm/memory-failure: fix missing ->mf_stats count in hugetlb poison

by Jane Chu

When a newly poisoned subpage ends up in an already poisoned hugetlb folio, 'num_poisoned_pages' is incremented, but the per node ->mf_stats is not. Fix the inconsistency by designating action_result() to update them both. While at it, define __get_huge_page_for_hwpoison() return values in terms of symbol names for better readibility. Also rename folio_set_hugetlb_hwpoison() to hugetlb_update_hwpoison() since the function does more than the conventional bit setting and the fact three possible return values are expected. Fixes: 18f41fa616ee4 ("mm: memory-failure: bump memory failure stats to pglist_data") Cc: <stable(a)vger.kernel.org> Signed-off-by: Jane Chu <jane.chu(a)oracle.com> --- v2 -> v3: No change. v1 -> v2: adapted David and Liam's comment, define __get_huge_page_for_hwpoison() return values in terms of symbol names instead of naked integers for better readibility. #define instead of enum is used since the function has footprint outside MF, just try to limit the MF specifics local. also renamed folio_set_hugetlb_hwpoison() to hugetlb_update_hwpoison() since the function does more than the conventional bit setting and the fact three possible return values are expected. --- mm/memory-failure.c | 56 ++++++++++++++++++++++++++------------------- 1 file changed, 33 insertions(+), 23 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fbc5a01260c8..8b47e8a1b12d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1883,12 +1883,18 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag) return count; } -static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page) +#define MF_HUGETLB_ALREADY_POISONED 3 /* already poisoned */ +#define MF_HUGETLB_ACC_EXISTING_POISON 4 /* accessed existing poisoned page */ +/* + * Set hugetlb folio as hwpoisoned, update folio private raw hwpoison list + * to keep track of the poisoned pages. + */ +static int hugetlb_update_hwpoison(struct folio *folio, struct page *page) { struct llist_head *head; struct raw_hwp_page *raw_hwp; struct raw_hwp_page *p; - int ret = folio_test_set_hwpoison(folio) ? -EHWPOISON : 0; + int ret = folio_test_set_hwpoison(folio) ? MF_HUGETLB_ALREADY_POISONED : 0; /* * Once the hwpoison hugepage has lost reliable raw error info, @@ -1896,20 +1902,18 @@ static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page) * so skip to add additional raw error info. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) - return -EHWPOISON; + return MF_HUGETLB_ALREADY_POISONED; + head = raw_hwp_list_head(folio); llist_for_each_entry(p, head->first, node) { if (p->page == page) - return -EHWPOISON; + return MF_HUGETLB_ACC_EXISTING_POISON; } raw_hwp = kmalloc(sizeof(struct raw_hwp_page), GFP_ATOMIC); if (raw_hwp) { raw_hwp->page = page; llist_add(&raw_hwp->node, head); - /* the first error event will be counted in action_result(). */ - if (ret) - num_poisoned_pages_inc(page_to_pfn(page)); } else { /* * Failed to save raw error info. We no longer trace all @@ -1955,32 +1959,30 @@ void folio_clear_hugetlb_hwpoison(struct folio *folio) folio_free_raw_hwp(folio, true); } +#define MF_HUGETLB_FREED 0 /* freed hugepage */ +#define MF_HUGETLB_IN_USED 1 /* in-use hugepage */ +#define MF_NOT_HUGETLB 2 /* not a hugepage */ + /* * Called from hugetlb code with hugetlb_lock held. - * - * Return values: - * 0 - free hugepage - * 1 - in-use hugepage - * 2 - not a hugepage - * -EBUSY - the hugepage is busy (try to retry) - * -EHWPOISON - the hugepage is already hwpoisoned */ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { struct page *page = pfn_to_page(pfn); struct folio *folio = page_folio(page); - int ret = 2; /* fallback to normal page handling */ + int ret = MF_NOT_HUGETLB; bool count_increased = false; + int rc; if (!folio_test_hugetlb(folio)) goto out; if (flags & MF_COUNT_INCREASED) { - ret = 1; + ret = MF_HUGETLB_IN_USED; count_increased = true; } else if (folio_test_hugetlb_freed(folio)) { - ret = 0; + ret = MF_HUGETLB_FREED; } else if (folio_test_hugetlb_migratable(folio)) { ret = folio_try_get(folio); if (ret) @@ -1991,8 +1993,9 @@ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, goto out; } - if (folio_set_hugetlb_hwpoison(folio, page)) { - ret = -EHWPOISON; + rc = hugetlb_update_hwpoison(folio, page); + if (rc >= MF_HUGETLB_ALREADY_POISONED) { + ret = rc; goto out; } @@ -2029,22 +2032,29 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb *hugetlb = 1; retry: res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared); - if (res == 2) { /* fallback to normal page handling */ + switch (res) { + case MF_NOT_HUGETLB: /* fallback to normal page handling */ *hugetlb = 0; return 0; - } else if (res == -EHWPOISON) { + case MF_HUGETLB_ALREADY_POISONED: + case MF_HUGETLB_ACC_EXISTING_POISON: if (flags & MF_ACTION_REQUIRED) { folio = page_folio(p); res = kill_accessing_process(current, folio_pfn(folio), flags); } - action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); + if (res == MF_HUGETLB_ALREADY_POISONED) + action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); + else + action_result(pfn, MF_MSG_HUGE, MF_FAILED); return res; - } else if (res == -EBUSY) { + case -EBUSY: if (!(flags & MF_NO_RETRY)) { flags |= MF_NO_RETRY; goto retry; } return action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED); + default: + break; } folio = page_folio(p); -- 2.43.5

22 hours, 46 minutes

3
5
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror December 2025