May 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] mm: fix copy_vma() error handling for hugetlb mappings" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-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-6.1.y git checkout FETCH_HEAD git cherry-pick -x ee40c9920ac286c5bfe7c811e66ff899266d2582 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052652-bloated-preoccupy-3ffb@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ee40c9920ac286c5bfe7c811e66ff899266d2582 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo=20Navarro?= <rcn(a)igalia.com> Date: Fri, 23 May 2025 14:19:10 +0200 Subject: [PATCH] mm: fix copy_vma() error handling for hugetlb mappings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If, during a mremap() operation for a hugetlb-backed memory mapping, copy_vma() fails after the source vma has been duplicated and opened (ie. vma_link() fails), the error is handled by closing the new vma. This updates the hugetlbfs reservation counter of the reservation map which at this point is referenced by both the source vma and the new copy. As a result, once the new vma has been freed and copy_vma() returns, the reservation counter for the source vma will be incorrect. This patch addresses this corner case by clearing the hugetlb private page reservation reference for the new vma and decrementing the reference before closing the vma, so that vma_close() won't update the reservation counter. This is also what copy_vma_and_data() does with the source vma if copy_vma() succeeds, so a helper function has been added to do the fixup in both functions. The issue was reported by a private syzbot instance and can be reproduced using the C reproducer in [1]. It's also a possible duplicate of public syzbot report [2]. The WARNING report is: ============================================================ page_counter underflow: -1024 nr_pages=1024 WARNING: CPU: 0 PID: 3287 at mm/page_counter.c:61 page_counter_cancel+0xf6/0x120 Modules linked in: CPU: 0 UID: 0 PID: 3287 Comm: repro__WARNING_ Not tainted 6.15.0-rc7+ #54 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-2-gc13ff2cd-prebuilt.qemu.org 04/01/2014 RIP: 0010:page_counter_cancel+0xf6/0x120 Code: ff 5b 41 5e 41 5f 5d c3 cc cc cc cc e8 f3 4f 8f ff c6 05 64 01 27 06 01 48 c7 c7 60 15 f8 85 48 89 de 4c 89 fa e8 2a a7 51 ff <0f> 0b e9 66 ff ff ff 44 89 f9 80 e1 07 38 c1 7c 9d 4c 81 RSP: 0018:ffffc900025df6a0 EFLAGS: 00010246 RAX: 2edfc409ebb44e00 RBX: fffffffffffffc00 RCX: ffff8880155f0000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: dffffc0000000000 R08: ffffffff81c4a23c R09: 1ffff1100330482a R10: dffffc0000000000 R11: ffffed100330482b R12: 0000000000000000 R13: ffff888058a882c0 R14: ffff888058a882c0 R15: 0000000000000400 FS: 0000000000000000(0000) GS:ffff88808fc53000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004b33e0 CR3: 00000000076d6000 CR4: 00000000000006f0 Call Trace: <TASK> page_counter_uncharge+0x33/0x80 hugetlb_cgroup_uncharge_counter+0xcb/0x120 hugetlb_vm_op_close+0x579/0x960 ? __pfx_hugetlb_vm_op_close+0x10/0x10 remove_vma+0x88/0x130 exit_mmap+0x71e/0xe00 ? __pfx_exit_mmap+0x10/0x10 ? __mutex_unlock_slowpath+0x22e/0x7f0 ? __pfx_exit_aio+0x10/0x10 ? __up_read+0x256/0x690 ? uprobe_clear_state+0x274/0x290 ? mm_update_next_owner+0xa9/0x810 __mmput+0xc9/0x370 exit_mm+0x203/0x2f0 ? __pfx_exit_mm+0x10/0x10 ? taskstats_exit+0x32b/0xa60 do_exit+0x921/0x2740 ? do_raw_spin_lock+0x155/0x3b0 ? __pfx_do_exit+0x10/0x10 ? __pfx_do_raw_spin_lock+0x10/0x10 ? _raw_spin_lock_irq+0xc5/0x100 do_group_exit+0x20c/0x2c0 get_signal+0x168c/0x1720 ? __pfx_get_signal+0x10/0x10 ? schedule+0x165/0x360 arch_do_signal_or_restart+0x8e/0x7d0 ? __pfx_arch_do_signal_or_restart+0x10/0x10 ? __pfx___se_sys_futex+0x10/0x10 syscall_exit_to_user_mode+0xb8/0x2c0 do_syscall_64+0x75/0x120 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x422dcd Code: Unable to access opcode bytes at 0x422da3. RSP: 002b:00007ff266cdb208 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 00007ff266cdbcdc RCX: 0000000000422dcd RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 00000000004c7bec RBP: 00007ff266cdb220 R08: 203a6362696c6720 R09: 203a6362696c6720 R10: 0000200000c00000 R11: 0000000000000246 R12: ffffffffffffffd0 R13: 0000000000000002 R14: 00007ffe1cb5f520 R15: 00007ff266cbb000 </TASK> ============================================================ Link: https://lkml.kernel.org/r/20250523-warning_in_page_counter_cancel-v2-1-b6df… Link: https://people.igalia.com/rcn/kernel_logs/20250422__WARNING_in_page_counter… [1] Link: https://lore.kernel.org/all/67000a50.050a0220.49194.048d.GAE@google.com/ [2] Signed-off-by: Ricardo Cañuelo Navarro <rcn(a)igalia.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Florent Revest <revest(a)google.com> Cc: Jann Horn <jannh(a)google.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8f3ac832ee7f..4861a7e304bb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -275,6 +275,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); +void fixup_hugetlb_reservations(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -468,6 +469,10 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } +static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ +} + #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 55e6796b24d0..6a3cf7935c14 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1250,7 +1250,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma) /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. - * This function should be only used by move_vma() and operate on + * This function should be only used by mremap and operate on * same sized vma. It should never come here with last ref on the * reservation. */ @@ -7939,3 +7939,17 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } + +/* + * For hugetlb, mremap() is an odd edge case - while the VMA copying is + * performed, we permit both the old and new VMAs to reference the same + * reservation. + * + * We fix this up after the operation succeeds, or if a newly allocated VMA + * is closed as a result of a failure to allocate memory. + */ +void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + clear_vma_resv_huge_pages(vma); +} diff --git a/mm/mremap.c b/mm/mremap.c index 7db9da609c84..0d4948b720e2 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1188,8 +1188,7 @@ static int copy_vma_and_data(struct vma_remap_struct *vrm, mremap_userfaultfd_prep(new_vma, vrm->uf); } - if (is_vm_hugetlb_page(vma)) - clear_vma_resv_huge_pages(vma); + fixup_hugetlb_reservations(vma); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) diff --git a/mm/vma.c b/mm/vma.c index 839d12f02c88..a468d4c29c0c 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -1834,6 +1834,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_vma_link: + fixup_hugetlb_reservations(new_vma); vma_close(new_vma); if (new_vma->vm_file)

1 month

1
0
0 0

FAILED: patch "[PATCH] mm: fix copy_vma() error handling for hugetlb mappings" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-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-6.6.y git checkout FETCH_HEAD git cherry-pick -x ee40c9920ac286c5bfe7c811e66ff899266d2582 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052651-capably-displease-37db@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ee40c9920ac286c5bfe7c811e66ff899266d2582 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo=20Navarro?= <rcn(a)igalia.com> Date: Fri, 23 May 2025 14:19:10 +0200 Subject: [PATCH] mm: fix copy_vma() error handling for hugetlb mappings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If, during a mremap() operation for a hugetlb-backed memory mapping, copy_vma() fails after the source vma has been duplicated and opened (ie. vma_link() fails), the error is handled by closing the new vma. This updates the hugetlbfs reservation counter of the reservation map which at this point is referenced by both the source vma and the new copy. As a result, once the new vma has been freed and copy_vma() returns, the reservation counter for the source vma will be incorrect. This patch addresses this corner case by clearing the hugetlb private page reservation reference for the new vma and decrementing the reference before closing the vma, so that vma_close() won't update the reservation counter. This is also what copy_vma_and_data() does with the source vma if copy_vma() succeeds, so a helper function has been added to do the fixup in both functions. The issue was reported by a private syzbot instance and can be reproduced using the C reproducer in [1]. It's also a possible duplicate of public syzbot report [2]. The WARNING report is: ============================================================ page_counter underflow: -1024 nr_pages=1024 WARNING: CPU: 0 PID: 3287 at mm/page_counter.c:61 page_counter_cancel+0xf6/0x120 Modules linked in: CPU: 0 UID: 0 PID: 3287 Comm: repro__WARNING_ Not tainted 6.15.0-rc7+ #54 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-2-gc13ff2cd-prebuilt.qemu.org 04/01/2014 RIP: 0010:page_counter_cancel+0xf6/0x120 Code: ff 5b 41 5e 41 5f 5d c3 cc cc cc cc e8 f3 4f 8f ff c6 05 64 01 27 06 01 48 c7 c7 60 15 f8 85 48 89 de 4c 89 fa e8 2a a7 51 ff <0f> 0b e9 66 ff ff ff 44 89 f9 80 e1 07 38 c1 7c 9d 4c 81 RSP: 0018:ffffc900025df6a0 EFLAGS: 00010246 RAX: 2edfc409ebb44e00 RBX: fffffffffffffc00 RCX: ffff8880155f0000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: dffffc0000000000 R08: ffffffff81c4a23c R09: 1ffff1100330482a R10: dffffc0000000000 R11: ffffed100330482b R12: 0000000000000000 R13: ffff888058a882c0 R14: ffff888058a882c0 R15: 0000000000000400 FS: 0000000000000000(0000) GS:ffff88808fc53000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004b33e0 CR3: 00000000076d6000 CR4: 00000000000006f0 Call Trace: <TASK> page_counter_uncharge+0x33/0x80 hugetlb_cgroup_uncharge_counter+0xcb/0x120 hugetlb_vm_op_close+0x579/0x960 ? __pfx_hugetlb_vm_op_close+0x10/0x10 remove_vma+0x88/0x130 exit_mmap+0x71e/0xe00 ? __pfx_exit_mmap+0x10/0x10 ? __mutex_unlock_slowpath+0x22e/0x7f0 ? __pfx_exit_aio+0x10/0x10 ? __up_read+0x256/0x690 ? uprobe_clear_state+0x274/0x290 ? mm_update_next_owner+0xa9/0x810 __mmput+0xc9/0x370 exit_mm+0x203/0x2f0 ? __pfx_exit_mm+0x10/0x10 ? taskstats_exit+0x32b/0xa60 do_exit+0x921/0x2740 ? do_raw_spin_lock+0x155/0x3b0 ? __pfx_do_exit+0x10/0x10 ? __pfx_do_raw_spin_lock+0x10/0x10 ? _raw_spin_lock_irq+0xc5/0x100 do_group_exit+0x20c/0x2c0 get_signal+0x168c/0x1720 ? __pfx_get_signal+0x10/0x10 ? schedule+0x165/0x360 arch_do_signal_or_restart+0x8e/0x7d0 ? __pfx_arch_do_signal_or_restart+0x10/0x10 ? __pfx___se_sys_futex+0x10/0x10 syscall_exit_to_user_mode+0xb8/0x2c0 do_syscall_64+0x75/0x120 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x422dcd Code: Unable to access opcode bytes at 0x422da3. RSP: 002b:00007ff266cdb208 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 00007ff266cdbcdc RCX: 0000000000422dcd RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 00000000004c7bec RBP: 00007ff266cdb220 R08: 203a6362696c6720 R09: 203a6362696c6720 R10: 0000200000c00000 R11: 0000000000000246 R12: ffffffffffffffd0 R13: 0000000000000002 R14: 00007ffe1cb5f520 R15: 00007ff266cbb000 </TASK> ============================================================ Link: https://lkml.kernel.org/r/20250523-warning_in_page_counter_cancel-v2-1-b6df… Link: https://people.igalia.com/rcn/kernel_logs/20250422__WARNING_in_page_counter… [1] Link: https://lore.kernel.org/all/67000a50.050a0220.49194.048d.GAE@google.com/ [2] Signed-off-by: Ricardo Cañuelo Navarro <rcn(a)igalia.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Florent Revest <revest(a)google.com> Cc: Jann Horn <jannh(a)google.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8f3ac832ee7f..4861a7e304bb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -275,6 +275,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); +void fixup_hugetlb_reservations(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -468,6 +469,10 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } +static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ +} + #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 55e6796b24d0..6a3cf7935c14 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1250,7 +1250,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma) /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. - * This function should be only used by move_vma() and operate on + * This function should be only used by mremap and operate on * same sized vma. It should never come here with last ref on the * reservation. */ @@ -7939,3 +7939,17 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } + +/* + * For hugetlb, mremap() is an odd edge case - while the VMA copying is + * performed, we permit both the old and new VMAs to reference the same + * reservation. + * + * We fix this up after the operation succeeds, or if a newly allocated VMA + * is closed as a result of a failure to allocate memory. + */ +void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + clear_vma_resv_huge_pages(vma); +} diff --git a/mm/mremap.c b/mm/mremap.c index 7db9da609c84..0d4948b720e2 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1188,8 +1188,7 @@ static int copy_vma_and_data(struct vma_remap_struct *vrm, mremap_userfaultfd_prep(new_vma, vrm->uf); } - if (is_vm_hugetlb_page(vma)) - clear_vma_resv_huge_pages(vma); + fixup_hugetlb_reservations(vma); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) diff --git a/mm/vma.c b/mm/vma.c index 839d12f02c88..a468d4c29c0c 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -1834,6 +1834,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_vma_link: + fixup_hugetlb_reservations(new_vma); vma_close(new_vma); if (new_vma->vm_file)

1 month

1
0
0 0

FAILED: patch "[PATCH] mm: fix copy_vma() error handling for hugetlb mappings" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-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-6.12.y git checkout FETCH_HEAD git cherry-pick -x ee40c9920ac286c5bfe7c811e66ff899266d2582 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052649-cymbal-eggplant-f524@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ee40c9920ac286c5bfe7c811e66ff899266d2582 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo=20Navarro?= <rcn(a)igalia.com> Date: Fri, 23 May 2025 14:19:10 +0200 Subject: [PATCH] mm: fix copy_vma() error handling for hugetlb mappings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If, during a mremap() operation for a hugetlb-backed memory mapping, copy_vma() fails after the source vma has been duplicated and opened (ie. vma_link() fails), the error is handled by closing the new vma. This updates the hugetlbfs reservation counter of the reservation map which at this point is referenced by both the source vma and the new copy. As a result, once the new vma has been freed and copy_vma() returns, the reservation counter for the source vma will be incorrect. This patch addresses this corner case by clearing the hugetlb private page reservation reference for the new vma and decrementing the reference before closing the vma, so that vma_close() won't update the reservation counter. This is also what copy_vma_and_data() does with the source vma if copy_vma() succeeds, so a helper function has been added to do the fixup in both functions. The issue was reported by a private syzbot instance and can be reproduced using the C reproducer in [1]. It's also a possible duplicate of public syzbot report [2]. The WARNING report is: ============================================================ page_counter underflow: -1024 nr_pages=1024 WARNING: CPU: 0 PID: 3287 at mm/page_counter.c:61 page_counter_cancel+0xf6/0x120 Modules linked in: CPU: 0 UID: 0 PID: 3287 Comm: repro__WARNING_ Not tainted 6.15.0-rc7+ #54 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-2-gc13ff2cd-prebuilt.qemu.org 04/01/2014 RIP: 0010:page_counter_cancel+0xf6/0x120 Code: ff 5b 41 5e 41 5f 5d c3 cc cc cc cc e8 f3 4f 8f ff c6 05 64 01 27 06 01 48 c7 c7 60 15 f8 85 48 89 de 4c 89 fa e8 2a a7 51 ff <0f> 0b e9 66 ff ff ff 44 89 f9 80 e1 07 38 c1 7c 9d 4c 81 RSP: 0018:ffffc900025df6a0 EFLAGS: 00010246 RAX: 2edfc409ebb44e00 RBX: fffffffffffffc00 RCX: ffff8880155f0000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: dffffc0000000000 R08: ffffffff81c4a23c R09: 1ffff1100330482a R10: dffffc0000000000 R11: ffffed100330482b R12: 0000000000000000 R13: ffff888058a882c0 R14: ffff888058a882c0 R15: 0000000000000400 FS: 0000000000000000(0000) GS:ffff88808fc53000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004b33e0 CR3: 00000000076d6000 CR4: 00000000000006f0 Call Trace: <TASK> page_counter_uncharge+0x33/0x80 hugetlb_cgroup_uncharge_counter+0xcb/0x120 hugetlb_vm_op_close+0x579/0x960 ? __pfx_hugetlb_vm_op_close+0x10/0x10 remove_vma+0x88/0x130 exit_mmap+0x71e/0xe00 ? __pfx_exit_mmap+0x10/0x10 ? __mutex_unlock_slowpath+0x22e/0x7f0 ? __pfx_exit_aio+0x10/0x10 ? __up_read+0x256/0x690 ? uprobe_clear_state+0x274/0x290 ? mm_update_next_owner+0xa9/0x810 __mmput+0xc9/0x370 exit_mm+0x203/0x2f0 ? __pfx_exit_mm+0x10/0x10 ? taskstats_exit+0x32b/0xa60 do_exit+0x921/0x2740 ? do_raw_spin_lock+0x155/0x3b0 ? __pfx_do_exit+0x10/0x10 ? __pfx_do_raw_spin_lock+0x10/0x10 ? _raw_spin_lock_irq+0xc5/0x100 do_group_exit+0x20c/0x2c0 get_signal+0x168c/0x1720 ? __pfx_get_signal+0x10/0x10 ? schedule+0x165/0x360 arch_do_signal_or_restart+0x8e/0x7d0 ? __pfx_arch_do_signal_or_restart+0x10/0x10 ? __pfx___se_sys_futex+0x10/0x10 syscall_exit_to_user_mode+0xb8/0x2c0 do_syscall_64+0x75/0x120 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x422dcd Code: Unable to access opcode bytes at 0x422da3. RSP: 002b:00007ff266cdb208 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 00007ff266cdbcdc RCX: 0000000000422dcd RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 00000000004c7bec RBP: 00007ff266cdb220 R08: 203a6362696c6720 R09: 203a6362696c6720 R10: 0000200000c00000 R11: 0000000000000246 R12: ffffffffffffffd0 R13: 0000000000000002 R14: 00007ffe1cb5f520 R15: 00007ff266cbb000 </TASK> ============================================================ Link: https://lkml.kernel.org/r/20250523-warning_in_page_counter_cancel-v2-1-b6df… Link: https://people.igalia.com/rcn/kernel_logs/20250422__WARNING_in_page_counter… [1] Link: https://lore.kernel.org/all/67000a50.050a0220.49194.048d.GAE@google.com/ [2] Signed-off-by: Ricardo Cañuelo Navarro <rcn(a)igalia.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Florent Revest <revest(a)google.com> Cc: Jann Horn <jannh(a)google.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8f3ac832ee7f..4861a7e304bb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -275,6 +275,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); +void fixup_hugetlb_reservations(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -468,6 +469,10 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } +static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ +} + #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 55e6796b24d0..6a3cf7935c14 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1250,7 +1250,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma) /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. - * This function should be only used by move_vma() and operate on + * This function should be only used by mremap and operate on * same sized vma. It should never come here with last ref on the * reservation. */ @@ -7939,3 +7939,17 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } + +/* + * For hugetlb, mremap() is an odd edge case - while the VMA copying is + * performed, we permit both the old and new VMAs to reference the same + * reservation. + * + * We fix this up after the operation succeeds, or if a newly allocated VMA + * is closed as a result of a failure to allocate memory. + */ +void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + clear_vma_resv_huge_pages(vma); +} diff --git a/mm/mremap.c b/mm/mremap.c index 7db9da609c84..0d4948b720e2 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1188,8 +1188,7 @@ static int copy_vma_and_data(struct vma_remap_struct *vrm, mremap_userfaultfd_prep(new_vma, vrm->uf); } - if (is_vm_hugetlb_page(vma)) - clear_vma_resv_huge_pages(vma); + fixup_hugetlb_reservations(vma); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) diff --git a/mm/vma.c b/mm/vma.c index 839d12f02c88..a468d4c29c0c 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -1834,6 +1834,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_vma_link: + fixup_hugetlb_reservations(new_vma); vma_close(new_vma); if (new_vma->vm_file)

1 month

1
0
0 0

FAILED: patch "[PATCH] mm: fix copy_vma() error handling for hugetlb mappings" failed to apply to 6.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.14-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-6.14.y git checkout FETCH_HEAD git cherry-pick -x ee40c9920ac286c5bfe7c811e66ff899266d2582 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052647-jokester-paralyses-8a1a@gregkh' --subject-prefix 'PATCH 6.14.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ee40c9920ac286c5bfe7c811e66ff899266d2582 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo=20Navarro?= <rcn(a)igalia.com> Date: Fri, 23 May 2025 14:19:10 +0200 Subject: [PATCH] mm: fix copy_vma() error handling for hugetlb mappings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If, during a mremap() operation for a hugetlb-backed memory mapping, copy_vma() fails after the source vma has been duplicated and opened (ie. vma_link() fails), the error is handled by closing the new vma. This updates the hugetlbfs reservation counter of the reservation map which at this point is referenced by both the source vma and the new copy. As a result, once the new vma has been freed and copy_vma() returns, the reservation counter for the source vma will be incorrect. This patch addresses this corner case by clearing the hugetlb private page reservation reference for the new vma and decrementing the reference before closing the vma, so that vma_close() won't update the reservation counter. This is also what copy_vma_and_data() does with the source vma if copy_vma() succeeds, so a helper function has been added to do the fixup in both functions. The issue was reported by a private syzbot instance and can be reproduced using the C reproducer in [1]. It's also a possible duplicate of public syzbot report [2]. The WARNING report is: ============================================================ page_counter underflow: -1024 nr_pages=1024 WARNING: CPU: 0 PID: 3287 at mm/page_counter.c:61 page_counter_cancel+0xf6/0x120 Modules linked in: CPU: 0 UID: 0 PID: 3287 Comm: repro__WARNING_ Not tainted 6.15.0-rc7+ #54 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-2-gc13ff2cd-prebuilt.qemu.org 04/01/2014 RIP: 0010:page_counter_cancel+0xf6/0x120 Code: ff 5b 41 5e 41 5f 5d c3 cc cc cc cc e8 f3 4f 8f ff c6 05 64 01 27 06 01 48 c7 c7 60 15 f8 85 48 89 de 4c 89 fa e8 2a a7 51 ff <0f> 0b e9 66 ff ff ff 44 89 f9 80 e1 07 38 c1 7c 9d 4c 81 RSP: 0018:ffffc900025df6a0 EFLAGS: 00010246 RAX: 2edfc409ebb44e00 RBX: fffffffffffffc00 RCX: ffff8880155f0000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: dffffc0000000000 R08: ffffffff81c4a23c R09: 1ffff1100330482a R10: dffffc0000000000 R11: ffffed100330482b R12: 0000000000000000 R13: ffff888058a882c0 R14: ffff888058a882c0 R15: 0000000000000400 FS: 0000000000000000(0000) GS:ffff88808fc53000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004b33e0 CR3: 00000000076d6000 CR4: 00000000000006f0 Call Trace: <TASK> page_counter_uncharge+0x33/0x80 hugetlb_cgroup_uncharge_counter+0xcb/0x120 hugetlb_vm_op_close+0x579/0x960 ? __pfx_hugetlb_vm_op_close+0x10/0x10 remove_vma+0x88/0x130 exit_mmap+0x71e/0xe00 ? __pfx_exit_mmap+0x10/0x10 ? __mutex_unlock_slowpath+0x22e/0x7f0 ? __pfx_exit_aio+0x10/0x10 ? __up_read+0x256/0x690 ? uprobe_clear_state+0x274/0x290 ? mm_update_next_owner+0xa9/0x810 __mmput+0xc9/0x370 exit_mm+0x203/0x2f0 ? __pfx_exit_mm+0x10/0x10 ? taskstats_exit+0x32b/0xa60 do_exit+0x921/0x2740 ? do_raw_spin_lock+0x155/0x3b0 ? __pfx_do_exit+0x10/0x10 ? __pfx_do_raw_spin_lock+0x10/0x10 ? _raw_spin_lock_irq+0xc5/0x100 do_group_exit+0x20c/0x2c0 get_signal+0x168c/0x1720 ? __pfx_get_signal+0x10/0x10 ? schedule+0x165/0x360 arch_do_signal_or_restart+0x8e/0x7d0 ? __pfx_arch_do_signal_or_restart+0x10/0x10 ? __pfx___se_sys_futex+0x10/0x10 syscall_exit_to_user_mode+0xb8/0x2c0 do_syscall_64+0x75/0x120 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x422dcd Code: Unable to access opcode bytes at 0x422da3. RSP: 002b:00007ff266cdb208 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 00007ff266cdbcdc RCX: 0000000000422dcd RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 00000000004c7bec RBP: 00007ff266cdb220 R08: 203a6362696c6720 R09: 203a6362696c6720 R10: 0000200000c00000 R11: 0000000000000246 R12: ffffffffffffffd0 R13: 0000000000000002 R14: 00007ffe1cb5f520 R15: 00007ff266cbb000 </TASK> ============================================================ Link: https://lkml.kernel.org/r/20250523-warning_in_page_counter_cancel-v2-1-b6df… Link: https://people.igalia.com/rcn/kernel_logs/20250422__WARNING_in_page_counter… [1] Link: https://lore.kernel.org/all/67000a50.050a0220.49194.048d.GAE@google.com/ [2] Signed-off-by: Ricardo Cañuelo Navarro <rcn(a)igalia.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Florent Revest <revest(a)google.com> Cc: Jann Horn <jannh(a)google.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8f3ac832ee7f..4861a7e304bb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -275,6 +275,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); +void fixup_hugetlb_reservations(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -468,6 +469,10 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } +static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ +} + #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 55e6796b24d0..6a3cf7935c14 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1250,7 +1250,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma) /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. - * This function should be only used by move_vma() and operate on + * This function should be only used by mremap and operate on * same sized vma. It should never come here with last ref on the * reservation. */ @@ -7939,3 +7939,17 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } + +/* + * For hugetlb, mremap() is an odd edge case - while the VMA copying is + * performed, we permit both the old and new VMAs to reference the same + * reservation. + * + * We fix this up after the operation succeeds, or if a newly allocated VMA + * is closed as a result of a failure to allocate memory. + */ +void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + clear_vma_resv_huge_pages(vma); +} diff --git a/mm/mremap.c b/mm/mremap.c index 7db9da609c84..0d4948b720e2 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1188,8 +1188,7 @@ static int copy_vma_and_data(struct vma_remap_struct *vrm, mremap_userfaultfd_prep(new_vma, vrm->uf); } - if (is_vm_hugetlb_page(vma)) - clear_vma_resv_huge_pages(vma); + fixup_hugetlb_reservations(vma); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) diff --git a/mm/vma.c b/mm/vma.c index 839d12f02c88..a468d4c29c0c 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -1834,6 +1834,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_vma_link: + fixup_hugetlb_reservations(new_vma); vma_close(new_vma); if (new_vma->vm_file)

1 month

1
0
0 0

FAILED: patch "[PATCH] kasan: avoid sleepable page allocation from atomic context" 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 b6ea95a34cbd014ab6ade4248107b86b0aaf2d6c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052642-trustful-pardon-7433@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b6ea95a34cbd014ab6ade4248107b86b0aaf2d6c Mon Sep 17 00:00:00 2001 From: Alexander Gordeev <agordeev(a)linux.ibm.com> Date: Thu, 15 May 2025 15:55:38 +0200 Subject: [PATCH] kasan: avoid sleepable page allocation from atomic context apply_to_pte_range() enters the lazy MMU mode and then invokes kasan_populate_vmalloc_pte() callback on each page table walk iteration. However, the callback can go into sleep when trying to allocate a single page, e.g. if an architecutre disables preemption on lazy MMU mode enter. On s390 if make arch_enter_lazy_mmu_mode() -> preempt_enable() and arch_leave_lazy_mmu_mode() -> preempt_disable(), such crash occurs: [ 0.663336] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:321 [ 0.663348] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd [ 0.663358] preempt_count: 1, expected: 0 [ 0.663366] RCU nest depth: 0, expected: 0 [ 0.663375] no locks held by kthreadd/2. [ 0.663383] Preemption disabled at: [ 0.663386] [<0002f3284cbb4eda>] apply_to_pte_range+0xfa/0x4a0 [ 0.663405] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.15.0-rc5-gcc-kasan-00043-gd76bb1ebb558-dirty #162 PREEMPT [ 0.663408] Hardware name: IBM 3931 A01 701 (KVM/Linux) [ 0.663409] Call Trace: [ 0.663410] [<0002f3284c385f58>] dump_stack_lvl+0xe8/0x140 [ 0.663413] [<0002f3284c507b9e>] __might_resched+0x66e/0x700 [ 0.663415] [<0002f3284cc4f6c0>] __alloc_frozen_pages_noprof+0x370/0x4b0 [ 0.663419] [<0002f3284ccc73c0>] alloc_pages_mpol+0x1a0/0x4a0 [ 0.663421] [<0002f3284ccc8518>] alloc_frozen_pages_noprof+0x88/0xc0 [ 0.663424] [<0002f3284ccc8572>] alloc_pages_noprof+0x22/0x120 [ 0.663427] [<0002f3284cc341ac>] get_free_pages_noprof+0x2c/0xc0 [ 0.663429] [<0002f3284cceba70>] kasan_populate_vmalloc_pte+0x50/0x120 [ 0.663433] [<0002f3284cbb4ef8>] apply_to_pte_range+0x118/0x4a0 [ 0.663435] [<0002f3284cbc7c14>] apply_to_pmd_range+0x194/0x3e0 [ 0.663437] [<0002f3284cbc99be>] __apply_to_page_range+0x2fe/0x7a0 [ 0.663440] [<0002f3284cbc9e88>] apply_to_page_range+0x28/0x40 [ 0.663442] [<0002f3284ccebf12>] kasan_populate_vmalloc+0x82/0xa0 [ 0.663445] [<0002f3284cc1578c>] alloc_vmap_area+0x34c/0xc10 [ 0.663448] [<0002f3284cc1c2a6>] __get_vm_area_node+0x186/0x2a0 [ 0.663451] [<0002f3284cc1e696>] __vmalloc_node_range_noprof+0x116/0x310 [ 0.663454] [<0002f3284cc1d950>] __vmalloc_node_noprof+0xd0/0x110 [ 0.663457] [<0002f3284c454b88>] alloc_thread_stack_node+0xf8/0x330 [ 0.663460] [<0002f3284c458d56>] dup_task_struct+0x66/0x4d0 [ 0.663463] [<0002f3284c45be90>] copy_process+0x280/0x4b90 [ 0.663465] [<0002f3284c460940>] kernel_clone+0xd0/0x4b0 [ 0.663467] [<0002f3284c46115e>] kernel_thread+0xbe/0xe0 [ 0.663469] [<0002f3284c4e440e>] kthreadd+0x50e/0x7f0 [ 0.663472] [<0002f3284c38c04a>] __ret_from_fork+0x8a/0xf0 [ 0.663475] [<0002f3284ed57ff2>] ret_from_fork+0xa/0x38 Instead of allocating single pages per-PTE, bulk-allocate the shadow memory prior to applying kasan_populate_vmalloc_pte() callback on a page range. Link: https://lkml.kernel.org/r/c61d3560297c93ed044f0b1af085610353a06a58.17473169… Fixes: 3c5c3cfb9ef4 ("kasan: support backing vmalloc space with real shadow memory") Signed-off-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Suggested-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Reviewed-by: Harry Yoo <harry.yoo(a)oracle.com> Cc: Daniel Axtens <dja(a)axtens.net> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 88d1c9dcb507..d2c70cd2afb1 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -292,33 +292,99 @@ void __init __weak kasan_populate_early_vm_area_shadow(void *start, { } +struct vmalloc_populate_data { + unsigned long start; + struct page **pages; +}; + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, - void *unused) + void *_data) { - unsigned long page; + struct vmalloc_populate_data *data = _data; + struct page *page; pte_t pte; + int index; if (likely(!pte_none(ptep_get(ptep)))) return 0; - page = __get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - __memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); - pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + index = PFN_DOWN(addr - data->start); + page = data->pages[index]; + __memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL); spin_lock(&init_mm.page_table_lock); if (likely(pte_none(ptep_get(ptep)))) { set_pte_at(&init_mm, addr, ptep, pte); - page = 0; + data->pages[index] = NULL; } spin_unlock(&init_mm.page_table_lock); - if (page) - free_page(page); + return 0; } +static void ___free_pages_bulk(struct page **pages, int nr_pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + if (pages[i]) { + __free_pages(pages[i], 0); + pages[i] = NULL; + } + } +} + +static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +{ + unsigned long nr_populated, nr_total = nr_pages; + struct page **page_array = pages; + + while (nr_pages) { + nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + if (!nr_populated) { + ___free_pages_bulk(page_array, nr_total - nr_pages); + return -ENOMEM; + } + pages += nr_populated; + nr_pages -= nr_populated; + } + + return 0; +} + +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +{ + unsigned long nr_pages, nr_total = PFN_UP(end - start); + struct vmalloc_populate_data data; + int ret = 0; + + data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!data.pages) + return -ENOMEM; + + while (nr_total) { + nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); + ret = ___alloc_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + data.start = start; + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, + kasan_populate_vmalloc_pte, &data); + ___free_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + start += nr_pages * PAGE_SIZE; + nr_total -= nr_pages; + } + + free_page((unsigned long)data.pages); + + return ret; +} + int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; @@ -348,9 +414,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = apply_to_page_range(&init_mm, shadow_start, - shadow_end - shadow_start, - kasan_populate_vmalloc_pte, NULL); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end); if (ret) return ret;

1 month

1
0
0 0

FAILED: patch "[PATCH] kasan: avoid sleepable page allocation from atomic context" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-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-5.15.y git checkout FETCH_HEAD git cherry-pick -x b6ea95a34cbd014ab6ade4248107b86b0aaf2d6c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052641-magnetize-unethical-6fd1@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b6ea95a34cbd014ab6ade4248107b86b0aaf2d6c Mon Sep 17 00:00:00 2001 From: Alexander Gordeev <agordeev(a)linux.ibm.com> Date: Thu, 15 May 2025 15:55:38 +0200 Subject: [PATCH] kasan: avoid sleepable page allocation from atomic context apply_to_pte_range() enters the lazy MMU mode and then invokes kasan_populate_vmalloc_pte() callback on each page table walk iteration. However, the callback can go into sleep when trying to allocate a single page, e.g. if an architecutre disables preemption on lazy MMU mode enter. On s390 if make arch_enter_lazy_mmu_mode() -> preempt_enable() and arch_leave_lazy_mmu_mode() -> preempt_disable(), such crash occurs: [ 0.663336] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:321 [ 0.663348] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd [ 0.663358] preempt_count: 1, expected: 0 [ 0.663366] RCU nest depth: 0, expected: 0 [ 0.663375] no locks held by kthreadd/2. [ 0.663383] Preemption disabled at: [ 0.663386] [<0002f3284cbb4eda>] apply_to_pte_range+0xfa/0x4a0 [ 0.663405] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.15.0-rc5-gcc-kasan-00043-gd76bb1ebb558-dirty #162 PREEMPT [ 0.663408] Hardware name: IBM 3931 A01 701 (KVM/Linux) [ 0.663409] Call Trace: [ 0.663410] [<0002f3284c385f58>] dump_stack_lvl+0xe8/0x140 [ 0.663413] [<0002f3284c507b9e>] __might_resched+0x66e/0x700 [ 0.663415] [<0002f3284cc4f6c0>] __alloc_frozen_pages_noprof+0x370/0x4b0 [ 0.663419] [<0002f3284ccc73c0>] alloc_pages_mpol+0x1a0/0x4a0 [ 0.663421] [<0002f3284ccc8518>] alloc_frozen_pages_noprof+0x88/0xc0 [ 0.663424] [<0002f3284ccc8572>] alloc_pages_noprof+0x22/0x120 [ 0.663427] [<0002f3284cc341ac>] get_free_pages_noprof+0x2c/0xc0 [ 0.663429] [<0002f3284cceba70>] kasan_populate_vmalloc_pte+0x50/0x120 [ 0.663433] [<0002f3284cbb4ef8>] apply_to_pte_range+0x118/0x4a0 [ 0.663435] [<0002f3284cbc7c14>] apply_to_pmd_range+0x194/0x3e0 [ 0.663437] [<0002f3284cbc99be>] __apply_to_page_range+0x2fe/0x7a0 [ 0.663440] [<0002f3284cbc9e88>] apply_to_page_range+0x28/0x40 [ 0.663442] [<0002f3284ccebf12>] kasan_populate_vmalloc+0x82/0xa0 [ 0.663445] [<0002f3284cc1578c>] alloc_vmap_area+0x34c/0xc10 [ 0.663448] [<0002f3284cc1c2a6>] __get_vm_area_node+0x186/0x2a0 [ 0.663451] [<0002f3284cc1e696>] __vmalloc_node_range_noprof+0x116/0x310 [ 0.663454] [<0002f3284cc1d950>] __vmalloc_node_noprof+0xd0/0x110 [ 0.663457] [<0002f3284c454b88>] alloc_thread_stack_node+0xf8/0x330 [ 0.663460] [<0002f3284c458d56>] dup_task_struct+0x66/0x4d0 [ 0.663463] [<0002f3284c45be90>] copy_process+0x280/0x4b90 [ 0.663465] [<0002f3284c460940>] kernel_clone+0xd0/0x4b0 [ 0.663467] [<0002f3284c46115e>] kernel_thread+0xbe/0xe0 [ 0.663469] [<0002f3284c4e440e>] kthreadd+0x50e/0x7f0 [ 0.663472] [<0002f3284c38c04a>] __ret_from_fork+0x8a/0xf0 [ 0.663475] [<0002f3284ed57ff2>] ret_from_fork+0xa/0x38 Instead of allocating single pages per-PTE, bulk-allocate the shadow memory prior to applying kasan_populate_vmalloc_pte() callback on a page range. Link: https://lkml.kernel.org/r/c61d3560297c93ed044f0b1af085610353a06a58.17473169… Fixes: 3c5c3cfb9ef4 ("kasan: support backing vmalloc space with real shadow memory") Signed-off-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Suggested-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Reviewed-by: Harry Yoo <harry.yoo(a)oracle.com> Cc: Daniel Axtens <dja(a)axtens.net> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 88d1c9dcb507..d2c70cd2afb1 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -292,33 +292,99 @@ void __init __weak kasan_populate_early_vm_area_shadow(void *start, { } +struct vmalloc_populate_data { + unsigned long start; + struct page **pages; +}; + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, - void *unused) + void *_data) { - unsigned long page; + struct vmalloc_populate_data *data = _data; + struct page *page; pte_t pte; + int index; if (likely(!pte_none(ptep_get(ptep)))) return 0; - page = __get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - __memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); - pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + index = PFN_DOWN(addr - data->start); + page = data->pages[index]; + __memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL); spin_lock(&init_mm.page_table_lock); if (likely(pte_none(ptep_get(ptep)))) { set_pte_at(&init_mm, addr, ptep, pte); - page = 0; + data->pages[index] = NULL; } spin_unlock(&init_mm.page_table_lock); - if (page) - free_page(page); + return 0; } +static void ___free_pages_bulk(struct page **pages, int nr_pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + if (pages[i]) { + __free_pages(pages[i], 0); + pages[i] = NULL; + } + } +} + +static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +{ + unsigned long nr_populated, nr_total = nr_pages; + struct page **page_array = pages; + + while (nr_pages) { + nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + if (!nr_populated) { + ___free_pages_bulk(page_array, nr_total - nr_pages); + return -ENOMEM; + } + pages += nr_populated; + nr_pages -= nr_populated; + } + + return 0; +} + +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +{ + unsigned long nr_pages, nr_total = PFN_UP(end - start); + struct vmalloc_populate_data data; + int ret = 0; + + data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!data.pages) + return -ENOMEM; + + while (nr_total) { + nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); + ret = ___alloc_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + data.start = start; + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, + kasan_populate_vmalloc_pte, &data); + ___free_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + start += nr_pages * PAGE_SIZE; + nr_total -= nr_pages; + } + + free_page((unsigned long)data.pages); + + return ret; +} + int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; @@ -348,9 +414,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = apply_to_page_range(&init_mm, shadow_start, - shadow_end - shadow_start, - kasan_populate_vmalloc_pte, NULL); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end); if (ret) return ret;

1 month

1
0
0 0

FAILED: patch "[PATCH] kasan: avoid sleepable page allocation from atomic context" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-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-6.1.y git checkout FETCH_HEAD git cherry-pick -x b6ea95a34cbd014ab6ade4248107b86b0aaf2d6c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052640-nintendo-dosage-797e@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b6ea95a34cbd014ab6ade4248107b86b0aaf2d6c Mon Sep 17 00:00:00 2001 From: Alexander Gordeev <agordeev(a)linux.ibm.com> Date: Thu, 15 May 2025 15:55:38 +0200 Subject: [PATCH] kasan: avoid sleepable page allocation from atomic context apply_to_pte_range() enters the lazy MMU mode and then invokes kasan_populate_vmalloc_pte() callback on each page table walk iteration. However, the callback can go into sleep when trying to allocate a single page, e.g. if an architecutre disables preemption on lazy MMU mode enter. On s390 if make arch_enter_lazy_mmu_mode() -> preempt_enable() and arch_leave_lazy_mmu_mode() -> preempt_disable(), such crash occurs: [ 0.663336] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:321 [ 0.663348] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd [ 0.663358] preempt_count: 1, expected: 0 [ 0.663366] RCU nest depth: 0, expected: 0 [ 0.663375] no locks held by kthreadd/2. [ 0.663383] Preemption disabled at: [ 0.663386] [<0002f3284cbb4eda>] apply_to_pte_range+0xfa/0x4a0 [ 0.663405] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.15.0-rc5-gcc-kasan-00043-gd76bb1ebb558-dirty #162 PREEMPT [ 0.663408] Hardware name: IBM 3931 A01 701 (KVM/Linux) [ 0.663409] Call Trace: [ 0.663410] [<0002f3284c385f58>] dump_stack_lvl+0xe8/0x140 [ 0.663413] [<0002f3284c507b9e>] __might_resched+0x66e/0x700 [ 0.663415] [<0002f3284cc4f6c0>] __alloc_frozen_pages_noprof+0x370/0x4b0 [ 0.663419] [<0002f3284ccc73c0>] alloc_pages_mpol+0x1a0/0x4a0 [ 0.663421] [<0002f3284ccc8518>] alloc_frozen_pages_noprof+0x88/0xc0 [ 0.663424] [<0002f3284ccc8572>] alloc_pages_noprof+0x22/0x120 [ 0.663427] [<0002f3284cc341ac>] get_free_pages_noprof+0x2c/0xc0 [ 0.663429] [<0002f3284cceba70>] kasan_populate_vmalloc_pte+0x50/0x120 [ 0.663433] [<0002f3284cbb4ef8>] apply_to_pte_range+0x118/0x4a0 [ 0.663435] [<0002f3284cbc7c14>] apply_to_pmd_range+0x194/0x3e0 [ 0.663437] [<0002f3284cbc99be>] __apply_to_page_range+0x2fe/0x7a0 [ 0.663440] [<0002f3284cbc9e88>] apply_to_page_range+0x28/0x40 [ 0.663442] [<0002f3284ccebf12>] kasan_populate_vmalloc+0x82/0xa0 [ 0.663445] [<0002f3284cc1578c>] alloc_vmap_area+0x34c/0xc10 [ 0.663448] [<0002f3284cc1c2a6>] __get_vm_area_node+0x186/0x2a0 [ 0.663451] [<0002f3284cc1e696>] __vmalloc_node_range_noprof+0x116/0x310 [ 0.663454] [<0002f3284cc1d950>] __vmalloc_node_noprof+0xd0/0x110 [ 0.663457] [<0002f3284c454b88>] alloc_thread_stack_node+0xf8/0x330 [ 0.663460] [<0002f3284c458d56>] dup_task_struct+0x66/0x4d0 [ 0.663463] [<0002f3284c45be90>] copy_process+0x280/0x4b90 [ 0.663465] [<0002f3284c460940>] kernel_clone+0xd0/0x4b0 [ 0.663467] [<0002f3284c46115e>] kernel_thread+0xbe/0xe0 [ 0.663469] [<0002f3284c4e440e>] kthreadd+0x50e/0x7f0 [ 0.663472] [<0002f3284c38c04a>] __ret_from_fork+0x8a/0xf0 [ 0.663475] [<0002f3284ed57ff2>] ret_from_fork+0xa/0x38 Instead of allocating single pages per-PTE, bulk-allocate the shadow memory prior to applying kasan_populate_vmalloc_pte() callback on a page range. Link: https://lkml.kernel.org/r/c61d3560297c93ed044f0b1af085610353a06a58.17473169… Fixes: 3c5c3cfb9ef4 ("kasan: support backing vmalloc space with real shadow memory") Signed-off-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Suggested-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Reviewed-by: Harry Yoo <harry.yoo(a)oracle.com> Cc: Daniel Axtens <dja(a)axtens.net> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 88d1c9dcb507..d2c70cd2afb1 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -292,33 +292,99 @@ void __init __weak kasan_populate_early_vm_area_shadow(void *start, { } +struct vmalloc_populate_data { + unsigned long start; + struct page **pages; +}; + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, - void *unused) + void *_data) { - unsigned long page; + struct vmalloc_populate_data *data = _data; + struct page *page; pte_t pte; + int index; if (likely(!pte_none(ptep_get(ptep)))) return 0; - page = __get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - __memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); - pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + index = PFN_DOWN(addr - data->start); + page = data->pages[index]; + __memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL); spin_lock(&init_mm.page_table_lock); if (likely(pte_none(ptep_get(ptep)))) { set_pte_at(&init_mm, addr, ptep, pte); - page = 0; + data->pages[index] = NULL; } spin_unlock(&init_mm.page_table_lock); - if (page) - free_page(page); + return 0; } +static void ___free_pages_bulk(struct page **pages, int nr_pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + if (pages[i]) { + __free_pages(pages[i], 0); + pages[i] = NULL; + } + } +} + +static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +{ + unsigned long nr_populated, nr_total = nr_pages; + struct page **page_array = pages; + + while (nr_pages) { + nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + if (!nr_populated) { + ___free_pages_bulk(page_array, nr_total - nr_pages); + return -ENOMEM; + } + pages += nr_populated; + nr_pages -= nr_populated; + } + + return 0; +} + +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +{ + unsigned long nr_pages, nr_total = PFN_UP(end - start); + struct vmalloc_populate_data data; + int ret = 0; + + data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!data.pages) + return -ENOMEM; + + while (nr_total) { + nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); + ret = ___alloc_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + data.start = start; + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, + kasan_populate_vmalloc_pte, &data); + ___free_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + start += nr_pages * PAGE_SIZE; + nr_total -= nr_pages; + } + + free_page((unsigned long)data.pages); + + return ret; +} + int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; @@ -348,9 +414,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = apply_to_page_range(&init_mm, shadow_start, - shadow_end - shadow_start, - kasan_populate_vmalloc_pte, NULL); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end); if (ret) return ret;

1 month

1
0
0 0

FAILED: patch "[PATCH] kasan: avoid sleepable page allocation from atomic context" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-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-6.6.y git checkout FETCH_HEAD git cherry-pick -x b6ea95a34cbd014ab6ade4248107b86b0aaf2d6c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052639-retold-smuggling-fedb@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b6ea95a34cbd014ab6ade4248107b86b0aaf2d6c Mon Sep 17 00:00:00 2001 From: Alexander Gordeev <agordeev(a)linux.ibm.com> Date: Thu, 15 May 2025 15:55:38 +0200 Subject: [PATCH] kasan: avoid sleepable page allocation from atomic context apply_to_pte_range() enters the lazy MMU mode and then invokes kasan_populate_vmalloc_pte() callback on each page table walk iteration. However, the callback can go into sleep when trying to allocate a single page, e.g. if an architecutre disables preemption on lazy MMU mode enter. On s390 if make arch_enter_lazy_mmu_mode() -> preempt_enable() and arch_leave_lazy_mmu_mode() -> preempt_disable(), such crash occurs: [ 0.663336] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:321 [ 0.663348] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd [ 0.663358] preempt_count: 1, expected: 0 [ 0.663366] RCU nest depth: 0, expected: 0 [ 0.663375] no locks held by kthreadd/2. [ 0.663383] Preemption disabled at: [ 0.663386] [<0002f3284cbb4eda>] apply_to_pte_range+0xfa/0x4a0 [ 0.663405] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.15.0-rc5-gcc-kasan-00043-gd76bb1ebb558-dirty #162 PREEMPT [ 0.663408] Hardware name: IBM 3931 A01 701 (KVM/Linux) [ 0.663409] Call Trace: [ 0.663410] [<0002f3284c385f58>] dump_stack_lvl+0xe8/0x140 [ 0.663413] [<0002f3284c507b9e>] __might_resched+0x66e/0x700 [ 0.663415] [<0002f3284cc4f6c0>] __alloc_frozen_pages_noprof+0x370/0x4b0 [ 0.663419] [<0002f3284ccc73c0>] alloc_pages_mpol+0x1a0/0x4a0 [ 0.663421] [<0002f3284ccc8518>] alloc_frozen_pages_noprof+0x88/0xc0 [ 0.663424] [<0002f3284ccc8572>] alloc_pages_noprof+0x22/0x120 [ 0.663427] [<0002f3284cc341ac>] get_free_pages_noprof+0x2c/0xc0 [ 0.663429] [<0002f3284cceba70>] kasan_populate_vmalloc_pte+0x50/0x120 [ 0.663433] [<0002f3284cbb4ef8>] apply_to_pte_range+0x118/0x4a0 [ 0.663435] [<0002f3284cbc7c14>] apply_to_pmd_range+0x194/0x3e0 [ 0.663437] [<0002f3284cbc99be>] __apply_to_page_range+0x2fe/0x7a0 [ 0.663440] [<0002f3284cbc9e88>] apply_to_page_range+0x28/0x40 [ 0.663442] [<0002f3284ccebf12>] kasan_populate_vmalloc+0x82/0xa0 [ 0.663445] [<0002f3284cc1578c>] alloc_vmap_area+0x34c/0xc10 [ 0.663448] [<0002f3284cc1c2a6>] __get_vm_area_node+0x186/0x2a0 [ 0.663451] [<0002f3284cc1e696>] __vmalloc_node_range_noprof+0x116/0x310 [ 0.663454] [<0002f3284cc1d950>] __vmalloc_node_noprof+0xd0/0x110 [ 0.663457] [<0002f3284c454b88>] alloc_thread_stack_node+0xf8/0x330 [ 0.663460] [<0002f3284c458d56>] dup_task_struct+0x66/0x4d0 [ 0.663463] [<0002f3284c45be90>] copy_process+0x280/0x4b90 [ 0.663465] [<0002f3284c460940>] kernel_clone+0xd0/0x4b0 [ 0.663467] [<0002f3284c46115e>] kernel_thread+0xbe/0xe0 [ 0.663469] [<0002f3284c4e440e>] kthreadd+0x50e/0x7f0 [ 0.663472] [<0002f3284c38c04a>] __ret_from_fork+0x8a/0xf0 [ 0.663475] [<0002f3284ed57ff2>] ret_from_fork+0xa/0x38 Instead of allocating single pages per-PTE, bulk-allocate the shadow memory prior to applying kasan_populate_vmalloc_pte() callback on a page range. Link: https://lkml.kernel.org/r/c61d3560297c93ed044f0b1af085610353a06a58.17473169… Fixes: 3c5c3cfb9ef4 ("kasan: support backing vmalloc space with real shadow memory") Signed-off-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Suggested-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Reviewed-by: Harry Yoo <harry.yoo(a)oracle.com> Cc: Daniel Axtens <dja(a)axtens.net> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 88d1c9dcb507..d2c70cd2afb1 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -292,33 +292,99 @@ void __init __weak kasan_populate_early_vm_area_shadow(void *start, { } +struct vmalloc_populate_data { + unsigned long start; + struct page **pages; +}; + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, - void *unused) + void *_data) { - unsigned long page; + struct vmalloc_populate_data *data = _data; + struct page *page; pte_t pte; + int index; if (likely(!pte_none(ptep_get(ptep)))) return 0; - page = __get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - __memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); - pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + index = PFN_DOWN(addr - data->start); + page = data->pages[index]; + __memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL); spin_lock(&init_mm.page_table_lock); if (likely(pte_none(ptep_get(ptep)))) { set_pte_at(&init_mm, addr, ptep, pte); - page = 0; + data->pages[index] = NULL; } spin_unlock(&init_mm.page_table_lock); - if (page) - free_page(page); + return 0; } +static void ___free_pages_bulk(struct page **pages, int nr_pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + if (pages[i]) { + __free_pages(pages[i], 0); + pages[i] = NULL; + } + } +} + +static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +{ + unsigned long nr_populated, nr_total = nr_pages; + struct page **page_array = pages; + + while (nr_pages) { + nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + if (!nr_populated) { + ___free_pages_bulk(page_array, nr_total - nr_pages); + return -ENOMEM; + } + pages += nr_populated; + nr_pages -= nr_populated; + } + + return 0; +} + +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +{ + unsigned long nr_pages, nr_total = PFN_UP(end - start); + struct vmalloc_populate_data data; + int ret = 0; + + data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!data.pages) + return -ENOMEM; + + while (nr_total) { + nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); + ret = ___alloc_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + data.start = start; + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, + kasan_populate_vmalloc_pte, &data); + ___free_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + start += nr_pages * PAGE_SIZE; + nr_total -= nr_pages; + } + + free_page((unsigned long)data.pages); + + return ret; +} + int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; @@ -348,9 +414,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = apply_to_page_range(&init_mm, shadow_start, - shadow_end - shadow_start, - kasan_populate_vmalloc_pte, NULL); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end); if (ret) return ret;

1 month

1
0
0 0

[PATCH v2] mac80211: Add null pointer check for ieee80211_link_get_chanctx()

by Wentao Liang

The function ieee80211_chsw_switch_vifs() calls the function ieee80211_link_get_chanctx(), but does not check its return value. The return value is a null pointer if the ieee80211_link_get_chanctx() fails. This will lead to a null pointer dereference in the following code "&old_ctx->conf". A proper implementation can be found in ieee80211_link_use_reserved_assign(). Add a null pointer check and goto error handling path if the function fails. Fixes: 5d52ee811019 ("mac80211: allow reservation of a running chanctx") Cc: stable(a)vger.kernel.org # v3.16 Signed-off-by: Wentao Liang <vulab(a)iscas.ac.cn> --- v2: Fix code error. net/mac80211/chan.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index a442cb667520..c9b703c283e7 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1503,6 +1503,10 @@ static int ieee80211_chsw_switch_vifs(struct ieee80211_local *local, continue; old_ctx = ieee80211_link_get_chanctx(link); + if (WARN_ON(!old_ctx)) { + err = -EINVAL; + goto out; + } vif_chsw[i].vif = &link->sdata->vif; vif_chsw[i].old_ctx = &old_ctx->conf; vif_chsw[i].new_ctx = &ctx->conf; -- 2.42.0.windows.2

1 month

3
5
0 0

[PATCH] mtd: nand: sunxi: Add randomizer configuration in sunxi_nfc_hw_ecc_write_chunk

by Wentao Liang

The function sunxi_nfc_hw_ecc_write_chunk() calls the sunxi_nfc_hw_ecc_write_chunk(), but does not call the configuration function sunxi_nfc_randomizer_config(). Consequently, the randomization might not conduct correctly, which will affect the lifespan of NAND flash. A proper implementation can be found in sunxi_nfc_hw_ecc_write_page_dma(). Add the sunxi_nfc_randomizer_config() to config randomizer. Fixes: 4be4e03efc7f ("mtd: nand: sunxi: add randomizer support") Cc: stable(a)vger.kernel.org # v4.6 Signed-off-by: Wentao Liang <vulab(a)iscas.ac.cn> --- drivers/mtd/nand/raw/sunxi_nand.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c index 9179719f639e..162cd5f4f234 100644 --- a/drivers/mtd/nand/raw/sunxi_nand.c +++ b/drivers/mtd/nand/raw/sunxi_nand.c @@ -1050,6 +1050,7 @@ static int sunxi_nfc_hw_ecc_write_chunk(struct nand_chip *nand, if (ret) return ret; + sunxi_nfc_randomizer_config(nand, page, false); sunxi_nfc_randomizer_enable(nand); sunxi_nfc_hw_ecc_set_prot_oob_bytes(nand, oob, 0, bbm, page); -- 2.42.0.windows.2

1 month

2
2
0 0

[PATCH] bus: fsl-mc: Fix an API misuse in fsl_mc_device_add()

by Haoxiang Li

In fsl_mc_device_add(), use put_device() to give up the device reference instead of kfree(). Fixes: bbf9d17d9875 ("staging: fsl-mc: Freescale Management Complex (fsl-mc) bus driver") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <haoxiang_li2024(a)163.com> --- drivers/bus/fsl-mc/fsl-mc-bus.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index a8be8cf246fb..dfd79ecf65b6 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -905,9 +905,7 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc, return 0; error_cleanup_dev: - kfree(mc_dev->regions); - kfree(mc_bus); - kfree(mc_dev); + put_device(&mc_dev->dev); return error; } -- 2.25.1

1 month

2
1
0 0

[PATCH] mac80211: Add null pointer check for ieee80211_link_get_chanctx()

by Wentao Liang

The function ieee80211_chsw_switch_vifs() calls the function ieee80211_link_get_chanctx(), but does not check its return value. The return value is a null pointer if the ieee80211_link_get_chanctx() fails. This will lead to a null pointer dereference in the following code "&old_ctx->conf". A proper implementation can be found in ieee80211_link_use_reserved_assign(). Add a null pointer check and goto error handling path if the function fails. Fixes: 5d52ee811019 ("mac80211: allow reservation of a running chanctx") Cc: stable(a)vger.kernel.org # v3.16 Signed-off-by: Wentao Liang <vulab(a)iscas.ac.cn> --- net/mac80211/chan.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index a442cb667520..9e6235001e0a 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1503,6 +1503,10 @@ static int ieee80211_chsw_switch_vifs(struct ieee80211_local *local, continue; old_ctx = ieee80211_link_get_chanctx(link); + if (WARN_ON(old_ctx)) { + err = -EINVAL; + goto out; + } vif_chsw[i].vif = &link->sdata->vif; vif_chsw[i].old_ctx = &old_ctx->conf; vif_chsw[i].new_ctx = &ctx->conf; -- 2.42.0.windows.2

1 month

2
1
0 0

IPC drop down on AMD epyc 7702P

by Jean-Baptiste Roquefere

Hi, We (Ateme, a video encoding company) may have found an unwanted behavior in the scheduler since 5.10 (commit 16b0a7a1a0af), then 5.16 (commit c5b0a7eefc70), then 5.19 (commit not found yet), then maybe some other commits from 5.19 to 6.12, with a consequence of IPC decrease. Problem still appears on lasts 6.12, 6.13 and 6.14 We have reverted both 16b0a7a1a0af and c5b0a7eefc70 commits that reduce our performances (see fair.patch attached, applicable on 6.12.17). Performances increase but still doesnt reach our reference on 5.4.152. Instead of trying to find every single commits from 5.18 to 6.12 that could decrease our performance, I chosed to bench 5.4.152 versus 6.12.17 with and without fair.patch. The problem appeared clear : a lot of CPU migrations go out of CCX, then L3 miss, then IPC decrease. Context of our bench: video decoder which work at a regulated speed, 1 process, 21 main threads, everyone of them creates 10 threads, 8 of them have a fine granularity, meaning they go to sleep quite often, giving the scheduler a lot of opportunities to act). Hardware is an AMD Epyc 7702P, 128 cores, grouped by shared LLC 4 cores +4 hyperthreaded cores. NUMA topology is set by the BIOS to 1 node per socket. Every pthread are created with default attributes. I use AMDuProf (-C -A system -a -m ipc,l1,l2,l3,memory) for CPU Utilization (%), CPU effective freq, IPC, L2 access (pti), L2 miss (pti), L3 miss (absolute) and Mem (GB/s, and perf (stat -d -d -d -a) for Context switches, CPU migrations and Real time (s). We noted that upgrade 5.4.152 to 6.12.17 without any special preempt configuration : Two fold increase in CPU migration 30% memory bandwidth increase 20% L3 cache misses increase 10% IPC decrease With the attached fair.patch applied to 6.12.17 (reminder : this patch reverts one commit appeared in 5.10 and another in 5.16) we managed to reduce CPU migrations and increase IPC but not as much as we had on 5.4.152. Our goal is to keep kernel "clean" without any patch (we don't want to apply and maintain fair.patch) then for the rest of my email we will consider stock kernel 6.12.17. I've reduced the "sub threads count" to stays below 128 threads. Then still 21 main threads and instead of 10 worker per main thread I set 5 workers (4 of them with fine granularity) giving 105 pthreads -> everything goes fine in 6.12.17, no extra CPU migration, no extra memory bandwidth... But as soon as we increase worker threads count (10 instead of 5) the problem appears. We know our decoder may have too many threads but that's out of our scope, it has been designed like that some years ago and moving from "lot of small threads to few of big thread" is for now not possible. We have a work around : we group threads using pthread affinities. Every main thread (and by inheritance of affinities every worker threads) on a single CCX so we reduce the L3 miss for them, then decrease memory bandwidth, then finally increasing IPC. With that solution, we go above our original performances, for both kernels, and they perform at the same level. However, it is impractical to productize as such. I've tried many kernel build configurations (CONFIG_PREMPT_*, CONFIG_SCHEDULER_*, tuning of fair.c:sysctl_sched_migration_cost) on 6.12.17, 6.12.21 (longterm), 6.13.9 (mainline), and 6.14.0 Nothing changes. Q: Is there anyway to tune the kernel so we can get our performance back without using the pthread affinities work around ? Feel free to ask an archive containing binaries and payload. I first posted on https://bugzilla.kernel.org/show_bug.cgi?id=220000 but one told me the best way to get answers where these mailing lists Regards, Jean-Baptiste Roquefere, Ateme Attached bench.tar.gz : * bench/fair.patch * bench/bench.ods with 2 sheets : - regulated : decoder speed is regulated to keep real time constant - no regul : decoder speed is not regulated and uses from 1 to 76 main threads with 10 worker per main thread * bench/regulated.csv : bench.ods:regulated exported in csv format * bench/not-regulated : bench.ods:no regul exported in csv format

1 month

5
15
0 0

[PATCH v3 1/2] iio: adc: max1363: Fix MAX1363_4X_CHANS/MAX1363_8X_CHANS[]

by Fabio Estevam

From: Fabio Estevam <festevam(a)denx.de> Since commit 2718f15403fb ("iio: sanity check available_scan_masks array"), booting a board populated with a MAX11601 results in a flood of warnings: max1363 1-0064: available_scan_mask 8 subset of 0. Never used max1363 1-0064: available_scan_mask 9 subset of 0. Never used max1363 1-0064: available_scan_mask 10 subset of 0. Never used max1363 1-0064: available_scan_mask 11 subset of 0. Never used max1363 1-0064: available_scan_mask 12 subset of 0. Never used max1363 1-0064: available_scan_mask 13 subset of 0. Never used ... These warnings are caused by incorrect offsets used for differential channels in the MAX1363_4X_CHANS() and MAX1363_8X_CHANS() macros. The max1363_mode_table[] defines the differential channel mappings as follows: MAX1363_MODE_DIFF_SINGLE(0, 1, 1 << 12), MAX1363_MODE_DIFF_SINGLE(2, 3, 1 << 13), MAX1363_MODE_DIFF_SINGLE(4, 5, 1 << 14), MAX1363_MODE_DIFF_SINGLE(6, 7, 1 << 15), MAX1363_MODE_DIFF_SINGLE(8, 9, 1 << 16), MAX1363_MODE_DIFF_SINGLE(10, 11, 1 << 17), MAX1363_MODE_DIFF_SINGLE(1, 0, 1 << 18), MAX1363_MODE_DIFF_SINGLE(3, 2, 1 << 19), MAX1363_MODE_DIFF_SINGLE(5, 4, 1 << 20), MAX1363_MODE_DIFF_SINGLE(7, 6, 1 << 21), MAX1363_MODE_DIFF_SINGLE(9, 8, 1 << 22), MAX1363_MODE_DIFF_SINGLE(11, 10, 1 << 23), Update the macros to follow this same pattern, ensuring that the scan masks are valid and preventing the warnings. Cc: <stable(a)vger.kernel.org> #6.12 Suggested-by: Jonathan Cameron <jic23(a)kernel.org> Signed-off-by: Fabio Estevam <festevam(a)denx.de> --- Changes since v2: - Removed incorrect Fixes: tag (Matti) Changes since v1: - Fix the problem by changing the MAX1363_4X_CHANS() and MAX1363_8X_CHANS() macros. (Jonathan) drivers/iio/adc/max1363.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c index a7e9912fb44a..bc44b4604ef4 100644 --- a/drivers/iio/adc/max1363.c +++ b/drivers/iio/adc/max1363.c @@ -511,10 +511,10 @@ static const struct iio_event_spec max1363_events[] = { MAX1363_CHAN_U(1, _s1, 1, bits, ev_spec, num_ev_spec), \ MAX1363_CHAN_U(2, _s2, 2, bits, ev_spec, num_ev_spec), \ MAX1363_CHAN_U(3, _s3, 3, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(0, 1, d0m1, 4, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(2, 3, d2m3, 5, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(1, 0, d1m0, 6, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(3, 2, d3m2, 7, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(0, 1, d0m1, 12, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(2, 3, d2m3, 13, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(1, 0, d1m0, 18, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(3, 2, d3m2, 19, bits, ev_spec, num_ev_spec), \ IIO_CHAN_SOFT_TIMESTAMP(8) \ } @@ -609,14 +609,14 @@ static const enum max1363_modes max11608_mode_list[] = { MAX1363_CHAN_U(5, _s5, 5, bits, NULL, 0), \ MAX1363_CHAN_U(6, _s6, 6, bits, NULL, 0), \ MAX1363_CHAN_U(7, _s7, 7, bits, NULL, 0), \ - MAX1363_CHAN_B(0, 1, d0m1, 8, bits, NULL, 0), \ - MAX1363_CHAN_B(2, 3, d2m3, 9, bits, NULL, 0), \ - MAX1363_CHAN_B(4, 5, d4m5, 10, bits, NULL, 0), \ - MAX1363_CHAN_B(6, 7, d6m7, 11, bits, NULL, 0), \ - MAX1363_CHAN_B(1, 0, d1m0, 12, bits, NULL, 0), \ - MAX1363_CHAN_B(3, 2, d3m2, 13, bits, NULL, 0), \ - MAX1363_CHAN_B(5, 4, d5m4, 14, bits, NULL, 0), \ - MAX1363_CHAN_B(7, 6, d7m6, 15, bits, NULL, 0), \ + MAX1363_CHAN_B(0, 1, d0m1, 12, bits, NULL, 0), \ + MAX1363_CHAN_B(2, 3, d2m3, 13, bits, NULL, 0), \ + MAX1363_CHAN_B(4, 5, d4m5, 14, bits, NULL, 0), \ + MAX1363_CHAN_B(6, 7, d6m7, 15, bits, NULL, 0), \ + MAX1363_CHAN_B(1, 0, d1m0, 18, bits, NULL, 0), \ + MAX1363_CHAN_B(3, 2, d3m2, 19, bits, NULL, 0), \ + MAX1363_CHAN_B(5, 4, d5m4, 20, bits, NULL, 0), \ + MAX1363_CHAN_B(7, 6, d7m6, 21, bits, NULL, 0), \ IIO_CHAN_SOFT_TIMESTAMP(16) \ } static const struct iio_chan_spec max11602_channels[] = MAX1363_8X_CHANS(8); -- 2.34.1

1 month

3
3
0 0

iommu crash when boot kernel 5.15.179 on DELL R7715/AMD 9015

by Wang Yugui

Hi, iommu crash when kernel 5.15.179 boot on DELL R7715/AMD 9015. but kernel 6.1.133/6.6.86 boot well. It is the first time to boot kernel 5.15.y on DELL R7715/AMD 9015, so yet no more info about other 5.15.y kernel version. It seems iommu related, but seems no relationship to 5.15.181 iommu-amd-return-an-error-if-vcpu-affinity-is-set-fo.patch 5.15.182 iommu-amd-fix-potential-buffer-overflow-in-parse_ivrs_acpihid.patch dmesg output: [ 4.658313] Trying to unpack rootfs image as initramfs... [ 4.663349] BUG: kernel NULL pointer dereference, address: 0000000000000030 [ 4.664346] #PF: supervisor read access in kernel mode [ 4.664346] #PF: error_code(0x0000) - not-present page [ 4.664346] PGD 0 [ 4.664346] Oops: 0000 [#1] SMP NOPTI [ 4.664346] CPU: 8 PID: 1 Comm: swapper/0 Not tainted 5.15.179-1.el9.x86_64 #1 [ 4.664346] Hardware name: Dell Inc. PowerEdge R7715/0KRFPX, BIOS 1.1.2 02/20/2025 [ 4.664346] RIP: 0010:sysfs_add_link_to_group+0x12/0x60 [ 4.664346] Code: cb ff ff 48 89 ef 5d 41 5c e9 ca b4 ff ff 5d 41 5c c3 cc cc cc cc 66 90 0f 1f 44 00 00 41 55 49 89 cd 41 54 49 89 d4 31 d2 55 <48> 8b 7f 30 e8 a5 b2 ff ff 48 85 c0 74 29 48 89 c5 4c 89 e6 48 89 [ 4.664346] RSP: 0018:ff3f20b800047c28 EFLAGS: 00010246 [ 4.664346] RAX: 0000000000000001 RBX: ff25a0fc800530a8 RCX: ff25a0fc82cdb410 [ 4.664346] RDX: 0000000000000000 RSI: ffffffff904726e7 RDI: 0000000000000000 [ 4.664346] RBP: ff25a0fc801320d0 R08: ff3f20b800047d00 R09: ff3f20b800047d00 [ 4.664346] R10: 0720072007200720 R11: 0720072007200720 R12: ff25a0fc801320d0 [ 4.664346] R13: ff25a0fc82cdb410 R14: ff3f20b800047d00 R15: 0000000000000000 [ 4.664346] FS: 0000000000000000(0000) GS:ff25a10c1d400000(0000) knlGS:0000000000000000 [ 4.664346] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4.664346] CR2: 0000000000000030 CR3: 0000001036a10001 CR4: 0000000000771ee0 [ 4.664346] PKRU: 55555554 [ 4.664346] Call Trace: [ 4.664346] <TASK> [ 4.664346] ? show_trace_log_lvl+0x1c1/0x2d9 [ 4.664346] ? show_trace_log_lvl+0x1c1/0x2d9 [ 4.664346] ? iommu_device_link+0x3f/0xb0 [ 4.664346] ? __die_body.cold+0x8/0xd [ 4.664346] ? page_fault_oops+0xac/0x140 [ 4.664346] ? exc_page_fault+0x62/0x130 [ 4.664346] ? asm_exc_page_fault+0x22/0x30 [ 4.664346] ? sysfs_add_link_to_group+0x12/0x60 [ 4.664346] iommu_device_link+0x3f/0xb0 [ 4.664346] __iommu_probe_device+0x188/0x260 [ 4.664346] ? __iommu_probe_device+0x260/0x260 [ 4.664346] probe_iommu_group+0x31/0x40 [ 4.664346] bus_for_each_dev+0x75/0xc0 [ 4.664346] bus_iommu_probe+0x48/0x2c0 [ 4.664346] ? kmem_cache_alloc_trace+0x165/0x290 [ 4.664346] ? __cond_resched+0x16/0x50 [ 4.664346] bus_set_iommu+0x8c/0xe0 [ 4.664346] amd_iommu_init_api+0x18/0x34 [ 4.664346] amd_iommu_init_pci+0x56/0x21c [ 4.664346] ? e820__memblock_setup+0x7d/0x7d [ 4.664346] state_next+0x19a/0x2d4 [ 4.664346] ? blake2s_update+0x48/0xc0 [ 4.664346] ? e820__memblock_setup+0x7d/0x7d [ 4.664346] iommu_go_to_state+0x24/0x2c [ 4.664346] amd_iommu_init+0xf/0x29 [ 4.664346] pci_iommu_init+0x16/0x43 [ 4.664346] do_one_initcall+0x41/0x1d0 [ 4.664346] do_initcalls+0xc6/0xdf [ 4.664346] kernel_init_freeable+0x14e/0x19d [ 4.664346] ? rest_init+0xc0/0xc0 [ 4.664346] kernel_init+0x16/0x130 [ 4.664346] ret_from_fork+0x1f/0x30 [ 4.664346] </TASK> [ 4.664346] Modules linked in: [ 4.664346] CR2: 0000000000000030 [ 4.664346] ---[ end trace 9672514da279163d ]--- [ 4.664346] RIP: 0010:sysfs_add_link_to_group+0x12/0x60 [ 4.664346] Code: cb ff ff 48 89 ef 5d 41 5c e9 ca b4 ff ff 5d 41 5c c3 cc cc cc cc 66 90 0f 1f 44 00 00 41 55 49 89 cd 41 54 49 89 d4 31 d2 55 <48> 8b 7f 30 e8 a5 b2 ff ff 48 85 c0 74 29 48 89 c5 4c 89 e6 48 89 [ 4.664346] RSP: 0018:ff3f20b800047c28 EFLAGS: 00010246 [ 4.664346] RAX: 0000000000000001 RBX: ff25a0fc800530a8 RCX: ff25a0fc82cdb410 [ 4.664346] RDX: 0000000000000000 RSI: ffffffff904726e7 RDI: 0000000000000000 [ 4.664346] RBP: ff25a0fc801320d0 R08: ff3f20b800047d00 R09: ff3f20b800047d00 [ 4.664346] R10: 0720072007200720 R11: 0720072007200720 R12: ff25a0fc801320d0 [ 4.664346] R13: ff25a0fc82cdb410 R14: ff3f20b800047d00 R15: 0000000000000000 [ 4.664346] FS: 0000000000000000(0000) GS:ff25a10c1d400000(0000) knlGS:0000000000000000 [ 4.664346] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4.664346] CR2: 0000000000000030 CR3: 0000001036a10001 CR4: 0000000000771ee0 [ 4.664346] PKRU: 55555554 [ 4.664346] Kernel panic - not syncing: Fatal exception [ 4.664346] Rebooting in 15 seconds.. Best Regards Wang Yugui (wangyugui(a)e16-tech.com) 2025/05/18

1 month

2
2
0 0

[PATCH] x86/pmem: Fix a null pointer dereference in register_e820_pmem()

by Haoxiang Li

Add check for the return value of platform_device_alloc() to prevent null pointer dereference. Fixes: 7a67832c7e44 ("libnvdimm, e820: make CONFIG_X86_PMEM_LEGACY a tristate option") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <haoxiang_li2024(a)163.com> --- arch/x86/kernel/pmem.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 23154d24b117..04fb221716ff 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -27,6 +27,8 @@ static __init int register_e820_pmem(void) * simply here to trigger the module to load on demand. */ pdev = platform_device_alloc("e820_pmem", -1); + if (!pdev) + return -ENOMEM; rc = platform_device_add(pdev); if (rc) -- 2.25.1

1 month

1
0
0 0

[PATCH] rust: compile libcore with edition 2024 for 1.87+

by Gary Guo

Rust 1.87 (released on 2025-05-15) compiles core library with edition 2024 instead of 2021 [1]. Ensure that the edition matches libcore's expectation to avoid potential breakage. Cc: stable(a)vger.kernel.org # Needed in 6.12.y and later (Rust is pinned in older LTSs). Link: https://github.com/rust-lang/rust/pull/138162 [1] Closes: https://github.com/Rust-for-Linux/linux/issues/1163 Signed-off-by: Gary Guo <gary(a)garyguo.net> --- rust/Makefile | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/rust/Makefile b/rust/Makefile index 3aca903a7d08..9e7f1ec06181 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -60,6 +60,12 @@ endif core-cfgs = \ --cfg no_fp_fmt_parse +ifeq ($(call rustc-min-version,108700),y) +core-cfgs += --edition=2024 +else +core-cfgs += --edition=2021 +endif + # `rustc` recognizes `--remap-path-prefix` since 1.26.0, but `rustdoc` only # since Rust 1.81.0. Moreover, `rustdoc` ICEs on out-of-tree builds since Rust # 1.82.0 (https://github.com/rust-lang/rust/issues/138520). Thus workaround both @@ -106,7 +112,7 @@ rustdoc-macros: $(src)/macros/lib.rs FORCE # Starting with Rust 1.82.0, skipping `-Wrustdoc::unescaped_backticks` should # not be needed -- see https://github.com/rust-lang/rust/pull/128307. -rustdoc-core: private skip_flags = -Wrustdoc::unescaped_backticks +rustdoc-core: private skip_flags = -Wrustdoc::unescaped_backticks --edition=2021 rustdoc-core: private rustc_target_flags = $(core-cfgs) rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE +$(call if_changed,rustdoc) @@ -416,7 +422,7 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L cmd_rustc_library = \ OBJTREE=$(abspath $(objtree)) \ $(if $(skip_clippy),$(RUSTC),$(RUSTC_OR_CLIPPY)) \ - $(filter-out $(skip_flags),$(rust_flags) $(rustc_target_flags)) \ + $(filter-out $(skip_flags),$(rust_flags)) $(rustc_target_flags) \ --emit=dep-info=$(depfile) --emit=obj=$@ \ --emit=metadata=$(dir $@)$(patsubst %.o,lib%.rmeta,$(notdir $@)) \ --crate-type rlib -L$(objtree)/$(obj) \ @@ -483,7 +489,7 @@ $(obj)/helpers/helpers.o: $(src)/helpers/helpers.c $(recordmcount_source) FORCE $(obj)/exports.o: private skip_gendwarfksyms = 1 $(obj)/core.o: private skip_clippy = 1 -$(obj)/core.o: private skip_flags = -Wunreachable_pub +$(obj)/core.o: private skip_flags = -Wunreachable_pub --edition=2021 $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym)) $(obj)/core.o: private rustc_target_flags = $(core-cfgs) $(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs \ base-commit: 172a9d94339cea832d89630b89d314e41d622bd8 -- 2.47.2

1 month

3
3
0 0

[PATCH v2 1/2] iio: adc: max1363: Fix MAX1363_4X_CHANS/MAX1363_8X_CHANS[]

by Fabio Estevam

From: Fabio Estevam <festevam(a)denx.de> Since commit 2718f15403fb ("iio: sanity check available_scan_masks array"), booting a board populated with a MAX11601 results in a flood of warnings: max1363 1-0064: available_scan_mask 8 subset of 0. Never used max1363 1-0064: available_scan_mask 9 subset of 0. Never used max1363 1-0064: available_scan_mask 10 subset of 0. Never used max1363 1-0064: available_scan_mask 11 subset of 0. Never used max1363 1-0064: available_scan_mask 12 subset of 0. Never used max1363 1-0064: available_scan_mask 13 subset of 0. Never used ... These warnings are caused by incorrect offsets used for differential channels in the MAX1363_4X_CHANS() and MAX1363_8X_CHANS() macros. The max1363_mode_table[] defines the differential channel mappings as follows: MAX1363_MODE_DIFF_SINGLE(0, 1, 1 << 12), MAX1363_MODE_DIFF_SINGLE(2, 3, 1 << 13), MAX1363_MODE_DIFF_SINGLE(4, 5, 1 << 14), MAX1363_MODE_DIFF_SINGLE(6, 7, 1 << 15), MAX1363_MODE_DIFF_SINGLE(8, 9, 1 << 16), MAX1363_MODE_DIFF_SINGLE(10, 11, 1 << 17), MAX1363_MODE_DIFF_SINGLE(1, 0, 1 << 18), MAX1363_MODE_DIFF_SINGLE(3, 2, 1 << 19), MAX1363_MODE_DIFF_SINGLE(5, 4, 1 << 20), MAX1363_MODE_DIFF_SINGLE(7, 6, 1 << 21), MAX1363_MODE_DIFF_SINGLE(9, 8, 1 << 22), MAX1363_MODE_DIFF_SINGLE(11, 10, 1 << 23), Update the macros to follow this same pattern, ensuring that the scan masks are valid and preventing the warnings. Cc: stable(a)vger.kernel.org Fixes: 2718f15403fb ("iio: sanity check available_scan_masks array") Suggested-by: Jonathan Cameron <jic23(a)kernel.org> Signed-off-by: Fabio Estevam <festevam(a)denx.de> --- Changes since v1: - Fix the problem by changing the MAX1363_4X_CHANS() and MAX1363_8X_CHANS() macros. (Jonathan) drivers/iio/adc/max1363.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c index a7e9912fb44a..bc44b4604ef4 100644 --- a/drivers/iio/adc/max1363.c +++ b/drivers/iio/adc/max1363.c @@ -511,10 +511,10 @@ static const struct iio_event_spec max1363_events[] = { MAX1363_CHAN_U(1, _s1, 1, bits, ev_spec, num_ev_spec), \ MAX1363_CHAN_U(2, _s2, 2, bits, ev_spec, num_ev_spec), \ MAX1363_CHAN_U(3, _s3, 3, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(0, 1, d0m1, 4, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(2, 3, d2m3, 5, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(1, 0, d1m0, 6, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(3, 2, d3m2, 7, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(0, 1, d0m1, 12, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(2, 3, d2m3, 13, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(1, 0, d1m0, 18, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(3, 2, d3m2, 19, bits, ev_spec, num_ev_spec), \ IIO_CHAN_SOFT_TIMESTAMP(8) \ } @@ -609,14 +609,14 @@ static const enum max1363_modes max11608_mode_list[] = { MAX1363_CHAN_U(5, _s5, 5, bits, NULL, 0), \ MAX1363_CHAN_U(6, _s6, 6, bits, NULL, 0), \ MAX1363_CHAN_U(7, _s7, 7, bits, NULL, 0), \ - MAX1363_CHAN_B(0, 1, d0m1, 8, bits, NULL, 0), \ - MAX1363_CHAN_B(2, 3, d2m3, 9, bits, NULL, 0), \ - MAX1363_CHAN_B(4, 5, d4m5, 10, bits, NULL, 0), \ - MAX1363_CHAN_B(6, 7, d6m7, 11, bits, NULL, 0), \ - MAX1363_CHAN_B(1, 0, d1m0, 12, bits, NULL, 0), \ - MAX1363_CHAN_B(3, 2, d3m2, 13, bits, NULL, 0), \ - MAX1363_CHAN_B(5, 4, d5m4, 14, bits, NULL, 0), \ - MAX1363_CHAN_B(7, 6, d7m6, 15, bits, NULL, 0), \ + MAX1363_CHAN_B(0, 1, d0m1, 12, bits, NULL, 0), \ + MAX1363_CHAN_B(2, 3, d2m3, 13, bits, NULL, 0), \ + MAX1363_CHAN_B(4, 5, d4m5, 14, bits, NULL, 0), \ + MAX1363_CHAN_B(6, 7, d6m7, 15, bits, NULL, 0), \ + MAX1363_CHAN_B(1, 0, d1m0, 18, bits, NULL, 0), \ + MAX1363_CHAN_B(3, 2, d3m2, 19, bits, NULL, 0), \ + MAX1363_CHAN_B(5, 4, d5m4, 20, bits, NULL, 0), \ + MAX1363_CHAN_B(7, 6, d7m6, 21, bits, NULL, 0), \ IIO_CHAN_SOFT_TIMESTAMP(16) \ } static const struct iio_chan_spec max11602_channels[] = MAX1363_8X_CHANS(8); -- 2.34.1

1 month

3
6
0 0

FAILED: patch "[PATCH] mmc: sdhci-of-dwcmshc: add PD workaround on RK3576" failed to apply to 6.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.14-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-6.14.y git checkout FETCH_HEAD git cherry-pick -x 08f959759e1e6e9c4b898c51a7d387ac3480630b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052516-factsheet-coagulant-3fb0@gregkh' --subject-prefix 'PATCH 6.14.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 08f959759e1e6e9c4b898c51a7d387ac3480630b Mon Sep 17 00:00:00 2001 From: Nicolas Frattaroli <nicolas.frattaroli(a)collabora.com> Date: Wed, 23 Apr 2025 09:53:32 +0200 Subject: [PATCH] mmc: sdhci-of-dwcmshc: add PD workaround on RK3576 RK3576's power domains have a peculiar design where the PD_NVM power domain, of which the sdhci controller is a part, seemingly does not have idempotent runtime disable/enable. The end effect is that if PD_NVM gets turned off by the generic power domain logic because all the devices depending on it are suspended, then the next time the sdhci device is unsuspended, it'll hang the SoC as soon as it tries accessing the CQHCI registers. RK3576's UFS support needed a new dev_pm_genpd_rpm_always_on function added to the generic power domains API to handle what appears to be a similar hardware design. Use this new function to ask for the same treatment in the sdhci controller by giving rk3576 its own platform data with its own postinit function. The benefit of doing this instead of marking the power domains always on in the power domain core is that we only do this if we know the platform we're running on actually uses the sdhci controller. For others, keeping PD_NVM always on would be a waste, as they won't run into this specific issue. The only other IP in PD_NVM that could be affected is FSPI0. If it gets a mainline driver, it will probably want to do the same thing. Acked-by: Adrian Hunter <adrian.hunter(a)intel.com> Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli(a)collabora.com> Reviewed-by: Shawn Lin <shawn.lin(a)rock-chips.com> Fixes: cfee1b507758 ("pmdomain: rockchip: Add support for RK3576 SoC") Cc: <stable(a)vger.kernel.org> # v6.15+ Link: https://lore.kernel.org/r/20250423-rk3576-emmc-fix-v3-1-0bf80e29967f@collab… Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org> diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index 09b9ab15e499..a20d03fdd6a9 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/pm_domain.h> #include <linux/pm_runtime.h> #include <linux/reset.h> #include <linux/sizes.h> @@ -745,6 +746,29 @@ static void dwcmshc_rk35xx_postinit(struct sdhci_host *host, struct dwcmshc_priv } } +static void dwcmshc_rk3576_postinit(struct sdhci_host *host, struct dwcmshc_priv *dwc_priv) +{ + struct device *dev = mmc_dev(host->mmc); + int ret; + + /* + * This works around the design of the RK3576's power domains, which + * makes the PD_NVM power domain, which the sdhci controller on the + * RK3576 is in, never come back the same way once it's run-time + * suspended once. This can happen during early kernel boot if no driver + * is using either PD_NVM or its child power domain PD_SDGMAC for a + * short moment, leading to it being turned off to save power. By + * keeping it on, sdhci suspending won't lead to PD_NVM becoming a + * candidate for getting turned off. + */ + ret = dev_pm_genpd_rpm_always_on(dev, true); + if (ret && ret != -EOPNOTSUPP) + dev_warn(dev, "failed to set PD rpm always on, SoC may hang later: %pe\n", + ERR_PTR(ret)); + + dwcmshc_rk35xx_postinit(host, dwc_priv); +} + static int th1520_execute_tuning(struct sdhci_host *host, u32 opcode) { struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); @@ -1176,6 +1200,18 @@ static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk35xx_pdata = { .postinit = dwcmshc_rk35xx_postinit, }; +static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk3576_pdata = { + .pdata = { + .ops = &sdhci_dwcmshc_rk35xx_ops, + .quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN | + SDHCI_QUIRK_BROKEN_TIMEOUT_VAL, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | + SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN, + }, + .init = dwcmshc_rk35xx_init, + .postinit = dwcmshc_rk3576_postinit, +}; + static const struct dwcmshc_pltfm_data sdhci_dwcmshc_th1520_pdata = { .pdata = { .ops = &sdhci_dwcmshc_th1520_ops, @@ -1274,6 +1310,10 @@ static const struct of_device_id sdhci_dwcmshc_dt_ids[] = { .compatible = "rockchip,rk3588-dwcmshc", .data = &sdhci_dwcmshc_rk35xx_pdata, }, + { + .compatible = "rockchip,rk3576-dwcmshc", + .data = &sdhci_dwcmshc_rk3576_pdata, + }, { .compatible = "rockchip,rk3568-dwcmshc", .data = &sdhci_dwcmshc_rk35xx_pdata,

1 month

1
0
0 0

FAILED: patch "[PATCH] mmc: sdhci-of-dwcmshc: add PD workaround on RK3576" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-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-6.12.y git checkout FETCH_HEAD git cherry-pick -x 08f959759e1e6e9c4b898c51a7d387ac3480630b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052515-headdress-overcome-c741@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 08f959759e1e6e9c4b898c51a7d387ac3480630b Mon Sep 17 00:00:00 2001 From: Nicolas Frattaroli <nicolas.frattaroli(a)collabora.com> Date: Wed, 23 Apr 2025 09:53:32 +0200 Subject: [PATCH] mmc: sdhci-of-dwcmshc: add PD workaround on RK3576 RK3576's power domains have a peculiar design where the PD_NVM power domain, of which the sdhci controller is a part, seemingly does not have idempotent runtime disable/enable. The end effect is that if PD_NVM gets turned off by the generic power domain logic because all the devices depending on it are suspended, then the next time the sdhci device is unsuspended, it'll hang the SoC as soon as it tries accessing the CQHCI registers. RK3576's UFS support needed a new dev_pm_genpd_rpm_always_on function added to the generic power domains API to handle what appears to be a similar hardware design. Use this new function to ask for the same treatment in the sdhci controller by giving rk3576 its own platform data with its own postinit function. The benefit of doing this instead of marking the power domains always on in the power domain core is that we only do this if we know the platform we're running on actually uses the sdhci controller. For others, keeping PD_NVM always on would be a waste, as they won't run into this specific issue. The only other IP in PD_NVM that could be affected is FSPI0. If it gets a mainline driver, it will probably want to do the same thing. Acked-by: Adrian Hunter <adrian.hunter(a)intel.com> Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli(a)collabora.com> Reviewed-by: Shawn Lin <shawn.lin(a)rock-chips.com> Fixes: cfee1b507758 ("pmdomain: rockchip: Add support for RK3576 SoC") Cc: <stable(a)vger.kernel.org> # v6.15+ Link: https://lore.kernel.org/r/20250423-rk3576-emmc-fix-v3-1-0bf80e29967f@collab… Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org> diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index 09b9ab15e499..a20d03fdd6a9 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/pm_domain.h> #include <linux/pm_runtime.h> #include <linux/reset.h> #include <linux/sizes.h> @@ -745,6 +746,29 @@ static void dwcmshc_rk35xx_postinit(struct sdhci_host *host, struct dwcmshc_priv } } +static void dwcmshc_rk3576_postinit(struct sdhci_host *host, struct dwcmshc_priv *dwc_priv) +{ + struct device *dev = mmc_dev(host->mmc); + int ret; + + /* + * This works around the design of the RK3576's power domains, which + * makes the PD_NVM power domain, which the sdhci controller on the + * RK3576 is in, never come back the same way once it's run-time + * suspended once. This can happen during early kernel boot if no driver + * is using either PD_NVM or its child power domain PD_SDGMAC for a + * short moment, leading to it being turned off to save power. By + * keeping it on, sdhci suspending won't lead to PD_NVM becoming a + * candidate for getting turned off. + */ + ret = dev_pm_genpd_rpm_always_on(dev, true); + if (ret && ret != -EOPNOTSUPP) + dev_warn(dev, "failed to set PD rpm always on, SoC may hang later: %pe\n", + ERR_PTR(ret)); + + dwcmshc_rk35xx_postinit(host, dwc_priv); +} + static int th1520_execute_tuning(struct sdhci_host *host, u32 opcode) { struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); @@ -1176,6 +1200,18 @@ static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk35xx_pdata = { .postinit = dwcmshc_rk35xx_postinit, }; +static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk3576_pdata = { + .pdata = { + .ops = &sdhci_dwcmshc_rk35xx_ops, + .quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN | + SDHCI_QUIRK_BROKEN_TIMEOUT_VAL, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | + SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN, + }, + .init = dwcmshc_rk35xx_init, + .postinit = dwcmshc_rk3576_postinit, +}; + static const struct dwcmshc_pltfm_data sdhci_dwcmshc_th1520_pdata = { .pdata = { .ops = &sdhci_dwcmshc_th1520_ops, @@ -1274,6 +1310,10 @@ static const struct of_device_id sdhci_dwcmshc_dt_ids[] = { .compatible = "rockchip,rk3588-dwcmshc", .data = &sdhci_dwcmshc_rk35xx_pdata, }, + { + .compatible = "rockchip,rk3576-dwcmshc", + .data = &sdhci_dwcmshc_rk3576_pdata, + }, { .compatible = "rockchip,rk3568-dwcmshc", .data = &sdhci_dwcmshc_rk35xx_pdata,

1 month

1
0
0 0

FAILED: patch "[PATCH] Input: synaptics-rmi - fix crash with unsupported versions of" 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 ca39500f6af9cfe6823dc5aa8fbaed788d6e35b2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052509-groom-ogle-5cfa@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ca39500f6af9cfe6823dc5aa8fbaed788d6e35b2 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov <dmitry.torokhov(a)gmail.com> Date: Mon, 5 May 2025 15:49:59 -0700 Subject: [PATCH] Input: synaptics-rmi - fix crash with unsupported versions of F34 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sysfs interface for updating firmware for RMI devices is available even when F34 probe fails. The code checks for presence of F34 "container" pointer and then tries to use the function data attached to the sub-device. F34 assigns the function data early, before it knows if probe will succeed, leaving behind a stale pointer. Fix this by expanding checks to not only test for presence of F34 "container" but also check if there is driver data assigned to the sub-device, and call dev_set_drvdata() only after we are certain that probe is successful. This is not a complete fix, since F34 will be freed during firmware update, so there is still a race when fetching and accessing this pointer. This race will be addressed in follow-up changes. Reported-by: Hanno Böck <hanno(a)hboeck.de> Fixes: 29fd0ec2bdbe ("Input: synaptics-rmi4 - add support for F34 device reflash") Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/aBlAl6sGulam-Qcx@google.com Signed-off-by: Dmitry Torokhov <dmitry.torokhov(a)gmail.com> diff --git a/drivers/input/rmi4/rmi_f34.c b/drivers/input/rmi4/rmi_f34.c index d760af4cc12e..f1947f03b06a 100644 --- a/drivers/input/rmi4/rmi_f34.c +++ b/drivers/input/rmi4/rmi_f34.c @@ -4,6 +4,7 @@ * Copyright (C) 2016 Zodiac Inflight Innovations */ +#include "linux/device.h" #include <linux/kernel.h> #include <linux/rmi.h> #include <linux/firmware.h> @@ -289,39 +290,30 @@ static int rmi_f34_update_firmware(struct f34_data *f34, return rmi_f34_flash_firmware(f34, syn_fw); } -static int rmi_f34_status(struct rmi_function *fn) -{ - struct f34_data *f34 = dev_get_drvdata(&fn->dev); - - /* - * The status is the percentage complete, or once complete, - * zero for success or a negative return code. - */ - return f34->update_status; -} - static ssize_t rmi_driver_bootloader_id_show(struct device *dev, struct device_attribute *dattr, char *buf) { struct rmi_driver_data *data = dev_get_drvdata(dev); - struct rmi_function *fn = data->f34_container; + struct rmi_function *fn; struct f34_data *f34; - if (fn) { - f34 = dev_get_drvdata(&fn->dev); + fn = data->f34_container; + if (!fn) + return -ENODEV; - if (f34->bl_version == 5) - return sysfs_emit(buf, "%c%c\n", - f34->bootloader_id[0], - f34->bootloader_id[1]); - else - return sysfs_emit(buf, "V%d.%d\n", - f34->bootloader_id[1], - f34->bootloader_id[0]); - } + f34 = dev_get_drvdata(&fn->dev); + if (!f34) + return -ENODEV; - return 0; + if (f34->bl_version == 5) + return sysfs_emit(buf, "%c%c\n", + f34->bootloader_id[0], + f34->bootloader_id[1]); + else + return sysfs_emit(buf, "V%d.%d\n", + f34->bootloader_id[1], + f34->bootloader_id[0]); } static DEVICE_ATTR(bootloader_id, 0444, rmi_driver_bootloader_id_show, NULL); @@ -334,13 +326,16 @@ static ssize_t rmi_driver_configuration_id_show(struct device *dev, struct rmi_function *fn = data->f34_container; struct f34_data *f34; - if (fn) { - f34 = dev_get_drvdata(&fn->dev); + fn = data->f34_container; + if (!fn) + return -ENODEV; - return sysfs_emit(buf, "%s\n", f34->configuration_id); - } + f34 = dev_get_drvdata(&fn->dev); + if (!f34) + return -ENODEV; - return 0; + + return sysfs_emit(buf, "%s\n", f34->configuration_id); } static DEVICE_ATTR(configuration_id, 0444, @@ -356,10 +351,14 @@ static int rmi_firmware_update(struct rmi_driver_data *data, if (!data->f34_container) { dev_warn(dev, "%s: No F34 present!\n", __func__); - return -EINVAL; + return -ENODEV; } f34 = dev_get_drvdata(&data->f34_container->dev); + if (!f34) { + dev_warn(dev, "%s: No valid F34 present!\n", __func__); + return -ENODEV; + } if (f34->bl_version >= 7) { if (data->pdt_props & HAS_BSR) { @@ -485,10 +484,18 @@ static ssize_t rmi_driver_update_fw_status_show(struct device *dev, char *buf) { struct rmi_driver_data *data = dev_get_drvdata(dev); - int update_status = 0; + struct f34_data *f34; + int update_status = -ENODEV; - if (data->f34_container) - update_status = rmi_f34_status(data->f34_container); + /* + * The status is the percentage complete, or once complete, + * zero for success or a negative return code. + */ + if (data->f34_container) { + f34 = dev_get_drvdata(&data->f34_container->dev); + if (f34) + update_status = f34->update_status; + } return sysfs_emit(buf, "%d\n", update_status); } @@ -508,33 +515,21 @@ static const struct attribute_group rmi_firmware_attr_group = { .attrs = rmi_firmware_attrs, }; -static int rmi_f34_probe(struct rmi_function *fn) +static int rmi_f34v5_probe(struct f34_data *f34) { - struct f34_data *f34; - unsigned char f34_queries[9]; + struct rmi_function *fn = f34->fn; + u8 f34_queries[9]; bool has_config_id; - u8 version = fn->fd.function_version; - int ret; - - f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL); - if (!f34) - return -ENOMEM; - - f34->fn = fn; - dev_set_drvdata(&fn->dev, f34); - - /* v5 code only supported version 0, try V7 probe */ - if (version > 0) - return rmi_f34v7_probe(f34); + int error; f34->bl_version = 5; - ret = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr, - f34_queries, sizeof(f34_queries)); - if (ret) { + error = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr, + f34_queries, sizeof(f34_queries)); + if (error) { dev_err(&fn->dev, "%s: Failed to query properties\n", __func__); - return ret; + return error; } snprintf(f34->bootloader_id, sizeof(f34->bootloader_id), @@ -560,11 +555,11 @@ static int rmi_f34_probe(struct rmi_function *fn) f34->v5.config_blocks); if (has_config_id) { - ret = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr, - f34_queries, sizeof(f34_queries)); - if (ret) { + error = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr, + f34_queries, sizeof(f34_queries)); + if (error) { dev_err(&fn->dev, "Failed to read F34 config ID\n"); - return ret; + return error; } snprintf(f34->configuration_id, sizeof(f34->configuration_id), @@ -573,12 +568,34 @@ static int rmi_f34_probe(struct rmi_function *fn) f34_queries[2], f34_queries[3]); rmi_dbg(RMI_DEBUG_FN, &fn->dev, "Configuration ID: %s\n", - f34->configuration_id); + f34->configuration_id); } return 0; } +static int rmi_f34_probe(struct rmi_function *fn) +{ + struct f34_data *f34; + u8 version = fn->fd.function_version; + int error; + + f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL); + if (!f34) + return -ENOMEM; + + f34->fn = fn; + + /* v5 code only supported version 0 */ + error = version == 0 ? rmi_f34v5_probe(f34) : rmi_f34v7_probe(f34); + if (error) + return error; + + dev_set_drvdata(&fn->dev, f34); + + return 0; +} + int rmi_f34_create_sysfs(struct rmi_device *rmi_dev) { return sysfs_create_group(&rmi_dev->dev.kobj, &rmi_firmware_attr_group);

1 month

1
0
0 0

FAILED: patch "[PATCH] Input: synaptics-rmi - fix crash with unsupported versions of" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-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-5.4.y git checkout FETCH_HEAD git cherry-pick -x ca39500f6af9cfe6823dc5aa8fbaed788d6e35b2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052509-resisting-guise-ad21@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ca39500f6af9cfe6823dc5aa8fbaed788d6e35b2 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov <dmitry.torokhov(a)gmail.com> Date: Mon, 5 May 2025 15:49:59 -0700 Subject: [PATCH] Input: synaptics-rmi - fix crash with unsupported versions of F34 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sysfs interface for updating firmware for RMI devices is available even when F34 probe fails. The code checks for presence of F34 "container" pointer and then tries to use the function data attached to the sub-device. F34 assigns the function data early, before it knows if probe will succeed, leaving behind a stale pointer. Fix this by expanding checks to not only test for presence of F34 "container" but also check if there is driver data assigned to the sub-device, and call dev_set_drvdata() only after we are certain that probe is successful. This is not a complete fix, since F34 will be freed during firmware update, so there is still a race when fetching and accessing this pointer. This race will be addressed in follow-up changes. Reported-by: Hanno Böck <hanno(a)hboeck.de> Fixes: 29fd0ec2bdbe ("Input: synaptics-rmi4 - add support for F34 device reflash") Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/aBlAl6sGulam-Qcx@google.com Signed-off-by: Dmitry Torokhov <dmitry.torokhov(a)gmail.com> diff --git a/drivers/input/rmi4/rmi_f34.c b/drivers/input/rmi4/rmi_f34.c index d760af4cc12e..f1947f03b06a 100644 --- a/drivers/input/rmi4/rmi_f34.c +++ b/drivers/input/rmi4/rmi_f34.c @@ -4,6 +4,7 @@ * Copyright (C) 2016 Zodiac Inflight Innovations */ +#include "linux/device.h" #include <linux/kernel.h> #include <linux/rmi.h> #include <linux/firmware.h> @@ -289,39 +290,30 @@ static int rmi_f34_update_firmware(struct f34_data *f34, return rmi_f34_flash_firmware(f34, syn_fw); } -static int rmi_f34_status(struct rmi_function *fn) -{ - struct f34_data *f34 = dev_get_drvdata(&fn->dev); - - /* - * The status is the percentage complete, or once complete, - * zero for success or a negative return code. - */ - return f34->update_status; -} - static ssize_t rmi_driver_bootloader_id_show(struct device *dev, struct device_attribute *dattr, char *buf) { struct rmi_driver_data *data = dev_get_drvdata(dev); - struct rmi_function *fn = data->f34_container; + struct rmi_function *fn; struct f34_data *f34; - if (fn) { - f34 = dev_get_drvdata(&fn->dev); + fn = data->f34_container; + if (!fn) + return -ENODEV; - if (f34->bl_version == 5) - return sysfs_emit(buf, "%c%c\n", - f34->bootloader_id[0], - f34->bootloader_id[1]); - else - return sysfs_emit(buf, "V%d.%d\n", - f34->bootloader_id[1], - f34->bootloader_id[0]); - } + f34 = dev_get_drvdata(&fn->dev); + if (!f34) + return -ENODEV; - return 0; + if (f34->bl_version == 5) + return sysfs_emit(buf, "%c%c\n", + f34->bootloader_id[0], + f34->bootloader_id[1]); + else + return sysfs_emit(buf, "V%d.%d\n", + f34->bootloader_id[1], + f34->bootloader_id[0]); } static DEVICE_ATTR(bootloader_id, 0444, rmi_driver_bootloader_id_show, NULL); @@ -334,13 +326,16 @@ static ssize_t rmi_driver_configuration_id_show(struct device *dev, struct rmi_function *fn = data->f34_container; struct f34_data *f34; - if (fn) { - f34 = dev_get_drvdata(&fn->dev); + fn = data->f34_container; + if (!fn) + return -ENODEV; - return sysfs_emit(buf, "%s\n", f34->configuration_id); - } + f34 = dev_get_drvdata(&fn->dev); + if (!f34) + return -ENODEV; - return 0; + + return sysfs_emit(buf, "%s\n", f34->configuration_id); } static DEVICE_ATTR(configuration_id, 0444, @@ -356,10 +351,14 @@ static int rmi_firmware_update(struct rmi_driver_data *data, if (!data->f34_container) { dev_warn(dev, "%s: No F34 present!\n", __func__); - return -EINVAL; + return -ENODEV; } f34 = dev_get_drvdata(&data->f34_container->dev); + if (!f34) { + dev_warn(dev, "%s: No valid F34 present!\n", __func__); + return -ENODEV; + } if (f34->bl_version >= 7) { if (data->pdt_props & HAS_BSR) { @@ -485,10 +484,18 @@ static ssize_t rmi_driver_update_fw_status_show(struct device *dev, char *buf) { struct rmi_driver_data *data = dev_get_drvdata(dev); - int update_status = 0; + struct f34_data *f34; + int update_status = -ENODEV; - if (data->f34_container) - update_status = rmi_f34_status(data->f34_container); + /* + * The status is the percentage complete, or once complete, + * zero for success or a negative return code. + */ + if (data->f34_container) { + f34 = dev_get_drvdata(&data->f34_container->dev); + if (f34) + update_status = f34->update_status; + } return sysfs_emit(buf, "%d\n", update_status); } @@ -508,33 +515,21 @@ static const struct attribute_group rmi_firmware_attr_group = { .attrs = rmi_firmware_attrs, }; -static int rmi_f34_probe(struct rmi_function *fn) +static int rmi_f34v5_probe(struct f34_data *f34) { - struct f34_data *f34; - unsigned char f34_queries[9]; + struct rmi_function *fn = f34->fn; + u8 f34_queries[9]; bool has_config_id; - u8 version = fn->fd.function_version; - int ret; - - f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL); - if (!f34) - return -ENOMEM; - - f34->fn = fn; - dev_set_drvdata(&fn->dev, f34); - - /* v5 code only supported version 0, try V7 probe */ - if (version > 0) - return rmi_f34v7_probe(f34); + int error; f34->bl_version = 5; - ret = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr, - f34_queries, sizeof(f34_queries)); - if (ret) { + error = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr, + f34_queries, sizeof(f34_queries)); + if (error) { dev_err(&fn->dev, "%s: Failed to query properties\n", __func__); - return ret; + return error; } snprintf(f34->bootloader_id, sizeof(f34->bootloader_id), @@ -560,11 +555,11 @@ static int rmi_f34_probe(struct rmi_function *fn) f34->v5.config_blocks); if (has_config_id) { - ret = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr, - f34_queries, sizeof(f34_queries)); - if (ret) { + error = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr, + f34_queries, sizeof(f34_queries)); + if (error) { dev_err(&fn->dev, "Failed to read F34 config ID\n"); - return ret; + return error; } snprintf(f34->configuration_id, sizeof(f34->configuration_id), @@ -573,12 +568,34 @@ static int rmi_f34_probe(struct rmi_function *fn) f34_queries[2], f34_queries[3]); rmi_dbg(RMI_DEBUG_FN, &fn->dev, "Configuration ID: %s\n", - f34->configuration_id); + f34->configuration_id); } return 0; } +static int rmi_f34_probe(struct rmi_function *fn) +{ + struct f34_data *f34; + u8 version = fn->fd.function_version; + int error; + + f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL); + if (!f34) + return -ENOMEM; + + f34->fn = fn; + + /* v5 code only supported version 0 */ + error = version == 0 ? rmi_f34v5_probe(f34) : rmi_f34v7_probe(f34); + if (error) + return error; + + dev_set_drvdata(&fn->dev, f34); + + return 0; +} + int rmi_f34_create_sysfs(struct rmi_device *rmi_dev) { return sysfs_create_group(&rmi_dev->dev.kobj, &rmi_firmware_attr_group);

1 month

1
0
0 0

FAILED: patch "[PATCH] Input: synaptics-rmi - fix crash with unsupported versions of" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-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-5.15.y git checkout FETCH_HEAD git cherry-pick -x ca39500f6af9cfe6823dc5aa8fbaed788d6e35b2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025052508-annuity-untapped-8fb8@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ca39500f6af9cfe6823dc5aa8fbaed788d6e35b2 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov <dmitry.torokhov(a)gmail.com> Date: Mon, 5 May 2025 15:49:59 -0700 Subject: [PATCH] Input: synaptics-rmi - fix crash with unsupported versions of F34 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sysfs interface for updating firmware for RMI devices is available even when F34 probe fails. The code checks for presence of F34 "container" pointer and then tries to use the function data attached to the sub-device. F34 assigns the function data early, before it knows if probe will succeed, leaving behind a stale pointer. Fix this by expanding checks to not only test for presence of F34 "container" but also check if there is driver data assigned to the sub-device, and call dev_set_drvdata() only after we are certain that probe is successful. This is not a complete fix, since F34 will be freed during firmware update, so there is still a race when fetching and accessing this pointer. This race will be addressed in follow-up changes. Reported-by: Hanno Böck <hanno(a)hboeck.de> Fixes: 29fd0ec2bdbe ("Input: synaptics-rmi4 - add support for F34 device reflash") Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/aBlAl6sGulam-Qcx@google.com Signed-off-by: Dmitry Torokhov <dmitry.torokhov(a)gmail.com> diff --git a/drivers/input/rmi4/rmi_f34.c b/drivers/input/rmi4/rmi_f34.c index d760af4cc12e..f1947f03b06a 100644 --- a/drivers/input/rmi4/rmi_f34.c +++ b/drivers/input/rmi4/rmi_f34.c @@ -4,6 +4,7 @@ * Copyright (C) 2016 Zodiac Inflight Innovations */ +#include "linux/device.h" #include <linux/kernel.h> #include <linux/rmi.h> #include <linux/firmware.h> @@ -289,39 +290,30 @@ static int rmi_f34_update_firmware(struct f34_data *f34, return rmi_f34_flash_firmware(f34, syn_fw); } -static int rmi_f34_status(struct rmi_function *fn) -{ - struct f34_data *f34 = dev_get_drvdata(&fn->dev); - - /* - * The status is the percentage complete, or once complete, - * zero for success or a negative return code. - */ - return f34->update_status; -} - static ssize_t rmi_driver_bootloader_id_show(struct device *dev, struct device_attribute *dattr, char *buf) { struct rmi_driver_data *data = dev_get_drvdata(dev); - struct rmi_function *fn = data->f34_container; + struct rmi_function *fn; struct f34_data *f34; - if (fn) { - f34 = dev_get_drvdata(&fn->dev); + fn = data->f34_container; + if (!fn) + return -ENODEV; - if (f34->bl_version == 5) - return sysfs_emit(buf, "%c%c\n", - f34->bootloader_id[0], - f34->bootloader_id[1]); - else - return sysfs_emit(buf, "V%d.%d\n", - f34->bootloader_id[1], - f34->bootloader_id[0]); - } + f34 = dev_get_drvdata(&fn->dev); + if (!f34) + return -ENODEV; - return 0; + if (f34->bl_version == 5) + return sysfs_emit(buf, "%c%c\n", + f34->bootloader_id[0], + f34->bootloader_id[1]); + else + return sysfs_emit(buf, "V%d.%d\n", + f34->bootloader_id[1], + f34->bootloader_id[0]); } static DEVICE_ATTR(bootloader_id, 0444, rmi_driver_bootloader_id_show, NULL); @@ -334,13 +326,16 @@ static ssize_t rmi_driver_configuration_id_show(struct device *dev, struct rmi_function *fn = data->f34_container; struct f34_data *f34; - if (fn) { - f34 = dev_get_drvdata(&fn->dev); + fn = data->f34_container; + if (!fn) + return -ENODEV; - return sysfs_emit(buf, "%s\n", f34->configuration_id); - } + f34 = dev_get_drvdata(&fn->dev); + if (!f34) + return -ENODEV; - return 0; + + return sysfs_emit(buf, "%s\n", f34->configuration_id); } static DEVICE_ATTR(configuration_id, 0444, @@ -356,10 +351,14 @@ static int rmi_firmware_update(struct rmi_driver_data *data, if (!data->f34_container) { dev_warn(dev, "%s: No F34 present!\n", __func__); - return -EINVAL; + return -ENODEV; } f34 = dev_get_drvdata(&data->f34_container->dev); + if (!f34) { + dev_warn(dev, "%s: No valid F34 present!\n", __func__); + return -ENODEV; + } if (f34->bl_version >= 7) { if (data->pdt_props & HAS_BSR) { @@ -485,10 +484,18 @@ static ssize_t rmi_driver_update_fw_status_show(struct device *dev, char *buf) { struct rmi_driver_data *data = dev_get_drvdata(dev); - int update_status = 0; + struct f34_data *f34; + int update_status = -ENODEV; - if (data->f34_container) - update_status = rmi_f34_status(data->f34_container); + /* + * The status is the percentage complete, or once complete, + * zero for success or a negative return code. + */ + if (data->f34_container) { + f34 = dev_get_drvdata(&data->f34_container->dev); + if (f34) + update_status = f34->update_status; + } return sysfs_emit(buf, "%d\n", update_status); } @@ -508,33 +515,21 @@ static const struct attribute_group rmi_firmware_attr_group = { .attrs = rmi_firmware_attrs, }; -static int rmi_f34_probe(struct rmi_function *fn) +static int rmi_f34v5_probe(struct f34_data *f34) { - struct f34_data *f34; - unsigned char f34_queries[9]; + struct rmi_function *fn = f34->fn; + u8 f34_queries[9]; bool has_config_id; - u8 version = fn->fd.function_version; - int ret; - - f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL); - if (!f34) - return -ENOMEM; - - f34->fn = fn; - dev_set_drvdata(&fn->dev, f34); - - /* v5 code only supported version 0, try V7 probe */ - if (version > 0) - return rmi_f34v7_probe(f34); + int error; f34->bl_version = 5; - ret = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr, - f34_queries, sizeof(f34_queries)); - if (ret) { + error = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr, + f34_queries, sizeof(f34_queries)); + if (error) { dev_err(&fn->dev, "%s: Failed to query properties\n", __func__); - return ret; + return error; } snprintf(f34->bootloader_id, sizeof(f34->bootloader_id), @@ -560,11 +555,11 @@ static int rmi_f34_probe(struct rmi_function *fn) f34->v5.config_blocks); if (has_config_id) { - ret = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr, - f34_queries, sizeof(f34_queries)); - if (ret) { + error = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr, + f34_queries, sizeof(f34_queries)); + if (error) { dev_err(&fn->dev, "Failed to read F34 config ID\n"); - return ret; + return error; } snprintf(f34->configuration_id, sizeof(f34->configuration_id), @@ -573,12 +568,34 @@ static int rmi_f34_probe(struct rmi_function *fn) f34_queries[2], f34_queries[3]); rmi_dbg(RMI_DEBUG_FN, &fn->dev, "Configuration ID: %s\n", - f34->configuration_id); + f34->configuration_id); } return 0; } +static int rmi_f34_probe(struct rmi_function *fn) +{ + struct f34_data *f34; + u8 version = fn->fd.function_version; + int error; + + f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL); + if (!f34) + return -ENOMEM; + + f34->fn = fn; + + /* v5 code only supported version 0 */ + error = version == 0 ? rmi_f34v5_probe(f34) : rmi_f34v7_probe(f34); + if (error) + return error; + + dev_set_drvdata(&fn->dev, f34); + + return 0; +} + int rmi_f34_create_sysfs(struct rmi_device *rmi_dev) { return sysfs_create_group(&rmi_dev->dev.kobj, &rmi_firmware_attr_group);

1 month

1
0
0 0

[merged mm-hotfixes-stable] mm-fix-copy_vma-error-handling-for-hugetlb-mappings.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: fix copy_vma() error handling for hugetlb mappings has been removed from the -mm tree. Its filename was mm-fix-copy_vma-error-handling-for-hugetlb-mappings.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: Ricardo Ca��uelo Navarro <rcn(a)igalia.com> Subject: mm: fix copy_vma() error handling for hugetlb mappings Date: Fri, 23 May 2025 14:19:10 +0200 If, during a mremap() operation for a hugetlb-backed memory mapping, copy_vma() fails after the source vma has been duplicated and opened (ie. vma_link() fails), the error is handled by closing the new vma. This updates the hugetlbfs reservation counter of the reservation map which at this point is referenced by both the source vma and the new copy. As a result, once the new vma has been freed and copy_vma() returns, the reservation counter for the source vma will be incorrect. This patch addresses this corner case by clearing the hugetlb private page reservation reference for the new vma and decrementing the reference before closing the vma, so that vma_close() won't update the reservation counter. This is also what copy_vma_and_data() does with the source vma if copy_vma() succeeds, so a helper function has been added to do the fixup in both functions. The issue was reported by a private syzbot instance and can be reproduced using the C reproducer in [1]. It's also a possible duplicate of public syzbot report [2]. The WARNING report is: ============================================================ page_counter underflow: -1024 nr_pages=1024 WARNING: CPU: 0 PID: 3287 at mm/page_counter.c:61 page_counter_cancel+0xf6/0x120 Modules linked in: CPU: 0 UID: 0 PID: 3287 Comm: repro__WARNING_ Not tainted 6.15.0-rc7+ #54 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-2-gc13ff2cd-prebuilt.qemu.org 04/01/2014 RIP: 0010:page_counter_cancel+0xf6/0x120 Code: ff 5b 41 5e 41 5f 5d c3 cc cc cc cc e8 f3 4f 8f ff c6 05 64 01 27 06 01 48 c7 c7 60 15 f8 85 48 89 de 4c 89 fa e8 2a a7 51 ff <0f> 0b e9 66 ff ff ff 44 89 f9 80 e1 07 38 c1 7c 9d 4c 81 RSP: 0018:ffffc900025df6a0 EFLAGS: 00010246 RAX: 2edfc409ebb44e00 RBX: fffffffffffffc00 RCX: ffff8880155f0000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: dffffc0000000000 R08: ffffffff81c4a23c R09: 1ffff1100330482a R10: dffffc0000000000 R11: ffffed100330482b R12: 0000000000000000 R13: ffff888058a882c0 R14: ffff888058a882c0 R15: 0000000000000400 FS: 0000000000000000(0000) GS:ffff88808fc53000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004b33e0 CR3: 00000000076d6000 CR4: 00000000000006f0 Call Trace: <TASK> page_counter_uncharge+0x33/0x80 hugetlb_cgroup_uncharge_counter+0xcb/0x120 hugetlb_vm_op_close+0x579/0x960 ? __pfx_hugetlb_vm_op_close+0x10/0x10 remove_vma+0x88/0x130 exit_mmap+0x71e/0xe00 ? __pfx_exit_mmap+0x10/0x10 ? __mutex_unlock_slowpath+0x22e/0x7f0 ? __pfx_exit_aio+0x10/0x10 ? __up_read+0x256/0x690 ? uprobe_clear_state+0x274/0x290 ? mm_update_next_owner+0xa9/0x810 __mmput+0xc9/0x370 exit_mm+0x203/0x2f0 ? __pfx_exit_mm+0x10/0x10 ? taskstats_exit+0x32b/0xa60 do_exit+0x921/0x2740 ? do_raw_spin_lock+0x155/0x3b0 ? __pfx_do_exit+0x10/0x10 ? __pfx_do_raw_spin_lock+0x10/0x10 ? _raw_spin_lock_irq+0xc5/0x100 do_group_exit+0x20c/0x2c0 get_signal+0x168c/0x1720 ? __pfx_get_signal+0x10/0x10 ? schedule+0x165/0x360 arch_do_signal_or_restart+0x8e/0x7d0 ? __pfx_arch_do_signal_or_restart+0x10/0x10 ? __pfx___se_sys_futex+0x10/0x10 syscall_exit_to_user_mode+0xb8/0x2c0 do_syscall_64+0x75/0x120 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x422dcd Code: Unable to access opcode bytes at 0x422da3. RSP: 002b:00007ff266cdb208 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 00007ff266cdbcdc RCX: 0000000000422dcd RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 00000000004c7bec RBP: 00007ff266cdb220 R08: 203a6362696c6720 R09: 203a6362696c6720 R10: 0000200000c00000 R11: 0000000000000246 R12: ffffffffffffffd0 R13: 0000000000000002 R14: 00007ffe1cb5f520 R15: 00007ff266cbb000 </TASK> ============================================================ Link: https://lkml.kernel.org/r/20250523-warning_in_page_counter_cancel-v2-1-b6df… Link: https://people.igalia.com/rcn/kernel_logs/20250422__WARNING_in_page_counter… [1] Link: https://lore.kernel.org/all/67000a50.050a0220.49194.048d.GAE@google.com/ [2] Signed-off-by: Ricardo Ca��uelo Navarro <rcn(a)igalia.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Florent Revest <revest(a)google.com> Cc: Jann Horn <jannh(a)google.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/hugetlb.h | 5 +++++ mm/hugetlb.c | 16 +++++++++++++++- mm/mremap.c | 3 +-- mm/vma.c | 1 + 4 files changed, 22 insertions(+), 3 deletions(-) --- a/include/linux/hugetlb.h~mm-fix-copy_vma-error-handling-for-hugetlb-mappings +++ a/include/linux/hugetlb.h @@ -275,6 +275,7 @@ long hugetlb_change_protection(struct vm bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); +void fixup_hugetlb_reservations(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -468,6 +469,10 @@ static inline vm_fault_t hugetlb_fault(s static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } +static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ +} + #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write --- a/mm/hugetlb.c~mm-fix-copy_vma-error-handling-for-hugetlb-mappings +++ a/mm/hugetlb.c @@ -1250,7 +1250,7 @@ void hugetlb_dup_vma_private(struct vm_a /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. - * This function should be only used by move_vma() and operate on + * This function should be only used by mremap and operate on * same sized vma. It should never come here with last ref on the * reservation. */ @@ -7939,3 +7939,17 @@ void hugetlb_unshare_all_pmds(struct vm_ hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } + +/* + * For hugetlb, mremap() is an odd edge case - while the VMA copying is + * performed, we permit both the old and new VMAs to reference the same + * reservation. + * + * We fix this up after the operation succeeds, or if a newly allocated VMA + * is closed as a result of a failure to allocate memory. + */ +void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + clear_vma_resv_huge_pages(vma); +} --- a/mm/mremap.c~mm-fix-copy_vma-error-handling-for-hugetlb-mappings +++ a/mm/mremap.c @@ -1188,8 +1188,7 @@ static int copy_vma_and_data(struct vma_ mremap_userfaultfd_prep(new_vma, vrm->uf); } - if (is_vm_hugetlb_page(vma)) - clear_vma_resv_huge_pages(vma); + fixup_hugetlb_reservations(vma); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) --- a/mm/vma.c~mm-fix-copy_vma-error-handling-for-hugetlb-mappings +++ a/mm/vma.c @@ -1834,6 +1834,7 @@ struct vm_area_struct *copy_vma(struct v return new_vma; out_vma_link: + fixup_hugetlb_reservations(new_vma); vma_close(new_vma); if (new_vma->vm_file) _ Patches currently in -mm which might be from rcn(a)igalia.com are

1 month

1
0
0 0

[merged mm-hotfixes-stable] memcg-always-call-cond_resched-after-fn.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: memcg: always call cond_resched() after fn() has been removed from the -mm tree. Its filename was memcg-always-call-cond_resched-after-fn.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: Breno Leitao <leitao(a)debian.org> Subject: memcg: always call cond_resched() after fn() Date: Fri, 23 May 2025 10:21:06 -0700 I am seeing soft lockup on certain machine types when a cgroup OOMs. This is happening because killing the process in certain machine might be very slow, which causes the soft lockup and RCU stalls. This happens usually when the cgroup has MANY processes and memory.oom.group is set. Example I am seeing in real production: [462012.244552] Memory cgroup out of memory: Killed process 3370438 (crosvm) .... .... [462037.318059] Memory cgroup out of memory: Killed process 4171372 (adb) .... [462037.348314] watchdog: BUG: soft lockup - CPU#64 stuck for 26s! [stat_manager-ag:1618982] .... Quick look at why this is so slow, it seems to be related to serial flush for certain machine types. For all the crashes I saw, the target CPU was at console_flush_all(). In the case above, there are thousands of processes in the cgroup, and it is soft locking up before it reaches the 1024 limit in the code (which would call the cond_resched()). So, cond_resched() in 1024 blocks is not sufficient. Remove the counter-based conditional rescheduling logic and call cond_resched() unconditionally after each task iteration, after fn() is called. This avoids the lockup independently of how slow fn() is. Link: https://lkml.kernel.org/r/20250523-memcg_fix-v1-1-ad3eafb60477@debian.org Fixes: ade81479c7dd ("memcg: fix soft lockup in the OOM process") Signed-off-by: Breno Leitao <leitao(a)debian.org> Suggested-by: Rik van Riel <riel(a)surriel.com> Acked-by: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: Michael van der Westhuizen <rmikey(a)meta.com> Cc: Usama Arif <usamaarif642(a)gmail.com> Cc: Pavel Begunkov <asml.silence(a)gmail.com> Cc: Chen Ridong <chenridong(a)huawei.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Roman Gushchin <roman.gushchin(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/memcontrol.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) --- a/mm/memcontrol.c~memcg-always-call-cond_resched-after-fn +++ a/mm/memcontrol.c @@ -1168,7 +1168,6 @@ void mem_cgroup_scan_tasks(struct mem_cg { struct mem_cgroup *iter; int ret = 0; - int i = 0; BUG_ON(mem_cgroup_is_root(memcg)); @@ -1178,10 +1177,9 @@ void mem_cgroup_scan_tasks(struct mem_cg css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); while (!ret && (task = css_task_iter_next(&it))) { - /* Avoid potential softlockup warning */ - if ((++i & 1023) == 0) - cond_resched(); ret = fn(task, arg); + /* Avoid potential softlockup warning */ + cond_resched(); } css_task_iter_end(&it); if (ret) { _ Patches currently in -mm which might be from leitao(a)debian.org are

1 month

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2025