November 2024 - Linux-stable-mirror

+ ocfs2-fix-ubsan-warning-in-ocfs2_verify_volume.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: ocfs2: fix UBSAN warning in ocfs2_verify_volume() has been added to the -mm mm-hotfixes-unstable branch. Its filename is ocfs2-fix-ubsan-warning-in-ocfs2_verify_volume.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Dmitry Antipov <dmantipov(a)yandex.ru> Subject: ocfs2: fix UBSAN warning in ocfs2_verify_volume() Date: Wed, 6 Nov 2024 12:21:00 +0300 Syzbot has reported the following splat triggered by UBSAN: UBSAN: shift-out-of-bounds in fs/ocfs2/super.c:2336:10 shift exponent 32768 is too large for 32-bit type 'int' CPU: 2 UID: 0 PID: 5255 Comm: repro Not tainted 6.12.0-rc4-syzkaller-00047-gc2ee9f594da8 #0 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-3.fc41 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x241/0x360 ? __pfx_dump_stack_lvl+0x10/0x10 ? __pfx__printk+0x10/0x10 ? __asan_memset+0x23/0x50 ? lockdep_init_map_type+0xa1/0x910 __ubsan_handle_shift_out_of_bounds+0x3c8/0x420 ocfs2_fill_super+0xf9c/0x5750 ? __pfx_ocfs2_fill_super+0x10/0x10 ? __pfx_validate_chain+0x10/0x10 ? __pfx_validate_chain+0x10/0x10 ? validate_chain+0x11e/0x5920 ? __lock_acquire+0x1384/0x2050 ? __pfx_validate_chain+0x10/0x10 ? string+0x26a/0x2b0 ? widen_string+0x3a/0x310 ? string+0x26a/0x2b0 ? bdev_name+0x2b1/0x3c0 ? pointer+0x703/0x1210 ? __pfx_pointer+0x10/0x10 ? __pfx_format_decode+0x10/0x10 ? __lock_acquire+0x1384/0x2050 ? vsnprintf+0x1ccd/0x1da0 ? snprintf+0xda/0x120 ? __pfx_lock_release+0x10/0x10 ? do_raw_spin_lock+0x14f/0x370 ? __pfx_snprintf+0x10/0x10 ? set_blocksize+0x1f9/0x360 ? sb_set_blocksize+0x98/0xf0 ? setup_bdev_super+0x4e6/0x5d0 mount_bdev+0x20c/0x2d0 ? __pfx_ocfs2_fill_super+0x10/0x10 ? __pfx_mount_bdev+0x10/0x10 ? vfs_parse_fs_string+0x190/0x230 ? __pfx_vfs_parse_fs_string+0x10/0x10 legacy_get_tree+0xf0/0x190 ? __pfx_ocfs2_mount+0x10/0x10 vfs_get_tree+0x92/0x2b0 do_new_mount+0x2be/0xb40 ? __pfx_do_new_mount+0x10/0x10 __se_sys_mount+0x2d6/0x3c0 ? __pfx___se_sys_mount+0x10/0x10 ? do_syscall_64+0x100/0x230 ? __x64_sys_mount+0x20/0xc0 do_syscall_64+0xf3/0x230 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f37cae96fda Code: 48 8b 0d 51 ce 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1e ce 0c 00 f7 d8 64 89 01 48 RSP: 002b:00007fff6c1aa228 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007fff6c1aa240 RCX: 00007f37cae96fda RDX: 00000000200002c0 RSI: 0000000020000040 RDI: 00007fff6c1aa240 RBP: 0000000000000004 R08: 00007fff6c1aa280 R09: 0000000000000000 R10: 00000000000008c0 R11: 0000000000000206 R12: 00000000000008c0 R13: 00007fff6c1aa280 R14: 0000000000000003 R15: 0000000001000000 </TASK> For a really damaged superblock, the value of 'i_super.s_blocksize_bits' may exceed the maximum possible shift for an underlying 'int'. So add an extra check whether the aforementioned field represents the valid block size, which is 512 bytes, 1K, 2K, or 4K. Link: https://lkml.kernel.org/r/20241106092100.2661330-1-dmantipov@yandex.ru Fixes: ccd979bdbce9 ("[PATCH] OCFS2: The Second Oracle Cluster Filesystem") Signed-off-by: Dmitry Antipov <dmantipov(a)yandex.ru> Reported-by: syzbot+56f7cd1abe4b8e475180(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=56f7cd1abe4b8e475180 Reviewed-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Cc: Mark Fasheh <mark(a)fasheh.com> Cc: Joel Becker <jlbec(a)evilplan.org> Cc: Junxiao Bi <junxiao.bi(a)oracle.com> Cc: Changwei Ge <gechangwei(a)live.cn> Cc: Jun Piao <piaojun(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/ocfs2/super.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) --- a/fs/ocfs2/super.c~ocfs2-fix-ubsan-warning-in-ocfs2_verify_volume +++ a/fs/ocfs2/super.c @@ -2319,6 +2319,7 @@ static int ocfs2_verify_volume(struct oc struct ocfs2_blockcheck_stats *stats) { int status = -EAGAIN; + u32 blksz_bits; if (memcmp(di->i_signature, OCFS2_SUPER_BLOCK_SIGNATURE, strlen(OCFS2_SUPER_BLOCK_SIGNATURE)) == 0) { @@ -2333,11 +2334,15 @@ static int ocfs2_verify_volume(struct oc goto out; } status = -EINVAL; - if ((1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits)) != blksz) { + /* Acceptable block sizes are 512 bytes, 1K, 2K and 4K. */ + blksz_bits = le32_to_cpu(di->id2.i_super.s_blocksize_bits); + if (blksz_bits < 9 || blksz_bits > 12) { mlog(ML_ERROR, "found superblock with incorrect block " - "size: found %u, should be %u\n", - 1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits), - blksz); + "size bits: found %u, should be 9, 10, 11, or 12\n", + blksz_bits); + } else if ((1 << le32_to_cpu(blksz_bits)) != blksz) { + mlog(ML_ERROR, "found superblock with incorrect block " + "size: found %u, should be %u\n", 1 << blksz_bits, blksz); } else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) != OCFS2_MAJOR_REV_LEVEL || le16_to_cpu(di->id2.i_super.s_minor_rev_level) != _ Patches currently in -mm which might be from dmantipov(a)yandex.ru are ocfs2-fix-ubsan-warning-in-ocfs2_verify_volume.patch ocfs2-fix-uninitialized-value-in-ocfs2_file_read_iter.patch

7 months, 3 weeks

1
0
0 0

+ nilfs2-fix-null-ptr-deref-in-block_dirty_buffer-tracepoint.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: nilfs2: fix null-ptr-deref in block_dirty_buffer tracepoint has been added to the -mm mm-hotfixes-unstable branch. Its filename is nilfs2-fix-null-ptr-deref-in-block_dirty_buffer-tracepoint.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Subject: nilfs2: fix null-ptr-deref in block_dirty_buffer tracepoint Date: Thu, 7 Nov 2024 01:07:33 +0900 When using the "block:block_dirty_buffer" tracepoint, mark_buffer_dirty() may cause a NULL pointer dereference, or a general protection fault when KASAN is enabled. This happens because, since the tracepoint was added in mark_buffer_dirty(), it references the dev_t member bh->b_bdev->bd_dev regardless of whether the buffer head has a pointer to a block_device structure. In the current implementation, nilfs_grab_buffer(), which grabs a buffer to read (or create) a block of metadata, including b-tree node blocks, does not set the block device, but instead does so only if the buffer is not in the "uptodate" state for each of its caller block reading functions. However, if the uptodate flag is set on a folio/page, and the buffer heads are detached from it by try_to_free_buffers(), and new buffer heads are then attached by create_empty_buffers(), the uptodate flag may be restored to each buffer without the block device being set to bh->b_bdev, and mark_buffer_dirty() may be called later in that state, resulting in the bug mentioned above. Fix this issue by making nilfs_grab_buffer() always set the block device of the super block structure to the buffer head, regardless of the state of the buffer's uptodate flag. Link: https://lkml.kernel.org/r/20241106160811.3316-3-konishi.ryusuke@gmail.com Fixes: 5305cb830834 ("block: add block_{touch|dirty}_buffer tracepoint") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: Tejun Heo <tj(a)kernel.org> Cc: Ubisectech Sirius <bugreport(a)valiantsec.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/nilfs2/btnode.c | 2 -- fs/nilfs2/gcinode.c | 4 +--- fs/nilfs2/mdt.c | 1 - fs/nilfs2/page.c | 1 + 4 files changed, 2 insertions(+), 6 deletions(-) --- a/fs/nilfs2/btnode.c~nilfs2-fix-null-ptr-deref-in-block_dirty_buffer-tracepoint +++ a/fs/nilfs2/btnode.c @@ -68,7 +68,6 @@ nilfs_btnode_create_block(struct address goto failed; } memset(bh->b_data, 0, i_blocksize(inode)); - bh->b_bdev = inode->i_sb->s_bdev; bh->b_blocknr = blocknr; set_buffer_mapped(bh); set_buffer_uptodate(bh); @@ -133,7 +132,6 @@ int nilfs_btnode_submit_block(struct add goto found; } set_buffer_mapped(bh); - bh->b_bdev = inode->i_sb->s_bdev; bh->b_blocknr = pblocknr; /* set block address for read */ bh->b_end_io = end_buffer_read_sync; get_bh(bh); --- a/fs/nilfs2/gcinode.c~nilfs2-fix-null-ptr-deref-in-block_dirty_buffer-tracepoint +++ a/fs/nilfs2/gcinode.c @@ -83,10 +83,8 @@ int nilfs_gccache_submit_read_data(struc goto out; } - if (!buffer_mapped(bh)) { - bh->b_bdev = inode->i_sb->s_bdev; + if (!buffer_mapped(bh)) set_buffer_mapped(bh); - } bh->b_blocknr = pbn; bh->b_end_io = end_buffer_read_sync; get_bh(bh); --- a/fs/nilfs2/mdt.c~nilfs2-fix-null-ptr-deref-in-block_dirty_buffer-tracepoint +++ a/fs/nilfs2/mdt.c @@ -89,7 +89,6 @@ static int nilfs_mdt_create_block(struct if (buffer_uptodate(bh)) goto failed_bh; - bh->b_bdev = sb->s_bdev; err = nilfs_mdt_insert_new_block(inode, block, bh, init_block); if (likely(!err)) { get_bh(bh); --- a/fs/nilfs2/page.c~nilfs2-fix-null-ptr-deref-in-block_dirty_buffer-tracepoint +++ a/fs/nilfs2/page.c @@ -63,6 +63,7 @@ struct buffer_head *nilfs_grab_buffer(st folio_put(folio); return NULL; } + bh->b_bdev = inode->i_sb->s_bdev; return bh; } _ Patches currently in -mm which might be from konishi.ryusuke(a)gmail.com are nilfs2-fix-null-ptr-deref-in-block_touch_buffer-tracepoint.patch nilfs2-fix-null-ptr-deref-in-block_dirty_buffer-tracepoint.patch

7 months, 3 weeks

1
0
0 0

+ nilfs2-fix-null-ptr-deref-in-block_touch_buffer-tracepoint.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: nilfs2: fix null-ptr-deref in block_touch_buffer tracepoint has been added to the -mm mm-hotfixes-unstable branch. Its filename is nilfs2-fix-null-ptr-deref-in-block_touch_buffer-tracepoint.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Subject: nilfs2: fix null-ptr-deref in block_touch_buffer tracepoint Date: Thu, 7 Nov 2024 01:07:32 +0900 Patch series "nilfs2: fix null-ptr-deref bugs on block tracepoints". This series fixes null pointer dereference bugs that occur when using nilfs2 and two block-related tracepoints. This patch (of 2): It has been reported that when using "block:block_touch_buffer" tracepoint, touch_buffer() called from __nilfs_get_folio_block() causes a NULL pointer dereference, or a general protection fault when KASAN is enabled. This happens because since the tracepoint was added in touch_buffer(), it references the dev_t member bh->b_bdev->bd_dev regardless of whether the buffer head has a pointer to a block_device structure. In the current implementation, the block_device structure is set after the function returns to the caller. Here, touch_buffer() is used to mark the folio/page that owns the buffer head as accessed, but the common search helper for folio/page used by the caller function was optimized to mark the folio/page as accessed when it was reimplemented a long time ago, eliminating the need to call touch_buffer() here in the first place. So this solves the issue by eliminating the touch_buffer() call itself. Link: https://lkml.kernel.org/r/20241106160811.3316-1-konishi.ryusuke@gmail.com Link: https://lkml.kernel.org/r/20241106160811.3316-2-konishi.ryusuke@gmail.com Fixes: 5305cb830834 ("block: add block_{touch|dirty}_buffer tracepoint") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: Ubisectech Sirius <bugreport(a)valiantsec.com> Closes: https://lkml.kernel.org/r/86bd3013-887e-4e38-960f-ca45c657f032.bugreport@va… Reported-by: syzbot+9982fb8d18eba905abe2(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=9982fb8d18eba905abe2 Tested-by: syzbot+9982fb8d18eba905abe2(a)syzkaller.appspotmail.com Cc: Tejun Heo <tj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/nilfs2/page.c | 1 - 1 file changed, 1 deletion(-) --- a/fs/nilfs2/page.c~nilfs2-fix-null-ptr-deref-in-block_touch_buffer-tracepoint +++ a/fs/nilfs2/page.c @@ -39,7 +39,6 @@ static struct buffer_head *__nilfs_get_f first_block = (unsigned long)index << (PAGE_SHIFT - blkbits); bh = get_nth_bh(bh, block - first_block); - touch_buffer(bh); wait_on_buffer(bh); return bh; } _ Patches currently in -mm which might be from konishi.ryusuke(a)gmail.com are nilfs2-fix-null-ptr-deref-in-block_touch_buffer-tracepoint.patch nilfs2-fix-null-ptr-deref-in-block_dirty_buffer-tracepoint.patch

7 months, 3 weeks

1
0
0 0

+ mm-page_alloc-move-mlocked-flag-clearance-into-free_pages_prepare.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: page_alloc: move mlocked flag clearance into free_pages_prepare() has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-page_alloc-move-mlocked-flag-clearance-into-free_pages_prepare.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Roman Gushchin <roman.gushchin(a)linux.dev> Subject: mm: page_alloc: move mlocked flag clearance into free_pages_prepare() Date: Wed, 6 Nov 2024 19:53:54 +0000 Syzbot reported a bad page state problem caused by a page being freed using free_page() still having a mlocked flag at free_pages_prepare() stage: BUG: Bad page state in process syz.5.504 pfn:61f45 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x61f45 flags: 0xfff00000080204(referenced|workingset|mlocked|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000080204 0000000000000000 dead000000000122 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x400dc0(GFP_KERNEL_ACCOUNT|__GFP_ZERO), pid 8443, tgid 8442 (syz.5.504), ts 201884660643, free_ts 201499827394 set_page_owner include/linux/page_owner.h:32 [inline] post_alloc_hook+0x1f3/0x230 mm/page_alloc.c:1537 prep_new_page mm/page_alloc.c:1545 [inline] get_page_from_freelist+0x303f/0x3190 mm/page_alloc.c:3457 __alloc_pages_noprof+0x292/0x710 mm/page_alloc.c:4733 alloc_pages_mpol_noprof+0x3e8/0x680 mm/mempolicy.c:2265 kvm_coalesced_mmio_init+0x1f/0xf0 virt/kvm/coalesced_mmio.c:99 kvm_create_vm virt/kvm/kvm_main.c:1235 [inline] kvm_dev_ioctl_create_vm virt/kvm/kvm_main.c:5488 [inline] kvm_dev_ioctl+0x12dc/0x2240 virt/kvm/kvm_main.c:5530 __do_compat_sys_ioctl fs/ioctl.c:1007 [inline] __se_compat_sys_ioctl+0x510/0xc90 fs/ioctl.c:950 do_syscall_32_irqs_on arch/x86/entry/common.c:165 [inline] __do_fast_syscall_32+0xb4/0x110 arch/x86/entry/common.c:386 do_fast_syscall_32+0x34/0x80 arch/x86/entry/common.c:411 entry_SYSENTER_compat_after_hwframe+0x84/0x8e page last free pid 8399 tgid 8399 stack trace: reset_page_owner include/linux/page_owner.h:25 [inline] free_pages_prepare mm/page_alloc.c:1108 [inline] free_unref_folios+0xf12/0x18d0 mm/page_alloc.c:2686 folios_put_refs+0x76c/0x860 mm/swap.c:1007 free_pages_and_swap_cache+0x5c8/0x690 mm/swap_state.c:335 __tlb_batch_free_encoded_pages mm/mmu_gather.c:136 [inline] tlb_batch_pages_flush mm/mmu_gather.c:149 [inline] tlb_flush_mmu_free mm/mmu_gather.c:366 [inline] tlb_flush_mmu+0x3a3/0x680 mm/mmu_gather.c:373 tlb_finish_mmu+0xd4/0x200 mm/mmu_gather.c:465 exit_mmap+0x496/0xc40 mm/mmap.c:1926 __mmput+0x115/0x390 kernel/fork.c:1348 exit_mm+0x220/0x310 kernel/exit.c:571 do_exit+0x9b2/0x28e0 kernel/exit.c:926 do_group_exit+0x207/0x2c0 kernel/exit.c:1088 __do_sys_exit_group kernel/exit.c:1099 [inline] __se_sys_exit_group kernel/exit.c:1097 [inline] __x64_sys_exit_group+0x3f/0x40 kernel/exit.c:1097 x64_sys_call+0x2634/0x2640 arch/x86/include/generated/asm/syscalls_64.h:232 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Modules linked in: CPU: 0 UID: 0 PID: 8442 Comm: syz.5.504 Not tainted 6.12.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 bad_page+0x176/0x1d0 mm/page_alloc.c:501 free_page_is_bad mm/page_alloc.c:918 [inline] free_pages_prepare mm/page_alloc.c:1100 [inline] free_unref_page+0xed0/0xf20 mm/page_alloc.c:2638 kvm_destroy_vm virt/kvm/kvm_main.c:1327 [inline] kvm_put_kvm+0xc75/0x1350 virt/kvm/kvm_main.c:1386 kvm_vcpu_release+0x54/0x60 virt/kvm/kvm_main.c:4143 __fput+0x23f/0x880 fs/file_table.c:431 task_work_run+0x24f/0x310 kernel/task_work.c:239 exit_task_work include/linux/task_work.h:43 [inline] do_exit+0xa2f/0x28e0 kernel/exit.c:939 do_group_exit+0x207/0x2c0 kernel/exit.c:1088 __do_sys_exit_group kernel/exit.c:1099 [inline] __se_sys_exit_group kernel/exit.c:1097 [inline] __ia32_sys_exit_group+0x3f/0x40 kernel/exit.c:1097 ia32_sys_call+0x2624/0x2630 arch/x86/include/generated/asm/syscalls_32.h:253 do_syscall_32_irqs_on arch/x86/entry/common.c:165 [inline] __do_fast_syscall_32+0xb4/0x110 arch/x86/entry/common.c:386 do_fast_syscall_32+0x34/0x80 arch/x86/entry/common.c:411 entry_SYSENTER_compat_after_hwframe+0x84/0x8e RIP: 0023:0xf745d579 Code: Unable to access opcode bytes at 0xf745d54f. RSP: 002b:00000000f75afd6c EFLAGS: 00000206 ORIG_RAX: 00000000000000fc RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 00000000ffffff9c RDI: 00000000f744cff4 RBP: 00000000f717ae61 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 </TASK> The problem was originally introduced by commit b109b87050df ("mm/munlock: replace clear_page_mlock() by final clearance"): it was focused on handling pagecache and anonymous memory and wasn't suitable for lower level get_page()/free_page() API's used for example by KVM, as with this reproducer. Fix it by moving the mlocked flag clearance down to free_page_prepare(). The bug itself if fairly old and harmless (aside from generating these warnings), aside from a small memory leak - "bad" pages are stopped from being allocated again. Link: https://lkml.kernel.org/r/20241106195354.270757-1-roman.gushchin@linux.dev Fixes: b109b87050df ("mm/munlock: replace clear_page_mlock() by final clearance") Signed-off-by: Roman Gushchin <roman.gushchin(a)linux.dev> Reported-by: syzbot+e985d3026c4fd041578e(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/6729f475.050a0220.701a.0019.GAE@google.com Acked-by: Hugh Dickins <hughd(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_alloc.c | 15 +++++++++++++++ mm/swap.c | 14 -------------- 2 files changed, 15 insertions(+), 14 deletions(-) --- a/mm/page_alloc.c~mm-page_alloc-move-mlocked-flag-clearance-into-free_pages_prepare +++ a/mm/page_alloc.c @@ -1048,6 +1048,7 @@ __always_inline bool free_pages_prepare( bool skip_kasan_poison = should_skip_kasan_poison(page); bool init = want_init_on_free(); bool compound = PageCompound(page); + struct folio *folio = page_folio(page); VM_BUG_ON_PAGE(PageTail(page), page); @@ -1057,6 +1058,20 @@ __always_inline bool free_pages_prepare( if (memcg_kmem_online() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); + /* + * In rare cases, when truncation or holepunching raced with + * munlock after VM_LOCKED was cleared, Mlocked may still be + * found set here. This does not indicate a problem, unless + * "unevictable_pgs_cleared" appears worryingly large. + */ + if (unlikely(folio_test_mlocked(folio))) { + long nr_pages = folio_nr_pages(folio); + + __folio_clear_mlocked(folio); + zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); + count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); + } + if (unlikely(PageHWPoison(page)) && !order) { /* Do not let hwpoison pages hit pcplists/buddy */ reset_page_owner(page, order); --- a/mm/swap.c~mm-page_alloc-move-mlocked-flag-clearance-into-free_pages_prepare +++ a/mm/swap.c @@ -78,20 +78,6 @@ static void __page_cache_release(struct lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } - - /* - * In rare cases, when truncation or holepunching raced with - * munlock after VM_LOCKED was cleared, Mlocked may still be - * found set here. This does not indicate a problem, unless - * "unevictable_pgs_cleared" appears worryingly large. - */ - if (unlikely(folio_test_mlocked(folio))) { - long nr_pages = folio_nr_pages(folio); - - __folio_clear_mlocked(folio); - zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); - count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); - } } /* _ Patches currently in -mm which might be from roman.gushchin(a)linux.dev are signal-restore-the-override_rlimit-logic.patch mm-page_alloc-move-mlocked-flag-clearance-into-free_pages_prepare.patch

7 months, 3 weeks

1
0
0 0

[PATCH v3] mm: page_alloc: move mlocked flag clearance into free_pages_prepare()

by Roman Gushchin

Syzbot reported a bad page state problem caused by a page being freed using free_page() still having a mlocked flag at free_pages_prepare() stage: BUG: Bad page state in process syz.5.504 pfn:61f45 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x61f45 flags: 0xfff00000080204(referenced|workingset|mlocked|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000080204 0000000000000000 dead000000000122 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x400dc0(GFP_KERNEL_ACCOUNT|__GFP_ZERO), pid 8443, tgid 8442 (syz.5.504), ts 201884660643, free_ts 201499827394 set_page_owner include/linux/page_owner.h:32 [inline] post_alloc_hook+0x1f3/0x230 mm/page_alloc.c:1537 prep_new_page mm/page_alloc.c:1545 [inline] get_page_from_freelist+0x303f/0x3190 mm/page_alloc.c:3457 __alloc_pages_noprof+0x292/0x710 mm/page_alloc.c:4733 alloc_pages_mpol_noprof+0x3e8/0x680 mm/mempolicy.c:2265 kvm_coalesced_mmio_init+0x1f/0xf0 virt/kvm/coalesced_mmio.c:99 kvm_create_vm virt/kvm/kvm_main.c:1235 [inline] kvm_dev_ioctl_create_vm virt/kvm/kvm_main.c:5488 [inline] kvm_dev_ioctl+0x12dc/0x2240 virt/kvm/kvm_main.c:5530 __do_compat_sys_ioctl fs/ioctl.c:1007 [inline] __se_compat_sys_ioctl+0x510/0xc90 fs/ioctl.c:950 do_syscall_32_irqs_on arch/x86/entry/common.c:165 [inline] __do_fast_syscall_32+0xb4/0x110 arch/x86/entry/common.c:386 do_fast_syscall_32+0x34/0x80 arch/x86/entry/common.c:411 entry_SYSENTER_compat_after_hwframe+0x84/0x8e page last free pid 8399 tgid 8399 stack trace: reset_page_owner include/linux/page_owner.h:25 [inline] free_pages_prepare mm/page_alloc.c:1108 [inline] free_unref_folios+0xf12/0x18d0 mm/page_alloc.c:2686 folios_put_refs+0x76c/0x860 mm/swap.c:1007 free_pages_and_swap_cache+0x5c8/0x690 mm/swap_state.c:335 __tlb_batch_free_encoded_pages mm/mmu_gather.c:136 [inline] tlb_batch_pages_flush mm/mmu_gather.c:149 [inline] tlb_flush_mmu_free mm/mmu_gather.c:366 [inline] tlb_flush_mmu+0x3a3/0x680 mm/mmu_gather.c:373 tlb_finish_mmu+0xd4/0x200 mm/mmu_gather.c:465 exit_mmap+0x496/0xc40 mm/mmap.c:1926 __mmput+0x115/0x390 kernel/fork.c:1348 exit_mm+0x220/0x310 kernel/exit.c:571 do_exit+0x9b2/0x28e0 kernel/exit.c:926 do_group_exit+0x207/0x2c0 kernel/exit.c:1088 __do_sys_exit_group kernel/exit.c:1099 [inline] __se_sys_exit_group kernel/exit.c:1097 [inline] __x64_sys_exit_group+0x3f/0x40 kernel/exit.c:1097 x64_sys_call+0x2634/0x2640 arch/x86/include/generated/asm/syscalls_64.h:232 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Modules linked in: CPU: 0 UID: 0 PID: 8442 Comm: syz.5.504 Not tainted 6.12.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 bad_page+0x176/0x1d0 mm/page_alloc.c:501 free_page_is_bad mm/page_alloc.c:918 [inline] free_pages_prepare mm/page_alloc.c:1100 [inline] free_unref_page+0xed0/0xf20 mm/page_alloc.c:2638 kvm_destroy_vm virt/kvm/kvm_main.c:1327 [inline] kvm_put_kvm+0xc75/0x1350 virt/kvm/kvm_main.c:1386 kvm_vcpu_release+0x54/0x60 virt/kvm/kvm_main.c:4143 __fput+0x23f/0x880 fs/file_table.c:431 task_work_run+0x24f/0x310 kernel/task_work.c:239 exit_task_work include/linux/task_work.h:43 [inline] do_exit+0xa2f/0x28e0 kernel/exit.c:939 do_group_exit+0x207/0x2c0 kernel/exit.c:1088 __do_sys_exit_group kernel/exit.c:1099 [inline] __se_sys_exit_group kernel/exit.c:1097 [inline] __ia32_sys_exit_group+0x3f/0x40 kernel/exit.c:1097 ia32_sys_call+0x2624/0x2630 arch/x86/include/generated/asm/syscalls_32.h:253 do_syscall_32_irqs_on arch/x86/entry/common.c:165 [inline] __do_fast_syscall_32+0xb4/0x110 arch/x86/entry/common.c:386 do_fast_syscall_32+0x34/0x80 arch/x86/entry/common.c:411 entry_SYSENTER_compat_after_hwframe+0x84/0x8e RIP: 0023:0xf745d579 Code: Unable to access opcode bytes at 0xf745d54f. RSP: 002b:00000000f75afd6c EFLAGS: 00000206 ORIG_RAX: 00000000000000fc RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 00000000ffffff9c RDI: 00000000f744cff4 RBP: 00000000f717ae61 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 </TASK> The problem was originally introduced by commit b109b87050df ("mm/munlock: replace clear_page_mlock() by final clearance"): it was handling focused on handling pagecache and anonymous memory and wasn't suitable for lower level get_page()/free_page() API's used for example by KVM, as with this reproducer. Fix it by moving the mlocked flag clearance down to free_page_prepare(). The bug itself if fairly old and harmless (aside from generating these warnings), aside from a small memory leak - "bad" pages are stopped from being allocated again. Reported-by: syzbot+e985d3026c4fd041578e(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/6729f475.050a0220.701a.0019.GAE@google.com Fixes: b109b87050df ("mm/munlock: replace clear_page_mlock() by final clearance") Signed-off-by: Roman Gushchin <roman.gushchin(a)linux.dev> Acked-by: Hugh Dickins <hughd(a)google.com> Cc: <stable(a)vger.kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> --- mm/page_alloc.c | 15 +++++++++++++++ mm/swap.c | 14 -------------- 2 files changed, 15 insertions(+), 14 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 47048b39b8ca..371d1c6c1fc7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1048,6 +1048,7 @@ __always_inline bool free_pages_prepare(struct page *page, bool skip_kasan_poison = should_skip_kasan_poison(page); bool init = want_init_on_free(); bool compound = PageCompound(page); + struct folio *folio = page_folio(page); VM_BUG_ON_PAGE(PageTail(page), page); @@ -1057,6 +1058,20 @@ __always_inline bool free_pages_prepare(struct page *page, if (memcg_kmem_online() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); + /* + * In rare cases, when truncation or holepunching raced with + * munlock after VM_LOCKED was cleared, Mlocked may still be + * found set here. This does not indicate a problem, unless + * "unevictable_pgs_cleared" appears worryingly large. + */ + if (unlikely(folio_test_mlocked(folio))) { + long nr_pages = folio_nr_pages(folio); + + __folio_clear_mlocked(folio); + zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); + count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); + } + if (unlikely(PageHWPoison(page)) && !order) { /* Do not let hwpoison pages hit pcplists/buddy */ reset_page_owner(page, order); diff --git a/mm/swap.c b/mm/swap.c index 638a3f001676..10decd9dffa1 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -78,20 +78,6 @@ static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } - - /* - * In rare cases, when truncation or holepunching raced with - * munlock after VM_LOCKED was cleared, Mlocked may still be - * found set here. This does not indicate a problem, unless - * "unevictable_pgs_cleared" appears worryingly large. - */ - if (unlikely(folio_test_mlocked(folio))) { - long nr_pages = folio_nr_pages(folio); - - __folio_clear_mlocked(folio); - zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); - count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); - } } /* -- 2.47.0.199.ga7371fff76-goog

7 months, 3 weeks

1
0
0 0

[PATCH v3] arm64/signal: Avoid corruption of SME state when entering signal handler

by Mark Brown

We intend that signal handlers are entered with PSTATE.{SM,ZA}={0,0}. The logic for this in setup_return() manipulates the saved state and live CPU state in an unsafe manner, and consequently, when a task enters a signal handler: * The task entering the signal handler might not have its PSTATE.{SM,ZA} bits cleared, and other register state that is affected by changes to PSTATE.{SM,ZA} might not be zeroed as expected. * An unrelated task might have its PSTATE.{SM,ZA} bits cleared unexpectedly, potentially zeroing other register state that is affected by changes to PSTATE.{SM,ZA}. Tasks which do not set PSTATE.{SM,ZA} (i.e. those only using plain FPSIMD or non-streaming SVE) are not affected, as there is no resulting change to PSTATE.{SM,ZA}. Consider for example two tasks on one CPU: A: Begins signal entry in kernel mode, is preempted prior to SMSTOP. B: Using SM and/or ZA in userspace with register state current on the CPU, is preempted. A: Scheduled in, no register state changes made as in kernel mode. A: Executes SMSTOP, modifying live register state. A: Scheduled out. B: Scheduled in, fpsimd_thread_switch() sees the register state on the CPU is tracked as being that for task B so the state is not reloaded prior to returning to userspace. Task B is now running with SM and ZA incorrectly cleared. Fix this by: * Checking TIF_FOREIGN_FPSTATE, and only updating the saved or live state as appropriate. * Using {get,put}_cpu_fpsimd_context() to ensure mutual exclusion against other code which manipulates this state. To allow their use, the logic is moved into a new fpsimd_enter_sighandler() helper in fpsimd.c. This race has been observed intermittently with fp-stress, especially with preempt disabled, commonly but not exclusively reporting "Bad SVCR: 0". While we're at it also fix a discrepancy between in register and in memory entries. When operating on the register state we issue a SMSTOP, exiting streaming mode if we were in it. This clears the V/Z and P register and FPMR but nothing else. The in memory version clears all the user FPSIMD state including FPCR and FPSR but does not clear FPMR. Add the clear of FPMR and limit the existing memset() to only cover the vregs, preserving the state of FPCR and FPSR like SMSTOP does. Fixes: 40a8e87bb3285 ("arm64/sme: Disable ZA and streaming mode when handling signals") Signed-off-by: Mark Brown <broonie(a)kernel.org> Cc: stable(a)vger.kernel.org --- Changes in v3: - Fix the in memory update to follow the behaviour of the SMSTOP we issue when updating in registers. - Link to v2: https://lore.kernel.org/r/20241030-arm64-fp-sme-sigentry-v2-1-43ce805d1b20@… Changes in v2: - Commit message tweaks. - Flush the task state when updating in memory to ensure we reload. - Link to v1: https://lore.kernel.org/r/20241023-arm64-fp-sme-sigentry-v1-1-249ff7ec3ad0@… --- arch/arm64/include/asm/fpsimd.h | 1 + arch/arm64/kernel/fpsimd.c | 39 +++++++++++++++++++++++++++++++++++++++ arch/arm64/kernel/signal.c | 19 +------------------ 3 files changed, 41 insertions(+), 18 deletions(-) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index f2a84efc361858d4deda99faf1967cc7cac386c1..09af7cfd9f6c2cec26332caa4c254976e117b1bf 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -76,6 +76,7 @@ extern void fpsimd_load_state(struct user_fpsimd_state *state); extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); +extern void fpsimd_enter_sighandler(void); extern void fpsimd_signal_preserve_current_state(void); extern void fpsimd_preserve_current_state(void); extern void fpsimd_restore_current_state(void); diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 77006df20a75aee7c991cf116b6d06bfe953d1a4..10c8efd1c5ce83f4ea4025b213111ab9519263b1 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1693,6 +1693,45 @@ void fpsimd_signal_preserve_current_state(void) sve_to_fpsimd(current); } +/* + * Called by the signal handling code when preparing current to enter + * a signal handler. Currently this only needs to take care of exiting + * streaming mode and clearing ZA on SME systems. + */ +void fpsimd_enter_sighandler(void) +{ + if (!system_supports_sme()) + return; + + get_cpu_fpsimd_context(); + + if (test_thread_flag(TIF_FOREIGN_FPSTATE)) { + /* + * Exiting streaming mode zeros the V/Z and P + * registers and FPMR. Zero FPMR and the V registers, + * marking the state as FPSIMD only to force a clear + * of the remaining bits during reload if needed. + */ + if (current->thread.svcr & SVCR_SM_MASK) { + memset(&current->thread.uw.fpsimd_state.vregs, 0, + sizeof(current->thread.uw.fpsimd_state.vregs)); + current->thread.uw.fpmr = 0; + current->thread.fp_type = FP_STATE_FPSIMD; + } + + current->thread.svcr &= ~(SVCR_ZA_MASK | + SVCR_SM_MASK); + + /* Ensure any copies on other CPUs aren't reused */ + fpsimd_flush_task_state(current); + } else { + /* The register state is current, just update it. */ + sme_smstop(); + } + + put_cpu_fpsimd_context(); +} + /* * Called by KVM when entering the guest. */ diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 5619869475304776fc005fe24a385bf86bfdd253..fe07d0bd9f7978d73973f07ce38b7bdd7914abb2 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -1218,24 +1218,7 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, /* TCO (Tag Check Override) always cleared for signal handlers */ regs->pstate &= ~PSR_TCO_BIT; - /* Signal handlers are invoked with ZA and streaming mode disabled */ - if (system_supports_sme()) { - /* - * If we were in streaming mode the saved register - * state was SVE but we will exit SM and use the - * FPSIMD register state - flush the saved FPSIMD - * register state in case it gets loaded. - */ - if (current->thread.svcr & SVCR_SM_MASK) { - memset(&current->thread.uw.fpsimd_state, 0, - sizeof(current->thread.uw.fpsimd_state)); - current->thread.fp_type = FP_STATE_FPSIMD; - } - - current->thread.svcr &= ~(SVCR_ZA_MASK | - SVCR_SM_MASK); - sme_smstop(); - } + fpsimd_enter_sighandler(); if (system_supports_poe()) write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0); --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241023-arm64-fp-sme-sigentry-a2bd7187e71b Best regards, -- Mark Brown <broonie(a)kernel.org>

7 months, 3 weeks

1
0
0 0

[PATCH] perf/x86/intel: Fix bitmask of OCR and FRONTEND events for LNC

by kan.liang＠linux.intel.com

From: Kan Liang <kan.liang(a)linux.intel.com> The released OCR and FRONTEND events utilized more bits on Lunar Lake p-core. The corresponding mask in the extra_regs has to be extended to unblock the extra bits. Add a dedicated intel_lnc_extra_regs. Fixes: a932aa0e868f ("perf/x86: Add Lunar Lake and Arrow Lake support") Reported-by: Andi Kleen <ak(a)linux.intel.com> Signed-off-by: Kan Liang <kan.liang(a)linux.intel.com> Cc: stable(a)vger.kernel.org --- arch/x86/events/intel/core.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index bb284aff7bfd..a347b4323256 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -429,6 +429,16 @@ static struct event_constraint intel_lnc_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_lnc_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0xfffffffffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0xfffffffffffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE), + INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), + INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0xf, FE), + INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), + EVENT_EXTRA_END +}; EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); @@ -6422,7 +6432,7 @@ static __always_inline void intel_pmu_init_lnc(struct pmu *pmu) intel_pmu_init_glc(pmu); hybrid(pmu, event_constraints) = intel_lnc_event_constraints; hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints; - hybrid(pmu, extra_regs) = intel_rwc_extra_regs; + hybrid(pmu, extra_regs) = intel_lnc_extra_regs; } static __always_inline void intel_pmu_init_skt(struct pmu *pmu) -- 2.38.1

7 months, 3 weeks

1
0
0 0

[PATCH 6.1.y 5.15.y 5.10.y] net: do not delay dst_entries_add() in dst_release()

by Abdelkareem Abdelsaamad

From: Eric Dumazet <edumazet(a)google.com> commit ac888d58869bb99753e7652be19a151df9ecb35d upstream. dst_entries_add() uses per-cpu data that might be freed at netns dismantle from ip6_route_net_exit() calling dst_entries_destroy() Before ip6_route_net_exit() can be called, we release all the dsts associated with this netns, via calls to dst_release(), which waits an rcu grace period before calling dst_destroy() dst_entries_add() use in dst_destroy() is racy, because dst_entries_destroy() could have been called already. Decrementing the number of dsts must happen sooner. Notes: 1) in CONFIG_XFRM case, dst_destroy() can call dst_release_immediate(child), this might also cause UAF if the child does not have DST_NOCOUNT set. IPSEC maintainers might take a look and see how to address this. 2) There is also discussion about removing this count of dst, which might happen in future kernels. Fixes: f88649721268 ("ipv4: fix dst race in sk_dst_get()") Closes: https://lore.kernel.org/lkml/CANn89iLCCGsP7SFn9HKpvnKu96Td4KD08xf7aGtiYgZnk… Reported-by: Naresh Kamboju <naresh.kamboju(a)linaro.org> Tested-by: Linux Kernel Functional Testing <lkft(a)linaro.org> Tested-by: Naresh Kamboju <naresh.kamboju(a)linaro.org> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: Xin Long <lucien.xin(a)gmail.com> Cc: Steffen Klassert <steffen.klassert(a)secunet.com> Reviewed-by: Xin Long <lucien.xin(a)gmail.com> Link: https://patch.msgid.link/20241008143110.1064899-1-edumazet@google.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> [Conflict due to bc9d3a9f2afc ("net: dst: Switch to rcuref_t reference counting") is not in the tree] Signed-off-by: Abdelkareem Abdelsaamad <kareemem(a)amazon.com> --- net/core/dst.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/net/core/dst.c b/net/core/dst.c index 453ec8aafc4a..5bb143857336 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -109,9 +109,6 @@ struct dst_entry *dst_destroy(struct dst_entry * dst) child = xdst->child; } #endif - if (!(dst->flags & DST_NOCOUNT)) - dst_entries_add(dst->ops, -1); - if (dst->ops->destroy) dst->ops->destroy(dst); if (dst->dev) @@ -162,6 +159,12 @@ void dst_dev_put(struct dst_entry *dst) } EXPORT_SYMBOL(dst_dev_put); +static void dst_count_dec(struct dst_entry *dst) +{ + if (!(dst->flags & DST_NOCOUNT)) + dst_entries_add(dst->ops, -1); +} + void dst_release(struct dst_entry *dst) { if (dst) { @@ -171,8 +174,10 @@ void dst_release(struct dst_entry *dst) if (WARN_ONCE(newrefcnt < 0, "dst_release underflow")) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); - if (!newrefcnt) + if (!newrefcnt){ + dst_count_dec(dst); call_rcu(&dst->rcu_head, dst_destroy_rcu); + } } } EXPORT_SYMBOL(dst_release); @@ -186,8 +191,10 @@ void dst_release_immediate(struct dst_entry *dst) if (WARN_ONCE(newrefcnt < 0, "dst_release_immediate underflow")) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); - if (!newrefcnt) + if (!newrefcnt){ + dst_count_dec(dst); dst_destroy(dst); + } } } EXPORT_SYMBOL(dst_release_immediate); -- 2.40.1

7 months, 3 weeks

1
0
0 0

[PATCH 22/31] ASoC: da7213: Populate max_register to regmap_config

by Claudiu

From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> On the Renesas RZ/G3S SMARC Carrier II board having a DA7212 codec (using da7213 driver) connected to one SSIF-2 available on the Renesas RZ/G3S SoC it has been discovered that using the runtime PM API for suspend/resume (as will be proposed in the following commits) leads to the codec not being propertly initialized after resume. This is because w/o max_register populated to regmap_config the regcache_rbtree_sync() breaks on base_reg > max condition and the regcache_sync_block() call is skipped. Fixes: ef5c2eba2412 ("ASoC: codecs: Add da7213 codec") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> --- sound/soc/codecs/da7213.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c index f3ef6fb55304..486db60bf2dd 100644 --- a/sound/soc/codecs/da7213.c +++ b/sound/soc/codecs/da7213.c @@ -2136,6 +2136,7 @@ static const struct regmap_config da7213_regmap_config = { .reg_bits = 8, .val_bits = 8, + .max_register = DA7213_TONE_GEN_OFF_PER, .reg_defaults = da7213_reg_defaults, .num_reg_defaults = ARRAY_SIZE(da7213_reg_defaults), .volatile_reg = da7213_volatile_register, -- 2.39.2

7 months, 3 weeks

4
3
0 0

[PATCH 6.11.y 1/2] rcu/kvfree: Add kvfree_rcu_barrier() API

by Suren Baghdasaryan

From: "Uladzislau Rezki (Sony)" <urezki(a)gmail.com> From: Uladzislau Rezki <urezki(a)gmail.com> commit 3c5d61ae919cc377c71118ccc76fa6e8518023f8 upstream. Add a kvfree_rcu_barrier() function. It waits until all in-flight pointers are freed over RCU machinery. It does not wait any GP completion and it is within its right to return immediately if there are no outstanding pointers. This function is useful when there is a need to guarantee that a memory is fully freed before destroying memory caches. For example, during unloading a kernel module. Signed-off-by: Uladzislau Rezki (Sony) <urezki(a)gmail.com> Signed-off-by: Vlastimil Babka <vbabka(a)suse.cz> --- include/linux/rcutiny.h | 5 ++ include/linux/rcutree.h | 1 + kernel/rcu/tree.c | 109 +++++++++++++++++++++++++++++++++++++--- 3 files changed, 107 insertions(+), 8 deletions(-) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index d9ac7b136aea..522123050ff8 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -111,6 +111,11 @@ static inline void __kvfree_call_rcu(struct rcu_head *head, void *ptr) kvfree(ptr); } +static inline void kvfree_rcu_barrier(void) +{ + rcu_barrier(); +} + #ifdef CONFIG_KASAN_GENERIC void kvfree_call_rcu(struct rcu_head *head, void *ptr); #else diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 254244202ea9..58e7db80f3a8 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -35,6 +35,7 @@ static inline void rcu_virt_note_context_switch(void) void synchronize_rcu_expedited(void); void kvfree_call_rcu(struct rcu_head *head, void *ptr); +void kvfree_rcu_barrier(void); void rcu_barrier(void); void rcu_momentary_dyntick_idle(void); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e641cc681901..be00aac5f4e7 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3584,18 +3584,15 @@ kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp) } /* - * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. + * Return: %true if a work is queued, %false otherwise. */ -static void kfree_rcu_monitor(struct work_struct *work) +static bool +kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp) { - struct kfree_rcu_cpu *krcp = container_of(work, - struct kfree_rcu_cpu, monitor_work.work); unsigned long flags; + bool queued = false; int i, j; - // Drain ready for reclaim. - kvfree_rcu_drain_ready(krcp); - raw_spin_lock_irqsave(&krcp->lock, flags); // Attempt to start a new batch. @@ -3634,11 +3631,27 @@ static void kfree_rcu_monitor(struct work_struct *work) // be that the work is in the pending state when // channels have been detached following by each // other. - queue_rcu_work(system_wq, &krwp->rcu_work); + queued = queue_rcu_work(system_wq, &krwp->rcu_work); } } raw_spin_unlock_irqrestore(&krcp->lock, flags); + return queued; +} + +/* + * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. + */ +static void kfree_rcu_monitor(struct work_struct *work) +{ + struct kfree_rcu_cpu *krcp = container_of(work, + struct kfree_rcu_cpu, monitor_work.work); + + // Drain ready for reclaim. + kvfree_rcu_drain_ready(krcp); + + // Queue a batch for a rest. + kvfree_rcu_queue_batch(krcp); // If there is nothing to detach, it means that our job is // successfully done here. In case of having at least one @@ -3859,6 +3872,86 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr) } EXPORT_SYMBOL_GPL(kvfree_call_rcu); +/** + * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete. + * + * Note that a single argument of kvfree_rcu() call has a slow path that + * triggers synchronize_rcu() following by freeing a pointer. It is done + * before the return from the function. Therefore for any single-argument + * call that will result in a kfree() to a cache that is to be destroyed + * during module exit, it is developer's responsibility to ensure that all + * such calls have returned before the call to kmem_cache_destroy(). + */ +void kvfree_rcu_barrier(void) +{ + struct kfree_rcu_cpu_work *krwp; + struct kfree_rcu_cpu *krcp; + bool queued; + int i, cpu; + + /* + * Firstly we detach objects and queue them over an RCU-batch + * for all CPUs. Finally queued works are flushed for each CPU. + * + * Please note. If there are outstanding batches for a particular + * CPU, those have to be finished first following by queuing a new. + */ + for_each_possible_cpu(cpu) { + krcp = per_cpu_ptr(&krc, cpu); + + /* + * Check if this CPU has any objects which have been queued for a + * new GP completion. If not(means nothing to detach), we are done + * with it. If any batch is pending/running for this "krcp", below + * per-cpu flush_rcu_work() waits its completion(see last step). + */ + if (!need_offload_krc(krcp)) + continue; + + while (1) { + /* + * If we are not able to queue a new RCU work it means: + * - batches for this CPU are still in flight which should + * be flushed first and then repeat; + * - no objects to detach, because of concurrency. + */ + queued = kvfree_rcu_queue_batch(krcp); + + /* + * Bail out, if there is no need to offload this "krcp" + * anymore. As noted earlier it can run concurrently. + */ + if (queued || !need_offload_krc(krcp)) + break; + + /* There are ongoing batches. */ + for (i = 0; i < KFREE_N_BATCHES; i++) { + krwp = &(krcp->krw_arr[i]); + flush_rcu_work(&krwp->rcu_work); + } + } + } + + /* + * Now we guarantee that all objects are flushed. + */ + for_each_possible_cpu(cpu) { + krcp = per_cpu_ptr(&krc, cpu); + + /* + * A monitor work can drain ready to reclaim objects + * directly. Wait its completion if running or pending. + */ + cancel_delayed_work_sync(&krcp->monitor_work); + + for (i = 0; i < KFREE_N_BATCHES; i++) { + krwp = &(krcp->krw_arr[i]); + flush_rcu_work(&krwp->rcu_work); + } + } +} +EXPORT_SYMBOL_GPL(kvfree_rcu_barrier); + static unsigned long kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { base-commit: 17365d66f1c6aa6bf4f4cb9842f5edeac027bcfb -- 2.47.0.105.g07ac214952-goog

7 months, 3 weeks

2
6
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror November 2024