October 2025 - Linux-stable-mirror

[PATCH 5.10.y 0/3] v5.10: fix build with GCC 15

by Matthieu Baerts (NGI0)

This kernel version doesn't build with GCC 15: In file included from include/uapi/linux/posix_types.h:5, from include/uapi/linux/types.h:14, from include/linux/types.h:6, from arch/x86/realmode/rm/wakeup.h:11, from arch/x86/realmode/rm/wakemain.c:2: include/linux/stddef.h:11:9: error: cannot use keyword 'false' as enumeration constant 11 | false = 0, | ^~~~~ include/linux/stddef.h:11:9: note: 'false' is a keyword with '-std=c23' onwards include/linux/types.h:30:33: error: 'bool' cannot be defined via 'typedef' 30 | typedef _Bool bool; | ^~~~ include/linux/types.h:30:33: note: 'bool' is a keyword with '-std=c23' onwards include/linux/types.h:30:1: warning: useless type name in empty declaration 30 | typedef _Bool bool; | ^~~~~~~ I initially fixed this by adding -std=gnu11 in arch/x86/Makefile, then I realised this fix was already done in an upstream commit, created before the GCC 15 release and not mentioning the error I had. This is the first patch. When I was investigating my error, I noticed other commits were already backported to stable versions. They were all adding -std=gnu11 in different Makefiles. In their commit message, they were mentioning 'gnu11' was picked to use the same as the one from the main Makefile. But this is not the case in this kernel version. Patch 2 fixes that. Finally, I noticed an extra warning that I didn't have in v5.15. Patch 3 fixes that. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Alexey Dobriyan (1): x86/boot: Compile boot code with -std=gnu11 too Matthieu Baerts (NGI0) (2): arch: back to -std=gnu89 in < v5.18 tracing: fix declaration-after-statement warning arch/parisc/boot/compressed/Makefile | 2 +- arch/s390/Makefile | 2 +- arch/s390/purgatory/Makefile | 2 +- arch/x86/Makefile | 2 +- arch/x86/boot/compressed/Makefile | 2 +- drivers/firmware/efi/libstub/Makefile | 2 +- kernel/trace/trace_events_synth.c | 3 ++- 7 files changed, 8 insertions(+), 7 deletions(-) --- base-commit: a32db271d59d9f35f3a937ac27fcc2db1e029cdc change-id: 20251017-v5-10-gcc-15-ad2510f784f7 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 week, 3 days

4
6
0 0

[PATCH 6.12.y] f2fs: fix to avoid panic once fallocation fails for pinfile

by Rajani Kantha

From: Chao Yu <chao(a)kernel.org> [ Upstream commit 48ea8b200414ac69ea96f4c231f5c7ef1fbeffef ] syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:2746! CPU: 0 UID: 0 PID: 5323 Comm: syz.0.0 Not tainted 6.13.0-rc2-syzkaller-00018-g7cb1b4663150 #0 RIP: 0010:get_new_segment fs/f2fs/segment.c:2746 [inline] RIP: 0010:new_curseg+0x1f52/0x1f70 fs/f2fs/segment.c:2876 Call Trace: <TASK> __allocate_new_segment+0x1ce/0x940 fs/f2fs/segment.c:3210 f2fs_allocate_new_section fs/f2fs/segment.c:3224 [inline] f2fs_allocate_pinning_section+0xfa/0x4e0 fs/f2fs/segment.c:3238 f2fs_expand_inode_data+0x696/0xca0 fs/f2fs/file.c:1830 f2fs_fallocate+0x537/0xa10 fs/f2fs/file.c:1940 vfs_fallocate+0x569/0x6e0 fs/open.c:327 do_vfs_ioctl+0x258c/0x2e40 fs/ioctl.c:885 __do_sys_ioctl fs/ioctl.c:904 [inline] __se_sys_ioctl+0x80/0x170 fs/ioctl.c:892 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 Concurrent pinfile allocation may run out of free section, result in panic in get_new_segment(), let's expand pin_sem lock coverage to include f2fs_gc(), so that we can make sure to reclaim enough free space for following allocation. In addition, do below changes to enhance error path handling: - call f2fs_bug_on() only in non-pinfile allocation path in get_new_segment(). - call reset_curseg_fields() to reset all fields of curseg in new_curseg() Fixes: f5a53edcf01e ("f2fs: support aligned pinned file") Reported-by: syzbot+15669ec8c35ddf6c3d43(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/675cd64e.050a0220.37aaf.00bb.GAE@g… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Rajani Kantha <681739313(a)139.com> --- fs/f2fs/file.c | 8 +++++--- fs/f2fs/segment.c | 20 ++++++++++---------- 2 files changed, 15 insertions(+), 13 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 2a108c561e8b..6317dd523ecd 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1836,18 +1836,20 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, map.m_len = sec_blks; next_alloc: + f2fs_down_write(&sbi->pin_sem); + if (has_not_enough_free_secs(sbi, 0, f2fs_sb_has_blkzoned(sbi) ? ZONED_PIN_SEC_REQUIRED_COUNT : GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) { f2fs_down_write(&sbi->gc_lock); stat_inc_gc_call_count(sbi, FOREGROUND); err = f2fs_gc(sbi, &gc_control); - if (err && err != -ENODATA) + if (err && err != -ENODATA) { + f2fs_up_write(&sbi->pin_sem); goto out_err; + } } - f2fs_down_write(&sbi->pin_sem); - err = f2fs_allocate_pinning_section(sbi); if (err) { f2fs_up_write(&sbi->pin_sem); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index e48b5e2efea2..8ac6206110a1 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -2749,7 +2749,7 @@ static int get_new_segment(struct f2fs_sb_info *sbi, MAIN_SECS(sbi)); if (secno >= MAIN_SECS(sbi)) { ret = -ENOSPC; - f2fs_bug_on(sbi, 1); + f2fs_bug_on(sbi, !pinning); goto out_unlock; } } @@ -2795,7 +2795,7 @@ static int get_new_segment(struct f2fs_sb_info *sbi, out_unlock: spin_unlock(&free_i->segmap_lock); - if (ret == -ENOSPC) + if (ret == -ENOSPC && !pinning) f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_NO_SEGMENT); return ret; } @@ -2868,6 +2868,13 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) return curseg->segno; } +static void reset_curseg_fields(struct curseg_info *curseg) +{ + curseg->inited = false; + curseg->segno = NULL_SEGNO; + curseg->next_segno = 0; +} + /* * Allocate a current working segment. * This function always allocates a free segment in LFS manner. @@ -2886,7 +2893,7 @@ static int new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec) ret = get_new_segment(sbi, &segno, new_sec, pinning); if (ret) { if (ret == -ENOSPC) - curseg->segno = NULL_SEGNO; + reset_curseg_fields(curseg); return ret; } @@ -3640,13 +3647,6 @@ static void f2fs_randomize_chunk(struct f2fs_sb_info *sbi, get_random_u32_inclusive(1, sbi->max_fragment_hole); } -static void reset_curseg_fields(struct curseg_info *curseg) -{ - curseg->inited = false; - curseg->segno = NULL_SEGNO; - curseg->next_segno = 0; -} - int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, -- 2.17.1

1 week, 3 days

1
0
0 0

+ nilfs2-avoid-having-an-active-sc_timer-before-freeing-sci.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: nilfs2: avoid having an active sc_timer before freeing sci has been added to the -mm mm-hotfixes-unstable branch. Its filename is nilfs2-avoid-having-an-active-sc_timer-before-freeing-sci.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: Edward Adam Davis <eadavis(a)qq.com> Subject: nilfs2: avoid having an active sc_timer before freeing sci Date: Thu, 30 Oct 2025 07:51:52 +0900 Because kthread_stop did not stop sc_task properly and returned -EINTR, the sc_timer was not properly closed, ultimately causing the problem [1] reported by syzbot when freeing sci due to the sc_timer not being closed. Because the thread sc_task main function nilfs_segctor_thread() returns 0 when it succeeds, when the return value of kthread_stop() is not 0 in nilfs_segctor_destroy(), we believe that it has not properly closed sc_timer. We use timer_shutdown_sync() to sync wait for sc_timer to shutdown, and set the value of sc_task to NULL under the protection of lock sc_state_lock, so as to avoid the issue caused by sc_timer not being properly shutdowned. [1] ODEBUG: free active (active state 0) object: 00000000dacb411a object type: timer_list hint: nilfs_construction_timeout Call trace: nilfs_segctor_destroy fs/nilfs2/segment.c:2811 [inline] nilfs_detach_log_writer+0x668/0x8cc fs/nilfs2/segment.c:2877 nilfs_put_super+0x4c/0x12c fs/nilfs2/super.c:509 Link: https://lkml.kernel.org/r/20251029225226.16044-1-konishi.ryusuke@gmail.com Fixes: 3f66cc261ccb ("nilfs2: use kthread_create and kthread_stop for the log writer thread") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+24d8b70f039151f65590(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=24d8b70f039151f65590 Tested-by: syzbot+24d8b70f039151f65590(a)syzkaller.appspotmail.com Signed-off-by: Edward Adam Davis <eadavis(a)qq.com> Cc: <stable(a)vger.kernel.org> [6.12+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/nilfs2/segment.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) --- a/fs/nilfs2/segment.c~nilfs2-avoid-having-an-active-sc_timer-before-freeing-sci +++ a/fs/nilfs2/segment.c @@ -2768,7 +2768,12 @@ static void nilfs_segctor_destroy(struct if (sci->sc_task) { wake_up(&sci->sc_wait_daemon); - kthread_stop(sci->sc_task); + if (kthread_stop(sci->sc_task)) { + spin_lock(&sci->sc_state_lock); + sci->sc_task = NULL; + timer_shutdown_sync(&sci->sc_timer); + spin_unlock(&sci->sc_state_lock); + } } spin_lock(&sci->sc_state_lock); _ Patches currently in -mm which might be from eadavis(a)qq.com are nilfs2-avoid-having-an-active-sc_timer-before-freeing-sci.patch

1 week, 3 days

1
0
0 0

+ scripts-decode_stacktracesh-fix-build-id-and-pc-source-parsing.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: scripts/decode_stacktrace.sh: fix build ID and PC source parsing has been added to the -mm mm-hotfixes-unstable branch. Its filename is scripts-decode_stacktracesh-fix-build-id-and-pc-source-parsing.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: Carlos Llamas <cmllamas(a)google.com> Subject: scripts/decode_stacktrace.sh: fix build ID and PC source parsing Date: Thu, 30 Oct 2025 01:03:33 +0000 Support for parsing PC source info in stacktraces (e.g. '(P)') was added in commit 2bff77c665ed ("scripts/decode_stacktrace.sh: fix decoding of lines with an additional info"). However, this logic was placed after the build ID processing. This incorrect order fails to parse lines containing both elements, e.g.: drm_gem_mmap_obj+0x114/0x200 [drm 03d0564e0529947d67bb2008c3548be77279fd27] (P) This patch fixes the problem by extracting the PC source info first and then processing the module build ID. With this change, the line above is now properly parsed as such: drm_gem_mmap_obj (./include/linux/mmap_lock.h:212 ./include/linux/mm.h:811 drivers/gpu/drm/drm_gem.c:1177) drm (P) While here, also add a brief explanation the build ID section. Link: https://lkml.kernel.org/r/20251030010347.2731925-1-cmllamas@google.com Fixes: bdf8eafbf7f5 ("arm64: stacktrace: report source of unwind data") Fixes: 2bff77c665ed ("scripts/decode_stacktrace.sh: fix decoding of lines with an additional info") Signed-off-by: Carlos Llamas <cmllamas(a)google.com> Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Reviewed-by: Luca Ceresoli <luca.ceresoli(a)bootlin.com> Cc: Breno Leitao <leitao(a)debian.org> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Marc Rutland <mark.rutland(a)arm.com> Cc: Mark Brown <broonie(a)kernel.org> Cc: Matthieu Baerts <matttbe(a)kernel.org> Cc: Miroslav Benes <mbenes(a)suse.cz> Cc: Puranjay Mohan <puranjay(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- scripts/decode_stacktrace.sh | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) --- a/scripts/decode_stacktrace.sh~scripts-decode_stacktracesh-fix-build-id-and-pc-source-parsing +++ a/scripts/decode_stacktrace.sh @@ -277,12 +277,6 @@ handle_line() { fi done - if [[ ${words[$last]} =~ ^[0-9a-f]+\] ]]; then - words[$last-1]="${words[$last-1]} ${words[$last]}" - unset words[$last] spaces[$last] - last=$(( $last - 1 )) - fi - # Extract info after the symbol if present. E.g.: # func_name+0x54/0x80 (P) # ^^^ @@ -294,6 +288,14 @@ handle_line() { unset words[$last] spaces[$last] last=$(( $last - 1 )) fi + + # Join module name with its build id if present, as these were + # split during tokenization (e.g. "[module" and "modbuildid]"). + if [[ ${words[$last]} =~ ^[0-9a-f]+\] ]]; then + words[$last-1]="${words[$last-1]} ${words[$last]}" + unset words[$last] spaces[$last] + last=$(( $last - 1 )) + fi if [[ ${words[$last]} =~ \[([^]]+)\] ]]; then module=${words[$last]} _ Patches currently in -mm which might be from cmllamas(a)google.com are scripts-decode_stacktracesh-fix-build-id-and-pc-source-parsing.patch

1 week, 3 days

1
0
0 0

[PATCH v2] usb: storage: Fix memory leak in USB bulk transport

by Desnes Nunes

A kernel memory leak was identified by the 'ioctl_sg01' test from Linux Test Project (LTP). The following bytes were mainly observed: 0x53425355. When USB storage devices incorrectly skip the data phase with status data, the code extracts/validates the CSW from the sg buffer, but fails to clear it afterwards. This leaves status protocol data in srb's transfer buffer, such as the US_BULK_CS_SIGN 'USBS' signature observed here. Thus, this can lead to USB protocols leaks to user space through SCSI generic (/dev/sg*) interfaces, such as the one seen here when the LTP test requested 512 KiB. Fix the leak by zeroing the CSW data in srb's transfer buffer immediately after the validation of devices that skip data phase. Note: Differently from CVE-2018-1000204, which fixed a big leak by zero- ing pages at allocation time, this leak occurs after allocation, when USB protocol data is written to already-allocated sg pages. v2: Use the same code style found on usb_stor_Bulk_transport() Fixes: a45b599ad808 ("scsi: sg: allocate with __GFP_ZERO in sg_build_indirect()") Cc: stable(a)vger.kernel.org Signed-off-by: Desnes Nunes <desnesn(a)redhat.com> --- drivers/usb/storage/transport.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 1aa1bd26c81f..ee6b89f7f9ac 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -1200,7 +1200,19 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us) US_BULK_CS_WRAP_LEN && bcs->Signature == cpu_to_le32(US_BULK_CS_SIGN)) { + unsigned char buf[US_BULK_CS_WRAP_LEN]; + + sg = NULL; + offset = 0; + memset(buf, 0, US_BULK_CS_WRAP_LEN); usb_stor_dbg(us, "Device skipped data phase\n"); + + if (usb_stor_access_xfer_buf(buf, + US_BULK_CS_WRAP_LEN, srb, &sg, + &offset, TO_XFER_BUF) != + US_BULK_CS_WRAP_LEN) + usb_stor_dbg(us, "Failed to clear CSW data\n"); + scsi_set_resid(srb, transfer_length); goto skipped_data_phase; } -- 2.51.0

1 week, 3 days

2
2
0 0

+ mm-damon-sysfs-change-next_update_jiffies-to-a-global-variable.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/sysfs: change next_update_jiffies to a global variable has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-sysfs-change-next_update_jiffies-to-a-global-variable.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: Quanmin Yan <yanquanmin1(a)huawei.com> Subject: mm/damon/sysfs: change next_update_jiffies to a global variable Date: Thu, 30 Oct 2025 10:07:46 +0800 In DAMON's damon_sysfs_repeat_call_fn(), time_before() is used to compare the current jiffies with next_update_jiffies to determine whether to update the sysfs files at this moment. On 32-bit systems, the kernel initializes jiffies to "-5 minutes" to make jiffies wrap bugs appear earlier. However, this causes time_before() in damon_sysfs_repeat_call_fn() to unexpectedly return true during the first 5 minutes after boot on 32-bit systems (see [1] for more explanation, which fixes another jiffies-related issue before). As a result, DAMON does not update sysfs files during that period. There is also an issue unrelated to the system's word size[2]: if the user stops DAMON just after next_update_jiffies is updated and restarts it after 'refresh_ms' or a longer delay, next_update_jiffies will retain an older value, causing time_before() to return false and the update to happen earlier than expected. Fix these issues by making next_update_jiffies a global variable and initializing it each time DAMON is started. Link: https://lkml.kernel.org/r/20251030020746.967174-3-yanquanmin1@huawei.com Link: https://lkml.kernel.org/r/20250822025057.1740854-1-ekffu200098@gmail.com [1] Link: https://lore.kernel.org/all/20251029013038.66625-1-sj@kernel.org/ [2] Fixes: d809a7c64ba8 ("mm/damon/sysfs: implement refresh_ms file internal work") Suggested-by: SeongJae Park <sj(a)kernel.org> Reviewed-by: SeongJae Park <sj(a)kernel.org> Signed-off-by: Quanmin Yan <yanquanmin1(a)huawei.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: ze zuo <zuoze1(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/sysfs.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) --- a/mm/damon/sysfs.c~mm-damon-sysfs-change-next_update_jiffies-to-a-global-variable +++ a/mm/damon/sysfs.c @@ -1552,16 +1552,17 @@ static struct damon_ctx *damon_sysfs_bui return ctx; } +static unsigned long damon_sysfs_next_update_jiffies; + static int damon_sysfs_repeat_call_fn(void *data) { struct damon_sysfs_kdamond *sysfs_kdamond = data; - static unsigned long next_update_jiffies; if (!sysfs_kdamond->refresh_ms) return 0; - if (time_before(jiffies, next_update_jiffies)) + if (time_before(jiffies, damon_sysfs_next_update_jiffies)) return 0; - next_update_jiffies = jiffies + + damon_sysfs_next_update_jiffies = jiffies + msecs_to_jiffies(sysfs_kdamond->refresh_ms); if (!mutex_trylock(&damon_sysfs_lock)) @@ -1607,6 +1608,9 @@ static int damon_sysfs_turn_damon_on(str } kdamond->damon_ctx = ctx; + damon_sysfs_next_update_jiffies = + jiffies + msecs_to_jiffies(kdamond->refresh_ms); + repeat_call_control->fn = damon_sysfs_repeat_call_fn; repeat_call_control->data = kdamond; repeat_call_control->repeat = true; _ Patches currently in -mm which might be from yanquanmin1(a)huawei.com are mm-damon-stat-change-last_refresh_jiffies-to-a-global-variable.patch mm-damon-sysfs-change-next_update_jiffies-to-a-global-variable.patch mm-damon-add-a-min_sz_region-parameter-to-damon_set_region_biggest_system_ram_default.patch mm-damon-reclaim-use-min_sz_region-for-core-address-alignment-when-setting-regions.patch

1 week, 3 days

1
0
0 0

+ mm-damon-stat-change-last_refresh_jiffies-to-a-global-variable.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/stat: change last_refresh_jiffies to a global variable has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-stat-change-last_refresh_jiffies-to-a-global-variable.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: Quanmin Yan <yanquanmin1(a)huawei.com> Subject: mm/damon/stat: change last_refresh_jiffies to a global variable Date: Thu, 30 Oct 2025 10:07:45 +0800 Patch series "mm/damon: fixes for the jiffies-related issues", v2. On 32-bit systems, the kernel initializes jiffies to "-5 minutes" to make jiffies wrap bugs appear earlier. However, this may cause the time_before() series of functions to return unexpected values, resulting in DAMON not functioning as intended. Meanwhile, similar issues exist in some specific user operation scenarios. This patchset addresses these issues. The first patch is about the DAMON_STAT module, and the second patch is about the core layer's sysfs. This patch (of 2): In DAMON_STAT's damon_stat_damon_call_fn(), time_before_eq() is used to avoid unnecessarily frequent stat update. On 32-bit systems, the kernel initializes jiffies to "-5 minutes" to make jiffies wrap bugs appear earlier. However, this causes time_before_eq() in DAMON_STAT to unexpectedly return true during the first 5 minutes after boot on 32-bit systems (see [1] for more explanation, which fixes another jiffies-related issue before). As a result, DAMON_STAT does not update any monitoring results during that period, which becomes more confusing when DAMON_STAT_ENABLED_DEFAULT is enabled. There is also an issue unrelated to the system's word size[2]: if the user stops DAMON_STAT just after last_refresh_jiffies is updated and restarts it after 5 seconds or a longer delay, last_refresh_jiffies will retain an older value, causing time_before_eq() to return false and the update to happen earlier than expected. Fix these issues by making last_refresh_jiffies a global variable and initializing it each time DAMON_STAT is started. Link: https://lkml.kernel.org/r/20251030020746.967174-2-yanquanmin1@huawei.com Link: https://lkml.kernel.org/r/20250822025057.1740854-1-ekffu200098@gmail.com [1] Link: https://lore.kernel.org/all/20251028143250.50144-1-sj@kernel.org/ [2] Fixes: fabdd1e911da ("mm/damon/stat: calculate and expose estimated memory bandwidth") Signed-off-by: Quanmin Yan <yanquanmin1(a)huawei.com> Suggested-by: SeongJae Park <sj(a)kernel.org> Reviewed-by: SeongJae Park <sj(a)kernel.org> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: ze zuo <zuoze1(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/stat.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) --- a/mm/damon/stat.c~mm-damon-stat-change-last_refresh_jiffies-to-a-global-variable +++ a/mm/damon/stat.c @@ -46,6 +46,8 @@ MODULE_PARM_DESC(aggr_interval_us, static struct damon_ctx *damon_stat_context; +static unsigned long damon_stat_last_refresh_jiffies; + static void damon_stat_set_estimated_memory_bandwidth(struct damon_ctx *c) { struct damon_target *t; @@ -130,13 +132,12 @@ static void damon_stat_set_idletime_perc static int damon_stat_damon_call_fn(void *data) { struct damon_ctx *c = data; - static unsigned long last_refresh_jiffies; /* avoid unnecessarily frequent stat update */ - if (time_before_eq(jiffies, last_refresh_jiffies + + if (time_before_eq(jiffies, damon_stat_last_refresh_jiffies + msecs_to_jiffies(5 * MSEC_PER_SEC))) return 0; - last_refresh_jiffies = jiffies; + damon_stat_last_refresh_jiffies = jiffies; aggr_interval_us = c->attrs.aggr_interval; damon_stat_set_estimated_memory_bandwidth(c); @@ -210,6 +211,8 @@ static int damon_stat_start(void) err = damon_start(&damon_stat_context, 1, true); if (err) return err; + + damon_stat_last_refresh_jiffies = jiffies; call_control.data = damon_stat_context; return damon_call(damon_stat_context, &call_control); } _ Patches currently in -mm which might be from yanquanmin1(a)huawei.com are mm-damon-stat-change-last_refresh_jiffies-to-a-global-variable.patch mm-damon-sysfs-change-next_update_jiffies-to-a-global-variable.patch mm-damon-add-a-min_sz_region-parameter-to-damon_set_region_biggest_system_ram_default.patch mm-damon-reclaim-use-min_sz_region-for-core-address-alignment-when-setting-regions.patch

1 week, 3 days

1
0
0 0

[to-be-updated] s390-fix-hugetlb-vmemmap-optimization-crash.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: s390: fix HugeTLB vmemmap optimization crash has been removed from the -mm tree. Its filename was s390-fix-hugetlb-vmemmap-optimization-crash.patch This patch was dropped because an updated version will be issued ------------------------------------------------------ From: Luiz Capitulino <luizcap(a)redhat.com> Subject: s390: fix HugeTLB vmemmap optimization crash Date: Tue, 28 Oct 2025 17:15:33 -0400 A reproducible crash occurs when enabling HugeTLB vmemmap optimization (HVO) on s390. The crash and the proposed fix were worked on an s390 KVM guest running on an older hypervisor, as I don't have access to an LPAR. However, the same issue should occur on bare-metal. Reproducer (it may take a few runs to trigger): # sysctl vm.hugetlb_optimize_vmemmap=1 # echo 1 > /proc/sys/vm/nr_hugepages # echo 0 > /proc/sys/vm/nr_hugepages Crash log: [ 52.340369] list_del corruption. prev->next should be 000000d382110008, but was 000000d7116d3880. (prev=000000d7116d3910) [ 52.340420] ------------[ cut here ]------------ [ 52.340424] kernel BUG at lib/list_debug.c:62! [ 52.340566] monitor event: 0040 ilc:2 [#1]SMP [ 52.340573] Modules linked in: ctcm fsm qeth ccwgroup zfcp scsi_transport_fc qdio dasd_fba_mod dasd_eckd_mod dasd_mod xfs ghash_s390 prng des_s390 libdes sha3_512_s390 sha3_256_s390 virtio_net virtio_blk net_failover sha_common failover dm_mirror dm_region_hash dm_log dm_mod paes_s390 crypto_engine pkey_cca pkey_ep11 zcrypt pkey_pckmo pkey aes_s390 [ 52.340606] CPU: 1 UID: 0 PID: 1672 Comm: root-rep2 Kdump: loaded Not tainted 6.18.0-rc3 #1 NONE [ 52.340610] Hardware name: IBM 3931 LA1 400 (KVM/Linux) [ 52.340611] Krnl PSW : 0704c00180000000 0000015710cda7fe (__list_del_entry_valid_or_report+0xfe/0x128) [ 52.340619] R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 RI:0 EA:3 [ 52.340622] Krnl GPRS: c0000000ffffefff 0000000100000027 000000000000006d 0000000000000000 [ 52.340623] 000000d7116d35d8 000000d7116d35d0 0000000000000002 000000d7116d39b0 [ 52.340625] 000000d7116d3880 000000d7116d3910 000000d7116d3910 000000d382110008 [ 52.340626] 000003ffac1ccd08 000000d7116d39b0 0000015710cda7fa 000000d7116d37d0 [ 52.340632] Krnl Code: 0000015710cda7ee: c020003e496f larl %r2,00000157114a3acc 0000015710cda7f4: c0e5ffd5280e brasl %r14,000001571077f810 #0000015710cda7fa: af000000 mc 0,0 >0000015710cda7fe: b9040029 lgr %r2,%r9 0000015710cda802: c0e5ffe5e193 brasl %r14,0000015710996b28 0000015710cda808: e34090080004 lg %r4,8(%r9) 0000015710cda80e: b9040059 lgr %r5,%r9 0000015710cda812: b9040038 lgr %r3,%r8 [ 52.340643] Call Trace: [ 52.340645] [<0000015710cda7fe>] __list_del_entry_valid_or_report+0xfe/0x128 [ 52.340649] ([<0000015710cda7fa>] __list_del_entry_valid_or_report+0xfa/0x128) [ 52.340652] [<0000015710a30b2e>] hugetlb_vmemmap_restore_folios+0x96/0x138 [ 52.340655] [<0000015710a268ac>] update_and_free_pages_bulk+0x64/0x150 [ 52.340659] [<0000015710a26f8a>] set_max_huge_pages+0x4ca/0x6f0 [ 52.340662] [<0000015710a273ba>] hugetlb_sysctl_handler_common+0xea/0x120 [ 52.340665] [<0000015710a27484>] hugetlb_sysctl_handler+0x44/0x50 [ 52.340667] [<0000015710b53ffa>] proc_sys_call_handler+0x17a/0x280 [ 52.340672] [<0000015710a90968>] vfs_write+0x2c8/0x3a0 [ 52.340676] [<0000015710a90bd2>] ksys_write+0x72/0x100 [ 52.340679] [<00000157111483a8>] __do_syscall+0x150/0x318 [ 52.340682] [<0000015711153a5e>] system_call+0x6e/0x90 [ 52.340684] Last Breaking-Event-Address: [ 52.340684] [<000001571077f85c>] _printk+0x4c/0x58 [ 52.340690] Kernel panic - not syncing: Fatal exception: panic_on_oops This issue was introduced by commit f13b83fdd996 ("hugetlb: batch TLB flushes when freeing vmemmap"). Before that change, the HVO implementation called flush_tlb_kernel_range() each time a vmemmap PMD split and remapping was performed. The mentioned commit changed this to issue a few flush_tlb_all() calls after performing all remappings. However, on s390, flush_tlb_kernel_range() expands to __tlb_flush_kernel() while flush_tlb_all() is not implemented. As a result, we went from flushing the TLB for every remapping to no flushing at all. This commit fixes this by implementing flush_tlb_all() on s390 as an alias to __tlb_flush_global(). This should cause a flush on all TLB entries on all CPUs as expected by the flush_tlb_all() semantics. Link: https://lkml.kernel.org/r/20251028211533.47694-1-luizcap@redhat.com Fixes: f13b83fdd996 ("hugetlb: batch TLB flushes when freeing vmemmap") Signed-off-by: Luiz Capitulino <luizcap(a)redhat.com> Acked-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)kernel.org> Cc: Christian Borntraeger <borntraeger(a)linux.ibm.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Gerald Schaefer <gerald.schaefer(a)linux.ibm.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Joao Martins <joao.m.martins(a)oracle.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vasily Gorbik <gor(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/s390/include/asm/tlbflush.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) --- a/arch/s390/include/asm/tlbflush.h~s390-fix-hugetlb-vmemmap-optimization-crash +++ a/arch/s390/include/asm/tlbflush.h @@ -103,9 +103,13 @@ static inline void __tlb_flush_mm_lazy(s * flush_tlb_range functions need to do the flush. */ #define flush_tlb() do { } while (0) -#define flush_tlb_all() do { } while (0) #define flush_tlb_page(vma, addr) do { } while (0) +static inline void flush_tlb_all(void) +{ + __tlb_flush_global(); +} + static inline void flush_tlb_mm(struct mm_struct *mm) { __tlb_flush_mm_lazy(mm); _ Patches currently in -mm which might be from luizcap(a)redhat.com are

1 week, 3 days

1
0
0 0

+ maple_tree-fix-tracepoint-string-pointers.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: maple_tree: fix tracepoint string pointers has been added to the -mm mm-hotfixes-unstable branch. Its filename is maple_tree-fix-tracepoint-string-pointers.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: Martin Kaiser <martin(a)kaiser.cx> Subject: maple_tree: fix tracepoint string pointers Date: Thu, 30 Oct 2025 16:55:05 +0100 maple_tree tracepoints contain pointers to function names. Such a pointer is saved when a tracepoint logs an event. There's no guarantee that it's still valid when the event is parsed later and the pointer is dereferenced. The kernel warns about these unsafe pointers. event 'ma_read' has unsafe pointer field 'fn' WARNING: kernel/trace/trace.c:3779 at ignore_event+0x1da/0x1e4 Mark the function names as tracepoint_string() to fix the events. Link: https://lkml.kernel.org/r/20251030155537.87972-1-martin@kaiser.cx Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Martin Kaiser <martin(a)kaiser.cx> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- lib/maple_tree.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) --- a/lib/maple_tree.c~maple_tree-fix-tracepoint-string-pointers +++ a/lib/maple_tree.c @@ -64,6 +64,8 @@ #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> +#define TP_FCT tracepoint_string(__func__) + /* * Kernel pointer hashing renders much of the maple tree dump useless as tagged * pointers get hashed to arbitrary values. @@ -2756,7 +2758,7 @@ static inline void mas_rebalance(struct MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); - trace_ma_op(__func__, mas); + trace_ma_op(TP_FCT, mas); /* * Rebalancing occurs if a node is insufficient. Data is rebalanced @@ -2997,7 +2999,7 @@ static void mas_split(struct ma_state *m MA_STATE(prev_l_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last); - trace_ma_op(__func__, mas); + trace_ma_op(TP_FCT, mas); mast.l = &l_mas; mast.r = &r_mas; @@ -3172,7 +3174,7 @@ static bool mas_is_span_wr(struct ma_wr_ return false; } - trace_ma_write(__func__, wr_mas->mas, wr_mas->r_max, entry); + trace_ma_write(TP_FCT, wr_mas->mas, wr_mas->r_max, entry); return true; } @@ -3416,7 +3418,7 @@ static noinline void mas_wr_spanning_sto * of data may happen. */ mas = wr_mas->mas; - trace_ma_op(__func__, mas); + trace_ma_op(TP_FCT, mas); if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry); @@ -3552,7 +3554,7 @@ done: } else { memcpy(wr_mas->node, newnode, sizeof(struct maple_node)); } - trace_ma_write(__func__, mas, 0, wr_mas->entry); + trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; return; @@ -3596,7 +3598,7 @@ static inline void mas_wr_slot_store(str mas->offset++; /* Keep mas accurate. */ } - trace_ma_write(__func__, mas, 0, wr_mas->entry); + trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); /* * Only update gap when the new entry is empty or there is an empty * entry in the original two ranges. @@ -3717,7 +3719,7 @@ static inline void mas_wr_append(struct mas_update_gap(mas); mas->end = new_end; - trace_ma_write(__func__, mas, new_end, wr_mas->entry); + trace_ma_write(TP_FCT, mas, new_end, wr_mas->entry); return; } @@ -3731,7 +3733,7 @@ static void mas_wr_bnode(struct ma_wr_st { struct maple_big_node b_node; - trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry); + trace_ma_write(TP_FCT, wr_mas->mas, 0, wr_mas->entry); memset(&b_node, 0, sizeof(struct maple_big_node)); mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end); mas_commit_b_node(wr_mas, &b_node); @@ -5062,7 +5064,7 @@ void *mas_store(struct ma_state *mas, vo { MA_WR_STATE(wr_mas, mas, entry); - trace_ma_write(__func__, mas, 0, entry); + trace_ma_write(TP_FCT, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, @@ -5163,7 +5165,7 @@ void mas_store_prealloc(struct ma_state } store: - trace_ma_write(__func__, mas, 0, entry); + trace_ma_write(TP_FCT, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); mas_destroy(mas); @@ -5882,7 +5884,7 @@ void *mtree_load(struct maple_tree *mt, MA_STATE(mas, mt, index, index); void *entry; - trace_ma_read(__func__, &mas); + trace_ma_read(TP_FCT, &mas); rcu_read_lock(); retry: entry = mas_start(&mas); @@ -5925,7 +5927,7 @@ int mtree_store_range(struct maple_tree MA_STATE(mas, mt, index, last); int ret = 0; - trace_ma_write(__func__, &mas, 0, entry); + trace_ma_write(TP_FCT, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; @@ -6148,7 +6150,7 @@ void *mtree_erase(struct maple_tree *mt, void *entry = NULL; MA_STATE(mas, mt, index, index); - trace_ma_op(__func__, &mas); + trace_ma_op(TP_FCT, &mas); mtree_lock(mt); entry = mas_erase(&mas); @@ -6485,7 +6487,7 @@ void *mt_find(struct maple_tree *mt, uns unsigned long copy = *index; #endif - trace_ma_read(__func__, &mas); + trace_ma_read(TP_FCT, &mas); if ((*index) > max) return NULL; _ Patches currently in -mm which might be from martin(a)kaiser.cx are maple_tree-fix-tracepoint-string-pointers.patch

1 week, 3 days

1
0
0 0

[PATCH v4] mm/huge_memory: preserve PG_has_hwpoisoned if a folio is split to >0 order

by Zi Yan

folio split clears PG_has_hwpoisoned, but the flag should be preserved in after-split folios containing pages with PG_hwpoisoned flag if the folio is split to >0 order folios. Scan all pages in a to-be-split folio to determine which after-split folios need the flag. An alternatives is to change PG_has_hwpoisoned to PG_maybe_hwpoisoned to avoid the scan and set it on all after-split folios, but resulting false positive has undesirable negative impact. To remove false positive, caller of folio_test_has_hwpoisoned() and folio_contain_hwpoisoned_page() needs to do the scan. That might be causing a hassle for current and future callers and more costly than doing the scan in the split code. More details are discussed in [1]. This issue can be exposed via: 1. splitting a has_hwpoisoned folio to >0 order from debugfs interface; 2. truncating part of a has_hwpoisoned folio in truncate_inode_partial_folio(). And later accesses to a hwpoisoned page could be possible due to the missing has_hwpoisoned folio flag. This will lead to MCE errors. Link: https://lore.kernel.org/all/CAHbLzkoOZm0PXxE9qwtF4gKR=cpRXrSrJ9V9Pm2DJexs98… [1] Fixes: c010d47f107f ("mm: thp: split huge page to any lower order pages") Cc: stable(a)vger.kernel.org Signed-off-by: Zi Yan <ziy(a)nvidia.com> --- From V3[1]: 1. Separated from the original series; 2. Added Fixes tag and cc'd stable; 3. Simplified page_range_has_hwpoisoned(); 4. Renamed check_poisoned_pages to handle_hwpoison, made it const, and shorten the statement; 5. Removed poisoned_new_folio variable and checked the condition directly. [1] https://lore.kernel.org/all/20251022033531.389351-2-ziy@nvidia.com/ mm/huge_memory.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index fc65ec3393d2..5215bb6aecfc 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3455,6 +3455,14 @@ bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) caller_pins; } +static bool page_range_has_hwpoisoned(struct page *page, long nr_pages) +{ + for (; nr_pages; page++, nr_pages--) + if (PageHWPoison(page)) + return true; + return false; +} + /* * It splits @folio into @new_order folios and copies the @folio metadata to * all the resulting folios. @@ -3462,17 +3470,24 @@ bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) static void __split_folio_to_order(struct folio *folio, int old_order, int new_order) { + /* Scan poisoned pages when split a poisoned folio to large folios */ + const bool handle_hwpoison = folio_test_has_hwpoisoned(folio) && new_order; long new_nr_pages = 1 << new_order; long nr_pages = 1 << old_order; long i; + folio_clear_has_hwpoisoned(folio); + + /* Check first new_nr_pages since the loop below skips them */ + if (handle_hwpoison && + page_range_has_hwpoisoned(folio_page(folio, 0), new_nr_pages)) + folio_set_has_hwpoisoned(folio); /* * Skip the first new_nr_pages, since the new folio from them have all * the flags from the original folio. */ for (i = new_nr_pages; i < nr_pages; i += new_nr_pages) { struct page *new_head = &folio->page + i; - /* * Careful: new_folio is not a "real" folio before we cleared PageTail. * Don't pass it around before clear_compound_head(). @@ -3514,6 +3529,10 @@ static void __split_folio_to_order(struct folio *folio, int old_order, (1L << PG_dirty) | LRU_GEN_MASK | LRU_REFS_MASK)); + if (handle_hwpoison && + page_range_has_hwpoisoned(new_head, new_nr_pages)) + folio_set_has_hwpoisoned(new_folio); + new_folio->mapping = folio->mapping; new_folio->index = folio->index + i; @@ -3600,8 +3619,6 @@ static int __split_unmapped_folio(struct folio *folio, int new_order, int start_order = uniform_split ? new_order : old_order - 1; int split_order; - folio_clear_has_hwpoisoned(folio); - /* * split to new_order one order at a time. For uniform split, * folio is split to new_order directly. -- 2.51.0

1 week, 3 days

9
11
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2025