- Linux-stable-mirror - lists.linaro.org

[PATCH v2 10/16] ext4: fix largest free orders lists corruption on mb_optimize_scan switch

by Baokun Li

The grp->bb_largest_free_order is updated regardless of whether mb_optimize_scan is enabled. This can lead to inconsistencies between grp->bb_largest_free_order and the actual s_mb_largest_free_orders list index when mb_optimize_scan is repeatedly enabled and disabled via remount. For example, if mb_optimize_scan is initially enabled, largest free order is 3, and the group is in s_mb_largest_free_orders[3]. Then, mb_optimize_scan is disabled via remount, block allocations occur, updating largest free order to 2. Finally, mb_optimize_scan is re-enabled via remount, more block allocations update largest free order to 1. At this point, the group would be removed from s_mb_largest_free_orders[3] under the protection of s_mb_largest_free_orders_locks[2]. This lock mismatch can lead to list corruption. To fix this, a new field bb_largest_free_order_idx is added to struct ext4_group_info to explicitly track the list index. Then still update bb_largest_free_order unconditionally, but only update bb_largest_free_order_idx when mb_optimize_scan is enabled. so that there is no inconsistency between the lock and the data to be protected. Fixes: 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning") CC: stable(a)vger.kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/ext4.h | 1 + fs/ext4/mballoc.c | 35 ++++++++++++++++------------------- 2 files changed, 17 insertions(+), 19 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 003b8d3726e8..0e574378c6a3 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3476,6 +3476,7 @@ struct ext4_group_info { int bb_avg_fragment_size_order; /* order of average fragment in BG */ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */ + ext4_grpblk_t bb_largest_free_order_idx; /* index of largest frag */ ext4_group_t bb_group; /* Group number */ struct list_head bb_prealloc_list; #ifdef DOUBLE_CHECK diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index e6d6c2da3c6e..dc82124f0905 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1152,33 +1152,29 @@ static void mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); - int i; + int new, old = grp->bb_largest_free_order_idx; - for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) - if (grp->bb_counters[i] > 0) + for (new = MB_NUM_ORDERS(sb) - 1; new >= 0; new--) + if (grp->bb_counters[new] > 0) break; + + grp->bb_largest_free_order = new; /* No need to move between order lists? */ - if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || - i == grp->bb_largest_free_order) { - grp->bb_largest_free_order = i; + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || new == old) return; - } - if (grp->bb_largest_free_order >= 0) { - write_lock(&sbi->s_mb_largest_free_orders_locks[ - grp->bb_largest_free_order]); + if (old >= 0) { + write_lock(&sbi->s_mb_largest_free_orders_locks[old]); list_del_init(&grp->bb_largest_free_order_node); - write_unlock(&sbi->s_mb_largest_free_orders_locks[ - grp->bb_largest_free_order]); + write_unlock(&sbi->s_mb_largest_free_orders_locks[old]); } - grp->bb_largest_free_order = i; - if (grp->bb_largest_free_order >= 0 && grp->bb_free) { - write_lock(&sbi->s_mb_largest_free_orders_locks[ - grp->bb_largest_free_order]); + + grp->bb_largest_free_order_idx = new; + if (new >= 0 && grp->bb_free) { + write_lock(&sbi->s_mb_largest_free_orders_locks[new]); list_add_tail(&grp->bb_largest_free_order_node, - &sbi->s_mb_largest_free_orders[grp->bb_largest_free_order]); - write_unlock(&sbi->s_mb_largest_free_orders_locks[ - grp->bb_largest_free_order]); + &sbi->s_mb_largest_free_orders[new]); + write_unlock(&sbi->s_mb_largest_free_orders_locks[new]); } } @@ -3391,6 +3387,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node); meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */ + meta_group_info[i]->bb_largest_free_order_idx = -1; /* uninit */ meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); -- 2.46.1

2 months, 2 weeks

2
2
0 0

[PATCH 0/2] Add dma-coherent for gs101 UFS dt node

by Peter Griffin

ufs-exynos driver enables the shareability option for gs101 which means the descriptors need to be allocated as cacheable. Fix the DT node and update bindings to add the dma-coherent property. This fixes the UFS stability issues we have seen with the upstream UFS driver. Note this DT fix can go in independently of the other UFS fixes series I sent recently [1], as the bootloader already leaves the sharability bits enabled. regards, Peter [1] https://lore.kernel.org/linux-scsi/20250226220414.343659-1-peter.griffin@li… To: André Draszik <andre.draszik(a)linaro.org> To: Tudor Ambarus <tudor.ambarus(a)linaro.org> To: Rob Herring <robh(a)kernel.org> To: Krzysztof Kozlowski <krzk+dt(a)kernel.org> To: Conor Dooley <conor+dt(a)kernel.org> To: Alim Akhtar <alim.akhtar(a)samsung.com> To: Avri Altman <avri.altman(a)wdc.com> To: Bart Van Assche <bvanassche(a)acm.org> To: Martin K. Petersen <martin.petersen(a)oracle.com> Cc: Krzysztof Kozlowski <krzysztof.kozlowski(a)linaro.org> Cc: linux-arm-kernel(a)lists.infradead.org Cc: linux-samsung-soc(a)vger.kernel.org Cc: devicetree(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: linux-scsi(a)vger.kernel.org Cc: kernel-team(a)android.com Cc: willmcvicker(a)google.com Signed-off-by: Peter Griffin <peter.griffin(a)linaro.org> --- Peter Griffin (2): arm64: dts: exynos: gs101: ufs: add dma-coherent property scsi: ufs: dt-bindings: exynos: add dma-coherent property for gs101 Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml | 2 ++ arch/arm64/boot/dts/exynos/google/gs101.dtsi | 1 + 2 files changed, 3 insertions(+) --- base-commit: b323d8e7bc03d27dec646bfdccb7d1a92411f189 change-id: 20250314-ufs-dma-coherent-980f2467690d Best regards, -- Peter Griffin <peter.griffin(a)linaro.org>

2 months, 2 weeks

6
13
0 0

[PATCH v2 09/16] ext4: fix zombie groups in average fragment size lists

by Baokun Li

Groups with no free blocks shouldn't be in any average fragment size list. However, when all blocks in a group are allocated(i.e., bb_fragments or bb_free is 0), we currently skip updating the average fragment size, which means the group isn't removed from its previous s_mb_avg_fragment_size[old] list. This created "zombie" groups that were always skipped during traversal as they couldn't satisfy any block allocation requests, negatively impacting traversal efficiency. Therefore, when a group becomes completely free, bb_avg_fragment_size_order is now set to -1. If the old order was not -1, a removal operation is performed; if the new order is not -1, an insertion is performed. Fixes: 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning") CC: stable(a)vger.kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/mballoc.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 94950b07a577..e6d6c2da3c6e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -841,30 +841,30 @@ static void mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); - int new_order; + int new, old; - if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0) + if (!test_opt2(sb, MB_OPTIMIZE_SCAN)) return; - new_order = mb_avg_fragment_size_order(sb, - grp->bb_free / grp->bb_fragments); - if (new_order == grp->bb_avg_fragment_size_order) + old = grp->bb_avg_fragment_size_order; + new = grp->bb_fragments == 0 ? -1 : + mb_avg_fragment_size_order(sb, grp->bb_free / grp->bb_fragments); + if (new == old) return; - if (grp->bb_avg_fragment_size_order != -1) { - write_lock(&sbi->s_mb_avg_fragment_size_locks[ - grp->bb_avg_fragment_size_order]); + if (old >= 0) { + write_lock(&sbi->s_mb_avg_fragment_size_locks[old]); list_del(&grp->bb_avg_fragment_size_node); - write_unlock(&sbi->s_mb_avg_fragment_size_locks[ - grp->bb_avg_fragment_size_order]); - } - grp->bb_avg_fragment_size_order = new_order; - write_lock(&sbi->s_mb_avg_fragment_size_locks[ - grp->bb_avg_fragment_size_order]); - list_add_tail(&grp->bb_avg_fragment_size_node, - &sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]); - write_unlock(&sbi->s_mb_avg_fragment_size_locks[ - grp->bb_avg_fragment_size_order]); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[old]); + } + + grp->bb_avg_fragment_size_order = new; + if (new >= 0) { + write_lock(&sbi->s_mb_avg_fragment_size_locks[new]); + list_add_tail(&grp->bb_avg_fragment_size_node, + &sbi->s_mb_avg_fragment_size[new]); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[new]); + } } /* -- 2.46.1

2 months, 2 weeks

2
2
0 0

Re: Patch "ASoC: codec: wcd9335: Convert to GPIO descriptors" has been added to the 6.15-stable tree

by Bartosz Golaszewski

On Fri, Jun 27, 2025 at 4:04 PM Sasha Levin <sashal(a)kernel.org> wrote: > > This is a note to let you know that I've just added the patch titled > > ASoC: codec: wcd9335: Convert to GPIO descriptors > > to the 6.15-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… > > The filename of the patch is: > asoc-codec-wcd9335-convert-to-gpio-descriptors.patch > and it can be found in the queue-6.15 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable(a)vger.kernel.org> know about it. > > Why is this being backported to stable? It's not a fix, just refactoring and updating to a more modern API. Bart

2 months, 2 weeks

2
2
0 0

[PATCH] nvmet: fix memory leak of bio integrity

by Dmitry Bogdanov

If nvmet receives commands with metadata there is a continuous memory leak of kmalloc-128 slab or more precisely bio->bi_integrity. Since that [1] patch series the integrity is not get free at bio_end_io for submitter owned integrity. It has to free explicitly. After commit bf4c89fc8797 ("block: don't call bio_uninit from bio_endio") each user of bio_init has to use bio_uninit as well. Otherwise the bio integrity is not getting free. Nvmet uses bio_init for inline bios. Uninit the inline bio to complete deallocation of integrity in bio. [1] https://lore.kernel.org/all/20240702151047.1746127-1-hch@lst.de/ Cc: stable(a)vger.kernel.org # 6.11 Signed-off-by: Dmitry Bogdanov <d.bogdanov(a)yadro.com> --- drivers/nvme/target/nvmet.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index df69a9dee71c..51df72f5e89b 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -867,6 +867,8 @@ static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio) { if (bio != &req->b.inline_bio) bio_put(bio); + else + bio_uninit(bio); } #ifdef CONFIG_NVME_TARGET_TCP_TLS -- 2.25.1

2 months, 2 weeks

2
1
0 0

[PATCH v3] lib/alloc_tag: do not acquire non-existent lock in alloc_tag_top_users()

by Harry Yoo

alloc_tag_top_users() attempts to lock alloc_tag_cttype->mod_lock even when the alloc_tag_cttype is not allocated because: 1) alloc tagging is disabled because mem profiling is disabled (!alloc_tag_cttype) 2) alloc tagging is enabled, but not yet initialized (!alloc_tag_cttype) 3) alloc tagging is enabled, but failed initialization (!alloc_tag_cttype or IS_ERR(alloc_tag_cttype)) In all cases, alloc_tag_cttype is not allocated, and therefore alloc_tag_top_users() should not attempt to acquire the semaphore. This leads to a crash on memory allocation failure by attempting to acquire a non-existent semaphore: Oops: general protection fault, probably for non-canonical address 0xdffffc000000001b: 0000 [#3] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x00000000000000d8-0x00000000000000df] CPU: 2 UID: 0 PID: 1 Comm: systemd Tainted: G D 6.16.0-rc2 #1 VOLUNTARY Tainted: [D]=DIE Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 RIP: 0010:down_read_trylock+0xaa/0x3b0 Code: d0 7c 08 84 d2 0f 85 a0 02 00 00 8b 0d df 31 dd 04 85 c9 75 29 48 b8 00 00 00 00 00 fc ff df 48 8d 6b 68 48 89 ea 48 c1 ea 03 <80> 3c 02 00 0f 85 88 02 00 00 48 3b 5b 68 0f 85 53 01 00 00 65 ff RSP: 0000:ffff8881002ce9b8 EFLAGS: 00010016 RAX: dffffc0000000000 RBX: 0000000000000070 RCX: 0000000000000000 RDX: 000000000000001b RSI: 000000000000000a RDI: 0000000000000070 RBP: 00000000000000d8 R08: 0000000000000001 R09: ffffed107dde49d1 R10: ffff8883eef24e8b R11: ffff8881002cec20 R12: 1ffff11020059d37 R13: 00000000003fff7b R14: ffff8881002cec20 R15: dffffc0000000000 FS: 00007f963f21d940(0000) GS:ffff888458ca6000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f963f5edf71 CR3: 000000010672c000 CR4: 0000000000350ef0 Call Trace: <TASK> codetag_trylock_module_list+0xd/0x20 alloc_tag_top_users+0x369/0x4b0 __show_mem+0x1cd/0x6e0 warn_alloc+0x2b1/0x390 __alloc_frozen_pages_noprof+0x12b9/0x21a0 alloc_pages_mpol+0x135/0x3e0 alloc_slab_page+0x82/0xe0 new_slab+0x212/0x240 ___slab_alloc+0x82a/0xe00 </TASK> As David Wang points out, this issue became easier to trigger after commit 780138b12381 ("alloc_tag: check mem_profiling_support in alloc_tag_init"). Before the commit, the issue occurred only when it failed to allocate and initialize alloc_tag_cttype or if a memory allocation fails before alloc_tag_init() is called. After the commit, it can be easily triggered when memory profiling is compiled but disabled at boot. To properly determine whether alloc_tag_init() has been called and its data structures initialized, verify that alloc_tag_cttype is a valid pointer before acquiring the semaphore. If the variable is NULL or an error value, it has not been properly initialized. In such a case, just skip and do not attempt to acquire the semaphore. Reported-by: kernel test robot <oliver.sang(a)intel.com> Closes: https://lore.kernel.org/oe-lkp/202506181351.bba867dd-lkp@intel.com Closes: https://lore.kernel.org/oe-lkp/202506131711.5b41931c-lkp@intel.com Fixes: 780138b12381 ("alloc_tag: check mem_profiling_support in alloc_tag_init") Fixes: 1438d349d16b ("lib: add memory allocations report in show_mem()") Cc: stable(a)vger.kernel.org Signed-off-by: Harry Yoo <harry.yoo(a)oracle.com> --- @Suren: I did not add another pr_warn() because every error path in alloc_tag_init() already has pr_err(). v2 -> v3: - Added another Closes: tag (David) - Moved the condition into a standalone if block for better readability (Suren) - Typo fix (Suren) lib/alloc_tag.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 41ccfb035b7b..e9b33848700a 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -127,6 +127,9 @@ size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sl struct codetag_bytes n; unsigned int i, nr = 0; + if (IS_ERR_OR_NULL(alloc_tag_cttype)) + return 0; + if (can_sleep) codetag_lock_module_list(alloc_tag_cttype, true); else if (!codetag_trylock_module_list(alloc_tag_cttype)) -- 2.43.0

2 months, 2 weeks

4
21
0 0

[PATCH v3 1/7] mm/shmem, swap: improve cached mTHP handling and fix potential hung

by Kairui Song

From: Kairui Song <kasong(a)tencent.com> The current swap-in code assumes that, when a swap entry in shmem mapping is order 0, its cached folios (if present) must be order 0 too, which turns out not always correct. The problem is shmem_split_large_entry is called before verifying the folio will eventually be swapped in, one possible race is: CPU1 CPU2 shmem_swapin_folio /* swap in of order > 0 swap entry S1 */ folio = swap_cache_get_folio /* folio = NULL */ order = xa_get_order /* order > 0 */ folio = shmem_swap_alloc_folio /* mTHP alloc failure, folio = NULL */ <... Interrupted ...> shmem_swapin_folio /* S1 is swapped in */ shmem_writeout /* S1 is swapped out, folio cached */ shmem_split_large_entry(..., S1) /* S1 is split, but the folio covering it has order > 0 now */ Now any following swapin of S1 will hang: `xa_get_order` returns 0, and folio lookup will return a folio with order > 0. The `xa_get_order(&mapping->i_pages, index) != folio_order(folio)` will always return false causing swap-in to return -EEXIST. And this looks fragile. So fix this up by allowing seeing a larger folio in swap cache, and check the whole shmem mapping range covered by the swapin have the right swap value upon inserting the folio. And drop the redundant tree walks before the insertion. This will actually improve performance, as it avoids two redundant Xarray tree walks in the hot path, and the only side effect is that in the failure path, shmem may redundantly reallocate a few folios causing temporary slight memory pressure. And worth noting, it may seems the order and value check before inserting might help reducing the lock contention, which is not true. The swap cache layer ensures raced swapin will either see a swap cache folio or failed to do a swapin (we have SWAP_HAS_CACHE bit even if swap cache is bypassed), so holding the folio lock and checking the folio flag is already good enough for avoiding the lock contention. The chance that a folio passes the swap entry value check but the shmem mapping slot has changed should be very low. Fixes: 809bc86517cc ("mm: shmem: support large folio swap out") Signed-off-by: Kairui Song <kasong(a)tencent.com> Reviewed-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Cc: <stable(a)vger.kernel.org> --- mm/shmem.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 334b7b4a61a0..e3c9a1365ff4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -884,7 +884,9 @@ static int shmem_add_to_page_cache(struct folio *folio, pgoff_t index, void *expected, gfp_t gfp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); - long nr = folio_nr_pages(folio); + unsigned long nr = folio_nr_pages(folio); + swp_entry_t iter, swap; + void *entry; VM_BUG_ON_FOLIO(index != round_down(index, nr), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); @@ -896,14 +898,24 @@ static int shmem_add_to_page_cache(struct folio *folio, gfp &= GFP_RECLAIM_MASK; folio_throttle_swaprate(folio, gfp); + swap = iter = radix_to_swp_entry(expected); do { xas_lock_irq(&xas); - if (expected != xas_find_conflict(&xas)) { - xas_set_err(&xas, -EEXIST); - goto unlock; + xas_for_each_conflict(&xas, entry) { + /* + * The range must either be empty, or filled with + * expected swap entries. Shmem swap entries are never + * partially freed without split of both entry and + * folio, so there shouldn't be any holes. + */ + if (!expected || entry != swp_to_radix_entry(iter)) { + xas_set_err(&xas, -EEXIST); + goto unlock; + } + iter.val += 1 << xas_get_order(&xas); } - if (expected && xas_find_conflict(&xas)) { + if (expected && iter.val - nr != swap.val) { xas_set_err(&xas, -EEXIST); goto unlock; } @@ -2323,7 +2335,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, error = -ENOMEM; goto failed; } - } else if (order != folio_order(folio)) { + } else if (order > folio_order(folio)) { /* * Swap readahead may swap in order 0 folios into swapcache * asynchronously, while the shmem mapping can still stores @@ -2348,15 +2360,15 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, swap = swp_entry(swp_type(swap), swp_offset(swap) + offset); } + } else if (order < folio_order(folio)) { + swap.val = round_down(swap.val, 1 << folio_order(folio)); } alloced: /* We have to do this with folio locked to prevent races */ folio_lock(folio); if ((!skip_swapcache && !folio_test_swapcache(folio)) || - folio->swap.val != swap.val || - !shmem_confirm_swap(mapping, index, swap) || - xa_get_order(&mapping->i_pages, index) != folio_order(folio)) { + folio->swap.val != swap.val) { error = -EEXIST; goto unlock; } -- 2.50.0

2 months, 2 weeks

2
1
0 0

+ mm-damon-core-handle-damon_call_control-as-normal-under-kdmond-deactivation.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/core: handle damon_call_control as normal under kdmond deactivation has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-core-handle-damon_call_control-as-normal-under-kdmond-deactivation.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: SeongJae Park <sj(a)kernel.org> Subject: mm/damon/core: handle damon_call_control as normal under kdmond deactivation Date: Sun, 29 Jun 2025 13:49:14 -0700 DAMON sysfs interface internally uses damon_call() to update DAMON parameters as users requested, online. However, DAMON core cancels any damon_call() requests when it is deactivated by DAMOS watermarks. As a result, users cannot change DAMON parameters online while DAMON is deactivated. Note that users can turn DAMON off and on with different watermarks to work around. Since deactivated DAMON is nearly same to stopped DAMON, the work around should have no big problem. Anyway, a bug is a bug. There is no real good reason to cancel the damon_call() request under DAMOS deactivation. Fix it by simply handling the request as normal, rather than cancelling under the situation. Link: https://lkml.kernel.org/r/20250629204914.54114-1-sj@kernel.org Fixes: 42b7491af14c ("mm/damon/core: introduce damon_call()") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> [6.14+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/core.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) --- a/mm/damon/core.c~mm-damon-core-handle-damon_call_control-as-normal-under-kdmond-deactivation +++ a/mm/damon/core.c @@ -2355,9 +2355,8 @@ static void kdamond_usleep(unsigned long * * If there is a &struct damon_call_control request that registered via * &damon_call() on @ctx, do or cancel the invocation of the function depending - * on @cancel. @cancel is set when the kdamond is deactivated by DAMOS - * watermarks, or the kdamond is already out of the main loop and therefore - * will be terminated. + * on @cancel. @cancel is set when the kdamond is already out of the main loop + * and therefore will be terminated. */ static void kdamond_call(struct damon_ctx *ctx, bool cancel) { @@ -2405,7 +2404,7 @@ static int kdamond_wait_activation(struc if (ctx->callback.after_wmarks_check && ctx->callback.after_wmarks_check(ctx)) break; - kdamond_call(ctx, true); + kdamond_call(ctx, false); damos_walk_cancel(ctx); } return -EBUSY; _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-core-handle-damon_call_control-as-normal-under-kdmond-deactivation.patch mm-damon-introduce-damon_stat-module.patch mm-damon-introduce-damon_stat-module-fix.patch mm-damon-stat-calculate-and-expose-estimated-memory-bandwidth.patch mm-damon-stat-calculate-and-expose-idle-time-percentiles.patch docs-admin-guide-mm-damon-add-damon_stat-usage-document.patch mm-damon-paddr-use-alloc_migartion_target-with-no-migration-fallback-nodemask.patch revert-mm-rename-alloc_demote_folio-to-alloc_migrate_folio.patch revert-mm-make-alloc_demote_folio-externally-invokable-for-migration.patch selftets-damon-add-a-test-for-memcg_path-leak.patch mm-damon-sysfs-schemes-decouple-from-damos_quota_goal_metric.patch mm-damon-sysfs-schemes-decouple-from-damos_action.patch mm-damon-sysfs-schemes-decouple-from-damos_wmark_metric.patch mm-damon-sysfs-schemes-decouple-from-damos_filter_type.patch mm-damon-sysfs-decouple-from-damon_ops_id.patch

2 months, 2 weeks

1
0
0 0

[PATCH] mm/damon/core: handle damon_call_control as normal under kdmond deactivation

by SeongJae Park

DAMON sysfs interface internally uses damon_call() to update DAMON parameters as users requested, online. However, DAMON core cancels any damon_call() requests when it is deactivated by DAMOS watermarks. As a result, users cannot change DAMON parameters online while DAMON is deactivated. Note that users can turn DAMON off and on with different watermarks to work around. Since deactivated DAMON is nearly same to stopped DAMON, the work around should have no big problem. Anyway, a bug is a bug. There is no real good reason to cancel the damon_call() request under DAMOS deactivation. Fix it by simply handling the request as normal, rather than cancelling under the situation. Fixes: 42b7491af14c ("mm/damon/core: introduce damon_call()") Cc: stable(a)vger.kernel.org # 6.14.x Signed-off-by: SeongJae Park <sj(a)kernel.org> --- mm/damon/core.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index b217e0120e09..bc2e58c1222d 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -2355,9 +2355,8 @@ static void kdamond_usleep(unsigned long usecs) * * If there is a &struct damon_call_control request that registered via * &damon_call() on @ctx, do or cancel the invocation of the function depending - * on @cancel. @cancel is set when the kdamond is deactivated by DAMOS - * watermarks, or the kdamond is already out of the main loop and therefore - * will be terminated. + * on @cancel. @cancel is set when the kdamond is already out of the main loop + * and therefore will be terminated. */ static void kdamond_call(struct damon_ctx *ctx, bool cancel) { @@ -2405,7 +2404,7 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) if (ctx->callback.after_wmarks_check && ctx->callback.after_wmarks_check(ctx)) break; - kdamond_call(ctx, true); + kdamond_call(ctx, false); damos_walk_cancel(ctx); } return -EBUSY; base-commit: 8f6082b6e60e05f9bcd5c39b19ede995a8975283 -- 2.39.5

2 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] io_uring/kbuf: flag partial buffer mappings" failed to apply to 6.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.15.y git checkout FETCH_HEAD git cherry-pick -x 178b8ff66ff827c41b4fa105e9aabb99a0b5c537 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062920-conch-hypnotist-d63d@gregkh' --subject-prefix 'PATCH 6.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 178b8ff66ff827c41b4fa105e9aabb99a0b5c537 Mon Sep 17 00:00:00 2001 From: Jens Axboe <axboe(a)kernel.dk> Date: Thu, 26 Jun 2025 12:17:48 -0600 Subject: [PATCH] io_uring/kbuf: flag partial buffer mappings A previous commit aborted mapping more for a non-incremental ring for bundle peeking, but depending on where in the process this peeking happened, it would not necessarily prevent a retry by the user. That can create gaps in the received/read data. Add struct buf_sel_arg->partial_map, which can pass this information back. The networking side can then map that to internal state and use it to gate retry as well. Since this necessitates a new flag, change io_sr_msg->retry to a retry_flags member, and store both the retry and partial map condition in there. Cc: stable(a)vger.kernel.org Fixes: 26ec15e4b0c1 ("io_uring/kbuf: don't truncate end buffer for multiple buffer peeks") Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index ce95e3af44a9..f2d2cc319faa 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -271,6 +271,7 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, if (len > arg->max_len) { len = arg->max_len; if (!(bl->flags & IOBL_INC)) { + arg->partial_map = 1; if (iov != arg->iovs) break; buf->len = len; diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h index 5d83c7adc739..723d0361898e 100644 --- a/io_uring/kbuf.h +++ b/io_uring/kbuf.h @@ -58,7 +58,8 @@ struct buf_sel_arg { size_t max_len; unsigned short nr_iovs; unsigned short mode; - unsigned buf_group; + unsigned short buf_group; + unsigned short partial_map; }; void __user *io_buffer_select(struct io_kiocb *req, size_t *len, diff --git a/io_uring/net.c b/io_uring/net.c index 5c1e8c4ba468..43a43522f406 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -75,12 +75,17 @@ struct io_sr_msg { u16 flags; /* initialised and used only by !msg send variants */ u16 buf_group; - bool retry; + unsigned short retry_flags; void __user *msg_control; /* used only for send zerocopy */ struct io_kiocb *notif; }; +enum sr_retry_flags { + IO_SR_MSG_RETRY = 1, + IO_SR_MSG_PARTIAL_MAP = 2, +}; + /* * Number of times we'll try and do receives if there's more data. If we * exceed this limit, then add us to the back of the queue and retry from @@ -187,7 +192,7 @@ static inline void io_mshot_prep_retry(struct io_kiocb *req, req->flags &= ~REQ_F_BL_EMPTY; sr->done_io = 0; - sr->retry = false; + sr->retry_flags = 0; sr->len = 0; /* get from the provided buffer */ } @@ -397,7 +402,7 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); sr->done_io = 0; - sr->retry = false; + sr->retry_flags = 0; sr->len = READ_ONCE(sqe->len); sr->flags = READ_ONCE(sqe->ioprio); if (sr->flags & ~SENDMSG_FLAGS) @@ -751,7 +756,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); sr->done_io = 0; - sr->retry = false; + sr->retry_flags = 0; if (unlikely(sqe->file_index || sqe->addr2)) return -EINVAL; @@ -823,7 +828,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, cflags |= io_put_kbufs(req, this_ret, io_bundle_nbufs(kmsg, this_ret), issue_flags); - if (sr->retry) + if (sr->retry_flags & IO_SR_MSG_RETRY) cflags = req->cqe.flags | (cflags & CQE_F_MASK); /* bundle with no more immediate buffers, we're done */ if (req->flags & REQ_F_BL_EMPTY) @@ -832,12 +837,12 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, * If more is available AND it was a full transfer, retry and * append to this one */ - if (!sr->retry && kmsg->msg.msg_inq > 1 && this_ret > 0 && + if (!sr->retry_flags && kmsg->msg.msg_inq > 1 && this_ret > 0 && !iov_iter_count(&kmsg->msg.msg_iter)) { req->cqe.flags = cflags & ~CQE_F_MASK; sr->len = kmsg->msg.msg_inq; sr->done_io += this_ret; - sr->retry = true; + sr->retry_flags |= IO_SR_MSG_RETRY; return false; } } else { @@ -1082,6 +1087,8 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg kmsg->vec.iovec = arg.iovs; req->flags |= REQ_F_NEED_CLEANUP; } + if (arg.partial_map) + sr->retry_flags |= IO_SR_MSG_PARTIAL_MAP; /* special case 1 vec, can be a fast path */ if (ret == 1) { @@ -1276,7 +1283,7 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) int ret; zc->done_io = 0; - zc->retry = false; + zc->retry_flags = 0; if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3))) return -EINVAL;

2 months, 2 weeks

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror