From a0f0625390858321525c2a8d04e174a546bd19b3 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 28 Oct 2024 16:23:00 +0000 Subject: [PATCH 01/16] btrfs: fix extent map merging not happening for adjacent extents If we have 3 or more adjacent extents in a file, that is, consecutive file extent items pointing to adjacent extents, within a contiguous file range and compatible flags, we end up not merging all the extents into a single extent map. For example: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt/sdc $ xfs_io -f -d -c "pwrite -b 64K 0 64K" \ -c "pwrite -b 64K 64K 64K" \ -c "pwrite -b 64K 128K 64K" \ -c "pwrite -b 64K 192K 64K" \ /mnt/sdc/foo After all the ordered extents complete we unpin the extent maps and try to merge them, but instead of getting a single extent map we get two because: 1) When the first ordered extent completes (file range [0, 64K)) we unpin its extent map and attempt to merge it with the extent map for the range [64K, 128K), but we can't because that extent map is still pinned; 2) When the second ordered extent completes (file range [64K, 128K)), we unpin its extent map and merge it with the previous extent map, for file range [0, 64K), but we can't merge with the next extent map, for the file range [128K, 192K), because this one is still pinned. The merged extent map for the file range [0, 128K) gets the flag EXTENT_MAP_MERGED set; 3) When the third ordered extent completes (file range [128K, 192K)), we unpin its extent map and attempt to merge it with the previous extent map, for file range [0, 128K), but we can't because that extent map has the flag EXTENT_MAP_MERGED set (mergeable_maps() returns false due to different flags) while the extent map for the range [128K, 192K) doesn't have that flag set. We also can't merge it with the next extent map, for file range [192K, 256K), because that one is still pinned. At this moment we have 3 extent maps: One for file range [0, 128K), with the flag EXTENT_MAP_MERGED set. One for file range [128K, 192K). One for file range [192K, 256K) which is still pinned; 4) When the fourth and final extent completes (file range [192K, 256K)), we unpin its extent map and attempt to merge it with the previous extent map, for file range [128K, 192K), which succeeds since none of these extent maps have the EXTENT_MAP_MERGED flag set. So we end up with 2 extent maps: One for file range [0, 128K), with the flag EXTENT_MAP_MERGED set. One for file range [128K, 256K), with the flag EXTENT_MAP_MERGED set. Since after merging extent maps we don't attempt to merge again, that is, merge the resulting extent map with the one that is now preceding it (and the one following it), we end up with those two extent maps, when we could have had a single extent map to represent the whole file. Fix this by making mergeable_maps() ignore the EXTENT_MAP_MERGED flag. While this doesn't present any functional issue, it prevents the merging of extent maps which allows to save memory, and can make defrag not merging extents too (that will be addressed in the next patch). Fixes: 199257a78bb0 ("btrfs: defrag: don't use merged extent map for their generation check") CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/extent_map.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 668c617444a5..1d93e1202c33 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -230,7 +230,12 @@ static bool mergeable_maps(const struct extent_map *prev, const struct extent_ma if (extent_map_end(prev) != next->start) return false; - if (prev->flags != next->flags) + /* + * The merged flag is not an on-disk flag, it just indicates we had the + * extent maps of 2 (or more) adjacent extents merged, so factor it out. + */ + if ((prev->flags & ~EXTENT_FLAG_MERGED) != + (next->flags & ~EXTENT_FLAG_MERGED)) return false; if (next->disk_bytenr < EXTENT_MAP_LAST_BYTE - 1) -- 2.51.0 From 77b0d113eec49a7390ff1a08ca1923e89f5f86c6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 29 Oct 2024 15:18:45 +0000 Subject: [PATCH 02/16] btrfs: fix defrag not merging contiguous extents due to merged extent maps When running defrag (manual defrag) against a file that has extents that are contiguous and we already have the respective extent maps loaded and merged, we end up not defragging the range covered by those contiguous extents. This happens when we have an extent map that was the result of merging multiple extent maps for contiguous extents and the length of the merged extent map is greater than or equals to the defrag threshold length. The script below reproduces this scenario: $ cat test.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi mkfs.btrfs -f $DEV mount $DEV $MNT # Create a 256K file with 4 extents of 64K each. xfs_io -f -c "falloc 0 64K" \ -c "pwrite 0 64K" \ -c "falloc 64K 64K" \ -c "pwrite 64K 64K" \ -c "falloc 128K 64K" \ -c "pwrite 128K 64K" \ -c "falloc 192K 64K" \ -c "pwrite 192K 64K" \ $MNT/foo umount $MNT echo -n "Initial number of file extent items: " btrfs inspect-internal dump-tree -t 5 $DEV | grep EXTENT_DATA | wc -l mount $DEV $MNT # Read the whole file in order to load and merge extent maps. cat $MNT/foo > /dev/null btrfs filesystem defragment -t 128K $MNT/foo umount $MNT echo -n "Number of file extent items after defrag with 128K threshold: " btrfs inspect-internal dump-tree -t 5 $DEV | grep EXTENT_DATA | wc -l mount $DEV $MNT # Read the whole file in order to load and merge extent maps. cat $MNT/foo > /dev/null btrfs filesystem defragment -t 256K $MNT/foo umount $MNT echo -n "Number of file extent items after defrag with 256K threshold: " btrfs inspect-internal dump-tree -t 5 $DEV | grep EXTENT_DATA | wc -l Running it: $ ./test.sh Initial number of file extent items: 4 Number of file extent items after defrag with 128K threshold: 4 Number of file extent items after defrag with 256K threshold: 4 The 4 extents don't get merged because we have an extent map with a size of 256K that is the result of merging the individual extent maps for each of the four 64K extents and at defrag_lookup_extent() we have a value of zero for the generation threshold ('newer_than' argument) since this is a manual defrag. As a consequence we don't call defrag_get_extent() to get an extent map representing a single file extent item in the inode's subvolume tree, so we end up using the merged extent map at defrag_collect_targets() and decide not to defrag. Fix this by updating defrag_lookup_extent() to always discard extent maps that were merged and call defrag_get_extent() regardless of the minimum generation threshold ('newer_than' argument). A test case for fstests will be sent along soon. CC: stable@vger.kernel.org # 6.1+ Fixes: 199257a78bb0 ("btrfs: defrag: don't use merged extent map for their generation check") Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/defrag.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index b95ef44c326b..968dae953948 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -763,12 +763,12 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start, * We can get a merged extent, in that case, we need to re-search * tree to get the original em for defrag. * - * If @newer_than is 0 or em::generation < newer_than, we can trust - * this em, as either we don't care about the generation, or the - * merged extent map will be rejected anyway. + * This is because even if we have adjacent extents that are contiguous + * and compatible (same type and flags), we still want to defrag them + * so that we use less metadata (extent items in the extent tree and + * file extent items in the inode's subvolume tree). */ - if (em && (em->flags & EXTENT_FLAG_MERGED) && - newer_than && em->generation >= newer_than) { + if (em && (em->flags & EXTENT_FLAG_MERGED)) { free_extent_map(em); em = NULL; } -- 2.51.0 From 3e8b7238b427e05498034c240451af5f5495afda Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Oct 2024 13:49:58 +0100 Subject: [PATCH 03/16] gpiolib: fix debugfs newline separators The gpiolib debugfs interface exports a list of all gpio chips in a system and the state of their pins. The gpio chip sections are supposed to be separated by a newline character, but a long-standing bug prevents the separator from being included when output is generated in multiple sessions, making the output inconsistent and hard to read. Make sure to only suppress the newline separator at the beginning of the file as intended. Fixes: f9c4a31f6150 ("gpiolib: Use seq_file's iterator interface") Cc: stable@vger.kernel.org # 3.7 Cc: Thierry Reding Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20241028125000.24051-2-johan+linaro@kernel.org Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index d5952ab7752c..e27488a90bc9 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -4926,6 +4926,8 @@ static void *gpiolib_seq_start(struct seq_file *s, loff_t *pos) return NULL; s->private = priv; + if (*pos > 0) + priv->newline = true; priv->idx = srcu_read_lock(&gpio_devices_srcu); list_for_each_entry_srcu(gdev, &gpio_devices, list, -- 2.51.0 From 604888f8c3d01fddd9366161efc65cb3182831f1 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Oct 2024 13:49:59 +0100 Subject: [PATCH 04/16] gpiolib: fix debugfs dangling chip separator Add the missing newline after entries for recently removed gpio chips so that the chip sections are separated by a newline as intended. Fixes: e348544f7994 ("gpio: protect the list of GPIO devices with SRCU") Cc: stable@vger.kernel.org # 6.9 Cc: Bartosz Golaszewski Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20241028125000.24051-3-johan+linaro@kernel.org Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e27488a90bc9..2b02655abb56 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -4971,7 +4971,7 @@ static int gpiolib_seq_show(struct seq_file *s, void *v) gc = srcu_dereference(gdev->chip, &gdev->srcu); if (!gc) { - seq_printf(s, "%s%s: (dangling chip)", + seq_printf(s, "%s%s: (dangling chip)\n", priv->newline ? "\n" : "", dev_name(&gdev->dev)); return 0; -- 2.51.0 From 85d16bceaf5d8112c9ffcfedd2f1bb9d0a1c1578 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Fri, 25 Oct 2024 21:15:28 +0300 Subject: [PATCH 05/16] mailmap: update Jarkko's email addresses Remove my previous work email, and the new one. The previous was never used in the commit log, so there's no good reason to spare it. Link: https://lkml.kernel.org/r/20241025181530.6151-1-jarkko@kernel.org Signed-off-by: Jarkko Sakkinen Cc: Alex Elder Cc: David S. Miller Cc: Geliang Tang Cc: Jiri Kosina Cc: Kees Cook Cc: Matthieu Baerts (NGI0) Cc: Matt Ranostay Cc: Neeraj Upadhyay Cc: Quentin Monnet Signed-off-by: Andrew Morton --- .mailmap | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 9a94c514e32c..5cf2fab5fe83 100644 --- a/.mailmap +++ b/.mailmap @@ -282,7 +282,7 @@ Jan Glauber Jan Kuliga Jarkko Sakkinen Jarkko Sakkinen -Jarkko Sakkinen +Jarkko Sakkinen Jason Gunthorpe Jason Gunthorpe Jason Gunthorpe -- 2.51.0 From 35e41024c4c2b02ef8207f61b9004f6956cf037b Mon Sep 17 00:00:00 2001 From: Gregory Price Date: Fri, 25 Oct 2024 10:17:24 -0400 Subject: [PATCH 06/16] vmscan,migrate: fix page count imbalance on node stats when demoting pages When numa balancing is enabled with demotion, vmscan will call migrate_pages when shrinking LRUs. migrate_pages will decrement the the node's isolated page count, leading to an imbalanced count when invoked from (MG)LRU code. The result is dmesg output like such: $ cat /proc/sys/vm/stat_refresh [77383.088417] vmstat_refresh: nr_isolated_anon -103212 [77383.088417] vmstat_refresh: nr_isolated_file -899642 This negative value may impact compaction and reclaim throttling. The following path produces the decrement: shrink_folio_list demote_folio_list migrate_pages migrate_pages_batch migrate_folio_move migrate_folio_done mod_node_page_state(-ve) <- decrement This path happens for SUCCESSFUL migrations, not failures. Typically callers to migrate_pages are required to handle putback/accounting for failures, but this is already handled in the shrink code. When accounting for migrations, instead do not decrement the count when the migration reason is MR_DEMOTION. As of v6.11, this demotion logic is the only source of MR_DEMOTION. Link: https://lkml.kernel.org/r/20241025141724.17927-1-gourry@gourry.net Fixes: 26aa2d199d6f ("mm/migrate: demote pages during reclaim") Signed-off-by: Gregory Price Reviewed-by: Yang Shi Reviewed-by: Davidlohr Bueso Reviewed-by: Shakeel Butt Reviewed-by: "Huang, Ying" Reviewed-by: Oscar Salvador Cc: Dave Hansen Cc: Wei Xu Cc: Signed-off-by: Andrew Morton --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/migrate.c b/mm/migrate.c index 7e520562d421..fab84a776088 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1178,7 +1178,7 @@ static void migrate_folio_done(struct folio *src, * not accounted to NR_ISOLATED_*. They can be recognized * as __folio_test_movable */ - if (likely(!__folio_test_movable(src))) + if (likely(!__folio_test_movable(src)) && reason != MR_DEMOTION) mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON + folio_is_file_lru(src), -folio_nr_pages(src)); -- 2.51.0 From 0173471d21ec964921f97ba4eca71af74beb29f7 Mon Sep 17 00:00:00 2001 From: Eugen Hristev Date: Fri, 25 Oct 2024 11:58:48 +0300 Subject: [PATCH 07/16] .mailmap: update e-mail address for Eugen Hristev Update e-mail address. Link: https://lkml.kernel.org/r/20241025085848.483149-1-eugen.hristev@linaro.org Signed-off-by: Eugen Hristev Signed-off-by: Andrew Morton --- .mailmap | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 5cf2fab5fe83..5378f04b2566 100644 --- a/.mailmap +++ b/.mailmap @@ -199,7 +199,8 @@ Elliot Berman Enric Balletbo i Serra Enric Balletbo i Serra Erik Kaneda -Eugen Hristev +Eugen Hristev +Eugen Hristev Evgeniy Polyakov Ezequiel Garcia Faith Ekstrand -- 2.51.0 From 15e8156713cc38031642fafc8baf7d53f19f2e83 Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Fri, 25 Oct 2024 06:09:42 +0000 Subject: [PATCH 08/16] mm: shrinker: avoid memleak in alloc_shrinker_info A memleak was found as below: unreferenced object 0xffff8881010d2a80 (size 32): comm "mkdir", pid 1559, jiffies 4294932666 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 40 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 @............... backtrace (crc 2e7ef6fa): [] __kmalloc_node_noprof+0x394/0x470 [] alloc_shrinker_info+0x7b/0x1a0 [] mem_cgroup_css_online+0x11a/0x3b0 [] online_css+0x29/0xa0 [] cgroup_apply_control_enable+0x20d/0x360 [] cgroup_mkdir+0x168/0x5f0 [] kernfs_iop_mkdir+0x5e/0x90 [] vfs_mkdir+0x144/0x220 [] do_mkdirat+0x87/0x130 [] __x64_sys_mkdir+0x49/0x70 [] do_syscall_64+0x68/0x140 [] entry_SYSCALL_64_after_hwframe+0x76/0x7e alloc_shrinker_info(), when shrinker_unit_alloc() returns an errer, the info won't be freed. Just fix it. Link: https://lkml.kernel.org/r/20241025060942.1049263-1-chenridong@huaweicloud.com Fixes: 307bececcd12 ("mm: shrinker: add a secondary array for shrinker_info::{map, nr_deferred}") Signed-off-by: Chen Ridong Acked-by: Qi Zheng Acked-by: Roman Gushchin Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Reviewed-by: Dave Chinner Cc: Anshuman Khandual Cc: Muchun Song Cc: Wang Weiyang Cc: Signed-off-by: Andrew Morton --- mm/shrinker.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/mm/shrinker.c b/mm/shrinker.c index dc5d2a6fcfc4..4a93fd433689 100644 --- a/mm/shrinker.c +++ b/mm/shrinker.c @@ -76,19 +76,21 @@ void free_shrinker_info(struct mem_cgroup *memcg) int alloc_shrinker_info(struct mem_cgroup *memcg) { - struct shrinker_info *info; int nid, ret = 0; int array_size = 0; mutex_lock(&shrinker_mutex); array_size = shrinker_unit_size(shrinker_nr_max); for_each_node(nid) { - info = kvzalloc_node(sizeof(*info) + array_size, GFP_KERNEL, nid); + struct shrinker_info *info = kvzalloc_node(sizeof(*info) + array_size, + GFP_KERNEL, nid); if (!info) goto err; info->map_nr_max = shrinker_nr_max; - if (shrinker_unit_alloc(info, NULL, nid)) + if (shrinker_unit_alloc(info, NULL, nid)) { + kvfree(info); goto err; + } rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } mutex_unlock(&shrinker_mutex); -- 2.51.0 From d4148aeab412432bf928f311eca8a2ba52bb05df Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 24 Oct 2024 17:12:29 +0200 Subject: [PATCH 09/16] mm, mmap: limit THP alignment of anonymous mappings to PMD-aligned sizes Since commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") a mmap() of anonymous memory without a specific address hint and of at least PMD_SIZE will be aligned to PMD so that it can benefit from a THP backing page. However this change has been shown to regress some workloads significantly. [1] reports regressions in various spec benchmarks, with up to 600% slowdown of the cactusBSSN benchmark on some platforms. The benchmark seems to create many mappings of 4632kB, which would have merged to a large THP-backed area before commit efa7df3e3bb5 and now they are fragmented to multiple areas each aligned to PMD boundary with gaps between. The regression then seems to be caused mainly due to the benchmark's memory access pattern suffering from TLB or cache aliasing due to the aligned boundaries of the individual areas. Another known regression bisected to commit efa7df3e3bb5 is darktable [2] [3] and early testing suggests this patch fixes the regression there as well. To fix the regression but still try to benefit from THP-friendly anonymous mapping alignment, add a condition that the size of the mapping must be a multiple of PMD size instead of at least PMD size. In case of many odd-sized mapping like the cactusBSSN creates, those will stop being aligned and with gaps between, and instead naturally merge again. Link: https://lkml.kernel.org/r/20241024151228.101841-2-vbabka@suse.cz Fixes: efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") Signed-off-by: Vlastimil Babka Reported-by: Michael Matz Debugged-by: Gabriel Krisman Bertazi Closes: https://bugzilla.suse.com/show_bug.cgi?id=1229012 [1] Reported-by: Matthias Bodenbinder Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219366 [2] Closes: https://lore.kernel.org/all/2050f0d4-57b0-481d-bab8-05e8d48fed0c@leemhuis.info/ [3] Reviewed-by: Lorenzo Stoakes Reviewed-by: Yang Shi Cc: Rik van Riel Cc: Jann Horn Cc: Liam R. Howlett Cc: Petr Tesarik Cc: Thorsten Leemhuis Cc: Signed-off-by: Andrew Morton --- mm/mmap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/mmap.c b/mm/mmap.c index 1e0e34cb993f..9841b41e3c76 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -900,7 +900,8 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (get_area) { addr = get_area(file, addr, len, pgoff, flags); - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) + && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ addr = thp_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, vm_flags); -- 2.51.0 From 071b24b54d2d05fbf39ddbb27dee08abd1d713f3 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 27 Oct 2024 22:31:15 -0700 Subject: [PATCH 10/16] Input: fix regression when re-registering input handlers Commit d469647bafd9 ("Input: simplify event handling logic") introduced code that would set handler->events() method to either input_handler_events_filter() or input_handler_events_default() or input_handler_events_null(), depending on the kind of input handler (a filter or a regular one) we are dealing with. Unfortunately this breaks cases when we try to re-register the same filter (as is the case with sysrq handler): after initial registration the handler will have 2 event handling methods defined, and will run afoul of the check in input_handler_check_methods(): input: input_handler_check_methods: only one event processing method can be defined (sysrq) sysrq: Failed to register input handler, error -22 Fix this by adding handle_events() method to input_handle structure and setting it up when registering a new input handle according to event handling methods defined in associated input_handler structure, thus avoiding modifying the input_handler structure. Reported-by: "Ned T. Crigler" Reported-by: Christian Heusel Tested-by: "Ned T. Crigler" Tested-by: Peter Seiderer Fixes: d469647bafd9 ("Input: simplify event handling logic") Link: https://lore.kernel.org/r/Zx2iQp6csn42PJA7@xavtug Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/input.c | 134 +++++++++++++++++++++++------------------- include/linux/input.h | 10 +++- 2 files changed, 82 insertions(+), 62 deletions(-) diff --git a/drivers/input/input.c b/drivers/input/input.c index 3c321671793f..3d2cc13e1f32 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -119,12 +119,12 @@ static void input_pass_values(struct input_dev *dev, handle = rcu_dereference(dev->grab); if (handle) { - count = handle->handler->events(handle, vals, count); + count = handle->handle_events(handle, vals, count); } else { list_for_each_entry_rcu(handle, &dev->h_list, d_node) if (handle->open) { - count = handle->handler->events(handle, vals, - count); + count = handle->handle_events(handle, vals, + count); if (!count) break; } @@ -2537,57 +2537,6 @@ static int input_handler_check_methods(const struct input_handler *handler) return 0; } -/* - * An implementation of input_handler's events() method that simply - * invokes handler->event() method for each event one by one. - */ -static unsigned int input_handler_events_default(struct input_handle *handle, - struct input_value *vals, - unsigned int count) -{ - struct input_handler *handler = handle->handler; - struct input_value *v; - - for (v = vals; v != vals + count; v++) - handler->event(handle, v->type, v->code, v->value); - - return count; -} - -/* - * An implementation of input_handler's events() method that invokes - * handler->filter() method for each event one by one and removes events - * that were filtered out from the "vals" array. - */ -static unsigned int input_handler_events_filter(struct input_handle *handle, - struct input_value *vals, - unsigned int count) -{ - struct input_handler *handler = handle->handler; - struct input_value *end = vals; - struct input_value *v; - - for (v = vals; v != vals + count; v++) { - if (handler->filter(handle, v->type, v->code, v->value)) - continue; - if (end != v) - *end = *v; - end++; - } - - return end - vals; -} - -/* - * An implementation of input_handler's events() method that does nothing. - */ -static unsigned int input_handler_events_null(struct input_handle *handle, - struct input_value *vals, - unsigned int count) -{ - return count; -} - /** * input_register_handler - register a new input handler * @handler: handler to be registered @@ -2607,13 +2556,6 @@ int input_register_handler(struct input_handler *handler) INIT_LIST_HEAD(&handler->h_list); - if (handler->filter) - handler->events = input_handler_events_filter; - else if (handler->event) - handler->events = input_handler_events_default; - else if (!handler->events) - handler->events = input_handler_events_null; - error = mutex_lock_interruptible(&input_mutex); if (error) return error; @@ -2687,6 +2629,75 @@ int input_handler_for_each_handle(struct input_handler *handler, void *data, } EXPORT_SYMBOL(input_handler_for_each_handle); +/* + * An implementation of input_handle's handle_events() method that simply + * invokes handler->event() method for each event one by one. + */ +static unsigned int input_handle_events_default(struct input_handle *handle, + struct input_value *vals, + unsigned int count) +{ + struct input_handler *handler = handle->handler; + struct input_value *v; + + for (v = vals; v != vals + count; v++) + handler->event(handle, v->type, v->code, v->value); + + return count; +} + +/* + * An implementation of input_handle's handle_events() method that invokes + * handler->filter() method for each event one by one and removes events + * that were filtered out from the "vals" array. + */ +static unsigned int input_handle_events_filter(struct input_handle *handle, + struct input_value *vals, + unsigned int count) +{ + struct input_handler *handler = handle->handler; + struct input_value *end = vals; + struct input_value *v; + + for (v = vals; v != vals + count; v++) { + if (handler->filter(handle, v->type, v->code, v->value)) + continue; + if (end != v) + *end = *v; + end++; + } + + return end - vals; +} + +/* + * An implementation of input_handle's handle_events() method that does nothing. + */ +static unsigned int input_handle_events_null(struct input_handle *handle, + struct input_value *vals, + unsigned int count) +{ + return count; +} + +/* + * Sets up appropriate handle->event_handler based on the input_handler + * associated with the handle. + */ +static void input_handle_setup_event_handler(struct input_handle *handle) +{ + struct input_handler *handler = handle->handler; + + if (handler->filter) + handle->handle_events = input_handle_events_filter; + else if (handler->event) + handle->handle_events = input_handle_events_default; + else if (handler->events) + handle->handle_events = handler->events; + else + handle->handle_events = input_handle_events_null; +} + /** * input_register_handle - register a new input handle * @handle: handle to register @@ -2704,6 +2715,7 @@ int input_register_handle(struct input_handle *handle) struct input_dev *dev = handle->dev; int error; + input_handle_setup_event_handler(handle); /* * We take dev->mutex here to prevent race with * input_release_device(). diff --git a/include/linux/input.h b/include/linux/input.h index 89a0be6ee0e2..cd866b020a01 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -339,12 +339,16 @@ struct input_handler { * @name: name given to the handle by handler that created it * @dev: input device the handle is attached to * @handler: handler that works with the device through this handle + * @handle_events: event sequence handler. It is set up by the input core + * according to event handling method specified in the @handler. See + * input_handle_setup_event_handler(). + * This method is being called by the input core with interrupts disabled + * and dev->event_lock spinlock held and so it may not sleep. * @d_node: used to put the handle on device's list of attached handles * @h_node: used to put the handle on handler's list of handles from which * it gets events */ struct input_handle { - void *private; int open; @@ -353,6 +357,10 @@ struct input_handle { struct input_dev *dev; struct input_handler *handler; + unsigned int (*handle_events)(struct input_handle *handle, + struct input_value *vals, + unsigned int count); + struct list_head d_node; struct list_head h_node; }; -- 2.51.0 From 2e766a1f5f94a142d9a906c9411d0f6101c4c721 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 3 Nov 2024 21:46:50 +0900 Subject: [PATCH 11/16] modpost: fix acpi MODULE_DEVICE_TABLE built with mismatched endianness When CONFIG_SATA_AHCI_PLATFORM=m, modpost outputs incorect acpi MODULE_ALIAS() if the endianness of the target and the build machine do not match. When the endianness of the target kernel and the build machine match, the output is correct: $ grep 'MODULE_ALIAS("acpi' drivers/ata/ahci_platform.mod.c MODULE_ALIAS("acpi*:APMC0D33:*"); MODULE_ALIAS("acpi*:010601:*"); However, when building a little-endian kernel on a big-endian machine (or vice versa), the output is incorrect: $ grep 'MODULE_ALIAS("acpi' drivers/ata/ahci_platform.mod.c MODULE_ALIAS("acpi*:APMC0D33:*"); MODULE_ALIAS("acpi*:0601??:*"); The 'cls' and 'cls_msk' fields are 32-bit. DEF_FIELD() must be used instead of DEF_FIELD_ADDR() to correctly handle endianness of these 32-bit fields. The check 'if (cls)' was unnecessary; it never became NULL, as it was the pointer to 'symval' plus the offset to the 'cls' field. Fixes: 26095a01d359 ("ACPI / scan: Add support for ACPI _CLS device matching") Signed-off-by: Masahiro Yamada --- scripts/mod/file2alias.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 99dce93a4188..16154449dde1 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -567,12 +567,12 @@ static int do_acpi_entry(const char *filename, void *symval, char *alias) { DEF_FIELD_ADDR(symval, acpi_device_id, id); - DEF_FIELD_ADDR(symval, acpi_device_id, cls); - DEF_FIELD_ADDR(symval, acpi_device_id, cls_msk); + DEF_FIELD(symval, acpi_device_id, cls); + DEF_FIELD(symval, acpi_device_id, cls_msk); if (id && strlen((const char *)*id)) sprintf(alias, "acpi*:%s:*", *id); - else if (cls) { + else { int i, byte_shift, cnt = 0; unsigned int msk; @@ -580,10 +580,10 @@ static int do_acpi_entry(const char *filename, cnt = 6; for (i = 1; i <= 3; i++) { byte_shift = 8 * (3-i); - msk = (*cls_msk >> byte_shift) & 0xFF; + msk = (cls_msk >> byte_shift) & 0xFF; if (msk) sprintf(&alias[cnt], "%02x", - (*cls >> byte_shift) & 0xFF); + (cls >> byte_shift) & 0xFF); else sprintf(&alias[cnt], "??"); cnt += 2; -- 2.51.0 From 77dc55a978e69625f9718460012e5ef0172dc4de Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 3 Nov 2024 21:52:57 +0900 Subject: [PATCH 12/16] modpost: fix input MODULE_DEVICE_TABLE() built for 64-bit on 32-bit host When building a 64-bit kernel on a 32-bit build host, incorrect input MODULE_ALIAS() entries may be generated. For example, when compiling a 64-bit kernel with CONFIG_INPUT_MOUSEDEV=m on a 64-bit build machine, you will get the correct output: $ grep MODULE_ALIAS drivers/input/mousedev.mod.c MODULE_ALIAS("input:b*v*p*e*-e*1,*2,*k*110,*r*0,*1,*a*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*2,*k*r*8,*a*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*3,*k*14A,*r*a*0,*1,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*3,*k*145,*r*a*0,*1,*18,*1C,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*3,*k*110,*r*a*0,*1,*m*l*s*f*w*"); However, building the same kernel on a 32-bit machine results in incorrect output: $ grep MODULE_ALIAS drivers/input/mousedev.mod.c MODULE_ALIAS("input:b*v*p*e*-e*1,*2,*k*110,*130,*r*0,*1,*a*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*2,*k*r*8,*a*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*3,*k*14A,*16A,*r*a*0,*1,*20,*21,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*3,*k*145,*165,*r*a*0,*1,*18,*1C,*20,*21,*38,*3C,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*3,*k*110,*130,*r*a*0,*1,*20,*21,*m*l*s*f*w*"); A similar issue occurs with CONFIG_INPUT_JOYDEV=m. On a 64-bit build machine, the output is: $ grep MODULE_ALIAS drivers/input/joydev.mod.c MODULE_ALIAS("input:b*v*p*e*-e*3,*k*r*a*0,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*3,*k*r*a*2,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*3,*k*r*a*8,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*3,*k*r*a*6,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*k*120,*r*a*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*k*130,*r*a*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*k*2C0,*r*a*m*l*s*f*w*"); However, on a 32-bit machine, the output is incorrect: $ grep MODULE_ALIAS drivers/input/joydev.mod.c MODULE_ALIAS("input:b*v*p*e*-e*3,*k*r*a*0,*20,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*3,*k*r*a*2,*22,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*3,*k*r*a*8,*28,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*3,*k*r*a*6,*26,*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*k*11F,*13F,*r*a*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*k*11F,*13F,*r*a*m*l*s*f*w*"); MODULE_ALIAS("input:b*v*p*e*-e*1,*k*2C0,*2E0,*r*a*m*l*s*f*w*"); When building a 64-bit kernel, BITS_PER_LONG is defined as 64. However, on a 32-bit build machine, the constant 1L is a signed 32-bit value. Left-shifting it beyond 32 bits causes wraparound, and shifting by 31 or 63 bits makes it a negative value. The fix in commit e0e92632715f ("[PATCH] PATCH: 1 line 2.6.18 bugfix: modpost-64bit-fix.patch") is incorrect; it only addresses cases where a 64-bit kernel is built on a 64-bit build machine, overlooking cases on a 32-bit build machine. Using 1ULL ensures a 64-bit width on both 32-bit and 64-bit machines, avoiding the wraparound issue. Fixes: e0e92632715f ("[PATCH] PATCH: 1 line 2.6.18 bugfix: modpost-64bit-fix.patch") Signed-off-by: Masahiro Yamada --- scripts/mod/file2alias.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 16154449dde1..c4cc11aa558f 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -743,7 +743,7 @@ static void do_input(char *alias, for (i = min / BITS_PER_LONG; i < max / BITS_PER_LONG + 1; i++) arr[i] = TO_NATIVE(arr[i]); for (i = min; i < max; i++) - if (arr[i / BITS_PER_LONG] & (1L << (i%BITS_PER_LONG))) + if (arr[i / BITS_PER_LONG] & (1ULL << (i%BITS_PER_LONG))) sprintf(alias + strlen(alias), "%X,*", i); } -- 2.51.0 From ddd6d8e975b171ea3f63a011a75820883ff0d479 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sat, 19 Oct 2024 01:29:38 +0000 Subject: [PATCH 13/16] mm: multi-gen LRU: remove MM_LEAF_OLD and MM_NONLEAF_TOTAL stats Patch series "mm: multi-gen LRU: Have secondary MMUs participate in MM_WALK". Today, the MM_WALK capability causes MGLRU to clear the young bit from PMDs and PTEs during the page table walk before eviction, but MGLRU does not call the clear_young() MMU notifier in this case. By not calling this notifier, the MM walk takes less time/CPU, but it causes pages that are accessed mostly through KVM / secondary MMUs to appear younger than they should be. We do call the clear_young() notifier today, but only when attempting to evict the page, so we end up clearing young/accessed information less frequently for secondary MMUs than for mm PTEs, and therefore they appear younger and are less likely to be evicted. Therefore, memory that is *not* being accessed mostly by KVM will be evicted *more* frequently, worsening performance. ChromeOS observed a tab-open latency regression when enabling MGLRU with a setup that involved running a VM: Tab-open latency histogram (ms) Version p50 mean p95 p99 max base 1315 1198 2347 3454 10319 mglru 2559 1311 7399 12060 43758 fix 1119 926 2470 4211 6947 This series replaces the final non-selftest patchs from this series[1], which introduced a similar change (and a new MMU notifier) with KVM optimizations. I'll send a separate series (to Sean and Paolo) for the KVM optimizations. This series also makes proactive reclaim with MGLRU possible for KVM memory. I have verified that this functions correctly with the selftest from [1], but given that that test is a KVM selftest, I'll send it with the rest of the KVM optimizations later. Andrew, let me know if you'd like to take the test now anyway. [1]: https://lore.kernel.org/linux-mm/20240926013506.860253-18-jthoughton@google.com/ This patch (of 2): The removed stats, MM_LEAF_OLD and MM_NONLEAF_TOTAL, are not very helpful and become more complicated to properly compute when adding test/clear_young() notifiers in MGLRU's mm walk. Link: https://lkml.kernel.org/r/20241019012940.3656292-1-jthoughton@google.com Link: https://lkml.kernel.org/r/20241019012940.3656292-2-jthoughton@google.com Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks") Signed-off-by: Yu Zhao Signed-off-by: James Houghton Cc: Axel Rasmussen Cc: David Matlack Cc: David Rientjes Cc: David Stevens Cc: Oliver Upton Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Wei Xu Cc: Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 -- mm/vmscan.c | 14 +++++--------- 2 files changed, 5 insertions(+), 11 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 17506e4a2835..9342e5692dab 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -458,9 +458,7 @@ struct lru_gen_folio { enum { MM_LEAF_TOTAL, /* total leaf entries */ - MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ - MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS diff --git a/mm/vmscan.c b/mm/vmscan.c index eb4e8440c507..4f1d33e4b360 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3399,7 +3399,6 @@ restart: continue; if (!pte_young(ptent)) { - walk->mm_stats[MM_LEAF_OLD]++; continue; } @@ -3552,7 +3551,6 @@ restart: walk->mm_stats[MM_LEAF_TOTAL]++; if (!pmd_young(val)) { - walk->mm_stats[MM_LEAF_OLD]++; continue; } @@ -3564,8 +3562,6 @@ restart: continue; } - walk->mm_stats[MM_NONLEAF_TOTAL]++; - if (!walk->force_scan && should_clear_pmd_young()) { if (!pmd_young(val)) continue; @@ -5254,11 +5250,11 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { - const char *s = " "; + const char *s = "xxx"; unsigned long n[3] = {}; if (seq == max_seq) { - s = "RT "; + s = "RTx"; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { @@ -5280,14 +5276,14 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { - const char *s = " "; + const char *s = "xxxx"; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { - s = "LOYNFA"; + s = "TYFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { - s = "loynfa"; + s = "tyfa"; n = READ_ONCE(mm_state->stats[hist][i]); } -- 2.51.0 From 1d4832becdc2cdb2cffe2a6050c9d9fd8ff1c58c Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Sat, 19 Oct 2024 01:29:39 +0000 Subject: [PATCH 14/16] mm: multi-gen LRU: use {ptep,pmdp}_clear_young_notify() When the MM_WALK capability is enabled, memory that is mostly accessed by a VM appears younger than it really is, therefore this memory will be less likely to be evicted. Therefore, the presence of a running VM can significantly increase swap-outs for non-VM memory, regressing the performance for the rest of the system. Fix this regression by always calling {ptep,pmdp}_clear_young_notify() whenever we clear the young bits on PMDs/PTEs. [jthoughton@google.com: fix link-time error] Link: https://lkml.kernel.org/r/20241019012940.3656292-3-jthoughton@google.com Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks") Signed-off-by: Yu Zhao Signed-off-by: James Houghton Reported-by: David Stevens Cc: Axel Rasmussen Cc: David Matlack Cc: David Rientjes Cc: Oliver Upton Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Wei Xu Cc: Cc: kernel test robot Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 5 ++- mm/rmap.c | 9 ++--- mm/vmscan.c | 88 +++++++++++++++++++++++------------------- 3 files changed, 55 insertions(+), 47 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9342e5692dab..5b1c984daf45 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -555,7 +555,7 @@ struct lru_gen_memcg { void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); @@ -574,8 +574,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } -static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { + return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) diff --git a/mm/rmap.c b/mm/rmap.c index a8797d1b3d49..73d5998677d4 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -885,13 +885,10 @@ static bool folio_referenced_one(struct folio *folio, return false; } - if (pvmw.pte) { - if (lru_gen_enabled() && - pte_young(ptep_get(pvmw.pte))) { - lru_gen_look_around(&pvmw); + if (lru_gen_enabled() && pvmw.pte) { + if (lru_gen_look_around(&pvmw)) referenced++; - } - + } else if (pvmw.pte) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) referenced++; diff --git a/mm/vmscan.c b/mm/vmscan.c index 4f1d33e4b360..ddaaff67642e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include @@ -3294,7 +3295,8 @@ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk return false; } -static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) +static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr, + struct pglist_data *pgdat) { unsigned long pfn = pte_pfn(pte); @@ -3306,13 +3308,20 @@ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; + if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm)) + return -1; + if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return -1; + return pfn; } -static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr) +static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr, + struct pglist_data *pgdat) { unsigned long pfn = pmd_pfn(pmd); @@ -3324,9 +3333,15 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; + if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm)) + return -1; + if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return -1; + return pfn; } @@ -3335,10 +3350,6 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, { struct folio *folio; - /* try to avoid unnecessary memory loads */ - if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) - return NULL; - folio = pfn_folio(pfn); if (folio_nid(folio) != pgdat->node_id) return NULL; @@ -3394,20 +3405,16 @@ restart: total++; walk->mm_stats[MM_LEAF_TOTAL]++; - pfn = get_pte_pfn(ptent, args->vma, addr); + pfn = get_pte_pfn(ptent, args->vma, addr, pgdat); if (pfn == -1) continue; - if (!pte_young(ptent)) { - continue; - } - folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) continue; - if (!ptep_test_and_clear_young(args->vma, addr, pte + i)) - VM_WARN_ON_ONCE(true); + if (!ptep_clear_young_notify(args->vma, addr, pte + i)) + continue; young++; walk->mm_stats[MM_LEAF_YOUNG]++; @@ -3473,21 +3480,25 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; - pfn = get_pmd_pfn(pmd[i], vma, addr); - if (pfn == -1) + if (!pmd_present(pmd[i])) goto next; if (!pmd_trans_huge(pmd[i])) { - if (!walk->force_scan && should_clear_pmd_young()) + if (!walk->force_scan && should_clear_pmd_young() && + !mm_has_notifiers(args->mm)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } + pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat); + if (pfn == -1) + goto next; + folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) goto next; - if (!pmdp_test_and_clear_young(vma, addr, pmd + i)) + if (!pmdp_clear_young_notify(vma, addr, pmd + i)) goto next; walk->mm_stats[MM_LEAF_YOUNG]++; @@ -3545,24 +3556,18 @@ restart: } if (pmd_trans_huge(val)) { - unsigned long pfn = pmd_pfn(val); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); + unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat); walk->mm_stats[MM_LEAF_TOTAL]++; - if (!pmd_young(val)) { - continue; - } - - /* try to avoid unnecessary memory loads */ - if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) - continue; - - walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); + if (pfn != -1) + walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } - if (!walk->force_scan && should_clear_pmd_young()) { + if (!walk->force_scan && should_clear_pmd_young() && + !mm_has_notifiers(args->mm)) { if (!pmd_young(val)) continue; @@ -4036,13 +4041,13 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; - int young = 0; + int young = 1; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; @@ -4058,12 +4063,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); + if (!ptep_clear_young_notify(vma, addr, pte)) + return false; + if (spin_is_contended(pvmw->ptl)) - return; + return true; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) - return; + return true; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; @@ -4071,6 +4079,9 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; + if (end - start == PAGE_SIZE) + return true; + if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; @@ -4084,7 +4095,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) - return; + return true; arch_enter_lazy_mmu_mode(); @@ -4094,19 +4105,16 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) unsigned long pfn; pte_t ptent = ptep_get(pte + i); - pfn = get_pte_pfn(ptent, vma, addr); + pfn = get_pte_pfn(ptent, vma, addr, pgdat); if (pfn == -1) continue; - if (!pte_young(ptent)) - continue; - folio = get_pfn_folio(pfn, memcg, pgdat, can_swap); if (!folio) continue; - if (!ptep_test_and_clear_young(vma, addr, pte + i)) - VM_WARN_ON_ONCE(true); + if (!ptep_clear_young_notify(vma, addr, pte + i)) + continue; young++; @@ -4136,6 +4144,8 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); + + return true; } /****************************************************************************** -- 2.51.0 From 59b723cd2adbac2a34fc8e12c74ae26ae45bf230 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 3 Nov 2024 14:05:52 -1000 Subject: [PATCH 15/16] Linux 6.12-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5e04e4abffd8..b8efbfe9da94 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* -- 2.51.0 From 4497ee914f10264894b08066cbee026604cd244f Mon Sep 17 00:00:00 2001 From: Yan Zhen Date: Mon, 23 Sep 2024 15:50:16 +0800 Subject: [PATCH 16/16] watchdog: fix typo in the comment Correctly spelled comments make it easier for the reader to understand the code. Fix typos: 'hearbeat' -> 'heartbeat', 'retrigggers' -> 'retriggers', 'funtions' -> 'functions', 'Resgister' -> 'Register'. Signed-off-by: Yan Zhen Reviewed-by: Wim Van Sebroeck Link: https://lore.kernel.org/r/20240923075016.2439774-1-yanzhen@vivo.com Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/pcwd.c | 2 +- drivers/watchdog/rzn1_wdt.c | 2 +- drivers/watchdog/smsc37b787_wdt.c | 2 +- drivers/watchdog/starfive-wdt.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/pcwd.c b/drivers/watchdog/pcwd.c index 1a4282235aac..31d3dcbf815e 100644 --- a/drivers/watchdog/pcwd.c +++ b/drivers/watchdog/pcwd.c @@ -833,7 +833,7 @@ static int pcwd_isa_match(struct device *dev, unsigned int id) port0 = inb_p(base_addr); port1 = inb_p(base_addr + 1); - /* Has either hearbeat bit changed? */ + /* Has either heartbeat bit changed? */ if ((port0 ^ last_port0) & WD_HRTBT || (port1 ^ last_port1) & WD_REVC_HRBT) { retval = 1; diff --git a/drivers/watchdog/rzn1_wdt.c b/drivers/watchdog/rzn1_wdt.c index 7d3192d34afd..96fd04fbc2a2 100644 --- a/drivers/watchdog/rzn1_wdt.c +++ b/drivers/watchdog/rzn1_wdt.c @@ -52,7 +52,7 @@ static int rzn1_wdt_ping(struct watchdog_device *w) { struct rzn1_watchdog *wdt = watchdog_get_drvdata(w); - /* Any value retrigggers the watchdog */ + /* Any value retriggers the watchdog */ writel(0, wdt->base + RZN1_WDT_RETRIGGER); return 0; diff --git a/drivers/watchdog/smsc37b787_wdt.c b/drivers/watchdog/smsc37b787_wdt.c index 97ca500ec8a8..3011e1af00f9 100644 --- a/drivers/watchdog/smsc37b787_wdt.c +++ b/drivers/watchdog/smsc37b787_wdt.c @@ -485,7 +485,7 @@ static long wb_smsc_wdt_ioctl(struct file *file, } } -/* -- Notifier funtions -----------------------------------------*/ +/* -- Notifier functions -----------------------------------------*/ static int wb_smsc_wdt_notify_sys(struct notifier_block *this, unsigned long code, void *unused) diff --git a/drivers/watchdog/starfive-wdt.c b/drivers/watchdog/starfive-wdt.c index 19a2620d3d38..a8b6cf767117 100644 --- a/drivers/watchdog/starfive-wdt.c +++ b/drivers/watchdog/starfive-wdt.c @@ -80,7 +80,7 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); struct starfive_wdt_variant { - unsigned int control; /* Watchdog Control Resgister for reset enable */ + unsigned int control; /* Watchdog Control Register for reset enable */ unsigned int load; /* Watchdog Load register */ unsigned int reload; /* Watchdog Reload Control register */ unsigned int enable; /* Watchdog Enable Register */ -- 2.51.0