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

[PATCH v5 1/2] drm/buddy: Optimize free block management with RB tree

by Arunpravin Paneer Selvam

Replace the freelist (O(n)) used for free block management with a red-black tree, providing more efficient O(log n) search, insert, and delete operations. This improves scalability and performance when managing large numbers of free blocks per order (e.g., hundreds or thousands). In the VK-CTS memory stress subtest, the buddy manager merges fragmented memory and inserts freed blocks into the freelist. Since freelist insertion is O(n), this becomes a bottleneck as fragmentation increases. Benchmarking shows list_insert_sorted() consumes ~52.69% CPU with the freelist, compared to just 0.03% with the RB tree (rbtree_insert.isra.0), despite performing the same sorted insert. This also improves performance in heavily fragmented workloads, such as games or graphics tests that stress memory. v3(Matthew): - Remove RB_EMPTY_NODE check in force_merge function. - Rename rb for loop macros to have less generic names and move to .c file. - Make the rb node rb and link field as union. v4(Jani Nikula): - The kernel-doc comment should be "/**" - Move all the rbtree macros to rbtree.h and add parens to ensure correct precedence. Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam(a)amd.com> --- drivers/gpu/drm/drm_buddy.c | 142 ++++++++++++++++++++++-------------- include/drm/drm_buddy.h | 9 ++- include/linux/rbtree.h | 56 ++++++++++++++ 3 files changed, 152 insertions(+), 55 deletions(-) diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index a94061f373de..978cabfbcf0f 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -31,6 +31,8 @@ static struct drm_buddy_block *drm_block_alloc(struct drm_buddy *mm, block->header |= order; block->parent = parent; + RB_CLEAR_NODE(&block->rb); + BUG_ON(block->header & DRM_BUDDY_HEADER_UNUSED); return block; } @@ -41,23 +43,53 @@ static void drm_block_free(struct drm_buddy *mm, kmem_cache_free(slab_blocks, block); } -static void list_insert_sorted(struct drm_buddy *mm, - struct drm_buddy_block *block) +static void rbtree_insert(struct drm_buddy *mm, + struct drm_buddy_block *block) { + struct rb_root *root = &mm->free_tree[drm_buddy_block_order(block)]; + struct rb_node **link = &root->rb_node; + struct rb_node *parent = NULL; struct drm_buddy_block *node; - struct list_head *head; + u64 offset; + + offset = drm_buddy_block_offset(block); - head = &mm->free_list[drm_buddy_block_order(block)]; - if (list_empty(head)) { - list_add(&block->link, head); - return; + while (*link) { + parent = *link; + node = rb_entry(parent, struct drm_buddy_block, rb); + + if (offset < drm_buddy_block_offset(node)) + link = &parent->rb_left; + else + link = &parent->rb_right; } - list_for_each_entry(node, head, link) - if (drm_buddy_block_offset(block) < drm_buddy_block_offset(node)) - break; + rb_link_node(&block->rb, parent, link); + rb_insert_color(&block->rb, root); +} + +static void rbtree_remove(struct drm_buddy *mm, + struct drm_buddy_block *block) +{ + struct rb_root *root; + + root = &mm->free_tree[drm_buddy_block_order(block)]; + rb_erase(&block->rb, root); - __list_add(&block->link, node->link.prev, &node->link); + RB_CLEAR_NODE(&block->rb); +} + +static inline struct drm_buddy_block * +rbtree_last_entry(struct drm_buddy *mm, unsigned int order) +{ + struct rb_node *node = rb_last(&mm->free_tree[order]); + + return node ? rb_entry(node, struct drm_buddy_block, rb) : NULL; +} + +static bool rbtree_is_empty(struct drm_buddy *mm, unsigned int order) +{ + return RB_EMPTY_ROOT(&mm->free_tree[order]); } static void clear_reset(struct drm_buddy_block *block) @@ -70,12 +102,13 @@ static void mark_cleared(struct drm_buddy_block *block) block->header |= DRM_BUDDY_HEADER_CLEAR; } -static void mark_allocated(struct drm_buddy_block *block) +static void mark_allocated(struct drm_buddy *mm, + struct drm_buddy_block *block) { block->header &= ~DRM_BUDDY_HEADER_STATE; block->header |= DRM_BUDDY_ALLOCATED; - list_del(&block->link); + rbtree_remove(mm, block); } static void mark_free(struct drm_buddy *mm, @@ -84,15 +117,16 @@ static void mark_free(struct drm_buddy *mm, block->header &= ~DRM_BUDDY_HEADER_STATE; block->header |= DRM_BUDDY_FREE; - list_insert_sorted(mm, block); + rbtree_insert(mm, block); } -static void mark_split(struct drm_buddy_block *block) +static void mark_split(struct drm_buddy *mm, + struct drm_buddy_block *block) { block->header &= ~DRM_BUDDY_HEADER_STATE; block->header |= DRM_BUDDY_SPLIT; - list_del(&block->link); + rbtree_remove(mm, block); } static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2) @@ -148,7 +182,7 @@ static unsigned int __drm_buddy_free(struct drm_buddy *mm, mark_cleared(parent); } - list_del(&buddy->link); + rbtree_remove(mm, buddy); if (force_merge && drm_buddy_block_is_clear(buddy)) mm->clear_avail -= drm_buddy_block_size(mm, buddy); @@ -179,9 +213,11 @@ static int __force_merge(struct drm_buddy *mm, return -EINVAL; for (i = min_order - 1; i >= 0; i--) { - struct drm_buddy_block *block, *prev; + struct drm_buddy_block *block, *prev_block, *first_block; + + first_block = rb_entry(rb_first(&mm->free_tree[i]), struct drm_buddy_block, rb); - list_for_each_entry_safe_reverse(block, prev, &mm->free_list[i], link) { + rbtree_reverse_for_each_entry_safe(block, prev_block, &mm->free_tree[i], rb) { struct drm_buddy_block *buddy; u64 block_start, block_end; @@ -206,10 +242,14 @@ static int __force_merge(struct drm_buddy *mm, * block in the next iteration as we would free the * buddy block as part of the free function. */ - if (prev == buddy) - prev = list_prev_entry(prev, link); + if (prev_block && prev_block == buddy) { + if (prev_block != first_block) + prev_block = rb_entry(rb_prev(&prev_block->rb), + struct drm_buddy_block, + rb); + } - list_del(&block->link); + rbtree_remove(mm, block); if (drm_buddy_block_is_clear(block)) mm->clear_avail -= drm_buddy_block_size(mm, block); @@ -258,14 +298,14 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size) BUG_ON(mm->max_order > DRM_BUDDY_MAX_ORDER); - mm->free_list = kmalloc_array(mm->max_order + 1, - sizeof(struct list_head), + mm->free_tree = kmalloc_array(mm->max_order + 1, + sizeof(struct rb_root), GFP_KERNEL); - if (!mm->free_list) + if (!mm->free_tree) return -ENOMEM; for (i = 0; i <= mm->max_order; ++i) - INIT_LIST_HEAD(&mm->free_list[i]); + mm->free_tree[i] = RB_ROOT; mm->n_roots = hweight64(size); @@ -273,7 +313,7 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size) sizeof(struct drm_buddy_block *), GFP_KERNEL); if (!mm->roots) - goto out_free_list; + goto out_free_tree; offset = 0; i = 0; @@ -312,8 +352,8 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size) while (i--) drm_block_free(mm, mm->roots[i]); kfree(mm->roots); -out_free_list: - kfree(mm->free_list); +out_free_tree: + kfree(mm->free_tree); return -ENOMEM; } EXPORT_SYMBOL(drm_buddy_init); @@ -323,7 +363,7 @@ EXPORT_SYMBOL(drm_buddy_init); * * @mm: DRM buddy manager to free * - * Cleanup memory manager resources and the freelist + * Cleanup memory manager resources and the freetree */ void drm_buddy_fini(struct drm_buddy *mm) { @@ -350,7 +390,7 @@ void drm_buddy_fini(struct drm_buddy *mm) WARN_ON(mm->avail != mm->size); kfree(mm->roots); - kfree(mm->free_list); + kfree(mm->free_tree); } EXPORT_SYMBOL(drm_buddy_fini); @@ -383,7 +423,7 @@ static int split_block(struct drm_buddy *mm, clear_reset(block); } - mark_split(block); + mark_split(mm, block); return 0; } @@ -412,7 +452,7 @@ EXPORT_SYMBOL(drm_get_buddy); * @is_clear: blocks clear state * * Reset the clear state based on @is_clear value for each block - * in the freelist. + * in the freetree. */ void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear) { @@ -433,7 +473,7 @@ void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear) for (i = 0; i <= mm->max_order; ++i) { struct drm_buddy_block *block; - list_for_each_entry_reverse(block, &mm->free_list[i], link) { + rbtree_reverse_for_each_entry(block, &mm->free_tree[i], rb) { if (is_clear != drm_buddy_block_is_clear(block)) { if (is_clear) { mark_cleared(block); @@ -641,7 +681,7 @@ get_maxblock(struct drm_buddy *mm, unsigned int order, for (i = order; i <= mm->max_order; ++i) { struct drm_buddy_block *tmp_block; - list_for_each_entry_reverse(tmp_block, &mm->free_list[i], link) { + rbtree_reverse_for_each_entry(tmp_block, &mm->free_tree[i], rb) { if (block_incompatible(tmp_block, flags)) continue; @@ -667,7 +707,7 @@ get_maxblock(struct drm_buddy *mm, unsigned int order, } static struct drm_buddy_block * -alloc_from_freelist(struct drm_buddy *mm, +alloc_from_freetree(struct drm_buddy *mm, unsigned int order, unsigned long flags) { @@ -684,7 +724,7 @@ alloc_from_freelist(struct drm_buddy *mm, for (tmp = order; tmp <= mm->max_order; ++tmp) { struct drm_buddy_block *tmp_block; - list_for_each_entry_reverse(tmp_block, &mm->free_list[tmp], link) { + rbtree_reverse_for_each_entry(tmp_block, &mm->free_tree[tmp], rb) { if (block_incompatible(tmp_block, flags)) continue; @@ -700,10 +740,8 @@ alloc_from_freelist(struct drm_buddy *mm, if (!block) { /* Fallback method */ for (tmp = order; tmp <= mm->max_order; ++tmp) { - if (!list_empty(&mm->free_list[tmp])) { - block = list_last_entry(&mm->free_list[tmp], - struct drm_buddy_block, - link); + if (!rbtree_is_empty(mm, tmp)) { + block = rbtree_last_entry(mm, tmp); if (block) break; } @@ -771,7 +809,7 @@ static int __alloc_range(struct drm_buddy *mm, if (contains(start, end, block_start, block_end)) { if (drm_buddy_block_is_free(block)) { - mark_allocated(block); + mark_allocated(mm, block); total_allocated += drm_buddy_block_size(mm, block); mm->avail -= drm_buddy_block_size(mm, block); if (drm_buddy_block_is_clear(block)) @@ -849,7 +887,6 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm, { u64 rhs_offset, lhs_offset, lhs_size, filled; struct drm_buddy_block *block; - struct list_head *list; LIST_HEAD(blocks_lhs); unsigned long pages; unsigned int order; @@ -862,11 +899,10 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm, if (order == 0) return -ENOSPC; - list = &mm->free_list[order]; - if (list_empty(list)) + if (rbtree_is_empty(mm, order)) return -ENOSPC; - list_for_each_entry_reverse(block, list, link) { + rbtree_reverse_for_each_entry(block, &mm->free_tree[order], rb) { /* Allocate blocks traversing RHS */ rhs_offset = drm_buddy_block_offset(block); err = __drm_buddy_alloc_range(mm, rhs_offset, size, @@ -976,7 +1012,7 @@ int drm_buddy_block_trim(struct drm_buddy *mm, list_add(&block->tmp_link, &dfs); err = __alloc_range(mm, &dfs, new_start, new_size, blocks, NULL); if (err) { - mark_allocated(block); + mark_allocated(mm, block); mm->avail -= drm_buddy_block_size(mm, block); if (drm_buddy_block_is_clear(block)) mm->clear_avail -= drm_buddy_block_size(mm, block); @@ -999,8 +1035,8 @@ __drm_buddy_alloc_blocks(struct drm_buddy *mm, return __drm_buddy_alloc_range_bias(mm, start, end, order, flags); else - /* Allocate from freelist */ - return alloc_from_freelist(mm, order, flags); + /* Allocate from freetree */ + return alloc_from_freetree(mm, order, flags); } /** @@ -1017,8 +1053,8 @@ __drm_buddy_alloc_blocks(struct drm_buddy *mm, * alloc_range_bias() called on range limitations, which traverses * the tree and returns the desired block. * - * alloc_from_freelist() called when *no* range restrictions - * are enforced, which picks the block from the freelist. + * alloc_from_freetree() called when *no* range restrictions + * are enforced, which picks the block from the freetree. * * Returns: * 0 on success, error code on failure. @@ -1120,7 +1156,7 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm, } } while (1); - mark_allocated(block); + mark_allocated(mm, block); mm->avail -= drm_buddy_block_size(mm, block); if (drm_buddy_block_is_clear(block)) mm->clear_avail -= drm_buddy_block_size(mm, block); @@ -1204,7 +1240,7 @@ void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p) struct drm_buddy_block *block; u64 count = 0, free; - list_for_each_entry(block, &mm->free_list[order], link) { + rbtree_for_each_entry(block, &mm->free_tree[order], rb) { BUG_ON(!drm_buddy_block_is_free(block)); count++; } diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index 513837632b7d..091823592034 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -10,6 +10,7 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/rbtree.h> #include <drm/drm_print.h> @@ -53,7 +54,11 @@ struct drm_buddy_block { * a list, if so desired. As soon as the block is freed with * drm_buddy_free* ownership is given back to the mm. */ - struct list_head link; + union { + struct rb_node rb; + struct list_head link; + }; + struct list_head tmp_link; }; @@ -68,7 +73,7 @@ struct drm_buddy_block { */ struct drm_buddy { /* Maintain a free list for each order. */ - struct list_head *free_list; + struct rb_root *free_tree; /* * Maintain explicit binary tree(s) to track the allocation of the diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index 8d2ba3749866..17190bb4837c 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -79,6 +79,62 @@ static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent ____ptr ? rb_entry(____ptr, type, member) : NULL; \ }) +/** + * rbtree_for_each_entry - iterate in-order over rb_root of given type + * + * @pos: the 'type *' to use as a loop cursor. + * @root: 'rb_root *' of the rbtree. + * @member: the name of the rb_node field within 'type'. + */ +#define rbtree_for_each_entry(pos, root, member) \ + for ((pos) = rb_entry_safe(rb_first(root), typeof(*(pos)), member); \ + (pos); \ + (pos) = rb_entry_safe(rb_next(&(pos)->member), typeof(*(pos)), member)) + +/** + * rbtree_reverse_for_each_entry - iterate in reverse in-order over rb_root + * of given type + * + * @pos: the 'type *' to use as a loop cursor. + * @root: 'rb_root *' of the rbtree. + * @member: the name of the rb_node field within 'type'. + */ +#define rbtree_reverse_for_each_entry(pos, root, member) \ + for ((pos) = rb_entry_safe(rb_last(root), typeof(*(pos)), member); \ + (pos); \ + (pos) = rb_entry_safe(rb_prev(&(pos)->member), typeof(*(pos)), member)) + +/** + * rbtree_for_each_entry_safe - iterate in-order over rb_root safe against removal + * + * @pos: the 'type *' to use as a loop cursor + * @n: another 'type *' to use as temporary storage + * @root: 'rb_root *' of the rbtree + * @member: the name of the rb_node field within 'type' + */ +#define rbtree_for_each_entry_safe(pos, n, root, member) \ + for ((pos) = rb_entry_safe(rb_first(root), typeof(*(pos)), member), \ + (n) = (pos) ? rb_entry_safe(rb_next(&(pos)->member), typeof(*(pos)), member) : NULL; \ + (pos); \ + (pos) = (n), \ + (n) = (pos) ? rb_entry_safe(rb_next(&(pos)->member), typeof(*(pos)), member) : NULL) + +/** + * rbtree_reverse_for_each_entry_safe - iterate in reverse in-order over rb_root + * safe against removal + * + * @pos: the struct type * to use as a loop cursor. + * @n: another struct type * to use as temporary storage. + * @root: pointer to struct rb_root to iterate. + * @member: name of the rb_node field within the struct. + */ +#define rbtree_reverse_for_each_entry_safe(pos, n, root, member) \ + for ((pos) = rb_entry_safe(rb_last(root), typeof(*(pos)), member), \ + (n) = (pos) ? rb_entry_safe(rb_prev(&(pos)->member), typeof(*(pos)), member) : NULL; \ + (pos); \ + (pos) = (n), \ + (n) = (pos) ? rb_entry_safe(rb_prev(&(pos)->member), typeof(*(pos)), member) : NULL) + /** * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of * given type allowing the backing memory of @pos to be invalidated base-commit: f4c75f975cf50fa2e1fd96c5aafe5aa62e55fbe4 -- 2.34.1

1 month, 3 weeks

5
6
0 0

[PATCH v2] media: staging/ipu7: fix isys device runtime PM usage in firmware closing

by bingbu.cao＠intel.com

From: Bingbu Cao <bingbu.cao(a)intel.com> The PM usage counter of isys was bumped up when start camera stream (opening firmware) but it was not dropped after stream stop(closing firmware), it forbids system fail to suspend due to the wrong PM state of ISYS. This patch drop the PM usage counter in firmware close to fix it. Cc: Stable(a)vger.kernel.org Fixes: a516d36bdc3d ("media: staging/ipu7: add IPU7 input system device driver") Signed-off-by: Bingbu Cao <bingbu.cao(a)intel.com> --- drivers/staging/media/ipu7/ipu7-isys-video.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/media/ipu7/ipu7-isys-video.c b/drivers/staging/media/ipu7/ipu7-isys-video.c index 8756da3a8fb0..173afd405d9b 100644 --- a/drivers/staging/media/ipu7/ipu7-isys-video.c +++ b/drivers/staging/media/ipu7/ipu7-isys-video.c @@ -946,6 +946,7 @@ void ipu7_isys_fw_close(struct ipu7_isys *isys) ipu7_fw_isys_close(isys); mutex_unlock(&isys->mutex); + pm_runtime_put(&isys->adev->auxdev.dev); } int ipu7_isys_setup_video(struct ipu7_isys_video *av, -- 2.34.1

1 month, 3 weeks

1
0
0 0

[PATCH] media: staging/ipu7: fix isys device runtime PM usage in firmware closing

by bingbu.cao＠intel.com

From: Bingbu Cao <bingbu.cao(a)intel.com> The PM usage counter of isys was bumped up when start camera stream (opening firmware) but it was not dropped after stream stop(closing firmware), it forbids system fail to suspend due to the wrong PM state of ISYS. This patch drop the PM usage counter in firmware close to fix it. Cc: Stable(a)vger.kernel.org Signed-off-by: Bingbu Cao <bingbu.cao(a)intel.com> --- drivers/staging/media/ipu7/ipu7-isys-video.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/media/ipu7/ipu7-isys-video.c b/drivers/staging/media/ipu7/ipu7-isys-video.c index 8756da3a8fb0..173afd405d9b 100644 --- a/drivers/staging/media/ipu7/ipu7-isys-video.c +++ b/drivers/staging/media/ipu7/ipu7-isys-video.c @@ -946,6 +946,7 @@ void ipu7_isys_fw_close(struct ipu7_isys *isys) ipu7_fw_isys_close(isys); mutex_unlock(&isys->mutex); + pm_runtime_put(&isys->adev->auxdev.dev); } int ipu7_isys_setup_video(struct ipu7_isys_video *av, -- 2.34.1

1 month, 3 weeks

2
1
0 0

[PATCH] zram: fix slot write race condition

by Sergey Senozhatsky

Parallel concurrent writes to the same zram index result in leaked zsmalloc handles. Schematically we can have something like this: CPU0 CPU1 zram_slot_lock() zs_free(handle) zram_slot_lock() zram_slot_lock() zs_free(handle) zram_slot_lock() compress compress handle = zs_malloc() handle = zs_malloc() zram_slot_lock zram_set_handle(handle) zram_slot_lock zram_slot_lock zram_set_handle(handle) zram_slot_lock Either CPU0 or CPU1 zsmalloc handle will leak because zs_free() is done too early. In fact, we need to reset zram entry right before we set its new handle, all under the same slot lock scope. Cc: stable(a)vger.kernel.org Reported-by: Changhui Zhong <czhong(a)redhat.com> Closes: https://lore.kernel.org/all/CAGVVp+UtpGoW5WEdEU7uVTtsSCjPN=ksN6EcvyypAtFDOU… Fixes: 71268035f5d73 ("zram: free slot memory early during write") Signed-off-by: Sergey Senozhatsky <senozhatsky(a)chromium.org> --- drivers/block/zram/zram_drv.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 9ac271b82780..dc4a1cdfaf98 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1788,6 +1788,7 @@ static int write_same_filled_page(struct zram *zram, unsigned long fill, u32 index) { zram_slot_lock(zram, index); + zram_free_page(zram, index); zram_set_flag(zram, index, ZRAM_SAME); zram_set_handle(zram, index, fill); zram_slot_unlock(zram, index); @@ -1820,11 +1821,13 @@ static int write_incompressible_page(struct zram *zram, struct page *page, return -ENOMEM; } + zram_slot_lock(zram, index); + zram_free_page(zram, index); + src = kmap_local_page(page); zs_obj_write(zram->mem_pool, handle, src, PAGE_SIZE); kunmap_local(src); - zram_slot_lock(zram, index); zram_set_flag(zram, index, ZRAM_HUGE); zram_set_handle(zram, index, handle); zram_set_obj_size(zram, index, PAGE_SIZE); @@ -1848,11 +1851,6 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index) unsigned long element; bool same_filled; - /* First, free memory allocated to this slot (if any) */ - zram_slot_lock(zram, index); - zram_free_page(zram, index); - zram_slot_unlock(zram, index); - mem = kmap_local_page(page); same_filled = page_same_filled(mem, &element); kunmap_local(mem); @@ -1890,10 +1888,11 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index) return -ENOMEM; } + zram_slot_lock(zram, index); + zram_free_page(zram, index); zs_obj_write(zram->mem_pool, handle, zstrm->buffer, comp_len); zcomp_stream_put(zstrm); - zram_slot_lock(zram, index); zram_set_handle(zram, index, handle); zram_set_obj_size(zram, index, comp_len); zram_slot_unlock(zram, index); -- 2.51.0.384.g4c02a37b29-goog

1 month, 3 weeks

1
1
0 0

[PATCH 0/3] samples/damon: fix boot time enable handling fixup merge mistakes

by SeongJae Park

First three patches of the patch series "mm/damon: fix misc bugs in DAMON modules" [1] was trying to fix boot time DAMON sample modules enabling issues by avoiding starting DAMON before the module initialization phase. However, probably by a mistake during a merge, only half of the change is merged, and the part for avoiding the starting of DAMON before the module initialized is missed. So the problem is not solved. Fix those. Note that the broken commits are merged into 6.17-rc1, but also backported to relevant stable kernels. So this series also need to be merged into the stable kernels. Hence Cc-ing stable@. [1] https://lore.kernel.org/20250706193207.39810-1-sj@kernel.org SeongJae Park (3): samples/damon/wsse: avoid starting DAMON before initialization samples/damon/prcl: avoid starting DAMON before initialization samples/damon/mtier: avoid starting DAMON before initialization samples/damon/mtier.c | 3 +++ samples/damon/prcl.c | 3 +++ samples/damon/wsse.c | 3 +++ 3 files changed, 9 insertions(+) base-commit: 186951910f4e44e20738d85c0421032634ddb298 -- 2.39.5

1 month, 3 weeks

2
7
0 0

+ nilfs2-fix-cfi-failure-when-accessing-sys-fs-nilfs2-features.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: nilfs2: fix CFI failure when accessing /sys/fs/nilfs2/features/* has been added to the -mm mm-hotfixes-unstable branch. Its filename is nilfs2-fix-cfi-failure-when-accessing-sys-fs-nilfs2-features.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: Nathan Chancellor <nathan(a)kernel.org> Subject: nilfs2: fix CFI failure when accessing /sys/fs/nilfs2/features/* Date: Sat, 6 Sep 2025 23:43:34 +0900 When accessing one of the files under /sys/fs/nilfs2/features when CONFIG_CFI_CLANG is enabled, there is a CFI violation: CFI failure at kobj_attr_show+0x59/0x80 (target: nilfs_feature_revision_show+0x0/0x30; expected type: 0xfc392c4d) ... Call Trace: <TASK> sysfs_kf_seq_show+0x2a6/0x390 ? __cfi_kobj_attr_show+0x10/0x10 kernfs_seq_show+0x104/0x15b seq_read_iter+0x580/0xe2b ... When the kobject of the kset for /sys/fs/nilfs2 is initialized, its ktype is set to kset_ktype, which has a ->sysfs_ops of kobj_sysfs_ops. When nilfs_feature_attr_group is added to that kobject via sysfs_create_group(), the kernfs_ops of each files is sysfs_file_kfops_rw, which will call sysfs_kf_seq_show() when ->seq_show() is called. sysfs_kf_seq_show() in turn calls kobj_attr_show() through ->sysfs_ops->show(). kobj_attr_show() casts the provided attribute out to a 'struct kobj_attribute' via container_of() and calls ->show(), resulting in the CFI violation since neither nilfs_feature_revision_show() nor nilfs_feature_README_show() match the prototype of ->show() in 'struct kobj_attribute'. Resolve the CFI violation by adjusting the second parameter in nilfs_feature_{revision,README}_show() from 'struct attribute' to 'struct kobj_attribute' to match the expected prototype. Link: https://lkml.kernel.org/r/20250906144410.22511-1-konishi.ryusuke@gmail.com Fixes: aebe17f68444 ("nilfs2: add /sys/fs/nilfs2/features group") Signed-off-by: Nathan Chancellor <nathan(a)kernel.org> Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: kernel test robot <oliver.sang(a)intel.com> Closes: https://lore.kernel.org/oe-lkp/202509021646.bc78d9ef-lkp@intel.com/ Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/nilfs2/sysfs.c | 4 ++-- fs/nilfs2/sysfs.h | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) --- a/fs/nilfs2/sysfs.c~nilfs2-fix-cfi-failure-when-accessing-sys-fs-nilfs2-features +++ a/fs/nilfs2/sysfs.c @@ -1075,7 +1075,7 @@ void nilfs_sysfs_delete_device_group(str ************************************************************************/ static ssize_t nilfs_feature_revision_show(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%d.%d\n", NILFS_CURRENT_REV, NILFS_MINOR_REV); @@ -1087,7 +1087,7 @@ static const char features_readme_str[] "(1) revision\n\tshow current revision of NILFS file system driver.\n"; static ssize_t nilfs_feature_README_show(struct kobject *kobj, - struct attribute *attr, + struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, features_readme_str); --- a/fs/nilfs2/sysfs.h~nilfs2-fix-cfi-failure-when-accessing-sys-fs-nilfs2-features +++ a/fs/nilfs2/sysfs.h @@ -50,16 +50,16 @@ struct nilfs_sysfs_dev_subgroups { struct completion sg_segments_kobj_unregister; }; -#define NILFS_COMMON_ATTR_STRUCT(name) \ +#define NILFS_KOBJ_ATTR_STRUCT(name) \ struct nilfs_##name##_attr { \ struct attribute attr; \ - ssize_t (*show)(struct kobject *, struct attribute *, \ + ssize_t (*show)(struct kobject *, struct kobj_attribute *, \ char *); \ - ssize_t (*store)(struct kobject *, struct attribute *, \ + ssize_t (*store)(struct kobject *, struct kobj_attribute *, \ const char *, size_t); \ } -NILFS_COMMON_ATTR_STRUCT(feature); +NILFS_KOBJ_ATTR_STRUCT(feature); #define NILFS_DEV_ATTR_STRUCT(name) \ struct nilfs_##name##_attr { \ _ Patches currently in -mm which might be from nathan(a)kernel.org are compiler-clangh-define-__sanitize___-macros-only-when-undefined.patch nilfs2-fix-cfi-failure-when-accessing-sys-fs-nilfs2-features.patch mm-rmap-convert-enum-rmap_level-to-enum-pgtable_level-fix.patch

1 month, 3 weeks

1
0
0 0

[PATCH] KVM: x86: Latch INITs only in specific CPU states in KVM_SET_VCPU_EVENTS

by Fei Li

Commit ff90afa75573 ("KVM: x86: Evaluate latched_init in KVM_SET_VCPU_EVENTS when vCPU not in SMM") changes KVM_SET_VCPU_EVENTS handler to set pending LAPIC INIT event regardless of if vCPU is in SMM mode or not. However, latch INIT without checking CPU state exists race condition, which causes the loss of INIT event. This is fatal during the VM startup process because it will cause some AP to never switch to non-root mode. Just as commit f4ef19108608 ("KVM: X86: Fix loss of pending INIT due to race") said: BSP AP kvm_vcpu_ioctl_x86_get_vcpu_events events->smi.latched_init = 0 kvm_vcpu_block kvm_vcpu_check_block schedule send INIT to AP kvm_vcpu_ioctl_x86_set_vcpu_events (e.g. `info registers -a` when VM starts/reboots) if (events->smi.latched_init == 0) clear INIT in pending_events kvm_apic_accept_events test_bit(KVM_APIC_INIT, &pe) == false vcpu->arch.mp_state maintains UNINITIALIZED send SIPI to AP kvm_apic_accept_events test_bit(KVM_APIC_SIPI, &pe) == false vcpu->arch.mp_state will never change to RUNNABLE (defy: UNINITIALIZED => INIT_RECEIVED => RUNNABLE) AP will never switch to non-root operation In such race result, VM hangs. E.g., BSP loops in SeaBIOS's SMPLock and AP will never be reset, and qemu hmp "info registers -a" shows: CPU#0 EAX=00000002 EBX=00000002 ECX=00000000 EDX=00020000 ESI=00000000 EDI=00000000 EBP=00000008 ESP=00006c6c EIP=000ef570 EFL=00000002 [-------] CPL=0 II=0 A20=1 SMM=0 HLT=0 ...... CPU#1 EAX=00000000 EBX=00000000 ECX=00000000 EDX=00080660 ESI=00000000 EDI=00000000 EBP=00000000 ESP=00000000 EIP=0000fff0 EFL=00000002 [-------] CPL=0 II=0 A20=1 SMM=0 HLT=0 ES =0000 00000000 0000ffff 00009300 CS =f000 ffff0000 0000ffff 00009b00 ...... Fix this by handling latched INITs only in specific CPU states (SMM, VMX non-root mode, SVM with GIF=0) in KVM_SET_VCPU_EVENTS. Cc: stable(a)vger.kernel.org Fixes: ff90afa75573 ("KVM: x86: Evaluate latched_init in KVM_SET_VCPU_EVENTS when vCPU not in SMM") Signed-off-by: Fei Li <lifei.shirley(a)bytedance.com> --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a1c49bc681c46..7001b2af00ed1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5556,7 +5556,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, return -EINVAL; #endif - if (lapic_in_kernel(vcpu)) { + if (!kvm_apic_init_sipi_allowed(vcpu) && lapic_in_kernel(vcpu)) { if (events->smi.latched_init) set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); else -- 2.39.2 (Apple Git-143)

1 month, 3 weeks

3
8
0 0

[PATCH net v2] net: mana: Remove redundant netdev_lock_ops_to_full() calls

by Saurabh Sengar

NET_SHAPER is always selected for MANA driver. When NET_SHAPER is enabled, netdev_lock_ops_to_full() reduces effectively to only an assert for lock, which is always held in the path when NET_SHAPER is enabled. Remove the redundant netdev_lock_ops_to_full() call. Signed-off-by: Saurabh Sengar <ssengar(a)linux.microsoft.com> --- [v2] - removed Fixes tag and stable CC drivers/net/ethernet/microsoft/mana/mana_en.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 550843e2164b..f0dbf4e82e0b 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2100,10 +2100,8 @@ static void mana_destroy_txq(struct mana_port_context *apc) napi = &apc->tx_qp[i].tx_cq.napi; if (apc->tx_qp[i].txq.napi_initialized) { napi_synchronize(napi); - netdev_lock_ops_to_full(napi->dev); napi_disable_locked(napi); netif_napi_del_locked(napi); - netdev_unlock_full_to_ops(napi->dev); apc->tx_qp[i].txq.napi_initialized = false; } mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object); @@ -2256,10 +2254,8 @@ static int mana_create_txq(struct mana_port_context *apc, mana_create_txq_debugfs(apc, i); set_bit(NAPI_STATE_NO_BUSY_POLL, &cq->napi.state); - netdev_lock_ops_to_full(net); netif_napi_add_locked(net, &cq->napi, mana_poll); napi_enable_locked(&cq->napi); - netdev_unlock_full_to_ops(net); txq->napi_initialized = true; mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); @@ -2295,10 +2291,8 @@ static void mana_destroy_rxq(struct mana_port_context *apc, if (napi_initialized) { napi_synchronize(napi); - netdev_lock_ops_to_full(napi->dev); napi_disable_locked(napi); netif_napi_del_locked(napi); - netdev_unlock_full_to_ops(napi->dev); } xdp_rxq_info_unreg(&rxq->xdp_rxq); @@ -2549,18 +2543,14 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, gc->cq_table[cq->gdma_id] = cq->gdma_cq; - netdev_lock_ops_to_full(ndev); netif_napi_add_weight_locked(ndev, &cq->napi, mana_poll, 1); - netdev_unlock_full_to_ops(ndev); WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx, cq->napi.napi_id)); WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL, rxq->page_pool)); - netdev_lock_ops_to_full(ndev); napi_enable_locked(&cq->napi); - netdev_unlock_full_to_ops(ndev); mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); out: -- 2.43.0

1 month, 3 weeks

2
1
0 0

+ samples-damon-mtier-avoid-starting-damon-before-initialization.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: samples/damon/mtier: avoid starting DAMON before initialization has been added to the -mm mm-hotfixes-unstable branch. Its filename is samples-damon-mtier-avoid-starting-damon-before-initialization.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: samples/damon/mtier: avoid starting DAMON before initialization Date: Mon, 8 Sep 2025 19:22:38 -0700 Commit 964314344eab ("samples/damon/mtier: support boot time enable setup") is somehow incompletely applying the origin patch [1]. It is missing the part that avoids starting DAMON before module initialization. Probably a mistake during a merge has happened. Fix it by applying the missed part again. Link: https://lkml.kernel.org/r/20250909022238.2989-4-sj@kernel.org Link: https://lore.kernel.org/20250706193207.39810-4-sj@kernel.org [1] Fixes: 964314344eab ("samples/damon/mtier: support boot time enable setup") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- samples/damon/mtier.c | 3 +++ 1 file changed, 3 insertions(+) --- a/samples/damon/mtier.c~samples-damon-mtier-avoid-starting-damon-before-initialization +++ a/samples/damon/mtier.c @@ -208,6 +208,9 @@ static int damon_sample_mtier_enable_sto if (enabled == is_enabled) return 0; + if (!init_called) + return 0; + if (enabled) { err = damon_sample_mtier_start(); if (err) _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-core-introduce-damon_call_control-dealloc_on_cancel.patch mm-damon-sysfs-use-dynamically-allocated-repeat-mode-damon_call_control.patch samples-damon-wsse-avoid-starting-damon-before-initialization.patch samples-damon-prcl-avoid-starting-damon-before-initialization.patch samples-damon-mtier-avoid-starting-damon-before-initialization.patch mm-zswap-store-page_size-compression-failed-page-as-is.patch mm-zswap-store-page_size-compression-failed-page-as-is-fix.patch mm-zswap-store-page_size-compression-failed-page-as-is-v5.patch mm-zswap-store-page_size-compression-failed-page-as-is-fix-2.patch mm-damon-core-add-damon_ctx-addr_unit.patch mm-damon-paddr-support-addr_unit-for-access-monitoring.patch mm-damon-paddr-support-addr_unit-for-damos_pageout.patch mm-damon-paddr-support-addr_unit-for-damos_lru_prio.patch mm-damon-paddr-support-addr_unit-for-migrate_hotcold.patch mm-damon-paddr-support-addr_unit-for-damos_stat.patch mm-damon-sysfs-implement-addr_unit-file-under-context-dir.patch docs-mm-damon-design-document-address-unit-parameter.patch docs-admin-guide-mm-damon-usage-document-addr_unit-file.patch docs-abi-damon-document-addr_unit-file.patch

1 month, 3 weeks

1
0
0 0

+ samples-damon-prcl-avoid-starting-damon-before-initialization.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: samples/damon/prcl: avoid starting DAMON before initialization has been added to the -mm mm-hotfixes-unstable branch. Its filename is samples-damon-prcl-avoid-starting-damon-before-initialization.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: samples/damon/prcl: avoid starting DAMON before initialization Date: Mon, 8 Sep 2025 19:22:37 -0700 Commit 2780505ec2b4 ("samples/damon/prcl: fix boot time enable crash") is somehow incompletely applying the origin patch [1]. It is missing the part that avoids starting DAMON before module initialization. Probably a mistake during a merge has happened. Fix it by applying the missed part again. Link: https://lkml.kernel.org/r/20250909022238.2989-3-sj@kernel.org Link: https://lore.kernel.org/20250706193207.39810-3-sj@kernel.org [1] Fixes: 2780505ec2b4 ("samples/damon/prcl: fix boot time enable crash") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- samples/damon/prcl.c | 3 +++ 1 file changed, 3 insertions(+) --- a/samples/damon/prcl.c~samples-damon-prcl-avoid-starting-damon-before-initialization +++ a/samples/damon/prcl.c @@ -137,6 +137,9 @@ static int damon_sample_prcl_enable_stor if (enabled == is_enabled) return 0; + if (!init_called) + return 0; + if (enabled) { err = damon_sample_prcl_start(); if (err) _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-core-introduce-damon_call_control-dealloc_on_cancel.patch mm-damon-sysfs-use-dynamically-allocated-repeat-mode-damon_call_control.patch samples-damon-wsse-avoid-starting-damon-before-initialization.patch samples-damon-prcl-avoid-starting-damon-before-initialization.patch samples-damon-mtier-avoid-starting-damon-before-initialization.patch mm-zswap-store-page_size-compression-failed-page-as-is.patch mm-zswap-store-page_size-compression-failed-page-as-is-fix.patch mm-zswap-store-page_size-compression-failed-page-as-is-v5.patch mm-zswap-store-page_size-compression-failed-page-as-is-fix-2.patch mm-damon-core-add-damon_ctx-addr_unit.patch mm-damon-paddr-support-addr_unit-for-access-monitoring.patch mm-damon-paddr-support-addr_unit-for-damos_pageout.patch mm-damon-paddr-support-addr_unit-for-damos_lru_prio.patch mm-damon-paddr-support-addr_unit-for-migrate_hotcold.patch mm-damon-paddr-support-addr_unit-for-damos_stat.patch mm-damon-sysfs-implement-addr_unit-file-under-context-dir.patch docs-mm-damon-design-document-address-unit-parameter.patch docs-admin-guide-mm-damon-usage-document-addr_unit-file.patch docs-abi-damon-document-addr_unit-file.patch

1 month, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror