Merge v6.13 into drm-next

A regression was caused by commit e4b5ccd392b9 ("drm/v3d: Ensure job
pointer is set to NULL after job completion"), but this commit is not
yet in next-fixes, fast-forward it.

Note that this recreates Linus merge in 96c84703f1cf ("Merge tag
'drm-next-2025-01-17' of https://gitlab.freedesktop.org/drm/kernel")
because I didn't want to backmerge a random point in the merge window.

Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch>

13 files changed, 146 insertions, 46 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 33b60d448fca..4f476411a9a2 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1523,7 +1523,7 @@ void folio_end_read(struct folio *folio, bool success)
 	/* Must be in bottom byte for x86 to work */
 	BUILD_BUG_ON(PG_uptodate > 7);
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
-	VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio);
+	VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio);
 
 	if (likely(success))
 		mask |= 1 << PG_uptodate;
@@ -2996,7 +2996,7 @@ static inline loff_t folio_seek_hole_data(struct xa_state *xas,
 		if (ops->is_partially_uptodate(folio, offset, bsz) ==
 							seek_data)
 			break;
-		start = (start + bsz) & ~(bsz - 1);
+		start = (start + bsz) & ~((u64)bsz - 1);
 		offset += bsz;
 	} while (offset < folio_size(folio));
 unlock:
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e53d83b3e5cf..db64116a4f84 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2206,6 +2206,16 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd)
 	return pmd;
 }
 
+static pmd_t clear_uffd_wp_pmd(pmd_t pmd)
+{
+	if (pmd_present(pmd))
+		pmd = pmd_clear_uffd_wp(pmd);
+	else if (is_swap_pmd(pmd))
+		pmd = pmd_swp_clear_uffd_wp(pmd);
+
+	return pmd;
+}
+
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		  unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
 {
@@ -2244,6 +2254,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
 		}
 		pmd = move_soft_dirty_pmd(pmd);
+		if (vma_has_uffd_without_event_remap(vma))
+			pmd = clear_uffd_wp_pmd(pmd);
 		set_pmd_at(mm, new_addr, new_pmd, pmd);
 		if (force_flush)
 			flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c498874a7170..eaaec19caa7c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5402,6 +5402,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
 			  unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte,
 			  unsigned long sz)
 {
+	bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *src_ptl, *dst_ptl;
@@ -5418,7 +5419,18 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 
 	pte = huge_ptep_get_and_clear(mm, old_addr, src_pte);
-	set_huge_pte_at(mm, new_addr, dst_pte, pte, sz);
+
+	if (need_clear_uffd_wp && pte_marker_uffd_wp(pte))
+		huge_pte_clear(mm, new_addr, dst_pte, sz);
+	else {
+		if (need_clear_uffd_wp) {
+			if (pte_present(pte))
+				pte = huge_pte_clear_uffd_wp(pte);
+			else if (is_swap_pte(pte))
+				pte = pte_swp_clear_uffd_wp(pte);
+		}
+		set_huge_pte_at(mm, new_addr, dst_pte, pte, sz);
+	}
 
 	if (src_ptl != dst_ptl)
 		spin_unlock(src_ptl);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 653dbb1ff05c..bad1e130eda8 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2422,7 +2422,7 @@ skip:
 			VM_BUG_ON(khugepaged_scan.address < hstart ||
 				  khugepaged_scan.address + HPAGE_PMD_SIZE >
 				  hend);
-			if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) {
+			if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) {
 				struct file *file = get_file(vma->vm_file);
 				pgoff_t pgoff = linear_page_index(vma,
 						khugepaged_scan.address);
@@ -2768,7 +2768,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		mmap_assert_locked(mm);
 		memset(cc->node_load, 0, sizeof(cc->node_load));
 		nodes_clear(cc->alloc_nmask);
-		if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) {
+		if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) {
 			struct file *file = get_file(vma->vm_file);
 			pgoff_t pgoff = linear_page_index(vma, addr);
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 737af23f4f4e..820ba3b5cbfc 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1093,7 +1093,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
 	pr_debug("%s(0x%px, %zu)\n", __func__, ptr, size);
 
 	if (kmemleak_enabled && ptr && !IS_ERR_PCPU(ptr))
-		create_object_percpu((__force unsigned long)ptr, size, 0, gfp);
+		create_object_percpu((__force unsigned long)ptr, size, 1, gfp);
 }
 EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu);
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 04f35659717a..162407fbf2bc 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2268,7 +2268,8 @@ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order,
 
 	page = __alloc_pages_noprof(gfp, order, nid, nodemask);
 
-	if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) {
+	if (unlikely(pol->mode == MPOL_INTERLEAVE ||
+		     pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) {
 		/* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */
 		if (static_branch_likely(&vm_numa_stat_key) &&
 		    page_to_nid(page) == nid) {
diff --git a/mm/mremap.c b/mm/mremap.c
index 60473413836b..cff7f552f909 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -138,6 +138,7 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		struct vm_area_struct *new_vma, pmd_t *new_pmd,
 		unsigned long new_addr, bool need_rmap_locks)
 {
+	bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma);
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *old_pte, *new_pte, pte;
 	pmd_t dummy_pmdval;
@@ -216,7 +217,18 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 			force_flush = true;
 		pte = move_pte(pte, old_addr, new_addr);
 		pte = move_soft_dirty_pte(pte);
-		set_pte_at(mm, new_addr, new_pte, pte);
+
+		if (need_clear_uffd_wp && pte_marker_uffd_wp(pte))
+			pte_clear(mm, new_addr, new_pte);
+		else {
+			if (need_clear_uffd_wp) {
+				if (pte_present(pte))
+					pte = pte_clear_uffd_wp(pte);
+				else if (is_swap_pte(pte))
+					pte = pte_swp_clear_uffd_wp(pte);
+			}
+			set_pte_at(mm, new_addr, new_pte, pte);
+		}
 	}
 
 	arch_leave_lazy_mmu_mode();
@@ -278,6 +290,15 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 	if (WARN_ON_ONCE(!pmd_none(*new_pmd)))
 		return false;
 
+	/* If this pmd belongs to a uffd vma with remap events disabled, we need
+	 * to ensure that the uffd-wp state is cleared from all pgtables. This
+	 * means recursing into lower page tables in move_page_tables(), and we
+	 * can reuse the existing code if we simply treat the entry as "not
+	 * moved".
+	 */
+	if (vma_has_uffd_without_event_remap(vma))
+		return false;
+
 	/*
 	 * We don't have to worry about the ordering of src and dst
 	 * ptlocks because exclusive mmap_lock prevents deadlock.
@@ -333,6 +354,15 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
 	if (WARN_ON_ONCE(!pud_none(*new_pud)))
 		return false;
 
+	/* If this pud belongs to a uffd vma with remap events disabled, we need
+	 * to ensure that the uffd-wp state is cleared from all pgtables. This
+	 * means recursing into lower page tables in move_page_tables(), and we
+	 * can reuse the existing code if we simply treat the entry as "not
+	 * moved".
+	 */
+	if (vma_has_uffd_without_event_remap(vma))
+		return false;
+
 	/*
 	 * We don't have to worry about the ordering of src and dst
 	 * ptlocks because exclusive mmap_lock prevents deadlock.
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d213ead95675..d9861e42b2bd 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -692,6 +692,8 @@ static unsigned long bdi_ratio_from_pages(unsigned long pages)
 	unsigned long ratio;
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
+	if (!dirty_thresh)
+		return -EINVAL;
 	ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh);
 
 	return ratio;
@@ -790,13 +792,15 @@ int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes)
 {
 	int ret;
 	unsigned long pages = min_bytes >> PAGE_SHIFT;
-	unsigned long min_ratio;
+	long min_ratio;
 
 	ret = bdi_check_pages_limit(pages);
 	if (ret)
 		return ret;
 
 	min_ratio = bdi_ratio_from_pages(pages);
+	if (min_ratio < 0)
+		return min_ratio;
 	return __bdi_set_min_ratio(bdi, min_ratio);
 }
 
@@ -809,13 +813,15 @@ int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes)
 {
 	int ret;
 	unsigned long pages = max_bytes >> PAGE_SHIFT;
-	unsigned long max_ratio;
+	long max_ratio;
 
 	ret = bdi_check_pages_limit(pages);
 	if (ret)
 		return ret;
 
 	max_ratio = bdi_ratio_from_pages(pages);
+	if (max_ratio < 0)
+		return max_ratio;
 	return __bdi_set_max_ratio(bdi, max_ratio);
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index cae7b93864c2..01eab25edf89 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5692,10 +5692,13 @@ __meminit void zone_pcp_init(struct zone *zone)
 			 zone->present_pages, zone_batchsize(zone));
 }
 
+static void setup_per_zone_lowmem_reserve(void);
+
 void adjust_managed_page_count(struct page *page, long count)
 {
 	atomic_long_add(count, &page_zone(page)->managed_pages);
 	totalram_pages_add(count);
+	setup_per_zone_lowmem_reserve();
 }
 EXPORT_SYMBOL(adjust_managed_page_count);
 
diff --git a/mm/shmem.c b/mm/shmem.c
index ac58d4fb2e6f..fdb5afa1cfe9 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -4368,7 +4368,7 @@ static int shmem_parse_opt_casefold(struct fs_context *fc, struct fs_parameter *
 				    bool latest_version)
 {
 	struct shmem_options *ctx = fc->fs_private;
-	unsigned int version = UTF8_LATEST;
+	int version = UTF8_LATEST;
 	struct unicode_map *encoding;
 	char *version_str = param->string + 5;
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9a859b7d18d7..b1ec5ece067e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4642,6 +4642,9 @@ retry:
 		reset_batch_size(walk);
 	}
 
+	__mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(),
+					stat.nr_demoted);
+
 	item = PGSTEAL_KSWAPD + reclaimer_offset();
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, reclaimed);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0889b75cef14..16bfe1c694dd 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -2122,10 +2122,20 @@ static void __init start_shepherd_timer(void)
 {
 	int cpu;
 
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
 		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
 			vmstat_update);
 
+		/*
+		 * For secondary CPUs during CPU hotplug scenarios,
+		 * vmstat_cpu_online() will enable the work.
+		 * mm/vmstat:online enables and disables vmstat_work
+		 * symmetrically during CPU hotplug events.
+		 */
+		if (!cpu_online(cpu))
+			disable_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+	}
+
 	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));
 }
diff --git a/mm/zswap.c b/mm/zswap.c
index 5a27af8d86ea..b84c20d889b1 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -251,7 +251,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	struct zswap_pool *pool;
 	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
-	int ret;
+	int ret, cpu;
 
 	if (!zswap_has_pool) {
 		/* if either are unset, pool initialization failed, and we
@@ -285,6 +285,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		goto error;
 	}
 
+	for_each_possible_cpu(cpu)
+		mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex);
+
 	ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
 				       &pool->node);
 	if (ret)
@@ -817,36 +820,41 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
-	struct crypto_acomp *acomp;
-	struct acomp_req *req;
+	struct crypto_acomp *acomp = NULL;
+	struct acomp_req *req = NULL;
+	u8 *buffer = NULL;
 	int ret;
 
-	mutex_init(&acomp_ctx->mutex);
-
-	acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-	if (!acomp_ctx->buffer)
-		return -ENOMEM;
+	buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!buffer) {
+		ret = -ENOMEM;
+		goto fail;
+	}
 
 	acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu));
 	if (IS_ERR(acomp)) {
 		pr_err("could not alloc crypto acomp %s : %ld\n",
 				pool->tfm_name, PTR_ERR(acomp));
 		ret = PTR_ERR(acomp);
-		goto acomp_fail;
+		goto fail;
 	}
-	acomp_ctx->acomp = acomp;
-	acomp_ctx->is_sleepable = acomp_is_async(acomp);
 
-	req = acomp_request_alloc(acomp_ctx->acomp);
+	req = acomp_request_alloc(acomp);
 	if (!req) {
 		pr_err("could not alloc crypto acomp_request %s\n",
 		       pool->tfm_name);
 		ret = -ENOMEM;
-		goto req_fail;
+		goto fail;
 	}
-	acomp_ctx->req = req;
 
+	/*
+	 * Only hold the mutex after completing allocations, otherwise we may
+	 * recurse into zswap through reclaim and attempt to hold the mutex
+	 * again resulting in a deadlock.
+	 */
+	mutex_lock(&acomp_ctx->mutex);
 	crypto_init_wait(&acomp_ctx->wait);
+
 	/*
 	 * if the backend of acomp is async zip, crypto_req_done() will wakeup
 	 * crypto_wait_req(); if the backend of acomp is scomp, the callback
@@ -855,12 +863,17 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   crypto_req_done, &acomp_ctx->wait);
 
+	acomp_ctx->buffer = buffer;
+	acomp_ctx->acomp = acomp;
+	acomp_ctx->is_sleepable = acomp_is_async(acomp);
+	acomp_ctx->req = req;
+	mutex_unlock(&acomp_ctx->mutex);
 	return 0;
 
-req_fail:
-	crypto_free_acomp(acomp_ctx->acomp);
-acomp_fail:
-	kfree(acomp_ctx->buffer);
+fail:
+	if (acomp)
+		crypto_free_acomp(acomp);
+	kfree(buffer);
 	return ret;
 }
 
@@ -869,27 +882,43 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
 
+	mutex_lock(&acomp_ctx->mutex);
 	if (!IS_ERR_OR_NULL(acomp_ctx)) {
 		if (!IS_ERR_OR_NULL(acomp_ctx->req))
 			acomp_request_free(acomp_ctx->req);
+		acomp_ctx->req = NULL;
 		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
 			crypto_free_acomp(acomp_ctx->acomp);
 		kfree(acomp_ctx->buffer);
 	}
+	mutex_unlock(&acomp_ctx->mutex);
 
 	return 0;
 }
 
-/* Prevent CPU hotplug from freeing up the per-CPU acomp_ctx resources */
-static struct crypto_acomp_ctx *acomp_ctx_get_cpu(struct crypto_acomp_ctx __percpu *acomp_ctx)
+static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool)
 {
-	cpus_read_lock();
-	return raw_cpu_ptr(acomp_ctx);
+	struct crypto_acomp_ctx *acomp_ctx;
+
+	for (;;) {
+		acomp_ctx = raw_cpu_ptr(pool->acomp_ctx);
+		mutex_lock(&acomp_ctx->mutex);
+		if (likely(acomp_ctx->req))
+			return acomp_ctx;
+		/*
+		 * It is possible that we were migrated to a different CPU after
+		 * getting the per-CPU ctx but before the mutex was acquired. If
+		 * the old CPU got offlined, zswap_cpu_comp_dead() could have
+		 * already freed ctx->req (among other things) and set it to
+		 * NULL. Just try again on the new CPU that we ended up on.
+		 */
+		mutex_unlock(&acomp_ctx->mutex);
+	}
 }
 
-static void acomp_ctx_put_cpu(void)
+static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx)
 {
-	cpus_read_unlock();
+	mutex_unlock(&acomp_ctx->mutex);
 }
 
 static bool zswap_compress(struct page *page, struct zswap_entry *entry,
@@ -905,9 +934,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry,
 	gfp_t gfp;
 	u8 *dst;
 
-	acomp_ctx = acomp_ctx_get_cpu(pool->acomp_ctx);
-	mutex_lock(&acomp_ctx->mutex);
-
+	acomp_ctx = acomp_ctx_get_cpu_lock(pool);
 	dst = acomp_ctx->buffer;
 	sg_init_table(&input, 1);
 	sg_set_page(&input, page, PAGE_SIZE, 0);
@@ -960,8 +987,7 @@ unlock:
 	else if (alloc_ret)
 		zswap_reject_alloc_fail++;
 
-	mutex_unlock(&acomp_ctx->mutex);
-	acomp_ctx_put_cpu();
+	acomp_ctx_put_unlock(acomp_ctx);
 	return comp_ret == 0 && alloc_ret == 0;
 }
 
@@ -972,9 +998,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 	struct crypto_acomp_ctx *acomp_ctx;
 	u8 *src;
 
-	acomp_ctx = acomp_ctx_get_cpu(entry->pool->acomp_ctx);
-	mutex_lock(&acomp_ctx->mutex);
-
+	acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool);
 	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
 	/*
 	 * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer
@@ -998,11 +1022,10 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE);
 	BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait));
 	BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
-	mutex_unlock(&acomp_ctx->mutex);
 
 	if (src != acomp_ctx->buffer)
 		zpool_unmap_handle(zpool, entry->handle);
-	acomp_ctx_put_cpu();
+	acomp_ctx_put_unlock(acomp_ctx);
 }
 
 /*********************************