Merge tag 'mm-hotfixes-stable-2022-12-02' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

torvalds · torvalds · commit bdaa78c6aa86 · 2022-12-02T13:39:38.000-08:00
Pull misc hotfixes from Andrew Morton:
 "15 hotfixes,  11 marked cc:stable.

  Only three or four of the latter address post-6.0 issues, which is
  hopefully a sign that things are converging"

* tag 'mm-hotfixes-stable-2022-12-02' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  revert "kbuild: fix -Wimplicit-function-declaration in license_is_gpl_compatible"
  Kconfig.debug: provide a little extra FRAME_WARN leeway when KASAN is enabled
  drm/amdgpu: temporarily disable broken Clang builds due to blown stack-frame
  mm/khugepaged: invoke MMU notifiers in shmem/file collapse paths
  mm/khugepaged: fix GUP-fast interaction by sending IPI
  mm/khugepaged: take the right locks for page table retraction
  mm: migrate: fix THP's mapcount on isolation
  mm: introduce arch_has_hw_nonleaf_pmd_young()
  mm: add dummy pmd_young() for architectures not having it
  mm/damon/sysfs: fix wrong empty schemes assumption under online tuning in damon_sysfs_set_schemes()
  tools/vm/slabinfo-gnuplot: use "grep -E" instead of "egrep"
  nilfs2: fix NULL pointer dereference in nilfs_palloc_commit_free_entry()
  hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing
  madvise: use zap_page_range_single for madvise dontneed
  mm: replace VM_WARN_ON to pr_warn if the node is offline with __GFP_THISNODE
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
@@ -490,6 +490,7 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return pmd;
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_ACCESSED);
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
@@ -622,6 +622,7 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return pmd;
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_ACCESSED);
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
@@ -600,6 +600,7 @@ static inline int pmd_dirty(pmd_t pmd)
 	return pte_dirty(pmd_pte(pmd));
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return pte_young(pmd_pte(pmd));
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
@@ -763,6 +763,7 @@ static inline int pmd_dirty(pmd_t pmd)
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
@@ -693,6 +693,7 @@ static inline unsigned long pmd_dirty(pmd_t pmd)
 	return pte_dirty(pte);
 }
 
+#define pmd_young pmd_young
 static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
@@ -139,6 +139,7 @@ static inline int pmd_dirty(pmd_t pmd)
 	return pmd_flags(pmd) & _PAGE_DIRTY;
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_ACCESSED;
@@ -1438,6 +1439,14 @@ static inline bool arch_has_hw_pte_young(void)
 	return true;
 }
 
+#ifdef CONFIG_XEN_PV
+#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young
+static inline bool arch_has_hw_nonleaf_pmd_young(void)
+{
+	return !cpu_feature_enabled(X86_FEATURE_XENPV);
+}
+#endif
+
 #ifdef CONFIG_PAGE_TABLE_CHECK
 static inline bool pte_user_accessible_page(pte_t pte)
 {
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
@@ -5,13 +5,20 @@ menu "Display Engine Configuration"
 config DRM_AMD_DC
 	bool "AMD DC - Enable new display engine"
 	default y
+	depends on BROKEN || !CC_IS_CLANG || X86_64 || SPARC64 || ARM64
 	select SND_HDA_COMPONENT if SND_HDA_CORE
 	select DRM_AMD_DC_DCN if (X86 || PPC_LONG_DOUBLE_128)
 	help
 	  Choose this option if you want to use the new display engine
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
+	  calculate_bandwidth() is presently broken on all !(X86_64 || SPARC64 || ARM64)
+	  architectures built with Clang (all released versions), whereby the stack
+	  frame gets blown up to well over 5k.  This would cause an immediate kernel
+	  panic on most architectures.  We'll revert this when the following bug report
+	  has been resolved: https://github.com/llvm/llvm-project/issues/41896.
+
 config DRM_AMD_DC_DCN
 	def_bool n
 	help
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
@@ -111,6 +111,13 @@ static void nilfs_dat_commit_free(struct inode *dat,
 	kunmap_atomic(kaddr);
 
 	nilfs_dat_commit_entry(dat, req);
+
+	if (unlikely(req->pr_desc_bh == NULL || req->pr_bitmap_bh == NULL)) {
+		nilfs_error(dat->i_sb,
+			    "state inconsistency probably due to duplicate use of vblocknr = %llu",
+			    (unsigned long long)req->pr_entry_nr);
+		return;
+	}
 	nilfs_palloc_commit_free_entry(dat, req);
 }
 
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
@@ -222,12 +222,16 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 #define tlb_needs_table_invalidate() (true)
 #endif
 
+void tlb_remove_table_sync_one(void);
+
 #else
 
 #ifdef tlb_needs_table_invalidate
 #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
 #endif
 
+static inline void tlb_remove_table_sync_one(void) { }
+
 #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
@@ -210,6 +210,20 @@ alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct p
 	return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array);
 }
 
+static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask)
+{
+	gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN);
+
+	if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN))
+		return;
+
+	if (node_online(this_node))
+		return;
+
+	pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node);
+	dump_stack();
+}
+
 /*
  * Allocate pages, preferring the node given as nid. The node must be valid and
  * online. For more general interface, see alloc_pages_node().
@@ -218,7 +232,7 @@ static inline struct page *
 __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
-	VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid));
+	warn_if_node_offline(nid, gfp_mask);
 
 	return __alloc_pages(gfp_mask, order, nid, NULL);
 }
@@ -227,7 +241,7 @@ static inline
 struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
-	VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid));
+	warn_if_node_offline(nid, gfp);
 
 	return __folio_alloc(gfp, order, nid, NULL);
 }
diff --git a/include/linux/license.h b/include/linux/license.h
@@ -2,8 +2,6 @@
 #ifndef __LICENSE_H
 #define __LICENSE_H
 
-#include <linux/string.h>
-
 static inline int license_is_gpl_compatible(const char *license)
 {
 	return (strcmp(license, "GPL") == 0
diff --git a/include/linux/mm.h b/include/linux/mm.h
@@ -1852,6 +1852,25 @@ static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodem
 	__show_free_areas(flags, nodemask, MAX_NR_ZONES - 1);
 }
 
+/*
+ * Parameter block passed down to zap_pte_range in exceptional cases.
+ */
+struct zap_details {
+	struct folio *single_folio;	/* Locked folio to be unmapped */
+	bool even_cows;			/* Zap COWed private pages too? */
+	zap_flags_t zap_flags;		/* Extra flags for zapping */
+};
+
+/*
+ * Whether to drop the pte markers, for example, the uffd-wp information for
+ * file-backed memory.  This should only be specified when we will completely
+ * drop the page in the mm, either by truncation or unmapping of the vma.  By
+ * default, the flag is not set.
+ */
+#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
+/* Set in unmap_vmas() to indicate a final unmap call.  Only used by hugetlb */
+#define  ZAP_FLAG_UNMAP              ((__force zap_flags_t) BIT(1))
+
 #ifdef CONFIG_MMU
 extern bool can_do_mlock(void);
 #else
@@ -1869,6 +1888,8 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		  unsigned long size);
 void zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		    unsigned long size);
+void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
+			   unsigned long size, struct zap_details *details);
 void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 		struct vm_area_struct *start_vma, unsigned long start,
 		unsigned long end);
@@ -3467,12 +3488,4 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 }
 #endif
 
-/*
- * Whether to drop the pte markers, for example, the uffd-wp information for
- * file-backed memory.  This should only be specified when we will completely
- * drop the page in the mm, either by truncation or unmapping of the vma.  By
- * default, the flag is not set.
- */
-#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
-
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
@@ -165,6 +165,13 @@ static inline pte_t *virt_to_kpte(unsigned long vaddr)
 	return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr);
 }
 
+#ifndef pmd_young
+static inline int pmd_young(pmd_t pmd)
+{
+	return 0;
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pte_t *ptep,
@@ -260,6 +267,17 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
+#ifndef arch_has_hw_nonleaf_pmd_young
+/*
+ * Return whether the accessed bit in non-leaf PMD entries is supported on the
+ * local CPU.
+ */
+static inline bool arch_has_hw_nonleaf_pmd_young(void)
+{
+	return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG);
+}
+#endif
+
 #ifndef arch_has_hw_pte_young
 /*
  * Return whether the accessed bit is supported on the local CPU.
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
@@ -399,6 +399,7 @@ config FRAME_WARN
 	default 2048 if GCC_PLUGIN_LATENT_ENTROPY
 	default 2048 if PARISC
 	default 1536 if (!64BIT && XTENSA)
+	default 1280 if KASAN && !64BIT
 	default 1024 if !64BIT
 	default 2048 if 64BIT
 	help
diff --git a/mm/compaction.c b/mm/compaction.c
@@ -984,29 +984,29 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			goto isolate_fail;
 		}
 
+		/*
+		 * Be careful not to clear PageLRU until after we're
+		 * sure the page is not being freed elsewhere -- the
+		 * page release code relies on it.
+		 */
+		if (unlikely(!get_page_unless_zero(page)))
+			goto isolate_fail;
+
 		/*
 		 * Migration will fail if an anonymous page is pinned in memory,
 		 * so avoid taking lru_lock and isolating it unnecessarily in an
 		 * admittedly racy check.
 		 */
 		mapping = page_mapping(page);
-		if (!mapping && page_count(page) > page_mapcount(page))
-			goto isolate_fail;
+		if (!mapping && (page_count(page) - 1) > total_mapcount(page))
+			goto isolate_fail_put;
 
 		/*
 		 * Only allow to migrate anonymous pages in GFP_NOFS context
 		 * because those do not depend on fs locks.
 		 */
 		if (!(cc->gfp_mask & __GFP_FS) && mapping)
-			goto isolate_fail;
-
-		/*
-		 * Be careful not to clear PageLRU until after we're
-		 * sure the page is not being freed elsewhere -- the
-		 * page release code relies on it.
-		 */
-		if (unlikely(!get_page_unless_zero(page)))
-			goto isolate_fail;
+			goto isolate_fail_put;
 
 		/* Only take pages on LRU: a check now makes later tests safe */
 		if (!PageLRU(page))
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
@@ -2283,12 +2283,54 @@ static struct damos *damon_sysfs_mk_scheme(
 			&wmarks);
 }
 
+static void damon_sysfs_update_scheme(struct damos *scheme,
+		struct damon_sysfs_scheme *sysfs_scheme)
+{
+	struct damon_sysfs_access_pattern *access_pattern =
+		sysfs_scheme->access_pattern;
+	struct damon_sysfs_quotas *sysfs_quotas = sysfs_scheme->quotas;
+	struct damon_sysfs_weights *sysfs_weights = sysfs_quotas->weights;
+	struct damon_sysfs_watermarks *sysfs_wmarks = sysfs_scheme->watermarks;
+
+	scheme->pattern.min_sz_region = access_pattern->sz->min;
+	scheme->pattern.max_sz_region = access_pattern->sz->max;
+	scheme->pattern.min_nr_accesses = access_pattern->nr_accesses->min;
+	scheme->pattern.max_nr_accesses = access_pattern->nr_accesses->max;
+	scheme->pattern.min_age_region = access_pattern->age->min;
+	scheme->pattern.max_age_region = access_pattern->age->max;
+
+	scheme->action = sysfs_scheme->action;
+
+	scheme->quota.ms = sysfs_quotas->ms;
+	scheme->quota.sz = sysfs_quotas->sz;
+	scheme->quota.reset_interval = sysfs_quotas->reset_interval_ms;
+	scheme->quota.weight_sz = sysfs_weights->sz;
+	scheme->quota.weight_nr_accesses = sysfs_weights->nr_accesses;
+	scheme->quota.weight_age = sysfs_weights->age;
+
+	scheme->wmarks.metric = sysfs_wmarks->metric;
+	scheme->wmarks.interval = sysfs_wmarks->interval_us;
+	scheme->wmarks.high = sysfs_wmarks->high;
+	scheme->wmarks.mid = sysfs_wmarks->mid;
+	scheme->wmarks.low = sysfs_wmarks->low;
+}
+
 static int damon_sysfs_set_schemes(struct damon_ctx *ctx,
 		struct damon_sysfs_schemes *sysfs_schemes)
 {
-	int i;
+	struct damos *scheme, *next;
+	int i = 0;
+
+	damon_for_each_scheme_safe(scheme, next, ctx) {
+		if (i < sysfs_schemes->nr)
+			damon_sysfs_update_scheme(scheme,
+					sysfs_schemes->schemes_arr[i]);
+		else
+			damon_destroy_scheme(scheme);
+		i++;
+	}
 
-	for (i = 0; i < sysfs_schemes->nr; i++) {
+	for (; i < sysfs_schemes->nr; i++) {
 		struct damos *scheme, *next;
 
 		scheme = damon_sysfs_mk_scheme(sysfs_schemes->schemes_arr[i]);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
@@ -5206,17 +5206,22 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 
 	__unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
 
-	/*
-	 * Unlock and free the vma lock before releasing i_mmap_rwsem.  When
-	 * the vma_lock is freed, this makes the vma ineligible for pmd
-	 * sharing.  And, i_mmap_rwsem is required to set up pmd sharing.
-	 * This is important as page tables for this unmapped range will
-	 * be asynchrously deleted.  If the page tables are shared, there
-	 * will be issues when accessed by someone else.
-	 */
-	__hugetlb_vma_unlock_write_free(vma);
-
-	i_mmap_unlock_write(vma->vm_file->f_mapping);
+	if (zap_flags & ZAP_FLAG_UNMAP) {	/* final unmap */
+		/*
+		 * Unlock and free the vma lock before releasing i_mmap_rwsem.
+		 * When the vma_lock is freed, this makes the vma ineligible
+		 * for pmd sharing.  And, i_mmap_rwsem is required to set up
+		 * pmd sharing.  This is important as page tables for this
+		 * unmapped range will be asynchrously deleted.  If the page
+		 * tables are shared, there will be issues when accessed by
+		 * someone else.
+		 */
+		__hugetlb_vma_unlock_write_free(vma);
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
+	} else {
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
+		hugetlb_vma_unlock_write(vma);
+	}
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
diff --git a/mm/madvise.c b/mm/madvise.c
diff --git a/mm/memory.c b/mm/memory.c
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
diff --git a/mm/vmscan.c b/mm/vmscan.c
diff --git a/tools/vm/slabinfo-gnuplot.sh b/tools/vm/slabinfo-gnuplot.sh

Original file line number	Diff line number	Diff line change
`@@ -490,6 +490,7 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)`
`490`	`490`	`return pmd;`
`491`	`491`	`}`
`492`	`492`
	`493`	`+#define pmd_young pmd_young`
`493`	`494`	`static inline int pmd_young(pmd_t pmd)`
`494`	`495`	`{`
`495`	`496`	`return !!(pmd_val(pmd) & _PAGE_ACCESSED);`
Original file line number	Diff line number	Diff line change
`@@ -622,6 +622,7 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)`
`622`	`622`	`return pmd;`
`623`	`623`	`}`
`624`	`624`
	`625`	`+#define pmd_young pmd_young`
`625`	`626`	`static inline int pmd_young(pmd_t pmd)`
`626`	`627`	`{`
`627`	`628`	`return !!(pmd_val(pmd) & _PAGE_ACCESSED);`
Original file line number	Diff line number	Diff line change
`@@ -600,6 +600,7 @@ static inline int pmd_dirty(pmd_t pmd)`
`600`	`600`	`return pte_dirty(pmd_pte(pmd));`
`601`	`601`	`}`
`602`	`602`
	`603`	`+#define pmd_young pmd_young`
`603`	`604`	`static inline int pmd_young(pmd_t pmd)`
`604`	`605`	`{`
`605`	`606`	`return pte_young(pmd_pte(pmd));`
Original file line number	Diff line number	Diff line change
`@@ -763,6 +763,7 @@ static inline int pmd_dirty(pmd_t pmd)`
`763`	`763`	`return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;`
`764`	`764`	`}`
`765`	`765`
	`766`	`+#define pmd_young pmd_young`
`766`	`767`	`static inline int pmd_young(pmd_t pmd)`
`767`	`768`	`{`
`768`	`769`	`return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;`
Original file line number	Diff line number	Diff line change
`@@ -693,6 +693,7 @@ static inline unsigned long pmd_dirty(pmd_t pmd)`
`693`	`693`	`return pte_dirty(pte);`
`694`	`694`	`}`
`695`	`695`
	`696`	`+#define pmd_young pmd_young`
`696`	`697`	`static inline unsigned long pmd_young(pmd_t pmd)`
`697`	`698`	`{`
`698`	`699`	`pte_t pte = __pte(pmd_val(pmd));`
Original file line number	Diff line number	Diff line change
`@@ -139,6 +139,7 @@ static inline int pmd_dirty(pmd_t pmd)`
`139`	`139`	`return pmd_flags(pmd) & _PAGE_DIRTY;`
`140`	`140`	`}`
`141`	`141`
	`142`	`+#define pmd_young pmd_young`
`142`	`143`	`static inline int pmd_young(pmd_t pmd)`
`143`	`144`	`{`
`144`	`145`	`return pmd_flags(pmd) & _PAGE_ACCESSED;`
`@@ -1438,6 +1439,14 @@ static inline bool arch_has_hw_pte_young(void)`
`1438`	`1439`	`return true;`
`1439`	`1440`	`}`
`1440`	`1441`
	`1442`	`+#ifdef CONFIG_XEN_PV`
	`1443`	`+#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young`
	`1444`	`+static inline bool arch_has_hw_nonleaf_pmd_young(void)`
	`1445`	`+{`
	`1446`	`+ return !cpu_feature_enabled(X86_FEATURE_XENPV);`
	`1447`	`+}`
	`1448`	`+#endif`
	`1449`	`+`
`1441`	`1450`	`#ifdef CONFIG_PAGE_TABLE_CHECK`
`1442`	`1451`	`static inline bool pte_user_accessible_page(pte_t pte)`
`1443`	`1452`	`{`