1 files changed, 193 insertions, 150 deletions

diff --git a/mm/debug.c b/mm/debug.c
index b5b1de8c71ac..77fa8fe1d641 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -16,15 +16,19 @@
 #include <linux/ctype.h>
 
 #include "internal.h"
+#include <trace/events/migrate.h>
+
+/*
+ * Define EM() and EMe() so that MIGRATE_REASON from trace/events/migrate.h can
+ * be used to populate migrate_reason_names[].
+ */
+#undef EM
+#undef EMe
+#define EM(a, b)	b,
+#define EMe(a, b)	b
 
 const char *migrate_reason_names[MR_TYPES] = {
-	"compaction",
-	"memory_failure",
-	"memory_hotplug",
-	"syscall_or_cpuset",
-	"mempolicy_mbind",
-	"numa_misplaced",
-	"cma",
+	MIGRATE_REASON
 };
 
 const struct trace_print_flags pageflag_names[] = {
@@ -42,151 +46,106 @@ const struct trace_print_flags vmaflag_names[] = {
 	{0, NULL}
 };
 
-void __dump_page(struct page *page, const char *reason)
-{
-	struct page *head = compound_head(page);
-	struct address_space *mapping;
-	bool page_poisoned = PagePoisoned(page);
-	bool compound = PageCompound(page);
-	/*
-	 * Accessing the pageblock without the zone lock. It could change to
-	 * "isolate" again in the meantime, but since we are just dumping the
-	 * state for debugging, it should be fine to accept a bit of
-	 * inaccuracy here due to racing.
-	 */
-	bool page_cma = is_migrate_cma_page(page);
-	int mapcount;
-	char *type = "";
+#define DEF_PAGETYPE_NAME(_name) [PGTY_##_name - 0xf0] =  __stringify(_name)
 
-	/*
-	 * If struct page is poisoned don't access Page*() functions as that
-	 * leads to recursive loop. Page*() check for poisoned pages, and calls
-	 * dump_page() when detected.
-	 */
-	if (page_poisoned) {
-		pr_warn("page:%px is uninitialized and poisoned", page);
-		goto hex_only;
-	}
+static const char *page_type_names[] = {
+	DEF_PAGETYPE_NAME(slab),
+	DEF_PAGETYPE_NAME(hugetlb),
+	DEF_PAGETYPE_NAME(offline),
+	DEF_PAGETYPE_NAME(guard),
+	DEF_PAGETYPE_NAME(table),
+	DEF_PAGETYPE_NAME(buddy),
+	DEF_PAGETYPE_NAME(unaccepted),
+};
 
-	if (page < head || (page >= head + MAX_ORDER_NR_PAGES)) {
-		/* Corrupt page, cannot call page_mapping */
-		mapping = page->mapping;
-		head = page;
-		compound = false;
-	} else {
-		mapping = page_mapping(page);
-	}
+static const char *page_type_name(unsigned int page_type)
+{
+	unsigned i = (page_type >> 24) - 0xf0;
 
-	/*
-	 * Avoid VM_BUG_ON() in page_mapcount().
-	 * page->_mapcount space in struct page is used by sl[aou]b pages to
-	 * encode own info.
-	 */
-	mapcount = PageSlab(head) ? 0 : page_mapcount(page);
-
-	if (compound)
-		if (hpage_pincount_available(page)) {
-			pr_warn("page:%px refcount:%d mapcount:%d mapping:%p "
-				"index:%#lx head:%px order:%u "
-				"compound_mapcount:%d compound_pincount:%d\n",
-				page, page_ref_count(head), mapcount,
-				mapping, page_to_pgoff(page), head,
-				compound_order(head), compound_mapcount(page),
-				compound_pincount(page));
-		} else {
-			pr_warn("page:%px refcount:%d mapcount:%d mapping:%p "
-				"index:%#lx head:%px order:%u "
-				"compound_mapcount:%d\n",
-				page, page_ref_count(head), mapcount,
-				mapping, page_to_pgoff(page), head,
-				compound_order(head), compound_mapcount(page));
-		}
-	else
-		pr_warn("page:%px refcount:%d mapcount:%d mapping:%p index:%#lx\n",
-			page, page_ref_count(page), mapcount,
-			mapping, page_to_pgoff(page));
-	if (PageKsm(page))
-		type = "ksm ";
-	else if (PageAnon(page))
-		type = "anon ";
-	else if (mapping) {
-		const struct inode *host;
-		const struct address_space_operations *a_ops;
-		const struct hlist_node *dentry_first;
-		const struct dentry *dentry_ptr;
-		struct dentry dentry;
-
-		/*
-		 * mapping can be invalid pointer and we don't want to crash
-		 * accessing it, so probe everything depending on it carefully
-		 */
-		if (probe_kernel_read(&host, &mapping->host,
-					sizeof(struct inode *)) ||
-		    probe_kernel_read(&a_ops, &mapping->a_ops,
-				sizeof(struct address_space_operations *))) {
-			pr_warn("failed to read mapping->host or a_ops, mapping not a valid kernel address?\n");
-			goto out_mapping;
-		}
+	if (i >= ARRAY_SIZE(page_type_names))
+		return "unknown";
+	return page_type_names[i];
+}
 
-		if (!host) {
-			pr_warn("mapping->a_ops:%ps\n", a_ops);
-			goto out_mapping;
-		}
+static void __dump_folio(const struct folio *folio, const struct page *page,
+		unsigned long pfn, unsigned long idx)
+{
+	struct address_space *mapping = folio_mapping(folio);
+	int mapcount = atomic_read(&page->_mapcount) + 1;
+	char *type = "";
 
-		if (probe_kernel_read(&dentry_first,
-			&host->i_dentry.first, sizeof(struct hlist_node *))) {
-			pr_warn("mapping->a_ops:%ps with invalid mapping->host inode address %px\n",
-				a_ops, host);
-			goto out_mapping;
-		}
+	if (page_mapcount_is_type(mapcount))
+		mapcount = 0;
 
-		if (!dentry_first) {
-			pr_warn("mapping->a_ops:%ps\n", a_ops);
-			goto out_mapping;
-		}
+	pr_warn("page: refcount:%d mapcount:%d mapping:%p index:%#lx pfn:%#lx\n",
+			folio_ref_count(folio), mapcount, mapping,
+			folio->index + idx, pfn);
+	if (folio_test_large(folio)) {
+		int pincount = 0;
 
-		dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias);
-		if (probe_kernel_read(&dentry, dentry_ptr,
-							sizeof(struct dentry))) {
-			pr_warn("mapping->aops:%ps with invalid mapping->host->i_dentry.first %px\n",
-				a_ops, dentry_ptr);
-		} else {
-			/*
-			 * if dentry is corrupted, the %pd handler may still
-			 * crash, but it's unlikely that we reach here with a
-			 * corrupted struct page
-			 */
-			pr_warn("mapping->aops:%ps dentry name:\"%pd\"\n",
-								a_ops, &dentry);
-		}
+		if (folio_has_pincount(folio))
+			pincount = atomic_read(&folio->_pincount);
+
+		pr_warn("head: order:%u mapcount:%d entire_mapcount:%d nr_pages_mapped:%d pincount:%d\n",
+				folio_order(folio),
+				folio_mapcount(folio),
+				folio_entire_mapcount(folio),
+				folio_nr_pages_mapped(folio),
+				pincount);
 	}
-out_mapping:
+
+#ifdef CONFIG_MEMCG
+	if (folio->memcg_data)
+		pr_warn("memcg:%lx\n", folio->memcg_data);
+#endif
+	if (folio_test_ksm(folio))
+		type = "ksm ";
+	else if (folio_test_anon(folio))
+		type = "anon ";
+	else if (mapping)
+		dump_mapping(mapping);
 	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
 
-	pr_warn("%sflags: %#lx(%pGp)%s\n", type, page->flags, &page->flags,
-		page_cma ? " CMA" : "");
+	/*
+	 * Accessing the pageblock without the zone lock. It could change to
+	 * "isolate" again in the meantime, but since we are just dumping the
+	 * state for debugging, it should be fine to accept a bit of
+	 * inaccuracy here due to racing.
+	 */
+	pr_warn("%sflags: %pGp%s\n", type, &folio->flags,
+		is_migrate_cma_folio(folio, pfn) ? " CMA" : "");
+	if (page_has_type(&folio->page))
+		pr_warn("page_type: %x(%s)\n", folio->page.page_type >> 24,
+				page_type_name(folio->page.page_type));
 
-hex_only:
 	print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32,
 			sizeof(unsigned long), page,
 			sizeof(struct page), false);
-	if (head != page)
+	if (folio_test_large(folio))
 		print_hex_dump(KERN_WARNING, "head: ", DUMP_PREFIX_NONE, 32,
-			sizeof(unsigned long), head,
-			sizeof(struct page), false);
+			sizeof(unsigned long), folio,
+			2 * sizeof(struct page), false);
+}
 
-	if (reason)
-		pr_warn("page dumped because: %s\n", reason);
+static void __dump_page(const struct page *page)
+{
+	struct page_snapshot ps;
 
-#ifdef CONFIG_MEMCG
-	if (!page_poisoned && page->mem_cgroup)
-		pr_warn("page->mem_cgroup:%px\n", page->mem_cgroup);
-#endif
+	snapshot_page(&ps, page);
+	if (!snapshot_page_is_faithful(&ps))
+		pr_warn("page does not match folio\n");
+
+	__dump_folio(&ps.folio_snapshot, &ps.page_snapshot, ps.pfn, ps.idx);
 }
 
-void dump_page(struct page *page, const char *reason)
+void dump_page(const struct page *page, const char *reason)
 {
-	__dump_page(page, reason);
+	if (PagePoisoned(page))
+		pr_warn("page:%p is uninitialized and poisoned\n", page);
+	else
+		__dump_page(page);
+	if (reason)
+		pr_warn("page dumped because: %s\n", reason);
 	dump_page_owner(page);
 }
 EXPORT_SYMBOL(dump_page);
@@ -195,34 +154,35 @@ EXPORT_SYMBOL(dump_page);
 
 void dump_vma(const struct vm_area_struct *vma)
 {
-	pr_emerg("vma %px start %px end %px\n"
-		"next %px prev %px mm %px\n"
+	pr_emerg("vma %px start %px end %px mm %px\n"
 		"prot %lx anon_vma %px vm_ops %px\n"
 		"pgoff %lx file %px private_data %px\n"
+#ifdef CONFIG_PER_VMA_LOCK
+		"refcnt %x\n"
+#endif
 		"flags: %#lx(%pGv)\n",
-		vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
-		vma->vm_prev, vma->vm_mm,
+		vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_mm,
 		(unsigned long)pgprot_val(vma->vm_page_prot),
 		vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
 		vma->vm_file, vma->vm_private_data,
+#ifdef CONFIG_PER_VMA_LOCK
+		refcount_read(&vma->vm_refcnt),
+#endif
 		vma->vm_flags, &vma->vm_flags);
 }
 EXPORT_SYMBOL(dump_vma);
 
 void dump_mm(const struct mm_struct *mm)
 {
-	pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n"
-#ifdef CONFIG_MMU
-		"get_unmapped_area %px\n"
-#endif
-		"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
+	pr_emerg("mm %px task_size %lu\n"
+		"mmap_base %lu mmap_legacy_base %lu\n"
 		"pgd %px mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n"
 		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
 		"pinned_vm %llx data_vm %lx exec_vm %lx stack_vm %lx\n"
 		"start_code %lx end_code %lx start_data %lx end_data %lx\n"
 		"start_brk %lx brk %lx start_stack %lx\n"
 		"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
-		"binfmt %px flags %lx core_state %px\n"
+		"binfmt %px flags %*pb\n"
 #ifdef CONFIG_AIO
 		"ioctx_table %px\n"
 #endif
@@ -239,11 +199,8 @@ void dump_mm(const struct mm_struct *mm)
 		"tlb_flush_pending %d\n"
 		"def_flags: %#lx(%pGv)\n",
 
-		mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size,
-#ifdef CONFIG_MMU
-		mm->get_unmapped_area,
-#endif
-		mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
+		mm, mm->task_size,
+		mm->mmap_base, mm->mmap_legacy_base,
 		mm->pgd, atomic_read(&mm->mm_users),
 		atomic_read(&mm->mm_count),
 		mm_pgtables_bytes(mm),
@@ -254,7 +211,7 @@ void dump_mm(const struct mm_struct *mm)
 		mm->start_code, mm->end_code, mm->start_data, mm->end_data,
 		mm->start_brk, mm->brk, mm->start_stack,
 		mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
-		mm->binfmt, mm->flags, mm->core_state,
+		mm->binfmt, NUM_MM_FLAG_BITS, __mm_flags_get_bitmap(mm),
 #ifdef CONFIG_AIO
 		mm->ioctx_table,
 #endif
@@ -272,6 +229,84 @@ void dump_mm(const struct mm_struct *mm)
 		mm->def_flags, &mm->def_flags
 	);
 }
+EXPORT_SYMBOL(dump_mm);
+
+void dump_vmg(const struct vma_merge_struct *vmg, const char *reason)
+{
+	if (reason)
+		pr_warn("vmg %px dumped because: %s\n", vmg, reason);
+
+	if (!vmg) {
+		pr_warn("vmg %px state: (NULL)\n", vmg);
+		return;
+	}
+
+	pr_warn("vmg %px state: mm %px pgoff %lx\n"
+		"vmi %px [%lx,%lx)\n"
+		"prev %px middle %px next %px target %px\n"
+		"start %lx end %lx flags %lx\n"
+		"file %px anon_vma %px policy %px\n"
+		"uffd_ctx %px\n"
+		"anon_name %px\n"
+		"state %x\n"
+		"just_expand %d\n"
+		"__adjust_middle_start %d __adjust_next_start %d\n"
+		"__remove_middle %d __remove_next %d\n",
+		vmg, vmg->mm, vmg->pgoff,
+		vmg->vmi, vmg->vmi ? vma_iter_addr(vmg->vmi) : 0,
+		vmg->vmi ? vma_iter_end(vmg->vmi) : 0,
+		vmg->prev, vmg->middle, vmg->next, vmg->target,
+		vmg->start, vmg->end, vmg->vm_flags,
+		vmg->file, vmg->anon_vma, vmg->policy,
+#ifdef CONFIG_USERFAULTFD
+		vmg->uffd_ctx.ctx,
+#else
+		(void *)0,
+#endif
+		vmg->anon_name,
+		(int)vmg->state,
+		vmg->just_expand,
+		vmg->__adjust_middle_start, vmg->__adjust_next_start,
+		vmg->__remove_middle, vmg->__remove_next);
+
+	if (vmg->mm) {
+		pr_warn("vmg %px mm:\n", vmg);
+		dump_mm(vmg->mm);
+	} else {
+		pr_warn("vmg %px mm: (NULL)\n", vmg);
+	}
+
+	if (vmg->prev) {
+		pr_warn("vmg %px prev:\n", vmg);
+		dump_vma(vmg->prev);
+	} else {
+		pr_warn("vmg %px prev: (NULL)\n", vmg);
+	}
+
+	if (vmg->middle) {
+		pr_warn("vmg %px middle:\n", vmg);
+		dump_vma(vmg->middle);
+	} else {
+		pr_warn("vmg %px middle: (NULL)\n", vmg);
+	}
+
+	if (vmg->next) {
+		pr_warn("vmg %px next:\n", vmg);
+		dump_vma(vmg->next);
+	} else {
+		pr_warn("vmg %px next: (NULL)\n", vmg);
+	}
+
+#ifdef CONFIG_DEBUG_VM_MAPLE_TREE
+	if (vmg->vmi) {
+		pr_warn("vmg %px vmi:\n", vmg);
+		vma_iter_dump_tree(vmg->vmi);
+	} else {
+		pr_warn("vmg %px vmi: (NULL)\n", vmg);
+	}
+#endif
+}
+EXPORT_SYMBOL(dump_vmg);
 
 static bool page_init_poisoning __read_mostly = true;
 
@@ -292,7 +327,7 @@ static int __init setup_vm_debug(char *str)
 
 	while (*str) {
 		switch (tolower(*str)) {
-		case'p':
+		case 'p':
 			__page_init_poisoning = true;
 			break;
 		default:
@@ -317,5 +352,13 @@ void page_init_poison(struct page *page, size_t size)
 	if (page_init_poisoning)
 		memset(page, PAGE_POISON_PATTERN, size);
 }
-EXPORT_SYMBOL_GPL(page_init_poison);
+
+void vma_iter_dump_tree(const struct vma_iterator *vmi)
+{
+#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
+	mas_dump(&vmi->mas);
+	mt_dump(vmi->mas.tree, mt_dump_hex);
+#endif	/* CONFIG_DEBUG_VM_MAPLE_TREE */
+}
+
 #endif		/* CONFIG_DEBUG_VM */