mm/memory: convert print_bad_pte() to print_bad_page_map()

print_bad_pte() looks like something that should actually be a WARN or
similar, but historically it apparently has proven to be useful to detect
corruption of page tables even on production systems -- report the issue
and keep the system running to make it easier to actually detect what is
going wrong (e.g., multiple such messages might shed a light).

As we want to unify vm_normal_page_*() handling for PTE/PMD/PUD, we'll
have to take care of print_bad_pte() as well.

Let's prepare for using print_bad_pte() also for non-PTEs by adjusting the
implementation and renaming the function to print_bad_page_map().  Provide
print_bad_pte() as a simple wrapper.

Document the implicit locking requirements for the page table re-walk.

To make the function a bit more readable, factor out the ratelimit check
into is_bad_page_map_ratelimited() and place the printing of page table
content into __print_bad_page_map_pgtable().  We'll now dump information
from each level in a single line, and just stop the table walk once we hit
something that is not a present page table.

The report will now look something like (dumping pgd to pmd values):

[   77.943408] BUG: Bad page map in process XXX  pte:80000001233f5867
[   77.944077] addr:00007fd84bb1c000 vm_flags:08100071 anon_vma: ...
[   77.945186] pgd:10a89f067 p4d:10a89f067 pud:10e5a2067 pmd:105327067

Not using pgdp_get(), because that does not work properly on some arm
configs where pgd_t is an array.  Note that we are dumping all levels even
when levels are folded for simplicity.

[david@redhat.com: drop warning]
  Link: https://lkml.kernel.org/r/923b279c-de33-44dd-a923-2959afad8626@redhat.com
Link: https://lkml.kernel.org/r/20250811112631.759341-9-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Juegren Gross <jgross@suse.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 102 insertions, 20 deletions

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 4f88e460eb9c..94249e671a7e 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1983,6 +1983,24 @@ enum pgtable_level {
 	PGTABLE_LEVEL_PGD,
 };
 
+static inline const char *pgtable_level_to_str(enum pgtable_level level)
+{
+	switch (level) {
+	case PGTABLE_LEVEL_PTE:
+		return "pte";
+	case PGTABLE_LEVEL_PMD:
+		return "pmd";
+	case PGTABLE_LEVEL_PUD:
+		return "pud";
+	case PGTABLE_LEVEL_P4D:
+		return "p4d";
+	case PGTABLE_LEVEL_PGD:
+		return "pgd";
+	default:
+		return "unknown";
+	}
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT)
diff --git a/mm/memory.c b/mm/memory.c
index 626caedce35e..dc0107354d37 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -491,22 +491,8 @@ static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss)
 			add_mm_counter(mm, i, rss[i]);
 }
 
-/*
- * This function is called to print an error when a bad pte
- * is found. For example, we might have a PFN-mapped pte in
- * a region that doesn't allow it.
- *
- * The calling function must still handle the error.
- */
-static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
-			  pte_t pte, struct page *page)
+static bool is_bad_page_map_ratelimited(void)
 {
-	pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
-	p4d_t *p4d = p4d_offset(pgd, addr);
-	pud_t *pud = pud_offset(p4d, addr);
-	pmd_t *pmd = pmd_offset(pud, addr);
-	struct address_space *mapping;
-	pgoff_t index;
 	static unsigned long resume;
 	static unsigned long nr_shown;
 	static unsigned long nr_unshown;
@@ -518,7 +504,7 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 	if (nr_shown == 60) {
 		if (time_before(jiffies, resume)) {
 			nr_unshown++;
-			return;
+			return true;
 		}
 		if (nr_unshown) {
 			pr_alert("BUG: Bad page map: %lu messages suppressed\n",
@@ -529,15 +515,91 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 	}
 	if (nr_shown++ == 0)
 		resume = jiffies + 60 * HZ;
+	return false;
+}
+
+static void __print_bad_page_map_pgtable(struct mm_struct *mm, unsigned long addr)
+{
+	unsigned long long pgdv, p4dv, pudv, pmdv;
+	p4d_t p4d, *p4dp;
+	pud_t pud, *pudp;
+	pmd_t pmd, *pmdp;
+	pgd_t *pgdp;
+
+	/*
+	 * Although this looks like a fully lockless pgtable walk, it is not:
+	 * see locking requirements for print_bad_page_map().
+	 */
+	pgdp = pgd_offset(mm, addr);
+	pgdv = pgd_val(*pgdp);
+
+	if (!pgd_present(*pgdp) || pgd_leaf(*pgdp)) {
+		pr_alert("pgd:%08llx\n", pgdv);
+		return;
+	}
+
+	p4dp = p4d_offset(pgdp, addr);
+	p4d = p4dp_get(p4dp);
+	p4dv = p4d_val(p4d);
+
+	if (!p4d_present(p4d) || p4d_leaf(p4d)) {
+		pr_alert("pgd:%08llx p4d:%08llx\n", pgdv, p4dv);
+		return;
+	}
+
+	pudp = pud_offset(p4dp, addr);
+	pud = pudp_get(pudp);
+	pudv = pud_val(pud);
+
+	if (!pud_present(pud) || pud_leaf(pud)) {
+		pr_alert("pgd:%08llx p4d:%08llx pud:%08llx\n", pgdv, p4dv, pudv);
+		return;
+	}
+
+	pmdp = pmd_offset(pudp, addr);
+	pmd = pmdp_get(pmdp);
+	pmdv = pmd_val(pmd);
+
+	/*
+	 * Dumping the PTE would be nice, but it's tricky with CONFIG_HIGHPTE,
+	 * because the table should already be mapped by the caller and
+	 * doing another map would be bad. print_bad_page_map() should
+	 * already take care of printing the PTE.
+	 */
+	pr_alert("pgd:%08llx p4d:%08llx pud:%08llx pmd:%08llx\n", pgdv,
+		 p4dv, pudv, pmdv);
+}
+
+/*
+ * This function is called to print an error when a bad page table entry (e.g.,
+ * corrupted page table entry) is found. For example, we might have a
+ * PFN-mapped pte in a region that doesn't allow it.
+ *
+ * The calling function must still handle the error.
+ *
+ * This function must be called during a proper page table walk, as it will
+ * re-walk the page table to dump information: the caller MUST prevent page
+ * table teardown (by holding mmap, vma or rmap lock) and MUST hold the leaf
+ * page table lock.
+ */
+static void print_bad_page_map(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long long entry, struct page *page,
+		enum pgtable_level level)
+{
+	struct address_space *mapping;
+	pgoff_t index;
+
+	if (is_bad_page_map_ratelimited())
+		return;
 
 	mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL;
 	index = linear_page_index(vma, addr);
 
-	pr_alert("BUG: Bad page map in process %s  pte:%08llx pmd:%08llx\n",
-		 current->comm,
-		 (long long)pte_val(pte), (long long)pmd_val(*pmd));
+	pr_alert("BUG: Bad page map in process %s  %s:%08llx", current->comm,
+		 pgtable_level_to_str(level), entry);
+	__print_bad_page_map_pgtable(vma->vm_mm, addr);
 	if (page)
-		dump_page(page, "bad pte");
+		dump_page(page, "bad page map");
 	pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n",
 		 (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
 	pr_alert("file:%pD fault:%ps mmap:%ps mmap_prepare: %ps read_folio:%ps\n",
@@ -549,6 +611,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 	dump_stack();
 	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 }
+#define print_bad_pte(vma, addr, pte, page) \
+	print_bad_page_map(vma, addr, pte_val(pte), page, PGTABLE_LEVEL_PTE)
 
 /*
  * vm_normal_page -- This function gets the "struct page" associated with a pte.