Merge tag 'mm-hotfixes-stable-2024-01-28-23-21' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "22 hotfixes. 11 are cc:stable and the remainder address post-6.7
  issues or aren't considered appropriate for backporting"

* tag 'mm-hotfixes-stable-2024-01-28-23-21' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (22 commits)
  mm: thp_get_unmapped_area must honour topdown preference
  mm: huge_memory: don't force huge page alignment on 32 bit
  userfaultfd: fix mmap_changing checking in mfill_atomic_hugetlb
  selftests/mm: ksm_tests should only MADV_HUGEPAGE valid memory
  scs: add CONFIG_MMU dependency for vfree_atomic()
  mm/memory: fix folio_set_dirty() vs. folio_mark_dirty() in zap_pte_range()
  mm/huge_memory: fix folio_set_dirty() vs. folio_mark_dirty()
  selftests/mm: Update va_high_addr_switch.sh to check CPU for la57 flag
  selftests: mm: fix map_hugetlb failure on 64K page size systems
  MAINTAINERS: supplement of zswap maintainers update
  stackdepot: make fast paths lock-less again
  stackdepot: add stats counters exported via debugfs
  mm, kmsan: fix infinite recursion due to RCU critical section
  mm/writeback: fix possible divide-by-zero in wb_dirty_limits(), again
  selftests/mm: switch to bash from sh
  MAINTAINERS: add man-pages git trees
  mm: memcontrol: don't throttle dying tasks on memory.high
  mm: mmap: map MAP_STACK to VM_NOHUGEPAGE
  uprobes: use pagesize-aligned virtual address when replacing pages
  selftests/mm: mremap_test: fix build warning
  ...

8 files changed, 61 insertions, 17 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 94ef5c02b459..94c958f7ebb5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -37,6 +37,7 @@
 #include <linux/page_owner.h>
 #include <linux/sched/sysctl.h>
 #include <linux/memory-tiers.h>
+#include <linux/compat.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -809,7 +810,10 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 {
 	loff_t off_end = off + len;
 	loff_t off_align = round_up(off, size);
-	unsigned long len_pad, ret;
+	unsigned long len_pad, ret, off_sub;
+
+	if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
+		return 0;
 
 	if (off_end <= off_align || (off_end - off_align) < size)
 		return 0;
@@ -835,7 +839,13 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 	if (ret == addr)
 		return addr;
 
-	ret += (off - ret) & (size - 1);
+	off_sub = (off - ret) & (size - 1);
+
+	if (current->mm->get_unmapped_area == arch_get_unmapped_area_topdown &&
+	    !off_sub)
+		return ret + size;
+
+	ret += off_sub;
 	return ret;
 }
 
@@ -2437,7 +2447,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			page = pmd_page(old_pmd);
 			folio = page_folio(page);
 			if (!folio_test_dirty(folio) && pmd_dirty(old_pmd))
-				folio_set_dirty(folio);
+				folio_mark_dirty(folio);
 			if (!folio_test_referenced(folio) && pmd_young(old_pmd))
 				folio_set_referenced(folio);
 			folio_remove_rmap_pmd(folio, page, vma);
@@ -3563,7 +3573,7 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	}
 
 	if (pmd_dirty(pmdval))
-		folio_set_dirty(folio);
+		folio_mark_dirty(folio);
 	if (pmd_write(pmdval))
 		entry = make_writable_migration_entry(page_to_pfn(page));
 	else if (anon_exclusive)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e4c8735e7c85..46d8d02114cf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2623,8 +2623,9 @@ static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
 }
 
 /*
- * Scheduled by try_charge() to be executed from the userland return path
- * and reclaims memory over the high limit.
+ * Reclaims memory over the high limit. Called directly from
+ * try_charge() (context permitting), as well as from the userland
+ * return path where reclaim is always able to block.
  */
 void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 {
@@ -2644,6 +2645,17 @@ void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 
 retry_reclaim:
 	/*
+	 * Bail if the task is already exiting. Unlike memory.max,
+	 * memory.high enforcement isn't as strict, and there is no
+	 * OOM killer involved, which means the excess could already
+	 * be much bigger (and still growing) than it could for
+	 * memory.max; the dying task could get stuck in fruitless
+	 * reclaim for a long time, which isn't desirable.
+	 */
+	if (task_is_dying())
+		goto out;
+
+	/*
 	 * The allocating task should reclaim at least the batch size, but for
 	 * subsequent retries we only want to do what's necessary to prevent oom
 	 * or breaching resource isolation.
@@ -2693,6 +2705,9 @@ retry_reclaim:
 	}
 
 	/*
+	 * Reclaim didn't manage to push usage below the limit, slow
+	 * this allocating task down.
+	 *
 	 * If we exit early, we're guaranteed to die (since
 	 * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
 	 * need to account for any ill-begotten jiffies to pay them off later.
@@ -2887,11 +2902,17 @@ done_restock:
 		}
 	} while ((memcg = parent_mem_cgroup(memcg)));
 
+	/*
+	 * Reclaim is set up above to be called from the userland
+	 * return path. But also attempt synchronous reclaim to avoid
+	 * excessive overrun while the task is still inside the
+	 * kernel. If this is successful, the return path will see it
+	 * when it rechecks the overage and simply bail out.
+	 */
 	if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
 	    !(current->flags & PF_MEMALLOC) &&
-	    gfpflags_allow_blocking(gfp_mask)) {
+	    gfpflags_allow_blocking(gfp_mask))
 		mem_cgroup_handle_over_high(gfp_mask);
-	}
 	return 0;
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f9b61f4a668..636280d04008 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -982,7 +982,7 @@ static bool has_extra_refcount(struct page_state *ps, struct page *p,
 	int count = page_count(p) - 1;
 
 	if (extra_pins)
-		count -= 1;
+		count -= folio_nr_pages(page_folio(p));
 
 	if (count > 0) {
 		pr_err("%#lx: %s still referenced by %d users\n",
diff --git a/mm/memory.c b/mm/memory.c
index 7e1f4849463a..89bcae0b224d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1464,7 +1464,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			delay_rmap = 0;
 			if (!folio_test_anon(folio)) {
 				if (pte_dirty(ptent)) {
-					folio_set_dirty(folio);
+					folio_mark_dirty(folio);
 					if (tlb_delay_rmap(tlb)) {
 						delay_rmap = 1;
 						force_flush = 1;
diff --git a/mm/mmap.c b/mm/mmap.c
index b78e83d351d2..d89770eaab6b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1825,15 +1825,17 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		/*
 		 * mmap_region() will call shmem_zero_setup() to create a file,
 		 * so use shmem's get_unmapped_area in case it can be huge.
-		 * do_mmap() will clear pgoff, so match alignment.
 		 */
-		pgoff = 0;
 		get_area = shmem_get_unmapped_area;
 	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
 		/* Ensures that larger anonymous mappings are THP aligned. */
 		get_area = thp_get_unmapped_area;
 	}
 
+	/* Always treat pgoff as zero for anonymous memory. */
+	if (!file)
+		pgoff = 0;
+
 	addr = get_area(file, addr, len, pgoff, flags);
 	if (IS_ERR_VALUE(addr))
 		return addr;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index cd4e4ae77c40..02147b61712b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1638,7 +1638,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
 	 */
 	dtc->wb_thresh = __wb_calc_thresh(dtc);
 	dtc->wb_bg_thresh = dtc->thresh ?
-		div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
+		div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need
diff --git a/mm/readahead.c b/mm/readahead.c
index 23620c57c122..2648ec4f0494 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -469,7 +469,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 
 	if (!folio)
 		return -ENOMEM;
-	mark = round_up(mark, 1UL << order);
+	mark = round_down(mark, 1UL << order);
 	if (index == mark)
 		folio_set_readahead(folio);
 	err = filemap_add_folio(ractl->mapping, folio, index, gfp);
@@ -575,7 +575,7 @@ static void ondemand_readahead(struct readahead_control *ractl,
 	 * It's the expected callback index, assume sequential access.
 	 * Ramp up sizes, and push forward the readahead window.
 	 */
-	expected = round_up(ra->start + ra->size - ra->async_size,
+	expected = round_down(ra->start + ra->size - ra->async_size,
 			1UL << order);
 	if (index == expected || index == (ra->start + ra->size)) {
 		ra->start += ra->size;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 20e3b0d9cf7e..75fcf1f783bc 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
 					      unsigned long dst_start,
 					      unsigned long src_start,
 					      unsigned long len,
+					      atomic_t *mmap_changing,
 					      uffd_flags_t flags)
 {
 	struct mm_struct *dst_mm = dst_vma->vm_mm;
@@ -472,6 +473,15 @@ retry:
 				goto out;
 			}
 			mmap_read_lock(dst_mm);
+			/*
+			 * If memory mappings are changing because of non-cooperative
+			 * operation (e.g. mremap) running in parallel, bail out and
+			 * request the user to retry later
+			 */
+			if (mmap_changing && atomic_read(mmap_changing)) {
+				err = -EAGAIN;
+				break;
+			}
 
 			dst_vma = NULL;
 			goto retry;
@@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma,
 				    unsigned long dst_start,
 				    unsigned long src_start,
 				    unsigned long len,
+				    atomic_t *mmap_changing,
 				    uffd_flags_t flags);
 #endif /* CONFIG_HUGETLB_PAGE */
 
@@ -622,8 +633,8 @@ retry:
 	 * If this is a HUGETLB vma, pass off to appropriate routine
 	 */
 	if (is_vm_hugetlb_page(dst_vma))
-		return  mfill_atomic_hugetlb(dst_vma, dst_start,
-					     src_start, len, flags);
+		return  mfill_atomic_hugetlb(dst_vma, dst_start, src_start,
+					     len, mmap_changing, flags);
 
 	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
 		goto out_unlock;