Merge tag 'mm-hotfixes-stable-2025-02-19-17-49' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

torvalds · torvalds · commit 87a132e73910 · 2025-02-19T18:11:28.000-08:00
Pull misc fixes from Andrew Morton:
 "18 hotfixes. 5 are cc:stable and the remainder address post-6.13
  issues or aren't considered necessary for -stable kernels.

  10 are for MM and 8 are for non-MM. All are singletons, please see the
  changelogs for details"

* tag 'mm-hotfixes-stable-2025-02-19-17-49' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  test_xarray: fix failure in check_pause when CONFIG_XARRAY_MULTI is not defined
  kasan: don't call find_vm_area() in a PREEMPT_RT kernel
  MAINTAINERS: update Nick's contact info
  selftests/mm: fix check for running THP tests
  mm: hugetlb: avoid fallback for specific node allocation of 1G pages
  memcg: avoid dead loop when setting memory.max
  mailmap: update Nick's entry
  mm: pgtable: fix incorrect reclaim of non-empty PTE pages
  taskstats: modify taskstats version
  getdelays: fix error format characters
  mm/migrate_device: don't add folio to be freed to LRU in migrate_device_finalize()
  tools/mm: fix build warnings with musl-libc
  mailmap: add entry for Feng Tang
  .mailmap: add entries for Jeff Johnson
  mm,madvise,hugetlb: check for 0-length range after end address adjustment
  mm/zswap: fix inconsistency when zswap_store_page() fails
  lib/iov_iter: fix import_iovec_ubuf iovec management
  procfs: fix a locking bug in a vmcore_add_device_dump() error path
diff --git a/.mailmap b/.mailmap
@@ -226,6 +226,7 @@ Fangrui Song <i@maskray.me> <maskray@google.com>
 Felipe W Damasio <felipewd@terra.com.br>
 Felix Kuhling <fxkuehl@gmx.de>
 Felix Moeller <felix@derklecks.de>
+Feng Tang <feng.79.tang@gmail.com> <feng.tang@intel.com>
 Fenglin Wu <quic_fenglinw@quicinc.com> <fenglinw@codeaurora.org>
 Filipe Lautert <filipe@icewall.org>
 Finn Thain <fthain@linux-m68k.org> <fthain@telegraphics.com.au>
@@ -317,6 +318,8 @@ Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com>
 Jean Tourrilhes <jt@hpl.hp.com>
 Jeevan Shriram <quic_jshriram@quicinc.com> <jshriram@codeaurora.org>
 Jeff Garzik <jgarzik@pretzel.yyz.us>
+Jeff Johnson <jeff.johnson@oss.qualcomm.com> <jjohnson@codeaurora.org>
+Jeff Johnson <jeff.johnson@oss.qualcomm.com> <quic_jjohnson@quicinc.com>
 Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net>
 Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com>
 Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
@@ -531,6 +534,7 @@ Nicholas Piggin <npiggin@gmail.com> <npiggin@kernel.dk>
 Nicholas Piggin <npiggin@gmail.com> <npiggin@suse.de>
 Nicholas Piggin <npiggin@gmail.com> <nickpiggin@yahoo.com.au>
 Nicholas Piggin <npiggin@gmail.com> <piggin@cyberone.com.au>
+Nick Desaulniers <nick.desaulniers+lkml@gmail.com> <ndesaulniers@google.com>
 Nicolas Ferre <nicolas.ferre@microchip.com> <nicolas.ferre@atmel.com>
 Nicolas Pitre <nico@fluxnic.net> <nicolas.pitre@linaro.org>
 Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org>
diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst
@@ -308,7 +308,7 @@ an involved disclosed party. The current ambassadors list:
 
   Google	Kees Cook <keescook@chromium.org>
 
-  LLVM		Nick Desaulniers <ndesaulniers@google.com>
+  LLVM		Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
   ============= ========================================================
 
 If you want your organization to be added to the ambassadors list, please
diff --git a/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst b/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst
@@ -287,7 +287,7 @@ revelada involucrada. La lista de embajadores actuales:
 
   Google	Kees Cook <keescook@chromium.org>
 
-  LLVM		Nick Desaulniers <ndesaulniers@google.com>
+  LLVM		Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
   ============= ========================================================
 
 Si quiere que su organización se añada a la lista de embajadores, por
diff --git a/MAINTAINERS b/MAINTAINERS
@@ -5655,7 +5655,7 @@ F:	.clang-format
 
 CLANG/LLVM BUILD SUPPORT
 M:	Nathan Chancellor <nathan@kernel.org>
-R:	Nick Desaulniers <ndesaulniers@google.com>
+R:	Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
 R:	Bill Wendling <morbo@google.com>
 R:	Justin Stitt <justinstitt@google.com>
 L:	llvm@lists.linux.dev
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
@@ -1524,14 +1524,17 @@ int vmcore_add_device_dump(struct vmcoredd_data *data)
 		pr_warn_once("Unexpected adding of device dump\n");
 	if (vmcore_open) {
 		ret = -EBUSY;
-		goto out_err;
+		goto unlock;
 	}
 
 	list_add_tail(&dump->list, &vmcoredd_list);
 	vmcoredd_update_size(data_size);
 	mutex_unlock(&vmcore_mutex);
 	return 0;
 
+unlock:
+	mutex_unlock(&vmcore_mutex);
+
 out_err:
 	vfree(buf);
 	vfree(dump);
diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h
@@ -34,7 +34,7 @@
  */
 
 
-#define TASKSTATS_VERSION	14
+#define TASKSTATS_VERSION	15
 #define TS_COMM_LEN		32	/* should be >= TASK_COMM_LEN
 					 * in linux/sched.h */
 
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
@@ -1428,6 +1428,8 @@ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec,
 	struct iovec *iov = *iovp;
 	ssize_t ret;
 
+	*iovp = NULL;
+
 	if (compat)
 		ret = copy_compat_iovec_from_user(iov, uvec, 1);
 	else
@@ -1438,7 +1440,6 @@ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec,
 	ret = import_ubuf(type, iov->iov_base, iov->iov_len, i);
 	if (unlikely(ret))
 		return ret;
-	*iovp = NULL;
 	return i->count;
 }
 
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
@@ -1418,7 +1418,7 @@ static noinline void check_pause(struct xarray *xa)
 {
 	XA_STATE(xas, xa, 0);
 	void *entry;
-	unsigned int order;
+	int order;
 	unsigned long index = 1;
 	unsigned int count = 0;
 
@@ -1450,7 +1450,7 @@ static noinline void check_pause(struct xarray *xa)
 	xa_destroy(xa);
 
 	index = 0;
-	for (order = XA_CHUNK_SHIFT; order > 0; order--) {
+	for (order = order_limit - 1; order >= 0; order--) {
 		XA_BUG_ON(xa, xa_store_order(xa, index, order,
 					xa_mk_index(index), GFP_KERNEL));
 		index += 1UL << order;
@@ -1462,24 +1462,25 @@ static noinline void check_pause(struct xarray *xa)
 	rcu_read_lock();
 	xas_for_each(&xas, entry, ULONG_MAX) {
 		XA_BUG_ON(xa, entry != xa_mk_index(index));
-		index += 1UL << (XA_CHUNK_SHIFT - count);
+		index += 1UL << (order_limit - count - 1);
 		count++;
 	}
 	rcu_read_unlock();
-	XA_BUG_ON(xa, count != XA_CHUNK_SHIFT);
+	XA_BUG_ON(xa, count != order_limit);
 
 	index = 0;
 	count = 0;
-	xas_set(&xas, XA_CHUNK_SIZE / 2 + 1);
+	/* test unaligned index */
+	xas_set(&xas, 1 % (1UL << (order_limit - 1)));
 	rcu_read_lock();
 	xas_for_each(&xas, entry, ULONG_MAX) {
 		XA_BUG_ON(xa, entry != xa_mk_index(index));
-		index += 1UL << (XA_CHUNK_SHIFT - count);
+		index += 1UL << (order_limit - count - 1);
 		count++;
 		xas_pause(&xas);
 	}
 	rcu_read_unlock();
-	XA_BUG_ON(xa, count != XA_CHUNK_SHIFT);
+	XA_BUG_ON(xa, count != order_limit);
 
 	xa_destroy(xa);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
@@ -3145,7 +3145,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid)
 
 	/* do node specific alloc */
 	if (nid != NUMA_NO_NODE) {
-		m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h),
+		m = memblock_alloc_exact_nid_raw(huge_page_size(h), huge_page_size(h),
 				0, MEMBLOCK_ALLOC_ACCESSIBLE, nid);
 		if (!m)
 			return 0;
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
@@ -370,6 +370,36 @@ static inline bool init_task_stack_addr(const void *addr)
 			sizeof(init_thread_union.stack));
 }
 
+/*
+ * This function is invoked with report_lock (a raw_spinlock) held. A
+ * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping
+ * rt_spinlock.
+ *
+ * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a
+ * lockdep warning for this raw_spinlock -> spinlock dependency. This config
+ * option is enabled by default to ensure better test coverage to expose this
+ * kind of RT kernel problem. This lockdep splat, however, can be suppressed
+ * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the
+ * invalid PREEMPT_RT case has been taken care of.
+ */
+static inline struct vm_struct *kasan_find_vm_area(void *addr)
+{
+	static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP);
+	struct vm_struct *va;
+
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		return NULL;
+
+	/*
+	 * Suppress lockdep warning and fetch vmalloc area of the
+	 * offending address.
+	 */
+	lock_map_acquire_try(&vmalloc_map);
+	va = find_vm_area(addr);
+	lock_map_release(&vmalloc_map);
+	return va;
+}
+
 static void print_address_description(void *addr, u8 tag,
 				      struct kasan_report_info *info)
 {
@@ -399,7 +429,7 @@ static void print_address_description(void *addr, u8 tag,
 	}
 
 	if (is_vmalloc_addr(addr)) {
-		struct vm_struct *va = find_vm_area(addr);
+		struct vm_struct *va = kasan_find_vm_area(addr);
 
 		if (va) {
 			pr_err("The buggy address belongs to the virtual mapping at\n"
@@ -409,6 +439,8 @@ static void print_address_description(void *addr, u8 tag,
 			pr_err("\n");
 
 			page = vmalloc_to_page(addr);
+		} else {
+			pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr);
 		}
 	}
 
diff --git a/mm/madvise.c b/mm/madvise.c
@@ -933,7 +933,16 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 			 */
 			end = vma->vm_end;
 		}
-		VM_WARN_ON(start >= end);
+		/*
+		 * If the memory region between start and end was
+		 * originally backed by 4kB pages and then remapped to
+		 * be backed by hugepages while mmap_lock was dropped,
+		 * the adjustment for hugetlb vma above may have rounded
+		 * end down to the start address.
+		 */
+		if (start == end)
+			return 0;
+		VM_WARN_ON(start > end);
 	}
 
 	if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
@@ -4166,6 +4166,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 		memcg_memory_event(memcg, MEMCG_OOM);
 		if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0))
 			break;
+		cond_resched();
 	}
 
 	memcg_wb_domain_size_changed(memcg);
diff --git a/mm/memory.c b/mm/memory.c
@@ -1719,7 +1719,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	pmd_t pmdval;
 	unsigned long start = addr;
 	bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details);
-	bool direct_reclaim = false;
+	bool direct_reclaim = true;
 	int nr;
 
 retry:
@@ -1734,20 +1734,31 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	do {
 		bool any_skipped = false;
 
-		if (need_resched())
+		if (need_resched()) {
+			direct_reclaim = false;
 			break;
+		}
 
 		nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss,
 				      &force_flush, &force_break, &any_skipped);
 		if (any_skipped)
 			can_reclaim_pt = false;
 		if (unlikely(force_break)) {
 			addr += nr * PAGE_SIZE;
+			direct_reclaim = false;
 			break;
 		}
 	} while (pte += nr, addr += PAGE_SIZE * nr, addr != end);
 
-	if (can_reclaim_pt && addr == end)
+	/*
+	 * Fast path: try to hold the pmd lock and unmap the PTE page.
+	 *
+	 * If the pte lock was released midway (retry case), or if the attempt
+	 * to hold the pmd lock failed, then we need to recheck all pte entries
+	 * to ensure they are still none, thereby preventing the pte entries
+	 * from being repopulated by another thread.
+	 */
+	if (can_reclaim_pt && direct_reclaim && addr == end)
 		direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval);
 
 	add_mm_rss_vec(mm, rss);
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
@@ -840,20 +840,15 @@ void migrate_device_finalize(unsigned long *src_pfns,
 			dst = src;
 		}
 
+		if (!folio_is_zone_device(dst))
+			folio_add_lru(dst);
 		remove_migration_ptes(src, dst, 0);
 		folio_unlock(src);
-
-		if (folio_is_zone_device(src))
-			folio_put(src);
-		else
-			folio_putback_lru(src);
+		folio_put(src);
 
 		if (dst != src) {
 			folio_unlock(dst);
-			if (folio_is_zone_device(dst))
-				folio_put(dst);
-			else
-				folio_putback_lru(dst);
+			folio_put(dst);
 		}
 	}
 }
diff --git a/mm/zswap.c b/mm/zswap.c
@@ -1445,9 +1445,9 @@ static void shrink_worker(struct work_struct *w)
 * main API
 **********************************/
 
-static ssize_t zswap_store_page(struct page *page,
-				struct obj_cgroup *objcg,
-				struct zswap_pool *pool)
+static bool zswap_store_page(struct page *page,
+			     struct obj_cgroup *objcg,
+			     struct zswap_pool *pool)
 {
 	swp_entry_t page_swpentry = page_swap_entry(page);
 	struct zswap_entry *entry, *old;
@@ -1456,7 +1456,7 @@ static ssize_t zswap_store_page(struct page *page,
 	entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page));
 	if (!entry) {
 		zswap_reject_kmemcache_fail++;
-		return -EINVAL;
+		return false;
 	}
 
 	if (!zswap_compress(page, entry, pool))
@@ -1483,13 +1483,17 @@ static ssize_t zswap_store_page(struct page *page,
 
 	/*
 	 * The entry is successfully compressed and stored in the tree, there is
-	 * no further possibility of failure. Grab refs to the pool and objcg.
-	 * These refs will be dropped by zswap_entry_free() when the entry is
-	 * removed from the tree.
+	 * no further possibility of failure. Grab refs to the pool and objcg,
+	 * charge zswap memory, and increment zswap_stored_pages.
+	 * The opposite actions will be performed by zswap_entry_free()
+	 * when the entry is removed from the tree.
 	 */
 	zswap_pool_get(pool);
-	if (objcg)
+	if (objcg) {
 		obj_cgroup_get(objcg);
+		obj_cgroup_charge_zswap(objcg, entry->length);
+	}
+	atomic_long_inc(&zswap_stored_pages);
 
 	/*
 	 * We finish initializing the entry while it's already in xarray.
@@ -1510,13 +1514,13 @@ static ssize_t zswap_store_page(struct page *page,
 		zswap_lru_add(&zswap_list_lru, entry);
 	}
 
-	return entry->length;
+	return true;
 
 store_failed:
 	zpool_free(pool->zpool, entry->handle);
 compress_failed:
 	zswap_entry_cache_free(entry);
-	return -EINVAL;
+	return false;
 }
 
 bool zswap_store(struct folio *folio)
@@ -1526,7 +1530,6 @@ bool zswap_store(struct folio *folio)
 	struct obj_cgroup *objcg = NULL;
 	struct mem_cgroup *memcg = NULL;
 	struct zswap_pool *pool;
-	size_t compressed_bytes = 0;
 	bool ret = false;
 	long index;
 
@@ -1564,20 +1567,14 @@ bool zswap_store(struct folio *folio)
 
 	for (index = 0; index < nr_pages; ++index) {
 		struct page *page = folio_page(folio, index);
-		ssize_t bytes;
 
-		bytes = zswap_store_page(page, objcg, pool);
-		if (bytes < 0)
+		if (!zswap_store_page(page, objcg, pool))
 			goto put_pool;
-		compressed_bytes += bytes;
 	}
 
-	if (objcg) {
-		obj_cgroup_charge_zswap(objcg, compressed_bytes);
+	if (objcg)
 		count_objcg_events(objcg, ZSWPOUT, nr_pages);
-	}
 
-	atomic_long_add(nr_pages, &zswap_stored_pages);
 	count_vm_events(ZSWPOUT, nr_pages);
 
 	ret = true;
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
