Sync mm-stable with mm-hotfixes-stable to pick up dependent patches

Merge branch 'mm-hotfixes-stable' into mm-stable

.mailmap

@@ -130,6 +130,7 @@ Domen Puncer <[email protected]>
 Douglas Gilbert <[email protected]>
 Ed L. Cashin <[email protected]>
 Erik Kaneda <[email protected]> <[email protected]>
+Eugen Hristev <[email protected]> <[email protected]>
 Evgeniy Polyakov <[email protected]>
 Ezequiel Garcia <[email protected]> <[email protected]>
 Felipe W Damasio <[email protected]>

Documentation/admin-guide/cgroup-v2.rst

@@ -1245,13 +1245,17 @@ PAGE_SIZE multiple when read back.
 	This is a simple interface to trigger memory reclaim in the
 	target cgroup.
 
-	This file accepts a string which contains the number of bytes to
-	reclaim.
+	This file accepts a single key, the number of bytes to reclaim.
+	No nested keys are currently supported.
 
 	Example::
 
 	  echo "1G" > memory.reclaim
 
+	The interface can be later extended with nested keys to
+	configure the reclaim behavior. For example, specify the
+	type of memory to reclaim from (anon, file, ..).
+
 	Please note that the kernel can over or under reclaim from
 	the target cgroup. If less bytes are reclaimed than the
 	specified amount, -EAGAIN is returned.
@@ -1263,13 +1267,6 @@ PAGE_SIZE multiple when read back.
 	This means that the networking layer will not adapt based on
 	reclaim induced by memory.reclaim.
 
-	This file also allows the user to specify the nodes to reclaim from,
-	via the 'nodes=' key, for example::
-
-	  echo "1G nodes=0,1" > memory.reclaim
-
-	The above instructs the kernel to reclaim memory from nodes 0,1.
-
   memory.peak
 	A read-only single value file which exists on non-root
 	cgroups.

arch/ia64/kernel/sys_ia64.c

@@ -170,6 +170,9 @@ ia64_mremap (unsigned long addr, unsigned long old_len, unsigned long new_len, u
 asmlinkage long
 ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *tp)
 {
+	struct timespec64 rtn_tp;
+	s64 tick_ns;
+
 	/*
 	 * ia64's clock_gettime() syscall is implemented as a vdso call
 	 * fsys_clock_gettime(). Currently it handles only
@@ -185,8 +188,8 @@ ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *
 	switch (which_clock) {
 	case CLOCK_REALTIME:
 	case CLOCK_MONOTONIC:
-		s64 tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq);
-		struct timespec64 rtn_tp = ns_to_timespec64(tick_ns);
+		tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq);
+		rtn_tp = ns_to_timespec64(tick_ns);
 		return put_timespec64(&rtn_tp, tp);
 	}
 

arch/sh/kernel/vmlinux.lds.S

@@ -4,6 +4,7 @@
  * Written by Niibe Yutaka and Paul Mundt
  */
 OUTPUT_ARCH(sh)
+#define RUNTIME_DISCARD_EXIT
 #include <asm/thread_info.h>
 #include <asm/cache.h>
 #include <asm/vmlinux.lds.h>

drivers/of/fdt.c

@@ -26,7 +26,6 @@
 #include <linux/serial_core.h>
 #include <linux/sysfs.h>
 #include <linux/random.h>
-#include <linux/kmemleak.h>
 
 #include <asm/setup.h>  /* for COMMAND_LINE_SIZE */
 #include <asm/page.h>
@@ -525,12 +524,9 @@ static int __init __reserved_mem_reserve_reg(unsigned long node,
 		size = dt_mem_next_cell(dt_root_size_cells, &prop);
 
 		if (size &&
-		    early_init_dt_reserve_memory(base, size, nomap) == 0) {
+		    early_init_dt_reserve_memory(base, size, nomap) == 0)
 			pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n",
 				uname, &base, (unsigned long)(size / SZ_1M));
-			if (!nomap)
-				kmemleak_alloc_phys(base, size, 0);
-		}
 		else
 			pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n",
 			       uname, &base, (unsigned long)(size / SZ_1M));

fs/freevxfs/Kconfig

@@ -8,7 +8,7 @@ config VXFS_FS
 	  of SCO UnixWare (and possibly others) and optionally available
 	  for Sunsoft Solaris, HP-UX and many other operating systems. However
 	  these particular OS implementations of vxfs may differ in on-disk
-	  data endianess and/or superblock offset. The vxfs module has been
+	  data endianness and/or superblock offset. The vxfs module has been
 	  tested with SCO UnixWare and HP-UX B.10.20 (pa-risc 1.1 arch.)
 	  Currently only readonly access is supported and VxFX versions
 	  2, 3 and 4. Tests were performed with HP-UX VxFS version 3.

fs/proc/task_mmu.c

@@ -745,9 +745,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 			page = pfn_swap_entry_to_page(swpent);
 	}
 	if (page) {
-		int mapcount = page_mapcount(page);
-
-		if (mapcount >= 2)
+		if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte))
 			mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
 		else
 			mss->private_hugetlb += huge_page_size(hstate_vma(vma));

fs/squashfs/squashfs_fs.h

@@ -183,7 +183,7 @@ static inline int squashfs_block_size(__le32 raw)
 #define SQUASHFS_ID_BLOCK_BYTES(A)	(SQUASHFS_ID_BLOCKS(A) *\
 					sizeof(u64))
 /* xattr id lookup table defines */
-#define SQUASHFS_XATTR_BYTES(A)		((A) * sizeof(struct squashfs_xattr_id))
+#define SQUASHFS_XATTR_BYTES(A)		(((u64) (A)) * sizeof(struct squashfs_xattr_id))
 
 #define SQUASHFS_XATTR_BLOCK(A)		(SQUASHFS_XATTR_BYTES(A) / \
 					SQUASHFS_METADATA_SIZE)

fs/squashfs/squashfs_fs_sb.h

@@ -63,7 +63,7 @@ struct squashfs_sb_info {
 	long long				bytes_used;
 	unsigned int				inodes;
 	unsigned int				fragments;
-	int					xattr_ids;
+	unsigned int				xattr_ids;
 	unsigned int				ids;
 	bool					panic_on_errors;
 	const struct squashfs_decompressor_thread_ops *thread_ops;

fs/squashfs/xattr.h

@@ -10,12 +10,12 @@
 
 #ifdef CONFIG_SQUASHFS_XATTR
 extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64,
-		u64 *, int *);
+		u64 *, unsigned int *);
 extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *,
 		unsigned int *, unsigned long long *);
 #else
 static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb,
-		u64 start, u64 *xattr_table_start, int *xattr_ids)
+		u64 start, u64 *xattr_table_start, unsigned int *xattr_ids)
 {
 	struct squashfs_xattr_id_table *id_table;
 

fs/squashfs/xattr_id.c

@@ -56,7 +56,7 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index,
  * Read uncompressed xattr id lookup table indexes from disk into memory
  */
 __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
-		u64 *xattr_table_start, int *xattr_ids)
+		u64 *xattr_table_start, unsigned int *xattr_ids)
 {
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
 	unsigned int len, indexes;
@@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
 	/* Sanity check values */
 
 	/* there is always at least one xattr id */
-	if (*xattr_ids == 0)
+	if (*xattr_ids <= 0)
 		return ERR_PTR(-EINVAL);
 
 	len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids);

include/linux/highmem-internal.h

@@ -200,7 +200,7 @@ static inline void *kmap_local_pfn(unsigned long pfn)
 static inline void __kunmap_local(const void *addr)
 {
 #ifdef ARCH_HAS_FLUSH_ON_KUNMAP
-	kunmap_flush_on_unmap(addr);
+	kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE));
 #endif
 }
 
@@ -227,7 +227,7 @@ static inline void *kmap_atomic_pfn(unsigned long pfn)
 static inline void __kunmap_atomic(const void *addr)
 {
 #ifdef ARCH_HAS_FLUSH_ON_KUNMAP
-	kunmap_flush_on_unmap(addr);
+	kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE));
 #endif
 	pagefault_enable();
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))

include/linux/hugetlb.h

@@ -8,6 +8,7 @@
 #include <linux/fs.h>
 #include <linux/hugetlb_inline.h>
 #include <linux/cgroup.h>
+#include <linux/page_ref.h>
 #include <linux/list.h>
 #include <linux/kref.h>
 #include <linux/pgtable.h>
@@ -1225,6 +1226,18 @@ static inline __init void hugetlb_cma_reserve(int order)
 }
 #endif
 
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+static inline bool hugetlb_pmd_shared(pte_t *pte)
+{
+	return page_count(virt_to_page(pte)) > 1;
+}
+#else
+static inline bool hugetlb_pmd_shared(pte_t *pte)
+{
+	return false;
+}
+#endif
+
 bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);
 
 #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE

include/linux/memcontrol.h

@@ -1688,10 +1688,13 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
 static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
 						  struct bdi_writeback *wb)
 {
+	struct mem_cgroup *memcg;
+
 	if (mem_cgroup_disabled())
 		return;
 
-	if (unlikely(&folio_memcg(folio)->css != wb->memcg_css))
+	memcg = folio_memcg(folio);
+	if (unlikely(memcg && &memcg->css != wb->memcg_css))
 		mem_cgroup_track_foreign_dirty_slowpath(folio, wb);
 }
 

include/linux/swap.h

@@ -418,8 +418,7 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 						  unsigned long nr_pages,
 						  gfp_t gfp_mask,
-						  unsigned int reclaim_options,
-						  nodemask_t *nodemask);
+						  unsigned int reclaim_options);
 extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
 						pg_data_t *pgdat,

lib/Kconfig.debug

@@ -754,6 +754,7 @@ config DEBUG_KMEMLEAK
 	select KALLSYMS
 	select CRC32
 	select STACKDEPOT
+	select STACKDEPOT_ALWAYS_INIT if !DEBUG_KMEMLEAK_DEFAULT_OFF
 	help
 	  Say Y here if you want to enable the memory leak
 	  detector. The memory allocation/freeing is traced in a way
@@ -1207,7 +1208,7 @@ config SCHED_DEBUG
 	depends on DEBUG_KERNEL && PROC_FS
 	default y
 	help
-	  If you say Y here, the /proc/sched_debug file will be provided
+	  If you say Y here, the /sys/kernel/debug/sched file will be provided
 	  that can help debug the scheduler. The runtime overhead of this
 	  option is minimal.
 

lib/maple_tree.c

@@ -667,12 +667,13 @@ static inline unsigned long mte_pivot(const struct maple_enode *mn,
 				 unsigned char piv)
 {
 	struct maple_node *node = mte_to_node(mn);
+	enum maple_type type = mte_node_type(mn);
 
-	if (piv >= mt_pivots[piv]) {
+	if (piv >= mt_pivots[type]) {
 		WARN_ON(1);
 		return 0;
 	}
-	switch (mte_node_type(mn)) {
+	switch (type) {
 	case maple_arange_64:
 		return node->ma64.pivot[piv];
 	case maple_range_64:
@@ -4876,7 +4877,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
 	unsigned long *pivots, *gaps;
 	void __rcu **slots;
 	unsigned long gap = 0;
-	unsigned long max, min, index;
+	unsigned long max, min;
 	unsigned char offset;
 
 	if (unlikely(mas_is_err(mas)))
@@ -4898,8 +4899,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
 		min = mas_safe_min(mas, pivots, --offset);
 
 	max = mas_safe_pivot(mas, pivots, offset, type);
-	index = mas->index;
-	while (index <= max) {
+	while (mas->index <= max) {
 		gap = 0;
 		if (gaps)
 			gap = gaps[offset];
@@ -4930,10 +4930,8 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
 		min = mas_safe_min(mas, pivots, offset);
 	}
 
-	if (unlikely(index > max)) {
-		mas_set_err(mas, -EBUSY);
-		return false;
-	}
+	if (unlikely((mas->index > max) || (size - 1 > max - mas->index)))
+		goto no_space;
 
 	if (unlikely(ma_is_leaf(type))) {
 		mas->offset = offset;
@@ -4950,9 +4948,11 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
 	return false;
 
 ascend:
-	if (mte_is_root(mas->node))
-		mas_set_err(mas, -EBUSY);
+	if (!mte_is_root(mas->node))
+		return false;
 
+no_space:
+	mas_set_err(mas, -EBUSY);
 	return false;
 }