Merge tag 'mm-stable-2024-07-21-14-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - In the series "mm: Avoid possible overflows in dirty throttling" Jan
   Kara addresses a couple of issues in the writeback throttling code.
   These fixes are also targetted at -stable kernels.

 - Ryusuke Konishi's series "nilfs2: fix potential issues related to
   reserved inodes" does that. This should actually be in the
   mm-nonmm-stable tree, along with the many other nilfs2 patches. My
   bad.

 - More folio conversions from Kefeng Wang in the series "mm: convert to
   folio_alloc_mpol()"

 - Kemeng Shi has sent some cleanups to the writeback code in the series
   "Add helper functions to remove repeated code and improve readability
   of cgroup writeback"

 - Kairui Song has made the swap code a little smaller and a little
   faster in the series "mm/swap: clean up and optimize swap cache
   index".

 - In the series "mm/memory: cleanly support zeropage in
   vm_insert_page*(), vm_map_pages*() and vmf_insert_mixed()" David
   Hildenbrand has reworked the rather sketchy handling of the use of
   the zeropage in MAP_SHARED mappings. I don't see any runtime effects
   here - more a cleanup/understandability/maintainablity thing.

 - Dev Jain has improved selftests/mm/va_high_addr_switch.c's handling
   of higher addresses, for aarch64. The (poorly named) series is
   "Restructure va_high_addr_switch".

 - The core TLB handling code gets some cleanups and possible slight
   optimizations in Bang Li's series "Add update_mmu_tlb_range() to
   simplify code".

 - Jane Chu has improved the handling of our
   fake-an-unrecoverable-memory-error testing feature MADV_HWPOISON in
   the series "Enhance soft hwpoison handling and injection".

 - Jeff Johnson has sent a billion patches everywhere to add
   MODULE_DESCRIPTION() to everything. Some landed in this pull.

 - In the series "mm: cleanup MIGRATE_SYNC_NO_COPY mode", Kefeng Wang
   has simplified migration's use of hardware-offload memory copying.

 - Yosry Ahmed performs more folio API conversions in his series "mm:
   zswap: trivial folio conversions".

 - In the series "large folios swap-in: handle refault cases first",
   Chuanhua Han inches us forward in the handling of large pages in the
   swap code. This is a cleanup and optimization, working toward the end
   objective of full support of large folio swapin/out.

 - In the series "mm,swap: cleanup VMA based swap readahead window
   calculation", Huang Ying has contributed some cleanups and a possible
   fixlet to his VMA based swap readahead code.

 - In the series "add mTHP support for anonymous shmem" Baolin Wang has
   taught anonymous shmem mappings to use multisize THP. By default this
   is a no-op - users must opt in vis sysfs controls. Dramatic
   improvements in pagefault latency are realized.

 - David Hildenbrand has some cleanups to our remaining use of
   page_mapcount() in the series "fs/proc: move page_mapcount() to
   fs/proc/internal.h".

 - David also has some highmem accounting cleanups in the series
   "mm/highmem: don't track highmem pages manually".

 - Build-time fixes and cleanups from John Hubbard in the series
   "cleanups, fixes, and progress towards avoiding "make headers"".

 - Cleanups and consolidation of the core pagemap handling from Barry
   Song in the series "mm: introduce pmd|pte_needs_soft_dirty_wp helpers
   and utilize them".

 - Lance Yang's series "Reclaim lazyfree THP without splitting" has
   reduced the latency of the reclaim of pmd-mapped THPs under fairly
   common circumstances. A 10x speedup is seen in a microbenchmark.

   It does this by punting to aother CPU but I guess that's a win unless
   all CPUs are pegged.

 - hugetlb_cgroup cleanups from Xiu Jianfeng in the series
   "mm/hugetlb_cgroup: rework on cftypes".

 - Miaohe Lin's series "Some cleanups for memory-failure" does just that
   thing.

 - Someone other than SeongJae has developed a DAMON feature in Honggyu
   Kim's series "DAMON based tiered memory management for CXL memory".
   This adds DAMON features which may be used to help determine the
   efficiency of our placement of CXL/PCIe attached DRAM.

 - DAMON user API centralization and simplificatio work in SeongJae
   Park's series "mm/damon: introduce DAMON parameters online commit
   function".

 - In the series "mm: page_type, zsmalloc and page_mapcount_reset()"
   David Hildenbrand does some maintenance work on zsmalloc - partially
   modernizing its use of pageframe fields.

 - Kefeng Wang provides more folio conversions in the series "mm: remove
   page_maybe_dma_pinned() and page_mkclean()".

 - More cleanup from David Hildenbrand, this time in the series
   "mm/memory_hotplug: use PageOffline() instead of PageReserved() for
   !ZONE_DEVICE". It "enlightens memory hotplug more about PageOffline()
   pages" and permits the removal of some virtio-mem hacks.

 - Barry Song's series "mm: clarify folio_add_new_anon_rmap() and
   __folio_add_anon_rmap()" is a cleanup to the anon folio handling in
   preparation for mTHP (multisize THP) swapin.

 - Kefeng Wang's series "mm: improve clear and copy user folio"
   implements more folio conversions, this time in the area of large
   folio userspace copying.

 - The series "Docs/mm/damon/maintaier-profile: document a mailing tool
   and community meetup series" tells people how to get better involved
   with other DAMON developers. From SeongJae Park.

 - A large series ("kmsan: Enable on s390") from Ilya Leoshkevich does
   that.

 - David Hildenbrand sends along more cleanups, this time against the
   migration code. The series is "mm/migrate: move NUMA hinting fault
   folio isolation + checks under PTL".

 - Jan Kara has found quite a lot of strangenesses and minor errors in
   the readahead code. He addresses this in the series "mm: Fix various
   readahead quirks".

 - SeongJae Park's series "selftests/damon: test DAMOS tried regions and
   {min,max}_nr_regions" adds features and addresses errors in DAMON's
   self testing code.

 - Gavin Shan has found a userspace-triggerable WARN in the pagecache
   code. The series "mm/filemap: Limit page cache size to that supported
   by xarray" addresses this. The series is marked cc:stable.

 - Chengming Zhou's series "mm/ksm: cmp_and_merge_page() optimizations
   and cleanup" cleans up and slightly optimizes KSM.

 - Roman Gushchin has separated the memcg-v1 and memcg-v2 code - lots of
   code motion. The series (which also makes the memcg-v1 code
   Kconfigurable) are "mm: memcg: separate legacy cgroup v1 code and put
   under config option" and "mm: memcg: put cgroup v1-specific memcg
   data under CONFIG_MEMCG_V1"

 - Dan Schatzberg's series "Add swappiness argument to memory.reclaim"
   adds an additional feature to this cgroup-v2 control file.

 - The series "Userspace controls soft-offline pages" from Jiaqi Yan
   permits userspace to stop the kernel's automatic treatment of
   excessive correctable memory errors. In order to permit userspace to
   monitor and handle this situation.

 - Kefeng Wang's series "mm: migrate: support poison recover from
   migrate folio" teaches the kernel to appropriately handle migration
   from poisoned source folios rather than simply panicing.

 - SeongJae Park's series "Docs/damon: minor fixups and improvements"
   does those things.

 - In the series "mm/zsmalloc: change back to per-size_class lock"
   Chengming Zhou improves zsmalloc's scalability and memory
   utilization.

 - Vivek Kasireddy's series "mm/gup: Introduce memfd_pin_folios() for
   pinning memfd folios" makes the GUP code use FOLL_PIN rather than
   bare refcount increments. So these paes can first be moved aside if
   they reside in the movable zone or a CMA block.

 - Andrii Nakryiko has added a binary ioctl()-based API to
   /proc/pid/maps for much faster reading of vma information. The series
   is "query VMAs from /proc/<pid>/maps".

 - In the series "mm: introduce per-order mTHP split counters" Lance
   Yang improves the kernel's presentation of developer information
   related to multisize THP splitting.

 - Michael Ellerman has developed the series "Reimplement huge pages
   without hugepd on powerpc (8xx, e500, book3s/64)". This permits
   userspace to use all available huge page sizes.

 - In the series "revert unconditional slab and page allocator fault
   injection calls" Vlastimil Babka removes a performance-affecting and
   not very useful feature from slab fault injection.

* tag 'mm-stable-2024-07-21-14-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (411 commits)
  mm/mglru: fix ineffective protection calculation
  mm/zswap: fix a white space issue
  mm/hugetlb: fix kernel NULL pointer dereference when migrating hugetlb folio
  mm/hugetlb: fix possible recursive locking detected warning
  mm/gup: clear the LRU flag of a page before adding to LRU batch
  mm/numa_balancing: teach mpol_to_str about the balancing mode
  mm: memcg1: convert charge move flags to unsigned long long
  alloc_tag: fix page_ext_get/page_ext_put sequence during page splitting
  lib: reuse page_ext_data() to obtain codetag_ref
  lib: add missing newline character in the warning message
  mm/mglru: fix overshooting shrinker memory
  mm/mglru: fix div-by-zero in vmpressure_calc_level()
  mm/kmemleak: replace strncpy() with strscpy()
  mm, page_alloc: put should_fail_alloc_page() back behing CONFIG_FAIL_PAGE_ALLOC
  mm, slab: put should_failslab() back behind CONFIG_SHOULD_FAILSLAB
  mm: ignore data-race in __swap_writepage
  hugetlbfs: ensure generic_hugetlb_get_unmapped_area() returns higher address than mmap_min_addr
  mm: shmem: rename mTHP shmem counters
  mm: swap_state: use folio_alloc_mpol() in __read_swap_cache_async()
  mm/migrate: putback split folios when numa hint migration fails
  ...

10 files changed, 194 insertions, 43 deletions

diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index b89159591ca0..46f5c9660616 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -13,6 +13,7 @@
 #define _S390_CHECKSUM_H
 
 #include <linux/instrumented.h>
+#include <linux/kmsan-checks.h>
 #include <linux/in6.h>
 
 static inline __wsum cksm(const void *buff, int len, __wsum sum)
@@ -23,6 +24,7 @@ static inline __wsum cksm(const void *buff, int len, __wsum sum)
 	};
 
 	instrument_read(buff, len);
+	kmsan_check_memory(buff, len);
 	asm volatile("\n"
 		"0:	cksm	%[sum],%[rp]\n"
 		"	jo	0b\n"
diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index c786538e397c..dae8843b164f 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -12,6 +12,7 @@
 #define _ASM_S390_CPACF_H
 
 #include <asm/facility.h>
+#include <linux/kmsan-checks.h>
 
 /*
  * Instruction opcodes for the CPACF instructions
@@ -542,6 +543,8 @@ static inline void cpacf_trng(u8 *ucbuf, unsigned long ucbuf_len,
 		: [ucbuf] "+&d" (u.pair), [cbuf] "+&d" (c.pair)
 		: [fc] "K" (CPACF_PRNO_TRNG), [opc] "i" (CPACF_PRNO)
 		: "cc", "memory", "0");
+	kmsan_unpoison_memory(ucbuf, ucbuf_len);
+	kmsan_unpoison_memory(cbuf, cbuf_len);
 }
 
 /**
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index a0de5b9b02ea..9e4bbc3e53f8 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -10,6 +10,7 @@
 #define _ASM_S390_CPU_MF_H
 
 #include <linux/errno.h>
+#include <linux/kmsan-checks.h>
 #include <asm/asm-extable.h>
 #include <asm/facility.h>
 
@@ -239,6 +240,11 @@ static __always_inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest)
 		: "=d" (cc)
 		: "Q" (*dest), "d" (range), "i" (set)
 		: "cc", "memory");
+	/*
+	 * If cc == 2, less than RANGE counters are stored, but it's not easy
+	 * to tell how many. Always unpoison the whole range for simplicity.
+	 */
+	kmsan_unpoison_memory(dest, range * sizeof(u64));
 	return cc;
 }
 
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index ce5f4fe8be4d..cf1b5d6fb1a6 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -19,7 +19,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte, unsigned long sz);
 void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
-pte_t huge_ptep_get(pte_t *ptep);
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep);
 
@@ -64,7 +64,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
 {
-	int changed = !pte_same(huge_ptep_get(ptep), pte);
+	int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
 	if (changed) {
 		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h
index 02427b205c11..bcab456dfb80 100644
--- a/arch/s390/include/asm/irqflags.h
+++ b/arch/s390/include/asm/irqflags.h
@@ -37,12 +37,18 @@ static __always_inline void __arch_local_irq_ssm(unsigned long flags)
 	asm volatile("ssm   %0" : : "Q" (flags) : "memory");
 }
 
-static __always_inline unsigned long arch_local_save_flags(void)
+#ifdef CONFIG_KMSAN
+#define arch_local_irq_attributes noinline notrace __no_sanitize_memory __maybe_unused
+#else
+#define arch_local_irq_attributes __always_inline
+#endif
+
+static arch_local_irq_attributes unsigned long arch_local_save_flags(void)
 {
 	return __arch_local_irq_stnsm(0xff);
 }
 
-static __always_inline unsigned long arch_local_irq_save(void)
+static arch_local_irq_attributes unsigned long arch_local_irq_save(void)
 {
 	return __arch_local_irq_stnsm(0xfc);
 }
@@ -52,7 +58,12 @@ static __always_inline void arch_local_irq_disable(void)
 	arch_local_irq_save();
 }
 
-static __always_inline void arch_local_irq_enable(void)
+static arch_local_irq_attributes void arch_local_irq_enable_external(void)
+{
+	__arch_local_irq_stosm(0x01);
+}
+
+static arch_local_irq_attributes void arch_local_irq_enable(void)
 {
 	__arch_local_irq_stosm(0x03);
 }
diff --git a/arch/s390/include/asm/kmsan.h b/arch/s390/include/asm/kmsan.h
new file mode 100644
index 000000000000..27db65fbf3f6
--- /dev/null
+++ b/arch/s390/include/asm/kmsan.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_KMSAN_H
+#define _ASM_S390_KMSAN_H
+
+#include <asm/lowcore.h>
+#include <asm/page.h>
+#include <linux/kmsan.h>
+#include <linux/mmzone.h>
+#include <linux/stddef.h>
+
+#ifndef MODULE
+
+static inline bool is_lowcore_addr(void *addr)
+{
+	return addr >= (void *)&S390_lowcore &&
+	       addr < (void *)(&S390_lowcore + 1);
+}
+
+static inline void *arch_kmsan_get_meta_or_null(void *addr, bool is_origin)
+{
+	if (is_lowcore_addr(addr)) {
+		/*
+		 * Different lowcores accessed via S390_lowcore are described
+		 * by the same struct page. Resolve the prefix manually in
+		 * order to get a distinct struct page.
+		 */
+		addr += (void *)lowcore_ptr[raw_smp_processor_id()] -
+			(void *)&S390_lowcore;
+		if (KMSAN_WARN_ON(is_lowcore_addr(addr)))
+			return NULL;
+		return kmsan_get_metadata(addr, is_origin);
+	}
+	return NULL;
+}
+
+static inline bool kmsan_virt_addr_valid(void *addr)
+{
+	bool ret;
+
+	/*
+	 * pfn_valid() relies on RCU, and may call into the scheduler on exiting
+	 * the critical section. However, this would result in recursion with
+	 * KMSAN. Therefore, disable preemption here, and re-enable preemption
+	 * below while suppressing reschedules to avoid recursion.
+	 *
+	 * Note, this sacrifices occasionally breaking scheduling guarantees.
+	 * Although, a kernel compiled with KMSAN has already given up on any
+	 * performance guarantees due to being heavily instrumented.
+	 */
+	preempt_disable();
+	ret = virt_addr_valid(addr);
+	preempt_enable_no_resched();
+
+	return ret;
+}
+
+#endif /* !MODULE */
+
+#endif /* _ASM_S390_KMSAN_H */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index b5632dbe5438..3fa280d0672a 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -107,6 +107,18 @@ static inline int is_module_addr(void *addr)
 	return 1;
 }
 
+#ifdef CONFIG_KMSAN
+#define KMSAN_VMALLOC_SIZE (VMALLOC_END - VMALLOC_START)
+#define KMSAN_VMALLOC_SHADOW_START VMALLOC_END
+#define KMSAN_VMALLOC_SHADOW_END (KMSAN_VMALLOC_SHADOW_START + KMSAN_VMALLOC_SIZE)
+#define KMSAN_VMALLOC_ORIGIN_START KMSAN_VMALLOC_SHADOW_END
+#define KMSAN_VMALLOC_ORIGIN_END (KMSAN_VMALLOC_ORIGIN_START + KMSAN_VMALLOC_SIZE)
+#define KMSAN_MODULES_SHADOW_START KMSAN_VMALLOC_ORIGIN_END
+#define KMSAN_MODULES_SHADOW_END (KMSAN_MODULES_SHADOW_START + MODULES_LEN)
+#define KMSAN_MODULES_ORIGIN_START KMSAN_MODULES_SHADOW_END
+#define KMSAN_MODULES_ORIGIN_END (KMSAN_MODULES_ORIGIN_START + MODULES_LEN)
+#endif
+
 #ifdef CONFIG_RANDOMIZE_BASE
 #define KASLR_LEN	(1UL << 31)
 #else
diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h
index 351685de53d2..2ab868cbae6c 100644
--- a/arch/s390/include/asm/string.h
+++ b/arch/s390/include/asm/string.h
@@ -15,15 +15,12 @@
 #define __HAVE_ARCH_MEMCPY	/* gcc builtin & arch function */
 #define __HAVE_ARCH_MEMMOVE	/* gcc builtin & arch function */
 #define __HAVE_ARCH_MEMSET	/* gcc builtin & arch function */
-#define __HAVE_ARCH_MEMSET16	/* arch function */
-#define __HAVE_ARCH_MEMSET32	/* arch function */
-#define __HAVE_ARCH_MEMSET64	/* arch function */
 
 void *memcpy(void *dest, const void *src, size_t n);
 void *memset(void *s, int c, size_t n);
 void *memmove(void *dest, const void *src, size_t n);
 
-#ifndef CONFIG_KASAN
+#if !defined(CONFIG_KASAN) && !defined(CONFIG_KMSAN)
 #define __HAVE_ARCH_MEMCHR	/* inline & arch function */
 #define __HAVE_ARCH_MEMCMP	/* arch function */
 #define __HAVE_ARCH_MEMSCAN	/* inline & arch function */
@@ -36,6 +33,9 @@ void *memmove(void *dest, const void *src, size_t n);
 #define __HAVE_ARCH_STRNCPY	/* arch function */
 #define __HAVE_ARCH_STRNLEN	/* inline & arch function */
 #define __HAVE_ARCH_STRSTR	/* arch function */
+#define __HAVE_ARCH_MEMSET16	/* arch function */
+#define __HAVE_ARCH_MEMSET32	/* arch function */
+#define __HAVE_ARCH_MEMSET64	/* arch function */
 
 /* Prototypes for non-inlined arch strings functions. */
 int memcmp(const void *s1, const void *s2, size_t n);
@@ -44,7 +44,7 @@ size_t strlcat(char *dest, const char *src, size_t n);
 char *strncat(char *dest, const char *src, size_t n);
 char *strncpy(char *dest, const char *src, size_t n);
 char *strstr(const char *s1, const char *s2);
-#endif /* !CONFIG_KASAN */
+#endif /* !defined(CONFIG_KASAN) && !defined(CONFIG_KMSAN) */
 
 #undef __HAVE_ARCH_STRCHR
 #undef __HAVE_ARCH_STRNCHR
@@ -74,20 +74,30 @@ void *__memset16(uint16_t *s, uint16_t v, size_t count);
 void *__memset32(uint32_t *s, uint32_t v, size_t count);
 void *__memset64(uint64_t *s, uint64_t v, size_t count);
 
+#ifdef __HAVE_ARCH_MEMSET16
 static inline void *memset16(uint16_t *s, uint16_t v, size_t count)
 {
 	return __memset16(s, v, count * sizeof(v));
 }
+#endif
 
+#ifdef __HAVE_ARCH_MEMSET32
 static inline void *memset32(uint32_t *s, uint32_t v, size_t count)
 {
 	return __memset32(s, v, count * sizeof(v));
 }
+#endif
 
+#ifdef __HAVE_ARCH_MEMSET64
+#ifdef IN_BOOT_STRING_C
+void *memset64(uint64_t *s, uint64_t v, size_t count);
+#else
 static inline void *memset64(uint64_t *s, uint64_t v, size_t count)
 {
 	return __memset64(s, v, count * sizeof(v));
 }
+#endif
+#endif
 
 #if !defined(IN_ARCH_STRING_C) && (!defined(CONFIG_FORTIFY_SOURCE) || defined(__NO_FORTIFY))
 
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index a674c7d25da5..d02a709717b8 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -16,7 +16,7 @@
 /*
  * General size of kernel stacks
  */
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) || defined(CONFIG_KMSAN)
 #define THREAD_SIZE_ORDER 4
 #else
 #define THREAD_SIZE_ORDER 2
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 81ae8a98e7ec..9213be0529ee 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -18,6 +18,7 @@
 #include <asm/extable.h>
 #include <asm/facility.h>
 #include <asm-generic/access_ok.h>
+#include <linux/instrumented.h>
 
 void debug_user_asce(int exit);
 
@@ -78,13 +79,24 @@ union oac {
 
 int __noreturn __put_user_bad(void);
 
-#define __put_user_asm(to, from, size)					\
-({									\
+#ifdef CONFIG_KMSAN
+#define get_put_user_noinstr_attributes \
+	noinline __maybe_unused __no_sanitize_memory
+#else
+#define get_put_user_noinstr_attributes __always_inline
+#endif
+
+#define DEFINE_PUT_USER(type)						\
+static get_put_user_noinstr_attributes int				\
+__put_user_##type##_noinstr(unsigned type __user *to,			\
+			    unsigned type *from,			\
+			    unsigned long size)				\
+{									\
 	union oac __oac_spec = {					\
 		.oac1.as = PSW_BITS_AS_SECONDARY,			\
 		.oac1.a = 1,						\
 	};								\
-	int __rc;							\
+	int rc;								\
 									\
 	asm volatile(							\
 		"	lr	0,%[spec]\n"				\
@@ -93,12 +105,28 @@ int __noreturn __put_user_bad(void);
 		"2:\n"							\
 		EX_TABLE_UA_STORE(0b, 2b, %[rc])			\
 		EX_TABLE_UA_STORE(1b, 2b, %[rc])			\
-		: [rc] "=&d" (__rc), [_to] "+Q" (*(to))			\
+		: [rc] "=&d" (rc), [_to] "+Q" (*(to))			\
 		: [_size] "d" (size), [_from] "Q" (*(from)),		\
 		  [spec] "d" (__oac_spec.val)				\
 		: "cc", "0");						\
-	__rc;								\
-})
+	return rc;							\
+}									\
+									\
+static __always_inline int						\
+__put_user_##type(unsigned type __user *to, unsigned type *from,	\
+		  unsigned long size)					\
+{									\
+	int rc;								\
+									\
+	rc = __put_user_##type##_noinstr(to, from, size);		\
+	instrument_put_user(*from, to, size);				\
+	return rc;							\
+}
+
+DEFINE_PUT_USER(char);
+DEFINE_PUT_USER(short);
+DEFINE_PUT_USER(int);
+DEFINE_PUT_USER(long);
 
 static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 {
@@ -106,24 +134,24 @@ static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned lon
 
 	switch (size) {
 	case 1:
-		rc = __put_user_asm((unsigned char __user *)ptr,
-				    (unsigned char *)x,
-				    size);
+		rc = __put_user_char((unsigned char __user *)ptr,
+				     (unsigned char *)x,
+				     size);
 		break;
 	case 2:
-		rc = __put_user_asm((unsigned short __user *)ptr,
-				    (unsigned short *)x,
-				    size);
+		rc = __put_user_short((unsigned short __user *)ptr,
+				      (unsigned short *)x,
+				      size);
 		break;
 	case 4:
-		rc = __put_user_asm((unsigned int __user *)ptr,
+		rc = __put_user_int((unsigned int __user *)ptr,
 				    (unsigned int *)x,
 				    size);
 		break;
 	case 8:
-		rc = __put_user_asm((unsigned long __user *)ptr,
-				    (unsigned long *)x,
-				    size);
+		rc = __put_user_long((unsigned long __user *)ptr,
+				     (unsigned long *)x,
+				     size);
 		break;
 	default:
 		__put_user_bad();
@@ -134,13 +162,17 @@ static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned lon
 
 int __noreturn __get_user_bad(void);
 
-#define __get_user_asm(to, from, size)					\
-({									\
+#define DEFINE_GET_USER(type)						\
+static get_put_user_noinstr_attributes int				\
+__get_user_##type##_noinstr(unsigned type *to,				\
+			    unsigned type __user *from,			\
+			    unsigned long size)				\
+{									\
 	union oac __oac_spec = {					\
 		.oac2.as = PSW_BITS_AS_SECONDARY,			\
 		.oac2.a = 1,						\
 	};								\
-	int __rc;							\
+	int rc;								\
 									\
 	asm volatile(							\
 		"	lr	0,%[spec]\n"				\
@@ -149,13 +181,29 @@ int __noreturn __get_user_bad(void);
 		"2:\n"							\
 		EX_TABLE_UA_LOAD_MEM(0b, 2b, %[rc], %[_to], %[_ksize])	\
 		EX_TABLE_UA_LOAD_MEM(1b, 2b, %[rc], %[_to], %[_ksize])	\
-		: [rc] "=&d" (__rc), "=Q" (*(to))			\
+		: [rc] "=&d" (rc), "=Q" (*(to))				\
 		: [_size] "d" (size), [_from] "Q" (*(from)),		\
 		  [spec] "d" (__oac_spec.val), [_to] "a" (to),		\
 		  [_ksize] "K" (size)					\
 		: "cc", "0");						\
-	__rc;								\
-})
+	return rc;							\
+}									\
+									\
+static __always_inline int						\
+__get_user_##type(unsigned type *to, unsigned type __user *from,	\
+		  unsigned long size)					\
+{									\
+	int rc;								\
+									\
+	rc = __get_user_##type##_noinstr(to, from, size);		\
+	instrument_get_user(*to);					\
+	return rc;							\
+}
+
+DEFINE_GET_USER(char);
+DEFINE_GET_USER(short);
+DEFINE_GET_USER(int);
+DEFINE_GET_USER(long);
 
 static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
 {
@@ -163,24 +211,24 @@ static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsign
 
 	switch (size) {
 	case 1:
-		rc = __get_user_asm((unsigned char *)x,
-				    (unsigned char __user *)ptr,
-				    size);
+		rc = __get_user_char((unsigned char *)x,
+				     (unsigned char __user *)ptr,
+				     size);
 		break;
 	case 2:
-		rc = __get_user_asm((unsigned short *)x,
-				    (unsigned short __user *)ptr,
-				    size);
+		rc = __get_user_short((unsigned short *)x,
+				      (unsigned short __user *)ptr,
+				      size);
 		break;
 	case 4:
-		rc = __get_user_asm((unsigned int *)x,
+		rc = __get_user_int((unsigned int *)x,
 				    (unsigned int __user *)ptr,
 				    size);
 		break;
 	case 8:
-		rc = __get_user_asm((unsigned long *)x,
-				    (unsigned long __user *)ptr,
-				    size);
+		rc = __get_user_long((unsigned long *)x,
+				     (unsigned long __user *)ptr,
+				     size);
 		break;
 	default:
 		__get_user_bad();