Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

65 files changed, 205 insertions, 117 deletions

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 8ebacf37a8cf..1f13995d00d7 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -490,3 +490,4 @@
 558	common	process_mrelease		sys_process_mrelease
 559	common  futex_waitv                     sys_futex_waitv
 560	common	set_mempolicy_home_node		sys_ni_syscall
+561	common	cachestat			sys_cachestat
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index e4c2677cc1e9..2f6163f05e93 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -74,6 +74,9 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
 		return 0;
 
 	pte = pte_offset_map_lock(current->mm, pmd, addr, &ptl);
+	if (unlikely(!pte))
+		return 0;
+
 	if (unlikely(!pte_present(*pte) || !pte_young(*pte) ||
 	    !pte_write(*pte) || !pte_dirty(*pte))) {
 		pte_unmap_unlock(pte, ptl);
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 0e49154454a6..ca5302b0b7ee 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -117,8 +117,11 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	 * must use the nested version.  This also means we need to
 	 * open-code the spin-locking.
 	 */
-	ptl = pte_lockptr(vma->vm_mm, pmd);
 	pte = pte_offset_map(pmd, address);
+	if (!pte)
+		return 0;
+
+	ptl = pte_lockptr(vma->vm_mm, pmd);
 	do_pte_lock(ptl);
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 2418f1efabd8..83598649a094 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -85,6 +85,9 @@ void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
 			break;
 
 		pte = pte_offset_map(pmd, addr);
+		if (!pte)
+			break;
+
 		pr_cont(", *pte=%08llx", (long long)pte_val(*pte));
 #ifndef CONFIG_ARM_LPAE
 		pr_cont(", *ppte=%08llx",
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index ac964612d8b0..8ebed8a13874 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -464,3 +464,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a05652ac66ce..d91829189dd4 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -120,6 +120,7 @@ config ARM64
 	select CRC32
 	select DCACHE_WORD_ACCESS
 	select DYNAMIC_FTRACE if FUNCTION_TRACER
+	select DMA_BOUNCE_UNALIGNED_KMALLOC
 	select DMA_DIRECT_REMAP
 	select EDAC_SUPPORT
 	select FRAME_POINTER
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index a51e6e8f3171..ceb368d33bf4 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -33,6 +33,7 @@
  * the CPU.
  */
 #define ARCH_DMA_MINALIGN	(128)
+#define ARCH_KMALLOC_MINALIGN	(8)
 
 #ifndef __ASSEMBLY__
 
@@ -90,6 +91,8 @@ static inline int cache_line_size_of_cpu(void)
 
 int cache_line_size(void);
 
+#define dma_get_cache_alignment	cache_line_size
+
 /*
  * Read the effective value of CTR_EL0.
  *
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 037feba03a51..64a514f90131 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -39,7 +39,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		451
+#define __NR_compat_syscalls		452
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 604a2053d006..d952a28463e0 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -907,6 +907,8 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 #define __NR_set_mempolicy_home_node 450
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
+#define __NR_cachestat 451
+__SYSCALL(__NR_cachestat, sys_cachestat)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index 7e89968bd282..4c5ef9b20065 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -416,10 +416,9 @@ long get_mte_ctrl(struct task_struct *task)
 static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
 				struct iovec *kiov, unsigned int gup_flags)
 {
-	struct vm_area_struct *vma;
 	void __user *buf = kiov->iov_base;
 	size_t len = kiov->iov_len;
-	int ret;
+	int err = 0;
 	int write = gup_flags & FOLL_WRITE;
 
 	if (!access_ok(buf, len))
@@ -429,14 +428,16 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
 		return -EIO;
 
 	while (len) {
+		struct vm_area_struct *vma;
 		unsigned long tags, offset;
 		void *maddr;
-		struct page *page = NULL;
+		struct page *page = get_user_page_vma_remote(mm, addr,
+							     gup_flags, &vma);
 
-		ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page,
-					    &vma, NULL);
-		if (ret <= 0)
+		if (IS_ERR_OR_NULL(page)) {
+			err = page == NULL ? -EIO : PTR_ERR(page);
 			break;
+		}
 
 		/*
 		 * Only copy tags if the page has been mapped as PROT_MTE
@@ -446,7 +447,7 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
 		 * was never mapped with PROT_MTE.
 		 */
 		if (!(vma->vm_flags & VM_MTE)) {
-			ret = -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
 			put_page(page);
 			break;
 		}
@@ -479,7 +480,7 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
 	kiov->iov_len = buf - kiov->iov_base;
 	if (!kiov->iov_len) {
 		/* check for error accessing the tracee's address space */
-		if (ret <= 0)
+		if (err)
 			return -EIO;
 		else
 			return -EFAULT;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 794a2dd3659a..8b70759cdbb9 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -1103,7 +1103,7 @@ static int kasan_handler(struct pt_regs *regs, unsigned long esr)
 	bool recover = esr & KASAN_ESR_RECOVER;
 	bool write = esr & KASAN_ESR_WRITE;
 	size_t size = KASAN_ESR_SIZE(esr);
-	u64 addr = regs->regs[0];
+	void *addr = (void *)regs->regs[0];
 	u64 pc = regs->pc;
 
 	kasan_report(addr, size, write, pc);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c85b6d70b222..c60100791bcc 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -188,6 +188,9 @@ static void show_pte(unsigned long addr)
 			break;
 
 		ptep = pte_offset_map(pmdp, addr);
+		if (!ptep)
+			break;
+
 		pte = READ_ONCE(*ptep);
 		pr_cont(", pte=%016llx", pte_val(pte));
 		pte_unmap(ptep);
@@ -328,7 +331,7 @@ static void report_tag_fault(unsigned long addr, unsigned long esr,
 	 * find out access size.
 	 */
 	bool is_write = !!(esr & ESR_ELx_WNR);
-	kasan_report(addr, 0, is_write, regs->pc);
+	kasan_report((void *)addr, 0, is_write, regs->pc);
 }
 #else
 /* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 95364e8bdc19..21716c940682 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -307,14 +307,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			return NULL;
 
 		WARN_ON(addr & (sz - 1));
-		/*
-		 * Note that if this code were ever ported to the
-		 * 32-bit arm platform then it will cause trouble in
-		 * the case where CONFIG_HIGHPTE is set, since there
-		 * will be no pte_unmap() to correspond with this
-		 * pte_alloc_map().
-		 */
-		ptep = pte_alloc_map(mm, pmdp, addr);
+		ptep = pte_alloc_huge(mm, pmdp, addr);
 	} else if (sz == PMD_SIZE) {
 		if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp)))
 			ptep = huge_pmd_share(mm, vma, addr, pudp);
@@ -366,7 +359,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return (pte_t *)pmdp;
 
 	if (sz == CONT_PTE_SIZE)
-		return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK));
+		return pte_offset_huge(pmdp, (addr & CONT_PTE_MASK));
 
 	return NULL;
 }
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index c28c2c8483cc..d31c3a9290c5 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -466,7 +466,12 @@ void __init bootmem_init(void)
  */
 void __init mem_init(void)
 {
-	swiotlb_init(max_pfn > PFN_DOWN(arm64_dma_phys_limit), SWIOTLB_VERBOSE);
+	bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit);
+
+	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC))
+		swiotlb = true;
+
+	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
 
 	/* this will put all unused low memory onto the freelists */
 	memblock_free_all();
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 72c929d9902b..f8c74ffeeefb 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -371,3 +371,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 78a02e026164..adc49f2d22e8 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -41,7 +41,7 @@ huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (pud) {
 		pmd = pmd_alloc(mm, pud, taddr);
 		if (pmd)
-			pte = pte_alloc_map(mm, pmd, taddr);
+			pte = pte_alloc_huge(mm, pmd, taddr);
 	}
 	return pte;
 }
@@ -64,7 +64,7 @@ huge_pte_offset (struct mm_struct *mm, unsigned long addr, unsigned long sz)
 			if (pud_present(*pud)) {
 				pmd = pmd_offset(pud, taddr);
 				if (pmd_present(*pmd))
-					pte = pte_offset_map(pmd, taddr);
+					pte = pte_offset_huge(pmd, taddr);
 			}
 		}
 	}
diff --git a/arch/m68k/include/asm/mmu_context.h b/arch/m68k/include/asm/mmu_context.h
index 8ed6ac14d99f..141bbdfad960 100644
--- a/arch/m68k/include/asm/mmu_context.h
+++ b/arch/m68k/include/asm/mmu_context.h
@@ -99,7 +99,7 @@ static inline void load_ksp_mmu(struct task_struct *task)
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t *pte;
+	pte_t *pte = NULL;
 	unsigned long mmuar;
 
 	local_irq_save(flags);
@@ -139,7 +139,7 @@ static inline void load_ksp_mmu(struct task_struct *task)
 
 	pte = (mmuar >= PAGE_OFFSET) ? pte_offset_kernel(pmd, mmuar)
 				     : pte_offset_map(pmd, mmuar);
-	if (pte_none(*pte) || !pte_present(*pte))
+	if (!pte || pte_none(*pte) || !pte_present(*pte))
 		goto bug;
 
 	set_pte(pte, pte_mkyoung(*pte));
@@ -161,6 +161,8 @@ static inline void load_ksp_mmu(struct task_struct *task)
 bug:
 	pr_info("ksp load failed: mm=0x%p ksp=0x08%lx\n", mm, mmuar);
 end:
+	if (pte && mmuar < PAGE_OFFSET)
+		pte_unmap(pte);
 	local_irq_restore(flags);
 }
 
diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
index bd0274c7592e..c586034d2a7a 100644
--- a/arch/m68k/kernel/sys_m68k.c
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -488,6 +488,8 @@ sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
 		if (!pmd_present(*pmd))
 			goto bad_access;
 		pte = pte_offset_map_lock(mm, pmd, (unsigned long)mem, &ptl);
+		if (!pte)
+			goto bad_access;
 		if (!pte_present(*pte) || !pte_dirty(*pte)
 		    || !pte_write(*pte)) {
 			pte_unmap_unlock(pte, ptl);
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index b1f3940bc298..4f504783371f 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -450,3 +450,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c
index 70aa0979e027..42f45abea37a 100644
--- a/arch/m68k/mm/mcfmmu.c
+++ b/arch/m68k/mm/mcfmmu.c
@@ -91,7 +91,8 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word)
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t *pte;
+	pte_t *pte = NULL;
+	int ret = -1;
 	int asid;
 
 	local_irq_save(flags);
@@ -100,47 +101,33 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word)
 		regs->pc + (extension_word * sizeof(long));
 
 	mm = (!user_mode(regs) && KMAPAREA(mmuar)) ? &init_mm : current->mm;
-	if (!mm) {
-		local_irq_restore(flags);
-		return -1;
-	}
+	if (!mm)
+		goto out;
 
 	pgd = pgd_offset(mm, mmuar);
-	if (pgd_none(*pgd))  {
-		local_irq_restore(flags);
-		return -1;
-	}
+	if (pgd_none(*pgd))
+		goto out;
 
 	p4d = p4d_offset(pgd, mmuar);
-	if (p4d_none(*p4d)) {
-		local_irq_restore(flags);
-		return -1;
-	}
+	if (p4d_none(*p4d))
+		goto out;
 
 	pud = pud_offset(p4d, mmuar);
-	if (pud_none(*pud)) {
-		local_irq_restore(flags);
-		return -1;
-	}
+	if (pud_none(*pud))
+		goto out;
 
 	pmd = pmd_offset(pud, mmuar);
-	if (pmd_none(*pmd)) {
-		local_irq_restore(flags);
-		return -1;
-	}
+	if (pmd_none(*pmd))
+		goto out;
 
 	pte = (KMAPAREA(mmuar)) ? pte_offset_kernel(pmd, mmuar)
 				: pte_offset_map(pmd, mmuar);
-	if (pte_none(*pte) || !pte_present(*pte)) {
-		local_irq_restore(flags);
-		return -1;
-	}
+	if (!pte || pte_none(*pte) || !pte_present(*pte))
+		goto out;
 
 	if (write) {
-		if (!pte_write(*pte)) {
-			local_irq_restore(flags);
-			return -1;
-		}
+		if (!pte_write(*pte))
+			goto out;
 		set_pte(pte, pte_mkdirty(*pte));
 	}
 
@@ -161,9 +148,12 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word)
 		mmu_write(MMUOR, MMUOR_ACC | MMUOR_UAA);
 	else
 		mmu_write(MMUOR, MMUOR_ITLB | MMUOR_ACC | MMUOR_UAA);
-
+	ret = 0;
+out:
+	if (pte && !KMAPAREA(mmuar))
+		pte_unmap(pte);
 	local_irq_restore(flags);
-	return 0;
+	return ret;
 }
 
 void __init cf_bootmem_alloc(void)
diff --git a/arch/microblaze/include/asm/cache.h b/arch/microblaze/include/asm/cache.h
index a149b3e711ec..1903988b9e23 100644
--- a/arch/microblaze/include/asm/cache.h
+++ b/arch/microblaze/include/asm/cache.h
@@ -18,4 +18,9 @@
 
 #define SMP_CACHE_BYTES	L1_CACHE_BYTES
 
+/* MS be sure that SLAB allocates aligned objects */
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+
+#define ARCH_SLAB_MINALIGN	L1_CACHE_BYTES
+
 #endif /* _ASM_MICROBLAZE_CACHE_H */
diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h
index 7b9861bcd458..337f23eabc71 100644
--- a/arch/microblaze/include/asm/page.h
+++ b/arch/microblaze/include/asm/page.h
@@ -30,11 +30,6 @@
 
 #ifndef __ASSEMBLY__
 
-/* MS be sure that SLAB allocates aligned objects */
-#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
-
-#define ARCH_SLAB_MINALIGN	L1_CACHE_BYTES
-
 /*
  * PAGE_OFFSET -- the first address of the first page of memory. With MMU
  * it is set to the kernel start address (aligned on a page boundary).
diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c
index c3aebec71c0c..c78a0ff48066 100644
--- a/arch/microblaze/kernel/signal.c
+++ b/arch/microblaze/kernel/signal.c
@@ -194,7 +194,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 
 	preempt_disable();
 	ptep = pte_offset_map(pmdp, address);
-	if (pte_present(*ptep)) {
+	if (ptep && pte_present(*ptep)) {
 		address = (unsigned long) page_address(pte_page(*ptep));
 		/* MS: I need add offset in page */
 		address += ((unsigned long)frame->tramp) & ~PAGE_MASK;
@@ -203,7 +203,8 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 		invalidate_icache_range(address, address + 8);
 		flush_dcache_range(address, address + 8);
 	}
-	pte_unmap(ptep);
+	if (ptep)
+		pte_unmap(ptep);
 	preempt_enable();
 	if (err)
 		return -EFAULT;
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 820145e47350..858d22bf275c 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -456,3 +456,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 253ff994ed2e..1976317d4e8b 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -389,3 +389,4 @@
 448	n32	process_mrelease		sys_process_mrelease
 449	n32	futex_waitv			sys_futex_waitv
 450	n32	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	n32	cachestat			sys_cachestat
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 3f1886ad9d80..cfda2511badf 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -365,3 +365,4 @@
 448	n64	process_mrelease		sys_process_mrelease
 449	n64	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	n64	cachestat			sys_cachestat
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 8f243e35a7b2..7692234c3768 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -438,3 +438,4 @@
 448	o32	process_mrelease		sys_process_mrelease
 449	o32	futex_waitv			sys_futex_waitv
 450	o32	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	o32	cachestat			sys_cachestat
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 1b939abbe4ca..93c2d695588a 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -297,7 +297,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
-	pte_t *ptep;
+	pte_t *ptep, *ptemap = NULL;
 	int idx, pid;
 
 	/*
@@ -344,7 +344,12 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	} else
 #endif
 	{
-		ptep = pte_offset_map(pmdp, address);
+		ptemap = ptep = pte_offset_map(pmdp, address);
+		/*
+		 * update_mmu_cache() is called between pte_offset_map_lock()
+		 * and pte_unmap_unlock(), so we can assume that ptep is not
+		 * NULL here: and what should be done below if it were NULL?
+		 */
 
 #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
 #ifdef CONFIG_XPA
@@ -373,6 +378,9 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	tlbw_use_hazard();
 	htw_start();
 	flush_micro_tlb_vm(vma);
+
+	if (ptemap)
+		pte_unmap(ptemap);
 	local_irq_restore(flags);
 }
 
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index ca4a302d4365..501160250bb7 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -426,10 +426,15 @@ void flush_dcache_page(struct page *page)
 		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
 		addr = mpnt->vm_start + offset;
 		if (parisc_requires_coherency()) {
+			bool needs_flush = false;
 			pte_t *ptep;
 
 			ptep = get_ptep(mpnt->vm_mm, addr);
-			if (ptep && pte_needs_flush(*ptep))
+			if (ptep) {
+				needs_flush = pte_needs_flush(*ptep);
+				pte_unmap(ptep);
+			}
+			if (needs_flush)
 				flush_user_cache_page(mpnt, addr);
 		} else {
 			/*
@@ -561,14 +566,20 @@ EXPORT_SYMBOL(flush_kernel_dcache_page_addr);
 static void flush_cache_page_if_present(struct vm_area_struct *vma,
 	unsigned long vmaddr, unsigned long pfn)
 {
-	pte_t *ptep = get_ptep(vma->vm_mm, vmaddr);
+	bool needs_flush = false;
+	pte_t *ptep;
 
 	/*
 	 * The pte check is racy and sometimes the flush will trigger
 	 * a non-access TLB miss. Hopefully, the page has already been
 	 * flushed.
 	 */
-	if (ptep && pte_needs_flush(*ptep))
+	ptep = get_ptep(vma->vm_mm, vmaddr);
+	if (ptep) {
+		needs_flush = pte_needs_flush(*ptep);
+		pte_unmap(ptep);
+	}
+	if (needs_flush)
 		flush_cache_page(vma, vmaddr, pfn);
 }
 
@@ -635,17 +646,22 @@ static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, u
 	pte_t *ptep;
 
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		bool needs_flush = false;
 		/*
 		 * The vma can contain pages that aren't present. Although
 		 * the pte search is expensive, we need the pte to find the
 		 * page pfn and to check whether the page should be flushed.
 		 */
 		ptep = get_ptep(vma->vm_mm, addr);
-		if (ptep && pte_needs_flush(*ptep)) {
+		if (ptep) {
+			needs_flush = pte_needs_flush(*ptep);
+			pfn = pte_pfn(*ptep);
+			pte_unmap(ptep);
+		}
+		if (needs_flush) {
 			if (parisc_requires_coherency()) {
 				flush_user_cache_page(vma, addr);
 			} else {
-				pfn = pte_pfn(*ptep);
 				if (WARN_ON(!pfn_valid(pfn)))
 					return;
 				__flush_cache_page(vma, addr, PFN_PHYS(pfn));
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 71ed5391f29d..415f12d5bab3 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -164,7 +164,7 @@ static inline void unmap_uncached_pte(pmd_t * pmd, unsigned long vaddr,
 		pmd_clear(pmd);
 		return;
 	}
-	pte = pte_offset_map(pmd, vaddr);
+	pte = pte_offset_kernel(pmd, vaddr);
 	vaddr &= ~PMD_MASK;
 	end = vaddr + size;
 	if (end > PMD_SIZE)
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 0e42fceb2d5e..3c71fad78318 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -448,3 +448,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index d1d3990b83f6..a8a1a7c1e16e 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -66,7 +66,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (pud) {
 		pmd = pmd_alloc(mm, pud, addr);
 		if (pmd)
-			pte = pte_alloc_map(mm, pmd, addr);
+			pte = pte_alloc_huge(mm, pmd, addr);
 	}
 	return pte;
 }
@@ -90,7 +90,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 			if (!pud_none(*pud)) {
 				pmd = pmd_offset(pud, addr);
 				if (!pmd_none(*pmd))
-					pte = pte_offset_map(pmd, addr);
+					pte = pte_offset_huge(pmd, addr);
 			}
 		}
 	}
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index ae0a68a838e8..69232231d270 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -33,6 +33,10 @@
 
 #define IFETCH_ALIGN_BYTES	(1 << IFETCH_ALIGN_SHIFT)
 
+#ifdef CONFIG_NOT_COHERENT_CACHE
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+#endif
+
 #if !defined(__ASSEMBLY__)
 #ifdef CONFIG_PPC64
 
diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h
index 56f217606327..b9ac9e3a771c 100644
--- a/arch/powerpc/include/asm/page_32.h
+++ b/arch/powerpc/include/asm/page_32.h
@@ -12,10 +12,6 @@
 
 #define VM_DATA_DEFAULT_FLAGS	VM_DATA_DEFAULT_FLAGS32
 
-#ifdef CONFIG_NOT_COHERENT_CACHE
-#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
-#endif
-
 #if defined(CONFIG_PPC_256K_PAGES) || \
     (defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES))
 #define PTE_SHIFT	(PAGE_SHIFT - PTE_T_LOG2 - 2)	/* 1/4 of a page */
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index a0be127475b1..8c0b08b7a80e 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -537,3 +537,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450 	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 461307b89c3a..572707858d65 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -509,7 +509,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
 		} else {
 			pte_t *pte;
 
-			pte = pte_offset_map(p, 0);
+			pte = pte_offset_kernel(p, 0);
 			kvmppc_unmap_free_pte(kvm, pte, full, lpid);
 			pmd_clear(p);
 		}
diff --git a/arch/powerpc/mm/book3s64/hash_tlb.c b/arch/powerpc/mm/book3s64/hash_tlb.c
index a64ea0a7ef96..21fcad97ae80 100644
--- a/arch/powerpc/mm/book3s64/hash_tlb.c
+++ b/arch/powerpc/mm/book3s64/hash_tlb.c
@@ -239,12 +239,16 @@ void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long
 	local_irq_save(flags);
 	arch_enter_lazy_mmu_mode();
 	start_pte = pte_offset_map(pmd, addr);
+	if (!start_pte)
+		goto out;
 	for (pte = start_pte; pte < start_pte + PTRS_PER_PTE; pte++) {
 		unsigned long pteval = pte_val(*pte);
 		if (pteval & H_PAGE_HASHPTE)
 			hpte_need_flush(mm, addr, pte, pteval, 0);
 		addr += PAGE_SIZE;
 	}
+	pte_unmap(start_pte);
+out:
 	arch_leave_lazy_mmu_mode();
 	local_irq_restore(flags);
 }
diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
index 81d7185e2ae8..d19fb1f3007d 100644
--- a/arch/powerpc/mm/book3s64/iommu_api.c
+++ b/arch/powerpc/mm/book3s64/iommu_api.c
@@ -105,7 +105,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 
 		ret = pin_user_pages(ua + (entry << PAGE_SHIFT), n,
 				FOLL_WRITE | FOLL_LONGTERM,
-				mem->hpages + entry, NULL);
+				mem->hpages + entry);
 		if (ret == n) {
 			pinned += n;
 			continue;
diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c
index b75a9fb99599..0dc85556dec5 100644
--- a/arch/powerpc/mm/book3s64/subpage_prot.c
+++ b/arch/powerpc/mm/book3s64/subpage_prot.c
@@ -71,6 +71,8 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
 	if (pmd_none(*pmd))
 		return;
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	if (!pte)
+		return;
 	arch_enter_lazy_mmu_mode();
 	for (; npages > 0; --npages) {
 		pte_update(mm, addr, pte, 0, 0, 0);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index b900933507da..f7c683b672c1 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -183,7 +183,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		return NULL;
 
 	if (IS_ENABLED(CONFIG_PPC_8xx) && pshift < PMD_SHIFT)
-		return pte_alloc_map(mm, (pmd_t *)hpdp, addr);
+		return pte_alloc_huge(mm, (pmd_t *)hpdp, addr);
 
 	BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
 
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 70c4c59a1a8f..fae747cc57d2 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -3376,12 +3376,15 @@ static void show_pte(unsigned long addr)
 	printf("pmdp @ 0x%px = 0x%016lx\n", pmdp, pmd_val(*pmdp));
 
 	ptep = pte_offset_map(pmdp, addr);
-	if (pte_none(*ptep)) {
+	if (!ptep || pte_none(*ptep)) {
+		if (ptep)
+			pte_unmap(ptep);
 		printf("no valid PTE\n");
 		return;
 	}
 
 	format_pte(ptep, pte_val(*ptep));
+	pte_unmap(ptep);
 
 	sync();
 	__delay(200);
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index e0ef56dc57b9..542883b3b49b 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -67,7 +67,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 
 	for_each_napot_order(order) {
 		if (napot_cont_size(order) == sz) {
-			pte = pte_alloc_map(mm, pmd, addr & napot_cont_mask(order));
+			pte = pte_alloc_huge(mm, pmd, addr & napot_cont_mask(order));
 			break;
 		}
 	}
@@ -114,7 +114,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 
 	for_each_napot_order(order) {
 		if (napot_cont_size(order) == sz) {
-			pte = pte_offset_kernel(pmd, addr & napot_cont_mask(order));
+			pte = pte_offset_huge(pmd, addr & napot_cont_mask(order));
 			break;
 		}
 	}
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index b68f47541169..a6935af2235c 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -453,3 +453,4 @@
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
 449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
 450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
+451  common	cachestat		sys_cachestat			sys_cachestat
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index cb2ee06df286..3c62d1b218b1 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -294,6 +294,8 @@ again:
 
 	rc = -ENXIO;
 	ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
+	if (!ptep)
+		goto out;
 	if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) {
 		page = pte_page(*ptep);
 		rc = -EAGAIN;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index da6dac36e959..9bd0a873f3b1 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2777,7 +2777,7 @@ static struct page *get_map_page(struct kvm *kvm, u64 uaddr)
 
 	mmap_read_lock(kvm->mm);
 	get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE,
-			      &page, NULL, NULL);
+			      &page, NULL);
 	mmap_read_unlock(kvm->mm);
 	return page;
 }
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index dc90d1eb0d55..f4b6fc746fce 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -895,12 +895,12 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
 
 /**
  * gmap_pte_op_end - release the page table lock
- * @ptl: pointer to the spinlock pointer
+ * @ptep: pointer to the locked pte
+ * @ptl: pointer to the page table spinlock
  */
-static void gmap_pte_op_end(spinlock_t *ptl)
+static void gmap_pte_op_end(pte_t *ptep, spinlock_t *ptl)
 {
-	if (ptl)
-		spin_unlock(ptl);
+	pte_unmap_unlock(ptep, ptl);
 }
 
 /**
@@ -1011,7 +1011,7 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
 {
 	int rc;
 	pte_t *ptep;
-	spinlock_t *ptl = NULL;
+	spinlock_t *ptl;
 	unsigned long pbits = 0;
 
 	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
@@ -1025,7 +1025,7 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
 	pbits |= (bits & GMAP_NOTIFY_SHADOW) ? PGSTE_VSIE_BIT : 0;
 	/* Protect and unlock. */
 	rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, pbits);
-	gmap_pte_op_end(ptl);
+	gmap_pte_op_end(ptep, ptl);
 	return rc;
 }
 
@@ -1154,7 +1154,7 @@ int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val)
 				/* Do *NOT* clear the _PAGE_INVALID bit! */
 				rc = 0;
 			}
-			gmap_pte_op_end(ptl);
+			gmap_pte_op_end(ptep, ptl);
 		}
 		if (!rc)
 			break;
@@ -1248,7 +1248,7 @@ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
 			if (!rc)
 				gmap_insert_rmap(sg, vmaddr, rmap);
 			spin_unlock(&sg->guest_table_lock);
-			gmap_pte_op_end(ptl);
+			gmap_pte_op_end(ptep, ptl);
 		}
 		radix_tree_preload_end();
 		if (rc) {
@@ -2156,7 +2156,7 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
 			tptep = (pte_t *) gmap_table_walk(sg, saddr, 0);
 			if (!tptep) {
 				spin_unlock(&sg->guest_table_lock);
-				gmap_pte_op_end(ptl);
+				gmap_pte_op_end(sptep, ptl);
 				radix_tree_preload_end();
 				break;
 			}
@@ -2167,7 +2167,7 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
 				rmap = NULL;
 				rc = 0;
 			}
-			gmap_pte_op_end(ptl);
+			gmap_pte_op_end(sptep, ptl);
 			spin_unlock(&sg->guest_table_lock);
 		}
 		radix_tree_preload_end();
@@ -2495,7 +2495,7 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4],
 				continue;
 			if (ptep_test_and_clear_uc(gmap->mm, vmaddr, ptep))
 				set_bit(i, bitmap);
-			spin_unlock(ptl);
+			pte_unmap_unlock(ptep, ptl);
 		}
 	}
 	gmap_pmd_op_end(gmap, pmdp);
@@ -2537,7 +2537,12 @@ static inline void thp_split_mm(struct mm_struct *mm)
  * Remove all empty zero pages from the mapping for lazy refaulting
  * - This must be called after mm->context.has_pgste is set, to avoid
  *   future creation of zero pages
- * - This must be called after THP was enabled
+ * - This must be called after THP was disabled.
+ *
+ * mm contracts with s390, that even if mm were to remove a page table,
+ * racing with the loop below and so causing pte_offset_map_lock() to fail,
+ * it will never insert a page table containing empty zero pages once
+ * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set.
  */
 static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
 			   unsigned long end, struct mm_walk *walk)
@@ -2549,6 +2554,8 @@ static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
 		spinlock_t *ptl;
 
 		ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+		if (!ptep)
+			break;
 		if (is_zero_pfn(pte_pfn(*ptep)))
 			ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID));
 		pte_unmap_unlock(ptep, ptl);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 6effb24de6d9..3bd2ab2a9a34 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -829,7 +829,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	default:
 		return -EFAULT;
 	}
-
+again:
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
@@ -850,6 +850,8 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	spin_unlock(ptl);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	new = old = pgste_get_lock(ptep);
 	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
 			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
@@ -938,7 +940,7 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	default:
 		return -EFAULT;
 	}
-
+again:
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
@@ -955,6 +957,8 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	spin_unlock(ptl);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	new = old = pgste_get_lock(ptep);
 	/* Reset guest reference bit only */
 	pgste_val(new) &= ~PGSTE_GR_BIT;
@@ -1000,7 +1004,7 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	default:
 		return -EFAULT;
 	}
-
+again:
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
@@ -1017,6 +1021,8 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	spin_unlock(ptl);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	pgste = pgste_get_lock(ptep);
 	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
 	paddr = pte_val(*ptep) & PAGE_MASK;
diff --git a/arch/sh/include/asm/cache.h b/arch/sh/include/asm/cache.h
index 32dfa6b82ec6..b38dbc975581 100644
--- a/arch/sh/include/asm/cache.h
+++ b/arch/sh/include/asm/cache.h
@@ -14,6 +14,12 @@
 
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
+/*
+ * Some drivers need to perform DMA into kmalloc'ed buffers
+ * and so we have to increase the kmalloc minalign for this.
+ */
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+
 #define __read_mostly __section(".data..read_mostly")
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sh/include/asm/page.h b/arch/sh/include/asm/page.h
index 09ac6c7faee0..62f4b9edcb98 100644
--- a/arch/sh/include/asm/page.h
+++ b/arch/sh/include/asm/page.h
@@ -174,10 +174,4 @@ typedef struct page *pgtable_t;
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
 
-/*
- * Some drivers need to perform DMA into kmalloc'ed buffers
- * and so we have to increase the kmalloc minalign for this.
- */
-#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
-
 #endif /* __ASM_SH_PAGE_H */
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 2de85c977f54..97377e8c5025 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -453,3 +453,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index 999ab5916e69..6cb0ad73dbb9 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -38,7 +38,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			if (pud) {
 				pmd = pmd_alloc(mm, pud, addr);
 				if (pmd)
-					pte = pte_alloc_map(mm, pmd, addr);
+					pte = pte_alloc_huge(mm, pmd, addr);
 			}
 		}
 	}
@@ -63,7 +63,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 			if (pud) {
 				pmd = pmd_offset(pud, addr);
 				if (pmd)
-					pte = pte_offset_map(pmd, addr);
+					pte = pte_offset_huge(pmd, addr);
 			}
 		}
 	}
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index dad38960d1a8..ca450c7bc53f 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -328,6 +328,8 @@ static void flush_signal_insns(unsigned long address)
 		goto out_irqs_on;
 
 	ptep = pte_offset_map(pmdp, address);
+	if (!ptep)
+		goto out_irqs_on;
 	pte = *ptep;
 	if (!pte_present(pte))
 		goto out_unmap;
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 4398cc6fb68d..faa835f3c54a 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -496,3 +496,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index d91305de694c..d8a407fbe350 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -99,6 +99,7 @@ static unsigned int get_user_insn(unsigned long tpc)
 	local_irq_disable();
 
 	pmdp = pmd_offset(pudp, tpc);
+again:
 	if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
 		goto out_irq_enable;
 
@@ -115,6 +116,8 @@ static unsigned int get_user_insn(unsigned long tpc)
 #endif
 	{
 		ptep = pte_offset_map(pmdp, tpc);
+		if (!ptep)
+			goto again;
 		pte = *ptep;
 		if (pte_present(pte)) {
 			pa  = (pte_pfn(pte) << PAGE_SHIFT);
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index d8e0e3c7038d..d7018823206c 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -298,7 +298,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		return NULL;
 	if (sz >= PMD_SIZE)
 		return (pte_t *)pmd;
-	return pte_alloc_map(mm, pmd, addr);
+	return pte_alloc_huge(mm, pmd, addr);
 }
 
 pte_t *huge_pte_offset(struct mm_struct *mm,
@@ -325,7 +325,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 	if (is_hugetlb_pmd(*pmd))
 		return (pte_t *)pmd;
-	return pte_offset_map(pmd, addr);
+	return pte_offset_huge(pmd, addr);
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index bf3e6d2fe5d9..133dd42570d6 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -244,7 +244,7 @@ static void *iounit_alloc(struct device *dev, size_t len,
 			long i;
 
 			pmdp = pmd_off_k(addr);
-			ptep = pte_offset_map(pmdp, addr);
+			ptep = pte_offset_kernel(pmdp, addr);
 
 			set_pte(ptep, mk_pte(virt_to_page(page), dvma_prot));
 
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 9e3f6933ca13..3a6caef68348 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -358,7 +358,7 @@ static void *sbus_iommu_alloc(struct device *dev, size_t len,
 				__flush_page_to_ram(page);
 
 			pmdp = pmd_off_k(addr);
-			ptep = pte_offset_map(pmdp, addr);
+			ptep = pte_offset_kernel(pmdp, addr);
 
 			set_pte(ptep, mk_pte(virt_to_page(page), dvma_prot));
 		}
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 9a725547578e..7ecf8556947a 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -149,6 +149,8 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 	pte_t *pte;
 
 	pte = pte_offset_map(&pmd, vaddr);
+	if (!pte)
+		return;
 	end = vaddr + HPAGE_SIZE;
 	while (vaddr < end) {
 		if (pte_val(*pte) & _PAGE_VALID) {
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 320480a8db4f..bc0a3c941b35 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -455,3 +455,4 @@
 448	i386	process_mrelease	sys_process_mrelease
 449	i386	futex_waitv		sys_futex_waitv
 450	i386	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	i386	cachestat		sys_cachestat
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index c84d12608cd2..227538b0ce80 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -372,6 +372,7 @@
 448	common	process_mrelease	sys_process_mrelease
 449	common	futex_waitv		sys_futex_waitv
 450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
+451	common	cachestat		sys_cachestat
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index 21ca0a831b70..5d390df21440 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -214,7 +214,7 @@ static int __sgx_encl_add_page(struct sgx_encl *encl,
 	if (!(vma->vm_flags & VM_MAYEXEC))
 		return -EACCES;
 
-	ret = get_user_pages(src, 1, 0, &src_page, NULL);
+	ret = get_user_pages(src, 1, 0, &src_page);
 	if (ret < 1)
 		return -EFAULT;
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 525876e7b9f4..adc67f98819a 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -367,8 +367,10 @@ static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
 
 		va = (unsigned long)ldt_slot_va(ldt->slot) + offset;
 		ptep = get_locked_pte(mm, va, &ptl);
-		pte_clear(mm, va, ptep);
-		pte_unmap_unlock(ptep, ptl);
+		if (!WARN_ON_ONCE(!ptep)) {
+			pte_clear(mm, va, ptep);
+			pte_unmap_unlock(ptep, ptl);
+		}
 	}
 
 	va = (unsigned long)ldt_slot_va(ldt->slot);
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index bfe22fd5a1d7..d73aeb16417f 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -188,7 +188,7 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
 	if (pmd_large(*pmd))
 		return;
 
-	pte = pte_offset_map(pmd, ppd->vaddr);
+	pte = pte_offset_kernel(pmd, ppd->vaddr);
 	if (pte_none(*pte))
 		set_pte(pte, __pte(ppd->paddr | ppd->pte_flags));
 }
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 52c94ab5c205..2b69c3c035b6 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -421,3 +421,4 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index 27a477dae232..0a11fc5f185b 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -179,6 +179,7 @@ static unsigned get_pte_for_vaddr(unsigned vaddr)
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
+	unsigned int pteval;
 
 	if (!mm)
 		mm = task->active_mm;
@@ -197,7 +198,9 @@ static unsigned get_pte_for_vaddr(unsigned vaddr)
 	pte = pte_offset_map(pmd, vaddr);
 	if (!pte)
 		return 0;
-	return pte_val(*pte);
+	pteval = pte_val(*pte);
+	pte_unmap(pte);
+	return pteval;
 }
 
 enum {