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()
  ...

9 files changed, 29 insertions, 21 deletions

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();