Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...

4 files changed, 57 insertions, 47 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5e0e0ccd47aa..96a6a08c8235 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -96,6 +96,7 @@
 #include <linux/time_namespace.h>
 #include <linux/resctrl.h>
 #include <linux/cn_proc.h>
+#include <linux/ksm.h>
 #include <trace/events/oom.h>
 #include "internal.h"
 #include "fd.h"
@@ -3207,6 +3208,8 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
 	mm = get_task_mm(task);
 	if (mm) {
 		seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items);
+		seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages);
+		seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm));
 		mmput(mm);
 	}
 
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 71157ee35c1a..25b44b303b35 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -24,7 +24,7 @@
 #include <linux/memblock.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/uaccess.h>
+#include <linux/uio.h>
 #include <asm/io.h>
 #include <linux/list.h>
 #include <linux/ioport.h>
@@ -307,10 +307,9 @@ static void append_kcore_note(char *notes, size_t *i, const char *name,
 	*i = ALIGN(*i + descsz, 4);
 }
 
-static ssize_t
-read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
+static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	char *buf = file->private_data;
+	loff_t *fpos = &iocb->ki_pos;
 	size_t phdrs_offset, notes_offset, data_offset;
 	size_t page_offline_frozen = 1;
 	size_t phdrs_len, notes_len;
@@ -318,6 +317,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 	size_t tsz;
 	int nphdr;
 	unsigned long start;
+	size_t buflen = iov_iter_count(iter);
 	size_t orig_buflen = buflen;
 	int ret = 0;
 
@@ -356,12 +356,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 		};
 
 		tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos);
-		if (copy_to_user(buffer, (char *)&ehdr + *fpos, tsz)) {
+		if (copy_to_iter((char *)&ehdr + *fpos, tsz, iter) != tsz) {
 			ret = -EFAULT;
 			goto out;
 		}
 
-		buffer += tsz;
 		buflen -= tsz;
 		*fpos += tsz;
 	}
@@ -398,15 +397,14 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 		}
 
 		tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos);
-		if (copy_to_user(buffer, (char *)phdrs + *fpos - phdrs_offset,
-				 tsz)) {
+		if (copy_to_iter((char *)phdrs + *fpos - phdrs_offset, tsz,
+				 iter) != tsz) {
 			kfree(phdrs);
 			ret = -EFAULT;
 			goto out;
 		}
 		kfree(phdrs);
 
-		buffer += tsz;
 		buflen -= tsz;
 		*fpos += tsz;
 	}
@@ -448,14 +446,13 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 				  min(vmcoreinfo_size, notes_len - i));
 
 		tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos);
-		if (copy_to_user(buffer, notes + *fpos - notes_offset, tsz)) {
+		if (copy_to_iter(notes + *fpos - notes_offset, tsz, iter) != tsz) {
 			kfree(notes);
 			ret = -EFAULT;
 			goto out;
 		}
 		kfree(notes);
 
-		buffer += tsz;
 		buflen -= tsz;
 		*fpos += tsz;
 	}
@@ -497,7 +494,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 		}
 
 		if (!m) {
-			if (clear_user(buffer, tsz)) {
+			if (iov_iter_zero(tsz, iter) != tsz) {
 				ret = -EFAULT;
 				goto out;
 			}
@@ -506,16 +503,33 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 
 		switch (m->type) {
 		case KCORE_VMALLOC:
-			vread(buf, (char *)start, tsz);
-			/* we have to zero-fill user buffer even if no read */
-			if (copy_to_user(buffer, buf, tsz)) {
-				ret = -EFAULT;
-				goto out;
+		{
+			const char *src = (char *)start;
+			size_t read = 0, left = tsz;
+
+			/*
+			 * vmalloc uses spinlocks, so we optimistically try to
+			 * read memory. If this fails, fault pages in and try
+			 * again until we are done.
+			 */
+			while (true) {
+				read += vread_iter(iter, src, left);
+				if (read == tsz)
+					break;
+
+				src += read;
+				left -= read;
+
+				if (fault_in_iov_iter_writeable(iter, left)) {
+					ret = -EFAULT;
+					goto out;
+				}
 			}
 			break;
+		}
 		case KCORE_USER:
 			/* User page is handled prior to normal kernel page: */
-			if (copy_to_user(buffer, (char *)start, tsz)) {
+			if (copy_to_iter((char *)start, tsz, iter) != tsz) {
 				ret = -EFAULT;
 				goto out;
 			}
@@ -531,7 +545,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 			 */
 			if (!page || PageOffline(page) ||
 			    is_page_hwpoison(page) || !pfn_is_ram(pfn)) {
-				if (clear_user(buffer, tsz)) {
+				if (iov_iter_zero(tsz, iter) != tsz) {
 					ret = -EFAULT;
 					goto out;
 				}
@@ -541,24 +555,17 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 		case KCORE_VMEMMAP:
 		case KCORE_TEXT:
 			/*
-			 * Using bounce buffer to bypass the
-			 * hardened user copy kernel text checks.
+			 * We use _copy_to_iter() to bypass usermode hardening
+			 * which would otherwise prevent this operation.
 			 */
-			if (copy_from_kernel_nofault(buf, (void *)start, tsz)) {
-				if (clear_user(buffer, tsz)) {
-					ret = -EFAULT;
-					goto out;
-				}
-			} else {
-				if (copy_to_user(buffer, buf, tsz)) {
-					ret = -EFAULT;
-					goto out;
-				}
+			if (_copy_to_iter((char *)start, tsz, iter) != tsz) {
+				ret = -EFAULT;
+				goto out;
 			}
 			break;
 		default:
 			pr_warn_once("Unhandled KCORE type: %d\n", m->type);
-			if (clear_user(buffer, tsz)) {
+			if (iov_iter_zero(tsz, iter) != tsz) {
 				ret = -EFAULT;
 				goto out;
 			}
@@ -566,7 +573,6 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 skip:
 		buflen -= tsz;
 		*fpos += tsz;
-		buffer += tsz;
 		start += tsz;
 		tsz = (buflen > PAGE_SIZE ? PAGE_SIZE : buflen);
 	}
@@ -589,10 +595,6 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;
 
-	filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!filp->private_data)
-		return -ENOMEM;
-
 	if (kcore_need_update)
 		kcore_update_ram();
 	if (i_size_read(inode) != proc_root_kcore->size) {
@@ -603,16 +605,9 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int release_kcore(struct inode *inode, struct file *file)
-{
-	kfree(file->private_data);
-	return 0;
-}
-
 static const struct proc_ops kcore_proc_ops = {
-	.proc_read	= read_kcore,
+	.proc_read_iter	= read_kcore_iter,
 	.proc_open	= open_kcore,
-	.proc_release	= release_kcore,
 	.proc_lseek	= default_llseek,
 };
 
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 440960110a42..b43d0bd42762 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -6,6 +6,7 @@
 #include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/mmzone.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/percpu.h>
 #include <linux/seq_file.h>
@@ -131,6 +132,18 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "VmallocChunk:   ", 0ul);
 	show_val_kb(m, "Percpu:         ", pcpu_nr_pages());
 
+#ifdef CONFIG_MEMTEST
+	if (early_memtest_done) {
+		unsigned long early_memtest_bad_size_kb;
+
+		early_memtest_bad_size_kb = early_memtest_bad_size>>10;
+		if (early_memtest_bad_size && !early_memtest_bad_size_kb)
+			early_memtest_bad_size_kb = 1;
+		/* When 0 is reported, it means there actually was a successful test */
+		seq_printf(m, "EarlyMemtestBad:   %5lu kB\n", early_memtest_bad_size_kb);
+	}
+#endif
+
 #ifdef CONFIG_MEMORY_FAILURE
 	seq_printf(m, "HardwareCorrupted: %5lu kB\n",
 		   atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10));
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6a96e1713fd5..cb49479acd2e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -782,7 +782,6 @@ static void smap_gather_stats(struct vm_area_struct *vma,
 	if (start >= vma->vm_end)
 		return;
 
-#ifdef CONFIG_SHMEM
 	if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
 		/*
 		 * For shared or readonly shmem mappings we know that all
@@ -803,7 +802,7 @@ static void smap_gather_stats(struct vm_area_struct *vma,
 			ops = &smaps_shmem_walk_ops;
 		}
 	}
-#endif
+
 	/* mmap_lock is held in m_start */
 	if (!start)
 		walk_page_vma(vma, ops, mss);