mm: vmalloc: convert vread() to vread_iter()

Having previously laid the foundation for converting vread() to an
iterator function, pull the trigger and do so.

This patch attempts to provide minimal refactoring and to reflect the
existing logic as best we can, for example we continue to zero portions of
memory not read, as before.

Overall, there should be no functional difference other than a performance
improvement in /proc/kcore access to vmalloc regions.

Now we have eliminated the need for a bounce buffer in read_kcore_iter(),
we dispense with it, and try to write to user memory optimistically but
with faults disabled via copy_page_to_iter_nofault().  We already have
preemption disabled by holding a spin lock.  We continue faulting in until
the operation is complete.

Additionally, we must account for the fact that at any point a copy may
fail (most likely due to a fault not being able to occur), we exit
indicating fewer bytes retrieved than expected.

[sfr@canb.auug.org.au: fix sparc64 warning]
  Link: https://lkml.kernel.org/r/20230320144721.663280c3@canb.auug.org.au
[lstoakes@gmail.com: redo Stephen's sparc build fix]
  Link: https://lkml.kernel.org/r/8506cbc667c39205e65a323f750ff9c11a463798.1679566220.git.lstoakes@gmail.com
[akpm@linux-foundation.org: unbreak uio.h includes]
Link: https://lkml.kernel.org/r/941f88bc5ab928e6656e1e2593b91bf0f8c81e1b.1679511146.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Liu Shixin <liushixin2@huawei.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 147 insertions, 88 deletions

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 978194dc2bb8..5291c6f02cf7 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -33,11 +33,11 @@
 #include <linux/compiler.h>
 #include <linux/memcontrol.h>
 #include <linux/llist.h>
+#include <linux/uio.h>
 #include <linux/bitops.h>
 #include <linux/rbtree_augmented.h>
 #include <linux/overflow.h>
 #include <linux/pgtable.h>
-#include <linux/uaccess.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/mm.h>
 #include <asm/tlbflush.h>
@@ -3442,62 +3442,96 @@ void *vmalloc_32_user(unsigned long size)
 EXPORT_SYMBOL(vmalloc_32_user);
 
 /*
- * small helper routine , copy contents to buf from addr.
- * If the page is not present, fill zero.
+ * Atomically zero bytes in the iterator.
+ *
+ * Returns the number of zeroed bytes.
  */
+static size_t zero_iter(struct iov_iter *iter, size_t count)
+{
+	size_t remains = count;
+
+	while (remains > 0) {
+		size_t num, copied;
+
+		num = remains < PAGE_SIZE ? remains : PAGE_SIZE;
+		copied = copy_page_to_iter_nofault(ZERO_PAGE(0), 0, num, iter);
+		remains -= copied;
+
+		if (copied < num)
+			break;
+	}
 
-static int aligned_vread(char *buf, char *addr, unsigned long count)
+	return count - remains;
+}
+
+/*
+ * small helper routine, copy contents to iter from addr.
+ * If the page is not present, fill zero.
+ *
+ * Returns the number of copied bytes.
+ */
+static size_t aligned_vread_iter(struct iov_iter *iter,
+				 const char *addr, size_t count)
 {
-	struct page *p;
-	int copied = 0;
+	size_t remains = count;
+	struct page *page;
 
-	while (count) {
+	while (remains > 0) {
 		unsigned long offset, length;
+		size_t copied = 0;
 
 		offset = offset_in_page(addr);
 		length = PAGE_SIZE - offset;
-		if (length > count)
-			length = count;
-		p = vmalloc_to_page(addr);
+		if (length > remains)
+			length = remains;
+		page = vmalloc_to_page(addr);
 		/*
-		 * To do safe access to this _mapped_ area, we need
-		 * lock. But adding lock here means that we need to add
-		 * overhead of vmalloc()/vfree() calls for this _debug_
-		 * interface, rarely used. Instead of that, we'll use
-		 * kmap() and get small overhead in this access function.
+		 * To do safe access to this _mapped_ area, we need lock. But
+		 * adding lock here means that we need to add overhead of
+		 * vmalloc()/vfree() calls for this _debug_ interface, rarely
+		 * used. Instead of that, we'll use an local mapping via
+		 * copy_page_to_iter_nofault() and accept a small overhead in
+		 * this access function.
 		 */
-		if (p) {
-			/* We can expect USER0 is not used -- see vread() */
-			void *map = kmap_atomic(p);
-			memcpy(buf, map + offset, length);
-			kunmap_atomic(map);
-		} else
-			memset(buf, 0, length);
+		if (page)
+			copied = copy_page_to_iter_nofault(page, offset,
+							   length, iter);
+		else
+			copied = zero_iter(iter, length);
 
-		addr += length;
-		buf += length;
-		copied += length;
-		count -= length;
+		addr += copied;
+		remains -= copied;
+
+		if (copied != length)
+			break;
 	}
-	return copied;
+
+	return count - remains;
 }
 
-static void vmap_ram_vread(char *buf, char *addr, int count, unsigned long flags)
+/*
+ * Read from a vm_map_ram region of memory.
+ *
+ * Returns the number of copied bytes.
+ */
+static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr,
+				  size_t count, unsigned long flags)
 {
 	char *start;
 	struct vmap_block *vb;
 	unsigned long offset;
-	unsigned int rs, re, n;
+	unsigned int rs, re;
+	size_t remains, n;
 
 	/*
 	 * If it's area created by vm_map_ram() interface directly, but
 	 * not further subdividing and delegating management to vmap_block,
 	 * handle it here.
 	 */
-	if (!(flags & VMAP_BLOCK)) {
-		aligned_vread(buf, addr, count);
-		return;
-	}
+	if (!(flags & VMAP_BLOCK))
+		return aligned_vread_iter(iter, addr, count);
+
+	remains = count;
 
 	/*
 	 * Area is split into regions and tracked with vmap_block, read out
@@ -3505,50 +3539,64 @@ static void vmap_ram_vread(char *buf, char *addr, int count, unsigned long flags
 	 */
 	vb = xa_load(&vmap_blocks, addr_to_vb_idx((unsigned long)addr));
 	if (!vb)
-		goto finished;
+		goto finished_zero;
 
 	spin_lock(&vb->lock);
 	if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) {
 		spin_unlock(&vb->lock);
-		goto finished;
+		goto finished_zero;
 	}
+
 	for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) {
-		if (!count)
-			break;
+		size_t copied;
+
+		if (remains == 0)
+			goto finished;
+
 		start = vmap_block_vaddr(vb->va->va_start, rs);
-		while (addr < start) {
-			if (count == 0)
-				goto unlock;
-			*buf = '\0';
-			buf++;
-			addr++;
-			count--;
+
+		if (addr < start) {
+			size_t to_zero = min_t(size_t, start - addr, remains);
+			size_t zeroed = zero_iter(iter, to_zero);
+
+			addr += zeroed;
+			remains -= zeroed;
+
+			if (remains == 0 || zeroed != to_zero)
+				goto finished;
 		}
+
 		/*it could start reading from the middle of used region*/
 		offset = offset_in_page(addr);
 		n = ((re - rs + 1) << PAGE_SHIFT) - offset;
-		if (n > count)
-			n = count;
-		aligned_vread(buf, start+offset, n);
+		if (n > remains)
+			n = remains;
+
+		copied = aligned_vread_iter(iter, start + offset, n);
 
-		buf += n;
-		addr += n;
-		count -= n;
+		addr += copied;
+		remains -= copied;
+
+		if (copied != n)
+			goto finished;
 	}
-unlock:
+
 	spin_unlock(&vb->lock);
 
-finished:
+finished_zero:
 	/* zero-fill the left dirty or free regions */
-	if (count)
-		memset(buf, 0, count);
+	return count - remains + zero_iter(iter, remains);
+finished:
+	/* We couldn't copy/zero everything */
+	spin_unlock(&vb->lock);
+	return count - remains;
 }
 
 /**
- * vread() - read vmalloc area in a safe way.
- * @buf:     buffer for reading data
- * @addr:    vm address.
- * @count:   number of bytes to be read.
+ * vread_iter() - read vmalloc area in a safe way to an iterator.
+ * @iter:         the iterator to which data should be written.
+ * @addr:         vm address.
+ * @count:        number of bytes to be read.
  *
  * This function checks that addr is a valid vmalloc'ed area, and
  * copy data from that area to a given buffer. If the given memory range
@@ -3568,13 +3616,12 @@ finished:
  * (same number as @count) or %0 if [addr...addr+count) doesn't
  * include any intersection with valid vmalloc area
  */
-long vread(char *buf, char *addr, unsigned long count)
+long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
 {
 	struct vmap_area *va;
 	struct vm_struct *vm;
-	char *vaddr, *buf_start = buf;
-	unsigned long buflen = count;
-	unsigned long n, size, flags;
+	char *vaddr;
+	size_t n, size, flags, remains;
 
 	addr = kasan_reset_tag(addr);
 
@@ -3582,18 +3629,22 @@ long vread(char *buf, char *addr, unsigned long count)
 	if ((unsigned long) addr + count < count)
 		count = -(unsigned long) addr;
 
+	remains = count;
+
 	spin_lock(&vmap_area_lock);
 	va = find_vmap_area_exceed_addr((unsigned long)addr);
 	if (!va)
-		goto finished;
+		goto finished_zero;
 
 	/* no intersects with alive vmap_area */
-	if ((unsigned long)addr + count <= va->va_start)
-		goto finished;
+	if ((unsigned long)addr + remains <= va->va_start)
+		goto finished_zero;
 
 	list_for_each_entry_from(va, &vmap_area_list, list) {
-		if (!count)
-			break;
+		size_t copied;
+
+		if (remains == 0)
+			goto finished;
 
 		vm = va->vm;
 		flags = va->flags & VMAP_FLAGS_MASK;
@@ -3608,6 +3659,7 @@ long vread(char *buf, char *addr, unsigned long count)
 
 		if (vm && (vm->flags & VM_UNINITIALIZED))
 			continue;
+
 		/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
 		smp_rmb();
 
@@ -3616,38 +3668,45 @@ long vread(char *buf, char *addr, unsigned long count)
 
 		if (addr >= vaddr + size)
 			continue;
-		while (addr < vaddr) {
-			if (count == 0)
+
+		if (addr < vaddr) {
+			size_t to_zero = min_t(size_t, vaddr - addr, remains);
+			size_t zeroed = zero_iter(iter, to_zero);
+
+			addr += zeroed;
+			remains -= zeroed;
+
+			if (remains == 0 || zeroed != to_zero)
 				goto finished;
-			*buf = '\0';
-			buf++;
-			addr++;
-			count--;
 		}
+
 		n = vaddr + size - addr;
-		if (n > count)
-			n = count;
+		if (n > remains)
+			n = remains;
 
 		if (flags & VMAP_RAM)
-			vmap_ram_vread(buf, addr, n, flags);
+			copied = vmap_ram_vread_iter(iter, addr, n, flags);
 		else if (!(vm->flags & VM_IOREMAP))
-			aligned_vread(buf, addr, n);
+			copied = aligned_vread_iter(iter, addr, n);
 		else /* IOREMAP area is treated as memory hole */
-			memset(buf, 0, n);
-		buf += n;
-		addr += n;
-		count -= n;
+			copied = zero_iter(iter, n);
+
+		addr += copied;
+		remains -= copied;
+
+		if (copied != n)
+			goto finished;
 	}
-finished:
-	spin_unlock(&vmap_area_lock);
 
-	if (buf == buf_start)
-		return 0;
+finished_zero:
+	spin_unlock(&vmap_area_lock);
 	/* zero-fill memory holes */
-	if (buf != buf_start + buflen)
-		memset(buf, 0, buflen - (buf - buf_start));
+	return count - remains + zero_iter(iter, remains);
+finished:
+	/* Nothing remains, or We couldn't copy/zero everything. */
+	spin_unlock(&vmap_area_lock);
 
-	return buflen;
+	return count - remains;
 }
 
 /**