From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
To: linux-mm@kvack.org, Andrew Morton <akpm@linux-foundation.org>
Cc: LKML <linux-kernel@vger.kernel.org>, Baoquan He <bhe@redhat.com>,
Lorenzo Stoakes <lstoakes@gmail.com>,
Christoph Hellwig <hch@infradead.org>,
Matthew Wilcox <willy@infradead.org>,
"Liam R . Howlett" <Liam.Howlett@oracle.com>,
Dave Chinner <david@fromorbit.com>,
"Paul E . McKenney" <paulmck@kernel.org>,
Joel Fernandes <joel@joelfernandes.org>,
Uladzislau Rezki <urezki@gmail.com>,
Oleksiy Avramchenko <oleksiy.avramchenko@sony.com>
Subject: [PATCH v2 7/9] mm: vmalloc: Support multiple nodes in vread_iter
Date: Tue, 29 Aug 2023 10:11:40 +0200 [thread overview]
Message-ID: <20230829081142.3619-8-urezki@gmail.com> (raw)
In-Reply-To: <20230829081142.3619-1-urezki@gmail.com>
Extend the vread_iter() to be able to perform a sequential
reading of VAs which are spread among multiple nodes. So a
data read over the /dev/kmem correctly reflects a vmalloc
memory layout.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
mm/vmalloc.c | 67 +++++++++++++++++++++++++++++++++++++++++-----------
1 file changed, 53 insertions(+), 14 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 4fd4915c532d..968144c16237 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -870,7 +870,7 @@ unsigned long vmalloc_nr_pages(void)
/* Look up the first VA which satisfies addr < va_end, NULL if none. */
static struct vmap_area *
-find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
+__find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
{
struct vmap_area *va = NULL;
struct rb_node *n = root->rb_node;
@@ -894,6 +894,41 @@ find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
return va;
}
+/*
+ * Returns a node where a first VA, that satisfies addr < va_end, resides.
+ * If success, a node is locked. A user is responsible to unlock it when a
+ * VA is no longer needed to be accessed.
+ *
+ * Returns NULL if nothing found.
+ */
+static struct vmap_node *
+find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va)
+{
+ struct vmap_node *vn, *va_node = NULL;
+ struct vmap_area *va_lowest;
+ int i;
+
+ for (i = 0; i < nr_nodes; i++) {
+ vn = &nodes[i];
+
+ spin_lock(&vn->busy.lock);
+ va_lowest = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
+ if (va_lowest) {
+ if (!va_node || va_lowest->va_start < (*va)->va_start) {
+ if (va_node)
+ spin_unlock(&va_node->busy.lock);
+
+ *va = va_lowest;
+ va_node = vn;
+ continue;
+ }
+ }
+ spin_unlock(&vn->busy.lock);
+ }
+
+ return va_node;
+}
+
static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
{
struct rb_node *n = root->rb_node;
@@ -4048,6 +4083,7 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
struct vm_struct *vm;
char *vaddr;
size_t n, size, flags, remains;
+ unsigned long next;
addr = kasan_reset_tag(addr);
@@ -4057,19 +4093,15 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
remains = count;
- /* Hooked to node_0 so far. */
- vn = addr_to_node(0);
- spin_lock(&vn->busy.lock);
-
- va = find_vmap_area_exceed_addr((unsigned long)addr, &vn->busy.root);
- if (!va)
+ vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va);
+ if (!vn)
goto finished_zero;
/* no intersects with alive vmap_area */
if ((unsigned long)addr + remains <= va->va_start)
goto finished_zero;
- list_for_each_entry_from(va, &vn->busy.head, list) {
+ do {
size_t copied;
if (remains == 0)
@@ -4084,10 +4116,10 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
WARN_ON(flags == VMAP_BLOCK);
if (!vm && !flags)
- continue;
+ goto next_va;
if (vm && (vm->flags & VM_UNINITIALIZED))
- continue;
+ goto next_va;
/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
smp_rmb();
@@ -4096,7 +4128,7 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
size = vm ? get_vm_area_size(vm) : va_size(va);
if (addr >= vaddr + size)
- continue;
+ goto next_va;
if (addr < vaddr) {
size_t to_zero = min_t(size_t, vaddr - addr, remains);
@@ -4125,15 +4157,22 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
if (copied != n)
goto finished;
- }
+
+ next_va:
+ next = va->va_end;
+ spin_unlock(&vn->busy.lock);
+ } while ((vn = find_vmap_area_exceed_addr_lock(next, &va)));
finished_zero:
- spin_unlock(&vn->busy.lock);
+ if (vn)
+ spin_unlock(&vn->busy.lock);
+
/* zero-fill memory holes */
return count - remains + zero_iter(iter, remains);
finished:
/* Nothing remains, or We couldn't copy/zero everything. */
- spin_unlock(&vn->busy.lock);
+ if (vn)
+ spin_unlock(&vn->busy.lock);
return count - remains;
}
--
2.30.2
next prev parent reply other threads:[~2023-08-29 8:12 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-29 8:11 [PATCH v2 0/9] Mitigate a vmap lock contention v2 Uladzislau Rezki (Sony)
2023-08-29 8:11 ` [PATCH v2 1/9] mm: vmalloc: Add va_alloc() helper Uladzislau Rezki (Sony)
2023-09-06 5:51 ` Baoquan He
2023-09-06 15:06 ` Uladzislau Rezki
2023-08-29 8:11 ` [PATCH v2 2/9] mm: vmalloc: Rename adjust_va_to_fit_type() function Uladzislau Rezki (Sony)
2023-09-06 5:51 ` Baoquan He
2023-09-06 16:27 ` Uladzislau Rezki
2023-08-29 8:11 ` [PATCH v2 3/9] mm: vmalloc: Move vmap_init_free_space() down in vmalloc.c Uladzislau Rezki (Sony)
2023-09-06 5:52 ` Baoquan He
2023-09-06 16:29 ` Uladzislau Rezki
2023-08-29 8:11 ` [PATCH v2 4/9] mm: vmalloc: Remove global vmap_area_root rb-tree Uladzislau Rezki (Sony)
2023-08-29 14:30 ` kernel test robot
2023-08-30 14:48 ` Uladzislau Rezki
2023-09-07 2:17 ` Baoquan He
2023-09-07 9:38 ` Baoquan He
2023-09-07 9:40 ` Uladzislau Rezki
2023-09-07 9:39 ` Uladzislau Rezki
2023-09-07 9:58 ` Baoquan He
2023-09-08 1:51 ` HAGIO KAZUHITO(萩尾 一仁)
2023-09-08 4:43 ` Baoquan He
2023-09-08 5:01 ` HAGIO KAZUHITO(萩尾 一仁)
2023-09-08 6:44 ` Baoquan He
2023-09-08 11:25 ` Uladzislau Rezki
2023-09-08 11:38 ` Baoquan He
2023-09-08 13:23 ` Uladzislau Rezki
2023-09-11 2:38 ` Baoquan He
2023-09-11 16:53 ` Uladzislau Rezki
2023-09-12 13:19 ` Baoquan He
2023-08-29 8:11 ` [PATCH v2 5/9] mm: vmalloc: Remove global purge_vmap_area_root rb-tree Uladzislau Rezki (Sony)
2023-09-11 2:57 ` Baoquan He
2023-09-11 17:00 ` Uladzislau Rezki
2023-08-29 8:11 ` [PATCH v2 6/9] mm: vmalloc: Offload free_vmap_area_lock lock Uladzislau Rezki (Sony)
2023-09-06 6:04 ` Baoquan He
2023-09-06 19:16 ` Uladzislau Rezki
2023-09-07 0:06 ` Baoquan He
2023-09-07 9:33 ` Uladzislau Rezki
2023-09-11 3:25 ` Baoquan He
2023-09-11 17:10 ` Uladzislau Rezki
2023-09-12 13:21 ` Baoquan He
2023-08-29 8:11 ` Uladzislau Rezki (Sony) [this message]
2023-09-11 3:58 ` [PATCH v2 7/9] mm: vmalloc: Support multiple nodes in vread_iter Baoquan He
2023-09-11 18:16 ` Uladzislau Rezki
2023-09-12 13:42 ` Baoquan He
2023-09-13 15:42 ` Uladzislau Rezki
2023-09-14 3:02 ` Baoquan He
2023-09-14 3:36 ` Baoquan He
2023-09-14 3:38 ` Baoquan He
2023-09-13 10:59 ` Baoquan He
2023-09-13 15:38 ` Uladzislau Rezki
2023-08-29 8:11 ` [PATCH v2 8/9] mm: vmalloc: Support multiple nodes in vmallocinfo Uladzislau Rezki (Sony)
2023-09-15 13:02 ` Baoquan He
2023-09-15 18:32 ` Uladzislau Rezki
2023-08-29 8:11 ` [PATCH v2 9/9] mm: vmalloc: Set nr_nodes/node_size based on CPU-cores Uladzislau Rezki (Sony)
2023-09-15 13:03 ` Baoquan He
2023-09-15 18:31 ` Uladzislau Rezki
2023-08-31 1:15 ` [PATCH v2 0/9] Mitigate a vmap lock contention v2 Baoquan He
2023-08-31 16:26 ` Uladzislau Rezki
2023-09-04 14:55 ` Uladzislau Rezki
2023-09-04 19:53 ` Andrew Morton
2023-09-05 6:53 ` Uladzislau Rezki
2023-09-06 20:04 ` Lorenzo Stoakes
2023-09-07 9:15 ` Uladzislau Rezki
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230829081142.3619-8-urezki@gmail.com \
--to=urezki@gmail.com \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=bhe@redhat.com \
--cc=david@fromorbit.com \
--cc=hch@infradead.org \
--cc=joel@joelfernandes.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lstoakes@gmail.com \
--cc=oleksiy.avramchenko@sony.com \
--cc=paulmck@kernel.org \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).