The patch titled
Subject: mm: vmalloc: support multiple nodes in vread_iter
has been added to the -mm mm-unstable branch. Its filename is
mm-vmalloc-support-multiple-nodes-in-vread_iter.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-vmalloc-support-multiple-nodes-in-vread_iter.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Uladzislau Rezki (Sony)" <urezki@xxxxxxxxx>
Subject: mm: vmalloc: support multiple nodes in vread_iter
Date: Tue, 29 Aug 2023 10:11:40 +0200
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.
Link: https://lkml.kernel.org/r/20230829081142.3619-8-urezki@xxxxxxxxx
Signed-off-by: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
Cc: Baoquan He <bhe@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Cc: Liam R. Howlett <Liam.Howlett@xxxxxxxxxx>
Cc: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@xxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/vmalloc.c | 67 ++++++++++++++++++++++++++++++++++++++-----------
1 file changed, 53 insertions(+), 14 deletions(-)
--- a/mm/vmalloc.c~mm-vmalloc-support-multiple-nodes-in-vread_iter
+++ a/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
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;
@@ -4052,6 +4087,7 @@ long vread_iter(struct iov_iter *iter, c
struct vm_struct *vm;
char *vaddr;
size_t n, size, flags, remains;
+ unsigned long next;
addr = kasan_reset_tag(addr);
@@ -4061,19 +4097,15 @@ long vread_iter(struct iov_iter *iter, c
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)
@@ -4088,10 +4120,10 @@ long vread_iter(struct iov_iter *iter, c
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();
@@ -4100,7 +4132,7 @@ long vread_iter(struct iov_iter *iter, c
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);
@@ -4129,15 +4161,22 @@ long vread_iter(struct iov_iter *iter, c
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;
}
_
Patches currently in -mm which might be from urezki@xxxxxxxxx are
mm-vmalloc-add-va_alloc-helper.patch
mm-vmalloc-rename-adjust_va_to_fit_type-function.patch
mm-vmalloc-move-vmap_init_free_space-down-in-vmallocc.patch
mm-vmalloc-remove-global-vmap_area_root-rb-tree.patch
mm-vmalloc-remove-global-vmap_area_root-rb-tree-fix.patch
mm-vmalloc-remove-global-purge_vmap_area_root-rb-tree.patch
mm-vmalloc-offload-free_vmap_area_lock-lock.patch
mm-vmalloc-support-multiple-nodes-in-vread_iter.patch
mm-vmalloc-support-multiple-nodes-in-vmallocinfo.patch
mm-vmalloc-set-nr_nodes-node_size-based-on-cpu-cores.patch
