The patch titled
Subject: mm: vmalloc: remove global purge_vmap_area_root rb-tree
has been added to the -mm mm-unstable branch. Its filename is
mm-vmalloc-remove-global-purge_vmap_area_root-rb-tree.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-vmalloc-remove-global-purge_vmap_area_root-rb-tree.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: remove global purge_vmap_area_root rb-tree
Date: Tue, 29 Aug 2023 10:11:38 +0200
Similar to busy VA, lazily-freed area is stored to a node it belongs to.
Such approach does not require any global locking primitive, instead an
access becomes scalable what mitigates a contention.
This patch removes a global purge-lock, global purge-tree and global purge
list.
Link: https://lkml.kernel.org/r/20230829081142.3619-6-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 | 135 +++++++++++++++++++++++++++++--------------------
1 file changed, 82 insertions(+), 53 deletions(-)
--- a/mm/vmalloc.c~mm-vmalloc-remove-global-purge_vmap_area_root-rb-tree
+++ a/mm/vmalloc.c
@@ -733,10 +733,6 @@ static DEFINE_SPINLOCK(free_vmap_area_lo
LIST_HEAD(vmap_area_list);
static bool vmap_initialized __read_mostly;
-static struct rb_root purge_vmap_area_root = RB_ROOT;
-static LIST_HEAD(purge_vmap_area_list);
-static DEFINE_SPINLOCK(purge_vmap_area_lock);
-
/*
* This kmem_cache is used for vmap_area objects. Instead of
* allocating from slab we reuse an object from this cache to
@@ -784,6 +780,12 @@ struct rb_list {
struct vmap_node {
/* Bookkeeping data of this node. */
struct rb_list busy;
+ struct rb_list lazy;
+
+ /*
+ * Ready-to-free areas.
+ */
+ struct list_head purge_list;
};
static struct vmap_node *nodes, snode;
@@ -1768,40 +1770,22 @@ static DEFINE_MUTEX(vmap_purge_lock);
/* for per-CPU blocks */
static void purge_fragmented_blocks_allcpus(void);
+static cpumask_t purge_nodes;
/*
* Purges all lazily-freed vmap areas.
*/
-static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
+static unsigned long
+purge_vmap_node(struct vmap_node *vn)
{
- unsigned long resched_threshold;
- unsigned int num_purged_areas = 0;
- struct list_head local_purge_list;
+ unsigned long num_purged_areas = 0;
struct vmap_area *va, *n_va;
- lockdep_assert_held(&vmap_purge_lock);
-
- spin_lock(&purge_vmap_area_lock);
- purge_vmap_area_root = RB_ROOT;
- list_replace_init(&purge_vmap_area_list, &local_purge_list);
- spin_unlock(&purge_vmap_area_lock);
-
- if (unlikely(list_empty(&local_purge_list)))
- goto out;
-
- start = min(start,
- list_first_entry(&local_purge_list,
- struct vmap_area, list)->va_start);
-
- end = max(end,
- list_last_entry(&local_purge_list,
- struct vmap_area, list)->va_end);
-
- flush_tlb_kernel_range(start, end);
- resched_threshold = lazy_max_pages() << 1;
+ if (list_empty(&vn->purge_list))
+ return 0;
spin_lock(&free_vmap_area_lock);
- list_for_each_entry_safe(va, n_va, &local_purge_list, list) {
+ list_for_each_entry_safe(va, n_va, &vn->purge_list, list) {
unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT;
unsigned long orig_start = va->va_start;
unsigned long orig_end = va->va_end;
@@ -1823,13 +1807,55 @@ static bool __purge_vmap_area_lazy(unsig
atomic_long_sub(nr, &vmap_lazy_nr);
num_purged_areas++;
-
- if (atomic_long_read(&vmap_lazy_nr) < resched_threshold)
- cond_resched_lock(&free_vmap_area_lock);
}
spin_unlock(&free_vmap_area_lock);
-out:
+ return num_purged_areas;
+}
+
+/*
+ * Purges all lazily-freed vmap areas.
+ */
+static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
+{
+ unsigned long num_purged_areas = 0;
+ struct vmap_node *vn;
+ int i;
+
+ lockdep_assert_held(&vmap_purge_lock);
+ purge_nodes = CPU_MASK_NONE;
+
+ for (i = 0; i < nr_nodes; i++) {
+ vn = &nodes[i];
+
+ INIT_LIST_HEAD(&vn->purge_list);
+
+ if (RB_EMPTY_ROOT(&vn->lazy.root))
+ continue;
+
+ spin_lock(&vn->lazy.lock);
+ WRITE_ONCE(vn->lazy.root.rb_node, NULL);
+ list_replace_init(&vn->lazy.head, &vn->purge_list);
+ spin_unlock(&vn->lazy.lock);
+
+ start = min(start, list_first_entry(&vn->purge_list,
+ struct vmap_area, list)->va_start);
+
+ end = max(end, list_last_entry(&vn->purge_list,
+ struct vmap_area, list)->va_end);
+
+ cpumask_set_cpu(i, &purge_nodes);
+ }
+
+ if (cpumask_weight(&purge_nodes) > 0) {
+ flush_tlb_kernel_range(start, end);
+
+ for_each_cpu(i, &purge_nodes) {
+ vn = &nodes[i];
+ num_purged_areas += purge_vmap_node(vn);
+ }
+ }
+
trace_purge_vmap_area_lazy(start, end, num_purged_areas);
return num_purged_areas > 0;
}
@@ -1848,16 +1874,9 @@ static void reclaim_and_purge_vmap_areas
static void drain_vmap_area_work(struct work_struct *work)
{
- unsigned long nr_lazy;
-
- do {
- mutex_lock(&vmap_purge_lock);
- __purge_vmap_area_lazy(ULONG_MAX, 0);
- mutex_unlock(&vmap_purge_lock);
-
- /* Recheck if further work is required. */
- nr_lazy = atomic_long_read(&vmap_lazy_nr);
- } while (nr_lazy > lazy_max_pages());
+ mutex_lock(&vmap_purge_lock);
+ __purge_vmap_area_lazy(ULONG_MAX, 0);
+ mutex_unlock(&vmap_purge_lock);
}
/*
@@ -1867,6 +1886,7 @@ static void drain_vmap_area_work(struct
*/
static void free_vmap_area_noflush(struct vmap_area *va)
{
+ struct vmap_node *vn = addr_to_node(va->va_start);
unsigned long nr_lazy_max = lazy_max_pages();
unsigned long va_start = va->va_start;
unsigned long nr_lazy;
@@ -1880,10 +1900,9 @@ static void free_vmap_area_noflush(struc
/*
* Merge or place it to the purge tree/list.
*/
- spin_lock(&purge_vmap_area_lock);
- merge_or_add_vmap_area(va,
- &purge_vmap_area_root, &purge_vmap_area_list);
- spin_unlock(&purge_vmap_area_lock);
+ spin_lock(&vn->lazy.lock);
+ merge_or_add_vmap_area(va, &vn->lazy.root, &vn->lazy.head);
+ spin_unlock(&vn->lazy.lock);
trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max);
@@ -4412,15 +4431,21 @@ static void show_numa_info(struct seq_fi
static void show_purge_info(struct seq_file *m)
{
+ struct vmap_node *vn;
struct vmap_area *va;
+ int i;
- spin_lock(&purge_vmap_area_lock);
- list_for_each_entry(va, &purge_vmap_area_list, list) {
- seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
- (void *)va->va_start, (void *)va->va_end,
- va->va_end - va->va_start);
+ for (i = 0; i < nr_nodes; i++) {
+ vn = &nodes[i];
+
+ spin_lock(&vn->lazy.lock);
+ list_for_each_entry(va, &vn->lazy.head, list) {
+ seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
+ (void *)va->va_start, (void *)va->va_end,
+ va->va_end - va->va_start);
+ }
+ spin_unlock(&vn->lazy.lock);
}
- spin_unlock(&purge_vmap_area_lock);
}
static int s_show(struct seq_file *m, void *p)
@@ -4567,6 +4592,10 @@ static void vmap_init_nodes(void)
vn->busy.root = RB_ROOT;
INIT_LIST_HEAD(&vn->busy.head);
spin_lock_init(&vn->busy.lock);
+
+ vn->lazy.root = RB_ROOT;
+ INIT_LIST_HEAD(&vn->lazy.head);
+ spin_lock_init(&vn->lazy.lock);
}
}
_
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
