Re: [PATCH v4 1/2] mm: refactor __vunmap() to avoid duplicated call to find_vm_area()
On Thu, Apr 18, 2019 at 03:24:31PM -0700, Andrew Morton wrote:
> On Thu, 18 Apr 2019 04:18:34 -0700 Matthew Wilcox wrote:
>
> > On Wed, Apr 17, 2019 at 02:58:27PM -0700, Andrew Morton wrote:
> > > On Wed, 17 Apr 2019 12:40:01 -0700 Roman Gushchin
> > > wrote:
> > > > +static struct vm_struct *__remove_vm_area(struct vmap_area *va)
> > > > +{
> > > > + struct vm_struct *vm = va->vm;
> > > > +
> > > > + might_sleep();
> > >
> > > Where might __remove_vm_area() sleep?
> > >
> > > >From a quick scan I'm only seeing vfree(), and that has the
> > > might_sleep_if(!in_interrupt()).
> > >
> > > So perhaps we can remove this...
> >
> > See commit 5803ed292e63 ("mm: mark all calls into the vmalloc subsystem as
> > potentially sleeping")
> >
> > It looks like the intent is to unconditionally check might_sleep() at
> > the entry points to the vmalloc code, rather than only catch them in
> > the occasional place where it happens to go wrong.
>
> afaict, vfree() will only do a mutex_trylock() in
> try_purge_vmap_area_lazy(). So does vfree actually sleep in any
> situation? Whether or not local interrupts are enabled?
IIRC, the original problem that used to prohibit vfree() in interrupts
was the use of spinlocks that were used in a lot of places by plain
spin_lock(). I'm not sure it could actually sleep in anything not
too ancient...
Re: [PATCH v4 1/2] mm: refactor __vunmap() to avoid duplicated call to find_vm_area()
On 04/18/2019 03:24 PM, Andrew Morton wrote: > afaict, vfree() will only do a mutex_trylock() in > try_purge_vmap_area_lazy(). So does vfree actually sleep in any > situation? Whether or not local interrupts are enabled? We would be in a big trouble if vfree() could potentially sleep... Random example : __free_fdtable() called from rcu callback.
Re: [PATCH v4 1/2] mm: refactor __vunmap() to avoid duplicated call to find_vm_area()
On Thu, 18 Apr 2019 04:18:34 -0700 Matthew Wilcox wrote:
> On Wed, Apr 17, 2019 at 02:58:27PM -0700, Andrew Morton wrote:
> > On Wed, 17 Apr 2019 12:40:01 -0700 Roman Gushchin wrote:
> > > +static struct vm_struct *__remove_vm_area(struct vmap_area *va)
> > > +{
> > > + struct vm_struct *vm = va->vm;
> > > +
> > > + might_sleep();
> >
> > Where might __remove_vm_area() sleep?
> >
> > >From a quick scan I'm only seeing vfree(), and that has the
> > might_sleep_if(!in_interrupt()).
> >
> > So perhaps we can remove this...
>
> See commit 5803ed292e63 ("mm: mark all calls into the vmalloc subsystem as
> potentially sleeping")
>
> It looks like the intent is to unconditionally check might_sleep() at
> the entry points to the vmalloc code, rather than only catch them in
> the occasional place where it happens to go wrong.
afaict, vfree() will only do a mutex_trylock() in
try_purge_vmap_area_lazy(). So does vfree actually sleep in any
situation? Whether or not local interrupts are enabled?
Re: [PATCH v4 1/2] mm: refactor __vunmap() to avoid duplicated call to find_vm_area()
On Wed, Apr 17, 2019 at 02:58:27PM -0700, Andrew Morton wrote:
> On Wed, 17 Apr 2019 12:40:01 -0700 Roman Gushchin wrote:
> > +static struct vm_struct *__remove_vm_area(struct vmap_area *va)
> > +{
> > + struct vm_struct *vm = va->vm;
> > +
> > + might_sleep();
>
> Where might __remove_vm_area() sleep?
>
> >From a quick scan I'm only seeing vfree(), and that has the
> might_sleep_if(!in_interrupt()).
>
> So perhaps we can remove this...
See commit 5803ed292e63 ("mm: mark all calls into the vmalloc subsystem as
potentially sleeping")
It looks like the intent is to unconditionally check might_sleep() at
the entry points to the vmalloc code, rather than only catch them in
the occasional place where it happens to go wrong.
Re: [PATCH v4 1/2] mm: refactor __vunmap() to avoid duplicated call to find_vm_area()
On Wed, Apr 17, 2019 at 02:58:27PM -0700, Andrew Morton wrote:
> On Wed, 17 Apr 2019 12:40:01 -0700 Roman Gushchin wrote:
>
> > __vunmap() calls find_vm_area() twice without an obvious reason:
> > first directly to get the area pointer, second indirectly by calling
> > remove_vm_area(), which is again searching for the area.
> >
> > To remove this redundancy, let's split remove_vm_area() into
> > __remove_vm_area(struct vmap_area *), which performs the actual area
> > removal, and remove_vm_area(const void *addr) wrapper, which can
> > be used everywhere, where it has been used before.
> >
> > On my test setup, I've got 5-10% speed up on vfree()'ing 100
> > of 4-pages vmalloc blocks.
> >
> > Perf report before:
> > 22.64% cat [kernel.vmlinux] [k] free_pcppages_bulk
> > 10.30% cat [kernel.vmlinux] [k] __vunmap
> >9.80% cat [kernel.vmlinux] [k] find_vmap_area
> >8.11% cat [kernel.vmlinux] [k] vunmap_page_range
> >4.20% cat [kernel.vmlinux] [k] __slab_free
> >3.56% cat [kernel.vmlinux] [k] __list_del_entry_valid
> >3.46% cat [kernel.vmlinux] [k] smp_call_function_many
> >3.33% cat [kernel.vmlinux] [k] kfree
> >3.32% cat [kernel.vmlinux] [k] free_unref_page
> >
> > Perf report after:
> > 23.01% cat [kernel.kallsyms] [k] free_pcppages_bulk
> >9.46% cat [kernel.kallsyms] [k] __vunmap
> >9.15% cat [kernel.kallsyms] [k] vunmap_page_range
> >6.17% cat [kernel.kallsyms] [k] __slab_free
> >5.61% cat [kernel.kallsyms] [k] kfree
> >4.86% cat [kernel.kallsyms] [k] bad_range
> >4.67% cat [kernel.kallsyms] [k] free_unref_page_commit
> >4.24% cat [kernel.kallsyms] [k] __list_del_entry_valid
> >3.68% cat [kernel.kallsyms] [k] free_unref_page
> >3.65% cat [kernel.kallsyms] [k] __list_add_valid
> >3.19% cat [kernel.kallsyms] [k] __purge_vmap_area_lazy
> >3.10% cat [kernel.kallsyms] [k] find_vmap_area
> >3.05% cat [kernel.kallsyms] [k] rcu_cblist_dequeue
> >
> > ...
> >
> > --- a/mm/vmalloc.c
> > +++ b/mm/vmalloc.c
> > @@ -2068,6 +2068,24 @@ struct vm_struct *find_vm_area(const void *addr)
> > return NULL;
> > }
> >
> > +static struct vm_struct *__remove_vm_area(struct vmap_area *va)
> > +{
> > + struct vm_struct *vm = va->vm;
> > +
> > + might_sleep();
>
> Where might __remove_vm_area() sleep?
>
> From a quick scan I'm only seeing vfree(), and that has the
> might_sleep_if(!in_interrupt()).
>
> So perhaps we can remove this...
Agree. Here is the patch.
Thank you!
--
>From 4adf58e4d3ffe45a542156ca0bce3dc9f6679939 Mon Sep 17 00:00:00 2001
From: Roman Gushchin
Date: Wed, 17 Apr 2019 15:55:49 -0700
Subject: [PATCH] mm: remove might_sleep() in __remove_vm_area()
__remove_vm_area() has a redundant might_sleep() call, which isn't
really required, because the only place it can sleep is vfree()
and it already contains might_sleep_if(!in_interrupt()).
Suggested-by: Andrew Morton
Signed-off-by: Roman Gushchin
---
mm/vmalloc.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 69a5673c4cd3..4a91acce4b5f 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2079,8 +2079,6 @@ static struct vm_struct *__remove_vm_area(struct
vmap_area *va)
{
struct vm_struct *vm = va->vm;
- might_sleep();
-
spin_lock(_area_lock);
va->vm = NULL;
va->flags &= ~VM_VM_AREA;
--
2.20.1
Re: [PATCH v4 1/2] mm: refactor __vunmap() to avoid duplicated call to find_vm_area()
On Wed, 17 Apr 2019 12:40:01 -0700 Roman Gushchin wrote:
> __vunmap() calls find_vm_area() twice without an obvious reason:
> first directly to get the area pointer, second indirectly by calling
> remove_vm_area(), which is again searching for the area.
>
> To remove this redundancy, let's split remove_vm_area() into
> __remove_vm_area(struct vmap_area *), which performs the actual area
> removal, and remove_vm_area(const void *addr) wrapper, which can
> be used everywhere, where it has been used before.
>
> On my test setup, I've got 5-10% speed up on vfree()'ing 100
> of 4-pages vmalloc blocks.
>
> Perf report before:
> 22.64% cat [kernel.vmlinux] [k] free_pcppages_bulk
> 10.30% cat [kernel.vmlinux] [k] __vunmap
>9.80% cat [kernel.vmlinux] [k] find_vmap_area
>8.11% cat [kernel.vmlinux] [k] vunmap_page_range
>4.20% cat [kernel.vmlinux] [k] __slab_free
>3.56% cat [kernel.vmlinux] [k] __list_del_entry_valid
>3.46% cat [kernel.vmlinux] [k] smp_call_function_many
>3.33% cat [kernel.vmlinux] [k] kfree
>3.32% cat [kernel.vmlinux] [k] free_unref_page
>
> Perf report after:
> 23.01% cat [kernel.kallsyms] [k] free_pcppages_bulk
>9.46% cat [kernel.kallsyms] [k] __vunmap
>9.15% cat [kernel.kallsyms] [k] vunmap_page_range
>6.17% cat [kernel.kallsyms] [k] __slab_free
>5.61% cat [kernel.kallsyms] [k] kfree
>4.86% cat [kernel.kallsyms] [k] bad_range
>4.67% cat [kernel.kallsyms] [k] free_unref_page_commit
>4.24% cat [kernel.kallsyms] [k] __list_del_entry_valid
>3.68% cat [kernel.kallsyms] [k] free_unref_page
>3.65% cat [kernel.kallsyms] [k] __list_add_valid
>3.19% cat [kernel.kallsyms] [k] __purge_vmap_area_lazy
>3.10% cat [kernel.kallsyms] [k] find_vmap_area
>3.05% cat [kernel.kallsyms] [k] rcu_cblist_dequeue
>
> ...
>
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -2068,6 +2068,24 @@ struct vm_struct *find_vm_area(const void *addr)
> return NULL;
> }
>
> +static struct vm_struct *__remove_vm_area(struct vmap_area *va)
> +{
> + struct vm_struct *vm = va->vm;
> +
> + might_sleep();
Where might __remove_vm_area() sleep?
>From a quick scan I'm only seeing vfree(), and that has the
might_sleep_if(!in_interrupt()).
So perhaps we can remove this...
> + spin_lock(_area_lock);
> + va->vm = NULL;
> + va->flags &= ~VM_VM_AREA;
> + va->flags |= VM_LAZY_FREE;
> + spin_unlock(_area_lock);
> +
> + kasan_free_shadow(vm);
> + free_unmap_vmap_area(va);
> +
> + return vm;
> +}
> +
[PATCH v4 1/2] mm: refactor __vunmap() to avoid duplicated call to find_vm_area()
__vunmap() calls find_vm_area() twice without an obvious reason:
first directly to get the area pointer, second indirectly by calling
remove_vm_area(), which is again searching for the area.
To remove this redundancy, let's split remove_vm_area() into
__remove_vm_area(struct vmap_area *), which performs the actual area
removal, and remove_vm_area(const void *addr) wrapper, which can
be used everywhere, where it has been used before.
On my test setup, I've got 5-10% speed up on vfree()'ing 100
of 4-pages vmalloc blocks.
Perf report before:
22.64% cat [kernel.vmlinux] [k] free_pcppages_bulk
10.30% cat [kernel.vmlinux] [k] __vunmap
9.80% cat [kernel.vmlinux] [k] find_vmap_area
8.11% cat [kernel.vmlinux] [k] vunmap_page_range
4.20% cat [kernel.vmlinux] [k] __slab_free
3.56% cat [kernel.vmlinux] [k] __list_del_entry_valid
3.46% cat [kernel.vmlinux] [k] smp_call_function_many
3.33% cat [kernel.vmlinux] [k] kfree
3.32% cat [kernel.vmlinux] [k] free_unref_page
Perf report after:
23.01% cat [kernel.kallsyms] [k] free_pcppages_bulk
9.46% cat [kernel.kallsyms] [k] __vunmap
9.15% cat [kernel.kallsyms] [k] vunmap_page_range
6.17% cat [kernel.kallsyms] [k] __slab_free
5.61% cat [kernel.kallsyms] [k] kfree
4.86% cat [kernel.kallsyms] [k] bad_range
4.67% cat [kernel.kallsyms] [k] free_unref_page_commit
4.24% cat [kernel.kallsyms] [k] __list_del_entry_valid
3.68% cat [kernel.kallsyms] [k] free_unref_page
3.65% cat [kernel.kallsyms] [k] __list_add_valid
3.19% cat [kernel.kallsyms] [k] __purge_vmap_area_lazy
3.10% cat [kernel.kallsyms] [k] find_vmap_area
3.05% cat [kernel.kallsyms] [k] rcu_cblist_dequeue
Signed-off-by: Roman Gushchin
Acked-by: Johannes Weiner
Reviewed-by: Matthew Wilcox
Acked-by: Vlastimil Babka
---
mm/vmalloc.c | 47 +++
1 file changed, 27 insertions(+), 20 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 92b784d8088c..8ad8e8464e55 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2068,6 +2068,24 @@ struct vm_struct *find_vm_area(const void *addr)
return NULL;
}
+static struct vm_struct *__remove_vm_area(struct vmap_area *va)
+{
+ struct vm_struct *vm = va->vm;
+
+ might_sleep();
+
+ spin_lock(_area_lock);
+ va->vm = NULL;
+ va->flags &= ~VM_VM_AREA;
+ va->flags |= VM_LAZY_FREE;
+ spin_unlock(_area_lock);
+
+ kasan_free_shadow(vm);
+ free_unmap_vmap_area(va);
+
+ return vm;
+}
+
/**
* remove_vm_area - find and remove a continuous kernel virtual area
* @addr: base address
@@ -2080,31 +2098,20 @@ struct vm_struct *find_vm_area(const void *addr)
*/
struct vm_struct *remove_vm_area(const void *addr)
{
+ struct vm_struct *vm = NULL;
struct vmap_area *va;
- might_sleep();
-
va = find_vmap_area((unsigned long)addr);
- if (va && va->flags & VM_VM_AREA) {
- struct vm_struct *vm = va->vm;
-
- spin_lock(_area_lock);
- va->vm = NULL;
- va->flags &= ~VM_VM_AREA;
- va->flags |= VM_LAZY_FREE;
- spin_unlock(_area_lock);
-
- kasan_free_shadow(vm);
- free_unmap_vmap_area(va);
+ if (va && va->flags & VM_VM_AREA)
+ vm = __remove_vm_area(va);
- return vm;
- }
- return NULL;
+ return vm;
}
static void __vunmap(const void *addr, int deallocate_pages)
{
struct vm_struct *area;
+ struct vmap_area *va;
if (!addr)
return;
@@ -2113,17 +2120,18 @@ static void __vunmap(const void *addr, int
deallocate_pages)
addr))
return;
- area = find_vm_area(addr);
- if (unlikely(!area)) {
+ va = find_vmap_area((unsigned long)addr);
+ if (unlikely(!va || !(va->flags & VM_VM_AREA))) {
WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
addr);
return;
}
+ area = va->vm;
debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
- remove_vm_area(addr);
+ __remove_vm_area(va);
if (deallocate_pages) {
int i;
@@ -2138,7 +2146,6 @@ static void __vunmap(const void *addr, int
deallocate_pages)
}
kfree(area);
- return;
}
static inline void __vfree_deferred(const void *addr)
--
2.20.1
