[PATCH v2] mm/vmalloc: use rb_tree instead of list for vread() lookups

[PATCH v2] mm/vmalloc: use rb_tree instead of list for vread() lookups

[Serapheim Dimitropoulos]

vread() has been linearly searching vmap_area_list for looking up
vmalloc areas to read from. These same areas are also tracked by
a rb_tree (vmap_area_root) which offers logarithmic lookup.

This patch modifies vread() to use the rb_tree structure instead
of the list and the speedup for heavy /proc/kcore readers can
be pretty significant. Below are the wall clock measurements of
a Python application that leverages the drgn debugging library
to read and interpret data read from /proc/kcore.

Before the patch:
-----
$ time sudo sdb -e 'dbuf | head 3000 | wc'
(unsigned long)3000

real	0m22.446s
user	0m2.321s
sys	0m20.690s
-----

With the patch:
-----
$ time sudo sdb -e 'dbuf | head 3000 | wc'
(unsigned long)3000

real	0m2.104s
user	0m2.043s
sys	0m0.921s
-----

Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
---
Changed in v2:

- Use __find_vmap_area() for initial lookup but keep iteration via
  va->list.

 mm/vmalloc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 49ab9b6c001d..eb133d000394 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2860,7 +2860,10 @@ long vread(char *buf, char *addr, unsigned long count)
 		count = -(unsigned long) addr;
 
 	spin_lock(&vmap_area_lock);
-	list_for_each_entry(va, &vmap_area_list, list) {
+	va = __find_vmap_area((unsigned long)addr);
+	if (!va)
+		goto finished;
+	list_for_each_entry_from(va, &vmap_area_list, list) {
 		if (!count)
 			break;
 
-- 
2.17.1

Re: [PATCH v2] mm/vmalloc: use rb_tree instead of list for vread() lookups

[Uladzislau Rezki]

> vread() has been linearly searching vmap_area_list for looking up
> vmalloc areas to read from. These same areas are also tracked by
> a rb_tree (vmap_area_root) which offers logarithmic lookup.
> 
> This patch modifies vread() to use the rb_tree structure instead
> of the list and the speedup for heavy /proc/kcore readers can
> be pretty significant. Below are the wall clock measurements of
> a Python application that leverages the drgn debugging library
> to read and interpret data read from /proc/kcore.
> 
> Before the patch:
> -----
> $ time sudo sdb -e 'dbuf | head 3000 | wc'
> (unsigned long)3000
> 
> real	0m22.446s
> user	0m2.321s
> sys	0m20.690s
> -----
> 
> With the patch:
> -----
> $ time sudo sdb -e 'dbuf | head 3000 | wc'
> (unsigned long)3000
> 
> real	0m2.104s
> user	0m2.043s
> sys	0m0.921s
> -----
> 
> Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
> ---
> Changed in v2:
> 
> - Use __find_vmap_area() for initial lookup but keep iteration via
>   va->list.
> 
>  mm/vmalloc.c | 5 ++++-
>  1 file changed, 4 insertions(+), 1 deletion(-)
> 
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 49ab9b6c001d..eb133d000394 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -2860,7 +2860,10 @@ long vread(char *buf, char *addr, unsigned long count)
>  		count = -(unsigned long) addr;
>  
>  	spin_lock(&vmap_area_lock);
> -	list_for_each_entry(va, &vmap_area_list, list) {
> +	va = __find_vmap_area((unsigned long)addr);
> +	if (!va)
> +		goto finished;
> +	list_for_each_entry_from(va, &vmap_area_list, list) {
>  		if (!count)
>  			break;
>  
> -- 
> 2.17.1
> 
Much better :)

Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>

--
Vlad Rezki