kmemleak warning in efifb_probe

Started by Alexandra N. Kossovsky on Jul 21, 2013 · 7 messages from 5 authors · Last reply Aug 30, 2013

open the first message on its own page

  1. [PATCH] Release efifb's colormap in efifb_destroy()
    Related patches

Alexandra N. Kossovsky

Message details and related content
Open message details and related content
Hello.

I am running linux-3.10.0 with kmemleak and see following warnings
in /sys/kernel/debug/kmemleak:

unreferenced object 0xffff880216fcfe00 (size 512):
  comm "swapper/0", pid 1, jiffies 4294895429 (age 1415.320s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 aa aa aa aa aa aa aa aa  ................
    55 55 55 55 55 55 55 55 ff ff ff ff ff ff ff ff  UUUUUUUU........
  backtrace:
    [<ffffffff813e415c>] kmemleak_alloc+0x21/0x3e
    [<ffffffff8111c17f>] kmemleak_alloc_recursive.constprop.57+0x16/0x18
    [<ffffffff8111e63b>] __kmalloc+0xf9/0x144
    [<ffffffff8123d9cf>] fb_alloc_cmap_gfp+0x47/0xe1
    [<ffffffff8123da77>] fb_alloc_cmap+0xe/0x10
    [<ffffffff81aff40a>] efifb_probe+0x3e9/0x48f
    [<ffffffff812c566f>] platform_drv_probe+0x34/0x5e
    [<ffffffff812c3e6d>] driver_probe_device+0x98/0x1b4
    [<ffffffff812c3fd7>] __driver_attach+0x4e/0x6f
    [<ffffffff812c25bf>] bus_for_each_dev+0x57/0x8a
    [<ffffffff812c3984>] driver_attach+0x19/0x1b
    [<ffffffff812c362b>] bus_add_driver+0xde/0x201
    [<ffffffff812c453f>] driver_register+0x8c/0x110
    [<ffffffff812c510d>] platform_driver_register+0x41/0x43
    [<ffffffff812c5127>] platform_driver_probe+0x18/0x8a
    [<ffffffff81aff002>] efifb_init+0x276/0x295
unreferenced object 0xffff880205e90e00 (size 512):
  comm "swapper/0", pid 1, jiffies 4294895429 (age 1415.320s)
  hex dump (first 32 bytes):
    00 00 00 00 aa aa aa aa 00 00 00 00 55 55 aa aa  ............UU..
    55 55 55 55 ff ff ff ff 55 55 55 55 ff ff ff ff  UUUU....UUUU....
  backtrace:
    [<ffffffff813e415c>] kmemleak_alloc+0x21/0x3e
    [<ffffffff8111c17f>] kmemleak_alloc_recursive.constprop.57+0x16/0x18
    [<ffffffff8111e63b>] __kmalloc+0xf9/0x144
    [<ffffffff8123d9ea>] fb_alloc_cmap_gfp+0x62/0xe1
    [<ffffffff8123da77>] fb_alloc_cmap+0xe/0x10
    [<ffffffff81aff40a>] efifb_probe+0x3e9/0x48f
    [<ffffffff812c566f>] platform_drv_probe+0x34/0x5e

61 more lines

Catalin Marinas replied to Alexandra N. Kossovsky

Message details and related content
Open message details and related content
On 21 July 2013 16:11, Alexandra N. Kossovsky
[off-list ref] wrote:
I am running linux-3.10.0 with kmemleak and see following warnings
in /sys/kernel/debug/kmemleak:

unreferenced object 0xffff880216fcfe00 (size 512):
  comm "swapper/0", pid 1, jiffies 4294895429 (age 1415.320s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 aa aa aa aa aa aa aa aa  ................
    55 55 55 55 55 55 55 55 ff ff ff ff ff ff ff ff  UUUUUUUU........
  backtrace:
    [<ffffffff813e415c>] kmemleak_alloc+0x21/0x3e
    [<ffffffff8111c17f>] kmemleak_alloc_recursive.constprop.57+0x16/0x18
    [<ffffffff8111e63b>] __kmalloc+0xf9/0x144
    [<ffffffff8123d9cf>] fb_alloc_cmap_gfp+0x47/0xe1
    [<ffffffff8123da77>] fb_alloc_cmap+0xe/0x10
    [<ffffffff81aff40a>] efifb_probe+0x3e9/0x48f
    [<ffffffff812c566f>] platform_drv_probe+0x34/0x5e
    [<ffffffff812c3e6d>] driver_probe_device+0x98/0x1b4
    [<ffffffff812c3fd7>] __driver_attach+0x4e/0x6f
    [<ffffffff812c25bf>] bus_for_each_dev+0x57/0x8a
    [<ffffffff812c3984>] driver_attach+0x19/0x1b
    [<ffffffff812c362b>] bus_add_driver+0xde/0x201
    [<ffffffff812c453f>] driver_register+0x8c/0x110
    [<ffffffff812c510d>] platform_driver_register+0x41/0x43
    [<ffffffff812c5127>] platform_driver_probe+0x18/0x8a
    [<ffffffff81aff002>] efifb_init+0x276/0x295
Does the efifb driver has any way to deallocate the cmap? I don't see
any explicit call to fb_dealloc_cmap() apart from the error handling.
My theory is that the efifb driver gets deregistered via
do_remove_conflicting_framebuffers(). I'm not familiar with this code,
just commenting from a kmemleak perspective.

-- 
Catalin

[PATCH] Release efifb's colormap in efifb_destroy()

Peter Jones replied to Catalin Marinas

Message details and related content
Open message details and related content
This was found by Alexandra Kossovsky, who noted this traceback from
kmemleak:

unreferenced object 0xffff880216fcfe00 (size 512):
  comm "swapper/0", pid 1, jiffies 4294895429 (age 1415.320s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 aa aa aa aa aa aa aa aa  ................
    55 55 55 55 55 55 55 55 ff ff ff ff ff ff ff ff  UUUUUUUU........
  backtrace:
    [<ffffffff813e415c>] kmemleak_alloc+0x21/0x3e
    [<ffffffff8111c17f>]
    kmemleak_alloc_recursive.constprop.57+0x16/0x18
    [<ffffffff8111e63b>] __kmalloc+0xf9/0x144
    [<ffffffff8123d9cf>] fb_alloc_cmap_gfp+0x47/0xe1
    [<ffffffff8123da77>] fb_alloc_cmap+0xe/0x10
    [<ffffffff81aff40a>] efifb_probe+0x3e9/0x48f
    [<ffffffff812c566f>] platform_drv_probe+0x34/0x5e
    [<ffffffff812c3e6d>] driver_probe_device+0x98/0x1b4
    [<ffffffff812c3fd7>] __driver_attach+0x4e/0x6f
    [<ffffffff812c25bf>] bus_for_each_dev+0x57/0x8a
    [<ffffffff812c3984>] driver_attach+0x19/0x1b
    [<ffffffff812c362b>] bus_add_driver+0xde/0x201
    [<ffffffff812c453f>] driver_register+0x8c/0x110
    [<ffffffff812c510d>] platform_driver_register+0x41/0x43
    [<ffffffff812c5127>] platform_driver_probe+0x18/0x8a
    [<ffffffff81aff002>] efifb_init+0x276/0x295
---
 drivers/video/efifb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
index 390b61b..1f3eab3 100644
--- a/drivers/video/efifb.c
+++ b/drivers/video/efifb.c
@@ -289,6 +289,7 @@ static void efifb_destroy(struct fb_info *info)
 	if (request_mem_succeeded)
 		release_mem_region(info->apertures->ranges[0].base,
 				   info->apertures->ranges[0].size);
+	fb_dealloc_cmap(&info->cmap);
 	framebuffer_release(info);
 }
 
-- 
1.8.3.1

Peter Jones replied to Catalin Marinas

Message details and related content
Open message details and related content
On Thu, Jul 25, 2013 at 01:18:31PM +0100, Catalin Marinas wrote:
On 21 July 2013 16:11, Alexandra N. Kossovsky
[off-list ref] wrote:
quoted
I am running linux-3.10.0 with kmemleak and see following warnings
in /sys/kernel/debug/kmemleak:

unreferenced object 0xffff880216fcfe00 (size 512):
  comm "swapper/0", pid 1, jiffies 4294895429 (age 1415.320s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 aa aa aa aa aa aa aa aa  ................
    55 55 55 55 55 55 55 55 ff ff ff ff ff ff ff ff  UUUUUUUU........
  backtrace:
    [<ffffffff813e415c>] kmemleak_alloc+0x21/0x3e
    [<ffffffff8111c17f>] kmemleak_alloc_recursive.constprop.57+0x16/0x18
    [<ffffffff8111e63b>] __kmalloc+0xf9/0x144
    [<ffffffff8123d9cf>] fb_alloc_cmap_gfp+0x47/0xe1
    [<ffffffff8123da77>] fb_alloc_cmap+0xe/0x10
    [<ffffffff81aff40a>] efifb_probe+0x3e9/0x48f
    [<ffffffff812c566f>] platform_drv_probe+0x34/0x5e
    [<ffffffff812c3e6d>] driver_probe_device+0x98/0x1b4
    [<ffffffff812c3fd7>] __driver_attach+0x4e/0x6f
    [<ffffffff812c25bf>] bus_for_each_dev+0x57/0x8a
    [<ffffffff812c3984>] driver_attach+0x19/0x1b
    [<ffffffff812c362b>] bus_add_driver+0xde/0x201
    [<ffffffff812c453f>] driver_register+0x8c/0x110
    [<ffffffff812c510d>] platform_driver_register+0x41/0x43
    [<ffffffff812c5127>] platform_driver_probe+0x18/0x8a
    [<ffffffff81aff002>] efifb_init+0x276/0x295
Does the efifb driver has any way to deallocate the cmap? I don't see
any explicit call to fb_dealloc_cmap() apart from the error handling.
My theory is that the efifb driver gets deregistered via
do_remove_conflicting_framebuffers(). I'm not familiar with this code,
just commenting from a kmemleak perspective.
You're right, that's the typical deregister path.  I'll follow up with a
patch to test.

-- 
        Peter

Re: [PATCH] Release efifb's colormap in efifb_destroy()

David Herrmann replied to Peter Jones

Message details and related content
Open message details and related content
Hi

On Thu, Jul 25, 2013 at 5:48 PM, Peter Jones [off-list ref] wrote:
This was found by Alexandra Kossovsky, who noted this traceback from
kmemleak:
quoted
unreferenced object 0xffff880216fcfe00 (size 512):
  comm "swapper/0", pid 1, jiffies 4294895429 (age 1415.320s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 aa aa aa aa aa aa aa aa  ................
    55 55 55 55 55 55 55 55 ff ff ff ff ff ff ff ff  UUUUUUUU........
  backtrace:
    [<ffffffff813e415c>] kmemleak_alloc+0x21/0x3e
    [<ffffffff8111c17f>]
    kmemleak_alloc_recursive.constprop.57+0x16/0x18
    [<ffffffff8111e63b>] __kmalloc+0xf9/0x144
    [<ffffffff8123d9cf>] fb_alloc_cmap_gfp+0x47/0xe1
    [<ffffffff8123da77>] fb_alloc_cmap+0xe/0x10
    [<ffffffff81aff40a>] efifb_probe+0x3e9/0x48f
    [<ffffffff812c566f>] platform_drv_probe+0x34/0x5e
    [<ffffffff812c3e6d>] driver_probe_device+0x98/0x1b4
    [<ffffffff812c3fd7>] __driver_attach+0x4e/0x6f
    [<ffffffff812c25bf>] bus_for_each_dev+0x57/0x8a
    [<ffffffff812c3984>] driver_attach+0x19/0x1b
    [<ffffffff812c362b>] bus_add_driver+0xde/0x201
    [<ffffffff812c453f>] driver_register+0x8c/0x110
    [<ffffffff812c510d>] platform_driver_register+0x41/0x43
    [<ffffffff812c5127>] platform_driver_probe+0x18/0x8a
    [<ffffffff81aff002>] efifb_init+0x276/0x295
(CC'ing fbdev maintainers)

Your signed-off-by is missing. Apart from that:
Reviewed-by: David Herrmann <redacted>

Regards
David
quoted hunk
---
 drivers/video/efifb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
index 390b61b..1f3eab3 100644
--- a/drivers/video/efifb.c
+++ b/drivers/video/efifb.c
@@ -289,6 +289,7 @@ static void efifb_destroy(struct fb_info *info)
        if (request_mem_succeeded)
                release_mem_region(info->apertures->ranges[0].base,
                                   info->apertures->ranges[0].size);
+       fb_dealloc_cmap(&info->cmap);
        framebuffer_release(info);
 }

--
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-fbdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] Release efifb's colormap in efifb_destroy()

Peter Jones replied to David Herrmann

Message details and related content
Open message details and related content
On Fri, Aug 16, 2013 at 03:51:34PM +0200, David Herrmann wrote:
Hi

On Thu, Jul 25, 2013 at 5:48 PM, Peter Jones [off-list ref] wrote:
quoted
This was found by Alexandra Kossovsky, who noted this traceback from
kmemleak:
quoted
unreferenced object 0xffff880216fcfe00 (size 512):
  comm "swapper/0", pid 1, jiffies 4294895429 (age 1415.320s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 aa aa aa aa aa aa aa aa  ................
    55 55 55 55 55 55 55 55 ff ff ff ff ff ff ff ff  UUUUUUUU........
  backtrace:
    [<ffffffff813e415c>] kmemleak_alloc+0x21/0x3e
    [<ffffffff8111c17f>]
    kmemleak_alloc_recursive.constprop.57+0x16/0x18
    [<ffffffff8111e63b>] __kmalloc+0xf9/0x144
    [<ffffffff8123d9cf>] fb_alloc_cmap_gfp+0x47/0xe1
    [<ffffffff8123da77>] fb_alloc_cmap+0xe/0x10
    [<ffffffff81aff40a>] efifb_probe+0x3e9/0x48f
    [<ffffffff812c566f>] platform_drv_probe+0x34/0x5e
    [<ffffffff812c3e6d>] driver_probe_device+0x98/0x1b4
    [<ffffffff812c3fd7>] __driver_attach+0x4e/0x6f
    [<ffffffff812c25bf>] bus_for_each_dev+0x57/0x8a
    [<ffffffff812c3984>] driver_attach+0x19/0x1b
    [<ffffffff812c362b>] bus_add_driver+0xde/0x201
    [<ffffffff812c453f>] driver_register+0x8c/0x110
    [<ffffffff812c510d>] platform_driver_register+0x41/0x43
    [<ffffffff812c5127>] platform_driver_probe+0x18/0x8a
    [<ffffffff81aff002>] efifb_init+0x276/0x295
(CC'ing fbdev maintainers)

Your signed-off-by is missing. Apart from that:
Reviewed-by: David Herrmann <redacted>
Indeed it is.  With that in mind:

Signed-off-by: Peter Jones <pjones@redhat.com>

Regards
David
quoted
---
 drivers/video/efifb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
index 390b61b..1f3eab3 100644
--- a/drivers/video/efifb.c
+++ b/drivers/video/efifb.c
@@ -289,6 +289,7 @@ static void efifb_destroy(struct fb_info *info)
        if (request_mem_succeeded)
                release_mem_region(info->apertures->ranges[0].base,
                                   info->apertures->ranges[0].size);
+       fb_dealloc_cmap(&info->cmap);
        framebuffer_release(info);
 }

--
1.8.3.1

--
-- 
        Peter

Re: [PATCH] Release efifb's colormap in efifb_destroy()

Tomi Valkeinen replied to Peter Jones

Message details and related content
Open message details and related content
On 25/07/13 18:48, Peter Jones wrote:
quoted hunk
This was found by Alexandra Kossovsky, who noted this traceback from
kmemleak:
quoted
unreferenced object 0xffff880216fcfe00 (size 512):
  comm "swapper/0", pid 1, jiffies 4294895429 (age 1415.320s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 aa aa aa aa aa aa aa aa  ................
    55 55 55 55 55 55 55 55 ff ff ff ff ff ff ff ff  UUUUUUUU........
  backtrace:
    [<ffffffff813e415c>] kmemleak_alloc+0x21/0x3e
    [<ffffffff8111c17f>]
    kmemleak_alloc_recursive.constprop.57+0x16/0x18
    [<ffffffff8111e63b>] __kmalloc+0xf9/0x144
    [<ffffffff8123d9cf>] fb_alloc_cmap_gfp+0x47/0xe1
    [<ffffffff8123da77>] fb_alloc_cmap+0xe/0x10
    [<ffffffff81aff40a>] efifb_probe+0x3e9/0x48f
    [<ffffffff812c566f>] platform_drv_probe+0x34/0x5e
    [<ffffffff812c3e6d>] driver_probe_device+0x98/0x1b4
    [<ffffffff812c3fd7>] __driver_attach+0x4e/0x6f
    [<ffffffff812c25bf>] bus_for_each_dev+0x57/0x8a
    [<ffffffff812c3984>] driver_attach+0x19/0x1b
    [<ffffffff812c362b>] bus_add_driver+0xde/0x201
    [<ffffffff812c453f>] driver_register+0x8c/0x110
    [<ffffffff812c510d>] platform_driver_register+0x41/0x43
    [<ffffffff812c5127>] platform_driver_probe+0x18/0x8a
    [<ffffffff81aff002>] efifb_init+0x276/0x295
---
 drivers/video/efifb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
index 390b61b..1f3eab3 100644
--- a/drivers/video/efifb.c
+++ b/drivers/video/efifb.c
@@ -289,6 +289,7 @@ static void efifb_destroy(struct fb_info *info)
 	if (request_mem_succeeded)
 		release_mem_region(info->apertures->ranges[0].base,
 				   info->apertures->ranges[0].size);
+	fb_dealloc_cmap(&info->cmap);
 	framebuffer_release(info);

2 more quoted lines

Thanks, queued for 3.12.

 Tomi
Keyboard shortcuts
hback out one level
jnext message in thread / next series-diff position
kprevious message in thread / previous series-diff position
ldrill in
Escclose help / fold thread tree
?toggle this help