diff mbox series

[net] devlink: use kvzalloc() to allocate devlink instance resources

Message ID 20240321123611.380158-1-wenjian1@xiaomi.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series [net] devlink: use kvzalloc() to allocate devlink instance resources | expand

Checks

Context Check Description
netdev/series_format success Single patches do not need cover letters
netdev/tree_selection success Clearly marked for net
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present fail Series targets non-next tree, but doesn't contain any Fixes tags
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 941 this patch: 941
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 3 maintainers not CCed: pabeni@redhat.com jiri@resnulli.us kuba@kernel.org
netdev/build_clang success Errors and warnings before: 957 this patch: 957
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 958 this patch: 958
netdev/checkpatch warning WARNING: From:/Signed-off-by: email address mismatch: 'From: Jian Wen <wenjianhn@gmail.com>' != 'Signed-off-by: Jian Wen <wenjian1@xiaomi.com>'
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-03-21--15-00 (tests: 909)

Commit Message

Jian Wen March 21, 2024, 12:36 p.m. UTC 
During live migration of a virtual machine, the SR-IOV VF need to be
re-registered. It may fail when the memory is badly fragmented.

The related log is as follows.

Mar  1 18:54:12  kernel: hv_netvsc 6045bdaa-c0d1-6045-bdaa-c0d16045bdaa eth0: VF slot 1 added
...
Mar  1 18:54:13  kernel: kworker/0:0: page allocation failure: order:7, mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null),cpuset=/,mems_allowed=0
Mar  1 18:54:13  kernel: CPU: 0 PID: 24006 Comm: kworker/0:0 Tainted: G            E     5.4...x86_64 #1
Mar  1 18:54:13  kernel: Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008  12/07/2018
Mar  1 18:54:13  kernel: Workqueue: events work_for_cpu_fn
Mar  1 18:54:13  kernel: Call Trace:
Mar  1 18:54:13  kernel: dump_stack+0x8b/0xc8
Mar  1 18:54:13  kernel: warn_alloc+0xff/0x170
Mar  1 18:54:13  kernel: __alloc_pages_slowpath+0x92c/0xb2b
Mar  1 18:54:13  kernel: ? get_page_from_freelist+0x1d4/0x1140
Mar  1 18:54:13  kernel: __alloc_pages_nodemask+0x2f9/0x320
Mar  1 18:54:13  kernel: alloc_pages_current+0x6a/0xb0
Mar  1 18:54:13  kernel: kmalloc_order+0x1e/0x70
Mar  1 18:54:13  kernel: kmalloc_order_trace+0x26/0xb0
Mar  1 18:54:13  kernel: ? __switch_to_asm+0x34/0x70
Mar  1 18:54:13  kernel: __kmalloc+0x276/0x280
Mar  1 18:54:13  kernel: ? _raw_spin_unlock_irqrestore+0x1e/0x40
Mar  1 18:54:13  kernel: devlink_alloc+0x29/0x110
Mar  1 18:54:13  kernel: mlx5_devlink_alloc+0x1a/0x20 [mlx5_core]
Mar  1 18:54:13  kernel: init_one+0x1d/0x650 [mlx5_core]
Mar  1 18:54:13  kernel: local_pci_probe+0x46/0x90
Mar  1 18:54:13  kernel: work_for_cpu_fn+0x1a/0x30
Mar  1 18:54:13  kernel: process_one_work+0x16d/0x390
Mar  1 18:54:13  kernel: worker_thread+0x1d3/0x3f0
Mar  1 18:54:13  kernel: kthread+0x105/0x140
Mar  1 18:54:13  kernel: ? max_active_store+0x80/0x80
Mar  1 18:54:13  kernel: ? kthread_bind+0x20/0x20
Mar  1 18:54:13  kernel: ret_from_fork+0x3a/0x50

Signed-off-by: Jian Wen <wenjian1@xiaomi.com>
---
 net/devlink/core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

Comments

Jiri Pirko March 21, 2024, 12:59 p.m. UTC | #1 
Thu, Mar 21, 2024 at 01:36:11PM CET, wenjianhn@gmail.com wrote:
>During live migration of a virtual machine, the SR-IOV VF need to be
>re-registered. It may fail when the memory is badly fragmented.
>
>The related log is as follows.
>
>Mar  1 18:54:12  kernel: hv_netvsc 6045bdaa-c0d1-6045-bdaa-c0d16045bdaa eth0: VF slot 1 added
>...
>Mar  1 18:54:13  kernel: kworker/0:0: page allocation failure: order:7, mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null),cpuset=/,mems_allowed=0
>Mar  1 18:54:13  kernel: CPU: 0 PID: 24006 Comm: kworker/0:0 Tainted: G            E     5.4...x86_64 #1
>Mar  1 18:54:13  kernel: Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008  12/07/2018
>Mar  1 18:54:13  kernel: Workqueue: events work_for_cpu_fn
>Mar  1 18:54:13  kernel: Call Trace:
>Mar  1 18:54:13  kernel: dump_stack+0x8b/0xc8
>Mar  1 18:54:13  kernel: warn_alloc+0xff/0x170
>Mar  1 18:54:13  kernel: __alloc_pages_slowpath+0x92c/0xb2b
>Mar  1 18:54:13  kernel: ? get_page_from_freelist+0x1d4/0x1140
>Mar  1 18:54:13  kernel: __alloc_pages_nodemask+0x2f9/0x320
>Mar  1 18:54:13  kernel: alloc_pages_current+0x6a/0xb0
>Mar  1 18:54:13  kernel: kmalloc_order+0x1e/0x70
>Mar  1 18:54:13  kernel: kmalloc_order_trace+0x26/0xb0
>Mar  1 18:54:13  kernel: ? __switch_to_asm+0x34/0x70
>Mar  1 18:54:13  kernel: __kmalloc+0x276/0x280
>Mar  1 18:54:13  kernel: ? _raw_spin_unlock_irqrestore+0x1e/0x40
>Mar  1 18:54:13  kernel: devlink_alloc+0x29/0x110
>Mar  1 18:54:13  kernel: mlx5_devlink_alloc+0x1a/0x20 [mlx5_core]
>Mar  1 18:54:13  kernel: init_one+0x1d/0x650 [mlx5_core]
>Mar  1 18:54:13  kernel: local_pci_probe+0x46/0x90
>Mar  1 18:54:13  kernel: work_for_cpu_fn+0x1a/0x30
>Mar  1 18:54:13  kernel: process_one_work+0x16d/0x390
>Mar  1 18:54:13  kernel: worker_thread+0x1d3/0x3f0
>Mar  1 18:54:13  kernel: kthread+0x105/0x140
>Mar  1 18:54:13  kernel: ? max_active_store+0x80/0x80
>Mar  1 18:54:13  kernel: ? kthread_bind+0x20/0x20
>Mar  1 18:54:13  kernel: ret_from_fork+0x3a/0x50
>
>Signed-off-by: Jian Wen <wenjian1@xiaomi.com>

This is not fixing a bug introduced by specific commit, is it? Or is
this a regression? In that case, you need to add "Fixes" tag.
Idk, looks more like net-next material. The patch itself looks okay to
me.


>---
> net/devlink/core.c | 6 +++---
> 1 file changed, 3 insertions(+), 3 deletions(-)
>
>diff --git a/net/devlink/core.c b/net/devlink/core.c
>index 7f0b093208d7..ffbac42918d7 100644
>--- a/net/devlink/core.c
>+++ b/net/devlink/core.c
>@@ -314,7 +314,7 @@ static void devlink_release(struct work_struct *work)
> 	mutex_destroy(&devlink->lock);
> 	lockdep_unregister_key(&devlink->lock_key);
> 	put_device(devlink->dev);
>-	kfree(devlink);
>+	kvfree(devlink);
> }
> 
> void devlink_put(struct devlink *devlink)
>@@ -420,7 +420,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
> 	if (!devlink_reload_actions_valid(ops))
> 		return NULL;
> 
>-	devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
>+	devlink = kvzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
> 	if (!devlink)
> 		return NULL;
> 
>@@ -455,7 +455,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
> 	return devlink;
> 
> err_xa_alloc:
>-	kfree(devlink);
>+	kvfree(devlink);
> 	return NULL;
> }
> EXPORT_SYMBOL_GPL(devlink_alloc_ns);
>-- 
>2.34.1
>
>
Jian Wen March 22, 2024, 1:59 a.m. UTC | #2 
On Thu, Mar 21, 2024 at 8:59 PM Jiri Pirko <jiri@resnulli.us> wrote:
>
> Thu, Mar 21, 2024 at 01:36:11PM CET, wenjianhn@gmail.com wrote:
> >During live migration of a virtual machine, the SR-IOV VF need to be
> >re-registered. It may fail when the memory is badly fragmented.
> >
> >The related log is as follows.
> >
> >Mar  1 18:54:12  kernel: hv_netvsc 6045bdaa-c0d1-6045-bdaa-c0d16045bdaa eth0: VF slot 1 added
> >...
> >Mar  1 18:54:13  kernel: kworker/0:0: page allocation failure: order:7, mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null),cpuset=/,mems_allowed=0
> >Mar  1 18:54:13  kernel: CPU: 0 PID: 24006 Comm: kworker/0:0 Tainted: G            E     5.4...x86_64 #1
> >Mar  1 18:54:13  kernel: Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008  12/07/2018
> >Mar  1 18:54:13  kernel: Workqueue: events work_for_cpu_fn
> >Mar  1 18:54:13  kernel: Call Trace:
> >Mar  1 18:54:13  kernel: dump_stack+0x8b/0xc8
> >Mar  1 18:54:13  kernel: warn_alloc+0xff/0x170
> >Mar  1 18:54:13  kernel: __alloc_pages_slowpath+0x92c/0xb2b
> >Mar  1 18:54:13  kernel: ? get_page_from_freelist+0x1d4/0x1140
> >Mar  1 18:54:13  kernel: __alloc_pages_nodemask+0x2f9/0x320
> >Mar  1 18:54:13  kernel: alloc_pages_current+0x6a/0xb0
> >Mar  1 18:54:13  kernel: kmalloc_order+0x1e/0x70
> >Mar  1 18:54:13  kernel: kmalloc_order_trace+0x26/0xb0
> >Mar  1 18:54:13  kernel: ? __switch_to_asm+0x34/0x70
> >Mar  1 18:54:13  kernel: __kmalloc+0x276/0x280
> >Mar  1 18:54:13  kernel: ? _raw_spin_unlock_irqrestore+0x1e/0x40
> >Mar  1 18:54:13  kernel: devlink_alloc+0x29/0x110
> >Mar  1 18:54:13  kernel: mlx5_devlink_alloc+0x1a/0x20 [mlx5_core]
> >Mar  1 18:54:13  kernel: init_one+0x1d/0x650 [mlx5_core]
> >Mar  1 18:54:13  kernel: local_pci_probe+0x46/0x90
> >Mar  1 18:54:13  kernel: work_for_cpu_fn+0x1a/0x30
> >Mar  1 18:54:13  kernel: process_one_work+0x16d/0x390
> >Mar  1 18:54:13  kernel: worker_thread+0x1d3/0x3f0
> >Mar  1 18:54:13  kernel: kthread+0x105/0x140
> >Mar  1 18:54:13  kernel: ? max_active_store+0x80/0x80
> >Mar  1 18:54:13  kernel: ? kthread_bind+0x20/0x20
> >Mar  1 18:54:13  kernel: ret_from_fork+0x3a/0x50
> >
> >Signed-off-by: Jian Wen <wenjian1@xiaomi.com>
>
> This is not fixing a bug introduced by specific commit, is it? Or is
> this a regression? In that case, you need to add "Fixes" tag.
> Idk, looks more like net-next material. The patch itself looks okay to
> me.
A patch against net-next has been sent. Please review.
Thanks.
>
>
> >---
> > net/devlink/core.c | 6 +++---
> > 1 file changed, 3 insertions(+), 3 deletions(-)
> >
> >diff --git a/net/devlink/core.c b/net/devlink/core.c
> >index 7f0b093208d7..ffbac42918d7 100644
> >--- a/net/devlink/core.c
> >+++ b/net/devlink/core.c
> >@@ -314,7 +314,7 @@ static void devlink_release(struct work_struct *work)
> >       mutex_destroy(&devlink->lock);
> >       lockdep_unregister_key(&devlink->lock_key);
> >       put_device(devlink->dev);
> >-      kfree(devlink);
> >+      kvfree(devlink);
> > }
> >
> > void devlink_put(struct devlink *devlink)
> >@@ -420,7 +420,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
> >       if (!devlink_reload_actions_valid(ops))
> >               return NULL;
> >
> >-      devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
> >+      devlink = kvzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
> >       if (!devlink)
> >               return NULL;
> >
> >@@ -455,7 +455,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
> >       return devlink;
> >
> > err_xa_alloc:
> >-      kfree(devlink);
> >+      kvfree(devlink);
> >       return NULL;
> > }
> > EXPORT_SYMBOL_GPL(devlink_alloc_ns);
> >--
> >2.34.1
> >
> >
Alexander Lobakin March 22, 2024, 11:44 a.m. UTC | #3 
From: Jian Wen <wenjianhn@gmail.com>
Date: Thu, 21 Mar 2024 20:36:11 +0800

> During live migration of a virtual machine, the SR-IOV VF need to be
> re-registered. It may fail when the memory is badly fragmented.
> 
> The related log is as follows.
> 
> Mar  1 18:54:12  kernel: hv_netvsc 6045bdaa-c0d1-6045-bdaa-c0d16045bdaa eth0: VF slot 1 added
> ...
> Mar  1 18:54:13  kernel: kworker/0:0: page allocation failure: order:7, mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null),cpuset=/,mems_allowed=0
> Mar  1 18:54:13  kernel: CPU: 0 PID: 24006 Comm: kworker/0:0 Tainted: G            E     5.4...x86_64 #1
> Mar  1 18:54:13  kernel: Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008  12/07/2018
> Mar  1 18:54:13  kernel: Workqueue: events work_for_cpu_fn
> Mar  1 18:54:13  kernel: Call Trace:
> Mar  1 18:54:13  kernel: dump_stack+0x8b/0xc8
> Mar  1 18:54:13  kernel: warn_alloc+0xff/0x170
> Mar  1 18:54:13  kernel: __alloc_pages_slowpath+0x92c/0xb2b
> Mar  1 18:54:13  kernel: ? get_page_from_freelist+0x1d4/0x1140
> Mar  1 18:54:13  kernel: __alloc_pages_nodemask+0x2f9/0x320
> Mar  1 18:54:13  kernel: alloc_pages_current+0x6a/0xb0
> Mar  1 18:54:13  kernel: kmalloc_order+0x1e/0x70
> Mar  1 18:54:13  kernel: kmalloc_order_trace+0x26/0xb0
> Mar  1 18:54:13  kernel: ? __switch_to_asm+0x34/0x70
> Mar  1 18:54:13  kernel: __kmalloc+0x276/0x280
> Mar  1 18:54:13  kernel: ? _raw_spin_unlock_irqrestore+0x1e/0x40
> Mar  1 18:54:13  kernel: devlink_alloc+0x29/0x110
> Mar  1 18:54:13  kernel: mlx5_devlink_alloc+0x1a/0x20 [mlx5_core]
> Mar  1 18:54:13  kernel: init_one+0x1d/0x650 [mlx5_core]
> Mar  1 18:54:13  kernel: local_pci_probe+0x46/0x90
> Mar  1 18:54:13  kernel: work_for_cpu_fn+0x1a/0x30
> Mar  1 18:54:13  kernel: process_one_work+0x16d/0x390
> Mar  1 18:54:13  kernel: worker_thread+0x1d3/0x3f0
> Mar  1 18:54:13  kernel: kthread+0x105/0x140
> Mar  1 18:54:13  kernel: ? max_active_store+0x80/0x80
> Mar  1 18:54:13  kernel: ? kthread_bind+0x20/0x20
> Mar  1 18:54:13  kernel: ret_from_fork+0x3a/0x50
> 
> Signed-off-by: Jian Wen <wenjian1@xiaomi.com>
> ---
>  net/devlink/core.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/net/devlink/core.c b/net/devlink/core.c
> index 7f0b093208d7..ffbac42918d7 100644
> --- a/net/devlink/core.c
> +++ b/net/devlink/core.c
> @@ -314,7 +314,7 @@ static void devlink_release(struct work_struct *work)
>  	mutex_destroy(&devlink->lock);
>  	lockdep_unregister_key(&devlink->lock_key);
>  	put_device(devlink->dev);
> -	kfree(devlink);
> +	kvfree(devlink);
>  }
>  
>  void devlink_put(struct devlink *devlink)
> @@ -420,7 +420,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
>  	if (!devlink_reload_actions_valid(ops))
>  		return NULL;
>  
> -	devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
> +	devlink = kvzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);

struct_size(devlink, priv, priv_size)?

>  	if (!devlink)
>  		return NULL;
>  
> @@ -455,7 +455,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
>  	return devlink;
>  
>  err_xa_alloc:
> -	kfree(devlink);
> +	kvfree(devlink);
>  	return NULL;
>  }
>  EXPORT_SYMBOL_GPL(devlink_alloc_ns);

Thanks,
Olek
diff mbox series

Patch

diff --git a/net/devlink/core.c b/net/devlink/core.c
index 7f0b093208d7..ffbac42918d7 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -314,7 +314,7 @@  static void devlink_release(struct work_struct *work)
 	mutex_destroy(&devlink->lock);
 	lockdep_unregister_key(&devlink->lock_key);
 	put_device(devlink->dev);
-	kfree(devlink);
+	kvfree(devlink);
 }
 
 void devlink_put(struct devlink *devlink)
@@ -420,7 +420,7 @@  struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
 	if (!devlink_reload_actions_valid(ops))
 		return NULL;
 
-	devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
+	devlink = kvzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
 	if (!devlink)
 		return NULL;
 
@@ -455,7 +455,7 @@  struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
 	return devlink;
 
 err_xa_alloc:
-	kfree(devlink);
+	kvfree(devlink);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(devlink_alloc_ns);