[PATCH 1/1] cxl/edac: Fix potential memory leak issues

[PATCH 1/1] cxl/edac: Fix potential memory leak issues

[Li Ming]

In cxl_store_rec_gen_media() and cxl_store_rec_dram(), use kmemdup() to
duplicate a cxl gen_media/dram event to store the event in a xarray by
xa_store(). The cxl gen_media/dram event allocated by kmemdup() should
be freed in the case that the xa_store() fails.

Fixes: 0b5ccb0de1e2 ("cxl/edac: Support for finding memory operation attributes from the current boot")
Signed-off-by: Li Ming <ming.li@zohomail.com>
---
base-commit: 87b42c114cdda76c8ad3002f2096699ad5146cb3 cxl/fixes
---
 drivers/cxl/core/edac.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c
index 2cbc664e5d62..b4c5c23a45d4 100644
--- a/drivers/cxl/core/edac.c
+++ b/drivers/cxl/core/edac.c
@@ -1086,13 +1086,13 @@ static void cxl_del_overflow_old_recs(struct xarray *rec_xarray)
 int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt)
 {
 	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
-	struct cxl_event_gen_media *rec;
 	void *old_rec;
 
 	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
 		return 0;
 
-	rec = kmemdup(&evt->gen_media, sizeof(*rec), GFP_KERNEL);
+	struct cxl_event_gen_media *rec __free(kfree) =
+		kmemdup(&evt->gen_media, sizeof(*rec), GFP_KERNEL);
 	if (!rec)
 		return -ENOMEM;
 
@@ -1106,6 +1106,7 @@ int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt)
 
 	cxl_del_expired_gmedia_recs(&array_rec->rec_gen_media, rec);
 	cxl_del_overflow_old_recs(&array_rec->rec_gen_media);
+	retain_and_null_ptr(rec);
 
 	return 0;
 }
@@ -1114,13 +1115,13 @@ EXPORT_SYMBOL_NS_GPL(cxl_store_rec_gen_media, "CXL");
 int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)
 {
 	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
-	struct cxl_event_dram *rec;
 	void *old_rec;
 
 	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
 		return 0;
 
-	rec = kmemdup(&evt->dram, sizeof(*rec), GFP_KERNEL);
+	struct cxl_event_dram *rec __free(kfree) =
+		kmemdup(&evt->dram, sizeof(*rec), GFP_KERNEL);
 	if (!rec)
 		return -ENOMEM;
 
@@ -1134,6 +1135,7 @@ int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)
 
 	cxl_del_expired_dram_recs(&array_rec->rec_dram, rec);
 	cxl_del_overflow_old_recs(&array_rec->rec_dram);
+	retain_and_null_ptr(rec);
 
 	return 0;
 }
-- 
2.34.1

RE: [PATCH 1/1] cxl/edac: Fix potential memory leak issues

[Shiju Jose]

>-----Original Message-----
>From: Li Ming <ming.li@zohomail.com>
>Sent: 11 June 2025 04:36
>To: dave@stgolabs.net; Jonathan Cameron <jonathan.cameron@huawei.com>;
>dave.jiang@intel.com; alison.schofield@intel.com; vishal.l.verma@intel.com;
>ira.weiny@intel.com; dan.j.williams@intel.com; Shiju Jose
><shiju.jose@huawei.com>
>Cc: linux-cxl@vger.kernel.org; linux-kernel@vger.kernel.org; Li Ming
><ming.li@zohomail.com>
>Subject: [PATCH 1/1] cxl/edac: Fix potential memory leak issues
>
>In cxl_store_rec_gen_media() and cxl_store_rec_dram(), use kmemdup() to
>duplicate a cxl gen_media/dram event to store the event in a xarray by
>xa_store(). The cxl gen_media/dram event allocated by kmemdup() should be
>freed in the case that the xa_store() fails.
>
>Fixes: 0b5ccb0de1e2 ("cxl/edac: Support for finding memory operation
>attributes from the current boot")
>Signed-off-by: Li Ming <ming.li@zohomail.com>

Thanks Ming for fixing. 

Tested-by: Shiju Jose <shiju.jose@huawei.com> 
Reviewed-by: Shiju Jose <shiju.jose@huawei.com>

>---
>base-commit: 87b42c114cdda76c8ad3002f2096699ad5146cb3 cxl/fixes
>---
> drivers/cxl/core/edac.c | 10 ++++++----
> 1 file changed, 6 insertions(+), 4 deletions(-)
>
>diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c index
>2cbc664e5d62..b4c5c23a45d4 100644
>--- a/drivers/cxl/core/edac.c
>+++ b/drivers/cxl/core/edac.c
>@@ -1086,13 +1086,13 @@ static void cxl_del_overflow_old_recs(struct xarray
>*rec_xarray)  int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union
>cxl_event *evt)  {
> 	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
>-	struct cxl_event_gen_media *rec;
> 	void *old_rec;
>
> 	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
> 		return 0;
>
>-	rec = kmemdup(&evt->gen_media, sizeof(*rec), GFP_KERNEL);
>+	struct cxl_event_gen_media *rec __free(kfree) =
>+		kmemdup(&evt->gen_media, sizeof(*rec), GFP_KERNEL);
> 	if (!rec)
> 		return -ENOMEM;
>
>@@ -1106,6 +1106,7 @@ int cxl_store_rec_gen_media(struct cxl_memdev
>*cxlmd, union cxl_event *evt)
>
> 	cxl_del_expired_gmedia_recs(&array_rec->rec_gen_media, rec);
> 	cxl_del_overflow_old_recs(&array_rec->rec_gen_media);
>+	retain_and_null_ptr(rec);
>
> 	return 0;
> }
>@@ -1114,13 +1115,13 @@
>EXPORT_SYMBOL_NS_GPL(cxl_store_rec_gen_media, "CXL");  int
>cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)  {
> 	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
>-	struct cxl_event_dram *rec;
> 	void *old_rec;
>
> 	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
> 		return 0;
>
>-	rec = kmemdup(&evt->dram, sizeof(*rec), GFP_KERNEL);
>+	struct cxl_event_dram *rec __free(kfree) =
>+		kmemdup(&evt->dram, sizeof(*rec), GFP_KERNEL);
> 	if (!rec)
> 		return -ENOMEM;
>
>@@ -1134,6 +1135,7 @@ int cxl_store_rec_dram(struct cxl_memdev *cxlmd,
>union cxl_event *evt)
>
> 	cxl_del_expired_dram_recs(&array_rec->rec_dram, rec);
> 	cxl_del_overflow_old_recs(&array_rec->rec_dram);
>+	retain_and_null_ptr(rec);
>
> 	return 0;
> }
>--
>2.34.1

Re: [PATCH 1/1] cxl/edac: Fix potential memory leak issues

[Jonathan Cameron]

On Wed, 11 Jun 2025 11:35:42 +0800
Li Ming <ming.li@zohomail.com> wrote:

> In cxl_store_rec_gen_media() and cxl_store_rec_dram(), use kmemdup() to
> duplicate a cxl gen_media/dram event to store the event in a xarray by
> xa_store(). The cxl gen_media/dram event allocated by kmemdup() should
> be freed in the case that the xa_store() fails.
> 
> Fixes: 0b5ccb0de1e2 ("cxl/edac: Support for finding memory operation attributes from the current boot")
> Signed-off-by: Li Ming <ming.li@zohomail.com>
Good fine but I'm not sure this is the best fix.

> ---
> base-commit: 87b42c114cdda76c8ad3002f2096699ad5146cb3 cxl/fixes
> ---
>  drivers/cxl/core/edac.c | 10 ++++++----
>  1 file changed, 6 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c
> index 2cbc664e5d62..b4c5c23a45d4 100644
> --- a/drivers/cxl/core/edac.c
> +++ b/drivers/cxl/core/edac.c
> @@ -1086,13 +1086,13 @@ static void cxl_del_overflow_old_recs(struct xarray *rec_xarray)
>  int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt)
>  {
>  	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
> -	struct cxl_event_gen_media *rec;
>  	void *old_rec;
>  
>  	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
>  		return 0;
>  
> -	rec = kmemdup(&evt->gen_media, sizeof(*rec), GFP_KERNEL);
> +	struct cxl_event_gen_media *rec __free(kfree) =
> +		kmemdup(&evt->gen_media, sizeof(*rec), GFP_KERNEL);
>  	if (!rec)
>  		return -ENOMEM;
>  
> @@ -1106,6 +1106,7 @@ int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt)
>  
>  	cxl_del_expired_gmedia_recs(&array_rec->rec_gen_media, rec);
>  	cxl_del_overflow_old_recs(&array_rec->rec_gen_media);
> +	retain_and_null_ptr(rec);
>  
>  	return 0;
>  }
> @@ -1114,13 +1115,13 @@ EXPORT_SYMBOL_NS_GPL(cxl_store_rec_gen_media, "CXL");
>  int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)
>  {
>  	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
> -	struct cxl_event_dram *rec;
>  	void *old_rec;
>  
>  	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
>  		return 0;
>  
> -	rec = kmemdup(&evt->dram, sizeof(*rec), GFP_KERNEL);
> +	struct cxl_event_dram *rec __free(kfree) =
> +		kmemdup(&evt->dram, sizeof(*rec), GFP_KERNEL);
>  	if (!rec)
>  		return -ENOMEM;
>  
> @@ -1134,6 +1135,7 @@ int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)
>  
>  	cxl_del_expired_dram_recs(&array_rec->rec_dram, rec);
>  	cxl_del_overflow_old_recs(&array_rec->rec_dram);
> +	retain_and_null_ptr(rec);

I'd move this up to immediately after we hand it over to the xa successfully.

Actually I'm not sure this is a good use of __free given we have a single
error path to handle it in and have to manually release it in a different
call to where it is passed to the xa_store() function.  Maybe better
to just kfree in the error path.


>  
>  	return 0;
>  }

Re: [PATCH 1/1] cxl/edac: Fix potential memory leak issues

[Li Ming]

On 6/11/2025 9:16 PM, Jonathan Cameron wrote:
> On Wed, 11 Jun 2025 11:35:42 +0800
> Li Ming <ming.li@zohomail.com> wrote:
>
>> In cxl_store_rec_gen_media() and cxl_store_rec_dram(), use kmemdup() to
>> duplicate a cxl gen_media/dram event to store the event in a xarray by
>> xa_store(). The cxl gen_media/dram event allocated by kmemdup() should
>> be freed in the case that the xa_store() fails.
>>
>> Fixes: 0b5ccb0de1e2 ("cxl/edac: Support for finding memory operation attributes from the current boot")
>> Signed-off-by: Li Ming <ming.li@zohomail.com>
> Good fine but I'm not sure this is the best fix.
>
>> ---
>> base-commit: 87b42c114cdda76c8ad3002f2096699ad5146cb3 cxl/fixes
>> ---
>>  drivers/cxl/core/edac.c | 10 ++++++----
>>  1 file changed, 6 insertions(+), 4 deletions(-)
>>
>> diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c
>> index 2cbc664e5d62..b4c5c23a45d4 100644
>> --- a/drivers/cxl/core/edac.c
>> +++ b/drivers/cxl/core/edac.c
>> @@ -1086,13 +1086,13 @@ static void cxl_del_overflow_old_recs(struct xarray *rec_xarray)
>>  int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt)
>>  {
>>  	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
>> -	struct cxl_event_gen_media *rec;
>>  	void *old_rec;
>>  
>>  	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
>>  		return 0;
>>  
>> -	rec = kmemdup(&evt->gen_media, sizeof(*rec), GFP_KERNEL);
>> +	struct cxl_event_gen_media *rec __free(kfree) =
>> +		kmemdup(&evt->gen_media, sizeof(*rec), GFP_KERNEL);
>>  	if (!rec)
>>  		return -ENOMEM;
>>  
>> @@ -1106,6 +1106,7 @@ int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt)
>>  
>>  	cxl_del_expired_gmedia_recs(&array_rec->rec_gen_media, rec);
>>  	cxl_del_overflow_old_recs(&array_rec->rec_gen_media);
>> +	retain_and_null_ptr(rec);
>>  
>>  	return 0;
>>  }
>> @@ -1114,13 +1115,13 @@ EXPORT_SYMBOL_NS_GPL(cxl_store_rec_gen_media, "CXL");
>>  int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)
>>  {
>>  	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
>> -	struct cxl_event_dram *rec;
>>  	void *old_rec;
>>  
>>  	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
>>  		return 0;
>>  
>> -	rec = kmemdup(&evt->dram, sizeof(*rec), GFP_KERNEL);
>> +	struct cxl_event_dram *rec __free(kfree) =
>> +		kmemdup(&evt->dram, sizeof(*rec), GFP_KERNEL);
>>  	if (!rec)
>>  		return -ENOMEM;
>>  
>> @@ -1134,6 +1135,7 @@ int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)
>>  
>>  	cxl_del_expired_dram_recs(&array_rec->rec_dram, rec);
>>  	cxl_del_overflow_old_recs(&array_rec->rec_dram);
>> +	retain_and_null_ptr(rec);
> I'd move this up to immediately after we hand it over to the xa successfully.
>
> Actually I'm not sure this is a good use of __free given we have a single
> error path to handle it in and have to manually release it in a different
> call to where it is passed to the xa_store() function.  Maybe better
> to just kfree in the error path.

Sure, I can do that, using kfree directly instead of the __free(kfree). Thanks for reviewing.


Ming

>
>
>>  
>>  	return 0;
>>  }