drm/amdgpu: Fix discovery initialization failure during pci rescan
Subsystems (2)
PATCH 1/1 drm/amdgpu: Fix discovery initialization failure during pci rescan
Waiting for system ready to fix the discovery initialization failure issue. This failure usually occurs when dGPU is removed and then rescanned via command line.
It's caused by following two errors:
[1] vram size is 0
[2] wrong binary signature
--- drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +12 -3
@@ -276,7 +276,12 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,msleep (1 ); } } - vram_size = (uint64_t )RREG32 (mmRCC_CONFIG_MEMSIZE) <<20 ; +for (i =0 ; i <100 ; i++) { + vram_size = (uint64_t )RREG32 (mmRCC_CONFIG_MEMSIZE) <<20 ; +if (vram_size) +break ; +usleep_range (1000 ,1100 ); + }if (vram_size) {uint64_t pos = vram_size -DISCOVERY_TMR_OFFSET ;
@@ -371,6 +376,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) {struct table_info *info;struct binary_header *bhdr; +int error_count =0 ;uint16_t offset;uint16_t size;uint16_t checksum;
@@ -380,7 +386,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) adev->mman.discovery_bin =kzalloc (adev->mman.discovery_tmr_size,GFP_KERNEL );if (!adev->mman.discovery_bin)return -ENOMEM ; - +retry:/* Read from file if it is the preferred option */ if (amdgpu_discovery ==2 ) {dev_info (adev->dev,"use ip discovery information from file" );
@@ -401,6 +407,10 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)/* check the ip discovery binary signature */ if (!amdgpu_discovery_verify_binary_signature (adev->mman.discovery_bin)) { +if (error_count++ <1 ) { +msleep (100 ); + goto retry; + }dev_err (adev->dev,"get invalid ip discovery binary signature\n" ); r = -EINVAL ;
@@ -515,7 +525,6 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)if (0 && offset) {struct mall_info_header *mhdr = (struct mall_info_header *)(adev->mman.discovery_bin + offset); -if (le32_to_cpu (mhdr->table_id) !=MALL_INFO_TABLE_ID ) {dev_err (adev->dev,"invalid ip discovery mall table id\n" ); r = -EINVAL ;
Signature · 1 line
2.34.1
Am 01.04.24 um 12:18 schrieb Ma Jun:
Quoted 17 lines
Waiting for system ready to fix the discovery initialization failure issue. This failure usually occurs when dGPU is removed and then rescanned via command line.
It's caused by following two errors:
[1] vram size is 0
[2] wrong binary signatureSigned-off-by Ma Jun <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev, · line 284
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +6
-1@@ -276,7 +276,12 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,msleep (1 ); } } - vram_size = (uint64_t )RREG32 (mmRCC_CONFIG_MEMSIZE) <<20 ; +for (i =0 ; i <100 ; i++) { + vram_size = (uint64_t )RREG32 (mmRCC_CONFIG_MEMSIZE) <<20 ; +if (vram_size) +break ; +usleep_range (1000 ,1100 ); + }
Nice that we come closer to a solution for this, but that here is really hacky.
Do we have any idea why mmRCC_CONFIG_MEMSIZE is zero when we re-scan? Is some initialization not completed yet or something like that.
Regards,
Christian.
Quoted 39 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +6
-2if (vram_size) {uint64_t pos = vram_size -DISCOVERY_TMR_OFFSET ;@@ -371,6 +376,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) {struct table_info *info;struct binary_header *bhdr; +int error_count =0 ;uint16_t offset;uint16_t size;uint16_t checksum;@@ -380,7 +386,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) adev->mman.discovery_bin =kzalloc (adev->mman.discovery_tmr_size,GFP_KERNEL );if (!adev->mman.discovery_bin)return -ENOMEM ; - +retry:/* Read from file if it is the preferred option */ if (amdgpu_discovery ==2 ) {dev_info (adev->dev,"use ip discovery information from file" );@@ -401,6 +407,10 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)/* check the ip discovery binary signature */ if (!amdgpu_discovery_verify_binary_signature (adev->mman.discovery_bin)) { +if (error_count++ <1 ) { +msleep (100 ); + goto retry; + }dev_err (adev->dev,"get invalid ip discovery binary signature\n" ); r = -EINVAL ;@@ -515,7 +525,6 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)if (0 && offset) {struct mall_info_header *mhdr = (struct mall_info_header *)(adev->mman.discovery_bin + offset); -if (le32_to_cpu (mhdr->table_id) !=MALL_INFO_TABLE_ID ) {dev_err (adev->dev,"invalid ip discovery mall table id\n" ); r = -EINVAL ;
Quoted 32 lines · Christian König
Am 01.04.24 um 12:18 schrieb Ma Jun:
Quoted 17 lines
Waiting for system ready to fix the discovery initialization failure issue. This failure usually occurs when dGPU is removed and then rescanned via command line.
It's caused by following two errors:
[1] vram size is 0
[2] wrong binary signatureSigned-off-by Ma Jun <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +0
-0drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev, · line 284
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +6
-1@@ -276,7 +276,12 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,msleep (1 ); } } - vram_size = (uint64_t )RREG32 (mmRCC_CONFIG_MEMSIZE) <<20 ; +for (i =0 ; i <100 ; i++) { + vram_size = (uint64_t )RREG32 (mmRCC_CONFIG_MEMSIZE) <<20 ; +if (vram_size) +break ; +usleep_range (1000 ,1100 ); + }Nice that we come closer to a solution for this, but that here is really hacky.
Quoted 3 lines
Do we have any idea why
mmRCC_CONFIG_MEMSIZEis zero when we re-scan? Is some initialization not completed yet or something like that.
I just found there is a patch related to my issue.
https://lore.kernel.org/all/[email protected]/
But I think it should not be limited to removable devices or devices with discovery_version=2 and 4.
I will submit v2 based on this patch.
Regards,
Ma Jun
Quoted 43 lines
Regards,
Christian.Quoted 39 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +6
-2if (vram_size) {uint64_t pos = vram_size -DISCOVERY_TMR_OFFSET ;@@ -371,6 +376,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) {struct table_info *info;struct binary_header *bhdr; +int error_count =0 ;uint16_t offset;uint16_t size;uint16_t checksum;@@ -380,7 +386,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) adev->mman.discovery_bin =kzalloc (adev->mman.discovery_tmr_size,GFP_KERNEL );if (!adev->mman.discovery_bin)return -ENOMEM ; - +retry:/* Read from file if it is the preferred option */ if (amdgpu_discovery ==2 ) {dev_info (adev->dev,"use ip discovery information from file" );@@ -401,6 +407,10 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)/* check the ip discovery binary signature */ if (!amdgpu_discovery_verify_binary_signature (adev->mman.discovery_bin)) { +if (error_count++ <1 ) { +msleep (100 ); + goto retry; + }dev_err (adev->dev,"get invalid ip discovery binary signature\n" ); r = -EINVAL ;@@ -515,7 +525,6 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)if (0 && offset) {struct mall_info_header *mhdr = (struct mall_info_header *)(adev->mman.discovery_bin + offset); -if (le32_to_cpu (mhdr->table_id) !=MALL_INFO_TABLE_ID ) {dev_err (adev->dev,"invalid ip discovery mall table id\n" ); r = -EINVAL ;