drm/amd/amdgpu: Replace kmap() with kmap_local_page()
Subsystems (3)
PATCH 1/1 drm/amd/amdgpu: Replace kmap() with kmap_local_page()
kmap() is being deprecated in favor of kmap_local_page().
There are two main problems with kmap(): (1) It comes with an overhead as mapping space is restricted and protected by a global lock for synchronization and (2) it also requires global TLB invalidation when the kmap’s pool wraps and it might block when the mapping space is fully utilized until a slot becomes available.
With kmap_local_page() the mappings are per thread, CPU local, can take page faults, and can be called from any context (including interrupts). It is faster than kmap() in kernels with HIGHMEM enabled. Furthermore, the tasks can be preempted and, when they are scheduled to run again, the kernel virtual addresses are restored and are still valid.
Since its use in amdgpu/amdgpu_ttm.c is safe, it should be preferred.
Therefore, replace kmap() with kmap_local_page() in amdgpu/amdgpu_ttm.c.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +4 -4
@@ -2301,9 +2301,9 @@ static ssize_t amdgpu_iomem_read(struct file *f, char __user *buf,if (p->mapping != adev->mman.bdev.dev_mapping)return -EPERM ; - ptr =kmap (p); + ptr =kmap_local_page (p); r =copy_to_user (buf, ptr + off, bytes); -kunmap (p); +kunmap_local (ptr);if (r)return -EFAULT ;
@@ -2352,9 +2352,9 @@ static ssize_t amdgpu_iomem_write(struct file *f, const char __user *buf,if (p->mapping != adev->mman.bdev.dev_mapping)return -EPERM ; - ptr =kmap (p); + ptr =kmap_local_page (p); r =copy_from_user (ptr + off, buf, bytes); -kunmap (p); +kunmap_local (ptr);if (r)return -EFAULT ;
Signature · 1 line
2.37.1
Am 12.08.22 um 19:57 schrieb Fabio M. De Francesco:
Quoted 14 lines
kmap()is being deprecated in favor ofkmap_local_page().There are two main problems with
kmap(): (1) It comes with an overhead as mapping space is restricted and protected by a global lock for synchronization and (2) it also requires global TLB invalidation when the kmap’s pool wraps and it might block when the mapping space is fully utilized until a slot becomes available.With
kmap_local_page()the mappings are per thread, CPU local, can take page faults, and can be called from any context (including interrupts). It is faster thankmap()in kernels with HIGHMEM enabled. Furthermore, the tasks can be preempted and, when they are scheduled to run again, the kernel virtual addresses are restored and are still valid.
Quoted 6 lines
Since its use in
amdgpu/amdgpu_ttm.cis safe, it should be preferred.Therefore, replace
kmap()withkmap_local_page()inamdgpu/amdgpu_ttm.c.Suggested-by Ira Weiny <[email protected]>Signed-off-by Fabio M. De Francesco <[email protected]>
For those two use cases that looks good to me. Feel free to add an Acked-by: Christian König <[email protected]>
Regards,
Christian.
Quoted 32 lines
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +4
-4@@ -2301,9 +2301,9 @@ static ssize_t amdgpu_iomem_read(struct file *f, char __user *buf,if (p->mapping != adev->mman.bdev.dev_mapping)return -EPERM ; - ptr =kmap (p); + ptr =kmap_local_page (p); r =copy_to_user (buf, ptr + off, bytes); -kunmap (p); +kunmap_local (ptr);if (r)return -EFAULT ;@@ -2352,9 +2352,9 @@ static ssize_t amdgpu_iomem_write(struct file *f, const char __user *buf,if (p->mapping != adev->mman.bdev.dev_mapping)return -EPERM ; - ptr =kmap (p); + ptr =kmap_local_page (p); r =copy_from_user (ptr + off, buf, bytes); -kunmap (p); +kunmap_local (ptr);if (r)return -EFAULT ;