The cma dma-buf heaps let userspace allocate buffers in CMA regions without enforcing limits. Register a dmem region per cma heap and charge against it when allocating a buffer in a cma heap.
For the default cma region, two heaps may be created for the same cma range: commit 854acbe75ff4 ("dma-buf: heaps: Give default CMA heap a fixed name") Introduced /dev/dma_heap/default_cma_region commit 4f5f8baf7341 ("dma-buf: heaps: cma: Create CMA heap for each CMA reserved region") Created a CMA heap for each CMA region, which might create a duplicate heap to the default one, e.g: /dev/dma_heap/default_cma_region /dev/dma_heap/reserved
Removing the legacy heap would break user API. So handle the special case by using one dmem between the two heaps to account charges correctly.
Signed-off-by: Eric Chanudet echanude@redhat.com --- In continuation with introducing cgroup for the system heap[1], this behavior is enabled based on dma_heap.mem_accounting, disabled by default.
dmem is chosen for CMA heaps as it allows limits to be set for each region backing each heap. There is one caveat for the default cma range that may accessible through two different cma heaps, which is treated as a special case.
[1] https://lore.kernel.org/all/20260116-dmabuf-heap-system-memcg-v3-0-ecc6b62cc... --- drivers/dma-buf/heaps/cma_heap.c | 51 ++++++++++++++++++++++++++++++++++++---- 1 file changed, 46 insertions(+), 5 deletions(-)
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 49cc45fb42dd7200c3c14384bcfdbe85323454b1..608af8ad6bce7fe0321da6d8f1b65a69f5d8d950 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -27,6 +27,7 @@ #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/cgroup_dmem.h>
#define DEFAULT_CMA_NAME "default_cma_region"
@@ -46,7 +47,9 @@ int __init dma_heap_cma_register_heap(struct cma *cma) struct cma_heap { struct dma_heap *heap; struct cma *cma; + struct dmem_cgroup_region *cg; }; +static struct dmem_cgroup_region *default_cma_cg;
struct cma_heap_buffer { struct cma_heap *heap; @@ -58,6 +61,7 @@ struct cma_heap_buffer { pgoff_t pagecount; int vmap_cnt; void *vaddr; + struct dmem_cgroup_pool_state *pool; };
struct dma_heap_attachment { @@ -276,6 +280,7 @@ static void cma_heap_dma_buf_release(struct dma_buf *dmabuf) kfree(buffer->pages); /* release memory */ cma_release(cma_heap->cma, buffer->cma_pages, buffer->pagecount); + dmem_cgroup_uncharge(buffer->pool, buffer->len); kfree(buffer); }
@@ -319,9 +324,16 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, if (align > CONFIG_CMA_ALIGNMENT) align = CONFIG_CMA_ALIGNMENT;
+ if (mem_accounting) { + ret = dmem_cgroup_try_charge(cma_heap->cg, size, + &buffer->pool, NULL); + if (ret) + goto free_buffer; + } + cma_pages = cma_alloc(cma_heap->cma, pagecount, align, false); if (!cma_pages) - goto free_buffer; + goto uncharge_cgroup;
/* Clear the cma pages */ if (PageHighMem(cma_pages)) { @@ -376,6 +388,8 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, kfree(buffer->pages); free_cma: cma_release(cma_heap->cma, cma_pages, pagecount); +uncharge_cgroup: + dmem_cgroup_uncharge(buffer->pool, size); free_buffer: kfree(buffer);
@@ -390,25 +404,52 @@ static int __init __add_cma_heap(struct cma *cma, const char *name) { struct dma_heap_export_info exp_info; struct cma_heap *cma_heap; + struct dmem_cgroup_region *region; + int ret;
cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL); if (!cma_heap) return -ENOMEM; cma_heap->cma = cma;
+ /* + * If two heaps are created for the default cma region, use the same + * dmem for them. They both use the same memory pool. + */ + if (dev_get_cma_area(NULL) == cma && default_cma_cg) + region = default_cma_cg; + else { + region = dmem_cgroup_register_region(cma_get_size(cma), "cma/%s", name); + if (IS_ERR(region)) { + ret = PTR_ERR(region); + goto free_cma_heap; + } + } + cma_heap->cg = region; + exp_info.name = name; exp_info.ops = &cma_heap_ops; exp_info.priv = cma_heap;
cma_heap->heap = dma_heap_add(&exp_info); if (IS_ERR(cma_heap->heap)) { - int ret = PTR_ERR(cma_heap->heap); - - kfree(cma_heap); - return ret; + ret = PTR_ERR(cma_heap->heap); + goto cg_unregister; }
+ if (dev_get_cma_area(NULL) == cma && !default_cma_cg) + default_cma_cg = region; + return 0; + +cg_unregister: + /* default_cma_cg == cma_heap->cg only for the duplicate heap. */ + if (default_cma_cg != cma_heap->cg) + dmem_cgroup_unregister_region(cma_heap->cg); +free_cma_heap: + kfree(cma_heap); + + return ret; }
static int __init add_cma_heaps(void)
--- base-commit: 3d65e4c276b32c03450261d114e495fda03c8e97 change-id: 20260128-dmabuf-heap-cma-dmem-f4120a2df4a8
Best regards,
Hi,
On Fri, Jan 30, 2026 at 05:55:30PM -0500, Eric Chanudet wrote:
The cma dma-buf heaps let userspace allocate buffers in CMA regions without enforcing limits. Register a dmem region per cma heap and charge against it when allocating a buffer in a cma heap.
For the default cma region, two heaps may be created for the same cma range: commit 854acbe75ff4 ("dma-buf: heaps: Give default CMA heap a fixed name") Introduced /dev/dma_heap/default_cma_region commit 4f5f8baf7341 ("dma-buf: heaps: cma: Create CMA heap for each CMA reserved region") Created a CMA heap for each CMA region, which might create a duplicate heap to the default one, e.g: /dev/dma_heap/default_cma_region /dev/dma_heap/reserved
Removing the legacy heap would break user API. So handle the special case by using one dmem between the two heaps to account charges correctly.
Signed-off-by: Eric Chanudet echanude@redhat.com
In continuation with introducing cgroup for the system heap[1], this behavior is enabled based on dma_heap.mem_accounting, disabled by default.
dmem is chosen for CMA heaps as it allows limits to be set for each region backing each heap. There is one caveat for the default cma range that may accessible through two different cma heaps, which is treated as a special case.
[1] https://lore.kernel.org/all/20260116-dmabuf-heap-system-memcg-v3-0-ecc6b62cc...
drivers/dma-buf/heaps/cma_heap.c | 51 ++++++++++++++++++++++++++++++++++++---- 1 file changed, 46 insertions(+), 5 deletions(-)
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 49cc45fb42dd7200c3c14384bcfdbe85323454b1..608af8ad6bce7fe0321da6d8f1b65a69f5d8d950 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -27,6 +27,7 @@ #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/cgroup_dmem.h> #define DEFAULT_CMA_NAME "default_cma_region" @@ -46,7 +47,9 @@ int __init dma_heap_cma_register_heap(struct cma *cma) struct cma_heap { struct dma_heap *heap; struct cma *cma;
- struct dmem_cgroup_region *cg;
}; +static struct dmem_cgroup_region *default_cma_cg; struct cma_heap_buffer { struct cma_heap *heap; @@ -58,6 +61,7 @@ struct cma_heap_buffer { pgoff_t pagecount; int vmap_cnt; void *vaddr;
- struct dmem_cgroup_pool_state *pool;
}; struct dma_heap_attachment { @@ -276,6 +280,7 @@ static void cma_heap_dma_buf_release(struct dma_buf *dmabuf) kfree(buffer->pages); /* release memory */ cma_release(cma_heap->cma, buffer->cma_pages, buffer->pagecount);
- dmem_cgroup_uncharge(buffer->pool, buffer->len); kfree(buffer);
} @@ -319,9 +324,16 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, if (align > CONFIG_CMA_ALIGNMENT) align = CONFIG_CMA_ALIGNMENT;
if (mem_accounting) {
ret = dmem_cgroup_try_charge(cma_heap->cg, size,&buffer->pool, NULL);if (ret)goto free_buffer;}
cma_pages = cma_alloc(cma_heap->cma, pagecount, align, false); if (!cma_pages)
goto free_buffer;
goto uncharge_cgroup;/* Clear the cma pages */ if (PageHighMem(cma_pages)) { @@ -376,6 +388,8 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, kfree(buffer->pages); free_cma: cma_release(cma_heap->cma, cma_pages, pagecount); +uncharge_cgroup:
- dmem_cgroup_uncharge(buffer->pool, size);
Should we make that conditional on mem_accounting == true ?
free_buffer: kfree(buffer); @@ -390,25 +404,52 @@ static int __init __add_cma_heap(struct cma *cma, const char *name) { struct dma_heap_export_info exp_info; struct cma_heap *cma_heap;
- struct dmem_cgroup_region *region;
- int ret;
cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL); if (!cma_heap) return -ENOMEM; cma_heap->cma = cma;
- /*
* If two heaps are created for the default cma region, use the same* dmem for them. They both use the same memory pool.*/- if (dev_get_cma_area(NULL) == cma && default_cma_cg)
region = default_cma_cg;- else {
region = dmem_cgroup_register_region(cma_get_size(cma), "cma/%s", name);if (IS_ERR(region)) {ret = PTR_ERR(region);goto free_cma_heap;}- }
- cma_heap->cg = region;
I'm not sure it's the best way to go with this. We want to track all relevant CMA allocations going forward, in the heaps and elsewhere.
If we were to do what you suggest, an allocation in, say, DRM or v4l2 wouldn't be tracked in the same region than one in the heaps, while we want to have it cumulated.
I think we'd be better off if we created a dmem region for each CMA region in the system, but we would charge from the heap so we don't account for every allocation.
I don't think we can register the dmem region when the CMA area is initialized though, since it will probably be too early in the kernel boot and SLAB isn't around yet.
But since we would need an accessor to get a dmem region from a cma region, we could do something like check if a dmem eregion already exists for that cma region, and allocate one otherwise. Or have a secondary initcall to allocate all dmem regions.
Maxime
On Mon, Feb 02, 2026 at 11:12:37AM +0100, Maxime Ripard wrote:
Hi,
On Fri, Jan 30, 2026 at 05:55:30PM -0500, Eric Chanudet wrote:
The cma dma-buf heaps let userspace allocate buffers in CMA regions without enforcing limits. Register a dmem region per cma heap and charge against it when allocating a buffer in a cma heap.
For the default cma region, two heaps may be created for the same cma range: commit 854acbe75ff4 ("dma-buf: heaps: Give default CMA heap a fixed name") Introduced /dev/dma_heap/default_cma_region commit 4f5f8baf7341 ("dma-buf: heaps: cma: Create CMA heap for each CMA reserved region") Created a CMA heap for each CMA region, which might create a duplicate heap to the default one, e.g: /dev/dma_heap/default_cma_region /dev/dma_heap/reserved
Removing the legacy heap would break user API. So handle the special case by using one dmem between the two heaps to account charges correctly.
Signed-off-by: Eric Chanudet echanude@redhat.com
In continuation with introducing cgroup for the system heap[1], this behavior is enabled based on dma_heap.mem_accounting, disabled by default.
dmem is chosen for CMA heaps as it allows limits to be set for each region backing each heap. There is one caveat for the default cma range that may accessible through two different cma heaps, which is treated as a special case.
[1] https://lore.kernel.org/all/20260116-dmabuf-heap-system-memcg-v3-0-ecc6b62cc...
drivers/dma-buf/heaps/cma_heap.c | 51 ++++++++++++++++++++++++++++++++++++---- 1 file changed, 46 insertions(+), 5 deletions(-)
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 49cc45fb42dd7200c3c14384bcfdbe85323454b1..608af8ad6bce7fe0321da6d8f1b65a69f5d8d950 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -27,6 +27,7 @@ #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/cgroup_dmem.h> #define DEFAULT_CMA_NAME "default_cma_region" @@ -46,7 +47,9 @@ int __init dma_heap_cma_register_heap(struct cma *cma) struct cma_heap { struct dma_heap *heap; struct cma *cma;
- struct dmem_cgroup_region *cg;
}; +static struct dmem_cgroup_region *default_cma_cg; struct cma_heap_buffer { struct cma_heap *heap; @@ -58,6 +61,7 @@ struct cma_heap_buffer { pgoff_t pagecount; int vmap_cnt; void *vaddr;
- struct dmem_cgroup_pool_state *pool;
}; struct dma_heap_attachment { @@ -276,6 +280,7 @@ static void cma_heap_dma_buf_release(struct dma_buf *dmabuf) kfree(buffer->pages); /* release memory */ cma_release(cma_heap->cma, buffer->cma_pages, buffer->pagecount);
- dmem_cgroup_uncharge(buffer->pool, buffer->len); kfree(buffer);
} @@ -319,9 +324,16 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, if (align > CONFIG_CMA_ALIGNMENT) align = CONFIG_CMA_ALIGNMENT;
if (mem_accounting) {
ret = dmem_cgroup_try_charge(cma_heap->cg, size,&buffer->pool, NULL);if (ret)goto free_buffer;}
cma_pages = cma_alloc(cma_heap->cma, pagecount, align, false); if (!cma_pages)
goto free_buffer;
goto uncharge_cgroup;/* Clear the cma pages */ if (PageHighMem(cma_pages)) { @@ -376,6 +388,8 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, kfree(buffer->pages); free_cma: cma_release(cma_heap->cma, cma_pages, pagecount); +uncharge_cgroup:
- dmem_cgroup_uncharge(buffer->pool, size);
Should we make that conditional on mem_accounting == true ?
free_buffer: kfree(buffer); @@ -390,25 +404,52 @@ static int __init __add_cma_heap(struct cma *cma, const char *name) { struct dma_heap_export_info exp_info; struct cma_heap *cma_heap;
- struct dmem_cgroup_region *region;
- int ret;
cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL); if (!cma_heap) return -ENOMEM; cma_heap->cma = cma;
- /*
* If two heaps are created for the default cma region, use the same* dmem for them. They both use the same memory pool.*/- if (dev_get_cma_area(NULL) == cma && default_cma_cg)
region = default_cma_cg;- else {
region = dmem_cgroup_register_region(cma_get_size(cma), "cma/%s", name);if (IS_ERR(region)) {ret = PTR_ERR(region);goto free_cma_heap;}- }
- cma_heap->cg = region;
I'm not sure it's the best way to go with this. We want to track all relevant CMA allocations going forward, in the heaps and elsewhere.
If we were to do what you suggest, an allocation in, say, DRM or v4l2 wouldn't be tracked in the same region than one in the heaps, while we want to have it cumulated.
I think we'd be better off if we created a dmem region for each CMA region in the system, but we would charge from the heap so we don't account for every allocation.
That makes more sense. I will do that in a v2.
I don't think we can register the dmem region when the CMA area is initialized though, since it will probably be too early in the kernel boot and SLAB isn't around yet.
But since we would need an accessor to get a dmem region from a cma region, we could do something like check if a dmem eregion already exists for that cma region, and allocate one otherwise. Or have a secondary initcall to allocate all dmem regions.
In an earlier series[1], you did this during cma_activate_area(), core_initcall is late enough, so I can start from this in your series.
[1] https://lore.kernel.org/all/20250310-dmem-cgroups-v1-1-2984c1bc9312@kernel.o...
Maxime
linaro-mm-sig@lists.linaro.org
-
Eric Chanudet -
Maxime Ripard