Mohamed Ahmed
2025-Oct-31 10:49 UTC
[PATCH v4 0/5] drm/nouveau: Enable variable page sizes and compression
The new VM_BIND interface only supported 4K pages. This was problematic as
it left performance on the table because GPUs don't have sophisticated TLB
and page walker hardware.
Additionally, the HW can only do compression on large (64K) and huge (2M)
pages, which is a major performance booster (>50% in some cases).
This patchset sets out to add support for larger page sizes and also
enable compression and set the compression tags when userspace binds with
the corresponding PTE kinds and alignment. It also increments the nouveau
version number which allows userspace to use compression only when the
kernel actually supports both features and avoid breaking the system if a
newer mesa version is paired with an older kernel version.
For the associated userspace MR, please see !36450:
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36450
- v4: Fix missing parenthesis in second patch in the series.
- v3: Add reviewed-by tags, revert page selection logic to v1 behavior.
- v2: Implement review comments, change page selection logic.
- v1: Initial implementation.
Ben Skeggs (2):
drm/nouveau/mmu/gp100: Remove unused/broken support for compression
drm/nouveau/mmu/tu102: Add support for compressed kinds
Mary Guillemard (2):
drm/nouveau/uvmm: Prepare for larger pages
drm/nouveau/uvmm: Allow larger pages
Mohamed Ahmed (1):
drm/nouveau/drm: Bump the driver version to 1.4.1 to report new
features
drivers/gpu/drm/nouveau/nouveau_drv.h | 4 +-
drivers/gpu/drm/nouveau/nouveau_uvmm.c | 102 +++++++++++++++---
drivers/gpu/drm/nouveau/nouveau_uvmm.h | 1 +
.../drm/nouveau/nvkm/subdev/mmu/vmmgp100.c | 69 +++++++-----
.../drm/nouveau/nvkm/subdev/mmu/vmmgp10b.c | 4 +-
5 files changed, 131 insertions(+), 49 deletions(-)
--
2.51.1
Mohamed Ahmed
2025-Oct-31 10:49 UTC
[PATCH v4 1/5] drm/nouveau/uvmm: Prepare for larger pages
From: Mary Guillemard <mary at mary.zone>
Currently memory allocated by VM_BIND uAPI can only have a granuality
matching PAGE_SIZE (4KiB in common case)
To have a better memory management and to allow big (64KiB) and huge
(2MiB) pages later in the series, we are now passing the page shift all
around the internals of UVMM.
Signed-off-by: Mary Guillemard <mary at mary.zone>
Co-developed-by: Mohamed Ahmed <mohamedahmedegypt2001 at gmail.com>
Signed-off-by: Mohamed Ahmed <mohamedahmedegypt2001 at gmail.com>
Reviewed-by: Lyude Paul <lyude at redhat.com>
---
drivers/gpu/drm/nouveau/nouveau_uvmm.c | 46 ++++++++++++++++----------
drivers/gpu/drm/nouveau/nouveau_uvmm.h | 1 +
2 files changed, 30 insertions(+), 17 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 79eefdfd08a2..2cd0835b05e8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -107,34 +107,34 @@ nouveau_uvmm_vmm_sparse_unref(struct nouveau_uvmm *uvmm,
static int
nouveau_uvmm_vmm_get(struct nouveau_uvmm *uvmm,
- u64 addr, u64 range)
+ u64 addr, u64 range, u8 page_shift)
{
struct nvif_vmm *vmm = &uvmm->vmm.vmm;
- return nvif_vmm_raw_get(vmm, addr, range, PAGE_SHIFT);
+ return nvif_vmm_raw_get(vmm, addr, range, page_shift);
}
static int
nouveau_uvmm_vmm_put(struct nouveau_uvmm *uvmm,
- u64 addr, u64 range)
+ u64 addr, u64 range, u8 page_shift)
{
struct nvif_vmm *vmm = &uvmm->vmm.vmm;
- return nvif_vmm_raw_put(vmm, addr, range, PAGE_SHIFT);
+ return nvif_vmm_raw_put(vmm, addr, range, page_shift);
}
static int
nouveau_uvmm_vmm_unmap(struct nouveau_uvmm *uvmm,
- u64 addr, u64 range, bool sparse)
+ u64 addr, u64 range, u8 page_shift, bool sparse)
{
struct nvif_vmm *vmm = &uvmm->vmm.vmm;
- return nvif_vmm_raw_unmap(vmm, addr, range, PAGE_SHIFT, sparse);
+ return nvif_vmm_raw_unmap(vmm, addr, range, page_shift, sparse);
}
static int
nouveau_uvmm_vmm_map(struct nouveau_uvmm *uvmm,
- u64 addr, u64 range,
+ u64 addr, u64 range, u8 page_shift,
u64 bo_offset, u8 kind,
struct nouveau_mem *mem)
{
@@ -163,7 +163,7 @@ nouveau_uvmm_vmm_map(struct nouveau_uvmm *uvmm,
return -ENOSYS;
}
- return nvif_vmm_raw_map(vmm, addr, range, PAGE_SHIFT,
+ return nvif_vmm_raw_map(vmm, addr, range, page_shift,
&args, argc,
&mem->mem, bo_offset);
}
@@ -182,8 +182,9 @@ nouveau_uvma_vmm_put(struct nouveau_uvma *uvma)
{
u64 addr = uvma->va.va.addr;
u64 range = uvma->va.va.range;
+ u8 page_shift = uvma->page_shift;
- return nouveau_uvmm_vmm_put(to_uvmm(uvma), addr, range);
+ return nouveau_uvmm_vmm_put(to_uvmm(uvma), addr, range, page_shift);
}
static int
@@ -193,9 +194,11 @@ nouveau_uvma_map(struct nouveau_uvma *uvma,
u64 addr = uvma->va.va.addr;
u64 offset = uvma->va.gem.offset;
u64 range = uvma->va.va.range;
+ u8 page_shift = uvma->page_shift;
return nouveau_uvmm_vmm_map(to_uvmm(uvma), addr, range,
- offset, uvma->kind, mem);
+ page_shift, offset, uvma->kind,
+ mem);
}
static int
@@ -203,12 +206,13 @@ nouveau_uvma_unmap(struct nouveau_uvma *uvma)
{
u64 addr = uvma->va.va.addr;
u64 range = uvma->va.va.range;
+ u8 page_shift = uvma->page_shift;
bool sparse = !!uvma->region;
if (drm_gpuva_invalidated(&uvma->va))
return 0;
- return nouveau_uvmm_vmm_unmap(to_uvmm(uvma), addr, range, sparse);
+ return nouveau_uvmm_vmm_unmap(to_uvmm(uvma), addr, range, page_shift, sparse);
}
static int
@@ -501,7 +505,8 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
if (vmm_get_range)
nouveau_uvmm_vmm_put(uvmm, vmm_get_start,
- vmm_get_range);
+ vmm_get_range,
+ PAGE_SHIFT);
break;
}
case DRM_GPUVA_OP_REMAP: {
@@ -528,6 +533,7 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
u64 ustart = va->va.addr;
u64 urange = va->va.range;
u64 uend = ustart + urange;
+ u8 page_shift = uvma_from_va(va)->page_shift;
/* Nothing to do for mappings we merge with. */
if (uend == vmm_get_start ||
@@ -538,7 +544,8 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
u64 vmm_get_range = ustart - vmm_get_start;
nouveau_uvmm_vmm_put(uvmm, vmm_get_start,
- vmm_get_range);
+ vmm_get_range,
+ page_shift);
}
vmm_get_start = uend;
break;
@@ -592,6 +599,7 @@ op_map_prepare(struct nouveau_uvmm *uvmm,
uvma->region = args->region;
uvma->kind = args->kind;
+ uvma->page_shift = PAGE_SHIFT;
drm_gpuva_map(&uvmm->base, &uvma->va, op);
@@ -633,7 +641,8 @@ nouveau_uvmm_sm_prepare(struct nouveau_uvmm *uvmm,
if (vmm_get_range) {
ret = nouveau_uvmm_vmm_get(uvmm, vmm_get_start,
- vmm_get_range);
+ vmm_get_range,
+ new->map->page_shift);
if (ret) {
op_map_prepare_unwind(new->map);
goto unwind;
@@ -689,6 +698,7 @@ nouveau_uvmm_sm_prepare(struct nouveau_uvmm *uvmm,
u64 ustart = va->va.addr;
u64 urange = va->va.range;
u64 uend = ustart + urange;
+ u8 page_shift = uvma_from_va(va)->page_shift;
op_unmap_prepare(u);
@@ -704,7 +714,7 @@ nouveau_uvmm_sm_prepare(struct nouveau_uvmm *uvmm,
u64 vmm_get_range = ustart - vmm_get_start;
ret = nouveau_uvmm_vmm_get(uvmm, vmm_get_start,
- vmm_get_range);
+ vmm_get_range, page_shift);
if (ret) {
op_unmap_prepare_unwind(va);
goto unwind;
@@ -799,10 +809,11 @@ op_unmap_range(struct drm_gpuva_op_unmap *u,
u64 addr, u64 range)
{
struct nouveau_uvma *uvma = uvma_from_va(u->va);
+ u8 page_shift = uvma->page_shift;
bool sparse = !!uvma->region;
if (!drm_gpuva_invalidated(u->va))
- nouveau_uvmm_vmm_unmap(to_uvmm(uvma), addr, range, sparse);
+ nouveau_uvmm_vmm_unmap(to_uvmm(uvma), addr, range, page_shift, sparse);
}
static void
@@ -882,6 +893,7 @@ nouveau_uvmm_sm_cleanup(struct nouveau_uvmm *uvmm,
struct drm_gpuva_op_map *n = r->next;
struct drm_gpuva *va = r->unmap->va;
struct nouveau_uvma *uvma = uvma_from_va(va);
+ u8 page_shift = uvma->page_shift;
if (unmap) {
u64 addr = va->va.addr;
@@ -893,7 +905,7 @@ nouveau_uvmm_sm_cleanup(struct nouveau_uvmm *uvmm,
if (n)
end = n->va.addr;
- nouveau_uvmm_vmm_put(uvmm, addr, end - addr);
+ nouveau_uvmm_vmm_put(uvmm, addr, end - addr, page_shift);
}
nouveau_uvma_gem_put(uvma);
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.h
b/drivers/gpu/drm/nouveau/nouveau_uvmm.h
index 9d3c348581eb..51925711ae90 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.h
@@ -33,6 +33,7 @@ struct nouveau_uvma {
struct nouveau_uvma_region *region;
u8 kind;
+ u8 page_shift;
};
#define uvmm_from_gpuvm(x) container_of((x), struct nouveau_uvmm, base)
--
2.51.1
From: Mary Guillemard <mary at mary.zone>
Now that everything in UVMM knows about the variable page shift, we can
select larger values.
The proposed approach relies on nouveau_bo::page unless if it would cause
alignment issues (in which case we fall back to searching for an
appropriate shift)
Signed-off-by: Mary Guillemard <mary at mary.zone>
Co-developed-by: Mohamed Ahmed <mohamedahmedegypt2001 at gmail.com>
Signed-off-by: Mohamed Ahmed <mohamedahmedegypt2001 at gmail.com>
---
drivers/gpu/drm/nouveau/nouveau_uvmm.c | 60 +++++++++++++++++++++++++-
1 file changed, 58 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 2cd0835b05e8..ab8933b88337 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -454,6 +454,62 @@ op_unmap_prepare_unwind(struct drm_gpuva *va)
drm_gpuva_insert(va->vm, va);
}
+static bool
+op_map_aligned_to_page_shift(const struct drm_gpuva_op_map *op, u8 page_shift)
+{
+ u64 non_page_bits = (1ULL << page_shift) - 1;
+
+ return (op->va.addr & non_page_bits) == 0 &&
+ (op->va.range & non_page_bits) == 0 &&
+ (op->gem.offset & non_page_bits) == 0;
+}
+
+static u8
+select_page_shift(struct nouveau_uvmm *uvmm, struct drm_gpuva_op_map *op)
+{
+ struct nouveau_bo *nvbo = nouveau_gem_object(op->gem.obj);
+
+ /* nouveau_bo_fixup_align() guarantees that the page size will be aligned
+ * for most cases, but it can't handle cases where userspace allocates
with
+ * a size and then binds with a smaller granularity. So in order to avoid
+ * breaking old userspace, we need to ensure that the VA is actually
+ * aligned before using it, and if it isn't, then we downgrade to the
first
+ * granularity that will fit, which is optimal from a correctness and
+ * performance perspective.
+ */
+ if (op_map_aligned_to_page_shift(op, nvbo->page))
+ return nvbo->page;
+
+ struct nouveau_mem *mem = nouveau_mem(nvbo->bo.resource);
+ struct nvif_vmm *vmm = &uvmm->vmm.vmm;
+ int i;
+
+ /* If the given granularity doesn't fit, let's find one that will fit.
*/
+ for (i = 0; i < vmm->page_nr; i++) {
+ /* Ignore anything that is bigger or identical to the BO preference. */
+ if (vmm->page[i].shift >= nvbo->page)
+ continue;
+
+ /* Skip incompatible domains. */
+ if ((mem->mem.type & NVIF_MEM_VRAM) && !vmm->page[i].vram)
+ continue;
+ if ((mem->mem.type & NVIF_MEM_HOST) &&
+ (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
+ continue;
+
+ /* If it fits, return the proposed shift. */
+ if (op_map_aligned_to_page_shift(op, vmm->page[i].shift))
+ return vmm->page[i].shift;
+ }
+
+ /* If we get here then nothing can reconcile the requirements. This should
never
+ * happen.
+ */
+ WARN_ON(1);
+
+ return PAGE_SHIFT;
+}
+
static void
nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
struct nouveau_uvma_prealloc *new,
@@ -506,7 +562,7 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
if (vmm_get_range)
nouveau_uvmm_vmm_put(uvmm, vmm_get_start,
vmm_get_range,
- PAGE_SHIFT);
+ select_page_shift(uvmm, &op->map));
break;
}
case DRM_GPUVA_OP_REMAP: {
@@ -599,7 +655,7 @@ op_map_prepare(struct nouveau_uvmm *uvmm,
uvma->region = args->region;
uvma->kind = args->kind;
- uvma->page_shift = PAGE_SHIFT;
+ uvma->page_shift = select_page_shift(uvmm, op);
drm_gpuva_map(&uvmm->base, &uvma->va, op);
--
2.51.1
Mohamed Ahmed
2025-Oct-31 10:49 UTC
[PATCH v4 3/5] drm/nouveau/mmu/gp100: Remove unused/broken support for compression
From: Ben Skeggs <bskeggs at nvidia.com>>From GP100 onwards it's not possible to initialise comptag RAM withoutPMU firmware, which nouveau has no support for. As such, this code is essentially a no-op and will always revert to the equivalent non-compressed kind due to comptag allocation failure. It's also broken for the needs of VM_BIND/Vulkan. Remove the code entirely to make way for supporting compression on GPUs that support GSM-RM. Signed-off-by: Ben Skeggs <bskeggs at nvidia.com> Signed-off-by: Mohamed Ahmed <mohamedahmedegypt2001 at gmail.com> Reviewed-by: Lyude Paul <lyude at redhat.com> --- .../drm/nouveau/nvkm/subdev/mmu/vmmgp100.c | 39 ++----------------- .../drm/nouveau/nvkm/subdev/mmu/vmmgp10b.c | 4 +- 2 files changed, 6 insertions(+), 37 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c index 851fd847a2a9..ecff1096a1bb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c @@ -21,9 +21,7 @@ */ #include "vmm.h" -#include <core/client.h> #include <subdev/fb.h> -#include <subdev/ltc.h> #include <subdev/timer.h> #include <engine/gr.h> @@ -117,8 +115,6 @@ gp100_vmm_pgt_pte(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt, { u64 data = (addr >> 4) | map->type; - map->type += ptes * map->ctag; - while (ptes--) { VMM_WO064(pt, vmm, ptei++ * 8, data); data += map->next; @@ -142,7 +138,6 @@ gp100_vmm_pgt_dma(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt, while (ptes--) { const u64 data = (*map->dma++ >> 4) | map->type; VMM_WO064(pt, vmm, ptei++ * 8, data); - map->type += map->ctag; } nvkm_done(pt->memory); return; @@ -200,8 +195,6 @@ gp100_vmm_pd0_pte(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt, { u64 data = (addr >> 4) | map->type; - map->type += ptes * map->ctag; - while (ptes--) { VMM_WO128(pt, vmm, ptei++ * 0x10, data, 0ULL); data += map->next; @@ -411,8 +404,6 @@ gp100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc, struct gp100_vmm_map_vn vn; struct gp100_vmm_map_v0 v0; } *args = argv; - struct nvkm_device *device = vmm->mmu->subdev.device; - struct nvkm_memory *memory = map->memory; u8 kind, kind_inv, priv, ro, vol; int kindn, aper, ret = -ENOSYS; const u8 *kindm; @@ -450,30 +441,8 @@ gp100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc, } if (kindm[kind] != kind) { - u64 tags = nvkm_memory_size(memory) >> 16; - if (aper != 0 || !(page->type & NVKM_VMM_PAGE_COMP)) { - VMM_DEBUG(vmm, "comp %d %02x", aper, page->type); - return -EINVAL; - } - - if (!map->no_comp) { - ret = nvkm_memory_tags_get(memory, device, tags, - nvkm_ltc_tags_clear, - &map->tags); - if (ret) { - VMM_DEBUG(vmm, "comp %d", ret); - return ret; - } - } - - if (!map->no_comp && map->tags->mn) { - tags = map->tags->mn->offset + (map->offset >> 16); - map->ctag |= ((1ULL << page->shift) >> 16) << 36; - map->type |= tags << 36; - map->next |= map->ctag; - } else { - kind = kindm[kind]; - } + /* Revert to non-compressed kind. */ + kind = kindm[kind]; } map->type |= BIT(0); @@ -592,8 +561,8 @@ gp100_vmm = { { 47, &gp100_vmm_desc_16[4], NVKM_VMM_PAGE_Sxxx }, { 38, &gp100_vmm_desc_16[3], NVKM_VMM_PAGE_Sxxx }, { 29, &gp100_vmm_desc_16[2], NVKM_VMM_PAGE_Sxxx }, - { 21, &gp100_vmm_desc_16[1], NVKM_VMM_PAGE_SVxC }, - { 16, &gp100_vmm_desc_16[0], NVKM_VMM_PAGE_SVxC }, + { 21, &gp100_vmm_desc_16[1], NVKM_VMM_PAGE_SVxx }, + { 16, &gp100_vmm_desc_16[0], NVKM_VMM_PAGE_SVxx }, { 12, &gp100_vmm_desc_12[0], NVKM_VMM_PAGE_SVHx }, {} } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp10b.c index e081239afe58..5791d134962b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp10b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp10b.c @@ -34,8 +34,8 @@ gp10b_vmm = { { 47, &gp100_vmm_desc_16[4], NVKM_VMM_PAGE_Sxxx }, { 38, &gp100_vmm_desc_16[3], NVKM_VMM_PAGE_Sxxx }, { 29, &gp100_vmm_desc_16[2], NVKM_VMM_PAGE_Sxxx }, - { 21, &gp100_vmm_desc_16[1], NVKM_VMM_PAGE_SxHC }, - { 16, &gp100_vmm_desc_16[0], NVKM_VMM_PAGE_SxHC }, + { 21, &gp100_vmm_desc_16[1], NVKM_VMM_PAGE_SxHx }, + { 16, &gp100_vmm_desc_16[0], NVKM_VMM_PAGE_SxHx }, { 12, &gp100_vmm_desc_12[0], NVKM_VMM_PAGE_SxHx }, {} } -- 2.51.1
Mohamed Ahmed
2025-Oct-31 10:49 UTC
[PATCH v4 4/5] drm/nouveau/mmu/tu102: Add support for compressed kinds
From: Ben Skeggs <bskeggs at nvidia.com>
Allow compressed PTE kinds to be written into PTEs when GSP-RM is
present, rather than reverting to their non-compressed versions.
Signed-off-by: Ben Skeggs <bskeggs at nvidia.com>
Signed-off-by: Mohamed Ahmed <mohamedahmedegypt2001 at gmail.com>
Reviewed-by: Lyude Paul <lyude at redhat.com>
---
.../drm/nouveau/nvkm/subdev/mmu/vmmgp100.c | 46 ++++++++++++++++++-
1 file changed, 44 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
index ecff1096a1bb..ed15a4475181 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
@@ -109,12 +109,34 @@ gp100_vmm_pgt_pfn(struct nvkm_vmm *vmm, struct nvkm_mmu_pt
*pt,
nvkm_done(pt->memory);
}
+static inline u64
+gp100_vmm_comptag_nr(u64 size)
+{
+ return size >> 16; /* One comptag per 64KiB VRAM. */
+}
+
+static inline u64
+gp100_vmm_pte_comptagline_base(u64 addr)
+{
+ /* RM allocates enough comptags for all of VRAM, so use a 1:1 mapping. */
+ return (1 + gp100_vmm_comptag_nr(addr)) << 36; /*
NV_MMU_VER2_PTE_COMPTAGLINE */
+}
+
+static inline u64
+gp100_vmm_pte_comptagline_incr(u32 page_size)
+{
+ return gp100_vmm_comptag_nr(page_size) << 36; /*
NV_MMU_VER2_PTE_COMPTAGLINE */
+}
+
static inline void
gp100_vmm_pgt_pte(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
u32 ptei, u32 ptes, struct nvkm_vmm_map *map, u64 addr)
{
u64 data = (addr >> 4) | map->type;
+ if (map->ctag)
+ data |= gp100_vmm_pte_comptagline_base(addr);
+
while (ptes--) {
VMM_WO064(pt, vmm, ptei++ * 8, data);
data += map->next;
@@ -195,6 +217,9 @@ gp100_vmm_pd0_pte(struct nvkm_vmm *vmm, struct nvkm_mmu_pt
*pt,
{
u64 data = (addr >> 4) | map->type;
+ if (map->ctag)
+ data |= gp100_vmm_pte_comptagline_base(addr);
+
while (ptes--) {
VMM_WO128(pt, vmm, ptei++ * 0x10, data, 0ULL);
data += map->next;
@@ -440,9 +465,26 @@ gp100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
return -EINVAL;
}
+ /* Handle compression. */
if (kindm[kind] != kind) {
- /* Revert to non-compressed kind. */
- kind = kindm[kind];
+ struct nvkm_device *device = vmm->mmu->subdev.device;
+
+ /* Compression is only supported when using GSP-RM, as
+ * PMU firmware is required in order to initialise the
+ * compbit backing store.
+ */
+ if (nvkm_gsp_rm(device->gsp)) {
+ /* Turing GPUs require PTE_COMPTAGLINE to be filled,
+ * in addition to specifying a compressed kind.
+ */
+ if (device->card_type < GA100) {
+ map->ctag = gp100_vmm_pte_comptagline_incr(1 <<
map->page->shift);
+ map->next |= map->ctag;
+ }
+ } else {
+ /* Revert to non-compressed kind. */
+ kind = kindm[kind];
+ }
}
map->type |= BIT(0);
--
2.51.1
Mohamed Ahmed
2025-Oct-31 10:49 UTC
[PATCH v4 5/5] drm/nouveau/drm: Bump the driver version to 1.4.1 to report new features
The HW can only do compression on large and huge pages, and enabling it on 4K pages leads to a MMU fault. Compression also needs kernel support for handling the compressed kinds and managing the compression tags. This increments the nouveau version number which allows NVK to enable it only when the kernel actually supports both features and avoid breaking the system if a newer mesa version is paired with an older kernel version. For the associated userspace MR, please see !36450: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36450 Signed-off-by: Mohamed Ahmed <mohamedahmedegypt2001 at gmail.com> Reviewed-by: Lyude Paul <lyude at redhat.com> --- drivers/gpu/drm/nouveau/nouveau_drv.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 55abc510067b..e5de4367e2cc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -10,7 +10,7 @@ #define DRIVER_MAJOR 1 #define DRIVER_MINOR 4 -#define DRIVER_PATCHLEVEL 0 +#define DRIVER_PATCHLEVEL 1 /* * 1.1.1: @@ -35,6 +35,8 @@ * programs that get directly linked with NVKM. * 1.3.1: * - implemented limited ABI16/NVIF interop + * 1.4.1: + * - add variable page sizes and compression for Turing+ */ #include <linux/notifier.h> -- 2.51.1