drm/amdgpu: add an option to allow gpu partition allocate all available memory

Current driver reports and limits memory allocation for each partition equally
among partitions using same memory partition. Application may not be able to
use all available memory when run on a partitioned gpu though system still has
enough free memory.

Add an option that app can use to have gpu partition allocate all available
memory.

Signed-off-by: Xiaogang Chen <xiaogang.chen@amd.com>
Reviewed-by: Philip Yang <philip.yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 4f27c75abedb6f227ebe0e238b0334a3005c9fa5..d9e283f3b57d5b267baed3889d736152ff3f46e2 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -805,7 +805,10 @@ u64 amdgpu_amdkfd_xcp_memory_size(struct amdgpu_device *adev, int xcp_id)
                } else {
                        tmp = adev->gmc.mem_partitions[mem_id].size;
                }
-               do_div(tmp, adev->xcp_mgr->num_xcp_per_mem_partition);
+
+               if (adev->xcp_mgr->mem_alloc_mode == AMDGPU_PARTITION_MEM_CAPPING_EVEN)
+                       do_div(tmp, adev->xcp_mgr->num_xcp_per_mem_partition);
+
                return ALIGN_DOWN(tmp, PAGE_SIZE);
        } else if (adev->apu_prefer_gtt) {
                return (ttm_tt_pages_limit() << PAGE_SHIFT);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index cab3196a87fb1105833e46c09c7dfb388eadcfa2..2956e45c92549b68760d351c351b0315f6a6b07b 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1580,6 +1580,36 @@ static ssize_t amdgpu_gfx_set_compute_partition(struct device *dev,
        return count;
 }
 
+static ssize_t compute_partition_mem_alloc_mode_show(struct device *dev,
+                                               struct device_attribute *addr,
+                                               char *buf)
+{
+       struct drm_device *ddev = dev_get_drvdata(dev);
+       struct amdgpu_device *adev = drm_to_adev(ddev);
+       int mode = adev->xcp_mgr->mem_alloc_mode;
+
+       return sysfs_emit(buf, "%s\n",
+                         amdgpu_gfx_compute_mem_alloc_mode_desc(mode));
+}
+
+
+static ssize_t compute_partition_mem_alloc_mode_store(struct device *dev,
+                                               struct device_attribute *addr,
+                                               const char *buf, size_t count)
+{
+       struct drm_device *ddev = dev_get_drvdata(dev);
+       struct amdgpu_device *adev = drm_to_adev(ddev);
+
+       if (!strncasecmp("CAPPING", buf, strlen("CAPPING")))
+               adev->xcp_mgr->mem_alloc_mode = AMDGPU_PARTITION_MEM_CAPPING_EVEN;
+       else if (!strncasecmp("ALL", buf, strlen("ALL")))
+               adev->xcp_mgr->mem_alloc_mode = AMDGPU_PARTITION_MEM_ALLOC_ALL;
+       else
+               return -EINVAL;
+
+       return count;
+}
+
 static const char *xcp_desc[] = {
        [AMDGPU_SPX_PARTITION_MODE] = "SPX",
        [AMDGPU_DPX_PARTITION_MODE] = "DPX",
@@ -1935,6 +1965,10 @@ static DEVICE_ATTR(gfx_reset_mask, 0444,
 static DEVICE_ATTR(compute_reset_mask, 0444,
                   amdgpu_gfx_get_compute_reset_mask, NULL);
 
+static DEVICE_ATTR(compute_partition_mem_alloc_mode, 0644,
+                  compute_partition_mem_alloc_mode_show,
+                  compute_partition_mem_alloc_mode_store);
+
 static int amdgpu_gfx_sysfs_xcp_init(struct amdgpu_device *adev)
 {
        struct amdgpu_xcp_mgr *xcp_mgr = adev->xcp_mgr;
@@ -1955,6 +1989,11 @@ static int amdgpu_gfx_sysfs_xcp_init(struct amdgpu_device *adev)
        if (r)
                return r;
 
+       r = device_create_file(adev->dev,
+                              &dev_attr_compute_partition_mem_alloc_mode);
+       if (r)
+               return r;
+
        if (xcp_switch_supported)
                r = device_create_file(adev->dev,
                                       &dev_attr_available_compute_partition);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 2785eda6fea52da9d0e8c74a8d8b70d7c27b6f25..a0cf0a3b41dafd9d39a2ef2569b4061d7ecf99c5 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -71,6 +71,11 @@ enum amdgpu_gfx_partition {
        AMDGPU_AUTO_COMPUTE_PARTITION_MODE = -2,
 };
 
+enum amdgpu_gfx_partition_mem_alloc_mode {
+       AMDGPU_PARTITION_MEM_CAPPING_EVEN = 0,
+       AMDGPU_PARTITION_MEM_ALLOC_ALL  = 1,
+};
+
 #define NUM_XCC(x) hweight16(x)
 
 enum amdgpu_gfx_ras_mem_id_type {
@@ -677,4 +682,16 @@ static inline const char *amdgpu_gfx_compute_mode_desc(int mode)
        }
 }
 
+static inline const char *amdgpu_gfx_compute_mem_alloc_mode_desc(int mode)
+{
+       switch (mode) {
+       case AMDGPU_PARTITION_MEM_CAPPING_EVEN:
+                       return "CAPPING";
+       case AMDGPU_PARTITION_MEM_ALLOC_ALL:
+               return "ALL";
+       default:
+               return "UNKNOWN";
+       }
+}
+
 #endif

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
index cc5f4e01e38f42906d5372b943d7966030efc83c..42be8ee155dde010e6043f01806993ccc07fb28e 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
@@ -181,6 +181,7 @@ int amdgpu_xcp_init(struct amdgpu_xcp_mgr *xcp_mgr, int num_xcps, int mode)
        }
 
        xcp_mgr->num_xcps = num_xcps;
+       xcp_mgr->mem_alloc_mode = AMDGPU_PARTITION_MEM_CAPPING_EVEN;
        amdgpu_xcp_update_partition_sched_list(adev);
 
        return 0;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h
index 8058e8f35d4149b4c10fd627ece3032cff42c70f..878c1c422893cf4b0688e70364461334fc21e6bb 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h
@@ -132,6 +132,8 @@ struct amdgpu_xcp_mgr {
        struct amdgpu_xcp_cfg *xcp_cfg;
        uint32_t supp_xcp_modes;
        uint32_t avail_xcp_modes;
+       /* used to determin KFD memory alloc mode for each partition */
+       uint32_t mem_alloc_mode;
 };
 
 struct amdgpu_xcp_mgr_funcs {