[PATCH 12/44] drm/amdkfd: add xnack enabled flag to kfd_process

Felix Kuehling Felix.Kuehling at amd.com
Mon Mar 22 10:58:28 UTC 2021


From: Alex Sierra <alex.sierra at amd.com>

This flag is useful at cpu invalidation page table
decision. Between select queue eviction or page fault.

Signed-off-by: Alex Sierra <alex.sierra at amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h    |  4 +++
 drivers/gpu/drm/amd/amdkfd/kfd_process.c | 36 ++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 7d70af26b5c7..d66430740e52 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -824,6 +824,8 @@ struct kfd_process {
 	/* shared virtual memory registered by this process */
 	struct svm_range_list svms;
 	bool svm_disabled;
+
+	bool xnack_enabled;
 };
 
 #define KFD_PROCESS_TABLE_SIZE 5 /* bits: 32 entries */
@@ -877,6 +879,8 @@ struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev,
 struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 							struct kfd_process *p);
 
+bool kfd_process_xnack_supported(struct kfd_process *p);
+
 int kfd_reserved_mem_mmap(struct kfd_dev *dev, struct kfd_process *process,
 			  struct vm_area_struct *vma);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 321895d7555a..c8479f6bd68c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1193,6 +1193,39 @@ void kfd_process_set_trap_handler(struct qcm_process_device *qpd,
 	}
 }
 
+bool kfd_process_xnack_supported(struct kfd_process *p)
+{
+	int i;
+
+	/* On most GFXv9 GPUs, the retry mode in the SQ must match the
+	 * boot time retry setting. Mixing processes with different
+	 * XNACK/retry settings can hang the GPU.
+	 *
+	 * Different GPUs can have different noretry settings depending
+	 * on HW bugs or limitations. We need to find at least one
+	 * XNACK mode for this process that's compatible with all GPUs.
+	 * Fortunately GPUs with retry enabled (noretry=0) can run code
+	 * built for XNACK-off. On GFXv9 it may perform slower.
+	 *
+	 * Therefore applications built for XNACK-off can always be
+	 * supported and will be our fallback if any GPU does not
+	 * support retry.
+	 */
+	for (i = 0; i < p->n_pdds; i++) {
+		struct kfd_dev *dev = p->pdds[i]->dev;
+
+		/* Only consider GFXv9 and higher GPUs. Older GPUs don't
+		 * support the SVM APIs and don't need to be considered
+		 * for the XNACK mode selection.
+		 */
+		if (dev->device_info->asic_family >= CHIP_VEGA10 &&
+		    dev->noretry)
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * On return the kfd_process is fully operational and will be freed when the
  * mm is released
@@ -1232,6 +1265,9 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 	if (err != 0)
 		goto err_init_apertures;
 
+	/* Check XNACK support after PDDs are created in kfd_init_apertures */
+	process->xnack_enabled = kfd_process_xnack_supported(process);
+
 	err = svm_range_list_init(process);
 	if (err)
 		goto err_init_svm_range_list;
-- 
2.31.0



More information about the amd-gfx mailing list