diff mbox series

[v5,01/27] drm/ttm: Remap all page faults to per process dummy page.

Message ID 20210428151207.1212258-2-andrey.grodzovsky@amd.com (mailing list archive)
State New, archived
Headers show
Series RFC Support hot device unplug in amdgpu | expand

Commit Message

Andrey Grodzovsky April 28, 2021, 3:11 p.m. UTC
On device removal reroute all CPU mappings to dummy page.

v3:
Remove loop to find DRM file and instead access it
by vma->vm_file->private_data. Move dummy page installation
into a separate function.

v4:
Map the entire BOs VA space into on demand allocated dummy page
on the first fault for that BO.

v5: Remove duplicate return.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo_vm.c | 79 ++++++++++++++++++++++++++++++++-
 include/drm/ttm/ttm_bo_api.h    |  2 +
 2 files changed, 80 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index b31b18058965..8b8300551a7f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -34,6 +34,8 @@ 
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_placement.h>
 #include <drm/drm_vma_manager.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_managed.h>
 #include <linux/mm.h>
 #include <linux/pfn_t.h>
 #include <linux/rbtree.h>
@@ -380,19 +382,94 @@  vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 }
 EXPORT_SYMBOL(ttm_bo_vm_fault_reserved);
 
+static void ttm_bo_release_dummy_page(struct drm_device *dev, void *res)
+{
+	struct page *dummy_page = (struct page *)res;
+
+	__free_page(dummy_page);
+}
+
+vm_fault_t ttm_bo_vm_dummy_page(struct vm_fault *vmf, pgprot_t prot)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct ttm_buffer_object *bo = vma->vm_private_data;
+	struct drm_device *ddev = bo->base.dev;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
+	unsigned long address = vma->vm_start;
+	unsigned long num_prefault = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long pfn;
+	struct page *page;
+	int i;
+
+	/*
+	 * Wait for buffer data in transit, due to a pipelined
+	 * move.
+	 */
+	ret = ttm_bo_vm_fault_idle(bo, vmf);
+	if (unlikely(ret != 0))
+		return ret;
+
+	/* Allocate new dummy page to map all the VA range in this VMA to it*/
+	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!page)
+		return VM_FAULT_OOM;
+
+	pfn = page_to_pfn(page);
+
+	/*
+	 * Prefault the entire VMA range right away to avoid further faults
+	 */
+	for (i = 0; i < num_prefault; ++i) {
+
+		if (unlikely(address >= vma->vm_end))
+			break;
+
+		if (vma->vm_flags & VM_MIXEDMAP)
+			ret = vmf_insert_mixed_prot(vma, address,
+						    __pfn_to_pfn_t(pfn, PFN_DEV),
+						    prot);
+		else
+			ret = vmf_insert_pfn_prot(vma, address, pfn, prot);
+
+		/* Never error on prefaulted PTEs */
+		if (unlikely((ret & VM_FAULT_ERROR))) {
+			if (i == 0)
+				return VM_FAULT_NOPAGE;
+			else
+				break;
+		}
+
+		address += PAGE_SIZE;
+	}
+
+	/* Set the page to be freed using drmm release action */
+	if (drmm_add_action_or_reset(ddev, ttm_bo_release_dummy_page, page))
+		return VM_FAULT_OOM;
+
+	return ret;
+}
+EXPORT_SYMBOL(ttm_bo_vm_dummy_page);
+
 vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	pgprot_t prot;
 	struct ttm_buffer_object *bo = vma->vm_private_data;
+	struct drm_device *ddev = bo->base.dev;
 	vm_fault_t ret;
+	int idx;
 
 	ret = ttm_bo_vm_reserve(bo, vmf);
 	if (ret)
 		return ret;
 
 	prot = vma->vm_page_prot;
-	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT, 1);
+	if (drm_dev_enter(ddev, &idx)) {
+		ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT, 1);
+		drm_dev_exit(idx);
+	} else {
+		ret = ttm_bo_vm_dummy_page(vmf, prot);
+	}
 	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
 		return ret;
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 3587f660e8f4..dbb00e495cb4 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -635,4 +635,6 @@  int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
 		     void *buf, int len, int write);
 bool ttm_bo_delayed_delete(struct ttm_device *bdev, bool remove_all);
 
+vm_fault_t ttm_bo_vm_dummy_page(struct vm_fault *vmf, pgprot_t prot);
+
 #endif