5.15-stable patches

added patches:
	drm-amdgpu-set-vmbo-destroy-after-pt-bo-is-created.patch

diff --git a/queue-5.15/drm-amdgpu-set-vmbo-destroy-after-pt-bo-is-created.patch b/queue-5.15/drm-amdgpu-set-vmbo-destroy-after-pt-bo-is-created.patch
new file mode 100644 (file)
index 0000000..702943e
--- /dev/null
+++ b/queue-5.15/drm-amdgpu-set-vmbo-destroy-after-pt-bo-is-created.patch
@@ -0,0 +1,68 @@
+From 9a3c6067bd2ee2ca2652fbb0679f422f3c9109f9 Mon Sep 17 00:00:00 2001
+From: Philip Yang <Philip.Yang@amd.com>
+Date: Mon, 3 Oct 2022 13:03:26 -0400
+Subject: drm/amdgpu: Set vmbo destroy after pt bo is created
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Philip Yang <Philip.Yang@amd.com>
+
+commit 9a3c6067bd2ee2ca2652fbb0679f422f3c9109f9 upstream.
+
+Under VRAM usage pression, map to GPU may fail to create pt bo and
+vmbo->shadow_list is not initialized, then ttm_bo_release calling
+amdgpu_bo_vm_destroy to access vmbo->shadow_list generates below
+dmesg and NULL pointer access backtrace:
+
+Set vmbo destroy callback to amdgpu_bo_vm_destroy only after creating pt
+bo successfully, otherwise use default callback amdgpu_bo_destroy.
+
+amdgpu: amdgpu_vm_bo_update failed
+amdgpu: update_gpuvm_pte() failed
+amdgpu: Failed to map bo to gpuvm
+amdgpu 0000:43:00.0: amdgpu: Failed to map peer:0000:43:00.0 mem_domain:2
+BUG: kernel NULL pointer dereference, address:
+ RIP: 0010:amdgpu_bo_vm_destroy+0x4d/0x80 [amdgpu]
+ Call Trace:
+  <TASK>
+  ttm_bo_release+0x207/0x320 [amdttm]
+  amdttm_bo_init_reserved+0x1d6/0x210 [amdttm]
+  amdgpu_bo_create+0x1ba/0x520 [amdgpu]
+  amdgpu_bo_create_vm+0x3a/0x80 [amdgpu]
+  amdgpu_vm_pt_create+0xde/0x270 [amdgpu]
+  amdgpu_vm_ptes_update+0x63b/0x710 [amdgpu]
+  amdgpu_vm_update_range+0x2e7/0x6e0 [amdgpu]
+  amdgpu_vm_bo_update+0x2bd/0x600 [amdgpu]
+  update_gpuvm_pte+0x160/0x420 [amdgpu]
+  amdgpu_amdkfd_gpuvm_map_memory_to_gpu+0x313/0x1130 [amdgpu]
+  kfd_ioctl_map_memory_to_gpu+0x115/0x390 [amdgpu]
+  kfd_ioctl+0x24a/0x5b0 [amdgpu]
+
+Signed-off-by: Philip Yang <Philip.Yang@amd.com>
+Reviewed-by: Christian König <christian.koenig@amd.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+[ This fixes a regression introduced by commit 1cc40dccad76 ("drm/amdgpu:
+  fix Null pointer dereference error in amdgpu_device_recover_vram") in
+  5.15.118. It's a hand modified cherry-pick because that commit that
+  introduced the regression touched nearby code and the context is now
+  incorrect. ]
+Cc: Linux Regressions <regressions@lists.linux.dev>
+Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2650
+Fixes: 1cc40dccad76 ("drm/amdgpu: fix Null pointer dereference error in amdgpu_device_recover_vram")
+Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/gpu/drm/amd/amdgpu/amdgpu_object.c |    1 -
+ 1 file changed, 1 deletion(-)
+
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+@@ -685,7 +685,6 @@ int amdgpu_bo_create_vm(struct amdgpu_de
+        * num of amdgpu_vm_pt entries.
+        */
+       BUG_ON(bp->bo_ptr_size < sizeof(struct amdgpu_bo_vm));
+-      bp->destroy = &amdgpu_bo_vm_destroy;
+       r = amdgpu_bo_create(adev, bp, &bo_ptr);
+       if (r)
+               return r;

diff --git a/queue-5.15/series b/queue-5.15/series
index f74c86f70406379f10c8e6f19b485afd74f773f5..deaadceeabc4d71fe28261507ceb16fa0f1b6f95 100644 (file)
--- a/queue-5.15/series
+++ b/queue-5.15/series
@@ -2,3 +2,4 @@ mptcp-fix-possible-divide-by-zero-in-recvmsg.patch
 mptcp-consolidate-fallback-and-non-fallback-state-machine.patch
 mm-hwpoison-try-to-recover-from-copy-on-write-faults.patch
 mm-hwpoison-when-copy-on-write-hits-poison-take-page-offline.patch
+drm-amdgpu-set-vmbo-destroy-after-pt-bo-is-created.patch