drm/radeon/kms: fence cleanup + more reliable GPU lockup detection V4

This patch cleanup the fence code, it drops the timeout field of
fence as the time to complete each IB is unpredictable and shouldn't
be bound.

The fence cleanup lead to GPU lockup detection improvement, this
patch introduce a callback, allowing to do asic specific test for
lockup detection. In this patch the CP is use as a first indicator
of GPU lockup. If CP doesn't make progress during 1second we assume
we are facing a GPU lockup.

To avoid overhead of testing GPU lockup frequently due to fence
taking time to be signaled we query the lockup callback every
500msec. There is plenty code comment explaining the design & choise
inside the code.

This have been tested mostly on R3XX/R5XX hw, in normal running
destkop (compiz firefox, quake3 running) the lockup callback wasn't
call once (1 hour session). Also tested with forcing GPU lockup and
lockup was reported after the 1s CP activity timeout.

V2 switch to 500ms timeout so GPU lockup get call at least 2 times
   in less than 2sec.
V3 store last jiffies in fence struct so on ERESTART, EBUSY we keep
   track of how long we already wait for a given fence
V4 make sure we got up to date cp read pointer so we don't have
   false positive

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 14 insertions, 1 deletions

diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index a4b4bc9fa32..7e21985139f 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -134,6 +134,7 @@ static struct radeon_asic r100_asic = {
 	.suspend = &r100_suspend,
 	.resume = &r100_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r100_gpu_is_lockup,
 	.gpu_reset = &r100_gpu_reset,
 	.gart_tlb_flush = &r100_pci_gart_tlb_flush,
 	.gart_set_page = &r100_pci_gart_set_page,
@@ -172,6 +173,7 @@ static struct radeon_asic r200_asic = {
 	.suspend = &r100_suspend,
 	.resume = &r100_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r100_gpu_is_lockup,
 	.gpu_reset = &r100_gpu_reset,
 	.gart_tlb_flush = &r100_pci_gart_tlb_flush,
 	.gart_set_page = &r100_pci_gart_set_page,
@@ -209,6 +211,7 @@ static struct radeon_asic r300_asic = {
 	.suspend = &r300_suspend,
 	.resume = &r300_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r300_gpu_is_lockup,
 	.gpu_reset = &r300_gpu_reset,
 	.gart_tlb_flush = &r100_pci_gart_tlb_flush,
 	.gart_set_page = &r100_pci_gart_set_page,
@@ -247,6 +250,7 @@ static struct radeon_asic r300_asic_pcie = {
 	.suspend = &r300_suspend,
 	.resume = &r300_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r300_gpu_is_lockup,
 	.gpu_reset = &r300_gpu_reset,
 	.gart_tlb_flush = &rv370_pcie_gart_tlb_flush,
 	.gart_set_page = &rv370_pcie_gart_set_page,
@@ -284,6 +288,7 @@ static struct radeon_asic r420_asic = {
 	.suspend = &r420_suspend,
 	.resume = &r420_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r300_gpu_is_lockup,
 	.gpu_reset = &r300_gpu_reset,
 	.gart_tlb_flush = &rv370_pcie_gart_tlb_flush,
 	.gart_set_page = &rv370_pcie_gart_set_page,
@@ -322,6 +327,7 @@ static struct radeon_asic rs400_asic = {
 	.suspend = &rs400_suspend,
 	.resume = &rs400_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r300_gpu_is_lockup,
 	.gpu_reset = &r300_gpu_reset,
 	.gart_tlb_flush = &rs400_gart_tlb_flush,
 	.gart_set_page = &rs400_gart_set_page,
@@ -360,6 +366,7 @@ static struct radeon_asic rs600_asic = {
 	.suspend = &rs600_suspend,
 	.resume = &rs600_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r300_gpu_is_lockup,
 	.gpu_reset = &r300_gpu_reset,
 	.gart_tlb_flush = &rs600_gart_tlb_flush,
 	.gart_set_page = &rs600_gart_set_page,
@@ -398,6 +405,7 @@ static struct radeon_asic rs690_asic = {
 	.suspend = &rs690_suspend,
 	.resume = &rs690_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r300_gpu_is_lockup,
 	.gpu_reset = &r300_gpu_reset,
 	.gart_tlb_flush = &rs400_gart_tlb_flush,
 	.gart_set_page = &rs400_gart_set_page,
@@ -436,6 +444,7 @@ static struct radeon_asic rv515_asic = {
 	.suspend = &rv515_suspend,
 	.resume = &rv515_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r300_gpu_is_lockup,
 	.gpu_reset = &rv515_gpu_reset,
 	.gart_tlb_flush = &rv370_pcie_gart_tlb_flush,
 	.gart_set_page = &rv370_pcie_gart_set_page,
@@ -474,6 +483,7 @@ static struct radeon_asic r520_asic = {
 	.suspend = &rv515_suspend,
 	.resume = &r520_resume,
 	.vga_set_state = &r100_vga_set_state,
+	.gpu_is_lockup = &r300_gpu_is_lockup,
 	.gpu_reset = &rv515_gpu_reset,
 	.gart_tlb_flush = &rv370_pcie_gart_tlb_flush,
 	.gart_set_page = &rv370_pcie_gart_set_page,
@@ -513,6 +523,7 @@ static struct radeon_asic r600_asic = {
 	.resume = &r600_resume,
 	.cp_commit = &r600_cp_commit,
 	.vga_set_state = &r600_vga_set_state,
+	.gpu_is_lockup = &r600_gpu_is_lockup,
 	.gpu_reset = &r600_gpu_reset,
 	.gart_tlb_flush = &r600_pcie_gart_tlb_flush,
 	.gart_set_page = &rs600_gart_set_page,
@@ -586,7 +597,8 @@ static struct radeon_asic rv770_asic = {
 	.suspend = &rv770_suspend,
 	.resume = &rv770_resume,
 	.cp_commit = &r600_cp_commit,
-	.gpu_reset = &rv770_gpu_reset,
+	.gpu_reset = &r600_gpu_reset,
+	.gpu_is_lockup = &r600_gpu_is_lockup,
 	.vga_set_state = &r600_vga_set_state,
 	.gart_tlb_flush = &r600_pcie_gart_tlb_flush,
 	.gart_set_page = &rs600_gart_set_page,
@@ -623,6 +635,7 @@ static struct radeon_asic evergreen_asic = {
 	.suspend = &evergreen_suspend,
 	.resume = &evergreen_resume,
 	.cp_commit = NULL,
+	.gpu_is_lockup = &evergreen_gpu_is_lockup,
 	.gpu_reset = &evergreen_gpu_reset,
 	.vga_set_state = &r600_vga_set_state,
 	.gart_tlb_flush = &r600_pcie_gart_tlb_flush,