From: Alex Deucher alexander.deucher@amd.com
Helpful for debugging GPUVM errors as we can see what hw block and page generated the fault in the log.
v2: simplify fault decoding
Signed-off-by: Alex Deucher alexander.deucher@amd.com Reviewed-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/radeon/evergreen.c | 10 ++- drivers/gpu/drm/radeon/ni.c | 161 ++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/radeon/nid.h | 16 ++++ 3 files changed, 185 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 9e14007..bc6936a 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -139,6 +139,8 @@ void evergreen_pcie_gen2_enable(struct radeon_device *rdev); void evergreen_program_aspm(struct radeon_device *rdev); extern void cayman_cp_int_cntl_setup(struct radeon_device *rdev, int ring, u32 cp_int_cntl); +extern void cayman_vm_decode_fault(struct radeon_device *rdev, + u32 status, u32 addr);
static const u32 evergreen_golden_registers[] = { @@ -4629,6 +4631,7 @@ int evergreen_irq_process(struct radeon_device *rdev) bool queue_hotplug = false; bool queue_hdmi = false; bool queue_thermal = false; + u32 status, addr;
if (!rdev->ih.enabled || rdev->shutdown) return IRQ_NONE; @@ -4915,11 +4918,14 @@ restart_ih: break; case 146: case 147: + addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR); + status = RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS); dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data); dev_err(rdev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", - RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR)); + addr); dev_err(rdev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", - RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS)); + status); + cayman_vm_decode_fault(rdev, status, addr); /* reset addr and status */ WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1); break; diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 465b17e..56bd4f3 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -2450,6 +2450,167 @@ void cayman_vm_fini(struct radeon_device *rdev) { }
+/** + * cayman_vm_decode_fault - print human readable fault info + * + * @rdev: radeon_device pointer + * @status: VM_CONTEXT1_PROTECTION_FAULT_STATUS register value + * @addr: VM_CONTEXT1_PROTECTION_FAULT_ADDR register value + * + * Print human readable fault information (cayman/TN). + */ +void cayman_vm_decode_fault(struct radeon_device *rdev, + u32 status, u32 addr) +{ + u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT; + u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT; + u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT; + char *block; + + switch (mc_id) { + case 32: + case 16: + case 96: + case 80: + case 160: + case 144: + case 224: + case 208: + block = "CB"; + break; + case 33: + case 17: + case 97: + case 81: + case 161: + case 145: + case 225: + case 209: + block = "CB_FMASK"; + break; + case 34: + case 18: + case 98: + case 82: + case 162: + case 146: + case 226: + case 210: + block = "CB_CMASK"; + break; + case 35: + case 19: + case 99: + case 83: + case 163: + case 147: + case 227: + case 211: + block = "CB_IMMED"; + break; + case 36: + case 20: + case 100: + case 84: + case 164: + case 148: + case 228: + case 212: + block = "DB"; + break; + case 37: + case 21: + case 101: + case 85: + case 165: + case 149: + case 229: + case 213: + block = "DB_HTILE"; + break; + case 38: + case 22: + case 102: + case 86: + case 166: + case 150: + case 230: + case 214: + block = "SX"; + break; + case 39: + case 23: + case 103: + case 87: + case 167: + case 151: + case 231: + case 215: + block = "DB_STEN"; + break; + case 40: + case 24: + case 104: + case 88: + case 232: + case 216: + case 168: + case 152: + block = "TC_TFETCH"; + break; + case 41: + case 25: + case 105: + case 89: + case 233: + case 217: + case 169: + case 153: + block = "TC_VFETCH"; + break; + case 42: + case 26: + case 106: + case 90: + case 234: + case 218: + case 170: + case 154: + block = "VC"; + break; + case 112: + block = "CP"; + break; + case 113: + case 114: + block = "SH"; + break; + case 115: + block = "VGT"; + break; + case 178: + block = "IH"; + break; + case 51: + block = "RLC"; + break; + case 55: + block = "DMA"; + break; + case 56: + block = "HDP"; + break; + default: + block = "unknown"; + break; + } + + printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n", + protections, vmid, addr, + (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read", + block, mc_id); +} + #define R600_ENTRY_VALID (1 << 0) #define R600_PTE_SYSTEM (1 << 1) #define R600_PTE_SNOOPED (1 << 2) diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h index fe24a93..22421bc 100644 --- a/drivers/gpu/drm/radeon/nid.h +++ b/drivers/gpu/drm/radeon/nid.h @@ -133,6 +133,22 @@ #define VM_CONTEXT1_CNTL2 0x1434 #define VM_INVALIDATE_REQUEST 0x1478 #define VM_INVALIDATE_RESPONSE 0x147c +#define VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x14FC +#define VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x14DC +#define PROTECTIONS_MASK (0xf << 0) +#define PROTECTIONS_SHIFT 0 + /* bit 0: range + * bit 2: pde0 + * bit 3: valid + * bit 4: read + * bit 5: write + */ +#define MEMORY_CLIENT_ID_MASK (0xff << 12) +#define MEMORY_CLIENT_ID_SHIFT 12 +#define MEMORY_CLIENT_RW_MASK (1 << 24) +#define MEMORY_CLIENT_RW_SHIFT 24 +#define FAULT_VMID_MASK (0x7 << 25) +#define FAULT_VMID_SHIFT 25 #define VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR 0x1518 #define VM_CONTEXT1_PROTECTION_FAULT_DEFAULT_ADDR 0x151c #define VM_CONTEXT0_PAGE_TABLE_BASE_ADDR 0x153C
From: Alex Deucher alexander.deucher@amd.com
Helpful for debugging GPUVM errors as we can see what hw block and page generated the fault in the log.
v2: simplify fault decoding
Signed-off-by: Alex Deucher alexander.deucher@amd.com Reviewed-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/radeon/si.c | 272 +++++++++++++++++++++++++++++++++++++++++- drivers/gpu/drm/radeon/sid.h | 14 ++ 2 files changed, 284 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index f305768..d3f0507 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -4390,6 +4390,270 @@ void si_vm_fini(struct radeon_device *rdev) }
/** + * si_vm_decode_fault - print human readable fault info + * + * @rdev: radeon_device pointer + * @status: VM_CONTEXT1_PROTECTION_FAULT_STATUS register value + * @addr: VM_CONTEXT1_PROTECTION_FAULT_ADDR register value + * + * Print human readable fault information (SI). + */ +static void si_vm_decode_fault(struct radeon_device *rdev, + u32 status, u32 addr) +{ + u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT; + u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT; + u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT; + char *block; + + if (rdev->family == CHIP_TAHITI) { + switch (mc_id) { + case 160: + case 144: + case 96: + case 80: + case 224: + case 208: + case 32: + case 16: + block = "CB"; + break; + case 161: + case 145: + case 97: + case 81: + case 225: + case 209: + case 33: + case 17: + block = "CB_FMASK"; + break; + case 162: + case 146: + case 98: + case 82: + case 226: + case 210: + case 34: + case 18: + block = "CB_CMASK"; + break; + case 163: + case 147: + case 99: + case 83: + case 227: + case 211: + case 35: + case 19: + block = "CB_IMMED"; + break; + case 164: + case 148: + case 100: + case 84: + case 228: + case 212: + case 36: + case 20: + block = "DB"; + break; + case 165: + case 149: + case 101: + case 85: + case 229: + case 213: + case 37: + case 21: + block = "DB_HTILE"; + break; + case 167: + case 151: + case 103: + case 87: + case 231: + case 215: + case 39: + case 23: + block = "DB_STEN"; + break; + case 72: + case 68: + case 64: + case 8: + case 4: + case 0: + case 136: + case 132: + case 128: + case 200: + case 196: + case 192: + block = "TC"; + break; + case 112: + case 48: + block = "CP"; + break; + case 49: + case 177: + case 50: + case 178: + block = "SH"; + break; + case 53: + case 190: + block = "VGT"; + break; + case 117: + block = "IH"; + break; + case 51: + case 115: + block = "RLC"; + break; + case 119: + case 183: + block = "DMA0"; + break; + case 61: + block = "DMA1"; + break; + case 248: + case 120: + block = "HDP"; + break; + default: + block = "unknown"; + break; + } + } else { + switch (mc_id) { + case 32: + case 16: + case 96: + case 80: + case 160: + case 144: + case 224: + case 208: + block = "CB"; + break; + case 33: + case 17: + case 97: + case 81: + case 161: + case 145: + case 225: + case 209: + block = "CB_FMASK"; + break; + case 34: + case 18: + case 98: + case 82: + case 162: + case 146: + case 226: + case 210: + block = "CB_CMASK"; + break; + case 35: + case 19: + case 99: + case 83: + case 163: + case 147: + case 227: + case 211: + block = "CB_IMMED"; + break; + case 36: + case 20: + case 100: + case 84: + case 164: + case 148: + case 228: + case 212: + block = "DB"; + break; + case 37: + case 21: + case 101: + case 85: + case 165: + case 149: + case 229: + case 213: + block = "DB_HTILE"; + break; + case 39: + case 23: + case 103: + case 87: + case 167: + case 151: + case 231: + case 215: + block = "DB_STEN"; + break; + case 72: + case 68: + case 8: + case 4: + case 136: + case 132: + case 200: + case 196: + block = "TC"; + break; + case 112: + case 48: + block = "CP"; + break; + case 49: + case 177: + case 50: + case 178: + block = "SH"; + break; + case 53: + block = "VGT"; + break; + case 117: + block = "IH"; + break; + case 51: + case 115: + block = "RLC"; + break; + case 119: + case 183: + block = "DMA0"; + break; + case 61: + block = "DMA1"; + break; + case 248: + case 120: + block = "HDP"; + break; + default: + block = "unknown"; + break; + } + } + + printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n", + protections, vmid, addr, + (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read", + block, mc_id); +} + +/** * si_vm_set_page - update the page tables using the CP * * @rdev: radeon_device pointer @@ -5755,6 +6019,7 @@ int si_irq_process(struct radeon_device *rdev) u32 ring_index; bool queue_hotplug = false; bool queue_thermal = false; + u32 status, addr;
if (!rdev->ih.enabled || rdev->shutdown) return IRQ_NONE; @@ -5990,11 +6255,14 @@ restart_ih: break; case 146: case 147: + addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR); + status = RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS); dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data); dev_err(rdev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", - RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR)); + addr); dev_err(rdev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", - RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS)); + status); + si_vm_decode_fault(rdev, status, addr); /* reset addr and status */ WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1); break; diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h index 12a20eb..2c8da27 100644 --- a/drivers/gpu/drm/radeon/sid.h +++ b/drivers/gpu/drm/radeon/sid.h @@ -367,6 +367,20 @@
#define VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x14FC #define VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x14DC +#define PROTECTIONS_MASK (0xf << 0) +#define PROTECTIONS_SHIFT 0 + /* bit 0: range + * bit 1: pde0 + * bit 2: valid + * bit 3: read + * bit 4: write + */ +#define MEMORY_CLIENT_ID_MASK (0xff << 12) +#define MEMORY_CLIENT_ID_SHIFT 12 +#define MEMORY_CLIENT_RW_MASK (1 << 24) +#define MEMORY_CLIENT_RW_SHIFT 24 +#define FAULT_VMID_MASK (0xf << 25) +#define FAULT_VMID_SHIFT 25
#define VM_INVALIDATE_REQUEST 0x1478 #define VM_INVALIDATE_RESPONSE 0x147c
From: Alex Deucher alexander.deucher@amd.com
Helpful for debugging GPUVM errors as we can see what hw block and page generated the fault in the log.
Signed-off-by: Alex Deucher alexander.deucher@amd.com --- drivers/gpu/drm/radeon/cik.c | 32 ++++++++++++++++++++++++++++++-- drivers/gpu/drm/radeon/cikd.h | 16 ++++++++++++++++ 2 files changed, 46 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index 27891d8..68b4fc5 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -4442,6 +4442,29 @@ void cik_vm_fini(struct radeon_device *rdev) }
/** + * cik_vm_decode_fault - print human readable fault info + * + * @rdev: radeon_device pointer + * @status: VM_CONTEXT1_PROTECTION_FAULT_STATUS register value + * @addr: VM_CONTEXT1_PROTECTION_FAULT_ADDR register value + * + * Print human readable fault information (CIK). + */ +static void cik_vm_decode_fault(struct radeon_device *rdev, + u32 status, u32 addr, u32 mc_client) +{ + u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT; + u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT; + u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT; + char *block = (char *)&mc_client; + + printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n", + protections, vmid, addr, + (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read", + block, mc_id); +} + +/** * cik_vm_flush - cik vm flush using the CP * * @rdev: radeon_device pointer @@ -5496,6 +5519,7 @@ int cik_irq_process(struct radeon_device *rdev) u32 ring_index; bool queue_hotplug = false; bool queue_reset = false; + u32 addr, status, mc_client;
if (!rdev->ih.enabled || rdev->shutdown) return IRQ_NONE; @@ -5731,11 +5755,15 @@ restart_ih: break; case 146: case 147: + addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR); + status = RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS); + mc_client = RREG32(VM_CONTEXT1_PROTECTION_FAULT_MCCLIENT); dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data); dev_err(rdev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", - RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR)); + addr); dev_err(rdev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", - RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS)); + status); + cik_vm_decode_fault(rdev, status, addr, mc_client); /* reset addr and status */ WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1); break; diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h index 63514b9..7e9275e 100644 --- a/drivers/gpu/drm/radeon/cikd.h +++ b/drivers/gpu/drm/radeon/cikd.h @@ -136,6 +136,22 @@ #define VM_INVALIDATE_RESPONSE 0x147c
#define VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x14DC +#define PROTECTIONS_MASK (0xf << 0) +#define PROTECTIONS_SHIFT 0 + /* bit 0: range + * bit 1: pde0 + * bit 2: valid + * bit 3: read + * bit 4: write + */ +#define MEMORY_CLIENT_ID_MASK (0xff << 12) +#define MEMORY_CLIENT_ID_SHIFT 12 +#define MEMORY_CLIENT_RW_MASK (1 << 24) +#define MEMORY_CLIENT_RW_SHIFT 24 +#define FAULT_VMID_MASK (0xf << 25) +#define FAULT_VMID_SHIFT 25 + +#define VM_CONTEXT1_PROTECTION_FAULT_MCCLIENT 0x14E4
#define VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x14FC
dri-devel@lists.freedesktop.org
-
alexdeucher＠gmail.com