[PATCH v4] drm/amdgpu/gfx9: replace BUG_ON/BUG with WARN_ON_ONCE in ring emission

[PATCH v4] drm/amdgpu/gfx9: replace BUG_ON/BUG with WARN_ON_ONCE in ring emission

[John B. Moore]

Replace BUG_ON() and BUG() assertions in the gfx_v9_0 ring emission
and support paths with WARN_ON_ONCE() and graceful recovery.  Nine
sites are converted across wait_reg_mem, gpu_early_init,
parse_ind_reg_list, init_rlc_save_restore_list, emit_ib_gfx,
emit_ib_compute, emit_fence, get_wptr_compute, and set_wptr_compute.

These assertions guard conditions that are either:
- Address alignment checks on a deprecated byte-swap encoding from
  legacy pre-amdgpu hardware (bits [1:0] must be zero), or
- Switch-case defaults that should be unreachable but are better
  handled with dev_err + return -EINVAL than a kernel panic.

Several of the address alignment BUG_ON sites in the IB emission
paths (emit_ib_gfx, emit_ib_compute) are reachable from unprivileged
userspace via crafted DRM_IOCTL_AMDGPU_CS submissions, causing a
fatal kernel panic in a scheduler worker thread.

For address checks, clear the reserved bits and proceed.  For
unreachable switch defaults, log the error and return.  For the
doorbell-only wptr paths, log with WARN_ONCE and return zero /
no-op.  For init_rlc_save_restore_list, return -EINVAL to abort
driver loading.  Ring emission callbacks return void, so
force-aligning and proceeding is the accepted pattern.

The kiq_read_clock BUG_ON is handled separately as it requires
a larger refactor (moving to amdgpu_ring.c as common code).

Found by a custom amdgpu DRM ioctl fuzzer.

Signed-off-by: John B. Moore <jbmoore61@gmail.com>
Cc: stable@vger.kernel.org
---
Changes v3 -> v4:
  - Fixed malformed patch (v3 had wrong hunk line count)

Changes v2 -> v3:
  - Dropped kiq_read_clock hunk (separate refactor per review)
  - init_rlc_save_restore_list: return -EINVAL instead of break,
    to abort driver loading (per Christian König review)
  - Dropped Fixes tag (issue predates the referenced commit)

 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 49 ++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 2eb32f92a..47e81c33d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1182,8 +1182,8 @@ static void gfx_v9_0_wait_reg_mem(struct amdgpu_ring *ring, int eng_sel,
 				 WAIT_REG_MEM_FUNCTION(3) |  /* equal */
 				 WAIT_REG_MEM_ENGINE(eng_sel)));
 
-	if (mem_space)
-		BUG_ON(addr0 & 0x3); /* Dword align */
+	if (mem_space && WARN_ON_ONCE(addr0 & 0x3))
+		addr0 &= ~0x3; /* Force dword align */
 	amdgpu_ring_write(ring, addr0);
 	amdgpu_ring_write(ring, addr1);
 	amdgpu_ring_write(ring, ref);
@@ -2107,8 +2107,10 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 			return err;
 		break;
 	default:
-		BUG();
-		break;
+		dev_err(adev->dev,
+			"unsupported GFX IP version 0x%x for gfx_v9_0\n",
+			amdgpu_ip_version(adev, GC_HWIP, 0));
+		return -EINVAL;
 	}
 
 	adev->gfx.config.gb_addr_config = gb_addr_config;
@@ -2808,7 +2810,8 @@ static void gfx_v9_1_parse_ind_reg_list(int *register_list_format,
 					break;
 			}
 
-			BUG_ON(idx >= unique_indirect_reg_count);
+			if (WARN_ON_ONCE(idx >= unique_indirect_reg_count))
+				break;
 
 			if (!unique_indirect_regs[idx])
 				unique_indirect_regs[idx] = register_list_format[indirect_offset];
@@ -2885,7 +2888,8 @@ static int gfx_v9_1_init_rlc_save_restore_list(struct amdgpu_device *adev)
 			}
 		}
 
-		BUG_ON(j >= unique_indirect_reg_count);
+		if (WARN_ON_ONCE(j >= unique_indirect_reg_count))
+			return -EINVAL;
 
 		i++;
 	}
@@ -5431,7 +5435,8 @@ static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	}
 
 	amdgpu_ring_write(ring, header);
-	BUG_ON(ib->gpu_addr & 0x3); /* Dword align */
+	if (WARN_ON_ONCE(ib->gpu_addr & 0x3)) /* Dword align */
+		ib->gpu_addr &= ~0x3ULL;
 	amdgpu_ring_write(ring,
 #ifdef __BIG_ENDIAN
 		(2 << 0) |
@@ -5527,7 +5532,8 @@ static void gfx_v9_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
 	}
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
-	BUG_ON(ib->gpu_addr & 0x3); /* Dword align */
+	if (WARN_ON_ONCE(ib->gpu_addr & 0x3)) /* Dword align */
+		ib->gpu_addr &= ~0x3ULL;
 	amdgpu_ring_write(ring,
 #ifdef __BIG_ENDIAN
 				(2 << 0) |
@@ -5567,10 +5573,13 @@ static void gfx_v9_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
 	 * the address should be Qword aligned if 64bit write, Dword
 	 * aligned if only send 32bit data low (discard data high)
 	 */
-	if (write64bit)
-		BUG_ON(addr & 0x7);
-	else
-		BUG_ON(addr & 0x3);
+	if (write64bit) {
+		if (WARN_ON_ONCE(addr & 0x7))
+			addr &= ~0x7ULL;
+	} else {
+		if (WARN_ON_ONCE(addr & 0x3))
+			addr &= ~0x3ULL;
+	}
 	amdgpu_ring_write(ring, lower_32_bits(addr));
 	amdgpu_ring_write(ring, upper_32_bits(addr));
 	amdgpu_ring_write(ring, lower_32_bits(seq));
@@ -5639,10 +5648,13 @@ static u64 gfx_v9_0_ring_get_wptr_compute(struct amdgpu_ring *ring)
 	u64 wptr;
 
 	/* XXX check if swapping is necessary on BE */
-	if (ring->use_doorbell)
+	if (ring->use_doorbell) {
 		wptr = atomic64_read((atomic64_t *)ring->wptr_cpu_addr);
-	else
-		BUG();
+	} else {
+		WARN_ONCE(1, "gfx_v9_0: non-doorbell wptr read on ring %s, only doorbell method supported on gfx9\n",
+			  ring->name);
+		wptr = 0;
+	}
 	return wptr;
 }
 
@@ -5654,8 +5666,9 @@ static void gfx_v9_0_ring_set_wptr_compute(struct amdgpu_ring *ring)
 	if (ring->use_doorbell) {
 		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, ring->wptr);
 		WDOORBELL64(ring->doorbell_index, ring->wptr);
-	} else{
-		BUG(); /* only DOORBELL method supported on gfx9 now */
+	} else {
+		WARN_ONCE(1, "gfx_v9_0: non-doorbell wptr write on ring %s, only doorbell method supported on gfx9\n",
+			  ring->name);
 	}
 }
 
-- 
2.43.0