linux-kernel - [PATCH AUTOSEL for 4.15 02/78] drm/amdgpu: use polling mem to set SDMA3 wptr for VF

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20180308045525.7662-2-alexander.levin@microsoft.com>
Date:   Thu, 8 Mar 2018 04:56:01 +0000
From:   Sasha Levin <Alexander.Levin@...rosoft.com>
To:     "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "stable@...r.kernel.org" <stable@...r.kernel.org>
CC:     Pixel Ding <Pixel.Ding@....com>,
        Alex Deucher <alexander.deucher@....com>,
        Sasha Levin <Alexander.Levin@...rosoft.com>
Subject: [PATCH AUTOSEL for 4.15 02/78] drm/amdgpu: use polling mem to set
 SDMA3 wptr for VF

From: Pixel Ding <Pixel.Ding@....com>

[ Upstream commit 2ffe31deb27579e2f2c9444e01f4d8abf385d145 ]

On Tonga VF, there're 2 sources updating wptr registers for
sdma3: 1) polling mem and 2) doorbell. When doorbell and polling
mem are both enabled on sdma3, there will be collision hit in
occasion between those two sources when ucode and h/w are doing
the updating on wptr register in parallel. Issue doesn't happen
on CP GFX/Compute since CP drops all doorbell writes when VF is
inactive. So enable polling mem and don't use doorbell for SDMA3.

Signed-off-by: Pixel Ding <Pixel.Ding@....com>
Reviewed-by: Monk Liu <monk.liu@....com>
Reviewed-by: Christian König <christian.koenig@....com>
Signed-off-by: Alex Deucher <alexander.deucher@....com>
Signed-off-by: Sasha Levin <alexander.levin@...rosoft.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h |  1 +
 drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c   | 27 +++++++++++++++++++--------
 2 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index b18c2b96691f..522a8742a60b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -187,6 +187,7 @@ struct amdgpu_ring {
 	uint64_t                eop_gpu_addr;
 	u32			doorbell_index;
 	bool			use_doorbell;
+	bool			use_pollmem;
 	unsigned		wptr_offs;
 	unsigned		fence_offs;
 	uint64_t		current_ctx;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 6d06f8eb659f..cc4fc2e43b7b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -355,7 +355,7 @@ static uint64_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	u32 wptr;
 
-	if (ring->use_doorbell) {
+	if (ring->use_doorbell || ring->use_pollmem) {
 		/* XXX check if swapping is necessary on BE */
 		wptr = ring->adev->wb.wb[ring->wptr_offs] >> 2;
 	} else {
@@ -380,10 +380,13 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 
 	if (ring->use_doorbell) {
 		u32 *wb = (u32 *)&adev->wb.wb[ring->wptr_offs];
-
 		/* XXX check if swapping is necessary on BE */
 		WRITE_ONCE(*wb, (lower_32_bits(ring->wptr) << 2));
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr) << 2);
+	} else if (ring->use_pollmem) {
+		u32 *wb = (u32 *)&adev->wb.wb[ring->wptr_offs];
+
+		WRITE_ONCE(*wb, (lower_32_bits(ring->wptr) << 2));
 	} else {
 		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
 
@@ -718,10 +721,14 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
 		WREG32(mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI + sdma_offsets[i],
 		       upper_32_bits(wptr_gpu_addr));
 		wptr_poll_cntl = RREG32(mmSDMA0_GFX_RB_WPTR_POLL_CNTL + sdma_offsets[i]);
-		if (amdgpu_sriov_vf(adev))
-			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 1);
+		if (ring->use_pollmem)
+			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl,
+						       SDMA0_GFX_RB_WPTR_POLL_CNTL,
+						       ENABLE, 1);
 		else
-			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 0);
+			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl,
+						       SDMA0_GFX_RB_WPTR_POLL_CNTL,
+						       ENABLE, 0);
 		WREG32(mmSDMA0_GFX_RB_WPTR_POLL_CNTL + sdma_offsets[i], wptr_poll_cntl);
 
 		/* enable DMA RB */
@@ -1203,9 +1210,13 @@ static int sdma_v3_0_sw_init(void *handle)
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		ring = &adev->sdma.instance[i].ring;
 		ring->ring_obj = NULL;
-		ring->use_doorbell = true;
-		ring->doorbell_index = (i == 0) ?
-			AMDGPU_DOORBELL_sDMA_ENGINE0 : AMDGPU_DOORBELL_sDMA_ENGINE1;
+		if (!amdgpu_sriov_vf(adev)) {
+			ring->use_doorbell = true;
+			ring->doorbell_index = (i == 0) ?
+				AMDGPU_DOORBELL_sDMA_ENGINE0 : AMDGPU_DOORBELL_sDMA_ENGINE1;
+		} else {
+			ring->use_pollmem = true;
+		}
 
 		sprintf(ring->name, "sdma%d", i);
 		r = amdgpu_ring_init(adev, ring, 1024,
-- 
2.14.1