drm/radeon/kms: simplify & improve GPU reset V2

This simplify and improve GPU reset for R1XX-R6XX hw, it's
not 100% reliable here are result:
- R1XX/R2XX works bunch of time in a row, sometimes it
  seems it can work indifinitly
- R3XX/R3XX the most unreliable one, sometimes you will be
  able to reset few times, sometimes not even once
- R5XX more reliable than previous hw, seems to work most
  of the times but once in a while it fails for no obvious
  reasons (same status than previous reset just no same
  happy ending)
- R6XX/R7XX are lot more reliable with this patch, still
  it seems that it can fail after a bunch (reset every
  2sec for 3hour bring down the GPU & computer)

This have been tested on various hw, for some odd reasons
i wasn't able to lockup RS480/RS690 (while they use to
love locking up).

Note that on R1XX-R5XX the cursor will disapear after
lockup haven't checked why, switch to console and back
to X will restore cursor.

Next step is to record the bogus command that leaded to
the lockup.

V2 Fix r6xx resume path to avoid reinitializing blit
module, use the gpu_lockup boolean to avoid entering
inifinite waiting loop on fence while reiniting the GPU

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

20 files changed, 508 insertions, 354 deletions

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 8bb91092bff..7a4a4fc276b 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -662,26 +662,6 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
 	if (r100_debugfs_cp_init(rdev)) {
 		DRM_ERROR("Failed to register debugfs file for CP !\n");
 	}
-	/* Reset CP */
-	tmp = RREG32(RADEON_CP_CSQ_STAT);
-	if ((tmp & (1 << 31))) {
-		DRM_INFO("radeon: cp busy (0x%08X) resetting\n", tmp);
-		WREG32(RADEON_CP_CSQ_MODE, 0);
-		WREG32(RADEON_CP_CSQ_CNTL, 0);
-		WREG32(RADEON_RBBM_SOFT_RESET, RADEON_SOFT_RESET_CP);
-		tmp = RREG32(RADEON_RBBM_SOFT_RESET);
-		mdelay(2);
-		WREG32(RADEON_RBBM_SOFT_RESET, 0);
-		tmp = RREG32(RADEON_RBBM_SOFT_RESET);
-		mdelay(2);
-		tmp = RREG32(RADEON_CP_CSQ_STAT);
-		if ((tmp & (1 << 31))) {
-			DRM_INFO("radeon: cp reset failed (0x%08X)\n", tmp);
-		}
-	} else {
-		DRM_INFO("radeon: cp idle (0x%08X)\n", tmp);
-	}
-
 	if (!rdev->me_fw) {
 		r = r100_cp_init_microcode(rdev);
 		if (r) {
@@ -786,39 +766,6 @@ void r100_cp_disable(struct radeon_device *rdev)
 	}
 }
 
-int r100_cp_reset(struct radeon_device *rdev)
-{
-	uint32_t tmp;
-	bool reinit_cp;
-	int i;
-
-	reinit_cp = rdev->cp.ready;
-	rdev->cp.ready = false;
-	WREG32(RADEON_CP_CSQ_MODE, 0);
-	WREG32(RADEON_CP_CSQ_CNTL, 0);
-	WREG32(RADEON_RBBM_SOFT_RESET, RADEON_SOFT_RESET_CP);
-	(void)RREG32(RADEON_RBBM_SOFT_RESET);
-	udelay(200);
-	WREG32(RADEON_RBBM_SOFT_RESET, 0);
-	/* Wait to prevent race in RBBM_STATUS */
-	mdelay(1);
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = RREG32(RADEON_RBBM_STATUS);
-		if (!(tmp & (1 << 16))) {
-			DRM_INFO("CP reset succeed (RBBM_STATUS=0x%08X)\n",
-				 tmp);
-			if (reinit_cp) {
-				return r100_cp_init(rdev, rdev->cp.ring_size);
-			}
-			return 0;
-		}
-		DRM_UDELAY(1);
-	}
-	tmp = RREG32(RADEON_RBBM_STATUS);
-	DRM_ERROR("Failed to reset CP (RBBM_STATUS=0x%08X)!\n", tmp);
-	return -1;
-}
-
 void r100_cp_commit(struct radeon_device *rdev)
 {
 	WREG32(RADEON_CP_RB_WPTR, rdev->cp.wptr);
@@ -1732,51 +1679,6 @@ int r100_mc_wait_for_idle(struct radeon_device *rdev)
 	return -1;
 }
 
-void r100_gpu_init(struct radeon_device *rdev)
-{
-	/* TODO: anythings to do here ? pipes ? */
-	r100_hdp_reset(rdev);
-}
-
-void r100_hdp_reset(struct radeon_device *rdev)
-{
-	uint32_t tmp;
-
-	tmp = RREG32(RADEON_HOST_PATH_CNTL) & RADEON_HDP_APER_CNTL;
-	tmp |= (7 << 28);
-	WREG32(RADEON_HOST_PATH_CNTL, tmp | RADEON_HDP_SOFT_RESET | RADEON_HDP_READ_BUFFER_INVALIDATE);
-	(void)RREG32(RADEON_HOST_PATH_CNTL);
-	udelay(200);
-	WREG32(RADEON_RBBM_SOFT_RESET, 0);
-	WREG32(RADEON_HOST_PATH_CNTL, tmp);
-	(void)RREG32(RADEON_HOST_PATH_CNTL);
-}
-
-int r100_rb2d_reset(struct radeon_device *rdev)
-{
-	uint32_t tmp;
-	int i;
-
-	WREG32(RADEON_RBBM_SOFT_RESET, RADEON_SOFT_RESET_E2);
-	(void)RREG32(RADEON_RBBM_SOFT_RESET);
-	udelay(200);
-	WREG32(RADEON_RBBM_SOFT_RESET, 0);
-	/* Wait to prevent race in RBBM_STATUS */
-	mdelay(1);
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = RREG32(RADEON_RBBM_STATUS);
-		if (!(tmp & (1 << 26))) {
-			DRM_INFO("RB2D reset succeed (RBBM_STATUS=0x%08X)\n",
-				 tmp);
-			return 0;
-		}
-		DRM_UDELAY(1);
-	}
-	tmp = RREG32(RADEON_RBBM_STATUS);
-	DRM_ERROR("Failed to reset RB2D (RBBM_STATUS=0x%08X)!\n", tmp);
-	return -1;
-}
-
 void r100_gpu_lockup_update(struct r100_gpu_lockup *lockup, struct radeon_cp *cp)
 {
 	lockup->last_cp_rptr = cp->rptr;
@@ -1863,31 +1765,77 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev)
 	return r100_gpu_cp_is_lockup(rdev, &rdev->config.r100.lockup, &rdev->cp);
 }
 
+void r100_bm_disable(struct radeon_device *rdev)
+{
+	u32 tmp;
+
+	/* disable bus mastering */
+	tmp = RREG32(R_000030_BUS_CNTL);
+	WREG32(R_000030_BUS_CNTL, (tmp & 0xFFFFFFFF) | 0x00000044);
+	mdelay(1);
+	WREG32(R_000030_BUS_CNTL, (tmp & 0xFFFFFFFF) | 0x00000042);
+	mdelay(1);
+	WREG32(R_000030_BUS_CNTL, (tmp & 0xFFFFFFFF) | 0x00000040);
+	tmp = RREG32(RADEON_BUS_CNTL);
+	mdelay(1);
+	pci_read_config_word(rdev->pdev, 0x4, (u16*)&tmp);
+	pci_write_config_word(rdev->pdev, 0x4, tmp & 0xFFFB);
+	mdelay(1);
+}
+
 int r100_asic_reset(struct radeon_device *rdev)
 {
-	uint32_t status;
+	struct r100_mc_save save;
+	u32 status, tmp;
 
-	/* reset order likely matter */
-	status = RREG32(RADEON_RBBM_STATUS);
-	/* reset HDP */
-	r100_hdp_reset(rdev);
-	/* reset rb2d */
-	if (status & ((1 << 17) | (1 << 18) | (1 << 27))) {
-		r100_rb2d_reset(rdev);
+	r100_mc_stop(rdev, &save);
+	status = RREG32(R_000E40_RBBM_STATUS);
+	if (!G_000E40_GUI_ACTIVE(status)) {
+		return 0;
 	}
-	/* TODO: reset 3D engine */
+	status = RREG32(R_000E40_RBBM_STATUS);
+	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
+	/* stop CP */
+	WREG32(RADEON_CP_CSQ_CNTL, 0);
+	tmp = RREG32(RADEON_CP_RB_CNTL);
+	WREG32(RADEON_CP_RB_CNTL, tmp | RADEON_RB_RPTR_WR_ENA);
+	WREG32(RADEON_CP_RB_RPTR_WR, 0);
+	WREG32(RADEON_CP_RB_WPTR, 0);
+	WREG32(RADEON_CP_RB_CNTL, tmp);
+	/* save PCI state */
+	pci_save_state(rdev->pdev);
+	/* disable bus mastering */
+	r100_bm_disable(rdev);
+	WREG32(R_0000F0_RBBM_SOFT_RESET, S_0000F0_SOFT_RESET_SE(1) |
+					S_0000F0_SOFT_RESET_RE(1) |
+					S_0000F0_SOFT_RESET_PP(1) |
+					S_0000F0_SOFT_RESET_RB(1));
+	RREG32(R_0000F0_RBBM_SOFT_RESET);
+	mdelay(500);
+	WREG32(R_0000F0_RBBM_SOFT_RESET, 0);
+	mdelay(1);
+	status = RREG32(R_000E40_RBBM_STATUS);
+	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
 	/* reset CP */
-	status = RREG32(RADEON_RBBM_STATUS);
-	if (status & (1 << 16)) {
-		r100_cp_reset(rdev);
-	}
+	WREG32(R_0000F0_RBBM_SOFT_RESET, S_0000F0_SOFT_RESET_CP(1));
+	RREG32(R_0000F0_RBBM_SOFT_RESET);
+	mdelay(500);
+	WREG32(R_0000F0_RBBM_SOFT_RESET, 0);
+	mdelay(1);
+	status = RREG32(R_000E40_RBBM_STATUS);
+	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
+	/* restore PCI & busmastering */
+	pci_restore_state(rdev->pdev);
+	r100_enable_bm(rdev);
 	/* Check if GPU is idle */
-	status = RREG32(RADEON_RBBM_STATUS);
-	if (status & RADEON_RBBM_ACTIVE) {
-		DRM_ERROR("Failed to reset GPU (RBBM_STATUS=0x%08X)\n", status);
+	if (G_000E40_SE_BUSY(status) || G_000E40_RE_BUSY(status) ||
+		G_000E40_TAM_BUSY(status) || G_000E40_PB_BUSY(status)) {
+		dev_err(rdev->dev, "failed to reset GPU\n");
+		rdev->gpu_lockup = true;
 		return -1;
 	}
-	DRM_INFO("GPU reset succeed (RBBM_STATUS=0x%08X)\n", status);
+	r100_mc_resume(rdev, &save);
+	dev_info(rdev->dev, "GPU reset succeed\n");
 	return 0;
 }
 
@@ -3475,7 +3423,7 @@ static int r100_startup(struct radeon_device *rdev)
 	/* Resume clock */
 	r100_clock_startup(rdev);
 	/* Initialize GPU configuration (# pipes, ...) */
-	r100_gpu_init(rdev);
+//	r100_gpu_init(rdev);
 	/* Initialize GART (initialize after TTM so we can allocate
 	 * memory through TTM but finalize after TTM) */
 	r100_enable_bm(rdev);
diff --git a/drivers/gpu/drm/radeon/r100d.h b/drivers/gpu/drm/radeon/r100d.h
index df29a630c46..de8abd104ab 100644
--- a/drivers/gpu/drm/radeon/r100d.h
+++ b/drivers/gpu/drm/radeon/r100d.h
@@ -74,6 +74,134 @@
 #define CP_PACKET3_GET_OPCODE(h) (((h) >> 8) & 0xFF)
 
 /* Registers */
+#define R_0000F0_RBBM_SOFT_RESET                     0x0000F0
+#define   S_0000F0_SOFT_RESET_CP(x)                    (((x) & 0x1) << 0)
+#define   G_0000F0_SOFT_RESET_CP(x)                    (((x) >> 0) & 0x1)
+#define   C_0000F0_SOFT_RESET_CP                       0xFFFFFFFE
+#define   S_0000F0_SOFT_RESET_HI(x)                    (((x) & 0x1) << 1)
+#define   G_0000F0_SOFT_RESET_HI(x)                    (((x) >> 1) & 0x1)
+#define   C_0000F0_SOFT_RESET_HI                       0xFFFFFFFD
+#define   S_0000F0_SOFT_RESET_SE(x)                    (((x) & 0x1) << 2)
+#define   G_0000F0_SOFT_RESET_SE(x)                    (((x) >> 2) & 0x1)
+#define   C_0000F0_SOFT_RESET_SE                       0xFFFFFFFB
+#define   S_0000F0_SOFT_RESET_RE(x)                    (((x) & 0x1) << 3)
+#define   G_0000F0_SOFT_RESET_RE(x)                    (((x) >> 3) & 0x1)
+#define   C_0000F0_SOFT_RESET_RE                       0xFFFFFFF7
+#define   S_0000F0_SOFT_RESET_PP(x)                    (((x) & 0x1) << 4)
+#define   G_0000F0_SOFT_RESET_PP(x)                    (((x) >> 4) & 0x1)
+#define   C_0000F0_SOFT_RESET_PP                       0xFFFFFFEF
+#define   S_0000F0_SOFT_RESET_E2(x)                    (((x) & 0x1) << 5)
+#define   G_0000F0_SOFT_RESET_E2(x)                    (((x) >> 5) & 0x1)
+#define   C_0000F0_SOFT_RESET_E2                       0xFFFFFFDF
+#define   S_0000F0_SOFT_RESET_RB(x)                    (((x) & 0x1) << 6)
+#define   G_0000F0_SOFT_RESET_RB(x)                    (((x) >> 6) & 0x1)
+#define   C_0000F0_SOFT_RESET_RB                       0xFFFFFFBF
+#define   S_0000F0_SOFT_RESET_HDP(x)                   (((x) & 0x1) << 7)
+#define   G_0000F0_SOFT_RESET_HDP(x)                   (((x) >> 7) & 0x1)
+#define   C_0000F0_SOFT_RESET_HDP                      0xFFFFFF7F
+#define   S_0000F0_SOFT_RESET_MC(x)                    (((x) & 0x1) << 8)
+#define   G_0000F0_SOFT_RESET_MC(x)                    (((x) >> 8) & 0x1)
+#define   C_0000F0_SOFT_RESET_MC                       0xFFFFFEFF
+#define   S_0000F0_SOFT_RESET_AIC(x)                   (((x) & 0x1) << 9)
+#define   G_0000F0_SOFT_RESET_AIC(x)                   (((x) >> 9) & 0x1)
+#define   C_0000F0_SOFT_RESET_AIC                      0xFFFFFDFF
+#define   S_0000F0_SOFT_RESET_VIP(x)                   (((x) & 0x1) << 10)
+#define   G_0000F0_SOFT_RESET_VIP(x)                   (((x) >> 10) & 0x1)
+#define   C_0000F0_SOFT_RESET_VIP                      0xFFFFFBFF
+#define   S_0000F0_SOFT_RESET_DISP(x)                  (((x) & 0x1) << 11)
+#define   G_0000F0_SOFT_RESET_DISP(x)                  (((x) >> 11) & 0x1)
+#define   C_0000F0_SOFT_RESET_DISP                     0xFFFFF7FF
+#define   S_0000F0_SOFT_RESET_CG(x)                    (((x) & 0x1) << 12)
+#define   G_0000F0_SOFT_RESET_CG(x)                    (((x) >> 12) & 0x1)
+#define   C_0000F0_SOFT_RESET_CG                       0xFFFFEFFF
+#define R_000030_BUS_CNTL                            0x000030
+#define   S_000030_BUS_DBL_RESYNC(x)                   (((x) & 0x1) << 0)
+#define   G_000030_BUS_DBL_RESYNC(x)                   (((x) >> 0) & 0x1)
+#define   C_000030_BUS_DBL_RESYNC                      0xFFFFFFFE
+#define   S_000030_BUS_MSTR_RESET(x)                   (((x) & 0x1) << 1)
+#define   G_000030_BUS_MSTR_RESET(x)                   (((x) >> 1) & 0x1)
+#define   C_000030_BUS_MSTR_RESET                      0xFFFFFFFD
+#define   S_000030_BUS_FLUSH_BUF(x)                    (((x) & 0x1) << 2)
+#define   G_000030_BUS_FLUSH_BUF(x)                    (((x) >> 2) & 0x1)
+#define   C_000030_BUS_FLUSH_BUF                       0xFFFFFFFB
+#define   S_000030_BUS_STOP_REQ_DIS(x)                 (((x) & 0x1) << 3)
+#define   G_000030_BUS_STOP_REQ_DIS(x)                 (((x) >> 3) & 0x1)
+#define   C_000030_BUS_STOP_REQ_DIS                    0xFFFFFFF7
+#define   S_000030_BUS_PM4_READ_COMBINE_EN(x)          (((x) & 0x1) << 4)
+#define   G_000030_BUS_PM4_READ_COMBINE_EN(x)          (((x) >> 4) & 0x1)
+#define   C_000030_BUS_PM4_READ_COMBINE_EN             0xFFFFFFEF
+#define   S_000030_BUS_WRT_COMBINE_EN(x)               (((x) & 0x1) << 5)
+#define   G_000030_BUS_WRT_COMBINE_EN(x)               (((x) >> 5) & 0x1)
+#define   C_000030_BUS_WRT_COMBINE_EN                  0xFFFFFFDF
+#define   S_000030_BUS_MASTER_DIS(x)                   (((x) & 0x1) << 6)
+#define   G_000030_BUS_MASTER_DIS(x)                   (((x) >> 6) & 0x1)
+#define   C_000030_BUS_MASTER_DIS                      0xFFFFFFBF
+#define   S_000030_BIOS_ROM_WRT_EN(x)                  (((x) & 0x1) << 7)
+#define   G_000030_BIOS_ROM_WRT_EN(x)                  (((x) >> 7) & 0x1)
+#define   C_000030_BIOS_ROM_WRT_EN                     0xFFFFFF7F
+#define   S_000030_BM_DAC_CRIPPLE(x)                   (((x) & 0x1) << 8)
+#define   G_000030_BM_DAC_CRIPPLE(x)                   (((x) >> 8) & 0x1)
+#define   C_000030_BM_DAC_CRIPPLE                      0xFFFFFEFF
+#define   S_000030_BUS_NON_PM4_READ_COMBINE_EN(x)      (((x) & 0x1) << 9)
+#define   G_000030_BUS_NON_PM4_READ_COMBINE_EN(x)      (((x) >> 9) & 0x1)
+#define   C_000030_BUS_NON_PM4_READ_COMBINE_EN         0xFFFFFDFF
+#define   S_000030_BUS_XFERD_DISCARD_EN(x)             (((x) & 0x1) << 10)
+#define   G_000030_BUS_XFERD_DISCARD_EN(x)             (((x) >> 10) & 0x1)
+#define   C_000030_BUS_XFERD_DISCARD_EN                0xFFFFFBFF
+#define   S_000030_BUS_SGL_READ_DISABLE(x)             (((x) & 0x1) << 11)
+#define   G_000030_BUS_SGL_READ_DISABLE(x)             (((x) >> 11) & 0x1)
+#define   C_000030_BUS_SGL_READ_DISABLE                0xFFFFF7FF
+#define   S_000030_BIOS_DIS_ROM(x)                     (((x) & 0x1) << 12)
+#define   G_000030_BIOS_DIS_ROM(x)                     (((x) >> 12) & 0x1)
+#define   C_000030_BIOS_DIS_ROM                        0xFFFFEFFF
+#define   S_000030_BUS_PCI_READ_RETRY_EN(x)            (((x) & 0x1) << 13)
+#define   G_000030_BUS_PCI_READ_RETRY_EN(x)            (((x) >> 13) & 0x1)
+#define   C_000030_BUS_PCI_READ_RETRY_EN               0xFFFFDFFF
+#define   S_000030_BUS_AGP_AD_STEPPING_EN(x)           (((x) & 0x1) << 14)
+#define   G_000030_BUS_AGP_AD_STEPPING_EN(x)           (((x) >> 14) & 0x1)
+#define   C_000030_BUS_AGP_AD_STEPPING_EN              0xFFFFBFFF
+#define   S_000030_BUS_PCI_WRT_RETRY_EN(x)             (((x) & 0x1) << 15)
+#define   G_000030_BUS_PCI_WRT_RETRY_EN(x)             (((x) >> 15) & 0x1)
+#define   C_000030_BUS_PCI_WRT_RETRY_EN                0xFFFF7FFF
+#define   S_000030_BUS_RETRY_WS(x)                     (((x) & 0xF) << 16)
+#define   G_000030_BUS_RETRY_WS(x)                     (((x) >> 16) & 0xF)
+#define   C_000030_BUS_RETRY_WS                        0xFFF0FFFF
+#define   S_000030_BUS_MSTR_RD_MULT(x)                 (((x) & 0x1) << 20)
+#define   G_000030_BUS_MSTR_RD_MULT(x)                 (((x) >> 20) & 0x1)
+#define   C_000030_BUS_MSTR_RD_MULT                    0xFFEFFFFF
+#define   S_000030_BUS_MSTR_RD_LINE(x)                 (((x) & 0x1) << 21)
+#define   G_000030_BUS_MSTR_RD_LINE(x)                 (((x) >> 21) & 0x1)
+#define   C_000030_BUS_MSTR_RD_LINE                    0xFFDFFFFF
+#define   S_000030_BUS_SUSPEND(x)                      (((x) & 0x1) << 22)
+#define   G_000030_BUS_SUSPEND(x)                      (((x) >> 22) & 0x1)
+#define   C_000030_BUS_SUSPEND                         0xFFBFFFFF
+#define   S_000030_LAT_16X(x)                          (((x) & 0x1) << 23)
+#define   G_000030_LAT_16X(x)                          (((x) >> 23) & 0x1)
+#define   C_000030_LAT_16X                             0xFF7FFFFF
+#define   S_000030_BUS_RD_DISCARD_EN(x)                (((x) & 0x1) << 24)
+#define   G_000030_BUS_RD_DISCARD_EN(x)                (((x) >> 24) & 0x1)
+#define   C_000030_BUS_RD_DISCARD_EN                   0xFEFFFFFF
+#define   S_000030_ENFRCWRDY(x)                        (((x) & 0x1) << 25)
+#define   G_000030_ENFRCWRDY(x)                        (((x) >> 25) & 0x1)
+#define   C_000030_ENFRCWRDY                           0xFDFFFFFF
+#define   S_000030_BUS_MSTR_WS(x)                      (((x) & 0x1) << 26)
+#define   G_000030_BUS_MSTR_WS(x)                      (((x) >> 26) & 0x1)
+#define   C_000030_BUS_MSTR_WS                         0xFBFFFFFF
+#define   S_000030_BUS_PARKING_DIS(x)                  (((x) & 0x1) << 27)
+#define   G_000030_BUS_PARKING_DIS(x)                  (((x) >> 27) & 0x1)
+#define   C_000030_BUS_PARKING_DIS                     0xF7FFFFFF
+#define   S_000030_BUS_MSTR_DISCONNECT_EN(x)           (((x) & 0x1) << 28)
+#define   G_000030_BUS_MSTR_DISCONNECT_EN(x)           (((x) >> 28) & 0x1)
+#define   C_000030_BUS_MSTR_DISCONNECT_EN              0xEFFFFFFF
+#define   S_000030_SERR_EN(x)                          (((x) & 0x1) << 29)
+#define   G_000030_SERR_EN(x)                          (((x) >> 29) & 0x1)
+#define   C_000030_SERR_EN                             0xDFFFFFFF
+#define   S_000030_BUS_READ_BURST(x)                   (((x) & 0x1) << 30)
+#define   G_000030_BUS_READ_BURST(x)                   (((x) >> 30) & 0x1)
+#define   C_000030_BUS_READ_BURST                      0xBFFFFFFF
+#define   S_000030_BUS_RDY_READ_DLY(x)                 (((x) & 0x1) << 31)
+#define   G_000030_BUS_RDY_READ_DLY(x)                 (((x) >> 31) & 0x1)
+#define   C_000030_BUS_RDY_READ_DLY                    0x7FFFFFFF
 #define R_000040_GEN_INT_CNTL                        0x000040
 #define   S_000040_CRTC_VBLANK(x)                      (((x) & 0x1) << 0)
 #define   G_000040_CRTC_VBLANK(x)                      (((x) >> 0) & 0x1)
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 7d5de5dbde2..199110ef8df 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -151,6 +151,10 @@ void rv370_pcie_gart_disable(struct radeon_device *rdev)
 	u32 tmp;
 	int r;
 
+	WREG32_PCIE(RADEON_PCIE_TX_GART_START_LO, 0);
+	WREG32_PCIE(RADEON_PCIE_TX_GART_END_LO, 0);
+	WREG32_PCIE(RADEON_PCIE_TX_GART_START_HI, 0);
+	WREG32_PCIE(RADEON_PCIE_TX_GART_END_HI, 0);
 	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_CNTL);
 	tmp |= RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_DISCARD;
 	WREG32_PCIE(RADEON_PCIE_TX_GART_CNTL, tmp & ~RADEON_PCIE_TX_GART_EN);
@@ -323,7 +327,6 @@ void r300_gpu_init(struct radeon_device *rdev)
 {
 	uint32_t gb_tile_config, tmp;
 
-	r100_hdp_reset(rdev);
 	/* FIXME: rv380 one pipes ? */
 	if ((rdev->family == CHIP_R300 && rdev->pdev->device != 0x4144) ||
 	    (rdev->family == CHIP_R350)) {
@@ -376,57 +379,6 @@ void r300_gpu_init(struct radeon_device *rdev)
 		 rdev->num_gb_pipes, rdev->num_z_pipes);
 }
 
-int r300_ga_reset(struct radeon_device *rdev)
-{
-	uint32_t tmp;
-	bool reinit_cp;
-	int i;
-
-	reinit_cp = rdev->cp.ready;
-	rdev->cp.ready = false;
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		WREG32(RADEON_CP_CSQ_MODE, 0);
-		WREG32(RADEON_CP_CSQ_CNTL, 0);
-		WREG32(RADEON_RBBM_SOFT_RESET, 0x32005);
-		(void)RREG32(RADEON_RBBM_SOFT_RESET);
-		udelay(200);
-		WREG32(RADEON_RBBM_SOFT_RESET, 0);
-		/* Wait to prevent race in RBBM_STATUS */
-		mdelay(1);
-		tmp = RREG32(RADEON_RBBM_STATUS);
-		if (tmp & ((1 << 20) | (1 << 26))) {
-			DRM_ERROR("VAP & CP still busy (RBBM_STATUS=0x%08X)", tmp);
-			/* GA still busy soft reset it */
-			WREG32(0x429C, 0x200);
-			WREG32(R300_VAP_PVS_STATE_FLUSH_REG, 0);
-			WREG32(R300_RE_SCISSORS_TL, 0);
-			WREG32(R300_RE_SCISSORS_BR, 0);
-			WREG32(0x24AC, 0);
-		}
-		/* Wait to prevent race in RBBM_STATUS */
-		mdelay(1);
-		tmp = RREG32(RADEON_RBBM_STATUS);
-		if (!(tmp & ((1 << 20) | (1 << 26)))) {
-			break;
-		}
-	}
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = RREG32(RADEON_RBBM_STATUS);
-		if (!(tmp & ((1 << 20) | (1 << 26)))) {
-			DRM_INFO("GA reset succeed (RBBM_STATUS=0x%08X)\n",
-				 tmp);
-			if (reinit_cp) {
-				return r100_cp_init(rdev, rdev->cp.ring_size);
-			}
-			return 0;
-		}
-		DRM_UDELAY(1);
-	}
-	tmp = RREG32(RADEON_RBBM_STATUS);
-	DRM_ERROR("Failed to reset GA ! (RBBM_STATUS=0x%08X)\n", tmp);
-	return -1;
-}
-
 bool r300_gpu_is_lockup(struct radeon_device *rdev)
 {
 	u32 rbbm_status;
@@ -451,37 +403,69 @@ bool r300_gpu_is_lockup(struct radeon_device *rdev)
 
 int r300_asic_reset(struct radeon_device *rdev)
 {
-	uint32_t status;
+	struct r100_mc_save save;
+	u32 status, tmp;
 
-	/* reset order likely matter */
-	status = RREG32(RADEON_RBBM_STATUS);
-	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
-	/* reset HDP */
-	r100_hdp_reset(rdev);
-	/* reset rb2d */
-	if (status & ((1 << 17) | (1 << 18) | (1 << 27))) {
-		r100_rb2d_reset(rdev);
-	}
-	/* reset GA */
-	if (status & ((1 << 20) | (1 << 26))) {
-		r300_ga_reset(rdev);
-	}
-	/* reset CP */
-	status = RREG32(RADEON_RBBM_STATUS);
-	if (status & (1 << 16)) {
-		r100_cp_reset(rdev);
+	r100_mc_stop(rdev, &save);
+	status = RREG32(R_000E40_RBBM_STATUS);
+	if (!G_000E40_GUI_ACTIVE(status)) {
+		return 0;
 	}
+	status = RREG32(R_000E40_RBBM_STATUS);
+	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
+	/* stop CP */
+	WREG32(RADEON_CP_CSQ_CNTL, 0);
+	tmp = RREG32(RADEON_CP_RB_CNTL);
+	WREG32(RADEON_CP_RB_CNTL, tmp | RADEON_RB_RPTR_WR_ENA);
+	WREG32(RADEON_CP_RB_RPTR_WR, 0);
+	WREG32(RADEON_CP_RB_WPTR, 0);
+	WREG32(RADEON_CP_RB_CNTL, tmp);
+	/* save PCI state */
+	pci_save_state(rdev->pdev);
+	/* disable bus mastering */
+	r100_bm_disable(rdev);
+	WREG32(R_0000F0_RBBM_SOFT_RESET, S_0000F0_SOFT_RESET_VAP(1) |
+					S_0000F0_SOFT_RESET_GA(1));
+	RREG32(R_0000F0_RBBM_SOFT_RESET);
+	mdelay(500);
+	WREG32(R_0000F0_RBBM_SOFT_RESET, 0);
+	mdelay(1);
+	status = RREG32(R_000E40_RBBM_STATUS);
+	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
+	/* resetting the CP seems to be problematic sometimes it end up
+	 * hard locking the computer, but it's necessary for successfull
+	 * reset more test & playing is needed on R3XX/R4XX to find a
+	 * reliable (if any solution)
+	 */
+	WREG32(R_0000F0_RBBM_SOFT_RESET, S_0000F0_SOFT_RESET_CP(1));
+	RREG32(R_0000F0_RBBM_SOFT_RESET);
+	mdelay(500);
+	WREG32(R_0000F0_RBBM_SOFT_RESET, 0);
+	mdelay(1);
+	status = RREG32(R_000E40_RBBM_STATUS);
+	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
+	/* reset MC */
+	WREG32(R_0000F0_RBBM_SOFT_RESET, S_0000F0_SOFT_RESET_MC(1));
+	RREG32(R_0000F0_RBBM_SOFT_RESET);
+	mdelay(500);
+	WREG32(R_0000F0_RBBM_SOFT_RESET, 0);
+	mdelay(1);
+	status = RREG32(R_000E40_RBBM_STATUS);
+	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
+	/* restore PCI & busmastering */
+	pci_restore_state(rdev->pdev);
+	r100_enable_bm(rdev);
 	/* Check if GPU is idle */
-	status = RREG32(RADEON_RBBM_STATUS);
-	if (status & RADEON_RBBM_ACTIVE) {
-		DRM_ERROR("Failed to reset GPU (RBBM_STATUS=0x%08X)\n", status);
+	if (G_000E40_GA_BUSY(status) || G_000E40_VAP_BUSY(status)) {
+		dev_err(rdev->dev, "failed to reset GPU\n");
+		rdev->gpu_lockup = true;
 		return -1;
 	}
-	DRM_INFO("GPU reset succeed (RBBM_STATUS=0x%08X)\n", status);
+	r100_mc_resume(rdev, &save);
+	dev_info(rdev->dev, "GPU reset succeed\n");
 	return 0;
 }
 
-
 /*
  * r300,r350,rv350,rv380 VRAM info
  */
diff --git a/drivers/gpu/drm/radeon/r300d.h b/drivers/gpu/drm/radeon/r300d.h
index 4c73114f0de..968a33317fb 100644
--- a/drivers/gpu/drm/radeon/r300d.h
+++ b/drivers/gpu/drm/radeon/r300d.h
@@ -209,7 +209,52 @@
 #define   S_000E40_GUI_ACTIVE(x)                       (((x) & 0x1) << 31)
 #define   G_000E40_GUI_ACTIVE(x)                       (((x) >> 31) & 0x1)
 #define   C_000E40_GUI_ACTIVE                          0x7FFFFFFF
-
+#define R_0000F0_RBBM_SOFT_RESET                     0x0000F0
+#define   S_0000F0_SOFT_RESET_CP(x)                    (((x) & 0x1) << 0)
+#define   G_0000F0_SOFT_RESET_CP(x)                    (((x) >> 0) & 0x1)
+#define   C_0000F0_SOFT_RESET_CP                       0xFFFFFFFE
+#define   S_0000F0_SOFT_RESET_HI(x)                    (((x) & 0x1) << 1)
+#define   G_0000F0_SOFT_RESET_HI(x)                    (((x) >> 1) & 0x1)
+#define   C_0000F0_SOFT_RESET_HI                       0xFFFFFFFD
+#define   S_0000F0_SOFT_RESET_VAP(x)                   (((x) & 0x1) << 2)
+#define   G_0000F0_SOFT_RESET_VAP(x)                   (((x) >> 2) & 0x1)
+#define   C_0000F0_SOFT_RESET_VAP                      0xFFFFFFFB
+#define   S_0000F0_SOFT_RESET_RE(x)                    (((x) & 0x1) << 3)
+#define   G_0000F0_SOFT_RESET_RE(x)                    (((x) >> 3) & 0x1)
+#define   C_0000F0_SOFT_RESET_RE                       0xFFFFFFF7
+#define   S_0000F0_SOFT_RESET_PP(x)                    (((x) & 0x1) << 4)
+#define   G_0000F0_SOFT_RESET_PP(x)                    (((x) >> 4) & 0x1)
+#define   C_0000F0_SOFT_RESET_PP                       0xFFFFFFEF
+#define   S_0000F0_SOFT_RESET_E2(x)                    (((x) & 0x1) << 5)
+#define   G_0000F0_SOFT_RESET_E2(x)                    (((x) >> 5) & 0x1)
+#define   C_0000F0_SOFT_RESET_E2                       0xFFFFFFDF
+#define   S_0000F0_SOFT_RESET_RB(x)                    (((x) & 0x1) << 6)
+#define   G_0000F0_SOFT_RESET_RB(x)                    (((x) >> 6) & 0x1)
+#define   C_0000F0_SOFT_RESET_RB                       0xFFFFFFBF
+#define   S_0000F0_SOFT_RESET_HDP(x)                   (((x) & 0x1) << 7)
+#define   G_0000F0_SOFT_RESET_HDP(x)                   (((x) >> 7) & 0x1)
+#define   C_0000F0_SOFT_RESET_HDP                      0xFFFFFF7F
+#define   S_0000F0_SOFT_RESET_MC(x)                    (((x) & 0x1) << 8)
+#define   G_0000F0_SOFT_RESET_MC(x)                    (((x) >> 8) & 0x1)
+#define   C_0000F0_SOFT_RESET_MC                       0xFFFFFEFF
+#define   S_0000F0_SOFT_RESET_AIC(x)                   (((x) & 0x1) << 9)
+#define   G_0000F0_SOFT_RESET_AIC(x)                   (((x) >> 9) & 0x1)
+#define   C_0000F0_SOFT_RESET_AIC                      0xFFFFFDFF
+#define   S_0000F0_SOFT_RESET_VIP(x)                   (((x) & 0x1) << 10)
+#define   G_0000F0_SOFT_RESET_VIP(x)                   (((x) >> 10) & 0x1)
+#define   C_0000F0_SOFT_RESET_VIP                      0xFFFFFBFF
+#define   S_0000F0_SOFT_RESET_DISP(x)                  (((x) & 0x1) << 11)
+#define   G_0000F0_SOFT_RESET_DISP(x)                  (((x) >> 11) & 0x1)
+#define   C_0000F0_SOFT_RESET_DISP                     0xFFFFF7FF
+#define   S_0000F0_SOFT_RESET_CG(x)                    (((x) & 0x1) << 12)
+#define   G_0000F0_SOFT_RESET_CG(x)                    (((x) >> 12) & 0x1)
+#define   C_0000F0_SOFT_RESET_CG                       0xFFFFEFFF
+#define   S_0000F0_SOFT_RESET_GA(x)                    (((x) & 0x1) << 13)
+#define   G_0000F0_SOFT_RESET_GA(x)                    (((x) >> 13) & 0x1)
+#define   C_0000F0_SOFT_RESET_GA                       0xFFFFDFFF
+#define   S_0000F0_SOFT_RESET_IDCT(x)                  (((x) & 0x1) << 14)
+#define   G_0000F0_SOFT_RESET_IDCT(x)                  (((x) >> 14) & 0x1)
+#define   C_0000F0_SOFT_RESET_IDCT                     0xFFFFBFFF
 
 #define R_00000D_SCLK_CNTL                           0x00000D
 #define   S_00000D_SCLK_SRC_SEL(x)                     (((x) & 0x7) << 0)
diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c
index 3ade473e69b..870111e26bd 100644
--- a/drivers/gpu/drm/radeon/r520.c
+++ b/drivers/gpu/drm/radeon/r520.c
@@ -53,7 +53,6 @@ static void r520_gpu_init(struct radeon_device *rdev)
 {
 	unsigned pipe_select_current, gb_pipe_select, tmp;
 
-	r100_hdp_reset(rdev);
 	rv515_vga_render_disable(rdev);
 	/*
 	 * DST_PIPE_CONFIG		0x170C
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 24fd5459fb4..13c9cc34231 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -749,7 +749,6 @@ int r600_gpu_soft_reset(struct radeon_device *rdev)
 			S_008014_DB2_BUSY(1) | S_008014_DB3_BUSY(1) |
 			S_008014_CB0_BUSY(1) | S_008014_CB1_BUSY(1) |
 			S_008014_CB2_BUSY(1) | S_008014_CB3_BUSY(1);
-	u32 srbm_reset = 0;
 	u32 tmp;
 
 	dev_info(rdev->dev, "GPU softreset \n");
@@ -764,7 +763,7 @@ int r600_gpu_soft_reset(struct radeon_device *rdev)
 		dev_warn(rdev->dev, "Wait for MC idle timedout !\n");
 	}
 	/* Disable CP parsing/prefetching */
-	WREG32(R_0086D8_CP_ME_CNTL, S_0086D8_CP_ME_HALT(0xff));
+	WREG32(R_0086D8_CP_ME_CNTL, S_0086D8_CP_ME_HALT(1));
 	/* Check if any of the rendering block is busy and reset it */
 	if ((RREG32(R_008010_GRBM_STATUS) & grbm_busy_mask) ||
 	    (RREG32(R_008014_GRBM_STATUS2) & grbm2_busy_mask)) {
@@ -783,55 +782,17 @@ int r600_gpu_soft_reset(struct radeon_device *rdev)
 			S_008020_SOFT_RESET_VGT(1);
 		dev_info(rdev->dev, "  R_008020_GRBM_SOFT_RESET=0x%08X\n", tmp);
 		WREG32(R_008020_GRBM_SOFT_RESET, tmp);
-		(void)RREG32(R_008020_GRBM_SOFT_RESET);
-		mdelay(1);
+		RREG32(R_008020_GRBM_SOFT_RESET);
+		mdelay(15);
 		WREG32(R_008020_GRBM_SOFT_RESET, 0);
-		(void)RREG32(R_008020_GRBM_SOFT_RESET);
 	}
 	/* Reset CP (we always reset CP) */
 	tmp = S_008020_SOFT_RESET_CP(1);
 	dev_info(rdev->dev, "R_008020_GRBM_SOFT_RESET=0x%08X\n", tmp);
 	WREG32(R_008020_GRBM_SOFT_RESET, tmp);
-	(void)RREG32(R_008020_GRBM_SOFT_RESET);
-	udelay(50);
+	RREG32(R_008020_GRBM_SOFT_RESET);
+	mdelay(15);
 	WREG32(R_008020_GRBM_SOFT_RESET, 0);
-	(void)RREG32(R_008020_GRBM_SOFT_RESET);
-	/* Reset others GPU block if necessary */
-	if (G_000E50_RLC_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_RLC(1);
-	if (G_000E50_GRBM_RQ_PENDING(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_GRBM(1);
-	if (G_000E50_HI_RQ_PENDING(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_IH(1);
-	if (G_000E50_VMC_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_VMC(1);
-	if (G_000E50_MCB_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_MC(1);
-	if (G_000E50_MCDZ_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_MC(1);
-	if (G_000E50_MCDY_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_MC(1);
-	if (G_000E50_MCDX_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_MC(1);
-	if (G_000E50_MCDW_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_MC(1);
-	if (G_000E50_RLC_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_RLC(1);
-	if (G_000E50_SEM_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_SEM(1);
-	if (G_000E50_BIF_BUSY(RREG32(R_000E50_SRBM_STATUS)))
-		srbm_reset |= S_000E60_SOFT_RESET_BIF(1);
-	dev_info(rdev->dev, "  R_000E60_SRBM_SOFT_RESET=0x%08X\n", srbm_reset);
-	WREG32(R_000E60_SRBM_SOFT_RESET, srbm_reset);
-	(void)RREG32(R_000E60_SRBM_SOFT_RESET);
-	mdelay(1);
-	WREG32(R_000E60_SRBM_SOFT_RESET, 0);
-	(void)RREG32(R_000E60_SRBM_SOFT_RESET);
-	WREG32(R_000E60_SRBM_SOFT_RESET, srbm_reset);
-	(void)RREG32(R_000E60_SRBM_SOFT_RESET);
-	mdelay(1);
-	WREG32(R_000E60_SRBM_SOFT_RESET, 0);
-	(void)RREG32(R_000E60_SRBM_SOFT_RESET);
 	/* Wait a little for things to settle down */
 	mdelay(1);
 	dev_info(rdev->dev, "  R_008010_GRBM_STATUS=0x%08X\n",
@@ -840,10 +801,6 @@ int r600_gpu_soft_reset(struct radeon_device *rdev)
 		RREG32(R_008014_GRBM_STATUS2));
 	dev_info(rdev->dev, "  R_000E50_SRBM_STATUS=0x%08X\n",
 		RREG32(R_000E50_SRBM_STATUS));
-	/* After reset we need to reinit the asic as GPU often endup in an
-	 * incoherent state.
-	 */
-	atom_asic_init(rdev->mode_info.atom_context);
 	rv515_mc_resume(rdev, &save);
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index f6c6c77db7e..d13622ae74e 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -447,6 +447,9 @@ int r600_blit_init(struct radeon_device *rdev)
 	u32 packet2s[16];
 	int num_packet2s = 0;
 
+	/* don't reinitialize blit */
+	if (rdev->r600_blit.shader_obj)
+		return 0;
 	mutex_init(&rdev->r600_blit.mutex);
 	rdev->r600_blit.state_offset = 0;
 
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 3cc5820b0e1..4ac97ab2894 100644
--- a/