Reworking of GPU reset logic + dumping

Reworking of GPU reset logic + dumping

[j.glisse]

Patches also available at:
http://people.freedesktop.org/~glisse/debug/

So it's the Christian series minus all the debugfs related to
ring/ib/mc. The last patch add a new blob dumping facilities
that dump everythings (pm4, relocs table, bo content). It's
just a proof of concept to show what i meant because code
speaks more clearly on this kind of topic.

The blob format we dump could be different i want with a
simple binary dword format:
type, id, size, [data (present if size > 0)]

Note that the benefit (simpler code, less code) of dumping
current debugfs seems to me greater than their usefullness.

Cheers,
Jerome

[PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files

[j.glisse]

From: Jerome Glisse <jglisse@redhat.com>

Those file never were really helpfull in debuging.

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
---
 drivers/gpu/drm/radeon/r100.c         |  186 ---------------------------------
 drivers/gpu/drm/radeon/r300.c         |   50 ---------
 drivers/gpu/drm/radeon/r420.c         |   45 --------
 drivers/gpu/drm/radeon/r520.c         |    1 -
 drivers/gpu/drm/radeon/r600.c         |   35 ------
 drivers/gpu/drm/radeon/radeon_asic.h  |    5 -
 drivers/gpu/drm/radeon/radeon_fence.c |   47 --------
 drivers/gpu/drm/radeon/radeon_ring.c  |  107 -------------------
 drivers/gpu/drm/radeon/rs400.c        |   88 ----------------
 drivers/gpu/drm/radeon/rs600.c        |    7 --
 drivers/gpu/drm/radeon/rs690.c        |    1 -
 drivers/gpu/drm/radeon/rv515.c        |   77 --------------
 12 files changed, 0 insertions(+), 649 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index fe33d35..9e69a95 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1094,9 +1094,6 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
 	uint32_t tmp;
 	int r;
 
-	if (r100_debugfs_cp_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for CP !\n");
-	}
 	if (!rdev->me_fw) {
 		r = r100_cp_init_microcode(rdev);
 		if (r) {
@@ -2604,178 +2601,6 @@ void r100_set_safe_registers(struct radeon_device *rdev)
 	}
 }
 
-/*
- * Debugfs info
- */
-#if defined(CONFIG_DEBUG_FS)
-static int r100_debugfs_rbbm_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	uint32_t reg, value;
-	unsigned i;
-
-	seq_printf(m, "RBBM_STATUS 0x%08x\n", RREG32(RADEON_RBBM_STATUS));
-	seq_printf(m, "RBBM_CMDFIFO_STAT 0x%08x\n", RREG32(0xE7C));
-	seq_printf(m, "CP_STAT 0x%08x\n", RREG32(RADEON_CP_STAT));
-	for (i = 0; i < 64; i++) {
-		WREG32(RADEON_RBBM_CMDFIFO_ADDR, i | 0x100);
-		reg = (RREG32(RADEON_RBBM_CMDFIFO_DATA) - 1) >> 2;
-		WREG32(RADEON_RBBM_CMDFIFO_ADDR, i);
-		value = RREG32(RADEON_RBBM_CMDFIFO_DATA);
-		seq_printf(m, "[0x%03X] 0x%04X=0x%08X\n", i, reg, value);
-	}
-	return 0;
-}
-
-static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	uint32_t rdp, wdp;
-	unsigned count, i, j;
-
-	radeon_ring_free_size(rdev, ring);
-	rdp = RREG32(RADEON_CP_RB_RPTR);
-	wdp = RREG32(RADEON_CP_RB_WPTR);
-	count = (rdp + ring->ring_size - wdp) & ring->ptr_mask;
-	seq_printf(m, "CP_STAT 0x%08x\n", RREG32(RADEON_CP_STAT));
-	seq_printf(m, "CP_RB_WPTR 0x%08x\n", wdp);
-	seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp);
-	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
-	seq_printf(m, "%u dwords in ring\n", count);
-	for (j = 0; j <= count; j++) {
-		i = (rdp + j) & ring->ptr_mask;
-		seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
-	}
-	return 0;
-}
-
-
-static int r100_debugfs_cp_csq_fifo(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	uint32_t csq_stat, csq2_stat, tmp;
-	unsigned r_rptr, r_wptr, ib1_rptr, ib1_wptr, ib2_rptr, ib2_wptr;
-	unsigned i;
-
-	seq_printf(m, "CP_STAT 0x%08x\n", RREG32(RADEON_CP_STAT));
-	seq_printf(m, "CP_CSQ_MODE 0x%08x\n", RREG32(RADEON_CP_CSQ_MODE));
-	csq_stat = RREG32(RADEON_CP_CSQ_STAT);
-	csq2_stat = RREG32(RADEON_CP_CSQ2_STAT);
-	r_rptr = (csq_stat >> 0) & 0x3ff;
-	r_wptr = (csq_stat >> 10) & 0x3ff;
-	ib1_rptr = (csq_stat >> 20) & 0x3ff;
-	ib1_wptr = (csq2_stat >> 0) & 0x3ff;
-	ib2_rptr = (csq2_stat >> 10) & 0x3ff;
-	ib2_wptr = (csq2_stat >> 20) & 0x3ff;
-	seq_printf(m, "CP_CSQ_STAT 0x%08x\n", csq_stat);
-	seq_printf(m, "CP_CSQ2_STAT 0x%08x\n", csq2_stat);
-	seq_printf(m, "Ring rptr %u\n", r_rptr);
-	seq_printf(m, "Ring wptr %u\n", r_wptr);
-	seq_printf(m, "Indirect1 rptr %u\n", ib1_rptr);
-	seq_printf(m, "Indirect1 wptr %u\n", ib1_wptr);
-	seq_printf(m, "Indirect2 rptr %u\n", ib2_rptr);
-	seq_printf(m, "Indirect2 wptr %u\n", ib2_wptr);
-	/* FIXME: 0, 128, 640 depends on fifo setup see cp_init_kms
-	 * 128 = indirect1_start * 8 & 640 = indirect2_start * 8 */
-	seq_printf(m, "Ring fifo:\n");
-	for (i = 0; i < 256; i++) {
-		WREG32(RADEON_CP_CSQ_ADDR, i << 2);
-		tmp = RREG32(RADEON_CP_CSQ_DATA);
-		seq_printf(m, "rfifo[%04d]=0x%08X\n", i, tmp);
-	}
-	seq_printf(m, "Indirect1 fifo:\n");
-	for (i = 256; i <= 512; i++) {
-		WREG32(RADEON_CP_CSQ_ADDR, i << 2);
-		tmp = RREG32(RADEON_CP_CSQ_DATA);
-		seq_printf(m, "ib1fifo[%04d]=0x%08X\n", i, tmp);
-	}
-	seq_printf(m, "Indirect2 fifo:\n");
-	for (i = 640; i < ib1_wptr; i++) {
-		WREG32(RADEON_CP_CSQ_ADDR, i << 2);
-		tmp = RREG32(RADEON_CP_CSQ_DATA);
-		seq_printf(m, "ib2fifo[%04d]=0x%08X\n", i, tmp);
-	}
-	return 0;
-}
-
-static int r100_debugfs_mc_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	uint32_t tmp;
-
-	tmp = RREG32(RADEON_CONFIG_MEMSIZE);
-	seq_printf(m, "CONFIG_MEMSIZE 0x%08x\n", tmp);
-	tmp = RREG32(RADEON_MC_FB_LOCATION);
-	seq_printf(m, "MC_FB_LOCATION 0x%08x\n", tmp);
-	tmp = RREG32(RADEON_BUS_CNTL);
-	seq_printf(m, "BUS_CNTL 0x%08x\n", tmp);
-	tmp = RREG32(RADEON_MC_AGP_LOCATION);
-	seq_printf(m, "MC_AGP_LOCATION 0x%08x\n", tmp);
-	tmp = RREG32(RADEON_AGP_BASE);
-	seq_printf(m, "AGP_BASE 0x%08x\n", tmp);
-	tmp = RREG32(RADEON_HOST_PATH_CNTL);
-	seq_printf(m, "HOST_PATH_CNTL 0x%08x\n", tmp);
-	tmp = RREG32(0x01D0);
-	seq_printf(m, "AIC_CTRL 0x%08x\n", tmp);
-	tmp = RREG32(RADEON_AIC_LO_ADDR);
-	seq_printf(m, "AIC_LO_ADDR 0x%08x\n", tmp);
-	tmp = RREG32(RADEON_AIC_HI_ADDR);
-	seq_printf(m, "AIC_HI_ADDR 0x%08x\n", tmp);
-	tmp = RREG32(0x01E4);
-	seq_printf(m, "AIC_TLB_ADDR 0x%08x\n", tmp);
-	return 0;
-}
-
-static struct drm_info_list r100_debugfs_rbbm_list[] = {
-	{"r100_rbbm_info", r100_debugfs_rbbm_info, 0, NULL},
-};
-
-static struct drm_info_list r100_debugfs_cp_list[] = {
-	{"r100_cp_ring_info", r100_debugfs_cp_ring_info, 0, NULL},
-	{"r100_cp_csq_fifo", r100_debugfs_cp_csq_fifo, 0, NULL},
-};
-
-static struct drm_info_list r100_debugfs_mc_info_list[] = {
-	{"r100_mc_info", r100_debugfs_mc_info, 0, NULL},
-};
-#endif
-
-int r100_debugfs_rbbm_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, r100_debugfs_rbbm_list, 1);
-#else
-	return 0;
-#endif
-}
-
-int r100_debugfs_cp_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, r100_debugfs_cp_list, 2);
-#else
-	return 0;
-#endif
-}
-
-int r100_debugfs_mc_info_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, r100_debugfs_mc_info_list, 1);
-#else
-	return 0;
-#endif
-}
-
 int r100_set_surface_reg(struct radeon_device *rdev, int reg,
 			 uint32_t tiling_flags, uint32_t pitch,
 			 uint32_t offset, uint32_t obj_size)
@@ -3868,15 +3693,6 @@ void r100_vga_render_disable(struct radeon_device *rdev)
 	WREG8(R_0003C2_GENMO_WT, C_0003C2_VGA_RAM_EN & tmp);
 }
 
-static void r100_debugfs(struct radeon_device *rdev)
-{
-	int r;
-
-	r = r100_debugfs_mc_info_init(rdev);
-	if (r)
-		dev_warn(rdev->dev, "Failed to create r100_mc debugfs file.\n");
-}
-
 static void r100_mc_program(struct radeon_device *rdev)
 {
 	struct r100_mc_save save;
@@ -4062,8 +3878,6 @@ int r100_init(struct radeon_device *rdev)
 {
 	int r;
 
-	/* Register debugfs file specific to this group of asics */
-	r100_debugfs(rdev);
 	/* Disable VGA */
 	r100_vga_render_disable(rdev);
 	/* Initialize scratch registers */
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index fa14383..c5237ab 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -52,8 +52,6 @@
 /*
  * rv370,rv380 PCIE GART
  */
-static int rv370_debugfs_pcie_gart_info_init(struct radeon_device *rdev);
-
 void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev)
 {
 	uint32_t tmp;
@@ -101,9 +99,6 @@ int rv370_pcie_gart_init(struct radeon_device *rdev)
 	r = radeon_gart_init(rdev);
 	if (r)
 		return r;
-	r = rv370_debugfs_pcie_gart_info_init(rdev);
-	if (r)
-		DRM_ERROR("Failed to register debugfs file for PCIE gart !\n");
 	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
 	rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
 	rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
@@ -576,45 +571,6 @@ int rv370_get_pcie_lanes(struct radeon_device *rdev)
 	}
 }
 
-#if defined(CONFIG_DEBUG_FS)
-static int rv370_debugfs_pcie_gart_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	uint32_t tmp;
-
-	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_CNTL);
-	seq_printf(m, "PCIE_TX_GART_CNTL 0x%08x\n", tmp);
-	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_BASE);
-	seq_printf(m, "PCIE_TX_GART_BASE 0x%08x\n", tmp);
-	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_START_LO);
-	seq_printf(m, "PCIE_TX_GART_START_LO 0x%08x\n", tmp);
-	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_START_HI);
-	seq_printf(m, "PCIE_TX_GART_START_HI 0x%08x\n", tmp);
-	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_END_LO);
-	seq_printf(m, "PCIE_TX_GART_END_LO 0x%08x\n", tmp);
-	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_END_HI);
-	seq_printf(m, "PCIE_TX_GART_END_HI 0x%08x\n", tmp);
-	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_ERROR);
-	seq_printf(m, "PCIE_TX_GART_ERROR 0x%08x\n", tmp);
-	return 0;
-}
-
-static struct drm_info_list rv370_pcie_gart_info_list[] = {
-	{"rv370_pcie_gart_info", rv370_debugfs_pcie_gart_info, 0, NULL},
-};
-#endif
-
-static int rv370_debugfs_pcie_gart_info_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, rv370_pcie_gart_info_list, 1);
-#else
-	return 0;
-#endif
-}
-
 static int r300_packet0_check(struct radeon_cs_parser *p,
 		struct radeon_cs_packet *pkt,
 		unsigned idx, unsigned reg)
@@ -1317,12 +1273,6 @@ void r300_set_reg_safe(struct radeon_device *rdev)
 void r300_mc_program(struct radeon_device *rdev)
 {
 	struct r100_mc_save save;
-	int r;
-
-	r = r100_debugfs_mc_info_init(rdev);
-	if (r) {
-		dev_err(rdev->dev, "Failed to create r100_mc debugfs file.\n");
-	}
 
 	/* Stops all mc clients */
 	r100_mc_stop(rdev, &save);
diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c
index f3fcaac..2eba44c 100644
--- a/drivers/gpu/drm/radeon/r420.c
+++ b/drivers/gpu/drm/radeon/r420.c
@@ -174,16 +174,6 @@ void r420_mc_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 	WREG32(R_0001FC_MC_IND_DATA, v);
 }
 
-static void r420_debugfs(struct radeon_device *rdev)
-{
-	if (r100_debugfs_rbbm_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for RBBM !\n");
-	}
-	if (r420_debugfs_pipes_info_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for pipes !\n");
-	}
-}
-
 static void r420_clock_resume(struct radeon_device *rdev)
 {
 	u32 sclk_cntl;
@@ -411,7 +401,6 @@ int r420_init(struct radeon_device *rdev)
 	}
 	/* initialize memory controller */
 	r300_mc_init(rdev);
-	r420_debugfs(rdev);
 	/* Fence driver */
 	r = radeon_fence_driver_init(rdev);
 	if (r) {
@@ -465,37 +454,3 @@ int r420_init(struct radeon_device *rdev)
 	}
 	return 0;
 }
-
-/*
- * Debugfs info
- */
-#if defined(CONFIG_DEBUG_FS)
-static int r420_debugfs_pipes_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	uint32_t tmp;
-
-	tmp = RREG32(R400_GB_PIPE_SELECT);
-	seq_printf(m, "GB_PIPE_SELECT 0x%08x\n", tmp);
-	tmp = RREG32(R300_GB_TILE_CONFIG);
-	seq_printf(m, "GB_TILE_CONFIG 0x%08x\n", tmp);
-	tmp = RREG32(R300_DST_PIPE_CONFIG);
-	seq_printf(m, "DST_PIPE_CONFIG 0x%08x\n", tmp);
-	return 0;
-}
-
-static struct drm_info_list r420_pipes_info_list[] = {
-	{"r420_pipes_info", r420_debugfs_pipes_info, 0, NULL},
-};
-#endif
-
-int r420_debugfs_pipes_info_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, r420_pipes_info_list, 1);
-#else
-	return 0;
-#endif
-}
diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c
index ebcc15b..2e5ff86 100644
--- a/drivers/gpu/drm/radeon/r520.c
+++ b/drivers/gpu/drm/radeon/r520.c
@@ -296,7 +296,6 @@ int r520_init(struct radeon_device *rdev)
 	}
 	/* initialize memory controller */
 	r520_mc_init(rdev);
-	rv515_debugfs(rdev);
 	/* Fence driver */
 	r = radeon_fence_driver_init(rdev);
 	if (r)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index de71243..62299d8 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -94,8 +94,6 @@ MODULE_FIRMWARE("radeon/SUMO_me.bin");
 MODULE_FIRMWARE("radeon/SUMO2_pfp.bin");
 MODULE_FIRMWARE("radeon/SUMO2_me.bin");
 
-int r600_debugfs_mc_info_init(struct radeon_device *rdev);
-
 /* r600,rv610,rv630,rv620,rv635,rv670 */
 int r600_mc_wait_for_idle(struct radeon_device *rdev);
 void r600_gpu_init(struct radeon_device *rdev);
@@ -2571,9 +2569,6 @@ int r600_init(struct radeon_device *rdev)
 {
 	int r;
 
-	if (r600_debugfs_mc_info_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for mc !\n");
-	}
 	/* This don't do much */
 	r = radeon_gem_init(rdev);
 	if (r)
@@ -3520,36 +3515,6 @@ restart_ih:
 	return IRQ_HANDLED;
 }
 
-/*
- * Debugfs info
- */
-#if defined(CONFIG_DEBUG_FS)
-
-static int r600_debugfs_mc_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-
-	DREG32_SYS(m, rdev, R_000E50_SRBM_STATUS);
-	DREG32_SYS(m, rdev, VM_L2_STATUS);
-	return 0;
-}
-
-static struct drm_info_list r600_mc_info_list[] = {
-	{"r600_mc_info", r600_debugfs_mc_info, 0, NULL},
-};
-#endif
-
-int r600_debugfs_mc_info_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, r600_mc_info_list, ARRAY_SIZE(r600_mc_info_list));
-#else
-	return 0;
-#endif
-}
-
 /**
  * r600_ioctl_wait_idle - flush host path cache on wait idle ioctl
  * rdev: radeon device structure
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 3d9f9f1..6f31f9a 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -92,8 +92,6 @@ void r100_hpd_fini(struct radeon_device *rdev);
 bool r100_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd);
 void r100_hpd_set_polarity(struct radeon_device *rdev,
 			   enum radeon_hpd_id hpd);
-int r100_debugfs_rbbm_init(struct radeon_device *rdev);
-int r100_debugfs_cp_init(struct radeon_device *rdev);
 void r100_cp_disable(struct radeon_device *rdev);
 int r100_cp_init(struct radeon_device *rdev, unsigned ring_size);
 void r100_cp_fini(struct radeon_device *rdev);
@@ -101,7 +99,6 @@ int r100_pci_gart_init(struct radeon_device *rdev);
 void r100_pci_gart_fini(struct radeon_device *rdev);
 int r100_pci_gart_enable(struct radeon_device *rdev);
 void r100_pci_gart_disable(struct radeon_device *rdev);
-int r100_debugfs_mc_info_init(struct radeon_device *rdev);
 int r100_gui_wait_for_idle(struct radeon_device *rdev);
 void r100_gpu_lockup_update(struct r100_gpu_lockup *lockup,
 			    struct radeon_ring *cp);
@@ -190,7 +187,6 @@ extern int r420_resume(struct radeon_device *rdev);
 extern void r420_pm_init_profile(struct radeon_device *rdev);
 extern u32 r420_mc_rreg(struct radeon_device *rdev, u32 reg);
 extern void r420_mc_wreg(struct radeon_device *rdev, u32 reg, u32 v);
-extern int r420_debugfs_pipes_info_init(struct radeon_device *rdev);
 extern void r420_pipes_init(struct radeon_device *rdev);
 
 /*
@@ -283,7 +279,6 @@ void rv515_set_safe_registers(struct radeon_device *rdev);
 void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save);
 void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save);
 void rv515_clock_startup(struct radeon_device *rdev);
-void rv515_debugfs(struct radeon_device *rdev);
 int rv515_mc_wait_for_idle(struct radeon_device *rdev);
 
 /*
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 4bd36a3..7f588d4 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -436,9 +436,6 @@ int radeon_fence_driver_init(struct radeon_device *rdev)
 		radeon_fence_driver_init_ring(rdev, ring);
 	}
 	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-	if (radeon_debugfs_fence_init(rdev)) {
-		dev_err(rdev->dev, "fence debugfs file creation failed\n");
-	}
 	return 0;
 }
 
@@ -458,47 +455,3 @@ void radeon_fence_driver_fini(struct radeon_device *rdev)
 		rdev->fence_drv[ring].initialized = false;
 	}
 }
-
-
-/*
- * Fence debugfs
- */
-#if defined(CONFIG_DEBUG_FS)
-static int radeon_debugfs_fence_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *)m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	struct radeon_fence *fence;
-	int i;
-
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		if (!rdev->fence_drv[i].initialized)
-			continue;
-
-		seq_printf(m, "--- ring %d ---\n", i);
-		seq_printf(m, "Last signaled fence 0x%08X\n",
-			   radeon_fence_read(rdev, i));
-		if (!list_empty(&rdev->fence_drv[i].emitted)) {
-			fence = list_entry(rdev->fence_drv[i].emitted.prev,
-					   struct radeon_fence, list);
-			seq_printf(m, "Last emitted fence %p with 0x%08X\n",
-				   fence,  fence->seq);
-		}
-	}
-	return 0;
-}
-
-static struct drm_info_list radeon_debugfs_fence_list[] = {
-	{"radeon_fence_info", &radeon_debugfs_fence_info, 0, NULL},
-};
-#endif
-
-int radeon_debugfs_fence_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, radeon_debugfs_fence_list, 1);
-#else
-	return 0;
-#endif
-}
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index cc33b3d..aac84b3 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -33,9 +33,6 @@
 #include "radeon.h"
 #include "atom.h"
 
-int radeon_debugfs_ib_init(struct radeon_device *rdev);
-int radeon_debugfs_ring_init(struct radeon_device *rdev);
-
 u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
 {
 	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
@@ -234,12 +231,6 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 	rdev->ib_pool.ready = true;
 	DRM_INFO("radeon: ib pool ready.\n");
 
-	if (radeon_debugfs_ib_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for IB !\n");
-	}
-	if (radeon_debugfs_ring_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for rings !\n");
-	}
 	radeon_mutex_unlock(&rdev->ib_pool.mutex);
 	return 0;
 }
@@ -435,101 +426,3 @@ void radeon_ring_fini(struct radeon_device *rdev, struct radeon_ring *ring)
 		radeon_bo_unref(&ring_obj);
 	}
 }
-
-/*
- * Debugfs info
- */
-#if defined(CONFIG_DEBUG_FS)
-
-static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	int ridx = *(int*)node->info_ent->data;
-	struct radeon_ring *ring = &rdev->ring[ridx];
-	unsigned count, i, j;
-
-	radeon_ring_free_size(rdev, ring);
-	count = (ring->ring_size / 4) - ring->ring_free_dw;
-	seq_printf(m, "wptr(0x%04x): 0x%08x\n", ring->wptr_reg, RREG32(ring->wptr_reg));
-	seq_printf(m, "rptr(0x%04x): 0x%08x\n", ring->rptr_reg, RREG32(ring->rptr_reg));
-	seq_printf(m, "driver's copy of the wptr: 0x%08x\n", ring->wptr);
-	seq_printf(m, "driver's copy of the rptr: 0x%08x\n", ring->rptr);
-	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
-	seq_printf(m, "%u dwords in ring\n", count);
-	i = ring->rptr;
-	for (j = 0; j <= count; j++) {
-		seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
-		i = (i + 1) & ring->ptr_mask;
-	}
-	return 0;
-}
-
-static int radeon_ring_type_gfx_index = RADEON_RING_TYPE_GFX_INDEX;
-static int cayman_ring_type_cp1_index = CAYMAN_RING_TYPE_CP1_INDEX;
-static int cayman_ring_type_cp2_index = CAYMAN_RING_TYPE_CP2_INDEX;
-
-static struct drm_info_list radeon_debugfs_ring_info_list[] = {
-	{"radeon_ring_gfx", radeon_debugfs_ring_info, 0, &radeon_ring_type_gfx_index},
-	{"radeon_ring_cp1", radeon_debugfs_ring_info, 0, &cayman_ring_type_cp1_index},
-	{"radeon_ring_cp2", radeon_debugfs_ring_info, 0, &cayman_ring_type_cp2_index},
-};
-
-static int radeon_debugfs_ib_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	struct radeon_ib *ib = &rdev->ib_pool.ibs[*((unsigned*)node->info_ent->data)];
-	unsigned i;
-
-	if (ib == NULL) {
-		return 0;
-	}
-	seq_printf(m, "IB %04u\n", ib->idx);
-	seq_printf(m, "IB fence %p\n", ib->fence);
-	seq_printf(m, "IB size %05u dwords\n", ib->length_dw);
-	for (i = 0; i < ib->length_dw; i++) {
-		seq_printf(m, "[%05u]=0x%08X\n", i, ib->ptr[i]);
-	}
-	return 0;
-}
-
-static struct drm_info_list radeon_debugfs_ib_list[RADEON_IB_POOL_SIZE];
-static char radeon_debugfs_ib_names[RADEON_IB_POOL_SIZE][32];
-static unsigned radeon_debugfs_ib_idx[RADEON_IB_POOL_SIZE];
-#endif
-
-int radeon_debugfs_ring_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	if (rdev->family >= CHIP_CAYMAN)
-		return radeon_debugfs_add_files(rdev, radeon_debugfs_ring_info_list,
-						ARRAY_SIZE(radeon_debugfs_ring_info_list));
-	else
-		return radeon_debugfs_add_files(rdev, radeon_debugfs_ring_info_list, 1);
-#else
-	return 0;
-#endif
-}
-
-int radeon_debugfs_ib_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	unsigned i;
-
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		sprintf(radeon_debugfs_ib_names[i], "radeon_ib_%04u", i);
-		radeon_debugfs_ib_idx[i] = i;
-		radeon_debugfs_ib_list[i].name = radeon_debugfs_ib_names[i];
-		radeon_debugfs_ib_list[i].show = &radeon_debugfs_ib_info;
-		radeon_debugfs_ib_list[i].driver_features = 0;
-		radeon_debugfs_ib_list[i].data = &radeon_debugfs_ib_idx[i];
-	}
-	return radeon_debugfs_add_files(rdev, radeon_debugfs_ib_list,
-					RADEON_IB_POOL_SIZE);
-#else
-	return 0;
-#endif
-}
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index 4cf381b..0c0a0df 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -33,8 +33,6 @@
 #include "rs400d.h"
 
 /* This files gather functions specifics to : rs400,rs480 */
-static int rs400_debugfs_pcie_gart_info_init(struct radeon_device *rdev);
-
 void rs400_gart_adjust_size(struct radeon_device *rdev)
 {
 	/* Check gart size */
@@ -98,8 +96,6 @@ int rs400_gart_init(struct radeon_device *rdev)
 	r = radeon_gart_init(rdev);
 	if (r)
 		return r;
-	if (rs400_debugfs_pcie_gart_info_init(rdev))
-		DRM_ERROR("Failed to register debugfs file for RS400 GART !\n");
 	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
 	return radeon_gart_table_ram_alloc(rdev);
 }
@@ -286,90 +282,6 @@ void rs400_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 	WREG32(RS480_NB_MC_INDEX, 0xff);
 }
 
-#if defined(CONFIG_DEBUG_FS)
-static int rs400_debugfs_gart_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	uint32_t tmp;
-
-	tmp = RREG32(RADEON_HOST_PATH_CNTL);
-	seq_printf(m, "HOST_PATH_CNTL 0x%08x\n", tmp);
-	tmp = RREG32(RADEON_BUS_CNTL);
-	seq_printf(m, "BUS_CNTL 0x%08x\n", tmp);
-	tmp = RREG32_MC(RS690_AIC_CTRL_SCRATCH);
-	seq_printf(m, "AIC_CTRL_SCRATCH 0x%08x\n", tmp);
-	if (rdev->family == CHIP_RS690 || (rdev->family == CHIP_RS740)) {
-		tmp = RREG32_MC(RS690_MCCFG_AGP_BASE);
-		seq_printf(m, "MCCFG_AGP_BASE 0x%08x\n", tmp);
-		tmp = RREG32_MC(RS690_MCCFG_AGP_BASE_2);
-		seq_printf(m, "MCCFG_AGP_BASE_2 0x%08x\n", tmp);
-		tmp = RREG32_MC(RS690_MCCFG_AGP_LOCATION);
-		seq_printf(m, "MCCFG_AGP_LOCATION 0x%08x\n", tmp);
-		tmp = RREG32_MC(RS690_MCCFG_FB_LOCATION);
-		seq_printf(m, "MCCFG_FB_LOCATION 0x%08x\n", tmp);
-		tmp = RREG32(RS690_HDP_FB_LOCATION);
-		seq_printf(m, "HDP_FB_LOCATION 0x%08x\n", tmp);
-	} else {
-		tmp = RREG32(RADEON_AGP_BASE);
-		seq_printf(m, "AGP_BASE 0x%08x\n", tmp);
-		tmp = RREG32(RS480_AGP_BASE_2);
-		seq_printf(m, "AGP_BASE_2 0x%08x\n", tmp);
-		tmp = RREG32(RADEON_MC_AGP_LOCATION);
-		seq_printf(m, "MC_AGP_LOCATION 0x%08x\n", tmp);
-	}
-	tmp = RREG32_MC(RS480_GART_BASE);
-	seq_printf(m, "GART_BASE 0x%08x\n", tmp);
-	tmp = RREG32_MC(RS480_GART_FEATURE_ID);
-	seq_printf(m, "GART_FEATURE_ID 0x%08x\n", tmp);
-	tmp = RREG32_MC(RS480_AGP_MODE_CNTL);
-	seq_printf(m, "AGP_MODE_CONTROL 0x%08x\n", tmp);
-	tmp = RREG32_MC(RS480_MC_MISC_CNTL);
-	seq_printf(m, "MC_MISC_CNTL 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x5F);
-	seq_printf(m, "MC_MISC_UMA_CNTL 0x%08x\n", tmp);
-	tmp = RREG32_MC(RS480_AGP_ADDRESS_SPACE_SIZE);
-	seq_printf(m, "AGP_ADDRESS_SPACE_SIZE 0x%08x\n", tmp);
-	tmp = RREG32_MC(RS480_GART_CACHE_CNTRL);
-	seq_printf(m, "GART_CACHE_CNTRL 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x3B);
-	seq_printf(m, "MC_GART_ERROR_ADDRESS 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x3C);
-	seq_printf(m, "MC_GART_ERROR_ADDRESS_HI 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x30);
-	seq_printf(m, "GART_ERROR_0 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x31);
-	seq_printf(m, "GART_ERROR_1 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x32);
-	seq_printf(m, "GART_ERROR_2 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x33);
-	seq_printf(m, "GART_ERROR_3 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x34);
-	seq_printf(m, "GART_ERROR_4 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x35);
-	seq_printf(m, "GART_ERROR_5 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x36);
-	seq_printf(m, "GART_ERROR_6 0x%08x\n", tmp);
-	tmp = RREG32_MC(0x37);
-	seq_printf(m, "GART_ERROR_7 0x%08x\n", tmp);
-	return 0;
-}
-
-static struct drm_info_list rs400_gart_info_list[] = {
-	{"rs400_gart_info", rs400_debugfs_gart_info, 0, NULL},
-};
-#endif
-
-static int rs400_debugfs_pcie_gart_info_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, rs400_gart_info_list, 1);
-#else
-	return 0;
-#endif
-}
-
 void rs400_mc_program(struct radeon_device *rdev)
 {
 	struct r100_mc_save save;
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index d25cf86..dc5ec8c 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -800,12 +800,6 @@ void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 	WREG32(R_000074_MC_IND_DATA, v);
 }
 
-void rs600_debugfs(struct radeon_device *rdev)
-{
-	if (r100_debugfs_rbbm_init(rdev))
-		DRM_ERROR("Failed to register debugfs file for RBBM !\n");
-}
-
 void rs600_set_safe_registers(struct radeon_device *rdev)
 {
 	rdev->config.r300.reg_safe_bm = rs600_reg_safe_bm;
@@ -989,7 +983,6 @@ int rs600_init(struct radeon_device *rdev)
 	radeon_get_clock_info(rdev->ddev);
 	/* initialize memory controller */
 	rs600_mc_init(rdev);
-	rs600_debugfs(rdev);
 	/* Fence driver */
 	r = radeon_fence_driver_init(rdev);
 	if (r)
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index f2c3b9d..752e81b 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -754,7 +754,6 @@ int rs690_init(struct radeon_device *rdev)
 	radeon_get_clock_info(rdev->ddev);
 	/* initialize memory controller */
 	rs690_mc_init(rdev);
-	rv515_debugfs(rdev);
 	/* Fence driver */
 	r = radeon_fence_driver_init(rdev);
 	if (r)
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index d8d78fe..2f9062a 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -35,24 +35,9 @@
 #include "rv515_reg_safe.h"
 
 /* This files gather functions specifics to: rv515 */
-int rv515_debugfs_pipes_info_init(struct radeon_device *rdev);
-int rv515_debugfs_ga_info_init(struct radeon_device *rdev);
 void rv515_gpu_init(struct radeon_device *rdev);
 int rv515_mc_wait_for_idle(struct radeon_device *rdev);
 
-void rv515_debugfs(struct radeon_device *rdev)
-{
-	if (r100_debugfs_rbbm_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for RBBM !\n");
-	}
-	if (rv515_debugfs_pipes_info_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for pipes !\n");
-	}
-	if (rv515_debugfs_ga_info_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for pipes !\n");
-	}
-}
-
 void rv515_ring_start(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	int r;
@@ -218,67 +203,6 @@ void rv515_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 	WREG32(MC_IND_INDEX, 0);
 }
 
-#if defined(CONFIG_DEBUG_FS)
-static int rv515_debugfs_pipes_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	uint32_t tmp;
-
-	tmp = RREG32(GB_PIPE_SELECT);
-	seq_printf(m, "GB_PIPE_SELECT 0x%08x\n", tmp);
-	tmp = RREG32(SU_REG_DEST);
-	seq_printf(m, "SU_REG_DEST 0x%08x\n", tmp);
-	tmp = RREG32(GB_TILE_CONFIG);
-	seq_printf(m, "GB_TILE_CONFIG 0x%08x\n", tmp);
-	tmp = RREG32(DST_PIPE_CONFIG);
-	seq_printf(m, "DST_PIPE_CONFIG 0x%08x\n", tmp);
-	return 0;
-}
-
-static int rv515_debugfs_ga_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct radeon_device *rdev = dev->dev_private;
-	uint32_t tmp;
-
-	tmp = RREG32(0x2140);
-	seq_printf(m, "VAP_CNTL_STATUS 0x%08x\n", tmp);
-	radeon_asic_reset(rdev);
-	tmp = RREG32(0x425C);
-	seq_printf(m, "GA_IDLE 0x%08x\n", tmp);
-	return 0;
-}
-
-static struct drm_info_list rv515_pipes_info_list[] = {
-	{"rv515_pipes_info", rv515_debugfs_pipes_info, 0, NULL},
-};
-
-static struct drm_info_list rv515_ga_info_list[] = {
-	{"rv515_ga_info", rv515_debugfs_ga_info, 0, NULL},
-};
-#endif
-
-int rv515_debugfs_pipes_info_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, rv515_pipes_info_list, 1);
-#else
-	return 0;
-#endif
-}
-
-int rv515_debugfs_ga_info_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, rv515_ga_info_list, 1);
-#else
-	return 0;
-#endif
-}
-
 void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save)
 {
 	save->d1vga_control = RREG32(R_000330_D1VGA_CONTROL);
@@ -528,7 +452,6 @@ int rv515_init(struct radeon_device *rdev)
 	}
 	/* initialize memory controller */
 	rv515_mc_init(rdev);
-	rv515_debugfs(rdev);
 	/* Fence driver */
 	r = radeon_fence_driver_init(rdev);
 	if (r)
-- 
1.7.7.6

Re: [PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files

[Christian König]

Hi Jerome,

I totally agree that we can remove the following debugfs files, since 
everything that just prints out or modifies register informations 
doesn't belongs into the kernel driver and should be moved to radeontool 
instead.
> static int r100_debugfs_rbbm_info(struct seq_file *m, void *data)
> static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data)
> static int r100_debugfs_cp_csq_fifo(struct seq_file *m, void *data)
> static int r100_debugfs_mc_info(struct seq_file *m, void *data)
> static int rv370_debugfs_pcie_gart_info(struct seq_file *m, void *data)
> static int r420_debugfs_pipes_info(struct seq_file *m, void *data)
> static int r600_debugfs_mc_info(struct seq_file *m, void *data)
> static int rs400_debugfs_gart_info(struct seq_file *m, void *data)
> static int rv515_debugfs_pipes_info(struct seq_file *m, void *data)
> static int rv515_debugfs_ga_info(struct seq_file *m, void *data)

But I disagree that we should remove the following two, cause they print 
out driver internal data structures and it isn't easy to gain access to 
those, at least without a debugger and allot of patience.
> static int radeon_debugfs_fence_info(struct seq_file *m, void *data)
> static int radeon_debugfs_sa_info(struct seq_file *m, void *data)

Also I think I should mention that your patch doesn't touches the 
following two debugfs files, probably because of the same reason as the 
two above.
> static int radeon_mm_dump_table(struct seq_file *m, void *data)
> static int radeon_debugfs_pm_info(struct seq_file *m, void *data)

I also think that we should keep the ring debugfs file but of course not 
with the IB dumping facility, since otherwise we pretty much lose any 
possibility to look into multi ring lockups, which is something I 
currently spend most of my time on.
> static int radeon_debugfs_ring_info(struct seq_file *m, void *data)

Additionally I have some comments on the dumping patch itself, but going 
to write that in a separate mail.

Cheers,
Christian.

Re: [PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files

[David Airlie]

----- Original Message -----
> From: "Christian König" <deathsimple@vodafone.de>
> To: "j glisse" <j.glisse@gmail.com>
> Cc: "Jerome Glisse" <jglisse@redhat.com>, dri-devel@lists.freedesktop.org
> Sent: Thursday, 26 April, 2012 10:11:12 AM
> Subject: Re: [PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files
> 
> Hi Jerome,
> 
> I totally agree that we can remove the following debugfs files, since
> everything that just prints out or modifies register informations
> doesn't belongs into the kernel driver and should be moved to
> radeontool
> instead.

In the future with secure boot we will need a better mechanism to diagnose things
than a userspace tool mapping pci bars, which we can't allow to happen in a secure
boot environment, so dropping all the files might not be a good idea unless we
provide a mechanism for radeontool to use. We can't allow userspace to read/write
arbitrary registers and stay secure.

Dave.
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files

[Jerome Glisse]

2012/4/26 David Airlie <airlied@redhat.com>:
>
>
> ----- Original Message -----
>> From: "Christian König" <deathsimple@vodafone.de>
>> To: "j glisse" <j.glisse@gmail.com>
>> Cc: "Jerome Glisse" <jglisse@redhat.com>, dri-devel@lists.freedesktop.org
>> Sent: Thursday, 26 April, 2012 10:11:12 AM
>> Subject: Re: [PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files
>>
>> Hi Jerome,
>>
>> I totally agree that we can remove the following debugfs files, since
>> everything that just prints out or modifies register informations
>> doesn't belongs into the kernel driver and should be moved to
>> radeontool
>> instead.
>
> In the future with secure boot we will need a better mechanism to diagnose things
> than a userspace tool mapping pci bars, which we can't allow to happen in a secure
> boot environment, so dropping all the files might not be a good idea unless we
> provide a mechanism for radeontool to use. We can't allow userspace to read/write
> arbitrary registers and stay secure.
>
> Dave.

Well those files are useless, each time i debug a lockup and try to
use them i loose
time on them as they never helped me so far and i seriously doubt they
would help
me in the future or anyone else.

For secure boot my guess is that radeontool will become obsolete and
by that time
we might need to add some reg dumping. But none of the current files
seems usefull
to me.

The fence and sa files might make sense to debug the associated code
as it's nice
to be able to dump associated kernel struct.

Cheers,
Jerome

Re: [PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files

[Alex Deucher]

On Thu, Apr 26, 2012 at 9:36 AM, Jerome Glisse <j.glisse@gmail.com> wrote:
> 2012/4/26 David Airlie <airlied@redhat.com>:
>>
>>
>> ----- Original Message -----
>>> From: "Christian König" <deathsimple@vodafone.de>
>>> To: "j glisse" <j.glisse@gmail.com>
>>> Cc: "Jerome Glisse" <jglisse@redhat.com>, dri-devel@lists.freedesktop.org
>>> Sent: Thursday, 26 April, 2012 10:11:12 AM
>>> Subject: Re: [PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files
>>>
>>> Hi Jerome,
>>>
>>> I totally agree that we can remove the following debugfs files, since
>>> everything that just prints out or modifies register informations
>>> doesn't belongs into the kernel driver and should be moved to
>>> radeontool
>>> instead.
>>
>> In the future with secure boot we will need a better mechanism to diagnose things
>> than a userspace tool mapping pci bars, which we can't allow to happen in a secure
>> boot environment, so dropping all the files might not be a good idea unless we
>> provide a mechanism for radeontool to use. We can't allow userspace to read/write
>> arbitrary registers and stay secure.
>>
>> Dave.
>
> Well those files are useless, each time i debug a lockup and try to
> use them i loose
> time on them as they never helped me so far and i seriously doubt they
> would help
> me in the future or anyone else.
>
> For secure boot my guess is that radeontool will become obsolete and
> by that time
> we might need to add some reg dumping. But none of the current files
> seems usefull
> to me.

We can always expose the mmio bar (and vbios for that matter) via
ioctl or sysfs for radeontool.  We should try and write a better
unified tool suite.

Alex

>
> The fence and sa files might make sense to debug the associated code
> as it's nice
> to be able to dump associated kernel struct.
>
> Cheers,
> Jerome
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 02/24] drm/radeon: make radeon_gpu_is_lockup a per ring function

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Different rings have different criteria to test
if they are stuck.

v2: rebased on current drm-next

Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon.h       |    4 +-
 drivers/gpu/drm/radeon/radeon_asic.c  |   44 ++++++++++++++++++--------------
 drivers/gpu/drm/radeon/radeon_fence.c |    2 +-
 3 files changed, 28 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 138b952..bea99e3 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1144,7 +1144,6 @@ struct radeon_asic {
 	int (*resume)(struct radeon_device *rdev);
 	int (*suspend)(struct radeon_device *rdev);
 	void (*vga_set_state)(struct radeon_device *rdev, bool state);
-	bool (*gpu_is_lockup)(struct radeon_device *rdev, struct radeon_ring *cp);
 	int (*asic_reset)(struct radeon_device *rdev);
 	/* ioctl hw specific callback. Some hw might want to perform special
 	 * operation on specific ioctl. For instance on wait idle some hw
@@ -1173,6 +1172,7 @@ struct radeon_asic {
 		void (*ring_start)(struct radeon_device *rdev, struct radeon_ring *cp);
 		int (*ring_test)(struct radeon_device *rdev, struct radeon_ring *cp);
 		int (*ib_test)(struct radeon_device *rdev, struct radeon_ring *cp);
+		bool (*is_lockup)(struct radeon_device *rdev, struct radeon_ring *cp);
 	} ring[RADEON_NUM_RINGS];
 	/* irqs */
 	struct {
@@ -1730,7 +1730,6 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_suspend(rdev) (rdev)->asic->suspend((rdev))
 #define radeon_cs_parse(rdev, r, p) (rdev)->asic->ring[(r)].cs_parse((p))
 #define radeon_vga_set_state(rdev, state) (rdev)->asic->vga_set_state((rdev), (state))
-#define radeon_gpu_is_lockup(rdev, cp) (rdev)->asic->gpu_is_lockup((rdev), (cp))
 #define radeon_asic_reset(rdev) (rdev)->asic->asic_reset((rdev))
 #define radeon_gart_tlb_flush(rdev) (rdev)->asic->gart.tlb_flush((rdev))
 #define radeon_gart_set_page(rdev, i, p) (rdev)->asic->gart.set_page((rdev), (i), (p))
@@ -1739,6 +1738,7 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_ib_test(rdev, r, cp) (rdev)->asic->ring[(r)].ib_test((rdev), (cp))
 #define radeon_ring_ib_execute(rdev, r, ib) (rdev)->asic->ring[(r)].ib_execute((rdev), (ib))
 #define radeon_ring_ib_parse(rdev, r, ib) (rdev)->asic->ring[(r)].ib_parse((rdev), (ib))
+#define radeon_ring_is_lockup(rdev, r, cp) (rdev)->asic->ring[(r)].is_lockup((rdev), (cp))
 #define radeon_irq_set(rdev) (rdev)->asic->irq.set((rdev))
 #define radeon_irq_process(rdev) (rdev)->asic->irq.process((rdev))
 #define radeon_get_vblank_counter(rdev, crtc) (rdev)->asic->display.get_vblank_counter((rdev), (crtc))
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index be4dc2f..958b9ea 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -134,7 +134,6 @@ 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,
 	.asic_reset = &r100_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -152,6 +151,7 @@ static struct radeon_asic r100_asic = {
 			.ring_start = &r100_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -208,7 +208,6 @@ 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,
 	.asic_reset = &r100_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -226,6 +225,7 @@ static struct radeon_asic r200_asic = {
 			.ring_start = &r100_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -282,7 +282,6 @@ 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,
 	.asic_reset = &r300_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -300,6 +299,7 @@ static struct radeon_asic r300_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r300_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -356,7 +356,6 @@ 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,
 	.asic_reset = &r300_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -374,6 +373,7 @@ static struct radeon_asic r300_asic_pcie = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r300_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -430,7 +430,6 @@ 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,
 	.asic_reset = &r300_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -448,6 +447,7 @@ static struct radeon_asic r420_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r300_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -504,7 +504,6 @@ 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,
 	.asic_reset = &r300_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -522,6 +521,7 @@ static struct radeon_asic rs400_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r300_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -578,7 +578,6 @@ 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,
 	.asic_reset = &rs600_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -596,6 +595,7 @@ static struct radeon_asic rs600_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r300_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -652,7 +652,6 @@ 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,
 	.asic_reset = &rs600_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -670,6 +669,7 @@ static struct radeon_asic rs690_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r300_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -726,7 +726,6 @@ 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,
 	.asic_reset = &rs600_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -744,6 +743,7 @@ static struct radeon_asic rv515_asic = {
 			.ring_start = &rv515_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r300_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -800,7 +800,6 @@ 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,
 	.asic_reset = &rs600_asic_reset,
 	.ioctl_wait_idle = NULL,
 	.gui_idle = &r100_gui_idle,
@@ -818,6 +817,7 @@ static struct radeon_asic r520_asic = {
 			.ring_start = &rv515_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
+			.is_lockup = &r300_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -874,7 +874,6 @@ static struct radeon_asic r600_asic = {
 	.suspend = &r600_suspend,
 	.resume = &r600_resume,
 	.vga_set_state = &r600_vga_set_state,
-	.gpu_is_lockup = &r600_gpu_is_lockup,
 	.asic_reset = &r600_asic_reset,
 	.ioctl_wait_idle = r600_ioctl_wait_idle,
 	.gui_idle = &r600_gui_idle,
@@ -891,6 +890,7 @@ static struct radeon_asic r600_asic = {
 			.cs_parse = &r600_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &r600_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -946,7 +946,6 @@ static struct radeon_asic rs780_asic = {
 	.fini = &r600_fini,
 	.suspend = &r600_suspend,
 	.resume = &r600_resume,
-	.gpu_is_lockup = &r600_gpu_is_lockup,
 	.vga_set_state = &r600_vga_set_state,
 	.asic_reset = &r600_asic_reset,
 	.ioctl_wait_idle = r600_ioctl_wait_idle,
@@ -964,6 +963,7 @@ static struct radeon_asic rs780_asic = {
 			.cs_parse = &r600_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &r600_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -1020,7 +1020,6 @@ static struct radeon_asic rv770_asic = {
 	.suspend = &rv770_suspend,
 	.resume = &rv770_resume,
 	.asic_reset = &r600_asic_reset,
-	.gpu_is_lockup = &r600_gpu_is_lockup,
 	.vga_set_state = &r600_vga_set_state,
 	.ioctl_wait_idle = r600_ioctl_wait_idle,
 	.gui_idle = &r600_gui_idle,
@@ -1037,6 +1036,7 @@ static struct radeon_asic rv770_asic = {
 			.cs_parse = &r600_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &r600_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -1092,7 +1092,6 @@ static struct radeon_asic evergreen_asic = {
 	.fini = &evergreen_fini,
 	.suspend = &evergreen_suspend,
 	.resume = &evergreen_resume,
-	.gpu_is_lockup = &evergreen_gpu_is_lockup,
 	.asic_reset = &evergreen_asic_reset,
 	.vga_set_state = &r600_vga_set_state,
 	.ioctl_wait_idle = r600_ioctl_wait_idle,
@@ -1110,6 +1109,7 @@ static struct radeon_asic evergreen_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &evergreen_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -1165,7 +1165,6 @@ static struct radeon_asic sumo_asic = {
 	.fini = &evergreen_fini,
 	.suspend = &evergreen_suspend,
 	.resume = &evergreen_resume,
-	.gpu_is_lockup = &evergreen_gpu_is_lockup,
 	.asic_reset = &evergreen_asic_reset,
 	.vga_set_state = &r600_vga_set_state,
 	.ioctl_wait_idle = r600_ioctl_wait_idle,
@@ -1183,6 +1182,7 @@ static struct radeon_asic sumo_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &evergreen_gpu_is_lockup,
 		},
 	},
 	.irq = {
@@ -1238,7 +1238,6 @@ static struct radeon_asic btc_asic = {
 	.fini = &evergreen_fini,
 	.suspend = &evergreen_suspend,
 	.resume = &evergreen_resume,
-	.gpu_is_lockup = &evergreen_gpu_is_lockup,
 	.asic_reset = &evergreen_asic_reset,
 	.vga_set_state = &r600_vga_set_state,
 	.ioctl_wait_idle = r600_ioctl_wait_idle,
@@ -1256,6 +1255,7 @@ static struct radeon_asic btc_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &evergreen_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -1321,7 +1321,6 @@ static struct radeon_asic cayman_asic = {
 	.fini = &cayman_fini,
 	.suspend = &cayman_suspend,
 	.resume = &cayman_resume,
-	.gpu_is_lockup = &cayman_gpu_is_lockup,
 	.asic_reset = &cayman_asic_reset,
 	.vga_set_state = &r600_vga_set_state,
 	.ioctl_wait_idle = r600_ioctl_wait_idle,
@@ -1340,6 +1339,7 @@ static struct radeon_asic cayman_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &cayman_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1349,6 +1349,7 @@ static struct radeon_asic cayman_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &cayman_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1358,6 +1359,7 @@ static struct radeon_asic cayman_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &cayman_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -1413,7 +1415,6 @@ static struct radeon_asic trinity_asic = {
 	.fini = &cayman_fini,
 	.suspend = &cayman_suspend,
 	.resume = &cayman_resume,
-	.gpu_is_lockup = &cayman_gpu_is_lockup,
 	.asic_reset = &cayman_asic_reset,
 	.vga_set_state = &r600_vga_set_state,
 	.ioctl_wait_idle = r600_ioctl_wait_idle,
@@ -1432,6 +1433,7 @@ static struct radeon_asic trinity_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &cayman_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1441,6 +1443,7 @@ static struct radeon_asic trinity_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &cayman_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1450,6 +1453,7 @@ static struct radeon_asic trinity_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &cayman_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -1515,7 +1519,6 @@ static struct radeon_asic si_asic = {
 	.fini = &si_fini,
 	.suspend = &si_suspend,
 	.resume = &si_resume,
-	.gpu_is_lockup = &si_gpu_is_lockup,
 	.asic_reset = &si_asic_reset,
 	.vga_set_state = &r600_vga_set_state,
 	.ioctl_wait_idle = r600_ioctl_wait_idle,
@@ -1534,6 +1537,7 @@ static struct radeon_asic si_asic = {
 			.cs_parse = NULL,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &si_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
 			.ib_execute = &si_ring_ib_execute,
@@ -1543,6 +1547,7 @@ static struct radeon_asic si_asic = {
 			.cs_parse = NULL,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &si_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
 			.ib_execute = &si_ring_ib_execute,
@@ -1552,6 +1557,7 @@ static struct radeon_asic si_asic = {
 			.cs_parse = NULL,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
+			.is_lockup = &si_gpu_is_lockup,
 		}
 	},
 	.irq = {
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 7f588d4..79ce829 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -259,7 +259,7 @@ retry:
 		 * if we experiencing a lockup the value doesn't change
 		 */
 		if (seq == rdev->fence_drv[fence->ring].last_seq &&
-		    radeon_gpu_is_lockup(rdev, &rdev->ring[fence->ring])) {
+		    radeon_ring_is_lockup(rdev, fence->ring, &rdev->ring[fence->ring])) {
 			/* good news we believe it's a lockup */
 			printk(KERN_WARNING "GPU lockup (waiting for 0x%08X last fence id 0x%08X)\n",
 			     fence->seq, seq);
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 03/24] drm/radeon: replace gpu_lockup with ring->ready flag

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

It makes no sense at all to have more than one flag.

Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/r100.c          |    1 -
 drivers/gpu/drm/radeon/r300.c          |    1 -
 drivers/gpu/drm/radeon/radeon.h        |    1 -
 drivers/gpu/drm/radeon/radeon_device.c |    1 -
 drivers/gpu/drm/radeon/radeon_fence.c  |   36 +++++++++++--------------------
 drivers/gpu/drm/radeon/rs600.c         |    1 -
 6 files changed, 13 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 9e69a95..01e597ad 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2293,7 +2293,6 @@ int r100_asic_reset(struct radeon_device *rdev)
 	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;
 		ret = -1;
 	} else
 		dev_info(rdev->dev, "GPU reset succeed\n");
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index c5237ab..40baaec 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -444,7 +444,6 @@ int r300_asic_reset(struct radeon_device *rdev)
 	/* Check if GPU is idle */
 	if (G_000E40_GA_BUSY(status) || G_000E40_VAP_BUSY(status)) {
 		dev_err(rdev->dev, "failed to reset GPU\n");
-		rdev->gpu_lockup = true;
 		ret = -1;
 	} else
 		dev_info(rdev->dev, "GPU reset succeed\n");
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index bea99e3..365334b 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1529,7 +1529,6 @@ struct radeon_device {
 	struct radeon_mutex		cs_mutex;
 	struct radeon_wb		wb;
 	struct radeon_dummy_page	dummy_page;
-	bool				gpu_lockup;
 	bool				shutdown;
 	bool				suspend;
 	bool				need_dma32;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index ea7df16..eb63a06 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -714,7 +714,6 @@ int radeon_device_init(struct radeon_device *rdev,
 	rdev->is_atom_bios = false;
 	rdev->usec_timeout = RADEON_MAX_USEC_TIMEOUT;
 	rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024;
-	rdev->gpu_lockup = false;
 	rdev->accel_working = false;
 
 	DRM_INFO("initializing kernel modesetting (%s 0x%04X:0x%04X 0x%04X:0x%04X).\n",
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 79ce829..c0ec19d 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -71,14 +71,7 @@ int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence)
 		return 0;
 	}
 	fence->seq = atomic_add_return(1, &rdev->fence_drv[fence->ring].seq);
-	if (!rdev->ring[fence->ring].ready)
-		/* FIXME: cp is not running assume everythings is done right
-		 * away
-		 */
-		radeon_fence_write(rdev, fence->seq, fence->ring);
-	else
-		radeon_fence_ring_emit(rdev, fence->ring, fence);
-
+	radeon_fence_ring_emit(rdev, fence->ring, fence);
 	trace_radeon_fence_emit(rdev->ddev, fence->seq);
 	fence->emitted = true;
 	list_move_tail(&fence->list, &rdev->fence_drv[fence->ring].emitted);
@@ -191,9 +184,6 @@ bool radeon_fence_signaled(struct radeon_fence *fence)
 	if (!fence)
 		return true;
 
-	if (fence->rdev->gpu_lockup)
-		return true;
-
 	write_lock_irqsave(&fence->rdev->fence_lock, irq_flags);
 	signaled = fence->signaled;
 	/* if we are shuting down report all fence as signaled */
@@ -260,18 +250,16 @@ retry:
 		 */
 		if (seq == rdev->fence_drv[fence->ring].last_seq &&
 		    radeon_ring_is_lockup(rdev, fence->ring, &rdev->ring[fence->ring])) {
+
 			/* good news we believe it's a lockup */
 			printk(KERN_WARNING "GPU lockup (waiting for 0x%08X last fence id 0x%08X)\n",
 			     fence->seq, seq);
-			/* FIXME: what should we do ? marking everyone
-			 * as signaled for now
-			 */
-			rdev->gpu_lockup = true;
+
+			/* mark the ring as not ready any more */
+			rdev->ring[fence->ring].ready = false;
 			r = radeon_gpu_reset(rdev);
 			if (r)
 				return r;
-			radeon_fence_write(rdev, fence->seq, fence->ring);
-			rdev->gpu_lockup = false;
 		}
 		timeout = RADEON_FENCE_JIFFIES_TIMEOUT;
 		write_lock_irqsave(&rdev->fence_lock, irq_flags);
@@ -289,10 +277,11 @@ int radeon_fence_wait_next(struct radeon_device *rdev, int ring)
 	struct radeon_fence *fence;
 	int r;
 
-	if (rdev->gpu_lockup) {
-		return 0;
-	}
 	write_lock_irqsave(&rdev->fence_lock, irq_flags);
+	if (!rdev->ring[ring].ready) {
+		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+		return -EBUSY;
+	}
 	if (list_empty(&rdev->fence_drv[ring].emitted)) {
 		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
 		return 0;
@@ -312,10 +301,11 @@ int radeon_fence_wait_last(struct radeon_device *rdev, int ring)
 	struct radeon_fence *fence;
 	int r;
 
-	if (rdev->gpu_lockup) {
-		return 0;
-	}
 	write_lock_irqsave(&rdev->fence_lock, irq_flags);
+	if (!rdev->ring[ring].ready) {
+		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+		return -EBUSY;
+	}
 	if (list_empty(&rdev->fence_drv[ring].emitted)) {
 		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
 		return 0;
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index dc5ec8c..7061aad 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -396,7 +396,6 @@ int rs600_asic_reset(struct radeon_device *rdev)
 	/* Check if GPU is idle */
 	if (G_000E40_GA_BUSY(status) || G_000E40_VAP_BUSY(status)) {
 		dev_err(rdev->dev, "failed to reset GPU\n");
-		rdev->gpu_lockup = true;
 		ret = -1;
 	} else
 		dev_info(rdev->dev, "GPU reset succeed\n");
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 04/24] drm/radeon: use central function for IB testing

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Removing all the different error messages and
having just one standard behaviour over all
chipset generations.

Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c   |    7 ++-----
 drivers/gpu/drm/radeon/ni.c          |    7 ++-----
 drivers/gpu/drm/radeon/r100.c        |    7 ++-----
 drivers/gpu/drm/radeon/r300.c        |    7 ++-----
 drivers/gpu/drm/radeon/r420.c        |    7 ++-----
 drivers/gpu/drm/radeon/r520.c        |    8 +++-----
 drivers/gpu/drm/radeon/r600.c        |    7 ++-----
 drivers/gpu/drm/radeon/radeon.h      |    1 +
 drivers/gpu/drm/radeon/radeon_ring.c |   30 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/radeon/rs400.c       |    7 ++-----
 drivers/gpu/drm/radeon/rs600.c       |    7 ++-----
 drivers/gpu/drm/radeon/rs690.c       |    7 ++-----
 drivers/gpu/drm/radeon/rv515.c       |    8 +++-----
 drivers/gpu/drm/radeon/rv770.c       |    7 ++-----
 14 files changed, 57 insertions(+), 60 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index cfa372c..ca47f52 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -3248,12 +3248,9 @@ static int evergreen_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		DRM_ERROR("radeon: failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	r = r600_audio_init(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index a48ca53..0146428 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1601,12 +1601,9 @@ static int cayman_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		DRM_ERROR("radeon: failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	r = radeon_vm_manager_start(rdev);
 	if (r)
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 01e597ad..be51f7b 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -3780,12 +3780,9 @@ static int r100_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		dev_err(rdev->dev, "failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 40baaec..ae15c10 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -1367,12 +1367,9 @@ static int r300_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		dev_err(rdev->dev, "failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c
index 2eba44c..744348b 100644
--- a/drivers/gpu/drm/radeon/r420.c
+++ b/drivers/gpu/drm/radeon/r420.c
@@ -269,12 +269,9 @@ static int r420_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		dev_err(rdev->dev, "failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c
index 2e5ff86..2ef0c34 100644
--- a/drivers/gpu/drm/radeon/r520.c
+++ b/drivers/gpu/drm/radeon/r520.c
@@ -207,12 +207,10 @@ static int r520_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		dev_err(rdev->dev, "failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 62299d8..bc3a2ef 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2492,12 +2492,9 @@ int r600_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		DRM_ERROR("radeon: failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 365334b..8801657 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -793,6 +793,7 @@ int radeon_ib_pool_init(struct radeon_device *rdev);
 void radeon_ib_pool_fini(struct radeon_device *rdev);
 int radeon_ib_pool_start(struct radeon_device *rdev);
 int radeon_ib_pool_suspend(struct radeon_device *rdev);
+int radeon_ib_ring_tests(struct radeon_device *rdev);
 /* Ring access between begin & end cannot sleep */
 int radeon_ring_index(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_free_size(struct radeon_device *rdev, struct radeon_ring *cp);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index aac84b3..e394131 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -261,6 +261,36 @@ int radeon_ib_pool_suspend(struct radeon_device *rdev)
 	return radeon_sa_bo_manager_suspend(rdev, &rdev->ib_pool.sa_manager);
 }
 
+int radeon_ib_ring_tests(struct radeon_device *rdev)
+{
+	unsigned i;
+	int r;
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		struct radeon_ring *ring = &rdev->ring[i];
+
+		if (!ring->ready)
+			continue;
+
+		r = radeon_ib_test(rdev, i, ring);
+		if (r) {
+			ring->ready = false;
+
+			if (i == RADEON_RING_TYPE_GFX_INDEX) {
+				/* oh, oh, that's really bad */
+				DRM_ERROR("radeon: failed testing IB on GFX ring (%d).\n", r);
+		                rdev->accel_working = false;
+				return r;
+
+			} else {
+				/* still not good, but we can live with it */
+				DRM_ERROR("radeon: failed testing IB on ring %d (%d).\n", i, r);
+			}
+		}
+	}
+	return 0;
+}
+
 /*
  * Ring.
  */
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index 0c0a0df..0120c63 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -342,12 +342,9 @@ static int rs400_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		dev_err(rdev->dev, "failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 7061aad..9c5d530 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -876,12 +876,9 @@ static int rs600_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		dev_err(rdev->dev, "failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 752e81b..024c2bb 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -647,12 +647,9 @@ static int rs690_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		dev_err(rdev->dev, "failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 2f9062a..6eaa075 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -336,12 +336,10 @@ static int rv515_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		dev_err(rdev->dev, "failed testing IB (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index c62ae4b..cacec0e 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -1114,12 +1114,9 @@ static int rv770_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	if (r) {
-		dev_err(rdev->dev, "IB test failed (%d).\n", r);
-		rdev->accel_working = false;
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
 		return r;
-	}
 
 	return 0;
 }
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 05/24] drm/radeon: rework gpu lockup detection and processing

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Previusly multiple rings could trigger multiple GPU
resets at the same time.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h       |    3 +-
 drivers/gpu/drm/radeon/radeon_fence.c |  150 +++++++++++++++++----------------
 2 files changed, 77 insertions(+), 76 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 8801657..85a3aa9 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -255,8 +255,7 @@ struct radeon_fence_driver {
 	volatile uint32_t		*cpu_addr;
 	atomic_t			seq;
 	uint32_t			last_seq;
-	unsigned long			last_jiffies;
-	unsigned long			last_timeout;
+	unsigned long			last_activity;
 	wait_queue_head_t		queue;
 	struct list_head		created;
 	struct list_head		emitted;
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index c0ec19d..5d2ca1d 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -74,6 +74,10 @@ int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence)
 	radeon_fence_ring_emit(rdev, fence->ring, fence);
 	trace_radeon_fence_emit(rdev->ddev, fence->seq);
 	fence->emitted = true;
+	/* are we the first fence on a previusly idle ring? */
+	if (list_empty(&rdev->fence_drv[fence->ring].emitted)) {
+		rdev->fence_drv[fence->ring].last_activity = jiffies;
+	}
 	list_move_tail(&fence->list, &rdev->fence_drv[fence->ring].emitted);
 	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
 	return 0;
@@ -85,34 +89,14 @@ static bool radeon_fence_poll_locked(struct radeon_device *rdev, int ring)
 	struct list_head *i, *n;
 	uint32_t seq;
 	bool wake = false;
-	unsigned long cjiffies;
 
 	seq = radeon_fence_read(rdev, ring);
-	if (seq != rdev->fence_drv[ring].last_seq) {
-		rdev->fence_drv[ring].last_seq = seq;
-		rdev->fence_drv[ring].last_jiffies = jiffies;
-		rdev->fence_drv[ring].last_timeout = RADEON_FENCE_JIFFIES_TIMEOUT;
-	} else {
-		cjiffies = jiffies;
-		if (time_after(cjiffies, rdev->fence_drv[ring].last_jiffies)) {
-			cjiffies -= rdev->fence_drv[ring].last_jiffies;
-			if (time_after(rdev->fence_drv[ring].last_timeout, cjiffies)) {
-				/* update the timeout */
-				rdev->fence_drv[ring].last_timeout -= cjiffies;
-			} else {
-				/* the 500ms timeout is elapsed we should test
-				 * for GPU lockup
-				 */
-				rdev->fence_drv[ring].last_timeout = 1;
-			}
-		} else {
-			/* wrap around update last jiffies, we will just wait
-			 * a little longer
-			 */
-			rdev->fence_drv[ring].last_jiffies = cjiffies;
-		}
+	if (seq == rdev->fence_drv[ring].last_seq)
 		return false;
-	}
+
+	rdev->fence_drv[ring].last_seq = seq;
+	rdev->fence_drv[ring].last_activity = jiffies;
+
 	n = NULL;
 	list_for_each(i, &rdev->fence_drv[ring].emitted) {
 		fence = list_entry(i, struct radeon_fence, list);
@@ -207,66 +191,84 @@ int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 	struct radeon_device *rdev;
 	unsigned long irq_flags, timeout;
 	u32 seq;
-	int r;
+	int i, r;
+	bool signaled;
 
 	if (fence == NULL) {
 		WARN(1, "Querying an invalid fence : %p !\n", fence);
-		return 0;
+		return -EINVAL;
 	}
+
 	rdev = fence->rdev;
-	if (radeon_fence_signaled(fence)) {
-		return 0;
-	}
-	timeout = rdev->fence_drv[fence->ring].last_timeout;
-retry:
-	/* save current sequence used to check for GPU lockup */
-	seq = rdev->fence_drv[fence->ring].last_seq;
-	trace_radeon_fence_wait_begin(rdev->ddev, seq);
-	if (intr) {
+	signaled = radeon_fence_signaled(fence);
+	while (!signaled) {
+		read_lock_irqsave(&rdev->fence_lock, irq_flags);
+		timeout = jiffies - RADEON_FENCE_JIFFIES_TIMEOUT;
+		if (time_after(rdev->fence_drv[fence->ring].last_activity, timeout)) {
+			/* the normal case, timeout is somewhere before last_activity */
+			timeout = rdev->fence_drv[fence->ring].last_activity - timeout;
+		} else {
+			/* either jiffies wrapped around, or no fence was signaled in the last 500ms
+			 * anyway we will just wait for the minimum amount and then check for a lockup */
+			timeout = 1;
+		}
+		/* save current sequence value used to check for GPU lockups */
+		seq = rdev->fence_drv[fence->ring].last_seq;
+		read_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+
+		trace_radeon_fence_wait_begin(rdev->ddev, seq);
 		radeon_irq_kms_sw_irq_get(rdev, fence->ring);
-		r = wait_event_interruptible_timeout(rdev->fence_drv[fence->ring].queue,
-				radeon_fence_signaled(fence), timeout);
+		if (intr) {
+			r = wait_event_interruptible_timeout(
+				rdev->fence_drv[fence->ring].queue,
+				(signaled = radeon_fence_signaled(fence)), timeout);
+		} else {
+			r = wait_event_timeout(
+				rdev->fence_drv[fence->ring].queue,
+				(signaled = radeon_fence_signaled(fence)), timeout);
+		}
 		radeon_irq_kms_sw_irq_put(rdev, fence->ring);
 		if (unlikely(r < 0)) {
 			return r;
 		}
-	} else {
-		radeon_irq_kms_sw_irq_get(rdev, fence->ring);
-		r = wait_event_timeout(rdev->fence_drv[fence->ring].queue,
-			 radeon_fence_signaled(fence), timeout);
-		radeon_irq_kms_sw_irq_put(rdev, fence->ring);
-	}
-	trace_radeon_fence_wait_end(rdev->ddev, seq);
-	if (unlikely(!radeon_fence_signaled(fence))) {
-		/* we were interrupted for some reason and fence isn't
-		 * isn't signaled yet, resume wait
-		 */
-		if (r) {
-			timeout = r;
-			goto retry;
-		}
-		/* don't protect read access to rdev->fence_drv[t].last_seq
-		 * if we experiencing a lockup the value doesn't change
-		 */
-		if (seq == rdev->fence_drv[fence->ring].last_seq &&
-		    radeon_ring_is_lockup(rdev, fence->ring, &rdev->ring[fence->ring])) {
-
-			/* good news we believe it's a lockup */
-			printk(KERN_WARNING "GPU lockup (waiting for 0x%08X last fence id 0x%08X)\n",
-			     fence->seq, seq);
-
-			/* mark the ring as not ready any more */
-			rdev->ring[fence->ring].ready = false;
-			r = radeon_gpu_reset(rdev);
-			if (r)
-				return r;
+		trace_radeon_fence_wait_end(rdev->ddev, seq);
+
+		if (unlikely(!signaled)) {
+			/* we were interrupted for some reason and fence
+			 * isn't signaled yet, resume waiting */
+			if (r) {
+				continue;
+			}
+
+			write_lock_irqsave(&rdev->fence_lock, irq_flags);
+			/* check if sequence value has changed since last_activity */
+			if (seq != rdev->fence_drv[fence->ring].last_seq) {
+				write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+				continue;
+			}
+
+			/* change sequence value on all rings, so nobody else things there is a lockup */
+			for (i = 0; i < RADEON_NUM_RINGS; ++i)
+				rdev->fence_drv[i].last_seq -= 0x10000;
+			write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+
+			if (radeon_ring_is_lockup(rdev, fence->ring, &rdev->ring[fence->ring])) {
+
+				/* good news we believe it's a lockup */
+				printk(KERN_WARNING "GPU lockup (waiting for 0x%08X last fence id 0x%08X)\n",
+				     fence->seq, seq);
+
+				/* mark the ring as not ready any more */
+				rdev->ring[fence->ring].ready = false;
+				r = radeon_gpu_reset(rdev);
+				if (r)
+					return r;
+
+				write_lock_irqsave(&rdev->fence_lock, irq_flags);
+				rdev->fence_drv[fence->ring].last_activity = jiffies;
+				write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+			}
 		}
-		timeout = RADEON_FENCE_JIFFIES_TIMEOUT;
-		write_lock_irqsave(&rdev->fence_lock, irq_flags);
-		rdev->fence_drv[fence->ring].last_timeout = RADEON_FENCE_JIFFIES_TIMEOUT;
-		rdev->fence_drv[fence->ring].last_jiffies = jiffies;
-		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-		goto retry;
 	}
 	return 0;
 }
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 06/24] drm/radeon: fix a critical bug in the SA code

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Aligning offset can make it bigger than tmp->offset
leading to an overrun bug in the following subtraction.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon_sa.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index 4cce47e..8fbfe69 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -150,7 +150,7 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 	offset = 0;
 	list_for_each_entry(tmp, &sa_manager->sa_bo, list) {
 		/* room before this object ? */
-		if ((tmp->offset - offset) >= size) {
+		if (offset < tmp->offset && (tmp->offset - offset) >= size) {
 			head = tmp->list.prev;
 			goto out;
 		}
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 07/24] drm/radeon: add proper locking to the SA v2

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Make the suballocator self containing to locking.

v2: split the bugfix into a seperate patch.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h    |    1 +
 drivers/gpu/drm/radeon/radeon_sa.c |   17 +++++++++++------
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 85a3aa9..1aefbd9 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -381,6 +381,7 @@ struct radeon_bo_list {
  * alignment).
  */
 struct radeon_sa_manager {
+	spinlock_t		lock;
 	struct radeon_bo	*bo;
 	struct list_head	sa_bo;
 	unsigned		size;
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index 8fbfe69..4ce5c51 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -37,6 +37,7 @@ int radeon_sa_bo_manager_init(struct radeon_device *rdev,
 {
 	int r;
 
+	spin_lock_init(&sa_manager->lock);
 	sa_manager->bo = NULL;
 	sa_manager->size = size;
 	sa_manager->domain = domain;
@@ -136,18 +137,19 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 	struct radeon_sa_bo *tmp;
 	struct list_head *head;
 	unsigned offset = 0, wasted = 0;
+	unsigned long flags;
 
 	BUG_ON(align > RADEON_GPU_PAGE_SIZE);
 	BUG_ON(size > sa_manager->size);
+	spin_lock_irqsave(&sa_manager->lock, flags);
 
 	/* no one ? */
-	head = sa_manager->sa_bo.prev;
 	if (list_empty(&sa_manager->sa_bo)) {
+		head = &sa_manager->sa_bo;
 		goto out;
 	}
 
 	/* look for a hole big enough */
-	offset = 0;
 	list_for_each_entry(tmp, &sa_manager->sa_bo, list) {
 		/* room before this object ? */
 		if (offset < tmp->offset && (tmp->offset - offset) >= size) {
@@ -157,9 +159,8 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 		offset = tmp->offset + tmp->size;
 		wasted = offset % align;
 		if (wasted) {
-			wasted = align - wasted;
+			offset += align - wasted;
 		}
-		offset += wasted;
 	}
 	/* room at the end ? */
 	head = sa_manager->sa_bo.prev;
@@ -167,11 +168,11 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 	offset = tmp->offset + tmp->size;
 	wasted = offset % align;
 	if (wasted) {
-		wasted = align - wasted;
+		offset += wasted = align - wasted;
 	}
-	offset += wasted;
 	if ((sa_manager->size - offset) < size) {
 		/* failed to find somethings big enough */
+		spin_unlock_irqrestore(&sa_manager->lock, flags);
 		return -ENOMEM;
 	}
 
@@ -180,10 +181,14 @@ out:
 	sa_bo->offset = offset;
 	sa_bo->size = size;
 	list_add(&sa_bo->list, head);
+	spin_unlock_irqrestore(&sa_manager->lock, flags);
 	return 0;
 }
 
 void radeon_sa_bo_free(struct radeon_device *rdev, struct radeon_sa_bo *sa_bo)
 {
+	unsigned long flags;
+	spin_lock_irqsave(&sa_bo->manager->lock, flags);
 	list_del_init(&sa_bo->list);
+	spin_unlock_irqrestore(&sa_bo->manager->lock, flags);
 }
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 08/24] drm/radeon: add biggest hole tracking and wakequeue to the sa v4

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

With that in place clients are automatically blocking
until their memory request can be handled.

v2: block only if the memory request can't be satisfied
    in the first try, the first version actually lacked
    a night of sleep.

v3: make blocking optional, update comments and fix
    another bug with biggest hole tracking.

v4: drop debugfs portion

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h        |    5 +-
 drivers/gpu/drm/radeon/radeon_gart.c   |    2 +-
 drivers/gpu/drm/radeon/radeon_object.h |    2 +-
 drivers/gpu/drm/radeon/radeon_ring.c   |   20 ++--
 drivers/gpu/drm/radeon/radeon_sa.c     |  178 ++++++++++++++++++++++----------
 5 files changed, 138 insertions(+), 69 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 1aefbd9..415a496 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -381,17 +381,16 @@ struct radeon_bo_list {
  * alignment).
  */
 struct radeon_sa_manager {
-	spinlock_t		lock;
+	wait_queue_head_t	queue;
 	struct radeon_bo	*bo;
 	struct list_head	sa_bo;
 	unsigned		size;
+	struct list_head	*biggest_hole;
 	uint64_t		gpu_addr;
 	void			*cpu_ptr;
 	uint32_t		domain;
 };
 
-struct radeon_sa_bo;
-
 /* sub-allocation buffer */
 struct radeon_sa_bo {
 	struct list_head		list;
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index c58a036..7af4ff9 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -395,7 +395,7 @@ int radeon_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm)
 retry:
 	r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager, &vm->sa_bo,
 			     RADEON_GPU_PAGE_ALIGN(vm->last_pfn * 8),
-			     RADEON_GPU_PAGE_SIZE);
+			     RADEON_GPU_PAGE_SIZE, false);
 	if (r) {
 		if (list_empty(&rdev->vm_manager.lru_vm)) {
 			return r;
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index f9104be..a181c2f 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -158,7 +158,7 @@ extern int radeon_sa_bo_manager_suspend(struct radeon_device *rdev,
 extern int radeon_sa_bo_new(struct radeon_device *rdev,
 			    struct radeon_sa_manager *sa_manager,
 			    struct radeon_sa_bo *sa_bo,
-			    unsigned size, unsigned align);
+			    unsigned size, unsigned align, bool block);
 extern void radeon_sa_bo_free(struct radeon_device *rdev,
 			      struct radeon_sa_bo *sa_bo);
 
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index e394131..b06e04f 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -121,7 +121,7 @@ retry:
 		if (rdev->ib_pool.ibs[idx].fence == NULL) {
 			r = radeon_sa_bo_new(rdev, &rdev->ib_pool.sa_manager,
 					     &rdev->ib_pool.ibs[idx].sa_bo,
-					     size, 256);
+					     size, 256, false);
 			if (!r) {
 				*ib = &rdev->ib_pool.ibs[idx];
 				(*ib)->ptr = rdev->ib_pool.sa_manager.cpu_ptr;
@@ -202,10 +202,16 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 
 int radeon_ib_pool_init(struct radeon_device *rdev)
 {
-	struct radeon_sa_manager tmp;
 	int i, r;
 
-	r = radeon_sa_bo_manager_init(rdev, &tmp,
+	radeon_mutex_lock(&rdev->ib_pool.mutex);
+	if (rdev->ib_pool.ready) {
+		return 0;
+	}
+	rdev->ib_pool.ready = true;
+	radeon_mutex_unlock(&rdev->ib_pool.mutex);
+
+	r = radeon_sa_bo_manager_init(rdev, &rdev->ib_pool.sa_manager,
 				      RADEON_IB_POOL_SIZE*64*1024,
 				      RADEON_GEM_DOMAIN_GTT);
 	if (r) {
@@ -213,14 +219,6 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 	}
 
 	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (rdev->ib_pool.ready) {
-		radeon_mutex_unlock(&rdev->ib_pool.mutex);
-		radeon_sa_bo_manager_fini(rdev, &tmp);
-		return 0;
-	}
-
-	rdev->ib_pool.sa_manager = tmp;
-	INIT_LIST_HEAD(&rdev->ib_pool.sa_manager.sa_bo);
 	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
 		rdev->ib_pool.ibs[i].fence = NULL;
 		rdev->ib_pool.ibs[i].idx = i;
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index 4ce5c51..3212293 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -26,6 +26,7 @@
 /*
  * Authors:
  *    Jerome Glisse <glisse@freedesktop.org>
+ *    Christian König <christian.koenig@amd.com>
  */
 #include "drmP.h"
 #include "drm.h"
@@ -37,9 +38,10 @@ int radeon_sa_bo_manager_init(struct radeon_device *rdev,
 {
 	int r;
 
-	spin_lock_init(&sa_manager->lock);
+	init_waitqueue_head(&sa_manager->queue);
 	sa_manager->bo = NULL;
 	sa_manager->size = size;
+	sa_manager->biggest_hole = &sa_manager->sa_bo;
 	sa_manager->domain = domain;
 	INIT_LIST_HEAD(&sa_manager->sa_bo);
 
@@ -58,6 +60,7 @@ void radeon_sa_bo_manager_fini(struct radeon_device *rdev,
 {
 	struct radeon_sa_bo *sa_bo, *tmp;
 
+	wake_up_all(&sa_manager->queue);
 	if (!list_empty(&sa_manager->sa_bo)) {
 		dev_err(rdev->dev, "sa_manager is not empty, clearing anyway\n");
 	}
@@ -114,81 +117,150 @@ int radeon_sa_bo_manager_suspend(struct radeon_device *rdev,
 	return r;
 }
 
+static inline unsigned radeon_sa_bo_hole_start(struct radeon_sa_manager *m,
+					       struct list_head *entry)
+{
+	struct radeon_sa_bo *sa_bo;
+
+	if (entry == &m->sa_bo)
+		return 0;
+
+	sa_bo = list_entry(entry, struct radeon_sa_bo, list);
+	return sa_bo->offset + sa_bo->size;
+}
+
+static inline unsigned radeon_sa_bo_hole_end(struct radeon_sa_manager *m,
+					     struct list_head *entry)
+{
+	if (entry->next == &m->sa_bo)
+		return m->size;
+
+	return list_entry(entry->next, struct radeon_sa_bo, list)->offset;
+}
+
+static inline unsigned radeon_sa_bo_min_free(struct radeon_sa_manager *m,
+					     unsigned align)
+{
+	unsigned start, end, wasted;
+	start = radeon_sa_bo_hole_start(m, m->biggest_hole);
+	wasted = start % align;
+	if (wasted)
+		start += align - wasted;
+
+	end = radeon_sa_bo_hole_end(m, m->biggest_hole);
+	return start < end ? end - start : 0;
+}
+
 /*
  * Principe is simple, we keep a list of sub allocation in offset
  * order (first entry has offset == 0, last entry has the highest
  * offset).
  *
- * When allocating new object we first check if there is room at
- * the end total_size - (last_object_offset + last_object_size) >=
- * alloc_size. If so we allocate new object there.
- *
- * When there is not enough room at the end, we start waiting for
- * each sub object until we reach object_offset+object_size >=
- * alloc_size, this object then become the sub object we return.
+ * When allocating new objects we start checking at what's currently
+ * assumed to be the biggest hole, if that's not big enough we continue
+ * searching the list until we find something big enough or reach the
+ * biggest hole again. If the later happen we optionally block for the
+ * biggest hole to increase in size.
  *
- * Alignment can't be bigger than page size
  */
 int radeon_sa_bo_new(struct radeon_device *rdev,
 		     struct radeon_sa_manager *sa_manager,
 		     struct radeon_sa_bo *sa_bo,
-		     unsigned size, unsigned align)
+		     unsigned size, unsigned align, bool block)
 {
-	struct radeon_sa_bo *tmp;
-	struct list_head *head;
-	unsigned offset = 0, wasted = 0;
-	unsigned long flags;
+	struct list_head *head, *curr, *hole;
+	unsigned start, currsize, wasted, holesize;
+	int r;
 
 	BUG_ON(align > RADEON_GPU_PAGE_SIZE);
 	BUG_ON(size > sa_manager->size);
-	spin_lock_irqsave(&sa_manager->lock, flags);
 
-	/* no one ? */
-	if (list_empty(&sa_manager->sa_bo)) {
-		head = &sa_manager->sa_bo;
-		goto out;
-	}
+	spin_lock_irq(&sa_manager->queue.lock);
+
+	do {
+		curr = head = hole = sa_manager->biggest_hole;
+		holesize = radeon_sa_bo_min_free(sa_manager, 1);
+		do {
+			start = radeon_sa_bo_hole_start(sa_manager, curr);
+			currsize = radeon_sa_bo_hole_end(sa_manager, curr) - start;
+
+			wasted = start % align;
+			if (wasted) {
+				wasted = align - wasted;
+			}
+
+			/* room after current big enough ? */
+			if (currsize >= (size + wasted)) {
+				sa_bo->manager = sa_manager;
+				sa_bo->offset = start + wasted;
+				sa_bo->size = size;
+				list_add(&sa_bo->list, curr);
+
+				/* consider the space left after the newly
+				   added sa_bo as the biggest hole */
+				currsize -= (size + wasted);
+				if (hole == sa_bo->list.prev || holesize < currsize) {
+					hole = &sa_bo->list;
+				}
+
+				if (sa_manager->biggest_hole != hole) {
+					sa_manager->biggest_hole = hole;
+					wake_up_locked(&sa_manager->queue);
+				}
+				spin_unlock_irq(&sa_manager->queue.lock);
+				return 0;
+			}
+
+			if (holesize < currsize) {
+				hole = curr;
+				holesize = currsize;
+			}
+
+			curr = curr->next;
+		} while (curr != head);
 
-	/* look for a hole big enough */
-	list_for_each_entry(tmp, &sa_manager->sa_bo, list) {
-		/* room before this object ? */
-		if (offset < tmp->offset && (tmp->offset - offset) >= size) {
-			head = tmp->list.prev;
-			goto out;
+		if (sa_manager->biggest_hole != hole) {
+			sa_manager->biggest_hole = hole;
 		}
-		offset = tmp->offset + tmp->size;
-		wasted = offset % align;
-		if (wasted) {
-			offset += align - wasted;
+
+		if (block) {
+			/* failed to find something big enough, wait
+			   for the biggest hole to increase in size */
+			r = wait_event_interruptible_locked_irq(sa_manager->queue,
+				radeon_sa_bo_min_free(sa_manager, align) >= size
+			);
+			if (r) {
+				spin_unlock_irq(&sa_manager->queue.lock);
+				return r;
+			}
 		}
-	}
-	/* room at the end ? */
-	head = sa_manager->sa_bo.prev;
-	tmp = list_entry(head, struct radeon_sa_bo, list);
-	offset = tmp->offset + tmp->size;
-	wasted = offset % align;
-	if (wasted) {
-		offset += wasted = align - wasted;
-	}
-	if ((sa_manager->size - offset) < size) {
-		/* failed to find somethings big enough */
-		spin_unlock_irqrestore(&sa_manager->lock, flags);
-		return -ENOMEM;
-	}
+	} while (block);
+	spin_unlock_irq(&sa_manager->queue.lock);
 
-out:
-	sa_bo->manager = sa_manager;
-	sa_bo->offset = offset;
-	sa_bo->size = size;
-	list_add(&sa_bo->list, head);
-	spin_unlock_irqrestore(&sa_manager->lock, flags);
-	return 0;
+	return -ENOMEM;
 }
 
 void radeon_sa_bo_free(struct radeon_device *rdev, struct radeon_sa_bo *sa_bo)
 {
+	struct radeon_sa_manager *sa_manager = sa_bo->manager;
+	unsigned bsize, fsize;
 	unsigned long flags;
-	spin_lock_irqsave(&sa_bo->manager->lock, flags);
+
+	spin_lock_irqsave(&sa_manager->queue.lock, flags);
+	if (&sa_bo->list == sa_manager->biggest_hole ||
+	    sa_bo->list.prev == sa_manager->biggest_hole) {
+
+		sa_manager->biggest_hole = sa_bo->list.prev;
+		wake_up_locked(&sa_manager->queue);
+	} else {
+		bsize = radeon_sa_bo_min_free(sa_manager, 1);
+		fsize = radeon_sa_bo_hole_start(sa_manager, sa_bo->list.prev);
+		fsize = radeon_sa_bo_hole_end(sa_manager, &sa_bo->list) - fsize;
+		if (fsize > bsize) {
+			sa_manager->biggest_hole = sa_bo->list.prev;
+			wake_up_locked(&sa_manager->queue);
+		}
+	}
 	list_del_init(&sa_bo->list);
-	spin_unlock_irqrestore(&sa_bo->manager->lock, flags);
+	spin_unlock_irqrestore(&sa_manager->queue.lock, flags);
 }
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 09/24] drm/radeon: simplify semaphore handling

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Directly use the suballocator to get small chunks
of memory. It's equally fast and doesn't crash when
we encounter a GPU reset.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/evergreen.c        |    1 -
 drivers/gpu/drm/radeon/ni.c               |    1 -
 drivers/gpu/drm/radeon/r600.c             |    1 -
 drivers/gpu/drm/radeon/radeon.h           |   29 +------
 drivers/gpu/drm/radeon/radeon_device.c    |    2 -
 drivers/gpu/drm/radeon/radeon_semaphore.c |  137 +++++------------------------
 drivers/gpu/drm/radeon/rv770.c            |    1 -
 drivers/gpu/drm/radeon/si.c               |    1 -
 8 files changed, 26 insertions(+), 147 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index ca47f52..a76389c 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -3431,7 +3431,6 @@ void evergreen_fini(struct radeon_device *rdev)
 	evergreen_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_agp_fini(rdev);
 	radeon_bo_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 0146428..c0b0956 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1773,7 +1773,6 @@ void cayman_fini(struct radeon_device *rdev)
 	cayman_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_bo_fini(rdev);
 	radeon_atombios_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index bc3a2ef..24e68fd 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2667,7 +2667,6 @@ void r600_fini(struct radeon_device *rdev)
 	r600_vram_scratch_fini(rdev);
 	radeon_agp_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_bo_fini(rdev);
 	radeon_atombios_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 415a496..222939f 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -427,34 +427,12 @@ int radeon_mode_dumb_destroy(struct drm_file *file_priv,
 /*
  * Semaphores.
  */
-struct radeon_ring;
-
-#define	RADEON_SEMAPHORE_BO_SIZE	256
-
-struct radeon_semaphore_driver {
-	rwlock_t			lock;
-	struct list_head		bo;
-};
-
-struct radeon_semaphore_bo;
-
-/* everything here is constant */
 struct radeon_semaphore {
-	struct list_head		list;
-	uint64_t			gpu_addr;
-	uint32_t			*cpu_ptr;
-	struct radeon_semaphore_bo	*bo;
-};
-
-struct radeon_semaphore_bo {
-	struct list_head		list;
-	struct radeon_ib		*ib;
-	struct list_head		free;
-	struct radeon_semaphore		semaphores[RADEON_SEMAPHORE_BO_SIZE/8];
-	unsigned			nused;
+	struct radeon_sa_bo	sa_bo;
+	signed			waiters;
+	uint64_t		gpu_addr;
 };
 
-void radeon_semaphore_driver_fini(struct radeon_device *rdev);
 int radeon_semaphore_create(struct radeon_device *rdev,
 			    struct radeon_semaphore **semaphore);
 void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
@@ -1518,7 +1496,6 @@ struct radeon_device {
 	struct radeon_mman		mman;
 	rwlock_t			fence_lock;
 	struct radeon_fence_driver	fence_drv[RADEON_NUM_RINGS];
-	struct radeon_semaphore_driver	semaphore_drv;
 	struct radeon_ring		ring[RADEON_NUM_RINGS];
 	struct radeon_ib_pool		ib_pool;
 	struct radeon_irq		irq;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index eb63a06..f314819 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -733,11 +733,9 @@ int radeon_device_init(struct radeon_device *rdev,
 	mutex_init(&rdev->pm.mutex);
 	mutex_init(&rdev->vram_mutex);
 	rwlock_init(&rdev->fence_lock);
-	rwlock_init(&rdev->semaphore_drv.lock);
 	INIT_LIST_HEAD(&rdev->gem.objects);
 	init_waitqueue_head(&rdev->irq.vblank_queue);
 	init_waitqueue_head(&rdev->irq.idle_queue);
-	INIT_LIST_HEAD(&rdev->semaphore_drv.bo);
 	/* initialize vm here */
 	rdev->vm_manager.use_bitmap = 1;
 	rdev->vm_manager.max_pfn = 1 << 20;
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index 61dd4e3..b67c259 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -31,108 +31,32 @@
 #include "drm.h"
 #include "radeon.h"
 
-static int radeon_semaphore_add_bo(struct radeon_device *rdev)
+int radeon_semaphore_create(struct radeon_device *rdev,
+			    struct radeon_semaphore **semaphore)
 {
-	struct radeon_semaphore_bo *bo;
-	unsigned long irq_flags;
-	uint64_t gpu_addr;
-	uint32_t *cpu_ptr;
-	int r, i;
-
+	void *cpu_ptr;
+	int r;
 
-	bo = kmalloc(sizeof(struct radeon_semaphore_bo), GFP_KERNEL);
-	if (bo == NULL) {
+	*semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL);
+	if (*semaphore == NULL) {
 		return -ENOMEM;
 	}
-	INIT_LIST_HEAD(&bo->free);
-	INIT_LIST_HEAD(&bo->list);
-	bo->nused = 0;
 
-	r = radeon_ib_get(rdev, 0, &bo->ib, RADEON_SEMAPHORE_BO_SIZE);
+	r = radeon_sa_bo_new(rdev, &rdev->ib_pool.sa_manager,
+			     &(*semaphore)->sa_bo, 8, 8, true);
 	if (r) {
-		dev_err(rdev->dev, "failed to get a bo after 5 retry\n");
-		kfree(bo);
+		kfree(*semaphore);
+		*semaphore = NULL;
 		return r;
 	}
-	gpu_addr = rdev->ib_pool.sa_manager.gpu_addr;
-	gpu_addr += bo->ib->sa_bo.offset;
-	cpu_ptr = rdev->ib_pool.sa_manager.cpu_ptr;
-	cpu_ptr += (bo->ib->sa_bo.offset >> 2);
-	for (i = 0; i < (RADEON_SEMAPHORE_BO_SIZE/8); i++) {
-		bo->semaphores[i].gpu_addr = gpu_addr;
-		bo->semaphores[i].cpu_ptr = cpu_ptr;
-		bo->semaphores[i].bo = bo;
-		list_add_tail(&bo->semaphores[i].list, &bo->free);
-		gpu_addr += 8;
-		cpu_ptr += 2;
-	}
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	list_add_tail(&bo->list, &rdev->semaphore_drv.bo);
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
-	return 0;
-}
-
-static void radeon_semaphore_del_bo_locked(struct radeon_device *rdev,
-					   struct radeon_semaphore_bo *bo)
-{
-	radeon_sa_bo_free(rdev, &bo->ib->sa_bo);
-	radeon_fence_unref(&bo->ib->fence);
-	list_del(&bo->list);
-	kfree(bo);
-}
-
-void radeon_semaphore_shrink_locked(struct radeon_device *rdev)
-{
-	struct radeon_semaphore_bo *bo, *n;
-
-	if (list_empty(&rdev->semaphore_drv.bo)) {
-		return;
-	}
-	/* only shrink if first bo has free semaphore */
-	bo = list_first_entry(&rdev->semaphore_drv.bo, struct radeon_semaphore_bo, list);
-	if (list_empty(&bo->free)) {
-		return;
-	}
-	list_for_each_entry_safe_continue(bo, n, &rdev->semaphore_drv.bo, list) {
-		if (bo->nused)
-			continue;
-		radeon_semaphore_del_bo_locked(rdev, bo);
-	}
-}
 
-int radeon_semaphore_create(struct radeon_device *rdev,
-			    struct radeon_semaphore **semaphore)
-{
-	struct radeon_semaphore_bo *bo;
-	unsigned long irq_flags;
-	bool do_retry = true;
-	int r;
-
-retry:
-	*semaphore = NULL;
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	list_for_each_entry(bo, &rdev->semaphore_drv.bo, list) {
-		if (list_empty(&bo->free))
-			continue;
-		*semaphore = list_first_entry(&bo->free, struct radeon_semaphore, list);
-		(*semaphore)->cpu_ptr[0] = 0;
-		(*semaphore)->cpu_ptr[1] = 0;
-		list_del(&(*semaphore)->list);
-		bo->nused++;
-		break;
-	}
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
+	(*semaphore)->waiters = 0;
+	(*semaphore)->gpu_addr = rdev->ib_pool.sa_manager.gpu_addr;
+	(*semaphore)->gpu_addr += (*semaphore)->sa_bo.offset;
 
-	if (*semaphore == NULL) {
-		if (do_retry) {
-			do_retry = false;
-			r = radeon_semaphore_add_bo(rdev);
-			if (r)
-				return r;
-			goto retry;
-		}
-		return -ENOMEM;
-	}
+	cpu_ptr = rdev->ib_pool.sa_manager.cpu_ptr;
+	cpu_ptr += (*semaphore)->sa_bo.offset;
+	*((uint64_t*)cpu_ptr) = 0;
 
 	return 0;
 }
@@ -140,39 +64,24 @@ retry:
 void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
 			          struct radeon_semaphore *semaphore)
 {
+	--semaphore->waiters;
 	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, false);
 }
 
 void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
 			        struct radeon_semaphore *semaphore)
 {
+	++semaphore->waiters;
 	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, true);
 }
 
 void radeon_semaphore_free(struct radeon_device *rdev,
 			   struct radeon_semaphore *semaphore)
 {
-	unsigned long irq_flags;
-
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	semaphore->bo->nused--;
-	list_add_tail(&semaphore->list, &semaphore->bo->free);
-	radeon_semaphore_shrink_locked(rdev);
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
-}
-
-void radeon_semaphore_driver_fini(struct radeon_device *rdev)
-{
-	struct radeon_semaphore_bo *bo, *n;
-	unsigned long irq_flags;
-
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	/* we force to free everything */
-	list_for_each_entry_safe(bo, n, &rdev->semaphore_drv.bo, list) {
-		if (!list_empty(&bo->free)) {
-			dev_err(rdev->dev, "still in use semaphore\n");
-		}
-		radeon_semaphore_del_bo_locked(rdev, bo);
+	if (semaphore->waiters > 0) {
+		dev_err(rdev->dev, "Semaphore %p has more waiters than signalers,"
+			" hardware lockup imminent!\n", semaphore);
 	}
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
+	radeon_sa_bo_free(rdev, &semaphore->sa_bo);
+	kfree(semaphore);
 }
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index cacec0e..c6ee54e 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -1278,7 +1278,6 @@ void rv770_fini(struct radeon_device *rdev)
 	rv770_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_agp_fini(rdev);
 	radeon_bo_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index ac7a199..ebe2c9b 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4118,7 +4118,6 @@ void si_fini(struct radeon_device *rdev)
 	si_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_bo_fini(rdev);
 	radeon_atombios_fini(rdev);
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 10/24] drm/radeon: return -ENOENT in fence_wait_next v2

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

We should signal the caller that we haven't waited at all.

v2: only change fence_wait_next not fence_wait_last.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon_fence.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 5d2ca1d..b8db542 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -286,7 +286,7 @@ int radeon_fence_wait_next(struct radeon_device *rdev, int ring)
 	}
 	if (list_empty(&rdev->fence_drv[ring].emitted)) {
 		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-		return 0;
+		return -ENOENT;
 	}
 	fence = list_entry(rdev->fence_drv[ring].emitted.next,
 			   struct radeon_fence, list);
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 11/24] drm/radeon: rename fence_wait_last to fence_wait_empty

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

As discussed with Michel that name better
describes the behavior of this function.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h        |    2 +-
 drivers/gpu/drm/radeon/radeon_device.c |    2 +-
 drivers/gpu/drm/radeon/radeon_fence.c  |    4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 222939f..7f73f40 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -285,7 +285,7 @@ void radeon_fence_process(struct radeon_device *rdev, int ring);
 bool radeon_fence_signaled(struct radeon_fence *fence);
 int radeon_fence_wait(struct radeon_fence *fence, bool interruptible);
 int radeon_fence_wait_next(struct radeon_device *rdev, int ring);
-int radeon_fence_wait_last(struct radeon_device *rdev, int ring);
+int radeon_fence_wait_empty(struct radeon_device *rdev, int ring);
 struct radeon_fence *radeon_fence_ref(struct radeon_fence *fence);
 void radeon_fence_unref(struct radeon_fence **fence);
 int radeon_fence_count_emitted(struct radeon_device *rdev, int ring);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index f314819..d77f19f 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -913,7 +913,7 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
 	radeon_bo_evict_vram(rdev);
 	/* wait for gpu to finish processing current batch */
 	for (i = 0; i < RADEON_NUM_RINGS; i++)
-		radeon_fence_wait_last(rdev, i);
+		radeon_fence_wait_empty(rdev, i);
 
 	radeon_save_bios_scratch_regs(rdev);
 
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index b8db542..c96d112 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -297,7 +297,7 @@ int radeon_fence_wait_next(struct radeon_device *rdev, int ring)
 	return r;
 }
 
-int radeon_fence_wait_last(struct radeon_device *rdev, int ring)
+int radeon_fence_wait_empty(struct radeon_device *rdev, int ring)
 {
 	unsigned long irq_flags;
 	struct radeon_fence *fence;
@@ -439,7 +439,7 @@ void radeon_fence_driver_fini(struct radeon_device *rdev)
 	for (ring = 0; ring < RADEON_NUM_RINGS; ring++) {
 		if (!rdev->fence_drv[ring].initialized)
 			continue;
-		radeon_fence_wait_last(rdev, ring);
+		radeon_fence_wait_empty(rdev, ring);
 		wake_up_all(&rdev->fence_drv[ring].queue);
 		write_lock_irqsave(&rdev->fence_lock, irq_flags);
 		radeon_scratch_free(rdev, rdev->fence_drv[ring].scratch_reg);
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 12/24] drm/radeon: rip out the ib pool v2

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

It isn't necessary any more and the suballocator
seems to perform even better.

v2: drop debugfs

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h           |   22 +---
 drivers/gpu/drm/radeon/radeon_device.c    |    1 -
 drivers/gpu/drm/radeon/radeon_fence.c     |   44 ++++++-
 drivers/gpu/drm/radeon/radeon_gart.c      |   12 +-
 drivers/gpu/drm/radeon/radeon_ring.c      |  187 ++++++++++-------------------
 drivers/gpu/drm/radeon/radeon_semaphore.c |    6 +-
 6 files changed, 116 insertions(+), 156 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 7f73f40..575dc05 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -249,6 +249,8 @@ extern void evergreen_tiling_fields(unsigned tiling_flags, unsigned *bankw,
 /*
  * Fences.
  */
+struct radeon_ib;
+
 struct radeon_fence_driver {
 	uint32_t			scratch_reg;
 	uint64_t			gpu_addr;
@@ -259,7 +261,6 @@ struct radeon_fence_driver {
 	wait_queue_head_t		queue;
 	struct list_head		created;
 	struct list_head		emitted;
-	struct list_head		signaled;
 	bool				initialized;
 };
 
@@ -274,6 +275,7 @@ struct radeon_fence {
 	/* RB, DMA, etc. */
 	int				ring;
 	struct radeon_semaphore		*semaphore;
+	struct radeon_ib		*ib;
 };
 
 int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring);
@@ -289,6 +291,7 @@ int radeon_fence_wait_empty(struct radeon_device *rdev, int ring);
 struct radeon_fence *radeon_fence_ref(struct radeon_fence *fence);
 void radeon_fence_unref(struct radeon_fence **fence);
 int radeon_fence_count_emitted(struct radeon_device *rdev, int ring);
+bool radeon_fence_set_associated_ib(struct radeon_fence *fence, struct radeon_ib *ib);
 
 /*
  * Tiling registers
@@ -603,7 +606,6 @@ void radeon_irq_kms_pflip_irq_put(struct radeon_device *rdev, int crtc);
 
 struct radeon_ib {
 	struct radeon_sa_bo	sa_bo;
-	unsigned		idx;
 	uint32_t		length_dw;
 	uint64_t		gpu_addr;
 	uint32_t		*ptr;
@@ -612,18 +614,6 @@ struct radeon_ib {
 	bool			is_const_ib;
 };
 
-/*
- * locking -
- * mutex protects scheduled_ibs, ready, alloc_bm
- */
-struct radeon_ib_pool {
-	struct radeon_mutex		mutex;
-	struct radeon_sa_manager	sa_manager;
-	struct radeon_ib		ibs[RADEON_IB_POOL_SIZE];
-	bool				ready;
-	unsigned			head_id;
-};
-
 struct radeon_ring {
 	struct radeon_bo	*ring_obj;
 	volatile uint32_t	*ring;
@@ -764,7 +754,6 @@ struct si_rlc {
 int radeon_ib_get(struct radeon_device *rdev, int ring,
 		  struct radeon_ib **ib, unsigned size);
 void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib);
-bool radeon_ib_try_free(struct radeon_device *rdev, struct radeon_ib *ib);
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib);
 int radeon_ib_pool_init(struct radeon_device *rdev);
 void radeon_ib_pool_fini(struct radeon_device *rdev);
@@ -1497,7 +1486,8 @@ struct radeon_device {
 	rwlock_t			fence_lock;
 	struct radeon_fence_driver	fence_drv[RADEON_NUM_RINGS];
 	struct radeon_ring		ring[RADEON_NUM_RINGS];
-	struct radeon_ib_pool		ib_pool;
+	bool				ib_pool_ready;
+	struct radeon_sa_manager	sa_manager;
 	struct radeon_irq		irq;
 	struct radeon_asic		*asic;
 	struct radeon_gem		gem;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index d77f19f..26fb9da 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -723,7 +723,6 @@ int radeon_device_init(struct radeon_device *rdev,
 	/* mutex initialization are all done here so we
 	 * can recall function without having locking issues */
 	radeon_mutex_init(&rdev->cs_mutex);
-	radeon_mutex_init(&rdev->ib_pool.mutex);
 	for (i = 0; i < RADEON_NUM_RINGS; ++i)
 		mutex_init(&rdev->ring[i].mutex);
 	mutex_init(&rdev->dc_hw_i2c_mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index c96d112..abd10f9 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -83,7 +83,8 @@ int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence)
 	return 0;
 }
 
-static bool radeon_fence_poll_locked(struct radeon_device *rdev, int ring)
+static bool radeon_fence_poll_locked(struct radeon_device *rdev, int ring,
+				     struct list_head *signaled)
 {
 	struct radeon_fence *fence;
 	struct list_head *i, *n;
@@ -110,7 +111,7 @@ static bool radeon_fence_poll_locked(struct radeon_device *rdev, int ring)
 		i = n;
 		do {
 			n = i->prev;
-			list_move_tail(i, &rdev->fence_drv[ring].signaled);
+			list_move_tail(i, signaled);
 			fence = list_entry(i, struct radeon_fence, list);
 			fence->signaled = true;
 			i = n;
@@ -120,6 +121,18 @@ static bool radeon_fence_poll_locked(struct radeon_device *rdev, int ring)
 	return wake;
 }
 
+static void radeon_fence_process_signaled(struct radeon_device *rdev, struct list_head *signaled)
+{
+	struct radeon_fence *fence;
+	struct list_head *i, *n;
+
+	list_for_each_safe(i, n, signaled) {
+		fence = list_entry(i, struct radeon_fence, list);
+		list_del_init(&fence->list);
+		radeon_ib_free(rdev, &fence->ib);
+	}
+}
+
 static void radeon_fence_destroy(struct kref *kref)
 {
 	unsigned long irq_flags;
@@ -152,6 +165,7 @@ int radeon_fence_create(struct radeon_device *rdev,
 	(*fence)->seq = 0;
 	(*fence)->ring = ring;
 	(*fence)->semaphore = NULL;
+	(*fence)->ib = NULL;
 	INIT_LIST_HEAD(&(*fence)->list);
 
 	write_lock_irqsave(&rdev->fence_lock, irq_flags);
@@ -164,6 +178,7 @@ bool radeon_fence_signaled(struct radeon_fence *fence)
 {
 	unsigned long irq_flags;
 	bool signaled = false;
+	LIST_HEAD(siglist);
 
 	if (!fence)
 		return true;
@@ -179,10 +194,12 @@ bool radeon_fence_signaled(struct radeon_fence *fence)
 		signaled = true;
 	}
 	if (!signaled) {
-		radeon_fence_poll_locked(fence->rdev, fence->ring);
+		radeon_fence_poll_locked(fence->rdev, fence->ring, &siglist);
 		signaled = fence->signaled;
 	}
 	write_unlock_irqrestore(&fence->rdev->fence_lock, irq_flags);
+	radeon_fence_process_signaled(fence->rdev, &siglist);
+
 	return signaled;
 }
 
@@ -341,10 +358,12 @@ void radeon_fence_process(struct radeon_device *rdev, int ring)
 {
 	unsigned long irq_flags;
 	bool wake;
+	LIST_HEAD(signaled);
 
 	write_lock_irqsave(&rdev->fence_lock, irq_flags);
-	wake = radeon_fence_poll_locked(rdev, ring);
+	wake = radeon_fence_poll_locked(rdev, ring, &signaled);
 	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+	radeon_fence_process_signaled(rdev, &signaled);
 	if (wake) {
 		wake_up_all(&rdev->fence_drv[ring].queue);
 	}
@@ -373,6 +392,22 @@ int radeon_fence_count_emitted(struct radeon_device *rdev, int ring)
 	return not_processed;
 }
 
+bool radeon_fence_set_associated_ib(struct radeon_fence *fence, struct radeon_ib *ib)
+{
+	struct radeon_device *rdev = fence->rdev;
+	unsigned long irq_flags;
+	bool isset = false;
+
+	/* a readlock is suficient, cause this should be called only once */
+	read_lock_irqsave(&rdev->fence_lock, irq_flags);
+	if (fence->emitted && !fence->signaled) {
+		fence->ib = ib;
+		isset = true;
+	}
+	read_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+	return isset;
+}
+
 int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring)
 {
 	unsigned long irq_flags;
@@ -413,7 +448,6 @@ static void radeon_fence_driver_init_ring(struct radeon_device *rdev, int ring)
 	atomic_set(&rdev->fence_drv[ring].seq, 0);
 	INIT_LIST_HEAD(&rdev->fence_drv[ring].created);
 	INIT_LIST_HEAD(&rdev->fence_drv[ring].emitted);
-	INIT_LIST_HEAD(&rdev->fence_drv[ring].signaled);
 	init_waitqueue_head(&rdev->fence_drv[ring].queue);
 	rdev->fence_drv[ring].initialized = false;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 7af4ff9..220dbb8 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -434,8 +434,8 @@ retry_id:
 	rdev->vm_manager.use_bitmap |= 1 << id;
 	vm->id = id;
 	list_add_tail(&vm->list, &rdev->vm_manager.lru_vm);
-	return radeon_vm_bo_update_pte(rdev, vm, rdev->ib_pool.sa_manager.bo,
-				       &rdev->ib_pool.sa_manager.bo->tbo.mem);
+	return radeon_vm_bo_update_pte(rdev, vm, rdev->sa_manager.bo,
+				       &rdev->sa_manager.bo->tbo.mem);
 }
 
 /* object have to be reserved */
@@ -633,7 +633,7 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 	/* map the ib pool buffer at 0 in virtual address space, set
 	 * read only
 	 */
-	r = radeon_vm_bo_add(rdev, vm, rdev->ib_pool.sa_manager.bo, 0,
+	r = radeon_vm_bo_add(rdev, vm, rdev->sa_manager.bo, 0,
 			     RADEON_VM_PAGE_READABLE | RADEON_VM_PAGE_SNOOPED);
 	return r;
 }
@@ -650,12 +650,12 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 	radeon_mutex_unlock(&rdev->cs_mutex);
 
 	/* remove all bo */
-	r = radeon_bo_reserve(rdev->ib_pool.sa_manager.bo, false);
+	r = radeon_bo_reserve(rdev->sa_manager.bo, false);
 	if (!r) {
-		bo_va = radeon_bo_va(rdev->ib_pool.sa_manager.bo, vm);
+		bo_va = radeon_bo_va(rdev->sa_manager.bo, vm);
 		list_del_init(&bo_va->bo_list);
 		list_del_init(&bo_va->vm_list);
-		radeon_bo_unreserve(rdev->ib_pool.sa_manager.bo);
+		radeon_bo_unreserve(rdev->sa_manager.bo);
 		kfree(bo_va);
 	}
 	if (!list_empty(&vm->va)) {
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index b06e04f..c8deae9 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -24,6 +24,7 @@
  * Authors: Dave Airlie
  *          Alex Deucher
  *          Jerome Glisse
+ *          Christian König
  */
 #include <linux/seq_file.h>
 #include <linux/slab.h>
@@ -33,6 +34,9 @@
 #include "radeon.h"
 #include "atom.h"
 
+/*
+ * IB.
+ */
 u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
 {
 	struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx];
@@ -58,123 +62,62 @@ u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
 	return idx_value;
 }
 
-void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
-{
-#if DRM_DEBUG_CODE
-	if (ring->count_dw <= 0) {
-		DRM_ERROR("radeon: writting more dword to ring than expected !\n");
-	}
-#endif
-	ring->ring[ring->wptr++] = v;
-	ring->wptr &= ring->ptr_mask;
-	ring->count_dw--;
-	ring->ring_free_dw--;
-}
-
-/*
- * IB.
- */
-bool radeon_ib_try_free(struct radeon_device *rdev, struct radeon_ib *ib)
-{
-	bool done = false;
-
-	/* only free ib which have been emited */
-	if (ib->fence && ib->fence->emitted) {
-		if (radeon_fence_signaled(ib->fence)) {
-			radeon_fence_unref(&ib->fence);
-			radeon_sa_bo_free(rdev, &ib->sa_bo);
-			done = true;
-		}
-	}
-	return done;
-}
-
 int radeon_ib_get(struct radeon_device *rdev, int ring,
 		  struct radeon_ib **ib, unsigned size)
 {
-	struct radeon_fence *fence;
-	unsigned cretry = 0;
-	int r = 0, i, idx;
+	int r;
 
-	*ib = NULL;
-	/* align size on 256 bytes */
-	size = ALIGN(size, 256);
+	*ib = kmalloc(sizeof(struct radeon_ib), GFP_KERNEL);
+	if (*ib == NULL) {
+		return -ENOMEM;
+	}
 
-	r = radeon_fence_create(rdev, &fence, ring);
+	r = radeon_sa_bo_new(rdev, &rdev->sa_manager, &(*ib)->sa_bo, size, 256, true);
 	if (r) {
-		dev_err(rdev->dev, "failed to create fence for new IB\n");
+		dev_err(rdev->dev, "failed to get a new IB (%d)\n", r);
+		kfree(*ib);
+		*ib = NULL;
 		return r;
 	}
 
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	idx = rdev->ib_pool.head_id;
-retry:
-	if (cretry > 5) {
-		dev_err(rdev->dev, "failed to get an ib after 5 retry\n");
-		radeon_mutex_unlock(&rdev->ib_pool.mutex);
-		radeon_fence_unref(&fence);
-		return -ENOMEM;
-	}
-	cretry++;
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		radeon_ib_try_free(rdev, &rdev->ib_pool.ibs[idx]);
-		if (rdev->ib_pool.ibs[idx].fence == NULL) {
-			r = radeon_sa_bo_new(rdev, &rdev->ib_pool.sa_manager,
-					     &rdev->ib_pool.ibs[idx].sa_bo,
-					     size, 256, false);
-			if (!r) {
-				*ib = &rdev->ib_pool.ibs[idx];
-				(*ib)->ptr = rdev->ib_pool.sa_manager.cpu_ptr;
-				(*ib)->ptr += ((*ib)->sa_bo.offset >> 2);
-				(*ib)->gpu_addr = rdev->ib_pool.sa_manager.gpu_addr;
-				(*ib)->gpu_addr += (*ib)->sa_bo.offset;
-				(*ib)->fence = fence;
-				(*ib)->vm_id = 0;
-				(*ib)->is_const_ib = false;
-				/* ib are most likely to be allocated in a ring fashion
-				 * thus rdev->ib_pool.head_id should be the id of the
-				 * oldest ib
-				 */
-				rdev->ib_pool.head_id = (1 + idx);
-				rdev->ib_pool.head_id &= (RADEON_IB_POOL_SIZE - 1);
-				radeon_mutex_unlock(&rdev->ib_pool.mutex);
-				return 0;
-			}
-		}
-		idx = (idx + 1) & (RADEON_IB_POOL_SIZE - 1);
-	}
-	/* this should be rare event, ie all ib scheduled none signaled yet.
-	 */
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		if (rdev->ib_pool.ibs[idx].fence && rdev->ib_pool.ibs[idx].fence->emitted) {
-			r = radeon_fence_wait(rdev->ib_pool.ibs[idx].fence, false);
-			if (!r) {
-				goto retry;
-			}
-			/* an error happened */
-			break;
-		}
-		idx = (idx + 1) & (RADEON_IB_POOL_SIZE - 1);
+	r = radeon_fence_create(rdev, &(*ib)->fence, ring);
+	if (r) {
+		dev_err(rdev->dev, "failed to create fence for new IB (%d)\n", r);
+		radeon_sa_bo_free(rdev, &(*ib)->sa_bo);
+		kfree(*ib);
+		*ib = NULL;
+		return r;
 	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
-	radeon_fence_unref(&fence);
-	return r;
+
+	(*ib)->ptr = rdev->sa_manager.cpu_ptr;
+	(*ib)->ptr += ((*ib)->sa_bo.offset >> 2);
+	(*ib)->gpu_addr = rdev->sa_manager.gpu_addr;
+	(*ib)->gpu_addr += (*ib)->sa_bo.offset;
+	(*ib)->vm_id = 0;
+	(*ib)->is_const_ib = false;
+
+	return 0;
 }
 
 void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib)
 {
 	struct radeon_ib *tmp = *ib;
+	bool destroy = true;
 
 	*ib = NULL;
 	if (tmp == NULL) {
 		return;
 	}
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (tmp->fence && !tmp->fence->emitted) {
+
+	if (tmp->fence) {
+		destroy = !radeon_fence_set_associated_ib(tmp->fence, tmp);
+	}
+
+	if (destroy) {
 		radeon_sa_bo_free(rdev, &tmp->sa_bo);
 		radeon_fence_unref(&tmp->fence);
+		kfree(tmp);
 	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
 }
 
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
@@ -184,7 +127,7 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 
 	if (!ib->length_dw || !ring->ready) {
 		/* TODO: Nothings in the ib we should report. */
-		DRM_ERROR("radeon: couldn't schedule IB(%u).\n", ib->idx);
+		DRM_ERROR("radeon: couldn't schedule IB.\n");
 		return -EINVAL;
 	}
 
@@ -202,61 +145,40 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 
 int radeon_ib_pool_init(struct radeon_device *rdev)
 {
-	int i, r;
+	int r;
 
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (rdev->ib_pool.ready) {
+	if (rdev->ib_pool_ready) {
 		return 0;
 	}
-	rdev->ib_pool.ready = true;
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
 
-	r = radeon_sa_bo_manager_init(rdev, &rdev->ib_pool.sa_manager,
+	r = radeon_sa_bo_manager_init(rdev, &rdev->sa_manager,
 				      RADEON_IB_POOL_SIZE*64*1024,
 				      RADEON_GEM_DOMAIN_GTT);
 	if (r) {
 		return r;
 	}
 
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		rdev->ib_pool.ibs[i].fence = NULL;
-		rdev->ib_pool.ibs[i].idx = i;
-		rdev->ib_pool.ibs[i].length_dw = 0;
-		INIT_LIST_HEAD(&rdev->ib_pool.ibs[i].sa_bo.list);
-	}
-	rdev->ib_pool.head_id = 0;
-	rdev->ib_pool.ready = true;
 	DRM_INFO("radeon: ib pool ready.\n");
-
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
+	rdev->ib_pool_ready = true;
 	return 0;
 }
 
 void radeon_ib_pool_fini(struct radeon_device *rdev)
 {
-	unsigned i;
-
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (rdev->ib_pool.ready) {
-		for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-			radeon_sa_bo_free(rdev, &rdev->ib_pool.ibs[i].sa_bo);
-			radeon_fence_unref(&rdev->ib_pool.ibs[i].fence);
-		}
-		radeon_sa_bo_manager_fini(rdev, &rdev->ib_pool.sa_manager);
-		rdev->ib_pool.ready = false;
+	if (rdev->ib_pool_ready) {
+		radeon_sa_bo_manager_fini(rdev, &rdev->sa_manager);
+		rdev->ib_pool_ready = false;
 	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
 }
 
 int radeon_ib_pool_start(struct radeon_device *rdev)
 {
-	return radeon_sa_bo_manager_start(rdev, &rdev->ib_pool.sa_manager);
+	return radeon_sa_bo_manager_start(rdev, &rdev->sa_manager);
 }
 
 int radeon_ib_pool_suspend(struct radeon_device *rdev)
 {
-	return radeon_sa_bo_manager_suspend(rdev, &rdev->ib_pool.sa_manager);
+	return radeon_sa_bo_manager_suspend(rdev, &rdev->sa_manager);
 }
 
 int radeon_ib_ring_tests(struct radeon_device *rdev)
@@ -292,6 +214,21 @@ int radeon_ib_ring_tests(struct radeon_device *rdev)
 /*
  * Ring.
  */
+int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);
+
+void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
+{
+#if DRM_DEBUG_CODE
+	if (ring->count_dw <= 0) {
+		DRM_ERROR("radeon: writting more dword to ring than expected !\n");
+	}
+#endif
+	ring->ring[ring->wptr++] = v;
+	ring->wptr &= ring->ptr_mask;
+	ring->count_dw--;
+	ring->ring_free_dw--;
+}
+
 int radeon_ring_index(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	/* r1xx-r5xx only has CP ring */
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index b67c259..9e2cf40 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -42,7 +42,7 @@ int radeon_semaphore_create(struct radeon_device *rdev,
 		return -ENOMEM;
 	}
 
-	r = radeon_sa_bo_new(rdev, &rdev->ib_pool.sa_manager,
+	r = radeon_sa_bo_new(rdev, &rdev->sa_manager,
 			     &(*semaphore)->sa_bo, 8, 8, true);
 	if (r) {
 		kfree(*semaphore);
@@ -51,10 +51,10 @@ int radeon_semaphore_create(struct radeon_device *rdev,
 	}
 
 	(*semaphore)->waiters = 0;
-	(*semaphore)->gpu_addr = rdev->ib_pool.sa_manager.gpu_addr;
+	(*semaphore)->gpu_addr = rdev->sa_manager.gpu_addr;
 	(*semaphore)->gpu_addr += (*semaphore)->sa_bo.offset;
 
-	cpu_ptr = rdev->ib_pool.sa_manager.cpu_ptr;
+	cpu_ptr = rdev->sa_manager.cpu_ptr;
 	cpu_ptr += (*semaphore)->sa_bo.offset;
 	*((uint64_t*)cpu_ptr) = 0;
 
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 13/24] drm/radeon: fix a bug with the ring syncing code

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Rings need to lock in order, otherwise
the ring subsystem can deadlock.

v2: fix error handling and number of locked doublewords.
v3: stop creating unneeded semaphores.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h           |    4 ++
 drivers/gpu/drm/radeon/radeon_cs.c        |   35 ++++++------------
 drivers/gpu/drm/radeon/radeon_semaphore.c |   56 +++++++++++++++++++++++++++++
 drivers/gpu/drm/radeon/radeon_ttm.c       |   48 +++++++++++--------------
 4 files changed, 93 insertions(+), 50 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 575dc05..c7f14d7 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -442,6 +442,10 @@ void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
 				  struct radeon_semaphore *semaphore);
 void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
 				struct radeon_semaphore *semaphore);
+int radeon_semaphore_sync_rings(struct radeon_device *rdev,
+				struct radeon_semaphore *semaphore,
+				bool sync_to[RADEON_NUM_RINGS],
+				int dst_ring);
 void radeon_semaphore_free(struct radeon_device *rdev,
 			   struct radeon_semaphore *semaphore);
 
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 5cac832..64b86e7 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -118,6 +118,7 @@ static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority
 static int radeon_cs_sync_rings(struct radeon_cs_parser *p)
 {
 	bool sync_to_ring[RADEON_NUM_RINGS] = { };
+	bool need_sync = false;
 	int i, r;
 
 	for (i = 0; i < p->nrelocs; i++) {
@@ -126,36 +127,24 @@ static int radeon_cs_sync_rings(struct radeon_cs_parser *p)
 
 		if (!(p->relocs[i].flags & RADEON_RELOC_DONT_SYNC)) {
 			struct radeon_fence *fence = p->relocs[i].robj->tbo.sync_obj;
-			if (!radeon_fence_signaled(fence)) {
+			if (fence->ring != p->ring && !radeon_fence_signaled(fence)) {
 				sync_to_ring[fence->ring] = true;
+				need_sync = true;
 			}
 		}
 	}
 
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		/* no need to sync to our own or unused rings */
-		if (i == p->ring || !sync_to_ring[i] || !p->rdev->ring[i].ready)
-			continue;
-
-		if (!p->ib->fence->semaphore) {
-			r = radeon_semaphore_create(p->rdev, &p->ib->fence->semaphore);
-			if (r)
-				return r;
-		}
-
-		r = radeon_ring_lock(p->rdev, &p->rdev->ring[i], 3);
-		if (r)
-			return r;
-		radeon_semaphore_emit_signal(p->rdev, i, p->ib->fence->semaphore);
-		radeon_ring_unlock_commit(p->rdev, &p->rdev->ring[i]);
+	if (!need_sync) {
+		return 0;
+	}
 
-		r = radeon_ring_lock(p->rdev, &p->rdev->ring[p->ring], 3);
-		if (r)
-			return r;
-		radeon_semaphore_emit_wait(p->rdev, p->ring, p->ib->fence->semaphore);
-		radeon_ring_unlock_commit(p->rdev, &p->rdev->ring[p->ring]);
+	r = radeon_semaphore_create(p->rdev, &p->ib->fence->semaphore);
+	if (r) {
+		return r;
 	}
-	return 0;
+
+	return radeon_semaphore_sync_rings(p->rdev, p->ib->fence->semaphore,
+					   sync_to_ring, p->ring);
 }
 
 int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index 9e2cf40..042dbfe 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -75,6 +75,62 @@ void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
 	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, true);
 }
 
+int radeon_semaphore_sync_rings(struct radeon_device *rdev,
+				struct radeon_semaphore *semaphore,
+				bool sync_to[RADEON_NUM_RINGS],
+				int dst_ring)
+{
+	int i, r;
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		unsigned num_ops = i == dst_ring ? RADEON_NUM_RINGS : 1;
+
+		/* don't lock unused rings */
+		if (!sync_to[i] && i != dst_ring)
+			continue;
+
+		/* prevent GPU deadlocks */
+		if (!rdev->ring[i].ready) {
+			dev_err(rdev->dev, "Trying to sync to a disabled ring!");
+			r = -EINVAL;
+			goto error;
+		}
+
+                r = radeon_ring_lock(rdev, &rdev->ring[i], num_ops * 8);
+                if (r)
+			goto error;
+	}
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		/* no need to sync to our own or unused rings */
+		if (!sync_to[i] || i == dst_ring)
+                        continue;
+
+		radeon_semaphore_emit_signal(rdev, i, semaphore);
+		radeon_semaphore_emit_wait(rdev, dst_ring, semaphore);
+	}
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+
+		/* don't unlock unused rings */
+		if (!sync_to[i] && i != dst_ring)
+			continue;
+
+		radeon_ring_unlock_commit(rdev, &rdev->ring[i]);
+	}
+
+	return 0;
+
+error:
+	/* unlock all locks taken so far */
+	for (--i; i >= 0; --i) {
+		if (sync_to[i] || i == dst_ring) {
+			radeon_ring_unlock_undo(rdev, &rdev->ring[i]);
+		}
+	}
+	return r;
+}
+
 void radeon_semaphore_free(struct radeon_device *rdev,
 			   struct radeon_semaphore *semaphore)
 {
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index f493c64..5e3d54d 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -222,8 +222,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 {
 	struct radeon_device *rdev;
 	uint64_t old_start, new_start;
-	struct radeon_fence *fence;
-	int r, i;
+	struct radeon_fence *fence, *old_fence;
+	int r;
 
 	rdev = radeon_get_rdev(bo->bdev);
 	r = radeon_fence_create(rdev, &fence, radeon_copy_ring_index(rdev));
@@ -242,6 +242,7 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 		break;
 	default:
 		DRM_ERROR("Unknown placement %d\n", old_mem->mem_type);
+		radeon_fence_unref(&fence);
 		return -EINVAL;
 	}
 	switch (new_mem->mem_type) {
@@ -253,42 +254,35 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 		break;
 	default:
 		DRM_ERROR("Unknown placement %d\n", old_mem->mem_type);
+		radeon_fence_unref(&fence);
 		return -EINVAL;
 	}
 	if (!rdev->ring[radeon_copy_ring_index(rdev)].ready) {
 		DRM_ERROR("Trying to move memory with ring turned off.\n");
+		radeon_fence_unref(&fence);
 		return -EINVAL;
 	}
 
 	BUILD_BUG_ON((PAGE_SIZE % RADEON_GPU_PAGE_SIZE) != 0);
 
 	/* sync other rings */
-	if (rdev->family >= CHIP_R600) {
-		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-			/* no need to sync to our own or unused rings */
-			if (i == radeon_copy_ring_index(rdev) || !rdev->ring[i].ready)
-				continue;
-
-			if (!fence->semaphore) {
-				r = radeon_semaphore_create(rdev, &fence->semaphore);
-				/* FIXME: handle semaphore error */
-				if (r)
-					continue;
-			}
+	old_fence = bo->sync_obj;
+	if (old_fence && old_fence->ring != fence->ring
+	    && !radeon_fence_signaled(old_fence)) {
+		bool sync_to_ring[RADEON_NUM_RINGS] = { };
+		sync_to_ring[old_fence->ring] = true;
+
+		r = radeon_semaphore_create(rdev, &fence->semaphore);
+		if (r) {
+			radeon_fence_unref(&fence);
+			return r;
+		}
 
-			r = radeon_ring_lock(rdev, &rdev->ring[i], 3);
-			/* FIXME: handle ring lock error */
-			if (r)
-				continue;
-			radeon_semaphore_emit_signal(rdev, i, fence->semaphore);
-			radeon_ring_unlock_commit(rdev, &rdev->ring[i]);
-
-			r = radeon_ring_lock(rdev, &rdev->ring[radeon_copy_ring_index(rdev)], 3);
-			/* FIXME: handle ring lock error */
-			if (r)
-				continue;
-			radeon_semaphore_emit_wait(rdev, radeon_copy_ring_index(rdev), fence->semaphore);
-			radeon_ring_unlock_commit(rdev, &rdev->ring[radeon_copy_ring_index(rdev)]);
+		r = radeon_semaphore_sync_rings(rdev, fence->semaphore,
+						sync_to_ring, fence->ring);
+		if (r) {
+			radeon_fence_unref(&fence);
+			return r;
 		}
 	}
 
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 14/24] drm/radeon: rework recursive gpu reset handling

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Instead of all this humpy pumpy with recursive
mutex (which also fixes only halve of the problem)
move the actual gpu reset out of the fence code,
return -EDEADLK and then reset the gpu in the
calling ioctl function.

v2: Split removal of radeon_mutex into separate patch.
    Return -EAGAIN if reset is successful.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon_cs.c     |   13 +++++++++++++
 drivers/gpu/drm/radeon/radeon_device.c |    5 -----
 drivers/gpu/drm/radeon/radeon_fence.c  |   10 +++-------
 drivers/gpu/drm/radeon/radeon_gem.c    |   16 ++++++++++++++++
 4 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 64b86e7..a0826bb 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -489,6 +489,16 @@ out:
 	return r;
 }
 
+static int radeon_cs_handle_lockup(struct radeon_device *rdev, int r)
+{
+	if (r == -EDEADLK) {
+		r = radeon_gpu_reset(rdev);
+		if (!r)
+			r = -EAGAIN;
+	}
+	return r;
+}
+
 int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	struct radeon_device *rdev = dev->dev_private;
@@ -510,6 +520,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
 		radeon_cs_parser_fini(&parser, r);
+		r = radeon_cs_handle_lockup(rdev, r);
 		radeon_mutex_unlock(&rdev->cs_mutex);
 		return r;
 	}
@@ -518,6 +529,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		if (r != -ERESTARTSYS)
 			DRM_ERROR("Failed to parse relocation %d!\n", r);
 		radeon_cs_parser_fini(&parser, r);
+		r = radeon_cs_handle_lockup(rdev, r);
 		radeon_mutex_unlock(&rdev->cs_mutex);
 		return r;
 	}
@@ -531,6 +543,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	}
 out:
 	radeon_cs_parser_fini(&parser, r);
+	r = radeon_cs_handle_lockup(rdev, r);
 	radeon_mutex_unlock(&rdev->cs_mutex);
 	return r;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 26fb9da..1dac27d 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -984,9 +984,6 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 	int r;
 	int resched;
 
-	/* Prevent CS ioctl from interfering */
-	radeon_mutex_lock(&rdev->cs_mutex);
-
 	radeon_save_bios_scratch_regs(rdev);
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
@@ -1001,8 +998,6 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 		ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched);
 	}
 
-	radeon_mutex_unlock(&rdev->cs_mutex);
-
 	if (r) {
 		/* bad news, how to tell it to userspace ? */
 		dev_info(rdev->dev, "GPU reset failed\n");
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index abd10f9..2868eda 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -267,6 +267,8 @@ int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 			/* change sequence value on all rings, so nobody else things there is a lockup */
 			for (i = 0; i < RADEON_NUM_RINGS; ++i)
 				rdev->fence_drv[i].last_seq -= 0x10000;
+
+			rdev->fence_drv[fence->ring].last_activity = jiffies;
 			write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
 
 			if (radeon_ring_is_lockup(rdev, fence->ring, &rdev->ring[fence->ring])) {
@@ -277,13 +279,7 @@ int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 
 				/* mark the ring as not ready any more */
 				rdev->ring[fence->ring].ready = false;
-				r = radeon_gpu_reset(rdev);
-				if (r)
-					return r;
-
-				write_lock_irqsave(&rdev->fence_lock, irq_flags);
-				rdev->fence_drv[fence->ring].last_activity = jiffies;
-				write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+				return -EDEADLK;
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index c7008b5..e15cb1f 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -154,6 +154,17 @@ void radeon_gem_object_close(struct drm_gem_object *obj,
 	radeon_bo_unreserve(rbo);
 }
 
+static int radeon_gem_handle_lockup(struct radeon_device *rdev, int r)
+{
+	if (r == -EDEADLK) {
+		radeon_mutex_lock(&rdev->cs_mutex);
+		r = radeon_gpu_reset(rdev);
+		if (!r)
+			r = -EAGAIN;
+		radeon_mutex_unlock(&rdev->cs_mutex);
+	}
+	return r;
+}
 
 /*
  * GEM ioctls.
@@ -210,12 +221,14 @@ int radeon_gem_create_ioctl(struct drm_device *dev, void *data,
 					args->initial_domain, false,
 					false, &gobj);
 	if (r) {
+		r = radeon_gem_handle_lockup(rdev, r);
 		return r;
 	}
 	r = drm_gem_handle_create(filp, gobj, &handle);
 	/* drop reference from allocate - handle holds it now */
 	drm_gem_object_unreference_unlocked(gobj);
 	if (r) {
+		r = radeon_gem_handle_lockup(rdev, r);
 		return r;
 	}
 	args->handle = handle;
@@ -245,6 +258,7 @@ int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 	r = radeon_gem_set_domain(gobj, args->read_domains, args->write_domain);
 
 	drm_gem_object_unreference_unlocked(gobj);
+	r = radeon_gem_handle_lockup(robj->rdev, r);
 	return r;
 }
 
@@ -301,6 +315,7 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
 		break;
 	}
 	drm_gem_object_unreference_unlocked(gobj);
+	r = radeon_gem_handle_lockup(robj->rdev, r);
 	return r;
 }
 
@@ -322,6 +337,7 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 	if (robj->rdev->asic->ioctl_wait_idle)
 		robj->rdev->asic->ioctl_wait_idle(robj->rdev, robj);
 	drm_gem_object_unreference_unlocked(gobj);
+	r = radeon_gem_handle_lockup(robj->rdev, r);
 	return r;
 }
 
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 15/24] drm/radeon: remove recursive mutex implementation

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Not needed anymore.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h        |   44 +-------------------------------
 drivers/gpu/drm/radeon/radeon_cs.c     |   10 +++---
 drivers/gpu/drm/radeon/radeon_device.c |    2 +-
 drivers/gpu/drm/radeon/radeon_gart.c   |   16 ++++++------
 drivers/gpu/drm/radeon/radeon_gem.c    |    4 +-
 5 files changed, 17 insertions(+), 59 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index c7f14d7..6ec4025 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -155,48 +155,6 @@ static inline int radeon_atrm_get_bios_chunk(uint8_t *bios, int offset, int len)
 #endif
 bool radeon_get_bios(struct radeon_device *rdev);
 
-
-/*
- * Mutex which allows recursive locking from the same process.
- */
-struct radeon_mutex {
-	struct mutex		mutex;
-	struct task_struct	*owner;
-	int			level;
-};
-
-static inline void radeon_mutex_init(struct radeon_mutex *mutex)
-{
-	mutex_init(&mutex->mutex);
-	mutex->owner = NULL;
-	mutex->level = 0;
-}
-
-static inline void radeon_mutex_lock(struct radeon_mutex *mutex)
-{
-	if (mutex_trylock(&mutex->mutex)) {
-		/* The mutex was unlocked before, so it's ours now */
-		mutex->owner = current;
-	} else if (mutex->owner != current) {
-		/* Another process locked the mutex, take it */
-		mutex_lock(&mutex->mutex);
-		mutex->owner = current;
-	}
-	/* Otherwise the mutex was already locked by this process */
-
-	mutex->level++;
-}
-
-static inline void radeon_mutex_unlock(struct radeon_mutex *mutex)
-{
-	if (--mutex->level > 0)
-		return;
-
-	mutex->owner = NULL;
-	mutex_unlock(&mutex->mutex);
-}
-
-
 /*
  * Dummy page
  */
@@ -1497,7 +1455,7 @@ struct radeon_device {
 	struct radeon_gem		gem;
 	struct radeon_pm		pm;
 	uint32_t			bios_scratch[RADEON_BIOS_NUM_SCRATCH];
-	struct radeon_mutex		cs_mutex;
+	struct mutex			cs_mutex;
 	struct radeon_wb		wb;
 	struct radeon_dummy_page	dummy_page;
 	bool				shutdown;
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index a0826bb..38e1496 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -505,9 +505,9 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	struct radeon_cs_parser parser;
 	int r;
 
-	radeon_mutex_lock(&rdev->cs_mutex);
+	mutex_lock(&rdev->cs_mutex);
 	if (!rdev->accel_working) {
-		radeon_mutex_unlock(&rdev->cs_mutex);
+		mutex_unlock(&rdev->cs_mutex);
 		return -EBUSY;
 	}
 	/* initialize parser */
@@ -521,7 +521,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		DRM_ERROR("Failed to initialize parser !\n");
 		radeon_cs_parser_fini(&parser, r);
 		r = radeon_cs_handle_lockup(rdev, r);
-		radeon_mutex_unlock(&rdev->cs_mutex);
+		mutex_unlock(&rdev->cs_mutex);
 		return r;
 	}
 	r = radeon_cs_parser_relocs(&parser);
@@ -530,7 +530,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			DRM_ERROR("Failed to parse relocation %d!\n", r);
 		radeon_cs_parser_fini(&parser, r);
 		r = radeon_cs_handle_lockup(rdev, r);
-		radeon_mutex_unlock(&rdev->cs_mutex);
+		mutex_unlock(&rdev->cs_mutex);
 		return r;
 	}
 	r = radeon_cs_ib_chunk(rdev, &parser);
@@ -544,7 +544,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 out:
 	radeon_cs_parser_fini(&parser, r);
 	r = radeon_cs_handle_lockup(rdev, r);
-	radeon_mutex_unlock(&rdev->cs_mutex);
+	mutex_unlock(&rdev->cs_mutex);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 1dac27d..5df53dd 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -722,7 +722,7 @@ int radeon_device_init(struct radeon_device *rdev,
 
 	/* mutex initialization are all done here so we
 	 * can recall function without having locking issues */
-	radeon_mutex_init(&rdev->cs_mutex);
+	mutex_init(&rdev->cs_mutex);
 	for (i = 0; i < RADEON_NUM_RINGS; ++i)
 		mutex_init(&rdev->ring[i].mutex);
 	mutex_init(&rdev->dc_hw_i2c_mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 220dbb8..b4a4982 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -356,13 +356,13 @@ int radeon_vm_manager_suspend(struct radeon_device *rdev)
 {
 	struct radeon_vm *vm, *tmp;
 
-	radeon_mutex_lock(&rdev->cs_mutex);
+	mutex_lock(&rdev->cs_mutex);
 	/* unbind all active vm */
 	list_for_each_entry_safe(vm, tmp, &rdev->vm_manager.lru_vm, list) {
 		radeon_vm_unbind_locked(rdev, vm);
 	}
 	rdev->vm_manager.funcs->fini(rdev);
-	radeon_mutex_unlock(&rdev->cs_mutex);
+	mutex_unlock(&rdev->cs_mutex);
 	return radeon_sa_bo_manager_suspend(rdev, &rdev->vm_manager.sa_manager);
 }
 
@@ -480,9 +480,9 @@ int radeon_vm_bo_add(struct radeon_device *rdev,
 	if (last_pfn > vm->last_pfn) {
 		/* grow va space 32M by 32M */
 		unsigned align = ((32 << 20) >> 12) - 1;
-		radeon_mutex_lock(&rdev->cs_mutex);
+		mutex_lock(&rdev->cs_mutex);
 		radeon_vm_unbind_locked(rdev, vm);
-		radeon_mutex_unlock(&rdev->cs_mutex);
+		mutex_unlock(&rdev->cs_mutex);
 		vm->last_pfn = (last_pfn + align) & ~align;
 	}
 	head = &vm->va;
@@ -598,9 +598,9 @@ int radeon_vm_bo_rmv(struct radeon_device *rdev,
 		return 0;
 
 	mutex_lock(&vm->mutex);
-	radeon_mutex_lock(&rdev->cs_mutex);
+	mutex_lock(&rdev->cs_mutex);
 	radeon_vm_bo_update_pte(rdev, vm, bo, NULL);
-	radeon_mutex_unlock(&rdev->cs_mutex);
+	mutex_unlock(&rdev->cs_mutex);
 	list_del(&bo_va->vm_list);
 	mutex_unlock(&vm->mutex);
 	list_del(&bo_va->bo_list);
@@ -645,9 +645,9 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 
 	mutex_lock(&vm->mutex);
 
-	radeon_mutex_lock(&rdev->cs_mutex);
+	mutex_lock(&rdev->cs_mutex);
 	radeon_vm_unbind_locked(rdev, vm);
-	radeon_mutex_unlock(&rdev->cs_mutex);
+	mutex_unlock(&rdev->cs_mutex);
 
 	/* remove all bo */
 	r = radeon_bo_reserve(rdev->sa_manager.bo, false);
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index e15cb1f..bd4521e 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -157,11 +157,11 @@ void radeon_gem_object_close(struct drm_gem_object *obj,
 static int radeon_gem_handle_lockup(struct radeon_device *rdev, int r)
 {
 	if (r == -EDEADLK) {
-		radeon_mutex_lock(&rdev->cs_mutex);
+		mutex_lock(&rdev->cs_mutex);
 		r = radeon_gpu_reset(rdev);
 		if (!r)
 			r = -EAGAIN;
-		radeon_mutex_unlock(&rdev->cs_mutex);
+		mutex_unlock(&rdev->cs_mutex);
 	}
 	return r;
 }
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 16/24] drm/radeon: move lockup detection code into radeon_ring.c v2

[j.glisse]

From: Jerome Glisse <jglisse@redhat.com>

It isn't chipset specific, so it makes no sense
to have that inside r100.c.

v2: rebase on debugfs removal

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/evergreen.c   |    5 +--
 drivers/gpu/drm/radeon/ni.c          |    5 +--
 drivers/gpu/drm/radeon/r100.c        |   57 +--------------------------------
 drivers/gpu/drm/radeon/r300.c        |    4 +-
 drivers/gpu/drm/radeon/r600.c        |   10 +-----
 drivers/gpu/drm/radeon/radeon.h      |   16 ++-------
 drivers/gpu/drm/radeon/radeon_asic.h |    5 ---
 drivers/gpu/drm/radeon/radeon_ring.c |   53 +++++++++++++++++++++++++++++++
 drivers/gpu/drm/radeon/si.c          |    5 +--
 9 files changed, 69 insertions(+), 91 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index a76389c..353d10a 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2424,7 +2424,6 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 	u32 srbm_status;
 	u32 grbm_status;
 	u32 grbm_status_se0, grbm_status_se1;
-	struct r100_gpu_lockup *lockup = &rdev->config.evergreen.lockup;
 	int r;
 
 	srbm_status = RREG32(SRBM_STATUS);
@@ -2432,7 +2431,7 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 	grbm_status_se0 = RREG32(GRBM_STATUS_SE0);
 	grbm_status_se1 = RREG32(GRBM_STATUS_SE1);
 	if (!(grbm_status & GUI_ACTIVE)) {
-		r100_gpu_lockup_update(lockup, ring);
+		radeon_ring_lockup_update(ring);
 		return false;
 	}
 	/* force CP activities */
@@ -2444,7 +2443,7 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 		radeon_ring_unlock_commit(rdev, ring);
 	}
 	ring->rptr = RREG32(CP_RB_RPTR);
-	return r100_gpu_cp_is_lockup(rdev, lockup, ring);
+	return radeon_ring_test_lockup(rdev, ring);
 }
 
 static int evergreen_gpu_soft_reset(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index c0b0956..4327b32 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1397,7 +1397,6 @@ bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	u32 srbm_status;
 	u32 grbm_status;
 	u32 grbm_status_se0, grbm_status_se1;
-	struct r100_gpu_lockup *lockup = &rdev->config.cayman.lockup;
 	int r;
 
 	srbm_status = RREG32(SRBM_STATUS);
@@ -1405,7 +1404,7 @@ bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	grbm_status_se0 = RREG32(GRBM_STATUS_SE0);
 	grbm_status_se1 = RREG32(GRBM_STATUS_SE1);
 	if (!(grbm_status & GUI_ACTIVE)) {
-		r100_gpu_lockup_update(lockup, ring);
+		radeon_ring_lockup_update(ring);
 		return false;
 	}
 	/* force CP activities */
@@ -1418,7 +1417,7 @@ bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	}
 	/* XXX deal with CP0,1,2 */
 	ring->rptr = RREG32(ring->rptr_reg);
-	return r100_gpu_cp_is_lockup(rdev, lockup, ring);
+	return radeon_ring_test_lockup(rdev, ring);
 }
 
 static int cayman_gpu_soft_reset(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index be51f7b..0a62ada 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2152,59 +2152,6 @@ int r100_mc_wait_for_idle(struct radeon_device *rdev)
 	return -1;
 }
 
-void r100_gpu_lockup_update(struct r100_gpu_lockup *lockup, struct radeon_ring *ring)
-{
-	lockup->last_cp_rptr = ring->rptr;
-	lockup->last_jiffies = jiffies;
-}
-
-/**
- * r100_gpu_cp_is_lockup() - check if CP is lockup by recording information
- * @rdev:	radeon device structure
- * @lockup:	r100_gpu_lockup structure holding CP lockup tracking informations
- * @cp:		radeon_cp structure holding CP information
- *
- * We don't need to initialize the lockup tracking information as we will either
- * have CP rptr to a different value of jiffies wrap around which will force
- * initialization of the lockup tracking informations.
- *
- * A possible false positivie is if we get call after while and last_cp_rptr ==
- * the current CP rptr, even if it's unlikely it might happen. To avoid this
- * if the elapsed time since last call is bigger than 2 second than we return
- * false and update the tracking information. Due to this the caller must call
- * r100_gpu_cp_is_lockup several time in less than 2sec for lockup to be reported
- * the fencing code should be cautious about that.
- *
- * Caller should write to the ring to force CP to do something so we don't get
- * false positive when CP is just gived nothing to do.
- *
- **/
-bool r100_gpu_cp_is_lockup(struct radeon_device *rdev, struct r100_gpu_lockup *lockup, struct radeon_ring *ring)
-{
-	unsigned long cjiffies, elapsed;
-
-	cjiffies = jiffies;
-	if (!time_after(cjiffies, lockup->last_jiffies)) {
-		/* likely a wrap around */
-		lockup->last_cp_rptr = ring->rptr;
-		lockup->last_jiffies = jiffies;
-		return false;
-	}
-	if (ring->rptr != lockup->last_cp_rptr) {
-		/* CP is still working no lockup */
-		lockup->last_cp_rptr = ring->rptr;
-		lockup->last_jiffies = jiffies;
-		return false;
-	}
-	elapsed = jiffies_to_msecs(cjiffies - lockup->last_jiffies);
-	if (elapsed >= 10000) {
-		dev_err(rdev->dev, "GPU lockup CP stall for more than %lumsec\n", elapsed);
-		return true;
-	}
-	/* give a chance to the GPU ... */
-	return false;
-}
-
 bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	u32 rbbm_status;
@@ -2212,7 +2159,7 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 
 	rbbm_status = RREG32(R_000E40_RBBM_STATUS);
 	if (!G_000E40_GUI_ACTIVE(rbbm_status)) {
-		r100_gpu_lockup_update(&rdev->config.r100.lockup, ring);
+		radeon_ring_lockup_update(ring);
 		return false;
 	}
 	/* force CP activities */
@@ -2224,7 +2171,7 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 		radeon_ring_unlock_commit(rdev, ring);
 	}
 	ring->rptr = RREG32(ring->rptr_reg);
-	return r100_gpu_cp_is_lockup(rdev, &rdev->config.r100.lockup, ring);
+	return radeon_ring_test_lockup(rdev, ring);
 }
 
 void r100_bm_disable(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index ae15c10..e46bbd0 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -379,7 +379,7 @@ bool r300_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 
 	rbbm_status = RREG32(R_000E40_RBBM_STATUS);
 	if (!G_000E40_GUI_ACTIVE(rbbm_status)) {
-		r100_gpu_lockup_update(&rdev->config.r300.lockup, ring);
+		radeon_ring_lockup_update(ring);
 		return false;
 	}
 	/* force CP activities */
@@ -391,7 +391,7 @@ bool r300_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 		radeon_ring_unlock_commit(rdev, ring);
 	}
 	ring->rptr = RREG32(RADEON_CP_RB_RPTR);
-	return r100_gpu_cp_is_lockup(rdev, &rdev->config.r300.lockup, ring);
+	return radeon_ring_test_lockup(rdev, ring);
 }
 
 int r300_asic_reset(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 24e68fd..87b1d25 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1348,19 +1348,13 @@ bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	u32 srbm_status;
 	u32 grbm_status;
 	u32 grbm_status2;
-	struct r100_gpu_lockup *lockup;
 	int r;
 
-	if (rdev->family >= CHIP_RV770)
-		lockup = &rdev->config.rv770.lockup;
-	else
-		lockup = &rdev->config.r600.lockup;
-
 	srbm_status = RREG32(R_000E50_SRBM_STATUS);
 	grbm_status = RREG32(R_008010_GRBM_STATUS);
 	grbm_status2 = RREG32(R_008014_GRBM_STATUS2);
 	if (!G_008010_GUI_ACTIVE(grbm_status)) {
-		r100_gpu_lockup_update(lockup, ring);
+		radeon_ring_lockup_update(ring);
 		return false;
 	}
 	/* force CP activities */
@@ -1372,7 +1366,7 @@ bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 		radeon_ring_unlock_commit(rdev, ring);
 	}
 	ring->rptr = RREG32(ring->rptr_reg);
-	return r100_gpu_cp_is_lockup(rdev, lockup, ring);
+	return radeon_ring_test_lockup(rdev, ring);
 }
 
 int r600_asic_reset(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 6ec4025..c0ed077 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -588,6 +588,8 @@ struct radeon_ring {
 	unsigned		ring_size;
 	unsigned		ring_free_dw;
 	int			count_dw;
+	unsigned long		last_activity;
+	unsigned		last_rptr;
 	uint64_t		gpu_addr;
 	uint32_t		align_mask;
 	uint32_t		ptr_mask;
@@ -731,6 +733,8 @@ void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *cp);
 int radeon_ring_test(struct radeon_device *rdev, struct radeon_ring *cp);
+void radeon_ring_lockup_update(struct radeon_ring *ring);
+bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
 int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ring_size,
 		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
 		     u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop);
@@ -1180,16 +1184,10 @@ struct radeon_asic {
 /*
  * Asic structures
  */
-struct r100_gpu_lockup {
-	unsigned long	last_jiffies;
-	u32		last_cp_rptr;
-};
-
 struct r100_asic {
 	const unsigned		*reg_safe_bm;
 	unsigned		reg_safe_bm_size;
 	u32			hdp_cntl;
-	struct r100_gpu_lockup	lockup;
 };
 
 struct r300_asic {
@@ -1197,7 +1195,6 @@ struct r300_asic {
 	unsigned		reg_safe_bm_size;
 	u32			resync_scratch;
 	u32			hdp_cntl;
-	struct r100_gpu_lockup	lockup;
 };
 
 struct r600_asic {
@@ -1219,7 +1216,6 @@ struct r600_asic {
 	unsigned		tiling_group_size;
 	unsigned		tile_config;
 	unsigned		backend_map;
-	struct r100_gpu_lockup	lockup;
 };
 
 struct rv770_asic {
@@ -1245,7 +1241,6 @@ struct rv770_asic {
 	unsigned		tiling_group_size;
 	unsigned		tile_config;
 	unsigned		backend_map;
-	struct r100_gpu_lockup	lockup;
 };
 
 struct evergreen_asic {
@@ -1272,7 +1267,6 @@ struct evergreen_asic {
 	unsigned tiling_group_size;
 	unsigned tile_config;
 	unsigned backend_map;
-	struct r100_gpu_lockup	lockup;
 };
 
 struct cayman_asic {
@@ -1311,7 +1305,6 @@ struct cayman_asic {
 	unsigned multi_gpu_tile_size;
 
 	unsigned tile_config;
-	struct r100_gpu_lockup	lockup;
 };
 
 struct si_asic {
@@ -1342,7 +1335,6 @@ struct si_asic {
 	unsigned multi_gpu_tile_size;
 
 	unsigned tile_config;
-	struct r100_gpu_lockup	lockup;
 };
 
 union radeon_asic_config {
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 6f31f9a..84f3552 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -100,11 +100,6 @@ void r100_pci_gart_fini(struct radeon_device *rdev);
 int r100_pci_gart_enable(struct radeon_device *rdev);
 void r100_pci_gart_disable(struct radeon_device *rdev);
 int r100_gui_wait_for_idle(struct radeon_device *rdev);
-void r100_gpu_lockup_update(struct r100_gpu_lockup *lockup,
-			    struct radeon_ring *cp);
-bool r100_gpu_cp_is_lockup(struct radeon_device *rdev,
-			   struct r100_gpu_lockup *lockup,
-			   struct radeon_ring *cp);
 void r100_ib_fini(struct radeon_device *rdev);
 int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
 void r100_irq_disable(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index c8deae9..f2dfcbf 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -325,6 +325,59 @@ void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *rin
 	mutex_unlock(&ring->mutex);
 }
 
+void radeon_ring_lockup_update(struct radeon_ring *ring)
+{
+	ring->last_rptr = ring->rptr;
+	ring->last_activity = jiffies;
+}
+
+/**
+ * radeon_ring_test_lockup() - check if ring is lockedup by recording information
+ * @rdev:       radeon device structure
+ * @ring:       radeon_ring structure holding ring information
+ *
+ * We don't need to initialize the lockup tracking information as we will either
+ * have CP rptr to a different value of jiffies wrap around which will force
+ * initialization of the lockup tracking informations.
+ *
+ * A possible false positivie is if we get call after while and last_cp_rptr ==
+ * the current CP rptr, even if it's unlikely it might happen. To avoid this
+ * if the elapsed time since last call is bigger than 2 second than we return
+ * false and update the tracking information. Due to this the caller must call
+ * radeon_ring_test_lockup several time in less than 2sec for lockup to be reported
+ * the fencing code should be cautious about that.
+ *
+ * Caller should write to the ring to force CP to do something so we don't get
+ * false positive when CP is just gived nothing to do.
+ *
+ **/
+bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	unsigned long cjiffies, elapsed;
+	uint32_t rptr;
+
+	cjiffies = jiffies;
+	if (!time_after(cjiffies, ring->last_activity)) {
+		/* likely a wrap around */
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	rptr = RREG32(ring->rptr_reg);
+	ring->rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
+	if (ring->rptr != ring->last_rptr) {
+		/* CP is still working no lockup */
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	elapsed = jiffies_to_msecs(cjiffies - ring->last_activity);
+	if (elapsed >= 10000) {
+		dev_err(rdev->dev, "GPU lockup CP stall for more than %lumsec\n", elapsed);
+		return true;
+	}
+	/* give a chance to the GPU ... */
+	return false;
+}
+
 int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size,
 		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
 		     u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index ebe2c9b..1bd5670 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2217,7 +2217,6 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	u32 srbm_status;
 	u32 grbm_status, grbm_status2;
 	u32 grbm_status_se0, grbm_status_se1;
-	struct r100_gpu_lockup *lockup = &rdev->config.si.lockup;
 	int r;
 
 	srbm_status = RREG32(SRBM_STATUS);
@@ -2226,7 +2225,7 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	grbm_status_se0 = RREG32(GRBM_STATUS_SE0);
 	grbm_status_se1 = RREG32(GRBM_STATUS_SE1);
 	if (!(grbm_status & GUI_ACTIVE)) {
-		r100_gpu_lockup_update(lockup, ring);
+		radeon_ring_lockup_update(ring);
 		return false;
 	}
 	/* force CP activities */
@@ -2239,7 +2238,7 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	}
 	/* XXX deal with CP0,1,2 */
 	ring->rptr = RREG32(ring->rptr_reg);
-	return r100_gpu_cp_is_lockup(rdev, lockup, ring);
+	return radeon_ring_test_lockup(rdev, ring);
 }
 
 static int si_gpu_soft_reset(struct radeon_device *rdev)
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 17/24] drm/radeon: make lockup timeout a module param

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Don't hard code the 10 seconds timeout. Compute jobs
can run much longer.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h      |    1 +
 drivers/gpu/drm/radeon/radeon_drv.c  |    4 ++++
 drivers/gpu/drm/radeon/radeon_ring.c |    2 +-
 3 files changed, 6 insertions(+), 1 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index c0ed077..fde5eaa 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -94,6 +94,7 @@ extern int radeon_disp_priority;
 extern int radeon_hw_i2c;
 extern int radeon_pcie_gen2;
 extern int radeon_msi;
+extern int radeon_lockup_timeout;
 
 /*
  * Copy from radeon_drv.h so we don't have to include both and have conflicting
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index ef7bb3f..e62e56a 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -128,6 +128,7 @@ int radeon_disp_priority = 0;
 int radeon_hw_i2c = 0;
 int radeon_pcie_gen2 = 0;
 int radeon_msi = -1;
+int radeon_lockup_timeout = 10000;
 
 MODULE_PARM_DESC(no_wb, "Disable AGP writeback for scratch registers");
 module_param_named(no_wb, radeon_no_wb, int, 0444);
@@ -177,6 +178,9 @@ module_param_named(pcie_gen2, radeon_pcie_gen2, int, 0444);
 MODULE_PARM_DESC(msi, "MSI support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(msi, radeon_msi, int, 0444);
 
+MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (defaul 10000 = 10 seconds, 0 = disable)");
+module_param_named(lockup_timeout, radeon_lockup_timeout, int, 0444);
+
 static int radeon_suspend(struct drm_device *dev, pm_message_t state)
 {
 	drm_radeon_private_t *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index f2dfcbf..d7245db 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -370,7 +370,7 @@ bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 		return false;
 	}
 	elapsed = jiffies_to_msecs(cjiffies - ring->last_activity);
-	if (elapsed >= 10000) {
+	if (radeon_lockup_timeout && elapsed >= radeon_lockup_timeout) {
 		dev_err(rdev->dev, "GPU lockup CP stall for more than %lumsec\n", elapsed);
 		return true;
 	}
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 18/24] drm/radeon: unlock the ring mutex while waiting for the next fence

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Fixing just another deadlock problem with gpu reset tests.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon_ring.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index d7245db..bb5715a 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -275,7 +275,9 @@ int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *ring, unsi
 		if (ndw < ring->ring_free_dw) {
 			break;
 		}
+		mutex_unlock(&ring->mutex);
 		r = radeon_fence_wait_next(rdev, radeon_ring_index(rdev, ring));
+		mutex_lock(&ring->mutex);
 		if (r)
 			return r;
 	}
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 19/24] drm/radeon: make forcing ring activity a common function

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Nothing chipset or ring specific with it,
so also move it to radon_ring.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/evergreen.c   |   10 +---------
 drivers/gpu/drm/radeon/ni.c          |   11 +----------
 drivers/gpu/drm/radeon/r100.c        |   10 +---------
 drivers/gpu/drm/radeon/r300.c        |   10 +---------
 drivers/gpu/drm/radeon/r600.c        |   10 +---------
 drivers/gpu/drm/radeon/radeon.h      |    1 +
 drivers/gpu/drm/radeon/radeon_ring.c |   16 ++++++++++++++++
 drivers/gpu/drm/radeon/si.c          |   11 +----------
 8 files changed, 23 insertions(+), 56 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 353d10a..ec61194 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2424,7 +2424,6 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 	u32 srbm_status;
 	u32 grbm_status;
 	u32 grbm_status_se0, grbm_status_se1;
-	int r;
 
 	srbm_status = RREG32(SRBM_STATUS);
 	grbm_status = RREG32(GRBM_STATUS);
@@ -2435,14 +2434,7 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 		return false;
 	}
 	/* force CP activities */
-	r = radeon_ring_lock(rdev, ring, 2);
-	if (!r) {
-		/* PACKET2 NOP */
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_unlock_commit(rdev, ring);
-	}
-	ring->rptr = RREG32(CP_RB_RPTR);
+	radeon_ring_force_activity(rdev, ring);
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 4327b32..8a9c85d 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1397,7 +1397,6 @@ bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	u32 srbm_status;
 	u32 grbm_status;
 	u32 grbm_status_se0, grbm_status_se1;
-	int r;
 
 	srbm_status = RREG32(SRBM_STATUS);
 	grbm_status = RREG32(GRBM_STATUS);
@@ -1408,15 +1407,7 @@ bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 		return false;
 	}
 	/* force CP activities */
-	r = radeon_ring_lock(rdev, ring, 2);
-	if (!r) {
-		/* PACKET2 NOP */
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_unlock_commit(rdev, ring);
-	}
-	/* XXX deal with CP0,1,2 */
-	ring->rptr = RREG32(ring->rptr_reg);
+	radeon_ring_force_activity(rdev, ring);
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 0a62ada..68b1674 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2155,7 +2155,6 @@ int r100_mc_wait_for_idle(struct radeon_device *rdev)
 bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	u32 rbbm_status;
-	int r;
 
 	rbbm_status = RREG32(R_000E40_RBBM_STATUS);
 	if (!G_000E40_GUI_ACTIVE(rbbm_status)) {
@@ -2163,14 +2162,7 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 		return false;
 	}
 	/* force CP activities */
-	r = radeon_ring_lock(rdev, ring, 2);
-	if (!r) {
-		/* PACKET2 NOP */
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_unlock_commit(rdev, ring);
-	}
-	ring->rptr = RREG32(ring->rptr_reg);
+	radeon_ring_force_activity(rdev, ring);
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index e46bbd0..c496778 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -375,7 +375,6 @@ void r300_gpu_init(struct radeon_device *rdev)
 bool r300_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	u32 rbbm_status;
-	int r;
 
 	rbbm_status = RREG32(R_000E40_RBBM_STATUS);
 	if (!G_000E40_GUI_ACTIVE(rbbm_status)) {
@@ -383,14 +382,7 @@ bool r300_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 		return false;
 	}
 	/* force CP activities */
-	r = radeon_ring_lock(rdev, ring, 2);
-	if (!r) {
-		/* PACKET2 NOP */
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_unlock_commit(rdev, ring);
-	}
-	ring->rptr = RREG32(RADEON_CP_RB_RPTR);
+	radeon_ring_force_activity(rdev, ring);
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 87b1d25..46b2a77 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1348,7 +1348,6 @@ bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	u32 srbm_status;
 	u32 grbm_status;
 	u32 grbm_status2;
-	int r;
 
 	srbm_status = RREG32(R_000E50_SRBM_STATUS);
 	grbm_status = RREG32(R_008010_GRBM_STATUS);
@@ -1358,14 +1357,7 @@ bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 		return false;
 	}
 	/* force CP activities */
-	r = radeon_ring_lock(rdev, ring, 2);
-	if (!r) {
-		/* PACKET2 NOP */
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_unlock_commit(rdev, ring);
-	}
-	ring->rptr = RREG32(ring->rptr_reg);
+	radeon_ring_force_activity(rdev, ring);
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index fde5eaa..91b48ac 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -734,6 +734,7 @@ void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *cp);
 int radeon_ring_test(struct radeon_device *rdev, struct radeon_ring *cp);
+void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *ring);
 void radeon_ring_lockup_update(struct radeon_ring *ring);
 bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
 int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ring_size,
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index bb5715a..f256eae 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -327,6 +327,22 @@ void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *rin
 	mutex_unlock(&ring->mutex);
 }
 
+void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	int r;
+
+	mutex_lock(&ring->mutex);
+	radeon_ring_free_size(rdev, ring);
+	if (ring->rptr == ring->wptr) {
+		r = radeon_ring_alloc(rdev, ring, 1);
+		if (!r) {
+			radeon_ring_write(ring, ring->nop);
+			radeon_ring_commit(rdev, ring);
+		}
+	}
+	mutex_unlock(&ring->mutex);
+}
+
 void radeon_ring_lockup_update(struct radeon_ring *ring)
 {
 	ring->last_rptr = ring->rptr;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 1bd5670..5a5819e 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2217,7 +2217,6 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	u32 srbm_status;
 	u32 grbm_status, grbm_status2;
 	u32 grbm_status_se0, grbm_status_se1;
-	int r;
 
 	srbm_status = RREG32(SRBM_STATUS);
 	grbm_status = RREG32(GRBM_STATUS);
@@ -2229,15 +2228,7 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 		return false;
 	}
 	/* force CP activities */
-	r = radeon_ring_lock(rdev, ring, 2);
-	if (!r) {
-		/* PACKET2 NOP */
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_write(ring, 0x80000000);
-		radeon_ring_unlock_commit(rdev, ring);
-	}
-	/* XXX deal with CP0,1,2 */
-	ring->rptr = RREG32(ring->rptr_reg);
+	radeon_ring_force_activity(rdev, ring);
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 20/24] drm/radeon: remove r300_gpu_is_lockup

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Since it is now identical to r100_gpu_is_lockup.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/r300.c        |   14 --------------
 drivers/gpu/drm/radeon/radeon_asic.c |   16 ++++++++--------
 drivers/gpu/drm/radeon/radeon_asic.h |    1 -
 3 files changed, 8 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index c496778..7c53729 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -372,20 +372,6 @@ void r300_gpu_init(struct radeon_device *rdev)
 		 rdev->num_gb_pipes, rdev->num_z_pipes);
 }
 
-bool r300_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	u32 rbbm_status;
-
-	rbbm_status = RREG32(R_000E40_RBBM_STATUS);
-	if (!G_000E40_GUI_ACTIVE(rbbm_status)) {
-		radeon_ring_lockup_update(ring);
-		return false;
-	}
-	/* force CP activities */
-	radeon_ring_force_activity(rdev, ring);
-	return radeon_ring_test_lockup(rdev, ring);
-}
-
 int r300_asic_reset(struct radeon_device *rdev)
 {
 	struct r100_mc_save save;
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 958b9ea..5e5694e 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -299,7 +299,7 @@ static struct radeon_asic r300_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
-			.is_lockup = &r300_gpu_is_lockup,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -373,7 +373,7 @@ static struct radeon_asic r300_asic_pcie = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
-			.is_lockup = &r300_gpu_is_lockup,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -447,7 +447,7 @@ static struct radeon_asic r420_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
-			.is_lockup = &r300_gpu_is_lockup,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -521,7 +521,7 @@ static struct radeon_asic rs400_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
-			.is_lockup = &r300_gpu_is_lockup,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -595,7 +595,7 @@ static struct radeon_asic rs600_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
-			.is_lockup = &r300_gpu_is_lockup,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -669,7 +669,7 @@ static struct radeon_asic rs690_asic = {
 			.ring_start = &r300_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
-			.is_lockup = &r300_gpu_is_lockup,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -743,7 +743,7 @@ static struct radeon_asic rv515_asic = {
 			.ring_start = &rv515_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
-			.is_lockup = &r300_gpu_is_lockup,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -817,7 +817,7 @@ static struct radeon_asic r520_asic = {
 			.ring_start = &rv515_ring_start,
 			.ring_test = &r100_ring_test,
 			.ib_test = &r100_ib_test,
-			.is_lockup = &r300_gpu_is_lockup,
+			.is_lockup = &r100_gpu_is_lockup,
 		}
 	},
 	.irq = {
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 84f3552..58454b4 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -151,7 +151,6 @@ extern int r300_init(struct radeon_device *rdev);
 extern void r300_fini(struct radeon_device *rdev);
 extern int r300_suspend(struct radeon_device *rdev);
 extern int r300_resume(struct radeon_device *rdev);
-extern bool r300_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
 extern int r300_asic_reset(struct radeon_device *rdev);
 extern void r300_ring_start(struct radeon_device *rdev, struct radeon_ring *ring);
 extern void r300_fence_ring_emit(struct radeon_device *rdev,
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 21/24] drm/radeon: remove cayman_gpu_is_lockup

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Since it is now identical to evergreen_gpu_is_lockup.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/ni.c          |   19 -------------------
 drivers/gpu/drm/radeon/radeon_asic.c |   12 ++++++------
 drivers/gpu/drm/radeon/radeon_asic.h |    1 -
 3 files changed, 6 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 8a9c85d..107b217 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1392,25 +1392,6 @@ int cayman_cp_resume(struct radeon_device *rdev)
 	return 0;
 }
 
-bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	u32 srbm_status;
-	u32 grbm_status;
-	u32 grbm_status_se0, grbm_status_se1;
-
-	srbm_status = RREG32(SRBM_STATUS);
-	grbm_status = RREG32(GRBM_STATUS);
-	grbm_status_se0 = RREG32(GRBM_STATUS_SE0);
-	grbm_status_se1 = RREG32(GRBM_STATUS_SE1);
-	if (!(grbm_status & GUI_ACTIVE)) {
-		radeon_ring_lockup_update(ring);
-		return false;
-	}
-	/* force CP activities */
-	radeon_ring_force_activity(rdev, ring);
-	return radeon_ring_test_lockup(rdev, ring);
-}
-
 static int cayman_gpu_soft_reset(struct radeon_device *rdev)
 {
 	struct evergreen_mc_save save;
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 5e5694e..f533df5 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1339,7 +1339,7 @@ static struct radeon_asic cayman_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gpu_is_lockup,
+			.is_lockup = &evergreen_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1349,7 +1349,7 @@ static struct radeon_asic cayman_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gpu_is_lockup,
+			.is_lockup = &evergreen_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1359,7 +1359,7 @@ static struct radeon_asic cayman_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gpu_is_lockup,
+			.is_lockup = &evergreen_gpu_is_lockup,
 		}
 	},
 	.irq = {
@@ -1433,7 +1433,7 @@ static struct radeon_asic trinity_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gpu_is_lockup,
+			.is_lockup = &evergreen_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP1_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1443,7 +1443,7 @@ static struct radeon_asic trinity_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gpu_is_lockup,
+			.is_lockup = &evergreen_gpu_is_lockup,
 		},
 		[CAYMAN_RING_TYPE_CP2_INDEX] = {
 			.ib_execute = &cayman_ring_ib_execute,
@@ -1453,7 +1453,7 @@ static struct radeon_asic trinity_asic = {
 			.cs_parse = &evergreen_cs_parse,
 			.ring_test = &r600_ring_test,
 			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gpu_is_lockup,
+			.is_lockup = &evergreen_gpu_is_lockup,
 		}
 	},
 	.irq = {
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 58454b4..ddb145d 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -435,7 +435,6 @@ int cayman_init(struct radeon_device *rdev);
 void cayman_fini(struct radeon_device *rdev);
 int cayman_suspend(struct radeon_device *rdev);
 int cayman_resume(struct radeon_device *rdev);
-bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
 int cayman_asic_reset(struct radeon_device *rdev);
 void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 int cayman_vm_init(struct radeon_device *rdev);
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 22/24] drm/radeon: extend ring debugfs files with fence info c2

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

That should aid in debugging multi ring lockups.

v2 rebase on top of debugfs removal

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h       |    1 +
 drivers/gpu/drm/radeon/radeon_fence.c |    1 +
 2 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 91b48ac..6377f8c 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -233,6 +233,7 @@ struct radeon_fence {
 	bool				signaled;
 	/* RB, DMA, etc. */
 	int				ring;
+	unsigned			emitted_at;
 	struct radeon_semaphore		*semaphore;
 	struct radeon_ib		*ib;
 };
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 2868eda..2e56101 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -71,6 +71,7 @@ int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence)
 		return 0;
 	}
 	fence->seq = atomic_add_return(1, &rdev->fence_drv[fence->ring].seq);
+	fence->emitted_at = rdev->ring[fence->ring].wptr;
 	radeon_fence_ring_emit(rdev, fence->ring, fence);
 	trace_radeon_fence_emit(rdev->ddev, fence->seq);
 	fence->emitted = true;
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 23/24] drm/radeon: keep the cs relocs inside the ib

[j.glisse]

From: Christian König <deathsimple@vodafone.de>

Free them wenn the ib is freed, another
step to better debugging.

Signed-off-by: Christian König <deathsimple@vodafone.de>
---
 drivers/gpu/drm/radeon/radeon.h      |    3 +++
 drivers/gpu/drm/radeon/radeon_cs.c   |   14 ++++++++++++--
 drivers/gpu/drm/radeon/radeon_ring.c |    3 +++
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 6377f8c..7b2125b 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -567,6 +567,7 @@ void radeon_irq_kms_pflip_irq_put(struct radeon_device *rdev, int crtc);
 /*
  * CP & rings.
  */
+struct radeon_cs_reloc;
 
 struct radeon_ib {
 	struct radeon_sa_bo	sa_bo;
@@ -576,6 +577,8 @@ struct radeon_ib {
 	struct radeon_fence	*fence;
 	unsigned		vm_id;
 	bool			is_const_ib;
+	unsigned		nrelocs;
+	struct radeon_cs_reloc	*relocs;
 };
 
 struct radeon_ring {
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 38e1496..ecef708 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -308,7 +308,6 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 		}
 	}
 	kfree(parser->track);
-	kfree(parser->relocs);
 	kfree(parser->relocs_ptr);
 	for (i = 0; i < parser->nchunks; i++) {
 		kfree(parser->chunks[i].kdata);
@@ -317,7 +316,18 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 	}
 	kfree(parser->chunks);
 	kfree(parser->chunks_array);
-	radeon_ib_free(parser->rdev, &parser->ib);
+
+	if (parser->ib) {
+		/* keep the relocs for debugging */
+		parser->ib->nrelocs = parser->nrelocs;
+		parser->ib->relocs = parser->relocs;
+
+		/* even if we locally free it the ib stays
+		   alive until it is processed */
+		radeon_ib_free(parser->rdev, &parser->ib);
+	} else {
+		kfree(parser->relocs);
+	}
 }
 
 static int radeon_cs_ib_chunk(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index f256eae..c635aad 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -95,6 +95,8 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
 	(*ib)->gpu_addr += (*ib)->sa_bo.offset;
 	(*ib)->vm_id = 0;
 	(*ib)->is_const_ib = false;
+	(*ib)->nrelocs = 0;
+	(*ib)->relocs = NULL;
 
 	return 0;
 }
@@ -116,6 +118,7 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib)
 	if (destroy) {
 		radeon_sa_bo_free(rdev, &tmp->sa_bo);
 		radeon_fence_unref(&tmp->fence);
+		kfree(tmp->relocs);
 		kfree(tmp);
 	}
 }
-- 
1.7.7.6

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 24/24] drm/radeon: add faulty command buffer dump facilities

[j.glisse]

From: Jerome Glisse <jglisse@redhat.com>

This add a command buffer dumping facilities, that will
dump command buffer and all associated bo that most likely
triggered a lockup.

Idea is that we go through unsignaled fence and we dump the
ib of the oldest unsignaled fence. Dumping is a 2 step process
on lockup detection we try to allocate a big object that will
old all the the current state (ib pm4 packet, bo content,
relocation table). Upon reading radeon_lockup_blob debugfs
file user will get this big blob and kernel will free memory.

Kernel side try to handle as gracefully as possible failure
such as mapping bo by not dumping such bo. Userspace tools
those need to have enough logic to handle such cases.

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
---
 drivers/gpu/drm/radeon/radeon.h        |   14 ++++-
 drivers/gpu/drm/radeon/radeon_cs.c     |   20 ++++--
 drivers/gpu/drm/radeon/radeon_device.c |    3 +
 drivers/gpu/drm/radeon/radeon_fence.c  |   19 +++++
 drivers/gpu/drm/radeon/radeon_gart.c   |   10 ++-
 drivers/gpu/drm/radeon/radeon_ring.c   |  118 ++++++++++++++++++++++++++++++++
 6 files changed, 173 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 7b2125b..c9f51be 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -241,6 +241,7 @@ struct radeon_fence {
 int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring);
 int radeon_fence_driver_init(struct radeon_device *rdev);
 void radeon_fence_driver_fini(struct radeon_device *rdev);
+void radeon_fence_blob_faulty_ib(struct radeon_device *rdev, int ring);
 int radeon_fence_create(struct radeon_device *rdev, struct radeon_fence **fence, int ring);
 int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence);
 void radeon_fence_process(struct radeon_device *rdev, int ring);
@@ -569,6 +570,10 @@ void radeon_irq_kms_pflip_irq_put(struct radeon_device *rdev, int crtc);
  */
 struct radeon_cs_reloc;
 
+#define RADEON_IB_TYPE_NONE		0
+#define RADEON_IB_TYPE_CS		1
+#define RADEON_IB_TYPE_CS_VM		2
+
 struct radeon_ib {
 	struct radeon_sa_bo	sa_bo;
 	uint32_t		length_dw;
@@ -579,6 +584,7 @@ struct radeon_ib {
 	bool			is_const_ib;
 	unsigned		nrelocs;
 	struct radeon_cs_reloc	*relocs;
+	unsigned		type;
 };
 
 struct radeon_ring {
@@ -745,6 +751,7 @@ int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *cp, unsigne
 		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
 		     u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop);
 void radeon_ring_fini(struct radeon_device *rdev, struct radeon_ring *cp);
+void radeon_lockup_build_blob(struct radeon_device *rdev, struct radeon_ib *ib);
 
 
 /*
@@ -756,6 +763,7 @@ struct radeon_cs_reloc {
 	struct radeon_bo_list		lobj;
 	uint32_t			handle;
 	uint32_t			flags;
+	uint64_t			gpu_addr;
 };
 
 struct radeon_cs_chunk {
@@ -1496,6 +1504,9 @@ struct radeon_device {
 	unsigned 		debugfs_count;
 	/* virtual memory */
 	struct radeon_vm_manager	vm_manager;
+	uint32_t			*blob;
+	unsigned			blob_size_dw;
+	struct mutex			blob_mutex;
 };
 
 int radeon_device_init(struct radeon_device *rdev,
@@ -1742,7 +1753,8 @@ void radeon_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm);
 int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 			    struct radeon_vm *vm,
 			    struct radeon_bo *bo,
-			    struct ttm_mem_reg *mem);
+			    struct ttm_mem_reg *mem,
+			    uint64_t *gpu_addr);
 void radeon_vm_bo_invalidate(struct radeon_device *rdev,
 			     struct radeon_bo *bo);
 int radeon_vm_bo_add(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index ecef708..0c0bcaa 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -334,6 +334,7 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 			      struct radeon_cs_parser *parser)
 {
 	struct radeon_cs_chunk *ib_chunk;
+	unsigned i;
 	int r;
 
 	if (parser->chunk_ib_idx == -1)
@@ -369,6 +370,10 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 		DRM_ERROR("Failed to synchronize rings !\n");
 	}
 	parser->ib->vm_id = 0;
+	parser->ib->type = RADEON_IB_TYPE_CS;
+	for (i = 0; i < parser->nrelocs; ++i) {
+		parser->relocs[i].gpu_addr = parser->relocs[i].lobj.gpu_offset;
+	}
 	r = radeon_ib_schedule(rdev, parser->ib);
 	if (r) {
 		DRM_ERROR("Failed to schedule IB !\n");
@@ -379,13 +384,13 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 static int radeon_bo_vm_update_pte(struct radeon_cs_parser *parser,
 				   struct radeon_vm *vm)
 {
-	struct radeon_bo_list *lobj;
-	struct radeon_bo *bo;
-	int r;
+	unsigned i;
+
+	for (i = 0; i < parser->nrelocs; ++i) {
+		struct radeon_bo *bo = parser->relocs[i].robj;
+		int r;
 
-	list_for_each_entry(lobj, &parser->validated, tv.head) {
-		bo = lobj->bo;
-		r = radeon_vm_bo_update_pte(parser->rdev, vm, bo, &bo->tbo.mem);
+		r = radeon_vm_bo_update_pte(parser->rdev, vm, bo, &bo->tbo.mem, &parser->relocs[i].gpu_addr);
 		if (r) {
 			return r;
 		}
@@ -476,17 +481,18 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 		 * offset inside the pool bo
 		 */
 		parser->const_ib->gpu_addr = parser->const_ib->sa_bo.offset;
+		parser->ib->type = RADEON_IB_TYPE_NONE;
 		r = radeon_ib_schedule(rdev, parser->const_ib);
 		if (r)
 			goto out;
 	}
 
-	parser->ib->vm_id = vm->id;
 	/* ib pool is bind at 0 in virtual address space to gpu_addr is the
 	 * offset inside the pool bo
 	 */
 	parser->ib->gpu_addr = parser->ib->sa_bo.offset;
 	parser->ib->is_const_ib = false;
+	parser->ib->type = RADEON_IB_TYPE_CS_VM;
 	r = radeon_ib_schedule(rdev, parser->ib);
 out:
 	if (!r) {
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 5df53dd..bf327fa 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -723,6 +723,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	/* mutex initialization are all done here so we
 	 * can recall function without having locking issues */
 	mutex_init(&rdev->cs_mutex);
+	mutex_init(&rdev->blob_mutex);
 	for (i = 0; i < RADEON_NUM_RINGS; ++i)
 		mutex_init(&rdev->ring[i].mutex);
 	mutex_init(&rdev->dc_hw_i2c_mutex);
@@ -984,6 +985,8 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 	int r;
 	int resched;
 
+	radeon_fence_blob_faulty_ib(rdev, RADEON_RING_TYPE_GFX_INDEX);
+
 	radeon_save_bios_scratch_regs(rdev);
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 2e56101..16cbc65 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -405,6 +405,25 @@ bool radeon_fence_set_associated_ib(struct radeon_fence *fence, struct radeon_ib
 	return isset;
 }
 
+void radeon_fence_blob_faulty_ib(struct radeon_device *rdev, int ring)
+{
+	struct radeon_fence *fence;
+	struct list_head *i;
+	unsigned long irq_flags;
+	uint32_t seq;
+
+	write_lock_irqsave(&rdev->fence_lock, irq_flags);
+	seq = radeon_fence_read(rdev, ring);
+	list_for_each(i, &rdev->fence_drv[ring].emitted) {
+		fence = list_entry(i, struct radeon_fence, list);
+		if (fence->seq != seq && fence->ib) {
+			radeon_lockup_build_blob(rdev, fence->ib);
+			break;
+		}
+	}
+	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+}
+
 int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring)
 {
 	unsigned long irq_flags;
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index b4a4982..a491edf 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -435,7 +435,7 @@ retry_id:
 	vm->id = id;
 	list_add_tail(&vm->list, &rdev->vm_manager.lru_vm);
 	return radeon_vm_bo_update_pte(rdev, vm, rdev->sa_manager.bo,
-				       &rdev->sa_manager.bo->tbo.mem);
+				       &rdev->sa_manager.bo->tbo.mem, NULL);
 }
 
 /* object have to be reserved */
@@ -542,7 +542,8 @@ static u64 radeon_vm_get_addr(struct radeon_device *rdev,
 int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 			    struct radeon_vm *vm,
 			    struct radeon_bo *bo,
-			    struct ttm_mem_reg *mem)
+			    struct ttm_mem_reg *mem,
+			    uint64_t *gpu_addr)
 {
 	struct radeon_bo_va *bo_va;
 	unsigned ngpu_pages, i;
@@ -562,6 +563,9 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 	if (bo_va->valid)
 		return 0;
 
+	if (gpu_addr) {
+		*gpu_addr = bo_va->soffset;
+	}
 	ngpu_pages = radeon_bo_ngpu_pages(bo);
 	bo_va->flags &= ~RADEON_VM_PAGE_VALID;
 	bo_va->flags &= ~RADEON_VM_PAGE_SYSTEM;
@@ -599,7 +603,7 @@ int radeon_vm_bo_rmv(struct radeon_device *rdev,
 
 	mutex_lock(&vm->mutex);
 	mutex_lock(&rdev->cs_mutex);
-	radeon_vm_bo_update_pte(rdev, vm, bo, NULL);
+	radeon_vm_bo_update_pte(rdev, vm, bo, NULL, NULL);
 	mutex_unlock(&rdev->cs_mutex);
 	list_del(&bo_va->vm_list);
 	mutex_unlock(&vm->mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index c635aad..de93ba3 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -34,6 +34,8 @@
 #include "radeon.h"
 #include "atom.h"
 
+static int radeon_debugfs_lockup_init(struct radeon_device *rdev);
+
 /*
  * IB.
  */
@@ -116,6 +118,7 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib)
 	}
 
 	if (destroy) {
+		tmp->type = RADEON_IB_TYPE_NONE;
 		radeon_sa_bo_free(rdev, &tmp->sa_bo);
 		radeon_fence_unref(&tmp->fence);
 		kfree(tmp->relocs);
@@ -163,6 +166,9 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 
 	DRM_INFO("radeon: ib pool ready.\n");
 	rdev->ib_pool_ready = true;
+	if (radeon_debugfs_lockup_init(rdev)) {
+		DRM_ERROR("Failed to register debugfs file for lockup blob!\n");
+	}
 	return 0;
 }
 
@@ -465,3 +471,115 @@ void radeon_ring_fini(struct radeon_device *rdev, struct radeon_ring *ring)
 		radeon_bo_unref(&ring_obj);
 	}
 }
+
+#define BLOB_TYPE_GLOBAL	0
+#define BLOB_TYPE_CS		1
+#define BLOB_TYPE_RELOC		2
+#define BLOB_TYPE_BO		3
+#define BLOB_TYPE_CS_VM		4
+
+static unsigned radeon_blob_out(u32 *blob, unsigned offset,
+				unsigned type, unsigned id,
+				unsigned size, void *ptr)
+{
+	blob[offset++] = type;
+	blob[offset++] = id;
+	blob[offset++] = size;
+	if (ptr) {
+		memcpy(&blob[offset], ptr, size * 4);
+		return offset + size;
+	}
+	return offset;
+}
+
+void radeon_lockup_build_blob(struct radeon_device *rdev, struct radeon_ib *ib)
+{
+	unsigned i, size_dw, offset;
+
+	/* 3 dwords per object: cs, relocs, and one for each bo  */
+	size_dw = 6 + ib->nrelocs * 4;
+	size_dw += ib->length_dw + ib->nrelocs * 3;
+	for (i = 0; i < ib->nrelocs; ++i) {
+		struct radeon_bo *bo = ib->relocs[i].robj;
+		size_dw += (radeon_bo_size(bo) >> 2);
+	}
+	mutex_lock(&rdev->blob_mutex);
+	vfree(rdev->blob);
+	rdev->blob = vmalloc(size_dw * 4);
+	if (rdev->blob == NULL) {
+		mutex_unlock(&rdev->blob_mutex);
+		return;
+	}
+
+	rdev->blob_size_dw = size_dw;
+	offset = 0;
+	offset = radeon_blob_out(rdev->blob, offset, BLOB_TYPE_GLOBAL,
+				 0, size_dw, NULL);
+	if (RADEON_IB_TYPE_CS_VM) {
+		offset = radeon_blob_out(rdev->blob, offset, BLOB_TYPE_CS_VM,
+					 0, ib->length_dw, ib->ptr);
+	} else {
+		offset = radeon_blob_out(rdev->blob, offset, BLOB_TYPE_CS,
+					 0, ib->length_dw, ib->ptr);
+	}
+	/* dump relocation */
+	rdev->blob[offset++] = BLOB_TYPE_RELOC;
+	rdev->blob[offset++] = 0;
+	rdev->blob[offset++] = ib->nrelocs * 4;
+	for (i = 0; i < ib->nrelocs; ++i) {
+		rdev->blob[offset++] = ib->relocs[i].handle;
+		rdev->blob[offset++] = lower_32_bits(ib->relocs[i].gpu_addr);
+		rdev->blob[offset++] = upper_32_bits(ib->relocs[i].gpu_addr);
+		rdev->blob[offset++] = ib->relocs[i].flags;
+	}
+	/* dump bo */
+	for (i = 0; i < ib->nrelocs; ++i) {
+		struct radeon_bo *bo = ib->relocs[i].robj;
+		void *ptr;
+
+		if (!radeon_bo_kmap(bo, &ptr)) {
+			offset = radeon_blob_out(rdev->blob, offset, BLOB_TYPE_BO,
+						 ib->relocs[i].handle,
+						 (radeon_bo_size(bo) >> 2),
+						 ptr);
+			radeon_bo_kunmap(bo);
+		}
+	}
+	mutex_unlock(&rdev->blob_mutex);
+}
+
+
+#if defined(CONFIG_DEBUG_FS)
+static int radeon_debugfs_blob(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	int r = 0;
+
+	mutex_lock(&rdev->blob_mutex);
+	if (rdev->blob) {
+		r = seq_write(m, rdev->blob, rdev->blob_size_dw * 4);
+		vfree(rdev->blob);
+		rdev->blob = 0;
+		rdev->blob_size_dw = 0;
+	}
+	mutex_unlock(&rdev->blob_mutex);
+	return r;
+}
+
+static struct drm_info_list radeon_debugfs_ring_info_list[] = {
+	{"radeon_lockup_blob", radeon_debugfs_blob, 0, NULL},
+};
+#endif
+
+
+static int radeon_debugfs_lockup_init(struct radeon_device *rdev)
+{
+#if defined(CONFIG_DEBUG_FS)
+	return radeon_debugfs_add_files(rdev, radeon_debugfs_ring_info_list,
+					ARRAY_SIZE(radeon_debugfs_ring_info_list));
+#else
+	return 0;
+#endif
+}
-- 
1.7.7.6

Re: [PATCH 24/24] drm/radeon: add faulty command buffer dump facilities

[Luca Tettamanti]

Hi Jerome,

On Wed, Apr 25, 2012 at 9:03 PM,  <j.glisse@gmail.com> wrote:
> From: Jerome Glisse <jglisse@redhat.com>
>
> This add a command buffer dumping facilities, that will
> dump command buffer and all associated bo that most likely
> triggered a lockup.
[cut]

I spotted this:

> +void radeon_fence_blob_faulty_ib(struct radeon_device *rdev, int ring)
> +{
> +       struct radeon_fence *fence;
> +       struct list_head *i;
> +       unsigned long irq_flags;
> +       uint32_t seq;
> +
> +       write_lock_irqsave(&rdev->fence_lock, irq_flags);
> +       seq = radeon_fence_read(rdev, ring);
> +       list_for_each(i, &rdev->fence_drv[ring].emitted) {
> +               fence = list_entry(i, struct radeon_fence, list);
> +               if (fence->seq != seq && fence->ib) {
> +                       radeon_lockup_build_blob(rdev, fence->ib);

radeon_lockup_build_blob() will take a mutex and call vmalloc() inside
an atomic context.

Luca
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH 24/24] drm/radeon: add faulty command buffer dump facilities

[Jerome Glisse]

On Wed, Apr 25, 2012 at 5:53 PM, Luca Tettamanti <kronos.it@gmail.com> wrote:
> Hi Jerome,
>
> On Wed, Apr 25, 2012 at 9:03 PM,  <j.glisse@gmail.com> wrote:
>> From: Jerome Glisse <jglisse@redhat.com>
>>
>> This add a command buffer dumping facilities, that will
>> dump command buffer and all associated bo that most likely
>> triggered a lockup.
> [cut]
>
> I spotted this:
>
>> +void radeon_fence_blob_faulty_ib(struct radeon_device *rdev, int ring)
>> +{
>> +       struct radeon_fence *fence;
>> +       struct list_head *i;
>> +       unsigned long irq_flags;
>> +       uint32_t seq;
>> +
>> +       write_lock_irqsave(&rdev->fence_lock, irq_flags);
>> +       seq = radeon_fence_read(rdev, ring);
>> +       list_for_each(i, &rdev->fence_drv[ring].emitted) {
>> +               fence = list_entry(i, struct radeon_fence, list);
>> +               if (fence->seq != seq && fence->ib) {
>> +                       radeon_lockup_build_blob(rdev, fence->ib);
>
> radeon_lockup_build_blob() will take a mutex and call vmalloc() inside
> an atomic context.
>
> Luca

Yeah, you right, i only compile tested, i haven't checked if it works
ok on lockup.
Thought solution for this is easy.

Cheers,
Jerome