<!DOCTYPE html><html><head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<p><br>
</p>
<div class="moz-cite-prefix">On 23-04-2024 21:35, José Roberto de
Souza wrote:<br>
</div>
<blockquote type="cite" cite="mid:20240423160626.77110-3-jose.souza@intel.com">
<pre class="moz-quote-pre" wrap="">This registers contains important information that can help with debug
of GPU hangs.
While at it also fixing the double line jump at the end of engine
registers for CCS engines.
v2:
- print other INSTDONE registers
v3:
- add for_each_geometry/compute_dss()
v4:
- print one slice_common_instdone per glice in DG2+
v5:
- rename registers prefix from DG2 to XEHPG (Zhanjun)
Cc: Rodrigo Vivi <a class="moz-txt-link-rfc2396E" href="mailto:rodrigo.vivi@intel.com"><rodrigo.vivi@intel.com></a>
Cc: Matt Roper <a class="moz-txt-link-rfc2396E" href="mailto:matthew.d.roper@intel.com"><matthew.d.roper@intel.com></a>
Cc: Zhanjun Dong <a class="moz-txt-link-rfc2396E" href="mailto:zhanjun.dong@intel.com"><zhanjun.dong@intel.com></a>
Reviewed-by: Rodrigo Vivi <a class="moz-txt-link-rfc2396E" href="mailto:rodrigo.vivi@intel.com"><rodrigo.vivi@intel.com></a>
Signed-off-by: José Roberto de Souza <a class="moz-txt-link-rfc2396E" href="mailto:jose.souza@intel.com"><jose.souza@intel.com></a>
---
drivers/gpu/drm/xe/regs/xe_engine_regs.h | 1 +
drivers/gpu/drm/xe/regs/xe_gt_regs.h | 13 +++
drivers/gpu/drm/xe/xe_hw_engine.c | 128 +++++++++++++++++++++++
drivers/gpu/drm/xe/xe_hw_engine_types.h | 16 +++
4 files changed, 158 insertions(+)
diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index af71b87d80301..97d2aed63e01c 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -65,6 +65,7 @@
#define RING_ACTHD_UDW(base) XE_REG((base) + 0x5c)
#define RING_DMA_FADD_UDW(base) XE_REG((base) + 0x60)
#define RING_IPEHR(base) XE_REG((base) + 0x68)
+#define RING_INSTDONE(base) XE_REG((base) + 0x6c)
#define RING_ACTHD(base) XE_REG((base) + 0x74)
#define RING_DMA_FADD(base) XE_REG((base) + 0x78)
#define RING_HWS_PGA(base) XE_REG((base) + 0x80)
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index 94445810ccc93..c7fbea46bb75e 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -98,6 +98,8 @@
#define FF_MODE2_TDS_TIMER_MASK REG_GENMASK(23, 16)
#define FF_MODE2_TDS_TIMER_128 REG_FIELD_PREP(FF_MODE2_TDS_TIMER_MASK, 4)
+#define XEHPG_INSTDONE_GEOM_SVGUNIT XE_REG_MCR(0x666c)
+
#define CACHE_MODE_1 XE_REG(0x7004, XE_REG_OPTION_MASKED)
#define MSAA_OPTIMIZATION_REDUC_DISABLE REG_BIT(11)
@@ -115,6 +117,14 @@
#define FLSH_IGNORES_PSD REG_BIT(10)
#define FD_END_COLLECT REG_BIT(5)
+#define SC_INSTDONE XE_REG(0x7100)
+#define SC_INSTDONE_EXTRA XE_REG(0x7104)
+#define SC_INSTDONE_EXTRA2 XE_REG(0x7108)
+
+#define XEHPG_SC_INSTDONE XE_REG_MCR(0x7100)
+#define XEHPG_SC_INSTDONE_EXTRA XE_REG_MCR(0x7104)
+#define XEHPG_SC_INSTDONE_EXTRA2 XE_REG_MCR(0x7108)
+
#define COMMON_SLICE_CHICKEN4 XE_REG(0x7300, XE_REG_OPTION_MASKED)
#define DISABLE_TDC_LOAD_BALANCING_CALC REG_BIT(6)
@@ -342,6 +352,9 @@
#define HALF_SLICE_CHICKEN5 XE_REG_MCR(0xe188, XE_REG_OPTION_MASKED)
#define DISABLE_SAMPLE_G_PERFORMANCE REG_BIT(0)
+#define SAMPLER_INSTDONE XE_REG_MCR(0xe160)
+#define ROW_INSTDONE XE_REG_MCR(0xe164)
+
#define SAMPLER_MODE XE_REG_MCR(0xe18c, XE_REG_OPTION_MASKED)
#define ENABLE_SMALLPL REG_BIT(15)
#define SC_DISABLE_POWER_OPTIMIZATION_EBB REG_BIT(9)
diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
index c84dbe8a8ed1d..5d4a8f7b903e4 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine.c
@@ -18,6 +18,7 @@
#include "xe_gt.h"
#include "xe_gt_ccs_mode.h"
#include "xe_gt_printk.h"
+#include "xe_gt_mcr.h"
#include "xe_gt_topology.h"
#include "xe_hw_fence.h"
#include "xe_irq.h"
@@ -766,6 +767,57 @@ void xe_hw_engine_handle_irq(struct xe_hw_engine *hwe, u16 intr_vec)
xe_hw_fence_irq_run(hwe->fence_irq);
}
+static bool
+is_slice_common_per_gslice(struct xe_device *xe)
+{
+ return GRAPHICS_VERx100(xe) >= 1255;
+}
+
+static void
+xe_he_engine_snapshot_instdone_capture(struct xe_hw_engine *hwe,
+ struct xe_hw_engine_snapshot *snapshot)</pre>
</blockquote>
<p>Nit: <br>
</p>
<p><span style="white-space: pre-wrap">s/xe_he_engine_snapshot_instdone_capture/xe_hw_engine_snapshot_instdone_capture</span></p>
<p><span style="white-space: pre-wrap">Doesn't make much difference since functions are static but to keep consistency in *_capture and *_print functions.
</span></p>
<p><br>
</p>
<blockquote type="cite" cite="mid:20240423160626.77110-3-jose.souza@intel.com">
<pre class="moz-quote-pre" wrap="">
+{
+ struct xe_gt *gt = hwe->gt;
+ struct xe_device *xe = gt_to_xe(gt);
+ unsigned int dss;
+ u16 group, instance;
+
+ snapshot->reg.instdone.ring = hw_engine_mmio_read32(hwe, RING_INSTDONE(0));
+
+ if (snapshot->hwe->class != XE_ENGINE_CLASS_RENDER)
+ return;
+
+ if (is_slice_common_per_gslice(xe) == false) {
+ snapshot->reg.instdone.slice_common[0] =
+ xe_mmio_read32(gt, SC_INSTDONE);
+ snapshot->reg.instdone.slice_common_extra[0] =
+ xe_mmio_read32(gt, SC_INSTDONE_EXTRA);
+ snapshot->reg.instdone.slice_common_extra2[0] =
+ xe_mmio_read32(gt, SC_INSTDONE_EXTRA2);
+ } else {
+ for_each_geometry_dss(dss, gt, group, instance) {
+ snapshot->reg.instdone.slice_common[dss] =
+ xe_gt_mcr_unicast_read(gt, XEHPG_SC_INSTDONE, group, instance);
+ snapshot->reg.instdone.slice_common_extra[dss] =
+ xe_gt_mcr_unicast_read(gt, XEHPG_SC_INSTDONE_EXTRA, group, instance);
+ snapshot->reg.instdone.slice_common_extra2[dss] =
+ xe_gt_mcr_unicast_read(gt, XEHPG_SC_INSTDONE_EXTRA2, group, instance);
+ }
+ }
+
+ for_each_geometry_dss(dss, gt, group, instance) {
+ snapshot->reg.instdone.sampler[dss] =
+ xe_gt_mcr_unicast_read(gt, SAMPLER_INSTDONE, group, instance);
+ snapshot->reg.instdone.row[dss] =
+ xe_gt_mcr_unicast_read(gt, ROW_INSTDONE, group, instance);
+
+ if (GRAPHICS_VERx100(xe) >= 1255)
+ snapshot->reg.instdone.geom_svg[dss] =
+ xe_gt_mcr_unicast_read(gt, XEHPG_INSTDONE_GEOM_SVGUNIT,
+ group, instance);
+ }
+}
+
/**
* xe_hw_engine_snapshot_capture - Take a quick snapshot of the HW Engine.
* @hwe: Xe HW Engine.
@@ -780,6 +832,7 @@ struct xe_hw_engine_snapshot *
xe_hw_engine_snapshot_capture(struct xe_hw_engine *hwe)
{
struct xe_hw_engine_snapshot *snapshot;
+ size_t len;
u64 val;
if (!xe_hw_engine_is_valid(hwe))
@@ -790,6 +843,28 @@ xe_hw_engine_snapshot_capture(struct xe_hw_engine *hwe)
if (!snapshot)
return NULL;
+ /* Because XE_MAX_DSS_FUSE_BITS is defined in xe_gt_types.h and it
+ * includes xe_hw_engine_types.h the length of this 3 registers can't be
+ * set in struct xe_hw_engine_snapshot, so here doing additional
+ * allocations.
+ */
+ len = (XE_MAX_DSS_FUSE_BITS * sizeof(u32));
+ snapshot->reg.instdone.slice_common = kzalloc(len, GFP_ATOMIC);
+ snapshot->reg.instdone.slice_common_extra = kzalloc(len, GFP_ATOMIC);
+ snapshot->reg.instdone.slice_common_extra2 = kzalloc(len, GFP_ATOMIC);
+ snapshot->reg.instdone.sampler = kzalloc(len, GFP_ATOMIC);
+ snapshot->reg.instdone.row = kzalloc(len, GFP_ATOMIC);
+ snapshot->reg.instdone.geom_svg = kzalloc(len, GFP_ATOMIC);
+ if (!snapshot->reg.instdone.slice_common ||
+ !snapshot->reg.instdone.slice_common_extra ||
+ !snapshot->reg.instdone.slice_common_extra2 ||
+ !snapshot->reg.instdone.sampler ||
+ !snapshot->reg.instdone.row ||
+ !snapshot->reg.instdone.geom_svg) {
+ xe_hw_engine_snapshot_free(snapshot);
+ return NULL;
+ }
+
snapshot->name = kstrdup(hwe->name, GFP_ATOMIC);
snapshot->hwe = hwe;
snapshot->logical_instance = hwe->logical_instance;
@@ -841,6 +916,7 @@ xe_hw_engine_snapshot_capture(struct xe_hw_engine *hwe)
snapshot->reg.ring_emr = hw_engine_mmio_read32(hwe, RING_EMR(0));
snapshot->reg.ring_eir = hw_engine_mmio_read32(hwe, RING_EIR(0));
snapshot->reg.ipehr = hw_engine_mmio_read32(hwe, RING_IPEHR(0));
+ xe_he_engine_snapshot_instdone_capture(hwe, snapshot);
if (snapshot->hwe->class == XE_ENGINE_CLASS_COMPUTE)
snapshot->reg.rcu_mode = xe_mmio_read32(hwe->gt, RCU_MODE);
@@ -848,6 +924,49 @@ xe_hw_engine_snapshot_capture(struct xe_hw_engine *hwe)
return snapshot;
}
+static void
+xe_hw_engine_snapshot_instdone_print(struct xe_hw_engine_snapshot *snapshot, struct drm_printer *p)
+{
+ struct xe_gt *gt = snapshot->hwe->gt;
+ struct xe_device *xe = gt_to_xe(gt);
+ u16 group, instance;
+ unsigned int dss;
+
+ drm_printf(p, "\tRING_INSTDONE: 0x%08x\n", snapshot->reg.instdone.ring);
+
+ if (snapshot->hwe->class != XE_ENGINE_CLASS_RENDER)
+ return;
+
+ if (is_slice_common_per_gslice(xe) == false) {
+ drm_printf(p, "\tSC_INSTDONE[0]: 0x%08x\n",
+ snapshot->reg.instdone.slice_common[0]);
+ drm_printf(p, "\tSC_INSTDONE_EXTRA[0]: 0x%08x\n",
+ snapshot->reg.instdone.slice_common_extra[0]);
+ drm_printf(p, "\tSC_INSTDONE_EXTRA2[0]: 0x%08x\n",
+ snapshot->reg.instdone.slice_common_extra2[0]);
+ } else {
+ for_each_geometry_dss(dss, gt, group, instance) {
+ drm_printf(p, "\tSC_INSTDONE[%u]: 0x%08x\n", dss,
+ snapshot->reg.instdone.slice_common[dss]);
+ drm_printf(p, "\tSC_INSTDONE_EXTRA[%u]: 0x%08x\n", dss,
+ snapshot->reg.instdone.slice_common_extra[dss]);
+ drm_printf(p, "\tSC_INSTDONE_EXTRA2[%u]: 0x%08x\n", dss,
+ snapshot->reg.instdone.slice_common_extra2[dss]);
+ }
+ }
+
+ for_each_geometry_dss(dss, gt, group, instance) {
+ drm_printf(p, "\tSAMPLER_INSTDONE[%u]: 0x%08x\n", dss,
+ snapshot->reg.instdone.sampler[dss]);
+ drm_printf(p, "\tROW_INSTDONE[%u]: 0x%08x\n", dss,
+ snapshot->reg.instdone.row[dss]);
+
+ if (GRAPHICS_VERx100(xe) >= 1255)
+ drm_printf(p, "\tINSTDONE_GEOM_SVGUNIT[%u]: 0x%08x\n",
+ dss, snapshot->reg.instdone.geom_svg[dss]);
+ }
+}
+
/**
* xe_hw_engine_snapshot_print - Print out a given Xe HW Engine snapshot.
* @snapshot: Xe HW Engine snapshot object.
@@ -887,9 +1006,12 @@ void xe_hw_engine_snapshot_print(struct xe_hw_engine_snapshot *snapshot,
drm_printf(p, "\tBBADDR: 0x%016llx\n", snapshot->reg.ring_bbaddr);
drm_printf(p, "\tDMA_FADDR: 0x%016llx\n", snapshot->reg.ring_dma_fadd);
drm_printf(p, "\tIPEHR: 0x%08x\n", snapshot->reg.ipehr);
+ xe_hw_engine_snapshot_instdone_print(snapshot, p);
+
if (snapshot->hwe->class == XE_ENGINE_CLASS_COMPUTE)
drm_printf(p, "\tRCU_MODE: 0x%08x\n",
snapshot->reg.rcu_mode);
+ drm_puts(p, "\n");
}
/**
@@ -904,6 +1026,12 @@ void xe_hw_engine_snapshot_free(struct xe_hw_engine_snapshot *snapshot)
if (!snapshot)
return;
+ kfree(snapshot->reg.instdone.slice_common);
+ kfree(snapshot->reg.instdone.slice_common_extra);
+ kfree(snapshot->reg.instdone.slice_common_extra2);
+ kfree(snapshot->reg.instdone.sampler);
+ kfree(snapshot->reg.instdone.row);
+ kfree(snapshot->reg.instdone.geom_svg);
kfree(snapshot->name);
kfree(snapshot);
}
diff --git a/drivers/gpu/drm/xe/xe_hw_engine_types.h b/drivers/gpu/drm/xe/xe_hw_engine_types.h
index 27deaa31efd31..9f9755e31b9fe 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_types.h
+++ b/drivers/gpu/drm/xe/xe_hw_engine_types.h
@@ -211,6 +211,22 @@ struct xe_hw_engine_snapshot {
u32 ipehr;
/** @reg.rcu_mode: RCU_MODE */
u32 rcu_mode;
+ struct {
+ /** @reg.instdone.ring: RING_INSTDONE */
+ u32 ring;
+ /** @reg.instdone.slice_common: SC_INSTDONE */
+ u32 *slice_common;
+ /** @reg.instdone.slice_common_extra: SC_INSTDONE_EXTRA */
+ u32 *slice_common_extra;
+ /** @reg.instdone.slice_common_extra2: SC_INSTDONE_EXTRA2 */
+ u32 *slice_common_extra2;
+ /** @reg.instdone.sampler: SAMPLER_INSTDONE */
+ u32 *sampler;
+ /** @reg.instdone.row: ROW_INSTDONE */
+ u32 *row;
+ /** @reg.instdone.geom_svg: INSTDONE_GEOM_SVGUNIT */
+ u32 *geom_svg;
+ } instdone;
} reg;
};
</pre>
</blockquote>
</body>
</html>