[Intel-gfx] [PATCH v4 6/6] drm/i915/gen8: Add WaRsRestoreWithPerCtxtBb workaround

[Arun Siluvery]

In Per context w/a batch buffer,
WaRsRestoreWithPerCtxtBb

v2: This patches modifies definitions of MI_LOAD_REGISTER_MEM and
MI_LOAD_REGISTER_REG; Add GEN8 specific defines for these instructions
so as to not break any future users of existing definitions (Michel)

v3: Length defined in current definitions of LRM, LRR instructions is not correct.
Correct and use existing definitions and also move them out of command parser
placeholder to appropriate place.
remove unnecessary padding and follow the WA programming sequence exactly
as mentioned in spec (Dave).

Signed-off-by: Rafael Barbalho <rafael.barbalho at intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_reg.h  | 29 +++++++++++++++++++--
 drivers/gpu/drm/i915/intel_lrc.c | 56 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 83 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 7637e64..208620d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -347,6 +347,31 @@
 #define   MI_INVALIDATE_BSD		(1<<7)
 #define   MI_FLUSH_DW_USE_GTT		(1<<2)
 #define   MI_FLUSH_DW_USE_PPGTT		(0<<2)
+#define MI_LOAD_REGISTER_MEM    MI_INSTR(0x29, 1)
+#define MI_LOAD_REGISTER_MEM_GEN8 MI_INSTR(0x29, 2)
+#define   MI_LRM_USE_GLOBAL_GTT (1<<22)
+#define   MI_LRM_ASYNC_MODE_ENABLE (1<<21)
+#define MI_LOAD_REGISTER_REG    MI_INSTR(0x2A, 1)
+#define MI_ATOMIC(len)	MI_INSTR(0x2F, (len-2))
+#define   MI_ATOMIC_MEMORY_TYPE_GGTT	(1<<22)
+#define   MI_ATOMIC_INLINE_DATA		(1<<18)
+#define   MI_ATOMIC_CS_STALL		(1<<17)
+#define   MI_ATOMIC_RETURN_DATA_CTL	(1<<16)
+#define MI_ATOMIC_OP_MASK(op)  ((op) << 8)
+#define MI_ATOMIC_AND	MI_ATOMIC_OP_MASK(0x01)
+#define MI_ATOMIC_OR	MI_ATOMIC_OP_MASK(0x02)
+#define MI_ATOMIC_XOR	MI_ATOMIC_OP_MASK(0x03)
+#define MI_ATOMIC_MOVE	MI_ATOMIC_OP_MASK(0x04)
+#define MI_ATOMIC_INC	MI_ATOMIC_OP_MASK(0x05)
+#define MI_ATOMIC_DEC	MI_ATOMIC_OP_MASK(0x06)
+#define MI_ATOMIC_ADD	MI_ATOMIC_OP_MASK(0x07)
+#define MI_ATOMIC_SUB	MI_ATOMIC_OP_MASK(0x08)
+#define MI_ATOMIC_RSUB	MI_ATOMIC_OP_MASK(0x09)
+#define MI_ATOMIC_IMAX	MI_ATOMIC_OP_MASK(0x0A)
+#define MI_ATOMIC_IMIN	MI_ATOMIC_OP_MASK(0x0B)
+#define MI_ATOMIC_UMAX	MI_ATOMIC_OP_MASK(0x0C)
+#define MI_ATOMIC_UMIN	MI_ATOMIC_OP_MASK(0x0D)
+
 #define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
 #define   MI_BATCH_NON_SECURE		(1)
 /* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
@@ -451,8 +476,6 @@
 #define MI_CLFLUSH              MI_INSTR(0x27, 0)
 #define MI_REPORT_PERF_COUNT    MI_INSTR(0x28, 0)
 #define   MI_REPORT_PERF_COUNT_GGTT (1<<0)
-#define MI_LOAD_REGISTER_MEM    MI_INSTR(0x29, 0)
-#define MI_LOAD_REGISTER_REG    MI_INSTR(0x2A, 0)
 #define MI_RS_STORE_DATA_IMM    MI_INSTR(0x2B, 0)
 #define MI_LOAD_URB_MEM         MI_INSTR(0x2C, 0)
 #define MI_STORE_URB_MEM        MI_INSTR(0x2D, 0)
@@ -1799,6 +1822,8 @@ enum skl_disp_power_wells {
 #define   GEN8_RC_SEMA_IDLE_MSG_DISABLE	(1 << 12)
 #define   GEN8_FF_DOP_CLOCK_GATE_DISABLE	(1<<10)
 
+#define GEN8_RS_PREEMPT_STATUS		0x215C
+
 /* Fuse readout registers for GT */
 #define CHV_FUSE_GT			(VLV_DISPLAY_BASE + 0x2168)
 #define   CHV_FGT_DISABLE_SS0		(1 << 10)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 27e6692..ebaba27 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1163,15 +1163,71 @@ static int gen8_init_perctx_bb(struct intel_engine_cs *ring,
 	uint32_t index;
 	struct page *page;
 	uint32_t *cmd;
+	u32 scratch_addr;
+	unsigned long flags = 0;
 
 	page = i915_gem_object_get_page(ring->wa_ctx.obj, 0);
 	cmd = kmap_atomic(page);
 
 	index = offset;
 
+	/* Actual scratch location is at 128 bytes offset */
+	scratch_addr = ring->scratch.gtt_offset + 2*CACHELINE_BYTES;
+	scratch_addr |= PIPE_CONTROL_GLOBAL_GTT;
+
 	/* WaDisableCtxRestoreArbitration:bdw,chv */
 	cmd[index++] = MI_ARB_ON_OFF | MI_ARB_ENABLE;
 
+	/*
+	 * As per Bspec, to workaround a known HW issue, SW must perform the
+	 * below programming sequence prior to programming MI_BATCH_BUFFER_END.
+	 *
+	 * This is only applicable for Gen8.
+	 */
+
+	/* WaRsRestoreWithPerCtxtBb:bdw,chv */
+	cmd[index++] = MI_LOAD_REGISTER_IMM(1);
+	cmd[index++] = INSTPM;
+	cmd[index++] = _MASKED_BIT_DISABLE(INSTPM_FORCE_ORDERING);
+
+	flags = MI_ATOMIC_MEMORY_TYPE_GGTT |
+		MI_ATOMIC_INLINE_DATA |
+		MI_ATOMIC_CS_STALL |
+		MI_ATOMIC_RETURN_DATA_CTL |
+		MI_ATOMIC_MOVE;
+
+	cmd[index++] = MI_ATOMIC(5) | flags;
+	cmd[index++] = scratch_addr;
+	cmd[index++] = 0;
+	cmd[index++] = _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING);
+	cmd[index++] = _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING);
+
+	/*
+	 * BSpec says MI_LOAD_REGISTER_MEM, MI_LOAD_REGISTER_REG and
+	 * MI_BATCH_BUFFER_END instructions in this sequence need to be
+	 * in the same cacheline. To satisfy this case even if more WA are
+	 * added in future, pad current cacheline and start remaining sequence
+	 * in new cacheline.
+	 */
+	while (((unsigned long) (cmd + index) % CACHELINE_BYTES) != 0)
+		cmd[index++] = MI_NOOP;
+
+	cmd[index++] = MI_LOAD_REGISTER_MEM_GEN8 |
+		MI_LRM_USE_GLOBAL_GTT |
+		MI_LRM_ASYNC_MODE_ENABLE;
+	cmd[index++] = INSTPM;
+	cmd[index++] = scratch_addr;
+	cmd[index++] = 0;
+
+	/*
+	 * BSpec says there should not be any commands programmed
+	 * between MI_LOAD_REGISTER_REG and MI_BATCH_BUFFER_END so
+	 * do not add any new commands
+	 */
+	cmd[index++] = MI_LOAD_REGISTER_REG;
+	cmd[index++] = GEN8_RS_PREEMPT_STATUS;
+	cmd[index++] = GEN8_RS_PREEMPT_STATUS;
+
 	cmd[index++] = MI_BATCH_BUFFER_END;
 
 	kunmap_atomic(cmd);
-- 
2.3.0