@@ -203,6 +203,20 @@
#define GFX_OP_DRAWRECT_INFO ((0x3<<29)|(0x1d<<24)|(0x80<<16)|(0x3))
#define GFX_OP_DRAWRECT_INFO_I965 ((0x7900<<16)|0x2)
+#define XY_CTRL_SURF_INSTR_SIZE 5
+#define MI_FLUSH_DW_SIZE 3
+#define XY_CTRL_SURF_COPY_BLT ((2 << 29) | (0x48 << 22) | 3)
+#define SRC_ACCESS_TYPE_SHIFT 21
+#define DST_ACCESS_TYPE_SHIFT 20
+#define CCS_SIZE_SHIFT 8
+#define XY_CTRL_SURF_MOCS_SHIFT 25
+#define NUM_CCS_BYTES_PER_BLOCK 256
+#define NUM_CCS_BLKS_PER_XFER 1024
+#define INDIRECT_ACCESS 0
+#define DIRECT_ACCESS 1
+#define MI_FLUSH_LLC BIT(9)
+#define MI_FLUSH_CCS BIT(16)
+
#define COLOR_BLT_CMD (2 << 29 | 0x40 << 22 | (5 - 2))
#define XY_COLOR_BLT_CMD (2 << 29 | 0x50 << 22)
#define SRC_COPY_BLT_CMD (2 << 29 | 0x43 << 22)
@@ -16,6 +16,8 @@ struct insert_pte_data {
};
#define CHUNK_SZ SZ_8M /* ~1ms at 8GiB/s preemption delay */
+#define GET_CCS_SIZE(i915, size) (HAS_FLAT_CCS(i915) ? \
+ DIV_ROUND_UP(size, NUM_CCS_BYTES_PER_BLOCK) : 0)
static bool engine_supports_migration(struct intel_engine_cs *engine)
{
@@ -594,19 +596,105 @@ intel_context_migrate_copy(struct intel_context *ce,
return err;
}
+static inline u32 *i915_flush_dw(u32 *cmd, u64 dst, u32 flags)
+{
+ /* Mask the 3 LSB to use the PPGTT address space */
+ *cmd++ = MI_FLUSH_DW | flags;
+ *cmd++ = lower_32_bits(dst);
+ *cmd++ = upper_32_bits(dst);
+
+ return cmd;
+}
+
+static u32 calc_ctrl_surf_instr_size(struct drm_i915_private *i915, int size)
+{
+ u32 num_cmds, num_blks, total_size;
+
+ if (!GET_CCS_SIZE(i915, size))
+ return 0;
+
+ /*
+ * XY_CTRL_SURF_COPY_BLT transfers CCS in 256 byte
+ * blocks. one XY_CTRL_SURF_COPY_BLT command can
+ * trnasfer upto 1024 blocks.
+ */
+ num_blks = GET_CCS_SIZE(i915, size);
+ num_cmds = (num_blks + (NUM_CCS_BLKS_PER_XFER - 1)) >> 10;
+ total_size = (XY_CTRL_SURF_INSTR_SIZE) * num_cmds;
+
+ /*
+ * We need to add a flush before and after
+ * XY_CTRL_SURF_COPY_BLT
+ */
+ total_size += 2 * MI_FLUSH_DW_SIZE;
+ return total_size;
+}
+
+static u32 *_i915_ctrl_surf_copy_blt(u32 *cmd, u64 src_addr, u64 dst_addr,
+ u8 src_mem_access, u8 dst_mem_access,
+ int src_mocs, int dst_mocs,
+ u16 num_ccs_blocks)
+{
+ int i = num_ccs_blocks;
+
+ /*
+ * The XY_CTRL_SURF_COPY_BLT instruction is used to copy the CCS
+ * data in and out of the CCS region.
+ *
+ * We can copy at most 1024 blocks of 256 bytes using one
+ * XY_CTRL_SURF_COPY_BLT instruction.
+ *
+ * In case we need to copy more than 1024 blocks, we need to add
+ * another instruction to the same batch buffer.
+ *
+ * 1024 blocks of 256 bytes of CCS represent a total 256KB of CCS.
+ *
+ * 256 KB of CCS represents 256 * 256 KB = 64 MB of LMEM.
+ */
+ do {
+ /*
+ * We use logical AND with 1023 since the size field
+ * takes values which is in the range of 0 - 1023
+ */
+ *cmd++ = ((XY_CTRL_SURF_COPY_BLT) |
+ (src_mem_access << SRC_ACCESS_TYPE_SHIFT) |
+ (dst_mem_access << DST_ACCESS_TYPE_SHIFT) |
+ (((i - 1) & 1023) << CCS_SIZE_SHIFT));
+ *cmd++ = lower_32_bits(src_addr);
+ *cmd++ = ((upper_32_bits(src_addr) & 0xFFFF) |
+ (src_mocs << XY_CTRL_SURF_MOCS_SHIFT));
+ *cmd++ = lower_32_bits(dst_addr);
+ *cmd++ = ((upper_32_bits(dst_addr) & 0xFFFF) |
+ (dst_mocs << XY_CTRL_SURF_MOCS_SHIFT));
+ src_addr += SZ_64M;
+ dst_addr += SZ_64M;
+ i -= NUM_CCS_BLKS_PER_XFER;
+ } while (i > 0);
+
+ return cmd;
+}
+
static int emit_clear(struct i915_request *rq,
u64 offset,
int size,
- u32 value)
+ u32 value,
+ bool is_lmem)
{
+ struct drm_i915_private *i915 = rq->engine->i915;
const int ver = GRAPHICS_VER(rq->engine->i915);
+ u32 num_ccs_blks, ccs_ring_size;
u32 *cs;
GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
offset += (u64)rq->engine->instance << 32;
- cs = intel_ring_begin(rq, ver >= 8 ? 8 : 6);
+ /* Clear flat css only when value is 0 */
+ ccs_ring_size = (is_lmem && !value) ?
+ calc_ctrl_surf_instr_size(i915, size)
+ : 0;
+
+ cs = intel_ring_begin(rq, round_up(ver >= 8 ? 8 + ccs_ring_size : 6, 2));
if (IS_ERR(cs))
return PTR_ERR(cs);
@@ -629,6 +717,26 @@ static int emit_clear(struct i915_request *rq,
*cs++ = value;
}
+ if (is_lmem && HAS_FLAT_CCS(i915) && !value) {
+ num_ccs_blks = GET_CCS_SIZE(i915, size);
+
+ /*
+ * Flat CCS surface can only be accessed via
+ * XY_CTRL_SURF_COPY_BLT CMD and using indirect
+ * mapping of associated LMEM.
+ * We can clear ccs surface by writing all 0s,
+ * so we will flush the previously cleared buffer
+ * and use it as a source.
+ */
+ cs = i915_flush_dw(cs, offset, MI_FLUSH_LLC | MI_FLUSH_CCS);
+ cs = _i915_ctrl_surf_copy_blt(cs, offset, offset,
+ DIRECT_ACCESS, INDIRECT_ACCESS,
+ 1, 1, num_ccs_blks);
+ cs = i915_flush_dw(cs, offset, MI_FLUSH_LLC | MI_FLUSH_CCS);
+
+ if (ccs_ring_size & 1)
+ *cs++ = MI_NOOP;
+ }
intel_ring_advance(rq, cs);
return 0;
}
@@ -694,7 +802,7 @@ intel_context_migrate_clear(struct intel_context *ce,
if (err)
goto out_rq;
- err = emit_clear(rq, offset, len, value);
+ err = emit_clear(rq, offset, len, value, is_lmem);
/* Arbitration is re-enabled between requests. */
out_rq: