diff options
Diffstat (limited to 'drivers/gpu/drm/xe/xe_gt_topology.c')
| -rw-r--r-- | drivers/gpu/drm/xe/xe_gt_topology.c | 154 |
1 files changed, 146 insertions, 8 deletions
diff --git a/drivers/gpu/drm/xe/xe_gt_topology.c b/drivers/gpu/drm/xe/xe_gt_topology.c index 5dc62fe1be49..0662f71c6ede 100644 --- a/drivers/gpu/drm/xe/xe_gt_topology.c +++ b/drivers/gpu/drm/xe/xe_gt_topology.c @@ -6,14 +6,13 @@ #include "xe_gt_topology.h" #include <linux/bitmap.h> +#include <linux/compiler.h> #include "regs/xe_gt_regs.h" +#include "xe_assert.h" #include "xe_gt.h" #include "xe_mmio.h" -#define XE_MAX_DSS_FUSE_BITS (32 * XE_MAX_DSS_FUSE_REGS) -#define XE_MAX_EU_FUSE_BITS (32 * XE_MAX_EU_FUSE_REGS) - static void load_dss_mask(struct xe_gt *gt, xe_dss_mask_t mask, int numregs, ...) { @@ -33,7 +32,7 @@ load_dss_mask(struct xe_gt *gt, xe_dss_mask_t mask, int numregs, ...) } static void -load_eu_mask(struct xe_gt *gt, xe_eu_mask_t mask) +load_eu_mask(struct xe_gt *gt, xe_eu_mask_t mask, enum xe_gt_eu_type *eu_type) { struct xe_device *xe = gt_to_xe(gt); u32 reg_val = xe_mmio_read32(gt, XELP_EU_ENABLE); @@ -49,11 +48,13 @@ load_eu_mask(struct xe_gt *gt, xe_eu_mask_t mask) if (GRAPHICS_VERx100(xe) < 1250) reg_val = ~reg_val & XELP_EU_MASK; - /* On PVC, one bit = one EU */ - if (GRAPHICS_VERx100(xe) == 1260) { + if (GRAPHICS_VERx100(xe) == 1260 || GRAPHICS_VER(xe) >= 20) { + /* SIMD16 EUs, one bit == one EU */ + *eu_type = XE_GT_EU_TYPE_SIMD16; val = reg_val; } else { - /* All other platforms, one bit = 2 EU */ + /* SIMD8 EUs, one bit == 2 EU */ + *eu_type = XE_GT_EU_TYPE_SIMD8; for (i = 0; i < fls(reg_val); i++) if (reg_val & BIT(i)) val |= 0x3 << 2 * i; @@ -62,6 +63,116 @@ load_eu_mask(struct xe_gt *gt, xe_eu_mask_t mask) bitmap_from_arr32(mask, &val, XE_MAX_EU_FUSE_BITS); } +/** + * gen_l3_mask_from_pattern - Replicate a bit pattern according to a mask + * + * It is used to compute the L3 bank masks in a generic format on + * various platforms where the internal representation of L3 node + * and masks from registers are different. + * + * @xe: device + * @dst: destination + * @pattern: pattern to replicate + * @patternbits: size of the pattern, in bits + * @mask: mask describing where to replicate the pattern + * + * Example 1: + * ---------- + * @pattern = 0b1111 + * └┬─┘ + * @patternbits = 4 (bits) + * @mask = 0b0101 + * ││││ + * │││└────────────────── 0b1111 (=1×0b1111) + * ││└──────────── 0b0000 │ (=0×0b1111) + * │└────── 0b1111 │ │ (=1×0b1111) + * └ 0b0000 │ │ │ (=0×0b1111) + * │ │ │ │ + * @dst = 0b0000 0b1111 0b0000 0b1111 + * + * Example 2: + * ---------- + * @pattern = 0b11111111 + * └┬─────┘ + * @patternbits = 8 (bits) + * @mask = 0b10 + * ││ + * ││ + * ││ + * │└────────── 0b00000000 (=0×0b11111111) + * └ 0b11111111 │ (=1×0b11111111) + * │ │ + * @dst = 0b11111111 0b00000000 + */ +static void +gen_l3_mask_from_pattern(struct xe_device *xe, xe_l3_bank_mask_t dst, + xe_l3_bank_mask_t pattern, int patternbits, + unsigned long mask) +{ + unsigned long bit; + + xe_assert(xe, find_last_bit(pattern, XE_MAX_L3_BANK_MASK_BITS) < patternbits || + bitmap_empty(pattern, XE_MAX_L3_BANK_MASK_BITS)); + xe_assert(xe, !mask || patternbits * (__fls(mask) + 1) <= XE_MAX_L3_BANK_MASK_BITS); + for_each_set_bit(bit, &mask, 32) { + xe_l3_bank_mask_t shifted_pattern = {}; + + bitmap_shift_left(shifted_pattern, pattern, bit * patternbits, + XE_MAX_L3_BANK_MASK_BITS); + bitmap_or(dst, dst, shifted_pattern, XE_MAX_L3_BANK_MASK_BITS); + } +} + +static void +load_l3_bank_mask(struct xe_gt *gt, xe_l3_bank_mask_t l3_bank_mask) +{ + struct xe_device *xe = gt_to_xe(gt); + u32 fuse3 = xe_mmio_read32(gt, MIRROR_FUSE3); + + if (GRAPHICS_VER(xe) >= 20) { + xe_l3_bank_mask_t per_node = {}; + u32 meml3_en = REG_FIELD_GET(XE2_NODE_ENABLE_MASK, fuse3); + u32 bank_val = REG_FIELD_GET(XE2_GT_L3_MODE_MASK, fuse3); + + bitmap_from_arr32(per_node, &bank_val, 32); + gen_l3_mask_from_pattern(xe, l3_bank_mask, per_node, 4, + meml3_en); + } else if (GRAPHICS_VERx100(xe) >= 1270) { + xe_l3_bank_mask_t per_node = {}; + xe_l3_bank_mask_t per_mask_bit = {}; + u32 meml3_en = REG_FIELD_GET(MEML3_EN_MASK, fuse3); + u32 fuse4 = xe_mmio_read32(gt, XEHP_FUSE4); + u32 bank_val = REG_FIELD_GET(GT_L3_EXC_MASK, fuse4); + + bitmap_set_value8(per_mask_bit, 0x3, 0); + gen_l3_mask_from_pattern(xe, per_node, per_mask_bit, 2, bank_val); + gen_l3_mask_from_pattern(xe, l3_bank_mask, per_node, 4, + meml3_en); + } else if (xe->info.platform == XE_PVC) { + xe_l3_bank_mask_t per_node = {}; + xe_l3_bank_mask_t per_mask_bit = {}; + u32 meml3_en = REG_FIELD_GET(MEML3_EN_MASK, fuse3); + u32 bank_val = REG_FIELD_GET(XEHPC_GT_L3_MODE_MASK, fuse3); + + bitmap_set_value8(per_mask_bit, 0xf, 0); + gen_l3_mask_from_pattern(xe, per_node, per_mask_bit, 4, + bank_val); + gen_l3_mask_from_pattern(xe, l3_bank_mask, per_node, 16, + meml3_en); + } else if (xe->info.platform == XE_DG2) { + xe_l3_bank_mask_t per_node = {}; + u32 mask = REG_FIELD_GET(MEML3_EN_MASK, fuse3); + + bitmap_set_value8(per_node, 0xff, 0); + gen_l3_mask_from_pattern(xe, l3_bank_mask, per_node, 8, mask); + } else { + /* 1:1 register bit to mask bit (inverted register bits) */ + u32 mask = REG_FIELD_GET(XELP_GT_L3_MODE_MASK, ~fuse3); + + bitmap_from_arr32(l3_bank_mask, &mask, 32); + } +} + static void get_num_dss_regs(struct xe_device *xe, int *geometry_regs, int *compute_regs) { @@ -105,13 +216,26 @@ xe_gt_topology_init(struct xe_gt *gt) XEHP_GT_COMPUTE_DSS_ENABLE, XEHPC_GT_COMPUTE_DSS_ENABLE_EXT, XE2_GT_COMPUTE_DSS_2); - load_eu_mask(gt, gt->fuse_topo.eu_mask_per_dss); + load_eu_mask(gt, gt->fuse_topo.eu_mask_per_dss, >->fuse_topo.eu_type); + load_l3_bank_mask(gt, gt->fuse_topo.l3_bank_mask); p = drm_dbg_printer(>_to_xe(gt)->drm, DRM_UT_DRIVER, "GT topology"); xe_gt_topology_dump(gt, &p); } +static const char *eu_type_to_str(enum xe_gt_eu_type eu_type) +{ + switch (eu_type) { + case XE_GT_EU_TYPE_SIMD16: + return "simd16"; + case XE_GT_EU_TYPE_SIMD8: + return "simd8"; + } + + return NULL; +} + void xe_gt_topology_dump(struct xe_gt *gt, struct drm_printer *p) { @@ -122,7 +246,11 @@ xe_gt_topology_dump(struct xe_gt *gt, struct drm_printer *p) drm_printf(p, "EU mask per DSS: %*pb\n", XE_MAX_EU_FUSE_BITS, gt->fuse_topo.eu_mask_per_dss); + drm_printf(p, "EU type: %s\n", + eu_type_to_str(gt->fuse_topo.eu_type)); + drm_printf(p, "L3 bank mask: %*pb\n", XE_MAX_L3_BANK_MASK_BITS, + gt->fuse_topo.l3_bank_mask); } /* @@ -169,3 +297,13 @@ bool xe_gt_topology_has_dss_in_quadrant(struct xe_gt *gt, int quad) return quad_first < (quad + 1) * dss_per_quad; } + +bool xe_gt_has_geometry_dss(struct xe_gt *gt, unsigned int dss) +{ + return test_bit(dss, gt->fuse_topo.g_dss_mask); +} + +bool xe_gt_has_compute_dss(struct xe_gt *gt, unsigned int dss) +{ + return test_bit(dss, gt->fuse_topo.c_dss_mask); +} |