diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_rps.c')
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_rps.c | 265 |
1 files changed, 252 insertions, 13 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 6b86250c31ab..6c34a83c24b3 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -625,9 +625,7 @@ static void gen5_rps_disable(struct intel_rps *rps) rgvswctl = intel_uncore_read16(uncore, MEMSWCTL); /* Ack interrupts, disable EFC interrupt */ - intel_uncore_write(uncore, MEMINTREN, - intel_uncore_read(uncore, MEMINTREN) & - ~MEMINT_EVAL_CHG_EN); + intel_uncore_rmw(uncore, MEMINTREN, MEMINT_EVAL_CHG_EN, 0); intel_uncore_write(uncore, MEMINTRSTS, MEMINT_EVAL_CHG); /* Go back to the starting frequency */ @@ -1016,9 +1014,15 @@ void intel_rps_boost(struct i915_request *rq) if (rps_uses_slpc(rps)) { slpc = rps_to_slpc(rps); + if (slpc->min_freq_softlimit >= slpc->boost_freq) + return; + /* Return if old value is non zero */ - if (!atomic_fetch_inc(&slpc->num_waiters)) + if (!atomic_fetch_inc(&slpc->num_waiters)) { + GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n", + rq->fence.context, rq->fence.seqno); schedule_work(&slpc->boost_work); + } return; } @@ -1085,15 +1089,25 @@ static u32 intel_rps_read_state_cap(struct intel_rps *rps) return intel_uncore_read(uncore, GEN6_RP_STATE_CAP); } -/** - * gen6_rps_get_freq_caps - Get freq caps exposed by HW - * @rps: the intel_rps structure - * @caps: returned freq caps - * - * Returned "caps" frequencies should be converted to MHz using - * intel_gpu_freq() - */ -void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps) +static void +mtl_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps) +{ + struct intel_uncore *uncore = rps_to_uncore(rps); + u32 rp_state_cap = rps_to_gt(rps)->type == GT_MEDIA ? + intel_uncore_read(uncore, MTL_MEDIAP_STATE_CAP) : + intel_uncore_read(uncore, MTL_RP_STATE_CAP); + u32 rpe = rps_to_gt(rps)->type == GT_MEDIA ? + intel_uncore_read(uncore, MTL_MPE_FREQUENCY) : + intel_uncore_read(uncore, MTL_GT_RPE_FREQUENCY); + + /* MTL values are in units of 16.67 MHz */ + caps->rp0_freq = REG_FIELD_GET(MTL_RP0_CAP_MASK, rp_state_cap); + caps->min_freq = REG_FIELD_GET(MTL_RPN_CAP_MASK, rp_state_cap); + caps->rp1_freq = REG_FIELD_GET(MTL_RPE_MASK, rpe); +} + +static void +__gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps) { struct drm_i915_private *i915 = rps_to_i915(rps); u32 rp_state_cap; @@ -1128,6 +1142,24 @@ void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *c } } +/** + * gen6_rps_get_freq_caps - Get freq caps exposed by HW + * @rps: the intel_rps structure + * @caps: returned freq caps + * + * Returned "caps" frequencies should be converted to MHz using + * intel_gpu_freq() + */ +void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps) +{ + struct drm_i915_private *i915 = rps_to_i915(rps); + + if (IS_METEORLAKE(i915)) + return mtl_get_freq_caps(rps, caps); + else + return __gen6_rps_get_freq_caps(rps, caps); +} + static void gen6_rps_init(struct intel_rps *rps) { struct drm_i915_private *i915 = rps_to_i915(rps); @@ -2191,6 +2223,213 @@ u32 intel_rps_get_rpn_frequency(struct intel_rps *rps) return intel_gpu_freq(rps, rps->min_freq); } +static void rps_frequency_dump(struct intel_rps *rps, struct drm_printer *p) +{ + struct intel_gt *gt = rps_to_gt(rps); + struct drm_i915_private *i915 = gt->i915; + struct intel_uncore *uncore = gt->uncore; + struct intel_rps_freq_caps caps; + u32 rp_state_limits; + u32 gt_perf_status; + u32 rpmodectl, rpinclimit, rpdeclimit; + u32 rpstat, cagf, reqf; + u32 rpcurupei, rpcurup, rpprevup; + u32 rpcurdownei, rpcurdown, rpprevdown; + u32 rpupei, rpupt, rpdownei, rpdownt; + u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask; + + rp_state_limits = intel_uncore_read(uncore, GEN6_RP_STATE_LIMITS); + gen6_rps_get_freq_caps(rps, &caps); + if (IS_GEN9_LP(i915)) + gt_perf_status = intel_uncore_read(uncore, BXT_GT_PERF_STATUS); + else + gt_perf_status = intel_uncore_read(uncore, GEN6_GT_PERF_STATUS); + + /* RPSTAT1 is in the GT power well */ + intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL); + + reqf = intel_uncore_read(uncore, GEN6_RPNSWREQ); + if (GRAPHICS_VER(i915) >= 9) { + reqf >>= 23; + } else { + reqf &= ~GEN6_TURBO_DISABLE; + if (IS_HASWELL(i915) || IS_BROADWELL(i915)) + reqf >>= 24; + else + reqf >>= 25; + } + reqf = intel_gpu_freq(rps, reqf); + + rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL); + rpinclimit = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD); + rpdeclimit = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD); + + rpstat = intel_uncore_read(uncore, GEN6_RPSTAT1); + rpcurupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK; + rpcurup = intel_uncore_read(uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK; + rpprevup = intel_uncore_read(uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK; + rpcurdownei = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK; + rpcurdown = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK; + rpprevdown = intel_uncore_read(uncore, GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK; + + rpupei = intel_uncore_read(uncore, GEN6_RP_UP_EI); + rpupt = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD); + + rpdownei = intel_uncore_read(uncore, GEN6_RP_DOWN_EI); + rpdownt = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD); + + cagf = intel_rps_read_actual_frequency(rps); + + intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL); + + if (GRAPHICS_VER(i915) >= 11) { + pm_ier = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE); + pm_imr = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK); + /* + * The equivalent to the PM ISR & IIR cannot be read + * without affecting the current state of the system + */ + pm_isr = 0; + pm_iir = 0; + } else if (GRAPHICS_VER(i915) >= 8) { + pm_ier = intel_uncore_read(uncore, GEN8_GT_IER(2)); + pm_imr = intel_uncore_read(uncore, GEN8_GT_IMR(2)); + pm_isr = intel_uncore_read(uncore, GEN8_GT_ISR(2)); + pm_iir = intel_uncore_read(uncore, GEN8_GT_IIR(2)); + } else { + pm_ier = intel_uncore_read(uncore, GEN6_PMIER); + pm_imr = intel_uncore_read(uncore, GEN6_PMIMR); + pm_isr = intel_uncore_read(uncore, GEN6_PMISR); + pm_iir = intel_uncore_read(uncore, GEN6_PMIIR); + } + pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK); + + drm_printf(p, "Video Turbo Mode: %s\n", + str_yes_no(rpmodectl & GEN6_RP_MEDIA_TURBO)); + drm_printf(p, "HW control enabled: %s\n", + str_yes_no(rpmodectl & GEN6_RP_ENABLE)); + drm_printf(p, "SW control enabled: %s\n", + str_yes_no((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == GEN6_RP_MEDIA_SW_MODE)); + + drm_printf(p, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n", + pm_ier, pm_imr, pm_mask); + if (GRAPHICS_VER(i915) <= 10) + drm_printf(p, "PM ISR=0x%08x IIR=0x%08x\n", + pm_isr, pm_iir); + drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n", + rps->pm_intrmsk_mbz); + drm_printf(p, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); + drm_printf(p, "Render p-state ratio: %d\n", + (gt_perf_status & (GRAPHICS_VER(i915) >= 9 ? 0x1ff00 : 0xff00)) >> 8); + drm_printf(p, "Render p-state VID: %d\n", + gt_perf_status & 0xff); + drm_printf(p, "Render p-state limit: %d\n", + rp_state_limits & 0xff); + drm_printf(p, "RPSTAT1: 0x%08x\n", rpstat); + drm_printf(p, "RPMODECTL: 0x%08x\n", rpmodectl); + drm_printf(p, "RPINCLIMIT: 0x%08x\n", rpinclimit); + drm_printf(p, "RPDECLIMIT: 0x%08x\n", rpdeclimit); + drm_printf(p, "RPNSWREQ: %dMHz\n", reqf); + drm_printf(p, "CAGF: %dMHz\n", cagf); + drm_printf(p, "RP CUR UP EI: %d (%lldns)\n", + rpcurupei, + intel_gt_pm_interval_to_ns(gt, rpcurupei)); + drm_printf(p, "RP CUR UP: %d (%lldns)\n", + rpcurup, intel_gt_pm_interval_to_ns(gt, rpcurup)); + drm_printf(p, "RP PREV UP: %d (%lldns)\n", + rpprevup, intel_gt_pm_interval_to_ns(gt, rpprevup)); + drm_printf(p, "Up threshold: %d%%\n", + rps->power.up_threshold); + drm_printf(p, "RP UP EI: %d (%lldns)\n", + rpupei, intel_gt_pm_interval_to_ns(gt, rpupei)); + drm_printf(p, "RP UP THRESHOLD: %d (%lldns)\n", + rpupt, intel_gt_pm_interval_to_ns(gt, rpupt)); + + drm_printf(p, "RP CUR DOWN EI: %d (%lldns)\n", + rpcurdownei, + intel_gt_pm_interval_to_ns(gt, rpcurdownei)); + drm_printf(p, "RP CUR DOWN: %d (%lldns)\n", + rpcurdown, + intel_gt_pm_interval_to_ns(gt, rpcurdown)); + drm_printf(p, "RP PREV DOWN: %d (%lldns)\n", + rpprevdown, + intel_gt_pm_interval_to_ns(gt, rpprevdown)); + drm_printf(p, "Down threshold: %d%%\n", + rps->power.down_threshold); + drm_printf(p, "RP DOWN EI: %d (%lldns)\n", + rpdownei, intel_gt_pm_interval_to_ns(gt, rpdownei)); + drm_printf(p, "RP DOWN THRESHOLD: %d (%lldns)\n", + rpdownt, intel_gt_pm_interval_to_ns(gt, rpdownt)); + + drm_printf(p, "Lowest (RPN) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.min_freq)); + drm_printf(p, "Nominal (RP1) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.rp1_freq)); + drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.rp0_freq)); + drm_printf(p, "Max overclocked frequency: %dMHz\n", + intel_gpu_freq(rps, rps->max_freq)); + + drm_printf(p, "Current freq: %d MHz\n", + intel_gpu_freq(rps, rps->cur_freq)); + drm_printf(p, "Actual freq: %d MHz\n", cagf); + drm_printf(p, "Idle freq: %d MHz\n", + intel_gpu_freq(rps, rps->idle_freq)); + drm_printf(p, "Min freq: %d MHz\n", + intel_gpu_freq(rps, rps->min_freq)); + drm_printf(p, "Boost freq: %d MHz\n", + intel_gpu_freq(rps, rps->boost_freq)); + drm_printf(p, "Max freq: %d MHz\n", + intel_gpu_freq(rps, rps->max_freq)); + drm_printf(p, + "efficient (RPe) frequency: %d MHz\n", + intel_gpu_freq(rps, rps->efficient_freq)); +} + +static void slpc_frequency_dump(struct intel_rps *rps, struct drm_printer *p) +{ + struct intel_gt *gt = rps_to_gt(rps); + struct intel_uncore *uncore = gt->uncore; + struct intel_rps_freq_caps caps; + u32 pm_mask; + + gen6_rps_get_freq_caps(rps, &caps); + pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK); + + drm_printf(p, "PM MASK=0x%08x\n", pm_mask); + drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n", + rps->pm_intrmsk_mbz); + drm_printf(p, "RPSTAT1: 0x%08x\n", intel_uncore_read(uncore, GEN6_RPSTAT1)); + drm_printf(p, "RPNSWREQ: %dMHz\n", intel_rps_get_requested_frequency(rps)); + drm_printf(p, "Lowest (RPN) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.min_freq)); + drm_printf(p, "Nominal (RP1) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.rp1_freq)); + drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n", + intel_gpu_freq(rps, caps.rp0_freq)); + drm_printf(p, "Current freq: %d MHz\n", + intel_rps_get_requested_frequency(rps)); + drm_printf(p, "Actual freq: %d MHz\n", + intel_rps_read_actual_frequency(rps)); + drm_printf(p, "Min freq: %d MHz\n", + intel_rps_get_min_frequency(rps)); + drm_printf(p, "Boost freq: %d MHz\n", + intel_rps_get_boost_frequency(rps)); + drm_printf(p, "Max freq: %d MHz\n", + intel_rps_get_max_frequency(rps)); + drm_printf(p, + "efficient (RPe) frequency: %d MHz\n", + intel_gpu_freq(rps, caps.rp1_freq)); +} + +void gen6_rps_frequency_dump(struct intel_rps *rps, struct drm_printer *p) +{ + if (rps_uses_slpc(rps)) + return slpc_frequency_dump(rps, p); + else + return rps_frequency_dump(rps, p); +} + static int set_max_freq(struct intel_rps *rps, u32 val) { struct drm_i915_private *i915 = rps_to_i915(rps); |