From fb261dccc26646b9c46e8c2a080b202034aabc0e Mon Sep 17 00:00:00 2001 From: David P Date: Mon, 24 Feb 2020 22:25:49 -0300 Subject: updpkg: libre/linux-libre-pae 5.5.5-1 Signed-off-by: David P --- ...eclists-Always-force-a-context-reload-whe.patch | 145 +++++++++++++++++++++ 1 file changed, 145 insertions(+) create mode 100644 libre/linux-libre-pae/0006-drm-i915-execlists-Always-force-a-context-reload-whe.patch (limited to 'libre/linux-libre-pae/0006-drm-i915-execlists-Always-force-a-context-reload-whe.patch') diff --git a/libre/linux-libre-pae/0006-drm-i915-execlists-Always-force-a-context-reload-whe.patch b/libre/linux-libre-pae/0006-drm-i915-execlists-Always-force-a-context-reload-whe.patch new file mode 100644 index 000000000..fda8482df --- /dev/null +++ b/libre/linux-libre-pae/0006-drm-i915-execlists-Always-force-a-context-reload-whe.patch @@ -0,0 +1,145 @@ +From db1660f27f62a515dde34ccb192d7c63acf7fde9 Mon Sep 17 00:00:00 2001 +From: Chris Wilson +Date: Fri, 7 Feb 2020 21:14:52 +0000 +Subject: [PATCH 06/13] drm/i915/execlists: Always force a context reload when + rewinding RING_TAIL + +If we rewind the RING_TAIL on a context, due to a preemption event, we +must force the context restore for the RING_TAIL update to be properly +handled. Rather than note which preemption events may cause us to rewind +the tail, compare the new request's tail with the previously submitted +RING_TAIL, as it turns out that timeslicing was causing unexpected +rewinds. + + -0 0d.s2 1280851190us : __execlists_submission_tasklet: 0000:00:02.0 rcs0: expired last=130:4698, prio=3, hint=3 + -0 0d.s2 1280851192us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 66:119966, current 119964 + -0 0d.s2 1280851195us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 130:4698, current 4695 + -0 0d.s2 1280851198us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 130:4696, current 4695 +^---- Note we unwind 2 requests from the same context + + -0 0d.s2 1280851208us : __i915_request_submit: 0000:00:02.0 rcs0: fence 130:4696, current 4695 + -0 0d.s2 1280851213us : __i915_request_submit: 0000:00:02.0 rcs0: fence 134:1508, current 1506 +^---- But to apply the new timeslice, we have to replay the first request + before the new client can start -- the unexpected RING_TAIL rewind + + -0 0d.s2 1280851219us : trace_ports: 0000:00:02.0 rcs0: submit { 130:4696*, 134:1508 } + synmark2-5425 2..s. 1280851239us : process_csb: 0000:00:02.0 rcs0: cs-irq head=5, tail=0 + synmark2-5425 2..s. 1280851240us : process_csb: 0000:00:02.0 rcs0: csb[0]: status=0x00008002:0x00000000 +^---- Preemption event for the ELSP update; note the lite-restore + + synmark2-5425 2..s. 1280851243us : trace_ports: 0000:00:02.0 rcs0: preempted { 130:4698, 66:119966 } + synmark2-5425 2..s. 1280851246us : trace_ports: 0000:00:02.0 rcs0: promote { 130:4696*, 134:1508 } + synmark2-5425 2.... 1280851462us : __i915_request_commit: 0000:00:02.0 rcs0: fence 130:4700, current 4695 + synmark2-5425 2.... 1280852111us : __i915_request_commit: 0000:00:02.0 rcs0: fence 130:4702, current 4695 + synmark2-5425 2.Ns1 1280852296us : process_csb: 0000:00:02.0 rcs0: cs-irq head=0, tail=2 + synmark2-5425 2.Ns1 1280852297us : process_csb: 0000:00:02.0 rcs0: csb[1]: status=0x00000814:0x00000000 + synmark2-5425 2.Ns1 1280852299us : trace_ports: 0000:00:02.0 rcs0: completed { 130:4696!, 134:1508 } + synmark2-5425 2.Ns1 1280852301us : process_csb: 0000:00:02.0 rcs0: csb[2]: status=0x00000818:0x00000040 + synmark2-5425 2.Ns1 1280852302us : trace_ports: 0000:00:02.0 rcs0: completed { 134:1508, 0:0 } + synmark2-5425 2.Ns1 1280852313us : process_csb: process_csb:2336 GEM_BUG_ON(!i915_request_completed(*execlists->active) && !reset_in_progress(execlists)) + +Fixes: 8ee36e048c98 ("drm/i915/execlists: Minimalistic timeslicing") +Referenecs: 82c69bf58650 ("drm/i915/gt: Detect if we miss WaIdleLiteRestore") +Signed-off-by: Chris Wilson +Cc: Mika Kuoppala +Reviewed-by: Mika Kuoppala +Cc: # v5.4+ +Link: https://patchwork.freedesktop.org/patch/msgid/20200207211452.2860634-1-chris@chris-wilson.co.uk +--- + drivers/gpu/drm/i915/gt/intel_lrc.c | 18 ++++++++---------- + drivers/gpu/drm/i915/gt/intel_ring.c | 1 + + drivers/gpu/drm/i915/gt/intel_ring.h | 8 ++++++++ + drivers/gpu/drm/i915/gt/intel_ring_types.h | 1 + + 4 files changed, 18 insertions(+), 10 deletions(-) + +diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c +index d925a1035c9d..1b4784bfa7e5 100644 +--- a/drivers/gpu/drm/i915/gt/intel_lrc.c ++++ b/drivers/gpu/drm/i915/gt/intel_lrc.c +@@ -1157,7 +1157,7 @@ static u64 execlists_update_context(struct i915_request *rq) + { + struct intel_context *ce = rq->hw_context; + u64 desc = ce->lrc_desc; +- u32 tail; ++ u32 tail, prev; + + /* + * WaIdleLiteRestore:bdw,skl +@@ -1170,9 +1170,15 @@ static u64 execlists_update_context(struct i915_request *rq) + * subsequent resubmissions (for lite restore). Should that fail us, + * and we try and submit the same tail again, force the context + * reload. ++ * ++ * If we need to return to a preempted context, we need to skip the ++ * lite-restore and force it to reload the RING_TAIL. Otherwise, the ++ * HW has a tendency to ignore us rewinding the TAIL to the end of ++ * an earlier request. + */ + tail = intel_ring_set_tail(rq->ring, rq->tail); +- if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail)) ++ prev = ce->lrc_reg_state[CTX_RING_TAIL]; ++ if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0)) + desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc_reg_state[CTX_RING_TAIL] = tail; + rq->tail = rq->wa_tail; +@@ -1651,14 +1657,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) + */ + __unwind_incomplete_requests(engine); + +- /* +- * If we need to return to the preempted context, we +- * need to skip the lite-restore and force it to +- * reload the RING_TAIL. Otherwise, the HW has a +- * tendency to ignore us rewinding the TAIL to the +- * end of an earlier request. +- */ +- last->hw_context->lrc_desc |= CTX_DESC_FORCE_RESTORE; + last = NULL; + } else if (need_timeslice(engine, last) && + timer_expired(&engine->execlists.timer)) { +diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c +index 374b28f13ca0..6ff803f397c4 100644 +--- a/drivers/gpu/drm/i915/gt/intel_ring.c ++++ b/drivers/gpu/drm/i915/gt/intel_ring.c +@@ -145,6 +145,7 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size) + + kref_init(&ring->ref); + ring->size = size; ++ ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size); + + /* + * Workaround an erratum on the i830 which causes a hang if +diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h +index ea2839d9e044..5bdce24994aa 100644 +--- a/drivers/gpu/drm/i915/gt/intel_ring.h ++++ b/drivers/gpu/drm/i915/gt/intel_ring.h +@@ -56,6 +56,14 @@ static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos) + return pos & (ring->size - 1); + } + ++static inline int intel_ring_direction(const struct intel_ring *ring, ++ u32 next, u32 prev) ++{ ++ typecheck(typeof(ring->size), next); ++ typecheck(typeof(ring->size), prev); ++ return (next - prev) << ring->wrap; ++} ++ + static inline bool + intel_ring_offset_valid(const struct intel_ring *ring, + unsigned int pos) +diff --git a/drivers/gpu/drm/i915/gt/intel_ring_types.h b/drivers/gpu/drm/i915/gt/intel_ring_types.h +index d9f17f38e0cc..3cd7fec7fd8d 100644 +--- a/drivers/gpu/drm/i915/gt/intel_ring_types.h ++++ b/drivers/gpu/drm/i915/gt/intel_ring_types.h +@@ -45,6 +45,7 @@ struct intel_ring { + + u32 space; + u32 size; ++ u32 wrap; + u32 effective_size; + }; + +-- +2.25.1 + -- cgit v1.2.3