From 74f6e183913b5dc90a004cafa84159ddb61cd0f0 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 26 Sep 2018 11:47:07 +0100 Subject: drm/i915: Convert to BITS_PER_TYPE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In commit 9144d75e22ca ("include/linux/bitops.h: introduce BITS_PER_TYPE"), we made BITS_PER_TYPE available to all and now we can use the macro to replace some open-coded computation of sizeof(T) * BITS_PER_BYTE. Suggested-by: Ville Syrjälä Signed-off-by: Chris Wilson Cc: Ville Syrjälä Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Tvrtko Ursulin Reviewed-by: Jani Nikula Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20180926104707.17410-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/intel_engine_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c') diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 217ed3ee1cab..6726d57f018f 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -335,7 +335,7 @@ int intel_engines_init_mmio(struct drm_i915_private *dev_priv) WARN_ON(ring_mask == 0); WARN_ON(ring_mask & - GENMASK(sizeof(mask) * BITS_PER_BYTE - 1, I915_NUM_ENGINES)); + GENMASK(BITS_PER_TYPE(mask) - 1, I915_NUM_ENGINES)); for (i = 0; i < ARRAY_SIZE(intel_engines); i++) { if (!HAS_ENGINE(dev_priv, i)) -- cgit From 85f5e1f385b7643ee31e0530a1daa2438ac27aaf Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 1 Oct 2018 13:32:04 +0100 Subject: drm/i915: Combine multiple internal plists into the same i915_priolist bucket As we are about to allow ourselves to slightly bump the user priority into a few different sublevels, packthose internal priority lists into the same i915_priolist to keep the rbtree compact and avoid having to allocate the default user priority even after the internal bumping. The downside to having an requests[] rather than a node per active list, is that we then have to walk over the empty higher priority lists. To compensate, we track the active buckets and use a small bitmap to skip over any inactive ones. v2: Use MASK of internal levels to simplify our usage. v3: Prevent overflow when SHIFT is zero. Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20181001123204.23982-4-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/intel_engine_cs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c') diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 6726d57f018f..1c6143bdf5a4 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -1534,10 +1534,10 @@ void intel_engine_dump(struct intel_engine_cs *engine, count = 0; drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority); for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) { - struct i915_priolist *p = - rb_entry(rb, typeof(*p), node); + struct i915_priolist *p = rb_entry(rb, typeof(*p), node); + int i; - list_for_each_entry(rq, &p->requests, sched.link) { + priolist_for_each_request(rq, p, i) { if (count++ < MAX_REQUESTS_TO_SHOW - 1) print_request(m, rq, "\t\tQ "); else -- cgit From 645ff9e371718476c77bfcd315f26d46ef587808 Mon Sep 17 00:00:00 2001 From: Michal Wajdeczko Date: Thu, 11 Oct 2018 13:00:08 +0000 Subject: drm/i915: Inject load failure inside intel_engines_init_mmio We need extra load failure point to better test error path in i915_driver_init_mmio. Suggested-by: Chris Wilson Signed-off-by: Michal Wajdeczko Cc: Chris Wilson Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20181011130008.24640-2-michal.wajdeczko@intel.com --- drivers/gpu/drm/i915/intel_engine_cs.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c') diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 1c6143bdf5a4..f27dbe26bcc1 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -337,6 +337,9 @@ int intel_engines_init_mmio(struct drm_i915_private *dev_priv) WARN_ON(ring_mask & GENMASK(BITS_PER_TYPE(mask) - 1, I915_NUM_ENGINES)); + if (i915_inject_load_failure()) + return -ENODEV; + for (i = 0; i < ARRAY_SIZE(intel_engines); i++) { if (!HAS_ENGINE(dev_priv, i)) continue; -- cgit From 410ed5731a6566498a3aa904420aa2e49ba0ba90 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 16 Oct 2018 15:29:38 +0300 Subject: drm/i915: Ensure intel_engine_init_execlist() builds with Clang Clang build with UBSAN enabled leads to the following build error: drivers/gpu/drm/i915/intel_engine_cs.o: In function `intel_engine_init_execlist': drivers/gpu/drm/i915/intel_engine_cs.c:411: undefined reference to `__compiletime_assert_411' Again, for this to work the code would first need to be inlined and then constant folded, which doesn't work for Clang because semantic analysis happens before optimization/inlining. Use GEM_BUG_ON() instead of BUILD_BUG_ON(). v2: Use is_power_of_2() from log2.h (Chris) References: http://mid.mail-archive.com/20181015203410.155997-1-swboyd@chromium.org Reported-by: Stephen Boyd Cc: Stephen Boyd Cc: Chris Wilson Tested-by: Nathan Chancellor Tested-by: Stephen Boyd Reviewed-by: Chris Wilson Reviewed-by: Nick Desaulniers Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20181016122938.18757-2-jani.nikula@intel.com --- drivers/gpu/drm/i915/intel_engine_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c') diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index f27dbe26bcc1..bc793b0c8806 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -466,7 +466,7 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine) struct intel_engine_execlists * const execlists = &engine->execlists; execlists->port_mask = 1; - BUILD_BUG_ON_NOT_POWER_OF_2(execlists_num_ports(execlists)); + GEM_BUG_ON(!is_power_of_2(execlists_num_ports(execlists))); GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS); execlists->queue_priority = INT_MIN; -- cgit From bbb8a9d7e000c906f490780fab1c64faa1d08604 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 12 Oct 2018 07:31:42 +0100 Subject: drm/i915: GEM_WARN_ON considered harmful GEM_WARN_ON currently has dangerous semantics where it is completely compiled out on !GEM_DEBUG builds. This can leave users who expect it to be more like a WARN_ON, just without a warning in non-debug builds, in complete ignorance. Another gotcha with it is that it cannot be used as a statement. Which is again different from a standard kernel WARN_ON. This patch fixes both problems by making it behave as one would expect. It can now be used both as an expression and as statement, and also the condition evaluates properly in all builds - code under the conditional will therefore not unexpectedly disappear. To satisfy call sites which really want the code under the conditional to completely disappear, we add GEM_DEBUG_WARN_ON and convert some of the callers to it. This one can also be used as both expression and statement. >From the above it follows GEM_DEBUG_WARN_ON should be used in situations where we are certain the condition will be hit during development, but at a place in code where error can be handled to the benefit of not crashing the machine. GEM_WARN_ON on the other hand should be used where condition may happen in production and we just want to distinguish the level of debugging output emitted between the production and debug build. v2: * Dropped BUG_ON hunk. Signed-off-by: Tvrtko Ursulin Cc: Chris Wilson Cc: Joonas Lahtinen Cc: Matthew Auld Cc: Mika Kuoppala Cc: Tomasz Lis Reviewed-by: Tomasz Lis Link: https://patchwork.freedesktop.org/patch/msgid/20181012063142.16080-1-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/intel_engine_cs.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c') diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index bc793b0c8806..8bfab22068a3 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -273,13 +273,13 @@ intel_engine_setup(struct drm_i915_private *dev_priv, BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH)); BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH)); - if (GEM_WARN_ON(info->class > MAX_ENGINE_CLASS)) + if (GEM_DEBUG_WARN_ON(info->class > MAX_ENGINE_CLASS)) return -EINVAL; - if (GEM_WARN_ON(info->instance > MAX_ENGINE_INSTANCE)) + if (GEM_DEBUG_WARN_ON(info->instance > MAX_ENGINE_INSTANCE)) return -EINVAL; - if (GEM_WARN_ON(dev_priv->engine_class[info->class][info->instance])) + if (GEM_DEBUG_WARN_ON(dev_priv->engine_class[info->class][info->instance])) return -EINVAL; GEM_BUG_ON(dev_priv->engine[id]); @@ -402,7 +402,7 @@ int intel_engines_init(struct drm_i915_private *dev_priv) err = -EINVAL; err_id = id; - if (GEM_WARN_ON(!init)) + if (GEM_DEBUG_WARN_ON(!init)) goto cleanup; err = init(engine); -- cgit From 9e7833758b9feebc37b9988d13b017534c90a4a2 Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi Date: Fri, 26 Oct 2018 12:51:42 -0700 Subject: drm/i915: Prefer IS_GEN check with bitmask. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Whenever possible we should stick with IS_GEN checks. Bitmaks has been introduced on commit ae7617f0ef18 ("drm/i915: Allow optimized platform checks") for efficiency. Let's stick with it whenever possible. This patch was generated with coccinelle: spatch -sp_file is_gen.cocci *{c,h} --in-place is_gen.cocci: @gen2@ expression e; @@ -INTEL_GEN(e) == 2 +IS_GEN2(e) @gen3@ expression e; @@ -INTEL_GEN(e) == 3 +IS_GEN3(e) @gen4@ expression e; @@ -INTEL_GEN(e) == 4 +IS_GEN4(e) @gen5@ expression e; @@ -INTEL_GEN(e) == 5 +IS_GEN5(e) @gen6@ expression e; @@ -INTEL_GEN(e) == 6 +IS_GEN6(e) @gen7@ expression e; @@ -INTEL_GEN(e) == 7 +IS_GEN7(e) @gen8@ expression e; @@ -INTEL_GEN(e) == 8 +IS_GEN8(e) @gen9@ expression e; @@ -INTEL_GEN(e) == 9 +IS_GEN9(e) @gen10@ expression e; @@ -INTEL_GEN(e) == 10 +IS_GEN10(e) @gen11@ expression e; @@ -INTEL_GEN(e) == 11 +IS_GEN11(e) Cc: Tvrtko Ursulin Signed-off-by: Rodrigo Vivi Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20181026195143.20353-1-rodrigo.vivi@intel.com --- drivers/gpu/drm/i915/intel_engine_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c') diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 8bfab22068a3..bc147d9e6c92 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -812,7 +812,7 @@ u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv) u32 slice = fls(sseu->slice_mask); u32 subslice = fls(sseu->subslice_mask[slice]); - if (INTEL_GEN(dev_priv) == 10) + if (IS_GEN10(dev_priv)) mcr_s_ss_select = GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice); else if (INTEL_GEN(dev_priv) >= 11) -- cgit From f911e7234f83efe4842a453406e90ceac3cabd8e Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 15 Nov 2018 20:38:51 +0000 Subject: drm/i915/selftests: Workaround an issue with unused lockdep subclass MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit lockdep insists that if we give a lock a subclass, it must be used. Failure to do so triggers a self-consistency check when reading lockdep_stats: [ 49.902002] DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused) [ 49.902009] WARNING: CPU: 3 PID: 383 at kernel/locking/lockdep_proc.c:249 lockdep_stats_show+0x984/0xa10 [ 49.902026] Modules linked in: nls_ascii nls_cp437 vfat fat crct10dif_pclmul crc32_pclmul crc32c_intel aesni_intel aes_x86_64 crypto_simd cryptd glue_helper intel_cstate intel_uncore intel_rapl_perf intel_gtt efivars prime_numbers ahci libahci i2c_i801 video button efivarfs [last unloaded: drm_kms_helper] [ 49.902059] CPU: 3 PID: 383 Comm: cat Tainted: G U 4.20.0-rc2+ #304 [ 49.902068] Hardware name: Intel Corporation NUC7i5BNK/NUC7i5BNB, BIOS BNKBL357.86A.0052.2017.0918.1346 09/18/2017 [ 49.902079] RIP: 0010:lockdep_stats_show+0x984/0xa10 [ 49.902086] Code: 00 85 c0 0f 84 aa f8 ff ff 8b 05 77 37 e2 00 85 c0 0f 85 9c f8 ff ff 48 c7 c6 e0 57 bc 81 48 c7 c7 28 30 bb 81 e8 6b 77 fa ff <0f> 0b e9 82 f8 ff ff 48 c7 44 24 50 00 00 00 00 45 31 e4 31 db 31 [ 49.902103] RSP: 0018:ffffc90000247d58 EFLAGS: 00010292 [ 49.902110] RAX: 0000000000000044 RBX: 00000000000002f0 RCX: 0000000000000000 [ 49.902118] RDX: 0000000000000002 RSI: 0000000000000001 RDI: ffffffff810b3464 [ 49.902126] RBP: 0000000000000039 R08: 0000000000000002 R09: 0000000000000000 [ 49.902133] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000007ead [ 49.902141] R13: 0000000000000001 R14: ffff88884c021000 R15: 0000000000000097 [ 49.902150] FS: 00007fb347e66540(0000) GS:ffff88885e600000(0000) knlGS:0000000000000000 [ 49.902159] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 49.902165] CR2: 00007fb347aeb000 CR3: 00000008544bd005 CR4: 00000000001606e0 Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: Michał Winiarski Cc: Matthew Auld Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20181115203851.25739-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/intel_engine_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c') diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index bc147d9e6c92..885a901b6e13 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -485,7 +485,7 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine) void intel_engine_setup_common(struct intel_engine_cs *engine) { i915_timeline_init(engine->i915, &engine->timeline, engine->name); - lockdep_set_subclass(&engine->timeline.lock, TIMELINE_ENGINE); + i915_timeline_set_subclass(&engine->timeline, TIMELINE_ENGINE); intel_engine_init_execlist(engine); intel_engine_init_hangcheck(engine); -- cgit From aa6a65daca110df41ac0224bea1198dc97fd6695 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 21 Nov 2018 15:16:53 +0000 Subject: drm/i915: Show waiter's status on engine dump When showing the list of waiters, include the task's status so that we can tell if they have been woken up and are waiting for the CPU, or if they are still waiting to be woken. v2: task_state_to_char() Signed-off-by: Chris Wilson Cc: Mika Kuoppala Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20181121151653.24595-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/intel_engine_cs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c') diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 885a901b6e13..759c0fd58f8c 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -1562,8 +1562,10 @@ void intel_engine_dump(struct intel_engine_cs *engine, for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) { struct intel_wait *w = rb_entry(rb, typeof(*w), node); - drm_printf(m, "\t%s [%d] waiting for %x\n", - w->tsk->comm, w->tsk->pid, w->seqno); + drm_printf(m, "\t%s [%d:%c] waiting for %x\n", + w->tsk->comm, w->tsk->pid, + task_state_to_char(w->tsk), + w->seqno); } spin_unlock(&b->rb_lock); local_irq_restore(flags); -- cgit