From: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> [ Upstream commit b24dcf1dc507f69ed3b5c66c2b6a0209ae80d4d4 ] Don't allow two engines to be reset in parallel, as they would both try to select a reset bit (and send requests to common registers) and wait on that register, at the same time. Serialize control of the reset requests/acks using the uncore->lock, which will also ensure that no other GT state changes at the same time as the actual reset. Cc: stable@xxxxxxxxxxxxxxx # v4.4 and upper Reported-by: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx> Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> Acked-by: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx> Reviewed-by: Andi Shyti <andi.shyti@xxxxxxxxx> Reviewed-by: Andrzej Hajda <andrzej.hajda@xxxxxxxxx> Acked-by: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx> Signed-off-by: Mauro Carvalho Chehab <mchehab@xxxxxxxxxx> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@xxxxxxxxx> Link: https://patchwork.freedesktop.org/patch/msgid/e0a2d894e77aed7c2e36b0d1abdc7dbac3011729.1657639152.git.mchehab@xxxxxxxxxx (cherry picked from commit 336561a914fc0c6f1218228718f633b31b7af1c3) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@xxxxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> --- drivers/gpu/drm/i915/gt/intel_reset.c | 37 ++++++++++++++++++++------- 1 file changed, 28 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index b6697c1d260a..18b0e57c58c1 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -293,9 +293,9 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask) return err; } -static int gen6_reset_engines(struct intel_gt *gt, - intel_engine_mask_t engine_mask, - unsigned int retry) +static int __gen6_reset_engines(struct intel_gt *gt, + intel_engine_mask_t engine_mask, + unsigned int retry) { static const u32 hw_engine_mask[] = { [RCS0] = GEN6_GRDOM_RENDER, @@ -322,6 +322,20 @@ static int gen6_reset_engines(struct intel_gt *gt, return gen6_hw_domain_reset(gt, hw_mask); } +static int gen6_reset_engines(struct intel_gt *gt, + intel_engine_mask_t engine_mask, + unsigned int retry) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(>->uncore->lock, flags); + ret = __gen6_reset_engines(gt, engine_mask, retry); + spin_unlock_irqrestore(>->uncore->lock, flags); + + return ret; +} + static struct intel_engine_cs *find_sfc_paired_vecs_engine(struct intel_engine_cs *engine) { int vecs_id; @@ -488,9 +502,9 @@ static void gen11_unlock_sfc(struct intel_engine_cs *engine) rmw_clear_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit); } -static int gen11_reset_engines(struct intel_gt *gt, - intel_engine_mask_t engine_mask, - unsigned int retry) +static int __gen11_reset_engines(struct intel_gt *gt, + intel_engine_mask_t engine_mask, + unsigned int retry) { static const u32 hw_engine_mask[] = { [RCS0] = GEN11_GRDOM_RENDER, @@ -601,8 +615,11 @@ static int gen8_reset_engines(struct intel_gt *gt, struct intel_engine_cs *engine; const bool reset_non_ready = retry >= 1; intel_engine_mask_t tmp; + unsigned long flags; int ret; + spin_lock_irqsave(>->uncore->lock, flags); + for_each_engine_masked(engine, gt, engine_mask, tmp) { ret = gen8_engine_reset_prepare(engine); if (ret && !reset_non_ready) @@ -630,17 +647,19 @@ static int gen8_reset_engines(struct intel_gt *gt, * This is best effort, so ignore any error from the initial reset. */ if (IS_DG2(gt->i915) && engine_mask == ALL_ENGINES) - gen11_reset_engines(gt, gt->info.engine_mask, 0); + __gen11_reset_engines(gt, gt->info.engine_mask, 0); if (GRAPHICS_VER(gt->i915) >= 11) - ret = gen11_reset_engines(gt, engine_mask, retry); + ret = __gen11_reset_engines(gt, engine_mask, retry); else - ret = gen6_reset_engines(gt, engine_mask, retry); + ret = __gen6_reset_engines(gt, engine_mask, retry); skip_reset: for_each_engine_masked(engine, gt, engine_mask, tmp) gen8_engine_reset_cancel(engine); + spin_unlock_irqrestore(>->uncore->lock, flags); + return ret; } -- 2.35.1
