[Intel-gfx] [PATCH v3 4/5] drm/i915/execlists: Read the context-status buffer from the HWSP

[Michel Thierry]

On 13/07/17 03:27, Chris Wilson wrote:
> The engine provides a mirror of the CSB in the HWSP. If we use the
> cacheable reads from the HWSP, we can shave off a few mmio reads per
> context-switch interrupt (which are quite frequent!). Just removing a
> couple of mmio is not enough to actually reduce any latency, but a small
> reduction in overall cpu usage.
> 
> Much appreciation for Ben dropping the bombshell that the CSB was in the
> HWSP and for Michel in digging out the details.
> 
> v2: Don't be lazy, add the defines for the indices.
> v3: Include the HWSP in debugfs/i915_engine_info
> v4: Check for GVT-g, it currently depends on intercepting CSB mmio
> 
> Suggested-by: Ben Widawsky <benjamin.widawsky at intel.com>
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Michel Thierry <michel.thierry at intel.com>
> Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
> Cc: Mika Kuoppala <mika.kuoppala at intel.com>
> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
> Cc: Zhenyu Wang <zhenyuw at linux.intel.com>
> Cc: Zhi Wang <zhi.a.wang at intel.com>
> Acked-by: Michel Thierry <michel.thierry at intel.com>
> ---
>   drivers/gpu/drm/i915/i915_debugfs.c     |  7 +++++--
>   drivers/gpu/drm/i915/intel_lrc.c        | 16 +++++++++++-----
>   drivers/gpu/drm/i915/intel_ringbuffer.h |  2 ++
>   3 files changed, 18 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index 620c9218d1c1..5fd01c14a3ec 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -3384,6 +3384,7 @@ static int i915_engine_info(struct seq_file *m, void *unused)
>   			   upper_32_bits(addr), lower_32_bits(addr));
>   
>   		if (i915.enable_execlists) {
> +			const u32 *hws = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
>   			u32 ptr, read, write;
>   			unsigned int idx;
>   
> @@ -3404,10 +3405,12 @@ static int i915_engine_info(struct seq_file *m, void *unused)
>   				write += GEN8_CSB_ENTRIES;
>   			while (read < write) {
>   				idx = ++read % GEN8_CSB_ENTRIES;
> -				seq_printf(m, "\tExeclist CSB[%d]: 0x%08x, context: %d\n",
> +				seq_printf(m, "\tExeclist CSB[%d]: 0x%08x [0x%08x in hwsp], context: %d [%d in hwsp]\n",
>   					   idx,
>   					   I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)),
> -					   I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)));
> +					   hws[idx * 2],
> +					   I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)),
> +					   hws[idx * 2 + 1]);
>   			}
>   
>   			rcu_read_lock();
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 3469badedbe0..5b721f65d232 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -547,10 +547,17 @@ static void intel_lrc_irq_handler(unsigned long data)
>   	while (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) {
>   		u32 __iomem *csb_mmio =
>   			dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine));
> -		u32 __iomem *buf =
> -			dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0));
> +		/* The HWSP contains a (cacheable) mirror of the CSB */
> +		const u32 *buf =
> +			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
>   		unsigned int head, tail;
>   
> +		/* However GVT emulation depends upon intercepting CSB mmio */
> +		if (unlikely(intel_vgpu_active(dev_priv))) {
> +			buf = (u32 * __force)
> +				(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));

RING_CONTEXT_STATUS_BUF_LO(engine, 0) instead of 
RING_CONTEXT_STATUS_PTR(engine)?

> +		}
> +
>   		/* The write will be ordered by the uncached read (itself
>   		 * a memory barrier), so we do not need another in the form
>   		 * of a locked instruction. The race between the interrupt
> @@ -590,13 +597,12 @@ static void intel_lrc_irq_handler(unsigned long data)
>   			 * status notifier.
>   			 */
>   
> -			status = readl(buf + 2 * head);
> +			status = buf[2 * head];
>   			if (!(status & GEN8_CTX_STATUS_COMPLETED_MASK))
>   				continue;
>   
>   			/* Check the context/desc id for this event matches */
> -			GEM_DEBUG_BUG_ON(readl(buf + 2 * head + 1) !=
> -					 port->context_id);
> +			GEM_DEBUG_BUG_ON(buf[2 * head + 1] != port->context_id);
>   
>   			rq = port_unpack(port, &count);
>   			GEM_BUG_ON(count == 0);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index d33c93444c0d..2c55cfa14fb5 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -496,6 +496,8 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
>   #define I915_GEM_HWS_SCRATCH_INDEX	0x40
>   #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
>   
> +#define I915_HWS_CSB_BUF0_INDEX		0x10
> +
>   struct intel_ring *
>   intel_engine_create_ring(struct intel_engine_cs *engine, int size);
>   int intel_ring_pin(struct intel_ring *ring,
>