linux_dsm_epyc7002/drivers/gpu/drm/i915/intel_lrc.h
Tvrtko Ursulin 27af5eea54 drm/i915: Move execlists irq handler to a bottom half
Doing a lot of work in the interrupt handler introduces huge
latencies to the system as a whole.

Most dramatic effect can be seen by running an all engine
stress test like igt/gem_exec_nop/all where, when the kernel
config is lean enough, the whole system can be brought into
multi-second periods of complete non-interactivty. That can
look for example like this:

 NMI watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/u8:3:143]
 Modules linked in: [redacted for brevity]
 CPU: 0 PID: 143 Comm: kworker/u8:3 Tainted: G     U       L  4.5.0-160321+ #183
 Hardware name: Intel Corporation Broadwell Client platform/WhiteTip Mountain 1
 Workqueue: i915 gen6_pm_rps_work [i915]
 task: ffff8800aae88000 ti: ffff8800aae90000 task.ti: ffff8800aae90000
 RIP: 0010:[<ffffffff8104a3c2>]  [<ffffffff8104a3c2>] __do_softirq+0x72/0x1d0
 RSP: 0000:ffff88014f403f38  EFLAGS: 00000206
 RAX: ffff8800aae94000 RBX: 0000000000000000 RCX: 00000000000006e0
 RDX: 0000000000000020 RSI: 0000000004208060 RDI: 0000000000215d80
 RBP: ffff88014f403f80 R08: 0000000b1b42c180 R09: 0000000000000022
 R10: 0000000000000004 R11: 00000000ffffffff R12: 000000000000a030
 R13: 0000000000000082 R14: ffff8800aa4d0080 R15: 0000000000000082
 FS:  0000000000000000(0000) GS:ffff88014f400000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007fa53b90c000 CR3: 0000000001a0a000 CR4: 00000000001406f0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 Stack:
  042080601b33869f ffff8800aae94000 00000000fffc2678 ffff88010000000a
  0000000000000000 000000000000a030 0000000000005302 ffff8800aa4d0080
  0000000000000206 ffff88014f403f90 ffffffff8104a716 ffff88014f403fa8
 Call Trace:
  <IRQ>
  [<ffffffff8104a716>] irq_exit+0x86/0x90
  [<ffffffff81031e7d>] smp_apic_timer_interrupt+0x3d/0x50
  [<ffffffff814f3eac>] apic_timer_interrupt+0x7c/0x90
  <EOI>
  [<ffffffffa01c5b40>] ? gen8_write64+0x1a0/0x1a0 [i915]
  [<ffffffff814f2b39>] ? _raw_spin_unlock_irqrestore+0x9/0x20
  [<ffffffffa01c5c44>] gen8_write32+0x104/0x1a0 [i915]
  [<ffffffff8132c6a2>] ? n_tty_receive_buf_common+0x372/0xae0
  [<ffffffffa017cc9e>] gen6_set_rps_thresholds+0x1be/0x330 [i915]
  [<ffffffffa017eaf0>] gen6_set_rps+0x70/0x200 [i915]
  [<ffffffffa0185375>] intel_set_rps+0x25/0x30 [i915]
  [<ffffffffa01768fd>] gen6_pm_rps_work+0x10d/0x2e0 [i915]
  [<ffffffff81063852>] ? finish_task_switch+0x72/0x1c0
  [<ffffffff8105ab29>] process_one_work+0x139/0x350
  [<ffffffff8105b186>] worker_thread+0x126/0x490
  [<ffffffff8105b060>] ? rescuer_thread+0x320/0x320
  [<ffffffff8105fa64>] kthread+0xc4/0xe0
  [<ffffffff8105f9a0>] ? kthread_create_on_node+0x170/0x170
  [<ffffffff814f351f>] ret_from_fork+0x3f/0x70
  [<ffffffff8105f9a0>] ? kthread_create_on_node+0x170/0x170

I could not explain, or find a code path, which would explain
a +20 second lockup, but from some instrumentation it was
apparent the interrupts off proportion of time was between
10-25% under heavy load which is quite bad.

When a interrupt "cliff" is reached, which was >~320k irq/s on
my machine, the whole system goes into a terrible state of the
above described multi-second lockups.

By moving the GT interrupt handling to a tasklet in a most
simple way, the problem above disappears completely.

Testing the effect on sytem-wide latencies using
igt/gem_syslatency shows the following before this patch:

gem_syslatency: cycles=1532739, latency mean=416531.829us max=2499237us
gem_syslatency: cycles=1839434, latency mean=1458099.157us max=4998944us
gem_syslatency: cycles=1432570, latency mean=2688.451us max=1201185us
gem_syslatency: cycles=1533543, latency mean=416520.499us max=2498886us

This shows that the unrelated process is experiencing huge
delays in its wake-up latency. After the patch the results
look like this:

gem_syslatency: cycles=808907, latency mean=53.133us max=1640us
gem_syslatency: cycles=862154, latency mean=62.778us max=2117us
gem_syslatency: cycles=856039, latency mean=58.079us max=2123us
gem_syslatency: cycles=841683, latency mean=56.914us max=1667us

Showing a huge improvement in the unrelated process wake-up
latency. It also shows an approximate halving in the number
of total empty batches submitted during the test. This may
not be worrying since the test puts the driver under
a very unrealistic load with ncpu threads doing empty batch
submission to all GPU engines each.

Another benefit compared to the hard-irq handling is that now
work on all engines can be dispatched in parallel since we can
have up to number of CPUs active tasklets. (While previously
a single hard-irq would serially dispatch on one engine after
another.)

More interesting scenario with regards to throughput is
"gem_latency -n 100" which  shows 25% better throughput and
CPU usage, and 14% better dispatch latencies.

I did not find any gains or regressions with Synmark2 or
GLbench under light testing. More benchmarking is certainly
required.

v2:
   * execlists_lock should be taken as spin_lock_bh when
     queuing work from userspace now. (Chris Wilson)
   * uncore.lock must be taken with spin_lock_irq when
     submitting requests since that now runs from either
     softirq or process context.

v3:
   * Expanded commit message with more testing data;
   * converted missed locking sites to _bh;
   * added execlist_lock comment. (Chris Wilson)

v4:
   * Mention dispatch parallelism in commit. (Chris Wilson)
   * Do not hold uncore.lock over MMIO reads since the block
     is already serialised per-engine via the tasklet itself.
     (Chris Wilson)
   * intel_lrc_irq_handler should be static. (Chris Wilson)
   * Cancel/sync the tasklet on GPU reset. (Chris Wilson)
   * Document and WARN that tasklet cannot be active/pending
     on engine cleanup. (Chris Wilson/Imre Deak)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Imre Deak <imre.deak@intel.com>
Testcase: igt/gem_exec_nop/all
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1459768316-6670-1-git-send-email-tvrtko.ursulin@linux.intel.com
2016-04-04 14:08:52 +01:00

124 lines
4.9 KiB
C

/*
* Copyright © 2014 Intel Corporation
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice (including the next
* paragraph) shall be included in all copies or substantial portions of the
* Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
#ifndef _INTEL_LRC_H_
#define _INTEL_LRC_H_
#define GEN8_LR_CONTEXT_ALIGN 4096
/* Execlists regs */
#define RING_ELSP(ring) _MMIO((ring)->mmio_base + 0x230)
#define RING_EXECLIST_STATUS_LO(ring) _MMIO((ring)->mmio_base + 0x234)
#define RING_EXECLIST_STATUS_HI(ring) _MMIO((ring)->mmio_base + 0x234 + 4)
#define RING_CONTEXT_CONTROL(ring) _MMIO((ring)->mmio_base + 0x244)
#define CTX_CTRL_INHIBIT_SYN_CTX_SWITCH (1 << 3)
#define CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT (1 << 0)
#define CTX_CTRL_RS_CTX_ENABLE (1 << 1)
#define RING_CONTEXT_STATUS_BUF_LO(ring, i) _MMIO((ring)->mmio_base + 0x370 + (i) * 8)
#define RING_CONTEXT_STATUS_BUF_HI(ring, i) _MMIO((ring)->mmio_base + 0x370 + (i) * 8 + 4)
#define RING_CONTEXT_STATUS_PTR(ring) _MMIO((ring)->mmio_base + 0x3a0)
/* The docs specify that the write pointer wraps around after 5h, "After status
* is written out to the last available status QW at offset 5h, this pointer
* wraps to 0."
*
* Therefore, one must infer than even though there are 3 bits available, 6 and
* 7 appear to be * reserved.
*/
#define GEN8_CSB_ENTRIES 6
#define GEN8_CSB_PTR_MASK 0x7
#define GEN8_CSB_READ_PTR_MASK (GEN8_CSB_PTR_MASK << 8)
#define GEN8_CSB_WRITE_PTR_MASK (GEN8_CSB_PTR_MASK << 0)
#define GEN8_CSB_WRITE_PTR(csb_status) \
(((csb_status) & GEN8_CSB_WRITE_PTR_MASK) >> 0)
#define GEN8_CSB_READ_PTR(csb_status) \
(((csb_status) & GEN8_CSB_READ_PTR_MASK) >> 8)
/* Logical Rings */
int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request);
int intel_logical_ring_reserve_space(struct drm_i915_gem_request *request);
void intel_logical_ring_stop(struct intel_engine_cs *engine);
void intel_logical_ring_cleanup(struct intel_engine_cs *engine);
int intel_logical_rings_init(struct drm_device *dev);
int intel_logical_ring_begin(struct drm_i915_gem_request *req, int num_dwords);
int logical_ring_flush_all_caches(struct drm_i915_gem_request *req);
/**
* intel_logical_ring_advance() - advance the ringbuffer tail
* @ringbuf: Ringbuffer to advance.
*
* The tail is only updated in our logical ringbuffer struct.
*/
static inline void intel_logical_ring_advance(struct intel_ringbuffer *ringbuf)
{
ringbuf->tail &= ringbuf->size - 1;
}
/**
* intel_logical_ring_emit() - write a DWORD to the ringbuffer.
* @ringbuf: Ringbuffer to write to.
* @data: DWORD to write.
*/
static inline void intel_logical_ring_emit(struct intel_ringbuffer *ringbuf,
u32 data)
{
iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
ringbuf->tail += 4;
}
static inline void intel_logical_ring_emit_reg(struct intel_ringbuffer *ringbuf,
i915_reg_t reg)
{
intel_logical_ring_emit(ringbuf, i915_mmio_reg_offset(reg));
}
/* Logical Ring Contexts */
/* One extra page is added before LRC for GuC as shared data */
#define LRC_GUCSHR_PN (0)
#define LRC_PPHWSP_PN (LRC_GUCSHR_PN + 1)
#define LRC_STATE_PN (LRC_PPHWSP_PN + 1)
void intel_lr_context_free(struct intel_context *ctx);
uint32_t intel_lr_context_size(struct intel_engine_cs *engine);
int intel_lr_context_deferred_alloc(struct intel_context *ctx,
struct intel_engine_cs *engine);
void intel_lr_context_unpin(struct intel_context *ctx,
struct intel_engine_cs *engine);
void intel_lr_context_reset(struct drm_device *dev,
struct intel_context *ctx);
uint64_t intel_lr_context_descriptor(struct intel_context *ctx,
struct intel_engine_cs *engine);
u32 intel_execlists_ctx_id(struct intel_context *ctx,
struct intel_engine_cs *engine);
/* Execlists */
int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);
struct i915_execbuffer_params;
int intel_execlists_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
struct list_head *vmas);
void intel_execlists_retire_requests(struct intel_engine_cs *engine);
#endif /* _INTEL_LRC_H_ */