OpenCloudOS-Kernel/drivers/gpu/drm/i915/intel_ringbuffer.h

282 lines
8.0 KiB
C
Raw Normal View History

#ifndef _INTEL_RINGBUFFER_H_
#define _INTEL_RINGBUFFER_H_
/*
* Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use"
* Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use"
* Gen4+ BSpec "vol1c Memory Interface and Command Stream" / 5.3.4.5 "Ring Buffer Use"
*
* "If the Ring Buffer Head Pointer and the Tail Pointer are on the same
* cacheline, the Head Pointer must not be greater than the Tail
* Pointer."
*/
#define I915_RING_FREE_SPACE 64
struct intel_hw_status_page {
u32 *page_addr;
unsigned int gfx_addr;
struct drm_i915_gem_object *obj;
};
#define I915_READ_TAIL(ring) I915_READ(RING_TAIL((ring)->mmio_base))
#define I915_WRITE_TAIL(ring, val) I915_WRITE(RING_TAIL((ring)->mmio_base), val)
#define I915_READ_START(ring) I915_READ(RING_START((ring)->mmio_base))
#define I915_WRITE_START(ring, val) I915_WRITE(RING_START((ring)->mmio_base), val)
#define I915_READ_HEAD(ring) I915_READ(RING_HEAD((ring)->mmio_base))
#define I915_WRITE_HEAD(ring, val) I915_WRITE(RING_HEAD((ring)->mmio_base), val)
#define I915_READ_CTL(ring) I915_READ(RING_CTL((ring)->mmio_base))
#define I915_WRITE_CTL(ring, val) I915_WRITE(RING_CTL((ring)->mmio_base), val)
#define I915_READ_IMR(ring) I915_READ(RING_IMR((ring)->mmio_base))
#define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
enum intel_ring_hangcheck_action {
HANGCHECK_IDLE = 0,
HANGCHECK_WAIT,
HANGCHECK_ACTIVE,
HANGCHECK_KICK,
HANGCHECK_HUNG,
};
struct intel_ring_hangcheck {
bool deadlock;
u32 seqno;
drm/i915: detect hang using per ring hangcheck_score Keep track of ring seqno progress and if there are no progress detected, declare hang. Use actual head (acthd) to distinguish between ring stuck and batchbuffer looping situation. Stuck ring will be kicked to trigger progress. This commit adds a hard limit for batchbuffer completion time. If batchbuffer completion time is more than 4.5 seconds, the gpu will be declared hung. Review comment from Ben which nicely clarifies the semantic change: "Maybe I'm just stating the functional changes of the patch, but in case they were unintended here is what I see as potential issues: 1. "If ring B is waiting on ring A via semaphore, and ring A is making progress, albeit slowly - the hangcheck will fire. The check will determine that A is moving, however ring B will appear hung because the ACTHD doesn't move. I honestly can't say if that's actually a realistic problem to hit it probably implies the timeout value is too low. 2. "There's also another corner case on the kick. If the seqno = 2 (though not stuck), and on the 3rd hangcheck, the ring is stuck, and we try to kick it... we don't actually try to find out if the kick helped" v2: use atchd to detect stuck ring from loop (Ben Widawsky) v3: Use acthd to check when ring needs kicking. Declare hang on third time in order to give time for kick_ring to take effect. v4: Update commit msg Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com> Reviewed-by: Ben Widawsky <ben@bwidawsk.net> [danvet: Paste in Ben's review comment.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-05-30 14:04:29 +08:00
u32 acthd;
int score;
enum intel_ring_hangcheck_action action;
};
struct intel_ring_buffer {
const char *name;
enum intel_ring_id {
RCS = 0x0,
VCS,
BCS,
VECS,
} id;
#define I915_NUM_RINGS 4
u32 mmio_base;
void __iomem *virtual_start;
struct drm_device *dev;
struct drm_i915_gem_object *obj;
u32 head;
u32 tail;
int space;
int size;
int effective_size;
struct intel_hw_status_page status_page;
drm/i915: Record the tail at each request and use it to estimate the head By recording the location of every request in the ringbuffer, we know that in order to retire the request the GPU must have finished reading it and so the GPU head is now beyond the tail of the request. We can therefore provide a conservative estimate of where the GPU is reading from in order to avoid having to read back the ring buffer registers when polling for space upon starting a new write into the ringbuffer. A secondary effect is that this allows us to convert intel_ring_buffer_wait() to use i915_wait_request() and so consolidate upon the single function to handle the complicated task of waiting upon the GPU. A necessary precaution is that we need to make that wait uninterruptible to match the existing conditions as all the callers of intel_ring_begin() have not been audited to handle ERESTARTSYS correctly. By using a conservative estimate for the head, and always processing all outstanding requests first, we prevent a race condition between using the estimate and direct reads of I915_RING_HEAD which could result in the value of the head going backwards, and the tail overflowing once again. We are also careful to mark any request that we skip over in order to free space in ring as consumed which provides a self-consistency check. Given sufficient abuse, such as a set of unthrottled GPU bound cairo-traces, avoiding the use of I915_RING_HEAD gives a 10-20% boost on Sandy Bridge (i5-2520m): firefox-paintball 18927ms -> 15646ms: 1.21x speedup firefox-fishtank 12563ms -> 11278ms: 1.11x speedup which is a mild consolation for the performance those traces achieved from exploiting the buggy autoreported head. v2: Add a few more comments and make request->tail a conservative estimate as suggested by Daniel Vetter. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> [danvet: resolve conflicts with retirement defering and the lack of the autoreport head removal (that will go in through -fixes).] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2012-02-15 19:25:36 +08:00
/** We track the position of the requests in the ring buffer, and
* when each is retired we increment last_retired_head as the GPU
* must have finished processing the request and so we know we
* can advance the ringbuffer up to that position.
*
* last_retired_head is set to -1 after the value is consumed so
* we can detect new retirements.
*/
u32 last_retired_head;
unsigned irq_refcount; /* protected by dev_priv->irq_lock */
u32 irq_enable_mask; /* bitmask to enable ring interrupt */
u32 trace_irq_seqno;
u32 sync_seqno[I915_NUM_RINGS-1];
bool __must_check (*irq_get)(struct intel_ring_buffer *ring);
void (*irq_put)(struct intel_ring_buffer *ring);
int (*init)(struct intel_ring_buffer *ring);
void (*write_tail)(struct intel_ring_buffer *ring,
u32 value);
int __must_check (*flush)(struct intel_ring_buffer *ring,
u32 invalidate_domains,
u32 flush_domains);
drm/i915: Preallocate next seqno before touching the ring Based on the work by Mika Kuoppala, we realised that we need to handle seqno wraparound prior to committing our changes to the ring. The most obvious point then is to grab the seqno inside intel_ring_begin(), and then to reuse that seqno for all ring operations until the next request. As intel_ring_begin() can fail, the callers must already be prepared to handle such failure and so we can safely add further checks. This patch looks like it should be split up into the interface changes and the tweaks to move seqno wrapping from the execbuffer into the core seqno increment. However, I found no easy way to break it into incremental steps without introducing further broken behaviour. v2: Mika found a silly mistake and a subtle error in the existing code; inside i915_gem_retire_requests() we were resetting the sync_seqno of the target ring based on the seqno from this ring - which are only related by the order of their allocation, not retirement. Hence we were applying the optimisation that the rings were synchronised too early, fortunately the only real casualty there is the handling of seqno wrapping. v3: Do not forget to reset the sync_seqno upon module reinitialisation, ala resume. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=863861 Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> [v2] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2012-11-28 00:22:52 +08:00
int (*add_request)(struct intel_ring_buffer *ring);
/* Some chipsets are not quite as coherent as advertised and need
* an expensive kick to force a true read of the up-to-date seqno.
* However, the up-to-date seqno is not always required and the last
* seen value is good enough. Note that the seqno will always be
* monotonic, even if not coherent.
*/
u32 (*get_seqno)(struct intel_ring_buffer *ring,
bool lazy_coherency);
void (*set_seqno)(struct intel_ring_buffer *ring,
u32 seqno);
int (*dispatch_execbuffer)(struct intel_ring_buffer *ring,
u32 offset, u32 length,
unsigned flags);
#define I915_DISPATCH_SECURE 0x1
#define I915_DISPATCH_PINNED 0x2
void (*cleanup)(struct intel_ring_buffer *ring);
int (*sync_to)(struct intel_ring_buffer *ring,
struct intel_ring_buffer *to,
u32 seqno);
/* our mbox written by others */
u32 semaphore_register[I915_NUM_RINGS];
/* mboxes this ring signals to */
u32 signal_mbox[I915_NUM_RINGS];
/**
* List of objects currently involved in rendering from the
* ringbuffer.
*
* Includes buffers having the contents of their GPU caches
* flushed, not necessarily primitives. last_rendering_seqno
* represents when the rendering involved will be completed.
*
* A reference is held on the buffer while on this list.
*/
struct list_head active_list;
/**
* List of breadcrumbs associated with GPU requests currently
* outstanding.
*/
struct list_head request_list;
/**
* Do we have some not yet emitted requests outstanding?
*/
struct drm_i915_gem_request *preallocated_lazy_request;
u32 outstanding_lazy_seqno;
2012-06-14 02:45:19 +08:00
bool gpu_caches_dirty;
bool fbc_dirty;
wait_queue_head_t irq_queue;
/**
* Do an explicit TLB flush before MI_SET_CONTEXT
*/
bool itlb_before_ctx_switch;
struct i915_hw_context *default_context;
struct i915_hw_context *last_context;
struct intel_ring_hangcheck hangcheck;
struct {
struct drm_i915_gem_object *obj;
u32 gtt_offset;
volatile u32 *cpu_page;
} scratch;
};
static inline bool
intel_ring_initialized(struct intel_ring_buffer *ring)
{
return ring->obj != NULL;
}
static inline unsigned
intel_ring_flag(struct intel_ring_buffer *ring)
{
return 1 << ring->id;
}
static inline u32
intel_ring_sync_index(struct intel_ring_buffer *ring,
struct intel_ring_buffer *other)
{
int idx;
/*
* cs -> 0 = vcs, 1 = bcs
* vcs -> 0 = bcs, 1 = cs,
* bcs -> 0 = cs, 1 = vcs.
*/
idx = (other - ring) - 1;
if (idx < 0)
idx += I915_NUM_RINGS;
return idx;
}
static inline u32
intel_read_status_page(struct intel_ring_buffer *ring,
int reg)
{
/* Ensure that the compiler doesn't optimize away the load. */
barrier();
return ring->status_page.page_addr[reg];
}
static inline void
intel_write_status_page(struct intel_ring_buffer *ring,
int reg, u32 value)
{
ring->status_page.page_addr[reg] = value;
}
/**
* Reads a dword out of the status page, which is written to from the command
* queue by automatic updates, MI_REPORT_HEAD, MI_STORE_DATA_INDEX, or
* MI_STORE_DATA_IMM.
*
* The following dwords have a reserved meaning:
* 0x00: ISR copy, updated when an ISR bit not set in the HWSTAM changes.
* 0x04: ring 0 head pointer
* 0x05: ring 1 head pointer (915-class)
* 0x06: ring 2 head pointer (915-class)
* 0x10-0x1b: Context status DWords (GM45)
* 0x1f: Last written status offset. (GM45)
*
* The area from dword 0x20 to 0x3ff is available for driver usage.
*/
#define I915_GEM_HWS_INDEX 0x20
#define I915_GEM_HWS_SCRATCH_INDEX 0x30
#define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);
int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n);
static inline void intel_ring_emit(struct intel_ring_buffer *ring,
u32 data)
{
iowrite32(data, ring->virtual_start + ring->tail);
ring->tail += 4;
}
drm/i915: Write RING_TAIL once per-request Ignoring the legacy DRI1 code, and a couple of special cases (to be discussed later), all access to the ring is mediated through requests. The first write to a ring will grab a seqno and mark the ring as having an outstanding_lazy_request. Either through explicitly adding a request after an execbuffer or through an implicit wait (either by the CPU or by a semaphore), that sequence of writes will be terminated with a request. So we can ellide all the intervening writes to the tail register and send the entire command stream to the GPU at once. This will reduce the number of *serialising* writes to the tail register by a factor or 3-5 times (depending upon architecture and number of workarounds, context switches, etc involved). This becomes even more noticeable when the register write is overloaded with a number of debugging tools. The astute reader will wonder if it is then possible to overflow the ring with a single command. It is not. When we start a command sequence to the ring, we check for available space and issue a wait in case we have not. The ring wait will in this case be forced to flush the outstanding register write and then poll the ACTHD for sufficient space to continue. The exception to the rule where everything is inside a request are a few initialisation cases where we may want to write GPU commands via the CS before userspace wakes up and page flips. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-08-11 05:16:32 +08:00
static inline void intel_ring_advance(struct intel_ring_buffer *ring)
{
ring->tail &= ring->size - 1;
}
void __intel_ring_advance(struct intel_ring_buffer *ring);
int __must_check intel_ring_idle(struct intel_ring_buffer *ring);
void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno);
int intel_ring_flush_all_caches(struct intel_ring_buffer *ring);
int intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring);
int intel_init_render_ring_buffer(struct drm_device *dev);
int intel_init_bsd_ring_buffer(struct drm_device *dev);
int intel_init_blt_ring_buffer(struct drm_device *dev);
int intel_init_vebox_ring_buffer(struct drm_device *dev);
u32 intel_ring_get_active_head(struct intel_ring_buffer *ring);
void intel_ring_setup_status_page(struct intel_ring_buffer *ring);
drm/i915: Record the tail at each request and use it to estimate the head By recording the location of every request in the ringbuffer, we know that in order to retire the request the GPU must have finished reading it and so the GPU head is now beyond the tail of the request. We can therefore provide a conservative estimate of where the GPU is reading from in order to avoid having to read back the ring buffer registers when polling for space upon starting a new write into the ringbuffer. A secondary effect is that this allows us to convert intel_ring_buffer_wait() to use i915_wait_request() and so consolidate upon the single function to handle the complicated task of waiting upon the GPU. A necessary precaution is that we need to make that wait uninterruptible to match the existing conditions as all the callers of intel_ring_begin() have not been audited to handle ERESTARTSYS correctly. By using a conservative estimate for the head, and always processing all outstanding requests first, we prevent a race condition between using the estimate and direct reads of I915_RING_HEAD which could result in the value of the head going backwards, and the tail overflowing once again. We are also careful to mark any request that we skip over in order to free space in ring as consumed which provides a self-consistency check. Given sufficient abuse, such as a set of unthrottled GPU bound cairo-traces, avoiding the use of I915_RING_HEAD gives a 10-20% boost on Sandy Bridge (i5-2520m): firefox-paintball 18927ms -> 15646ms: 1.21x speedup firefox-fishtank 12563ms -> 11278ms: 1.11x speedup which is a mild consolation for the performance those traces achieved from exploiting the buggy autoreported head. v2: Add a few more comments and make request->tail a conservative estimate as suggested by Daniel Vetter. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> [danvet: resolve conflicts with retirement defering and the lack of the autoreport head removal (that will go in through -fixes).] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2012-02-15 19:25:36 +08:00
static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring)
{
return ring->tail;
}
drm/i915: Preallocate next seqno before touching the ring Based on the work by Mika Kuoppala, we realised that we need to handle seqno wraparound prior to committing our changes to the ring. The most obvious point then is to grab the seqno inside intel_ring_begin(), and then to reuse that seqno for all ring operations until the next request. As intel_ring_begin() can fail, the callers must already be prepared to handle such failure and so we can safely add further checks. This patch looks like it should be split up into the interface changes and the tweaks to move seqno wrapping from the execbuffer into the core seqno increment. However, I found no easy way to break it into incremental steps without introducing further broken behaviour. v2: Mika found a silly mistake and a subtle error in the existing code; inside i915_gem_retire_requests() we were resetting the sync_seqno of the target ring based on the seqno from this ring - which are only related by the order of their allocation, not retirement. Hence we were applying the optimisation that the rings were synchronised too early, fortunately the only real casualty there is the handling of seqno wrapping. v3: Do not forget to reset the sync_seqno upon module reinitialisation, ala resume. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=863861 Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> [v2] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2012-11-28 00:22:52 +08:00
static inline u32 intel_ring_get_seqno(struct intel_ring_buffer *ring)
{
BUG_ON(ring->outstanding_lazy_seqno == 0);
return ring->outstanding_lazy_seqno;
drm/i915: Preallocate next seqno before touching the ring Based on the work by Mika Kuoppala, we realised that we need to handle seqno wraparound prior to committing our changes to the ring. The most obvious point then is to grab the seqno inside intel_ring_begin(), and then to reuse that seqno for all ring operations until the next request. As intel_ring_begin() can fail, the callers must already be prepared to handle such failure and so we can safely add further checks. This patch looks like it should be split up into the interface changes and the tweaks to move seqno wrapping from the execbuffer into the core seqno increment. However, I found no easy way to break it into incremental steps without introducing further broken behaviour. v2: Mika found a silly mistake and a subtle error in the existing code; inside i915_gem_retire_requests() we were resetting the sync_seqno of the target ring based on the seqno from this ring - which are only related by the order of their allocation, not retirement. Hence we were applying the optimisation that the rings were synchronised too early, fortunately the only real casualty there is the handling of seqno wrapping. v3: Do not forget to reset the sync_seqno upon module reinitialisation, ala resume. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=863861 Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> [v2] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2012-11-28 00:22:52 +08:00
}
static inline void i915_trace_irq_get(struct intel_ring_buffer *ring, u32 seqno)
{
if (ring->trace_irq_seqno == 0 && ring->irq_get(ring))
ring->trace_irq_seqno = seqno;
}
drm/i915: Initialise ring vfuncs for old DRI paths We weren't setting up the vfunc table when initialising the old DRI ringbuffer, leading to such OOPSes as: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<(null)>] (null) PGD 10c441067 PUD 1185e5067 PMD 0 Oops: 0010 [#1] PREEMPT SMP last sysfs file: /sys/class/dmi/id/chassis_asset_tag CPU 3 Modules linked in: i915 drm_kms_helper drm fb fbdev i2c_algo_bit cfbcopyarea video backlight output cfbimgblt cfbfillrect autofs4 ipv6 nfs lockd fscache nfs_acl auth_rpcgss sunrpc coretemp hwmon_vid mousedev usbhid hid option usb_wwan snd_hda_codec_via asus_atk0110 atl1e usbserial snd_hda_intel snd_hda_codec firmware_class snd_hwdep snd_pcm snd_seq snd_timer snd_seq_device processor parport_pc thermal snd thermal_sys parport 8250_pnp button rng_core rtc_cmos shpchp hwmon rtc_core ehci_hcd pci_hotplug uhci_hcd soundcore tpm_tis i2c_i801 rtc_lib tpm serio_raw snd_page_alloc tpm_bios i2c_core usbcore psmouse intel_agp sg pcspkr sr_mod evdev cdrom ext3 jbd mbcache dm_mod sd_mod ata_piix libata scsi_mod unix Jan 18 15:49:29 lithui kernel: Pid: 3605, comm: Xorg Not tainted 2.6.36.2 #5 P5KPL-CM/System Product Name RIP: 0010:[<0000000000000000>] [<(null)>] (null) RSP: 0018:ffff8801150d1d40 EFLAGS: 00010202 RAX: 000000000001ffff RBX: ffff88011a011b00 RCX: 000000000001a704 RDX: ffff880118566028 RSI: ffff880118566028 RDI: ffff880117876800 RBP: ffff8801150d1d48 R08: ffff8801195fe300 R09: 00000000c0086444 R10: 0000000000000001 R11: 0000000000003206 R12: ffff880117876800 R13: ffff880118566000 R14: ffff880117876820 R15: ffff8801150d1df8 FS: 00007f1038d456e0(0000) GS:ffff880001780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000001187e7000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process Xorg (pid: 3605, threadinfo ffff8801150d0000, task ffff88011b016e40) Stack: ffffffffa043b8e6 ffff8801150d1d98 ffffffffa041768b dead000000000000 <0> 0000000000000048 00007f1023f2a000 0000000000000044 0000000000000008 <0> ffff88010d26bd80 ffff880117876800 ffff8801150d1df8 ffff8801150d1ea8 Call Trace: [<ffffffffa043b8e6>] ? intel_ring_advance+0x16/0x20 [i915] [<ffffffffa041768b>] i915_irq_emit+0x15b/0x240 [i915] [<ffffffffa03ea7b1>] drm_ioctl+0x1f1/0x460 [drm] [<ffffffffa0417530>] ? i915_irq_emit+0x0/0x240 [i915] [<ffffffff810dd8f1>] ? do_sync_read+0xd1/0x120 [<ffffffff81025b1f>] ? do_page_fault+0x1df/0x3d0 [<ffffffff810ed5c7>] do_vfs_ioctl+0x97/0x550 [<ffffffff8115c2ea>] ? security_file_permission+0x7a/0x90 [<ffffffff810edb19>] sys_ioctl+0x99/0xa0 [<ffffffff810024ab>] system_call_fastpath+0x16/0x1b Code: Bad RIP value. RIP [<(null)>] (null) RSP <ffff8801150d1d40> CR2: 0000000000000000 Reported-by: Herbert Xu <herbert@gondor.apana.org.au> Tested-by: Herbert Xu <herbert@gondor.apana.org.au> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=29153 Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=23172 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: stable@kernel.org
2011-01-20 17:57:11 +08:00
/* DRI warts */
int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size);
#endif /* _INTEL_RINGBUFFER_H_ */