From e8616b6ced6137085e6657cc63bc2fe3900b8616 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 20 Jan 2011 09:57:11 +0000
Subject: 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
---
drivers/gpu/drm/i915/intel_ringbuffer.c | 42 +++++++++++++++++++++++++++++++++
1 file changed, 42 insertions(+)
(limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c')
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 03e337072517..51fbc5e33c55 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1291,6 +1291,48 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
return intel_init_ring_buffer(dev, ring);
}
+int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
+{
+ drm_i915_private_t *dev_priv = dev->dev_private;
+ struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+
+ *ring = render_ring;
+ if (INTEL_INFO(dev)->gen >= 6) {
+ ring->add_request = gen6_add_request;
+ ring->irq_get = gen6_render_ring_get_irq;
+ ring->irq_put = gen6_render_ring_put_irq;
+ } else if (IS_GEN5(dev)) {
+ ring->add_request = pc_render_add_request;
+ ring->get_seqno = pc_render_get_seqno;
+ }
+
+ ring->dev = dev;
+ INIT_LIST_HEAD(&ring->active_list);
+ INIT_LIST_HEAD(&ring->request_list);
+ INIT_LIST_HEAD(&ring->gpu_write_list);
+
+ ring->size = size;
+ ring->effective_size = ring->size;
+ if (IS_I830(ring->dev))
+ ring->effective_size -= 128;
+
+ ring->map.offset = start;
+ ring->map.size = size;
+ ring->map.type = 0;
+ ring->map.flags = 0;
+ ring->map.mtrr = 0;
+
+ drm_core_ioremap_wc(&ring->map, dev);
+ if (ring->map.handle == NULL) {
+ DRM_ERROR("can not ioremap virtual address for"
+ " ring buffer\n");
+ return -ENOMEM;
+ }
+
+ ring->virtual_start = (void __force __iomem *)ring->map.handle;
+ return 0;
+}
+
int intel_init_bsd_ring_buffer(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
--
cgit v1.2.3
From c7dca47bd6fbb7c215cb1ce6bc40398b4b017752 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 20 Jan 2011 17:00:10 +0000
Subject: drm/i915/ringbuffer: Fix use of stale HEAD position whilst polling
for space
During suspend, Linus found that his machine would hang for 3 seconds,
and identified that intel_ring_buffer_wait() was the culprit:
"Because from looking at the code, I get the notion that
"intel_read_status_page()" may not be exact. But what happens if that
inexact value matches our cached ring->actual_head, so we never even
try to read the exact case? Does it _stay_ inexact for arbitrarily
long times? If so, we might wait for the ring to empty forever (well,
until the timeout - the behavior I see), even though the ring really
_is_ empty."
As the reported HEAD position is only updated every time it crosses a
64k boundary, whilst draining the ring it is indeed likely to remain one
value. If that value matches the last known HEAD position, we never read
the true value from the register and so trigger a timeout.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/intel_ringbuffer.c | 40 ++++++++++++++++++++-------------
drivers/gpu/drm/i915/intel_ringbuffer.h | 1 -
2 files changed, 24 insertions(+), 17 deletions(-)
(limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c')
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 51fbc5e33c55..6218fa97aa1e 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -34,6 +34,14 @@
#include "i915_trace.h"
#include "intel_drv.h"
+static inline int ring_space(struct intel_ring_buffer *ring)
+{
+ int space = (ring->head & HEAD_ADDR) - (ring->tail + 8);
+ if (space < 0)
+ space += ring->size;
+ return space;
+}
+
static u32 i915_gem_get_seqno(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
@@ -204,11 +212,9 @@ static int init_ring_common(struct intel_ring_buffer *ring)
if (!drm_core_check_feature(ring->dev, DRIVER_MODESET))
i915_kernel_lost_context(ring->dev);
else {
- ring->head = I915_READ_HEAD(ring) & HEAD_ADDR;
+ ring->head = I915_READ_HEAD(ring);
ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
- ring->space = ring->head - (ring->tail + 8);
- if (ring->space < 0)
- ring->space += ring->size;
+ ring->space = ring_space(ring);
}
return 0;
@@ -921,7 +927,7 @@ static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring)
}
ring->tail = 0;
- ring->space = ring->head - 8;
+ ring->space = ring_space(ring);
return 0;
}
@@ -933,20 +939,22 @@ int intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n)
unsigned long end;
u32 head;
+ /* If the reported head position has wrapped or hasn't advanced,
+ * fallback to the slow and accurate path.
+ */
+ head = intel_read_status_page(ring, 4);
+ if (head > ring->head) {
+ ring->head = head;
+ ring->space = ring_space(ring);
+ if (ring->space >= n)
+ return 0;
+ }
+
trace_i915_ring_wait_begin (dev);
end = jiffies + 3 * HZ;
do {
- /* If the reported head position has wrapped or hasn't advanced,
- * fallback to the slow and accurate path.
- */
- head = intel_read_status_page(ring, 4);
- if (head < ring->actual_head)
- head = I915_READ_HEAD(ring);
- ring->actual_head = head;
- ring->head = head & HEAD_ADDR;
- ring->space = ring->head - (ring->tail + 8);
- if (ring->space < 0)
- ring->space += ring->size;
+ ring->head = I915_READ_HEAD(ring);
+ ring->space = ring_space(ring);
if (ring->space >= n) {
trace_i915_ring_wait_end(dev);
return 0;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 61d5220c4b58..6d6fde85a636 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -47,7 +47,6 @@ struct intel_ring_buffer {
struct drm_device *dev;
struct drm_i915_gem_object *obj;
- u32 actual_head;
u32 head;
u32 tail;
int space;
--
cgit v1.2.3
From 71a77e07d0e33b57d4a50c173e5ce4fabceddbec Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 2 Feb 2011 12:13:49 +0000
Subject: drm/i915: Invalidate TLB caches on SNB BLT/BSD rings
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@kernel.org
---
drivers/gpu/drm/i915/i915_reg.h | 4 +++-
drivers/gpu/drm/i915/intel_ringbuffer.c | 26 ++++++++++++++++----------
2 files changed, 19 insertions(+), 11 deletions(-)
(limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c')
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5cfc68940f17..15d94c63918c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -174,7 +174,9 @@
* address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
*/
#define MI_LOAD_REGISTER_IMM(x) MI_INSTR(0x22, 2*x-1)
-#define MI_FLUSH_DW MI_INSTR(0x26, 2) /* for GEN6 */
+#define MI_FLUSH_DW MI_INSTR(0x26, 1) /* for GEN6 */
+#define MI_INVALIDATE_TLB (1<<18)
+#define MI_INVALIDATE_BSD (1<<7)
#define MI_BATCH_BUFFER MI_INSTR(0x30, 1)
#define MI_BATCH_NON_SECURE (1)
#define MI_BATCH_NON_SECURE_I965 (1<<8)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 6218fa97aa1e..445f27efe677 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1059,22 +1059,25 @@ static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring,
}
static int gen6_ring_flush(struct intel_ring_buffer *ring,
- u32 invalidate_domains,
- u32 flush_domains)
+ u32 invalidate, u32 flush)
{
+ uint32_t cmd;
int ret;
- if ((flush_domains & I915_GEM_DOMAIN_RENDER) == 0)
+ if (((invalidate | flush) & I915_GEM_GPU_DOMAINS) == 0)
return 0;
ret = intel_ring_begin(ring, 4);
if (ret)
return ret;
- intel_ring_emit(ring, MI_FLUSH_DW);
- intel_ring_emit(ring, 0);
+ cmd = MI_FLUSH_DW;
+ if (invalidate & I915_GEM_GPU_DOMAINS)
+ cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD;
+ intel_ring_emit(ring, cmd);
intel_ring_emit(ring, 0);
intel_ring_emit(ring, 0);
+ intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
return 0;
}
@@ -1230,22 +1233,25 @@ static int blt_ring_begin(struct intel_ring_buffer *ring,
}
static int blt_ring_flush(struct intel_ring_buffer *ring,
- u32 invalidate_domains,
- u32 flush_domains)
+ u32 invalidate, u32 flush)
{
+ uint32_t cmd;
int ret;
- if ((flush_domains & I915_GEM_DOMAIN_RENDER) == 0)
+ if (((invalidate | flush) & I915_GEM_DOMAIN_RENDER) == 0)
return 0;
ret = blt_ring_begin(ring, 4);
if (ret)
return ret;
- intel_ring_emit(ring, MI_FLUSH_DW);
- intel_ring_emit(ring, 0);
+ cmd = MI_FLUSH_DW;
+ if (invalidate & I915_GEM_DOMAIN_RENDER)
+ cmd |= MI_INVALIDATE_TLB;
+ intel_ring_emit(ring, cmd);
intel_ring_emit(ring, 0);
intel_ring_emit(ring, 0);
+ intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
return 0;
}
--
cgit v1.2.3