From: j.glisse@gmail.com
To: dri-devel@lists.freedesktop.org
Cc: "Jerome Glisse" <jglisse@redhat.com>,
"Christian König" <deathsimple@vodafone.de>
Subject: [PATCH 16/24] drm/radeon: move lockup detection code into radeon_ring.c v2
Date: Wed, 25 Apr 2012 15:03:21 -0400 [thread overview]
Message-ID: <1335380609-5804-17-git-send-email-j.glisse@gmail.com> (raw)
In-Reply-To: <1335380609-5804-1-git-send-email-j.glisse@gmail.com>
From: Jerome Glisse <jglisse@redhat.com>
It isn't chipset specific, so it makes no sense
to have that inside r100.c.
v2: rebase on debugfs removal
Signed-off-by: Christian König <deathsimple@vodafone.de>
---
drivers/gpu/drm/radeon/evergreen.c | 5 +--
drivers/gpu/drm/radeon/ni.c | 5 +--
drivers/gpu/drm/radeon/r100.c | 57 +--------------------------------
drivers/gpu/drm/radeon/r300.c | 4 +-
drivers/gpu/drm/radeon/r600.c | 10 +-----
drivers/gpu/drm/radeon/radeon.h | 16 ++-------
drivers/gpu/drm/radeon/radeon_asic.h | 5 ---
drivers/gpu/drm/radeon/radeon_ring.c | 53 +++++++++++++++++++++++++++++++
drivers/gpu/drm/radeon/si.c | 5 +--
9 files changed, 69 insertions(+), 91 deletions(-)
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index a76389c..353d10a 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2424,7 +2424,6 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
u32 srbm_status;
u32 grbm_status;
u32 grbm_status_se0, grbm_status_se1;
- struct r100_gpu_lockup *lockup = &rdev->config.evergreen.lockup;
int r;
srbm_status = RREG32(SRBM_STATUS);
@@ -2432,7 +2431,7 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
grbm_status_se0 = RREG32(GRBM_STATUS_SE0);
grbm_status_se1 = RREG32(GRBM_STATUS_SE1);
if (!(grbm_status & GUI_ACTIVE)) {
- r100_gpu_lockup_update(lockup, ring);
+ radeon_ring_lockup_update(ring);
return false;
}
/* force CP activities */
@@ -2444,7 +2443,7 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
radeon_ring_unlock_commit(rdev, ring);
}
ring->rptr = RREG32(CP_RB_RPTR);
- return r100_gpu_cp_is_lockup(rdev, lockup, ring);
+ return radeon_ring_test_lockup(rdev, ring);
}
static int evergreen_gpu_soft_reset(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index c0b0956..4327b32 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1397,7 +1397,6 @@ bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
u32 srbm_status;
u32 grbm_status;
u32 grbm_status_se0, grbm_status_se1;
- struct r100_gpu_lockup *lockup = &rdev->config.cayman.lockup;
int r;
srbm_status = RREG32(SRBM_STATUS);
@@ -1405,7 +1404,7 @@ bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
grbm_status_se0 = RREG32(GRBM_STATUS_SE0);
grbm_status_se1 = RREG32(GRBM_STATUS_SE1);
if (!(grbm_status & GUI_ACTIVE)) {
- r100_gpu_lockup_update(lockup, ring);
+ radeon_ring_lockup_update(ring);
return false;
}
/* force CP activities */
@@ -1418,7 +1417,7 @@ bool cayman_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
}
/* XXX deal with CP0,1,2 */
ring->rptr = RREG32(ring->rptr_reg);
- return r100_gpu_cp_is_lockup(rdev, lockup, ring);
+ return radeon_ring_test_lockup(rdev, ring);
}
static int cayman_gpu_soft_reset(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index be51f7b..0a62ada 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2152,59 +2152,6 @@ int r100_mc_wait_for_idle(struct radeon_device *rdev)
return -1;
}
-void r100_gpu_lockup_update(struct r100_gpu_lockup *lockup, struct radeon_ring *ring)
-{
- lockup->last_cp_rptr = ring->rptr;
- lockup->last_jiffies = jiffies;
-}
-
-/**
- * r100_gpu_cp_is_lockup() - check if CP is lockup by recording information
- * @rdev: radeon device structure
- * @lockup: r100_gpu_lockup structure holding CP lockup tracking informations
- * @cp: radeon_cp structure holding CP information
- *
- * We don't need to initialize the lockup tracking information as we will either
- * have CP rptr to a different value of jiffies wrap around which will force
- * initialization of the lockup tracking informations.
- *
- * A possible false positivie is if we get call after while and last_cp_rptr ==
- * the current CP rptr, even if it's unlikely it might happen. To avoid this
- * if the elapsed time since last call is bigger than 2 second than we return
- * false and update the tracking information. Due to this the caller must call
- * r100_gpu_cp_is_lockup several time in less than 2sec for lockup to be reported
- * the fencing code should be cautious about that.
- *
- * Caller should write to the ring to force CP to do something so we don't get
- * false positive when CP is just gived nothing to do.
- *
- **/
-bool r100_gpu_cp_is_lockup(struct radeon_device *rdev, struct r100_gpu_lockup *lockup, struct radeon_ring *ring)
-{
- unsigned long cjiffies, elapsed;
-
- cjiffies = jiffies;
- if (!time_after(cjiffies, lockup->last_jiffies)) {
- /* likely a wrap around */
- lockup->last_cp_rptr = ring->rptr;
- lockup->last_jiffies = jiffies;
- return false;
- }
- if (ring->rptr != lockup->last_cp_rptr) {
- /* CP is still working no lockup */
- lockup->last_cp_rptr = ring->rptr;
- lockup->last_jiffies = jiffies;
- return false;
- }
- elapsed = jiffies_to_msecs(cjiffies - lockup->last_jiffies);
- if (elapsed >= 10000) {
- dev_err(rdev->dev, "GPU lockup CP stall for more than %lumsec\n", elapsed);
- return true;
- }
- /* give a chance to the GPU ... */
- return false;
-}
-
bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
{
u32 rbbm_status;
@@ -2212,7 +2159,7 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
rbbm_status = RREG32(R_000E40_RBBM_STATUS);
if (!G_000E40_GUI_ACTIVE(rbbm_status)) {
- r100_gpu_lockup_update(&rdev->config.r100.lockup, ring);
+ radeon_ring_lockup_update(ring);
return false;
}
/* force CP activities */
@@ -2224,7 +2171,7 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
radeon_ring_unlock_commit(rdev, ring);
}
ring->rptr = RREG32(ring->rptr_reg);
- return r100_gpu_cp_is_lockup(rdev, &rdev->config.r100.lockup, ring);
+ return radeon_ring_test_lockup(rdev, ring);
}
void r100_bm_disable(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index ae15c10..e46bbd0 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -379,7 +379,7 @@ bool r300_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
rbbm_status = RREG32(R_000E40_RBBM_STATUS);
if (!G_000E40_GUI_ACTIVE(rbbm_status)) {
- r100_gpu_lockup_update(&rdev->config.r300.lockup, ring);
+ radeon_ring_lockup_update(ring);
return false;
}
/* force CP activities */
@@ -391,7 +391,7 @@ bool r300_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
radeon_ring_unlock_commit(rdev, ring);
}
ring->rptr = RREG32(RADEON_CP_RB_RPTR);
- return r100_gpu_cp_is_lockup(rdev, &rdev->config.r300.lockup, ring);
+ return radeon_ring_test_lockup(rdev, ring);
}
int r300_asic_reset(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 24e68fd..87b1d25 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1348,19 +1348,13 @@ bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
u32 srbm_status;
u32 grbm_status;
u32 grbm_status2;
- struct r100_gpu_lockup *lockup;
int r;
- if (rdev->family >= CHIP_RV770)
- lockup = &rdev->config.rv770.lockup;
- else
- lockup = &rdev->config.r600.lockup;
-
srbm_status = RREG32(R_000E50_SRBM_STATUS);
grbm_status = RREG32(R_008010_GRBM_STATUS);
grbm_status2 = RREG32(R_008014_GRBM_STATUS2);
if (!G_008010_GUI_ACTIVE(grbm_status)) {
- r100_gpu_lockup_update(lockup, ring);
+ radeon_ring_lockup_update(ring);
return false;
}
/* force CP activities */
@@ -1372,7 +1366,7 @@ bool r600_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
radeon_ring_unlock_commit(rdev, ring);
}
ring->rptr = RREG32(ring->rptr_reg);
- return r100_gpu_cp_is_lockup(rdev, lockup, ring);
+ return radeon_ring_test_lockup(rdev, ring);
}
int r600_asic_reset(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 6ec4025..c0ed077 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -588,6 +588,8 @@ struct radeon_ring {
unsigned ring_size;
unsigned ring_free_dw;
int count_dw;
+ unsigned long last_activity;
+ unsigned last_rptr;
uint64_t gpu_addr;
uint32_t align_mask;
uint32_t ptr_mask;
@@ -731,6 +733,8 @@ void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *cp);
void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *cp);
void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *cp);
int radeon_ring_test(struct radeon_device *rdev, struct radeon_ring *cp);
+void radeon_ring_lockup_update(struct radeon_ring *ring);
+bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ring_size,
unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop);
@@ -1180,16 +1184,10 @@ struct radeon_asic {
/*
* Asic structures
*/
-struct r100_gpu_lockup {
- unsigned long last_jiffies;
- u32 last_cp_rptr;
-};
-
struct r100_asic {
const unsigned *reg_safe_bm;
unsigned reg_safe_bm_size;
u32 hdp_cntl;
- struct r100_gpu_lockup lockup;
};
struct r300_asic {
@@ -1197,7 +1195,6 @@ struct r300_asic {
unsigned reg_safe_bm_size;
u32 resync_scratch;
u32 hdp_cntl;
- struct r100_gpu_lockup lockup;
};
struct r600_asic {
@@ -1219,7 +1216,6 @@ struct r600_asic {
unsigned tiling_group_size;
unsigned tile_config;
unsigned backend_map;
- struct r100_gpu_lockup lockup;
};
struct rv770_asic {
@@ -1245,7 +1241,6 @@ struct rv770_asic {
unsigned tiling_group_size;
unsigned tile_config;
unsigned backend_map;
- struct r100_gpu_lockup lockup;
};
struct evergreen_asic {
@@ -1272,7 +1267,6 @@ struct evergreen_asic {
unsigned tiling_group_size;
unsigned tile_config;
unsigned backend_map;
- struct r100_gpu_lockup lockup;
};
struct cayman_asic {
@@ -1311,7 +1305,6 @@ struct cayman_asic {
unsigned multi_gpu_tile_size;
unsigned tile_config;
- struct r100_gpu_lockup lockup;
};
struct si_asic {
@@ -1342,7 +1335,6 @@ struct si_asic {
unsigned multi_gpu_tile_size;
unsigned tile_config;
- struct r100_gpu_lockup lockup;
};
union radeon_asic_config {
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 6f31f9a..84f3552 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -100,11 +100,6 @@ void r100_pci_gart_fini(struct radeon_device *rdev);
int r100_pci_gart_enable(struct radeon_device *rdev);
void r100_pci_gart_disable(struct radeon_device *rdev);
int r100_gui_wait_for_idle(struct radeon_device *rdev);
-void r100_gpu_lockup_update(struct r100_gpu_lockup *lockup,
- struct radeon_ring *cp);
-bool r100_gpu_cp_is_lockup(struct radeon_device *rdev,
- struct r100_gpu_lockup *lockup,
- struct radeon_ring *cp);
void r100_ib_fini(struct radeon_device *rdev);
int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
void r100_irq_disable(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index c8deae9..f2dfcbf 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -325,6 +325,59 @@ void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *rin
mutex_unlock(&ring->mutex);
}
+void radeon_ring_lockup_update(struct radeon_ring *ring)
+{
+ ring->last_rptr = ring->rptr;
+ ring->last_activity = jiffies;
+}
+
+/**
+ * radeon_ring_test_lockup() - check if ring is lockedup by recording information
+ * @rdev: radeon device structure
+ * @ring: radeon_ring structure holding ring information
+ *
+ * We don't need to initialize the lockup tracking information as we will either
+ * have CP rptr to a different value of jiffies wrap around which will force
+ * initialization of the lockup tracking informations.
+ *
+ * A possible false positivie is if we get call after while and last_cp_rptr ==
+ * the current CP rptr, even if it's unlikely it might happen. To avoid this
+ * if the elapsed time since last call is bigger than 2 second than we return
+ * false and update the tracking information. Due to this the caller must call
+ * radeon_ring_test_lockup several time in less than 2sec for lockup to be reported
+ * the fencing code should be cautious about that.
+ *
+ * Caller should write to the ring to force CP to do something so we don't get
+ * false positive when CP is just gived nothing to do.
+ *
+ **/
+bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+ unsigned long cjiffies, elapsed;
+ uint32_t rptr;
+
+ cjiffies = jiffies;
+ if (!time_after(cjiffies, ring->last_activity)) {
+ /* likely a wrap around */
+ radeon_ring_lockup_update(ring);
+ return false;
+ }
+ rptr = RREG32(ring->rptr_reg);
+ ring->rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
+ if (ring->rptr != ring->last_rptr) {
+ /* CP is still working no lockup */
+ radeon_ring_lockup_update(ring);
+ return false;
+ }
+ elapsed = jiffies_to_msecs(cjiffies - ring->last_activity);
+ if (elapsed >= 10000) {
+ dev_err(rdev->dev, "GPU lockup CP stall for more than %lumsec\n", elapsed);
+ return true;
+ }
+ /* give a chance to the GPU ... */
+ return false;
+}
+
int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size,
unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index ebe2c9b..1bd5670 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2217,7 +2217,6 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
u32 srbm_status;
u32 grbm_status, grbm_status2;
u32 grbm_status_se0, grbm_status_se1;
- struct r100_gpu_lockup *lockup = &rdev->config.si.lockup;
int r;
srbm_status = RREG32(SRBM_STATUS);
@@ -2226,7 +2225,7 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
grbm_status_se0 = RREG32(GRBM_STATUS_SE0);
grbm_status_se1 = RREG32(GRBM_STATUS_SE1);
if (!(grbm_status & GUI_ACTIVE)) {
- r100_gpu_lockup_update(lockup, ring);
+ radeon_ring_lockup_update(ring);
return false;
}
/* force CP activities */
@@ -2239,7 +2238,7 @@ bool si_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
}
/* XXX deal with CP0,1,2 */
ring->rptr = RREG32(ring->rptr_reg);
- return r100_gpu_cp_is_lockup(rdev, lockup, ring);
+ return radeon_ring_test_lockup(rdev, ring);
}
static int si_gpu_soft_reset(struct radeon_device *rdev)
--
1.7.7.6
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2012-04-25 19:04 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-04-25 19:03 Reworking of GPU reset logic + dumping j.glisse
2012-04-25 19:03 ` [PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files j.glisse
2012-04-26 9:11 ` Christian König
2012-04-26 9:18 ` David Airlie
2012-04-26 13:36 ` Jerome Glisse
2012-04-26 13:58 ` Alex Deucher
2012-04-25 19:03 ` [PATCH 02/24] drm/radeon: make radeon_gpu_is_lockup a per ring function j.glisse
2012-04-25 19:03 ` [PATCH 03/24] drm/radeon: replace gpu_lockup with ring->ready flag j.glisse
2012-04-25 19:03 ` [PATCH 04/24] drm/radeon: use central function for IB testing j.glisse
2012-04-25 19:03 ` [PATCH 05/24] drm/radeon: rework gpu lockup detection and processing j.glisse
2012-04-25 19:03 ` [PATCH 06/24] drm/radeon: fix a critical bug in the SA code j.glisse
2012-04-25 19:03 ` [PATCH 07/24] drm/radeon: add proper locking to the SA v2 j.glisse
2012-04-25 19:03 ` [PATCH 08/24] drm/radeon: add biggest hole tracking and wakequeue to the sa v4 j.glisse
2012-04-25 19:03 ` [PATCH 09/24] drm/radeon: simplify semaphore handling j.glisse
2012-04-25 19:03 ` [PATCH 10/24] drm/radeon: return -ENOENT in fence_wait_next v2 j.glisse
2012-04-25 19:03 ` [PATCH 11/24] drm/radeon: rename fence_wait_last to fence_wait_empty j.glisse
2012-04-25 19:03 ` [PATCH 12/24] drm/radeon: rip out the ib pool v2 j.glisse
2012-04-25 19:03 ` [PATCH 13/24] drm/radeon: fix a bug with the ring syncing code j.glisse
2012-04-25 19:03 ` [PATCH 14/24] drm/radeon: rework recursive gpu reset handling j.glisse
2012-04-25 19:03 ` [PATCH 15/24] drm/radeon: remove recursive mutex implementation j.glisse
2012-04-25 19:03 ` j.glisse [this message]
2012-04-25 19:03 ` [PATCH 17/24] drm/radeon: make lockup timeout a module param j.glisse
2012-04-25 19:03 ` [PATCH 18/24] drm/radeon: unlock the ring mutex while waiting for the next fence j.glisse
2012-04-25 19:03 ` [PATCH 19/24] drm/radeon: make forcing ring activity a common function j.glisse
2012-04-25 19:03 ` [PATCH 20/24] drm/radeon: remove r300_gpu_is_lockup j.glisse
2012-04-25 19:03 ` [PATCH 21/24] drm/radeon: remove cayman_gpu_is_lockup j.glisse
2012-04-25 19:03 ` [PATCH 22/24] drm/radeon: extend ring debugfs files with fence info c2 j.glisse
2012-04-25 19:03 ` [PATCH 23/24] drm/radeon: keep the cs relocs inside the ib j.glisse
2012-04-25 19:03 ` [PATCH 24/24] drm/radeon: add faulty command buffer dump facilities j.glisse
2012-04-25 21:53 ` Luca Tettamanti
2012-04-25 22:30 ` Jerome Glisse
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1335380609-5804-17-git-send-email-j.glisse@gmail.com \
--to=j.glisse@gmail.com \
--cc=deathsimple@vodafone.de \
--cc=dri-devel@lists.freedesktop.org \
--cc=jglisse@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.