* [PATCH 01/20] drm/msm: remove dangling submitqueue references
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 06/20] drm/msm/gpu: add dev_to_gpu() helper Rob Clark
` (10 subsequent siblings)
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter,
open list:DRM DRIVER FOR MSM ADRENO GPU, open list
From: Rob Clark <robdclark@chromium.org>
Currently it doesn't matter, since we free the ctx immediately. But
when we start refcnt'ing the ctx, we don't want old dangling list
entries to hang around.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
---
drivers/gpu/drm/msm/msm_submitqueue.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index a1d94be7883a..90c9d84e6155 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -49,8 +49,10 @@ void msm_submitqueue_close(struct msm_file_private *ctx)
* No lock needed in close and there won't
* be any more user ioctls coming our way
*/
- list_for_each_entry_safe(entry, tmp, &ctx->submitqueues, node)
+ list_for_each_entry_safe(entry, tmp, &ctx->submitqueues, node) {
+ list_del(&entry->node);
msm_submitqueue_put(entry);
+ }
}
int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 06/20] drm/msm/gpu: add dev_to_gpu() helper
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
2020-08-24 18:37 ` [PATCH 01/20] drm/msm: remove dangling submitqueue references Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 07/20] drm/msm: set adreno_smmu as gpu's drvdata Rob Clark
` (9 subsequent siblings)
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter, Shawn Guo,
Sharat Masetty, open list:DRM DRIVER FOR MSM ADRENO GPU,
open list
From: Rob Clark <robdclark@chromium.org>
In a later patch, the drvdata will not directly be 'struct msm_gpu *',
so add a helper to reduce the churn.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
---
drivers/gpu/drm/msm/adreno/adreno_device.c | 10 ++++------
drivers/gpu/drm/msm/msm_gpu.c | 6 +++---
drivers/gpu/drm/msm/msm_gpu.h | 5 +++++
3 files changed, 12 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 9eeb46bf2a5d..26664e1b30c0 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -282,7 +282,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
int ret;
if (pdev)
- gpu = platform_get_drvdata(pdev);
+ gpu = dev_to_gpu(&pdev->dev);
if (!gpu) {
dev_err_once(dev->dev, "no GPU device was found\n");
@@ -425,7 +425,7 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
static void adreno_unbind(struct device *dev, struct device *master,
void *data)
{
- struct msm_gpu *gpu = dev_get_drvdata(dev);
+ struct msm_gpu *gpu = dev_to_gpu(dev);
pm_runtime_force_suspend(dev);
gpu->funcs->destroy(gpu);
@@ -490,16 +490,14 @@ static const struct of_device_id dt_match[] = {
#ifdef CONFIG_PM
static int adreno_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct msm_gpu *gpu = platform_get_drvdata(pdev);
+ struct msm_gpu *gpu = dev_to_gpu(dev);
return gpu->funcs->pm_resume(gpu);
}
static int adreno_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct msm_gpu *gpu = platform_get_drvdata(pdev);
+ struct msm_gpu *gpu = dev_to_gpu(dev);
return gpu->funcs->pm_suspend(gpu);
}
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index d5645472b25d..6aa9e04e52e7 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -24,7 +24,7 @@
static int msm_devfreq_target(struct device *dev, unsigned long *freq,
u32 flags)
{
- struct msm_gpu *gpu = platform_get_drvdata(to_platform_device(dev));
+ struct msm_gpu *gpu = dev_to_gpu(dev);
struct dev_pm_opp *opp;
opp = devfreq_recommended_opp(dev, freq, flags);
@@ -45,7 +45,7 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq,
static int msm_devfreq_get_dev_status(struct device *dev,
struct devfreq_dev_status *status)
{
- struct msm_gpu *gpu = platform_get_drvdata(to_platform_device(dev));
+ struct msm_gpu *gpu = dev_to_gpu(dev);
ktime_t time;
if (gpu->funcs->gpu_get_freq)
@@ -64,7 +64,7 @@ static int msm_devfreq_get_dev_status(struct device *dev,
static int msm_devfreq_get_cur_freq(struct device *dev, unsigned long *freq)
{
- struct msm_gpu *gpu = platform_get_drvdata(to_platform_device(dev));
+ struct msm_gpu *gpu = dev_to_gpu(dev);
if (gpu->funcs->gpu_get_freq)
*freq = gpu->funcs->gpu_get_freq(gpu);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 0db117a7339b..8bda7beaed4b 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -141,6 +141,11 @@ struct msm_gpu {
struct msm_gpu_state *crashstate;
};
+static inline struct msm_gpu *dev_to_gpu(struct device *dev)
+{
+ return dev_get_drvdata(dev);
+}
+
/* It turns out that all targets use the same ringbuffer size */
#define MSM_GPU_RINGBUFFER_SZ SZ_32K
#define MSM_GPU_RINGBUFFER_BLKSIZE 32
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 07/20] drm/msm: set adreno_smmu as gpu's drvdata
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
2020-08-24 18:37 ` [PATCH 01/20] drm/msm: remove dangling submitqueue references Rob Clark
2020-08-24 18:37 ` [PATCH 06/20] drm/msm/gpu: add dev_to_gpu() helper Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 11/20] drm/msm: Add a context pointer to the submitqueue Rob Clark
` (8 subsequent siblings)
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter, Shawn Guo,
Sharat Masetty, open list:DRM DRIVER FOR MSM ADRENO GPU,
open list
From: Rob Clark <robdclark@chromium.org>
This will be populated by adreno-smmu, to provide a way for coordinating
enabling/disabling TTBR0 translation.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
---
drivers/gpu/drm/msm/adreno/adreno_device.c | 2 --
drivers/gpu/drm/msm/msm_gpu.c | 2 +-
drivers/gpu/drm/msm/msm_gpu.h | 6 +++++-
3 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 26664e1b30c0..58e03b20e1c7 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -417,8 +417,6 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
return PTR_ERR(gpu);
}
- dev_set_drvdata(dev, gpu);
-
return 0;
}
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 6aa9e04e52e7..806eb0957280 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -892,7 +892,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
gpu->gpu_cx = NULL;
gpu->pdev = pdev;
- platform_set_drvdata(pdev, gpu);
+ platform_set_drvdata(pdev, &gpu->adreno_smmu);
msm_devfreq_init(gpu);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 8bda7beaed4b..f91b141add75 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -7,6 +7,7 @@
#ifndef __MSM_GPU_H__
#define __MSM_GPU_H__
+#include <linux/adreno-smmu-priv.h>
#include <linux/clk.h>
#include <linux/interconnect.h>
#include <linux/pm_opp.h>
@@ -73,6 +74,8 @@ struct msm_gpu {
struct platform_device *pdev;
const struct msm_gpu_funcs *funcs;
+ struct adreno_smmu_priv adreno_smmu;
+
/* performance counters (hw & sw): */
spinlock_t perf_lock;
bool perfcntr_active;
@@ -143,7 +146,8 @@ struct msm_gpu {
static inline struct msm_gpu *dev_to_gpu(struct device *dev)
{
- return dev_get_drvdata(dev);
+ struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev);
+ return container_of(adreno_smmu, struct msm_gpu, adreno_smmu);
}
/* It turns out that all targets use the same ringbuffer size */
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 11/20] drm/msm: Add a context pointer to the submitqueue
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
` (2 preceding siblings ...)
2020-08-24 18:37 ` [PATCH 07/20] drm/msm: set adreno_smmu as gpu's drvdata Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 12/20] drm/msm: Drop context arg to gpu->submit() Rob Clark
` (7 subsequent siblings)
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter,
open list:DRM DRIVER FOR MSM ADRENO GPU, open list
From: Jordan Crouse <jcrouse@codeaurora.org>
Each submitqueue is attached to a context. Add a pointer to the
context to the submitqueue at create time and refcount it so
that it stays around through the life of the queue.
Co-developed-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/msm_drv.c | 3 ++-
drivers/gpu/drm/msm/msm_drv.h | 20 ++++++++++++++++++++
drivers/gpu/drm/msm/msm_gem.h | 1 +
drivers/gpu/drm/msm/msm_gem_submit.c | 6 +++---
drivers/gpu/drm/msm/msm_gpu.h | 1 +
drivers/gpu/drm/msm/msm_submitqueue.c | 3 +++
6 files changed, 30 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 79333842f70a..75cd7639f560 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -594,6 +594,7 @@ static int context_init(struct drm_device *dev, struct drm_file *file)
if (!ctx)
return -ENOMEM;
+ kref_init(&ctx->ref);
msm_submitqueue_init(dev, ctx);
ctx->aspace = priv->gpu ? priv->gpu->aspace : NULL;
@@ -615,7 +616,7 @@ static int msm_open(struct drm_device *dev, struct drm_file *file)
static void context_close(struct msm_file_private *ctx)
{
msm_submitqueue_close(ctx);
- kfree(ctx);
+ msm_file_private_put(ctx);
}
static void msm_postclose(struct drm_device *dev, struct drm_file *file)
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index af259b0573ea..4561bfb5e745 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -57,6 +57,7 @@ struct msm_file_private {
struct list_head submitqueues;
int queueid;
struct msm_gem_address_space *aspace;
+ struct kref ref;
};
enum msm_mdp_plane_property {
@@ -428,6 +429,25 @@ void msm_submitqueue_close(struct msm_file_private *ctx);
void msm_submitqueue_destroy(struct kref *kref);
+static inline void __msm_file_private_destroy(struct kref *kref)
+{
+ struct msm_file_private *ctx = container_of(kref,
+ struct msm_file_private, ref);
+
+ kfree(ctx);
+}
+
+static inline void msm_file_private_put(struct msm_file_private *ctx)
+{
+ kref_put(&ctx->ref, __msm_file_private_destroy);
+}
+
+static inline struct msm_file_private *msm_file_private_get(
+ struct msm_file_private *ctx)
+{
+ kref_get(&ctx->ref);
+ return ctx;
+}
#define DBG(fmt, ...) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__)
#define VERB(fmt, ...) if (0) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__)
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 972490b14ba5..9c573c4269cb 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -142,6 +142,7 @@ struct msm_gem_submit {
bool valid; /* true if no cmdstream patching needed */
bool in_rb; /* "sudo" mode, copy cmds into RB */
struct msm_ringbuffer *ring;
+ struct msm_file_private *ctx;
unsigned int nr_cmds;
unsigned int nr_bos;
u32 ident; /* A "identifier" for the submit for logging */
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 8cb9aa15ff90..1464b04d25d3 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -27,7 +27,7 @@
#define BO_PINNED 0x2000
static struct msm_gem_submit *submit_create(struct drm_device *dev,
- struct msm_gpu *gpu, struct msm_gem_address_space *aspace,
+ struct msm_gpu *gpu,
struct msm_gpu_submitqueue *queue, uint32_t nr_bos,
uint32_t nr_cmds)
{
@@ -43,7 +43,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
return NULL;
submit->dev = dev;
- submit->aspace = aspace;
+ submit->aspace = queue->ctx->aspace;
submit->gpu = gpu;
submit->fence = NULL;
submit->cmd = (void *)&submit->bos[nr_bos];
@@ -677,7 +677,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
}
}
- submit = submit_create(dev, gpu, ctx->aspace, queue, args->nr_bos,
+ submit = submit_create(dev, gpu, queue, args->nr_bos,
args->nr_cmds);
if (!submit) {
ret = -ENOMEM;
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index f91b141add75..97c527e98391 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -190,6 +190,7 @@ struct msm_gpu_submitqueue {
u32 flags;
u32 prio;
int faults;
+ struct msm_file_private *ctx;
struct list_head node;
struct kref ref;
};
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 90c9d84e6155..c3d206105d28 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -12,6 +12,8 @@ void msm_submitqueue_destroy(struct kref *kref)
struct msm_gpu_submitqueue *queue = container_of(kref,
struct msm_gpu_submitqueue, ref);
+ msm_file_private_put(queue->ctx);
+
kfree(queue);
}
@@ -83,6 +85,7 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
write_lock(&ctx->queuelock);
+ queue->ctx = msm_file_private_get(ctx);
queue->id = ctx->queueid++;
if (id)
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 12/20] drm/msm: Drop context arg to gpu->submit()
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
` (3 preceding siblings ...)
2020-08-24 18:37 ` [PATCH 11/20] drm/msm: Add a context pointer to the submitqueue Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 13/20] drm/msm: Set the global virtual address range from the IOMMU domain Rob Clark
` (6 subsequent siblings)
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter,
Thomas Zimmermann, Emil Velikov, Sharat Masetty, Fabio Estevam,
Wambui Karuga, Shawn Guo, open list:DRM DRIVER FOR MSM ADRENO GPU,
open list
From: Jordan Crouse <jcrouse@codeaurora.org>
Now that we can get the ctx from the submitqueue, the extra arg is
redundant.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
[split out of previous patch to reduce churny noise]
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 12 +++++-------
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 5 ++---
drivers/gpu/drm/msm/adreno/adreno_gpu.c | 5 ++---
drivers/gpu/drm/msm/adreno/adreno_gpu.h | 3 +--
drivers/gpu/drm/msm/msm_gem_submit.c | 2 +-
drivers/gpu/drm/msm/msm_gpu.c | 9 ++++-----
drivers/gpu/drm/msm/msm_gpu.h | 6 ++----
7 files changed, 17 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 9e63a190642c..eff2439ea57b 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -43,8 +43,7 @@ static void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
gpu_write(gpu, REG_A5XX_CP_RB_WPTR, wptr);
}
-static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit,
- struct msm_file_private *ctx)
+static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit)
{
struct msm_drm_private *priv = gpu->dev->dev_private;
struct msm_ringbuffer *ring = submit->ring;
@@ -57,7 +56,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit
case MSM_SUBMIT_CMD_IB_TARGET_BUF:
break;
case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
- if (priv->lastctx == ctx)
+ if (priv->lastctx == submit->queue->ctx)
break;
/* fall-thru */
case MSM_SUBMIT_CMD_BUF:
@@ -103,8 +102,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit
msm_gpu_retire(gpu);
}
-static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
- struct msm_file_private *ctx)
+static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
@@ -114,7 +112,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
if (IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) && submit->in_rb) {
priv->lastctx = NULL;
- a5xx_submit_in_rb(gpu, submit, ctx);
+ a5xx_submit_in_rb(gpu, submit);
return;
}
@@ -148,7 +146,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
case MSM_SUBMIT_CMD_IB_TARGET_BUF:
break;
case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
- if (priv->lastctx == ctx)
+ if (priv->lastctx == submit->queue->ctx)
break;
/* fall-thru */
case MSM_SUBMIT_CMD_BUF:
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index c5a3e4d4c007..5eabb0109577 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -81,8 +81,7 @@ static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter,
OUT_RING(ring, upper_32_bits(iova));
}
-static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
- struct msm_file_private *ctx)
+static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
{
unsigned int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT;
struct msm_drm_private *priv = gpu->dev->dev_private;
@@ -115,7 +114,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
case MSM_SUBMIT_CMD_IB_TARGET_BUF:
break;
case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
- if (priv->lastctx == ctx)
+ if (priv->lastctx == submit->queue->ctx)
break;
/* fall-thru */
case MSM_SUBMIT_CMD_BUF:
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index d2dbb6968cba..533a34b4cce2 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -457,8 +457,7 @@ void adreno_recover(struct msm_gpu *gpu)
}
}
-void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
- struct msm_file_private *ctx)
+void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
struct msm_drm_private *priv = gpu->dev->dev_private;
@@ -472,7 +471,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
break;
case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
/* ignore if there has not been a ctx switch: */
- if (priv->lastctx == ctx)
+ if (priv->lastctx == submit->queue->ctx)
break;
/* fall-thru */
case MSM_SUBMIT_CMD_BUF:
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index e55abae365b5..848632758450 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -269,8 +269,7 @@ struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu,
const struct firmware *fw, u64 *iova);
int adreno_hw_init(struct msm_gpu *gpu);
void adreno_recover(struct msm_gpu *gpu);
-void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
- struct msm_file_private *ctx);
+void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit);
void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 1464b04d25d3..aa5c60a7132d 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -785,7 +785,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
}
}
- msm_gpu_submit(gpu, submit, ctx);
+ msm_gpu_submit(gpu, submit);
args->fence = submit->fence->seqno;
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 806eb0957280..e1a3cbe25a0c 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -520,7 +520,7 @@ static void recover_worker(struct work_struct *work)
struct msm_ringbuffer *ring = gpu->rb[i];
list_for_each_entry(submit, &ring->submits, node)
- gpu->funcs->submit(gpu, submit, NULL);
+ gpu->funcs->submit(gpu, submit);
}
}
@@ -747,8 +747,7 @@ void msm_gpu_retire(struct msm_gpu *gpu)
}
/* add bo's to gpu's ring, and kick gpu: */
-void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
- struct msm_file_private *ctx)
+void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
{
struct drm_device *dev = gpu->dev;
struct msm_drm_private *priv = dev->dev_private;
@@ -788,8 +787,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
msm_gem_move_to_active(&msm_obj->base, gpu, false, submit->fence);
}
- gpu->funcs->submit(gpu, submit, ctx);
- priv->lastctx = ctx;
+ gpu->funcs->submit(gpu, submit);
+ priv->lastctx = submit->queue->ctx;
hangcheck_timer_reset(gpu);
}
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 97c527e98391..1f96ac0d9049 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -45,8 +45,7 @@ struct msm_gpu_funcs {
int (*hw_init)(struct msm_gpu *gpu);
int (*pm_suspend)(struct msm_gpu *gpu);
int (*pm_resume)(struct msm_gpu *gpu);
- void (*submit)(struct msm_gpu *gpu, struct msm_gem_submit *submit,
- struct msm_file_private *ctx);
+ void (*submit)(struct msm_gpu *gpu, struct msm_gem_submit *submit);
void (*flush)(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
irqreturn_t (*irq)(struct msm_gpu *irq);
struct msm_ringbuffer *(*active_ring)(struct msm_gpu *gpu);
@@ -290,8 +289,7 @@ int msm_gpu_perfcntr_sample(struct msm_gpu *gpu, uint32_t *activetime,
uint32_t *totaltime, uint32_t ncntrs, uint32_t *cntrs);
void msm_gpu_retire(struct msm_gpu *gpu);
-void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
- struct msm_file_private *ctx);
+void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit);
int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 13/20] drm/msm: Set the global virtual address range from the IOMMU domain
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
` (4 preceding siblings ...)
2020-08-24 18:37 ` [PATCH 12/20] drm/msm: Drop context arg to gpu->submit() Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 14/20] drm/msm: Add support to create a local pagetable Rob Clark
` (5 subsequent siblings)
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter, Fabio Estevam,
open list:DRM DRIVER FOR MSM ADRENO GPU, open list
From: Jordan Crouse <jcrouse@codeaurora.org>
Use the aperture settings from the IOMMU domain to set up the virtual
address range for the GPU. This allows us to transparently deal with
IOMMU side features (like split pagetables).
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/adreno/adreno_gpu.c | 13 +++++++++++--
drivers/gpu/drm/msm/msm_iommu.c | 7 +++++++
2 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 533a34b4cce2..34e6242c1767 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -192,9 +192,18 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu,
struct iommu_domain *iommu = iommu_domain_alloc(&platform_bus_type);
struct msm_mmu *mmu = msm_iommu_new(&pdev->dev, iommu);
struct msm_gem_address_space *aspace;
+ u64 start, size;
- aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M,
- 0xffffffff - SZ_16M);
+ /*
+ * Use the aperture start or SZ_16M, whichever is greater. This will
+ * ensure that we align with the allocated pagetable range while still
+ * allowing room in the lower 32 bits for GMEM and whatnot
+ */
+ start = max_t(u64, SZ_16M, iommu->geometry.aperture_start);
+ size = iommu->geometry.aperture_end - start + 1;
+
+ aspace = msm_gem_address_space_create(mmu, "gpu",
+ start & GENMASK(48, 0), size);
if (IS_ERR(aspace) && !IS_ERR(mmu))
mmu->funcs->destroy(mmu);
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 3a381a9674c9..1b6635504069 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -36,6 +36,10 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova,
struct msm_iommu *iommu = to_msm_iommu(mmu);
size_t ret;
+ /* The arm-smmu driver expects the addresses to be sign extended */
+ if (iova & BIT_ULL(48))
+ iova |= GENMASK_ULL(63, 49);
+
ret = iommu_map_sg(iommu->domain, iova, sgt->sgl, sgt->nents, prot);
WARN_ON(!ret);
@@ -46,6 +50,9 @@ static int msm_iommu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len)
{
struct msm_iommu *iommu = to_msm_iommu(mmu);
+ if (iova & BIT_ULL(48))
+ iova |= GENMASK_ULL(63, 49);
+
iommu_unmap(iommu->domain, iova, len);
return 0;
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 14/20] drm/msm: Add support to create a local pagetable
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
` (5 preceding siblings ...)
2020-08-24 18:37 ` [PATCH 13/20] drm/msm: Set the global virtual address range from the IOMMU domain Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 15/20] drm/msm: Add support for private address space instances Rob Clark
` (4 subsequent siblings)
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter,
open list:DRM DRIVER FOR MSM ADRENO GPU, open list
From: Jordan Crouse <jcrouse@codeaurora.org>
Add support to create a io-pgtable for use by targets that support
per-instance pagetables. In order to support per-instance pagetables the
GPU SMMU device needs to have the qcom,adreno-smmu compatible string and
split pagetables enabled.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/Kconfig | 1 +
drivers/gpu/drm/msm/msm_gpummu.c | 2 +-
drivers/gpu/drm/msm/msm_iommu.c | 199 ++++++++++++++++++++++++++++++-
drivers/gpu/drm/msm/msm_mmu.h | 16 ++-
4 files changed, 215 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 6deaa7d01654..5102a58830b9 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -8,6 +8,7 @@ config DRM_MSM
depends on MMU
depends on INTERCONNECT || !INTERCONNECT
depends on QCOM_OCMEM || QCOM_OCMEM=n
+ select IOMMU_IO_PGTABLE
select QCOM_MDT_LOADER if ARCH_QCOM
select REGULATOR
select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/msm/msm_gpummu.c b/drivers/gpu/drm/msm/msm_gpummu.c
index 310a31b05faa..aab121f4beb7 100644
--- a/drivers/gpu/drm/msm/msm_gpummu.c
+++ b/drivers/gpu/drm/msm/msm_gpummu.c
@@ -102,7 +102,7 @@ struct msm_mmu *msm_gpummu_new(struct device *dev, struct msm_gpu *gpu)
}
gpummu->gpu = gpu;
- msm_mmu_init(&gpummu->base, dev, &funcs);
+ msm_mmu_init(&gpummu->base, dev, &funcs, MSM_MMU_GPUMMU);
return &gpummu->base;
}
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 1b6635504069..697cc0a059d6 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -4,15 +4,210 @@
* Author: Rob Clark <robdclark@gmail.com>
*/
+#include <linux/adreno-smmu-priv.h>
+#include <linux/io-pgtable.h>
#include "msm_drv.h"
#include "msm_mmu.h"
struct msm_iommu {
struct msm_mmu base;
struct iommu_domain *domain;
+ atomic_t pagetables;
};
+
#define to_msm_iommu(x) container_of(x, struct msm_iommu, base)
+struct msm_iommu_pagetable {
+ struct msm_mmu base;
+ struct msm_mmu *parent;
+ struct io_pgtable_ops *pgtbl_ops;
+ phys_addr_t ttbr;
+ u32 asid;
+};
+static struct msm_iommu_pagetable *to_pagetable(struct msm_mmu *mmu)
+{
+ return container_of(mmu, struct msm_iommu_pagetable, base);
+}
+
+static int msm_iommu_pagetable_unmap(struct msm_mmu *mmu, u64 iova,
+ size_t size)
+{
+ struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
+ struct io_pgtable_ops *ops = pagetable->pgtbl_ops;
+ size_t unmapped = 0;
+
+ /* Unmap the block one page at a time */
+ while (size) {
+ unmapped += ops->unmap(ops, iova, 4096, NULL);
+ iova += 4096;
+ size -= 4096;
+ }
+
+ iommu_flush_tlb_all(to_msm_iommu(pagetable->parent)->domain);
+
+ return (unmapped == size) ? 0 : -EINVAL;
+}
+
+static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova,
+ struct sg_table *sgt, size_t len, int prot)
+{
+ struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
+ struct io_pgtable_ops *ops = pagetable->pgtbl_ops;
+ struct scatterlist *sg;
+ size_t mapped = 0;
+ u64 addr = iova;
+ unsigned int i;
+
+ for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+ size_t size = sg->length;
+ phys_addr_t phys = sg_phys(sg);
+
+ /* Map the block one page at a time */
+ while (size) {
+ if (ops->map(ops, addr, phys, 4096, prot, GFP_KERNEL)) {
+ msm_iommu_pagetable_unmap(mmu, iova, mapped);
+ return -EINVAL;
+ }
+
+ phys += 4096;
+ addr += 4096;
+ size -= 4096;
+ mapped += 4096;
+ }
+ }
+
+ return 0;
+}
+
+static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu)
+{
+ struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
+ struct msm_iommu *iommu = to_msm_iommu(pagetable->parent);
+ struct adreno_smmu_priv *adreno_smmu =
+ dev_get_drvdata(pagetable->parent->dev);
+
+ /*
+ * If this is the last attached pagetable for the parent,
+ * disable TTBR0 in the arm-smmu driver
+ */
+ if (atomic_dec_return(&iommu->pagetables) == 0)
+ adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL);
+
+ free_io_pgtable_ops(pagetable->pgtbl_ops);
+ kfree(pagetable);
+}
+
+int msm_iommu_pagetable_params(struct msm_mmu *mmu,
+ phys_addr_t *ttbr, int *asid)
+{
+ struct msm_iommu_pagetable *pagetable;
+
+ if (mmu->type != MSM_MMU_IOMMU_PAGETABLE)
+ return -EINVAL;
+
+ pagetable = to_pagetable(mmu);
+
+ if (ttbr)
+ *ttbr = pagetable->ttbr;
+
+ if (asid)
+ *asid = pagetable->asid;
+
+ return 0;
+}
+
+static const struct msm_mmu_funcs pagetable_funcs = {
+ .map = msm_iommu_pagetable_map,
+ .unmap = msm_iommu_pagetable_unmap,
+ .destroy = msm_iommu_pagetable_destroy,
+};
+
+static void msm_iommu_tlb_flush_all(void *cookie)
+{
+}
+
+static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size,
+ size_t granule, void *cookie)
+{
+}
+
+static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
+ unsigned long iova, size_t granule, void *cookie)
+{
+}
+
+static const struct iommu_flush_ops null_tlb_ops = {
+ .tlb_flush_all = msm_iommu_tlb_flush_all,
+ .tlb_flush_walk = msm_iommu_tlb_flush_walk,
+ .tlb_flush_leaf = msm_iommu_tlb_flush_walk,
+ .tlb_add_page = msm_iommu_tlb_add_page,
+};
+
+struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
+{
+ struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(parent->dev);
+ struct msm_iommu *iommu = to_msm_iommu(parent);
+ struct msm_iommu_pagetable *pagetable;
+ const struct io_pgtable_cfg *ttbr1_cfg = NULL;
+ struct io_pgtable_cfg ttbr0_cfg;
+ int ret;
+
+ /* Get the pagetable configuration from the domain */
+ if (adreno_smmu->cookie)
+ ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie);
+ if (!ttbr1_cfg)
+ return ERR_PTR(-ENODEV);
+
+ pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL);
+ if (!pagetable)
+ return ERR_PTR(-ENOMEM);
+
+ msm_mmu_init(&pagetable->base, parent->dev, &pagetable_funcs,
+ MSM_MMU_IOMMU_PAGETABLE);
+
+ /* Clone the TTBR1 cfg as starting point for TTBR0 cfg: */
+ ttbr0_cfg = *ttbr1_cfg;
+
+ /* The incoming cfg will have the TTBR1 quirk enabled */
+ ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1;
+ ttbr0_cfg.tlb = &null_tlb_ops;
+
+ pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1,
+ &ttbr0_cfg, iommu->domain);
+
+ if (!pagetable->pgtbl_ops) {
+ kfree(pagetable);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ /*
+ * If this is the first pagetable that we've allocated, send it back to
+ * the arm-smmu driver as a trigger to set up TTBR0
+ */
+ if (atomic_inc_return(&iommu->pagetables) == 1) {
+ ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg);
+ if (ret) {
+ free_io_pgtable_ops(pagetable->pgtbl_ops);
+ kfree(pagetable);
+ return ERR_PTR(ret);
+ }
+ }
+
+ /* Needed later for TLB flush */
+ pagetable->parent = parent;
+ pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr;
+
+ /*
+ * TODO we would like each set of page tables to have a unique ASID
+ * to optimize TLB invalidation. But iommu_flush_tlb_all() will
+ * end up flushing the ASID used for TTBR1 pagetables, which is not
+ * what we want. So for now just use the same ASID as TTBR1.
+ */
+ pagetable->asid = 0;
+
+ return &pagetable->base;
+}
+
static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
unsigned long iova, int flags, void *arg)
{
@@ -85,9 +280,11 @@ struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain)
return ERR_PTR(-ENOMEM);
iommu->domain = domain;
- msm_mmu_init(&iommu->base, dev, &funcs);
+ msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU);
iommu_set_fault_handler(domain, msm_fault_handler, iommu);
+ atomic_set(&iommu->pagetables, 0);
+
ret = iommu_attach_device(iommu->domain, dev);
if (ret) {
kfree(iommu);
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index 3a534ee59bf6..61ade89d9e48 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -17,18 +17,26 @@ struct msm_mmu_funcs {
void (*destroy)(struct msm_mmu *mmu);
};
+enum msm_mmu_type {
+ MSM_MMU_GPUMMU,
+ MSM_MMU_IOMMU,
+ MSM_MMU_IOMMU_PAGETABLE,
+};
+
struct msm_mmu {
const struct msm_mmu_funcs *funcs;
struct device *dev;
int (*handler)(void *arg, unsigned long iova, int flags);
void *arg;
+ enum msm_mmu_type type;
};
static inline void msm_mmu_init(struct msm_mmu *mmu, struct device *dev,
- const struct msm_mmu_funcs *funcs)
+ const struct msm_mmu_funcs *funcs, enum msm_mmu_type type)
{
mmu->dev = dev;
mmu->funcs = funcs;
+ mmu->type = type;
}
struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain);
@@ -41,7 +49,13 @@ static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg,
mmu->handler = handler;
}
+struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent);
+
void msm_gpummu_params(struct msm_mmu *mmu, dma_addr_t *pt_base,
dma_addr_t *tran_error);
+
+int msm_iommu_pagetable_params(struct msm_mmu *mmu, phys_addr_t *ttbr,
+ int *asid);
+
#endif /* __MSM_MMU_H__ */
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 15/20] drm/msm: Add support for private address space instances
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
` (6 preceding siblings ...)
2020-08-24 18:37 ` [PATCH 14/20] drm/msm: Add support to create a local pagetable Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 16/20] drm/msm/a6xx: Add support for per-instance pagetables Rob Clark
` (3 subsequent siblings)
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter,
open list:DRM DRIVER FOR MSM ADRENO GPU, open list
From: Jordan Crouse <jcrouse@codeaurora.org>
Add support for allocating private address space instances. Targets that
support per-context pagetables should implement their own function to
allocate private address spaces.
The default will return a pointer to the global address space.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/msm_drv.c | 13 +++++++------
drivers/gpu/drm/msm/msm_drv.h | 5 +++++
drivers/gpu/drm/msm/msm_gem_vma.c | 9 +++++++++
drivers/gpu/drm/msm/msm_gpu.c | 22 ++++++++++++++++++++++
drivers/gpu/drm/msm/msm_gpu.h | 5 +++++
5 files changed, 48 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 75cd7639f560..7e963f707852 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -597,7 +597,7 @@ static int context_init(struct drm_device *dev, struct drm_file *file)
kref_init(&ctx->ref);
msm_submitqueue_init(dev, ctx);
- ctx->aspace = priv->gpu ? priv->gpu->aspace : NULL;
+ ctx->aspace = msm_gpu_create_private_address_space(priv->gpu);
file->driver_priv = ctx;
return 0;
@@ -780,18 +780,19 @@ static int msm_ioctl_gem_cpu_fini(struct drm_device *dev, void *data,
}
static int msm_ioctl_gem_info_iova(struct drm_device *dev,
- struct drm_gem_object *obj, uint64_t *iova)
+ struct drm_file *file, struct drm_gem_object *obj,
+ uint64_t *iova)
{
- struct msm_drm_private *priv = dev->dev_private;
+ struct msm_file_private *ctx = file->driver_priv;
- if (!priv->gpu)
+ if (!ctx->aspace)
return -EINVAL;
/*
* Don't pin the memory here - just get an address so that userspace can
* be productive
*/
- return msm_gem_get_iova(obj, priv->gpu->aspace, iova);
+ return msm_gem_get_iova(obj, ctx->aspace, iova);
}
static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
@@ -830,7 +831,7 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
args->value = msm_gem_mmap_offset(obj);
break;
case MSM_INFO_GET_IOVA:
- ret = msm_ioctl_gem_info_iova(dev, obj, &args->value);
+ ret = msm_ioctl_gem_info_iova(dev, file, obj, &args->value);
break;
case MSM_INFO_SET_NAME:
/* length check should leave room for terminating null: */
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 4561bfb5e745..2ca9c3c03845 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -249,6 +249,10 @@ int msm_gem_map_vma(struct msm_gem_address_space *aspace,
void msm_gem_close_vma(struct msm_gem_address_space *aspace,
struct msm_gem_vma *vma);
+
+struct msm_gem_address_space *
+msm_gem_address_space_get(struct msm_gem_address_space *aspace);
+
void msm_gem_address_space_put(struct msm_gem_address_space *aspace);
struct msm_gem_address_space *
@@ -434,6 +438,7 @@ static inline void __msm_file_private_destroy(struct kref *kref)
struct msm_file_private *ctx = container_of(kref,
struct msm_file_private, ref);
+ msm_gem_address_space_put(ctx->aspace);
kfree(ctx);
}
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index 5f6a11211b64..29cc1305cf37 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -27,6 +27,15 @@ void msm_gem_address_space_put(struct msm_gem_address_space *aspace)
kref_put(&aspace->kref, msm_gem_address_space_destroy);
}
+struct msm_gem_address_space *
+msm_gem_address_space_get(struct msm_gem_address_space *aspace)
+{
+ if (!IS_ERR_OR_NULL(aspace))
+ kref_get(&aspace->kref);
+
+ return aspace;
+}
+
/* Actually unmap memory for the vma */
void msm_gem_purge_vma(struct msm_gem_address_space *aspace,
struct msm_gem_vma *vma)
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index e1a3cbe25a0c..951850804d77 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -823,6 +823,28 @@ static int get_clocks(struct platform_device *pdev, struct msm_gpu *gpu)
return 0;
}
+/* Return a new address space for a msm_drm_private instance */
+struct msm_gem_address_space *
+msm_gpu_create_private_address_space(struct msm_gpu *gpu)
+{
+ struct msm_gem_address_space *aspace = NULL;
+
+ if (!gpu)
+ return NULL;
+
+ /*
+ * If the target doesn't support private address spaces then return
+ * the global one
+ */
+ if (gpu->funcs->create_private_address_space)
+ aspace = gpu->funcs->create_private_address_space(gpu);
+
+ if (IS_ERR_OR_NULL(aspace))
+ aspace = msm_gem_address_space_get(gpu->aspace);
+
+ return aspace;
+}
+
int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
const char *name, struct msm_gpu_config *config)
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 1f96ac0d9049..4052a18e18c2 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -65,6 +65,8 @@ struct msm_gpu_funcs {
void (*gpu_set_freq)(struct msm_gpu *gpu, struct dev_pm_opp *opp);
struct msm_gem_address_space *(*create_address_space)
(struct msm_gpu *gpu, struct platform_device *pdev);
+ struct msm_gem_address_space *(*create_private_address_space)
+ (struct msm_gpu *gpu);
};
struct msm_gpu {
@@ -295,6 +297,9 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
const char *name, struct msm_gpu_config *config);
+struct msm_gem_address_space *
+msm_gpu_create_private_address_space(struct msm_gpu *gpu);
+
void msm_gpu_cleanup(struct msm_gpu *gpu);
struct msm_gpu *adreno_load_gpu(struct drm_device *dev);
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 16/20] drm/msm/a6xx: Add support for per-instance pagetables
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
` (7 preceding siblings ...)
2020-08-24 18:37 ` [PATCH 15/20] drm/msm: Add support for private address space instances Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 17/20] arm: dts: qcom: sm845: Set the compatible string for the GPU SMMU Rob Clark
` (2 subsequent siblings)
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter, Emil Velikov,
Sharat Masetty, open list:DRM DRIVER FOR MSM ADRENO GPU,
open list
From: Jordan Crouse <jcrouse@codeaurora.org>
Add support for using per-instance pagetables if all the dependencies are
available.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Akhil P Oommen <akhilpo@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 63 +++++++++++++++++++++++++++
drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 1 +
drivers/gpu/drm/msm/msm_ringbuffer.h | 1 +
3 files changed, 65 insertions(+)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 5eabb0109577..d7ad6c78d787 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -81,6 +81,49 @@ static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter,
OUT_RING(ring, upper_32_bits(iova));
}
+static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
+ struct msm_ringbuffer *ring, struct msm_file_private *ctx)
+{
+ phys_addr_t ttbr;
+ u32 asid;
+ u64 memptr = rbmemptr(ring, ttbr0);
+
+ if (ctx == a6xx_gpu->cur_ctx)
+ return;
+
+ if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
+ return;
+
+ /* Execute the table update */
+ OUT_PKT7(ring, CP_SMMU_TABLE_UPDATE, 4);
+ OUT_RING(ring, CP_SMMU_TABLE_UPDATE_0_TTBR0_LO(lower_32_bits(ttbr)));
+
+ OUT_RING(ring,
+ CP_SMMU_TABLE_UPDATE_1_TTBR0_HI(upper_32_bits(ttbr)) |
+ CP_SMMU_TABLE_UPDATE_1_ASID(asid));
+ OUT_RING(ring, CP_SMMU_TABLE_UPDATE_2_CONTEXTIDR(0));
+ OUT_RING(ring, CP_SMMU_TABLE_UPDATE_3_CONTEXTBANK(0));
+
+ /*
+ * Write the new TTBR0 to the memstore. This is good for debugging.
+ */
+ OUT_PKT7(ring, CP_MEM_WRITE, 4);
+ OUT_RING(ring, CP_MEM_WRITE_0_ADDR_LO(lower_32_bits(memptr)));
+ OUT_RING(ring, CP_MEM_WRITE_1_ADDR_HI(upper_32_bits(memptr)));
+ OUT_RING(ring, lower_32_bits(ttbr));
+ OUT_RING(ring, (asid << 16) | upper_32_bits(ttbr));
+
+ /*
+ * And finally, trigger a uche flush to be sure there isn't anything
+ * lingering in that part of the GPU
+ */
+
+ OUT_PKT7(ring, CP_EVENT_WRITE, 1);
+ OUT_RING(ring, 0x31);
+
+ a6xx_gpu->cur_ctx = ctx;
+}
+
static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
{
unsigned int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT;
@@ -90,6 +133,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
struct msm_ringbuffer *ring = submit->ring;
unsigned int i;
+ a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
+
get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
rbmemptr_stats(ring, index, cpcycles_start));
@@ -696,6 +741,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
/* Always come up on rb 0 */
a6xx_gpu->cur_ring = gpu->rb[0];
+ a6xx_gpu->cur_ctx = NULL;
+
/* Enable the SQE_to start the CP engine */
gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1);
@@ -1008,6 +1055,21 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
return (unsigned long)busy_time;
}
+static struct msm_gem_address_space *
+a6xx_create_private_address_space(struct msm_gpu *gpu)
+{
+ struct msm_gem_address_space *aspace = NULL;
+ struct msm_mmu *mmu;
+
+ mmu = msm_iommu_pagetable_create(gpu->aspace->mmu);
+
+ if (!IS_ERR(mmu))
+ aspace = msm_gem_address_space_create(mmu,
+ "gpu", 0x100000000ULL, 0x1ffffffffULL);
+
+ return aspace;
+}
+
static const struct adreno_gpu_funcs funcs = {
.base = {
.get_param = adreno_get_param,
@@ -1031,6 +1093,7 @@ static const struct adreno_gpu_funcs funcs = {
.gpu_state_put = a6xx_gpu_state_put,
#endif
.create_address_space = adreno_iommu_create_address_space,
+ .create_private_address_space = a6xx_create_private_address_space,
},
.get_timestamp = a6xx_get_timestamp,
};
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 03ba60d5b07f..da22d7549d9b 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -19,6 +19,7 @@ struct a6xx_gpu {
uint64_t sqe_iova;
struct msm_ringbuffer *cur_ring;
+ struct msm_file_private *cur_ctx;
struct a6xx_gmu gmu;
};
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h
index 7764373d0ed2..0987d6bf848c 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.h
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.h
@@ -31,6 +31,7 @@ struct msm_rbmemptrs {
volatile uint32_t fence;
volatile struct msm_gpu_submit_stats stats[MSM_GPU_SUBMIT_STATS_COUNT];
+ volatile u64 ttbr0;
};
struct msm_ringbuffer {
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 17/20] arm: dts: qcom: sm845: Set the compatible string for the GPU SMMU
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
` (8 preceding siblings ...)
2020-08-24 18:37 ` [PATCH 16/20] drm/msm/a6xx: Add support for per-instance pagetables Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 18/20] arm: dts: qcom: sc7180: " Rob Clark
2020-08-24 18:37 ` [PATCH 20/20] drm/msm: show process names in gem_describe Rob Clark
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Andy Gross, Rob Herring, open list:ARM/QUALCOMM SUPPORT,
open list:OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS,
open list
From: Jordan Crouse <jcrouse@codeaurora.org>
Set the qcom,adreno-smmu compatible string for the GPU SMMU to enable
split pagetables and per-instance pagetables for drm/msm.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi | 9 +++++++++
arch/arm64/boot/dts/qcom/sdm845.dtsi | 2 +-
2 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi
index 64fc1bfd66fa..39f23cdcbd02 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi
@@ -633,6 +633,15 @@ &mdss_mdp {
status = "okay";
};
+/*
+ * Cheza fw does not properly program the GPU aperture to allow the
+ * GPU to update the SMMU pagetables for context switches. Work
+ * around this by dropping the "qcom,adreno-smmu" compat string.
+ */
+&adreno_smmu {
+ compatible = "qcom,sdm845-smmu-v2", "qcom,smmu-v2";
+};
+
&mss_pil {
iommus = <&apps_smmu 0x781 0x0>,
<&apps_smmu 0x724 0x3>;
diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index 2884577dcb77..76a8a34640ae 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -4058,7 +4058,7 @@ opp-257000000 {
};
adreno_smmu: iommu@5040000 {
- compatible = "qcom,sdm845-smmu-v2", "qcom,smmu-v2";
+ compatible = "qcom,sdm845-smmu-v2", "qcom,adreno-smmu", "qcom,smmu-v2";
reg = <0 0x5040000 0 0x10000>;
#iommu-cells = <1>;
#global-interrupts = <2>;
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 18/20] arm: dts: qcom: sc7180: Set the compatible string for the GPU SMMU
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
` (9 preceding siblings ...)
2020-08-24 18:37 ` [PATCH 17/20] arm: dts: qcom: sm845: Set the compatible string for the GPU SMMU Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
2020-08-24 18:37 ` [PATCH 20/20] drm/msm: show process names in gem_describe Rob Clark
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Andy Gross, Rob Herring, open list:ARM/QUALCOMM SUPPORT,
open list:OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS,
open list
From: Rob Clark <robdclark@chromium.org>
Set the qcom,adreno-smmu compatible string for the GPU SMMU to enable
split pagetables and per-instance pagetables for drm/msm.
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
arch/arm64/boot/dts/qcom/sc7180.dtsi | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi
index d46b3833e52f..f3bef1cad889 100644
--- a/arch/arm64/boot/dts/qcom/sc7180.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi
@@ -1937,7 +1937,7 @@ opp-180000000 {
};
adreno_smmu: iommu@5040000 {
- compatible = "qcom,sc7180-smmu-v2", "qcom,smmu-v2";
+ compatible = "qcom,sc7180-smmu-v2", "qcom,adreno-smmu", "qcom,smmu-v2";
reg = <0 0x05040000 0 0x10000>;
#iommu-cells = <1>;
#global-interrupts = <2>;
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 20/20] drm/msm: show process names in gem_describe
2020-08-24 18:37 [PATCH 00/20] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
` (10 preceding siblings ...)
2020-08-24 18:37 ` [PATCH 18/20] arm: dts: qcom: sc7180: " Rob Clark
@ 2020-08-24 18:37 ` Rob Clark
11 siblings, 0 replies; 14+ messages in thread
From: Rob Clark @ 2020-08-24 18:37 UTC (permalink / raw)
To: dri-devel, iommu
Cc: Sai Prakash Ranjan, Will Deacon, freedreno, Bjorn Andersson,
Sibi Sankar, Vivek Gautam, Stephen Boyd, Robin Murphy,
Joerg Roedel, Rob Clark, Akhil P Oommen,
AngeloGioacchino Del Regno, Ben Dooks, Brian Masney, Eric Anholt,
Joerg Roedel, John Stultz, Jonathan Marek, Jordan Crouse,
Rob Clark, Sean Paul, David Airlie, Daniel Vetter,
open list:DRM DRIVER FOR MSM ADRENO GPU, open list
From: Rob Clark <robdclark@chromium.org>
In $debugfs/gem we already show any vma(s) associated with an object.
Also show process names if the vma's address space is a per-process
address space.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
---
drivers/gpu/drm/msm/msm_drv.c | 2 +-
drivers/gpu/drm/msm/msm_gem.c | 25 +++++++++++++++++++++----
drivers/gpu/drm/msm/msm_gem.h | 5 +++++
drivers/gpu/drm/msm/msm_gem_vma.c | 1 +
drivers/gpu/drm/msm/msm_gpu.c | 8 +++++---
drivers/gpu/drm/msm/msm_gpu.h | 2 +-
6 files changed, 34 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 7e963f707852..7143756b7e83 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -597,7 +597,7 @@ static int context_init(struct drm_device *dev, struct drm_file *file)
kref_init(&ctx->ref);
msm_submitqueue_init(dev, ctx);
- ctx->aspace = msm_gpu_create_private_address_space(priv->gpu);
+ ctx->aspace = msm_gpu_create_private_address_space(priv->gpu, current);
file->driver_priv = ctx;
return 0;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 3cb7aeb93fd3..76a6c5271e57 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -842,11 +842,28 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
seq_puts(m, " vmas:");
- list_for_each_entry(vma, &msm_obj->vmas, list)
- seq_printf(m, " [%s: %08llx,%s,inuse=%d]",
- vma->aspace != NULL ? vma->aspace->name : NULL,
- vma->iova, vma->mapped ? "mapped" : "unmapped",
+ list_for_each_entry(vma, &msm_obj->vmas, list) {
+ const char *name, *comm;
+ if (vma->aspace) {
+ struct msm_gem_address_space *aspace = vma->aspace;
+ struct task_struct *task =
+ get_pid_task(aspace->pid, PIDTYPE_PID);
+ if (task) {
+ comm = kstrdup(task->comm, GFP_KERNEL);
+ } else {
+ comm = NULL;
+ }
+ name = aspace->name;
+ } else {
+ name = comm = NULL;
+ }
+ seq_printf(m, " [%s%s%s: aspace=%p, %08llx,%s,inuse=%d]",
+ name, comm ? ":" : "", comm ? comm : "",
+ vma->aspace, vma->iova,
+ vma->mapped ? "mapped" : "unmapped",
vma->inuse);
+ kfree(comm);
+ }
seq_puts(m, "\n");
}
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 9c573c4269cb..7b1c7a5f8eef 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -24,6 +24,11 @@ struct msm_gem_address_space {
spinlock_t lock; /* Protects drm_mm node allocation/removal */
struct msm_mmu *mmu;
struct kref kref;
+
+ /* For address spaces associated with a specific process, this
+ * will be non-NULL:
+ */
+ struct pid *pid;
};
struct msm_gem_vma {
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index 29cc1305cf37..80a8a266d68f 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -17,6 +17,7 @@ msm_gem_address_space_destroy(struct kref *kref)
drm_mm_takedown(&aspace->mm);
if (aspace->mmu)
aspace->mmu->funcs->destroy(aspace->mmu);
+ put_pid(aspace->pid);
kfree(aspace);
}
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 951850804d77..ac8961187a73 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -825,10 +825,9 @@ static int get_clocks(struct platform_device *pdev, struct msm_gpu *gpu)
/* Return a new address space for a msm_drm_private instance */
struct msm_gem_address_space *
-msm_gpu_create_private_address_space(struct msm_gpu *gpu)
+msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *task)
{
struct msm_gem_address_space *aspace = NULL;
-
if (!gpu)
return NULL;
@@ -836,8 +835,11 @@ msm_gpu_create_private_address_space(struct msm_gpu *gpu)
* If the target doesn't support private address spaces then return
* the global one
*/
- if (gpu->funcs->create_private_address_space)
+ if (gpu->funcs->create_private_address_space) {
aspace = gpu->funcs->create_private_address_space(gpu);
+ if (!IS_ERR(aspace))
+ aspace->pid = get_pid(task_pid(task));
+ }
if (IS_ERR_OR_NULL(aspace))
aspace = msm_gem_address_space_get(gpu->aspace);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 4052a18e18c2..59f26bd0fe42 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -298,7 +298,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
const char *name, struct msm_gpu_config *config);
struct msm_gem_address_space *
-msm_gpu_create_private_address_space(struct msm_gpu *gpu);
+msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *task);
void msm_gpu_cleanup(struct msm_gpu *gpu);
--
2.26.2
^ permalink raw reply related [flat|nested] 14+ messages in thread