#include <linux/completion.h>
#include <linux/iopoll.h>
#include <linux/iosys-map.h>
#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <drm/drm_file.h>
#include <drm/drm_gem_shmem_helper.h>
#include <drm/panfrost_drm.h>
#include "panfrost_device.h"
#include "panfrost_features.h"
#include "panfrost_gem.h"
#include "panfrost_issues.h"
#include "panfrost_job.h"
#include "panfrost_mmu.h"
#include "panfrost_perfcnt.h"
#include "panfrost_regs.h"
#define COUNTERS_PER_BLOCK 64
#define BYTES_PER_COUNTER 4
#define BLOCKS_PER_COREGROUP 8
#define V4_SHADERS_PER_COREGROUP 4
struct panfrost_perfcnt {
struct panfrost_gem_mapping *mapping;
size_t bosize;
void *buf;
struct panfrost_file_priv *user;
struct mutex lock;
struct completion dump_comp;
};
void panfrost_perfcnt_clean_cache_done(struct panfrost_device *pfdev)
{
complete(&pfdev->perfcnt->dump_comp);
}
void panfrost_perfcnt_sample_done(struct panfrost_device *pfdev)
{
gpu_write(pfdev, GPU_CMD, GPU_CMD_CLEAN_CACHES);
}
static int panfrost_perfcnt_dump_locked(struct panfrost_device *pfdev)
{
u64 gpuva;
int ret;
reinit_completion(&pfdev->perfcnt->dump_comp);
gpuva = pfdev->perfcnt->mapping->mmnode.start << PAGE_SHIFT;
gpu_write(pfdev, GPU_PERFCNT_BASE_LO, lower_32_bits(gpuva));
gpu_write(pfdev, GPU_PERFCNT_BASE_HI, upper_32_bits(gpuva));
gpu_write(pfdev, GPU_INT_CLEAR,
GPU_IRQ_CLEAN_CACHES_COMPLETED |
GPU_IRQ_PERFCNT_SAMPLE_COMPLETED);
gpu_write(pfdev, GPU_CMD, GPU_CMD_PERFCNT_SAMPLE);
ret = wait_for_completion_interruptible_timeout(&pfdev->perfcnt->dump_comp,
msecs_to_jiffies(1000));
if (!ret)
ret = -ETIMEDOUT;
else if (ret > 0)
ret = 0;
return ret;
}
static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev,
struct drm_file *file_priv,
unsigned int counterset)
{
struct panfrost_file_priv *user = file_priv->driver_priv;
struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
struct iosys_map map;
struct drm_gem_shmem_object *bo;
u32 cfg, as;
int ret;
if (user == perfcnt->user)
return 0;
else if (perfcnt->user)
return -EBUSY;
ret = pm_runtime_get_sync(pfdev->dev);
if (ret < 0)
goto err_put_pm;
bo = drm_gem_shmem_create(pfdev->ddev, perfcnt->bosize);
if (IS_ERR(bo)) {
ret = PTR_ERR(bo);
goto err_put_pm;
}
ret = panfrost_gem_open(&bo->base, file_priv);
if (ret)
goto err_put_bo;
perfcnt->mapping = panfrost_gem_mapping_get(to_panfrost_bo(&bo->base),
user);
if (!perfcnt->mapping) {
ret = -EINVAL;
goto err_close_bo;
}
ret = drm_gem_vmap_unlocked(&bo->base, &map);
if (ret)
goto err_put_mapping;
perfcnt->buf = map.vaddr;
reinit_completion(&pfdev->perfcnt->dump_comp);
gpu_write(pfdev, GPU_INT_CLEAR,
GPU_IRQ_CLEAN_CACHES_COMPLETED |
GPU_IRQ_PERFCNT_SAMPLE_COMPLETED);
gpu_write(pfdev, GPU_CMD, GPU_CMD_PERFCNT_CLEAR);
gpu_write(pfdev, GPU_CMD, GPU_CMD_CLEAN_INV_CACHES);
ret = wait_for_completion_timeout(&pfdev->perfcnt->dump_comp,
msecs_to_jiffies(1000));
if (!ret) {
ret = -ETIMEDOUT;
goto err_vunmap;
}
perfcnt->user = user;
as = panfrost_mmu_as_get(pfdev, perfcnt->mapping->mmu);
cfg = GPU_PERFCNT_CFG_AS(as) |
GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_MANUAL);
if (panfrost_model_is_bifrost(pfdev))
cfg |= GPU_PERFCNT_CFG_SETSEL(counterset);
gpu_write(pfdev, GPU_PRFCNT_JM_EN, 0xffffffff);
gpu_write(pfdev, GPU_PRFCNT_SHADER_EN, 0xffffffff);
gpu_write(pfdev, GPU_PRFCNT_MMU_L2_EN, 0xffffffff);
if (panfrost_has_hw_issue(pfdev, HW_ISSUE_8186))
gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0);
else
gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0xffffffff);
gpu_write(pfdev, GPU_PERFCNT_CFG, cfg);
if (panfrost_has_hw_issue(pfdev, HW_ISSUE_8186))
gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0xffffffff);
drm_gem_object_put(&bo->base);
return 0;
err_vunmap:
drm_gem_vunmap_unlocked(&bo->base, &map);
err_put_mapping:
panfrost_gem_mapping_put(perfcnt->mapping);
err_close_bo:
panfrost_gem_close(&bo->base, file_priv);
err_put_bo:
drm_gem_object_put(&bo->base);
err_put_pm:
pm_runtime_put(pfdev->dev);
return ret;
}
static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev,
struct drm_file *file_priv)
{
struct panfrost_file_priv *user = file_priv->driver_priv;
struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
struct iosys_map map = IOSYS_MAP_INIT_VADDR(perfcnt->buf);
if (user != perfcnt->user)
return -EINVAL;
gpu_write(pfdev, GPU_PRFCNT_JM_EN, 0x0);
gpu_write(pfdev, GPU_PRFCNT_SHADER_EN, 0x0);
gpu_write(pfdev, GPU_PRFCNT_MMU_L2_EN, 0x0);
gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0);
gpu_write(pfdev, GPU_PERFCNT_CFG,
GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_OFF));
perfcnt->user = NULL;
drm_gem_vunmap_unlocked(&perfcnt->mapping->obj->base.base, &map);
perfcnt->buf = NULL;
panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv);
panfrost_mmu_as_put(pfdev, perfcnt->mapping->mmu);
panfrost_gem_mapping_put(perfcnt->mapping);
perfcnt->mapping = NULL;
pm_runtime_mark_last_busy(pfdev->dev);
pm_runtime_put_autosuspend(pfdev->dev);
return 0;
}
int panfrost_ioctl_perfcnt_enable(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
struct panfrost_device *pfdev = dev->dev_private;
struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
struct drm_panfrost_perfcnt_enable *req = data;
int ret;
ret = panfrost_unstable_ioctl_check();
if (ret)
return ret;
if (req->counterset > (panfrost_model_is_bifrost(pfdev) ? 1 : 0))
return -EINVAL;
mutex_lock(&perfcnt->lock);
if (req->enable)
ret = panfrost_perfcnt_enable_locked(pfdev, file_priv,
req->counterset);
else
ret = panfrost_perfcnt_disable_locked(pfdev, file_priv);
mutex_unlock(&perfcnt->lock);
return ret;
}
int panfrost_ioctl_perfcnt_dump(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
struct panfrost_device *pfdev = dev->dev_private;
struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
struct drm_panfrost_perfcnt_dump *req = data;
void __user *user_ptr = (void __user *)(uintptr_t)req->buf_ptr;
int ret;
ret = panfrost_unstable_ioctl_check();
if (ret)
return ret;
mutex_lock(&perfcnt->lock);
if (perfcnt->user != file_priv->driver_priv) {
ret = -EINVAL;
goto out;
}
ret = panfrost_perfcnt_dump_locked(pfdev);
if (ret)
goto out;
if (copy_to_user(user_ptr, perfcnt->buf, perfcnt->bosize))
ret = -EFAULT;
out:
mutex_unlock(&perfcnt->lock);
return ret;
}
void panfrost_perfcnt_close(struct drm_file *file_priv)
{
struct panfrost_file_priv *pfile = file_priv->driver_priv;
struct panfrost_device *pfdev = pfile->pfdev;
struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
pm_runtime_get_sync(pfdev->dev);
mutex_lock(&perfcnt->lock);
if (perfcnt->user == pfile)
panfrost_perfcnt_disable_locked(pfdev, file_priv);
mutex_unlock(&perfcnt->lock);
pm_runtime_mark_last_busy(pfdev->dev);
pm_runtime_put_autosuspend(pfdev->dev);
}
int panfrost_perfcnt_init(struct panfrost_device *pfdev)
{
struct panfrost_perfcnt *perfcnt;
size_t size;
if (panfrost_has_hw_feature(pfdev, HW_FEATURE_V4)) {
unsigned int ncoregroups;
ncoregroups = hweight64(pfdev->features.l2_present);
size = ncoregroups * BLOCKS_PER_COREGROUP *
COUNTERS_PER_BLOCK * BYTES_PER_COUNTER;
} else {
unsigned int nl2c, ncores;
nl2c = ((pfdev->features.mem_features >> 8) & GENMASK(3, 0)) + 1;
ncores = fls64(pfdev->features.shader_present);
size = (nl2c + ncores + 2) *
COUNTERS_PER_BLOCK * BYTES_PER_COUNTER;
}
perfcnt = devm_kzalloc(pfdev->dev, sizeof(*perfcnt), GFP_KERNEL);
if (!perfcnt)
return -ENOMEM;
perfcnt->bosize = size;
gpu_write(pfdev, GPU_PERFCNT_CFG,
GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_OFF));
gpu_write(pfdev, GPU_PRFCNT_JM_EN, 0);
gpu_write(pfdev, GPU_PRFCNT_SHADER_EN, 0);
gpu_write(pfdev, GPU_PRFCNT_MMU_L2_EN, 0);
gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0);
init_completion(&perfcnt->dump_comp);
mutex_init(&perfcnt->lock);
pfdev->perfcnt = perfcnt;
return 0;
}
void panfrost_perfcnt_fini(struct panfrost_device *pfdev)
{
gpu_write(pfdev, GPU_PERFCNT_CFG,
GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_OFF));
gpu_write(pfdev, GPU_PRFCNT_JM_EN, 0);
gpu_write(pfdev, GPU_PRFCNT_SHADER_EN, 0);
gpu_write(pfdev, GPU_PRFCNT_MMU_L2_EN, 0);
gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0);
}