From f89823c212246d0671cc51e69894a3df1a743aee Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Thu, 3 Aug 2017 18:05:50 +0100 Subject: [PATCH] drm/i915/perf: Implement I915_PERF_ADD/REMOVE_CONFIG interface The motivation behind this new interface is expose at runtime the creation of new OA configs which can be used as part of the i915 perf open interface. This will enable the kernel to learn new configs which may be experimental, or otherwise not part of the core set currently available through the i915 perf interface. v2: Drop DRM_ERROR for userspace errors (Matthew) Add padding to userspace structure (Matthew) s/guid/uuid/ (Matthew) v3: Use u32 instead of int to iterate through registers (Matthew) v4: Lock access to dynamic config list (Lionel) v5: by Matthew: Fix uninitialized error values Fix incorrect unwiding when opening perf stream Use kmalloc_array() to store register Use uuid_is_valid() to valid config uuids Declare ioctls as write only Check padding members are set to 0 by Lionel: Return ENOENT rather than EINVAL when trying to remove non existing config v6: by Chris: Use ref counts for OA configs Store UUID in drm_i915_perf_oa_config rather then using pointer Shuffle fields of drm_i915_perf_oa_config to avoid padding v7: by Chris Rename uapi pointers fields to end with '_ptr' v8: by Andrzej, Marek, Sebastian Update register whitelisting by Lionel Add more register names for documentation Allow configuration programming in non-paranoid mode Add support for value filter for a couple of registers already programmed in other part of the kernel v9: Documentation fix (Lionel) Allow writing WAIT_FOR_RC6_EXIT only on Gen8+ (Andrzej) v10: Perform read access_ok() on register pointers (Lionel) Signed-off-by: Matthew Auld Signed-off-by: Lionel Landwerlin Signed-off-by: Andrzej Datczuk Reviewed-by: Andrzej Datczuk Link: https://patchwork.freedesktop.org/patch/msgid/20170803165812.2373-2-lionel.g.landwerlin@intel.com --- Documentation/gpu/i915.rst | 4 + drivers/gpu/drm/i915/i915_drv.c | 2 + drivers/gpu/drm/i915/i915_drv.h | 47 +++ drivers/gpu/drm/i915/i915_perf.c | 471 ++++++++++++++++++++++++++++++- drivers/gpu/drm/i915/i915_reg.h | 70 ++++- include/uapi/drm/i915_drm.h | 20 ++ 6 files changed, 597 insertions(+), 17 deletions(-) diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst index 9c7ed3e3f1e9..46875c2bcc31 100644 --- a/Documentation/gpu/i915.rst +++ b/Documentation/gpu/i915.rst @@ -417,6 +417,10 @@ integrate with drm/i915 and to handle the `DRM_I915_PERF_OPEN` ioctl. :functions: i915_perf_open_ioctl .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c :functions: i915_perf_release +.. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c + :functions: i915_perf_add_config_ioctl +.. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c + :functions: i915_perf_remove_config_ioctl i915 Perf Stream ---------------- diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 214555e813f1..cc25115c2db7 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -2729,6 +2729,8 @@ static const struct drm_ioctl_desc i915_ioctls[] = { DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_GETPARAM, i915_gem_context_getparam_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_SETPARAM, i915_gem_context_setparam_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_PERF_OPEN, i915_perf_open_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_PERF_ADD_CONFIG, i915_perf_add_config_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_PERF_REMOVE_CONFIG, i915_perf_remove_config_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), }; static struct drm_driver driver = { diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 32749425d7bf..39ac2dd49ac9 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1935,6 +1935,8 @@ struct i915_oa_config { struct attribute_group sysfs_metric; struct attribute *attrs[2]; struct device_attribute sysfs_metric_id; + + atomic_t ref_count; }; struct i915_perf_stream; @@ -2060,6 +2062,25 @@ struct i915_perf_stream { * struct i915_oa_ops - Gen specific implementation of an OA unit stream */ struct i915_oa_ops { + /** + * @is_valid_b_counter_reg: Validates register's address for + * programming boolean counters for a particular platform. + */ + bool (*is_valid_b_counter_reg)(struct drm_i915_private *dev_priv, + u32 addr); + + /** + * @is_valid_mux_reg: Validates register's address for programming mux + * for a particular platform. + */ + bool (*is_valid_mux_reg)(struct drm_i915_private *dev_priv, u32 addr); + + /** + * @is_valid_flex_reg: Validates register's address for programming + * flex EU filtering for a particular platform. + */ + bool (*is_valid_flex_reg)(struct drm_i915_private *dev_priv, u32 addr); + /** * @init_oa_buffer: Resets the head and tail pointers of the * circular buffer for periodic OA reports. @@ -2444,10 +2465,32 @@ struct drm_i915_private { struct kobject *metrics_kobj; struct ctl_table_header *sysctl_header; + /* + * Lock associated with adding/modifying/removing OA configs + * in dev_priv->perf.metrics_idr. + */ + struct mutex metrics_lock; + + /* + * List of dynamic configurations, you need to hold + * dev_priv->perf.metrics_lock to access it. + */ + struct idr metrics_idr; + + /* + * Lock associated with anything below within this structure + * except exclusive_stream. + */ struct mutex lock; struct list_head streams; struct { + /* + * The stream currently using the OA unit. If accessed + * outside a syscall associated to its file + * descriptor, you need to hold + * dev_priv->drm.struct_mutex. + */ struct i915_perf_stream *exclusive_stream; u32 specific_ctx_id; @@ -3637,6 +3680,10 @@ i915_gem_context_lookup_timeline(struct i915_gem_context *ctx, int i915_perf_open_ioctl(struct drm_device *dev, void *data, struct drm_file *file); +int i915_perf_add_config_ioctl(struct drm_device *dev, void *data, + struct drm_file *file); +int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data, + struct drm_file *file); void i915_oa_init_reg_state(struct intel_engine_cs *engine, struct i915_gem_context *ctx, uint32_t *reg_state); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 06a5e1e83e6c..221a996f1985 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -193,6 +193,7 @@ #include #include +#include #include "i915_drv.h" #include "i915_oa_hsw.h" @@ -357,6 +358,54 @@ struct perf_open_properties { int oa_period_exponent; }; +static void free_oa_config(struct drm_i915_private *dev_priv, + struct i915_oa_config *oa_config) +{ + if (!PTR_ERR(oa_config->flex_regs)) + kfree(oa_config->flex_regs); + if (!PTR_ERR(oa_config->b_counter_regs)) + kfree(oa_config->b_counter_regs); + if (!PTR_ERR(oa_config->mux_regs)) + kfree(oa_config->mux_regs); + kfree(oa_config); +} + +static void put_oa_config(struct drm_i915_private *dev_priv, + struct i915_oa_config *oa_config) +{ + if (!atomic_dec_and_test(&oa_config->ref_count)) + return; + + free_oa_config(dev_priv, oa_config); +} + +static int get_oa_config(struct drm_i915_private *dev_priv, + int metrics_set, + struct i915_oa_config **out_config) +{ + int ret; + + if (metrics_set == 1) { + *out_config = &dev_priv->perf.oa.test_config; + atomic_inc(&dev_priv->perf.oa.test_config.ref_count); + return 0; + } + + ret = mutex_lock_interruptible(&dev_priv->perf.metrics_lock); + if (ret) + return ret; + + *out_config = idr_find(&dev_priv->perf.metrics_idr, metrics_set); + if (!*out_config) + ret = -EINVAL; + else + atomic_inc(&(*out_config)->ref_count); + + mutex_unlock(&dev_priv->perf.metrics_lock); + + return ret; +} + static u32 gen8_oa_hw_tail_read(struct drm_i915_private *dev_priv) { return I915_READ(GEN8_OATAILPTR) & GEN8_OATAILPTR_MASK; @@ -1246,8 +1295,8 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) BUG_ON(stream != dev_priv->perf.oa.exclusive_stream); /* - * Unset exclusive_stream first, it might be checked while - * disabling the metric set on gen8+. + * Unset exclusive_stream first, it will be checked while disabling + * the metric set on gen8+. */ mutex_lock(&dev_priv->drm.struct_mutex); dev_priv->perf.oa.exclusive_stream = NULL; @@ -1263,6 +1312,8 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) if (stream->ctx) oa_put_render_ctx_id(stream); + put_oa_config(dev_priv, stream->oa_config); + if (dev_priv->perf.oa.spurious_report_rs.missed) { DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n", dev_priv->perf.oa.spurious_report_rs.missed); @@ -1950,15 +2001,6 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = { .read = i915_oa_read, }; -static struct i915_oa_config *get_oa_config(struct drm_i915_private *dev_priv, - int metrics_set) -{ - if (metrics_set == 1) - return &dev_priv->perf.oa.test_config; - - return NULL; -} - /** * i915_oa_stream_init - validate combined props for OA stream and init * @stream: An i915 perf stream @@ -2062,9 +2104,9 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, return ret; } - stream->oa_config = get_oa_config(dev_priv, props->metrics_set); - if (!stream->oa_config) - return -EINVAL; + ret = get_oa_config(dev_priv, props->metrics_set, &stream->oa_config); + if (ret) + goto err_config; /* PRM - observability performance counters: * @@ -2112,8 +2154,12 @@ err_enable: free_oa_buffer(dev_priv); err_oa_buf_alloc: + put_oa_config(dev_priv, stream->oa_config); + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); intel_runtime_pm_put(dev_priv); + +err_config: if (stream->ctx) oa_put_render_ctx_id(stream); @@ -2127,6 +2173,8 @@ void i915_oa_init_reg_state(struct intel_engine_cs *engine, struct drm_i915_private *dev_priv = engine->i915; struct i915_perf_stream *stream = dev_priv->perf.oa.exclusive_stream; + lockdep_assert_held(&dev_priv->drm.struct_mutex); + if (engine->id != RCS) return; @@ -2894,6 +2942,9 @@ void i915_perf_register(struct drm_i915_private *dev_priv) &dev_priv->perf.oa.test_config.sysfs_metric); if (ret) goto sysfs_error; + + atomic_set(&dev_priv->perf.oa.test_config.ref_count, 1); + goto exit; sysfs_error: @@ -2925,6 +2976,367 @@ void i915_perf_unregister(struct drm_i915_private *dev_priv) dev_priv->perf.metrics_kobj = NULL; } +static bool gen8_is_valid_flex_addr(struct drm_i915_private *dev_priv, u32 addr) +{ + static const i915_reg_t flex_eu_regs[] = { + EU_PERF_CNTL0, + EU_PERF_CNTL1, + EU_PERF_CNTL2, + EU_PERF_CNTL3, + EU_PERF_CNTL4, + EU_PERF_CNTL5, + EU_PERF_CNTL6, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(flex_eu_regs); i++) { + if (flex_eu_regs[i].reg == addr) + return true; + } + return false; +} + +static bool gen7_is_valid_b_counter_addr(struct drm_i915_private *dev_priv, u32 addr) +{ + return (addr >= OASTARTTRIG1.reg && addr <= OASTARTTRIG8.reg) || + (addr >= OAREPORTTRIG1.reg && addr <= OAREPORTTRIG8.reg) || + (addr >= OACEC0_0.reg && addr <= OACEC7_1.reg); +} + +static bool gen7_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr) +{ + return addr == HALF_SLICE_CHICKEN2.reg || + (addr >= MICRO_BP0_0.reg && addr <= NOA_WRITE.reg) || + (addr >= OA_PERFCNT1_LO.reg && addr <= OA_PERFCNT2_HI.reg) || + (addr >= OA_PERFMATRIX_LO.reg && addr <= OA_PERFMATRIX_HI.reg); +} + +static bool gen8_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr) +{ + return gen7_is_valid_mux_addr(dev_priv, addr) || + addr == WAIT_FOR_RC6_EXIT.reg || + (addr >= RPM_CONFIG0.reg && addr <= NOA_CONFIG(8).reg); +} + +static bool hsw_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr) +{ + return gen7_is_valid_mux_addr(dev_priv, addr) || + (addr >= 0x25100 && addr <= 0x2FF90) || + addr == 0x9ec0; +} + +static bool chv_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr) +{ + return gen7_is_valid_mux_addr(dev_priv, addr) || + (addr >= 0x182300 && addr <= 0x1823A4); +} + +static uint32_t mask_reg_value(u32 reg, u32 val) +{ + /* HALF_SLICE_CHICKEN2 is programmed with a the + * WaDisableSTUnitPowerOptimization workaround. Make sure the value + * programmed by userspace doesn't change this. + */ + if (HALF_SLICE_CHICKEN2.reg == reg) + val = val & ~_MASKED_BIT_ENABLE(GEN8_ST_PO_DISABLE); + + /* WAIT_FOR_RC6_EXIT has only one bit fullfilling the function + * indicated by its name and a bunch of selection fields used by OA + * configs. + */ + if (WAIT_FOR_RC6_EXIT.reg == reg) + val = val & ~_MASKED_BIT_ENABLE(HSW_WAIT_FOR_RC6_EXIT_ENABLE); + + return val; +} + +static struct i915_oa_reg *alloc_oa_regs(struct drm_i915_private *dev_priv, + bool (*is_valid)(struct drm_i915_private *dev_priv, u32 addr), + u32 __user *regs, + u32 n_regs) +{ + struct i915_oa_reg *oa_regs; + int err; + u32 i; + + if (!n_regs) + return NULL; + + if (!access_ok(VERIFY_READ, regs, n_regs * sizeof(u32) * 2)) + return ERR_PTR(-EFAULT); + + /* No is_valid function means we're not allowing any register to be programmed. */ + GEM_BUG_ON(!is_valid); + if (!is_valid) + return ERR_PTR(-EINVAL); + + oa_regs = kmalloc_array(n_regs, sizeof(*oa_regs), GFP_KERNEL); + if (!oa_regs) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < n_regs; i++) { + u32 addr, value; + + err = get_user(addr, regs); + if (err) + goto addr_err; + + if (!is_valid(dev_priv, addr)) { + DRM_DEBUG("Invalid oa_reg address: %X\n", addr); + err = -EINVAL; + goto addr_err; + } + + err = get_user(value, regs + 1); + if (err) + goto addr_err; + + oa_regs[i].addr = _MMIO(addr); + oa_regs[i].value = mask_reg_value(addr, value); + + regs += 2; + } + + return oa_regs; + +addr_err: + kfree(oa_regs); + return ERR_PTR(err); +} + +static ssize_t show_dynamic_id(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct i915_oa_config *oa_config = + container_of(attr, typeof(*oa_config), sysfs_metric_id); + + return sprintf(buf, "%d\n", oa_config->id); +} + +static int create_dynamic_oa_sysfs_entry(struct drm_i915_private *dev_priv, + struct i915_oa_config *oa_config) +{ + oa_config->sysfs_metric_id.attr.name = "id"; + oa_config->sysfs_metric_id.attr.mode = S_IRUGO; + oa_config->sysfs_metric_id.show = show_dynamic_id; + oa_config->sysfs_metric_id.store = NULL; + + oa_config->attrs[0] = &oa_config->sysfs_metric_id.attr; + oa_config->attrs[1] = NULL; + + oa_config->sysfs_metric.name = oa_config->uuid; + oa_config->sysfs_metric.attrs = oa_config->attrs; + + return sysfs_create_group(dev_priv->perf.metrics_kobj, + &oa_config->sysfs_metric); +} + +/** + * i915_perf_add_config_ioctl - DRM ioctl() for userspace to add a new OA config + * @dev: drm device + * @data: ioctl data (pointer to struct drm_i915_perf_oa_config) copied from + * userspace (unvalidated) + * @file: drm file + * + * Validates the submitted OA register to be saved into a new OA config that + * can then be used for programming the OA unit and its NOA network. + * + * Returns: A new allocated config number to be used with the perf open ioctl + * or a negative error code on failure. + */ +int i915_perf_add_config_ioctl(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_perf_oa_config *args = data; + struct i915_oa_config *oa_config, *tmp; + int err, id; + + if (!dev_priv->perf.initialized) { + DRM_DEBUG("i915 perf interface not available for this system\n"); + return -ENOTSUPP; + } + + if (!dev_priv->perf.metrics_kobj) { + DRM_DEBUG("OA metrics weren't advertised via sysfs\n"); + return -EINVAL; + } + + if (i915_perf_stream_paranoid && !capable(CAP_SYS_ADMIN)) { + DRM_DEBUG("Insufficient privileges to add i915 OA config\n"); + return -EACCES; + } + + if ((!args->mux_regs_ptr || !args->n_mux_regs) && + (!args->boolean_regs_ptr || !args->n_boolean_regs) && + (!args->flex_regs_ptr || !args->n_flex_regs)) { + DRM_DEBUG("No OA registers given\n"); + return -EINVAL; + } + + oa_config = kzalloc(sizeof(*oa_config), GFP_KERNEL); + if (!oa_config) { + DRM_DEBUG("Failed to allocate memory for the OA config\n"); + return -ENOMEM; + } + + atomic_set(&oa_config->ref_count, 1); + + if (!uuid_is_valid(args->uuid)) { + DRM_DEBUG("Invalid uuid format for OA config\n"); + err = -EINVAL; + goto reg_err; + } + + /* Last character in oa_config->uuid will be 0 because oa_config is + * kzalloc. + */ + memcpy(oa_config->uuid, args->uuid, sizeof(args->uuid)); + + oa_config->mux_regs_len = args->n_mux_regs; + oa_config->mux_regs = + alloc_oa_regs(dev_priv, + dev_priv->perf.oa.ops.is_valid_mux_reg, + u64_to_user_ptr(args->mux_regs_ptr), + args->n_mux_regs); + + if (IS_ERR(oa_config->mux_regs)) { + DRM_DEBUG("Failed to create OA config for mux_regs\n"); + err = PTR_ERR(oa_config->mux_regs); + goto reg_err; + } + + oa_config->b_counter_regs_len = args->n_boolean_regs; + oa_config->b_counter_regs = + alloc_oa_regs(dev_priv, + dev_priv->perf.oa.ops.is_valid_b_counter_reg, + u64_to_user_ptr(args->boolean_regs_ptr), + args->n_boolean_regs); + + if (IS_ERR(oa_config->b_counter_regs)) { + DRM_DEBUG("Failed to create OA config for b_counter_regs\n"); + err = PTR_ERR(oa_config->b_counter_regs); + goto reg_err; + } + + if (INTEL_GEN(dev_priv) < 8) { + if (args->n_flex_regs != 0) { + err = -EINVAL; + goto reg_err; + } + } else { + oa_config->flex_regs_len = args->n_flex_regs; + oa_config->flex_regs = + alloc_oa_regs(dev_priv, + dev_priv->perf.oa.ops.is_valid_flex_reg, + u64_to_user_ptr(args->flex_regs_ptr), + args->n_flex_regs); + + if (IS_ERR(oa_config->flex_regs)) { + DRM_DEBUG("Failed to create OA config for flex_regs\n"); + err = PTR_ERR(oa_config->flex_regs); + goto reg_err; + } + } + + err = mutex_lock_interruptible(&dev_priv->perf.metrics_lock); + if (err) + goto reg_err; + + /* We shouldn't have too many configs, so this iteration shouldn't be + * too costly. + */ + idr_for_each_entry(&dev_priv->perf.metrics_idr, tmp, id) { + if (!strcmp(tmp->uuid, oa_config->uuid)) { + DRM_DEBUG("OA config already exists with this uuid\n"); + err = -EADDRINUSE; + goto sysfs_err; + } + } + + err = create_dynamic_oa_sysfs_entry(dev_priv, oa_config); + if (err) { + DRM_DEBUG("Failed to create sysfs entry for OA config\n"); + goto sysfs_err; + } + + /* Config id 0 is invalid, id 1 for kernel stored test config. */ + oa_config->id = idr_alloc(&dev_priv->perf.metrics_idr, + oa_config, 2, + 0, GFP_KERNEL); + if (oa_config->id < 0) { + DRM_DEBUG("Failed to create sysfs entry for OA config\n"); + err = oa_config->id; + goto sysfs_err; + } + + mutex_unlock(&dev_priv->perf.metrics_lock); + + return oa_config->id; + +sysfs_err: + mutex_unlock(&dev_priv->perf.metrics_lock); +reg_err: + put_oa_config(dev_priv, oa_config); + DRM_DEBUG("Failed to add new OA config\n"); + return err; +} + +/** + * i915_perf_remove_config_ioctl - DRM ioctl() for userspace to remove an OA config + * @dev: drm device + * @data: ioctl data (pointer to u64 integer) copied from userspace + * @file: drm file + * + * Configs can be removed while being used, the will stop appearing in sysfs + * and their content will be freed when the stream using the config is closed. + * + * Returns: 0 on success or a negative error code on failure. + */ +int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u64 *arg = data; + struct i915_oa_config *oa_config; + int ret; + + if (!dev_priv->perf.initialized) { + DRM_DEBUG("i915 perf interface not available for this system\n"); + return -ENOTSUPP; + } + + if (i915_perf_stream_paranoid && !capable(CAP_SYS_ADMIN)) { + DRM_DEBUG("Insufficient privileges to remove i915 OA config\n"); + return -EACCES; + } + + ret = mutex_lock_interruptible(&dev_priv->perf.metrics_lock); + if (ret) + goto lock_err; + + oa_config = idr_find(&dev_priv->perf.metrics_idr, *arg); + if (!oa_config) { + DRM_DEBUG("Failed to remove unknown OA config\n"); + ret = -ENOENT; + goto config_err; + } + + GEM_BUG_ON(*arg != oa_config->id); + + sysfs_remove_group(dev_priv->perf.metrics_kobj, + &oa_config->sysfs_metric); + + idr_remove(&dev_priv->perf.metrics_idr, *arg); + put_oa_config(dev_priv, oa_config); + +config_err: + mutex_unlock(&dev_priv->perf.metrics_lock); +lock_err: + return ret; +} + static struct ctl_table oa_table[] = { { .procname = "perf_stream_paranoid", @@ -2981,6 +3393,11 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.timestamp_frequency = 0; if (IS_HASWELL(dev_priv)) { + dev_priv->perf.oa.ops.is_valid_b_counter_reg = + gen7_is_valid_b_counter_addr; + dev_priv->perf.oa.ops.is_valid_mux_reg = + hsw_is_valid_mux_addr; + dev_priv->perf.oa.ops.is_valid_flex_reg = NULL; dev_priv->perf.oa.ops.init_oa_buffer = gen7_init_oa_buffer; dev_priv->perf.oa.ops.enable_metric_set = hsw_enable_metric_set; dev_priv->perf.oa.ops.disable_metric_set = hsw_disable_metric_set; @@ -3000,6 +3417,12 @@ void i915_perf_init(struct drm_i915_private *dev_priv) * worth the complexity to maintain now that BDW+ enable * execlist mode by default. */ + dev_priv->perf.oa.ops.is_valid_b_counter_reg = + gen7_is_valid_b_counter_addr; + dev_priv->perf.oa.ops.is_valid_mux_reg = + gen8_is_valid_mux_addr; + dev_priv->perf.oa.ops.is_valid_flex_reg = + gen8_is_valid_flex_addr; dev_priv->perf.oa.ops.init_oa_buffer = gen8_init_oa_buffer; dev_priv->perf.oa.ops.enable_metric_set = gen8_enable_metric_set; @@ -3018,6 +3441,10 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.timestamp_frequency = 12500000; dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<25); + if (IS_CHERRYVIEW(dev_priv)) { + dev_priv->perf.oa.ops.is_valid_mux_reg = + chv_is_valid_mux_addr; + } } else if (IS_GEN9(dev_priv)) { dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128; dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de; @@ -3056,10 +3483,23 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.timestamp_frequency / 2; dev_priv->perf.sysctl_header = register_sysctl_table(dev_root); + mutex_init(&dev_priv->perf.metrics_lock); + idr_init(&dev_priv->perf.metrics_idr); + dev_priv->perf.initialized = true; } } +static int destroy_config(int id, void *p, void *data) +{ + struct drm_i915_private *dev_priv = data; + struct i915_oa_config *oa_config = p; + + put_oa_config(dev_priv, oa_config); + + return 0; +} + /** * i915_perf_fini - Counter part to i915_perf_init() * @dev_priv: i915 device instance @@ -3069,6 +3509,9 @@ void i915_perf_fini(struct drm_i915_private *dev_priv) if (!dev_priv->perf.initialized) return; + idr_for_each(&dev_priv->perf.metrics_idr, destroy_config, dev_priv); + idr_destroy(&dev_priv->perf.metrics_idr); + unregister_sysctl_table(dev_priv->perf.sysctl_header); memset(&dev_priv->perf.oa.ops, 0, sizeof(dev_priv->perf.oa.ops)); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0a42b6071ea1..b2546ade2c45 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -229,6 +229,28 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN8_RPCS_EU_MIN_SHIFT 0 #define GEN8_RPCS_EU_MIN_MASK (0xf << GEN8_RPCS_EU_MIN_SHIFT) +#define WAIT_FOR_RC6_EXIT _MMIO(0x20CC) +/* HSW only */ +#define HSW_SELECTIVE_READ_ADDRESSING_SHIFT 2 +#define HSW_SELECTIVE_READ_ADDRESSING_MASK (0x3 << HSW_SLECTIVE_READ_ADDRESSING_SHIFT) +#define HSW_SELECTIVE_WRITE_ADDRESS_SHIFT 4 +#define HSW_SELECTIVE_WRITE_ADDRESS_MASK (0x7 << HSW_SELECTIVE_WRITE_ADDRESS_SHIFT) +/* HSW+ */ +#define HSW_WAIT_FOR_RC6_EXIT_ENABLE (1 << 0) +#define HSW_RCS_CONTEXT_ENABLE (1 << 7) +#define HSW_RCS_INHIBIT (1 << 8) +/* Gen8 */ +#define GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT 4 +#define GEN8_SELECTIVE_WRITE_ADDRESS_MASK (0x3 << GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT) +#define GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT 4 +#define GEN8_SELECTIVE_WRITE_ADDRESS_MASK (0x3 << GEN8_SELECTIVE_WRITE_ADDRESS_SHIFT) +#define GEN8_SELECTIVE_WRITE_ADDRESSING_ENABLE (1 << 6) +#define GEN8_SELECTIVE_READ_SUBSLICE_SELECT_SHIFT 9 +#define GEN8_SELECTIVE_READ_SUBSLICE_SELECT_MASK (0x3 << GEN8_SELECTIVE_READ_SUBSLICE_SELECT_SHIFT) +#define GEN8_SELECTIVE_READ_SLICE_SELECT_SHIFT 11 +#define GEN8_SELECTIVE_READ_SLICE_SELECT_MASK (0x3 << GEN8_SELECTIVE_READ_SLICE_SELECT_SHIFT) +#define GEN8_SELECTIVE_READ_ADDRESSING_ENABLE (1 << 13) + #define GAM_ECOCHK _MMIO(0x4090) #define BDW_DISABLE_HDC_INVALIDATION (1<<25) #define ECOCHK_SNB_BIT (1<<10) @@ -729,9 +751,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define EU_PERF_CNTL5 _MMIO(0xe55c) #define EU_PERF_CNTL6 _MMIO(0xe65c) -#define GDT_CHICKEN_BITS _MMIO(0x9840) -#define GT_NOA_ENABLE 0x00000080 - /* * OA Boolean state */ @@ -994,6 +1013,51 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define OACEC7_0 _MMIO(0x27a8) #define OACEC7_1 _MMIO(0x27ac) +/* OA perf counters */ +#define OA_PERFCNT1_LO _MMIO(0x91B8) +#define OA_PERFCNT1_HI _MMIO(0x91BC) +#define OA_PERFCNT2_LO _MMIO(0x91C0) +#define OA_PERFCNT2_HI _MMIO(0x91C4) + +#define OA_PERFMATRIX_LO _MMIO(0x91C8) +#define OA_PERFMATRIX_HI _MMIO(0x91CC) + +/* RPM unit config (Gen8+) */ +#define RPM_CONFIG0 _MMIO(0x0D00) +#define RPM_CONFIG1 _MMIO(0x0D04) + +/* RPC unit config (Gen8+) */ +#define RPM_CONFIG _MMIO(0x0D08) + +/* NOA (Gen8+) */ +#define NOA_CONFIG(i) _MMIO(0x0D0C + (i) * 4) + +#define MICRO_BP0_0 _MMIO(0x9800) +#define MICRO_BP0_2 _MMIO(0x9804) +#define MICRO_BP0_1 _MMIO(0x9808) + +#define MICRO_BP1_0 _MMIO(0x980C) +#define MICRO_BP1_2 _MMIO(0x9810) +#define MICRO_BP1_1 _MMIO(0x9814) + +#define MICRO_BP2_0 _MMIO(0x9818) +#define MICRO_BP2_2 _MMIO(0x981C) +#define MICRO_BP2_1 _MMIO(0x9820) + +#define MICRO_BP3_0 _MMIO(0x9824) +#define MICRO_BP3_2 _MMIO(0x9828) +#define MICRO_BP3_1 _MMIO(0x982C) + +#define MICRO_BP_TRIGGER _MMIO(0x9830) +#define MICRO_BP3_COUNT_STATUS01 _MMIO(0x9834) +#define MICRO_BP3_COUNT_STATUS23 _MMIO(0x9838) +#define MICRO_BP_FIRED_ARMED _MMIO(0x983C) + +#define GDT_CHICKEN_BITS _MMIO(0x9840) +#define GT_NOA_ENABLE 0x00000080 + +#define NOA_DATA _MMIO(0x986C) +#define NOA_WRITE _MMIO(0x9888) #define _GEN7_PIPEA_DE_LOAD_SL 0x70068 #define _GEN7_PIPEB_DE_LOAD_SL 0x71068 diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 7ccbd6a2bbe0..ce3833fa1e06 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -260,6 +260,8 @@ typedef struct _drm_i915_sarea { #define DRM_I915_GEM_CONTEXT_GETPARAM 0x34 #define DRM_I915_GEM_CONTEXT_SETPARAM 0x35 #define DRM_I915_PERF_OPEN 0x36 +#define DRM_I915_PERF_ADD_CONFIG 0x37 +#define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -315,6 +317,8 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param) +#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) +#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -1467,6 +1471,22 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; +/** + * Structure to upload perf dynamic configuration into the kernel. + */ +struct drm_i915_perf_oa_config { + /** String formatted like "%08x-%04x-%04x-%04x-%012x" */ + char uuid[36]; + + __u32 n_mux_regs; + __u32 n_boolean_regs; + __u32 n_flex_regs; + + __u64 __user mux_regs_ptr; + __u64 __user boolean_regs_ptr; + __u64 __user flex_regs_ptr; +}; + #if defined(__cplusplus) } #endif -- 2.20.1