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 <matthew.auld@intel.com>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Andrzej Datczuk <andrzej.datczuk@intel.com>
Reviewed-by: Andrzej Datczuk <andrzej.datczuk@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170803165812.2373-2-lionel.g.landwerlin@intel.com

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
 ----------------

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 = {

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);

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

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