#define DRIVER_NAME "i915"
#define DRIVER_DESC "Intel Graphics"
-#define DRIVER_DATE "20150327"
+#define DRIVER_DATE "20150522"
#undef WARN_ON
/* Many gcc seem to no see through this and fall over :( */
*
* This value doesn't count the cursor plane.
*/
-#define I915_MAX_PLANES 3
+#define I915_MAX_PLANES 4
enum plane {
PLANE_A = 0,
#define for_each_crtc(dev, crtc) \
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
+#define for_each_intel_plane(dev, intel_plane) \
+ list_for_each_entry(intel_plane, \
+ &dev->mode_config.plane_list, \
+ base.head)
+
#define for_each_intel_crtc(dev, intel_crtc) \
list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head)
&dev->mode_config.connector_list, \
base.head)
-
#define for_each_encoder_on_crtc(dev, __crtc, intel_encoder) \
list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \
if ((intel_encoder)->base.crtc == (__crtc))
struct i915_mm_struct;
struct i915_mmu_object;
+struct drm_i915_file_private {
+ struct drm_i915_private *dev_priv;
+ struct drm_file *file;
+
+ struct {
+ spinlock_t lock;
+ struct list_head request_list;
+/* 20ms is a fairly arbitrary limit (greater than the average frame time)
+ * chosen to prevent the CPU getting more than a frame ahead of the GPU
+ * (when using lax throttling for the frontbuffer). We also use it to
+ * offer free GPU waitboosts for severely congested workloads.
+ */
+#define DRM_I915_THROTTLE_JIFFIES msecs_to_jiffies(20)
+ } mm;
+ struct idr context_idr;
+
+ struct intel_rps_client {
+ struct list_head link;
+ unsigned boosts;
+ } rps;
+
+ struct intel_engine_cs *bsd_ring;
+};
+
enum intel_dpll_id {
DPLL_ID_PRIVATE = -1, /* non-shared dpll in use */
/* real shared dpll ids must be >= 0 */
/* skl */
/*
* DPLL_CTRL1 has 6 bits for each each this DPLL. We store those in
- * lower part of crtl1 and they get shifted into position when writing
+ * lower part of ctrl1 and they get shifted into position when writing
* the register. This allows us to easily compare the state to share
* the DPLL.
*/
uint32_t ctrl1;
/* HDMI only, 0 when used for DP */
uint32_t cfgcr1, cfgcr2;
+
+ /* bxt */
+ uint32_t ebb0, pll0, pll1, pll2, pll3, pll6, pll8, pll10, pcsdw12;
};
struct intel_shared_dpll_config {
u32 semaphore_seqno[I915_NUM_RINGS - 1];
/* Register state */
+ u32 start;
u32 tail;
u32 head;
u32 ctl;
struct drm_i915_error_buffer {
u32 size;
u32 name;
- u32 rseqno, wseqno;
+ u32 rseqno[I915_NUM_RINGS], wseqno;
u32 gtt_offset;
u32 read_domains;
u32 write_domain;
#define for_each_fw_domain(domain__, dev_priv__, i__) \
for_each_fw_domain_mask(domain__, FORCEWAKE_ALL, dev_priv__, i__)
+enum csr_state {
+ FW_UNINITIALIZED = 0,
+ FW_LOADED,
+ FW_FAILED
+};
+
+struct intel_csr {
+ const char *fw_path;
+ __be32 *dmc_payload;
+ uint32_t dmc_fw_size;
+ uint32_t mmio_count;
+ uint32_t mmioaddr[8];
+ uint32_t mmiodata[8];
+ enum csr_state state;
+};
+
#define DEV_INFO_FOR_EACH_FLAG(func, sep) \
func(is_mobile) sep \
func(is_i85x) sep \
* context).
* @hang_stats: information about the role of this context in possible GPU
* hangs.
- * @vm: virtual memory space used by this context.
+ * @ppgtt: virtual memory space used by this context.
* @legacy_hw_ctx: render context backing object and whether it is correctly
* initialized (legacy ring submission mechanism only).
* @link: link in the global list of contexts.
struct kref ref;
int user_handle;
uint8_t remap_slice;
+ struct drm_i915_private *i915;
struct drm_i915_file_private *file_priv;
struct i915_ctx_hang_stats hang_stats;
struct i915_hw_ppgtt *ppgtt;
bool active;
struct delayed_work work;
unsigned busy_frontbuffer_bits;
- bool link_standby;
+ bool psr2_support;
+ bool aux_frame_sync;
};
enum intel_pch {
u8 rp0_freq; /* Non-overclocked max frequency. */
u32 cz_freq;
+ u8 up_threshold; /* Current %busy required to uplock */
+ u8 down_threshold; /* Current %busy required to downclock */
+
int last_adj;
enum { LOW_POWER, BETWEEN, HIGH_POWER } power;
+ spinlock_t client_lock;
+ struct list_head clients;
+ bool client_boost;
+
bool enabled;
struct delayed_work delayed_resume_work;
+ unsigned boosts;
+
+ struct intel_rps_client semaphores, mmioflips;
/* manual wa residency calculations */
struct intel_rps_ei up_ei, down_ei;
/*
* Protects RPS/RC6 register access and PCU communication.
- * Must be taken after struct_mutex if nested.
+ * Must be taken after struct_mutex if nested. Note that
+ * this lock may be held for long periods of time when
+ * talking to hw - so only take it when talking to hw!
*/
struct mutex hw_lock;
};
int which_slice;
};
-struct i915_gem_batch_pool {
- struct drm_device *dev;
- struct list_head cache_list;
-};
-
struct i915_gem_mm {
/** Memory allocator for GTT stolen memory */
struct drm_mm stolen;
*/
struct list_head unbound_list;
- /*
- * A pool of objects to use as shadow copies of client batch buffers
- * when the command parser is enabled. Prevents the client from
- * modifying the batch contents after software parsing.
- */
- struct i915_gem_batch_pool batch_pool;
-
/** Usable portion of the GTT for GEM */
unsigned long stolen_base; /* limited to low memory (32-bit) */
bool edp_initialized;
bool edp_support;
int edp_bpp;
- bool edp_low_vswing;
struct edp_power_seq edp_pps;
struct {
struct skl_ddb_allocation {
struct skl_ddb_entry pipe[I915_MAX_PIPES];
- struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES];
+ struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* packed/uv */
+ struct skl_ddb_entry y_plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* y-plane */
struct skl_ddb_entry cursor[I915_MAX_PIPES];
};
struct drm_i915_private {
struct drm_device *dev;
- struct kmem_cache *slab;
+ struct kmem_cache *objects;
+ struct kmem_cache *vmas;
+ struct kmem_cache *requests;
const struct intel_device_info info;
struct i915_virtual_gpu vgpu;
- struct intel_gmbus gmbus[GMBUS_NUM_PORTS];
+ struct intel_csr csr;
+
+ /* Display CSR-related protection */
+ struct mutex csr_lock;
+ struct intel_gmbus gmbus[GMBUS_NUM_PINS];
/** gmbus_mutex protects against concurrent usage of the single hw gmbus
* controller on different i2c buses. */
/* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
struct pm_qos_request pm_qos;
- /* DPIO indirect register protection */
- struct mutex dpio_lock;
+ /* Sideband mailbox protection */
+ struct mutex sb_lock;
/** Cached value of IMR to avoid reads in updating the bitfield */
union {
int num_fence_regs; /* 8 on pre-965, 16 otherwise */
unsigned int fsb_freq, mem_freq, is_ddr3;
- unsigned int vlv_cdclk_freq;
+ unsigned int skl_boot_cdclk;
+ unsigned int cdclk_freq;
unsigned int hpll_freq;
/**
u32 fdi_rx_config;
+ u32 chv_phy_control;
+
u32 suspend_count;
struct i915_suspend_saved_registers regfile;
struct vlv_s0ix_state vlv_s0ix_state;
/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
struct {
- int (*do_execbuf)(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
- struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags);
+ int (*execbuf_submit)(struct drm_device *dev, struct drm_file *file,
+ struct intel_engine_cs *ring,
+ struct intel_context *ctx,
+ struct drm_i915_gem_execbuffer2 *args,
+ struct list_head *vmas,
+ struct drm_i915_gem_object *batch_obj,
+ u64 exec_start, u32 flags);
int (*init_rings)(struct drm_device *dev);
void (*cleanup_ring)(struct intel_engine_cs *ring);
void (*stop_ring)(struct intel_engine_cs *ring);
} gt;
- uint32_t request_uniq;
+ bool edp_low_vswing;
/*
* NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
struct drm_mm_node *stolen;
struct list_head global_list;
- struct list_head ring_list;
+ struct list_head ring_list[I915_NUM_RINGS];
/** Used in execbuf to temporarily hold a ref */
struct list_head obj_exec_link;
- struct list_head batch_pool_list;
+ struct list_head batch_pool_link;
/**
* This is set if the object is on the active lists (has pending
* rendering and so a non-zero seqno), and is not set if it i s on
* inactive (ready to be unbound) list.
*/
- unsigned int active:1;
+ unsigned int active:I915_NUM_RINGS;
/**
* This is set if the object has been written to since last bound
* accurate mappable working set.
*/
unsigned int fault_mappable:1;
- unsigned int pin_mappable:1;
- unsigned int pin_display:1;
/*
* Is the object to be mapped as read-only to the GPU
unsigned int cache_level:3;
unsigned int cache_dirty:1;
- unsigned int has_dma_mapping:1;
-
unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS;
+ unsigned int pin_display;
+
struct sg_table *pages;
int pages_pin_count;
+ struct get_page {
+ struct scatterlist *sg;
+ int last;
+ } get_page;
/* prime dma-buf support */
void *dma_buf_vmapping;
int vmapping_count;
- /** Breadcrumb of last rendering to the buffer. */
- struct drm_i915_gem_request *last_read_req;
+ /** Breadcrumb of last rendering to the buffer.
+ * There can only be one writer, but we allow for multiple readers.
+ * If there is a writer that necessarily implies that all other
+ * read requests are complete - but we may only be lazily clearing
+ * the read requests. A read request is naturally the most recent
+ * request on a ring, so we may have two different write and read
+ * requests on one ring where the write request is older than the
+ * read request. This allows for the CPU to read from an active
+ * buffer by only waiting for the write to complete.
+ * */
+ struct drm_i915_gem_request *last_read_req[I915_NUM_RINGS];
struct drm_i915_gem_request *last_write_req;
/** Breadcrumb of last fenced GPU access to the buffer. */
struct drm_i915_gem_request *last_fenced_req;
struct kref ref;
/** On Which ring this request was generated */
+ struct drm_i915_private *i915;
struct intel_engine_cs *ring;
/** GEM sequence number associated with this request. */
/** process identifier submitting this request */
struct pid *pid;
- uint32_t uniq;
-
/**
* The ELSP only accepts two elements at a time, so we queue
* context/tail pairs on a given queue (ring->execlist_queue) until the
};
+int i915_gem_request_alloc(struct intel_engine_cs *ring,
+ struct intel_context *ctx);
void i915_gem_request_free(struct kref *req_ref);
static inline uint32_t
return req ? req->ring : NULL;
}
-static inline void
+static inline struct drm_i915_gem_request *
i915_gem_request_reference(struct drm_i915_gem_request *req)
{
- kref_get(&req->ref);
+ if (req)
+ kref_get(&req->ref);
+ return req;
}
static inline void
kref_put(&req->ref, i915_gem_request_free);
}
+static inline void
+i915_gem_request_unreference__unlocked(struct drm_i915_gem_request *req)
+{
+ struct drm_device *dev;
+
+ if (!req)
+ return;
+
+ dev = req->ring->dev;
+ if (kref_put_mutex(&req->ref, i915_gem_request_free, &dev->struct_mutex))
+ mutex_unlock(&dev->struct_mutex);
+}
+
static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst,
struct drm_i915_gem_request *src)
{
* a later patch when the call to i915_seqno_passed() is obsoleted...
*/
-struct drm_i915_file_private {
- struct drm_i915_private *dev_priv;
- struct drm_file *file;
-
- struct {
- spinlock_t lock;
- struct list_head request_list;
- struct delayed_work idle_work;
- } mm;
- struct idr context_idr;
-
- atomic_t rps_wait_boost;
- struct intel_engine_cs *bsd_ring;
-};
-
/*
* A command that requires special handling by the command parser.
*/
* Describes where to find a register address in the command to check
* against the ring's register whitelist. Only valid if flags has the
* CMD_DESC_REGISTER bit set.
+ *
+ * A non-zero step value implies that the command may access multiple
+ * registers in sequence (e.g. LRI), in that case step gives the
+ * distance in dwords between individual offset fields.
*/
struct {
u32 offset;
u32 mask;
+ u32 step;
} reg;
#define MAX_CMD_DESC_BITMASKS 3
#define IS_HASWELL(dev) (INTEL_INFO(dev)->is_haswell)
#define IS_BROADWELL(dev) (!INTEL_INFO(dev)->is_valleyview && IS_GEN8(dev))
#define IS_SKYLAKE(dev) (INTEL_INFO(dev)->is_skylake)
+#define IS_BROXTON(dev) (!INTEL_INFO(dev)->is_skylake && IS_GEN9(dev))
#define IS_MOBILE(dev) (INTEL_INFO(dev)->is_mobile)
#define IS_HSW_EARLY_SDV(dev) (IS_HASWELL(dev) && \
(INTEL_DEVID(dev) & 0xFF00) == 0x0C00)
#define SKL_REVID_C0 (0x2)
#define SKL_REVID_D0 (0x3)
#define SKL_REVID_E0 (0x4)
+#define SKL_REVID_F0 (0x5)
+
+#define BXT_REVID_A0 (0x0)
+#define BXT_REVID_B0 (0x3)
+#define BXT_REVID_C0 (0x6)
/*
* The genX designation typically refers to the render engine, so render
#define HAS_IPS(dev) (IS_HSW_ULT(dev) || IS_BROADWELL(dev))
+#define HAS_DP_MST(dev) (IS_HASWELL(dev) || IS_BROADWELL(dev) || \
+ INTEL_INFO(dev)->gen >= 9)
+
#define HAS_DDI(dev) (INTEL_INFO(dev)->has_ddi)
#define HAS_FPGA_DBG_UNCLAIMED(dev) (INTEL_INFO(dev)->has_fpga_dbg)
#define HAS_PSR(dev) (IS_HASWELL(dev) || IS_BROADWELL(dev) || \
IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev) || \
IS_SKYLAKE(dev))
#define HAS_RUNTIME_PM(dev) (IS_GEN6(dev) || IS_HASWELL(dev) || \
- IS_BROADWELL(dev) || IS_VALLEYVIEW(dev))
+ IS_BROADWELL(dev) || IS_VALLEYVIEW(dev) || \
+ IS_SKYLAKE(dev))
#define HAS_RC6(dev) (INTEL_INFO(dev)->gen >= 6)
#define HAS_RC6p(dev) (INTEL_INFO(dev)->gen == 6 || IS_IVYBRIDGE(dev))
+#define HAS_CSR(dev) (IS_SKYLAKE(dev))
+
#define INTEL_PCH_DEVICE_ID_MASK 0xff00
#define INTEL_PCH_IBX_DEVICE_ID_TYPE 0x3b00
#define INTEL_PCH_CPT_DEVICE_ID_TYPE 0x1c00
int mmio_debug;
bool verbose_state_checks;
bool nuclear_pageflip;
+ int edp_vswing;
};
extern struct i915_params i915 __read_mostly;
extern void i915_update_gfx_val(struct drm_i915_private *dev_priv);
int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
+void i915_firmware_load_error_print(const char *fw_path, int err);
/* i915_irq.c */
void i915_queue_hangcheck(struct drm_device *dev);
enum forcewake_domains domains);
void intel_uncore_forcewake_put(struct drm_i915_private *dev_priv,
enum forcewake_domains domains);
+/* Like above but the caller must manage the uncore.lock itself.
+ * Must be used with I915_READ_FW and friends.
+ */
+void intel_uncore_forcewake_get__locked(struct drm_i915_private *dev_priv,
+ enum forcewake_domains domains);
+void intel_uncore_forcewake_put__locked(struct drm_i915_private *dev_priv,
+ enum forcewake_domains domains);
void assert_forcewakes_inactive(struct drm_i915_private *dev_priv);
static inline bool intel_vgpu_active(struct drm_device *dev)
{
void i915_gem_free_object(struct drm_gem_object *obj);
void i915_gem_vma_destroy(struct i915_vma *vma);
-#define PIN_MAPPABLE 0x1
-#define PIN_NONBLOCK 0x2
-#define PIN_GLOBAL 0x4
-#define PIN_OFFSET_BIAS 0x8
+/* Flags used by pin/bind&friends. */
+#define PIN_MAPPABLE (1<<0)
+#define PIN_NONBLOCK (1<<1)
+#define PIN_GLOBAL (1<<2)
+#define PIN_OFFSET_BIAS (1<<3)
+#define PIN_USER (1<<4)
+#define PIN_UPDATE (1<<5)
#define PIN_OFFSET_MASK (~4095)
int __must_check
i915_gem_object_pin(struct drm_i915_gem_object *obj,
int *needs_clflush);
int __must_check i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
-static inline struct page *i915_gem_object_get_page(struct drm_i915_gem_object *obj, int n)
+
+static inline int __sg_page_count(struct scatterlist *sg)
+{
+ return sg->length >> PAGE_SHIFT;
+}
+
+static inline struct page *
+i915_gem_object_get_page(struct drm_i915_gem_object *obj, int n)
{
- struct sg_page_iter sg_iter;
+ if (WARN_ON(n >= obj->base.size >> PAGE_SHIFT))
+ return NULL;
- for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, n)
- return sg_page_iter_page(&sg_iter);
+ if (n < obj->get_page.last) {
+ obj->get_page.sg = obj->pages->sgl;
+ obj->get_page.last = 0;
+ }
+
+ while (obj->get_page.last + __sg_page_count(obj->get_page.sg) <= n) {
+ obj->get_page.last += __sg_page_count(obj->get_page.sg++);
+ if (unlikely(sg_is_chain(obj->get_page.sg)))
+ obj->get_page.sg = sg_chain_ptr(obj->get_page.sg);
+ }
- return NULL;
+ return nth_page(sg_page(obj->get_page.sg), n - obj->get_page.last);
}
+
static inline void i915_gem_object_pin_pages(struct drm_i915_gem_object *obj)
{
BUG_ON(obj->pages == NULL);
void i915_gem_reset(struct drm_device *dev);
bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
-int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
int __must_check i915_gem_init(struct drm_device *dev);
int i915_gem_init_rings(struct drm_device *dev);
int __must_check i915_gem_init_hw(struct drm_device *dev);
unsigned reset_counter,
bool interruptible,
s64 *timeout,
- struct drm_i915_file_private *file_priv);
+ struct intel_rps_client *rps);
int __must_check i915_wait_request(struct drm_i915_gem_request *req);
int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
int __must_check
+i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
+ bool readonly);
+int __must_check
i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj,
bool write);
int __must_check
int i915_debugfs_init(struct drm_minor *minor);
void i915_debugfs_cleanup(struct drm_minor *minor);
#ifdef CONFIG_DEBUG_FS
+int i915_debugfs_connector_add(struct drm_connector *connector);
void intel_display_crc_init(struct drm_device *dev);
#else
+static inline int i915_debugfs_connector_add(struct drm_connector *connector)
+{ return 0; }
static inline void intel_display_crc_init(struct drm_device *dev) {}
#endif
void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone);
const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
-/* i915_gem_batch_pool.c */
-void i915_gem_batch_pool_init(struct drm_device *dev,
- struct i915_gem_batch_pool *pool);
-void i915_gem_batch_pool_fini(struct i915_gem_batch_pool *pool);
-struct drm_i915_gem_object*
-i915_gem_batch_pool_get(struct i915_gem_batch_pool *pool, size_t size);
-
/* i915_cmd_parser.c */
int i915_cmd_parser_get_version(void);
int i915_cmd_parser_init_ring(struct intel_engine_cs *ring);
/* intel_i2c.c */
extern int intel_setup_gmbus(struct drm_device *dev);
extern void intel_teardown_gmbus(struct drm_device *dev);
-static inline bool intel_gmbus_is_port_valid(unsigned port)
-{
- return (port >= GMBUS_PORT_SSC && port <= GMBUS_PORT_DPD);
-}
+extern bool intel_gmbus_is_valid_pin(struct drm_i915_private *dev_priv,
+ unsigned int pin);
-extern struct i2c_adapter *intel_gmbus_get_adapter(
- struct drm_i915_private *dev_priv, unsigned port);
+extern struct i2c_adapter *
+intel_gmbus_get_adapter(struct drm_i915_private *dev_priv, unsigned int pin);
extern void intel_gmbus_set_speed(struct i2c_adapter *adapter, int speed);
extern void intel_gmbus_force_bit(struct i2c_adapter *adapter, bool force_bit);
static inline bool intel_gmbus_is_forced_bit(struct i2c_adapter *adapter)
#define POSTING_READ(reg) (void)I915_READ_NOTRACE(reg)
#define POSTING_READ16(reg) (void)I915_READ16_NOTRACE(reg)
+/* These are untraced mmio-accessors that are only valid to be used inside
+ * criticial sections inside IRQ handlers where forcewake is explicitly
+ * controlled.
+ * Think twice, and think again, before using these.
+ * Note: Should only be used between intel_uncore_forcewake_irqlock() and
+ * intel_uncore_forcewake_irqunlock().
+ */
+#define I915_READ_FW(reg__) readl(dev_priv->regs + (reg__))
+#define I915_WRITE_FW(reg__, val__) writel(val__, dev_priv->regs + (reg__))
+#define POSTING_READ_FW(reg__) (void)I915_READ_FW(reg__)
+
/* "Broadcast RGB" property */
#define INTEL_BROADCAST_RGB_AUTO 0
#define INTEL_BROADCAST_RGB_FULL 1
projects / linux-drm-fsl-dcu.git / blobdiff