# Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
ccflags-y := -Iinclude/drm
-i915-y := i915_drv.o i915_dma.o i915_irq.o \
- i915_gpu_error.o \
+
+# Please keep these build lists sorted!
+
+# core driver code
+i915-y := i915_drv.o \
+ i915_params.o \
i915_suspend.o \
- i915_gem.o \
+ i915_sysfs.o \
+ intel_pm.o
+i915-$(CONFIG_COMPAT) += i915_ioc32.o
+i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o
+
+# GEM code
+i915-y += i915_cmd_parser.o \
i915_gem_context.o \
i915_gem_debug.o \
+ i915_gem_dmabuf.o \
i915_gem_evict.o \
i915_gem_execbuffer.o \
i915_gem_gtt.o \
+ i915_gem.o \
i915_gem_stolen.o \
i915_gem_tiling.o \
- i915_params.o \
- i915_sysfs.o \
+ i915_gpu_error.o \
+ i915_irq.o \
i915_trace_points.o \
- i915_ums.o \
+ intel_ringbuffer.o \
+ intel_uncore.o
+
+# modesetting core code
+i915-y += intel_bios.o \
intel_display.o \
- intel_crt.o \
- intel_lvds.o \
- intel_dsi.o \
- intel_dsi_cmd.o \
- intel_dsi_pll.o \
- intel_bios.o \
- intel_ddi.o \
- intel_dp.o \
- intel_hdmi.o \
- intel_sdvo.o \
intel_modes.o \
- intel_opregion.o \
- intel_panel.o \
- intel_pm.o \
- intel_i2c.o \
- intel_tv.o \
- intel_dvo.o \
- intel_ringbuffer.o \
intel_overlay.o \
- intel_sprite.o \
intel_sideband.o \
- intel_uncore.o \
+ intel_sprite.o
- i915-$(CONFIG_ACPI) += intel_acpi.o
++i915-$(CONFIG_ACPI) += intel_acpi.o intel_opregion.o
+i915-$(CONFIG_DRM_I915_FBDEV) += intel_fbdev.o
+
+# modesetting output/encoder code
+i915-y += dvo_ch7017.o \
dvo_ch7xxx.o \
- dvo_ch7017.o \
dvo_ivch.o \
- dvo_tfp410.o \
- dvo_sil164.o \
dvo_ns2501.o \
- i915_gem_dmabuf.o
-
-i915-$(CONFIG_COMPAT) += i915_ioc32.o
-
-i915-$(CONFIG_ACPI) += intel_acpi.o intel_opregion.o
-
-i915-$(CONFIG_DRM_I915_FBDEV) += intel_fbdev.o
+ dvo_sil164.o \
+ dvo_tfp410.o \
+ intel_crt.o \
+ intel_ddi.o \
+ intel_dp.o \
+ intel_dsi_cmd.o \
+ intel_dsi.o \
+ intel_dsi_pll.o \
+ intel_dvo.o \
+ intel_hdmi.o \
+ intel_i2c.o \
+ intel_lvds.o \
+ intel_panel.o \
+ intel_sdvo.o \
+ intel_tv.o
-i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o
+# legacy horrors
+i915-y += i915_dma.o \
+ i915_ums.o
obj-$(CONFIG_DRM_I915) += i915.o
};
#define plane_name(p) ((p) + 'A')
-#define sprite_name(p, s) ((p) * INTEL_INFO(dev)->num_sprites + (s) + 'A')
+#define sprite_name(p, s) ((p) * INTEL_INFO(dev)->num_sprites[(p)] + (s) + 'A')
enum port {
PORT_A = 0,
POWER_DOMAIN_TRANSCODER_B,
POWER_DOMAIN_TRANSCODER_C,
POWER_DOMAIN_TRANSCODER_EDP,
+ POWER_DOMAIN_PORT_DDI_A_2_LANES,
+ POWER_DOMAIN_PORT_DDI_A_4_LANES,
+ POWER_DOMAIN_PORT_DDI_B_2_LANES,
+ POWER_DOMAIN_PORT_DDI_B_4_LANES,
+ POWER_DOMAIN_PORT_DDI_C_2_LANES,
+ POWER_DOMAIN_PORT_DDI_C_4_LANES,
+ POWER_DOMAIN_PORT_DDI_D_2_LANES,
+ POWER_DOMAIN_PORT_DDI_D_4_LANES,
+ POWER_DOMAIN_PORT_DSI,
+ POWER_DOMAIN_PORT_CRT,
+ POWER_DOMAIN_PORT_OTHER,
POWER_DOMAIN_VGA,
POWER_DOMAIN_AUDIO,
POWER_DOMAIN_INIT,
POWER_DOMAIN_NUM,
};
-#define POWER_DOMAIN_MASK (BIT(POWER_DOMAIN_NUM) - 1)
-
#define POWER_DOMAIN_PIPE(pipe) ((pipe) + POWER_DOMAIN_PIPE_A)
#define POWER_DOMAIN_PIPE_PANEL_FITTER(pipe) \
((pipe) + POWER_DOMAIN_PIPE_A_PANEL_FITTER)
((tran) == TRANSCODER_EDP ? POWER_DOMAIN_TRANSCODER_EDP : \
(tran) + POWER_DOMAIN_TRANSCODER_A)
-#define HSW_ALWAYS_ON_POWER_DOMAINS ( \
- BIT(POWER_DOMAIN_PIPE_A) | \
- BIT(POWER_DOMAIN_TRANSCODER_EDP))
-#define BDW_ALWAYS_ON_POWER_DOMAINS ( \
- BIT(POWER_DOMAIN_PIPE_A) | \
- BIT(POWER_DOMAIN_TRANSCODER_EDP) | \
- BIT(POWER_DOMAIN_PIPE_A_PANEL_FITTER))
-
enum hpd_pin {
HPD_NONE = 0,
HPD_PORT_A = HPD_NONE, /* PORT_A is internal */
I915_GEM_DOMAIN_VERTEX)
#define for_each_pipe(p) for ((p) = 0; (p) < INTEL_INFO(dev)->num_pipes; (p)++)
+#define for_each_sprite(p, s) for ((s) = 0; (s) < INTEL_INFO(dev)->num_sprites[(p)]; (s)++)
#define for_each_encoder_on_crtc(dev, __crtc, intel_encoder) \
list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \
struct kref ref;
struct timeval time;
+ char error_msg[128];
+ u32 reset_count;
+ u32 suspend_count;
+
/* Generic register state */
u32 eir;
u32 pgtbl_er;
int page_count;
u32 gtt_offset;
u32 *pages[0];
- } *ringbuffer, *batchbuffer, *ctx, *hws_page;
+ } *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
struct drm_i915_error_request {
long jiffies;
u32 pp_dir_base;
};
} vm_info;
+
+ pid_t pid;
+ char comm[TASK_COMM_LEN];
} ring[I915_NUM_RINGS];
struct drm_i915_error_buffer {
u32 size;
unsigned fw_rendercount;
unsigned fw_mediacount;
- struct delayed_work force_wake_work;
+ struct timer_list force_wake_timer;
};
#define DEV_INFO_FOR_EACH_FLAG(func, sep) \
struct intel_device_info {
u32 display_mmio_offset;
u8 num_pipes:3;
- u8 num_sprites:2;
+ u8 num_sprites[I915_MAX_PIPES];
u8 gen;
u8 ring_mask; /* Rings supported by the HW */
DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG, SEP_SEMICOLON);
enum i915_cache_level level,
bool valid); /* Create a valid PTE */
void (*clear_range)(struct i915_address_space *vm,
- unsigned int first_entry,
- unsigned int num_entries,
+ uint64_t start,
+ uint64_t length,
bool use_scratch);
void (*insert_entries)(struct i915_address_space *vm,
struct sg_table *st,
- unsigned int first_entry,
+ uint64_t start,
enum i915_cache_level cache_level);
void (*cleanup)(struct i915_address_space *vm);
};
};
#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT)
+#define GEN8_LEGACY_PDPS 4
struct i915_hw_ppgtt {
struct i915_address_space base;
struct kref ref;
struct drm_mm_node node;
unsigned num_pd_entries;
+ unsigned num_pd_pages; /* gen8+ */
union {
struct page **pt_pages;
- struct page *gen8_pt_pages;
+ struct page **gen8_pt_pages[GEN8_LEGACY_PDPS];
};
struct page *pd_pages;
- int num_pd_pages;
- int num_pt_pages;
union {
uint32_t pd_offset;
- dma_addr_t pd_dma_addr[4];
+ dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS];
};
union {
dma_addr_t *pt_dma_addr;
struct drm_i915_gem_object *renderctx;
};
+struct drm_i915_private;
+struct i915_power_well;
+
+struct i915_power_well_ops {
+ /*
+ * Synchronize the well's hw state to match the current sw state, for
+ * example enable/disable it based on the current refcount. Called
+ * during driver init and resume time, possibly after first calling
+ * the enable/disable handlers.
+ */
+ void (*sync_hw)(struct drm_i915_private *dev_priv,
+ struct i915_power_well *power_well);
+ /*
+ * Enable the well and resources that depend on it (for example
+ * interrupts located on the well). Called after the 0->1 refcount
+ * transition.
+ */
+ void (*enable)(struct drm_i915_private *dev_priv,
+ struct i915_power_well *power_well);
+ /*
+ * Disable the well and resources that depend on it. Called after
+ * the 1->0 refcount transition.
+ */
+ void (*disable)(struct drm_i915_private *dev_priv,
+ struct i915_power_well *power_well);
+ /* Returns the hw enabled state. */
+ bool (*is_enabled)(struct drm_i915_private *dev_priv,
+ struct i915_power_well *power_well);
+};
+
/* Power well structure for haswell */
struct i915_power_well {
const char *name;
/* power well enable/disable usage count */
int count;
unsigned long domains;
- void *data;
- void (*set)(struct drm_device *dev, struct i915_power_well *power_well,
- bool enable);
- bool (*is_enabled)(struct drm_device *dev,
- struct i915_power_well *power_well);
+ unsigned long data;
+ const struct i915_power_well_ops *ops;
};
struct i915_power_domains {
*/
bool interruptible;
+ /**
+ * Is the GPU currently considered idle, or busy executing userspace
+ * requests? Whilst idle, we attempt to power down the hardware and
+ * display clocks. In order to reduce the effect on performance, there
+ * is a slight delay before we do so.
+ */
+ bool busy;
+
/** Bit 6 swizzling required for X tiling */
uint32_t bit_6_swizzle_x;
/** Bit 6 swizzling required for Y tiling */
* Ideally every piece of our code that needs PC8+ disabled would call
* hsw_disable_package_c8, which would increment disable_count and prevent the
* system from reaching PC8+. But we don't have a symmetric way to do this for
- * everything, so we have the requirements_met and gpu_idle variables. When we
- * switch requirements_met or gpu_idle to true we decrease disable_count, and
- * increase it in the opposite case. The requirements_met variable is true when
- * all the CRTCs, encoders and the power well are disabled. The gpu_idle
- * variable is true when the GPU is idle.
+ * everything, so we have the requirements_met variable. When we switch
+ * requirements_met to true we decrease disable_count, and increase it in the
+ * opposite case. The requirements_met variable is true when all the CRTCs,
+ * encoders and the power well are disabled.
*
* In addition to everything, we only actually enable PC8+ if disable_count
* stays at zero for at least some seconds. This is implemented with the
*/
struct i915_package_c8 {
bool requirements_met;
- bool gpu_idle;
bool irqs_disabled;
/* Only true after the delayed work task actually enables it. */
bool enabled;
/* protects the irq masks */
spinlock_t irq_lock;
+ bool display_irqs_enabled;
+
/* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
struct pm_qos_request pm_qos;
struct i915_dri1_state dri1;
/* Old ums support infrastructure, same warning applies. */
struct i915_ums_state ums;
+
+ u32 suspend_count;
} drm_i915_private_t;
static inline struct drm_i915_private *to_i915(const struct drm_device *dev)
/** for phy allocated objects */
struct drm_i915_gem_phys_object *phys_obj;
};
-#define to_gem_object(obj) (&((struct drm_i915_gem_object *)(obj))->base)
#define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
struct drm_i915_file_private {
struct drm_i915_private *dev_priv;
+ struct drm_file *file;
struct {
spinlock_t lock;
atomic_t rps_wait_boost;
};
+/*
+ * A command that requires special handling by the command parser.
+ */
+struct drm_i915_cmd_descriptor {
+ /*
+ * Flags describing how the command parser processes the command.
+ *
+ * CMD_DESC_FIXED: The command has a fixed length if this is set,
+ * a length mask if not set
+ * CMD_DESC_SKIP: The command is allowed but does not follow the
+ * standard length encoding for the opcode range in
+ * which it falls
+ * CMD_DESC_REJECT: The command is never allowed
+ * CMD_DESC_REGISTER: The command should be checked against the
+ * register whitelist for the appropriate ring
+ * CMD_DESC_MASTER: The command is allowed if the submitting process
+ * is the DRM master
+ */
+ u32 flags;
+#define CMD_DESC_FIXED (1<<0)
+#define CMD_DESC_SKIP (1<<1)
+#define CMD_DESC_REJECT (1<<2)
+#define CMD_DESC_REGISTER (1<<3)
+#define CMD_DESC_BITMASK (1<<4)
+#define CMD_DESC_MASTER (1<<5)
+
+ /*
+ * The command's unique identification bits and the bitmask to get them.
+ * This isn't strictly the opcode field as defined in the spec and may
+ * also include type, subtype, and/or subop fields.
+ */
+ struct {
+ u32 value;
+ u32 mask;
+ } cmd;
+
+ /*
+ * The command's length. The command is either fixed length (i.e. does
+ * not include a length field) or has a length field mask. The flag
+ * CMD_DESC_FIXED indicates a fixed length. Otherwise, the command has
+ * a length mask. All command entries in a command table must include
+ * length information.
+ */
+ union {
+ u32 fixed;
+ u32 mask;
+ } length;
+
+ /*
+ * 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.
+ */
+ struct {
+ u32 offset;
+ u32 mask;
+ } reg;
+
+#define MAX_CMD_DESC_BITMASKS 3
+ /*
+ * Describes command checks where a particular dword is masked and
+ * compared against an expected value. If the command does not match
+ * the expected value, the parser rejects it. Only valid if flags has
+ * the CMD_DESC_BITMASK bit set. Only entries where mask is non-zero
+ * are valid.
+ */
+ struct {
+ u32 offset;
+ u32 mask;
+ u32 expected;
+ } bits[MAX_CMD_DESC_BITMASKS];
+};
+
+/*
+ * A table of commands requiring special handling by the command parser.
+ *
+ * Each ring has an array of tables. Each table consists of an array of command
+ * descriptors, which must be sorted with command opcodes in ascending order.
+ */
+struct drm_i915_cmd_table {
+ const struct drm_i915_cmd_descriptor *table;
+ int count;
+};
+
#define INTEL_INFO(dev) (&to_i915(dev)->info)
#define IS_I830(dev) ((dev)->pdev->device == 0x3577)
/* Early gen2 have a totally busted CS tlb and require pinned batches. */
#define HAS_BROKEN_CS_TLB(dev) (IS_I830(dev) || IS_845G(dev))
+ /*
+ * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
+ * even when in MSI mode. This results in spurious interrupt warnings if the
+ * legacy irq no. is shared with another device. The kernel then disables that
+ * interrupt source and so prevents the other device from working properly.
+ */
+ #define HAS_AUX_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
+ #define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
/* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
* rows, which changed the alignment requirements and fence programming.
int enable_pc8;
int pc8_timeout;
int invert_brightness;
+ int enable_cmd_parser;
/* leave bools at the end to not create holes */
bool enable_hangcheck;
bool fastboot;
/* i915_irq.c */
void i915_queue_hangcheck(struct drm_device *dev);
-void i915_handle_error(struct drm_device *dev, bool wedged);
+__printf(3, 4)
+void i915_handle_error(struct drm_device *dev, bool wedged,
+ const char *fmt, ...);
void gen6_set_pm_mask(struct drm_i915_private *dev_priv, u32 pm_iir,
int new_delay);
i915_disable_pipestat(drm_i915_private_t *dev_priv, enum pipe pipe,
u32 status_mask);
+void valleyview_enable_display_irqs(struct drm_i915_private *dev_priv);
+void valleyview_disable_display_irqs(struct drm_i915_private *dev_priv);
+
/* i915_gem.c */
int i915_gem_init_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
void i915_gem_release_mmap(struct drm_i915_gem_object *obj);
void i915_gem_lastclose(struct drm_device *dev);
+int i915_gem_obj_prepare_shmem_read(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)
{
}
}
+struct drm_i915_gem_request *
+i915_gem_find_active_request(struct intel_ring_buffer *ring);
+
bool i915_gem_retire_requests(struct drm_device *dev);
-void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring);
int __must_check i915_gem_check_wedge(struct i915_gpu_error *error,
bool interruptible);
static inline bool i915_reset_in_progress(struct i915_gpu_error *error)
intel_gtt_chipset_flush();
}
int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
-static inline bool intel_enable_ppgtt(struct drm_device *dev, bool full)
-{
- if (i915.enable_ppgtt == 0 || !HAS_ALIASING_PPGTT(dev))
- return false;
-
- if (i915.enable_ppgtt == 1 && full)
- return false;
-
-#ifdef CONFIG_INTEL_IOMMU
- /* Disable ppgtt on SNB if VT-d is on. */
- if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) {
- DRM_INFO("Disabling PPGTT because VT-d is on\n");
- return false;
- }
-#endif
-
- if (full)
- return HAS_PPGTT(dev);
- else
- return HAS_ALIASING_PPGTT(dev);
-}
-
-static inline void ppgtt_release(struct kref *kref)
-{
- struct i915_hw_ppgtt *ppgtt = container_of(kref, struct i915_hw_ppgtt, ref);
- struct drm_device *dev = ppgtt->base.dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct i915_address_space *vm = &ppgtt->base;
-
- if (ppgtt == dev_priv->mm.aliasing_ppgtt ||
- (list_empty(&vm->active_list) && list_empty(&vm->inactive_list))) {
- ppgtt->base.cleanup(&ppgtt->base);
- return;
- }
-
- /*
- * Make sure vmas are unbound before we take down the drm_mm
- *
- * FIXME: Proper refcounting should take care of this, this shouldn't be
- * needed at all.
- */
- if (!list_empty(&vm->active_list)) {
- struct i915_vma *vma;
-
- list_for_each_entry(vma, &vm->active_list, mm_list)
- if (WARN_ON(list_empty(&vma->vma_link) ||
- list_is_singular(&vma->vma_link)))
- break;
-
- i915_gem_evict_vm(&ppgtt->base, true);
- } else {
- i915_gem_retire_requests(dev);
- i915_gem_evict_vm(&ppgtt->base, false);
- }
-
- ppgtt->base.cleanup(&ppgtt->base);
-}
+bool intel_enable_ppgtt(struct drm_device *dev, bool full);
/* i915_gem_stolen.c */
int i915_gem_init_stolen(struct drm_device *dev);
{
kfree(eb->buf);
}
-void i915_capture_error_state(struct drm_device *dev);
+void i915_capture_error_state(struct drm_device *dev, bool wedge,
+ const char *error_msg);
void i915_error_state_get(struct drm_device *dev,
struct i915_error_state_file_priv *error_priv);
void i915_error_state_put(struct i915_error_state_file_priv *error_priv);
void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone);
const char *i915_cache_level_str(int type);
+/* i915_cmd_parser.c */
+void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring);
+bool i915_needs_cmd_parser(struct intel_ring_buffer *ring);
+int i915_parse_cmds(struct intel_ring_buffer *ring,
+ struct drm_i915_gem_object *batch_obj,
+ u32 batch_start_offset,
+ bool is_master);
+
/* i915_suspend.c */
extern int i915_save_state(struct drm_device *dev);
extern int i915_restore_state(struct drm_device *dev);
/* intel_opregion.c */
struct intel_encoder;
- extern int intel_opregion_setup(struct drm_device *dev);
#ifdef CONFIG_ACPI
+ extern int intel_opregion_setup(struct drm_device *dev);
extern void intel_opregion_init(struct drm_device *dev);
extern void intel_opregion_fini(struct drm_device *dev);
extern void intel_opregion_asle_intr(struct drm_device *dev);
extern int intel_opregion_notify_adapter(struct drm_device *dev,
pci_power_t state);
#else
+ static inline int intel_opregion_setup(struct drm_device *dev) { return 0; }
static inline void intel_opregion_init(struct drm_device *dev) { return; }
static inline void intel_opregion_fini(struct drm_device *dev) { return; }
static inline void intel_opregion_asle_intr(struct drm_device *dev) { return; }
extern void intel_modeset_setup_hw_state(struct drm_device *dev,
bool force_restore);
extern void i915_redisable_vga(struct drm_device *dev);
+extern void i915_redisable_vga_power_on(struct drm_device *dev);
extern bool intel_fbc_enabled(struct drm_device *dev);
extern void intel_disable_fbc(struct drm_device *dev);
extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
*/
void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine);
void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine);
+void assert_force_wake_inactive(struct drm_i915_private *dev_priv);
int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u8 mbox, u32 *val);
int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val);
/*
* Copyright © 2010 Daniel Vetter
+ * Copyright © 2011-2014 Intel Corporation
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
#include "i915_trace.h"
#include "intel_drv.h"
+bool intel_enable_ppgtt(struct drm_device *dev, bool full)
+{
+ if (i915.enable_ppgtt == 0 || !HAS_ALIASING_PPGTT(dev))
+ return false;
+
+ if (i915.enable_ppgtt == 1 && full)
+ return false;
+
+#ifdef CONFIG_INTEL_IOMMU
+ /* Disable ppgtt on SNB if VT-d is on. */
+ if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) {
+ DRM_INFO("Disabling PPGTT because VT-d is on\n");
+ return false;
+ }
+#endif
+
+ /* Full ppgtt disabled by default for now due to issues. */
+ if (full)
+ return false; /* HAS_PPGTT(dev) */
+ else
+ return HAS_ALIASING_PPGTT(dev);
+}
+
#define GEN6_PPGTT_PD_ENTRIES 512
#define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t))
typedef uint64_t gen8_gtt_pte_t;
#define GEN8_PTES_PER_PAGE (PAGE_SIZE / sizeof(gen8_gtt_pte_t))
#define GEN8_PDES_PER_PAGE (PAGE_SIZE / sizeof(gen8_ppgtt_pde_t))
-#define GEN8_LEGACY_PDPS 4
+
+/* GEN8 legacy style addressis defined as a 3 level page table:
+ * 31:30 | 29:21 | 20:12 | 11:0
+ * PDPE | PDE | PTE | offset
+ * The difference as compared to normal x86 3 level page table is the PDPEs are
+ * programmed via register.
+ */
+#define GEN8_PDPE_SHIFT 30
+#define GEN8_PDPE_MASK 0x3
+#define GEN8_PDE_SHIFT 21
+#define GEN8_PDE_MASK 0x1ff
+#define GEN8_PTE_SHIFT 12
+#define GEN8_PTE_MASK 0x1ff
#define PPAT_UNCACHED_INDEX (_PAGE_PWT | _PAGE_PCD)
#define PPAT_CACHED_PDE_INDEX 0 /* WB LLC */
}
static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
- unsigned first_entry,
- unsigned num_entries,
+ uint64_t start,
+ uint64_t length,
bool use_scratch)
{
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
gen8_gtt_pte_t *pt_vaddr, scratch_pte;
- unsigned act_pt = first_entry / GEN8_PTES_PER_PAGE;
- unsigned first_pte = first_entry % GEN8_PTES_PER_PAGE;
+ unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
+ unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
+ unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
+ unsigned num_entries = length >> PAGE_SHIFT;
unsigned last_pte, i;
scratch_pte = gen8_pte_encode(ppgtt->base.scratch.addr,
I915_CACHE_LLC, use_scratch);
while (num_entries) {
- struct page *page_table = &ppgtt->gen8_pt_pages[act_pt];
+ struct page *page_table = ppgtt->gen8_pt_pages[pdpe][pde];
- last_pte = first_pte + num_entries;
+ last_pte = pte + num_entries;
if (last_pte > GEN8_PTES_PER_PAGE)
last_pte = GEN8_PTES_PER_PAGE;
pt_vaddr = kmap_atomic(page_table);
- for (i = first_pte; i < last_pte; i++)
+ for (i = pte; i < last_pte; i++) {
pt_vaddr[i] = scratch_pte;
+ num_entries--;
+ }
kunmap_atomic(pt_vaddr);
- num_entries -= last_pte - first_pte;
- first_pte = 0;
- act_pt++;
+ pte = 0;
+ if (++pde == GEN8_PDES_PER_PAGE) {
+ pdpe++;
+ pde = 0;
+ }
}
}
static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
struct sg_table *pages,
- unsigned first_entry,
+ uint64_t start,
enum i915_cache_level cache_level)
{
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
gen8_gtt_pte_t *pt_vaddr;
- unsigned act_pt = first_entry / GEN8_PTES_PER_PAGE;
- unsigned act_pte = first_entry % GEN8_PTES_PER_PAGE;
+ unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
+ unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
+ unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
struct sg_page_iter sg_iter;
pt_vaddr = NULL;
+
for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
+ if (WARN_ON(pdpe >= GEN8_LEGACY_PDPS))
+ break;
+
if (pt_vaddr == NULL)
- pt_vaddr = kmap_atomic(&ppgtt->gen8_pt_pages[act_pt]);
+ pt_vaddr = kmap_atomic(ppgtt->gen8_pt_pages[pdpe][pde]);
- pt_vaddr[act_pte] =
+ pt_vaddr[pte] =
gen8_pte_encode(sg_page_iter_dma_address(&sg_iter),
cache_level, true);
- if (++act_pte == GEN8_PTES_PER_PAGE) {
+ if (++pte == GEN8_PTES_PER_PAGE) {
kunmap_atomic(pt_vaddr);
pt_vaddr = NULL;
- act_pt++;
- act_pte = 0;
+ if (++pde == GEN8_PDES_PER_PAGE) {
+ pdpe++;
+ pde = 0;
+ }
+ pte = 0;
}
}
if (pt_vaddr)
kunmap_atomic(pt_vaddr);
}
-static void gen8_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
+static void gen8_free_page_tables(struct page **pt_pages)
+{
+ int i;
+
+ if (pt_pages == NULL)
+ return;
+
+ for (i = 0; i < GEN8_PDES_PER_PAGE; i++)
+ if (pt_pages[i])
+ __free_pages(pt_pages[i], 0);
+}
+
+static void gen8_ppgtt_free(const struct i915_hw_ppgtt *ppgtt)
{
int i;
- for (i = 0; i < ppgtt->num_pd_pages ; i++)
+ for (i = 0; i < ppgtt->num_pd_pages; i++) {
+ gen8_free_page_tables(ppgtt->gen8_pt_pages[i]);
+ kfree(ppgtt->gen8_pt_pages[i]);
kfree(ppgtt->gen8_pt_dma_addr[i]);
+ }
- __free_pages(ppgtt->gen8_pt_pages, get_order(ppgtt->num_pt_pages << PAGE_SHIFT));
__free_pages(ppgtt->pd_pages, get_order(ppgtt->num_pd_pages << PAGE_SHIFT));
}
static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
{
+ struct pci_dev *hwdev = ppgtt->base.dev->pdev;
int i, j;
for (i = 0; i < ppgtt->num_pd_pages; i++) {
if (!ppgtt->pd_dma_addr[i])
continue;
- pci_unmap_page(ppgtt->base.dev->pdev,
- ppgtt->pd_dma_addr[i],
- PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+ pci_unmap_page(hwdev, ppgtt->pd_dma_addr[i], PAGE_SIZE,
+ PCI_DMA_BIDIRECTIONAL);
for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
dma_addr_t addr = ppgtt->gen8_pt_dma_addr[i][j];
if (addr)
- pci_unmap_page(ppgtt->base.dev->pdev,
- addr,
- PAGE_SIZE,
- PCI_DMA_BIDIRECTIONAL);
-
+ pci_unmap_page(hwdev, addr, PAGE_SIZE,
+ PCI_DMA_BIDIRECTIONAL);
}
}
}
gen8_ppgtt_free(ppgtt);
}
-/**
- * GEN8 legacy ppgtt programming is accomplished through 4 PDP registers with a
- * net effect resembling a 2-level page table in normal x86 terms. Each PDP
- * represents 1GB of memory
- * 4 * 512 * 512 * 4096 = 4GB legacy 32b address space.
- *
- * TODO: Do something with the size parameter
- **/
-static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
+static struct page **__gen8_alloc_page_tables(void)
{
- struct page *pt_pages;
- int i, j, ret = -ENOMEM;
- const int max_pdp = DIV_ROUND_UP(size, 1 << 30);
- const int num_pt_pages = GEN8_PDES_PER_PAGE * max_pdp;
+ struct page **pt_pages;
+ int i;
- if (size % (1<<30))
- DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size);
+ pt_pages = kcalloc(GEN8_PDES_PER_PAGE, sizeof(struct page *), GFP_KERNEL);
+ if (!pt_pages)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < GEN8_PDES_PER_PAGE; i++) {
+ pt_pages[i] = alloc_page(GFP_KERNEL);
+ if (!pt_pages[i])
+ goto bail;
+ }
- /* FIXME: split allocation into smaller pieces. For now we only ever do
- * this once, but with full PPGTT, the multiple contiguous allocations
- * will be bad.
+ return pt_pages;
+
+bail:
+ gen8_free_page_tables(pt_pages);
+ kfree(pt_pages);
+ return ERR_PTR(-ENOMEM);
+}
+
+static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt,
+ const int max_pdp)
+{
+ struct page **pt_pages[GEN8_LEGACY_PDPS];
+ int i, ret;
+
+ for (i = 0; i < max_pdp; i++) {
+ pt_pages[i] = __gen8_alloc_page_tables();
+ if (IS_ERR(pt_pages[i])) {
+ ret = PTR_ERR(pt_pages[i]);
+ goto unwind_out;
+ }
+ }
+
+ /* NB: Avoid touching gen8_pt_pages until last to keep the allocation,
+ * "atomic" - for cleanup purposes.
*/
+ for (i = 0; i < max_pdp; i++)
+ ppgtt->gen8_pt_pages[i] = pt_pages[i];
+
+ return 0;
+
+unwind_out:
+ while (i--) {
+ gen8_free_page_tables(pt_pages[i]);
+ kfree(pt_pages[i]);
+ }
+
+ return ret;
+}
+
+static int gen8_ppgtt_allocate_dma(struct i915_hw_ppgtt *ppgtt)
+{
+ int i;
+
+ for (i = 0; i < ppgtt->num_pd_pages; i++) {
+ ppgtt->gen8_pt_dma_addr[i] = kcalloc(GEN8_PDES_PER_PAGE,
+ sizeof(dma_addr_t),
+ GFP_KERNEL);
+ if (!ppgtt->gen8_pt_dma_addr[i])
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int gen8_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt,
+ const int max_pdp)
+{
ppgtt->pd_pages = alloc_pages(GFP_KERNEL, get_order(max_pdp << PAGE_SHIFT));
if (!ppgtt->pd_pages)
return -ENOMEM;
- pt_pages = alloc_pages(GFP_KERNEL, get_order(num_pt_pages << PAGE_SHIFT));
- if (!pt_pages) {
+ ppgtt->num_pd_pages = 1 << get_order(max_pdp << PAGE_SHIFT);
+ BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS);
+
+ return 0;
+}
+
+static int gen8_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt,
+ const int max_pdp)
+{
+ int ret;
+
+ ret = gen8_ppgtt_allocate_page_directories(ppgtt, max_pdp);
+ if (ret)
+ return ret;
+
+ ret = gen8_ppgtt_allocate_page_tables(ppgtt, max_pdp);
+ if (ret) {
__free_pages(ppgtt->pd_pages, get_order(max_pdp << PAGE_SHIFT));
- return -ENOMEM;
+ return ret;
}
- ppgtt->gen8_pt_pages = pt_pages;
- ppgtt->num_pd_pages = 1 << get_order(max_pdp << PAGE_SHIFT);
- ppgtt->num_pt_pages = 1 << get_order(num_pt_pages << PAGE_SHIFT);
ppgtt->num_pd_entries = max_pdp * GEN8_PDES_PER_PAGE;
- ppgtt->enable = gen8_ppgtt_enable;
- ppgtt->switch_mm = gen8_mm_switch;
- ppgtt->base.clear_range = gen8_ppgtt_clear_range;
- ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
- ppgtt->base.cleanup = gen8_ppgtt_cleanup;
- ppgtt->base.start = 0;
- ppgtt->base.total = ppgtt->num_pt_pages * GEN8_PTES_PER_PAGE * PAGE_SIZE;
- BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS);
+ ret = gen8_ppgtt_allocate_dma(ppgtt);
+ if (ret)
+ gen8_ppgtt_free(ppgtt);
- /*
- * - Create a mapping for the page directories.
- * - For each page directory:
- * allocate space for page table mappings.
- * map each page table
- */
- for (i = 0; i < max_pdp; i++) {
- dma_addr_t temp;
- temp = pci_map_page(ppgtt->base.dev->pdev,
- &ppgtt->pd_pages[i], 0,
- PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
- if (pci_dma_mapping_error(ppgtt->base.dev->pdev, temp))
- goto err_out;
+ return ret;
+}
- ppgtt->pd_dma_addr[i] = temp;
+static int gen8_ppgtt_setup_page_directories(struct i915_hw_ppgtt *ppgtt,
+ const int pd)
+{
+ dma_addr_t pd_addr;
+ int ret;
- ppgtt->gen8_pt_dma_addr[i] = kmalloc(sizeof(dma_addr_t) * GEN8_PDES_PER_PAGE, GFP_KERNEL);
- if (!ppgtt->gen8_pt_dma_addr[i])
- goto err_out;
+ pd_addr = pci_map_page(ppgtt->base.dev->pdev,
+ &ppgtt->pd_pages[pd], 0,
+ PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
- for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
- struct page *p = &pt_pages[i * GEN8_PDES_PER_PAGE + j];
- temp = pci_map_page(ppgtt->base.dev->pdev,
- p, 0, PAGE_SIZE,
- PCI_DMA_BIDIRECTIONAL);
+ ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pd_addr);
+ if (ret)
+ return ret;
+
+ ppgtt->pd_dma_addr[pd] = pd_addr;
+
+ return 0;
+}
- if (pci_dma_mapping_error(ppgtt->base.dev->pdev, temp))
- goto err_out;
+static int gen8_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt,
+ const int pd,
+ const int pt)
+{
+ dma_addr_t pt_addr;
+ struct page *p;
+ int ret;
- ppgtt->gen8_pt_dma_addr[i][j] = temp;
+ p = ppgtt->gen8_pt_pages[pd][pt];
+ pt_addr = pci_map_page(ppgtt->base.dev->pdev,
+ p, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+ ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pt_addr);
+ if (ret)
+ return ret;
+
+ ppgtt->gen8_pt_dma_addr[pd][pt] = pt_addr;
+
+ return 0;
+}
+
+/**
+ * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
+ * with a net effect resembling a 2-level page table in normal x86 terms. Each
+ * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
+ * space.
+ *
+ * FIXME: split allocation into smaller pieces. For now we only ever do this
+ * once, but with full PPGTT, the multiple contiguous allocations will be bad.
+ * TODO: Do something with the size parameter
+ */
+static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
+{
+ const int max_pdp = DIV_ROUND_UP(size, 1 << 30);
+ const int min_pt_pages = GEN8_PDES_PER_PAGE * max_pdp;
+ int i, j, ret;
+
+ if (size % (1<<30))
+ DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size);
+
+ /* 1. Do all our allocations for page directories and page tables. */
+ ret = gen8_ppgtt_alloc(ppgtt, max_pdp);
+ if (ret)
+ return ret;
+
+ /*
+ * 2. Create DMA mappings for the page directories and page tables.
+ */
+ for (i = 0; i < max_pdp; i++) {
+ ret = gen8_ppgtt_setup_page_directories(ppgtt, i);
+ if (ret)
+ goto bail;
+
+ for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
+ ret = gen8_ppgtt_setup_page_tables(ppgtt, i, j);
+ if (ret)
+ goto bail;
}
}
- /* For now, the PPGTT helper functions all require that the PDEs are
+ /*
+ * 3. Map all the page directory entires to point to the page tables
+ * we've allocated.
+ *
+ * For now, the PPGTT helper functions all require that the PDEs are
* plugged in correctly. So we do that now/here. For aliasing PPGTT, we
- * will never need to touch the PDEs again */
+ * will never need to touch the PDEs again.
+ */
for (i = 0; i < max_pdp; i++) {
gen8_ppgtt_pde_t *pd_vaddr;
pd_vaddr = kmap_atomic(&ppgtt->pd_pages[i]);
kunmap_atomic(pd_vaddr);
}
- ppgtt->base.clear_range(&ppgtt->base, 0,
- ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE,
- true);
+ ppgtt->enable = gen8_ppgtt_enable;
+ ppgtt->switch_mm = gen8_mm_switch;
+ ppgtt->base.clear_range = gen8_ppgtt_clear_range;
+ ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
+ ppgtt->base.cleanup = gen8_ppgtt_cleanup;
+ ppgtt->base.start = 0;
+ ppgtt->base.total = ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE * PAGE_SIZE;
+
+ ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
DRM_DEBUG_DRIVER("Allocated %d pages for page directories (%d wasted)\n",
ppgtt->num_pd_pages, ppgtt->num_pd_pages - max_pdp);
DRM_DEBUG_DRIVER("Allocated %d pages for page tables (%lld wasted)\n",
- ppgtt->num_pt_pages,
- (ppgtt->num_pt_pages - num_pt_pages) +
- size % (1<<30));
+ ppgtt->num_pd_entries,
+ (ppgtt->num_pd_entries - min_pt_pages) + size % (1<<30));
return 0;
-err_out:
- ppgtt->base.cleanup(&ppgtt->base);
+bail:
+ gen8_ppgtt_unmap_pages(ppgtt);
+ gen8_ppgtt_free(ppgtt);
return ret;
}
/* PPGTT support for Sandybdrige/Gen6 and later */
static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
- unsigned first_entry,
- unsigned num_entries,
+ uint64_t start,
+ uint64_t length,
bool use_scratch)
{
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
gen6_gtt_pte_t *pt_vaddr, scratch_pte;
+ unsigned first_entry = start >> PAGE_SHIFT;
+ unsigned num_entries = length >> PAGE_SHIFT;
unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
unsigned last_pte, i;
static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
struct sg_table *pages,
- unsigned first_entry,
+ uint64_t start,
enum i915_cache_level cache_level)
{
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
gen6_gtt_pte_t *pt_vaddr;
+ unsigned first_entry = start >> PAGE_SHIFT;
unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES;
struct sg_page_iter sg_iter;
kunmap_atomic(pt_vaddr);
}
-static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+static void gen6_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
{
- struct i915_hw_ppgtt *ppgtt =
- container_of(vm, struct i915_hw_ppgtt, base);
int i;
- list_del(&vm->global_link);
- drm_mm_takedown(&ppgtt->base.mm);
- drm_mm_remove_node(&ppgtt->node);
-
if (ppgtt->pt_dma_addr) {
for (i = 0; i < ppgtt->num_pd_entries; i++)
pci_unmap_page(ppgtt->base.dev->pdev,
ppgtt->pt_dma_addr[i],
4096, PCI_DMA_BIDIRECTIONAL);
}
+}
+
+static void gen6_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
+{
+ int i;
kfree(ppgtt->pt_dma_addr);
for (i = 0; i < ppgtt->num_pd_entries; i++)
__free_page(ppgtt->pt_pages[i]);
kfree(ppgtt->pt_pages);
- kfree(ppgtt);
}
-static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+{
+ struct i915_hw_ppgtt *ppgtt =
+ container_of(vm, struct i915_hw_ppgtt, base);
+
+ list_del(&vm->global_link);
+ drm_mm_takedown(&ppgtt->base.mm);
+ drm_mm_remove_node(&ppgtt->node);
+
+ gen6_ppgtt_unmap_pages(ppgtt);
+ gen6_ppgtt_free(ppgtt);
+}
+
+static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
{
#define GEN6_PD_ALIGN (PAGE_SIZE * 16)
#define GEN6_PD_SIZE (GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE)
struct drm_device *dev = ppgtt->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
bool retried = false;
- int i, ret;
+ int ret;
/* PPGTT PDEs reside in the GGTT and consists of 512 entries. The
* allocator works in address space sizes, so it's multiplied by page
if (ppgtt->node.start < dev_priv->gtt.mappable_end)
DRM_DEBUG("Forced to use aperture for PDEs\n");
- ppgtt->base.pte_encode = dev_priv->gtt.base.pte_encode;
ppgtt->num_pd_entries = GEN6_PPGTT_PD_ENTRIES;
- if (IS_GEN6(dev)) {
- ppgtt->enable = gen6_ppgtt_enable;
- ppgtt->switch_mm = gen6_mm_switch;
- } else if (IS_HASWELL(dev)) {
- ppgtt->enable = gen7_ppgtt_enable;
- ppgtt->switch_mm = hsw_mm_switch;
- } else if (IS_GEN7(dev)) {
- ppgtt->enable = gen7_ppgtt_enable;
- ppgtt->switch_mm = gen7_mm_switch;
- } else
- BUG();
- ppgtt->base.clear_range = gen6_ppgtt_clear_range;
- ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
- ppgtt->base.cleanup = gen6_ppgtt_cleanup;
- ppgtt->base.scratch = dev_priv->gtt.base.scratch;
- ppgtt->base.start = 0;
- ppgtt->base.total = GEN6_PPGTT_PD_ENTRIES * I915_PPGTT_PT_ENTRIES * PAGE_SIZE;
+ return ret;
+}
+
+static int gen6_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt)
+{
+ int i;
+
ppgtt->pt_pages = kcalloc(ppgtt->num_pd_entries, sizeof(struct page *),
GFP_KERNEL);
- if (!ppgtt->pt_pages) {
- drm_mm_remove_node(&ppgtt->node);
+
+ if (!ppgtt->pt_pages)
return -ENOMEM;
- }
for (i = 0; i < ppgtt->num_pd_entries; i++) {
ppgtt->pt_pages[i] = alloc_page(GFP_KERNEL);
- if (!ppgtt->pt_pages[i])
- goto err_pt_alloc;
+ if (!ppgtt->pt_pages[i]) {
+ gen6_ppgtt_free(ppgtt);
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
+static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
+{
+ int ret;
+
+ ret = gen6_ppgtt_allocate_page_directories(ppgtt);
+ if (ret)
+ return ret;
+
+ ret = gen6_ppgtt_allocate_page_tables(ppgtt);
+ if (ret) {
+ drm_mm_remove_node(&ppgtt->node);
+ return ret;
}
ppgtt->pt_dma_addr = kcalloc(ppgtt->num_pd_entries, sizeof(dma_addr_t),
GFP_KERNEL);
- if (!ppgtt->pt_dma_addr)
- goto err_pt_alloc;
+ if (!ppgtt->pt_dma_addr) {
+ drm_mm_remove_node(&ppgtt->node);
+ gen6_ppgtt_free(ppgtt);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int gen6_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt)
+{
+ struct drm_device *dev = ppgtt->base.dev;
+ int i;
for (i = 0; i < ppgtt->num_pd_entries; i++) {
dma_addr_t pt_addr;
PCI_DMA_BIDIRECTIONAL);
if (pci_dma_mapping_error(dev->pdev, pt_addr)) {
- ret = -EIO;
- goto err_pd_pin;
-
+ gen6_ppgtt_unmap_pages(ppgtt);
+ return -EIO;
}
+
ppgtt->pt_dma_addr[i] = pt_addr;
}
- ppgtt->base.clear_range(&ppgtt->base, 0,
- ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES, true);
+ return 0;
+}
+
+static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+{
+ struct drm_device *dev = ppgtt->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int ret;
+
+ ppgtt->base.pte_encode = dev_priv->gtt.base.pte_encode;
+ if (IS_GEN6(dev)) {
+ ppgtt->enable = gen6_ppgtt_enable;
+ ppgtt->switch_mm = gen6_mm_switch;
+ } else if (IS_HASWELL(dev)) {
+ ppgtt->enable = gen7_ppgtt_enable;
+ ppgtt->switch_mm = hsw_mm_switch;
+ } else if (IS_GEN7(dev)) {
+ ppgtt->enable = gen7_ppgtt_enable;
+ ppgtt->switch_mm = gen7_mm_switch;
+ } else
+ BUG();
+
+ ret = gen6_ppgtt_alloc(ppgtt);
+ if (ret)
+ return ret;
+
+ ret = gen6_ppgtt_setup_page_tables(ppgtt);
+ if (ret) {
+ gen6_ppgtt_free(ppgtt);
+ return ret;
+ }
+
+ ppgtt->base.clear_range = gen6_ppgtt_clear_range;
+ ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
+ ppgtt->base.cleanup = gen6_ppgtt_cleanup;
+ ppgtt->base.scratch = dev_priv->gtt.base.scratch;
+ ppgtt->base.start = 0;
+ ppgtt->base.total = GEN6_PPGTT_PD_ENTRIES * I915_PPGTT_PT_ENTRIES * PAGE_SIZE;
ppgtt->debug_dump = gen6_dump_ppgtt;
- DRM_DEBUG_DRIVER("Allocated pde space (%ldM) at GTT entry: %lx\n",
- ppgtt->node.size >> 20,
- ppgtt->node.start / PAGE_SIZE);
ppgtt->pd_offset =
ppgtt->node.start / PAGE_SIZE * sizeof(gen6_gtt_pte_t);
- return 0;
+ ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
-err_pd_pin:
- if (ppgtt->pt_dma_addr) {
- for (i--; i >= 0; i--)
- pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i],
- 4096, PCI_DMA_BIDIRECTIONAL);
- }
-err_pt_alloc:
- kfree(ppgtt->pt_dma_addr);
- for (i = 0; i < ppgtt->num_pd_entries; i++) {
- if (ppgtt->pt_pages[i])
- __free_page(ppgtt->pt_pages[i]);
- }
- kfree(ppgtt->pt_pages);
- drm_mm_remove_node(&ppgtt->node);
+ DRM_DEBUG_DRIVER("Allocated pde space (%ldM) at GTT entry: %lx\n",
+ ppgtt->node.size >> 20,
+ ppgtt->node.start / PAGE_SIZE);
- return ret;
+ return 0;
}
int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
enum i915_cache_level cache_level,
u32 flags)
{
- const unsigned long entry = vma->node.start >> PAGE_SHIFT;
-
WARN_ON(flags);
- vma->vm->insert_entries(vma->vm, vma->obj->pages, entry, cache_level);
+ vma->vm->insert_entries(vma->vm, vma->obj->pages, vma->node.start,
+ cache_level);
}
static void ppgtt_unbind_vma(struct i915_vma *vma)
{
- const unsigned long entry = vma->node.start >> PAGE_SHIFT;
-
vma->vm->clear_range(vma->vm,
- entry,
- vma->obj->base.size >> PAGE_SHIFT,
+ vma->node.start,
+ vma->obj->base.size,
true);
}
i915_check_and_clear_faults(dev);
dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
- dev_priv->gtt.base.start / PAGE_SIZE,
- dev_priv->gtt.base.total / PAGE_SIZE,
+ dev_priv->gtt.base.start,
+ dev_priv->gtt.base.total,
false);
}
/* First fill our portion of the GTT with scratch pages */
dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
- dev_priv->gtt.base.start / PAGE_SIZE,
- dev_priv->gtt.base.total / PAGE_SIZE,
+ dev_priv->gtt.base.start,
+ dev_priv->gtt.base.total,
true);
list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
struct sg_table *st,
- unsigned int first_entry,
+ uint64_t start,
enum i915_cache_level level)
{
struct drm_i915_private *dev_priv = vm->dev->dev_private;
+ unsigned first_entry = start >> PAGE_SHIFT;
gen8_gtt_pte_t __iomem *gtt_entries =
(gen8_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
int i = 0;
*/
static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
struct sg_table *st,
- unsigned int first_entry,
+ uint64_t start,
enum i915_cache_level level)
{
struct drm_i915_private *dev_priv = vm->dev->dev_private;
+ unsigned first_entry = start >> PAGE_SHIFT;
gen6_gtt_pte_t __iomem *gtt_entries =
(gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
int i = 0;
}
static void gen8_ggtt_clear_range(struct i915_address_space *vm,
- unsigned int first_entry,
- unsigned int num_entries,
+ uint64_t start,
+ uint64_t length,
bool use_scratch)
{
struct drm_i915_private *dev_priv = vm->dev->dev_private;
+ unsigned first_entry = start >> PAGE_SHIFT;
+ unsigned num_entries = length >> PAGE_SHIFT;
gen8_gtt_pte_t scratch_pte, __iomem *gtt_base =
(gen8_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
}
static void gen6_ggtt_clear_range(struct i915_address_space *vm,
- unsigned int first_entry,
- unsigned int num_entries,
+ uint64_t start,
+ uint64_t length,
bool use_scratch)
{
struct drm_i915_private *dev_priv = vm->dev->dev_private;
+ unsigned first_entry = start >> PAGE_SHIFT;
+ unsigned num_entries = length >> PAGE_SHIFT;
gen6_gtt_pte_t scratch_pte, __iomem *gtt_base =
(gen6_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
}
static void i915_ggtt_clear_range(struct i915_address_space *vm,
- unsigned int first_entry,
- unsigned int num_entries,
+ uint64_t start,
+ uint64_t length,
bool unused)
{
+ unsigned first_entry = start >> PAGE_SHIFT;
+ unsigned num_entries = length >> PAGE_SHIFT;
intel_gtt_clear_range(first_entry, num_entries);
}
struct drm_device *dev = vma->vm->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj = vma->obj;
- const unsigned long entry = vma->node.start >> PAGE_SHIFT;
/* If there is no aliasing PPGTT, or the caller needs a global mapping,
* or we have a global mapping already but the cacheability flags have
if (!dev_priv->mm.aliasing_ppgtt || flags & GLOBAL_BIND) {
if (!obj->has_global_gtt_mapping ||
(cache_level != obj->cache_level)) {
- vma->vm->insert_entries(vma->vm, obj->pages, entry,
+ vma->vm->insert_entries(vma->vm, obj->pages,
+ vma->node.start,
cache_level);
obj->has_global_gtt_mapping = 1;
}
(cache_level != obj->cache_level))) {
struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
appgtt->base.insert_entries(&appgtt->base,
- vma->obj->pages, entry, cache_level);
+ vma->obj->pages,
+ vma->node.start,
+ cache_level);
vma->obj->has_aliasing_ppgtt_mapping = 1;
}
}
struct drm_device *dev = vma->vm->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj = vma->obj;
- const unsigned long entry = vma->node.start >> PAGE_SHIFT;
if (obj->has_global_gtt_mapping) {
- vma->vm->clear_range(vma->vm, entry,
- vma->obj->base.size >> PAGE_SHIFT,
+ vma->vm->clear_range(vma->vm,
+ vma->node.start,
+ obj->base.size,
true);
obj->has_global_gtt_mapping = 0;
}
if (obj->has_aliasing_ppgtt_mapping) {
struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
appgtt->base.clear_range(&appgtt->base,
- entry,
- obj->base.size >> PAGE_SHIFT,
+ vma->node.start,
+ obj->base.size,
true);
obj->has_aliasing_ppgtt_mapping = 0;
}
/* Clear any non-preallocated blocks */
drm_mm_for_each_hole(entry, &ggtt_vm->mm, hole_start, hole_end) {
- const unsigned long count = (hole_end - hole_start) / PAGE_SIZE;
DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
hole_start, hole_end);
- ggtt_vm->clear_range(ggtt_vm, hole_start / PAGE_SIZE, count, true);
+ ggtt_vm->clear_range(ggtt_vm, hole_start,
+ hole_end - hole_start, true);
}
/* And finally clear the reserved guard page */
- ggtt_vm->clear_range(ggtt_vm, end / PAGE_SIZE - 1, 1, true);
+ ggtt_vm->clear_range(ggtt_vm, end - PAGE_SIZE, PAGE_SIZE, true);
}
void i915_gem_init_global_gtt(struct drm_device *dev)
bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
if (bdw_gmch_ctl)
bdw_gmch_ctl = 1 << bdw_gmch_ctl;
- if (bdw_gmch_ctl > 4) {
- WARN_ON(!i915.preliminary_hw_support);
- return 4<<20;
- }
-
return bdw_gmch_ctl << 20;
}
size_t gtt_size)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- phys_addr_t gtt_bus_addr;
+ phys_addr_t gtt_phys_addr;
int ret;
/* For Modern GENs the PTEs and register space are split in the BAR */
- gtt_bus_addr = pci_resource_start(dev->pdev, 0) +
+ gtt_phys_addr = pci_resource_start(dev->pdev, 0) +
(pci_resource_len(dev->pdev, 0) / 2);
- dev_priv->gtt.gsm = ioremap_wc(gtt_bus_addr, gtt_size);
+ dev_priv->gtt.gsm = ioremap_wc(gtt_phys_addr, gtt_size);
if (!dev_priv->gtt.gsm) {
DRM_ERROR("Failed to map the gtt page table\n");
return -ENOMEM;
va_list tmp;
va_copy(tmp, args);
- if (!__i915_error_seek(e, vsnprintf(NULL, 0, f, tmp)))
+ len = vsnprintf(NULL, 0, f, tmp);
+ va_end(tmp);
+
+ if (!__i915_error_seek(e, len))
return;
}
va_end(args);
}
+static void print_error_obj(struct drm_i915_error_state_buf *m,
+ struct drm_i915_error_object *obj)
+{
+ int page, offset, elt;
+
+ for (page = offset = 0; page < obj->page_count; page++) {
+ for (elt = 0; elt < PAGE_SIZE/4; elt++) {
+ err_printf(m, "%08x : %08x\n", offset,
+ obj->pages[page][elt]);
+ offset += 4;
+ }
+ }
+}
+
int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
const struct i915_error_state_file_priv *error_priv)
{
struct drm_device *dev = error_priv->dev;
drm_i915_private_t *dev_priv = dev->dev_private;
struct drm_i915_error_state *error = error_priv->error;
- int i, j, page, offset, elt;
+ int i, j, offset, elt;
+ int max_hangcheck_score;
if (!error) {
err_printf(m, "no error state collected\n");
goto out;
}
+ err_printf(m, "%s\n", error->error_msg);
err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
error->time.tv_usec);
err_printf(m, "Kernel: " UTS_RELEASE "\n");
+ max_hangcheck_score = 0;
+ for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
+ if (error->ring[i].hangcheck_score > max_hangcheck_score)
+ max_hangcheck_score = error->ring[i].hangcheck_score;
+ }
+ for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
+ if (error->ring[i].hangcheck_score == max_hangcheck_score &&
+ error->ring[i].pid != -1) {
+ err_printf(m, "Active process (on ring %s): %s [%d]\n",
+ ring_str(i),
+ error->ring[i].comm,
+ error->ring[i].pid);
+ }
+ }
+ err_printf(m, "Reset count: %u\n", error->reset_count);
+ err_printf(m, "Suspend count: %u\n", error->suspend_count);
err_printf(m, "PCI ID: 0x%04x\n", dev->pdev->device);
err_printf(m, "EIR: 0x%08x\n", error->eir);
err_printf(m, "IER: 0x%08x\n", error->ier);
for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
struct drm_i915_error_object *obj;
- if ((obj = error->ring[i].batchbuffer)) {
- err_printf(m, "%s --- gtt_offset = 0x%08x\n",
- dev_priv->ring[i].name,
+ obj = error->ring[i].batchbuffer;
+ if (obj) {
+ err_puts(m, dev_priv->ring[i].name);
+ if (error->ring[i].pid != -1)
+ err_printf(m, " (submitted by %s [%d])",
+ error->ring[i].comm,
+ error->ring[i].pid);
+ err_printf(m, " --- gtt_offset = 0x%08x\n",
obj->gtt_offset);
- offset = 0;
- for (page = 0; page < obj->page_count; page++) {
- for (elt = 0; elt < PAGE_SIZE/4; elt++) {
- err_printf(m, "%08x : %08x\n", offset,
- obj->pages[page][elt]);
- offset += 4;
- }
- }
+ print_error_obj(m, obj);
+ }
+
+ obj = error->ring[i].wa_batchbuffer;
+ if (obj) {
+ err_printf(m, "%s (w/a) --- gtt_offset = 0x%08x\n",
+ dev_priv->ring[i].name, obj->gtt_offset);
+ print_error_obj(m, obj);
}
if (error->ring[i].num_requests) {
err_printf(m, "%s --- ringbuffer = 0x%08x\n",
dev_priv->ring[i].name,
obj->gtt_offset);
- offset = 0;
- for (page = 0; page < obj->page_count; page++) {
- for (elt = 0; elt < PAGE_SIZE/4; elt++) {
- err_printf(m, "%08x : %08x\n",
- offset,
- obj->pages[page][elt]);
- offset += 4;
- }
- }
+ print_error_obj(m, obj);
}
if ((obj = error->ring[i].hws_page)) {
* It's only a small step better than a random number in its current form.
*/
static uint32_t i915_error_generate_code(struct drm_i915_private *dev_priv,
- struct drm_i915_error_state *error)
+ struct drm_i915_error_state *error,
+ int *ring_id)
{
uint32_t error_code = 0;
int i;
* synchronization commands which almost always appear in the case
* strictly a client bug. Use instdone to differentiate those some.
*/
- for (i = 0; i < I915_NUM_RINGS; i++)
- if (error->ring[i].hangcheck_action == HANGCHECK_HUNG)
+ for (i = 0; i < I915_NUM_RINGS; i++) {
+ if (error->ring[i].hangcheck_action == HANGCHECK_HUNG) {
+ if (ring_id)
+ *ring_id = i;
+
return error->ring[i].ipehr ^ error->ring[i].instdone;
+ }
+ }
return error_code;
}
}
}
-/* This assumes all batchbuffers are executed from the PPGTT. It might have to
- * change in the future. */
-static bool is_active_vm(struct i915_address_space *vm,
- struct intel_ring_buffer *ring)
-{
- struct drm_device *dev = vm->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct i915_hw_ppgtt *ppgtt;
-
- if (INTEL_INFO(dev)->gen < 7)
- return i915_is_ggtt(vm);
-
- /* FIXME: This ignores that the global gtt vm is also on this list. */
- ppgtt = container_of(vm, struct i915_hw_ppgtt, base);
-
- if (INTEL_INFO(dev)->gen >= 8) {
- u64 pdp0 = (u64)I915_READ(GEN8_RING_PDP_UDW(ring, 0)) << 32;
- pdp0 |= I915_READ(GEN8_RING_PDP_LDW(ring, 0));
- return pdp0 == ppgtt->pd_dma_addr[0];
- } else {
- u32 pp_db;
- pp_db = I915_READ(RING_PP_DIR_BASE(ring));
- return (pp_db >> 10) == ppgtt->pd_offset;
- }
-}
-
-static struct drm_i915_error_object *
-i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
- struct intel_ring_buffer *ring)
-{
- struct i915_address_space *vm;
- struct i915_vma *vma;
- struct drm_i915_gem_object *obj;
- bool found_active = false;
- u32 seqno;
-
- if (!ring->get_seqno)
- return NULL;
-
- if (HAS_BROKEN_CS_TLB(dev_priv->dev)) {
- u32 acthd = I915_READ(ACTHD);
-
- if (WARN_ON(ring->id != RCS))
- return NULL;
-
- obj = ring->scratch.obj;
- if (obj != NULL &&
- acthd >= i915_gem_obj_ggtt_offset(obj) &&
- acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
- return i915_error_ggtt_object_create(dev_priv, obj);
- }
-
- seqno = ring->get_seqno(ring, false);
- list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
- if (!is_active_vm(vm, ring))
- continue;
-
- found_active = true;
-
- list_for_each_entry(vma, &vm->active_list, mm_list) {
- obj = vma->obj;
- if (obj->ring != ring)
- continue;
-
- if (i915_seqno_passed(seqno, obj->last_read_seqno))
- continue;
-
- if ((obj->base.read_domains & I915_GEM_DOMAIN_COMMAND) == 0)
- continue;
-
- /* We need to copy these to an anonymous buffer as the simplest
- * method to avoid being overwritten by userspace.
- */
- return i915_error_object_create(dev_priv, obj, vm);
- }
- }
-
- WARN_ON(!found_active);
- return NULL;
-}
-
static void i915_record_ring_state(struct drm_device *dev,
struct intel_ring_buffer *ring,
struct drm_i915_error_ring *ering)
i915_record_ring_state(dev, ring, &error->ring[i]);
- error->ring[i].batchbuffer =
- i915_error_first_batchbuffer(dev_priv, ring);
+ error->ring[i].pid = -1;
+ request = i915_gem_find_active_request(ring);
+ if (request) {
+ /* We need to copy these to an anonymous buffer
+ * as the simplest method to avoid being overwritten
+ * by userspace.
+ */
+ error->ring[i].batchbuffer =
+ i915_error_object_create(dev_priv,
+ request->batch_obj,
+ request->ctx ?
+ request->ctx->vm :
+ &dev_priv->gtt.base);
+
+ if (HAS_BROKEN_CS_TLB(dev_priv->dev) &&
+ ring->scratch.obj)
+ error->ring[i].wa_batchbuffer =
+ i915_error_ggtt_object_create(dev_priv,
+ ring->scratch.obj);
+
+ if (request->file_priv) {
+ struct task_struct *task;
+
+ rcu_read_lock();
+ task = pid_task(request->file_priv->file->pid,
+ PIDTYPE_PID);
+ if (task) {
+ strcpy(error->ring[i].comm, task->comm);
+ error->ring[i].pid = task->pid;
+ }
+ rcu_read_unlock();
+ }
+ }
error->ring[i].ringbuffer =
i915_error_ggtt_object_create(dev_priv, ring->obj);
i915_get_extra_instdone(dev, error->extra_instdone);
}
+static void i915_error_capture_msg(struct drm_device *dev,
+ struct drm_i915_error_state *error,
+ bool wedged,
+ const char *error_msg)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 ecode;
+ int ring_id = -1, len;
+
+ ecode = i915_error_generate_code(dev_priv, error, &ring_id);
+
+ len = scnprintf(error->error_msg, sizeof(error->error_msg),
+ "GPU HANG: ecode %d:0x%08x", ring_id, ecode);
+
+ if (ring_id != -1 && error->ring[ring_id].pid != -1)
+ len += scnprintf(error->error_msg + len,
+ sizeof(error->error_msg) - len,
+ ", in %s [%d]",
+ error->ring[ring_id].comm,
+ error->ring[ring_id].pid);
+
+ scnprintf(error->error_msg + len, sizeof(error->error_msg) - len,
+ ", reason: %s, action: %s",
+ error_msg,
+ wedged ? "reset" : "continue");
+}
+
+static void i915_capture_gen_state(struct drm_i915_private *dev_priv,
+ struct drm_i915_error_state *error)
+{
+ error->reset_count = i915_reset_count(&dev_priv->gpu_error);
+ error->suspend_count = dev_priv->suspend_count;
+}
+
/**
* i915_capture_error_state - capture an error record for later analysis
* @dev: drm device
* out a structure which becomes available in debugfs for user level tools
* to pick up.
*/
-void i915_capture_error_state(struct drm_device *dev)
+void i915_capture_error_state(struct drm_device *dev, bool wedged,
+ const char *error_msg)
{
static bool warned;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_error_state *error;
unsigned long flags;
- uint32_t ecode;
-
- spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
- error = dev_priv->gpu_error.first_error;
- spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
- if (error)
- return;
/* Account for pipe specific data like PIPE*STAT */
error = kzalloc(sizeof(*error), GFP_ATOMIC);
return;
}
- DRM_INFO("GPU crash dump saved to /sys/class/drm/card%d/error\n",
- dev->primary->index);
kref_init(&error->ref);
+ i915_capture_gen_state(dev_priv, error);
i915_capture_reg_state(dev_priv, error);
i915_gem_capture_buffers(dev_priv, error);
i915_gem_record_fences(dev, error);
i915_gem_record_rings(dev, error);
- ecode = i915_error_generate_code(dev_priv, error);
-
- if (!warned) {
- DRM_INFO("GPU HANG [%x]\n", ecode);
- DRM_INFO("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n");
- DRM_INFO("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
- DRM_INFO("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
- DRM_INFO("The gpu crash dump is required to analyze gpu hangs, so please always attach it.\n");
- warned = true;
- }
do_gettimeofday(&error->time);
error->overlay = intel_overlay_capture_error_state(dev);
error->display = intel_display_capture_error_state(dev);
+ i915_error_capture_msg(dev, error, wedged, error_msg);
+ DRM_INFO("%s\n", error->error_msg);
+
spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
if (dev_priv->gpu_error.first_error == NULL) {
dev_priv->gpu_error.first_error = error;
}
spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
- if (error)
+ if (error) {
i915_error_state_free(&error->ref);
+ return;
+ }
+
+ if (!warned) {
+ DRM_INFO("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n");
+ DRM_INFO("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
+ DRM_INFO("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
+ DRM_INFO("The gpu crash dump is required to analyze gpu hangs, so please always attach it.\n");
+ DRM_INFO("GPU crash dump saved to /sys/class/drm/card%d/error\n", dev->primary->index);
+ warned = true;
+ }
}
void i915_error_state_get(struct drm_device *dev,
*
* Returns the previous state of underrun reporting.
*/
-bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
- enum pipe pipe, bool enable)
+bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
+ enum pipe pipe, bool enable)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- unsigned long flags;
bool ret;
- spin_lock_irqsave(&dev_priv->irq_lock, flags);
+ assert_spin_locked(&dev_priv->irq_lock);
ret = !intel_crtc->cpu_fifo_underrun_disabled;
broadwell_set_fifo_underrun_reporting(dev, pipe, enable);
done:
+ return ret;
+}
+
+bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
+ enum pipe pipe, bool enable)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned long flags;
+ bool ret;
+
+ spin_lock_irqsave(&dev_priv->irq_lock, flags);
+ ret = __intel_set_cpu_fifo_underrun_reporting(dev, pipe, enable);
spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+
return ret;
}
}
-void
+static void
__i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
u32 enable_mask, u32 status_mask)
{
POSTING_READ(reg);
}
-void
+static void
__i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
u32 enable_mask, u32 status_mask)
{
vbl_start = mode->crtc_vblank_start * mode->crtc_htotal;
} else {
- enum transcoder cpu_transcoder =
- intel_pipe_to_cpu_transcoder(dev_priv, pipe);
+ enum transcoder cpu_transcoder = (enum transcoder) pipe;
u32 htotal;
htotal = ((I915_READ(HTOTAL(cpu_transcoder)) >> 16) & 0x1fff) + 1;
if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
GT_BSD_CS_ERROR_INTERRUPT |
GT_RENDER_CS_MASTER_ERROR_INTERRUPT)) {
- DRM_ERROR("GT error interrupt 0x%08x\n", gt_iir);
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false, "GT error interrupt 0x%08x",
+ gt_iir);
}
if (gt_iir & GT_PARITY_ERROR(dev))
notify_ring(dev_priv->dev, &dev_priv->ring[VECS]);
if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT) {
- DRM_ERROR("VEBOX CS error interrupt 0x%08x\n", pm_iir);
- i915_handle_error(dev_priv->dev, false);
+ i915_handle_error(dev_priv->dev, false,
+ "VEBOX CS error interrupt 0x%08x",
+ pm_iir);
}
}
}
static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- enum pipe i;
+ enum pipe pipe;
if (de_iir & DE_ERR_INT_IVB)
ivb_err_int_handler(dev);
if (de_iir & DE_GSE_IVB)
intel_opregion_asle_intr(dev);
- for_each_pipe(i) {
- if (de_iir & (DE_PIPE_VBLANK_IVB(i)))
- drm_handle_vblank(dev, i);
+ for_each_pipe(pipe) {
+ if (de_iir & (DE_PIPE_VBLANK_IVB(pipe)))
+ drm_handle_vblank(dev, pipe);
/* plane/pipes map 1:1 on ilk+ */
- if (de_iir & DE_PLANE_FLIP_DONE_IVB(i)) {
- intel_prepare_page_flip(dev, i);
- intel_finish_page_flip_plane(dev, i);
+ if (de_iir & DE_PLANE_FLIP_DONE_IVB(pipe)) {
+ intel_prepare_page_flip(dev, pipe);
+ intel_finish_page_flip_plane(dev, pipe);
}
}
* so userspace knows something bad happened (should trigger collection
* of a ring dump etc.).
*/
-void i915_handle_error(struct drm_device *dev, bool wedged)
+void i915_handle_error(struct drm_device *dev, bool wedged,
+ const char *fmt, ...)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ va_list args;
+ char error_msg[80];
+
+ va_start(args, fmt);
+ vscnprintf(error_msg, sizeof(error_msg), fmt, args);
+ va_end(args);
- i915_capture_error_state(dev);
+ i915_capture_error_state(dev, wedged, error_msg);
i915_report_and_clear_eir(dev);
if (wedged) {
*/
tmp = I915_READ_CTL(ring);
if (tmp & RING_WAIT) {
- DRM_ERROR("Kicking stuck wait on %s\n",
- ring->name);
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Kicking stuck wait on %s",
+ ring->name);
I915_WRITE_CTL(ring, tmp);
return HANGCHECK_KICK;
}
default:
return HANGCHECK_HUNG;
case 1:
- DRM_ERROR("Kicking stuck semaphore on %s\n",
- ring->name);
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Kicking stuck semaphore on %s",
+ ring->name);
I915_WRITE_CTL(ring, tmp);
return HANGCHECK_KICK;
case 0:
}
if (rings_hung)
- return i915_handle_error(dev, true);
+ return i915_handle_error(dev, true, "Ring hung");
if (busy_count)
/* Reset timer case chip hangs without another request
return 0;
}
+static void valleyview_display_irqs_install(struct drm_i915_private *dev_priv)
+{
+ u32 pipestat_mask;
+ u32 iir_mask;
+
+ pipestat_mask = PIPESTAT_INT_STATUS_MASK |
+ PIPE_FIFO_UNDERRUN_STATUS;
+
+ I915_WRITE(PIPESTAT(PIPE_A), pipestat_mask);
+ I915_WRITE(PIPESTAT(PIPE_B), pipestat_mask);
+ POSTING_READ(PIPESTAT(PIPE_A));
+
+ pipestat_mask = PLANE_FLIP_DONE_INT_STATUS_VLV |
+ PIPE_CRC_DONE_INTERRUPT_STATUS;
+
+ i915_enable_pipestat(dev_priv, PIPE_A, pipestat_mask |
+ PIPE_GMBUS_INTERRUPT_STATUS);
+ i915_enable_pipestat(dev_priv, PIPE_B, pipestat_mask);
+
+ iir_mask = I915_DISPLAY_PORT_INTERRUPT |
+ I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
+ I915_DISPLAY_PIPE_B_EVENT_INTERRUPT;
+ dev_priv->irq_mask &= ~iir_mask;
+
+ I915_WRITE(VLV_IIR, iir_mask);
+ I915_WRITE(VLV_IIR, iir_mask);
+ I915_WRITE(VLV_IMR, dev_priv->irq_mask);
+ I915_WRITE(VLV_IER, ~dev_priv->irq_mask);
+ POSTING_READ(VLV_IER);
+}
+
+static void valleyview_display_irqs_uninstall(struct drm_i915_private *dev_priv)
+{
+ u32 pipestat_mask;
+ u32 iir_mask;
+
+ iir_mask = I915_DISPLAY_PORT_INTERRUPT |
+ I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
+ I915_DISPLAY_PIPE_A_EVENT_INTERRUPT;
+
+ dev_priv->irq_mask |= iir_mask;
+ I915_WRITE(VLV_IER, ~dev_priv->irq_mask);
+ I915_WRITE(VLV_IMR, dev_priv->irq_mask);
+ I915_WRITE(VLV_IIR, iir_mask);
+ I915_WRITE(VLV_IIR, iir_mask);
+ POSTING_READ(VLV_IIR);
+
+ pipestat_mask = PLANE_FLIP_DONE_INT_STATUS_VLV |
+ PIPE_CRC_DONE_INTERRUPT_STATUS;
+
+ i915_disable_pipestat(dev_priv, PIPE_A, pipestat_mask |
+ PIPE_GMBUS_INTERRUPT_STATUS);
+ i915_disable_pipestat(dev_priv, PIPE_B, pipestat_mask);
+
+ pipestat_mask = PIPESTAT_INT_STATUS_MASK |
+ PIPE_FIFO_UNDERRUN_STATUS;
+ I915_WRITE(PIPESTAT(PIPE_A), pipestat_mask);
+ I915_WRITE(PIPESTAT(PIPE_B), pipestat_mask);
+ POSTING_READ(PIPESTAT(PIPE_A));
+}
+
+void valleyview_enable_display_irqs(struct drm_i915_private *dev_priv)
+{
+ assert_spin_locked(&dev_priv->irq_lock);
+
+ if (dev_priv->display_irqs_enabled)
+ return;
+
+ dev_priv->display_irqs_enabled = true;
+
+ if (dev_priv->dev->irq_enabled)
+ valleyview_display_irqs_install(dev_priv);
+}
+
+void valleyview_disable_display_irqs(struct drm_i915_private *dev_priv)
+{
+ assert_spin_locked(&dev_priv->irq_lock);
+
+ if (!dev_priv->display_irqs_enabled)
+ return;
+
+ dev_priv->display_irqs_enabled = false;
+
+ if (dev_priv->dev->irq_enabled)
+ valleyview_display_irqs_uninstall(dev_priv);
+}
+
static int valleyview_irq_postinstall(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
- u32 enable_mask;
- u32 pipestat_enable = PLANE_FLIP_DONE_INT_STATUS_VLV |
- PIPE_CRC_DONE_INTERRUPT_STATUS;
unsigned long irqflags;
- enable_mask = I915_DISPLAY_PORT_INTERRUPT;
- enable_mask |= I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
- I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT |
- I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
- I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
-
- /*
- *Leave vblank interrupts masked initially. enable/disable will
- * toggle them based on usage.
- */
- dev_priv->irq_mask = (~enable_mask) |
- I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT |
- I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
+ dev_priv->irq_mask = ~0;
I915_WRITE(PORT_HOTPLUG_EN, 0);
POSTING_READ(PORT_HOTPLUG_EN);
I915_WRITE(VLV_IMR, dev_priv->irq_mask);
- I915_WRITE(VLV_IER, enable_mask);
+ I915_WRITE(VLV_IER, ~dev_priv->irq_mask);
I915_WRITE(VLV_IIR, 0xffffffff);
- I915_WRITE(PIPESTAT(0), 0xffff);
- I915_WRITE(PIPESTAT(1), 0xffff);
POSTING_READ(VLV_IER);
/* Interrupt setup is already guaranteed to be single-threaded, this is
* just to make the assert_spin_locked check happy. */
spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
- i915_enable_pipestat(dev_priv, PIPE_A, pipestat_enable);
- i915_enable_pipestat(dev_priv, PIPE_A, PIPE_GMBUS_INTERRUPT_STATUS);
- i915_enable_pipestat(dev_priv, PIPE_B, pipestat_enable);
+ if (dev_priv->display_irqs_enabled)
+ valleyview_display_irqs_install(dev_priv);
spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
I915_WRITE(VLV_IIR, 0xffffffff);
static void valleyview_irq_uninstall(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+ unsigned long irqflags;
int pipe;
if (!dev_priv)
I915_WRITE(HWSTAM, 0xffffffff);
I915_WRITE(PORT_HOTPLUG_EN, 0);
I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
- for_each_pipe(pipe)
- I915_WRITE(PIPESTAT(pipe), 0xffff);
+
+ spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+ if (dev_priv->display_irqs_enabled)
+ valleyview_display_irqs_uninstall(dev_priv);
+ spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+
+ dev_priv->irq_mask = 0;
+
I915_WRITE(VLV_IIR, 0xffffffff);
I915_WRITE(VLV_IMR, 0xffffffff);
I915_WRITE(VLV_IER, 0x0);
*/
spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Command parser error, iir 0x%08x",
+ iir);
for_each_pipe(pipe) {
int reg = PIPESTAT(pipe);
*/
spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Command parser error, iir 0x%08x",
+ iir);
for_each_pipe(pipe) {
int reg = PIPESTAT(pipe);
*/
spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
- i915_handle_error(dev, false);
+ i915_handle_error(dev, false,
+ "Command parser error, iir 0x%08x",
+ iir);
for_each_pipe(pipe) {
int reg = PIPESTAT(pipe);
if (pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE)
state = true;
- if (!intel_display_power_enabled(dev_priv->dev,
+ if (!intel_display_power_enabled(dev_priv,
POWER_DOMAIN_TRANSCODER(cpu_transcoder))) {
cur_state = false;
} else {
enum pipe pipe)
{
struct drm_device *dev = dev_priv->dev;
- int reg, i;
+ int reg, sprite;
u32 val;
if (IS_VALLEYVIEW(dev)) {
- for (i = 0; i < INTEL_INFO(dev)->num_sprites; i++) {
- reg = SPCNTR(pipe, i);
+ for_each_sprite(pipe, sprite) {
+ reg = SPCNTR(pipe, sprite);
val = I915_READ(reg);
WARN((val & SP_ENABLE),
"sprite %c assertion failure, should be off on pipe %c but is still active\n",
- sprite_name(pipe, i), pipe_name(pipe));
+ sprite_name(pipe, sprite), pipe_name(pipe));
}
} else if (INTEL_INFO(dev)->gen >= 7) {
reg = SPRCTL(pipe);
return ret;
}
+static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc)
+{
+ struct drm_device *dev = crtc->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ unsigned long flags;
+ bool pending;
+
+ if (i915_reset_in_progress(&dev_priv->gpu_error) ||
+ intel_crtc->reset_counter != atomic_read(&dev_priv->gpu_error.reset_counter))
+ return false;
+
+ spin_lock_irqsave(&dev->event_lock, flags);
+ pending = to_intel_crtc(crtc)->unpin_work != NULL;
+ spin_unlock_irqrestore(&dev->event_lock, flags);
+
+ return pending;
+}
+
static int
intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
struct drm_framebuffer *fb)
struct drm_framebuffer *old_fb;
int ret;
+ if (intel_crtc_has_pending_flip(crtc)) {
+ DRM_ERROR("pipe is still busy with an old pageflip\n");
+ return -EBUSY;
+ }
+
/* no fb bound */
if (!fb) {
DRM_ERROR("No FB bound\n");
udelay(100);
}
-static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc)
-{
- struct drm_device *dev = crtc->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- unsigned long flags;
- bool pending;
-
- if (i915_reset_in_progress(&dev_priv->gpu_error) ||
- intel_crtc->reset_counter != atomic_read(&dev_priv->gpu_error.reset_counter))
- return false;
-
- spin_lock_irqsave(&dev->event_lock, flags);
- pending = to_intel_crtc(crtc)->unpin_work != NULL;
- spin_unlock_irqrestore(&dev->event_lock, flags);
-
- return pending;
-}
-
bool intel_has_pending_fb_unpin(struct drm_device *dev)
{
struct intel_crtc *crtc;
I915_WRITE(BCLRPAT(crtc->pipe), 0);
}
+#define for_each_power_domain(domain, mask) \
+ for ((domain) = 0; (domain) < POWER_DOMAIN_NUM; (domain)++) \
+ if ((1 << (domain)) & (mask))
+
+enum intel_display_power_domain
+intel_display_port_power_domain(struct intel_encoder *intel_encoder)
+{
+ struct drm_device *dev = intel_encoder->base.dev;
+ struct intel_digital_port *intel_dig_port;
+
+ switch (intel_encoder->type) {
+ case INTEL_OUTPUT_UNKNOWN:
+ /* Only DDI platforms should ever use this output type */
+ WARN_ON_ONCE(!HAS_DDI(dev));
+ case INTEL_OUTPUT_DISPLAYPORT:
+ case INTEL_OUTPUT_HDMI:
+ case INTEL_OUTPUT_EDP:
+ intel_dig_port = enc_to_dig_port(&intel_encoder->base);
+ switch (intel_dig_port->port) {
+ case PORT_A:
+ return POWER_DOMAIN_PORT_DDI_A_4_LANES;
+ case PORT_B:
+ return POWER_DOMAIN_PORT_DDI_B_4_LANES;
+ case PORT_C:
+ return POWER_DOMAIN_PORT_DDI_C_4_LANES;
+ case PORT_D:
+ return POWER_DOMAIN_PORT_DDI_D_4_LANES;
+ default:
+ WARN_ON_ONCE(1);
+ return POWER_DOMAIN_PORT_OTHER;
+ }
+ case INTEL_OUTPUT_ANALOG:
+ return POWER_DOMAIN_PORT_CRT;
+ case INTEL_OUTPUT_DSI:
+ return POWER_DOMAIN_PORT_DSI;
+ default:
+ return POWER_DOMAIN_PORT_OTHER;
+ }
+}
+
+static unsigned long get_crtc_power_domains(struct drm_crtc *crtc)
+{
+ struct drm_device *dev = crtc->dev;
+ struct intel_encoder *intel_encoder;
+ struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ enum pipe pipe = intel_crtc->pipe;
+ bool pfit_enabled = intel_crtc->config.pch_pfit.enabled;
+ unsigned long mask;
+ enum transcoder transcoder;
+
+ transcoder = intel_pipe_to_cpu_transcoder(dev->dev_private, pipe);
+
+ mask = BIT(POWER_DOMAIN_PIPE(pipe));
+ mask |= BIT(POWER_DOMAIN_TRANSCODER(transcoder));
+ if (pfit_enabled)
+ mask |= BIT(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe));
+
+ for_each_encoder_on_crtc(dev, crtc, intel_encoder)
+ mask |= BIT(intel_display_port_power_domain(intel_encoder));
+
+ return mask;
+}
+
+void intel_display_set_init_power(struct drm_i915_private *dev_priv,
+ bool enable)
+{
+ if (dev_priv->power_domains.init_power_on == enable)
+ return;
+
+ if (enable)
+ intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+ else
+ intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+
+ dev_priv->power_domains.init_power_on = enable;
+}
+
+static void modeset_update_crtc_power_domains(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned long pipe_domains[I915_MAX_PIPES] = { 0, };
+ struct intel_crtc *crtc;
+
+ /*
+ * First get all needed power domains, then put all unneeded, to avoid
+ * any unnecessary toggling of the power wells.
+ */
+ list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+ enum intel_display_power_domain domain;
+
+ if (!crtc->base.enabled)
+ continue;
+
+ pipe_domains[crtc->pipe] = get_crtc_power_domains(&crtc->base);
+
+ for_each_power_domain(domain, pipe_domains[crtc->pipe])
+ intel_display_power_get(dev_priv, domain);
+ }
+
+ list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+ enum intel_display_power_domain domain;
+
+ for_each_power_domain(domain, crtc->enabled_power_domains)
+ intel_display_power_put(dev_priv, domain);
+
+ crtc->enabled_power_domains = pipe_domains[crtc->pipe];
+ }
+
+ intel_display_set_init_power(dev_priv, false);
+}
+
int valleyview_get_vco(struct drm_i915_private *dev_priv)
{
int hpll_freq, vco_freq[] = { 800, 1600, 2000, 2400 };
if (req_cdclk != cur_cdclk)
valleyview_set_cdclk(dev, req_cdclk);
+ modeset_update_crtc_power_domains(dev);
}
static void valleyview_crtc_enable(struct drm_crtc *crtc)
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t tmp;
+ if (!intel_display_power_enabled(dev_priv,
+ POWER_DOMAIN_PIPE(crtc->pipe)))
+ return false;
+
pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
pipe_config->shared_dpll = DPLL_ID_PRIVATE;
* is 2.5%; use 5% for safety's sake.
*/
u32 bps = target_clock * bpp * 21 / 20;
- return bps / (link_bw * 8) + 1;
+ return DIV_ROUND_UP(bps, link_bw * 8);
}
static bool ironlake_needs_fb_cb_tune(struct dpll *dpll, int factor)
mutex_unlock(&dev_priv->pc8.lock);
}
-static void hsw_package_c8_gpu_idle(struct drm_i915_private *dev_priv)
-{
- if (!HAS_PC8(dev_priv->dev))
- return;
-
- mutex_lock(&dev_priv->pc8.lock);
- if (!dev_priv->pc8.gpu_idle) {
- dev_priv->pc8.gpu_idle = true;
- __hsw_enable_package_c8(dev_priv);
- }
- mutex_unlock(&dev_priv->pc8.lock);
-}
-
-static void hsw_package_c8_gpu_busy(struct drm_i915_private *dev_priv)
-{
- if (!HAS_PC8(dev_priv->dev))
- return;
-
- mutex_lock(&dev_priv->pc8.lock);
- if (dev_priv->pc8.gpu_idle) {
- dev_priv->pc8.gpu_idle = false;
- __hsw_disable_package_c8(dev_priv);
- }
- mutex_unlock(&dev_priv->pc8.lock);
-}
-
-#define for_each_power_domain(domain, mask) \
- for ((domain) = 0; (domain) < POWER_DOMAIN_NUM; (domain)++) \
- if ((1 << (domain)) & (mask))
-
-static unsigned long get_pipe_power_domains(struct drm_device *dev,
- enum pipe pipe, bool pfit_enabled)
-{
- unsigned long mask;
- enum transcoder transcoder;
-
- transcoder = intel_pipe_to_cpu_transcoder(dev->dev_private, pipe);
-
- mask = BIT(POWER_DOMAIN_PIPE(pipe));
- mask |= BIT(POWER_DOMAIN_TRANSCODER(transcoder));
- if (pfit_enabled)
- mask |= BIT(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe));
-
- return mask;
-}
-
-void intel_display_set_init_power(struct drm_device *dev, bool enable)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- if (dev_priv->power_domains.init_power_on == enable)
- return;
-
- if (enable)
- intel_display_power_get(dev, POWER_DOMAIN_INIT);
- else
- intel_display_power_put(dev, POWER_DOMAIN_INIT);
-
- dev_priv->power_domains.init_power_on = enable;
-}
-
-static void modeset_update_power_wells(struct drm_device *dev)
-{
- unsigned long pipe_domains[I915_MAX_PIPES] = { 0, };
- struct intel_crtc *crtc;
-
- /*
- * First get all needed power domains, then put all unneeded, to avoid
- * any unnecessary toggling of the power wells.
- */
- list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
- enum intel_display_power_domain domain;
-
- if (!crtc->base.enabled)
- continue;
-
- pipe_domains[crtc->pipe] = get_pipe_power_domains(dev,
- crtc->pipe,
- crtc->config.pch_pfit.enabled);
-
- for_each_power_domain(domain, pipe_domains[crtc->pipe])
- intel_display_power_get(dev, domain);
- }
-
- list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
- enum intel_display_power_domain domain;
-
- for_each_power_domain(domain, crtc->enabled_power_domains)
- intel_display_power_put(dev, domain);
-
- crtc->enabled_power_domains = pipe_domains[crtc->pipe];
- }
-
- intel_display_set_init_power(dev, false);
-}
-
static void haswell_modeset_global_resources(struct drm_device *dev)
{
- modeset_update_power_wells(dev);
+ modeset_update_crtc_power_domains(dev);
hsw_update_package_c8(dev);
}
enum intel_display_power_domain pfit_domain;
uint32_t tmp;
+ if (!intel_display_power_enabled(dev_priv,
+ POWER_DOMAIN_PIPE(crtc->pipe)))
+ return false;
+
pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
pipe_config->shared_dpll = DPLL_ID_PRIVATE;
pipe_config->cpu_transcoder = TRANSCODER_EDP;
}
- if (!intel_display_power_enabled(dev,
+ if (!intel_display_power_enabled(dev_priv,
POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder)))
return false;
intel_get_pipe_timings(crtc, pipe_config);
pfit_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe);
- if (intel_display_power_enabled(dev, pfit_domain))
+ if (intel_display_power_enabled(dev_priv, pfit_domain))
ironlake_get_pfit_config(crtc, pipe_config);
if (IS_HASWELL(dev))
return -ENOENT;
if (obj->base.size < width * height * 4) {
- DRM_ERROR("buffer is to small\n");
+ DRM_DEBUG_KMS("buffer is to small\n");
ret = -ENOMEM;
goto fail;
}
unsigned alignment;
if (obj->tiling_mode) {
- DRM_ERROR("cursor cannot be tiled\n");
+ DRM_DEBUG_KMS("cursor cannot be tiled\n");
ret = -EINVAL;
goto fail_locked;
}
ret = i915_gem_object_pin_to_display_plane(obj, alignment, NULL);
if (ret) {
- DRM_ERROR("failed to move cursor bo into the GTT\n");
+ DRM_DEBUG_KMS("failed to move cursor bo into the GTT\n");
goto fail_locked;
}
ret = i915_gem_object_put_fence(obj);
if (ret) {
- DRM_ERROR("failed to release fence for cursor");
+ DRM_DEBUG_KMS("failed to release fence for cursor");
goto fail_unpin;
}
(intel_crtc->pipe == 0) ? I915_GEM_PHYS_CURSOR_0 : I915_GEM_PHYS_CURSOR_1,
align);
if (ret) {
- DRM_ERROR("failed to attach phys object\n");
+ DRM_DEBUG_KMS("failed to attach phys object\n");
goto fail_locked;
}
addr = obj->phys_obj->handle->busaddr;
return ERR_PTR(ret);
}
-struct drm_framebuffer *
+static struct drm_framebuffer *
intel_framebuffer_create(struct drm_device *dev,
struct drm_mode_fb_cmd2 *mode_cmd,
struct drm_i915_gem_object *obj)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- hsw_package_c8_gpu_busy(dev_priv);
+ if (dev_priv->mm.busy)
+ return;
+
+ hsw_disable_package_c8(dev_priv);
i915_update_gfx_val(dev_priv);
+ dev_priv->mm.busy = true;
}
void intel_mark_idle(struct drm_device *dev)
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_crtc *crtc;
- hsw_package_c8_gpu_idle(dev_priv);
+ if (!dev_priv->mm.busy)
+ return;
+
+ dev_priv->mm.busy = false;
if (!i915.powersave)
- return;
+ goto out;
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
if (!crtc->fb)
if (INTEL_INFO(dev)->gen >= 6)
gen6_rps_idle(dev->dev_private);
+
+out:
+ hsw_enable_package_c8(dev_priv);
}
void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
if (ring->id == RCS)
len += 6;
+ /*
+ * BSpec MI_DISPLAY_FLIP for IVB:
+ * "The full packet must be contained within the same cache line."
+ *
+ * Currently the LRI+SRM+MI_DISPLAY_FLIP all fit within the same
+ * cacheline, if we ever start emitting more commands before
+ * the MI_DISPLAY_FLIP we may need to first emit everything else,
+ * then do the cacheline alignment, and finally emit the
+ * MI_DISPLAY_FLIP.
+ */
+ ret = intel_ring_cacheline_align(ring);
+ if (ret)
+ goto err_unpin;
+
ret = intel_ring_begin(ring, len);
if (ret)
goto err_unpin;
fb->pitches[0] != crtc->fb->pitches[0]))
return -EINVAL;
+ if (i915_terminally_wedged(&dev_priv->gpu_error))
+ goto out_hang;
+
work = kzalloc(sizeof(*work), GFP_KERNEL);
if (work == NULL)
return -ENOMEM;
free_work:
kfree(work);
+ if (ret == -EIO) {
+out_hang:
+ intel_crtc_wait_for_pending_flips(crtc);
+ ret = intel_pipe_set_base(crtc, crtc->x, crtc->y, fb);
+ if (ret == 0 && event)
+ drm_send_vblank_event(dev, intel_crtc->pipe, event);
+ }
return ret;
}
.create_handle = intel_user_framebuffer_create_handle,
};
-int intel_framebuffer_init(struct drm_device *dev,
- struct intel_framebuffer *intel_fb,
- struct drm_mode_fb_cmd2 *mode_cmd,
- struct drm_i915_gem_object *obj)
+static int intel_framebuffer_init(struct drm_device *dev,
+ struct intel_framebuffer *intel_fb,
+ struct drm_mode_fb_cmd2 *mode_cmd,
+ struct drm_i915_gem_object *obj)
{
int aligned_height;
int pitch_limit;
void intel_modeset_init(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- int i, j, ret;
+ int sprite, ret;
+ enum pipe pipe;
drm_mode_config_init(dev);
INTEL_INFO(dev)->num_pipes,
INTEL_INFO(dev)->num_pipes > 1 ? "s" : "");
- for_each_pipe(i) {
- intel_crtc_init(dev, i);
- for (j = 0; j < INTEL_INFO(dev)->num_sprites; j++) {
- ret = intel_plane_init(dev, i, j);
+ for_each_pipe(pipe) {
+ intel_crtc_init(dev, pipe);
+ for_each_sprite(pipe, sprite) {
+ ret = intel_plane_init(dev, pipe, sprite);
if (ret)
DRM_DEBUG_KMS("pipe %c sprite %c init failed: %d\n",
- pipe_name(i), sprite_name(i, j), ret);
+ pipe_name(pipe), sprite_name(pipe, sprite), ret);
}
}
/* Just in case the BIOS is doing something questionable. */
intel_disable_fbc(dev);
+ mutex_lock(&dev->mode_config.mutex);
intel_modeset_setup_hw_state(dev, false);
+ mutex_unlock(&dev->mode_config.mutex);
}
static void
* the crtc fixup. */
}
-void i915_redisable_vga(struct drm_device *dev)
+void i915_redisable_vga_power_on(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
u32 vga_reg = i915_vgacntrl_reg(dev);
+ if (!(I915_READ(vga_reg) & VGA_DISP_DISABLE)) {
+ DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
+ i915_disable_vga(dev);
+ }
+}
+
+void i915_redisable_vga(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
/* This function can be called both from intel_modeset_setup_hw_state or
* at a very early point in our resume sequence, where the power well
* structures are not yet restored. Since this function is at a very
* level, just check if the power well is enabled instead of trying to
* follow the "don't touch the power well if we don't need it" policy
* the rest of the driver uses. */
- if ((IS_HASWELL(dev) || IS_BROADWELL(dev)) &&
- (I915_READ(HSW_PWR_WELL_DRIVER) & HSW_PWR_WELL_STATE_ENABLED) == 0)
+ if (!intel_display_power_enabled(dev_priv, POWER_DOMAIN_VGA))
return;
- if (!(I915_READ(vga_reg) & VGA_DISP_DISABLE)) {
- DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
- i915_disable_vga(dev);
- }
+ i915_redisable_vga_power_on(dev);
}
static void intel_modeset_readout_hw_state(struct drm_device *dev)
for_each_pipe(i) {
error->pipe[i].power_domain_on =
- intel_display_power_enabled_sw(dev, POWER_DOMAIN_PIPE(i));
+ intel_display_power_enabled_sw(dev_priv,
+ POWER_DOMAIN_PIPE(i));
if (!error->pipe[i].power_domain_on)
continue;
enum transcoder cpu_transcoder = transcoders[i];
error->transcoder[i].power_domain_on =
- intel_display_power_enabled_sw(dev,
+ intel_display_power_enabled_sw(dev_priv,
POWER_DOMAIN_TRANSCODER(cpu_transcoder));
if (!error->transcoder[i].power_domain_on)
continue;
int i, ret, recv_bytes;
uint32_t status;
int try, clock = 0;
- bool has_aux_irq = true;
+ bool has_aux_irq = HAS_AUX_IRQ(dev);
/* dp aux is extremely sensitive to irq latency, hence request the
* lowest possible wakeup latency and so prevent the cpu from going into
uint8_t msg[20];
int msg_bytes;
uint8_t ack;
+ int retry;
if (WARN_ON(send_bytes > 16))
return -E2BIG;
msg[3] = send_bytes - 1;
memcpy(&msg[4], send, send_bytes);
msg_bytes = send_bytes + 4;
- for (;;) {
+ for (retry = 0; retry < 7; retry++) {
ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes, &ack, 1);
if (ret < 0)
return ret;
ack >>= 4;
if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_ACK)
- break;
+ return send_bytes;
else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
- udelay(100);
+ usleep_range(400, 500);
else
return -EIO;
}
- return send_bytes;
+
+ DRM_ERROR("too many retries, giving up\n");
+ return -EIO;
}
/* Write a single byte to the aux channel in native mode */
int reply_bytes;
uint8_t ack;
int ret;
+ int retry;
if (WARN_ON(recv_bytes > 19))
return -E2BIG;
msg_bytes = 4;
reply_bytes = recv_bytes + 1;
- for (;;) {
+ for (retry = 0; retry < 7; retry++) {
ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes,
reply, reply_bytes);
if (ret == 0)
return ret - 1;
}
else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
- udelay(100);
+ usleep_range(400, 500);
else
return -EIO;
}
+
+ DRM_ERROR("too many retries, giving up\n");
+ return -EIO;
}
static int
mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock,
bpp);
- for (clock = 0; clock <= max_clock; clock++) {
- for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) {
+ for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) {
+ for (clock = 0; clock <= max_clock; clock++) {
link_clock = drm_dp_bw_code_to_link_rate(bws[clock]);
link_avail = intel_dp_max_data_rate(link_clock,
lane_count);
pp = ironlake_get_pp_control(intel_dp);
/* We need to switch off panel power _and_ force vdd, for otherwise some
* panels get very unhappy and cease to work. */
- pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+ pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_FORCE_VDD |
+ EDP_BLC_ENABLE);
pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
enum port port = dp_to_dig_port(intel_dp)->port;
struct drm_device *dev = encoder->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 tmp = I915_READ(intel_dp->output_reg);
+ enum intel_display_power_domain power_domain;
+ u32 tmp;
+
+ power_domain = intel_display_port_power_domain(encoder);
+ if (!intel_display_power_enabled(dev_priv, power_domain))
+ return false;
+
+ tmp = I915_READ(intel_dp->output_reg);
if (!(tmp & DP_PORT_EN))
return false;
/* Make sure the panel is off before trying to change the mode. But also
* ensure that we have vdd while we switch off the panel. */
+ edp_panel_vdd_on(intel_dp);
intel_edp_backlight_off(intel_dp);
intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
intel_edp_panel_off(intel_dp);
+ edp_panel_vdd_off(intel_dp, true);
/* cpu edp my only be disable _after_ the cpu pipe/plane is disabled. */
if (!(port == PORT_A || IS_VALLEYVIEW(dev)))
mutex_unlock(&dev_priv->dpio_lock);
- /* init power sequencer on this pipe and port */
- intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
- intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
- &power_seq);
+ if (is_edp(intel_dp)) {
+ /* init power sequencer on this pipe and port */
+ intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
+ intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
+ &power_seq);
+ }
intel_enable_dp(encoder);
struct drm_device *dev = connector->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
enum drm_connector_status status;
+ enum intel_display_power_domain power_domain;
struct edid *edid = NULL;
intel_runtime_pm_get(dev_priv);
+ power_domain = intel_display_port_power_domain(intel_encoder);
+ intel_display_power_get(dev_priv, power_domain);
+
DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
connector->base.id, drm_get_connector_name(connector));
status = connector_status_connected;
out:
+ intel_display_power_put(dev_priv, power_domain);
+
intel_runtime_pm_put(dev_priv);
+
return status;
}
static int intel_dp_get_modes(struct drm_connector *connector)
{
struct intel_dp *intel_dp = intel_attached_dp(connector);
+ struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+ struct intel_encoder *intel_encoder = &intel_dig_port->base;
struct intel_connector *intel_connector = to_intel_connector(connector);
struct drm_device *dev = connector->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ enum intel_display_power_domain power_domain;
int ret;
/* We should parse the EDID data and find out if it has an audio sink
*/
+ power_domain = intel_display_port_power_domain(intel_encoder);
+ intel_display_power_get(dev_priv, power_domain);
+
ret = intel_dp_get_edid_modes(connector, &intel_dp->adapter);
+ intel_display_power_put(dev_priv, power_domain);
if (ret)
return ret;
intel_dp_detect_audio(struct drm_connector *connector)
{
struct intel_dp *intel_dp = intel_attached_dp(connector);
+ struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+ struct intel_encoder *intel_encoder = &intel_dig_port->base;
+ struct drm_device *dev = connector->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ enum intel_display_power_domain power_domain;
struct edid *edid;
bool has_audio = false;
+ power_domain = intel_display_port_power_domain(intel_encoder);
+ intel_display_power_get(dev_priv, power_domain);
+
edid = intel_dp_get_edid(connector, &intel_dp->adapter);
if (edid) {
has_audio = drm_detect_monitor_audio(edid);
kfree(edid);
}
+ intel_display_power_put(dev_priv, power_domain);
+
return has_audio;
}
* to use MI_WAIT_FOR_EVENT within the CS. It should already be
* programmed to '1' on all products.
*
- * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
+ * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw
*/
if (INTEL_INFO(dev)->gen >= 6)
I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
if (IS_I830(ring->dev) || IS_845G(ring->dev))
ring->effective_size -= 128;
+ i915_cmd_parser_init_ring(ring);
+
return 0;
err_unmap:
return 0;
}
+ /* Align the ring tail to a cacheline boundary */
+ int intel_ring_cacheline_align(struct intel_ring_buffer *ring)
+ {
+ int num_dwords = (64 - (ring->tail & 63)) / sizeof(uint32_t);
+ int ret;
+
+ if (num_dwords == 0)
+ return 0;
+
+ ret = intel_ring_begin(ring, num_dwords);
+ if (ret)
+ return ret;
+
+ while (num_dwords--)
+ intel_ring_emit(ring, MI_NOOP);
+
+ intel_ring_advance(ring);
+
+ return 0;
+ }
+
void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
{
struct drm_i915_private *dev_priv = ring->dev->dev_private;
u32 gtt_offset;
volatile u32 *cpu_page;
} scratch;
+
+ /*
+ * Tables of commands the command parser needs to know about
+ * for this ring.
+ */
+ const struct drm_i915_cmd_table *cmd_tables;
+ int cmd_table_count;
+
+ /*
+ * Table of registers allowed in commands that read/write registers.
+ */
+ const u32 *reg_table;
+ int reg_count;
+
+ /*
+ * Table of registers allowed in commands that read/write registers, but
+ * only from the DRM master.
+ */
+ const u32 *master_reg_table;
+ int master_reg_count;
+
+ /*
+ * Returns the bitmask for the length field of the specified command.
+ * Return 0 for an unrecognized/invalid command.
+ *
+ * If the command parser finds an entry for a command in the ring's
+ * cmd_tables, it gets the command's length based on the table entry.
+ * If not, it calls this function to determine the per-ring length field
+ * encoding for the command (i.e. certain opcode ranges use certain bits
+ * to encode the command length in the header).
+ */
+ u32 (*get_cmd_length_mask)(u32 cmd_header);
};
static inline bool
void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);
int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n);
+ int __must_check intel_ring_cacheline_align(struct intel_ring_buffer *ring);
static inline void intel_ring_emit(struct intel_ring_buffer *ring,
u32 data)
{
projects / cascardo / linux.git / commitdiff