diff options
author | Yunhong Jiang <yunhong.jiang@intel.com> | 2015-08-04 12:17:53 -0700 |
---|---|---|
committer | Yunhong Jiang <yunhong.jiang@intel.com> | 2015-08-04 15:44:42 -0700 |
commit | 9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 (patch) | |
tree | 1c9cafbcd35f783a87880a10f85d1a060db1a563 /kernel/drivers/gpu/drm/i915/i915_gem_gtt.h | |
parent | 98260f3884f4a202f9ca5eabed40b1354c489b29 (diff) |
Add the rt linux 4.1.3-rt3 as base
Import the rt linux 4.1.3-rt3 as OPNFV kvm base.
It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and
the base is:
commit 0917f823c59692d751951bf5ea699a2d1e2f26a2
Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Sat Jul 25 12:13:34 2015 +0200
Prepare v4.1.3-rt3
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
We lose all the git history this way and it's not good. We
should apply another opnfv project repo in future.
Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423
Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
Diffstat (limited to 'kernel/drivers/gpu/drm/i915/i915_gem_gtt.h')
-rw-r--r-- | kernel/drivers/gpu/drm/i915/i915_gem_gtt.h | 438 |
1 files changed, 438 insertions, 0 deletions
diff --git a/kernel/drivers/gpu/drm/i915/i915_gem_gtt.h b/kernel/drivers/gpu/drm/i915/i915_gem_gtt.h new file mode 100644 index 000000000..fc03c9931 --- /dev/null +++ b/kernel/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -0,0 +1,438 @@ +/* + * Copyright © 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"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + * Please try to maintain the following order within this file unless it makes + * sense to do otherwise. From top to bottom: + * 1. typedefs + * 2. #defines, and macros + * 3. structure definitions + * 4. function prototypes + * + * Within each section, please try to order by generation in ascending order, + * from top to bottom (ie. gen6 on the top, gen8 on the bottom). + */ + +#ifndef __I915_GEM_GTT_H__ +#define __I915_GEM_GTT_H__ + +struct drm_i915_file_private; + +typedef uint32_t gen6_pte_t; +typedef uint64_t gen8_pte_t; +typedef uint64_t gen8_pde_t; + +#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT) + + +/* gen6-hsw has bit 11-4 for physical addr bit 39-32 */ +#define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0)) +#define GEN6_PTE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) +#define GEN6_PDE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) +#define GEN6_PTE_CACHE_LLC (2 << 1) +#define GEN6_PTE_UNCACHED (1 << 1) +#define GEN6_PTE_VALID (1 << 0) + +#define I915_PTES(pte_len) (PAGE_SIZE / (pte_len)) +#define I915_PTE_MASK(pte_len) (I915_PTES(pte_len) - 1) +#define I915_PDES 512 +#define I915_PDE_MASK (I915_PDES - 1) +#define NUM_PTE(pde_shift) (1 << (pde_shift - PAGE_SHIFT)) + +#define GEN6_PTES I915_PTES(sizeof(gen6_pte_t)) +#define GEN6_PD_SIZE (I915_PDES * PAGE_SIZE) +#define GEN6_PD_ALIGN (PAGE_SIZE * 16) +#define GEN6_PDE_SHIFT 22 +#define GEN6_PDE_VALID (1 << 0) + +#define GEN7_PTE_CACHE_L3_LLC (3 << 1) + +#define BYT_PTE_SNOOPED_BY_CPU_CACHES (1 << 2) +#define BYT_PTE_WRITEABLE (1 << 1) + +/* Cacheability Control is a 4-bit value. The low three bits are stored in bits + * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE. + */ +#define HSW_CACHEABILITY_CONTROL(bits) ((((bits) & 0x7) << 1) | \ + (((bits) & 0x8) << (11 - 3))) +#define HSW_WB_LLC_AGE3 HSW_CACHEABILITY_CONTROL(0x2) +#define HSW_WB_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x3) +#define HSW_WB_ELLC_LLC_AGE3 HSW_CACHEABILITY_CONTROL(0x8) +#define HSW_WB_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0xb) +#define HSW_WT_ELLC_LLC_AGE3 HSW_CACHEABILITY_CONTROL(0x7) +#define HSW_WT_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x6) +#define HSW_PTE_UNCACHED (0) +#define HSW_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0x7f0)) +#define HSW_PTE_ADDR_ENCODE(addr) HSW_GTT_ADDR_ENCODE(addr) + +/* GEN8 legacy style address is 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 GEN8_LEGACY_PDPES 4 +#define GEN8_PTES I915_PTES(sizeof(gen8_pte_t)) + +#define PPAT_UNCACHED_INDEX (_PAGE_PWT | _PAGE_PCD) +#define PPAT_CACHED_PDE_INDEX 0 /* WB LLC */ +#define PPAT_CACHED_INDEX _PAGE_PAT /* WB LLCeLLC */ +#define PPAT_DISPLAY_ELLC_INDEX _PAGE_PCD /* WT eLLC */ + +#define CHV_PPAT_SNOOP (1<<6) +#define GEN8_PPAT_AGE(x) (x<<4) +#define GEN8_PPAT_LLCeLLC (3<<2) +#define GEN8_PPAT_LLCELLC (2<<2) +#define GEN8_PPAT_LLC (1<<2) +#define GEN8_PPAT_WB (3<<0) +#define GEN8_PPAT_WT (2<<0) +#define GEN8_PPAT_WC (1<<0) +#define GEN8_PPAT_UC (0<<0) +#define GEN8_PPAT_ELLC_OVERRIDE (0<<2) +#define GEN8_PPAT(i, x) ((uint64_t) (x) << ((i) * 8)) + +enum i915_ggtt_view_type { + I915_GGTT_VIEW_NORMAL = 0, + I915_GGTT_VIEW_ROTATED +}; + +struct intel_rotation_info { + unsigned int height; + unsigned int pitch; + uint32_t pixel_format; + uint64_t fb_modifier; +}; + +struct i915_ggtt_view { + enum i915_ggtt_view_type type; + + struct sg_table *pages; + + union { + struct intel_rotation_info rotation_info; + }; +}; + +extern const struct i915_ggtt_view i915_ggtt_view_normal; +extern const struct i915_ggtt_view i915_ggtt_view_rotated; + +enum i915_cache_level; + +/** + * A VMA represents a GEM BO that is bound into an address space. Therefore, a + * VMA's presence cannot be guaranteed before binding, or after unbinding the + * object into/from the address space. + * + * To make things as simple as possible (ie. no refcounting), a VMA's lifetime + * will always be <= an objects lifetime. So object refcounting should cover us. + */ +struct i915_vma { + struct drm_mm_node node; + struct drm_i915_gem_object *obj; + struct i915_address_space *vm; + + /** Flags and address space this VMA is bound to */ +#define GLOBAL_BIND (1<<0) +#define LOCAL_BIND (1<<1) +#define PTE_READ_ONLY (1<<2) + unsigned int bound : 4; + + /** + * Support different GGTT views into the same object. + * This means there can be multiple VMA mappings per object and per VM. + * i915_ggtt_view_type is used to distinguish between those entries. + * The default one of zero (I915_GGTT_VIEW_NORMAL) is default and also + * assumed in GEM functions which take no ggtt view parameter. + */ + struct i915_ggtt_view ggtt_view; + + /** This object's place on the active/inactive lists */ + struct list_head mm_list; + + struct list_head vma_link; /* Link in the object's VMA list */ + + /** This vma's place in the batchbuffer or on the eviction list */ + struct list_head exec_list; + + /** + * Used for performing relocations during execbuffer insertion. + */ + struct hlist_node exec_node; + unsigned long exec_handle; + struct drm_i915_gem_exec_object2 *exec_entry; + + /** + * How many users have pinned this object in GTT space. The following + * users can each hold at most one reference: pwrite/pread, execbuffer + * (objects are not allowed multiple times for the same batchbuffer), + * and the framebuffer code. When switching/pageflipping, the + * framebuffer code has at most two buffers pinned per crtc. + * + * In the worst case this is 1 + 1 + 1 + 2*2 = 7. That would fit into 3 + * bits with absolutely no headroom. So use 4 bits. */ + unsigned int pin_count:4; +#define DRM_I915_GEM_OBJECT_MAX_PIN_COUNT 0xf + + /** Unmap an object from an address space. This usually consists of + * setting the valid PTE entries to a reserved scratch page. */ + void (*unbind_vma)(struct i915_vma *vma); + /* Map an object into an address space with the given cache flags. */ + void (*bind_vma)(struct i915_vma *vma, + enum i915_cache_level cache_level, + u32 flags); +}; + +struct i915_page_table_entry { + struct page *page; + dma_addr_t daddr; + + unsigned long *used_ptes; +}; + +struct i915_page_directory_entry { + struct page *page; /* NULL for GEN6-GEN7 */ + union { + uint32_t pd_offset; + dma_addr_t daddr; + }; + + struct i915_page_table_entry *page_table[I915_PDES]; /* PDEs */ +}; + +struct i915_page_directory_pointer_entry { + /* struct page *page; */ + struct i915_page_directory_entry *page_directory[GEN8_LEGACY_PDPES]; +}; + +struct i915_address_space { + struct drm_mm mm; + struct drm_device *dev; + struct list_head global_link; + unsigned long start; /* Start offset always 0 for dri2 */ + size_t total; /* size addr space maps (ex. 2GB for ggtt) */ + + struct { + dma_addr_t addr; + struct page *page; + } scratch; + + /** + * List of objects currently involved in rendering. + * + * Includes buffers having the contents of their GPU caches + * flushed, not necessarily primitives. last_read_req + * represents when the rendering involved will be completed. + * + * A reference is held on the buffer while on this list. + */ + struct list_head active_list; + + /** + * LRU list of objects which are not in the ringbuffer and + * are ready to unbind, but are still in the GTT. + * + * last_read_req is NULL while an object is in this list. + * + * A reference is not held on the buffer while on this list, + * as merely being GTT-bound shouldn't prevent its being + * freed, and we'll pull it off the list in the free path. + */ + struct list_head inactive_list; + + /* FIXME: Need a more generic return type */ + gen6_pte_t (*pte_encode)(dma_addr_t addr, + enum i915_cache_level level, + bool valid, u32 flags); /* Create a valid PTE */ + int (*allocate_va_range)(struct i915_address_space *vm, + uint64_t start, + uint64_t length); + void (*clear_range)(struct i915_address_space *vm, + uint64_t start, + uint64_t length, + bool use_scratch); + void (*insert_entries)(struct i915_address_space *vm, + struct sg_table *st, + uint64_t start, + enum i915_cache_level cache_level, u32 flags); + void (*cleanup)(struct i915_address_space *vm); +}; + +/* The Graphics Translation Table is the way in which GEN hardware translates a + * Graphics Virtual Address into a Physical Address. In addition to the normal + * collateral associated with any va->pa translations GEN hardware also has a + * portion of the GTT which can be mapped by the CPU and remain both coherent + * and correct (in cases like swizzling). That region is referred to as GMADR in + * the spec. + */ +struct i915_gtt { + struct i915_address_space base; + size_t stolen_size; /* Total size of stolen memory */ + + unsigned long mappable_end; /* End offset that we can CPU map */ + struct io_mapping *mappable; /* Mapping to our CPU mappable region */ + phys_addr_t mappable_base; /* PA of our GMADR */ + + /** "Graphics Stolen Memory" holds the global PTEs */ + void __iomem *gsm; + + bool do_idle_maps; + + int mtrr; + + /* global gtt ops */ + int (*gtt_probe)(struct drm_device *dev, size_t *gtt_total, + size_t *stolen, phys_addr_t *mappable_base, + unsigned long *mappable_end); +}; + +struct i915_hw_ppgtt { + struct i915_address_space base; + struct kref ref; + struct drm_mm_node node; + unsigned long pd_dirty_rings; + unsigned num_pd_entries; + unsigned num_pd_pages; /* gen8+ */ + union { + struct i915_page_directory_pointer_entry pdp; + struct i915_page_directory_entry pd; + }; + + struct i915_page_table_entry *scratch_pt; + + struct drm_i915_file_private *file_priv; + + gen6_pte_t __iomem *pd_addr; + + int (*enable)(struct i915_hw_ppgtt *ppgtt); + int (*switch_mm)(struct i915_hw_ppgtt *ppgtt, + struct intel_engine_cs *ring); + void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m); +}; + +/* For each pde iterates over every pde between from start until start + length. + * If start, and start+length are not perfectly divisible, the macro will round + * down, and up as needed. The macro modifies pde, start, and length. Dev is + * only used to differentiate shift values. Temp is temp. On gen6/7, start = 0, + * and length = 2G effectively iterates over every PDE in the system. + * + * XXX: temp is not actually needed, but it saves doing the ALIGN operation. + */ +#define gen6_for_each_pde(pt, pd, start, length, temp, iter) \ + for (iter = gen6_pde_index(start); \ + pt = (pd)->page_table[iter], length > 0 && iter < I915_PDES; \ + iter++, \ + temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT) - start, \ + temp = min_t(unsigned, temp, length), \ + start += temp, length -= temp) + +static inline uint32_t i915_pte_index(uint64_t address, uint32_t pde_shift) +{ + const uint32_t mask = NUM_PTE(pde_shift) - 1; + + return (address >> PAGE_SHIFT) & mask; +} + +/* Helper to counts the number of PTEs within the given length. This count + * does not cross a page table boundary, so the max value would be + * GEN6_PTES for GEN6, and GEN8_PTES for GEN8. +*/ +static inline uint32_t i915_pte_count(uint64_t addr, size_t length, + uint32_t pde_shift) +{ + const uint64_t mask = ~((1 << pde_shift) - 1); + uint64_t end; + + WARN_ON(length == 0); + WARN_ON(offset_in_page(addr|length)); + + end = addr + length; + + if ((addr & mask) != (end & mask)) + return NUM_PTE(pde_shift) - i915_pte_index(addr, pde_shift); + + return i915_pte_index(end, pde_shift) - i915_pte_index(addr, pde_shift); +} + +static inline uint32_t i915_pde_index(uint64_t addr, uint32_t shift) +{ + return (addr >> shift) & I915_PDE_MASK; +} + +static inline uint32_t gen6_pte_index(uint32_t addr) +{ + return i915_pte_index(addr, GEN6_PDE_SHIFT); +} + +static inline size_t gen6_pte_count(uint32_t addr, uint32_t length) +{ + return i915_pte_count(addr, length, GEN6_PDE_SHIFT); +} + +static inline uint32_t gen6_pde_index(uint32_t addr) +{ + return i915_pde_index(addr, GEN6_PDE_SHIFT); +} + +int i915_gem_gtt_init(struct drm_device *dev); +void i915_gem_init_global_gtt(struct drm_device *dev); +void i915_global_gtt_cleanup(struct drm_device *dev); + + +int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt); +int i915_ppgtt_init_hw(struct drm_device *dev); +void i915_ppgtt_release(struct kref *kref); +struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_device *dev, + struct drm_i915_file_private *fpriv); +static inline void i915_ppgtt_get(struct i915_hw_ppgtt *ppgtt) +{ + if (ppgtt) + kref_get(&ppgtt->ref); +} +static inline void i915_ppgtt_put(struct i915_hw_ppgtt *ppgtt) +{ + if (ppgtt) + kref_put(&ppgtt->ref, i915_ppgtt_release); +} + +void i915_check_and_clear_faults(struct drm_device *dev); +void i915_gem_suspend_gtt_mappings(struct drm_device *dev); +void i915_gem_restore_gtt_mappings(struct drm_device *dev); + +int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj); +void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj); + +static inline bool +i915_ggtt_view_equal(const struct i915_ggtt_view *a, + const struct i915_ggtt_view *b) +{ + if (WARN_ON(!a || !b)) + return false; + + return a->type == b->type; +} + +#endif |