#define __I915_GEM_GTT_H__
#include <linux/io-mapping.h>
+#include <linux/kref.h>
#include <linux/mm.h>
#include <linux/pagevec.h>
+#include <linux/workqueue.h>
+#include <drm/drm_mm.h>
+
+#include "gt/intel_reset.h"
+#include "i915_gem_fence_reg.h"
#include "i915_request.h"
-#include "i915_reset.h"
+#include "i915_scatterlist.h"
#include "i915_selftest.h"
-#include "i915_timeline.h"
+#include "gt/intel_timeline.h"
#define I915_GTT_PAGE_SIZE_4K BIT_ULL(12)
#define I915_GTT_PAGE_SIZE_64K BIT_ULL(16)
#define I915_MAX_NUM_FENCE_BITS 6
struct drm_i915_file_private;
-struct drm_i915_fence_reg;
+struct drm_i915_gem_object;
struct i915_vma;
+struct intel_gt;
typedef u32 gen6_pte_t;
typedef u64 gen8_pte_t;
-typedef u64 gen8_pde_t;
-typedef u64 gen8_ppgtt_pdpe_t;
-typedef u64 gen8_ppgtt_pml4e_t;
#define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT)
#define HSW_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0x7f0))
#define HSW_PTE_ADDR_ENCODE(addr) HSW_GTT_ADDR_ENCODE(addr)
-/* GEN8 32b style address is defined as a 3 level page table:
+/*
+ * GEN8 32b 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_3LVL_PDPES 4
-#define GEN8_PDE_SHIFT 21
-#define GEN8_PDE_MASK 0x1ff
-#define GEN8_PTE_SHIFT 12
-#define GEN8_PTE_MASK 0x1ff
-#define GEN8_PTES I915_PTES(sizeof(gen8_pte_t))
-
-/* GEN8 48b style address is defined as a 4 level page table:
+ *
+ * GEN8 48b style address is defined as a 4 level page table:
* 47:39 | 38:30 | 29:21 | 20:12 | 11:0
* PML4E | PDPE | PDE | PTE | offset
*/
-#define GEN8_PML4ES_PER_PML4 512
-#define GEN8_PML4E_SHIFT 39
-#define GEN8_PML4E_MASK (GEN8_PML4ES_PER_PML4 - 1)
-#define GEN8_PDPE_SHIFT 30
-/* NB: GEN8_PDPE_MASK is untrue for 32b platforms, but it has no impact on 32b page
- * tables */
-#define GEN8_PDPE_MASK 0x1ff
+#define GEN8_3LVL_PDPES 4
#define PPAT_UNCACHED (_PAGE_PWT | _PAGE_PCD)
#define PPAT_CACHED_PDE 0 /* WB LLC */
#define GEN8_PPAT_ELLC_OVERRIDE (0<<2)
#define GEN8_PPAT(i, x) ((u64)(x) << ((i) * 8))
-#define GEN8_PPAT_GET_CA(x) ((x) & 3)
-#define GEN8_PPAT_GET_TC(x) ((x) & (3 << 2))
-#define GEN8_PPAT_GET_AGE(x) ((x) & (3 << 4))
-#define CHV_PPAT_GET_SNOOP(x) ((x) & (1 << 6))
-
#define GEN8_PDE_IPS_64K BIT(11)
#define GEN8_PDE_PS_2M BIT(7)
-struct sg_table;
+#define for_each_sgt_dma(__dmap, __iter, __sgt) \
+ __for_each_sgt_dma(__dmap, __iter, __sgt, I915_GTT_PAGE_SIZE)
+
+struct intel_remapped_plane_info {
+ /* in gtt pages */
+ unsigned int width, height, stride, offset;
+} __packed;
+
+struct intel_remapped_info {
+ struct intel_remapped_plane_info plane[2];
+ unsigned int unused_mbz;
+} __packed;
struct intel_rotation_info {
- struct intel_rotation_plane_info {
- /* tiles */
- unsigned int width, height, stride, offset;
- } plane[2];
+ struct intel_remapped_plane_info plane[2];
} __packed;
struct intel_partial_info {
I915_GGTT_VIEW_NORMAL = 0,
I915_GGTT_VIEW_ROTATED = sizeof(struct intel_rotation_info),
I915_GGTT_VIEW_PARTIAL = sizeof(struct intel_partial_info),
+ I915_GGTT_VIEW_REMAPPED = sizeof(struct intel_remapped_info),
};
static inline void assert_i915_gem_gtt_types(void)
{
BUILD_BUG_ON(sizeof(struct intel_rotation_info) != 8*sizeof(unsigned int));
BUILD_BUG_ON(sizeof(struct intel_partial_info) != sizeof(u64) + sizeof(unsigned int));
+ BUILD_BUG_ON(sizeof(struct intel_remapped_info) != 9*sizeof(unsigned int));
+
+ /* Check that rotation/remapped shares offsets for simplicity */
+ BUILD_BUG_ON(offsetof(struct intel_remapped_info, plane[0]) !=
+ offsetof(struct intel_rotation_info, plane[0]));
+ BUILD_BUG_ON(offsetofend(struct intel_remapped_info, plane[1]) !=
+ offsetofend(struct intel_rotation_info, plane[1]));
/* As we encode the size of each branch inside the union into its type,
* we have to be careful that each branch has a unique size.
case I915_GGTT_VIEW_NORMAL:
case I915_GGTT_VIEW_PARTIAL:
case I915_GGTT_VIEW_ROTATED:
+ case I915_GGTT_VIEW_REMAPPED:
/* gcc complains if these are identical cases */
break;
}
/* Members need to contain no holes/padding */
struct intel_partial_info partial;
struct intel_rotation_info rotated;
+ struct intel_remapped_info remapped;
};
};
struct i915_page_dma {
struct page *page;
- int order;
union {
dma_addr_t daddr;
};
};
-#define px_base(px) (&(px)->base)
-#define px_dma(px) (px_base(px)->daddr)
+struct i915_page_scratch {
+ struct i915_page_dma base;
+ u64 encode;
+};
struct i915_page_table {
struct i915_page_dma base;
- unsigned int used_ptes;
+ atomic_t used;
};
struct i915_page_directory {
- struct i915_page_dma base;
-
- struct i915_page_table *page_table[I915_PDES]; /* PDEs */
- unsigned int used_pdes;
+ struct i915_page_table pt;
+ spinlock_t lock;
+ void *entry[512];
};
-struct i915_page_directory_pointer {
- struct i915_page_dma base;
- struct i915_page_directory **page_directory;
- unsigned int used_pdpes;
-};
+#define __px_choose_expr(x, type, expr, other) \
+ __builtin_choose_expr( \
+ __builtin_types_compatible_p(typeof(x), type) || \
+ __builtin_types_compatible_p(typeof(x), const type), \
+ ({ type __x = (type)(x); expr; }), \
+ other)
+
+#define px_base(px) \
+ __px_choose_expr(px, struct i915_page_dma *, __x, \
+ __px_choose_expr(px, struct i915_page_scratch *, &__x->base, \
+ __px_choose_expr(px, struct i915_page_table *, &__x->base, \
+ __px_choose_expr(px, struct i915_page_directory *, &__x->pt.base, \
+ (void)0))))
+#define px_dma(px) (px_base(px)->daddr)
-struct i915_pml4 {
- struct i915_page_dma base;
- struct i915_page_directory_pointer *pdps[GEN8_PML4ES_PER_PML4];
-};
+#define px_pt(px) \
+ __px_choose_expr(px, struct i915_page_table *, __x, \
+ __px_choose_expr(px, struct i915_page_directory *, &__x->pt, \
+ (void)0))
+#define px_used(px) (&px_pt(px)->used)
struct i915_vma_ops {
/* Map an object into an address space with the given cache flags. */
};
struct i915_address_space {
+ struct kref ref;
+ struct rcu_work rcu;
+
struct drm_mm mm;
+ struct intel_gt *gt;
struct drm_i915_private *i915;
struct device *dma;
/* Every address space belongs to a struct file - except for the global
#define VM_CLASS_GGTT 0
#define VM_CLASS_PPGTT 1
- u64 scratch_pte;
- struct i915_page_dma scratch_page;
- struct i915_page_table *scratch_pt;
- struct i915_page_directory *scratch_pd;
- struct i915_page_directory_pointer *scratch_pdp; /* GEN8+ & 48b PPGTT */
+ struct i915_page_scratch scratch[4];
+ unsigned int scratch_order;
+ unsigned int top;
/**
* List of vma currently bound.
#define i915_is_ggtt(vm) ((vm)->is_ggtt)
static inline bool
-i915_vm_is_48bit(const struct i915_address_space *vm)
+i915_vm_is_4lvl(const struct i915_address_space *vm)
{
return (vm->total - 1) >> 32;
}
static inline bool
i915_vm_has_scratch_64K(struct i915_address_space *vm)
{
- return vm->scratch_page.order == get_order(I915_GTT_PAGE_SIZE_64K);
+ return vm->scratch_order == get_order(I915_GTT_PAGE_SIZE_64K);
}
/* The Graphics Translation Table is the way in which GEN hardware translates a
/** "Graphics Stolen Memory" holds the global PTEs */
void __iomem *gsm;
- void (*invalidate)(struct drm_i915_private *dev_priv);
+ void (*invalidate)(struct i915_ggtt *ggtt);
+
+ /** PPGTT used for aliasing the PPGTT with the GTT */
+ struct i915_ppgtt *alias;
bool do_idle_maps;
u32 pin_bias;
+ unsigned int num_fences;
+ struct i915_fence_reg fence_regs[I915_MAX_NUM_FENCES];
+ struct list_head fence_list;
+
+ /** List of all objects in gtt_space, currently mmaped by userspace.
+ * All objects within this list must also be on bound_list.
+ */
+ struct list_head userfault_list;
+
+ /* Manual runtime pm autosuspend delay for user GGTT mmaps */
+ struct intel_wakeref_auto userfault_wakeref;
+
struct drm_mm_node error_capture;
+ struct drm_mm_node uc_fw;
};
-struct i915_hw_ppgtt {
+struct i915_ppgtt {
struct i915_address_space vm;
- struct kref ref;
- unsigned long pd_dirty_rings;
- union {
- struct i915_pml4 pml4; /* GEN8+ & 48b PPGTT */
- struct i915_page_directory_pointer pdp; /* GEN8+ */
- struct i915_page_directory pd; /* GEN6-7 */
- };
+ intel_engine_mask_t pd_dirty_engines;
+ struct i915_page_directory *pd;
};
-struct gen6_hw_ppgtt {
- struct i915_hw_ppgtt base;
+struct gen6_ppgtt {
+ struct i915_ppgtt base;
struct i915_vma *vma;
gen6_pte_t __iomem *pd_addr;
bool scan_for_unused_pt;
};
-#define __to_gen6_ppgtt(base) container_of(base, struct gen6_hw_ppgtt, base)
+#define __to_gen6_ppgtt(base) container_of(base, struct gen6_ppgtt, base)
-static inline struct gen6_hw_ppgtt *to_gen6_ppgtt(struct i915_hw_ppgtt *base)
+static inline struct gen6_ppgtt *to_gen6_ppgtt(struct i915_ppgtt *base)
{
- BUILD_BUG_ON(offsetof(struct gen6_hw_ppgtt, base));
+ BUILD_BUG_ON(offsetof(struct gen6_ppgtt, base));
return __to_gen6_ppgtt(base);
}
#define gen6_for_each_pde(pt, pd, start, length, iter) \
for (iter = gen6_pde_index(start); \
length > 0 && iter < I915_PDES && \
- (pt = (pd)->page_table[iter], true); \
+ (pt = i915_pt_entry(pd, iter), true); \
({ u32 temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT); \
temp = min(temp - start, length); \
start += temp, length -= temp; }), ++iter)
#define gen6_for_all_pdes(pt, pd, iter) \
for (iter = 0; \
iter < I915_PDES && \
- (pt = (pd)->page_table[iter], true); \
+ (pt = i915_pt_entry(pd, iter), true); \
++iter)
static inline u32 i915_pte_index(u64 address, unsigned int pde_shift)
return i915_pde_index(addr, GEN6_PDE_SHIFT);
}
-static inline unsigned int
-i915_pdpes_per_pdp(const struct i915_address_space *vm)
-{
- if (i915_vm_is_48bit(vm))
- return GEN8_PML4ES_PER_PML4;
-
- return GEN8_3LVL_PDPES;
-}
-
-/* Equivalent to the gen6 version, For each pde iterates over every pde
- * between from start until start + length. On gen8+ it simply iterates
- * over every page directory entry in a page directory.
- */
-#define gen8_for_each_pde(pt, pd, start, length, iter) \
- for (iter = gen8_pde_index(start); \
- length > 0 && iter < I915_PDES && \
- (pt = (pd)->page_table[iter], true); \
- ({ u64 temp = ALIGN(start+1, 1 << GEN8_PDE_SHIFT); \
- temp = min(temp - start, length); \
- start += temp, length -= temp; }), ++iter)
-
-#define gen8_for_each_pdpe(pd, pdp, start, length, iter) \
- for (iter = gen8_pdpe_index(start); \
- length > 0 && iter < i915_pdpes_per_pdp(vm) && \
- (pd = (pdp)->page_directory[iter], true); \
- ({ u64 temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT); \
- temp = min(temp - start, length); \
- start += temp, length -= temp; }), ++iter)
-
-#define gen8_for_each_pml4e(pdp, pml4, start, length, iter) \
- for (iter = gen8_pml4e_index(start); \
- length > 0 && iter < GEN8_PML4ES_PER_PML4 && \
- (pdp = (pml4)->pdps[iter], true); \
- ({ u64 temp = ALIGN(start+1, 1ULL << GEN8_PML4E_SHIFT); \
- temp = min(temp - start, length); \
- start += temp, length -= temp; }), ++iter)
-
-static inline u32 gen8_pte_index(u64 address)
-{
- return i915_pte_index(address, GEN8_PDE_SHIFT);
-}
-
-static inline u32 gen8_pde_index(u64 address)
-{
- return i915_pde_index(address, GEN8_PDE_SHIFT);
-}
-
-static inline u32 gen8_pdpe_index(u64 address)
+static inline struct i915_page_table *
+i915_pt_entry(const struct i915_page_directory * const pd,
+ const unsigned short n)
{
- return (address >> GEN8_PDPE_SHIFT) & GEN8_PDPE_MASK;
+ return pd->entry[n];
}
-static inline u32 gen8_pml4e_index(u64 address)
+static inline struct i915_page_directory *
+i915_pd_entry(const struct i915_page_directory * const pdp,
+ const unsigned short n)
{
- return (address >> GEN8_PML4E_SHIFT) & GEN8_PML4E_MASK;
-}
-
-static inline u64 gen8_pte_count(u64 address, u64 length)
-{
- return i915_pte_count(address, length, GEN8_PDE_SHIFT);
+ return pdp->entry[n];
}
static inline dma_addr_t
-i915_page_dir_dma_addr(const struct i915_hw_ppgtt *ppgtt, const unsigned n)
+i915_page_dir_dma_addr(const struct i915_ppgtt *ppgtt, const unsigned int n)
{
- return px_dma(ppgtt->pdp.page_directory[n]);
+ struct i915_page_dma *pt = ppgtt->pd->entry[n];
+
+ return px_dma(pt ?: px_base(&ppgtt->vm.scratch[ppgtt->vm.top]));
}
static inline struct i915_ggtt *
i915_vm_to_ggtt(struct i915_address_space *vm)
{
+ BUILD_BUG_ON(offsetof(struct i915_ggtt, vm));
GEM_BUG_ON(!i915_is_ggtt(vm));
return container_of(vm, struct i915_ggtt, vm);
}
-#define INTEL_MAX_PPAT_ENTRIES 8
-#define INTEL_PPAT_PERFECT_MATCH (~0U)
-
-struct intel_ppat;
-
-struct intel_ppat_entry {
- struct intel_ppat *ppat;
- struct kref ref;
- u8 value;
-};
-
-struct intel_ppat {
- struct intel_ppat_entry entries[INTEL_MAX_PPAT_ENTRIES];
- DECLARE_BITMAP(used, INTEL_MAX_PPAT_ENTRIES);
- DECLARE_BITMAP(dirty, INTEL_MAX_PPAT_ENTRIES);
- unsigned int max_entries;
- u8 clear_value;
- /*
- * Return a score to show how two PPAT values match,
- * a INTEL_PPAT_PERFECT_MATCH indicates a perfect match
- */
- unsigned int (*match)(u8 src, u8 dst);
- void (*update_hw)(struct drm_i915_private *i915);
-
- struct drm_i915_private *i915;
-};
-
-const struct intel_ppat_entry *
-intel_ppat_get(struct drm_i915_private *i915, u8 value);
-void intel_ppat_put(const struct intel_ppat_entry *entry);
-
-int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915);
-void i915_gem_fini_aliasing_ppgtt(struct drm_i915_private *i915);
+static inline struct i915_ppgtt *
+i915_vm_to_ppgtt(struct i915_address_space *vm)
+{
+ BUILD_BUG_ON(offsetof(struct i915_ppgtt, vm));
+ GEM_BUG_ON(i915_is_ggtt(vm));
+ return container_of(vm, struct i915_ppgtt, vm);
+}
int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv);
int i915_ggtt_init_hw(struct drm_i915_private *dev_priv);
int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv);
-void i915_ggtt_enable_guc(struct drm_i915_private *i915);
-void i915_ggtt_disable_guc(struct drm_i915_private *i915);
-int i915_gem_init_ggtt(struct drm_i915_private *dev_priv);
-void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv);
-
-int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv);
-void i915_ppgtt_release(struct kref *kref);
-struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv,
- struct drm_i915_file_private *fpriv);
-void i915_ppgtt_close(struct i915_address_space *vm);
-static inline void i915_ppgtt_get(struct i915_hw_ppgtt *ppgtt)
+void i915_ggtt_enable_guc(struct i915_ggtt *ggtt);
+void i915_ggtt_disable_guc(struct i915_ggtt *ggtt);
+int i915_init_ggtt(struct drm_i915_private *dev_priv);
+void i915_ggtt_driver_release(struct drm_i915_private *dev_priv);
+
+int i915_ppgtt_init_hw(struct intel_gt *gt);
+
+struct i915_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv);
+
+static inline struct i915_address_space *
+i915_vm_get(struct i915_address_space *vm)
{
- if (ppgtt)
- kref_get(&ppgtt->ref);
+ kref_get(&vm->ref);
+ return vm;
}
-static inline void i915_ppgtt_put(struct i915_hw_ppgtt *ppgtt)
+
+void i915_vm_release(struct kref *kref);
+
+static inline void i915_vm_put(struct i915_address_space *vm)
{
- if (ppgtt)
- kref_put(&ppgtt->ref, i915_ppgtt_release);
+ kref_put(&vm->ref, i915_vm_release);
}
-int gen6_ppgtt_pin(struct i915_hw_ppgtt *base);
-void gen6_ppgtt_unpin(struct i915_hw_ppgtt *base);
+int gen6_ppgtt_pin(struct i915_ppgtt *base);
+void gen6_ppgtt_unpin(struct i915_ppgtt *base);
+void gen6_ppgtt_unpin_all(struct i915_ppgtt *base);
-void i915_check_and_clear_faults(struct drm_i915_private *dev_priv);
void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv);
void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv);