diff options
Diffstat (limited to 'drivers/gpu')
35 files changed, 3658 insertions, 2539 deletions
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 543b9b3..fe304f9 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -147,33 +147,27 @@ static void drm_mm_insert_helper(struct drm_mm_node *hole_node, } } -struct drm_mm_node *drm_mm_create_block(struct drm_mm *mm, - unsigned long start, - unsigned long size, - bool atomic) +int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node) { - struct drm_mm_node *hole, *node; - unsigned long end = start + size; + struct drm_mm_node *hole; + unsigned long end = node->start + node->size; unsigned long hole_start; unsigned long hole_end; + BUG_ON(node == NULL); + + /* Find the relevant hole to add our node to */ drm_mm_for_each_hole(hole, mm, hole_start, hole_end) { - if (hole_start > start || hole_end < end) + if (hole_start > node->start || hole_end < end) continue; - node = drm_mm_kmalloc(mm, atomic); - if (unlikely(node == NULL)) - return NULL; - - node->start = start; - node->size = size; node->mm = mm; node->allocated = 1; INIT_LIST_HEAD(&node->hole_stack); list_add(&node->node_list, &hole->node_list); - if (start == hole_start) { + if (node->start == hole_start) { hole->hole_follows = 0; list_del_init(&hole->hole_stack); } @@ -184,13 +178,14 @@ struct drm_mm_node *drm_mm_create_block(struct drm_mm *mm, node->hole_follows = 1; } - return node; + return 0; } - WARN(1, "no hole found for block 0x%lx + 0x%lx\n", start, size); - return NULL; + WARN(1, "no hole found for node 0x%lx + 0x%lx\n", + node->start, node->size); + return -ENOSPC; } -EXPORT_SYMBOL(drm_mm_create_block); +EXPORT_SYMBOL(drm_mm_reserve_node); struct drm_mm_node *drm_mm_get_block_generic(struct drm_mm_node *hole_node, unsigned long size, diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 40034ec..9d1da7c 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -5,6 +5,7 @@ ccflags-y := -Iinclude/drm i915-y := i915_drv.o i915_dma.o i915_irq.o \ i915_debugfs.o \ + i915_gpu_error.o \ i915_suspend.o \ i915_gem.o \ i915_gem_context.o \ diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 47d6c74..9d871c7 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -30,7 +30,6 @@ #include <linux/debugfs.h> #include <linux/slab.h> #include <linux/export.h> -#include <generated/utsrelease.h> #include <drm/drmP.h> #include "intel_drv.h" #include "intel_ringbuffer.h" @@ -90,16 +89,6 @@ static const char *get_tiling_flag(struct drm_i915_gem_object *obj) } } -static const char *cache_level_str(int type) -{ - switch (type) { - case I915_CACHE_NONE: return " uncached"; - case I915_CACHE_LLC: return " snooped (LLC)"; - case I915_CACHE_LLC_MLC: return " snooped (LLC+MLC)"; - default: return ""; - } -} - static void describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) { @@ -113,7 +102,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) obj->last_read_seqno, obj->last_write_seqno, obj->last_fenced_seqno, - cache_level_str(obj->cache_level), + i915_cache_level_str(obj->cache_level), obj->dirty ? " dirty" : "", obj->madv == I915_MADV_DONTNEED ? " purgeable" : ""); if (obj->base.name) @@ -122,9 +111,9 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) seq_printf(m, " (pinned x %d)", obj->pin_count); if (obj->fence_reg != I915_FENCE_REG_NONE) seq_printf(m, " (fence: %d)", obj->fence_reg); - if (obj->gtt_space != NULL) - seq_printf(m, " (gtt offset: %08x, size: %08x)", - obj->gtt_offset, (unsigned int)obj->gtt_space->size); + if (i915_gem_obj_ggtt_bound(obj)) + seq_printf(m, " (gtt offset: %08lx, size: %08x)", + i915_gem_obj_ggtt_offset(obj), (unsigned int)i915_gem_obj_ggtt_size(obj)); if (obj->stolen) seq_printf(m, " (stolen: %08lx)", obj->stolen->start); if (obj->pin_mappable || obj->fault_mappable) { @@ -146,7 +135,8 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data) uintptr_t list = (uintptr_t) node->info_ent->data; struct list_head *head; struct drm_device *dev = node->minor->dev; - drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *vm = &dev_priv->gtt.base; struct drm_i915_gem_object *obj; size_t total_obj_size, total_gtt_size; int count, ret; @@ -157,12 +147,12 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data) switch (list) { case ACTIVE_LIST: - seq_printf(m, "Active:\n"); - head = &dev_priv->mm.active_list; + seq_puts(m, "Active:\n"); + head = &vm->active_list; break; case INACTIVE_LIST: - seq_printf(m, "Inactive:\n"); - head = &dev_priv->mm.inactive_list; + seq_puts(m, "Inactive:\n"); + head = &vm->inactive_list; break; default: mutex_unlock(&dev->struct_mutex); @@ -171,11 +161,11 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data) total_obj_size = total_gtt_size = count = 0; list_for_each_entry(obj, head, mm_list) { - seq_printf(m, " "); + seq_puts(m, " "); describe_obj(m, obj); - seq_printf(m, "\n"); + seq_putc(m, '\n'); total_obj_size += obj->base.size; - total_gtt_size += obj->gtt_space->size; + total_gtt_size += i915_gem_obj_ggtt_size(obj); count++; } mutex_unlock(&dev->struct_mutex); @@ -187,10 +177,10 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data) #define count_objects(list, member) do { \ list_for_each_entry(obj, list, member) { \ - size += obj->gtt_space->size; \ + size += i915_gem_obj_ggtt_size(obj); \ ++count; \ if (obj->map_and_fenceable) { \ - mappable_size += obj->gtt_space->size; \ + mappable_size += i915_gem_obj_ggtt_size(obj); \ ++mappable_count; \ } \ } \ @@ -209,7 +199,7 @@ static int per_file_stats(int id, void *ptr, void *data) stats->count++; stats->total += obj->base.size; - if (obj->gtt_space) { + if (i915_gem_obj_ggtt_bound(obj)) { if (!list_empty(&obj->ring_list)) stats->active += obj->base.size; else @@ -222,7 +212,7 @@ static int per_file_stats(int id, void *ptr, void *data) return 0; } -static int i915_gem_object_info(struct seq_file *m, void* data) +static int i915_gem_object_info(struct seq_file *m, void *data) { struct drm_info_node *node = (struct drm_info_node *) m->private; struct drm_device *dev = node->minor->dev; @@ -230,6 +220,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data) u32 count, mappable_count, purgeable_count; size_t size, mappable_size, purgeable_size; struct drm_i915_gem_object *obj; + struct i915_address_space *vm = &dev_priv->gtt.base; struct drm_file *file; int ret; @@ -247,12 +238,12 @@ static int i915_gem_object_info(struct seq_file *m, void* data) count, mappable_count, size, mappable_size); size = count = mappable_size = mappable_count = 0; - count_objects(&dev_priv->mm.active_list, mm_list); + count_objects(&vm->active_list, mm_list); seq_printf(m, " %u [%u] active objects, %zu [%zu] bytes\n", count, mappable_count, size, mappable_size); size = count = mappable_size = mappable_count = 0; - count_objects(&dev_priv->mm.inactive_list, mm_list); + count_objects(&vm->inactive_list, mm_list); seq_printf(m, " %u [%u] inactive objects, %zu [%zu] bytes\n", count, mappable_count, size, mappable_size); @@ -267,11 +258,11 @@ static int i915_gem_object_info(struct seq_file *m, void* data) size = count = mappable_size = mappable_count = 0; list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { if (obj->fault_mappable) { - size += obj->gtt_space->size; + size += i915_gem_obj_ggtt_size(obj); ++count; } if (obj->pin_mappable) { - mappable_size += obj->gtt_space->size; + mappable_size += i915_gem_obj_ggtt_size(obj); ++mappable_count; } if (obj->madv == I915_MADV_DONTNEED) { @@ -287,10 +278,10 @@ static int i915_gem_object_info(struct seq_file *m, void* data) count, size); seq_printf(m, "%zu [%lu] gtt total\n", - dev_priv->gtt.total, - dev_priv->gtt.mappable_end - dev_priv->gtt.start); + dev_priv->gtt.base.total, + dev_priv->gtt.mappable_end - dev_priv->gtt.base.start); - seq_printf(m, "\n"); + seq_putc(m, '\n'); list_for_each_entry_reverse(file, &dev->filelist, lhead) { struct file_stats stats; @@ -310,7 +301,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data) return 0; } -static int i915_gem_gtt_info(struct seq_file *m, void* data) +static int i915_gem_gtt_info(struct seq_file *m, void *data) { struct drm_info_node *node = (struct drm_info_node *) m->private; struct drm_device *dev = node->minor->dev; @@ -329,11 +320,11 @@ static int i915_gem_gtt_info(struct seq_file *m, void* data) if (list == PINNED_LIST && obj->pin_count == 0) continue; - seq_printf(m, " "); + seq_puts(m, " "); describe_obj(m, obj); - seq_printf(m, "\n"); + seq_putc(m, '\n'); total_obj_size += obj->base.size; - total_gtt_size += obj->gtt_space->size; + total_gtt_size += i915_gem_obj_ggtt_size(obj); count++; } @@ -371,20 +362,22 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data) pipe, plane); } if (work->enable_stall_check) - seq_printf(m, "Stall check enabled, "); + seq_puts(m, "Stall check enabled, "); else - seq_printf(m, "Stall check waiting for page flip ioctl, "); + seq_puts(m, "Stall check waiting for page flip ioctl, "); seq_printf(m, "%d prepares\n", atomic_read(&work->pending)); if (work->old_fb_obj) { struct drm_i915_gem_object *obj = work->old_fb_obj; if (obj) - seq_printf(m, "Old framebuffer gtt_offset 0x%08x\n", obj->gtt_offset); + seq_printf(m, "Old framebuffer gtt_offset 0x%08lx\n", + i915_gem_obj_ggtt_offset(obj)); } if (work->pending_flip_obj) { struct drm_i915_gem_object *obj = work->pending_flip_obj; if (obj) - seq_printf(m, "New framebuffer gtt_offset 0x%08x\n", obj->gtt_offset); + seq_printf(m, "New framebuffer gtt_offset 0x%08lx\n", + i915_gem_obj_ggtt_offset(obj)); } } spin_unlock_irqrestore(&dev->event_lock, flags); @@ -424,7 +417,7 @@ static int i915_gem_request_info(struct seq_file *m, void *data) mutex_unlock(&dev->struct_mutex); if (count == 0) - seq_printf(m, "No requests\n"); + seq_puts(m, "No requests\n"); return 0; } @@ -574,10 +567,10 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data) seq_printf(m, "Fence %d, pin count = %d, object = ", i, dev_priv->fence_regs[i].pin_count); if (obj == NULL) - seq_printf(m, "unused"); + seq_puts(m, "unused"); else describe_obj(m, obj); - seq_printf(m, "\n"); + seq_putc(m, '\n'); } mutex_unlock(&dev->struct_mutex); @@ -606,361 +599,6 @@ static int i915_hws_info(struct seq_file *m, void *data) return 0; } -static const char *ring_str(int ring) -{ - switch (ring) { - case RCS: return "render"; - case VCS: return "bsd"; - case BCS: return "blt"; - case VECS: return "vebox"; - default: return ""; - } -} - -static const char *pin_flag(int pinned) -{ - if (pinned > 0) - return " P"; - else if (pinned < 0) - return " p"; - else - return ""; -} - -static const char *tiling_flag(int tiling) -{ - switch (tiling) { - default: - case I915_TILING_NONE: return ""; - case I915_TILING_X: return " X"; - case I915_TILING_Y: return " Y"; - } -} - -static const char *dirty_flag(int dirty) -{ - return dirty ? " dirty" : ""; -} - -static const char *purgeable_flag(int purgeable) -{ - return purgeable ? " purgeable" : ""; -} - -static bool __i915_error_ok(struct drm_i915_error_state_buf *e) -{ - - if (!e->err && WARN(e->bytes > (e->size - 1), "overflow")) { - e->err = -ENOSPC; - return false; - } - - if (e->bytes == e->size - 1 || e->err) - return false; - - return true; -} - -static bool __i915_error_seek(struct drm_i915_error_state_buf *e, - unsigned len) -{ - if (e->pos + len <= e->start) { - e->pos += len; - return false; - } - - /* First vsnprintf needs to fit in its entirety for memmove */ - if (len >= e->size) { - e->err = -EIO; - return false; - } - - return true; -} - -static void __i915_error_advance(struct drm_i915_error_state_buf *e, - unsigned len) -{ - /* If this is first printf in this window, adjust it so that - * start position matches start of the buffer - */ - - if (e->pos < e->start) { - const size_t off = e->start - e->pos; - - /* Should not happen but be paranoid */ - if (off > len || e->bytes) { - e->err = -EIO; - return; - } - - memmove(e->buf, e->buf + off, len - off); - e->bytes = len - off; - e->pos = e->start; - return; - } - - e->bytes += len; - e->pos += len; -} - -static void i915_error_vprintf(struct drm_i915_error_state_buf *e, - const char *f, va_list args) -{ - unsigned len; - - if (!__i915_error_ok(e)) - return; - - /* Seek the first printf which is hits start position */ - if (e->pos < e->start) { - len = vsnprintf(NULL, 0, f, args); - if (!__i915_error_seek(e, len)) - return; - } - - len = vsnprintf(e->buf + e->bytes, e->size - e->bytes, f, args); - if (len >= e->size - e->bytes) - len = e->size - e->bytes - 1; - - __i915_error_advance(e, len); -} - -static void i915_error_puts(struct drm_i915_error_state_buf *e, - const char *str) -{ - unsigned len; - - if (!__i915_error_ok(e)) - return; - - len = strlen(str); - - /* Seek the first printf which is hits start position */ - if (e->pos < e->start) { - if (!__i915_error_seek(e, len)) - return; - } - - if (len >= e->size - e->bytes) - len = e->size - e->bytes - 1; - memcpy(e->buf + e->bytes, str, len); - - __i915_error_advance(e, len); -} - -void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...) -{ - va_list args; - - va_start(args, f); - i915_error_vprintf(e, f, args); - va_end(args); -} - -#define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__) -#define err_puts(e, s) i915_error_puts(e, s) - -static void print_error_buffers(struct drm_i915_error_state_buf *m, - const char *name, - struct drm_i915_error_buffer *err, - int count) -{ - err_printf(m, "%s [%d]:\n", name, count); - - while (count--) { - err_printf(m, " %08x %8u %02x %02x %x %x", - err->gtt_offset, - err->size, - err->read_domains, - err->write_domain, - err->rseqno, err->wseqno); - err_puts(m, pin_flag(err->pinned)); - err_puts(m, tiling_flag(err->tiling)); - err_puts(m, dirty_flag(err->dirty)); - err_puts(m, purgeable_flag(err->purgeable)); - err_puts(m, err->ring != -1 ? " " : ""); - err_puts(m, ring_str(err->ring)); - err_puts(m, cache_level_str(err->cache_level)); - - if (err->name) - err_printf(m, " (name: %d)", err->name); - if (err->fence_reg != I915_FENCE_REG_NONE) - err_printf(m, " (fence: %d)", err->fence_reg); - - err_puts(m, "\n"); - err++; - } -} - -static void i915_ring_error_state(struct drm_i915_error_state_buf *m, - struct drm_device *dev, - struct drm_i915_error_state *error, - unsigned ring) -{ - BUG_ON(ring >= I915_NUM_RINGS); /* shut up confused gcc */ - err_printf(m, "%s command stream:\n", ring_str(ring)); - err_printf(m, " HEAD: 0x%08x\n", error->head[ring]); - err_printf(m, " TAIL: 0x%08x\n", error->tail[ring]); - err_printf(m, " CTL: 0x%08x\n", error->ctl[ring]); - err_printf(m, " ACTHD: 0x%08x\n", error->acthd[ring]); - err_printf(m, " IPEIR: 0x%08x\n", error->ipeir[ring]); - err_printf(m, " IPEHR: 0x%08x\n", error->ipehr[ring]); - err_printf(m, " INSTDONE: 0x%08x\n", error->instdone[ring]); - if (ring == RCS && INTEL_INFO(dev)->gen >= 4) - err_printf(m, " BBADDR: 0x%08llx\n", error->bbaddr); - - if (INTEL_INFO(dev)->gen >= 4) - err_printf(m, " INSTPS: 0x%08x\n", error->instps[ring]); - err_printf(m, " INSTPM: 0x%08x\n", error->instpm[ring]); - err_printf(m, " FADDR: 0x%08x\n", error->faddr[ring]); - if (INTEL_INFO(dev)->gen >= 6) { - err_printf(m, " RC PSMI: 0x%08x\n", error->rc_psmi[ring]); - err_printf(m, " FAULT_REG: 0x%08x\n", error->fault_reg[ring]); - err_printf(m, " SYNC_0: 0x%08x [last synced 0x%08x]\n", - error->semaphore_mboxes[ring][0], - error->semaphore_seqno[ring][0]); - err_printf(m, " SYNC_1: 0x%08x [last synced 0x%08x]\n", - error->semaphore_mboxes[ring][1], - error->semaphore_seqno[ring][1]); - } - err_printf(m, " seqno: 0x%08x\n", error->seqno[ring]); - err_printf(m, " waiting: %s\n", yesno(error->waiting[ring])); - err_printf(m, " ring->head: 0x%08x\n", error->cpu_ring_head[ring]); - err_printf(m, " ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]); -} - -struct i915_error_state_file_priv { - struct drm_device *dev; - struct drm_i915_error_state *error; -}; - - -static int i915_error_state(struct i915_error_state_file_priv *error_priv, - struct drm_i915_error_state_buf *m) - -{ - 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; - struct intel_ring_buffer *ring; - int i, j, page, offset, elt; - - if (!error) { - err_printf(m, "no error state collected\n"); - return 0; - } - - err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec, - error->time.tv_usec); - err_printf(m, "Kernel: " UTS_RELEASE "\n"); - err_printf(m, "PCI ID: 0x%04x\n", dev->pci_device); - err_printf(m, "EIR: 0x%08x\n", error->eir); - err_printf(m, "IER: 0x%08x\n", error->ier); - err_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er); - err_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake); - err_printf(m, "DERRMR: 0x%08x\n", error->derrmr); - err_printf(m, "CCID: 0x%08x\n", error->ccid); - - for (i = 0; i < dev_priv->num_fence_regs; i++) - err_printf(m, " fence[%d] = %08llx\n", i, error->fence[i]); - - for (i = 0; i < ARRAY_SIZE(error->extra_instdone); i++) - err_printf(m, " INSTDONE_%d: 0x%08x\n", i, - error->extra_instdone[i]); - - if (INTEL_INFO(dev)->gen >= 6) { - err_printf(m, "ERROR: 0x%08x\n", error->error); - err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg); - } - - if (INTEL_INFO(dev)->gen == 7) - err_printf(m, "ERR_INT: 0x%08x\n", error->err_int); - - for_each_ring(ring, dev_priv, i) - i915_ring_error_state(m, dev, error, i); - - if (error->active_bo) - print_error_buffers(m, "Active", - error->active_bo, - error->active_bo_count); - - if (error->pinned_bo) - print_error_buffers(m, "Pinned", - error->pinned_bo, - error->pinned_bo_count); - - 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->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; - } - } - } - - if (error->ring[i].num_requests) { - err_printf(m, "%s --- %d requests\n", - dev_priv->ring[i].name, - error->ring[i].num_requests); - for (j = 0; j < error->ring[i].num_requests; j++) { - err_printf(m, " seqno 0x%08x, emitted %ld, tail 0x%08x\n", - error->ring[i].requests[j].seqno, - error->ring[i].requests[j].jiffies, - error->ring[i].requests[j].tail); - } - } - - if ((obj = error->ring[i].ringbuffer)) { - 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; - } - } - } - - obj = error->ring[i].ctx; - if (obj) { - err_printf(m, "%s --- HW Context = 0x%08x\n", - dev_priv->ring[i].name, - obj->gtt_offset); - offset = 0; - for (elt = 0; elt < PAGE_SIZE/16; elt += 4) { - err_printf(m, "[%04x] %08x %08x %08x %08x\n", - offset, - obj->pages[0][elt], - obj->pages[0][elt+1], - obj->pages[0][elt+2], - obj->pages[0][elt+3]); - offset += 16; - } - } - } - - if (error->overlay) - intel_overlay_print_error_state(m, error->overlay); - - if (error->display) - intel_display_print_error_state(m, dev, error->display); - - return 0; -} - static ssize_t i915_error_state_write(struct file *filp, const char __user *ubuf, @@ -986,9 +624,7 @@ i915_error_state_write(struct file *filp, static int i915_error_state_open(struct inode *inode, struct file *file) { struct drm_device *dev = inode->i_private; - drm_i915_private_t *dev_priv = dev->dev_private; struct i915_error_state_file_priv *error_priv; - unsigned long flags; error_priv = kzalloc(sizeof(*error_priv), GFP_KERNEL); if (!error_priv) @@ -996,11 +632,7 @@ static int i915_error_state_open(struct inode *inode, struct file *file) error_priv->dev = dev; - spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); - error_priv->error = dev_priv->gpu_error.first_error; - if (error_priv->error) - kref_get(&error_priv->error->ref); - spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); + i915_error_state_get(dev, error_priv); file->private_data = error_priv; @@ -1011,8 +643,7 @@ static int i915_error_state_release(struct inode *inode, struct file *file) { struct i915_error_state_file_priv *error_priv = file->private_data; - if (error_priv->error) - kref_put(&error_priv->error->ref, i915_error_state_free); + i915_error_state_put(error_priv); kfree(error_priv); return 0; @@ -1025,40 +656,15 @@ static ssize_t i915_error_state_read(struct file *file, char __user *userbuf, struct drm_i915_error_state_buf error_str; loff_t tmp_pos = 0; ssize_t ret_count = 0; - int ret = 0; - - memset(&error_str, 0, sizeof(error_str)); - - /* We need to have enough room to store any i915_error_state printf - * so that we can move it to start position. - */ - error_str.size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE; - error_str.buf = kmalloc(error_str.size, - GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN); - - if (error_str.buf == NULL) { - error_str.size = PAGE_SIZE; - error_str.buf = kmalloc(error_str.size, GFP_TEMPORARY); - } - - if (error_str.buf == NULL) { - error_str.size = 128; - error_str.buf = kmalloc(error_str.size, GFP_TEMPORARY); - } - - if (error_str.buf == NULL) - return -ENOMEM; - - error_str.start = *pos; + int ret; - ret = i915_error_state(error_priv, &error_str); + ret = i915_error_state_buf_init(&error_str, count, *pos); if (ret) - goto out; + return ret; - if (error_str.bytes == 0 && error_str.err) { - ret = error_str.err; + ret = i915_error_state_to_str(&error_str, error_priv); + if (ret) goto out; - } ret_count = simple_read_from_buffer(userbuf, count, &tmp_pos, error_str.buf, @@ -1069,7 +675,7 @@ static ssize_t i915_error_state_read(struct file *file, char __user *userbuf, else *pos = error_str.start + ret_count; out: - kfree(error_str.buf); + i915_error_state_buf_release(&error_str); return ret ?: ret_count; } @@ -1246,7 +852,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) (freq_sts >> 8) & 0xff)); mutex_unlock(&dev_priv->rps.hw_lock); } else { - seq_printf(m, "no P-state info available\n"); + seq_puts(m, "no P-state info available\n"); } return 0; @@ -1341,28 +947,28 @@ static int ironlake_drpc_info(struct seq_file *m) seq_printf(m, "RS2 VID: %d\n", ((crstandvid >> 8) & 0x3f)); seq_printf(m, "Render standby enabled: %s\n", (rstdbyctl & RCX_SW_EXIT) ? "no" : "yes"); - seq_printf(m, "Current RS state: "); + seq_puts(m, "Current RS state: "); switch (rstdbyctl & RSX_STATUS_MASK) { case RSX_STATUS_ON: - seq_printf(m, "on\n"); + seq_puts(m, "on\n"); break; case RSX_STATUS_RC1: - seq_printf(m, "RC1\n"); + seq_puts(m, "RC1\n"); break; case RSX_STATUS_RC1E: - seq_printf(m, "RC1E\n"); + seq_puts(m, "RC1E\n"); break; case RSX_STATUS_RS1: - seq_printf(m, "RS1\n"); + seq_puts(m, "RS1\n"); break; case RSX_STATUS_RS2: - seq_printf(m, "RS2 (RC6)\n"); + seq_puts(m, "RS2 (RC6)\n"); break; case RSX_STATUS_RS3: - seq_printf(m, "RC3 (RC6+)\n"); + seq_puts(m, "RC3 (RC6+)\n"); break; default: - seq_printf(m, "unknown\n"); + seq_puts(m, "unknown\n"); break; } @@ -1377,8 +983,7 @@ static int gen6_drpc_info(struct seq_file *m) struct drm_i915_private *dev_priv = dev->dev_private; u32 rpmodectl1, gt_core_status, rcctl1, rc6vids = 0; unsigned forcewake_count; - int count=0, ret; - + int count = 0, ret; ret = mutex_lock_interruptible(&dev->struct_mutex); if (ret) @@ -1389,8 +994,8 @@ static int gen6_drpc_info(struct seq_file *m) spin_unlock_irq(&dev_priv->gt_lock); if (forcewake_count) { - seq_printf(m, "RC information inaccurate because somebody " - "holds a forcewake reference \n"); + seq_puts(m, "RC information inaccurate because somebody " + "holds a forcewake reference \n"); } else { /* NB: we cannot use forcewake, else we read the wrong values */ while (count++ < 50 && (I915_READ_NOTRACE(FORCEWAKE_ACK) & 1)) @@ -1423,25 +1028,25 @@ static int gen6_drpc_info(struct seq_file *m) yesno(rcctl1 & GEN6_RC_CTL_RC6p_ENABLE)); seq_printf(m, "Deepest RC6 Enabled: %s\n", yesno(rcctl1 & GEN6_RC_CTL_RC6pp_ENABLE)); - seq_printf(m, "Current RC state: "); + seq_puts(m, "Current RC state: "); switch (gt_core_status & GEN6_RCn_MASK) { case GEN6_RC0: if (gt_core_status & GEN6_CORE_CPD_STATE_MASK) - seq_printf(m, "Core Power Down\n"); + seq_puts(m, "Core Power Down\n"); else - seq_printf(m, "on\n"); + seq_puts(m, "on\n"); break; case GEN6_RC3: - seq_printf(m, "RC3\n"); + seq_puts(m, "RC3\n"); break; case GEN6_RC6: - seq_printf(m, "RC6\n"); + seq_puts(m, "RC6\n"); break; case GEN6_RC7: - seq_printf(m, "RC7\n"); + seq_puts(m, "RC7\n"); break; default: - seq_printf(m, "Unknown\n"); + seq_puts(m, "Unknown\n"); break; } @@ -1485,43 +1090,46 @@ static int i915_fbc_status(struct seq_file *m, void *unused) drm_i915_private_t *dev_priv = dev->dev_private; if (!I915_HAS_FBC(dev)) { - seq_printf(m, "FBC unsupported on this chipset\n"); + seq_puts(m, "FBC unsupported on this chipset\n"); return 0; } if (intel_fbc_enabled(dev)) { - seq_printf(m, "FBC enabled\n"); + seq_puts(m, "FBC enabled\n"); } else { - seq_printf(m, "FBC disabled: "); - switch (dev_priv->no_fbc_reason) { + seq_puts(m, "FBC disabled: "); + switch (dev_priv->fbc.no_fbc_reason) { case FBC_NO_OUTPUT: - seq_printf(m, "no outputs"); + seq_puts(m, "no outputs"); break; case FBC_STOLEN_TOO_SMALL: - seq_printf(m, "not enough stolen memory"); + seq_puts(m, "not enough stolen memory"); break; case FBC_UNSUPPORTED_MODE: - seq_printf(m, "mode not supported"); + seq_puts(m, "mode not supported"); break; case FBC_MODE_TOO_LARGE: - seq_printf(m, "mode too large"); + seq_puts(m, "mode too large"); break; case FBC_BAD_PLANE: - seq_printf(m, "FBC unsupported on plane"); + seq_puts(m, "FBC unsupported on plane"); break; case FBC_NOT_TILED: - seq_printf(m, "scanout buffer not tiled"); + seq_puts(m, "scanout buffer not tiled"); break; case FBC_MULTIPLE_PIPES: - seq_printf(m, "multiple pipes are enabled"); + seq_puts(m, "multiple pipes are enabled"); break; case FBC_MODULE_PARAM: - seq_printf(m, "disabled per module param (default off)"); + seq_puts(m, "disabled per module param (default off)"); + break; + case FBC_CHIP_DEFAULT: + seq_puts(m, "disabled per chip default"); break; default: - seq_printf(m, "unknown reason"); + seq_puts(m, "unknown reason"); } - seq_printf(m, "\n"); + seq_putc(m, '\n'); } return 0; } @@ -1604,7 +1212,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused) int gpu_freq, ia_freq; if (!(IS_GEN6(dev) || IS_GEN7(dev))) { - seq_printf(m, "unsupported on this chipset\n"); + seq_puts(m, "unsupported on this chipset\n"); return 0; } @@ -1612,7 +1220,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused) if (ret) return ret; - seq_printf(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n"); + seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n"); for (gpu_freq = dev_priv->rps.min_delay; gpu_freq <= dev_priv->rps.max_delay; @@ -1701,7 +1309,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) fb->base.bits_per_pixel, atomic_read(&fb->base.refcount.refcount)); describe_obj(m, fb->obj); - seq_printf(m, "\n"); + seq_putc(m, '\n'); mutex_unlock(&dev->mode_config.mutex); mutex_lock(&dev->mode_config.fb_lock); @@ -1716,7 +1324,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) fb->base.bits_per_pixel, atomic_read(&fb->base.refcount.refcount)); describe_obj(m, fb->obj); - seq_printf(m, "\n"); + seq_putc(m, '\n'); } mutex_unlock(&dev->mode_config.fb_lock); @@ -1736,22 +1344,22 @@ static int i915_context_status(struct seq_file *m, void *unused) return ret; if (dev_priv->ips.pwrctx) { - seq_printf(m, "power context "); + seq_puts(m, "power context "); describe_obj(m, dev_priv->ips.pwrctx); - seq_printf(m, "\n"); + seq_putc(m, '\n'); } if (dev_priv->ips.renderctx) { - seq_printf(m, "render context "); + seq_puts(m, "render context "); describe_obj(m, dev_priv->ips.renderctx); - seq_printf(m, "\n"); + seq_putc(m, '\n'); } for_each_ring(ring, dev_priv, i) { if (ring->default_context) { seq_printf(m, "HW default context %s ring ", ring->name); describe_obj(m, ring->default_context->obj); - seq_printf(m, "\n"); + seq_putc(m, '\n'); } } @@ -1778,7 +1386,7 @@ static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data) static const char *swizzle_string(unsigned swizzle) { - switch(swizzle) { + switch (swizzle) { case I915_BIT_6_SWIZZLE_NONE: return "none"; case I915_BIT_6_SWIZZLE_9: @@ -1868,7 +1476,7 @@ static int i915_ppgtt_info(struct seq_file *m, void *data) if (dev_priv->mm.aliasing_ppgtt) { struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; - seq_printf(m, "aliasing PPGTT:\n"); + seq_puts(m, "aliasing PPGTT:\n"); seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd_offset); } seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK)); @@ -1886,7 +1494,7 @@ static int i915_dpio_info(struct seq_file *m, void *data) if (!IS_VALLEYVIEW(dev)) { - seq_printf(m, "unsupported\n"); + seq_puts(m, "unsupported\n"); return 0; } @@ -1924,6 +1532,148 @@ static int i915_dpio_info(struct seq_file *m, void *data) return 0; } +static int i915_llc(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_device *dev = node->minor->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + /* Size calculation for LLC is a bit of a pain. Ignore for now. */ + seq_printf(m, "LLC: %s\n", yesno(HAS_LLC(dev))); + seq_printf(m, "eLLC: %zuMB\n", dev_priv->ellc_size); + + return 0; +} + +static int i915_edp_psr_status(struct seq_file *m, void *data) +{ + struct drm_info_node *node = m->private; + struct drm_device *dev = node->minor->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 psrstat, psrperf; + + if (!IS_HASWELL(dev)) { + seq_puts(m, "PSR not supported on this platform\n"); + } else if (IS_HASWELL(dev) && I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE) { + seq_puts(m, "PSR enabled\n"); + } else { + seq_puts(m, "PSR disabled: "); + switch (dev_priv->no_psr_reason) { + case PSR_NO_SOURCE: + seq_puts(m, "not supported on this platform"); + break; + case PSR_NO_SINK: + seq_puts(m, "not supported by panel"); + break; + case PSR_MODULE_PARAM: + seq_puts(m, "disabled by flag"); + break; + case PSR_CRTC_NOT_ACTIVE: + seq_puts(m, "crtc not active"); + break; + case PSR_PWR_WELL_ENABLED: + seq_puts(m, "power well enabled"); + break; + case PSR_NOT_TILED: + seq_puts(m, "not tiled"); + break; + case PSR_SPRITE_ENABLED: + seq_puts(m, "sprite enabled"); + break; + case PSR_S3D_ENABLED: + seq_puts(m, "stereo 3d enabled"); + break; + case PSR_INTERLACED_ENABLED: + seq_puts(m, "interlaced enabled"); + break; + case PSR_HSW_NOT_DDIA: + seq_puts(m, "HSW ties PSR to DDI A (eDP)"); + break; + default: + seq_puts(m, "unknown reason"); + } + seq_puts(m, "\n"); + return 0; + } + + psrstat = I915_READ(EDP_PSR_STATUS_CTL); + + seq_puts(m, "PSR Current State: "); + switch (psrstat & EDP_PSR_STATUS_STATE_MASK) { + case EDP_PSR_STATUS_STATE_IDLE: + seq_puts(m, "Reset state\n"); + break; + case EDP_PSR_STATUS_STATE_SRDONACK: + seq_puts(m, "Wait for TG/Stream to send on frame of data after SRD conditions are met\n"); + break; + case EDP_PSR_STATUS_STATE_SRDENT: + seq_puts(m, "SRD entry\n"); + break; + case EDP_PSR_STATUS_STATE_BUFOFF: + seq_puts(m, "Wait for buffer turn off\n"); + break; + case EDP_PSR_STATUS_STATE_BUFON: + seq_puts(m, "Wait for buffer turn on\n"); + break; + case EDP_PSR_STATUS_STATE_AUXACK: + seq_puts(m, "Wait for AUX to acknowledge on SRD exit\n"); + break; + case EDP_PSR_STATUS_STATE_SRDOFFACK: + seq_puts(m, "Wait for TG/Stream to acknowledge the SRD VDM exit\n"); + break; + default: + seq_puts(m, "Unknown\n"); + break; + } + + seq_puts(m, "Link Status: "); + switch (psrstat & EDP_PSR_STATUS_LINK_MASK) { + case EDP_PSR_STATUS_LINK_FULL_OFF: + seq_puts(m, "Link is fully off\n"); + break; + case EDP_PSR_STATUS_LINK_FULL_ON: + seq_puts(m, "Link is fully on\n"); + break; + case EDP_PSR_STATUS_LINK_STANDBY: + seq_puts(m, "Link is in standby\n"); + break; + default: + seq_puts(m, "Unknown\n"); + break; + } + + seq_printf(m, "PSR Entry Count: %u\n", + psrstat >> EDP_PSR_STATUS_COUNT_SHIFT & + EDP_PSR_STATUS_COUNT_MASK); + + seq_printf(m, "Max Sleep Timer Counter: %u\n", + psrstat >> EDP_PSR_STATUS_MAX_SLEEP_TIMER_SHIFT & + EDP_PSR_STATUS_MAX_SLEEP_TIMER_MASK); + + seq_printf(m, "Had AUX error: %s\n", + yesno(psrstat & EDP_PSR_STATUS_AUX_ERROR)); + + seq_printf(m, "Sending AUX: %s\n", + yesno(psrstat & EDP_PSR_STATUS_AUX_SENDING)); + + seq_printf(m, "Sending Idle: %s\n", + yesno(psrstat & EDP_PSR_STATUS_SENDING_IDLE)); + + seq_printf(m, "Sending TP2 TP3: %s\n", + yesno(psrstat & EDP_PSR_STATUS_SENDING_TP2_TP3)); + + seq_printf(m, "Sending TP1: %s\n", + yesno(psrstat & EDP_PSR_STATUS_SENDING_TP1)); + + seq_printf(m, "Idle Count: %u\n", + psrstat & EDP_PSR_STATUS_IDLE_MASK); + + psrperf = (I915_READ(EDP_PSR_PERF_CNT)) & EDP_PSR_PERF_CNT_MASK; + seq_printf(m, "Performance Counter: %u\n", psrperf); + + return 0; +} + static int i915_wedged_get(void *data, u64 *val) { @@ -2006,6 +1756,7 @@ i915_drop_caches_set(void *data, u64 val) struct drm_device *dev = data; struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj, *next; + struct i915_address_space *vm = &dev_priv->gtt.base; int ret; DRM_DEBUG_DRIVER("Dropping caches: 0x%08llx\n", val); @@ -2026,7 +1777,8 @@ i915_drop_caches_set(void *data, u64 val) i915_gem_retire_requests(dev); if (val & DROP_BOUND) { - list_for_each_entry_safe(obj, next, &dev_priv->mm.inactive_list, mm_list) + list_for_each_entry_safe(obj, next, &vm->inactive_list, + mm_list) if (obj->pin_count == 0) { ret = i915_gem_object_unbind(obj); if (ret) @@ -2353,64 +2105,40 @@ static struct drm_info_list i915_debugfs_list[] = { {"i915_swizzle_info", i915_swizzle_info, 0}, {"i915_ppgtt_info", i915_ppgtt_info, 0}, {"i915_dpio", i915_dpio_info, 0}, + {"i915_llc", i915_llc, 0}, + {"i915_edp_psr_status", i915_edp_psr_status, 0}, }; #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list) +struct i915_debugfs_files { + const char *name; + const struct file_operations *fops; +} i915_debugfs_files[] = { + {"i915_wedged", &i915_wedged_fops}, + {"i915_max_freq", &i915_max_freq_fops}, + {"i915_min_freq", &i915_min_freq_fops}, + {"i915_cache_sharing", &i915_cache_sharing_fops}, + {"i915_ring_stop", &i915_ring_stop_fops}, + {"i915_gem_drop_caches", &i915_drop_caches_fops}, + {"i915_error_state", &i915_error_state_fops}, + {"i915_next_seqno", &i915_next_seqno_fops}, +}; + int i915_debugfs_init(struct drm_minor *minor) { - int ret; - - ret = i915_debugfs_create(minor->debugfs_root, minor, - "i915_wedged", - &i915_wedged_fops); - if (ret) - return ret; + int ret, i; ret = i915_forcewake_create(minor->debugfs_root, minor); if (ret) return ret; - ret = i915_debugfs_create(minor->debugfs_root, minor, - "i915_max_freq", - &i915_max_freq_fops); - if (ret) - return ret; - - ret = i915_debugfs_create(minor->debugfs_root, minor, - "i915_min_freq", - &i915_min_freq_fops); - if (ret) - return ret; - - ret = i915_debugfs_create(minor->debugfs_root, minor, - "i915_cache_sharing", - &i915_cache_sharing_fops); - if (ret) - return ret; - - ret = i915_debugfs_create(minor->debugfs_root, minor, - "i915_ring_stop", - &i915_ring_stop_fops); - if (ret) - return ret; - - ret = i915_debugfs_create(minor->debugfs_root, minor, - "i915_gem_drop_caches", - &i915_drop_caches_fops); - if (ret) - return ret; - - ret = i915_debugfs_create(minor->debugfs_root, minor, - "i915_error_state", - &i915_error_state_fops); - if (ret) - return ret; - - ret = i915_debugfs_create(minor->debugfs_root, minor, - "i915_next_seqno", - &i915_next_seqno_fops); - if (ret) - return ret; + for (i = 0; i < ARRAY_SIZE(i915_debugfs_files); i++) { + ret = i915_debugfs_create(minor->debugfs_root, minor, + i915_debugfs_files[i].name, + i915_debugfs_files[i].fops); + if (ret) + return ret; + } return drm_debugfs_create_files(i915_debugfs_list, I915_DEBUGFS_ENTRIES, @@ -2419,26 +2147,18 @@ int i915_debugfs_init(struct drm_minor *minor) void i915_debugfs_cleanup(struct drm_minor *minor) { + int i; + drm_debugfs_remove_files(i915_debugfs_list, I915_DEBUGFS_ENTRIES, minor); drm_debugfs_remove_files((struct drm_info_list *) &i915_forcewake_fops, 1, minor); - drm_debugfs_remove_files((struct drm_info_list *) &i915_wedged_fops, - 1, minor); - drm_debugfs_remove_files((struct drm_info_list *) &i915_max_freq_fops, - 1, minor); - drm_debugfs_remove_files((struct drm_info_list *) &i915_min_freq_fops, - 1, minor); - drm_debugfs_remove_files((struct drm_info_list *) &i915_cache_sharing_fops, - 1, minor); - drm_debugfs_remove_files((struct drm_info_list *) &i915_drop_caches_fops, - 1, minor); - drm_debugfs_remove_files((struct drm_info_list *) &i915_ring_stop_fops, - 1, minor); - drm_debugfs_remove_files((struct drm_info_list *) &i915_error_state_fops, - 1, minor); - drm_debugfs_remove_files((struct drm_info_list *) &i915_next_seqno_fops, - 1, minor); + for (i = 0; i < ARRAY_SIZE(i915_debugfs_files); i++) { + struct drm_info_list *info_list = + (struct drm_info_list *) i915_debugfs_files[i].fops; + + drm_debugfs_remove_files(info_list, 1, minor); + } } #endif /* CONFIG_DEBUG_FS */ diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 67ec54f..1c5b397 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1323,10 +1323,8 @@ static int i915_load_modeset_init(struct drm_device *dev) /* Always safe in the mode setting case. */ /* FIXME: do pre/post-mode set stuff in core KMS code */ dev->vblank_disable_allowed = 1; - if (INTEL_INFO(dev)->num_pipes == 0) { - dev_priv->mm.suspended = 0; + if (INTEL_INFO(dev)->num_pipes == 0) return 0; - } ret = intel_fbdev_init(dev); if (ret) @@ -1352,9 +1350,6 @@ static int i915_load_modeset_init(struct drm_device *dev) drm_kms_helper_poll_init(dev); - /* We're off and running w/KMS */ - dev_priv->mm.suspended = 0; - return 0; cleanup_gem: @@ -1363,7 +1358,7 @@ cleanup_gem: i915_gem_context_fini(dev); mutex_unlock(&dev->struct_mutex); i915_gem_cleanup_aliasing_ppgtt(dev); - drm_mm_takedown(&dev_priv->mm.gtt_space); + drm_mm_takedown(&dev_priv->gtt.base.mm); cleanup_irq: drm_irq_uninstall(dev); cleanup_gem_stolen: @@ -1497,14 +1492,18 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) spin_lock_init(&dev_priv->irq_lock); spin_lock_init(&dev_priv->gpu_error.lock); - spin_lock_init(&dev_priv->rps.lock); spin_lock_init(&dev_priv->backlight.lock); + spin_lock_init(&dev_priv->gt_lock); mutex_init(&dev_priv->dpio_lock); mutex_init(&dev_priv->rps.hw_lock); mutex_init(&dev_priv->modeset_restore_lock); i915_dump_device_info(dev_priv); + INIT_LIST_HEAD(&dev_priv->vm_list); + INIT_LIST_HEAD(&dev_priv->gtt.base.global_link); + list_add(&dev_priv->gtt.base.global_link, &dev_priv->vm_list); + if (i915_get_bridge_dev(dev)) { ret = -EIO; goto free_priv; @@ -1532,6 +1531,16 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) intel_early_sanitize_regs(dev); + if (IS_HASWELL(dev) && (I915_READ(HSW_EDRAM_PRESENT) == 1)) { + /* The docs do not explain exactly how the calculation can be + * made. It is somewhat guessable, but for now, it's always + * 128MB. + * NB: We can't write IDICR yet because we do not have gt funcs + * set up */ + dev_priv->ellc_size = 128; + DRM_INFO("Found %zuMB of eLLC\n", dev_priv->ellc_size); + } + ret = i915_gem_gtt_init(dev); if (ret) goto put_bridge; @@ -1566,8 +1575,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto out_rmmap; } - dev_priv->mm.gtt_mtrr = arch_phys_wc_add(dev_priv->gtt.mappable_base, - aperture_size); + dev_priv->gtt.mtrr = arch_phys_wc_add(dev_priv->gtt.mappable_base, + aperture_size); /* The i915 workqueue is primarily used for batched retirement of * requests (and thus managing bo) once the task has been completed @@ -1629,9 +1638,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto out_gem_unload; } - /* Start out suspended */ - dev_priv->mm.suspended = 1; - if (HAS_POWER_WELL(dev)) i915_init_power_well(dev); @@ -1641,6 +1647,9 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) DRM_ERROR("failed to init modeset\n"); goto out_gem_unload; } + } else { + /* Start out suspended in ums mode. */ + dev_priv->ums.mm_suspended = 1; } i915_setup_sysfs(dev); @@ -1667,9 +1676,9 @@ out_gem_unload: intel_teardown_mchbar(dev); destroy_workqueue(dev_priv->wq); out_mtrrfree: - arch_phys_wc_del(dev_priv->mm.gtt_mtrr); + arch_phys_wc_del(dev_priv->gtt.mtrr); io_mapping_free(dev_priv->gtt.mappable); - dev_priv->gtt.gtt_remove(dev); + dev_priv->gtt.base.cleanup(&dev_priv->gtt.base); out_rmmap: pci_iounmap(dev->pdev, dev_priv->regs); put_bridge: @@ -1705,7 +1714,7 @@ int i915_driver_unload(struct drm_device *dev) cancel_delayed_work_sync(&dev_priv->mm.retire_work); io_mapping_free(dev_priv->gtt.mappable); - arch_phys_wc_del(dev_priv->mm.gtt_mtrr); + arch_phys_wc_del(dev_priv->gtt.mtrr); acpi_video_unregister(); @@ -1754,7 +1763,9 @@ int i915_driver_unload(struct drm_device *dev) i915_free_hws(dev); } - drm_mm_takedown(&dev_priv->mm.gtt_space); + list_del(&dev_priv->gtt.base.global_link); + WARN_ON(!list_empty(&dev_priv->vm_list)); + drm_mm_takedown(&dev_priv->gtt.base.mm); if (dev_priv->regs != NULL) pci_iounmap(dev->pdev, dev_priv->regs); @@ -1764,7 +1775,7 @@ int i915_driver_unload(struct drm_device *dev) destroy_workqueue(dev_priv->wq); pm_qos_remove_request(&dev_priv->pm_qos); - dev_priv->gtt.gtt_remove(dev); + dev_priv->gtt.base.cleanup(&dev_priv->gtt.base); if (dev_priv->slab) kmem_cache_destroy(dev_priv->slab); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 45b3c03..5849b0a 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -118,6 +118,10 @@ module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, int, 0600); MODULE_PARM_DESC(i915_enable_ppgtt, "Enable PPGTT (default: true)"); +int i915_enable_psr __read_mostly = 0; +module_param_named(enable_psr, i915_enable_psr, int, 0600); +MODULE_PARM_DESC(enable_psr, "Enable PSR (default: false)"); + unsigned int i915_preliminary_hw_support __read_mostly = 0; module_param_named(preliminary_hw_support, i915_preliminary_hw_support, int, 0600); MODULE_PARM_DESC(preliminary_hw_support, @@ -132,6 +136,16 @@ int i915_enable_ips __read_mostly = 1; module_param_named(enable_ips, i915_enable_ips, int, 0600); MODULE_PARM_DESC(enable_ips, "Enable IPS (default: true)"); +bool i915_fastboot __read_mostly = 0; +module_param_named(fastboot, i915_fastboot, bool, 0600); +MODULE_PARM_DESC(fastboot, "Try to skip unnecessary mode sets at boot time " + "(default: false)"); + +bool i915_prefault_disable __read_mostly; +module_param_named(prefault_disable, i915_prefault_disable, bool, 0600); +MODULE_PARM_DESC(prefault_disable, + "Disable page prefaulting for pread/pwrite/reloc (default:false). For developers only."); + static struct drm_driver driver; extern int intel_agp_enabled; @@ -551,7 +565,11 @@ static int i915_drm_freeze(struct drm_device *dev) /* If KMS is active, we do the leavevt stuff here */ if (drm_core_check_feature(dev, DRIVER_MODESET)) { - int error = i915_gem_idle(dev); + int error; + + mutex_lock(&dev->struct_mutex); + error = i915_gem_idle(dev); + mutex_unlock(&dev->struct_mutex); if (error) { dev_err(&dev->pdev->dev, "GEM idle failed, resume might fail\n"); @@ -656,7 +674,6 @@ static int __i915_drm_thaw(struct drm_device *dev) intel_init_pch_refclk(dev); mutex_lock(&dev->struct_mutex); - dev_priv->mm.suspended = 0; error = i915_gem_init_hw(dev); mutex_unlock(&dev->struct_mutex); @@ -793,28 +810,29 @@ static int i965_reset_complete(struct drm_device *dev) static int i965_do_reset(struct drm_device *dev) { int ret; - u8 gdrst; /* * Set the domains we want to reset (GRDOM/bits 2 and 3) as * well as the reset bit (GR/bit 0). Setting the GR bit * triggers the reset; when done, the hardware will clear it. */ - pci_read_config_byte(dev->pdev, I965_GDRST, &gdrst); pci_write_config_byte(dev->pdev, I965_GDRST, - gdrst | GRDOM_RENDER | - GRDOM_RESET_ENABLE); + GRDOM_RENDER | GRDOM_RESET_ENABLE); ret = wait_for(i965_reset_complete(dev), 500); if (ret) return ret; /* We can't reset render&media without also resetting display ... */ - pci_read_config_byte(dev->pdev, I965_GDRST, &gdrst); pci_write_config_byte(dev->pdev, I965_GDRST, - gdrst | GRDOM_MEDIA | - GRDOM_RESET_ENABLE); + GRDOM_MEDIA | GRDOM_RESET_ENABLE); - return wait_for(i965_reset_complete(dev), 500); + ret = wait_for(i965_reset_complete(dev), 500); + if (ret) + return ret; + + pci_write_config_byte(dev->pdev, I965_GDRST, 0); + + return 0; } static int ironlake_do_reset(struct drm_device *dev) @@ -955,11 +973,11 @@ int i915_reset(struct drm_device *dev) * switched away). */ if (drm_core_check_feature(dev, DRIVER_MODESET) || - !dev_priv->mm.suspended) { + !dev_priv->ums.mm_suspended) { struct intel_ring_buffer *ring; int i; - dev_priv->mm.suspended = 0; + dev_priv->ums.mm_suspended = 0; i915_gem_init_swizzling(dev); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index d2ee334..331c00b 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -144,6 +144,7 @@ enum intel_dpll_id { struct intel_dpll_hw_state { uint32_t dpll; + uint32_t dpll_md; uint32_t fp0; uint32_t fp1; }; @@ -156,6 +157,8 @@ struct intel_shared_dpll { /* should match the index in the dev_priv->shared_dplls array */ enum intel_dpll_id id; struct intel_dpll_hw_state hw_state; + void (*mode_set)(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll); void (*enable)(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll); void (*disable)(struct drm_i915_private *dev_priv, @@ -364,6 +367,7 @@ struct drm_i915_display_funcs { * fills out the pipe-config with the hw state. */ bool (*get_pipe_config)(struct intel_crtc *, struct intel_crtc_config *); + void (*get_clock)(struct intel_crtc *, struct intel_crtc_config *); int (*crtc_mode_set)(struct drm_crtc *crtc, int x, int y, struct drm_framebuffer *old_fb); @@ -442,6 +446,54 @@ enum i915_cache_level { typedef uint32_t gen6_gtt_pte_t; +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_rendering_seqno + * 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_rendering_seqno is 0 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_gtt_pte_t (*pte_encode)(dma_addr_t addr, + enum i915_cache_level level); + void (*clear_range)(struct i915_address_space *vm, + unsigned int first_entry, + unsigned int num_entries); + void (*insert_entries)(struct i915_address_space *vm, + struct sg_table *st, + unsigned int first_entry, + enum i915_cache_level cache_level); + 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 @@ -450,8 +502,7 @@ typedef uint32_t gen6_gtt_pte_t; * the spec. */ struct i915_gtt { - unsigned long start; /* Start offset of used GTT */ - size_t total; /* Total size GTT can map */ + 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 */ @@ -462,50 +513,35 @@ struct i915_gtt { void __iomem *gsm; bool do_idle_maps; - dma_addr_t scratch_page_dma; - struct page *scratch_page; + + 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); - void (*gtt_remove)(struct drm_device *dev); - void (*gtt_clear_range)(struct drm_device *dev, - unsigned int first_entry, - unsigned int num_entries); - void (*gtt_insert_entries)(struct drm_device *dev, - struct sg_table *st, - unsigned int pg_start, - enum i915_cache_level cache_level); - gen6_gtt_pte_t (*pte_encode)(struct drm_device *dev, - dma_addr_t addr, - enum i915_cache_level level); }; -#define gtt_total_entries(gtt) ((gtt).total >> PAGE_SHIFT) +#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT) -#define I915_PPGTT_PD_ENTRIES 512 -#define I915_PPGTT_PT_ENTRIES 1024 struct i915_hw_ppgtt { - struct drm_device *dev; + struct i915_address_space base; unsigned num_pd_entries; struct page **pt_pages; uint32_t pd_offset; dma_addr_t *pt_dma_addr; - dma_addr_t scratch_page_dma_addr; - /* pte functions, mirroring the interface of the global gtt. */ - void (*clear_range)(struct i915_hw_ppgtt *ppgtt, - unsigned int first_entry, - unsigned int num_entries); - void (*insert_entries)(struct i915_hw_ppgtt *ppgtt, - struct sg_table *st, - unsigned int pg_start, - enum i915_cache_level cache_level); - gen6_gtt_pte_t (*pte_encode)(struct drm_device *dev, - dma_addr_t addr, - enum i915_cache_level level); int (*enable)(struct drm_device *dev); - void (*cleanup)(struct i915_hw_ppgtt *ppgtt); +}; + +/* 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; + + struct list_head vma_link; /* Link in the object's VMA list */ }; struct i915_ctx_hang_stats { @@ -528,15 +564,46 @@ struct i915_hw_context { struct i915_ctx_hang_stats hang_stats; }; -enum no_fbc_reason { - FBC_NO_OUTPUT, /* no outputs enabled to compress */ - FBC_STOLEN_TOO_SMALL, /* not enough space to hold compressed buffers */ - FBC_UNSUPPORTED_MODE, /* interlace or doublescanned mode */ - FBC_MODE_TOO_LARGE, /* mode too large for compression */ - FBC_BAD_PLANE, /* fbc not supported on plane */ - FBC_NOT_TILED, /* buffer not tiled */ - FBC_MULTIPLE_PIPES, /* more than one pipe active */ - FBC_MODULE_PARAM, +struct i915_fbc { + unsigned long size; + unsigned int fb_id; + enum plane plane; + int y; + + struct drm_mm_node *compressed_fb; + struct drm_mm_node *compressed_llb; + + struct intel_fbc_work { + struct delayed_work work; + struct drm_crtc *crtc; + struct drm_framebuffer *fb; + int interval; + } *fbc_work; + + enum { + FBC_NO_OUTPUT, /* no outputs enabled to compress */ + FBC_STOLEN_TOO_SMALL, /* not enough space for buffers */ + FBC_UNSUPPORTED_MODE, /* interlace or doublescanned mode */ + FBC_MODE_TOO_LARGE, /* mode too large for compression */ + FBC_BAD_PLANE, /* fbc not supported on plane */ + FBC_NOT_TILED, /* buffer not tiled */ + FBC_MULTIPLE_PIPES, /* more than one pipe active */ + FBC_MODULE_PARAM, + FBC_CHIP_DEFAULT, /* disabled by default on this chip */ + } no_fbc_reason; +}; + +enum no_psr_reason { + PSR_NO_SOURCE, /* Not supported on platform */ + PSR_NO_SINK, /* Not supported by panel */ + PSR_MODULE_PARAM, + PSR_CRTC_NOT_ACTIVE, + PSR_PWR_WELL_ENABLED, + PSR_NOT_TILED, + PSR_SPRITE_ENABLED, + PSR_S3D_ENABLED, + PSR_INTERLACED_ENABLED, + PSR_HSW_NOT_DDIA, }; enum intel_pch { @@ -722,12 +789,12 @@ struct i915_suspend_saved_registers { }; struct intel_gen6_power_mgmt { + /* work and pm_iir are protected by dev_priv->irq_lock */ struct work_struct work; - struct delayed_work vlv_work; u32 pm_iir; - /* lock - irqsave spinlock that protectects the work_struct and - * pm_iir. */ - spinlock_t lock; + + /* On vlv we need to manually drop to Vmin with a delayed work. */ + struct delayed_work vlv_work; /* The below variables an all the rps hw state are protected by * dev->struct mutext. */ @@ -793,6 +860,18 @@ struct i915_dri1_state { uint32_t counter; }; +struct i915_ums_state { + /** + * Flag if the X Server, and thus DRM, is not currently in + * control of the device. + * + * This is set between LeaveVT and EnterVT. It needs to be + * replaced with a semaphore. It also needs to be + * transitioned away from for kernel modesetting. + */ + int mm_suspended; +}; + struct intel_l3_parity { u32 *remap_info; struct work_struct error_work; @@ -801,8 +880,6 @@ struct intel_l3_parity { struct i915_gem_mm { /** Memory allocator for GTT stolen memory */ struct drm_mm stolen; - /** Memory allocator for GTT */ - struct drm_mm gtt_space; /** List of all objects in gtt_space. Used to restore gtt * mappings on resume */ struct list_head bound_list; @@ -816,37 +893,12 @@ struct i915_gem_mm { /** Usable portion of the GTT for GEM */ unsigned long stolen_base; /* limited to low memory (32-bit) */ - int gtt_mtrr; - /** PPGTT used for aliasing the PPGTT with the GTT */ struct i915_hw_ppgtt *aliasing_ppgtt; struct shrinker inactive_shrinker; bool shrinker_no_lock_stealing; - /** - * List of objects currently involved in rendering. - * - * Includes buffers having the contents of their GPU caches - * flushed, not necessarily primitives. last_rendering_seqno - * 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_rendering_seqno is 0 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; - /** LRU list of objects with fence regs on them. */ struct list_head fence_list; @@ -865,16 +917,6 @@ struct i915_gem_mm { */ bool interruptible; - /** - * Flag if the X Server, and thus DRM, is not currently in - * control of the device. - * - * This is set between LeaveVT and EnterVT. It needs to be - * replaced with a semaphore. It also needs to be - * transitioned away from for kernel modesetting. - */ - int suspended; - /** Bit 6 swizzling required for X tiling */ uint32_t bit_6_swizzle_x; /** Bit 6 swizzling required for Y tiling */ @@ -897,6 +939,11 @@ struct drm_i915_error_state_buf { loff_t pos; }; +struct i915_error_state_file_priv { + struct drm_device *dev; + struct drm_i915_error_state *error; +}; + struct i915_gpu_error { /* For hangcheck timer */ #define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */ @@ -1059,12 +1106,7 @@ typedef struct drm_i915_private { int num_plane; - unsigned long cfb_size; - unsigned int cfb_fb; - enum plane cfb_plane; - int cfb_y; - struct intel_fbc_work *fbc_work; - + struct i915_fbc fbc; struct intel_opregion opregion; struct intel_vbt_data vbt; @@ -1081,8 +1123,6 @@ typedef struct drm_i915_private { } backlight; /* LVDS info */ - struct drm_display_mode *lfp_lvds_vbt_mode; /* if any */ - struct drm_display_mode *sdvo_lvds_vbt_mode; /* if any */ bool no_aux_handshake; struct drm_i915_fence_reg fence_regs[I915_MAX_NUM_FENCES]; /* assume 965 */ @@ -1105,7 +1145,8 @@ typedef struct drm_i915_private { enum modeset_restore modeset_restore; struct mutex modeset_restore_lock; - struct i915_gtt gtt; + struct list_head vm_list; /* Global list of all address spaces */ + struct i915_gtt gtt; /* VMA representing the global address space */ struct i915_gem_mm mm; @@ -1132,6 +1173,9 @@ typedef struct drm_i915_private { struct intel_l3_parity l3_parity; + /* Cannot be determined by PCIID. You must always read a register. */ + size_t ellc_size; + /* gen6+ rps state */ struct intel_gen6_power_mgmt rps; @@ -1142,10 +1186,7 @@ typedef struct drm_i915_private { /* Haswell power well */ struct i915_power_well power_well; - enum no_fbc_reason no_fbc_reason; - - struct drm_mm_node *compressed_fb; - struct drm_mm_node *compressed_llb; + enum no_psr_reason no_psr_reason; struct i915_gpu_error gpu_error; @@ -1173,6 +1214,8 @@ typedef struct drm_i915_private { /* Old dri1 support infrastructure, beware the dragons ya fools entering * here! */ struct i915_dri1_state dri1; + /* Old ums support infrastructure, same warning applies. */ + struct i915_ums_state ums; } drm_i915_private_t; /* Iterate over initialised rings */ @@ -1187,7 +1230,7 @@ enum hdmi_force_audio { HDMI_AUDIO_ON, /* force turn on HDMI audio */ }; -#define I915_GTT_RESERVED ((struct drm_mm_node *)0x1) +#define I915_GTT_OFFSET_NONE ((u32)-1) struct drm_i915_gem_object_ops { /* Interface between the GEM object and its backing storage. @@ -1212,8 +1255,9 @@ struct drm_i915_gem_object { const struct drm_i915_gem_object_ops *ops; - /** Current space allocated to this object in the GTT, if any. */ - struct drm_mm_node *gtt_space; + /** List of VMAs backed by this object */ + struct list_head vma_list; + /** Stolen memory for this object, instead of being backed by shmem. */ struct drm_mm_node *stolen; struct list_head global_list; @@ -1314,13 +1358,6 @@ struct drm_i915_gem_object { unsigned long exec_handle; struct drm_i915_gem_exec_object2 *exec_entry; - /** - * Current offset of the object in GTT space. - * - * This is the same as gtt_space->start - */ - uint32_t gtt_offset; - struct intel_ring_buffer *ring; /** Breadcrumb of last rendering to the buffer. */ @@ -1346,6 +1383,52 @@ struct drm_i915_gem_object { #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base) +/* This is a temporary define to help transition us to real VMAs. If you see + * this, you're either reviewing code, or bisecting it. */ +static inline struct i915_vma * +__i915_gem_obj_to_vma(struct drm_i915_gem_object *obj) +{ + if (list_empty(&obj->vma_list)) + return NULL; + return list_first_entry(&obj->vma_list, struct i915_vma, vma_link); +} + +/* Whether or not this object is currently mapped by the translation tables */ +static inline bool +i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *o) +{ + struct i915_vma *vma = __i915_gem_obj_to_vma(o); + if (vma == NULL) + return false; + return drm_mm_node_allocated(&vma->node); +} + +/* Offset of the first PTE pointing to this object */ +static inline unsigned long +i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o) +{ + BUG_ON(list_empty(&o->vma_list)); + return __i915_gem_obj_to_vma(o)->node.start; +} + +/* The size used in the translation tables may be larger than the actual size of + * the object on GEN2/GEN3 because of the way tiling is handled. See + * i915_gem_get_gtt_size() for more details. + */ +static inline unsigned long +i915_gem_obj_ggtt_size(struct drm_i915_gem_object *o) +{ + BUG_ON(list_empty(&o->vma_list)); + return __i915_gem_obj_to_vma(o)->node.size; +} + +static inline void +i915_gem_obj_ggtt_set_color(struct drm_i915_gem_object *o, + enum i915_cache_level color) +{ + __i915_gem_obj_to_vma(o)->node.color = color; +} + /** * Request queue structure. * @@ -1540,9 +1623,12 @@ extern int i915_enable_rc6 __read_mostly; extern int i915_enable_fbc __read_mostly; extern bool i915_enable_hangcheck __read_mostly; extern int i915_enable_ppgtt __read_mostly; +extern int i915_enable_psr __read_mostly; extern unsigned int i915_preliminary_hw_support __read_mostly; extern int i915_disable_power_well __read_mostly; extern int i915_enable_ips __read_mostly; +extern bool i915_fastboot __read_mostly; +extern bool i915_prefault_disable __read_mostly; extern int i915_suspend(struct drm_device *dev, pm_message_t state); extern int i915_resume(struct drm_device *dev); @@ -1578,6 +1664,7 @@ extern void i915_update_gfx_val(struct drm_i915_private *dev_priv); extern void intel_console_resume(struct work_struct *work); /* i915_irq.c */ +void i915_queue_hangcheck(struct drm_device *dev); void i915_hangcheck_elapsed(unsigned long data); void i915_handle_error(struct drm_device *dev, bool wedged); @@ -1586,21 +1673,12 @@ extern void intel_hpd_init(struct drm_device *dev); extern void intel_gt_init(struct drm_device *dev); extern void intel_gt_sanitize(struct drm_device *dev); -void i915_error_state_free(struct kref *error_ref); - void i915_enable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask); void i915_disable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask); -#ifdef CONFIG_DEBUG_FS -extern void i915_destroy_error_state(struct drm_device *dev); -#else -#define i915_destroy_error_state(x) -#endif - - /* i915_gem.c */ int i915_gem_init_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); @@ -1657,6 +1735,9 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, size_t size); void i915_gem_free_object(struct drm_gem_object *obj); +struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj, + struct i915_address_space *vm); +void i915_gem_vma_destroy(struct i915_vma *vma); int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj, uint32_t alignment, @@ -1827,7 +1908,7 @@ static inline void i915_gem_context_unreference(struct i915_hw_context *ctx) } struct i915_ctx_hang_stats * __must_check -i915_gem_context_get_hang_stats(struct intel_ring_buffer *ring, +i915_gem_context_get_hang_stats(struct drm_device *dev, struct drm_file *file, u32 id); int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, @@ -1911,8 +1992,27 @@ void i915_gem_dump_object(struct drm_i915_gem_object *obj, int len, /* i915_debugfs.c */ int i915_debugfs_init(struct drm_minor *minor); void i915_debugfs_cleanup(struct drm_minor *minor); + +/* i915_gpu_error.c */ __printf(2, 3) void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...); +int i915_error_state_to_str(struct drm_i915_error_state_buf *estr, + const struct i915_error_state_file_priv *error); +int i915_error_state_buf_init(struct drm_i915_error_state_buf *eb, + size_t count, loff_t pos); +static inline void i915_error_state_buf_release( + struct drm_i915_error_state_buf *eb) +{ + kfree(eb->buf); +} +void i915_capture_error_state(struct drm_device *dev); +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_destroy_error_state(struct drm_device *dev); + +void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone); +const char *i915_cache_level_str(int type); /* i915_suspend.c */ extern int i915_save_state(struct drm_device *dev); @@ -1992,7 +2092,6 @@ int i915_reg_read_ioctl(struct drm_device *dev, void *data, struct drm_file *file); /* overlay */ -#ifdef CONFIG_DEBUG_FS extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev); extern void intel_overlay_print_error_state(struct drm_i915_error_state_buf *e, struct intel_overlay_error_state *error); @@ -2001,7 +2100,6 @@ extern struct intel_display_error_state *intel_display_capture_error_state(struc extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e, struct drm_device *dev, struct intel_display_error_state *error); -#endif /* On SNB platform, before reading ring registers forcewake bit * must be set to prevent GT core from power down and stale values being diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index d9e2208..eceab96 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -135,7 +135,7 @@ int i915_mutex_lock_interruptible(struct drm_device *dev) static inline bool i915_gem_object_is_inactive(struct drm_i915_gem_object *obj) { - return obj->gtt_space && !obj->active; + return i915_gem_obj_ggtt_bound(obj) && !obj->active; } int @@ -178,10 +178,10 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, mutex_lock(&dev->struct_mutex); list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) if (obj->pin_count) - pinned += obj->gtt_space->size; + pinned += i915_gem_obj_ggtt_size(obj); mutex_unlock(&dev->struct_mutex); - args->aper_size = dev_priv->gtt.total; + args->aper_size = dev_priv->gtt.base.total; args->aper_available_size = args->aper_size - pinned; return 0; @@ -219,16 +219,10 @@ i915_gem_create(struct drm_file *file, return -ENOMEM; ret = drm_gem_handle_create(file, &obj->base, &handle); - if (ret) { - drm_gem_object_release(&obj->base); - i915_gem_info_remove_obj(dev->dev_private, obj->base.size); - i915_gem_object_free(obj); - return ret; - } - /* drop reference from allocate - handle holds it now */ - drm_gem_object_unreference(&obj->base); - trace_i915_gem_object_create(obj); + drm_gem_object_unreference_unlocked(&obj->base); + if (ret) + return ret; *handle_p = handle; return 0; @@ -422,7 +416,7 @@ i915_gem_shmem_pread(struct drm_device *dev, * anyway again before the next pread happens. */ if (obj->cache_level == I915_CACHE_NONE) needs_clflush = 1; - if (obj->gtt_space) { + if (i915_gem_obj_ggtt_bound(obj)) { ret = i915_gem_object_set_to_gtt_domain(obj, false); if (ret) return ret; @@ -465,7 +459,7 @@ i915_gem_shmem_pread(struct drm_device *dev, mutex_unlock(&dev->struct_mutex); - if (!prefaulted) { + if (likely(!i915_prefault_disable) && !prefaulted) { ret = fault_in_multipages_writeable(user_data, remain); /* Userspace is tricking us, but we've already clobbered * its pages with the prefault and promised to write the @@ -609,7 +603,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, user_data = to_user_ptr(args->data_ptr); remain = args->size; - offset = obj->gtt_offset + args->offset; + offset = i915_gem_obj_ggtt_offset(obj) + args->offset; while (remain > 0) { /* Operation in this page @@ -739,7 +733,7 @@ i915_gem_shmem_pwrite(struct drm_device *dev, * right away and we therefore have to clflush anyway. */ if (obj->cache_level == I915_CACHE_NONE) needs_clflush_after = 1; - if (obj->gtt_space) { + if (i915_gem_obj_ggtt_bound(obj)) { ret = i915_gem_object_set_to_gtt_domain(obj, true); if (ret) return ret; @@ -860,10 +854,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, args->size)) return -EFAULT; - ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr), - args->size); - if (ret) - return -EFAULT; + if (likely(!i915_prefault_disable)) { + ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr), + args->size); + if (ret) + return -EFAULT; + } ret = i915_mutex_lock_interruptible(dev); if (ret) @@ -1360,8 +1356,9 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) obj->fault_mappable = true; - pfn = ((dev_priv->gtt.mappable_base + obj->gtt_offset) >> PAGE_SHIFT) + - page_offset; + pfn = dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj); + pfn >>= PAGE_SHIFT; + pfn += page_offset; /* Finally, remap it using the new GTT offset */ ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn); @@ -1667,7 +1664,7 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj) if (obj->pages == NULL) return 0; - BUG_ON(obj->gtt_space); + BUG_ON(i915_gem_obj_ggtt_bound(obj)); if (obj->pages_pin_count) return -EBUSY; @@ -1691,6 +1688,7 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target, bool purgeable_only) { struct drm_i915_gem_object *obj, *next; + struct i915_address_space *vm = &dev_priv->gtt.base; long count = 0; list_for_each_entry_safe(obj, next, @@ -1704,9 +1702,7 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target, } } - list_for_each_entry_safe(obj, next, - &dev_priv->mm.inactive_list, - mm_list) { + list_for_each_entry_safe(obj, next, &vm->inactive_list, mm_list) { if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) && i915_gem_object_unbind(obj) == 0 && i915_gem_object_put_pages(obj) == 0) { @@ -1877,6 +1873,7 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *vm = &dev_priv->gtt.base; u32 seqno = intel_ring_get_seqno(ring); BUG_ON(ring == NULL); @@ -1893,7 +1890,7 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, } /* Move from whatever list we were on to the tail of execution. */ - list_move_tail(&obj->mm_list, &dev_priv->mm.active_list); + list_move_tail(&obj->mm_list, &vm->active_list); list_move_tail(&obj->ring_list, &ring->active_list); obj->last_read_seqno = seqno; @@ -1917,11 +1914,12 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj) { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *vm = &dev_priv->gtt.base; BUG_ON(obj->base.write_domain & ~I915_GEM_GPU_DOMAINS); BUG_ON(!obj->active); - list_move_tail(&obj->mm_list, &dev_priv->mm.inactive_list); + list_move_tail(&obj->mm_list, &vm->inactive_list); list_del_init(&obj->ring_list); obj->ring = NULL; @@ -2085,11 +2083,9 @@ int __i915_add_request(struct intel_ring_buffer *ring, trace_i915_gem_request_add(ring, request->seqno); ring->outstanding_lazy_request = 0; - if (!dev_priv->mm.suspended) { - if (i915_enable_hangcheck) { - mod_timer(&dev_priv->gpu_error.hangcheck_timer, - round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES)); - } + if (!dev_priv->ums.mm_suspended) { + i915_queue_hangcheck(ring->dev); + if (was_empty) { queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, @@ -2121,8 +2117,8 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request) static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj) { - if (acthd >= obj->gtt_offset && - acthd < obj->gtt_offset + obj->base.size) + if (acthd >= i915_gem_obj_ggtt_offset(obj) && + acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size) return true; return false; @@ -2180,11 +2176,11 @@ static void i915_set_reset_status(struct intel_ring_buffer *ring, if (ring->hangcheck.action != wait && i915_request_guilty(request, acthd, &inside)) { - DRM_ERROR("%s hung %s bo (0x%x ctx %d) at 0x%x\n", + DRM_ERROR("%s hung %s bo (0x%lx ctx %d) at 0x%x\n", ring->name, inside ? "inside" : "flushing", request->batch_obj ? - request->batch_obj->gtt_offset : 0, + i915_gem_obj_ggtt_offset(request->batch_obj) : 0, request->ctx ? request->ctx->id : 0, acthd); @@ -2275,6 +2271,7 @@ void i915_gem_restore_fences(struct drm_device *dev) void i915_gem_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *vm = &dev_priv->gtt.base; struct drm_i915_gem_object *obj; struct intel_ring_buffer *ring; int i; @@ -2285,12 +2282,8 @@ void i915_gem_reset(struct drm_device *dev) /* Move everything out of the GPU domains to ensure we do any * necessary invalidation upon reuse. */ - list_for_each_entry(obj, - &dev_priv->mm.inactive_list, - mm_list) - { + list_for_each_entry(obj, &vm->inactive_list, mm_list) obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS; - } i915_gem_restore_fences(dev); } @@ -2400,7 +2393,7 @@ i915_gem_retire_work_handler(struct work_struct *work) idle &= list_empty(&ring->request_list); } - if (!dev_priv->mm.suspended && !idle) + if (!dev_priv->ums.mm_suspended && !idle) queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, round_jiffies_up_relative(HZ)); if (idle) @@ -2593,9 +2586,10 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj) { drm_i915_private_t *dev_priv = obj->base.dev->dev_private; + struct i915_vma *vma; int ret; - if (obj->gtt_space == NULL) + if (!i915_gem_obj_ggtt_bound(obj)) return 0; if (obj->pin_count) @@ -2630,13 +2624,20 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj) i915_gem_object_unpin_pages(obj); list_del(&obj->mm_list); - list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list); /* Avoid an unnecessary call to unbind on rebind. */ obj->map_and_fenceable = true; - drm_mm_put_block(obj->gtt_space); - obj->gtt_space = NULL; - obj->gtt_offset = 0; + vma = __i915_gem_obj_to_vma(obj); + list_del(&vma->vma_link); + drm_mm_remove_node(&vma->node); + i915_gem_vma_destroy(vma); + + /* Since the unbound list is global, only move to that list if + * no more VMAs exist. + * NB: Until we have real VMAs there will only ever be one */ + WARN_ON(!list_empty(&obj->vma_list)); + if (list_empty(&obj->vma_list)) + list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list); return 0; } @@ -2691,12 +2692,12 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, POSTING_READ(fence_reg); if (obj) { - u32 size = obj->gtt_space->size; + u32 size = i915_gem_obj_ggtt_size(obj); uint64_t val; - val = (uint64_t)((obj->gtt_offset + size - 4096) & + val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) & 0xfffff000) << 32; - val |= obj->gtt_offset & 0xfffff000; + val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000; val |= (uint64_t)((obj->stride / 128) - 1) << fence_pitch_shift; if (obj->tiling_mode == I915_TILING_Y) val |= 1 << I965_FENCE_TILING_Y_SHIFT; @@ -2720,15 +2721,15 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg, u32 val; if (obj) { - u32 size = obj->gtt_space->size; + u32 size = i915_gem_obj_ggtt_size(obj); int pitch_val; int tile_width; - WARN((obj->gtt_offset & ~I915_FENCE_START_MASK) || + WARN((i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK) || (size & -size) != size || - (obj->gtt_offset & (size - 1)), - "object 0x%08x [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n", - obj->gtt_offset, obj->map_and_fenceable, size); + (i915_gem_obj_ggtt_offset(obj) & (size - 1)), + "object 0x%08lx [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n", + i915_gem_obj_ggtt_offset(obj), obj->map_and_fenceable, size); if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev)) tile_width = 128; @@ -2739,7 +2740,7 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg, pitch_val = obj->stride / tile_width; pitch_val = ffs(pitch_val) - 1; - val = obj->gtt_offset; + val = i915_gem_obj_ggtt_offset(obj); if (obj->tiling_mode == I915_TILING_Y) val |= 1 << I830_FENCE_TILING_Y_SHIFT; val |= I915_FENCE_SIZE_BITS(size); @@ -2764,19 +2765,19 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg, uint32_t val; if (obj) { - u32 size = obj->gtt_space->size; + u32 size = i915_gem_obj_ggtt_size(obj); uint32_t pitch_val; - WARN((obj->gtt_offset & ~I830_FENCE_START_MASK) || + WARN((i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK) || (size & -size) != size || - (obj->gtt_offset & (size - 1)), - "object 0x%08x not 512K or pot-size 0x%08x aligned\n", - obj->gtt_offset, size); + (i915_gem_obj_ggtt_offset(obj) & (size - 1)), + "object 0x%08lx not 512K or pot-size 0x%08x aligned\n", + i915_gem_obj_ggtt_offset(obj), size); pitch_val = obj->stride / 128; pitch_val = ffs(pitch_val) - 1; - val = obj->gtt_offset; + val = i915_gem_obj_ggtt_offset(obj); if (obj->tiling_mode == I915_TILING_Y) val |= 1 << I830_FENCE_TILING_Y_SHIFT; val |= I830_FENCE_SIZE_BITS(size); @@ -2997,7 +2998,7 @@ static bool i915_gem_valid_gtt_space(struct drm_device *dev, if (HAS_LLC(dev)) return true; - if (gtt_space == NULL) + if (!drm_mm_node_allocated(gtt_space)) return true; if (list_empty(>t_space->node_list)) @@ -3030,8 +3031,8 @@ static void i915_gem_verify_gtt(struct drm_device *dev) if (obj->cache_level != obj->gtt_space->color) { printk(KERN_ERR "object reserved space [%08lx, %08lx] with wrong color, cache_level=%x, color=%lx\n", - obj->gtt_space->start, - obj->gtt_space->start + obj->gtt_space->size, + i915_gem_obj_ggtt_offset(obj), + i915_gem_obj_ggtt_offset(obj) + i915_gem_obj_ggtt_size(obj), obj->cache_level, obj->gtt_space->color); err++; @@ -3042,8 +3043,8 @@ static void i915_gem_verify_gtt(struct drm_device *dev) obj->gtt_space, obj->cache_level)) { printk(KERN_ERR "invalid GTT space found at [%08lx, %08lx] - color=%x\n", - obj->gtt_space->start, - obj->gtt_space->start + obj->gtt_space->size, + i915_gem_obj_ggtt_offset(obj), + i915_gem_obj_ggtt_offset(obj) + i915_gem_obj_ggtt_size(obj), obj->cache_level); err++; continue; @@ -3065,13 +3066,17 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; drm_i915_private_t *dev_priv = dev->dev_private; - struct drm_mm_node *node; + struct i915_address_space *vm = &dev_priv->gtt.base; u32 size, fence_size, fence_alignment, unfenced_alignment; bool mappable, fenceable; size_t gtt_max = map_and_fenceable ? - dev_priv->gtt.mappable_end : dev_priv->gtt.total; + dev_priv->gtt.mappable_end : dev_priv->gtt.base.total; + struct i915_vma *vma; int ret; + if (WARN_ON(!list_empty(&obj->vma_list))) + return -EBUSY; + fence_size = i915_gem_get_gtt_size(dev, obj->base.size, obj->tiling_mode); @@ -3110,14 +3115,15 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, i915_gem_object_pin_pages(obj); - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (node == NULL) { - i915_gem_object_unpin_pages(obj); - return -ENOMEM; + vma = i915_gem_vma_create(obj, &dev_priv->gtt.base); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err_unpin; } search_free: - ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node, + ret = drm_mm_insert_node_in_range_generic(&dev_priv->gtt.base.mm, + &vma->node, size, alignment, obj->cache_level, 0, gtt_max); if (ret) { @@ -3128,41 +3134,42 @@ search_free: if (ret == 0) goto search_free; - i915_gem_object_unpin_pages(obj); - kfree(node); - return ret; + goto err_free_vma; } - if (WARN_ON(!i915_gem_valid_gtt_space(dev, node, obj->cache_level))) { - i915_gem_object_unpin_pages(obj); - drm_mm_put_block(node); - return -EINVAL; + if (WARN_ON(!i915_gem_valid_gtt_space(dev, &vma->node, + obj->cache_level))) { + ret = -EINVAL; + goto err_remove_node; } ret = i915_gem_gtt_prepare_object(obj); - if (ret) { - i915_gem_object_unpin_pages(obj); - drm_mm_put_block(node); - return ret; - } + if (ret) + goto err_remove_node; list_move_tail(&obj->global_list, &dev_priv->mm.bound_list); - list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list); - - obj->gtt_space = node; - obj->gtt_offset = node->start; + list_add_tail(&obj->mm_list, &vm->inactive_list); + list_add(&vma->vma_link, &obj->vma_list); fenceable = - node->size == fence_size && - (node->start & (fence_alignment - 1)) == 0; + i915_gem_obj_ggtt_size(obj) == fence_size && + (i915_gem_obj_ggtt_offset(obj) & (fence_alignment - 1)) == 0; - mappable = - obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end; + mappable = i915_gem_obj_ggtt_offset(obj) + obj->base.size <= + dev_priv->gtt.mappable_end; obj->map_and_fenceable = mappable && fenceable; trace_i915_gem_object_bind(obj, map_and_fenceable); i915_gem_verify_gtt(dev); return 0; + +err_remove_node: + drm_mm_remove_node(&vma->node); +err_free_vma: + i915_gem_vma_destroy(vma); +err_unpin: + i915_gem_object_unpin_pages(obj); + return ret; } void @@ -3258,7 +3265,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) int ret; /* Not valid to be called on unbound objects. */ - if (obj->gtt_space == NULL) + if (!i915_gem_obj_ggtt_bound(obj)) return -EINVAL; if (obj->base.write_domain == I915_GEM_DOMAIN_GTT) @@ -3297,7 +3304,8 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) /* And bump the LRU for this access */ if (i915_gem_object_is_inactive(obj)) - list_move_tail(&obj->mm_list, &dev_priv->mm.inactive_list); + list_move_tail(&obj->mm_list, + &dev_priv->gtt.base.inactive_list); return 0; } @@ -3307,6 +3315,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; drm_i915_private_t *dev_priv = dev->dev_private; + struct i915_vma *vma = __i915_gem_obj_to_vma(obj); int ret; if (obj->cache_level == cache_level) @@ -3317,13 +3326,13 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, return -EBUSY; } - if (!i915_gem_valid_gtt_space(dev, obj->gtt_space, cache_level)) { + if (vma && !i915_gem_valid_gtt_space(dev, &vma->node, cache_level)) { ret = i915_gem_object_unbind(obj); if (ret) return ret; } - if (obj->gtt_space) { + if (i915_gem_obj_ggtt_bound(obj)) { ret = i915_gem_object_finish_gpu(obj); if (ret) return ret; @@ -3346,7 +3355,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt, obj, cache_level); - obj->gtt_space->color = cache_level; + i915_gem_obj_ggtt_set_color(obj, cache_level); } if (cache_level == I915_CACHE_NONE) { @@ -3627,14 +3636,14 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj, if (WARN_ON(obj->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT)) return -EBUSY; - if (obj->gtt_space != NULL) { - if ((alignment && obj->gtt_offset & (alignment - 1)) || + if (i915_gem_obj_ggtt_bound(obj)) { + if ((alignment && i915_gem_obj_ggtt_offset(obj) & (alignment - 1)) || (map_and_fenceable && !obj->map_and_fenceable)) { WARN(obj->pin_count, "bo is already pinned with incorrect alignment:" - " offset=%x, req.alignment=%x, req.map_and_fenceable=%d," + " offset=%lx, req.alignment=%x, req.map_and_fenceable=%d," " obj->map_and_fenceable=%d\n", - obj->gtt_offset, alignment, + i915_gem_obj_ggtt_offset(obj), alignment, map_and_fenceable, obj->map_and_fenceable); ret = i915_gem_object_unbind(obj); @@ -3643,7 +3652,7 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj, } } - if (obj->gtt_space == NULL) { + if (!i915_gem_obj_ggtt_bound(obj)) { struct drm_i915_private *dev_priv = obj->base.dev->dev_private; ret = i915_gem_object_bind_to_gtt(obj, alignment, @@ -3669,7 +3678,7 @@ void i915_gem_object_unpin(struct drm_i915_gem_object *obj) { BUG_ON(obj->pin_count == 0); - BUG_ON(obj->gtt_space == NULL); + BUG_ON(!i915_gem_obj_ggtt_bound(obj)); if (--obj->pin_count == 0) obj->pin_mappable = false; @@ -3719,7 +3728,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data, * as the X server doesn't manage domains yet */ i915_gem_object_flush_cpu_write_domain(obj); - args->offset = obj->gtt_offset; + args->offset = i915_gem_obj_ggtt_offset(obj); out: drm_gem_object_unreference(&obj->base); unlock: @@ -3862,6 +3871,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, INIT_LIST_HEAD(&obj->global_list); INIT_LIST_HEAD(&obj->ring_list); INIT_LIST_HEAD(&obj->exec_list); + INIT_LIST_HEAD(&obj->vma_list); obj->ops = ops; @@ -3926,6 +3936,8 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, } else obj->cache_level = I915_CACHE_NONE; + trace_i915_gem_object_create(obj); + return obj; } @@ -3982,15 +3994,33 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) i915_gem_object_free(obj); } +struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj, + struct i915_address_space *vm) +{ + struct i915_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL); + if (vma == NULL) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&vma->vma_link); + vma->vm = vm; + vma->obj = obj; + + return vma; +} + +void i915_gem_vma_destroy(struct i915_vma *vma) +{ + WARN_ON(vma->node.allocated); + kfree(vma); +} + int i915_gem_idle(struct drm_device *dev) { drm_i915_private_t *dev_priv = dev->dev_private; int ret; - mutex_lock(&dev->struct_mutex); - - if (dev_priv->mm.suspended) { + if (dev_priv->ums.mm_suspended) { mutex_unlock(&dev->struct_mutex); return 0; } @@ -4006,18 +4036,11 @@ i915_gem_idle(struct drm_device *dev) if (!drm_core_check_feature(dev, DRIVER_MODESET)) i915_gem_evict_everything(dev); - /* Hack! Don't let anybody do execbuf while we don't control the chip. - * We need to replace this with a semaphore, or something. - * And not confound mm.suspended! - */ - dev_priv->mm.suspended = 1; del_timer_sync(&dev_priv->gpu_error.hangcheck_timer); i915_kernel_lost_context(dev); i915_gem_cleanup_ringbuffer(dev); - mutex_unlock(&dev->struct_mutex); - /* Cancel the retire work handler, which should be idle now. */ cancel_delayed_work_sync(&dev_priv->mm.retire_work); @@ -4150,8 +4173,8 @@ i915_gem_init_hw(struct drm_device *dev) if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt()) return -EIO; - if (IS_HASWELL(dev) && (I915_READ(0x120010) == 1)) - I915_WRITE(0x9008, I915_READ(0x9008) | 0xf0000); + if (dev_priv->ellc_size) + I915_WRITE(HSW_IDICR, I915_READ(HSW_IDICR) | IDIHASHMSK(0xf)); if (HAS_PCH_NOP(dev)) { u32 temp = I915_READ(GEN7_MSG_CTL); @@ -4227,7 +4250,7 @@ int i915_gem_entervt_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = dev->dev_private; int ret; if (drm_core_check_feature(dev, DRIVER_MODESET)) @@ -4239,7 +4262,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, } mutex_lock(&dev->struct_mutex); - dev_priv->mm.suspended = 0; + dev_priv->ums.mm_suspended = 0; ret = i915_gem_init_hw(dev); if (ret != 0) { @@ -4247,7 +4270,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, return ret; } - BUG_ON(!list_empty(&dev_priv->mm.active_list)); + BUG_ON(!list_empty(&dev_priv->gtt.base.active_list)); mutex_unlock(&dev->struct_mutex); ret = drm_irq_install(dev); @@ -4259,7 +4282,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, cleanup_ringbuffer: mutex_lock(&dev->struct_mutex); i915_gem_cleanup_ringbuffer(dev); - dev_priv->mm.suspended = 1; + dev_priv->ums.mm_suspended = 1; mutex_unlock(&dev->struct_mutex); return ret; @@ -4269,11 +4292,26 @@ int i915_gem_leavevt_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct drm_i915_private *dev_priv = dev->dev_private; + int ret; + if (drm_core_check_feature(dev, DRIVER_MODESET)) return 0; drm_irq_uninstall(dev); - return i915_gem_idle(dev); + + mutex_lock(&dev->struct_mutex); + ret = i915_gem_idle(dev); + + /* Hack! Don't let anybody do execbuf while we don't control the chip. + * We need to replace this with a semaphore, or something. + * And not confound ums.mm_suspended! + */ + if (ret != 0) + dev_priv->ums.mm_suspended = 1; + mutex_unlock(&dev->struct_mutex); + + return ret; } void @@ -4284,9 +4322,11 @@ i915_gem_lastclose(struct drm_device *dev) if (drm_core_check_feature(dev, DRIVER_MODESET)) return; + mutex_lock(&dev->struct_mutex); ret = i915_gem_idle(dev); if (ret) DRM_ERROR("failed to idle hardware: %d\n", ret); + mutex_unlock(&dev->struct_mutex); } static void @@ -4308,8 +4348,8 @@ i915_gem_load(struct drm_device *dev) SLAB_HWCACHE_ALIGN, NULL); - INIT_LIST_HEAD(&dev_priv->mm.active_list); - INIT_LIST_HEAD(&dev_priv->mm.inactive_list); + INIT_LIST_HEAD(&dev_priv->gtt.base.active_list); + INIT_LIST_HEAD(&dev_priv->gtt.base.inactive_list); INIT_LIST_HEAD(&dev_priv->mm.unbound_list); INIT_LIST_HEAD(&dev_priv->mm.bound_list); INIT_LIST_HEAD(&dev_priv->mm.fence_list); @@ -4580,6 +4620,7 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) struct drm_i915_private, mm.inactive_shrinker); struct drm_device *dev = dev_priv->dev; + struct i915_address_space *vm = &dev_priv->gtt.base; struct drm_i915_gem_object *obj; int nr_to_scan = sc->nr_to_scan; bool unlock = true; @@ -4608,7 +4649,7 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) if (obj->pages_pin_count == 0) cnt += obj->base.size >> PAGE_SHIFT; - list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list) + list_for_each_entry(obj, &vm->inactive_list, mm_list) if (obj->pin_count == 0 && obj->pages_pin_count == 0) cnt += obj->base.size >> PAGE_SHIFT; diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 51b7a21..2470206 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -304,31 +304,24 @@ static int context_idr_cleanup(int id, void *p, void *data) } struct i915_ctx_hang_stats * -i915_gem_context_get_hang_stats(struct intel_ring_buffer *ring, +i915_gem_context_get_hang_stats(struct drm_device *dev, struct drm_file *file, u32 id) { - struct drm_i915_private *dev_priv = ring->dev->dev_private; + struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_file_private *file_priv = file->driver_priv; - struct i915_hw_context *to; - - if (dev_priv->hw_contexts_disabled) - return ERR_PTR(-ENOENT); - - if (ring->id != RCS) - return ERR_PTR(-EINVAL); - - if (file == NULL) - return ERR_PTR(-EINVAL); + struct i915_hw_context *ctx; if (id == DEFAULT_CONTEXT_ID) return &file_priv->hang_stats; - to = i915_gem_context_get(file->driver_priv, id); - if (to == NULL) + ctx = NULL; + if (!dev_priv->hw_contexts_disabled) + ctx = i915_gem_context_get(file->driver_priv, id); + if (ctx == NULL) return ERR_PTR(-ENOENT); - return &to->hang_stats; + return &ctx->hang_stats; } void i915_gem_context_close(struct drm_device *dev, struct drm_file *file) @@ -377,7 +370,7 @@ mi_set_context(struct intel_ring_buffer *ring, intel_ring_emit(ring, MI_NOOP); intel_ring_emit(ring, MI_SET_CONTEXT); - intel_ring_emit(ring, new_context->obj->gtt_offset | + intel_ring_emit(ring, i915_gem_obj_ggtt_offset(new_context->obj) | MI_MM_SPACE_GTT | MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN | diff --git a/drivers/gpu/drm/i915/i915_gem_debug.c b/drivers/gpu/drm/i915/i915_gem_debug.c index 582e6a5..bf945a3 100644 --- a/drivers/gpu/drm/i915/i915_gem_debug.c +++ b/drivers/gpu/drm/i915/i915_gem_debug.c @@ -97,7 +97,7 @@ i915_verify_lists(struct drm_device *dev) } } - list_for_each_entry(obj, &dev_priv->mm.inactive_list, list) { + list_for_each_entry(obj, &i915_gtt_vm->inactive_list, list) { if (obj->base.dev != dev || !atomic_read(&obj->base.refcount.refcount)) { DRM_ERROR("freed inactive %p\n", obj); diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index c86d5d9..df61f33 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -34,11 +34,13 @@ static bool mark_free(struct drm_i915_gem_object *obj, struct list_head *unwind) { + struct i915_vma *vma = __i915_gem_obj_to_vma(obj); + if (obj->pin_count) return false; list_add(&obj->exec_list, unwind); - return drm_mm_scan_add_block(obj->gtt_space); + return drm_mm_scan_add_block(&vma->node); } int @@ -47,7 +49,9 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, bool mappable, bool nonblocking) { drm_i915_private_t *dev_priv = dev->dev_private; + struct i915_address_space *vm = &dev_priv->gtt.base; struct list_head eviction_list, unwind_list; + struct i915_vma *vma; struct drm_i915_gem_object *obj; int ret = 0; @@ -78,15 +82,14 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, INIT_LIST_HEAD(&unwind_list); if (mappable) - drm_mm_init_scan_with_range(&dev_priv->mm.gtt_space, - min_size, alignment, cache_level, - 0, dev_priv->gtt.mappable_end); + drm_mm_init_scan_with_range(&vm->mm, min_size, + alignment, cache_level, 0, + dev_priv->gtt.mappable_end); else - drm_mm_init_scan(&dev_priv->mm.gtt_space, - min_size, alignment, cache_level); + drm_mm_init_scan(&vm->mm, min_size, alignment, cache_level); /* First see if there is a large enough contiguous idle region... */ - list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list) { + list_for_each_entry(obj, &vm->inactive_list, mm_list) { if (mark_free(obj, &unwind_list)) goto found; } @@ -95,7 +98,7 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, goto none; /* Now merge in the soon-to-be-expired objects... */ - list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) { + list_for_each_entry(obj, &vm->active_list, mm_list) { if (mark_free(obj, &unwind_list)) goto found; } @@ -106,8 +109,8 @@ none: obj = list_first_entry(&unwind_list, struct drm_i915_gem_object, exec_list); - - ret = drm_mm_scan_remove_block(obj->gtt_space); + vma = __i915_gem_obj_to_vma(obj); + ret = drm_mm_scan_remove_block(&vma->node); BUG_ON(ret); list_del_init(&obj->exec_list); @@ -127,7 +130,8 @@ found: obj = list_first_entry(&unwind_list, struct drm_i915_gem_object, exec_list); - if (drm_mm_scan_remove_block(obj->gtt_space)) { + vma = __i915_gem_obj_to_vma(obj); + if (drm_mm_scan_remove_block(&vma->node)) { list_move(&obj->exec_list, &eviction_list); drm_gem_object_reference(&obj->base); continue; @@ -154,12 +158,13 @@ int i915_gem_evict_everything(struct drm_device *dev) { drm_i915_private_t *dev_priv = dev->dev_private; + struct i915_address_space *vm = &dev_priv->gtt.base; struct drm_i915_gem_object *obj, *next; bool lists_empty; int ret; - lists_empty = (list_empty(&dev_priv->mm.inactive_list) && - list_empty(&dev_priv->mm.active_list)); + lists_empty = (list_empty(&vm->inactive_list) && + list_empty(&vm->active_list)); if (lists_empty) return -ENOSPC; @@ -176,8 +181,7 @@ i915_gem_evict_everything(struct drm_device *dev) i915_gem_retire_requests(dev); /* Having flushed everything, unbind() should never raise an error */ - list_for_each_entry_safe(obj, next, - &dev_priv->mm.inactive_list, mm_list) + list_for_each_entry_safe(obj, next, &vm->inactive_list, mm_list) if (obj->pin_count == 0) WARN_ON(i915_gem_object_unbind(obj)); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 87a3227..1734825 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -188,7 +188,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, return -ENOENT; target_i915_obj = to_intel_bo(target_obj); - target_offset = target_i915_obj->gtt_offset; + target_offset = i915_gem_obj_ggtt_offset(target_i915_obj); /* Sandybridge PPGTT errata: We need a global gtt mapping for MI and * pipe_control writes because the gpu doesn't properly redirect them @@ -280,7 +280,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, return ret; /* Map the page containing the relocation we're going to perform. */ - reloc->offset += obj->gtt_offset; + reloc->offset += i915_gem_obj_ggtt_offset(obj); reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable, reloc->offset & PAGE_MASK); reloc_entry = (uint32_t __iomem *) @@ -436,8 +436,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, obj->has_aliasing_ppgtt_mapping = 1; } - if (entry->offset != obj->gtt_offset) { - entry->offset = obj->gtt_offset; + if (entry->offset != i915_gem_obj_ggtt_offset(obj)) { + entry->offset = i915_gem_obj_ggtt_offset(obj); *need_reloc = true; } @@ -458,7 +458,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj) { struct drm_i915_gem_exec_object2 *entry; - if (!obj->gtt_space) + if (!i915_gem_obj_ggtt_bound(obj)) return; entry = obj->exec_entry; @@ -530,7 +530,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; bool need_fence, need_mappable; - if (!obj->gtt_space) + if (!i915_gem_obj_ggtt_bound(obj)) continue; need_fence = @@ -539,7 +539,8 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, obj->tiling_mode != I915_TILING_NONE; need_mappable = need_fence || need_reloc_mappable(obj); - if ((entry->alignment && obj->gtt_offset & (entry->alignment - 1)) || + if ((entry->alignment && + i915_gem_obj_ggtt_offset(obj) & (entry->alignment - 1)) || (need_mappable && !obj->map_and_fenceable)) ret = i915_gem_object_unbind(obj); else @@ -550,7 +551,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, /* Bind fresh objects */ list_for_each_entry(obj, objects, exec_list) { - if (obj->gtt_space) + if (i915_gem_obj_ggtt_bound(obj)) continue; ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs); @@ -758,8 +759,10 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec, if (!access_ok(VERIFY_WRITE, ptr, length)) return -EFAULT; - if (fault_in_multipages_readable(ptr, length)) - return -EFAULT; + if (likely(!i915_prefault_disable)) { + if (fault_in_multipages_readable(ptr, length)) + return -EFAULT; + } } return 0; @@ -872,7 +875,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, break; case I915_EXEC_BSD: ring = &dev_priv->ring[VCS]; - if (ctx_id != 0) { + if (ctx_id != DEFAULT_CONTEXT_ID) { DRM_DEBUG("Ring %s doesn't support contexts\n", ring->name); return -EPERM; @@ -880,7 +883,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, break; case I915_EXEC_BLT: ring = &dev_priv->ring[BCS]; - if (ctx_id != 0) { + if (ctx_id != DEFAULT_CONTEXT_ID) { DRM_DEBUG("Ring %s doesn't support contexts\n", ring->name); return -EPERM; @@ -888,7 +891,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, break; case I915_EXEC_VEBOX: ring = &dev_priv->ring[VECS]; - if (ctx_id != 0) { + if (ctx_id != DEFAULT_CONTEXT_ID) { DRM_DEBUG("Ring %s doesn't support contexts\n", ring->name); return -EPERM; @@ -972,7 +975,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, if (ret) goto pre_mutex_err; - if (dev_priv->mm.suspended) { + if (dev_priv->ums.mm_suspended) { mutex_unlock(&dev->struct_mutex); ret = -EBUSY; goto pre_mutex_err; @@ -1058,7 +1061,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto err; } - exec_start = batch_obj->gtt_offset + args->batch_start_offset; + exec_start = i915_gem_obj_ggtt_offset(batch_obj) + args->batch_start_offset; exec_len = args->batch_len; if (cliprects) { for (i = 0; i < args->num_cliprects; i++) { diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 5101ab6..3b639a9 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -28,8 +28,12 @@ #include "i915_trace.h" #include "intel_drv.h" +#define GEN6_PPGTT_PD_ENTRIES 512 +#define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t)) + /* PPGTT stuff */ #define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0)) +#define HSW_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0x7f0)) #define GEN6_PDE_VALID (1 << 0) /* gen6+ has bit 11-4 for physical addr bit 39-32 */ @@ -41,9 +45,17 @@ #define GEN6_PTE_CACHE_LLC (2 << 1) #define GEN6_PTE_CACHE_LLC_MLC (3 << 1) #define GEN6_PTE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) +#define HSW_PTE_ADDR_ENCODE(addr) HSW_GTT_ADDR_ENCODE(addr) + +/* 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_AGE0 HSW_CACHEABILITY_CONTROL(0x3) +#define HSW_WB_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0xb) -static gen6_gtt_pte_t gen6_pte_encode(struct drm_device *dev, - dma_addr_t addr, +static gen6_gtt_pte_t gen6_pte_encode(dma_addr_t addr, enum i915_cache_level level) { gen6_gtt_pte_t pte = GEN6_PTE_VALID; @@ -69,8 +81,7 @@ static gen6_gtt_pte_t gen6_pte_encode(struct drm_device *dev, #define BYT_PTE_WRITEABLE (1 << 1) #define BYT_PTE_SNOOPED_BY_CPU_CACHES (1 << 2) -static gen6_gtt_pte_t byt_pte_encode(struct drm_device *dev, - dma_addr_t addr, +static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr, enum i915_cache_level level) { gen6_gtt_pte_t pte = GEN6_PTE_VALID; @@ -87,22 +98,33 @@ static gen6_gtt_pte_t byt_pte_encode(struct drm_device *dev, return pte; } -static gen6_gtt_pte_t hsw_pte_encode(struct drm_device *dev, - dma_addr_t addr, +static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr, enum i915_cache_level level) { gen6_gtt_pte_t pte = GEN6_PTE_VALID; - pte |= GEN6_PTE_ADDR_ENCODE(addr); + pte |= HSW_PTE_ADDR_ENCODE(addr); if (level != I915_CACHE_NONE) - pte |= GEN6_PTE_CACHE_LLC; + pte |= HSW_WB_LLC_AGE0; + + return pte; +} + +static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr, + enum i915_cache_level level) +{ + gen6_gtt_pte_t pte = GEN6_PTE_VALID; + pte |= HSW_PTE_ADDR_ENCODE(addr); + + if (level != I915_CACHE_NONE) + pte |= HSW_WB_ELLC_LLC_AGE0; return pte; } static void gen6_write_pdes(struct i915_hw_ppgtt *ppgtt) { - struct drm_i915_private *dev_priv = ppgtt->dev->dev_private; + struct drm_i915_private *dev_priv = ppgtt->base.dev->dev_private; gen6_gtt_pte_t __iomem *pd_addr; uint32_t pd_entry; int i; @@ -181,18 +203,18 @@ static int gen6_ppgtt_enable(struct drm_device *dev) } /* PPGTT support for Sandybdrige/Gen6 and later */ -static void gen6_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt, +static void gen6_ppgtt_clear_range(struct i915_address_space *vm, unsigned first_entry, unsigned num_entries) { + struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); gen6_gtt_pte_t *pt_vaddr, scratch_pte; unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES; unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES; unsigned last_pte, i; - scratch_pte = ppgtt->pte_encode(ppgtt->dev, - ppgtt->scratch_page_dma_addr, - I915_CACHE_LLC); + scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC); while (num_entries) { last_pte = first_pte + num_entries; @@ -212,11 +234,13 @@ static void gen6_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt, } } -static void gen6_ppgtt_insert_entries(struct i915_hw_ppgtt *ppgtt, +static void gen6_ppgtt_insert_entries(struct i915_address_space *vm, struct sg_table *pages, unsigned first_entry, 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 act_pt = first_entry / I915_PPGTT_PT_ENTRIES; unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES; @@ -227,8 +251,7 @@ static void gen6_ppgtt_insert_entries(struct i915_hw_ppgtt *ppgtt, dma_addr_t page_addr; page_addr = sg_page_iter_dma_address(&sg_iter); - pt_vaddr[act_pte] = ppgtt->pte_encode(ppgtt->dev, page_addr, - cache_level); + pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level); if (++act_pte == I915_PPGTT_PT_ENTRIES) { kunmap_atomic(pt_vaddr); act_pt++; @@ -240,13 +263,17 @@ static void gen6_ppgtt_insert_entries(struct i915_hw_ppgtt *ppgtt, kunmap_atomic(pt_vaddr); } -static void gen6_ppgtt_cleanup(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); int i; + drm_mm_takedown(&ppgtt->base.mm); + if (ppgtt->pt_dma_addr) { for (i = 0; i < ppgtt->num_pd_entries; i++) - pci_unmap_page(ppgtt->dev->pdev, + pci_unmap_page(ppgtt->base.dev->pdev, ppgtt->pt_dma_addr[i], 4096, PCI_DMA_BIDIRECTIONAL); } @@ -260,7 +287,7 @@ static void gen6_ppgtt_cleanup(struct i915_hw_ppgtt *ppgtt) static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) { - struct drm_device *dev = ppgtt->dev; + struct drm_device *dev = ppgtt->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; unsigned first_pd_entry_in_global_pt; int i; @@ -272,17 +299,18 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) first_pd_entry_in_global_pt = gtt_total_entries(dev_priv->gtt); if (IS_HASWELL(dev)) { - ppgtt->pte_encode = hsw_pte_encode; + ppgtt->base.pte_encode = hsw_pte_encode; } else if (IS_VALLEYVIEW(dev)) { - ppgtt->pte_encode = byt_pte_encode; + ppgtt->base.pte_encode = byt_pte_encode; } else { - ppgtt->pte_encode = gen6_pte_encode; + ppgtt->base.pte_encode = gen6_pte_encode; } - ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES; + ppgtt->num_pd_entries = GEN6_PPGTT_PD_ENTRIES; ppgtt->enable = gen6_ppgtt_enable; - ppgtt->clear_range = gen6_ppgtt_clear_range; - ppgtt->insert_entries = gen6_ppgtt_insert_entries; - ppgtt->cleanup = gen6_ppgtt_cleanup; + 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->pt_pages = kzalloc(sizeof(struct page *)*ppgtt->num_pd_entries, GFP_KERNEL); if (!ppgtt->pt_pages) @@ -313,8 +341,8 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) ppgtt->pt_dma_addr[i] = pt_addr; } - ppgtt->clear_range(ppgtt, 0, - ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES); + ppgtt->base.clear_range(&ppgtt->base, 0, + ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES); ppgtt->pd_offset = first_pd_entry_in_global_pt * sizeof(gen6_gtt_pte_t); @@ -347,8 +375,7 @@ static int i915_gem_init_aliasing_ppgtt(struct drm_device *dev) if (!ppgtt) return -ENOMEM; - ppgtt->dev = dev; - ppgtt->scratch_page_dma_addr = dev_priv->gtt.scratch_page_dma; + ppgtt->base.dev = dev; if (INTEL_INFO(dev)->gen < 8) ret = gen6_ppgtt_init(ppgtt); @@ -357,8 +384,11 @@ static int i915_gem_init_aliasing_ppgtt(struct drm_device *dev) if (ret) kfree(ppgtt); - else + else { dev_priv->mm.aliasing_ppgtt = ppgtt; + drm_mm_init(&ppgtt->base.mm, ppgtt->base.start, + ppgtt->base.total); + } return ret; } @@ -371,7 +401,7 @@ void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev) if (!ppgtt) return; - ppgtt->cleanup(ppgtt); + ppgtt->base.cleanup(&ppgtt->base); dev_priv->mm.aliasing_ppgtt = NULL; } @@ -379,17 +409,17 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt, struct drm_i915_gem_object *obj, enum i915_cache_level cache_level) { - ppgtt->insert_entries(ppgtt, obj->pages, - obj->gtt_space->start >> PAGE_SHIFT, - cache_level); + ppgtt->base.insert_entries(&ppgtt->base, obj->pages, + i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT, + cache_level); } void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt, struct drm_i915_gem_object *obj) { - ppgtt->clear_range(ppgtt, - obj->gtt_space->start >> PAGE_SHIFT, - obj->base.size >> PAGE_SHIFT); + ppgtt->base.clear_range(&ppgtt->base, + i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT); } extern int intel_iommu_gfx_mapped; @@ -436,8 +466,9 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev) struct drm_i915_gem_object *obj; /* First fill our portion of the GTT with scratch pages */ - dev_priv->gtt.gtt_clear_range(dev, dev_priv->gtt.start / PAGE_SIZE, - dev_priv->gtt.total / PAGE_SIZE); + dev_priv->gtt.base.clear_range(&dev_priv->gtt.base, + dev_priv->gtt.base.start / PAGE_SIZE, + dev_priv->gtt.base.total / PAGE_SIZE); list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { i915_gem_clflush_object(obj); @@ -466,12 +497,12 @@ int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj) * within the global GTT as well as accessible by the GPU through the GMADR * mapped BAR (dev_priv->mm.gtt->gtt). */ -static void gen6_ggtt_insert_entries(struct drm_device *dev, +static void gen6_ggtt_insert_entries(struct i915_address_space *vm, struct sg_table *st, unsigned int first_entry, enum i915_cache_level level) { - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = vm->dev->dev_private; gen6_gtt_pte_t __iomem *gtt_entries = (gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry; int i = 0; @@ -480,8 +511,7 @@ static void gen6_ggtt_insert_entries(struct drm_device *dev, for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) { addr = sg_page_iter_dma_address(&sg_iter); - iowrite32(dev_priv->gtt.pte_encode(dev, addr, level), - >t_entries[i]); + iowrite32(vm->pte_encode(addr, level), >t_entries[i]); i++; } @@ -492,8 +522,8 @@ static void gen6_ggtt_insert_entries(struct drm_device *dev, * hardware should work, we must keep this posting read for paranoia. */ if (i != 0) - WARN_ON(readl(>t_entries[i-1]) - != dev_priv->gtt.pte_encode(dev, addr, level)); + WARN_ON(readl(>t_entries[i-1]) != + vm->pte_encode(addr, level)); /* This next bit makes the above posting read even more important. We * want to flush the TLBs only after we're certain all the PTE updates @@ -503,11 +533,11 @@ static void gen6_ggtt_insert_entries(struct drm_device *dev, POSTING_READ(GFX_FLSH_CNTL_GEN6); } -static void gen6_ggtt_clear_range(struct drm_device *dev, +static void gen6_ggtt_clear_range(struct i915_address_space *vm, unsigned int first_entry, unsigned int num_entries) { - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = vm->dev->dev_private; 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; @@ -518,16 +548,14 @@ static void gen6_ggtt_clear_range(struct drm_device *dev, first_entry, num_entries, max_entries)) num_entries = max_entries; - scratch_pte = dev_priv->gtt.pte_encode(dev, - dev_priv->gtt.scratch_page_dma, - I915_CACHE_LLC); + scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC); for (i = 0; i < num_entries; i++) iowrite32(scratch_pte, >t_base[i]); readl(gtt_base); } -static void i915_ggtt_insert_entries(struct drm_device *dev, +static void i915_ggtt_insert_entries(struct i915_address_space *vm, struct sg_table *st, unsigned int pg_start, enum i915_cache_level cache_level) @@ -539,7 +567,7 @@ static void i915_ggtt_insert_entries(struct drm_device *dev, } -static void i915_ggtt_clear_range(struct drm_device *dev, +static void i915_ggtt_clear_range(struct i915_address_space *vm, unsigned int first_entry, unsigned int num_entries) { @@ -552,10 +580,11 @@ void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + const unsigned long entry = i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT; - dev_priv->gtt.gtt_insert_entries(dev, obj->pages, - obj->gtt_space->start >> PAGE_SHIFT, - cache_level); + dev_priv->gtt.base.insert_entries(&dev_priv->gtt.base, obj->pages, + entry, + cache_level); obj->has_global_gtt_mapping = 1; } @@ -564,10 +593,11 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj) { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + const unsigned long entry = i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT; - dev_priv->gtt.gtt_clear_range(obj->base.dev, - obj->gtt_space->start >> PAGE_SHIFT, - obj->base.size >> PAGE_SHIFT); + dev_priv->gtt.base.clear_range(&dev_priv->gtt.base, + entry, + obj->base.size >> PAGE_SHIFT); obj->has_global_gtt_mapping = 0; } @@ -626,37 +656,42 @@ void i915_gem_setup_global_gtt(struct drm_device *dev, BUG_ON(mappable_end > end); /* Subtract the guard page ... */ - drm_mm_init(&dev_priv->mm.gtt_space, start, end - start - PAGE_SIZE); + drm_mm_init(&dev_priv->gtt.base.mm, start, end - start - PAGE_SIZE); if (!HAS_LLC(dev)) - dev_priv->mm.gtt_space.color_adjust = i915_gtt_color_adjust; + dev_priv->gtt.base.mm.color_adjust = i915_gtt_color_adjust; /* Mark any preallocated objects as occupied */ list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { - DRM_DEBUG_KMS("reserving preallocated space: %x + %zx\n", - obj->gtt_offset, obj->base.size); - - BUG_ON(obj->gtt_space != I915_GTT_RESERVED); - obj->gtt_space = drm_mm_create_block(&dev_priv->mm.gtt_space, - obj->gtt_offset, - obj->base.size, - false); + struct i915_vma *vma = __i915_gem_obj_to_vma(obj); + int ret; + DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n", + i915_gem_obj_ggtt_offset(obj), obj->base.size); + + WARN_ON(i915_gem_obj_ggtt_bound(obj)); + ret = drm_mm_reserve_node(&dev_priv->gtt.base.mm, &vma->node); + if (ret) + DRM_DEBUG_KMS("Reservation failed\n"); obj->has_global_gtt_mapping = 1; + list_add(&vma->vma_link, &obj->vma_list); } - dev_priv->gtt.start = start; - dev_priv->gtt.total = end - start; + dev_priv->gtt.base.start = start; + dev_priv->gtt.base.total = end - start; /* Clear any non-preallocated blocks */ - drm_mm_for_each_hole(entry, &dev_priv->mm.gtt_space, + drm_mm_for_each_hole(entry, &dev_priv->gtt.base.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); - dev_priv->gtt.gtt_clear_range(dev, hole_start / PAGE_SIZE, - (hole_end-hole_start) / PAGE_SIZE); + dev_priv->gtt.base.clear_range(&dev_priv->gtt.base, + hole_start / PAGE_SIZE, + count); } /* And finally clear the reserved guard page */ - dev_priv->gtt.gtt_clear_range(dev, end / PAGE_SIZE - 1, 1); + dev_priv->gtt.base.clear_range(&dev_priv->gtt.base, + end / PAGE_SIZE - 1, 1); } static bool @@ -679,7 +714,7 @@ void i915_gem_init_global_gtt(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; unsigned long gtt_size, mappable_size; - gtt_size = dev_priv->gtt.total; + gtt_size = dev_priv->gtt.base.total; mappable_size = dev_priv->gtt.mappable_end; if (intel_enable_ppgtt(dev) && HAS_ALIASING_PPGTT(dev)) { @@ -688,7 +723,7 @@ void i915_gem_init_global_gtt(struct drm_device *dev) if (INTEL_INFO(dev)->gen <= 7) { /* PPGTT pdes are stolen from global gtt ptes, so shrink the * aperture accordingly when using aliasing ppgtt. */ - gtt_size -= I915_PPGTT_PD_ENTRIES*PAGE_SIZE; + gtt_size -= GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE; } i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size); @@ -698,8 +733,8 @@ void i915_gem_init_global_gtt(struct drm_device *dev) return; DRM_ERROR("Aliased PPGTT setup failed %d\n", ret); - drm_mm_takedown(&dev_priv->mm.gtt_space); - gtt_size += I915_PPGTT_PD_ENTRIES*PAGE_SIZE; + drm_mm_takedown(&dev_priv->gtt.base.mm); + gtt_size += GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE; } i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size); } @@ -724,8 +759,8 @@ static int setup_scratch_page(struct drm_device *dev) #else dma_addr = page_to_phys(page); #endif - dev_priv->gtt.scratch_page = page; - dev_priv->gtt.scratch_page_dma = dma_addr; + dev_priv->gtt.base.scratch.page = page; + dev_priv->gtt.base.scratch.addr = dma_addr; return 0; } @@ -733,11 +768,13 @@ static int setup_scratch_page(struct drm_device *dev) static void teardown_scratch_page(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - set_pages_wb(dev_priv->gtt.scratch_page, 1); - pci_unmap_page(dev->pdev, dev_priv->gtt.scratch_page_dma, + struct page *page = dev_priv->gtt.base.scratch.page; + + set_pages_wb(page, 1); + pci_unmap_page(dev->pdev, dev_priv->gtt.base.scratch.addr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - put_page(dev_priv->gtt.scratch_page); - __free_page(dev_priv->gtt.scratch_page); + put_page(page); + __free_page(page); } static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl) @@ -800,17 +837,18 @@ static int gen6_gmch_probe(struct drm_device *dev, if (ret) DRM_ERROR("Scratch setup failed\n"); - dev_priv->gtt.gtt_clear_range = gen6_ggtt_clear_range; - dev_priv->gtt.gtt_insert_entries = gen6_ggtt_insert_entries; + dev_priv->gtt.base.clear_range = gen6_ggtt_clear_range; + dev_priv->gtt.base.insert_entries = gen6_ggtt_insert_entries; return ret; } -static void gen6_gmch_remove(struct drm_device *dev) +static void gen6_gmch_remove(struct i915_address_space *vm) { - struct drm_i915_private *dev_priv = dev->dev_private; - iounmap(dev_priv->gtt.gsm); - teardown_scratch_page(dev_priv->dev); + + struct i915_gtt *gtt = container_of(vm, struct i915_gtt, base); + iounmap(gtt->gsm); + teardown_scratch_page(vm->dev); } static int i915_gmch_probe(struct drm_device *dev, @@ -831,13 +869,13 @@ static int i915_gmch_probe(struct drm_device *dev, intel_gtt_get(gtt_total, stolen, mappable_base, mappable_end); dev_priv->gtt.do_idle_maps = needs_idle_maps(dev_priv->dev); - dev_priv->gtt.gtt_clear_range = i915_ggtt_clear_range; - dev_priv->gtt.gtt_insert_entries = i915_ggtt_insert_entries; + dev_priv->gtt.base.clear_range = i915_ggtt_clear_range; + dev_priv->gtt.base.insert_entries = i915_ggtt_insert_entries; return 0; } -static void i915_gmch_remove(struct drm_device *dev) +static void i915_gmch_remove(struct i915_address_space *vm) { intel_gmch_remove(); } @@ -849,34 +887,33 @@ int i915_gem_gtt_init(struct drm_device *dev) int ret; if (INTEL_INFO(dev)->gen <= 5) { - dev_priv->gtt.gtt_probe = i915_gmch_probe; - dev_priv->gtt.gtt_remove = i915_gmch_remove; + gtt->gtt_probe = i915_gmch_probe; + gtt->base.cleanup = i915_gmch_remove; } else { - dev_priv->gtt.gtt_probe = gen6_gmch_probe; - dev_priv->gtt.gtt_remove = gen6_gmch_remove; - if (IS_HASWELL(dev)) { - dev_priv->gtt.pte_encode = hsw_pte_encode; - } else if (IS_VALLEYVIEW(dev)) { - dev_priv->gtt.pte_encode = byt_pte_encode; - } else { - dev_priv->gtt.pte_encode = gen6_pte_encode; - } + gtt->gtt_probe = gen6_gmch_probe; + gtt->base.cleanup = gen6_gmch_remove; + if (IS_HASWELL(dev) && dev_priv->ellc_size) + gtt->base.pte_encode = iris_pte_encode; + else if (IS_HASWELL(dev)) + gtt->base.pte_encode = hsw_pte_encode; + else if (IS_VALLEYVIEW(dev)) + gtt->base.pte_encode = byt_pte_encode; + else + gtt->base.pte_encode = gen6_pte_encode; } - ret = dev_priv->gtt.gtt_probe(dev, &dev_priv->gtt.total, - &dev_priv->gtt.stolen_size, - >t->mappable_base, - >t->mappable_end); + ret = gtt->gtt_probe(dev, >t->base.total, >t->stolen_size, + >t->mappable_base, >t->mappable_end); if (ret) return ret; + gtt->base.dev = dev; + /* GMADR is the PCI mmio aperture into the global GTT. */ DRM_INFO("Memory usable by graphics device = %zdM\n", - dev_priv->gtt.total >> 20); - DRM_DEBUG_DRIVER("GMADR size = %ldM\n", - dev_priv->gtt.mappable_end >> 20); - DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", - dev_priv->gtt.stolen_size >> 20); + gtt->base.total >> 20); + DRM_DEBUG_DRIVER("GMADR size = %ldM\n", gtt->mappable_end >> 20); + DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", gtt->stolen_size >> 20); return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 982d473..4bbde2a 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -45,49 +45,48 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct pci_dev *pdev = dev_priv->bridge_dev; + struct resource *r; u32 base; - /* On the machines I have tested the Graphics Base of Stolen Memory - * is unreliable, so on those compute the base by subtracting the - * stolen memory from the Top of Low Usable DRAM which is where the - * BIOS places the graphics stolen memory. + /* Almost universally we can find the Graphics Base of Stolen Memory + * at offset 0x5c in the igfx configuration space. On a few (desktop) + * machines this is also mirrored in the bridge device at different + * locations, or in the MCHBAR. On gen2, the layout is again slightly + * different with the Graphics Segment immediately following Top of + * Memory (or Top of Usable DRAM). Note it appears that TOUD is only + * reported by 865g, so we just use the top of memory as determined + * by the e820 probe. * - * On gen2, the layout is slightly different with the Graphics Segment - * immediately following Top of Memory (or Top of Usable DRAM). Note - * it appears that TOUD is only reported by 865g, so we just use the - * top of memory as determined by the e820 probe. - * - * XXX gen2 requires an unavailable symbol and 945gm fails with - * its value of TOLUD. + * XXX However gen2 requires an unavailable symbol. */ base = 0; - if (IS_VALLEYVIEW(dev)) { + if (INTEL_INFO(dev)->gen >= 3) { + /* Read Graphics Base of Stolen Memory directly */ pci_read_config_dword(dev->pdev, 0x5c, &base); base &= ~((1<<20) - 1); - } else if (INTEL_INFO(dev)->gen >= 6) { - /* Read Base Data of Stolen Memory Register (BDSM) directly. - * Note that there is also a MCHBAR miror at 0x1080c0 or - * we could use device 2:0x5c instead. - */ - pci_read_config_dword(pdev, 0xB0, &base); - base &= ~4095; /* lower bits used for locking register */ - } else if (INTEL_INFO(dev)->gen > 3 || IS_G33(dev)) { - /* Read Graphics Base of Stolen Memory directly */ - pci_read_config_dword(pdev, 0xA4, &base); + } else { /* GEN2 */ #if 0 - } else if (IS_GEN3(dev)) { - u8 val; - /* Stolen is immediately below Top of Low Usable DRAM */ - pci_read_config_byte(pdev, 0x9c, &val); - base = val >> 3 << 27; - base -= dev_priv->mm.gtt->stolen_size; - } else { /* Stolen is immediately above Top of Memory */ base = max_low_pfn_mapped << PAGE_SHIFT; #endif } + if (base == 0) + return 0; + + /* Verify that nothing else uses this physical address. Stolen + * memory should be reserved by the BIOS and hidden from the + * kernel. So if the region is already marked as busy, something + * is seriously wrong. + */ + r = devm_request_mem_region(dev->dev, base, dev_priv->gtt.stolen_size, + "Graphics Stolen Memory"); + if (r == NULL) { + DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n", + base, base + (uint32_t)dev_priv->gtt.stolen_size); + base = 0; + } + return base; } @@ -120,7 +119,7 @@ static int i915_setup_compression(struct drm_device *dev, int size) if (!compressed_llb) goto err_fb; - dev_priv->compressed_llb = compressed_llb; + dev_priv->fbc.compressed_llb = compressed_llb; I915_WRITE(FBC_CFB_BASE, dev_priv->mm.stolen_base + compressed_fb->start); @@ -128,8 +127,8 @@ static int i915_setup_compression(struct drm_device *dev, int size) dev_priv->mm.stolen_base + compressed_llb->start); } - dev_priv->compressed_fb = compressed_fb; - dev_priv->cfb_size = size; + dev_priv->fbc.compressed_fb = compressed_fb; + dev_priv->fbc.size = size; DRM_DEBUG_KMS("reserved %d bytes of contiguous stolen space for FBC\n", size); @@ -150,7 +149,7 @@ int i915_gem_stolen_setup_compression(struct drm_device *dev, int size) if (!drm_mm_initialized(&dev_priv->mm.stolen)) return -ENODEV; - if (size < dev_priv->cfb_size) + if (size < dev_priv->fbc.size) return 0; /* Release any current block */ @@ -163,16 +162,16 @@ void i915_gem_stolen_cleanup_compression(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - if (dev_priv->cfb_size == 0) + if (dev_priv->fbc.size == 0) return; - if (dev_priv->compressed_fb) - drm_mm_put_block(dev_priv->compressed_fb); + if (dev_priv->fbc.compressed_fb) + drm_mm_put_block(dev_priv->fbc.compressed_fb); - if (dev_priv->compressed_llb) - drm_mm_put_block(dev_priv->compressed_llb); + if (dev_priv->fbc.compressed_llb) + drm_mm_put_block(dev_priv->fbc.compressed_llb); - dev_priv->cfb_size = 0; + dev_priv->fbc.size = 0; } void i915_gem_cleanup_stolen(struct drm_device *dev) @@ -201,6 +200,9 @@ int i915_gem_init_stolen(struct drm_device *dev) if (IS_VALLEYVIEW(dev)) bios_reserved = 1024*1024; /* top 1M on VLV/BYT */ + if (WARN_ON(bios_reserved > dev_priv->gtt.stolen_size)) + return 0; + /* Basic memrange allocator for stolen space */ drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->gtt.stolen_size - bios_reserved); @@ -331,8 +333,11 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, u32 size) { struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *vm = &dev_priv->gtt.base; struct drm_i915_gem_object *obj; struct drm_mm_node *stolen; + struct i915_vma *vma; + int ret; if (!drm_mm_initialized(&dev_priv->mm.stolen)) return NULL; @@ -347,11 +352,16 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, if (WARN_ON(size == 0)) return NULL; - stolen = drm_mm_create_block(&dev_priv->mm.stolen, - stolen_offset, size, - false); - if (stolen == NULL) { + stolen = kzalloc(sizeof(*stolen), GFP_KERNEL); + if (!stolen) + return NULL; + + stolen->start = stolen_offset; + stolen->size = size; + ret = drm_mm_reserve_node(&dev_priv->mm.stolen, stolen); + if (ret) { DRM_DEBUG_KMS("failed to allocate stolen space\n"); + kfree(stolen); return NULL; } @@ -363,33 +373,42 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, } /* Some objects just need physical mem from stolen space */ - if (gtt_offset == -1) + if (gtt_offset == I915_GTT_OFFSET_NONE) return obj; + vma = i915_gem_vma_create(obj, &dev_priv->gtt.base); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err_out; + } + /* To simplify the initialisation sequence between KMS and GTT, * we allow construction of the stolen object prior to * setting up the GTT space. The actual reservation will occur * later. */ - if (drm_mm_initialized(&dev_priv->mm.gtt_space)) { - obj->gtt_space = drm_mm_create_block(&dev_priv->mm.gtt_space, - gtt_offset, size, - false); - if (obj->gtt_space == NULL) { + vma->node.start = gtt_offset; + vma->node.size = size; + if (drm_mm_initialized(&dev_priv->gtt.base.mm)) { + ret = drm_mm_reserve_node(&dev_priv->gtt.base.mm, &vma->node); + if (ret) { DRM_DEBUG_KMS("failed to allocate stolen GTT space\n"); - drm_gem_object_unreference(&obj->base); - return NULL; + i915_gem_vma_destroy(vma); + goto err_out; } - } else - obj->gtt_space = I915_GTT_RESERVED; + } - obj->gtt_offset = gtt_offset; obj->has_global_gtt_mapping = 1; list_add_tail(&obj->global_list, &dev_priv->mm.bound_list); - list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list); + list_add_tail(&obj->mm_list, &vm->inactive_list); return obj; + +err_out: + drm_mm_put_block(stolen); + drm_gem_object_unreference(&obj->base); + return NULL; } void diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 537545b..92a8d27 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -268,18 +268,18 @@ i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode) return true; if (INTEL_INFO(obj->base.dev)->gen == 3) { - if (obj->gtt_offset & ~I915_FENCE_START_MASK) + if (i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK) return false; } else { - if (obj->gtt_offset & ~I830_FENCE_START_MASK) + if (i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK) return false; } size = i915_gem_get_gtt_size(obj->base.dev, obj->base.size, tiling_mode); - if (obj->gtt_space->size != size) + if (i915_gem_obj_ggtt_size(obj) != size) return false; - if (obj->gtt_offset & (size - 1)) + if (i915_gem_obj_ggtt_offset(obj) & (size - 1)) return false; return true; @@ -359,8 +359,8 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, */ obj->map_and_fenceable = - obj->gtt_space == NULL || - (obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end && + !i915_gem_obj_ggtt_bound(obj) || + (i915_gem_obj_ggtt_offset(obj) + obj->base.size <= dev_priv->gtt.mappable_end && i915_gem_object_fence_ok(obj, args->tiling_mode)); /* Rebind if we need a change of alignment */ @@ -369,7 +369,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, i915_gem_get_gtt_alignment(dev, obj->base.size, args->tiling_mode, false); - if (obj->gtt_offset & (unfenced_alignment - 1)) + if (i915_gem_obj_ggtt_offset(obj) & (unfenced_alignment - 1)) ret = i915_gem_object_unbind(obj); } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c new file mode 100644 index 0000000..d970d84 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -0,0 +1,973 @@ +/* + * Copyright (c) 2008 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. + * + * Authors: + * Eric Anholt <eric@anholt.net> + * Keith Packard <keithp@keithp.com> + * Mika Kuoppala <mika.kuoppala@intel.com> + * + */ + +#include <generated/utsrelease.h> +#include "i915_drv.h" + +static const char *yesno(int v) +{ + return v ? "yes" : "no"; +} + +static const char *ring_str(int ring) +{ + switch (ring) { + case RCS: return "render"; + case VCS: return "bsd"; + case BCS: return "blt"; + case VECS: return "vebox"; + default: return ""; + } +} + +static const char *pin_flag(int pinned) +{ + if (pinned > 0) + return " P"; + else if (pinned < 0) + return " p"; + else + return ""; +} + +static const char *tiling_flag(int tiling) +{ + switch (tiling) { + default: + case I915_TILING_NONE: return ""; + case I915_TILING_X: return " X"; + case I915_TILING_Y: return " Y"; + } +} + +static const char *dirty_flag(int dirty) +{ + return dirty ? " dirty" : ""; +} + +static const char *purgeable_flag(int purgeable) +{ + return purgeable ? " purgeable" : ""; +} + +static bool __i915_error_ok(struct drm_i915_error_state_buf *e) +{ + + if (!e->err && WARN(e->bytes > (e->size - 1), "overflow")) { + e->err = -ENOSPC; + return false; + } + + if (e->bytes == e->size - 1 || e->err) + return false; + + return true; +} + +static bool __i915_error_seek(struct drm_i915_error_state_buf *e, + unsigned len) +{ + if (e->pos + len <= e->start) { + e->pos += len; + return false; + } + + /* First vsnprintf needs to fit in its entirety for memmove */ + if (len >= e->size) { + e->err = -EIO; + return false; + } + + return true; +} + +static void __i915_error_advance(struct drm_i915_error_state_buf *e, + unsigned len) +{ + /* If this is first printf in this window, adjust it so that + * start position matches start of the buffer + */ + + if (e->pos < e->start) { + const size_t off = e->start - e->pos; + + /* Should not happen but be paranoid */ + if (off > len || e->bytes) { + e->err = -EIO; + return; + } + + memmove(e->buf, e->buf + off, len - off); + e->bytes = len - off; + e->pos = e->start; + return; + } + + e->bytes += len; + e->pos += len; +} + +static void i915_error_vprintf(struct drm_i915_error_state_buf *e, + const char *f, va_list args) +{ + unsigned len; + + if (!__i915_error_ok(e)) + return; + + /* Seek the first printf which is hits start position */ + if (e->pos < e->start) { + len = vsnprintf(NULL, 0, f, args); + if (!__i915_error_seek(e, len)) + return; + } + + len = vsnprintf(e->buf + e->bytes, e->size - e->bytes, f, args); + if (len >= e->size - e->bytes) + len = e->size - e->bytes - 1; + + __i915_error_advance(e, len); +} + +static void i915_error_puts(struct drm_i915_error_state_buf *e, + const char *str) +{ + unsigned len; + + if (!__i915_error_ok(e)) + return; + + len = strlen(str); + + /* Seek the first printf which is hits start position */ + if (e->pos < e->start) { + if (!__i915_error_seek(e, len)) + return; + } + + if (len >= e->size - e->bytes) + len = e->size - e->bytes - 1; + memcpy(e->buf + e->bytes, str, len); + + __i915_error_advance(e, len); +} + +#define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__) +#define err_puts(e, s) i915_error_puts(e, s) + +static void print_error_buffers(struct drm_i915_error_state_buf *m, + const char *name, + struct drm_i915_error_buffer *err, + int count) +{ + err_printf(m, "%s [%d]:\n", name, count); + + while (count--) { + err_printf(m, " %08x %8u %02x %02x %x %x", + err->gtt_offset, + err->size, + err->read_domains, + err->write_domain, + err->rseqno, err->wseqno); + err_puts(m, pin_flag(err->pinned)); + err_puts(m, tiling_flag(err->tiling)); + err_puts(m, dirty_flag(err->dirty)); + err_puts(m, purgeable_flag(err->purgeable)); + err_puts(m, err->ring != -1 ? " " : ""); + err_puts(m, ring_str(err->ring)); + err_puts(m, i915_cache_level_str(err->cache_level)); + + if (err->name) + err_printf(m, " (name: %d)", err->name); + if (err->fence_reg != I915_FENCE_REG_NONE) + err_printf(m, " (fence: %d)", err->fence_reg); + + err_puts(m, "\n"); + err++; + } +} + +static void i915_ring_error_state(struct drm_i915_error_state_buf *m, + struct drm_device *dev, + struct drm_i915_error_state *error, + unsigned ring) +{ + BUG_ON(ring >= I915_NUM_RINGS); /* shut up confused gcc */ + err_printf(m, "%s command stream:\n", ring_str(ring)); + err_printf(m, " HEAD: 0x%08x\n", error->head[ring]); + err_printf(m, " TAIL: 0x%08x\n", error->tail[ring]); + err_printf(m, " CTL: 0x%08x\n", error->ctl[ring]); + err_printf(m, " ACTHD: 0x%08x\n", error->acthd[ring]); + err_printf(m, " IPEIR: 0x%08x\n", error->ipeir[ring]); + err_printf(m, " IPEHR: 0x%08x\n", error->ipehr[ring]); + err_printf(m, " INSTDONE: 0x%08x\n", error->instdone[ring]); + if (ring == RCS && INTEL_INFO(dev)->gen >= 4) + err_printf(m, " BBADDR: 0x%08llx\n", error->bbaddr); + + if (INTEL_INFO(dev)->gen >= 4) + err_printf(m, " INSTPS: 0x%08x\n", error->instps[ring]); + err_printf(m, " INSTPM: 0x%08x\n", error->instpm[ring]); + err_printf(m, " FADDR: 0x%08x\n", error->faddr[ring]); + if (INTEL_INFO(dev)->gen >= 6) { + err_printf(m, " RC PSMI: 0x%08x\n", error->rc_psmi[ring]); + err_printf(m, " FAULT_REG: 0x%08x\n", error->fault_reg[ring]); + err_printf(m, " SYNC_0: 0x%08x [last synced 0x%08x]\n", + error->semaphore_mboxes[ring][0], + error->semaphore_seqno[ring][0]); + err_printf(m, " SYNC_1: 0x%08x [last synced 0x%08x]\n", + error->semaphore_mboxes[ring][1], + error->semaphore_seqno[ring][1]); + } + err_printf(m, " seqno: 0x%08x\n", error->seqno[ring]); + err_printf(m, " waiting: %s\n", yesno(error->waiting[ring])); + err_printf(m, " ring->head: 0x%08x\n", error->cpu_ring_head[ring]); + err_printf(m, " ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]); +} + +void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...) +{ + va_list args; + + va_start(args, f); + i915_error_vprintf(e, f, args); + va_end(args); +} + +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; + struct intel_ring_buffer *ring; + int i, j, page, offset, elt; + + if (!error) { + err_printf(m, "no error state collected\n"); + goto out; + } + + err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec, + error->time.tv_usec); + err_printf(m, "Kernel: " UTS_RELEASE "\n"); + err_printf(m, "PCI ID: 0x%04x\n", dev->pci_device); + err_printf(m, "EIR: 0x%08x\n", error->eir); + err_printf(m, "IER: 0x%08x\n", error->ier); + err_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er); + err_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake); + err_printf(m, "DERRMR: 0x%08x\n", error->derrmr); + err_printf(m, "CCID: 0x%08x\n", error->ccid); + + for (i = 0; i < dev_priv->num_fence_regs; i++) + err_printf(m, " fence[%d] = %08llx\n", i, error->fence[i]); + + for (i = 0; i < ARRAY_SIZE(error->extra_instdone); i++) + err_printf(m, " INSTDONE_%d: 0x%08x\n", i, + error->extra_instdone[i]); + + if (INTEL_INFO(dev)->gen >= 6) { + err_printf(m, "ERROR: 0x%08x\n", error->error); + err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg); + } + + if (INTEL_INFO(dev)->gen == 7) + err_printf(m, "ERR_INT: 0x%08x\n", error->err_int); + + for_each_ring(ring, dev_priv, i) + i915_ring_error_state(m, dev, error, i); + + if (error->active_bo) + print_error_buffers(m, "Active", + error->active_bo, + error->active_bo_count); + + if (error->pinned_bo) + print_error_buffers(m, "Pinned", + error->pinned_bo, + error->pinned_bo_count); + + 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->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; + } + } + } + + if (error->ring[i].num_requests) { + err_printf(m, "%s --- %d requests\n", + dev_priv->ring[i].name, + error->ring[i].num_requests); + for (j = 0; j < error->ring[i].num_requests; j++) { + err_printf(m, " seqno 0x%08x, emitted %ld, tail 0x%08x\n", + error->ring[i].requests[j].seqno, + error->ring[i].requests[j].jiffies, + error->ring[i].requests[j].tail); + } + } + + if ((obj = error->ring[i].ringbuffer)) { + 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; + } + } + } + + obj = error->ring[i].ctx; + if (obj) { + err_printf(m, "%s --- HW Context = 0x%08x\n", + dev_priv->ring[i].name, + obj->gtt_offset); + offset = 0; + for (elt = 0; elt < PAGE_SIZE/16; elt += 4) { + err_printf(m, "[%04x] %08x %08x %08x %08x\n", + offset, + obj->pages[0][elt], + obj->pages[0][elt+1], + obj->pages[0][elt+2], + obj->pages[0][elt+3]); + offset += 16; + } + } + } + + if (error->overlay) + intel_overlay_print_error_state(m, error->overlay); + + if (error->display) + intel_display_print_error_state(m, dev, error->display); + +out: + if (m->bytes == 0 && m->err) + return m->err; + + return 0; +} + +int i915_error_state_buf_init(struct drm_i915_error_state_buf *ebuf, + size_t count, loff_t pos) +{ + memset(ebuf, 0, sizeof(*ebuf)); + + /* We need to have enough room to store any i915_error_state printf + * so that we can move it to start position. + */ + ebuf->size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE; + ebuf->buf = kmalloc(ebuf->size, + GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN); + + if (ebuf->buf == NULL) { + ebuf->size = PAGE_SIZE; + ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY); + } + + if (ebuf->buf == NULL) { + ebuf->size = 128; + ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY); + } + + if (ebuf->buf == NULL) + return -ENOMEM; + + ebuf->start = pos; + + return 0; +} + +static void i915_error_object_free(struct drm_i915_error_object *obj) +{ + int page; + + if (obj == NULL) + return; + + for (page = 0; page < obj->page_count; page++) + kfree(obj->pages[page]); + + kfree(obj); +} + +static void i915_error_state_free(struct kref *error_ref) +{ + struct drm_i915_error_state *error = container_of(error_ref, + typeof(*error), ref); + int i; + + for (i = 0; i < ARRAY_SIZE(error->ring); i++) { + i915_error_object_free(error->ring[i].batchbuffer); + i915_error_object_free(error->ring[i].ringbuffer); + i915_error_object_free(error->ring[i].ctx); + kfree(error->ring[i].requests); + } + + kfree(error->active_bo); + kfree(error->overlay); + kfree(error->display); + kfree(error); +} + +static struct drm_i915_error_object * +i915_error_object_create_sized(struct drm_i915_private *dev_priv, + struct drm_i915_gem_object *src, + const int num_pages) +{ + struct drm_i915_error_object *dst; + int i; + u32 reloc_offset; + + if (src == NULL || src->pages == NULL) + return NULL; + + dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), GFP_ATOMIC); + if (dst == NULL) + return NULL; + + reloc_offset = dst->gtt_offset = i915_gem_obj_ggtt_offset(src); + for (i = 0; i < num_pages; i++) { + unsigned long flags; + void *d; + + d = kmalloc(PAGE_SIZE, GFP_ATOMIC); + if (d == NULL) + goto unwind; + + local_irq_save(flags); + if (reloc_offset < dev_priv->gtt.mappable_end && + src->has_global_gtt_mapping) { + void __iomem *s; + + /* Simply ignore tiling or any overlapping fence. + * It's part of the error state, and this hopefully + * captures what the GPU read. + */ + + s = io_mapping_map_atomic_wc(dev_priv->gtt.mappable, + reloc_offset); + memcpy_fromio(d, s, PAGE_SIZE); + io_mapping_unmap_atomic(s); + } else if (src->stolen) { + unsigned long offset; + + offset = dev_priv->mm.stolen_base; + offset += src->stolen->start; + offset += i << PAGE_SHIFT; + + memcpy_fromio(d, (void __iomem *) offset, PAGE_SIZE); + } else { + struct page *page; + void *s; + + page = i915_gem_object_get_page(src, i); + + drm_clflush_pages(&page, 1); + + s = kmap_atomic(page); + memcpy(d, s, PAGE_SIZE); + kunmap_atomic(s); + + drm_clflush_pages(&page, 1); + } + local_irq_restore(flags); + + dst->pages[i] = d; + + reloc_offset += PAGE_SIZE; + } + dst->page_count = num_pages; + + return dst; + +unwind: + while (i--) + kfree(dst->pages[i]); + kfree(dst); + return NULL; +} +#define i915_error_object_create(dev_priv, src) \ + i915_error_object_create_sized((dev_priv), (src), \ + (src)->base.size>>PAGE_SHIFT) + +static void capture_bo(struct drm_i915_error_buffer *err, + struct drm_i915_gem_object *obj) +{ + err->size = obj->base.size; + err->name = obj->base.name; + err->rseqno = obj->last_read_seqno; + err->wseqno = obj->last_write_seqno; + err->gtt_offset = i915_gem_obj_ggtt_offset(obj); + err->read_domains = obj->base.read_domains; + err->write_domain = obj->base.write_domain; + err->fence_reg = obj->fence_reg; + err->pinned = 0; + if (obj->pin_count > 0) + err->pinned = 1; + if (obj->user_pin_count > 0) + err->pinned = -1; + err->tiling = obj->tiling_mode; + err->dirty = obj->dirty; + err->purgeable = obj->madv != I915_MADV_WILLNEED; + err->ring = obj->ring ? obj->ring->id : -1; + err->cache_level = obj->cache_level; +} + +static u32 capture_active_bo(struct drm_i915_error_buffer *err, + int count, struct list_head *head) +{ + struct drm_i915_gem_object *obj; + int i = 0; + + list_for_each_entry(obj, head, mm_list) { + capture_bo(err++, obj); + if (++i == count) + break; + } + + return i; +} + +static u32 capture_pinned_bo(struct drm_i915_error_buffer *err, + int count, struct list_head *head) +{ + struct drm_i915_gem_object *obj; + int i = 0; + + list_for_each_entry(obj, head, global_list) { + if (obj->pin_count == 0) + continue; + + capture_bo(err++, obj); + if (++i == count) + break; + } + + return i; +} + +static void i915_gem_record_fences(struct drm_device *dev, + struct drm_i915_error_state *error) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int i; + + /* Fences */ + switch (INTEL_INFO(dev)->gen) { + case 7: + case 6: + for (i = 0; i < dev_priv->num_fence_regs; i++) + error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8)); + break; + case 5: + case 4: + for (i = 0; i < 16; i++) + error->fence[i] = I915_READ64(FENCE_REG_965_0 + (i * 8)); + break; + case 3: + if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) + for (i = 0; i < 8; i++) + error->fence[i+8] = I915_READ(FENCE_REG_945_8 + (i * 4)); + case 2: + for (i = 0; i < 8; i++) + error->fence[i] = I915_READ(FENCE_REG_830_0 + (i * 4)); + break; + + default: + BUG(); + } +} + +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 = &dev_priv->gtt.base; + struct drm_i915_gem_object *obj; + 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->private; + if (acthd >= i915_gem_obj_ggtt_offset(obj) && + acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size) + return i915_error_object_create(dev_priv, obj); + } + + seqno = ring->get_seqno(ring, false); + list_for_each_entry(obj, &vm->active_list, mm_list) { + 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); + } + + return NULL; +} + +static void i915_record_ring_state(struct drm_device *dev, + struct drm_i915_error_state *error, + struct intel_ring_buffer *ring) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (INTEL_INFO(dev)->gen >= 6) { + error->rc_psmi[ring->id] = I915_READ(ring->mmio_base + 0x50); + error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring)); + error->semaphore_mboxes[ring->id][0] + = I915_READ(RING_SYNC_0(ring->mmio_base)); + error->semaphore_mboxes[ring->id][1] + = I915_READ(RING_SYNC_1(ring->mmio_base)); + error->semaphore_seqno[ring->id][0] = ring->sync_seqno[0]; + error->semaphore_seqno[ring->id][1] = ring->sync_seqno[1]; + } + + if (INTEL_INFO(dev)->gen >= 4) { + error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base)); + error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base)); + error->ipehr[ring->id] = I915_READ(RING_IPEHR(ring->mmio_base)); + error->instdone[ring->id] = I915_READ(RING_INSTDONE(ring->mmio_base)); + error->instps[ring->id] = I915_READ(RING_INSTPS(ring->mmio_base)); + if (ring->id == RCS) + error->bbaddr = I915_READ64(BB_ADDR); + } else { + error->faddr[ring->id] = I915_READ(DMA_FADD_I8XX); + error->ipeir[ring->id] = I915_READ(IPEIR); + error->ipehr[ring->id] = I915_READ(IPEHR); + error->instdone[ring->id] = I915_READ(INSTDONE); + } + + error->waiting[ring->id] = waitqueue_active(&ring->irq_queue); + error->instpm[ring->id] = I915_READ(RING_INSTPM(ring->mmio_base)); + error->seqno[ring->id] = ring->get_seqno(ring, false); + error->acthd[ring->id] = intel_ring_get_active_head(ring); + error->head[ring->id] = I915_READ_HEAD(ring); + error->tail[ring->id] = I915_READ_TAIL(ring); + error->ctl[ring->id] = I915_READ_CTL(ring); + + error->cpu_ring_head[ring->id] = ring->head; + error->cpu_ring_tail[ring->id] = ring->tail; +} + + +static void i915_gem_record_active_context(struct intel_ring_buffer *ring, + struct drm_i915_error_state *error, + struct drm_i915_error_ring *ering) +{ + struct drm_i915_private *dev_priv = ring->dev->dev_private; + struct drm_i915_gem_object *obj; + + /* Currently render ring is the only HW context user */ + if (ring->id != RCS || !error->ccid) + return; + + list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { + if ((error->ccid & PAGE_MASK) == i915_gem_obj_ggtt_offset(obj)) { + ering->ctx = i915_error_object_create_sized(dev_priv, + obj, 1); + break; + } + } +} + +static void i915_gem_record_rings(struct drm_device *dev, + struct drm_i915_error_state *error) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_ring_buffer *ring; + struct drm_i915_gem_request *request; + int i, count; + + for_each_ring(ring, dev_priv, i) { + i915_record_ring_state(dev, error, ring); + + error->ring[i].batchbuffer = + i915_error_first_batchbuffer(dev_priv, ring); + + error->ring[i].ringbuffer = + i915_error_object_create(dev_priv, ring->obj); + + + i915_gem_record_active_context(ring, error, &error->ring[i]); + + count = 0; + list_for_each_entry(request, &ring->request_list, list) + count++; + + error->ring[i].num_requests = count; + error->ring[i].requests = + kmalloc(count*sizeof(struct drm_i915_error_request), + GFP_ATOMIC); + if (error->ring[i].requests == NULL) { + error->ring[i].num_requests = 0; + continue; + } + + count = 0; + list_for_each_entry(request, &ring->request_list, list) { + struct drm_i915_error_request *erq; + + erq = &error->ring[i].requests[count++]; + erq->seqno = request->seqno; + erq->jiffies = request->emitted_jiffies; + erq->tail = request->tail; + } + } +} + +static void i915_gem_capture_buffers(struct drm_i915_private *dev_priv, + struct drm_i915_error_state *error) +{ + struct i915_address_space *vm = &dev_priv->gtt.base; + struct drm_i915_gem_object *obj; + int i; + + i = 0; + list_for_each_entry(obj, &vm->active_list, mm_list) + i++; + error->active_bo_count = i; + list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) + if (obj->pin_count) + i++; + error->pinned_bo_count = i - error->active_bo_count; + + if (i) { + error->active_bo = kmalloc(sizeof(*error->active_bo)*i, + GFP_ATOMIC); + if (error->active_bo) + error->pinned_bo = + error->active_bo + error->active_bo_count; + } + + if (error->active_bo) + error->active_bo_count = + capture_active_bo(error->active_bo, + error->active_bo_count, + &vm->active_list); + + if (error->pinned_bo) + error->pinned_bo_count = + capture_pinned_bo(error->pinned_bo, + error->pinned_bo_count, + &dev_priv->mm.bound_list); +} + +/** + * i915_capture_error_state - capture an error record for later analysis + * @dev: drm device + * + * Should be called when an error is detected (either a hang or an error + * interrupt) to capture error state from the time of the error. Fills + * out a structure which becomes available in debugfs for user level tools + * to pick up. + */ +void i915_capture_error_state(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_error_state *error; + unsigned long flags; + int pipe; + + 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); + if (!error) { + DRM_DEBUG_DRIVER("out of memory, not capturing error state\n"); + return; + } + + DRM_INFO("capturing error event; look for more information in " + "/sys/class/drm/card%d/error\n", dev->primary->index); + + kref_init(&error->ref); + error->eir = I915_READ(EIR); + error->pgtbl_er = I915_READ(PGTBL_ER); + if (HAS_HW_CONTEXTS(dev)) + error->ccid = I915_READ(CCID); + + if (HAS_PCH_SPLIT(dev)) + error->ier = I915_READ(DEIER) | I915_READ(GTIER); + else if (IS_VALLEYVIEW(dev)) + error->ier = I915_READ(GTIER) | I915_READ(VLV_IER); + else if (IS_GEN2(dev)) + error->ier = I915_READ16(IER); + else + error->ier = I915_READ(IER); + + if (INTEL_INFO(dev)->gen >= 6) + error->derrmr = I915_READ(DERRMR); + + if (IS_VALLEYVIEW(dev)) + error->forcewake = I915_READ(FORCEWAKE_VLV); + else if (INTEL_INFO(dev)->gen >= 7) + error->forcewake = I915_READ(FORCEWAKE_MT); + else if (INTEL_INFO(dev)->gen == 6) + error->forcewake = I915_READ(FORCEWAKE); + + if (!HAS_PCH_SPLIT(dev)) + for_each_pipe(pipe) + error->pipestat[pipe] = I915_READ(PIPESTAT(pipe)); + + if (INTEL_INFO(dev)->gen >= 6) { + error->error = I915_READ(ERROR_GEN6); + error->done_reg = I915_READ(DONE_REG); + } + + if (INTEL_INFO(dev)->gen == 7) + error->err_int = I915_READ(GEN7_ERR_INT); + + i915_get_extra_instdone(dev, error->extra_instdone); + + i915_gem_capture_buffers(dev_priv, error); + i915_gem_record_fences(dev, error); + i915_gem_record_rings(dev, error); + + do_gettimeofday(&error->time); + + error->overlay = intel_overlay_capture_error_state(dev); + error->display = intel_display_capture_error_state(dev); + + spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); + if (dev_priv->gpu_error.first_error == NULL) { + dev_priv->gpu_error.first_error = error; + error = NULL; + } + spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); + + if (error) + i915_error_state_free(&error->ref); +} + +void i915_error_state_get(struct drm_device *dev, + struct i915_error_state_file_priv *error_priv) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + unsigned long flags; + + spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); + error_priv->error = dev_priv->gpu_error.first_error; + if (error_priv->error) + kref_get(&error_priv->error->ref); + spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); + +} + +void i915_error_state_put(struct i915_error_state_file_priv *error_priv) +{ + if (error_priv->error) + kref_put(&error_priv->error->ref, i915_error_state_free); +} + +void i915_destroy_error_state(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_error_state *error; + unsigned long flags; + + spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); + error = dev_priv->gpu_error.first_error; + dev_priv->gpu_error.first_error = NULL; + spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); + + if (error) + kref_put(&error->ref, i915_error_state_free); +} + +const char *i915_cache_level_str(int type) +{ + switch (type) { + case I915_CACHE_NONE: return " uncached"; + case I915_CACHE_LLC: return " snooped (LLC)"; + case I915_CACHE_LLC_MLC: return " snooped (LLC+MLC)"; + default: return ""; + } +} + +/* NB: please notice the memset */ +void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + memset(instdone, 0, sizeof(*instdone) * I915_NUM_INSTDONE_REG); + + switch (INTEL_INFO(dev)->gen) { + case 2: + case 3: + instdone[0] = I915_READ(INSTDONE); + break; + case 4: + case 5: + case 6: + instdone[0] = I915_READ(INSTDONE_I965); + instdone[1] = I915_READ(INSTDONE1); + break; + default: + WARN_ONCE(1, "Unsupported platform\n"); + case 7: + instdone[0] = I915_READ(GEN7_INSTDONE_1); + instdone[1] = I915_READ(GEN7_SC_INSTDONE); + instdone[2] = I915_READ(GEN7_SAMPLER_INSTDONE); + instdone[3] = I915_READ(GEN7_ROW_INSTDONE); + break; + } +} diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 3d92a7c..f708e4e 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -128,6 +128,8 @@ static bool cpt_can_enable_serr_int(struct drm_device *dev) enum pipe pipe; struct intel_crtc *crtc; + assert_spin_locked(&dev_priv->irq_lock); + for_each_pipe(pipe) { crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]); @@ -152,38 +154,66 @@ static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev, } static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev, - bool enable) + enum pipe pipe, bool enable) { struct drm_i915_private *dev_priv = dev->dev_private; - if (enable) { + I915_WRITE(GEN7_ERR_INT, ERR_INT_FIFO_UNDERRUN(pipe)); + if (!ivb_can_enable_err_int(dev)) return; - I915_WRITE(GEN7_ERR_INT, ERR_INT_FIFO_UNDERRUN_A | - ERR_INT_FIFO_UNDERRUN_B | - ERR_INT_FIFO_UNDERRUN_C); - ironlake_enable_display_irq(dev_priv, DE_ERR_INT_IVB); } else { + bool was_enabled = !(I915_READ(DEIMR) & DE_ERR_INT_IVB); + + /* Change the state _after_ we've read out the current one. */ ironlake_disable_display_irq(dev_priv, DE_ERR_INT_IVB); + + if (!was_enabled && + (I915_READ(GEN7_ERR_INT) & ERR_INT_FIFO_UNDERRUN(pipe))) { + DRM_DEBUG_KMS("uncleared fifo underrun on pipe %c\n", + pipe_name(pipe)); + } } } -static void ibx_set_fifo_underrun_reporting(struct intel_crtc *crtc, +/** + * ibx_display_interrupt_update - update SDEIMR + * @dev_priv: driver private + * @interrupt_mask: mask of interrupt bits to update + * @enabled_irq_mask: mask of interrupt bits to enable + */ +static void ibx_display_interrupt_update(struct drm_i915_private *dev_priv, + uint32_t interrupt_mask, + uint32_t enabled_irq_mask) +{ + uint32_t sdeimr = I915_READ(SDEIMR); + sdeimr &= ~interrupt_mask; + sdeimr |= (~enabled_irq_mask & interrupt_mask); + + assert_spin_locked(&dev_priv->irq_lock); + + I915_WRITE(SDEIMR, sdeimr); + POSTING_READ(SDEIMR); +} +#define ibx_enable_display_interrupt(dev_priv, bits) \ + ibx_display_interrupt_update((dev_priv), (bits), (bits)) +#define ibx_disable_display_interrupt(dev_priv, bits) \ + ibx_display_interrupt_update((dev_priv), (bits), 0) + +static void ibx_set_fifo_underrun_reporting(struct drm_device *dev, + enum transcoder pch_transcoder, bool enable) { - struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t bit = (crtc->pipe == PIPE_A) ? SDE_TRANSA_FIFO_UNDER : - SDE_TRANSB_FIFO_UNDER; + uint32_t bit = (pch_transcoder == TRANSCODER_A) ? + SDE_TRANSA_FIFO_UNDER : SDE_TRANSB_FIFO_UNDER; if (enable) - I915_WRITE(SDEIMR, I915_READ(SDEIMR) & ~bit); + ibx_enable_display_interrupt(dev_priv, bit); else - I915_WRITE(SDEIMR, I915_READ(SDEIMR) | bit); - - POSTING_READ(SDEIMR); + ibx_disable_display_interrupt(dev_priv, bit); } static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, @@ -193,19 +223,26 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, struct drm_i915_private *dev_priv = dev->dev_private; if (enable) { + I915_WRITE(SERR_INT, + SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder)); + if (!cpt_can_enable_serr_int(dev)) return; - I915_WRITE(SERR_INT, SERR_INT_TRANS_A_FIFO_UNDERRUN | - SERR_INT_TRANS_B_FIFO_UNDERRUN | - SERR_INT_TRANS_C_FIFO_UNDERRUN); - - I915_WRITE(SDEIMR, I915_READ(SDEIMR) & ~SDE_ERROR_CPT); + ibx_enable_display_interrupt(dev_priv, SDE_ERROR_CPT); } else { - I915_WRITE(SDEIMR, I915_READ(SDEIMR) | SDE_ERROR_CPT); - } + uint32_t tmp = I915_READ(SERR_INT); + bool was_enabled = !(I915_READ(SDEIMR) & SDE_ERROR_CPT); - POSTING_READ(SDEIMR); + /* Change the state _after_ we've read out the current one. */ + ibx_disable_display_interrupt(dev_priv, SDE_ERROR_CPT); + + if (!was_enabled && + (tmp & SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder))) { + DRM_DEBUG_KMS("uncleared pch fifo underrun on pch transcoder %c\n", + transcoder_name(pch_transcoder)); + } + } } /** @@ -243,7 +280,7 @@ bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, if (IS_GEN5(dev) || IS_GEN6(dev)) ironlake_set_fifo_underrun_reporting(dev, pipe, enable); else if (IS_GEN7(dev)) - ivybridge_set_fifo_underrun_reporting(dev, enable); + ivybridge_set_fifo_underrun_reporting(dev, pipe, enable); done: spin_unlock_irqrestore(&dev_priv->irq_lock, flags); @@ -269,29 +306,19 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev, bool enable) { struct drm_i915_private *dev_priv = dev->dev_private; - enum pipe p; - struct drm_crtc *crtc; - struct intel_crtc *intel_crtc; + struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pch_transcoder]; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); unsigned long flags; bool ret; - if (HAS_PCH_LPT(dev)) { - crtc = NULL; - for_each_pipe(p) { - struct drm_crtc *c = dev_priv->pipe_to_crtc_mapping[p]; - if (intel_pipe_has_type(c, INTEL_OUTPUT_ANALOG)) { - crtc = c; - break; - } - } - if (!crtc) { - DRM_ERROR("PCH FIFO underrun, but no CRTC using the PCH found\n"); - return false; - } - } else { - crtc = dev_priv->pipe_to_crtc_mapping[pch_transcoder]; - } - intel_crtc = to_intel_crtc(crtc); + /* + * NOTE: Pre-LPT has a fixed cpu pipe -> pch transcoder mapping, but LPT + * has only one pch transcoder A that all pipes can use. To avoid racy + * pch transcoder -> pipe lookups from interrupt code simply store the + * underrun statistics in crtc A. Since we never expose this anywhere + * nor use it outside of the fifo underrun code here using the "wrong" + * crtc on LPT won't cause issues. + */ spin_lock_irqsave(&dev_priv->irq_lock, flags); @@ -303,7 +330,7 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev, intel_crtc->pch_fifo_underrun_disabled = !enable; if (HAS_PCH_IBX(dev)) - ibx_set_fifo_underrun_reporting(intel_crtc, enable); + ibx_set_fifo_underrun_reporting(dev, pch_transcoder, enable); else cpt_set_fifo_underrun_reporting(dev, pch_transcoder, enable); @@ -319,6 +346,8 @@ i915_enable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask) u32 reg = PIPESTAT(pipe); u32 pipestat = I915_READ(reg) & 0x7fff0000; + assert_spin_locked(&dev_priv->irq_lock); + if ((pipestat & mask) == mask) return; @@ -334,6 +363,8 @@ i915_disable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask) u32 reg = PIPESTAT(pipe); u32 pipestat = I915_READ(reg) & 0x7fff0000; + assert_spin_locked(&dev_priv->irq_lock); + if ((pipestat & mask) == 0) return; @@ -625,14 +656,13 @@ static void i915_hotplug_work_func(struct work_struct *work) drm_kms_helper_hotplug_event(dev); } -static void ironlake_handle_rps_change(struct drm_device *dev) +static void ironlake_rps_change_irq_handler(struct drm_device *dev) { drm_i915_private_t *dev_priv = dev->dev_private; u32 busy_up, busy_down, max_avg, min_avg; u8 new_delay; - unsigned long flags; - spin_lock_irqsave(&mchdev_lock, flags); + spin_lock(&mchdev_lock); I915_WRITE16(MEMINTRSTS, I915_READ(MEMINTRSTS)); @@ -660,7 +690,7 @@ static void ironlake_handle_rps_change(struct drm_device *dev) if (ironlake_set_drps(dev, new_delay)) dev_priv->ips.cur_delay = new_delay; - spin_unlock_irqrestore(&mchdev_lock, flags); + spin_unlock(&mchdev_lock); return; } @@ -668,18 +698,13 @@ static void ironlake_handle_rps_change(struct drm_device *dev) static void notify_ring(struct drm_device *dev, struct intel_ring_buffer *ring) { - struct drm_i915_private *dev_priv = dev->dev_private; - if (ring->obj == NULL) return; trace_i915_gem_request_complete(ring, ring->get_seqno(ring, false)); wake_up_all(&ring->irq_queue); - if (i915_enable_hangcheck) { - mod_timer(&dev_priv->gpu_error.hangcheck_timer, - round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES)); - } + i915_queue_hangcheck(dev); } static void gen6_pm_rps_work(struct work_struct *work) @@ -689,13 +714,13 @@ static void gen6_pm_rps_work(struct work_struct *work) u32 pm_iir, pm_imr; u8 new_delay; - spin_lock_irq(&dev_priv->rps.lock); + spin_lock_irq(&dev_priv->irq_lock); pm_iir = dev_priv->rps.pm_iir; dev_priv->rps.pm_iir = 0; pm_imr = I915_READ(GEN6_PMIMR); /* Make sure not to corrupt PMIMR state used by ringbuffer code */ I915_WRITE(GEN6_PMIMR, pm_imr & ~GEN6_PM_RPS_EVENTS); - spin_unlock_irq(&dev_priv->rps.lock); + spin_unlock_irq(&dev_priv->irq_lock); if ((pm_iir & GEN6_PM_RPS_EVENTS) == 0) return; @@ -787,7 +812,7 @@ static void ivybridge_parity_work(struct work_struct *work) mutex_unlock(&dev_priv->dev->struct_mutex); - parity_event[0] = "L3_PARITY_ERROR=1"; + parity_event[0] = I915_L3_PARITY_UEVENT "=1"; parity_event[1] = kasprintf(GFP_KERNEL, "ROW=%d", row); parity_event[2] = kasprintf(GFP_KERNEL, "BANK=%d", bank); parity_event[3] = kasprintf(GFP_KERNEL, "SUBBANK=%d", subbank); @@ -804,22 +829,32 @@ static void ivybridge_parity_work(struct work_struct *work) kfree(parity_event[1]); } -static void ivybridge_handle_parity_error(struct drm_device *dev) +static void ivybridge_parity_error_irq_handler(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; - unsigned long flags; if (!HAS_L3_GPU_CACHE(dev)) return; - spin_lock_irqsave(&dev_priv->irq_lock, flags); + spin_lock(&dev_priv->irq_lock); dev_priv->gt_irq_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT; I915_WRITE(GTIMR, dev_priv->gt_irq_mask); - spin_unlock_irqrestore(&dev_priv->irq_lock, flags); + spin_unlock(&dev_priv->irq_lock); queue_work(dev_priv->wq, &dev_priv->l3_parity.error_work); } +static void ilk_gt_irq_handler(struct drm_device *dev, + struct drm_i915_private *dev_priv, + u32 gt_iir) +{ + if (gt_iir & + (GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT)) + notify_ring(dev, &dev_priv->ring[RCS]); + if (gt_iir & ILK_BSD_USER_INTERRUPT) + notify_ring(dev, &dev_priv->ring[VCS]); +} + static void snb_gt_irq_handler(struct drm_device *dev, struct drm_i915_private *dev_priv, u32 gt_iir) @@ -841,15 +876,13 @@ static void snb_gt_irq_handler(struct drm_device *dev, } if (gt_iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT) - ivybridge_handle_parity_error(dev); + ivybridge_parity_error_irq_handler(dev); } /* Legacy way of handling PM interrupts */ -static void gen6_queue_rps_work(struct drm_i915_private *dev_priv, - u32 pm_iir) +static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, + u32 pm_iir) { - unsigned long flags; - /* * IIR bits should never already be set because IMR should * prevent an interrupt from being shown in IIR. The warning @@ -860,11 +893,11 @@ static void gen6_queue_rps_work(struct drm_i915_private *dev_priv, * The mask bit in IMR is cleared by dev_priv->rps.work. */ - spin_lock_irqsave(&dev_priv->rps.lock, flags); + spin_lock(&dev_priv->irq_lock); dev_priv->rps.pm_iir |= pm_iir; I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir); POSTING_READ(GEN6_PMIMR); - spin_unlock_irqrestore(&dev_priv->rps.lock, flags); + spin_unlock(&dev_priv->irq_lock); queue_work(dev_priv->wq, &dev_priv->rps.work); } @@ -928,7 +961,7 @@ static void dp_aux_irq_handler(struct drm_device *dev) wake_up_all(&dev_priv->gmbus_wait_queue); } -/* Unlike gen6_queue_rps_work() from which this function is originally derived, +/* Unlike gen6_rps_irq_handler() from which this function is originally derived, * we must be able to deal with other PM interrupts. This is complicated because * of the way in which we use the masks to defer the RPS work (which for * posterity is necessary because of forcewake). @@ -936,27 +969,23 @@ static void dp_aux_irq_handler(struct drm_device *dev) static void hsw_pm_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir) { - unsigned long flags; - - spin_lock_irqsave(&dev_priv->rps.lock, flags); - dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_RPS_EVENTS; - if (dev_priv->rps.pm_iir) { + if (pm_iir & GEN6_PM_RPS_EVENTS) { + spin_lock(&dev_priv->irq_lock); + dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_RPS_EVENTS; I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir); /* never want to mask useful interrupts. (also posting read) */ WARN_ON(I915_READ_NOTRACE(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS); - /* TODO: if queue_work is slow, move it out of the spinlock */ + spin_unlock(&dev_priv->irq_lock); + queue_work(dev_priv->wq, &dev_priv->rps.work); } - spin_unlock_irqrestore(&dev_priv->rps.lock, flags); - if (pm_iir & ~GEN6_PM_RPS_EVENTS) { - if (pm_iir & PM_VEBOX_USER_INTERRUPT) - notify_ring(dev_priv->dev, &dev_priv->ring[VECS]); + if (pm_iir & PM_VEBOX_USER_INTERRUPT) + 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); - } + 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); } } @@ -1029,7 +1058,7 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg) gmbus_irq_handler(dev); if (pm_iir & GEN6_PM_RPS_EVENTS) - gen6_queue_rps_work(dev_priv, pm_iir); + gen6_rps_irq_handler(dev_priv, pm_iir); I915_WRITE(GTIIR, gt_iir); I915_WRITE(GEN6_PMIIR, pm_iir); @@ -1179,13 +1208,100 @@ static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir) cpt_serr_int_handler(dev); } -static irqreturn_t ivybridge_irq_handler(int irq, void *arg) +static void ilk_display_irq_handler(struct drm_device *dev, u32 de_iir) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (de_iir & DE_AUX_CHANNEL_A) + dp_aux_irq_handler(dev); + + if (de_iir & DE_GSE) + intel_opregion_asle_intr(dev); + + if (de_iir & DE_PIPEA_VBLANK) + drm_handle_vblank(dev, 0); + + if (de_iir & DE_PIPEB_VBLANK) + drm_handle_vblank(dev, 1); + + if (de_iir & DE_POISON) + DRM_ERROR("Poison interrupt\n"); + + if (de_iir & DE_PIPEA_FIFO_UNDERRUN) + if (intel_set_cpu_fifo_underrun_reporting(dev, PIPE_A, false)) + DRM_DEBUG_DRIVER("Pipe A FIFO underrun\n"); + + if (de_iir & DE_PIPEB_FIFO_UNDERRUN) + if (intel_set_cpu_fifo_underrun_reporting(dev, PIPE_B, false)) + DRM_DEBUG_DRIVER("Pipe B FIFO underrun\n"); + + if (de_iir & DE_PLANEA_FLIP_DONE) { + intel_prepare_page_flip(dev, 0); + intel_finish_page_flip_plane(dev, 0); + } + + if (de_iir & DE_PLANEB_FLIP_DONE) { + intel_prepare_page_flip(dev, 1); + intel_finish_page_flip_plane(dev, 1); + } + + /* check event from PCH */ + if (de_iir & DE_PCH_EVENT) { + u32 pch_iir = I915_READ(SDEIIR); + + if (HAS_PCH_CPT(dev)) + cpt_irq_handler(dev, pch_iir); + else + ibx_irq_handler(dev, pch_iir); + + /* should clear PCH hotplug event before clear CPU irq */ + I915_WRITE(SDEIIR, pch_iir); + } + + if (IS_GEN5(dev) && de_iir & DE_PCU_EVENT) + ironlake_rps_change_irq_handler(dev); +} + +static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int i; + + if (de_iir & DE_ERR_INT_IVB) + ivb_err_int_handler(dev); + + if (de_iir & DE_AUX_CHANNEL_A_IVB) + dp_aux_irq_handler(dev); + + if (de_iir & DE_GSE_IVB) + intel_opregion_asle_intr(dev); + + for (i = 0; i < 3; i++) { + if (de_iir & (DE_PIPEA_VBLANK_IVB << (5 * i))) + drm_handle_vblank(dev, i); + if (de_iir & (DE_PLANEA_FLIP_DONE_IVB << (5 * i))) { + intel_prepare_page_flip(dev, i); + intel_finish_page_flip_plane(dev, i); + } + } + + /* check event from PCH */ + if (!HAS_PCH_NOP(dev) && (de_iir & DE_PCH_EVENT_IVB)) { + u32 pch_iir = I915_READ(SDEIIR); + + cpt_irq_handler(dev, pch_iir); + + /* clear PCH hotplug event before clear CPU irq */ + I915_WRITE(SDEIIR, pch_iir); + } +} + +static irqreturn_t ironlake_irq_handler(int irq, void *arg) { struct drm_device *dev = (struct drm_device *) arg; drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; - u32 de_iir, gt_iir, de_ier, pm_iir, sde_ier = 0; + u32 de_iir, gt_iir, de_ier, sde_ier = 0; irqreturn_t ret = IRQ_NONE; - int i; atomic_inc(&dev_priv->irq_received); @@ -1200,6 +1316,7 @@ static irqreturn_t ivybridge_irq_handler(int irq, void *arg) /* disable master interrupt before clearing iir */ de_ier = I915_READ(DEIER); I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL); + POSTING_READ(DEIER); /* Disable south interrupts. We'll only write to SDEIIR once, so further * interrupts will will be stored on its back queue, and then we'll be @@ -1223,53 +1340,34 @@ static irqreturn_t ivybridge_irq_handler(int irq, void *arg) gt_iir = I915_READ(GTIIR); if (gt_iir) { - snb_gt_irq_handler(dev, dev_priv, gt_iir); + if (INTEL_INFO(dev)->gen >= 6) + snb_gt_irq_handler(dev, dev_priv, gt_iir); + else + ilk_gt_irq_handler(dev, dev_priv, gt_iir); I915_WRITE(GTIIR, gt_iir); ret = IRQ_HANDLED; } de_iir = I915_READ(DEIIR); if (de_iir) { - if (de_iir & DE_ERR_INT_IVB) - ivb_err_int_handler(dev); - - if (de_iir & DE_AUX_CHANNEL_A_IVB) - dp_aux_irq_handler(dev); - - if (de_iir & DE_GSE_IVB) - intel_opregion_asle_intr(dev); - - for (i = 0; i < 3; i++) { - if (de_iir & (DE_PIPEA_VBLANK_IVB << (5 * i))) - drm_handle_vblank(dev, i); - if (de_iir & (DE_PLANEA_FLIP_DONE_IVB << (5 * i))) { - intel_prepare_page_flip(dev, i); - intel_finish_page_flip_plane(dev, i); - } - } - - /* check event from PCH */ - if (!HAS_PCH_NOP(dev) && (de_iir & DE_PCH_EVENT_IVB)) { - u32 pch_iir = I915_READ(SDEIIR); - - cpt_irq_handler(dev, pch_iir); - - /* clear PCH hotplug event before clear CPU irq */ - I915_WRITE(SDEIIR, pch_iir); - } - + if (INTEL_INFO(dev)->gen >= 7) + ivb_display_irq_handler(dev, de_iir); + else + ilk_display_irq_handler(dev, de_iir); I915_WRITE(DEIIR, de_iir); ret = IRQ_HANDLED; } - pm_iir = I915_READ(GEN6_PMIIR); - if (pm_iir) { - if (IS_HASWELL(dev)) - hsw_pm_irq_handler(dev_priv, pm_iir); - else if (pm_iir & GEN6_PM_RPS_EVENTS) - gen6_queue_rps_work(dev_priv, pm_iir); - I915_WRITE(GEN6_PMIIR, pm_iir); - ret = IRQ_HANDLED; + if (INTEL_INFO(dev)->gen >= 6) { + u32 pm_iir = I915_READ(GEN6_PMIIR); + if (pm_iir) { + if (IS_HASWELL(dev)) + hsw_pm_irq_handler(dev_priv, pm_iir); + else if (pm_iir & GEN6_PM_RPS_EVENTS) + gen6_rps_irq_handler(dev_priv, pm_iir); + I915_WRITE(GEN6_PMIIR, pm_iir); + ret = IRQ_HANDLED; + } } if (IS_HASWELL(dev)) { @@ -1289,119 +1387,6 @@ static irqreturn_t ivybridge_irq_handler(int irq, void *arg) return ret; } -static void ilk_gt_irq_handler(struct drm_device *dev, - struct drm_i915_private *dev_priv, - u32 gt_iir) -{ - if (gt_iir & - (GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT)) - notify_ring(dev, &dev_priv->ring[RCS]); - if (gt_iir & ILK_BSD_USER_INTERRUPT) - notify_ring(dev, &dev_priv->ring[VCS]); -} - -static irqreturn_t ironlake_irq_handler(int irq, void *arg) -{ - struct drm_device *dev = (struct drm_device *) arg; - drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; - int ret = IRQ_NONE; - u32 de_iir, gt_iir, de_ier, pm_iir, sde_ier; - - atomic_inc(&dev_priv->irq_received); - - /* disable master interrupt before clearing iir */ - de_ier = I915_READ(DEIER); - I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL); - POSTING_READ(DEIER); - - /* Disable south interrupts. We'll only write to SDEIIR once, so further - * interrupts will will be stored on its back queue, and then we'll be - * able to process them after we restore SDEIER (as soon as we restore - * it, we'll get an interrupt if SDEIIR still has something to process - * due to its back queue). */ - sde_ier = I915_READ(SDEIER); - I915_WRITE(SDEIER, 0); - POSTING_READ(SDEIER); - - de_iir = I915_READ(DEIIR); - gt_iir = I915_READ(GTIIR); - pm_iir = I915_READ(GEN6_PMIIR); - - if (de_iir == 0 && gt_iir == 0 && (!IS_GEN6(dev) || pm_iir == 0)) - goto done; - - ret = IRQ_HANDLED; - - if (IS_GEN5(dev)) - ilk_gt_irq_handler(dev, dev_priv, gt_iir); - else - snb_gt_irq_handler(dev, dev_priv, gt_iir); - - if (de_iir & DE_AUX_CHANNEL_A) - dp_aux_irq_handler(dev); - - if (de_iir & DE_GSE) - intel_opregion_asle_intr(dev); - - if (de_iir & DE_PIPEA_VBLANK) - drm_handle_vblank(dev, 0); - - if (de_iir & DE_PIPEB_VBLANK) - drm_handle_vblank(dev, 1); - - if (de_iir & DE_POISON) - DRM_ERROR("Poison interrupt\n"); - - if (de_iir & DE_PIPEA_FIFO_UNDERRUN) - if (intel_set_cpu_fifo_underrun_reporting(dev, PIPE_A, false)) - DRM_DEBUG_DRIVER("Pipe A FIFO underrun\n"); - - if (de_iir & DE_PIPEB_FIFO_UNDERRUN) - if (intel_set_cpu_fifo_underrun_reporting(dev, PIPE_B, false)) - DRM_DEBUG_DRIVER("Pipe B FIFO underrun\n"); - - if (de_iir & DE_PLANEA_FLIP_DONE) { - intel_prepare_page_flip(dev, 0); - intel_finish_page_flip_plane(dev, 0); - } - - if (de_iir & DE_PLANEB_FLIP_DONE) { - intel_prepare_page_flip(dev, 1); - intel_finish_page_flip_plane(dev, 1); - } - - /* check event from PCH */ - if (de_iir & DE_PCH_EVENT) { - u32 pch_iir = I915_READ(SDEIIR); - - if (HAS_PCH_CPT(dev)) - cpt_irq_handler(dev, pch_iir); - else - ibx_irq_handler(dev, pch_iir); - - /* should clear PCH hotplug event before clear CPU irq */ - I915_WRITE(SDEIIR, pch_iir); - } - - if (IS_GEN5(dev) && de_iir & DE_PCU_EVENT) - ironlake_handle_rps_change(dev); - - if (IS_GEN6(dev) && pm_iir & GEN6_PM_RPS_EVENTS) - gen6_queue_rps_work(dev_priv, pm_iir); - - I915_WRITE(GTIIR, gt_iir); - I915_WRITE(DEIIR, de_iir); - I915_WRITE(GEN6_PMIIR, pm_iir); - -done: - I915_WRITE(DEIER, de_ier); - POSTING_READ(DEIER); - I915_WRITE(SDEIER, sde_ier); - POSTING_READ(SDEIER); - - return ret; -} - /** * i915_error_work_func - do process context error handling work * @work: work struct @@ -1417,9 +1402,9 @@ static void i915_error_work_func(struct work_struct *work) gpu_error); struct drm_device *dev = dev_priv->dev; struct intel_ring_buffer *ring; - char *error_event[] = { "ERROR=1", NULL }; - char *reset_event[] = { "RESET=1", NULL }; - char *reset_done_event[] = { "ERROR=0", NULL }; + char *error_event[] = { I915_ERROR_UEVENT "=1", NULL }; + char *reset_event[] = { I915_RESET_UEVENT "=1", NULL }; + char *reset_done_event[] = { I915_ERROR_UEVENT "=0", NULL }; int i, ret; kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, error_event); @@ -1470,535 +1455,6 @@ static void i915_error_work_func(struct work_struct *work) } } -/* NB: please notice the memset */ -static void i915_get_extra_instdone(struct drm_device *dev, - uint32_t *instdone) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - memset(instdone, 0, sizeof(*instdone) * I915_NUM_INSTDONE_REG); - - switch(INTEL_INFO(dev)->gen) { - case 2: - case 3: - instdone[0] = I915_READ(INSTDONE); - break; - case 4: - case 5: - case 6: - instdone[0] = I915_READ(INSTDONE_I965); - instdone[1] = I915_READ(INSTDONE1); - break; - default: - WARN_ONCE(1, "Unsupported platform\n"); - case 7: - instdone[0] = I915_READ(GEN7_INSTDONE_1); - instdone[1] = I915_READ(GEN7_SC_INSTDONE); - instdone[2] = I915_READ(GEN7_SAMPLER_INSTDONE); - instdone[3] = I915_READ(GEN7_ROW_INSTDONE); - break; - } -} - -#ifdef CONFIG_DEBUG_FS -static struct drm_i915_error_object * -i915_error_object_create_sized(struct drm_i915_private *dev_priv, - struct drm_i915_gem_object *src, - const int num_pages) -{ - struct drm_i915_error_object *dst; - int i; - u32 reloc_offset; - - if (src == NULL || src->pages == NULL) - return NULL; - - dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), GFP_ATOMIC); - if (dst == NULL) - return NULL; - - reloc_offset = src->gtt_offset; - for (i = 0; i < num_pages; i++) { - unsigned long flags; - void *d; - - d = kmalloc(PAGE_SIZE, GFP_ATOMIC); - if (d == NULL) - goto unwind; - - local_irq_save(flags); - if (reloc_offset < dev_priv->gtt.mappable_end && - src->has_global_gtt_mapping) { - void __iomem *s; - - /* Simply ignore tiling or any overlapping fence. - * It's part of the error state, and this hopefully - * captures what the GPU read. - */ - - s = io_mapping_map_atomic_wc(dev_priv->gtt.mappable, - reloc_offset); - memcpy_fromio(d, s, PAGE_SIZE); - io_mapping_unmap_atomic(s); - } else if (src->stolen) { - unsigned long offset; - - offset = dev_priv->mm.stolen_base; - offset += src->stolen->start; - offset += i << PAGE_SHIFT; - - memcpy_fromio(d, (void __iomem *) offset, PAGE_SIZE); - } else { - struct page *page; - void *s; - - page = i915_gem_object_get_page(src, i); - - drm_clflush_pages(&page, 1); - - s = kmap_atomic(page); - memcpy(d, s, PAGE_SIZE); - kunmap_atomic(s); - - drm_clflush_pages(&page, 1); - } - local_irq_restore(flags); - - dst->pages[i] = d; - - reloc_offset += PAGE_SIZE; - } - dst->page_count = num_pages; - dst->gtt_offset = src->gtt_offset; - - return dst; - -unwind: - while (i--) - kfree(dst->pages[i]); - kfree(dst); - return NULL; -} -#define i915_error_object_create(dev_priv, src) \ - i915_error_object_create_sized((dev_priv), (src), \ - (src)->base.size>>PAGE_SHIFT) - -static void -i915_error_object_free(struct drm_i915_error_object *obj) -{ - int page; - - if (obj == NULL) - return; - - for (page = 0; page < obj->page_count; page++) - kfree(obj->pages[page]); - - kfree(obj); -} - -void -i915_error_state_free(struct kref *error_ref) -{ - struct drm_i915_error_state *error = container_of(error_ref, - typeof(*error), ref); - int i; - - for (i = 0; i < ARRAY_SIZE(error->ring); i++) { - i915_error_object_free(error->ring[i].batchbuffer); - i915_error_object_free(error->ring[i].ringbuffer); - i915_error_object_free(error->ring[i].ctx); - kfree(error->ring[i].requests); - } - - kfree(error->active_bo); - kfree(error->overlay); - kfree(error->display); - kfree(error); -} -static void capture_bo(struct drm_i915_error_buffer *err, - struct drm_i915_gem_object *obj) -{ - err->size = obj->base.size; - err->name = obj->base.name; - err->rseqno = obj->last_read_seqno; - err->wseqno = obj->last_write_seqno; - err->gtt_offset = obj->gtt_offset; - err->read_domains = obj->base.read_domains; - err->write_domain = obj->base.write_domain; - err->fence_reg = obj->fence_reg; - err->pinned = 0; - if (obj->pin_count > 0) - err->pinned = 1; - if (obj->user_pin_count > 0) - err->pinned = -1; - err->tiling = obj->tiling_mode; - err->dirty = obj->dirty; - err->purgeable = obj->madv != I915_MADV_WILLNEED; - err->ring = obj->ring ? obj->ring->id : -1; - err->cache_level = obj->cache_level; -} - -static u32 capture_active_bo(struct drm_i915_error_buffer *err, - int count, struct list_head *head) -{ - struct drm_i915_gem_object *obj; - int i = 0; - - list_for_each_entry(obj, head, mm_list) { - capture_bo(err++, obj); - if (++i == count) - break; - } - - return i; -} - -static u32 capture_pinned_bo(struct drm_i915_error_buffer *err, - int count, struct list_head *head) -{ - struct drm_i915_gem_object *obj; - int i = 0; - - list_for_each_entry(obj, head, global_list) { - if (obj->pin_count == 0) - continue; - - capture_bo(err++, obj); - if (++i == count) - break; - } - - return i; -} - -static void i915_gem_record_fences(struct drm_device *dev, - struct drm_i915_error_state *error) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - int i; - - /* Fences */ - switch (INTEL_INFO(dev)->gen) { - case 7: - case 6: - for (i = 0; i < dev_priv->num_fence_regs; i++) - error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8)); - break; - case 5: - case 4: - for (i = 0; i < 16; i++) - error->fence[i] = I915_READ64(FENCE_REG_965_0 + (i * 8)); - break; - case 3: - if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) - for (i = 0; i < 8; i++) - error->fence[i+8] = I915_READ(FENCE_REG_945_8 + (i * 4)); - case 2: - for (i = 0; i < 8; i++) - error->fence[i] = I915_READ(FENCE_REG_830_0 + (i * 4)); - break; - - default: - BUG(); - } -} - -static struct drm_i915_error_object * -i915_error_first_batchbuffer(struct drm_i915_private *dev_priv, - struct intel_ring_buffer *ring) -{ - struct drm_i915_gem_object *obj; - 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->private; - if (acthd >= obj->gtt_offset && - acthd < obj->gtt_offset + obj->base.size) - return i915_error_object_create(dev_priv, obj); - } - - seqno = ring->get_seqno(ring, false); - list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) { - 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); - } - - return NULL; -} - -static void i915_record_ring_state(struct drm_device *dev, - struct drm_i915_error_state *error, - struct intel_ring_buffer *ring) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - - if (INTEL_INFO(dev)->gen >= 6) { - error->rc_psmi[ring->id] = I915_READ(ring->mmio_base + 0x50); - error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring)); - error->semaphore_mboxes[ring->id][0] - = I915_READ(RING_SYNC_0(ring->mmio_base)); - error->semaphore_mboxes[ring->id][1] - = I915_READ(RING_SYNC_1(ring->mmio_base)); - error->semaphore_seqno[ring->id][0] = ring->sync_seqno[0]; - error->semaphore_seqno[ring->id][1] = ring->sync_seqno[1]; - } - - if (INTEL_INFO(dev)->gen >= 4) { - error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base)); - error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base)); - error->ipehr[ring->id] = I915_READ(RING_IPEHR(ring->mmio_base)); - error->instdone[ring->id] = I915_READ(RING_INSTDONE(ring->mmio_base)); - error->instps[ring->id] = I915_READ(RING_INSTPS(ring->mmio_base)); - if (ring->id == RCS) - error->bbaddr = I915_READ64(BB_ADDR); - } else { - error->faddr[ring->id] = I915_READ(DMA_FADD_I8XX); - error->ipeir[ring->id] = I915_READ(IPEIR); - error->ipehr[ring->id] = I915_READ(IPEHR); - error->instdone[ring->id] = I915_READ(INSTDONE); - } - - error->waiting[ring->id] = waitqueue_active(&ring->irq_queue); - error->instpm[ring->id] = I915_READ(RING_INSTPM(ring->mmio_base)); - error->seqno[ring->id] = ring->get_seqno(ring, false); - error->acthd[ring->id] = intel_ring_get_active_head(ring); - error->head[ring->id] = I915_READ_HEAD(ring); - error->tail[ring->id] = I915_READ_TAIL(ring); - error->ctl[ring->id] = I915_READ_CTL(ring); - - error->cpu_ring_head[ring->id] = ring->head; - error->cpu_ring_tail[ring->id] = ring->tail; -} - - -static void i915_gem_record_active_context(struct intel_ring_buffer *ring, - struct drm_i915_error_state *error, - struct drm_i915_error_ring *ering) -{ - struct drm_i915_private *dev_priv = ring->dev->dev_private; - struct drm_i915_gem_object *obj; - - /* Currently render ring is the only HW context user */ - if (ring->id != RCS || !error->ccid) - return; - - list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { - if ((error->ccid & PAGE_MASK) == obj->gtt_offset) { - ering->ctx = i915_error_object_create_sized(dev_priv, - obj, 1); - } - } -} - -static void i915_gem_record_rings(struct drm_device *dev, - struct drm_i915_error_state *error) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; - struct drm_i915_gem_request *request; - int i, count; - - for_each_ring(ring, dev_priv, i) { - i915_record_ring_state(dev, error, ring); - - error->ring[i].batchbuffer = - i915_error_first_batchbuffer(dev_priv, ring); - - error->ring[i].ringbuffer = - i915_error_object_create(dev_priv, ring->obj); - - - i915_gem_record_active_context(ring, error, &error->ring[i]); - - count = 0; - list_for_each_entry(request, &ring->request_list, list) - count++; - - error->ring[i].num_requests = count; - error->ring[i].requests = - kmalloc(count*sizeof(struct drm_i915_error_request), - GFP_ATOMIC); - if (error->ring[i].requests == NULL) { - error->ring[i].num_requests = 0; - continue; - } - - count = 0; - list_for_each_entry(request, &ring->request_list, list) { - struct drm_i915_error_request *erq; - - erq = &error->ring[i].requests[count++]; - erq->seqno = request->seqno; - erq->jiffies = request->emitted_jiffies; - erq->tail = request->tail; - } - } -} - -/** - * i915_capture_error_state - capture an error record for later analysis - * @dev: drm device - * - * Should be called when an error is detected (either a hang or an error - * interrupt) to capture error state from the time of the error. Fills - * out a structure which becomes available in debugfs for user level tools - * to pick up. - */ -static void i915_capture_error_state(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_i915_gem_object *obj; - struct drm_i915_error_state *error; - unsigned long flags; - int i, pipe; - - 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); - if (!error) { - DRM_DEBUG_DRIVER("out of memory, not capturing error state\n"); - return; - } - - DRM_INFO("capturing error event; look for more information in " - "/sys/kernel/debug/dri/%d/i915_error_state\n", - dev->primary->index); - - kref_init(&error->ref); - error->eir = I915_READ(EIR); - error->pgtbl_er = I915_READ(PGTBL_ER); - if (HAS_HW_CONTEXTS(dev)) - error->ccid = I915_READ(CCID); - - if (HAS_PCH_SPLIT(dev)) - error->ier = I915_READ(DEIER) | I915_READ(GTIER); - else if (IS_VALLEYVIEW(dev)) - error->ier = I915_READ(GTIER) | I915_READ(VLV_IER); - else if (IS_GEN2(dev)) - error->ier = I915_READ16(IER); - else - error->ier = I915_READ(IER); - - if (INTEL_INFO(dev)->gen >= 6) - error->derrmr = I915_READ(DERRMR); - - if (IS_VALLEYVIEW(dev)) - error->forcewake = I915_READ(FORCEWAKE_VLV); - else if (INTEL_INFO(dev)->gen >= 7) - error->forcewake = I915_READ(FORCEWAKE_MT); - else if (INTEL_INFO(dev)->gen == 6) - error->forcewake = I915_READ(FORCEWAKE); - - if (!HAS_PCH_SPLIT(dev)) - for_each_pipe(pipe) - error->pipestat[pipe] = I915_READ(PIPESTAT(pipe)); - - if (INTEL_INFO(dev)->gen >= 6) { - error->error = I915_READ(ERROR_GEN6); - error->done_reg = I915_READ(DONE_REG); - } - - if (INTEL_INFO(dev)->gen == 7) - error->err_int = I915_READ(GEN7_ERR_INT); - - i915_get_extra_instdone(dev, error->extra_instdone); - - i915_gem_record_fences(dev, error); - i915_gem_record_rings(dev, error); - - /* Record buffers on the active and pinned lists. */ - error->active_bo = NULL; - error->pinned_bo = NULL; - - i = 0; - list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) - i++; - error->active_bo_count = i; - list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) - if (obj->pin_count) - i++; - error->pinned_bo_count = i - error->active_bo_count; - - error->active_bo = NULL; - error->pinned_bo = NULL; - if (i) { - error->active_bo = kmalloc(sizeof(*error->active_bo)*i, - GFP_ATOMIC); - if (error->active_bo) - error->pinned_bo = - error->active_bo + error->active_bo_count; - } - - if (error->active_bo) - error->active_bo_count = - capture_active_bo(error->active_bo, - error->active_bo_count, - &dev_priv->mm.active_list); - - if (error->pinned_bo) - error->pinned_bo_count = - capture_pinned_bo(error->pinned_bo, - error->pinned_bo_count, - &dev_priv->mm.bound_list); - - do_gettimeofday(&error->time); - - error->overlay = intel_overlay_capture_error_state(dev); - error->display = intel_display_capture_error_state(dev); - - spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); - if (dev_priv->gpu_error.first_error == NULL) { - dev_priv->gpu_error.first_error = error; - error = NULL; - } - spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); - - if (error) - i915_error_state_free(&error->ref); -} - -void i915_destroy_error_state(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_i915_error_state *error; - unsigned long flags; - - spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); - error = dev_priv->gpu_error.first_error; - dev_priv->gpu_error.first_error = NULL; - spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); - - if (error) - kref_put(&error->ref, i915_error_state_free); -} -#else -#define i915_capture_error_state(x) -#endif - static void i915_report_and_clear_eir(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -2155,10 +1611,10 @@ static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, in if (INTEL_INFO(dev)->gen >= 4) { int dspsurf = DSPSURF(intel_crtc->plane); stall_detected = I915_HI_DISPBASE(I915_READ(dspsurf)) == - obj->gtt_offset; + i915_gem_obj_ggtt_offset(obj); } else { int dspaddr = DSPADDR(intel_crtc->plane); - stall_detected = I915_READ(dspaddr) == (obj->gtt_offset + + stall_detected = I915_READ(dspaddr) == (i915_gem_obj_ggtt_offset(obj) + crtc->y * crtc->fb->pitches[0] + crtc->x * crtc->fb->bits_per_pixel/8); } @@ -2202,29 +1658,14 @@ static int ironlake_enable_vblank(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; unsigned long irqflags; + uint32_t bit = (INTEL_INFO(dev)->gen >= 7) ? DE_PIPE_VBLANK_IVB(pipe) : + DE_PIPE_VBLANK_ILK(pipe); if (!i915_pipe_enabled(dev, pipe)) return -EINVAL; spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - ironlake_enable_display_irq(dev_priv, (pipe == 0) ? - DE_PIPEA_VBLANK : DE_PIPEB_VBLANK); - spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); - - return 0; -} - -static int ivybridge_enable_vblank(struct drm_device *dev, int pipe) -{ - drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; - unsigned long irqflags; - - if (!i915_pipe_enabled(dev, pipe)) - return -EINVAL; - - spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - ironlake_enable_display_irq(dev_priv, - DE_PIPEA_VBLANK_IVB << (5 * pipe)); + ironlake_enable_display_irq(dev_priv, bit); spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); return 0; @@ -2275,21 +1716,11 @@ static void ironlake_disable_vblank(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; unsigned long irqflags; + uint32_t bit = (INTEL_INFO(dev)->gen >= 7) ? DE_PIPE_VBLANK_IVB(pipe) : + DE_PIPE_VBLANK_ILK(pipe); spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - ironlake_disable_display_irq(dev_priv, (pipe == 0) ? - DE_PIPEA_VBLANK : DE_PIPEB_VBLANK); - spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); -} - -static void ivybridge_disable_vblank(struct drm_device *dev, int pipe) -{ - drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; - unsigned long irqflags; - - spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - ironlake_disable_display_irq(dev_priv, - DE_PIPEA_VBLANK_IVB << (pipe * 5)); + ironlake_disable_display_irq(dev_priv, bit); spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); } @@ -2536,9 +1967,17 @@ void i915_hangcheck_elapsed(unsigned long data) if (busy_count) /* Reset timer case chip hangs without another request * being added */ - mod_timer(&dev_priv->gpu_error.hangcheck_timer, - round_jiffies_up(jiffies + - DRM_I915_HANGCHECK_JIFFIES)); + i915_queue_hangcheck(dev); +} + +void i915_queue_hangcheck(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + if (!i915_enable_hangcheck) + return; + + mod_timer(&dev_priv->gpu_error.hangcheck_timer, + round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES)); } static void ibx_irq_preinstall(struct drm_device *dev) @@ -2560,31 +1999,26 @@ static void ibx_irq_preinstall(struct drm_device *dev) POSTING_READ(SDEIER); } -/* drm_dma.h hooks -*/ -static void ironlake_irq_preinstall(struct drm_device *dev) +static void gen5_gt_irq_preinstall(struct drm_device *dev) { - drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; - - atomic_set(&dev_priv->irq_received, 0); - - I915_WRITE(HWSTAM, 0xeffe); - - /* XXX hotplug from PCH */ - - I915_WRITE(DEIMR, 0xffffffff); - I915_WRITE(DEIER, 0x0); - POSTING_READ(DEIER); + struct drm_i915_private *dev_priv = dev->dev_private; /* and GT */ I915_WRITE(GTIMR, 0xffffffff); I915_WRITE(GTIER, 0x0); POSTING_READ(GTIER); - ibx_irq_preinstall(dev); + if (INTEL_INFO(dev)->gen >= 6) { + /* and PM */ + I915_WRITE(GEN6_PMIMR, 0xffffffff); + I915_WRITE(GEN6_PMIER, 0x0); + POSTING_READ(GEN6_PMIER); + } } -static void ivybridge_irq_preinstall(struct drm_device *dev) +/* drm_dma.h hooks +*/ +static void ironlake_irq_preinstall(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; @@ -2592,21 +2026,11 @@ static void ivybridge_irq_preinstall(struct drm_device *dev) I915_WRITE(HWSTAM, 0xeffe); - /* XXX hotplug from PCH */ - I915_WRITE(DEIMR, 0xffffffff); I915_WRITE(DEIER, 0x0); POSTING_READ(DEIER); - /* and GT */ - I915_WRITE(GTIMR, 0xffffffff); - I915_WRITE(GTIER, 0x0); - POSTING_READ(GTIER); - - /* Power management */ - I915_WRITE(GEN6_PMIMR, 0xffffffff); - I915_WRITE(GEN6_PMIER, 0x0); - POSTING_READ(GEN6_PMIER); + gen5_gt_irq_preinstall(dev); ibx_irq_preinstall(dev); } @@ -2627,9 +2051,8 @@ static void valleyview_irq_preinstall(struct drm_device *dev) /* and GT */ I915_WRITE(GTIIR, I915_READ(GTIIR)); I915_WRITE(GTIIR, I915_READ(GTIIR)); - I915_WRITE(GTIMR, 0xffffffff); - I915_WRITE(GTIER, 0x0); - POSTING_READ(GTIER); + + gen5_gt_irq_preinstall(dev); I915_WRITE(DPINVGTT, 0xff); @@ -2648,22 +2071,21 @@ static void ibx_hpd_irq_setup(struct drm_device *dev) drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; struct drm_mode_config *mode_config = &dev->mode_config; struct intel_encoder *intel_encoder; - u32 mask = ~I915_READ(SDEIMR); - u32 hotplug; + u32 hotplug_irqs, hotplug, enabled_irqs = 0; if (HAS_PCH_IBX(dev)) { - mask &= ~SDE_HOTPLUG_MASK; + hotplug_irqs = SDE_HOTPLUG_MASK; list_for_each_entry(intel_encoder, &mode_config->encoder_list, base.head) if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED) - mask |= hpd_ibx[intel_encoder->hpd_pin]; + enabled_irqs |= hpd_ibx[intel_encoder->hpd_pin]; } else { - mask &= ~SDE_HOTPLUG_MASK_CPT; + hotplug_irqs = SDE_HOTPLUG_MASK_CPT; list_for_each_entry(intel_encoder, &mode_config->encoder_list, base.head) if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED) - mask |= hpd_cpt[intel_encoder->hpd_pin]; + enabled_irqs |= hpd_cpt[intel_encoder->hpd_pin]; } - I915_WRITE(SDEIMR, ~mask); + ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); /* * Enable digital hotplug on the PCH, and configure the DP short pulse @@ -2700,123 +2122,102 @@ static void ibx_irq_postinstall(struct drm_device *dev) I915_WRITE(SDEIMR, ~mask); } -static int ironlake_irq_postinstall(struct drm_device *dev) +static void gen5_gt_irq_postinstall(struct drm_device *dev) { - unsigned long irqflags; - - drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; - /* enable kind of interrupts always enabled */ - u32 display_mask = DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT | - DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE | - DE_AUX_CHANNEL_A | DE_PIPEB_FIFO_UNDERRUN | - DE_PIPEA_FIFO_UNDERRUN | DE_POISON; - u32 gt_irqs; - - dev_priv->irq_mask = ~display_mask; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 pm_irqs, gt_irqs; - /* should always can generate irq */ - I915_WRITE(DEIIR, I915_READ(DEIIR)); - I915_WRITE(DEIMR, dev_priv->irq_mask); - I915_WRITE(DEIER, display_mask | - DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT); - POSTING_READ(DEIER); + pm_irqs = gt_irqs = 0; dev_priv->gt_irq_mask = ~0; + if (HAS_L3_GPU_CACHE(dev)) { + /* L3 parity interrupt is always unmasked. */ + dev_priv->gt_irq_mask = ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT; + gt_irqs |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT; + } - I915_WRITE(GTIIR, I915_READ(GTIIR)); - I915_WRITE(GTIMR, dev_priv->gt_irq_mask); - - gt_irqs = GT_RENDER_USER_INTERRUPT; - - if (IS_GEN6(dev)) - gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT; - else + gt_irqs |= GT_RENDER_USER_INTERRUPT; + if (IS_GEN5(dev)) { gt_irqs |= GT_RENDER_PIPECTL_NOTIFY_INTERRUPT | ILK_BSD_USER_INTERRUPT; + } else { + gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT; + } + I915_WRITE(GTIIR, I915_READ(GTIIR)); + I915_WRITE(GTIMR, dev_priv->gt_irq_mask); I915_WRITE(GTIER, gt_irqs); POSTING_READ(GTIER); - ibx_irq_postinstall(dev); + if (INTEL_INFO(dev)->gen >= 6) { + pm_irqs |= GEN6_PM_RPS_EVENTS; - if (IS_IRONLAKE_M(dev)) { - /* Enable PCU event interrupts - * - * spinlocking not required here for correctness since interrupt - * setup is guaranteed to run in single-threaded context. But we - * need it to make the assert_spin_locked happy. */ - spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - ironlake_enable_display_irq(dev_priv, DE_PCU_EVENT); - spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); - } + if (HAS_VEBOX(dev)) + pm_irqs |= PM_VEBOX_USER_INTERRUPT; - return 0; + I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR)); + I915_WRITE(GEN6_PMIMR, 0xffffffff); + I915_WRITE(GEN6_PMIER, pm_irqs); + POSTING_READ(GEN6_PMIER); + } } -static int ivybridge_irq_postinstall(struct drm_device *dev) +static int ironlake_irq_postinstall(struct drm_device *dev) { + unsigned long irqflags; drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; - /* enable kind of interrupts always enabled */ - u32 display_mask = - DE_MASTER_IRQ_CONTROL | DE_GSE_IVB | DE_PCH_EVENT_IVB | - DE_PLANEC_FLIP_DONE_IVB | - DE_PLANEB_FLIP_DONE_IVB | - DE_PLANEA_FLIP_DONE_IVB | - DE_AUX_CHANNEL_A_IVB | - DE_ERR_INT_IVB; - u32 pm_irqs = GEN6_PM_RPS_EVENTS; - u32 gt_irqs; + u32 display_mask, extra_mask; + + if (INTEL_INFO(dev)->gen >= 7) { + display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE_IVB | + DE_PCH_EVENT_IVB | DE_PLANEC_FLIP_DONE_IVB | + DE_PLANEB_FLIP_DONE_IVB | + DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB | + DE_ERR_INT_IVB); + extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB | + DE_PIPEA_VBLANK_IVB); + + I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT)); + } else { + display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT | + DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE | + DE_AUX_CHANNEL_A | DE_PIPEB_FIFO_UNDERRUN | + DE_PIPEA_FIFO_UNDERRUN | DE_POISON); + extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT; + } dev_priv->irq_mask = ~display_mask; /* should always can generate irq */ - I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT)); I915_WRITE(DEIIR, I915_READ(DEIIR)); I915_WRITE(DEIMR, dev_priv->irq_mask); - I915_WRITE(DEIER, - display_mask | - DE_PIPEC_VBLANK_IVB | - DE_PIPEB_VBLANK_IVB | - DE_PIPEA_VBLANK_IVB); + I915_WRITE(DEIER, display_mask | extra_mask); POSTING_READ(DEIER); - dev_priv->gt_irq_mask = ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT; - - I915_WRITE(GTIIR, I915_READ(GTIIR)); - I915_WRITE(GTIMR, dev_priv->gt_irq_mask); - - gt_irqs = GT_RENDER_USER_INTERRUPT | GT_BSD_USER_INTERRUPT | - GT_BLT_USER_INTERRUPT | GT_RENDER_L3_PARITY_ERROR_INTERRUPT; - I915_WRITE(GTIER, gt_irqs); - POSTING_READ(GTIER); - - I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR)); - if (HAS_VEBOX(dev)) - pm_irqs |= PM_VEBOX_USER_INTERRUPT | - PM_VEBOX_CS_ERROR_INTERRUPT; - - /* Our enable/disable rps functions may touch these registers so - * make sure to set a known state for only the non-RPS bits. - * The RMW is extra paranoia since this should be called after being set - * to a known state in preinstall. - * */ - I915_WRITE(GEN6_PMIMR, - (I915_READ(GEN6_PMIMR) | ~GEN6_PM_RPS_EVENTS) & ~pm_irqs); - I915_WRITE(GEN6_PMIER, - (I915_READ(GEN6_PMIER) & GEN6_PM_RPS_EVENTS) | pm_irqs); - POSTING_READ(GEN6_PMIER); + gen5_gt_irq_postinstall(dev); ibx_irq_postinstall(dev); + if (IS_IRONLAKE_M(dev)) { + /* Enable PCU event interrupts + * + * spinlocking not required here for correctness since interrupt + * setup is guaranteed to run in single-threaded context. But we + * need it to make the assert_spin_locked happy. */ + spin_lock_irqsave(&dev_priv->irq_lock, irqflags); + ironlake_enable_display_irq(dev_priv, DE_PCU_EVENT); + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + } + return 0; } static int valleyview_irq_postinstall(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; - u32 gt_irqs; u32 enable_mask; u32 pipestat_enable = PLANE_FLIP_DONE_INT_EN_VLV; + unsigned long irqflags; enable_mask = I915_DISPLAY_PORT_INTERRUPT; enable_mask |= I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | @@ -2842,20 +2243,18 @@ static int valleyview_irq_postinstall(struct drm_device *dev) 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, 0, pipestat_enable); i915_enable_pipestat(dev_priv, 0, PIPE_GMBUS_EVENT_ENABLE); i915_enable_pipestat(dev_priv, 1, pipestat_enable); + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); I915_WRITE(VLV_IIR, 0xffffffff); I915_WRITE(VLV_IIR, 0xffffffff); - I915_WRITE(GTIIR, I915_READ(GTIIR)); - I915_WRITE(GTIMR, dev_priv->gt_irq_mask); - - gt_irqs = GT_RENDER_USER_INTERRUPT | GT_BSD_USER_INTERRUPT | - GT_BLT_USER_INTERRUPT; - I915_WRITE(GTIER, gt_irqs); - POSTING_READ(GTIER); + gen5_gt_irq_postinstall(dev); /* ack & enable invalid PTE error interrupts */ #if 0 /* FIXME: add support to irq handler for checking these bits */ @@ -3323,6 +2722,7 @@ static int i965_irq_postinstall(struct drm_device *dev) drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; u32 enable_mask; u32 error_mask; + unsigned long irqflags; /* Unmask the interrupts that we always want on. */ dev_priv->irq_mask = ~(I915_ASLE_INTERRUPT | @@ -3341,7 +2741,11 @@ static int i965_irq_postinstall(struct drm_device *dev) if (IS_G4X(dev)) enable_mask |= I915_BSD_USER_INTERRUPT; + /* 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, 0, PIPE_GMBUS_EVENT_ENABLE); + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); /* * Enable some error detection, note the instruction error mask @@ -3616,15 +3020,6 @@ void intel_irq_init(struct drm_device *dev) dev->driver->enable_vblank = valleyview_enable_vblank; dev->driver->disable_vblank = valleyview_disable_vblank; dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup; - } else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) { - /* Share uninstall handlers with ILK/SNB */ - dev->driver->irq_handler = ivybridge_irq_handler; - dev->driver->irq_preinstall = ivybridge_irq_preinstall; - dev->driver->irq_postinstall = ivybridge_irq_postinstall; - dev->driver->irq_uninstall = ironlake_irq_uninstall; - dev->driver->enable_vblank = ivybridge_enable_vblank; - dev->driver->disable_vblank = ivybridge_disable_vblank; - dev_priv->display.hpd_irq_setup = ibx_hpd_irq_setup; } else if (HAS_PCH_SPLIT(dev)) { dev->driver->irq_handler = ironlake_irq_handler; dev->driver->irq_preinstall = ironlake_irq_preinstall; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f2326fc..6caa748 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -363,6 +363,7 @@ #define PUNIT_REG_GPU_LFM 0xd3 #define PUNIT_REG_GPU_FREQ_REQ 0xd4 #define PUNIT_REG_GPU_FREQ_STS 0xd8 +#define GENFREQSTATUS (1<<0) #define PUNIT_REG_MEDIA_TURBO_FREQ_REQ 0xdc #define PUNIT_FUSE_BUS2 0xf6 /* bits 47:40 */ @@ -680,6 +681,7 @@ #define ERR_INT_FIFO_UNDERRUN_C (1<<6) #define ERR_INT_FIFO_UNDERRUN_B (1<<3) #define ERR_INT_FIFO_UNDERRUN_A (1<<0) +#define ERR_INT_FIFO_UNDERRUN(pipe) (1<<(pipe*3)) #define FPGA_DBG 0x42300 #define FPGA_DBG_RM_NOCLAIM (1<<31) @@ -1125,7 +1127,8 @@ #define _DPLL_B (dev_priv->info->display_mmio_offset + 0x6018) #define DPLL(pipe) _PIPE(pipe, _DPLL_A, _DPLL_B) #define DPLL_VCO_ENABLE (1 << 31) -#define DPLL_DVO_HIGH_SPEED (1 << 30) +#define DPLL_SDVO_HIGH_SPEED (1 << 30) +#define DPLL_DVO_2X_MODE (1 << 30) #define DPLL_EXT_BUFFER_ENABLE_VLV (1 << 30) #define DPLL_SYNCLOCK_ENABLE (1 << 29) #define DPLL_REFA_CLK_ENABLE_VLV (1 << 29) @@ -1776,6 +1779,71 @@ #define BCLRPAT(pipe) _PIPE(pipe, _BCLRPAT_A, _BCLRPAT_B) #define VSYNCSHIFT(trans) _TRANSCODER(trans, _VSYNCSHIFT_A, _VSYNCSHIFT_B) +/* HSW eDP PSR registers */ +#define EDP_PSR_CTL 0x64800 +#define EDP_PSR_ENABLE (1<<31) +#define EDP_PSR_LINK_DISABLE (0<<27) +#define EDP_PSR_LINK_STANDBY (1<<27) +#define EDP_PSR_MIN_LINK_ENTRY_TIME_MASK (3<<25) +#define EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES (0<<25) +#define EDP_PSR_MIN_LINK_ENTRY_TIME_4_LINES (1<<25) +#define EDP_PSR_MIN_LINK_ENTRY_TIME_2_LINES (2<<25) +#define EDP_PSR_MIN_LINK_ENTRY_TIME_0_LINES (3<<25) +#define EDP_PSR_MAX_SLEEP_TIME_SHIFT 20 +#define EDP_PSR_SKIP_AUX_EXIT (1<<12) +#define EDP_PSR_TP1_TP2_SEL (0<<11) +#define EDP_PSR_TP1_TP3_SEL (1<<11) +#define EDP_PSR_TP2_TP3_TIME_500us (0<<8) +#define EDP_PSR_TP2_TP3_TIME_100us (1<<8) +#define EDP_PSR_TP2_TP3_TIME_2500us (2<<8) +#define EDP_PSR_TP2_TP3_TIME_0us (3<<8) +#define EDP_PSR_TP1_TIME_500us (0<<4) +#define EDP_PSR_TP1_TIME_100us (1<<4) +#define EDP_PSR_TP1_TIME_2500us (2<<4) +#define EDP_PSR_TP1_TIME_0us (3<<4) +#define EDP_PSR_IDLE_FRAME_SHIFT 0 + +#define EDP_PSR_AUX_CTL 0x64810 +#define EDP_PSR_AUX_DATA1 0x64814 +#define EDP_PSR_DPCD_COMMAND 0x80060000 +#define EDP_PSR_AUX_DATA2 0x64818 +#define EDP_PSR_DPCD_NORMAL_OPERATION (1<<24) +#define EDP_PSR_AUX_DATA3 0x6481c +#define EDP_PSR_AUX_DATA4 0x64820 +#define EDP_PSR_AUX_DATA5 0x64824 + +#define EDP_PSR_STATUS_CTL 0x64840 +#define EDP_PSR_STATUS_STATE_MASK (7<<29) +#define EDP_PSR_STATUS_STATE_IDLE (0<<29) +#define EDP_PSR_STATUS_STATE_SRDONACK (1<<29) +#define EDP_PSR_STATUS_STATE_SRDENT (2<<29) +#define EDP_PSR_STATUS_STATE_BUFOFF (3<<29) +#define EDP_PSR_STATUS_STATE_BUFON (4<<29) +#define EDP_PSR_STATUS_STATE_AUXACK (5<<29) +#define EDP_PSR_STATUS_STATE_SRDOFFACK (6<<29) +#define EDP_PSR_STATUS_LINK_MASK (3<<26) +#define EDP_PSR_STATUS_LINK_FULL_OFF (0<<26) +#define EDP_PSR_STATUS_LINK_FULL_ON (1<<26) +#define EDP_PSR_STATUS_LINK_STANDBY (2<<26) +#define EDP_PSR_STATUS_MAX_SLEEP_TIMER_SHIFT 20 +#define EDP_PSR_STATUS_MAX_SLEEP_TIMER_MASK 0x1f +#define EDP_PSR_STATUS_COUNT_SHIFT 16 +#define EDP_PSR_STATUS_COUNT_MASK 0xf +#define EDP_PSR_STATUS_AUX_ERROR (1<<15) +#define EDP_PSR_STATUS_AUX_SENDING (1<<12) +#define EDP_PSR_STATUS_SENDING_IDLE (1<<9) +#define EDP_PSR_STATUS_SENDING_TP2_TP3 (1<<8) +#define EDP_PSR_STATUS_SENDING_TP1 (1<<4) +#define EDP_PSR_STATUS_IDLE_MASK 0xf + +#define EDP_PSR_PERF_CNT 0x64844 +#define EDP_PSR_PERF_CNT_MASK 0xffffff + +#define EDP_PSR_DEBUG_CTL 0x64860 +#define EDP_PSR_DEBUG_MASK_LPSP (1<<27) +#define EDP_PSR_DEBUG_MASK_MEMUP (1<<26) +#define EDP_PSR_DEBUG_MASK_HPD (1<<25) + /* VGA port control */ #define ADPA 0x61100 #define PCH_ADPA 0xe1100 @@ -2045,6 +2113,7 @@ * (Haswell and newer) to see which VIDEO_DIP_DATA byte corresponds to each byte * of the infoframe structure specified by CEA-861. */ #define VIDEO_DIP_DATA_SIZE 32 +#define VIDEO_DIP_VSC_DATA_SIZE 36 #define VIDEO_DIP_CTL 0x61170 /* Pre HSW: */ #define VIDEO_DIP_ENABLE (1 << 31) @@ -2192,6 +2261,8 @@ #define BLC_PWM_CPU_CTL2 0x48250 #define BLC_PWM_CPU_CTL 0x48254 +#define HSW_BLC_PWM2_CTL 0x48350 + /* PCH CTL1 is totally different, all but the below bits are reserved. CTL2 is * like the normal CTL from gen4 and earlier. Hooray for confusing naming. */ #define BLC_PWM_PCH_CTL1 0xc8250 @@ -2200,6 +2271,12 @@ #define BLM_PCH_POLARITY (1 << 29) #define BLC_PWM_PCH_CTL2 0xc8254 +#define UTIL_PIN_CTL 0x48400 +#define UTIL_PIN_ENABLE (1 << 31) + +#define PCH_GTC_CTL 0xe7000 +#define PCH_GTC_ENABLE (1 << 31) + /* TV port control */ #define TV_CTL 0x68000 /** Enables the TV encoder */ @@ -3718,6 +3795,9 @@ #define DE_PLANEA_FLIP_DONE_IVB (1<<3) #define DE_PIPEA_VBLANK_IVB (1<<0) +#define DE_PIPE_VBLANK_ILK(pipe) (1 << ((pipe * 8) + 7)) +#define DE_PIPE_VBLANK_IVB(pipe) (1 << (pipe * 5)) + #define VLV_MASTER_IER 0x4400c /* Gunit master IER */ #define MASTER_INTERRUPT_ENABLE (1<<31) @@ -3880,6 +3960,7 @@ #define SERR_INT_TRANS_C_FIFO_UNDERRUN (1<<6) #define SERR_INT_TRANS_B_FIFO_UNDERRUN (1<<3) #define SERR_INT_TRANS_A_FIFO_UNDERRUN (1<<0) +#define SERR_INT_TRANS_FIFO_UNDERRUN(pipe) (1<<(pipe*3)) /* digital port hotplug */ #define PCH_PORT_HOTPLUG 0xc4030 /* SHOTPLUG_CTL */ @@ -4080,6 +4161,13 @@ #define HSW_TVIDEO_DIP_VSC_DATA(trans) \ _TRANSCODER(trans, HSW_VIDEO_DIP_VSC_DATA_A, HSW_VIDEO_DIP_VSC_DATA_B) +#define HSW_STEREO_3D_CTL_A 0x70020 +#define S3D_ENABLE (1<<31) +#define HSW_STEREO_3D_CTL_B 0x71020 + +#define HSW_STEREO_3D_CTL(trans) \ + _TRANSCODER(trans, HSW_STEREO_3D_CTL_A, HSW_STEREO_3D_CTL_A) + #define _PCH_TRANS_HTOTAL_B 0xe1000 #define _PCH_TRANS_HBLANK_B 0xe1004 #define _PCH_TRANS_HSYNC_B 0xe1008 @@ -4468,6 +4556,10 @@ #define GT_FIFO_FREE_ENTRIES 0x120008 #define GT_FIFO_NUM_RESERVED_ENTRIES 20 +#define HSW_IDICR 0x9008 +#define IDIHASHMSK(x) (((x) & 0x3f) << 16) +#define HSW_EDRAM_PRESENT 0x120010 + #define GEN6_UCGCTL1 0x9400 # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE (1 << 5) # define GEN6_CSUNIT_CLOCK_GATE_DISABLE (1 << 7) @@ -4858,7 +4950,8 @@ #define SBI_SSCAUXDIV6 0x0610 #define SBI_SSCAUXDIV_FINALDIV2SEL(x) ((x)<<4) #define SBI_DBUFF0 0x2a00 -#define SBI_DBUFF0_ENABLE (1<<0) +#define SBI_GEN0 0x1f00 +#define SBI_GEN0_CFG_BUFFENABLE_DISABLE (1<<0) /* LPT PIXCLK_GATE */ #define PIXCLK_GATE 0xC6020 @@ -4924,7 +5017,14 @@ #define LCPLL_CLK_FREQ_450 (0<<26) #define LCPLL_CD_CLOCK_DISABLE (1<<25) #define LCPLL_CD2X_CLOCK_DISABLE (1<<23) +#define LCPLL_POWER_DOWN_ALLOW (1<<22) #define LCPLL_CD_SOURCE_FCLK (1<<21) +#define LCPLL_CD_SOURCE_FCLK_DONE (1<<19) + +#define D_COMP (MCHBAR_MIRROR_BASE_SNB + 0x5F0C) +#define D_COMP_RCOMP_IN_PROGRESS (1<<9) +#define D_COMP_COMP_FORCE (1<<8) +#define D_COMP_COMP_DISABLE (1<<0) /* Pipe WM_LINETIME - watermark line time */ #define PIPE_WM_LINETIME_A 0x45270 diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 6875b56..a777e7f 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -409,6 +409,71 @@ static const struct attribute *gen6_attrs[] = { NULL, }; +static ssize_t error_state_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) +{ + + struct device *kdev = container_of(kobj, struct device, kobj); + struct drm_minor *minor = container_of(kdev, struct drm_minor, kdev); + struct drm_device *dev = minor->dev; + struct i915_error_state_file_priv error_priv; + struct drm_i915_error_state_buf error_str; + ssize_t ret_count = 0; + int ret; + + memset(&error_priv, 0, sizeof(error_priv)); + + ret = i915_error_state_buf_init(&error_str, count, off); + if (ret) + return ret; + + error_priv.dev = dev; + i915_error_state_get(dev, &error_priv); + + ret = i915_error_state_to_str(&error_str, &error_priv); + if (ret) + goto out; + + ret_count = count < error_str.bytes ? count : error_str.bytes; + + memcpy(buf, error_str.buf, ret_count); +out: + i915_error_state_put(&error_priv); + i915_error_state_buf_release(&error_str); + + return ret ?: ret_count; +} + +static ssize_t error_state_write(struct file *file, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) +{ + struct device *kdev = container_of(kobj, struct device, kobj); + struct drm_minor *minor = container_of(kdev, struct drm_minor, kdev); + struct drm_device *dev = minor->dev; + int ret; + + DRM_DEBUG_DRIVER("Resetting error state\n"); + + ret = mutex_lock_interruptible(&dev->struct_mutex); + if (ret) + return ret; + + i915_destroy_error_state(dev); + mutex_unlock(&dev->struct_mutex); + + return count; +} + +static struct bin_attribute error_state_attr = { + .attr.name = "error", + .attr.mode = S_IRUSR | S_IWUSR, + .size = 0, + .read = error_state_read, + .write = error_state_write, +}; + void i915_setup_sysfs(struct drm_device *dev) { int ret; @@ -432,10 +497,16 @@ void i915_setup_sysfs(struct drm_device *dev) if (ret) DRM_ERROR("gen6 sysfs setup failed\n"); } + + ret = sysfs_create_bin_file(&dev->primary->kdev.kobj, + &error_state_attr); + if (ret) + DRM_ERROR("error_state sysfs setup failed\n"); } void i915_teardown_sysfs(struct drm_device *dev) { + sysfs_remove_bin_file(&dev->primary->kdev.kobj, &error_state_attr); sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs); device_remove_bin_file(&dev->primary->kdev, &dpf_attrs); #ifdef CONFIG_PM diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 3db4a68..7d283b5 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -46,8 +46,8 @@ TRACE_EVENT(i915_gem_object_bind, TP_fast_assign( __entry->obj = obj; - __entry->offset = obj->gtt_space->start; - __entry->size = obj->gtt_space->size; + __entry->offset = i915_gem_obj_ggtt_offset(obj); + __entry->size = i915_gem_obj_ggtt_size(obj); __entry->mappable = mappable; ), @@ -68,8 +68,8 @@ TRACE_EVENT(i915_gem_object_unbind, TP_fast_assign( __entry->obj = obj; - __entry->offset = obj->gtt_space->start; - __entry->size = obj->gtt_space->size; + __entry->offset = i915_gem_obj_ggtt_offset(obj); + __entry->size = i915_gem_obj_ggtt_size(obj); ), TP_printk("obj=%p, offset=%08x size=%x", diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 3acec8c..0c0d4e8 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -613,6 +613,10 @@ intel_crt_detect(struct drm_connector *connector, bool force) enum drm_connector_status status; struct intel_load_detect_pipe tmp; + DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n", + connector->base.id, drm_get_connector_name(connector), + force); + if (I915_HAS_HOTPLUG(dev)) { /* We can not rely on the HPD pin always being correctly wired * up, for example many KVM do not pass it through, and so diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index b042ee5..931b4bb 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1118,6 +1118,7 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder) intel_dp_stop_link_train(intel_dp); ironlake_edp_backlight_on(intel_dp); + intel_edp_psr_enable(intel_dp); } if (intel_crtc->eld_vld && type != INTEL_OUTPUT_EDP) { @@ -1148,6 +1149,7 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder) if (type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + intel_edp_psr_disable(intel_dp); ironlake_edp_backlight_off(intel_dp); } } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 5fb3058..baaefd7 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -45,6 +45,11 @@ bool intel_pipe_has_type(struct drm_crtc *crtc, int type); static void intel_increase_pllclock(struct drm_crtc *crtc); static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on); +static void i9xx_crtc_clock_get(struct intel_crtc *crtc, + struct intel_crtc_config *pipe_config); +static void ironlake_crtc_clock_get(struct intel_crtc *crtc, + struct intel_crtc_config *pipe_config); + typedef struct { int min, max; } intel_range_t; @@ -84,7 +89,7 @@ intel_fdi_link_freq(struct drm_device *dev) return 27; } -static const intel_limit_t intel_limits_i8xx_dvo = { +static const intel_limit_t intel_limits_i8xx_dac = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 930000, .max = 1400000 }, .n = { .min = 3, .max = 16 }, @@ -97,6 +102,19 @@ static const intel_limit_t intel_limits_i8xx_dvo = { .p2_slow = 4, .p2_fast = 2 }, }; +static const intel_limit_t intel_limits_i8xx_dvo = { + .dot = { .min = 25000, .max = 350000 }, + .vco = { .min = 930000, .max = 1400000 }, + .n = { .min = 3, .max = 16 }, + .m = { .min = 96, .max = 140 }, + .m1 = { .min = 18, .max = 26 }, + .m2 = { .min = 6, .max = 16 }, + .p = { .min = 4, .max = 128 }, + .p1 = { .min = 2, .max = 33 }, + .p2 = { .dot_limit = 165000, + .p2_slow = 4, .p2_fast = 4 }, +}; + static const intel_limit_t intel_limits_i8xx_lvds = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 930000, .max = 1400000 }, @@ -405,8 +423,10 @@ static const intel_limit_t *intel_limit(struct drm_crtc *crtc, int refclk) } else { if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) limit = &intel_limits_i8xx_lvds; - else + else if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DVO)) limit = &intel_limits_i8xx_dvo; + else + limit = &intel_limits_i8xx_dac; } return limit; } @@ -892,8 +912,8 @@ static const char *state_string(bool enabled) } /* Only for pre-ILK configs */ -static void assert_pll(struct drm_i915_private *dev_priv, - enum pipe pipe, bool state) +void assert_pll(struct drm_i915_private *dev_priv, + enum pipe pipe, bool state) { int reg; u32 val; @@ -906,10 +926,8 @@ static void assert_pll(struct drm_i915_private *dev_priv, "PLL state assertion failure (expected %s, current %s)\n", state_string(state), state_string(cur_state)); } -#define assert_pll_enabled(d, p) assert_pll(d, p, true) -#define assert_pll_disabled(d, p) assert_pll(d, p, false) -static struct intel_shared_dpll * +struct intel_shared_dpll * intel_crtc_to_shared_dpll(struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; @@ -921,9 +939,9 @@ intel_crtc_to_shared_dpll(struct intel_crtc *crtc) } /* For ILK+ */ -static void assert_shared_dpll(struct drm_i915_private *dev_priv, - struct intel_shared_dpll *pll, - bool state) +void assert_shared_dpll(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll, + bool state) { bool cur_state; struct intel_dpll_hw_state hw_state; @@ -942,8 +960,6 @@ static void assert_shared_dpll(struct drm_i915_private *dev_priv, "%s assertion failure (expected %s, current %s)\n", pll->name, state_string(state), state_string(cur_state)); } -#define assert_shared_dpll_enabled(d, p) assert_shared_dpll(d, p, true) -#define assert_shared_dpll_disabled(d, p) assert_shared_dpll(d, p, false) static void assert_fdi_tx(struct drm_i915_private *dev_priv, enum pipe pipe, bool state) @@ -1007,15 +1023,19 @@ static void assert_fdi_tx_pll_enabled(struct drm_i915_private *dev_priv, WARN(!(val & FDI_TX_PLL_ENABLE), "FDI TX PLL assertion failure, should be active but is disabled\n"); } -static void assert_fdi_rx_pll_enabled(struct drm_i915_private *dev_priv, - enum pipe pipe) +void assert_fdi_rx_pll(struct drm_i915_private *dev_priv, + enum pipe pipe, bool state) { int reg; u32 val; + bool cur_state; reg = FDI_RX_CTL(pipe); val = I915_READ(reg); - WARN(!(val & FDI_RX_PLL_ENABLE), "FDI RX PLL assertion failure, should be active but is disabled\n"); + cur_state = !!(val & FDI_RX_PLL_ENABLE); + WARN(cur_state != state, + "FDI RX PLL assertion failure (expected %s, current %s)\n", + state_string(state), state_string(cur_state)); } static void assert_panel_unlocked(struct drm_i915_private *dev_priv, @@ -1111,7 +1131,7 @@ static void assert_planes_disabled(struct drm_i915_private *dev_priv, } /* Need to check both planes against the pipe */ - for (i = 0; i < INTEL_INFO(dev)->num_pipes; i++) { + for_each_pipe(i) { reg = DSPCNTR(i); val = I915_READ(reg); cur_pipe = (val & DISPPLANE_SEL_PIPE_MASK) >> @@ -1301,51 +1321,92 @@ static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv, assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMID); } -/** - * intel_enable_pll - enable a PLL - * @dev_priv: i915 private structure - * @pipe: pipe PLL to enable - * - * Enable @pipe's PLL so we can start pumping pixels from a plane. Check to - * make sure the PLL reg is writable first though, since the panel write - * protect mechanism may be enabled. - * - * Note! This is for pre-ILK only. - * - * Unfortunately needed by dvo_ns2501 since the dvo depends on it running. - */ -static void intel_enable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) +static void vlv_enable_pll(struct intel_crtc *crtc) { - int reg; - u32 val; + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int reg = DPLL(crtc->pipe); + u32 dpll = crtc->config.dpll_hw_state.dpll; - assert_pipe_disabled(dev_priv, pipe); + assert_pipe_disabled(dev_priv, crtc->pipe); /* No really, not for ILK+ */ - BUG_ON(!IS_VALLEYVIEW(dev_priv->dev) && dev_priv->info->gen >= 5); + BUG_ON(!IS_VALLEYVIEW(dev_priv->dev)); /* PLL is protected by panel, make sure we can write it */ if (IS_MOBILE(dev_priv->dev) && !IS_I830(dev_priv->dev)) - assert_panel_unlocked(dev_priv, pipe); + assert_panel_unlocked(dev_priv, crtc->pipe); - reg = DPLL(pipe); - val = I915_READ(reg); - val |= DPLL_VCO_ENABLE; + I915_WRITE(reg, dpll); + POSTING_READ(reg); + udelay(150); + + if (wait_for(((I915_READ(reg) & DPLL_LOCK_VLV) == DPLL_LOCK_VLV), 1)) + DRM_ERROR("DPLL %d failed to lock\n", crtc->pipe); + + I915_WRITE(DPLL_MD(crtc->pipe), crtc->config.dpll_hw_state.dpll_md); + POSTING_READ(DPLL_MD(crtc->pipe)); /* We do this three times for luck */ - I915_WRITE(reg, val); + I915_WRITE(reg, dpll); POSTING_READ(reg); udelay(150); /* wait for warmup */ - I915_WRITE(reg, val); + I915_WRITE(reg, dpll); POSTING_READ(reg); udelay(150); /* wait for warmup */ - I915_WRITE(reg, val); + I915_WRITE(reg, dpll); + POSTING_READ(reg); + udelay(150); /* wait for warmup */ +} + +static void i9xx_enable_pll(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int reg = DPLL(crtc->pipe); + u32 dpll = crtc->config.dpll_hw_state.dpll; + + assert_pipe_disabled(dev_priv, crtc->pipe); + + /* No really, not for ILK+ */ + BUG_ON(dev_priv->info->gen >= 5); + + /* PLL is protected by panel, make sure we can write it */ + if (IS_MOBILE(dev) && !IS_I830(dev)) + assert_panel_unlocked(dev_priv, crtc->pipe); + + I915_WRITE(reg, dpll); + + /* Wait for the clocks to stabilize. */ + POSTING_READ(reg); + udelay(150); + + if (INTEL_INFO(dev)->gen >= 4) { + I915_WRITE(DPLL_MD(crtc->pipe), + crtc->config.dpll_hw_state.dpll_md); + } else { + /* The pixel multiplier can only be updated once the + * DPLL is enabled and the clocks are stable. + * + * So write it again. + */ + I915_WRITE(reg, dpll); + } + + /* We do this three times for luck */ + I915_WRITE(reg, dpll); + POSTING_READ(reg); + udelay(150); /* wait for warmup */ + I915_WRITE(reg, dpll); + POSTING_READ(reg); + udelay(150); /* wait for warmup */ + I915_WRITE(reg, dpll); POSTING_READ(reg); udelay(150); /* wait for warmup */ } /** - * intel_disable_pll - disable a PLL + * i9xx_disable_pll - disable a PLL * @dev_priv: i915 private structure * @pipe: pipe PLL to disable * @@ -1353,11 +1414,8 @@ static void intel_enable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) * * Note! This is for pre-ILK only. */ -static void intel_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) +static void i9xx_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) { - int reg; - u32 val; - /* Don't disable pipe A or pipe A PLLs if needed */ if (pipe == PIPE_A && (dev_priv->quirks & QUIRK_PIPEA_FORCE)) return; @@ -1365,11 +1423,8 @@ static void intel_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) /* Make sure the pipe isn't still relying on us */ assert_pipe_disabled(dev_priv, pipe); - reg = DPLL(pipe); - val = I915_READ(reg); - val &= ~DPLL_VCO_ENABLE; - I915_WRITE(reg, val); - POSTING_READ(reg); + I915_WRITE(DPLL(pipe), 0); + POSTING_READ(DPLL(pipe)); } void vlv_wait_port_ready(struct drm_i915_private *dev_priv, int port) @@ -1942,16 +1997,17 @@ static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb, intel_crtc->dspaddr_offset = linear_offset; } - DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n", - obj->gtt_offset, linear_offset, x, y, fb->pitches[0]); + DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n", + i915_gem_obj_ggtt_offset(obj), linear_offset, x, y, + fb->pitches[0]); I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); if (INTEL_INFO(dev)->gen >= 4) { I915_MODIFY_DISPBASE(DSPSURF(plane), - obj->gtt_offset + intel_crtc->dspaddr_offset); + i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); I915_WRITE(DSPTILEOFF(plane), (y << 16) | x); I915_WRITE(DSPLINOFF(plane), linear_offset); } else - I915_WRITE(DSPADDR(plane), obj->gtt_offset + linear_offset); + I915_WRITE(DSPADDR(plane), i915_gem_obj_ggtt_offset(obj) + linear_offset); POSTING_READ(reg); return 0; @@ -2031,11 +2087,12 @@ static int ironlake_update_plane(struct drm_crtc *crtc, fb->pitches[0]); linear_offset -= intel_crtc->dspaddr_offset; - DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n", - obj->gtt_offset, linear_offset, x, y, fb->pitches[0]); + DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n", + i915_gem_obj_ggtt_offset(obj), linear_offset, x, y, + fb->pitches[0]); I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); I915_MODIFY_DISPBASE(DSPSURF(plane), - obj->gtt_offset + intel_crtc->dspaddr_offset); + i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); if (IS_HASWELL(dev)) { I915_WRITE(DSPOFFSET(plane), (y << 16) | x); } else { @@ -2183,6 +2240,20 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, return ret; } + /* Update pipe size and adjust fitter if needed */ + if (i915_fastboot) { + I915_WRITE(PIPESRC(intel_crtc->pipe), + ((crtc->mode.hdisplay - 1) << 16) | + (crtc->mode.vdisplay - 1)); + if (!intel_crtc->config.pch_pfit.size && + (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) || + intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))) { + I915_WRITE(PF_CTL(intel_crtc->pipe), 0); + I915_WRITE(PF_WIN_POS(intel_crtc->pipe), 0); + I915_WRITE(PF_WIN_SZ(intel_crtc->pipe), 0); + } + } + ret = dev_priv->display.update_plane(crtc, fb, x, y); if (ret) { intel_unpin_fb_obj(to_intel_framebuffer(fb)->obj); @@ -2203,6 +2274,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, } intel_update_fbc(dev); + intel_edp_psr_update(dev); mutex_unlock(&dev->struct_mutex); intel_crtc_update_sarea_pos(crtc, x, y); @@ -2927,15 +2999,8 @@ static void ironlake_pch_enable(struct drm_crtc *crtc) /* For PCH output, training FDI link */ dev_priv->display.fdi_link_train(crtc); - /* XXX: pch pll's can be enabled any time before we enable the PCH - * transcoder, and we actually should do this to not upset any PCH - * transcoder that already use the clock when we share it. - * - * Note that enable_shared_dpll tries to do the right thing, but - * get_shared_dpll unconditionally resets the pll - we need that to have - * the right LVDS enable sequence. */ - ironlake_enable_shared_dpll(intel_crtc); - + /* We need to program the right clock selection before writing the pixel + * mutliplier into the DPLL. */ if (HAS_PCH_CPT(dev)) { u32 sel; @@ -2949,6 +3014,15 @@ static void ironlake_pch_enable(struct drm_crtc *crtc) I915_WRITE(PCH_DPLL_SEL, temp); } + /* XXX: pch pll's can be enabled any time before we enable the PCH + * transcoder, and we actually should do this to not upset any PCH + * transcoder that already use the clock when we share it. + * + * Note that enable_shared_dpll tries to do the right thing, but + * get_shared_dpll unconditionally resets the pll - we need that to have + * the right LVDS enable sequence. */ + ironlake_enable_shared_dpll(intel_crtc); + /* set transcoder timing, panel must allow it */ assert_panel_unlocked(dev_priv, pipe); ironlake_pch_transcoder_set_timings(intel_crtc, pipe); @@ -3031,7 +3105,7 @@ static void intel_put_shared_dpll(struct intel_crtc *crtc) crtc->config.shared_dpll = DPLL_ID_PRIVATE; } -static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc, u32 dpll, u32 fp) +static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc); @@ -3045,7 +3119,7 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc, if (HAS_PCH_IBX(dev_priv->dev)) { /* Ironlake PCH has a fixed PLL->PCH pipe mapping. */ - i = crtc->pipe; + i = (enum intel_dpll_id) crtc->pipe; pll = &dev_priv->shared_dplls[i]; DRM_DEBUG_KMS("CRTC:%d using pre-allocated %s\n", @@ -3061,8 +3135,8 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc, if (pll->refcount == 0) continue; - if (dpll == (I915_READ(PCH_DPLL(pll->id)) & 0x7fffffff) && - fp == I915_READ(PCH_FP0(pll->id))) { + if (memcmp(&crtc->config.dpll_hw_state, &pll->hw_state, + sizeof(pll->hw_state)) == 0) { DRM_DEBUG_KMS("CRTC:%d sharing existing %s (refcount %d, ative %d)\n", crtc->base.base.id, pll->name, pll->refcount, pll->active); @@ -3096,13 +3170,7 @@ found: WARN_ON(pll->on); assert_shared_dpll_disabled(dev_priv, pll); - /* Wait for the clocks to stabilize before rewriting the regs */ - I915_WRITE(PCH_DPLL(pll->id), dpll & ~DPLL_VCO_ENABLE); - POSTING_READ(PCH_DPLL(pll->id)); - udelay(150); - - I915_WRITE(PCH_FP0(pll->id), fp); - I915_WRITE(PCH_DPLL(pll->id), dpll & ~DPLL_VCO_ENABLE); + pll->mode_set(dev_priv, pll); } pll->refcount++; @@ -3174,7 +3242,6 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) struct intel_encoder *encoder; int pipe = intel_crtc->pipe; int plane = intel_crtc->plane; - u32 temp; WARN_ON(!crtc->enabled); @@ -3188,12 +3255,9 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) intel_update_watermarks(dev); - if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) { - temp = I915_READ(PCH_LVDS); - if ((temp & LVDS_PORT_EN) == 0) - I915_WRITE(PCH_LVDS, temp | LVDS_PORT_EN); - } - + for_each_encoder_on_crtc(dev, crtc, encoder) + if (encoder->pre_enable) + encoder->pre_enable(encoder); if (intel_crtc->config.has_pch_encoder) { /* Note: FDI PLL enabling _must_ be done before we enable the @@ -3205,10 +3269,6 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) assert_fdi_rx_disabled(dev_priv, pipe); } - for_each_encoder_on_crtc(dev, crtc, encoder) - if (encoder->pre_enable) - encoder->pre_enable(encoder); - ironlake_pfit_enable(intel_crtc); /* @@ -3389,7 +3449,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) intel_crtc_wait_for_pending_flips(crtc); drm_vblank_off(dev, pipe); - if (dev_priv->cfb_plane == plane) + if (dev_priv->fbc.plane == plane) intel_disable_fbc(dev); intel_crtc_update_cursor(crtc, false); @@ -3462,7 +3522,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) drm_vblank_off(dev, pipe); /* FBC must be disabled before disabling the plane on HSW. */ - if (dev_priv->cfb_plane == plane) + if (dev_priv->fbc.plane == plane) intel_disable_fbc(dev); hsw_disable_ips(intel_crtc); @@ -3599,7 +3659,7 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc) if (encoder->pre_pll_enable) encoder->pre_pll_enable(encoder); - intel_enable_pll(dev_priv, pipe); + vlv_enable_pll(intel_crtc); for_each_encoder_on_crtc(dev, crtc, encoder) if (encoder->pre_enable) @@ -3640,12 +3700,12 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc) intel_crtc->active = true; intel_update_watermarks(dev); - intel_enable_pll(dev_priv, pipe); - for_each_encoder_on_crtc(dev, crtc, encoder) if (encoder->pre_enable) encoder->pre_enable(encoder); + i9xx_enable_pll(intel_crtc); + i9xx_pfit_enable(intel_crtc); intel_crtc_load_lut(crtc); @@ -3701,7 +3761,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc) intel_crtc_wait_for_pending_flips(crtc); drm_vblank_off(dev, pipe); - if (dev_priv->cfb_plane == plane) + if (dev_priv->fbc.plane == plane) intel_disable_fbc(dev); intel_crtc_dpms_overlay(intel_crtc, false); @@ -3717,7 +3777,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc) if (encoder->post_disable) encoder->post_disable(encoder); - intel_disable_pll(dev_priv, pipe); + i9xx_disable_pll(dev_priv, pipe); intel_crtc->active = false; intel_update_fbc(dev); @@ -4266,14 +4326,17 @@ static void i9xx_update_pll_dividers(struct intel_crtc *crtc, } I915_WRITE(FP0(pipe), fp); + crtc->config.dpll_hw_state.fp0 = fp; crtc->lowfreq_avail = false; if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_LVDS) && reduced_clock && i915_powersave) { I915_WRITE(FP1(pipe), fp2); + crtc->config.dpll_hw_state.fp1 = fp2; crtc->lowfreq_avail = true; } else { I915_WRITE(FP1(pipe), fp); + crtc->config.dpll_hw_state.fp1 = fp; } } @@ -4351,7 +4414,6 @@ static void vlv_update_pll(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_encoder *encoder; int pipe = crtc->pipe; u32 dpll, mdiv; u32 bestn, bestm1, bestm2, bestp1, bestp2; @@ -4407,7 +4469,7 @@ static void vlv_update_pll(struct intel_crtc *crtc) intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_ANALOG) || intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_HDMI)) vlv_dpio_write(dev_priv, DPIO_LPF_COEFF(pipe), - 0x005f0021); + 0x009f0003); else vlv_dpio_write(dev_priv, DPIO_LPF_COEFF(pipe), 0x00d0000f); @@ -4440,10 +4502,6 @@ static void vlv_update_pll(struct intel_crtc *crtc) vlv_dpio_write(dev_priv, DPIO_PLL_CML(pipe), 0x87871000); - for_each_encoder_on_crtc(dev, &crtc->base, encoder) - if (encoder->pre_pll_enable) - encoder->pre_pll_enable(encoder); - /* Enable DPIO clock input */ dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV; @@ -4451,17 +4509,11 @@ static void vlv_update_pll(struct intel_crtc *crtc) dpll |= DPLL_INTEGRATED_CRI_CLK_VLV; dpll |= DPLL_VCO_ENABLE; - I915_WRITE(DPLL(pipe), dpll); - POSTING_READ(DPLL(pipe)); - udelay(150); - - if (wait_for(((I915_READ(DPLL(pipe)) & DPLL_LOCK_VLV) == DPLL_LOCK_VLV), 1)) - DRM_ERROR("DPLL %d failed to lock\n", pipe); + crtc->config.dpll_hw_state.dpll = dpll; dpll_md = (crtc->config.pixel_multiplier - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT; - I915_WRITE(DPLL_MD(pipe), dpll_md); - POSTING_READ(DPLL_MD(pipe)); + crtc->config.dpll_hw_state.dpll_md = dpll_md; if (crtc->config.has_dp_encoder) intel_dp_set_m_n(crtc); @@ -4475,8 +4527,6 @@ static void i9xx_update_pll(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_encoder *encoder; - int pipe = crtc->pipe; u32 dpll; bool is_sdvo; struct dpll *clock = &crtc->config.dpll; @@ -4499,10 +4549,10 @@ static void i9xx_update_pll(struct intel_crtc *crtc, } if (is_sdvo) - dpll |= DPLL_DVO_HIGH_SPEED; + dpll |= DPLL_SDVO_HIGH_SPEED; if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DISPLAYPORT)) - dpll |= DPLL_DVO_HIGH_SPEED; + dpll |= DPLL_SDVO_HIGH_SPEED; /* compute bitmask from p1 value */ if (IS_PINEVIEW(dev)) @@ -4538,35 +4588,16 @@ static void i9xx_update_pll(struct intel_crtc *crtc, dpll |= PLL_REF_INPUT_DREFCLK; dpll |= DPLL_VCO_ENABLE; - I915_WRITE(DPLL(pipe), dpll & ~DPLL_VCO_ENABLE); - POSTING_READ(DPLL(pipe)); - udelay(150); - - for_each_encoder_on_crtc(dev, &crtc->base, encoder) - if (encoder->pre_pll_enable) - encoder->pre_pll_enable(encoder); - - if (crtc->config.has_dp_encoder) - intel_dp_set_m_n(crtc); - - I915_WRITE(DPLL(pipe), dpll); - - /* Wait for the clocks to stabilize. */ - POSTING_READ(DPLL(pipe)); - udelay(150); + crtc->config.dpll_hw_state.dpll = dpll; if (INTEL_INFO(dev)->gen >= 4) { u32 dpll_md = (crtc->config.pixel_multiplier - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT; - I915_WRITE(DPLL_MD(pipe), dpll_md); - } else { - /* The pixel multiplier can only be updated once the - * DPLL is enabled and the clocks are stable. - * - * So write it again. - */ - I915_WRITE(DPLL(pipe), dpll); + crtc->config.dpll_hw_state.dpll_md = dpll_md; } + + if (crtc->config.has_dp_encoder) + intel_dp_set_m_n(crtc); } static void i8xx_update_pll(struct intel_crtc *crtc, @@ -4575,8 +4606,6 @@ static void i8xx_update_pll(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_encoder *encoder; - int pipe = crtc->pipe; u32 dpll; struct dpll *clock = &crtc->config.dpll; @@ -4595,6 +4624,9 @@ static void i8xx_update_pll(struct intel_crtc *crtc, dpll |= PLL_P2_DIVIDE_BY_4; } + if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO)) + dpll |= DPLL_DVO_2X_MODE; + if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_LVDS) && intel_panel_use_ssc(dev_priv) && num_connectors < 2) dpll |= PLLB_REF_INPUT_SPREADSPECTRUMIN; @@ -4602,26 +4634,7 @@ static void i8xx_update_pll(struct intel_crtc *crtc, dpll |= PLL_REF_INPUT_DREFCLK; dpll |= DPLL_VCO_ENABLE; - I915_WRITE(DPLL(pipe), dpll & ~DPLL_VCO_ENABLE); - POSTING_READ(DPLL(pipe)); - udelay(150); - - for_each_encoder_on_crtc(dev, &crtc->base, encoder) - if (encoder->pre_pll_enable) - encoder->pre_pll_enable(encoder); - - I915_WRITE(DPLL(pipe), dpll); - - /* Wait for the clocks to stabilize. */ - POSTING_READ(DPLL(pipe)); - udelay(150); - - /* The pixel multiplier can only be updated once the - * DPLL is enabled and the clocks are stable. - * - * So write it again. - */ - I915_WRITE(DPLL(pipe), dpll); + crtc->config.dpll_hw_state.dpll = dpll; } static void intel_set_pipe_timings(struct intel_crtc *intel_crtc) @@ -4727,6 +4740,27 @@ static void intel_get_pipe_timings(struct intel_crtc *crtc, pipe_config->requested_mode.hdisplay = ((tmp >> 16) & 0xffff) + 1; } +static void intel_crtc_mode_from_pipe_config(struct intel_crtc *intel_crtc, + struct intel_crtc_config *pipe_config) +{ + struct drm_crtc *crtc = &intel_crtc->base; + + crtc->mode.hdisplay = pipe_config->adjusted_mode.crtc_hdisplay; + crtc->mode.htotal = pipe_config->adjusted_mode.crtc_htotal; + crtc->mode.hsync_start = pipe_config->adjusted_mode.crtc_hsync_start; + crtc->mode.hsync_end = pipe_config->adjusted_mode.crtc_hsync_end; + + crtc->mode.vdisplay = pipe_config->adjusted_mode.crtc_vdisplay; + crtc->mode.vtotal = pipe_config->adjusted_mode.crtc_vtotal; + crtc->mode.vsync_start = pipe_config->adjusted_mode.crtc_vsync_start; + crtc->mode.vsync_end = pipe_config->adjusted_mode.crtc_vsync_end; + + crtc->mode.flags = pipe_config->adjusted_mode.flags; + + crtc->mode.clock = pipe_config->adjusted_mode.clock; + crtc->mode.flags |= pipe_config->adjusted_mode.flags; +} + static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc) { struct drm_device *dev = intel_crtc->base.dev; @@ -4939,7 +4973,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, struct drm_i915_private *dev_priv = dev->dev_private; uint32_t tmp; - pipe_config->cpu_transcoder = crtc->pipe; + pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; tmp = I915_READ(PIPECONF(crtc->pipe)); @@ -4955,6 +4989,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, pipe_config->pixel_multiplier = ((tmp & DPLL_MD_UDI_MULTIPLIER_MASK) >> DPLL_MD_UDI_MULTIPLIER_SHIFT) + 1; + pipe_config->dpll_hw_state.dpll_md = tmp; } else if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) { tmp = I915_READ(DPLL(crtc->pipe)); pipe_config->pixel_multiplier = @@ -4966,6 +5001,16 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, * function. */ pipe_config->pixel_multiplier = 1; } + pipe_config->dpll_hw_state.dpll = I915_READ(DPLL(crtc->pipe)); + if (!IS_VALLEYVIEW(dev)) { + pipe_config->dpll_hw_state.fp0 = I915_READ(FP0(crtc->pipe)); + pipe_config->dpll_hw_state.fp1 = I915_READ(FP1(crtc->pipe)); + } else { + /* Mask out read-only status bits. */ + pipe_config->dpll_hw_state.dpll &= ~(DPLL_LOCK_VLV | + DPLL_PORTC_READY_MASK | + DPLL_PORTB_READY_MASK); + } return true; } @@ -5119,74 +5164,37 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) BUG_ON(val != final); } -/* Sequence to enable CLKOUT_DP for FDI usage and configure PCH FDI I/O. */ -static void lpt_init_pch_refclk(struct drm_device *dev) +static void lpt_reset_fdi_mphy(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_mode_config *mode_config = &dev->mode_config; - struct intel_encoder *encoder; - bool has_vga = false; - bool is_sdv = false; - u32 tmp; - - list_for_each_entry(encoder, &mode_config->encoder_list, base.head) { - switch (encoder->type) { - case INTEL_OUTPUT_ANALOG: - has_vga = true; - break; - } - } - - if (!has_vga) - return; - - mutex_lock(&dev_priv->dpio_lock); - - /* XXX: Rip out SDV support once Haswell ships for real. */ - if (IS_HASWELL(dev) && (dev->pci_device & 0xFF00) == 0x0C00) - is_sdv = true; - - tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); - tmp &= ~SBI_SSCCTL_DISABLE; - tmp |= SBI_SSCCTL_PATHALT; - intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); - - udelay(24); + uint32_t tmp; - tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); - tmp &= ~SBI_SSCCTL_PATHALT; - intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); + tmp = I915_READ(SOUTH_CHICKEN2); + tmp |= FDI_MPHY_IOSFSB_RESET_CTL; + I915_WRITE(SOUTH_CHICKEN2, tmp); - if (!is_sdv) { - tmp = I915_READ(SOUTH_CHICKEN2); - tmp |= FDI_MPHY_IOSFSB_RESET_CTL; - I915_WRITE(SOUTH_CHICKEN2, tmp); + if (wait_for_atomic_us(I915_READ(SOUTH_CHICKEN2) & + FDI_MPHY_IOSFSB_RESET_STATUS, 100)) + DRM_ERROR("FDI mPHY reset assert timeout\n"); - if (wait_for_atomic_us(I915_READ(SOUTH_CHICKEN2) & - FDI_MPHY_IOSFSB_RESET_STATUS, 100)) - DRM_ERROR("FDI mPHY reset assert timeout\n"); + tmp = I915_READ(SOUTH_CHICKEN2); + tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL; + I915_WRITE(SOUTH_CHICKEN2, tmp); - tmp = I915_READ(SOUTH_CHICKEN2); - tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL; - I915_WRITE(SOUTH_CHICKEN2, tmp); + if (wait_for_atomic_us((I915_READ(SOUTH_CHICKEN2) & + FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100)) + DRM_ERROR("FDI mPHY reset de-assert timeout\n"); +} - if (wait_for_atomic_us((I915_READ(SOUTH_CHICKEN2) & - FDI_MPHY_IOSFSB_RESET_STATUS) == 0, - 100)) - DRM_ERROR("FDI mPHY reset de-assert timeout\n"); - } +/* WaMPhyProgramming:hsw */ +static void lpt_program_fdi_mphy(struct drm_i915_private *dev_priv) +{ + uint32_t tmp; tmp = intel_sbi_read(dev_priv, 0x8008, SBI_MPHY); tmp &= ~(0xFF << 24); tmp |= (0x12 << 24); intel_sbi_write(dev_priv, 0x8008, tmp, SBI_MPHY); - if (is_sdv) { - tmp = intel_sbi_read(dev_priv, 0x800C, SBI_MPHY); - tmp |= 0x7FFF; - intel_sbi_write(dev_priv, 0x800C, tmp, SBI_MPHY); - } - tmp = intel_sbi_read(dev_priv, 0x2008, SBI_MPHY); tmp |= (1 << 11); intel_sbi_write(dev_priv, 0x2008, tmp, SBI_MPHY); @@ -5195,24 +5203,6 @@ static void lpt_init_pch_refclk(struct drm_device *dev) tmp |= (1 << 11); intel_sbi_write(dev_priv, 0x2108, tmp, SBI_MPHY); - if (is_sdv) { - tmp = intel_sbi_read(dev_priv, 0x2038, SBI_MPHY); - tmp |= (0x3F << 24) | (0xF << 20) | (0xF << 16); - intel_sbi_write(dev_priv, 0x2038, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x2138, SBI_MPHY); - tmp |= (0x3F << 24) | (0xF << 20) | (0xF << 16); - intel_sbi_write(dev_priv, 0x2138, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x203C, SBI_MPHY); - tmp |= (0x3F << 8); - intel_sbi_write(dev_priv, 0x203C, tmp, SBI_MPHY); - - tmp = intel_sbi_read(dev_priv, 0x213C, SBI_MPHY); - tmp |= (0x3F << 8); - intel_sbi_write(dev_priv, 0x213C, tmp, SBI_MPHY); - } - tmp = intel_sbi_read(dev_priv, 0x206C, SBI_MPHY); tmp |= (1 << 24) | (1 << 21) | (1 << 18); intel_sbi_write(dev_priv, 0x206C, tmp, SBI_MPHY); @@ -5221,17 +5211,15 @@ static void lpt_init_pch_refclk(struct drm_device *dev) tmp |= (1 << 24) | (1 << 21) | (1 << 18); intel_sbi_write(dev_priv, 0x216C, tmp, SBI_MPHY); - if (!is_sdv) { - tmp = intel_sbi_read(dev_priv, 0x2080, SBI_MPHY); - tmp &= ~(7 << 13); - tmp |= (5 << 13); - intel_sbi_write(dev_priv, 0x2080, tmp, SBI_MPHY); + tmp = intel_sbi_read(dev_priv, 0x2080, SBI_MPHY); + tmp &= ~(7 << 13); + tmp |= (5 << 13); + intel_sbi_write(dev_priv, 0x2080, tmp, SBI_MPHY); - tmp = intel_sbi_read(dev_priv, 0x2180, SBI_MPHY); - tmp &= ~(7 << 13); - tmp |= (5 << 13); - intel_sbi_write(dev_priv, 0x2180, tmp, SBI_MPHY); - } + tmp = intel_sbi_read(dev_priv, 0x2180, SBI_MPHY); + tmp &= ~(7 << 13); + tmp |= (5 << 13); + intel_sbi_write(dev_priv, 0x2180, tmp, SBI_MPHY); tmp = intel_sbi_read(dev_priv, 0x208C, SBI_MPHY); tmp &= ~0xFF; @@ -5253,34 +5241,120 @@ static void lpt_init_pch_refclk(struct drm_device *dev) tmp |= (0x1C << 16); intel_sbi_write(dev_priv, 0x2198, tmp, SBI_MPHY); - if (!is_sdv) { - tmp = intel_sbi_read(dev_priv, 0x20C4, SBI_MPHY); - tmp |= (1 << 27); - intel_sbi_write(dev_priv, 0x20C4, tmp, SBI_MPHY); + tmp = intel_sbi_read(dev_priv, 0x20C4, SBI_MPHY); + tmp |= (1 << 27); + intel_sbi_write(dev_priv, 0x20C4, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x21C4, SBI_MPHY); + tmp |= (1 << 27); + intel_sbi_write(dev_priv, 0x21C4, tmp, SBI_MPHY); - tmp = intel_sbi_read(dev_priv, 0x21C4, SBI_MPHY); - tmp |= (1 << 27); - intel_sbi_write(dev_priv, 0x21C4, tmp, SBI_MPHY); + tmp = intel_sbi_read(dev_priv, 0x20EC, SBI_MPHY); + tmp &= ~(0xF << 28); + tmp |= (4 << 28); + intel_sbi_write(dev_priv, 0x20EC, tmp, SBI_MPHY); + + tmp = intel_sbi_read(dev_priv, 0x21EC, SBI_MPHY); + tmp &= ~(0xF << 28); + tmp |= (4 << 28); + intel_sbi_write(dev_priv, 0x21EC, tmp, SBI_MPHY); +} - tmp = intel_sbi_read(dev_priv, 0x20EC, SBI_MPHY); - tmp &= ~(0xF << 28); - tmp |= (4 << 28); - intel_sbi_write(dev_priv, 0x20EC, tmp, SBI_MPHY); +/* Implements 3 different sequences from BSpec chapter "Display iCLK + * Programming" based on the parameters passed: + * - Sequence to enable CLKOUT_DP + * - Sequence to enable CLKOUT_DP without spread + * - Sequence to enable CLKOUT_DP for FDI usage and configure PCH FDI I/O + */ +static void lpt_enable_clkout_dp(struct drm_device *dev, bool with_spread, + bool with_fdi) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t reg, tmp; - tmp = intel_sbi_read(dev_priv, 0x21EC, SBI_MPHY); - tmp &= ~(0xF << 28); - tmp |= (4 << 28); - intel_sbi_write(dev_priv, 0x21EC, tmp, SBI_MPHY); + if (WARN(with_fdi && !with_spread, "FDI requires downspread\n")) + with_spread = true; + if (WARN(dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE && + with_fdi, "LP PCH doesn't have FDI\n")) + with_fdi = false; + + mutex_lock(&dev_priv->dpio_lock); + + tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); + tmp &= ~SBI_SSCCTL_DISABLE; + tmp |= SBI_SSCCTL_PATHALT; + intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); + + udelay(24); + + if (with_spread) { + tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); + tmp &= ~SBI_SSCCTL_PATHALT; + intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); + + if (with_fdi) { + lpt_reset_fdi_mphy(dev_priv); + lpt_program_fdi_mphy(dev_priv); + } } - /* ULT uses SBI_GEN0, but ULT doesn't have VGA, so we don't care. */ - tmp = intel_sbi_read(dev_priv, SBI_DBUFF0, SBI_ICLK); - tmp |= SBI_DBUFF0_ENABLE; - intel_sbi_write(dev_priv, SBI_DBUFF0, tmp, SBI_ICLK); + reg = (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) ? + SBI_GEN0 : SBI_DBUFF0; + tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK); + tmp |= SBI_GEN0_CFG_BUFFENABLE_DISABLE; + intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK); + + mutex_unlock(&dev_priv->dpio_lock); +} + +/* Sequence to disable CLKOUT_DP */ +static void lpt_disable_clkout_dp(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t reg, tmp; + + mutex_lock(&dev_priv->dpio_lock); + + reg = (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) ? + SBI_GEN0 : SBI_DBUFF0; + tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK); + tmp &= ~SBI_GEN0_CFG_BUFFENABLE_DISABLE; + intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK); + + tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK); + if (!(tmp & SBI_SSCCTL_DISABLE)) { + if (!(tmp & SBI_SSCCTL_PATHALT)) { + tmp |= SBI_SSCCTL_PATHALT; + intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); + udelay(32); + } + tmp |= SBI_SSCCTL_DISABLE; + intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK); + } mutex_unlock(&dev_priv->dpio_lock); } +static void lpt_init_pch_refclk(struct drm_device *dev) +{ + struct drm_mode_config *mode_config = &dev->mode_config; + struct intel_encoder *encoder; + bool has_vga = false; + + list_for_each_entry(encoder, &mode_config->encoder_list, base.head) { + switch (encoder->type) { + case INTEL_OUTPUT_ANALOG: + has_vga = true; + break; + } + } + + if (has_vga) + lpt_enable_clkout_dp(dev, true, true); + else + lpt_disable_clkout_dp(dev); +} + /* * Initialize reference clocks when the driver loads */ @@ -5610,9 +5684,9 @@ static uint32_t ironlake_compute_dpll(struct intel_crtc *intel_crtc, << PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT; if (is_sdvo) - dpll |= DPLL_DVO_HIGH_SPEED; + dpll |= DPLL_SDVO_HIGH_SPEED; if (intel_crtc->config.has_dp_encoder) - dpll |= DPLL_DVO_HIGH_SPEED; + dpll |= DPLL_SDVO_HIGH_SPEED; /* compute bitmask from p1 value */ dpll |= (1 << (intel_crtc->config.dpll.p1 - 1)) << DPLL_FPA01_P1_POST_DIV_SHIFT; @@ -5708,7 +5782,7 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, else intel_crtc->config.dpll_hw_state.fp1 = fp; - pll = intel_get_shared_dpll(intel_crtc, dpll, fp); + pll = intel_get_shared_dpll(intel_crtc); if (pll == NULL) { DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n", pipe_name(pipe)); @@ -5720,10 +5794,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, if (intel_crtc->config.has_dp_encoder) intel_dp_set_m_n(intel_crtc); - for_each_encoder_on_crtc(dev, crtc, encoder) - if (encoder->pre_pll_enable) - encoder->pre_pll_enable(encoder); - if (is_lvds && has_reduced_clock && i915_powersave) intel_crtc->lowfreq_avail = true; else @@ -5732,23 +5802,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, if (intel_crtc->config.has_pch_encoder) { pll = intel_crtc_to_shared_dpll(intel_crtc); - I915_WRITE(PCH_DPLL(pll->id), dpll); - - /* Wait for the clocks to stabilize. */ - POSTING_READ(PCH_DPLL(pll->id)); - udelay(150); - - /* The pixel multiplier can only be updated once the - * DPLL is enabled and the clocks are stable. - * - * So write it again. - */ - I915_WRITE(PCH_DPLL(pll->id), dpll); - - if (has_reduced_clock) - I915_WRITE(PCH_FP1(pll->id), fp2); - else - I915_WRITE(PCH_FP1(pll->id), fp); } intel_set_pipe_timings(intel_crtc); @@ -5820,7 +5873,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, struct drm_i915_private *dev_priv = dev->dev_private; uint32_t tmp; - pipe_config->cpu_transcoder = crtc->pipe; + pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; tmp = I915_READ(PIPECONF(crtc->pipe)); @@ -5838,12 +5891,9 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, ironlake_get_fdi_m_n_config(crtc, pipe_config); - /* XXX: Can't properly read out the pch dpll pixel multiplier - * since we don't have state tracking for pch clocks yet. */ - pipe_config->pixel_multiplier = 1; - if (HAS_PCH_IBX(dev_priv->dev)) { - pipe_config->shared_dpll = crtc->pipe; + pipe_config->shared_dpll = + (enum intel_dpll_id) crtc->pipe; } else { tmp = I915_READ(PCH_DPLL_SEL); if (tmp & TRANS_DPLLB_SEL(crtc->pipe)) @@ -5856,6 +5906,11 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, WARN_ON(!pll->get_hw_state(dev_priv, pll, &pipe_config->dpll_hw_state)); + + tmp = pipe_config->dpll_hw_state.dpll; + pipe_config->pixel_multiplier = + ((tmp & PLL_REF_SDVO_HDMI_MULTIPLIER_MASK) + >> PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT) + 1; } else { pipe_config->pixel_multiplier = 1; } @@ -5867,6 +5922,142 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, return true; } +static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + struct intel_ddi_plls *plls = &dev_priv->ddi_plls; + struct intel_crtc *crtc; + unsigned long irqflags; + uint32_t val, pch_hpd_mask; + + pch_hpd_mask = SDE_PORTB_HOTPLUG_CPT | SDE_PORTC_HOTPLUG_CPT; + if (!(dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE)) + pch_hpd_mask |= SDE_PORTD_HOTPLUG_CPT | SDE_CRT_HOTPLUG_CPT; + + list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) + WARN(crtc->base.enabled, "CRTC for pipe %c enabled\n", + pipe_name(crtc->pipe)); + + WARN(I915_READ(HSW_PWR_WELL_DRIVER), "Power well on\n"); + WARN(plls->spll_refcount, "SPLL enabled\n"); + WARN(plls->wrpll1_refcount, "WRPLL1 enabled\n"); + WARN(plls->wrpll2_refcount, "WRPLL2 enabled\n"); + WARN(I915_READ(PCH_PP_STATUS) & PP_ON, "Panel power on\n"); + WARN(I915_READ(BLC_PWM_CPU_CTL2) & BLM_PWM_ENABLE, + "CPU PWM1 enabled\n"); + WARN(I915_READ(HSW_BLC_PWM2_CTL) & BLM_PWM_ENABLE, + "CPU PWM2 enabled\n"); + WARN(I915_READ(BLC_PWM_PCH_CTL1) & BLM_PCH_PWM_ENABLE, + "PCH PWM1 enabled\n"); + WARN(I915_READ(UTIL_PIN_CTL) & UTIL_PIN_ENABLE, + "Utility pin enabled\n"); + WARN(I915_READ(PCH_GTC_CTL) & PCH_GTC_ENABLE, "PCH GTC enabled\n"); + + spin_lock_irqsave(&dev_priv->irq_lock, irqflags); + val = I915_READ(DEIMR); + WARN((val & ~DE_PCH_EVENT_IVB) != val, + "Unexpected DEIMR bits enabled: 0x%x\n", val); + val = I915_READ(SDEIMR); + WARN((val & ~pch_hpd_mask) != val, + "Unexpected SDEIMR bits enabled: 0x%x\n", val); + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); +} + +/* + * This function implements pieces of two sequences from BSpec: + * - Sequence for display software to disable LCPLL + * - Sequence for display software to allow package C8+ + * The steps implemented here are just the steps that actually touch the LCPLL + * register. Callers should take care of disabling all the display engine + * functions, doing the mode unset, fixing interrupts, etc. + */ +void hsw_disable_lcpll(struct drm_i915_private *dev_priv, + bool switch_to_fclk, bool allow_power_down) +{ + uint32_t val; + + assert_can_disable_lcpll(dev_priv); + + val = I915_READ(LCPLL_CTL); + + if (switch_to_fclk) { + val |= LCPLL_CD_SOURCE_FCLK; + I915_WRITE(LCPLL_CTL, val); + + if (wait_for_atomic_us(I915_READ(LCPLL_CTL) & + LCPLL_CD_SOURCE_FCLK_DONE, 1)) + DRM_ERROR("Switching to FCLK failed\n"); + + val = I915_READ(LCPLL_CTL); + } + + val |= LCPLL_PLL_DISABLE; + I915_WRITE(LCPLL_CTL, val); + POSTING_READ(LCPLL_CTL); + + if (wait_for((I915_READ(LCPLL_CTL) & LCPLL_PLL_LOCK) == 0, 1)) + DRM_ERROR("LCPLL still locked\n"); + + val = I915_READ(D_COMP); + val |= D_COMP_COMP_DISABLE; + I915_WRITE(D_COMP, val); + POSTING_READ(D_COMP); + ndelay(100); + + if (wait_for((I915_READ(D_COMP) & D_COMP_RCOMP_IN_PROGRESS) == 0, 1)) + DRM_ERROR("D_COMP RCOMP still in progress\n"); + + if (allow_power_down) { + val = I915_READ(LCPLL_CTL); + val |= LCPLL_POWER_DOWN_ALLOW; + I915_WRITE(LCPLL_CTL, val); + POSTING_READ(LCPLL_CTL); + } +} + +/* + * Fully restores LCPLL, disallowing power down and switching back to LCPLL + * source. + */ +void hsw_restore_lcpll(struct drm_i915_private *dev_priv) +{ + uint32_t val; + + val = I915_READ(LCPLL_CTL); + + if ((val & (LCPLL_PLL_LOCK | LCPLL_PLL_DISABLE | LCPLL_CD_SOURCE_FCLK | + LCPLL_POWER_DOWN_ALLOW)) == LCPLL_PLL_LOCK) + return; + + if (val & LCPLL_POWER_DOWN_ALLOW) { + val &= ~LCPLL_POWER_DOWN_ALLOW; + I915_WRITE(LCPLL_CTL, val); + } + + val = I915_READ(D_COMP); + val |= D_COMP_COMP_FORCE; + val &= ~D_COMP_COMP_DISABLE; + I915_WRITE(D_COMP, val); + I915_READ(D_COMP); + + val = I915_READ(LCPLL_CTL); + val &= ~LCPLL_PLL_DISABLE; + I915_WRITE(LCPLL_CTL, val); + + if (wait_for(I915_READ(LCPLL_CTL) & LCPLL_PLL_LOCK, 5)) + DRM_ERROR("LCPLL not locked yet\n"); + + if (val & LCPLL_CD_SOURCE_FCLK) { + val = I915_READ(LCPLL_CTL); + val &= ~LCPLL_CD_SOURCE_FCLK; + I915_WRITE(LCPLL_CTL, val); + + if (wait_for_atomic_us((I915_READ(LCPLL_CTL) & + LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1)) + DRM_ERROR("Switching back to LCPLL failed\n"); + } +} + static void haswell_modeset_global_resources(struct drm_device *dev) { bool enable = false; @@ -5935,7 +6126,7 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, enum intel_display_power_domain pfit_domain; uint32_t tmp; - pipe_config->cpu_transcoder = crtc->pipe; + pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)); @@ -6548,7 +6739,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc, goto fail_unpin; } - addr = obj->gtt_offset; + addr = i915_gem_obj_ggtt_offset(obj); } else { int align = IS_I830(dev) ? 16 * 1024 : 256; ret = i915_gem_attach_phys_object(dev, obj, @@ -6875,11 +7066,12 @@ void intel_release_load_detect_pipe(struct drm_connector *connector, } /* Returns the clock of the currently programmed mode of the given pipe. */ -static int intel_crtc_clock_get(struct drm_device *dev, struct drm_crtc *crtc) +static void i9xx_crtc_clock_get(struct intel_crtc *crtc, + struct intel_crtc_config *pipe_config) { + struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int pipe = intel_crtc->pipe; + int pipe = pipe_config->cpu_transcoder; u32 dpll = I915_READ(DPLL(pipe)); u32 fp; intel_clock_t clock; @@ -6918,7 +7110,8 @@ static int intel_crtc_clock_get(struct drm_device *dev, struct drm_crtc *crtc) default: DRM_DEBUG_KMS("Unknown DPLL mode %08x in programmed " "mode\n", (int)(dpll & DPLL_MODE_MASK)); - return 0; + pipe_config->adjusted_mode.clock = 0; + return; } if (IS_PINEVIEW(dev)) @@ -6955,12 +7148,55 @@ static int intel_crtc_clock_get(struct drm_device *dev, struct drm_crtc *crtc) } } - /* XXX: It would be nice to validate the clocks, but we can't reuse - * i830PllIsValid() because it relies on the xf86_config connector - * configuration being accurate, which it isn't necessarily. + pipe_config->adjusted_mode.clock = clock.dot * + pipe_config->pixel_multiplier; +} + +static void ironlake_crtc_clock_get(struct intel_crtc *crtc, + struct intel_crtc_config *pipe_config) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + enum transcoder cpu_transcoder = pipe_config->cpu_transcoder; + int link_freq, repeat; + u64 clock; + u32 link_m, link_n; + + repeat = pipe_config->pixel_multiplier; + + /* + * The calculation for the data clock is: + * pixel_clock = ((m/n)*(link_clock * nr_lanes * repeat))/bpp + * But we want to avoid losing precison if possible, so: + * pixel_clock = ((m * link_clock * nr_lanes * repeat)/(n*bpp)) + * + * and the link clock is simpler: + * link_clock = (m * link_clock * repeat) / n */ - return clock.dot; + /* + * We need to get the FDI or DP link clock here to derive + * the M/N dividers. + * + * For FDI, we read it from the BIOS or use a fixed 2.7GHz. + * For DP, it's either 1.62GHz or 2.7GHz. + * We do our calculations in 10*MHz since we don't need much precison. + */ + if (pipe_config->has_pch_encoder) + link_freq = intel_fdi_link_freq(dev) * 10000; + else + link_freq = pipe_config->port_clock; + + link_m = I915_READ(PIPE_LINK_M1(cpu_transcoder)); + link_n = I915_READ(PIPE_LINK_N1(cpu_transcoder)); + + if (!link_m || !link_n) + return; + + clock = ((u64)link_m * (u64)link_freq * (u64)repeat); + do_div(clock, link_n); + + pipe_config->adjusted_mode.clock = clock; } /** Returns the currently programmed mode of the given pipe. */ @@ -6971,6 +7207,7 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, struct intel_crtc *intel_crtc = to_intel_crtc(crtc); enum transcoder cpu_transcoder = intel_crtc->config.cpu_transcoder; struct drm_display_mode *mode; + struct intel_crtc_config pipe_config; int htot = I915_READ(HTOTAL(cpu_transcoder)); int hsync = I915_READ(HSYNC(cpu_transcoder)); int vtot = I915_READ(VTOTAL(cpu_transcoder)); @@ -6980,7 +7217,18 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, if (!mode) return NULL; - mode->clock = intel_crtc_clock_get(dev, crtc); + /* + * Construct a pipe_config sufficient for getting the clock info + * back out of crtc_clock_get. + * + * Note, if LVDS ever uses a non-1 pixel multiplier, we'll need + * to use a real value here instead. + */ + pipe_config.cpu_transcoder = (enum transcoder) intel_crtc->pipe; + pipe_config.pixel_multiplier = 1; + i9xx_crtc_clock_get(intel_crtc, &pipe_config); + + mode->clock = pipe_config.adjusted_mode.clock; mode->hdisplay = (htot & 0xffff) + 1; mode->htotal = ((htot & 0xffff0000) >> 16) + 1; mode->hsync_start = (hsync & 0xffff) + 1; @@ -7263,7 +7511,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); - intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); intel_ring_emit(ring, 0); /* aux display base address, unused */ intel_mark_page_flip_active(intel_crtc); @@ -7304,7 +7552,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); - intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); intel_ring_emit(ring, MI_NOOP); intel_mark_page_flip_active(intel_crtc); @@ -7344,7 +7592,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev, MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); intel_ring_emit(ring, - (obj->gtt_offset + intel_crtc->dspaddr_offset) | + (i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset) | obj->tiling_mode); /* XXX Enabling the panel-fitter across page-flip is so far @@ -7387,7 +7635,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode); - intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); /* Contrary to the suggestions in the documentation, * "Enable Panel Fitter" does not seem to be required when page @@ -7452,7 +7700,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit); intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode)); - intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); intel_ring_emit(ring, (MI_NOOP)); intel_mark_page_flip_active(intel_crtc); @@ -7806,7 +8054,8 @@ intel_modeset_pipe_config(struct drm_crtc *crtc, drm_mode_copy(&pipe_config->adjusted_mode, mode); drm_mode_copy(&pipe_config->requested_mode, mode); - pipe_config->cpu_transcoder = to_intel_crtc(crtc)->pipe; + pipe_config->cpu_transcoder = + (enum transcoder) to_intel_crtc(crtc)->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; /* Compute a starting value for pipe_config->pipe_bpp taking the source @@ -8041,6 +8290,28 @@ intel_modeset_update_state(struct drm_device *dev, unsigned prepare_pipes) } +static bool intel_fuzzy_clock_check(struct intel_crtc_config *cur, + struct intel_crtc_config *new) +{ + int clock1, clock2, diff; + + clock1 = cur->adjusted_mode.clock; + clock2 = new->adjusted_mode.clock; + + if (clock1 == clock2) + return true; + + if (!clock1 || !clock2) + return false; + + diff = abs(clock1 - clock2); + + if (((((diff + clock1 + clock2) * 100)) / (clock1 + clock2)) < 105) + return true; + + return false; +} + #define for_each_intel_crtc_masked(dev, mask, intel_crtc) \ list_for_each_entry((intel_crtc), \ &(dev)->mode_config.crtc_list, \ @@ -8072,7 +8343,7 @@ intel_pipe_config_compare(struct drm_device *dev, #define PIPE_CONF_CHECK_FLAGS(name, mask) \ if ((current_config->name ^ pipe_config->name) & (mask)) { \ - DRM_ERROR("mismatch in " #name " " \ + DRM_ERROR("mismatch in " #name "(" #mask ") " \ "(expected %i, found %i)\n", \ current_config->name & (mask), \ pipe_config->name & (mask)); \ @@ -8106,8 +8377,7 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_I(adjusted_mode.crtc_vsync_start); PIPE_CONF_CHECK_I(adjusted_mode.crtc_vsync_end); - if (!HAS_PCH_SPLIT(dev)) - PIPE_CONF_CHECK_I(pixel_multiplier); + PIPE_CONF_CHECK_I(pixel_multiplier); PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags, DRM_MODE_FLAG_INTERLACE); @@ -8138,6 +8408,7 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_I(shared_dpll); PIPE_CONF_CHECK_X(dpll_hw_state.dpll); + PIPE_CONF_CHECK_X(dpll_hw_state.dpll_md); PIPE_CONF_CHECK_X(dpll_hw_state.fp0); PIPE_CONF_CHECK_X(dpll_hw_state.fp1); @@ -8146,6 +8417,15 @@ intel_pipe_config_compare(struct drm_device *dev, #undef PIPE_CONF_CHECK_FLAGS #undef PIPE_CONF_QUIRK + if (!IS_HASWELL(dev)) { + if (!intel_fuzzy_clock_check(current_config, pipe_config)) { + DRM_ERROR("mismatch in clock (expected %d, found %d)\n", + current_config->adjusted_mode.clock, + pipe_config->adjusted_mode.clock); + return false; + } + } + return true; } @@ -8275,6 +8555,9 @@ check_crtc_state(struct drm_device *dev) encoder->get_config(encoder, &pipe_config); } + if (dev_priv->display.get_clock) + dev_priv->display.get_clock(crtc, &pipe_config); + WARN(crtc->active != active, "crtc active state doesn't match with hw state " "(expected %i, found %i)\n", crtc->active, active); @@ -8571,8 +8854,16 @@ intel_set_config_compute_mode_changes(struct drm_mode_set *set, } else if (set->crtc->fb != set->fb) { /* If we have no fb then treat it as a full mode set */ if (set->crtc->fb == NULL) { - DRM_DEBUG_KMS("crtc has no fb, full mode set\n"); - config->mode_changed = true; + struct intel_crtc *intel_crtc = + to_intel_crtc(set->crtc); + + if (intel_crtc->active && i915_fastboot) { + DRM_DEBUG_KMS("crtc has no fb, will flip\n"); + config->fb_changed = true; + } else { + DRM_DEBUG_KMS("inactive crtc, full mode set\n"); + config->mode_changed = true; + } } else if (set->fb == NULL) { config->mode_changed = true; } else if (set->fb->pixel_format != @@ -8802,19 +9093,32 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv, return val & DPLL_VCO_ENABLE; } +static void ibx_pch_dpll_mode_set(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll) +{ + I915_WRITE(PCH_FP0(pll->id), pll->hw_state.fp0); + I915_WRITE(PCH_FP1(pll->id), pll->hw_state.fp1); +} + static void ibx_pch_dpll_enable(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll) { - uint32_t reg, val; - /* PCH refclock must be enabled first */ assert_pch_refclk_enabled(dev_priv); - reg = PCH_DPLL(pll->id); - val = I915_READ(reg); - val |= DPLL_VCO_ENABLE; - I915_WRITE(reg, val); - POSTING_READ(reg); + I915_WRITE(PCH_DPLL(pll->id), pll->hw_state.dpll); + + /* Wait for the clocks to stabilize. */ + POSTING_READ(PCH_DPLL(pll->id)); + udelay(150); + + /* The pixel multiplier can only be updated once the + * DPLL is enabled and the clocks are stable. + * + * So write it again. + */ + I915_WRITE(PCH_DPLL(pll->id), pll->hw_state.dpll); + POSTING_READ(PCH_DPLL(pll->id)); udelay(200); } @@ -8823,7 +9127,6 @@ static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv, { struct drm_device *dev = dev_priv->dev; struct intel_crtc *crtc; - uint32_t reg, val; /* Make sure no transcoder isn't still depending on us. */ list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { @@ -8831,11 +9134,8 @@ static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv, assert_pch_transcoder_disabled(dev_priv, crtc->pipe); } - reg = PCH_DPLL(pll->id); - val = I915_READ(reg); - val &= ~DPLL_VCO_ENABLE; - I915_WRITE(reg, val); - POSTING_READ(reg); + I915_WRITE(PCH_DPLL(pll->id), 0); + POSTING_READ(PCH_DPLL(pll->id)); udelay(200); } @@ -8854,6 +9154,7 @@ static void ibx_pch_dpll_init(struct drm_device *dev) for (i = 0; i < dev_priv->num_shared_dpll; i++) { dev_priv->shared_dplls[i].id = i; dev_priv->shared_dplls[i].name = ibx_pch_dpll_names[i]; + dev_priv->shared_dplls[i].mode_set = ibx_pch_dpll_mode_set; dev_priv->shared_dplls[i].enable = ibx_pch_dpll_enable; dev_priv->shared_dplls[i].disable = ibx_pch_dpll_disable; dev_priv->shared_dplls[i].get_hw_state = @@ -9270,6 +9571,7 @@ static void intel_init_display(struct drm_device *dev) dev_priv->display.update_plane = ironlake_update_plane; } else if (HAS_PCH_SPLIT(dev)) { dev_priv->display.get_pipe_config = ironlake_get_pipe_config; + dev_priv->display.get_clock = ironlake_crtc_clock_get; dev_priv->display.crtc_mode_set = ironlake_crtc_mode_set; dev_priv->display.crtc_enable = ironlake_crtc_enable; dev_priv->display.crtc_disable = ironlake_crtc_disable; @@ -9277,6 +9579,7 @@ static void intel_init_display(struct drm_device *dev) dev_priv->display.update_plane = ironlake_update_plane; } else if (IS_VALLEYVIEW(dev)) { dev_priv->display.get_pipe_config = i9xx_get_pipe_config; + dev_priv->display.get_clock = i9xx_crtc_clock_get; dev_priv->display.crtc_mode_set = i9xx_crtc_mode_set; dev_priv->display.crtc_enable = valleyview_crtc_enable; dev_priv->display.crtc_disable = i9xx_crtc_disable; @@ -9284,6 +9587,7 @@ static void intel_init_display(struct drm_device *dev) dev_priv->display.update_plane = i9xx_update_plane; } else { dev_priv->display.get_pipe_config = i9xx_get_pipe_config; + dev_priv->display.get_clock = i9xx_crtc_clock_get; dev_priv->display.crtc_mode_set = i9xx_crtc_mode_set; dev_priv->display.crtc_enable = i9xx_crtc_enable; dev_priv->display.crtc_disable = i9xx_crtc_disable; @@ -9584,7 +9888,7 @@ void intel_modeset_init(struct drm_device *dev) INTEL_INFO(dev)->num_pipes, INTEL_INFO(dev)->num_pipes > 1 ? "s" : ""); - for (i = 0; i < INTEL_INFO(dev)->num_pipes; i++) { + for_each_pipe(i) { intel_crtc_init(dev, i); for (j = 0; j < dev_priv->num_plane; j++) { ret = intel_plane_init(dev, i, j); @@ -9860,6 +10164,15 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) pipe); } + list_for_each_entry(crtc, &dev->mode_config.crtc_list, + base.head) { + if (!crtc->active) + continue; + if (dev_priv->display.get_clock) + dev_priv->display.get_clock(crtc, + &crtc->config); + } + list_for_each_entry(connector, &dev->mode_config.connector_list, base.head) { if (connector->get_hw_state(connector)) { @@ -9891,6 +10204,22 @@ void intel_modeset_setup_hw_state(struct drm_device *dev, intel_modeset_readout_hw_state(dev); + /* + * Now that we have the config, copy it to each CRTC struct + * Note that this could go away if we move to using crtc_config + * checking everywhere. + */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, + base.head) { + if (crtc->active && i915_fastboot) { + intel_crtc_mode_from_pipe_config(crtc, &crtc->config); + + DRM_DEBUG_KMS("[CRTC:%d] found active mode: ", + crtc->base.base.id); + drm_mode_debug_printmodeline(&crtc->base.mode); + } + } + /* HW state is read out, now we need to sanitize this mess. */ list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) { @@ -10033,9 +10362,6 @@ int intel_modeset_vga_set_state(struct drm_device *dev, bool state) return 0; } -#ifdef CONFIG_DEBUG_FS -#include <linux/seq_file.h> - struct intel_display_error_state { u32 power_well_driver; @@ -10179,4 +10505,3 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m, err_printf(m, " BASE: %08x\n", error->cursor[i].base); } } -#endif diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 26e162b..c6996ce 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -276,29 +276,12 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq) return status; } -static int -intel_dp_aux_ch(struct intel_dp *intel_dp, - uint8_t *send, int send_bytes, - uint8_t *recv, int recv_size) +static uint32_t get_aux_clock_divider(struct intel_dp *intel_dp) { struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); struct drm_device *dev = intel_dig_port->base.base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t ch_ctl = intel_dp->aux_ch_ctl_reg; - uint32_t ch_data = ch_ctl + 4; - int i, ret, recv_bytes; - uint32_t status; - uint32_t aux_clock_divider; - int try, precharge; - bool has_aux_irq = INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev); - /* dp aux is extremely sensitive to irq latency, hence request the - * lowest possible wakeup latency and so prevent the cpu from going into - * deep sleep states. - */ - pm_qos_update_request(&dev_priv->pm_qos, 0); - - intel_dp_check_edp(intel_dp); /* The clock divider is based off the hrawclk, * and would like to run at 2MHz. So, take the * hrawclk value and divide by 2 and use that @@ -307,23 +290,48 @@ intel_dp_aux_ch(struct intel_dp *intel_dp, * clock divider. */ if (IS_VALLEYVIEW(dev)) { - aux_clock_divider = 100; + return 100; } else if (intel_dig_port->port == PORT_A) { if (HAS_DDI(dev)) - aux_clock_divider = DIV_ROUND_CLOSEST( + return DIV_ROUND_CLOSEST( intel_ddi_get_cdclk_freq(dev_priv), 2000); else if (IS_GEN6(dev) || IS_GEN7(dev)) - aux_clock_divider = 200; /* SNB & IVB eDP input clock at 400Mhz */ + return 200; /* SNB & IVB eDP input clock at 400Mhz */ else - aux_clock_divider = 225; /* eDP input clock at 450Mhz */ + return 225; /* eDP input clock at 450Mhz */ } else if (dev_priv->pch_id == INTEL_PCH_LPT_DEVICE_ID_TYPE) { /* Workaround for non-ULT HSW */ - aux_clock_divider = 74; + return 74; } else if (HAS_PCH_SPLIT(dev)) { - aux_clock_divider = DIV_ROUND_UP(intel_pch_rawclk(dev), 2); + return DIV_ROUND_UP(intel_pch_rawclk(dev), 2); } else { - aux_clock_divider = intel_hrawclk(dev) / 2; + return intel_hrawclk(dev) / 2; } +} + +static int +intel_dp_aux_ch(struct intel_dp *intel_dp, + uint8_t *send, int send_bytes, + uint8_t *recv, int recv_size) +{ + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct drm_device *dev = intel_dig_port->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t ch_ctl = intel_dp->aux_ch_ctl_reg; + uint32_t ch_data = ch_ctl + 4; + int i, ret, recv_bytes; + uint32_t status; + uint32_t aux_clock_divider = get_aux_clock_divider(intel_dp); + int try, precharge; + bool has_aux_irq = INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev); + + /* dp aux is extremely sensitive to irq latency, hence request the + * lowest possible wakeup latency and so prevent the cpu from going into + * deep sleep states. + */ + pm_qos_update_request(&dev_priv->pm_qos, 0); + + intel_dp_check_edp(intel_dp); if (IS_GEN6(dev)) precharge = 3; @@ -710,8 +718,11 @@ intel_dp_compute_config(struct intel_encoder *encoder, /* Walk through all bpp values. Luckily they're all nicely spaced with 2 * bpc in between. */ bpp = pipe_config->pipe_bpp; - if (is_edp(intel_dp) && dev_priv->vbt.edp_bpp) + if (is_edp(intel_dp) && dev_priv->vbt.edp_bpp) { + DRM_DEBUG_KMS("clamping bpp for eDP panel to BIOS-provided %i\n", + dev_priv->vbt.edp_bpp); bpp = min_t(int, bpp, dev_priv->vbt.edp_bpp); + } for (; bpp >= 6*3; bpp -= 2*3) { mode_rate = intel_dp_link_required(adjusted_mode->clock, bpp); @@ -1360,6 +1371,266 @@ static void intel_dp_get_config(struct intel_encoder *encoder, } pipe_config->adjusted_mode.flags |= flags; + + if (dp_to_dig_port(intel_dp)->port == PORT_A) { + if ((I915_READ(DP_A) & DP_PLL_FREQ_MASK) == DP_PLL_FREQ_160MHZ) + pipe_config->port_clock = 162000; + else + pipe_config->port_clock = 270000; + } +} + +static bool is_edp_psr(struct intel_dp *intel_dp) +{ + return is_edp(intel_dp) && + intel_dp->psr_dpcd[0] & DP_PSR_IS_SUPPORTED; +} + +static bool intel_edp_is_psr_enabled(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (!IS_HASWELL(dev)) + return false; + + return I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE; +} + +static void intel_edp_psr_write_vsc(struct intel_dp *intel_dp, + struct edp_vsc_psr *vsc_psr) +{ + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_device *dev = dig_port->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *crtc = to_intel_crtc(dig_port->base.base.crtc); + u32 ctl_reg = HSW_TVIDEO_DIP_CTL(crtc->config.cpu_transcoder); + u32 data_reg = HSW_TVIDEO_DIP_VSC_DATA(crtc->config.cpu_transcoder); + uint32_t *data = (uint32_t *) vsc_psr; + unsigned int i; + + /* As per BSPec (Pipe Video Data Island Packet), we need to disable + the video DIP being updated before program video DIP data buffer + registers for DIP being updated. */ + I915_WRITE(ctl_reg, 0); + POSTING_READ(ctl_reg); + + for (i = 0; i < VIDEO_DIP_VSC_DATA_SIZE; i += 4) { + if (i < sizeof(struct edp_vsc_psr)) + I915_WRITE(data_reg + i, *data++); + else + I915_WRITE(data_reg + i, 0); + } + + I915_WRITE(ctl_reg, VIDEO_DIP_ENABLE_VSC_HSW); + POSTING_READ(ctl_reg); +} + +static void intel_edp_psr_setup(struct intel_dp *intel_dp) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + struct drm_i915_private *dev_priv = dev->dev_private; + struct edp_vsc_psr psr_vsc; + + if (intel_dp->psr_setup_done) + return; + + /* Prepare VSC packet as per EDP 1.3 spec, Table 3.10 */ + memset(&psr_vsc, 0, sizeof(psr_vsc)); + psr_vsc.sdp_header.HB0 = 0; + psr_vsc.sdp_header.HB1 = 0x7; + psr_vsc.sdp_header.HB2 = 0x2; + psr_vsc.sdp_header.HB3 = 0x8; + intel_edp_psr_write_vsc(intel_dp, &psr_vsc); + + /* Avoid continuous PSR exit by masking memup and hpd */ + I915_WRITE(EDP_PSR_DEBUG_CTL, EDP_PSR_DEBUG_MASK_MEMUP | + EDP_PSR_DEBUG_MASK_HPD); + + intel_dp->psr_setup_done = true; +} + +static void intel_edp_psr_enable_sink(struct intel_dp *intel_dp) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t aux_clock_divider = get_aux_clock_divider(intel_dp); + int precharge = 0x3; + int msg_size = 5; /* Header(4) + Message(1) */ + + /* Enable PSR in sink */ + if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT) + intel_dp_aux_native_write_1(intel_dp, DP_PSR_EN_CFG, + DP_PSR_ENABLE & + ~DP_PSR_MAIN_LINK_ACTIVE); + else + intel_dp_aux_native_write_1(intel_dp, DP_PSR_EN_CFG, + DP_PSR_ENABLE | + DP_PSR_MAIN_LINK_ACTIVE); + + /* Setup AUX registers */ + I915_WRITE(EDP_PSR_AUX_DATA1, EDP_PSR_DPCD_COMMAND); + I915_WRITE(EDP_PSR_AUX_DATA2, EDP_PSR_DPCD_NORMAL_OPERATION); + I915_WRITE(EDP_PSR_AUX_CTL, + DP_AUX_CH_CTL_TIME_OUT_400us | + (msg_size << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT) | + (precharge << DP_AUX_CH_CTL_PRECHARGE_2US_SHIFT) | + (aux_clock_divider << DP_AUX_CH_CTL_BIT_CLOCK_2X_SHIFT)); +} + +static void intel_edp_psr_enable_source(struct intel_dp *intel_dp) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t max_sleep_time = 0x1f; + uint32_t idle_frames = 1; + uint32_t val = 0x0; + + if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT) { + val |= EDP_PSR_LINK_STANDBY; + val |= EDP_PSR_TP2_TP3_TIME_0us; + val |= EDP_PSR_TP1_TIME_0us; + val |= EDP_PSR_SKIP_AUX_EXIT; + } else + val |= EDP_PSR_LINK_DISABLE; + + I915_WRITE(EDP_PSR_CTL, val | + EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES | + max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT | + idle_frames << EDP_PSR_IDLE_FRAME_SHIFT | + EDP_PSR_ENABLE); +} + +static bool intel_edp_psr_match_conditions(struct intel_dp *intel_dp) +{ + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_device *dev = dig_port->base.base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_crtc *crtc = dig_port->base.base.crtc; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct drm_i915_gem_object *obj = to_intel_framebuffer(crtc->fb)->obj; + struct intel_encoder *intel_encoder = &dp_to_dig_port(intel_dp)->base; + + if (!IS_HASWELL(dev)) { + DRM_DEBUG_KMS("PSR not supported on this platform\n"); + dev_priv->no_psr_reason = PSR_NO_SOURCE; + return false; + } + + if ((intel_encoder->type != INTEL_OUTPUT_EDP) || + (dig_port->port != PORT_A)) { + DRM_DEBUG_KMS("HSW ties PSR to DDI A (eDP)\n"); + dev_priv->no_psr_reason = PSR_HSW_NOT_DDIA; + return false; + } + + if (!is_edp_psr(intel_dp)) { + DRM_DEBUG_KMS("PSR not supported by this panel\n"); + dev_priv->no_psr_reason = PSR_NO_SINK; + return false; + } + + if (!i915_enable_psr) { + DRM_DEBUG_KMS("PSR disable by flag\n"); + dev_priv->no_psr_reason = PSR_MODULE_PARAM; + return false; + } + + if (!intel_crtc->active || !crtc->fb || !crtc->mode.clock) { + DRM_DEBUG_KMS("crtc not active for PSR\n"); + dev_priv->no_psr_reason = PSR_CRTC_NOT_ACTIVE; + return false; + } + + if (obj->tiling_mode != I915_TILING_X || + obj->fence_reg == I915_FENCE_REG_NONE) { + DRM_DEBUG_KMS("PSR condition failed: fb not tiled or fenced\n"); + dev_priv->no_psr_reason = PSR_NOT_TILED; + return false; + } + + if (I915_READ(SPRCTL(intel_crtc->pipe)) & SPRITE_ENABLE) { + DRM_DEBUG_KMS("PSR condition failed: Sprite is Enabled\n"); + dev_priv->no_psr_reason = PSR_SPRITE_ENABLED; + return false; + } + + if (I915_READ(HSW_STEREO_3D_CTL(intel_crtc->config.cpu_transcoder)) & + S3D_ENABLE) { + DRM_DEBUG_KMS("PSR condition failed: Stereo 3D is Enabled\n"); + dev_priv->no_psr_reason = PSR_S3D_ENABLED; + return false; + } + + if (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE) { + DRM_DEBUG_KMS("PSR condition failed: Interlaced is Enabled\n"); + dev_priv->no_psr_reason = PSR_INTERLACED_ENABLED; + return false; + } + + return true; +} + +static void intel_edp_psr_do_enable(struct intel_dp *intel_dp) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + + if (!intel_edp_psr_match_conditions(intel_dp) || + intel_edp_is_psr_enabled(dev)) + return; + + /* Setup PSR once */ + intel_edp_psr_setup(intel_dp); + + /* Enable PSR on the panel */ + intel_edp_psr_enable_sink(intel_dp); + + /* Enable PSR on the host */ + intel_edp_psr_enable_source(intel_dp); +} + +void intel_edp_psr_enable(struct intel_dp *intel_dp) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + + if (intel_edp_psr_match_conditions(intel_dp) && + !intel_edp_is_psr_enabled(dev)) + intel_edp_psr_do_enable(intel_dp); +} + +void intel_edp_psr_disable(struct intel_dp *intel_dp) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + struct drm_i915_private *dev_priv = dev->dev_private; + + if (!intel_edp_is_psr_enabled(dev)) + return; + + I915_WRITE(EDP_PSR_CTL, I915_READ(EDP_PSR_CTL) & ~EDP_PSR_ENABLE); + + /* Wait till PSR is idle */ + if (_wait_for((I915_READ(EDP_PSR_STATUS_CTL) & + EDP_PSR_STATUS_STATE_MASK) == 0, 2000, 10)) + DRM_ERROR("Timed out waiting for PSR Idle State\n"); +} + +void intel_edp_psr_update(struct drm_device *dev) +{ + struct intel_encoder *encoder; + struct intel_dp *intel_dp = NULL; + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) + if (encoder->type == INTEL_OUTPUT_EDP) { + intel_dp = enc_to_intel_dp(&encoder->base); + + if (!is_edp_psr(intel_dp)) + return; + + if (!intel_edp_psr_match_conditions(intel_dp)) + intel_edp_psr_disable(intel_dp); + else + if (!intel_edp_is_psr_enabled(dev)) + intel_edp_psr_do_enable(intel_dp); + } } static void intel_disable_dp(struct intel_encoder *encoder) @@ -2275,6 +2546,13 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) if (intel_dp->dpcd[DP_DPCD_REV] == 0) return false; /* DPCD not present */ + /* Check if the panel supports PSR */ + memset(intel_dp->psr_dpcd, 0, sizeof(intel_dp->psr_dpcd)); + intel_dp_aux_native_read_retry(intel_dp, DP_PSR_SUPPORT, + intel_dp->psr_dpcd, + sizeof(intel_dp->psr_dpcd)); + if (is_edp_psr(intel_dp)) + DRM_DEBUG_KMS("Detected EDP PSR Panel.\n"); if (!(intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT)) return true; /* native DP sink */ @@ -2542,6 +2820,9 @@ intel_dp_detect(struct drm_connector *connector, bool force) enum drm_connector_status status; struct edid *edid = NULL; + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", + connector->base.id, drm_get_connector_name(connector)); + intel_dp->has_audio = false; if (HAS_PCH_SPLIT(dev)) @@ -3166,6 +3447,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port, WARN(error, "intel_dp_i2c_init failed with error %d for port %c\n", error, port_name(port)); + intel_dp->psr_setup_done = false; + if (!intel_edp_init_connector(intel_dp, intel_connector)) { i2c_del_adapter(&intel_dp->adapter); if (is_edp(intel_dp)) { diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index b7d6e09..3fbe80b 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -487,6 +487,7 @@ struct intel_dp { uint8_t link_bw; uint8_t lane_count; uint8_t dpcd[DP_RECEIVER_CAP_SIZE]; + uint8_t psr_dpcd[EDP_PSR_RECEIVER_CAP_SIZE]; uint8_t downstream_ports[DP_MAX_DOWNSTREAM_PORTS]; struct i2c_adapter adapter; struct i2c_algo_dp_aux_data algo; @@ -498,6 +499,7 @@ struct intel_dp { int backlight_off_delay; struct delayed_work panel_vdd_work; bool want_panel_vdd; + bool psr_setup_done; struct intel_connector *attached_connector; }; @@ -549,13 +551,6 @@ struct intel_unpin_work { bool enable_stall_check; }; -struct intel_fbc_work { - struct delayed_work work; - struct drm_crtc *crtc; - struct drm_framebuffer *fb; - int interval; -}; - int intel_pch_rawclk(struct drm_device *dev); int intel_connector_update_modes(struct drm_connector *connector, @@ -747,6 +742,22 @@ extern int intel_overlay_attrs(struct drm_device *dev, void *data, extern void intel_fb_output_poll_changed(struct drm_device *dev); extern void intel_fb_restore_mode(struct drm_device *dev); +struct intel_shared_dpll * +intel_crtc_to_shared_dpll(struct intel_crtc *crtc); + +void assert_shared_dpll(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll, + bool state); +#define assert_shared_dpll_enabled(d, p) assert_shared_dpll(d, p, true) +#define assert_shared_dpll_disabled(d, p) assert_shared_dpll(d, p, false) +void assert_pll(struct drm_i915_private *dev_priv, + enum pipe pipe, bool state); +#define assert_pll_enabled(d, p) assert_pll(d, p, true) +#define assert_pll_disabled(d, p) assert_pll(d, p, false) +void assert_fdi_rx_pll(struct drm_i915_private *dev_priv, + enum pipe pipe, bool state); +#define assert_fdi_rx_pll_enabled(d, p) assert_fdi_rx_pll(d, p, true) +#define assert_fdi_rx_pll_disabled(d, p) assert_fdi_rx_pll(d, p, false) extern void assert_pipe(struct drm_i915_private *dev_priv, enum pipe pipe, bool state); #define assert_pipe_enabled(d, p) assert_pipe(d, p, true) @@ -780,7 +791,6 @@ extern int intel_sprite_get_colorkey(struct drm_device *dev, void *data, extern void intel_init_pm(struct drm_device *dev); /* FBC */ extern bool intel_fbc_enabled(struct drm_device *dev); -extern void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval); extern void intel_update_fbc(struct drm_device *dev); /* IPS */ extern void intel_gpu_ips_init(struct drm_i915_private *dev_priv); @@ -825,4 +835,11 @@ extern bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev, enum transcoder pch_transcoder, bool enable); +extern void intel_edp_psr_enable(struct intel_dp *intel_dp); +extern void intel_edp_psr_disable(struct intel_dp *intel_dp); +extern void intel_edp_psr_update(struct drm_device *dev); +extern void hsw_disable_lcpll(struct drm_i915_private *dev_priv, + bool switch_to_fclk, bool allow_power_down); +extern void hsw_restore_lcpll(struct drm_i915_private *dev_priv); + #endif /* __INTEL_DRV_H__ */ diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index eb2020e..8b4ad27 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -283,7 +283,6 @@ static void intel_dvo_mode_set(struct drm_encoder *encoder, int pipe = intel_crtc->pipe; u32 dvo_val; u32 dvo_reg = intel_dvo->dev.dvo_reg, dvo_srcdim_reg; - int dpll_reg = DPLL(pipe); switch (dvo_reg) { case DVOA: @@ -314,8 +313,6 @@ static void intel_dvo_mode_set(struct drm_encoder *encoder, if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) dvo_val |= DVO_VSYNC_ACTIVE_HIGH; - I915_WRITE(dpll_reg, I915_READ(dpll_reg) | DPLL_DVO_HIGH_SPEED); - /*I915_WRITE(DVOB_SRCDIM, (adjusted_mode->hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) | (adjusted_mode->VDisplay << DVO_SRCDIM_VERTICAL_SHIFT));*/ @@ -335,6 +332,8 @@ static enum drm_connector_status intel_dvo_detect(struct drm_connector *connector, bool force) { struct intel_dvo *intel_dvo = intel_attached_dvo(connector); + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", + connector->base.id, drm_get_connector_name(connector)); return intel_dvo->dev.dev_ops->detect(&intel_dvo->dev); } diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index dff669e..f3c97e0 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -139,11 +139,11 @@ static int intelfb_create(struct drm_fb_helper *helper, info->apertures->ranges[0].base = dev->mode_config.fb_base; info->apertures->ranges[0].size = dev_priv->gtt.mappable_end; - info->fix.smem_start = dev->mode_config.fb_base + obj->gtt_offset; + info->fix.smem_start = dev->mode_config.fb_base + i915_gem_obj_ggtt_offset(obj); info->fix.smem_len = size; info->screen_base = - ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset, + ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj), size); if (!info->screen_base) { ret = -ENOSPC; @@ -166,9 +166,9 @@ static int intelfb_create(struct drm_fb_helper *helper, /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */ - DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x, bo %p\n", + DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08lx, bo %p\n", fb->width, fb->height, - obj->gtt_offset, obj); + i915_gem_obj_ggtt_offset(obj), obj); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 98df2a0..af18da7 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -866,6 +866,9 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) struct edid *edid; enum drm_connector_status status = connector_status_disconnected; + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", + connector->base.id, drm_get_connector_name(connector)); + intel_hdmi->has_hdmi_sink = false; intel_hdmi->has_audio = false; intel_hdmi->rgb_quant_range_selectable = false; diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 61348ea..2110df2 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -122,17 +122,25 @@ static void intel_lvds_get_config(struct intel_encoder *encoder, * This is an exception to the general rule that mode_set doesn't turn * things on. */ -static void intel_pre_pll_enable_lvds(struct intel_encoder *encoder) +static void intel_pre_enable_lvds(struct intel_encoder *encoder) { struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); + struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); struct drm_display_mode *fixed_mode = lvds_encoder->attached_connector->base.panel.fixed_mode; - int pipe = intel_crtc->pipe; + int pipe = crtc->pipe; u32 temp; + if (HAS_PCH_SPLIT(dev)) { + assert_fdi_rx_pll_disabled(dev_priv, pipe); + assert_shared_dpll_disabled(dev_priv, + intel_crtc_to_shared_dpll(crtc)); + } else { + assert_pll_disabled(dev_priv, pipe); + } + temp = I915_READ(lvds_encoder->reg); temp |= LVDS_PORT_EN | LVDS_A0A2_CLKA_POWER_UP; @@ -149,7 +157,7 @@ static void intel_pre_pll_enable_lvds(struct intel_encoder *encoder) /* set the corresponsding LVDS_BORDER bit */ temp &= ~LVDS_BORDER_ENABLE; - temp |= intel_crtc->config.gmch_pfit.lvds_border_bits; + temp |= crtc->config.gmch_pfit.lvds_border_bits; /* Set the B0-B3 data pairs corresponding to whether we're going to * set the DPLLs for dual-channel mode or not. */ @@ -169,8 +177,7 @@ static void intel_pre_pll_enable_lvds(struct intel_encoder *encoder) if (INTEL_INFO(dev)->gen == 4) { /* Bspec wording suggests that LVDS port dithering only exists * for 18bpp panels. */ - if (intel_crtc->config.dither && - intel_crtc->config.pipe_bpp == 18) + if (crtc->config.dither && crtc->config.pipe_bpp == 18) temp |= LVDS_ENABLE_DITHER; else temp &= ~LVDS_ENABLE_DITHER; @@ -336,6 +343,9 @@ intel_lvds_detect(struct drm_connector *connector, bool force) struct drm_device *dev = connector->dev; enum drm_connector_status status; + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", + connector->base.id, drm_get_connector_name(connector)); + status = intel_panel_detect(dev); if (status != connector_status_unknown) return status; @@ -959,7 +969,7 @@ void intel_lvds_init(struct drm_device *dev) DRM_MODE_ENCODER_LVDS); intel_encoder->enable = intel_enable_lvds; - intel_encoder->pre_pll_enable = intel_pre_pll_enable_lvds; + intel_encoder->pre_enable = intel_pre_enable_lvds; intel_encoder->compute_config = intel_lvds_compute_config; intel_encoder->disable = intel_disable_lvds; intel_encoder->get_hw_state = intel_lvds_get_hw_state; diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index a369881..9ec5a4e 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -196,7 +196,7 @@ intel_overlay_map_regs(struct intel_overlay *overlay) regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_obj->handle->vaddr; else regs = io_mapping_map_wc(dev_priv->gtt.mappable, - overlay->reg_bo->gtt_offset); + i915_gem_obj_ggtt_offset(overlay->reg_bo)); return regs; } @@ -740,7 +740,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, swidth = params->src_w; swidthsw = calc_swidthsw(overlay->dev, params->offset_Y, tmp_width); sheight = params->src_h; - iowrite32(new_bo->gtt_offset + params->offset_Y, ®s->OBUF_0Y); + iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_Y, ®s->OBUF_0Y); ostride = params->stride_Y; if (params->format & I915_OVERLAY_YUV_PLANAR) { @@ -754,8 +754,8 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, params->src_w/uv_hscale); swidthsw |= max_t(u32, tmp_U, tmp_V) << 16; sheight |= (params->src_h/uv_vscale) << 16; - iowrite32(new_bo->gtt_offset + params->offset_U, ®s->OBUF_0U); - iowrite32(new_bo->gtt_offset + params->offset_V, ®s->OBUF_0V); + iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_U, ®s->OBUF_0U); + iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_V, ®s->OBUF_0V); ostride |= params->stride_UV << 16; } @@ -1333,7 +1333,9 @@ void intel_setup_overlay(struct drm_device *dev) overlay->dev = dev; - reg_bo = i915_gem_object_create_stolen(dev, PAGE_SIZE); + reg_bo = NULL; + if (!OVERLAY_NEEDS_PHYSICAL(dev)) + reg_bo = i915_gem_object_create_stolen(dev, PAGE_SIZE); if (reg_bo == NULL) reg_bo = i915_gem_alloc_object(dev, PAGE_SIZE); if (reg_bo == NULL) @@ -1355,7 +1357,7 @@ void intel_setup_overlay(struct drm_device *dev) DRM_ERROR("failed to pin overlay register bo\n"); goto out_free_bo; } - overlay->flip_addr = reg_bo->gtt_offset; + overlay->flip_addr = i915_gem_obj_ggtt_offset(reg_bo); ret = i915_gem_object_set_to_gtt_domain(reg_bo, true); if (ret) { @@ -1412,9 +1414,6 @@ void intel_cleanup_overlay(struct drm_device *dev) kfree(dev_priv->overlay); } -#ifdef CONFIG_DEBUG_FS -#include <linux/seq_file.h> - struct intel_overlay_error_state { struct overlay_registers regs; unsigned long base; @@ -1435,7 +1434,7 @@ intel_overlay_map_regs_atomic(struct intel_overlay *overlay) overlay->reg_bo->phys_obj->handle->vaddr; else regs = io_mapping_map_atomic_wc(dev_priv->gtt.mappable, - overlay->reg_bo->gtt_offset); + i915_gem_obj_ggtt_offset(overlay->reg_bo)); return regs; } @@ -1468,7 +1467,7 @@ intel_overlay_capture_error_state(struct drm_device *dev) if (OVERLAY_NEEDS_PHYSICAL(overlay->dev)) error->base = (__force long)overlay->reg_bo->phys_obj->handle->vaddr; else - error->base = overlay->reg_bo->gtt_offset; + error->base = i915_gem_obj_ggtt_offset(overlay->reg_bo); regs = intel_overlay_map_regs_atomic(overlay); if (!regs) @@ -1537,4 +1536,3 @@ intel_overlay_print_error_state(struct drm_i915_error_state_buf *m, P(UVSCALEV); #undef P } -#endif diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 6a347f5..74d6c4d 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -30,6 +30,7 @@ #include "intel_drv.h" #include "../../../platform/x86/intel_ips.h" #include <linux/module.h> +#include <drm/i915_powerwell.h> #define FORCEWAKE_ACK_TIMEOUT_MS 2 @@ -86,7 +87,7 @@ static void i8xx_enable_fbc(struct drm_crtc *crtc, unsigned long interval) int plane, i; u32 fbc_ctl, fbc_ctl2; - cfb_pitch = dev_priv->cfb_size / FBC_LL_SIZE; + cfb_pitch = dev_priv->fbc.size / FBC_LL_SIZE; if (fb->pitches[0] < cfb_pitch) cfb_pitch = fb->pitches[0]; @@ -217,7 +218,7 @@ static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval) (stall_watermark << DPFC_RECOMP_STALL_WM_SHIFT) | (interval << DPFC_RECOMP_TIMER_COUNT_SHIFT)); I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->y); - I915_WRITE(ILK_FBC_RT_BASE, obj->gtt_offset | ILK_FBC_RT_VALID); + I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj) | ILK_FBC_RT_VALID); /* enable it... */ I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); @@ -274,7 +275,7 @@ static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval) struct drm_i915_gem_object *obj = intel_fb->obj; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - I915_WRITE(IVB_FBC_RT_BASE, obj->gtt_offset); + I915_WRITE(IVB_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj)); I915_WRITE(ILK_DPFC_CONTROL, DPFC_CTL_EN | DPFC_CTL_LIMIT_1X | IVB_DPFC_CTL_FENCE_EN | @@ -325,7 +326,7 @@ static void intel_fbc_work_fn(struct work_struct *__work) struct drm_i915_private *dev_priv = dev->dev_private; mutex_lock(&dev->struct_mutex); - if (work == dev_priv->fbc_work) { + if (work == dev_priv->fbc.fbc_work) { /* Double check that we haven't switched fb without cancelling * the prior work. */ @@ -333,12 +334,12 @@ static void intel_fbc_work_fn(struct work_struct *__work) dev_priv->display.enable_fbc(work->crtc, work->interval); - dev_priv->cfb_plane = to_intel_crtc(work->crtc)->plane; - dev_priv->cfb_fb = work->crtc->fb->base.id; - dev_priv->cfb_y = work->crtc->y; + dev_priv->fbc.plane = to_intel_crtc(work->crtc)->plane; + dev_priv->fbc.fb_id = work->crtc->fb->base.id; + dev_priv->fbc.y = work->crtc->y; } - dev_priv->fbc_work = NULL; + dev_priv->fbc.fbc_work = NULL; } mutex_unlock(&dev->struct_mutex); @@ -347,28 +348,28 @@ static void intel_fbc_work_fn(struct work_struct *__work) static void intel_cancel_fbc_work(struct drm_i915_private *dev_priv) { - if (dev_priv->fbc_work == NULL) + if (dev_priv->fbc.fbc_work == NULL) return; DRM_DEBUG_KMS("cancelling pending FBC enable\n"); /* Synchronisation is provided by struct_mutex and checking of - * dev_priv->fbc_work, so we can perform the cancellation + * dev_priv->fbc.fbc_work, so we can perform the cancellation * entirely asynchronously. */ - if (cancel_delayed_work(&dev_priv->fbc_work->work)) + if (cancel_delayed_work(&dev_priv->fbc.fbc_work->work)) /* tasklet was killed before being run, clean up */ - kfree(dev_priv->fbc_work); + kfree(dev_priv->fbc.fbc_work); /* Mark the work as no longer wanted so that if it does * wake-up (because the work was already running and waiting * for our mutex), it will discover that is no longer * necessary to run. */ - dev_priv->fbc_work = NULL; + dev_priv->fbc.fbc_work = NULL; } -void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval) +static void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval) { struct intel_fbc_work *work; struct drm_device *dev = crtc->dev; @@ -381,6 +382,7 @@ void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval) work = kzalloc(sizeof *work, GFP_KERNEL); if (work == NULL) { + DRM_ERROR("Failed to allocate FBC work structure\n"); dev_priv->display.enable_fbc(crtc, interval); return; } @@ -390,9 +392,7 @@ void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval) work->interval = interval; INIT_DELAYED_WORK(&work->work, intel_fbc_work_fn); - dev_priv->fbc_work = work; - - DRM_DEBUG_KMS("scheduling delayed FBC enable\n"); + dev_priv->fbc.fbc_work = work; /* Delay the actual enabling to let pageflipping cease and the * display to settle before starting the compression. Note that @@ -404,6 +404,8 @@ void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval) * following the termination of the page-flipping sequence * and indeed performing the enable as a co-routine and not * waiting synchronously upon the vblank. + * + * WaFbcWaitForVBlankBeforeEnable:ilk,snb */ schedule_delayed_work(&work->work, msecs_to_jiffies(50)); } @@ -418,7 +420,7 @@ void intel_disable_fbc(struct drm_device *dev) return; dev_priv->display.disable_fbc(dev); - dev_priv->cfb_plane = -1; + dev_priv->fbc.plane = -1; } /** @@ -448,7 +450,6 @@ void intel_update_fbc(struct drm_device *dev) struct drm_framebuffer *fb; struct intel_framebuffer *intel_fb; struct drm_i915_gem_object *obj; - int enable_fbc; unsigned int max_hdisplay, max_vdisplay; if (!i915_powersave) @@ -471,7 +472,8 @@ void intel_update_fbc(struct drm_device *dev) !to_intel_crtc(tmp_crtc)->primary_disabled) { if (crtc) { DRM_DEBUG_KMS("more than one pipe active, disabling compression\n"); - dev_priv->no_fbc_reason = FBC_MULTIPLE_PIPES; + dev_priv->fbc.no_fbc_reason = + FBC_MULTIPLE_PIPES; goto out_disable; } crtc = tmp_crtc; @@ -480,7 +482,7 @@ void intel_update_fbc(struct drm_device *dev) if (!crtc || crtc->fb == NULL) { DRM_DEBUG_KMS("no output, disabling\n"); - dev_priv->no_fbc_reason = FBC_NO_OUTPUT; + dev_priv->fbc.no_fbc_reason = FBC_NO_OUTPUT; goto out_disable; } @@ -489,23 +491,22 @@ void intel_update_fbc(struct drm_device *dev) intel_fb = to_intel_framebuffer(fb); obj = intel_fb->obj; - enable_fbc = i915_enable_fbc; - if (enable_fbc < 0) { - DRM_DEBUG_KMS("fbc set to per-chip default\n"); - enable_fbc = 1; - if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) - enable_fbc = 0; + if (i915_enable_fbc < 0 && + INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) { + DRM_DEBUG_KMS("disabled per chip default\n"); + dev_priv->fbc.no_fbc_reason = FBC_CHIP_DEFAULT; + goto out_disable; } - if (!enable_fbc) { + if (!i915_enable_fbc) { DRM_DEBUG_KMS("fbc disabled per module param\n"); - dev_priv->no_fbc_reason = FBC_MODULE_PARAM; + dev_priv->fbc.no_fbc_reason = FBC_MODULE_PARAM; goto out_disable; } if ((crtc->mode.flags & DRM_MODE_FLAG_INTERLACE) || (crtc->mode.flags & DRM_MODE_FLAG_DBLSCAN)) { DRM_DEBUG_KMS("mode incompatible with compression, " "disabling\n"); - dev_priv->no_fbc_reason = FBC_UNSUPPORTED_MODE; + dev_priv->fbc.no_fbc_reason = FBC_UNSUPPORTED_MODE; goto out_disable; } @@ -519,13 +520,13 @@ void intel_update_fbc(struct drm_device *dev) if ((crtc->mode.hdisplay > max_hdisplay) || (crtc->mode.vdisplay > max_vdisplay)) { DRM_DEBUG_KMS("mode too large for compression, disabling\n"); - dev_priv->no_fbc_reason = FBC_MODE_TOO_LARGE; + dev_priv->fbc.no_fbc_reason = FBC_MODE_TOO_LARGE; goto out_disable; } if ((IS_I915GM(dev) || IS_I945GM(dev) || IS_HASWELL(dev)) && intel_crtc->plane != 0) { DRM_DEBUG_KMS("plane not 0, disabling compression\n"); - dev_priv->no_fbc_reason = FBC_BAD_PLANE; + dev_priv->fbc.no_fbc_reason = FBC_BAD_PLANE; goto out_disable; } @@ -535,7 +536,7 @@ void intel_update_fbc(struct drm_device *dev) if (obj->tiling_mode != I915_TILING_X || obj->fence_reg == I915_FENCE_REG_NONE) { DRM_DEBUG_KMS("framebuffer not tiled or fenced, disabling compression\n"); - dev_priv->no_fbc_reason = FBC_NOT_TILED; + dev_priv->fbc.no_fbc_reason = FBC_NOT_TILED; goto out_disable; } @@ -545,7 +546,7 @@ void intel_update_fbc(struct drm_device *dev) if (i915_gem_stolen_setup_compression(dev, intel_fb->obj->base.size)) { DRM_DEBUG_KMS("framebuffer too large, disabling compression\n"); - dev_priv->no_fbc_reason = FBC_STOLEN_TOO_SMALL; + dev_priv->fbc.no_fbc_reason = FBC_STOLEN_TOO_SMALL; goto out_disable; } @@ -554,9 +555,9 @@ void intel_update_fbc(struct drm_device *dev) * cannot be unpinned (and have its GTT offset and fence revoked) * without first being decoupled from the scanout and FBC disabled. */ - if (dev_priv->cfb_plane == intel_crtc->plane && - dev_priv->cfb_fb == fb->base.id && - dev_priv->cfb_y == crtc->y) + if (dev_priv->fbc.plane == intel_crtc->plane && + dev_priv->fbc.fb_id == fb->base.id && + dev_priv->fbc.y == crtc->y) return; if (intel_fbc_enabled(dev)) { @@ -2468,8 +2469,8 @@ static void hsw_compute_wm_results(struct drm_device *dev, /* Find the result with the highest level enabled. Check for enable_fbc_wm in * case both are at the same level. Prefer r1 in case they're the same. */ -struct hsw_wm_values *hsw_find_best_result(struct hsw_wm_values *r1, - struct hsw_wm_values *r2) +static struct hsw_wm_values *hsw_find_best_result(struct hsw_wm_values *r1, + struct hsw_wm_values *r2) { int i, val_r1 = 0, val_r2 = 0; @@ -3076,19 +3077,12 @@ void gen6_set_rps(struct drm_device *dev, u8 val) */ static void vlv_update_rps_cur_delay(struct drm_i915_private *dev_priv) { - unsigned long timeout = jiffies + msecs_to_jiffies(10); u32 pval; WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock)); - do { - pval = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS); - if (time_after(jiffies, timeout)) { - DRM_DEBUG_DRIVER("timed out waiting for Punit\n"); - break; - } - udelay(10); - } while (pval & 1); + if (wait_for(((pval = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS)) & GENFREQSTATUS) == 0, 10)) + DRM_DEBUG_DRIVER("timed out waiting for Punit\n"); pval >>= 8; @@ -3129,13 +3123,10 @@ void valleyview_set_rps(struct drm_device *dev, u8 val) trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv->mem_freq, val)); } - -static void gen6_disable_rps(struct drm_device *dev) +static void gen6_disable_rps_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - I915_WRITE(GEN6_RC_CONTROL, 0); - I915_WRITE(GEN6_RPNSWREQ, 1 << 31); I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) & ~GEN6_PM_RPS_EVENTS); /* Complete PM interrupt masking here doesn't race with the rps work @@ -3143,30 +3134,30 @@ static void gen6_disable_rps(struct drm_device *dev) * register (PMIMR) to mask PM interrupts. The only risk is in leaving * stale bits in PMIIR and PMIMR which gen6_enable_rps will clean up. */ - spin_lock_irq(&dev_priv->rps.lock); + spin_lock_irq(&dev_priv->irq_lock); dev_priv->rps.pm_iir = 0; - spin_unlock_irq(&dev_priv->rps.lock); + spin_unlock_irq(&dev_priv->irq_lock); I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS); } -static void valleyview_disable_rps(struct drm_device *dev) +static void gen6_disable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; I915_WRITE(GEN6_RC_CONTROL, 0); - I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); - I915_WRITE(GEN6_PMIER, 0); - /* Complete PM interrupt masking here doesn't race with the rps work - * item again unmasking PM interrupts because that is using a different - * register (PMIMR) to mask PM interrupts. The only risk is in leaving - * stale bits in PMIIR and PMIMR which gen6_enable_rps will clean up. */ + I915_WRITE(GEN6_RPNSWREQ, 1 << 31); - spin_lock_irq(&dev_priv->rps.lock); - dev_priv->rps.pm_iir = 0; - spin_unlock_irq(&dev_priv->rps.lock); + gen6_disable_rps_interrupts(dev); +} + +static void valleyview_disable_rps(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; - I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR)); + I915_WRITE(GEN6_RC_CONTROL, 0); + + gen6_disable_rps_interrupts(dev); if (dev_priv->vlv_pctx) { drm_gem_object_unreference(&dev_priv->vlv_pctx->base); @@ -3176,6 +3167,10 @@ static void valleyview_disable_rps(struct drm_device *dev) int intel_enable_rc6(const struct drm_device *dev) { + /* No RC6 before Ironlake */ + if (INTEL_INFO(dev)->gen < 5) + return 0; + /* Respect the kernel parameter if it is set */ if (i915_enable_rc6 >= 0) return i915_enable_rc6; @@ -3199,6 +3194,19 @@ int intel_enable_rc6(const struct drm_device *dev) return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE); } +static void gen6_enable_rps_interrupts(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + spin_lock_irq(&dev_priv->irq_lock); + WARN_ON(dev_priv->rps.pm_iir); + I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS); + I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS); + spin_unlock_irq(&dev_priv->irq_lock); + /* unmask all PM interrupts */ + I915_WRITE(GEN6_PMINTRMSK, 0); +} + static void gen6_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3327,17 +3335,7 @@ static void gen6_enable_rps(struct drm_device *dev) gen6_set_rps(dev_priv->dev, (gt_perf_status & 0xff00) >> 8); - /* requires MSI enabled */ - I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) | GEN6_PM_RPS_EVENTS); - spin_lock_irq(&dev_priv->rps.lock); - /* FIXME: Our interrupt enabling sequence is bonghits. - * dev_priv->rps.pm_iir really should be 0 here. */ - dev_priv->rps.pm_iir = 0; - I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS); - I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS); - spin_unlock_irq(&dev_priv->rps.lock); - /* unmask all PM interrupts */ - I915_WRITE(GEN6_PMINTRMSK, 0); + gen6_enable_rps_interrupts(dev); rc6vids = 0; ret = sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS, &rc6vids); @@ -3482,7 +3480,7 @@ static void valleyview_setup_pctx(struct drm_device *dev) pcbr_offset = (pcbr & (~4095)) - dev_priv->mm.stolen_base; pctx = i915_gem_object_create_stolen_for_preallocated(dev_priv->dev, pcbr_offset, - -1, + I915_GTT_OFFSET_NONE, pctx_size); goto out; } @@ -3607,14 +3605,7 @@ static void valleyview_enable_rps(struct drm_device *dev) valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay); - /* requires MSI enabled */ - I915_WRITE(GEN6_PMIER, GEN6_PM_RPS_EVENTS); - spin_lock_irq(&dev_priv->rps.lock); - WARN_ON(dev_priv->rps.pm_iir != 0); - I915_WRITE(GEN6_PMIMR, 0); - spin_unlock_irq(&dev_priv->rps.lock); - /* enable all PM interrupts */ - I915_WRITE(GEN6_PMINTRMSK, 0); + gen6_enable_rps_interrupts(dev); gen6_gt_force_wake_put(dev_priv); } @@ -3708,7 +3699,7 @@ static void ironlake_enable_rc6(struct drm_device *dev) intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN); intel_ring_emit(ring, MI_SET_CONTEXT); - intel_ring_emit(ring, dev_priv->ips.renderctx->gtt_offset | + intel_ring_emit(ring, i915_gem_obj_ggtt_offset(dev_priv->ips.renderctx) | MI_MM_SPACE_GTT | MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN | @@ -3731,7 +3722,7 @@ static void ironlake_enable_rc6(struct drm_device *dev) return; } - I915_WRITE(PWRCTXA, dev_priv->ips.pwrctx->gtt_offset | PWRCTX_EN); + I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN); I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT); } @@ -4429,7 +4420,10 @@ static void ironlake_init_clock_gating(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; uint32_t dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE; - /* Required for FBC */ + /* + * Required for FBC + * WaFbcDisableDpfcClockGating:ilk + */ dspclk_gate |= ILK_DPFCRUNIT_CLOCK_GATE_DISABLE | ILK_DPFCUNIT_CLOCK_GATE_DISABLE | ILK_DPFDUNIT_CLOCK_GATE_ENABLE; @@ -4466,6 +4460,7 @@ static void ironlake_init_clock_gating(struct drm_device *dev) * The bit 7,8,9 of 0x42020. */ if (IS_IRONLAKE_M(dev)) { + /* WaFbcAsynchFlipDisableFbcQueue:ilk */ I915_WRITE(ILK_DISPLAY_CHICKEN1, I915_READ(ILK_DISPLAY_CHICKEN1) | ILK_FBCQ_DIS); @@ -4602,6 +4597,8 @@ static void gen6_init_clock_gating(struct drm_device *dev) * The bit5 and bit7 of 0x42020 * The bit14 of 0x70180 * The bit14 of 0x71180 + * + * WaFbcAsynchFlipDisableFbcQueue:snb */ I915_WRITE(ILK_DISPLAY_CHICKEN1, I915_READ(ILK_DISPLAY_CHICKEN1) | @@ -5497,8 +5494,6 @@ void intel_gt_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - spin_lock_init(&dev_priv->gt_lock); - if (IS_VALLEYVIEW(dev)) { dev_priv->gt.force_wake_get = vlv_force_wake_get; dev_priv->gt.force_wake_put = vlv_force_wake_put; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 664118d..8527ea0 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -440,14 +440,14 @@ static int init_ring_common(struct intel_ring_buffer *ring) * registers with the above sequence (the readback of the HEAD registers * also enforces ordering), otherwise the hw might lose the new ring * register values. */ - I915_WRITE_START(ring, obj->gtt_offset); + I915_WRITE_START(ring, i915_gem_obj_ggtt_offset(obj)); I915_WRITE_CTL(ring, ((ring->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID); /* If the head is still not zero, the ring is dead */ if (wait_for((I915_READ_CTL(ring) & RING_VALID) != 0 && - I915_READ_START(ring) == obj->gtt_offset && + I915_READ_START(ring) == i915_gem_obj_ggtt_offset(obj) && (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) { DRM_ERROR("%s initialization failed " "ctl %08x head %08x tail %08x start %08x\n", @@ -505,7 +505,7 @@ init_pipe_control(struct intel_ring_buffer *ring) if (ret) goto err_unref; - pc->gtt_offset = obj->gtt_offset; + pc->gtt_offset = i915_gem_obj_ggtt_offset(obj); pc->cpu_page = kmap(sg_page(obj->pages->sgl)); if (pc->cpu_page == NULL) { ret = -ENOMEM; @@ -836,7 +836,7 @@ gen5_ring_get_irq(struct intel_ring_buffer *ring) return false; spin_lock_irqsave(&dev_priv->irq_lock, flags); - if (ring->irq_refcount.gt++ == 0) { + if (ring->irq_refcount++ == 0) { dev_priv->gt_irq_mask &= ~ring->irq_enable_mask; I915_WRITE(GTIMR, dev_priv->gt_irq_mask); POSTING_READ(GTIMR); @@ -854,7 +854,7 @@ gen5_ring_put_irq(struct intel_ring_buffer *ring) unsigned long flags; spin_lock_irqsave(&dev_priv->irq_lock, flags); - if (--ring->irq_refcount.gt == 0) { + if (--ring->irq_refcount == 0) { dev_priv->gt_irq_mask |= ring->irq_enable_mask; I915_WRITE(GTIMR, dev_priv->gt_irq_mask); POSTING_READ(GTIMR); @@ -873,7 +873,7 @@ i9xx_ring_get_irq(struct intel_ring_buffer *ring) return false; spin_lock_irqsave(&dev_priv->irq_lock, flags); - if (ring->irq_refcount.gt++ == 0) { + if (ring->irq_refcount++ == 0) { dev_priv->irq_mask &= ~ring->irq_enable_mask; I915_WRITE(IMR, dev_priv->irq_mask); POSTING_READ(IMR); @@ -891,7 +891,7 @@ i9xx_ring_put_irq(struct intel_ring_buffer *ring) unsigned long flags; spin_lock_irqsave(&dev_priv->irq_lock, flags); - if (--ring->irq_refcount.gt == 0) { + if (--ring->irq_refcount == 0) { dev_priv->irq_mask |= ring->irq_enable_mask; I915_WRITE(IMR, dev_priv->irq_mask); POSTING_READ(IMR); @@ -910,7 +910,7 @@ i8xx_ring_get_irq(struct intel_ring_buffer *ring) return false; spin_lock_irqsave(&dev_priv->irq_lock, flags); - if (ring->irq_refcount.gt++ == 0) { + if (ring->irq_refcount++ == 0) { dev_priv->irq_mask &= ~ring->irq_enable_mask; I915_WRITE16(IMR, dev_priv->irq_mask); POSTING_READ16(IMR); @@ -928,7 +928,7 @@ i8xx_ring_put_irq(struct intel_ring_buffer *ring) unsigned long flags; spin_lock_irqsave(&dev_priv->irq_lock, flags); - if (--ring->irq_refcount.gt == 0) { + if (--ring->irq_refcount == 0) { dev_priv->irq_mask |= ring->irq_enable_mask; I915_WRITE16(IMR, dev_priv->irq_mask); POSTING_READ16(IMR); @@ -1021,7 +1021,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring) gen6_gt_force_wake_get(dev_priv); spin_lock_irqsave(&dev_priv->irq_lock, flags); - if (ring->irq_refcount.gt++ == 0) { + if (ring->irq_refcount++ == 0) { if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS) I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | @@ -1045,7 +1045,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring) unsigned long flags; spin_lock_irqsave(&dev_priv->irq_lock, flags); - if (--ring->irq_refcount.gt == 0) { + if (--ring->irq_refcount == 0) { if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS) I915_WRITE_IMR(ring, ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT); @@ -1070,14 +1070,14 @@ hsw_vebox_get_irq(struct intel_ring_buffer *ring) if (!dev->irq_enabled) return false; - spin_lock_irqsave(&dev_priv->rps.lock, flags); - if (ring->irq_refcount.pm++ == 0) { + spin_lock_irqsave(&dev_priv->irq_lock, flags); + if (ring->irq_refcount++ == 0) { u32 pm_imr = I915_READ(GEN6_PMIMR); I915_WRITE_IMR(ring, ~ring->irq_enable_mask); I915_WRITE(GEN6_PMIMR, pm_imr & ~ring->irq_enable_mask); POSTING_READ(GEN6_PMIMR); } - spin_unlock_irqrestore(&dev_priv->rps.lock, flags); + spin_unlock_irqrestore(&dev_priv->irq_lock, flags); return true; } @@ -1092,14 +1092,14 @@ hsw_vebox_put_irq(struct intel_ring_buffer *ring) if (!dev->irq_enabled) return; - spin_lock_irqsave(&dev_priv->rps.lock, flags); - if (--ring->irq_refcount.pm == 0) { + spin_lock_irqsave(&dev_priv->irq_lock, flags); + if (--ring->irq_refcount == 0) { u32 pm_imr = I915_READ(GEN6_PMIMR); I915_WRITE_IMR(ring, ~0); I915_WRITE(GEN6_PMIMR, pm_imr | ring->irq_enable_mask); POSTING_READ(GEN6_PMIMR); } - spin_unlock_irqrestore(&dev_priv->rps.lock, flags); + spin_unlock_irqrestore(&dev_priv->irq_lock, flags); } static int @@ -1144,7 +1144,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring, intel_ring_advance(ring); } else { struct drm_i915_gem_object *obj = ring->private; - u32 cs_offset = obj->gtt_offset; + u32 cs_offset = i915_gem_obj_ggtt_offset(obj); if (len > I830_BATCH_LIMIT) return -ENOSPC; @@ -1229,7 +1229,7 @@ static int init_status_page(struct intel_ring_buffer *ring) goto err_unref; } - ring->status_page.gfx_addr = obj->gtt_offset; + ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj); ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl)); if (ring->status_page.page_addr == NULL) { ret = -ENOMEM; @@ -1316,7 +1316,7 @@ static int intel_init_ring_buffer(struct drm_device *dev, goto err_unpin; ring->virtual_start = - ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset, + ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj), ring->size); if (ring->virtual_start == NULL) { DRM_ERROR("Failed to map ringbuffer.\n"); @@ -2008,8 +2008,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev) ring->add_request = gen6_add_request; ring->get_seqno = gen6_ring_get_seqno; ring->set_seqno = ring_set_seqno; - ring->irq_enable_mask = PM_VEBOX_USER_INTERRUPT | - PM_VEBOX_CS_ERROR_INTERRUPT; + ring->irq_enable_mask = PM_VEBOX_USER_INTERRUPT; ring->irq_get = hsw_vebox_get_irq; ring->irq_put = hsw_vebox_put_irq; ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 799f04c..6e38256 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -78,10 +78,7 @@ struct intel_ring_buffer { */ u32 last_retired_head; - struct { - u32 gt; /* protected by dev_priv->irq_lock */ - u32 pm; /* protected by dev_priv->rps.lock (sucks) */ - } irq_refcount; + unsigned irq_refcount; /* protected by dev_priv->irq_lock */ u32 irq_enable_mask; /* bitmask to enable ring interrupt */ u32 trace_irq_seqno; u32 sync_seqno[I915_NUM_RINGS-1]; diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 2628d56..c3b59b8 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1357,22 +1357,21 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, } /* Cross check the port pixel multiplier with the sdvo encoder state. */ - intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_CLOCK_RATE_MULT, &val, 1); - switch (val) { - case SDVO_CLOCK_RATE_MULT_1X: - encoder_pixel_multiplier = 1; - break; - case SDVO_CLOCK_RATE_MULT_2X: - encoder_pixel_multiplier = 2; - break; - case SDVO_CLOCK_RATE_MULT_4X: - encoder_pixel_multiplier = 4; - break; + if (intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_CLOCK_RATE_MULT, + &val, 1)) { + switch (val) { + case SDVO_CLOCK_RATE_MULT_1X: + encoder_pixel_multiplier = 1; + break; + case SDVO_CLOCK_RATE_MULT_2X: + encoder_pixel_multiplier = 2; + break; + case SDVO_CLOCK_RATE_MULT_4X: + encoder_pixel_multiplier = 4; + break; + } } - if(HAS_PCH_SPLIT(dev)) - return; /* no pixel multiplier readout support yet */ - WARN(encoder_pixel_multiplier != pipe_config->pixel_multiplier, "SDVO pixel multiplier mismatch, port: %i, encoder: %i\n", pipe_config->pixel_multiplier, encoder_pixel_multiplier); @@ -1697,6 +1696,9 @@ intel_sdvo_detect(struct drm_connector *connector, bool force) struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); enum drm_connector_status ret; + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", + connector->base.id, drm_get_connector_name(connector)); + if (!intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ATTACHED_DISPLAYS, &response, 2)) diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 1fa5612..55bdf70 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -133,7 +133,7 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb, I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w); I915_WRITE(SPCNTR(pipe, plane), sprctl); - I915_MODIFY_DISPBASE(SPSURF(pipe, plane), obj->gtt_offset + + I915_MODIFY_DISPBASE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) + sprsurf_offset); POSTING_READ(SPSURF(pipe, plane)); } @@ -308,7 +308,8 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb, if (intel_plane->can_scale) I915_WRITE(SPRSCALE(pipe), sprscale); I915_WRITE(SPRCTL(pipe), sprctl); - I915_MODIFY_DISPBASE(SPRSURF(pipe), obj->gtt_offset + sprsurf_offset); + I915_MODIFY_DISPBASE(SPRSURF(pipe), + i915_gem_obj_ggtt_offset(obj) + sprsurf_offset); POSTING_READ(SPRSURF(pipe)); /* potentially re-enable LP watermarks */ @@ -478,7 +479,8 @@ ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb, I915_WRITE(DVSSIZE(pipe), (crtc_h << 16) | crtc_w); I915_WRITE(DVSSCALE(pipe), dvsscale); I915_WRITE(DVSCNTR(pipe), dvscntr); - I915_MODIFY_DISPBASE(DVSSURF(pipe), obj->gtt_offset + dvssurf_offset); + I915_MODIFY_DISPBASE(DVSSURF(pipe), + i915_gem_obj_ggtt_offset(obj) + dvssurf_offset); POSTING_READ(DVSSURF(pipe)); } diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 39debd8..b0b446f 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1305,6 +1305,10 @@ intel_tv_detect(struct drm_connector *connector, bool force) struct intel_tv *intel_tv = intel_attached_tv(connector); int type; + DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n", + connector->base.id, drm_get_connector_name(connector), + force); + mode = reported_modes[0]; if (force) { |