Need MST sideband message transaction to power up/down nodes.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
return 1;
}
-static uint32_t find_bb_size(struct parser_exec_state *s)
+static int find_bb_size(struct parser_exec_state *s)
{
unsigned long gma = 0;
struct cmd_info *info;
- uint32_t bb_size = 0;
+ int bb_size = 0;
uint32_t cmd_len = 0;
bool met_bb_end = false;
struct intel_vgpu *vgpu = s->vgpu;
/* get the size of the batch buffer */
bb_size = find_bb_size(s);
+ if (bb_size < 0)
+ return -EINVAL;
/* allocate shadow batch buffer */
entry_obj = kmalloc(sizeof(*entry_obj), GFP_KERNEL);
{
struct intel_vgpu *vgpu = workload->vgpu;
unsigned long gma_head, gma_tail, gma_top, guest_rb_size;
- u32 *cs;
+ void *shadow_ring_buffer_va;
+ int ring_id = workload->ring_id;
int ret;
guest_rb_size = _RING_CTL_BUF_SIZE(workload->rb_ctl);
gma_tail = workload->rb_start + workload->rb_tail;
gma_top = workload->rb_start + guest_rb_size;
- /* allocate shadow ring buffer */
- cs = intel_ring_begin(workload->req, workload->rb_len / sizeof(u32));
- if (IS_ERR(cs))
- return PTR_ERR(cs);
+ if (workload->rb_len > vgpu->reserve_ring_buffer_size[ring_id]) {
+ void *va = vgpu->reserve_ring_buffer_va[ring_id];
+ /* realloc the new ring buffer if needed */
+ vgpu->reserve_ring_buffer_va[ring_id] =
+ krealloc(va, workload->rb_len, GFP_KERNEL);
+ if (!vgpu->reserve_ring_buffer_va[ring_id]) {
+ gvt_vgpu_err("fail to alloc reserve ring buffer\n");
+ return -ENOMEM;
+ }
+ vgpu->reserve_ring_buffer_size[ring_id] = workload->rb_len;
+ }
+
+ shadow_ring_buffer_va = vgpu->reserve_ring_buffer_va[ring_id];
/* get shadow ring buffer va */
- workload->shadow_ring_buffer_va = cs;
+ workload->shadow_ring_buffer_va = shadow_ring_buffer_va;
/* head > tail --> copy head <-> top */
if (gma_head > gma_tail) {
ret = copy_gma_to_hva(vgpu, vgpu->gtt.ggtt_mm,
- gma_head, gma_top, cs);
+ gma_head, gma_top, shadow_ring_buffer_va);
if (ret < 0) {
gvt_vgpu_err("fail to copy guest ring buffer\n");
return ret;
}
- cs += ret / sizeof(u32);
+ shadow_ring_buffer_va += ret;
gma_head = workload->rb_start;
}
/* copy head or start <-> tail */
- ret = copy_gma_to_hva(vgpu, vgpu->gtt.ggtt_mm, gma_head, gma_tail, cs);
+ ret = copy_gma_to_hva(vgpu, vgpu->gtt.ggtt_mm, gma_head, gma_tail,
+ shadow_ring_buffer_va);
if (ret < 0) {
gvt_vgpu_err("fail to copy guest ring buffer\n");
return ret;
}
- cs += ret / sizeof(u32);
- intel_ring_advance(workload->req, cs);
return 0;
}
unmap_src:
i915_gem_object_unpin_map(obj);
put_obj:
- i915_gem_object_put(wa_ctx->indirect_ctx.obj);
+ i915_gem_object_put(obj);
return ret;
}
#include <linux/debugfs.h>
#include <linux/sort.h>
+ #include <linux/sched/mm.h>
#include "intel_drv.h"
static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node)
#undef PRINT_FLAG
kernel_param_lock(THIS_MODULE);
-#define PRINT_PARAM(T, x) seq_print_param(m, #x, #T, &i915.x);
+#define PRINT_PARAM(T, x, ...) seq_print_param(m, #x, #T, &i915_modparams.x);
I915_PARAMS_FOR_EACH(PRINT_PARAM);
#undef PRINT_PARAM
kernel_param_unlock(THIS_MODULE);
if (waitqueue_active(&dev_priv->gpu_error.reset_queue))
seq_puts(m, "struct_mutex blocked for reset\n");
- if (!i915.enable_hangcheck) {
+ if (!i915_modparams.enable_hangcheck) {
seq_puts(m, "Hangcheck disabled\n");
return 0;
}
struct intel_uncore_forcewake_domain *fw_domain;
unsigned int tmp;
+ seq_printf(m, "user.bypass_count = %u\n",
+ i915->uncore.user_forcewake.count);
+
for_each_fw_domain(fw_domain, i915, tmp)
seq_printf(m, "%s.wake_count = %u\n",
intel_uncore_forcewake_domain_to_str(fw_domain->id),
intel_runtime_pm_get(dev_priv);
seq_printf(m, "Enabled by kernel parameter: %s\n",
- yesno(i915.enable_ips));
+ yesno(i915_modparams.enable_ips));
if (INTEL_GEN(dev_priv) >= 8) {
seq_puts(m, "Currently: unknown\n");
enum intel_engine_id id;
int ret;
- if (!i915.enable_execlists) {
+ if (!i915_modparams.enable_execlists) {
seq_printf(m, "Logical Ring Contexts are disabled\n");
return 0;
}
seq_printf(m, "\tPriority %d, GuC stage index: %u, PD offset 0x%x\n",
client->priority, client->stage_id, client->proc_desc_offset);
- seq_printf(m, "\tDoorbell id %d, offset: 0x%lx, cookie 0x%x\n",
- client->doorbell_id, client->doorbell_offset, client->doorbell_cookie);
- seq_printf(m, "\tWQ size %d, offset: 0x%x, tail %d\n",
- client->wq_size, client->wq_offset, client->wq_tail);
-
- seq_printf(m, "\tWork queue full: %u\n", client->no_wq_space);
+ seq_printf(m, "\tDoorbell id %d, offset: 0x%lx\n",
+ client->doorbell_id, client->doorbell_offset);
for_each_engine(engine, dev_priv, id) {
u64 submissions = client->submissions[id];
if (!dev_priv->guc.log.vma)
return -EINVAL;
- *val = i915.guc_log_level;
+ *val = i915_modparams.guc_log_level;
return 0;
}
seq_printf(m, "\tBBADDR: 0x%08x_%08x\n",
upper_32_bits(addr), lower_32_bits(addr));
- if (i915.enable_execlists) {
+ if (i915_modparams.enable_execlists) {
+ const u32 *hws = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
+ struct intel_engine_execlists * const execlists = &engine->execlists;
u32 ptr, read, write;
unsigned int idx;
ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine));
read = GEN8_CSB_READ_PTR(ptr);
write = GEN8_CSB_WRITE_PTR(ptr);
- seq_printf(m, "\tExeclist CSB read %d, write %d, interrupt posted? %s\n",
- read, write,
+ seq_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s\n",
+ read, execlists->csb_head,
+ write,
+ intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
yesno(test_bit(ENGINE_IRQ_EXECLIST,
&engine->irq_posted)));
if (read >= GEN8_CSB_ENTRIES)
write += GEN8_CSB_ENTRIES;
while (read < write) {
idx = ++read % GEN8_CSB_ENTRIES;
- seq_printf(m, "\tExeclist CSB[%d]: 0x%08x, context: %d\n",
+ seq_printf(m, "\tExeclist CSB[%d]: 0x%08x [0x%08x in hwsp], context: %d [%d in hwsp]\n",
idx,
I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)),
- I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)));
+ hws[idx * 2],
+ I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)),
+ hws[idx * 2 + 1]);
}
rcu_read_lock();
- for (idx = 0; idx < ARRAY_SIZE(engine->execlist_port); idx++) {
+ for (idx = 0; idx < execlists_num_ports(execlists); idx++) {
unsigned int count;
- rq = port_unpack(&engine->execlist_port[idx],
- &count);
+ rq = port_unpack(&execlists->port[idx], &count);
if (rq) {
seq_printf(m, "\t\tELSP[%d] count=%d, ",
idx, count);
rcu_read_unlock();
spin_lock_irq(&engine->timeline->lock);
- for (rb = engine->execlist_first; rb; rb = rb_next(rb)){
+ for (rb = execlists->first; rb; rb = rb_next(rb)) {
struct i915_priolist *p =
rb_entry(rb, typeof(*p), node);
enum intel_engine_id id;
int j, ret;
- if (!i915.semaphores) {
+ if (!i915_modparams.semaphores) {
seq_puts(m, "Semaphores are disabled\n");
return 0;
}
return 0;
}
+static int i915_ipc_status_show(struct seq_file *m, void *data)
+{
+ struct drm_i915_private *dev_priv = m->private;
+
+ seq_printf(m, "Isochronous Priority Control: %s\n",
+ yesno(dev_priv->ipc_enabled));
+ return 0;
+}
+
+static int i915_ipc_status_open(struct inode *inode, struct file *file)
+{
+ struct drm_i915_private *dev_priv = inode->i_private;
+
+ if (!HAS_IPC(dev_priv))
+ return -ENODEV;
+
+ return single_open(file, i915_ipc_status_show, dev_priv);
+}
+
+static ssize_t i915_ipc_status_write(struct file *file, const char __user *ubuf,
+ size_t len, loff_t *offp)
+{
+ struct seq_file *m = file->private_data;
+ struct drm_i915_private *dev_priv = m->private;
+ int ret;
+ bool enable;
+
+ ret = kstrtobool_from_user(ubuf, len, &enable);
+ if (ret < 0)
+ return ret;
+
+ intel_runtime_pm_get(dev_priv);
+ if (!dev_priv->ipc_enabled && enable)
+ DRM_INFO("Enabling IPC: WM will be proper only after next commit\n");
+ dev_priv->wm.distrust_bios_wm = true;
+ dev_priv->ipc_enabled = enable;
+ intel_enable_ipc(dev_priv);
+ intel_runtime_pm_put(dev_priv);
+
+ return len;
+}
+
+static const struct file_operations i915_ipc_status_fops = {
+ .owner = THIS_MODULE,
+ .open = i915_ipc_status_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .write = i915_ipc_status_write
+};
+
static int i915_ddb_info(struct seq_file *m, void *unused)
{
struct drm_i915_private *dev_priv = node_to_i915(m->private);
mutex_unlock(&dev->struct_mutex);
}
- lockdep_set_current_reclaim_state(GFP_KERNEL);
+ fs_reclaim_acquire(GFP_KERNEL);
if (val & DROP_BOUND)
- i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND);
+ i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_BOUND);
if (val & DROP_UNBOUND)
- i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_UNBOUND);
+ i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_UNBOUND);
if (val & DROP_SHRINK_ALL)
i915_gem_shrink_all(dev_priv);
- lockdep_clear_current_reclaim_state();
+ fs_reclaim_release(GFP_KERNEL);
if (val & DROP_FREED) {
synchronize_rcu();
static int i915_forcewake_open(struct inode *inode, struct file *file)
{
- struct drm_i915_private *dev_priv = inode->i_private;
+ struct drm_i915_private *i915 = inode->i_private;
- if (INTEL_GEN(dev_priv) < 6)
+ if (INTEL_GEN(i915) < 6)
return 0;
- intel_runtime_pm_get(dev_priv);
- intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+ intel_runtime_pm_get(i915);
+ intel_uncore_forcewake_user_get(i915);
return 0;
}
static int i915_forcewake_release(struct inode *inode, struct file *file)
{
- struct drm_i915_private *dev_priv = inode->i_private;
+ struct drm_i915_private *i915 = inode->i_private;
- if (INTEL_GEN(dev_priv) < 6)
+ if (INTEL_GEN(i915) < 6)
return 0;
- intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
- intel_runtime_pm_put(dev_priv);
+ intel_uncore_forcewake_user_put(i915);
+ intel_runtime_pm_put(i915);
return 0;
}
{"i915_dp_test_type", &i915_displayport_test_type_fops},
{"i915_dp_test_active", &i915_displayport_test_active_fops},
{"i915_guc_log_control", &i915_guc_log_control_fops},
- {"i915_hpd_storm_ctl", &i915_hpd_storm_ctl_fops}
+ {"i915_hpd_storm_ctl", &i915_hpd_storm_ctl_fops},
+ {"i915_ipc_status", &i915_ipc_status_fops}
};
int i915_debugfs_register(struct drm_i915_private *dev_priv)
#define I915_STATE_WARN(condition, format...) ({ \
int __ret_warn_on = !!(condition); \
if (unlikely(__ret_warn_on)) \
- if (!WARN(i915.verbose_state_checks, format)) \
+ if (!WARN(i915_modparams.verbose_state_checks, format)) \
DRM_ERROR(format); \
unlikely(__ret_warn_on); \
})
{
uint_fixed_16_16_t fp;
- WARN_ON(val >> 16);
+ WARN_ON(val > U16_MAX);
fp.val = val << 16;
return fp;
static inline uint_fixed_16_16_t clamp_u64_to_fixed16(uint64_t val)
{
uint_fixed_16_16_t fp;
- WARN_ON(val >> 32);
- fp.val = clamp_t(uint32_t, val, 0, ~0);
+ WARN_ON(val > U32_MAX);
+ fp.val = (uint32_t) val;
return fp;
}
intermediate_val = (uint64_t) val * mul.val;
intermediate_val = DIV_ROUND_UP_ULL(intermediate_val, 1 << 16);
- WARN_ON(intermediate_val >> 32);
- return clamp_t(uint32_t, intermediate_val, 0, ~0);
+ WARN_ON(intermediate_val > U32_MAX);
+ return (uint32_t) intermediate_val;
}
static inline uint_fixed_16_16_t mul_fixed16(uint_fixed_16_16_t val,
interm_val = (uint64_t)val << 16;
interm_val = DIV_ROUND_UP_ULL(interm_val, d.val);
- WARN_ON(interm_val >> 32);
- return clamp_t(uint32_t, interm_val, 0, ~0);
+ WARN_ON(interm_val > U32_MAX);
+ return (uint32_t) interm_val;
}
static inline uint_fixed_16_16_t mul_u32_fixed16(uint32_t val,
struct drm_atomic_state *old_state);
void (*crtc_disable)(struct intel_crtc_state *old_crtc_state,
struct drm_atomic_state *old_state);
- void (*update_crtcs)(struct drm_atomic_state *state,
- unsigned int *crtc_vblank_mask);
+ void (*update_crtcs)(struct drm_atomic_state *state);
void (*audio_codec_enable)(struct drm_connector *connector,
struct intel_encoder *encoder,
const struct drm_display_mode *adjusted_mode);
func(has_fpga_dbg); \
func(has_full_ppgtt); \
func(has_full_48bit_ppgtt); \
- func(has_gmbus_irq); \
func(has_gmch_display); \
func(has_guc); \
func(has_guc_ct); \
func(cursor_needs_physical); \
func(hws_needs_physical); \
func(overlay_needs_physical); \
- func(supports_tv);
+ func(supports_tv); \
+ func(has_ipc);
struct sseu_dev_info {
u8 slice_mask;
};
struct intel_device_info {
- u32 display_mmio_offset;
u16 device_id;
- u8 num_pipes;
- u8 num_sprites[I915_MAX_PIPES];
- u8 num_scalers[I915_MAX_PIPES];
- u8 gen;
u16 gen_mask;
- enum intel_platform platform;
+
+ u8 gen;
u8 gt; /* GT number, 0 if undefined */
- u8 ring_mask; /* Rings supported by the HW */
u8 num_rings;
+ u8 ring_mask; /* Rings supported by the HW */
+
+ enum intel_platform platform;
+ u32 platform_mask;
+
+ u32 display_mmio_offset;
+
+ u8 num_pipes;
+ u8 num_sprites[I915_MAX_PIPES];
+ u8 num_scalers[I915_MAX_PIPES];
+
#define DEFINE_FLAG(name) u8 name:1
DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG);
#undef DEFINE_FLAG
u16 ddb_size; /* in blocks */
+
/* Register offsets for the various display pipes and transcoders */
int pipe_offsets[I915_MAX_TRANSCODERS];
int trans_offsets[I915_MAX_TRANSCODERS];
u32 seqno;
u32 head;
u32 tail;
- } *requests, execlist[2];
+ } *requests, execlist[EXECLIST_MAX_PORTS];
+ unsigned int num_ports;
struct drm_i915_error_waiter {
char comm[TASK_COMM_LEN];
bool y_cord_support;
bool colorimetry_support;
bool alpm;
+
+ void (*enable_source)(struct intel_dp *,
+ const struct intel_crtc_state *);
+ void (*disable_source)(struct intel_dp *,
+ const struct intel_crtc_state *);
+ void (*enable_sink)(struct intel_dp *);
+ void (*activate)(struct intel_dp *);
+ void (*setup_vsc)(struct intel_dp *, const struct intel_crtc_state *);
};
enum intel_pch {
uint8_t plane_res_l;
};
+/* Stores plane specific WM parameters */
+struct skl_wm_params {
+ bool x_tiled, y_tiled;
+ bool rc_surface;
+ uint32_t width;
+ uint8_t cpp;
+ uint32_t plane_pixel_rate;
+ uint32_t y_min_scanlines;
+ uint32_t plane_bytes_per_line;
+ uint_fixed_16_16_t plane_blocks_per_line;
+ uint_fixed_16_16_t y_tile_minimum;
+ uint32_t linetime_us;
+};
+
/*
* This struct helps tracking the state needed for runtime PM, which puts the
* device in PCI D3 state. Notice that when this happens, nothing on the
DECLARE_HASHTABLE(mm_structs, 7);
struct mutex mm_lock;
+ struct intel_ppat ppat;
+
/* Kernel Modesetting */
struct intel_crtc *plane_to_crtc_mapping[I915_MAX_PIPES];
#define for_each_sgt_dma(__dmap, __iter, __sgt) \
for ((__iter) = __sgt_iter((__sgt)->sgl, true); \
((__dmap) = (__iter).dma + (__iter).curr); \
- (((__iter).curr += PAGE_SIZE) < (__iter).max) || \
- ((__iter) = __sgt_iter(__sg_next((__iter).sgp), true), 0))
+ (((__iter).curr += PAGE_SIZE) >= (__iter).max) ? \
+ (__iter) = __sgt_iter(__sg_next((__iter).sgp), true), 0 : 0)
/**
* for_each_sgt_page - iterate over the pages of the given sg_table
for ((__iter) = __sgt_iter((__sgt)->sgl, false); \
((__pp) = (__iter).pfn == 0 ? NULL : \
pfn_to_page((__iter).pfn + ((__iter).curr >> PAGE_SHIFT))); \
- (((__iter).curr += PAGE_SIZE) < (__iter).max) || \
- ((__iter) = __sgt_iter(__sg_next((__iter).sgp), false), 0))
+ (((__iter).curr += PAGE_SIZE) >= (__iter).max) ? \
+ (__iter) = __sgt_iter(__sg_next((__iter).sgp), false), 0 : 0)
+
+static inline unsigned int i915_sg_segment_size(void)
+{
+ unsigned int size = swiotlb_max_segment();
+
+ if (size == 0)
+ return SCATTERLIST_MAX_SEGMENT;
+
+ size = rounddown(size, PAGE_SIZE);
+ /* swiotlb_max_segment_size can return 1 byte when it means one page. */
+ if (size < PAGE_SIZE)
+ size = PAGE_SIZE;
+
+ return size;
+}
static inline const struct intel_device_info *
intel_info(const struct drm_i915_private *dev_priv)
#define INTEL_REVID(dev_priv) ((dev_priv)->drm.pdev->revision)
#define GEN_FOREVER (0)
+
+#define INTEL_GEN_MASK(s, e) ( \
+ BUILD_BUG_ON_ZERO(!__builtin_constant_p(s)) + \
+ BUILD_BUG_ON_ZERO(!__builtin_constant_p(e)) + \
+ GENMASK((e) != GEN_FOREVER ? (e) - 1 : BITS_PER_LONG - 1, \
+ (s) != GEN_FOREVER ? (s) - 1 : 0) \
+)
+
/*
* Returns true if Gen is in inclusive range [Start, End].
*
* Use GEN_FOREVER for unbound start and or end.
*/
-#define IS_GEN(dev_priv, s, e) ({ \
- unsigned int __s = (s), __e = (e); \
- BUILD_BUG_ON(!__builtin_constant_p(s)); \
- BUILD_BUG_ON(!__builtin_constant_p(e)); \
- if ((__s) != GEN_FOREVER) \
- __s = (s) - 1; \
- if ((__e) == GEN_FOREVER) \
- __e = BITS_PER_LONG - 1; \
- else \
- __e = (e) - 1; \
- !!((dev_priv)->info.gen_mask & GENMASK((__e), (__s))); \
-})
+#define IS_GEN(dev_priv, s, e) \
+ (!!((dev_priv)->info.gen_mask & INTEL_GEN_MASK((s), (e))))
/*
* Return true if revision is in range [since,until] inclusive.
#define IS_REVID(p, since, until) \
(INTEL_REVID(p) >= (since) && INTEL_REVID(p) <= (until))
-#define IS_I830(dev_priv) ((dev_priv)->info.platform == INTEL_I830)
-#define IS_I845G(dev_priv) ((dev_priv)->info.platform == INTEL_I845G)
-#define IS_I85X(dev_priv) ((dev_priv)->info.platform == INTEL_I85X)
-#define IS_I865G(dev_priv) ((dev_priv)->info.platform == INTEL_I865G)
-#define IS_I915G(dev_priv) ((dev_priv)->info.platform == INTEL_I915G)
-#define IS_I915GM(dev_priv) ((dev_priv)->info.platform == INTEL_I915GM)
-#define IS_I945G(dev_priv) ((dev_priv)->info.platform == INTEL_I945G)
-#define IS_I945GM(dev_priv) ((dev_priv)->info.platform == INTEL_I945GM)
-#define IS_I965G(dev_priv) ((dev_priv)->info.platform == INTEL_I965G)
-#define IS_I965GM(dev_priv) ((dev_priv)->info.platform == INTEL_I965GM)
-#define IS_G45(dev_priv) ((dev_priv)->info.platform == INTEL_G45)
-#define IS_GM45(dev_priv) ((dev_priv)->info.platform == INTEL_GM45)
+#define IS_PLATFORM(dev_priv, p) ((dev_priv)->info.platform_mask & BIT(p))
+
+#define IS_I830(dev_priv) IS_PLATFORM(dev_priv, INTEL_I830)
+#define IS_I845G(dev_priv) IS_PLATFORM(dev_priv, INTEL_I845G)
+#define IS_I85X(dev_priv) IS_PLATFORM(dev_priv, INTEL_I85X)
+#define IS_I865G(dev_priv) IS_PLATFORM(dev_priv, INTEL_I865G)
+#define IS_I915G(dev_priv) IS_PLATFORM(dev_priv, INTEL_I915G)
+#define IS_I915GM(dev_priv) IS_PLATFORM(dev_priv, INTEL_I915GM)
+#define IS_I945G(dev_priv) IS_PLATFORM(dev_priv, INTEL_I945G)
+#define IS_I945GM(dev_priv) IS_PLATFORM(dev_priv, INTEL_I945GM)
+#define IS_I965G(dev_priv) IS_PLATFORM(dev_priv, INTEL_I965G)
+#define IS_I965GM(dev_priv) IS_PLATFORM(dev_priv, INTEL_I965GM)
+#define IS_G45(dev_priv) IS_PLATFORM(dev_priv, INTEL_G45)
+#define IS_GM45(dev_priv) IS_PLATFORM(dev_priv, INTEL_GM45)
#define IS_G4X(dev_priv) (IS_G45(dev_priv) || IS_GM45(dev_priv))
#define IS_PINEVIEW_G(dev_priv) (INTEL_DEVID(dev_priv) == 0xa001)
#define IS_PINEVIEW_M(dev_priv) (INTEL_DEVID(dev_priv) == 0xa011)
-#define IS_PINEVIEW(dev_priv) ((dev_priv)->info.platform == INTEL_PINEVIEW)
-#define IS_G33(dev_priv) ((dev_priv)->info.platform == INTEL_G33)
+#define IS_PINEVIEW(dev_priv) IS_PLATFORM(dev_priv, INTEL_PINEVIEW)
+#define IS_G33(dev_priv) IS_PLATFORM(dev_priv, INTEL_G33)
#define IS_IRONLAKE_M(dev_priv) (INTEL_DEVID(dev_priv) == 0x0046)
-#define IS_IVYBRIDGE(dev_priv) ((dev_priv)->info.platform == INTEL_IVYBRIDGE)
+#define IS_IVYBRIDGE(dev_priv) IS_PLATFORM(dev_priv, INTEL_IVYBRIDGE)
#define IS_IVB_GT1(dev_priv) (IS_IVYBRIDGE(dev_priv) && \
(dev_priv)->info.gt == 1)
-#define IS_VALLEYVIEW(dev_priv) ((dev_priv)->info.platform == INTEL_VALLEYVIEW)
-#define IS_CHERRYVIEW(dev_priv) ((dev_priv)->info.platform == INTEL_CHERRYVIEW)
-#define IS_HASWELL(dev_priv) ((dev_priv)->info.platform == INTEL_HASWELL)
-#define IS_BROADWELL(dev_priv) ((dev_priv)->info.platform == INTEL_BROADWELL)
-#define IS_SKYLAKE(dev_priv) ((dev_priv)->info.platform == INTEL_SKYLAKE)
-#define IS_BROXTON(dev_priv) ((dev_priv)->info.platform == INTEL_BROXTON)
-#define IS_KABYLAKE(dev_priv) ((dev_priv)->info.platform == INTEL_KABYLAKE)
-#define IS_GEMINILAKE(dev_priv) ((dev_priv)->info.platform == INTEL_GEMINILAKE)
-#define IS_COFFEELAKE(dev_priv) ((dev_priv)->info.platform == INTEL_COFFEELAKE)
-#define IS_CANNONLAKE(dev_priv) ((dev_priv)->info.platform == INTEL_CANNONLAKE)
+#define IS_VALLEYVIEW(dev_priv) IS_PLATFORM(dev_priv, INTEL_VALLEYVIEW)
+#define IS_CHERRYVIEW(dev_priv) IS_PLATFORM(dev_priv, INTEL_CHERRYVIEW)
+#define IS_HASWELL(dev_priv) IS_PLATFORM(dev_priv, INTEL_HASWELL)
+#define IS_BROADWELL(dev_priv) IS_PLATFORM(dev_priv, INTEL_BROADWELL)
+#define IS_SKYLAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_SKYLAKE)
+#define IS_BROXTON(dev_priv) IS_PLATFORM(dev_priv, INTEL_BROXTON)
+#define IS_KABYLAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_KABYLAKE)
+#define IS_GEMINILAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_GEMINILAKE)
+#define IS_COFFEELAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_COFFEELAKE)
+#define IS_CANNONLAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_CANNONLAKE)
#define IS_MOBILE(dev_priv) ((dev_priv)->info.is_mobile)
#define IS_HSW_EARLY_SDV(dev_priv) (IS_HASWELL(dev_priv) && \
(INTEL_DEVID(dev_priv) & 0xFF00) == 0x0C00)
(dev_priv)->info.gt == 3)
#define IS_CFL_ULT(dev_priv) (IS_COFFEELAKE(dev_priv) && \
(INTEL_DEVID(dev_priv) & 0x00F0) == 0x00A0)
+#define IS_CFL_GT2(dev_priv) (IS_COFFEELAKE(dev_priv) && \
+ (dev_priv)->info.gt == 2)
#define IS_ALPHA_SUPPORT(intel_info) ((intel_info)->is_alpha_support)
#define HAS_LOGICAL_RING_CONTEXTS(dev_priv) \
((dev_priv)->info.has_logical_ring_contexts)
-#define USES_PPGTT(dev_priv) (i915.enable_ppgtt)
-#define USES_FULL_PPGTT(dev_priv) (i915.enable_ppgtt >= 2)
-#define USES_FULL_48BIT_PPGTT(dev_priv) (i915.enable_ppgtt == 3)
+#define USES_PPGTT(dev_priv) (i915_modparams.enable_ppgtt)
+#define USES_FULL_PPGTT(dev_priv) (i915_modparams.enable_ppgtt >= 2)
+#define USES_FULL_48BIT_PPGTT(dev_priv) (i915_modparams.enable_ppgtt == 3)
#define HAS_OVERLAY(dev_priv) ((dev_priv)->info.has_overlay)
#define OVERLAY_NEEDS_PHYSICAL(dev_priv) \
* even when in MSI mode. This results in spurious interrupt warnings if the
* legacy irq no. is shared with another device. The kernel then disables that
* interrupt source and so prevents the other device from working properly.
+ *
+ * Since we don't enable MSI anymore on gen4, we can always use GMBUS/AUX
+ * interrupts.
*/
-#define HAS_AUX_IRQ(dev_priv) ((dev_priv)->info.gen >= 5)
-#define HAS_GMBUS_IRQ(dev_priv) ((dev_priv)->info.has_gmbus_irq)
+#define HAS_AUX_IRQ(dev_priv) true
+#define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
/* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
* rows, which changed the alignment requirements and fence programming.
#define HAS_RUNTIME_PM(dev_priv) ((dev_priv)->info.has_runtime_pm)
#define HAS_64BIT_RELOC(dev_priv) ((dev_priv)->info.has_64bit_reloc)
+#define HAS_IPC(dev_priv) ((dev_priv)->info.has_ipc)
+
/*
* For now, anything with a GuC requires uCode loading, and then supports
* command submission once loaded. But these are logically independent
{
unsigned long delay;
- if (unlikely(!i915.enable_hangcheck))
+ if (unlikely(!i915_modparams.enable_hangcheck))
return;
/* Don't continually defer the hangcheck so that it is always run at
return dev_priv->vgpu.active;
}
+u32 i915_pipestat_enable_mask(struct drm_i915_private *dev_priv,
+ enum pipe pipe);
void
i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
u32 status_mask);
/* i915_gem_shrinker.c */
unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
unsigned long target,
+ unsigned long *nr_scanned,
unsigned flags);
#define I915_SHRINK_PURGEABLE 0x1
#define I915_SHRINK_UNBOUND 0x2
unsigned long addr, unsigned long pfn, unsigned long size,
struct io_mapping *iomap);
+static inline int intel_hws_csb_write_index(struct drm_i915_private *i915)
+{
+ if (INTEL_GEN(i915) >= 10)
+ return CNL_HWS_CSB_WRITE_INDEX;
+ else
+ return I915_HWS_CSB_WRITE_INDEX;
+}
+
#endif
* the alignment of the buddy allocation will naturally match.
*/
phys = drm_pci_alloc(obj->base.dev,
- obj->base.size,
+ roundup_pow_of_two(obj->base.size),
roundup_pow_of_two(obj->base.size));
if (!phys)
return ERR_PTR(-ENOMEM);
switch (obj->base.write_domain) {
case I915_GEM_DOMAIN_GTT:
- if (INTEL_GEN(dev_priv) >= 6 && !HAS_LLC(dev_priv)) {
+ if (!HAS_LLC(dev_priv)) {
intel_runtime_pm_get(dev_priv);
spin_lock_irq(&dev_priv->uncore.lock);
- POSTING_READ_FW(RING_ACTHD(dev_priv->engine[RCS]->mmio_base));
+ POSTING_READ_FW(RING_HEAD(dev_priv->engine[RCS]->mmio_base));
spin_unlock_irq(&dev_priv->uncore.lock);
intel_runtime_pm_put(dev_priv);
}
struct sgt_iter sgt_iter;
struct page *page;
unsigned long last_pfn = 0; /* suppress gcc warning */
- unsigned int max_segment;
+ unsigned int max_segment = i915_sg_segment_size();
gfp_t noreclaim;
int ret;
GEM_BUG_ON(obj->base.read_domains & I915_GEM_GPU_DOMAINS);
GEM_BUG_ON(obj->base.write_domain & I915_GEM_GPU_DOMAINS);
- max_segment = swiotlb_max_segment();
- if (!max_segment)
- max_segment = rounddown(UINT_MAX, PAGE_SIZE);
-
st = kmalloc(sizeof(*st), GFP_KERNEL);
if (st == NULL)
return ERR_PTR(-ENOMEM);
goto err_sg;
}
- i915_gem_shrink(dev_priv, 2 * page_count, *s++);
+ i915_gem_shrink(dev_priv, 2 * page_count, NULL, *s++);
cond_resched();
/* We've tried hard to allocate the memory by reaping
if (n_pages > ARRAY_SIZE(stack_pages)) {
/* Too big for stack -- allocate temporary array instead */
- pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_TEMPORARY);
+ pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
if (!pages)
return NULL;
}
* Turning off the engine->irq_tasklet until the reset is over
* prevents the race.
*/
- tasklet_kill(&engine->irq_tasklet);
- tasklet_disable(&engine->irq_tasklet);
+ tasklet_kill(&engine->execlists.irq_tasklet);
+ tasklet_disable(&engine->execlists.irq_tasklet);
if (engine->irq_seqno_barrier)
engine->irq_seqno_barrier(engine);
void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
{
- tasklet_enable(&engine->irq_tasklet);
+ tasklet_enable(&engine->execlists.irq_tasklet);
kthread_unpark(engine->breadcrumbs.signaler);
}
static void engine_set_wedged(struct intel_engine_cs *engine)
{
- struct drm_i915_gem_request *request;
- unsigned long flags;
-
/* We need to be sure that no thread is running the old callback as
* we install the nop handler (otherwise we would submit a request
* to hardware that will never complete). In order to prevent this
engine->submit_request = nop_submit_request;
/* Mark all executing requests as skipped */
- spin_lock_irqsave(&engine->timeline->lock, flags);
- list_for_each_entry(request, &engine->timeline->requests, link)
- if (!i915_gem_request_completed(request))
- dma_fence_set_error(&request->fence, -EIO);
- spin_unlock_irqrestore(&engine->timeline->lock, flags);
-
- /*
- * Clear the execlists queue up before freeing the requests, as those
- * are the ones that keep the context and ringbuffer backing objects
- * pinned in place.
- */
-
- if (i915.enable_execlists) {
- struct execlist_port *port = engine->execlist_port;
- unsigned long flags;
- unsigned int n;
-
- spin_lock_irqsave(&engine->timeline->lock, flags);
-
- for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++)
- i915_gem_request_put(port_request(&port[n]));
- memset(engine->execlist_port, 0, sizeof(engine->execlist_port));
- engine->execlist_queue = RB_ROOT;
- engine->execlist_first = NULL;
-
- spin_unlock_irqrestore(&engine->timeline->lock, flags);
-
- /* The port is checked prior to scheduling a tasklet, but
- * just in case we have suspended the tasklet to do the
- * wedging make sure that when it wakes, it decides there
- * is no work to do by clearing the irq_posted bit.
- */
- clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
- }
+ engine->cancel_requests(engine);
/* Mark all pending requests as complete so that any concurrent
* (lockless) lookup doesn't try and wait upon the request as we
return false;
/* TODO: make semaphores and Execlists play nicely together */
- if (i915.enable_execlists)
+ if (i915_modparams.enable_execlists)
return false;
if (value >= 0)
dev_priv->mm.unordered_timeline = dma_fence_context_alloc(1);
- if (!i915.enable_execlists) {
+ if (!i915_modparams.enable_execlists) {
dev_priv->gt.resume = intel_legacy_submission_resume;
dev_priv->gt.cleanup_engine = intel_engine_cleanup;
} else {
* the objects as well, see i915_gem_freeze()
*/
- i915_gem_shrink(dev_priv, -1UL, I915_SHRINK_UNBOUND);
+ i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_UNBOUND);
i915_gem_drain_freed_objects(dev_priv);
mutex_lock(&dev_priv->drm.struct_mutex);
#define __EXEC_HAS_RELOC BIT(31)
#define __EXEC_VALIDATED BIT(30)
+#define __EXEC_INTERNAL_FLAGS (~0u << 30)
#define UPDATE PIN_OFFSET_FIXED
#define BATCH_OFFSET_BIAS (256*1024)
* as possible to perform the allocation and warn
* if it fails.
*/
- flags = GFP_TEMPORARY;
+ flags = GFP_KERNEL;
if (size > 1)
flags |= __GFP_NORETRY | __GFP_NOWARN;
static int eb_lookup_vmas(struct i915_execbuffer *eb)
{
struct radix_tree_root *handles_vma = &eb->ctx->handles_vma;
- struct drm_i915_gem_object *uninitialized_var(obj);
+ struct drm_i915_gem_object *obj;
unsigned int i;
int err;
goto err_obj;
}
+ /* transfer ref to ctx */
vma->open_count++;
list_add(&lut->obj_link, &obj->lut_list);
list_add(&lut->ctx_link, &eb->ctx->handles_list);
lut->ctx = eb->ctx;
lut->handle = handle;
- /* transfer ref to ctx */
- obj = NULL;
-
add_vma:
err = eb_add_vma(eb, i, vma);
if (unlikely(err))
- goto err_obj;
+ goto err_vma;
GEM_BUG_ON(vma != eb->vma[i]);
GEM_BUG_ON(vma->exec_flags != &eb->flags[i]);
return eb_reserve(eb);
err_obj:
- if (obj)
- i915_gem_object_put(obj);
+ i915_gem_object_put(obj);
err_vma:
eb->vma[i] = NULL;
return err;
urelocs = u64_to_user_ptr(eb->exec[i].relocs_ptr);
size = nreloc * sizeof(*relocs);
- relocs = kvmalloc_array(size, 1, GFP_TEMPORARY);
+ relocs = kvmalloc_array(size, 1, GFP_KERNEL);
if (!relocs) {
kvfree(relocs);
err = -ENOMEM;
const unsigned int count = eb->buffer_count;
unsigned int i;
- if (unlikely(i915.prefault_disable))
+ if (unlikely(i915_modparams.prefault_disable))
return 0;
for (i = 0; i < count; i++) {
return ERR_PTR(-EFAULT);
fences = kvmalloc_array(args->num_cliprects, sizeof(*fences),
- __GFP_NOWARN | GFP_TEMPORARY);
+ __GFP_NOWARN | GFP_KERNEL);
if (!fences)
return ERR_PTR(-ENOMEM);
int out_fence_fd = -1;
int err;
+ BUILD_BUG_ON(__EXEC_INTERNAL_FLAGS & ~__I915_EXEC_ILLEGAL_FLAGS);
BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS &
~__EXEC_OBJECT_UNKNOWN_FLAGS);
/* Copy in the exec list from userland */
exec_list = kvmalloc_array(args->buffer_count, sizeof(*exec_list),
- __GFP_NOWARN | GFP_TEMPORARY);
+ __GFP_NOWARN | GFP_KERNEL);
exec2_list = kvmalloc_array(args->buffer_count + 1, sz,
- __GFP_NOWARN | GFP_TEMPORARY);
+ __GFP_NOWARN | GFP_KERNEL);
if (exec_list == NULL || exec2_list == NULL) {
DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
args->buffer_count);
/* Allocate an extra slot for use by the command parser */
exec2_list = kvmalloc_array(args->buffer_count + 1, sz,
- __GFP_NOWARN | GFP_TEMPORARY);
+ __GFP_NOWARN | GFP_KERNEL);
if (exec2_list == NULL) {
DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
args->buffer_count);
return 0;
}
- if (INTEL_GEN(dev_priv) >= 8 && i915.enable_execlists) {
+ if (INTEL_GEN(dev_priv) >= 8 && i915_modparams.enable_execlists) {
if (has_full_48bit_ppgtt)
return 3;
switch (level) {
case I915_CACHE_NONE:
- pte |= PPAT_UNCACHED_INDEX;
+ pte |= PPAT_UNCACHED;
break;
case I915_CACHE_WT:
- pte |= PPAT_DISPLAY_ELLC_INDEX;
+ pte |= PPAT_DISPLAY_ELLC;
break;
default:
- pte |= PPAT_CACHED_INDEX;
+ pte |= PPAT_CACHED;
break;
}
gen8_pde_t pde = _PAGE_PRESENT | _PAGE_RW;
pde |= addr;
if (level != I915_CACHE_NONE)
- pde |= PPAT_CACHED_PDE_INDEX;
+ pde |= PPAT_CACHED_PDE;
else
- pde |= PPAT_UNCACHED_INDEX;
+ pde |= PPAT_UNCACHED;
return pde;
}
unsigned int pde;
gen8_for_each_pde(pt, pd, start, length, pde) {
+ int count = gen8_pte_count(start, length);
+
if (pt == vm->scratch_pt) {
pt = alloc_pt(vm);
if (IS_ERR(pt))
goto unwind;
- gen8_initialize_pt(vm, pt);
+ if (count < GEN8_PTES)
+ gen8_initialize_pt(vm, pt);
gen8_ppgtt_set_pde(vm, pd, pt, pde);
pd->used_pdes++;
GEM_BUG_ON(pd->used_pdes > I915_PDES);
}
- pt->used_ptes += gen8_pte_count(start, length);
+ pt->used_ptes += count;
}
return 0;
/* In the case of execlists, PPGTT is enabled by the context descriptor
* and the PDPs are contained within the context itself. We don't
* need to do anything here. */
- if (i915.enable_execlists)
+ if (i915_modparams.enable_execlists)
return 0;
if (!USES_PPGTT(dev_priv))
*/
GEM_BUG_ON(obj->mm.pages == pages);
} while (i915_gem_shrink(to_i915(obj->base.dev),
- obj->base.size >> PAGE_SHIFT,
+ obj->base.size >> PAGE_SHIFT, NULL,
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND |
I915_SHRINK_ACTIVE));
return 0;
}
-static void cnl_setup_private_ppat(struct drm_i915_private *dev_priv)
+static struct intel_ppat_entry *
+__alloc_ppat_entry(struct intel_ppat *ppat, unsigned int index, u8 value)
+{
+ struct intel_ppat_entry *entry = &ppat->entries[index];
+
+ GEM_BUG_ON(index >= ppat->max_entries);
+ GEM_BUG_ON(test_bit(index, ppat->used));
+
+ entry->ppat = ppat;
+ entry->value = value;
+ kref_init(&entry->ref);
+ set_bit(index, ppat->used);
+ set_bit(index, ppat->dirty);
+
+ return entry;
+}
+
+static void __free_ppat_entry(struct intel_ppat_entry *entry)
+{
+ struct intel_ppat *ppat = entry->ppat;
+ unsigned int index = entry - ppat->entries;
+
+ GEM_BUG_ON(index >= ppat->max_entries);
+ GEM_BUG_ON(!test_bit(index, ppat->used));
+
+ entry->value = ppat->clear_value;
+ clear_bit(index, ppat->used);
+ set_bit(index, ppat->dirty);
+}
+
+/**
+ * intel_ppat_get - get a usable PPAT entry
+ * @i915: i915 device instance
+ * @value: the PPAT value required by the caller
+ *
+ * The function tries to search if there is an existing PPAT entry which
+ * matches with the required value. If perfectly matched, the existing PPAT
+ * entry will be used. If only partially matched, it will try to check if
+ * there is any available PPAT index. If yes, it will allocate a new PPAT
+ * index for the required entry and update the HW. If not, the partially
+ * matched entry will be used.
+ */
+const struct intel_ppat_entry *
+intel_ppat_get(struct drm_i915_private *i915, u8 value)
+{
+ struct intel_ppat *ppat = &i915->ppat;
+ struct intel_ppat_entry *entry;
+ unsigned int scanned, best_score;
+ int i;
+
+ GEM_BUG_ON(!ppat->max_entries);
+
+ scanned = best_score = 0;
+ for_each_set_bit(i, ppat->used, ppat->max_entries) {
+ unsigned int score;
+
+ score = ppat->match(ppat->entries[i].value, value);
+ if (score > best_score) {
+ entry = &ppat->entries[i];
+ if (score == INTEL_PPAT_PERFECT_MATCH) {
+ kref_get(&entry->ref);
+ return entry;
+ }
+ best_score = score;
+ }
+ scanned++;
+ }
+
+ if (scanned == ppat->max_entries) {
+ if (!best_score)
+ return ERR_PTR(-ENOSPC);
+
+ kref_get(&entry->ref);
+ return entry;
+ }
+
+ i = find_first_zero_bit(ppat->used, ppat->max_entries);
+ entry = __alloc_ppat_entry(ppat, i, value);
+ ppat->update_hw(i915);
+ return entry;
+}
+
+static void release_ppat(struct kref *kref)
+{
+ struct intel_ppat_entry *entry =
+ container_of(kref, struct intel_ppat_entry, ref);
+ struct drm_i915_private *i915 = entry->ppat->i915;
+
+ __free_ppat_entry(entry);
+ entry->ppat->update_hw(i915);
+}
+
+/**
+ * intel_ppat_put - put back the PPAT entry got from intel_ppat_get()
+ * @entry: an intel PPAT entry
+ *
+ * Put back the PPAT entry got from intel_ppat_get(). If the PPAT index of the
+ * entry is dynamically allocated, its reference count will be decreased. Once
+ * the reference count becomes into zero, the PPAT index becomes free again.
+ */
+void intel_ppat_put(const struct intel_ppat_entry *entry)
+{
+ struct intel_ppat *ppat = entry->ppat;
+ unsigned int index = entry - ppat->entries;
+
+ GEM_BUG_ON(!ppat->max_entries);
+
+ kref_put(&ppat->entries[index].ref, release_ppat);
+}
+
+static void cnl_private_pat_update_hw(struct drm_i915_private *dev_priv)
+{
+ struct intel_ppat *ppat = &dev_priv->ppat;
+ int i;
+
+ for_each_set_bit(i, ppat->dirty, ppat->max_entries) {
+ I915_WRITE(GEN10_PAT_INDEX(i), ppat->entries[i].value);
+ clear_bit(i, ppat->dirty);
+ }
+}
+
+static void bdw_private_pat_update_hw(struct drm_i915_private *dev_priv)
+{
+ struct intel_ppat *ppat = &dev_priv->ppat;
+ u64 pat = 0;
+ int i;
+
+ for (i = 0; i < ppat->max_entries; i++)
+ pat |= GEN8_PPAT(i, ppat->entries[i].value);
+
+ bitmap_clear(ppat->dirty, 0, ppat->max_entries);
+
+ I915_WRITE(GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
+ I915_WRITE(GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
+}
+
+static unsigned int bdw_private_pat_match(u8 src, u8 dst)
{
+ unsigned int score = 0;
+ enum {
+ AGE_MATCH = BIT(0),
+ TC_MATCH = BIT(1),
+ CA_MATCH = BIT(2),
+ };
+
+ /* Cache attribute has to be matched. */
+ if (GEN8_PPAT_GET_CA(src) != GEN8_PPAT_GET_CA(dst))
+ return 0;
+
+ score |= CA_MATCH;
+
+ if (GEN8_PPAT_GET_TC(src) == GEN8_PPAT_GET_TC(dst))
+ score |= TC_MATCH;
+
+ if (GEN8_PPAT_GET_AGE(src) == GEN8_PPAT_GET_AGE(dst))
+ score |= AGE_MATCH;
+
+ if (score == (AGE_MATCH | TC_MATCH | CA_MATCH))
+ return INTEL_PPAT_PERFECT_MATCH;
+
+ return score;
+}
+
+static unsigned int chv_private_pat_match(u8 src, u8 dst)
+{
+ return (CHV_PPAT_GET_SNOOP(src) == CHV_PPAT_GET_SNOOP(dst)) ?
+ INTEL_PPAT_PERFECT_MATCH : 0;
+}
+
+static void cnl_setup_private_ppat(struct intel_ppat *ppat)
+{
+ ppat->max_entries = 8;
+ ppat->update_hw = cnl_private_pat_update_hw;
+ ppat->match = bdw_private_pat_match;
+ ppat->clear_value = GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3);
+
/* XXX: spec is unclear if this is still needed for CNL+ */
- if (!USES_PPGTT(dev_priv)) {
- I915_WRITE(GEN10_PAT_INDEX(0), GEN8_PPAT_UC);
+ if (!USES_PPGTT(ppat->i915)) {
+ __alloc_ppat_entry(ppat, 0, GEN8_PPAT_UC);
return;
}
- I915_WRITE(GEN10_PAT_INDEX(0), GEN8_PPAT_WB | GEN8_PPAT_LLC);
- I915_WRITE(GEN10_PAT_INDEX(1), GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
- I915_WRITE(GEN10_PAT_INDEX(2), GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
- I915_WRITE(GEN10_PAT_INDEX(3), GEN8_PPAT_UC);
- I915_WRITE(GEN10_PAT_INDEX(4), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
- I915_WRITE(GEN10_PAT_INDEX(5), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
- I915_WRITE(GEN10_PAT_INDEX(6), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
- I915_WRITE(GEN10_PAT_INDEX(7), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+ __alloc_ppat_entry(ppat, 0, GEN8_PPAT_WB | GEN8_PPAT_LLC);
+ __alloc_ppat_entry(ppat, 1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
+ __alloc_ppat_entry(ppat, 2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
+ __alloc_ppat_entry(ppat, 3, GEN8_PPAT_UC);
+ __alloc_ppat_entry(ppat, 4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
+ __alloc_ppat_entry(ppat, 5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
+ __alloc_ppat_entry(ppat, 6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
+ __alloc_ppat_entry(ppat, 7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
}
/* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
* bits. When using advanced contexts each context stores its own PAT, but
* writing this data shouldn't be harmful even in those cases. */
-static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
+static void bdw_setup_private_ppat(struct intel_ppat *ppat)
{
- u64 pat;
+ ppat->max_entries = 8;
+ ppat->update_hw = bdw_private_pat_update_hw;
+ ppat->match = bdw_private_pat_match;
+ ppat->clear_value = GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3);
- pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC) | /* for normal objects, no eLLC */
- GEN8_PPAT(1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC) | /* for something pointing to ptes? */
- GEN8_PPAT(2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC) | /* for scanout with eLLC */
- GEN8_PPAT(3, GEN8_PPAT_UC) | /* Uncached objects, mostly for scanout */
- GEN8_PPAT(4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)) |
- GEN8_PPAT(5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)) |
- GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
- GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
-
- if (!USES_PPGTT(dev_priv))
+ if (!USES_PPGTT(ppat->i915)) {
/* Spec: "For GGTT, there is NO pat_sel[2:0] from the entry,
* so RTL will always use the value corresponding to
* pat_sel = 000".
* So we can still hold onto all our assumptions wrt cpu
* clflushing on LLC machines.
*/
- pat = GEN8_PPAT(0, GEN8_PPAT_UC);
+ __alloc_ppat_entry(ppat, 0, GEN8_PPAT_UC);
+ return;
+ }
- /* XXX: spec defines this as 2 distinct registers. It's unclear if a 64b
- * write would work. */
- I915_WRITE(GEN8_PRIVATE_PAT_LO, pat);
- I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32);
+ __alloc_ppat_entry(ppat, 0, GEN8_PPAT_WB | GEN8_PPAT_LLC); /* for normal objects, no eLLC */
+ __alloc_ppat_entry(ppat, 1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC); /* for something pointing to ptes? */
+ __alloc_ppat_entry(ppat, 2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC); /* for scanout with eLLC */
+ __alloc_ppat_entry(ppat, 3, GEN8_PPAT_UC); /* Uncached objects, mostly for scanout */
+ __alloc_ppat_entry(ppat, 4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
+ __alloc_ppat_entry(ppat, 5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
+ __alloc_ppat_entry(ppat, 6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
+ __alloc_ppat_entry(ppat, 7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
}
-static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
+static void chv_setup_private_ppat(struct intel_ppat *ppat)
{
- u64 pat;
+ ppat->max_entries = 8;
+ ppat->update_hw = bdw_private_pat_update_hw;
+ ppat->match = chv_private_pat_match;
+ ppat->clear_value = CHV_PPAT_SNOOP;
/*
* Map WB on BDW to snooped on CHV.
* Which means we must set the snoop bit in PAT entry 0
* in order to keep the global status page working.
*/
- pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) |
- GEN8_PPAT(1, 0) |
- GEN8_PPAT(2, 0) |
- GEN8_PPAT(3, 0) |
- GEN8_PPAT(4, CHV_PPAT_SNOOP) |
- GEN8_PPAT(5, CHV_PPAT_SNOOP) |
- GEN8_PPAT(6, CHV_PPAT_SNOOP) |
- GEN8_PPAT(7, CHV_PPAT_SNOOP);
- I915_WRITE(GEN8_PRIVATE_PAT_LO, pat);
- I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32);
+ __alloc_ppat_entry(ppat, 0, CHV_PPAT_SNOOP);
+ __alloc_ppat_entry(ppat, 1, 0);
+ __alloc_ppat_entry(ppat, 2, 0);
+ __alloc_ppat_entry(ppat, 3, 0);
+ __alloc_ppat_entry(ppat, 4, CHV_PPAT_SNOOP);
+ __alloc_ppat_entry(ppat, 5, CHV_PPAT_SNOOP);
+ __alloc_ppat_entry(ppat, 6, CHV_PPAT_SNOOP);
+ __alloc_ppat_entry(ppat, 7, CHV_PPAT_SNOOP);
}
static void gen6_gmch_remove(struct i915_address_space *vm)
cleanup_scratch_page(vm);
}
+static void setup_private_pat(struct drm_i915_private *dev_priv)
+{
+ struct intel_ppat *ppat = &dev_priv->ppat;
+ int i;
+
+ ppat->i915 = dev_priv;
+
+ if (INTEL_GEN(dev_priv) >= 10)
+ cnl_setup_private_ppat(ppat);
+ else if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
+ chv_setup_private_ppat(ppat);
+ else
+ bdw_setup_private_ppat(ppat);
+
+ GEM_BUG_ON(ppat->max_entries > INTEL_MAX_PPAT_ENTRIES);
+
+ for_each_clear_bit(i, ppat->used, ppat->max_entries) {
+ ppat->entries[i].value = ppat->clear_value;
+ ppat->entries[i].ppat = ppat;
+ set_bit(i, ppat->dirty);
+ }
+
+ ppat->update_hw(dev_priv);
+}
+
static int gen8_gmch_probe(struct i915_ggtt *ggtt)
{
struct drm_i915_private *dev_priv = ggtt->base.i915;
}
ggtt->base.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
-
- if (INTEL_GEN(dev_priv) >= 10)
- cnl_setup_private_ppat(dev_priv);
- else if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
- chv_setup_private_ppat(dev_priv);
- else
- bdw_setup_private_ppat(dev_priv);
-
ggtt->base.cleanup = gen6_gmch_remove;
ggtt->base.bind_vma = ggtt_bind_vma;
ggtt->base.unbind_vma = ggtt_unbind_vma;
ggtt->invalidate = gen6_ggtt_invalidate;
+ setup_private_pat(dev_priv);
+
return ggtt_probe_common(ggtt, size);
}
* currently don't have any bits spare to pass in this upper
* restriction!
*/
- if (HAS_GUC(dev_priv) && i915.enable_guc_loading) {
+ if (HAS_GUC(dev_priv) && i915_modparams.enable_guc_loading) {
ggtt->base.total = min_t(u64, ggtt->base.total, GUC_GGTT_TOP);
ggtt->mappable_end = min(ggtt->mappable_end, ggtt->base.total);
}
ggtt->base.closed = false;
if (INTEL_GEN(dev_priv) >= 8) {
- if (INTEL_GEN(dev_priv) >= 10)
- cnl_setup_private_ppat(dev_priv);
- else if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
- chv_setup_private_ppat(dev_priv);
- else
- bdw_setup_private_ppat(dev_priv);
+ struct intel_ppat *ppat = &dev_priv->ppat;
+ bitmap_set(ppat->dirty, 0, ppat->max_entries);
+ dev_priv->ppat.update_hw(dev_priv);
return;
}
/* Allocate a temporary list of source pages for random access. */
page_addr_list = kvmalloc_array(n_pages,
sizeof(dma_addr_t),
- GFP_TEMPORARY);
+ GFP_KERNEL);
if (!page_addr_list)
return ERR_PTR(ret);
spinlock_t lock;
struct hlist_node node;
struct mmu_notifier mn;
- struct rb_root objects;
+ struct rb_root_cached objects;
struct workqueue_struct *wq;
};
struct interval_tree_node *it;
LIST_HEAD(cancelled);
- if (RB_EMPTY_ROOT(&mn->objects))
+ if (RB_EMPTY_ROOT(&mn->objects.rb_root))
return;
/* interval ranges are inclusive, but invalidate range is exclusive */
spin_lock_init(&mn->lock);
mn->mn.ops = &i915_gem_userptr_notifier;
- mn->objects = RB_ROOT;
+ mn->objects = RB_ROOT_CACHED;
mn->wq = alloc_workqueue("i915-userptr-release", WQ_UNBOUND, 0);
if (mn->wq == NULL) {
kfree(mn);
struct task_struct *task;
};
-#if IS_ENABLED(CONFIG_SWIOTLB)
-#define swiotlb_active() swiotlb_nr_tbl()
-#else
-#define swiotlb_active() 0
-#endif
-
-static int
-st_set_pages(struct sg_table **st, struct page **pvec, int num_pages)
-{
- struct scatterlist *sg;
- int ret, n;
-
- *st = kmalloc(sizeof(**st), GFP_KERNEL);
- if (*st == NULL)
- return -ENOMEM;
-
- if (swiotlb_active()) {
- ret = sg_alloc_table(*st, num_pages, GFP_KERNEL);
- if (ret)
- goto err;
-
- for_each_sg((*st)->sgl, sg, num_pages, n)
- sg_set_page(sg, pvec[n], PAGE_SIZE, 0);
- } else {
- ret = sg_alloc_table_from_pages(*st, pvec, num_pages,
- 0, num_pages << PAGE_SHIFT,
- GFP_KERNEL);
- if (ret)
- goto err;
- }
-
- return 0;
-
-err:
- kfree(*st);
- *st = NULL;
- return ret;
-}
-
static struct sg_table *
-__i915_gem_userptr_set_pages(struct drm_i915_gem_object *obj,
- struct page **pvec, int num_pages)
+__i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
+ struct page **pvec, int num_pages)
{
- struct sg_table *pages;
+ unsigned int max_segment = i915_sg_segment_size();
+ struct sg_table *st;
int ret;
- ret = st_set_pages(&pages, pvec, num_pages);
- if (ret)
+ st = kmalloc(sizeof(*st), GFP_KERNEL);
+ if (!st)
+ return ERR_PTR(-ENOMEM);
+
+alloc_table:
+ ret = __sg_alloc_table_from_pages(st, pvec, num_pages,
+ 0, num_pages << PAGE_SHIFT,
+ max_segment,
+ GFP_KERNEL);
+ if (ret) {
+ kfree(st);
return ERR_PTR(ret);
+ }
- ret = i915_gem_gtt_prepare_pages(obj, pages);
+ ret = i915_gem_gtt_prepare_pages(obj, st);
if (ret) {
- sg_free_table(pages);
- kfree(pages);
+ sg_free_table(st);
+
+ if (max_segment > PAGE_SIZE) {
+ max_segment = PAGE_SIZE;
+ goto alloc_table;
+ }
+
+ kfree(st);
return ERR_PTR(ret);
}
- return pages;
+ return st;
}
static int
ret = -ENOMEM;
pinned = 0;
- pvec = kvmalloc_array(npages, sizeof(struct page *), GFP_TEMPORARY);
+ pvec = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
if (pvec != NULL) {
struct mm_struct *mm = obj->userptr.mm->mm;
unsigned int flags = 0;
struct sg_table *pages = ERR_PTR(ret);
if (pinned == npages) {
- pages = __i915_gem_userptr_set_pages(obj, pvec, npages);
+ pages = __i915_gem_userptr_alloc_pages(obj, pvec,
+ npages);
if (!IS_ERR(pages)) {
__i915_gem_object_set_pages(obj, pages);
pinned = 0;
if (mm == current->mm) {
pvec = kvmalloc_array(num_pages, sizeof(struct page *),
- GFP_TEMPORARY |
+ GFP_KERNEL |
__GFP_NORETRY |
__GFP_NOWARN);
if (pvec) /* defer to worker if malloc fails */
pages = __i915_gem_userptr_get_pages_schedule(obj);
active = pages == ERR_PTR(-EAGAIN);
} else {
- pages = __i915_gem_userptr_set_pages(obj, pvec, num_pages);
+ pages = __i915_gem_userptr_alloc_pages(obj, pvec, num_pages);
active = !IS_ERR(pages);
}
if (active)
hash_init(dev_priv->mm_structs);
dev_priv->mm.userptr_wq =
- alloc_workqueue("i915-userptr-acquire", WQ_HIGHPRI, 0);
+ alloc_workqueue("i915-userptr-acquire",
+ WQ_HIGHPRI | WQ_MEM_RECLAIM,
+ 0);
if (!dev_priv->mm.userptr_wq)
return -ENOMEM;
static void error_print_engine(struct drm_i915_error_state_buf *m,
const struct drm_i915_error_engine *ee)
{
+ int n;
+
err_printf(m, "%s command stream:\n", engine_str(ee->engine_id));
err_printf(m, " START: 0x%08x\n", ee->start);
err_printf(m, " HEAD: 0x%08x [0x%08x]\n", ee->head, ee->rq_head);
jiffies_to_msecs(jiffies - ee->hangcheck_timestamp));
err_printf(m, " engine reset count: %u\n", ee->reset_count);
- error_print_request(m, " ELSP[0]: ", &ee->execlist[0]);
- error_print_request(m, " ELSP[1]: ", &ee->execlist[1]);
+ for (n = 0; n < ee->num_ports; n++) {
+ err_printf(m, " ELSP[%d]:", n);
+ error_print_request(m, " ", &ee->execlist[n]);
+ }
+
error_print_context(m, " Active context: ", &ee->context);
}
static void err_print_params(struct drm_i915_error_state_buf *m,
const struct i915_params *p)
{
-#define PRINT(T, x) err_print_param(m, #x, #T, &p->x);
+#define PRINT(T, x, ...) err_print_param(m, #x, #T, &p->x);
I915_PARAMS_FOR_EACH(PRINT);
#undef PRINT
}
*/
ebuf->size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE;
ebuf->buf = kmalloc(ebuf->size,
- GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN);
+ GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
if (ebuf->buf == NULL) {
ebuf->size = PAGE_SIZE;
- ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY);
+ ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL);
}
if (ebuf->buf == NULL) {
ebuf->size = 128;
- ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY);
+ ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL);
}
if (ebuf->buf == NULL)
kfree(error->overlay);
kfree(error->display);
-#define FREE(T, x) free_param(#T, &error->params.x);
+#define FREE(T, x, ...) free_param(#T, &error->params.x);
I915_PARAMS_FOR_EACH(FREE);
#undef FREE
static void error_record_engine_execlists(struct intel_engine_cs *engine,
struct drm_i915_error_engine *ee)
{
- const struct execlist_port *port = engine->execlist_port;
+ const struct intel_engine_execlists * const execlists = &engine->execlists;
unsigned int n;
- for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) {
- struct drm_i915_gem_request *rq = port_request(&port[n]);
+ for (n = 0; n < execlists_num_ports(execlists); n++) {
+ struct drm_i915_gem_request *rq = port_request(&execlists->port[n]);
if (!rq)
break;
record_request(rq, &ee->execlist[n]);
}
+
+ ee->num_ports = n;
}
static void record_context(struct drm_i915_error_context *e,
struct i915_gpu_state *error)
{
/* Capturing log buf contents won't be useful if logging was disabled */
- if (!dev_priv->guc.log.vma || (i915.guc_log_level < 0))
+ if (!dev_priv->guc.log.vma || (i915_modparams.guc_log_level < 0))
return;
error->guc_log = i915_error_object_create(dev_priv,
ktime_to_timeval(ktime_sub(ktime_get(),
error->i915->gt.last_init_time));
- error->params = i915;
-#define DUP(T, x) dup_param(#T, &error->params.x);
+ error->params = i915_modparams;
+#define DUP(T, x, ...) dup_param(#T, &error->params.x);
I915_PARAMS_FOR_EACH(DUP);
#undef DUP
struct i915_gpu_state *error;
unsigned long flags;
- if (!i915.error_capture)
+ if (!i915_modparams.error_capture)
return;
if (READ_ONCE(dev_priv->gpu_error.first_error))
/* reset doesn't touch the display */
- if (!i915.force_reset_modeset_test &&
+ if (!i915_modparams.force_reset_modeset_test &&
!gpu_reset_clobbers_display(dev_priv))
return;
int ret;
/* reset doesn't touch the display */
- if (!i915.force_reset_modeset_test &&
+ if (!i915_modparams.force_reset_modeset_test &&
!gpu_reset_clobbers_display(dev_priv))
return;
assert_plane_enabled(dev_priv, crtc->plane);
if (IS_BROADWELL(dev_priv)) {
mutex_lock(&dev_priv->rps.hw_lock);
- WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0xc0000000));
+ WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL,
+ IPS_ENABLE | IPS_PCODE_CONTROL));
mutex_unlock(&dev_priv->rps.hw_lock);
/* Quoting Art Runyan: "its not safe to expect any particular
* value in IPS_CTL bit 31 after enabling IPS through the
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = to_i915(dev);
- pipe_config->ips_enabled = i915.enable_ips &&
+ pipe_config->ips_enabled = i915_modparams.enable_ips &&
hsw_crtc_supports_ips(crtc) &&
pipe_config_supports_ips(dev_priv, pipe_config);
}
static inline bool intel_panel_use_ssc(struct drm_i915_private *dev_priv)
{
- if (i915.panel_use_ssc >= 0)
- return i915.panel_use_ssc != 0;
+ if (i915_modparams.panel_use_ssc >= 0)
+ return i915_modparams.panel_use_ssc != 0;
return dev_priv->vbt.lvds_use_ssc
&& !(dev_priv->quirks & QUIRK_LVDS_SSC_DISABLE);
}
pipe_config->gamma_mode =
I915_READ(GAMMA_MODE(crtc->pipe)) & GAMMA_MODE_MODE_MASK;
- if (IS_BROADWELL(dev_priv) || dev_priv->info.gen >= 9) {
+ if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9) {
u32 tmp = I915_READ(PIPEMISC(crtc->pipe));
bool clrspace_yuv = tmp & PIPEMISC_OUTPUT_COLORSPACE_YUV;
- if (IS_GEMINILAKE(dev_priv) || dev_priv->info.gen >= 10) {
+ if (IS_GEMINILAKE(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
bool blend_mode_420 = tmp &
PIPEMISC_YUV420_MODE_FULL_BLEND;
if (!m_n->link_n)
return 0;
- return div_u64((u64)m_n->link_m * link_freq, m_n->link_n);
+ return div_u64(mul_u32_u32(m_n->link_m, link_freq), m_n->link_n);
}
static void ironlake_pch_clock_get(struct intel_crtc *crtc,
return ret;
}
- if (i915.fastboot &&
+ if (i915_modparams.fastboot &&
intel_pipe_config_compare(dev_priv,
to_intel_crtc_state(old_crtc_state),
pipe_config, true)) {
return dev->driver->get_vblank_counter(dev, crtc->pipe);
}
- static void intel_atomic_wait_for_vblanks(struct drm_device *dev,
- struct drm_i915_private *dev_priv,
- unsigned crtc_mask)
- {
- unsigned last_vblank_count[I915_MAX_PIPES];
- enum pipe pipe;
- int ret;
-
- if (!crtc_mask)
- return;
-
- for_each_pipe(dev_priv, pipe) {
- struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv,
- pipe);
-
- if (!((1 << pipe) & crtc_mask))
- continue;
-
- ret = drm_crtc_vblank_get(&crtc->base);
- if (WARN_ON(ret != 0)) {
- crtc_mask &= ~(1 << pipe);
- continue;
- }
-
- last_vblank_count[pipe] = drm_crtc_vblank_count(&crtc->base);
- }
-
- for_each_pipe(dev_priv, pipe) {
- struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv,
- pipe);
- long lret;
-
- if (!((1 << pipe) & crtc_mask))
- continue;
-
- lret = wait_event_timeout(dev->vblank[pipe].queue,
- last_vblank_count[pipe] !=
- drm_crtc_vblank_count(&crtc->base),
- msecs_to_jiffies(50));
-
- WARN(!lret, "pipe %c vblank wait timed out\n", pipe_name(pipe));
-
- drm_crtc_vblank_put(&crtc->base);
- }
- }
-
- static bool needs_vblank_wait(struct intel_crtc_state *crtc_state)
- {
- /* fb updated, need to unpin old fb */
- if (crtc_state->fb_changed)
- return true;
-
- /* wm changes, need vblank before final wm's */
- if (crtc_state->update_wm_post)
- return true;
-
- if (crtc_state->wm.need_postvbl_update)
- return true;
-
- return false;
- }
-
static void intel_update_crtc(struct drm_crtc *crtc,
struct drm_atomic_state *state,
struct drm_crtc_state *old_crtc_state,
- struct drm_crtc_state *new_crtc_state,
- unsigned int *crtc_vblank_mask)
+ struct drm_crtc_state *new_crtc_state)
{
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = to_i915(dev);
}
drm_atomic_helper_commit_planes_on_crtc(old_crtc_state);
-
- if (needs_vblank_wait(pipe_config))
- *crtc_vblank_mask |= drm_crtc_mask(crtc);
}
- static void intel_update_crtcs(struct drm_atomic_state *state,
- unsigned int *crtc_vblank_mask)
+ static void intel_update_crtcs(struct drm_atomic_state *state)
{
struct drm_crtc *crtc;
struct drm_crtc_state *old_crtc_state, *new_crtc_state;
continue;
intel_update_crtc(crtc, state, old_crtc_state,
- new_crtc_state, crtc_vblank_mask);
+ new_crtc_state);
}
}
- static void skl_update_crtcs(struct drm_atomic_state *state,
- unsigned int *crtc_vblank_mask)
+ static void skl_update_crtcs(struct drm_atomic_state *state)
{
struct drm_i915_private *dev_priv = to_i915(state->dev);
struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
vbl_wait = true;
intel_update_crtc(crtc, state, old_crtc_state,
- new_crtc_state, crtc_vblank_mask);
+ new_crtc_state);
if (vbl_wait)
intel_wait_for_vblank(dev_priv, pipe);
struct drm_crtc_state *old_crtc_state, *new_crtc_state;
struct drm_crtc *crtc;
struct intel_crtc_state *intel_cstate;
- bool hw_check = intel_state->modeset;
u64 put_domains[I915_MAX_PIPES] = {};
- unsigned crtc_vblank_mask = 0;
int i;
intel_atomic_commit_fence_wait(intel_state);
if (needs_modeset(new_crtc_state) ||
to_intel_crtc_state(new_crtc_state)->update_pipe) {
- hw_check = true;
put_domains[to_intel_crtc(crtc)->pipe] =
modeset_get_crtc_power_domains(crtc,
}
/* Now enable the clocks, plane, pipe, and connectors that we set up. */
- dev_priv->display.update_crtcs(state, &crtc_vblank_mask);
+ dev_priv->display.update_crtcs(state);
/* FIXME: We should call drm_atomic_helper_commit_hw_done() here
* already, but still need the state for the delayed optimization. To
* - switch over to the vblank wait helper in the core after that since
* we don't need out special handling any more.
*/
- if (!state->legacy_cursor_update)
- intel_atomic_wait_for_vblanks(dev, dev_priv, crtc_vblank_mask);
+ drm_atomic_helper_wait_for_flip_done(dev, state);
/*
* Now that the vblank has passed, we can go ahead and program the
goto slow;
old_plane_state = plane->state;
+ /*
+ * Don't do an async update if there is an outstanding commit modifying
+ * the plane. This prevents our async update's changes from getting
+ * overridden by a previous synchronous update's state.
+ */
+ if (old_plane_state->commit &&
+ !try_wait_for_completion(&old_plane_state->commit->hw_done))
+ goto slow;
/*
* If any parameters change that may affect watermarks,
}
old_fb = old_plane_state->fb;
- old_vma = to_intel_plane_state(old_plane_state)->vma;
i915_gem_track_fb(intel_fb_obj(old_fb), intel_fb_obj(fb),
intel_plane->frontbuffer_bit);
/* Swap plane state */
- new_plane_state->fence = old_plane_state->fence;
- *to_intel_plane_state(old_plane_state) = *to_intel_plane_state(new_plane_state);
- new_plane_state->fence = NULL;
- new_plane_state->fb = old_fb;
- to_intel_plane_state(new_plane_state)->vma = NULL;
+ plane->state = new_plane_state;
if (plane->state->visible) {
trace_intel_update_plane(plane, to_intel_crtc(crtc));
intel_plane->disable_plane(intel_plane, to_intel_crtc(crtc));
}
+ old_vma = fetch_and_zero(&to_intel_plane_state(old_plane_state)->vma);
if (old_vma)
intel_unpin_fb_vma(old_vma);
out_unlock:
mutex_unlock(&dev_priv->drm.struct_mutex);
out_free:
- intel_plane_destroy_state(plane, new_plane_state);
+ if (ret)
+ intel_plane_destroy_state(plane, new_plane_state);
+ else
+ intel_plane_destroy_state(plane, old_plane_state);
return ret;
slow:
dev_priv->display.fdi_link_train = hsw_fdi_link_train;
}
- if (dev_priv->info.gen >= 9)
+ if (INTEL_GEN(dev_priv) >= 9)
dev_priv->display.update_crtcs = skl_update_crtcs;
else
dev_priv->display.update_crtcs = intel_update_crtcs;
if (!ret)
ret = __intel_display_resume(dev, state, &ctx);
+ intel_enable_ipc(dev_priv);
drm_modeset_drop_locks(&ctx);
drm_modeset_acquire_fini(&ctx);
return x;
}
-static inline u32 i915_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
-{
- return upper_32_bits((u64)prandom_u32_state(state) * ep_ro);
-}
-
void i915_random_reorder(unsigned int *order, unsigned int count,
struct rnd_state *state)
{
{
unsigned int *order, i;
- order = kmalloc_array(count, sizeof(*order), GFP_TEMPORARY);
+ order = kmalloc_array(count, sizeof(*order), GFP_KERNEL);
if (!order)
return order;
return vb2_dc_mmap(dbuf->priv, vma);
}
- static struct dma_buf_ops vb2_dc_dmabuf_ops = {
+ static const struct dma_buf_ops vb2_dc_dmabuf_ops = {
.attach = vb2_dc_dmabuf_ops_attach,
.detach = vb2_dc_dmabuf_ops_detach,
.map_dma_buf = vb2_dc_dmabuf_ops_map,
{
struct vb2_dc_buf *buf;
struct frame_vector *vec;
- unsigned long offset;
+ unsigned int offset;
int n_pages, i;
int ret = 0;
struct sg_table *sgt;
buf->dev = dev;
buf->dma_dir = dma_dir;
- offset = vaddr & ~PAGE_MASK;
+ offset = lower_32_bits(offset_in_page(vaddr));
- vec = vb2_create_framevec(vaddr, size, dma_dir == DMA_FROM_DEVICE);
+ vec = vb2_create_framevec(vaddr, size, dma_dir == DMA_FROM_DEVICE ||
+ dma_dir == DMA_BIDIRECTIONAL);
if (IS_ERR(vec)) {
ret = PTR_ERR(vec);
goto fail_buf;
projects / linux-2.6-block.git / commitdiff