!Idrivers/gpu/drm/i915/i915_gem_shrinker.c
</sect2>
</sect1>
+ <sect1>
+ <title>GuC-based Command Submission</title>
+ <sect2>
+ <title>GuC</title>
+!Pdrivers/gpu/drm/i915/intel_guc_loader.c GuC-specific firmware loader
+!Idrivers/gpu/drm/i915/intel_guc_loader.c
+ </sect2>
+ <sect2>
+ <title>GuC Client</title>
+!Pdrivers/gpu/drm/i915/i915_guc_submission.c GuC-based command submissison
+!Idrivers/gpu/drm/i915/i915_guc_submission.c
+ </sect2>
+ </sect1>
+
<sect1>
<title> Tracing </title>
<para>
extern int amdgpu_deep_color;
extern int amdgpu_vm_size;
extern int amdgpu_vm_block_size;
+extern int amdgpu_vm_fault_stop;
+extern int amdgpu_vm_debug;
extern int amdgpu_enable_scheduler;
extern int amdgpu_sched_jobs;
extern int amdgpu_sched_hw_submission;
#define AMDGPU_PTE_FRAG_64KB (4 << 7)
#define AMDGPU_LOG2_PAGES_PER_FRAG 4
+/* How to programm VM fault handling */
+#define AMDGPU_VM_FAULT_STOP_NEVER 0
+#define AMDGPU_VM_FAULT_STOP_FIRST 1
+#define AMDGPU_VM_FAULT_STOP_ALWAYS 2
+
struct amdgpu_vm_pt {
struct amdgpu_bo *bo;
uint64_t addr;
/*
* SDMA
*/
-struct amdgpu_sdma {
+struct amdgpu_sdma_instance {
/* SDMA firmware */
const struct firmware *fw;
uint32_t fw_version;
bool burst_nop;
};
+struct amdgpu_sdma {
+ struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES];
+ struct amdgpu_irq_src trap_irq;
+ struct amdgpu_irq_src illegal_inst_irq;
+ int num_instances;
+};
+
/*
* Firmware
*/
struct amdgpu_gfx gfx;
/* sdma */
- struct amdgpu_sdma sdma[AMDGPU_MAX_SDMA_INSTANCES];
- struct amdgpu_irq_src sdma_trap_irq;
- struct amdgpu_irq_src sdma_illegal_inst_irq;
+ struct amdgpu_sdma sdma;
/* uvd */
bool has_uvd;
ring->ring_free_dw--;
}
-static inline struct amdgpu_sdma * amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
+static inline struct amdgpu_sdma_instance *
+amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
int i;
- for (i = 0; i < AMDGPU_MAX_SDMA_INSTANCES; i++)
- if (&adev->sdma[i].ring == ring)
+ for (i = 0; i < adev->sdma.num_instances; i++)
+ if (&adev->sdma.instance[i].ring == ring)
break;
if (i < AMDGPU_MAX_SDMA_INSTANCES)
- return &adev->sdma[i];
+ return &adev->sdma.instance[i];
else
return NULL;
}
#include <linux/acpi.h>
#include <linux/slab.h>
#include <linux/power_supply.h>
-#include <linux/vga_switcheroo.h>
#include <acpi/video.h>
#include <drm/drmP.h>
#include <drm/drm_crtc_helper.h>
case KGD_ENGINE_SDMA1:
hdr = (const union amdgpu_firmware_header *)
- adev->sdma[0].fw->data;
+ adev->sdma.instance[0].fw->data;
break;
case KGD_ENGINE_SDMA2:
hdr = (const union amdgpu_firmware_header *)
- adev->sdma[1].fw->data;
+ adev->sdma.instance[1].fw->data;
break;
default:
case KGD_ENGINE_SDMA1:
hdr = (const union amdgpu_firmware_header *)
- adev->sdma[0].fw->data;
+ adev->sdma.instance[0].fw->data;
break;
case KGD_ENGINE_SDMA2:
hdr = (const union amdgpu_firmware_header *)
- adev->sdma[1].fw->data;
+ adev->sdma.instance[1].fw->data;
break;
default:
if (has_atpx && vga_count == 2) {
acpi_get_name(amdgpu_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer);
- printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
+ printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n",
acpi_method_name);
amdgpu_atpx_priv.atpx_detected = true;
return true;
#include "amdgpu.h"
#include "atom.h"
-#include <linux/vga_switcheroo.h>
#include <linux/slab.h>
#include <linux/acpi.h>
/*
}
break;
case AMDGPU_HW_IP_DMA:
- if (ring < 2) {
- *out_ring = &adev->sdma[ring].ring;
+ if (ring < adev->sdma.num_instances) {
+ *out_ring = &adev->sdma.instance[ring].ring;
} else {
- DRM_ERROR("only two SDMA rings are supported\n");
+ DRM_ERROR("only %d SDMA rings are supported\n",
+ adev->sdma.num_instances);
return -EINVAL;
}
break;
if (r)
return r;
}
+
+ }
+
+ r = amdgpu_vm_clear_invalids(adev, vm, &p->ibs[0].sync);
+
+ if (amdgpu_vm_debug && p->bo_list) {
+ /* Invalidate all BOs to test for userspace bugs */
+ for (i = 0; i < p->bo_list->num_entries; i++) {
+ /* ignore duplicates */
+ bo = p->bo_list->array[i].robj;
+ if (!bo)
+ continue;
+
+ amdgpu_vm_bo_invalidate(adev, bo);
+ }
}
- return amdgpu_vm_clear_invalids(adev, vm, &p->ibs[0].sync);
+ return r;
}
static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
* amdgpu_switcheroo_set_state - set switcheroo state
*
* @pdev: pci dev pointer
- * @state: vga switcheroo state
+ * @state: vga_switcheroo state
*
* Callback for the switcheroo driver. Suspends or resumes the
* the asics before or after it is powered up using ACPI methods.
}
drm_modeset_unlock_all(dev);
- /* unpin the front buffers */
+ /* unpin the front buffers and cursors */
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+ struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
struct amdgpu_framebuffer *rfb = to_amdgpu_framebuffer(crtc->primary->fb);
struct amdgpu_bo *robj;
+ if (amdgpu_crtc->cursor_bo) {
+ struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+ r = amdgpu_bo_reserve(aobj, false);
+ if (r == 0) {
+ amdgpu_bo_unpin(aobj);
+ amdgpu_bo_unreserve(aobj);
+ }
+ }
+
if (rfb == NULL || rfb->obj == NULL) {
continue;
}
{
struct drm_connector *connector;
struct amdgpu_device *adev = dev->dev_private;
+ struct drm_crtc *crtc;
int r;
if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
if (r)
return r;
+ /* pin cursors */
+ list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+ struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+
+ if (amdgpu_crtc->cursor_bo) {
+ struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+ r = amdgpu_bo_reserve(aobj, false);
+ if (r == 0) {
+ r = amdgpu_bo_pin(aobj,
+ AMDGPU_GEM_DOMAIN_VRAM,
+ &amdgpu_crtc->cursor_addr);
+ if (r != 0)
+ DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
+ amdgpu_bo_unreserve(aobj);
+ }
+ }
+ }
+
/* blat the mode back in */
if (fbcon) {
drm_helper_resume_force_mode(dev);
int amdgpu_deep_color = 0;
int amdgpu_vm_size = 8;
int amdgpu_vm_block_size = -1;
+int amdgpu_vm_fault_stop = 0;
+int amdgpu_vm_debug = 0;
int amdgpu_exp_hw_support = 0;
-int amdgpu_enable_scheduler = 0;
+int amdgpu_enable_scheduler = 1;
int amdgpu_sched_jobs = 16;
int amdgpu_sched_hw_submission = 2;
-int amdgpu_enable_semaphores = 1;
+int amdgpu_enable_semaphores = 0;
MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
MODULE_PARM_DESC(vm_block_size, "VM page table size in bits (default depending on vm_size)");
module_param_named(vm_block_size, amdgpu_vm_block_size, int, 0444);
+MODULE_PARM_DESC(vm_fault_stop, "Stop on VM fault (0 = never (default), 1 = print first, 2 = always)");
+module_param_named(vm_fault_stop, amdgpu_vm_fault_stop, int, 0444);
+
+MODULE_PARM_DESC(vm_debug, "Debug VM handling (0 = disabled (default), 1 = enabled)");
+module_param_named(vm_debug, amdgpu_vm_debug, int, 0644);
+
MODULE_PARM_DESC(exp_hw_support, "experimental hw support (1 = enable, 0 = disable (default))");
module_param_named(exp_hw_support, amdgpu_exp_hw_support, int, 0444);
-MODULE_PARM_DESC(enable_scheduler, "enable SW GPU scheduler (1 = enable, 0 = disable ((default))");
+MODULE_PARM_DESC(enable_scheduler, "enable SW GPU scheduler (1 = enable (default), 0 = disable)");
module_param_named(enable_scheduler, amdgpu_enable_scheduler, int, 0444);
MODULE_PARM_DESC(sched_jobs, "the max number of jobs supported in the sw queue (default 16)");
MODULE_PARM_DESC(sched_hw_submission, "the max number of HW submissions (default 2)");
module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444);
-MODULE_PARM_DESC(enable_semaphores, "Enable semaphores (1 = enable (default), 0 = disable)");
+MODULE_PARM_DESC(enable_semaphores, "Enable semaphores (1 = enable, 0 = disable (default))");
module_param_named(enable_semaphores, amdgpu_enable_semaphores, int, 0644);
static struct pci_device_id pciidlist[] = {
init_waitqueue_head(&ring->fence_drv.fence_queue);
if (amdgpu_enable_scheduler) {
+ long timeout = msecs_to_jiffies(amdgpu_lockup_timeout);
+ if (timeout == 0) {
+ /*
+ * FIXME:
+ * Delayed workqueue cannot use it directly,
+ * so the scheduler will not use delayed workqueue if
+ * MAX_SCHEDULE_TIMEOUT is set.
+ * Currently keep it simple and silly.
+ */
+ timeout = MAX_SCHEDULE_TIMEOUT;
+ }
r = amd_sched_init(&ring->sched, &amdgpu_sched_ops,
- amdgpu_sched_hw_submission, ring->name);
+ amdgpu_sched_hw_submission,
+ timeout, ring->name);
if (r) {
DRM_ERROR("Failed to create scheduler on ring %s.\n",
ring->name);
break;
case AMDGPU_HW_IP_DMA:
type = AMD_IP_BLOCK_TYPE_SDMA;
- ring_mask = adev->sdma[0].ring.ready ? 1 : 0;
- ring_mask |= ((adev->sdma[1].ring.ready ? 1 : 0) << 1);
+ for (i = 0; i < adev->sdma.num_instances; i++)
+ ring_mask |= ((adev->sdma.instance[i].ring.ready ? 1 : 0) << i);
ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
ib_size_alignment = 1;
break;
fw_info.feature = 0;
break;
case AMDGPU_INFO_FW_SDMA:
- if (info->query_fw.index >= 2)
+ if (info->query_fw.index >= adev->sdma.num_instances)
return -EINVAL;
- fw_info.ver = adev->sdma[info->query_fw.index].fw_version;
- fw_info.feature = adev->sdma[info->query_fw.index].feature_version;
+ fw_info.ver = adev->sdma.instance[info->query_fw.index].fw_version;
+ fw_info.feature = adev->sdma.instance[info->query_fw.index].feature_version;
break;
default:
return -EINVAL;
*
* @dev: drm dev pointer
*
- * Switch vga switcheroo state after last close (all asics).
+ * Switch vga_switcheroo state after last close (all asics).
*/
void amdgpu_driver_lastclose_kms(struct drm_device *dev)
{
uint32_t crtc_offset;
struct drm_gem_object *cursor_bo;
uint64_t cursor_addr;
+ int cursor_x;
+ int cursor_y;
+ int cursor_hot_x;
+ int cursor_hot_y;
int cursor_width;
int cursor_height;
int max_cursor_width;
placements[c].fpfn = 0;
placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
TTM_PL_FLAG_VRAM;
+ if (!(flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED))
+ placements[c - 1].flags |= TTM_PL_FLAG_TOPDOWN;
}
if (domain & AMDGPU_GEM_DOMAIN_GTT) {
static int amdgpu_gfx_index = offsetof(struct amdgpu_device, gfx.gfx_ring[0]);
static int cayman_cp1_index = offsetof(struct amdgpu_device, gfx.compute_ring[0]);
static int cayman_cp2_index = offsetof(struct amdgpu_device, gfx.compute_ring[1]);
-static int amdgpu_dma1_index = offsetof(struct amdgpu_device, sdma[0].ring);
-static int amdgpu_dma2_index = offsetof(struct amdgpu_device, sdma[1].ring);
+static int amdgpu_dma1_index = offsetof(struct amdgpu_device, sdma.instance[0].ring);
+static int amdgpu_dma2_index = offsetof(struct amdgpu_device, sdma.instance[1].ring);
static int r600_uvd_index = offsetof(struct amdgpu_device, uvd.ring);
static int si_vce1_index = offsetof(struct amdgpu_device, vce.ring[0]);
static int si_vce2_index = offsetof(struct amdgpu_device, vce.ring[1]);
__entry->offset, __entry->flags)
);
-TRACE_EVENT(amdgpu_vm_bo_update,
+DECLARE_EVENT_CLASS(amdgpu_vm_mapping,
TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
TP_ARGS(mapping),
TP_STRUCT__entry(
__entry->soffset, __entry->eoffset, __entry->flags)
);
+DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_update,
+ TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
+ TP_ARGS(mapping)
+);
+
+DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_mapping,
+ TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
+ TP_ARGS(mapping)
+);
+
TRACE_EVENT(amdgpu_vm_set_page,
TP_PROTO(uint64_t pe, uint64_t addr, unsigned count,
uint32_t incr, uint32_t flags),
spin_lock(&glob->lru_lock);
ret = drm_mm_dump_table(m, mm);
spin_unlock(&glob->lru_lock);
+ if (ttm_pl == TTM_PL_VRAM)
+ seq_printf(m, "man size:%llu pages, ram usage:%luMB, vis usage:%luMB\n",
+ adev->mman.bdev.man[ttm_pl].size,
+ atomic64_read(&adev->vram_usage) >> 20,
+ atomic64_read(&adev->vram_vis_usage) >> 20);
return ret;
}
/* check if the id is still valid */
if (vm_id->id && vm_id->last_id_use &&
- vm_id->last_id_use == adev->vm_manager.active[vm_id->id])
+ vm_id->last_id_use == adev->vm_manager.active[vm_id->id]) {
+ trace_amdgpu_vm_grab_id(vm_id->id, ring->idx);
return 0;
+ }
/* we definately need to flush */
vm_id->pd_gpu_addr = ~0ll;
return r;
}
+ if (trace_amdgpu_vm_bo_mapping_enabled()) {
+ list_for_each_entry(mapping, &bo_va->valids, list)
+ trace_amdgpu_vm_bo_mapping(mapping);
+
+ list_for_each_entry(mapping, &bo_va->invalids, list)
+ trace_amdgpu_vm_bo_mapping(mapping);
+ }
+
spin_lock(&vm->status_lock);
list_splice_init(&bo_va->invalids, &bo_va->valids);
list_del_init(&bo_va->vm_status);
}
}
+static void atom_op_div32(atom_exec_context *ctx, int *ptr, int arg)
+{
+ uint64_t val64;
+ uint8_t attr = U8((*ptr)++);
+ uint32_t dst, src;
+ SDEBUG(" src1: ");
+ dst = atom_get_dst(ctx, arg, attr, ptr, NULL, 1);
+ SDEBUG(" src2: ");
+ src = atom_get_src(ctx, attr, ptr);
+ if (src != 0) {
+ val64 = dst;
+ val64 |= ((uint64_t)ctx->ctx->divmul[1]) << 32;
+ do_div(val64, src);
+ ctx->ctx->divmul[0] = lower_32_bits(val64);
+ ctx->ctx->divmul[1] = upper_32_bits(val64);
+ } else {
+ ctx->ctx->divmul[0] = 0;
+ ctx->ctx->divmul[1] = 0;
+ }
+}
+
static void atom_op_eot(atom_exec_context *ctx, int *ptr, int arg)
{
/* functionally, a nop */
ctx->ctx->divmul[0] = dst * src;
}
+static void atom_op_mul32(atom_exec_context *ctx, int *ptr, int arg)
+{
+ uint64_t val64;
+ uint8_t attr = U8((*ptr)++);
+ uint32_t dst, src;
+ SDEBUG(" src1: ");
+ dst = atom_get_dst(ctx, arg, attr, ptr, NULL, 1);
+ SDEBUG(" src2: ");
+ src = atom_get_src(ctx, attr, ptr);
+ val64 = (uint64_t)dst * (uint64_t)src;
+ ctx->ctx->divmul[0] = lower_32_bits(val64);
+ ctx->ctx->divmul[1] = upper_32_bits(val64);
+}
+
static void atom_op_nop(atom_exec_context *ctx, int *ptr, int arg)
{
/* nothing */
static void atom_op_debug(atom_exec_context *ctx, int *ptr, int arg)
{
- printk(KERN_INFO "unimplemented!\n");
+ uint8_t val = U8((*ptr)++);
+ SDEBUG("DEBUG output: 0x%02X\n", val);
+}
+
+static void atom_op_processds(atom_exec_context *ctx, int *ptr, int arg)
+{
+ uint16_t val = U16(*ptr);
+ (*ptr) += val + 2;
+ SDEBUG("PROCESSDS output: 0x%02X\n", val);
}
static struct {
atom_op_shr, ATOM_ARG_FB}, {
atom_op_shr, ATOM_ARG_PLL}, {
atom_op_shr, ATOM_ARG_MC}, {
-atom_op_debug, 0},};
+ atom_op_debug, 0}, {
+ atom_op_processds, 0}, {
+ atom_op_mul32, ATOM_ARG_PS}, {
+ atom_op_mul32, ATOM_ARG_WS}, {
+ atom_op_div32, ATOM_ARG_PS}, {
+ atom_op_div32, ATOM_ARG_WS},
+};
static int amdgpu_atom_execute_table_locked(struct atom_context *ctx, int index, uint32_t * params)
{
#define ATOM_CT_PS_MASK 0x7F
#define ATOM_CT_CODE_PTR 6
-#define ATOM_OP_CNT 123
+#define ATOM_OP_CNT 127
#define ATOM_OP_EOT 91
#define ATOM_CASE_MAGIC 0x63
{
const char *chip_name;
char fw_name[30];
- int err, i;
+ int err = 0, i;
DRM_DEBUG("\n");
default: BUG();
}
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
if (i == 0)
snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma.bin", chip_name);
else
snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma1.bin", chip_name);
- err = request_firmware(&adev->sdma[i].fw, fw_name, adev->dev);
+ err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev);
if (err)
goto out;
- err = amdgpu_ucode_validate(adev->sdma[i].fw);
+ err = amdgpu_ucode_validate(adev->sdma.instance[i].fw);
}
out:
if (err) {
printk(KERN_ERR
"cik_sdma: Failed to load firmware \"%s\"\n",
fw_name);
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
- release_firmware(adev->sdma[i].fw);
- adev->sdma[i].fw = NULL;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ release_firmware(adev->sdma.instance[i].fw);
+ adev->sdma.instance[i].fw = NULL;
}
}
return err;
static uint32_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- u32 me = (ring == &adev->sdma[0].ring) ? 0 : 1;
+ u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
return (RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) & 0x3fffc) >> 2;
}
static void cik_sdma_ring_set_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- u32 me = (ring == &adev->sdma[0].ring) ? 0 : 1;
+ u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], (ring->wptr << 2) & 0x3fffc);
}
static void cik_sdma_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
{
- struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ring);
+ struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring);
int i;
for (i = 0; i < count; i++)
SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
u32 ref_and_mask;
- if (ring == &ring->adev->sdma[0].ring)
+ if (ring == &ring->adev->sdma.instance[0].ring)
ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA0_MASK;
else
ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA1_MASK;
*/
static void cik_sdma_gfx_stop(struct amdgpu_device *adev)
{
- struct amdgpu_ring *sdma0 = &adev->sdma[0].ring;
- struct amdgpu_ring *sdma1 = &adev->sdma[1].ring;
+ struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring;
+ struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring;
u32 rb_cntl;
int i;
(adev->mman.buffer_funcs_ring == sdma1))
amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size);
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
rb_cntl &= ~SDMA0_GFX_RB_CNTL__RB_ENABLE_MASK;
WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i], rb_cntl);
cik_sdma_rlc_stop(adev);
}
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
me_cntl = RREG32(mmSDMA0_F32_CNTL + sdma_offsets[i]);
if (enable)
me_cntl &= ~SDMA0_F32_CNTL__HALT_MASK;
u32 wb_offset;
int i, j, r;
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
- ring = &adev->sdma[i].ring;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
wb_offset = (ring->rptr_offs * 4);
mutex_lock(&adev->srbm_mutex);
u32 fw_size;
int i, j;
- if (!adev->sdma[0].fw || !adev->sdma[1].fw)
- return -EINVAL;
-
/* halt the MEs */
cik_sdma_enable(adev, false);
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
- hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ if (!adev->sdma.instance[i].fw)
+ return -EINVAL;
+ hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
amdgpu_ucode_print_sdma_hdr(&hdr->header);
fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
- adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
- adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
- if (adev->sdma[i].feature_version >= 20)
- adev->sdma[i].burst_nop = true;
+ adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
+ adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
+ if (adev->sdma.instance[i].feature_version >= 20)
+ adev->sdma.instance[i].burst_nop = true;
fw_data = (const __le32 *)
- (adev->sdma[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes));
+ (adev->sdma.instance[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
for (j = 0; j < fw_size; j++)
WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
- WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma[i].fw_version);
+ WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version);
}
return 0;
*/
static void cik_sdma_vm_pad_ib(struct amdgpu_ib *ib)
{
- struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ib->ring);
+ struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ib->ring);
u32 pad_count;
int i;
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ adev->sdma.num_instances = SDMA_MAX_INSTANCE;
+
cik_sdma_set_ring_funcs(adev);
cik_sdma_set_irq_funcs(adev);
cik_sdma_set_buffer_funcs(adev);
{
struct amdgpu_ring *ring;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- int r;
+ int r, i;
r = cik_sdma_init_microcode(adev);
if (r) {
}
/* SDMA trap event */
- r = amdgpu_irq_add_id(adev, 224, &adev->sdma_trap_irq);
+ r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq);
if (r)
return r;
/* SDMA Privileged inst */
- r = amdgpu_irq_add_id(adev, 241, &adev->sdma_illegal_inst_irq);
+ r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq);
if (r)
return r;
/* SDMA Privileged inst */
- r = amdgpu_irq_add_id(adev, 247, &adev->sdma_illegal_inst_irq);
- if (r)
- return r;
-
- ring = &adev->sdma[0].ring;
- ring->ring_obj = NULL;
-
- ring = &adev->sdma[1].ring;
- ring->ring_obj = NULL;
-
- ring = &adev->sdma[0].ring;
- sprintf(ring->name, "sdma0");
- r = amdgpu_ring_init(adev, ring, 256 * 1024,
- SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0), 0xf,
- &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP0,
- AMDGPU_RING_TYPE_SDMA);
+ r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq);
if (r)
return r;
- ring = &adev->sdma[1].ring;
- sprintf(ring->name, "sdma1");
- r = amdgpu_ring_init(adev, ring, 256 * 1024,
- SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0), 0xf,
- &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP1,
- AMDGPU_RING_TYPE_SDMA);
- if (r)
- return r;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
+ ring->ring_obj = NULL;
+ sprintf(ring->name, "sdma%d", i);
+ r = amdgpu_ring_init(adev, ring, 256 * 1024,
+ SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0), 0xf,
+ &adev->sdma.trap_irq,
+ (i == 0) ?
+ AMDGPU_SDMA_IRQ_TRAP0 : AMDGPU_SDMA_IRQ_TRAP1,
+ AMDGPU_RING_TYPE_SDMA);
+ if (r)
+ return r;
+ }
return r;
}
static int cik_sdma_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int i;
- amdgpu_ring_fini(&adev->sdma[0].ring);
- amdgpu_ring_fini(&adev->sdma[1].ring);
+ for (i = 0; i < adev->sdma.num_instances; i++)
+ amdgpu_ring_fini(&adev->sdma.instance[i].ring);
return 0;
}
dev_info(adev->dev, "CIK SDMA registers\n");
dev_info(adev->dev, " SRBM_STATUS2=0x%08X\n",
RREG32(mmSRBM_STATUS2));
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
dev_info(adev->dev, " SDMA%d_STATUS_REG=0x%08X\n",
i, RREG32(mmSDMA0_STATUS_REG + sdma_offsets[i]));
dev_info(adev->dev, " SDMA%d_ME_CNTL=0x%08X\n",
case 0:
switch (queue_id) {
case 0:
- amdgpu_fence_process(&adev->sdma[0].ring);
+ amdgpu_fence_process(&adev->sdma.instance[0].ring);
break;
case 1:
/* XXX compute */
case 1:
switch (queue_id) {
case 0:
- amdgpu_fence_process(&adev->sdma[1].ring);
+ amdgpu_fence_process(&adev->sdma.instance[1].ring);
break;
case 1:
/* XXX compute */
static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev)
{
- adev->sdma[0].ring.funcs = &cik_sdma_ring_funcs;
- adev->sdma[1].ring.funcs = &cik_sdma_ring_funcs;
+ int i;
+
+ for (i = 0; i < adev->sdma.num_instances; i++)
+ adev->sdma.instance[i].ring.funcs = &cik_sdma_ring_funcs;
}
static const struct amdgpu_irq_src_funcs cik_sdma_trap_irq_funcs = {
static void cik_sdma_set_irq_funcs(struct amdgpu_device *adev)
{
- adev->sdma_trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
- adev->sdma_trap_irq.funcs = &cik_sdma_trap_irq_funcs;
- adev->sdma_illegal_inst_irq.funcs = &cik_sdma_illegal_inst_irq_funcs;
+ adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
+ adev->sdma.trap_irq.funcs = &cik_sdma_trap_irq_funcs;
+ adev->sdma.illegal_inst_irq.funcs = &cik_sdma_illegal_inst_irq_funcs;
}
/**
{
if (adev->mman.buffer_funcs == NULL) {
adev->mman.buffer_funcs = &cik_sdma_buffer_funcs;
- adev->mman.buffer_funcs_ring = &adev->sdma[0].ring;
+ adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
}
}
{
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &cik_sdma_vm_pte_funcs;
- adev->vm_manager.vm_pte_funcs_ring = &adev->sdma[0].ring;
+ adev->vm_manager.vm_pte_funcs_ring = &adev->sdma.instance[0].ring;
adev->vm_manager.vm_pte_funcs_ring->is_pte_ring = true;
}
}
struct amdgpu_device *adev = crtc->dev->dev_private;
u32 tmp;
+ WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
+ upper_32_bits(amdgpu_crtc->cursor_addr));
+ WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset,
+ lower_32_bits(amdgpu_crtc->cursor_addr));
+
tmp = RREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset);
tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_EN, 1);
tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_MODE, 2);
WREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset, tmp);
}
-static void dce_v10_0_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj,
- uint64_t gpu_addr)
-{
- struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
-
- WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
- upper_32_bits(gpu_addr));
- WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset,
- lower_32_bits(gpu_addr));
-}
-
-static int dce_v10_0_crtc_cursor_move(struct drm_crtc *crtc,
- int x, int y)
+static int dce_v10_0_cursor_move_locked(struct drm_crtc *crtc,
+ int x, int y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
struct amdgpu_device *adev = crtc->dev->dev_private;
y = 0;
}
- dce_v10_0_lock_cursor(crtc, true);
WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
- dce_v10_0_lock_cursor(crtc, false);
+
+ amdgpu_crtc->cursor_x = x;
+ amdgpu_crtc->cursor_y = y;
return 0;
}
-static int dce_v10_0_crtc_cursor_set(struct drm_crtc *crtc,
- struct drm_file *file_priv,
- uint32_t handle,
- uint32_t width,
- uint32_t height)
+static int dce_v10_0_crtc_cursor_move(struct drm_crtc *crtc,
+ int x, int y)
+{
+ int ret;
+
+ dce_v10_0_lock_cursor(crtc, true);
+ ret = dce_v10_0_cursor_move_locked(crtc, x, y);
+ dce_v10_0_lock_cursor(crtc, false);
+
+ return ret;
+}
+
+static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc,
+ struct drm_file *file_priv,
+ uint32_t handle,
+ uint32_t width,
+ uint32_t height,
+ int32_t hot_x,
+ int32_t hot_y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
struct drm_gem_object *obj;
- struct amdgpu_bo *robj;
- uint64_t gpu_addr;
+ struct amdgpu_bo *aobj;
int ret;
if (!handle) {
return -ENOENT;
}
- robj = gem_to_amdgpu_bo(obj);
- ret = amdgpu_bo_reserve(robj, false);
- if (unlikely(ret != 0))
- goto fail;
- ret = amdgpu_bo_pin_restricted(robj, AMDGPU_GEM_DOMAIN_VRAM,
- 0, 0, &gpu_addr);
- amdgpu_bo_unreserve(robj);
- if (ret)
- goto fail;
+ aobj = gem_to_amdgpu_bo(obj);
+ ret = amdgpu_bo_reserve(aobj, false);
+ if (ret != 0) {
+ drm_gem_object_unreference_unlocked(obj);
+ return ret;
+ }
+
+ ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+ amdgpu_bo_unreserve(aobj);
+ if (ret) {
+ DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
+ drm_gem_object_unreference_unlocked(obj);
+ return ret;
+ }
amdgpu_crtc->cursor_width = width;
amdgpu_crtc->cursor_height = height;
dce_v10_0_lock_cursor(crtc, true);
- dce_v10_0_set_cursor(crtc, obj, gpu_addr);
+
+ if (hot_x != amdgpu_crtc->cursor_hot_x ||
+ hot_y != amdgpu_crtc->cursor_hot_y) {
+ int x, y;
+
+ x = amdgpu_crtc->cursor_x + amdgpu_crtc->cursor_hot_x - hot_x;
+ y = amdgpu_crtc->cursor_y + amdgpu_crtc->cursor_hot_y - hot_y;
+
+ dce_v10_0_cursor_move_locked(crtc, x, y);
+
+ amdgpu_crtc->cursor_hot_x = hot_x;
+ amdgpu_crtc->cursor_hot_y = hot_y;
+ }
+
dce_v10_0_show_cursor(crtc);
dce_v10_0_lock_cursor(crtc, false);
unpin:
if (amdgpu_crtc->cursor_bo) {
- robj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
- ret = amdgpu_bo_reserve(robj, false);
+ struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+ ret = amdgpu_bo_reserve(aobj, false);
if (likely(ret == 0)) {
- amdgpu_bo_unpin(robj);
- amdgpu_bo_unreserve(robj);
+ amdgpu_bo_unpin(aobj);
+ amdgpu_bo_unreserve(aobj);
}
drm_gem_object_unreference_unlocked(amdgpu_crtc->cursor_bo);
}
amdgpu_crtc->cursor_bo = obj;
return 0;
-fail:
- drm_gem_object_unreference_unlocked(obj);
+}
- return ret;
+static void dce_v10_0_cursor_reset(struct drm_crtc *crtc)
+{
+ struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+
+ if (amdgpu_crtc->cursor_bo) {
+ dce_v10_0_lock_cursor(crtc, true);
+
+ dce_v10_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
+ amdgpu_crtc->cursor_y);
+
+ dce_v10_0_show_cursor(crtc);
+
+ dce_v10_0_lock_cursor(crtc, false);
+ }
}
static void dce_v10_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
}
static const struct drm_crtc_funcs dce_v10_0_crtc_funcs = {
- .cursor_set = dce_v10_0_crtc_cursor_set,
+ .cursor_set2 = dce_v10_0_crtc_cursor_set2,
.cursor_move = dce_v10_0_crtc_cursor_move,
.gamma_set = dce_v10_0_crtc_gamma_set,
.set_config = amdgpu_crtc_set_config,
dce_v10_0_crtc_do_set_base(crtc, old_fb, x, y, 0);
amdgpu_atombios_crtc_overscan_setup(crtc, mode, adjusted_mode);
amdgpu_atombios_crtc_scaler_setup(crtc);
+ dce_v10_0_cursor_reset(crtc);
/* update the hw version fpr dpm */
amdgpu_crtc->hw_mode = *adjusted_mode;
unsigned type,
enum amdgpu_interrupt_state state)
{
- u32 reg, reg_block;
- /* now deal with page flip IRQ */
- switch (type) {
- case AMDGPU_PAGEFLIP_IRQ_D1:
- reg_block = CRTC0_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D2:
- reg_block = CRTC1_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D3:
- reg_block = CRTC2_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D4:
- reg_block = CRTC3_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D5:
- reg_block = CRTC4_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D6:
- reg_block = CRTC5_REGISTER_OFFSET;
- break;
- default:
- DRM_ERROR("invalid pageflip crtc %d\n", type);
- return -EINVAL;
+ u32 reg;
+
+ if (type >= adev->mode_info.num_crtc) {
+ DRM_ERROR("invalid pageflip crtc %d\n", type);
+ return -EINVAL;
}
- reg = RREG32(mmGRPH_INTERRUPT_CONTROL + reg_block);
+ reg = RREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type]);
if (state == AMDGPU_IRQ_STATE_DISABLE)
- WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
+ WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type],
+ reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
else
- WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
+ WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type],
+ reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
return 0;
}
struct amdgpu_irq_src *source,
struct amdgpu_iv_entry *entry)
{
- int reg_block;
unsigned long flags;
unsigned crtc_id;
struct amdgpu_crtc *amdgpu_crtc;
crtc_id = (entry->src_id - 8) >> 1;
amdgpu_crtc = adev->mode_info.crtcs[crtc_id];
- /* ack the interrupt */
- switch(crtc_id){
- case AMDGPU_PAGEFLIP_IRQ_D1:
- reg_block = CRTC0_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D2:
- reg_block = CRTC1_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D3:
- reg_block = CRTC2_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D4:
- reg_block = CRTC3_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D5:
- reg_block = CRTC4_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D6:
- reg_block = CRTC5_REGISTER_OFFSET;
- break;
- default:
- DRM_ERROR("invalid pageflip crtc %d\n", crtc_id);
- return -EINVAL;
+ if (crtc_id >= adev->mode_info.num_crtc) {
+ DRM_ERROR("invalid pageflip crtc %d\n", crtc_id);
+ return -EINVAL;
}
- if (RREG32(mmGRPH_INTERRUPT_STATUS + reg_block) & GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK)
- WREG32(mmGRPH_INTERRUPT_STATUS + reg_block, GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK);
+ if (RREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id]) &
+ GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK)
+ WREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id],
+ GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK);
/* IRQ could occur when in initial stage */
if (amdgpu_crtc == NULL)
struct amdgpu_device *adev = crtc->dev->dev_private;
u32 tmp;
+ WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
+ upper_32_bits(amdgpu_crtc->cursor_addr));
+ WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset,
+ lower_32_bits(amdgpu_crtc->cursor_addr));
+
tmp = RREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset);
tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_EN, 1);
tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_MODE, 2);
WREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset, tmp);
}
-static void dce_v11_0_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj,
- uint64_t gpu_addr)
-{
- struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
-
- WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
- upper_32_bits(gpu_addr));
- WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset,
- lower_32_bits(gpu_addr));
-}
-
-static int dce_v11_0_crtc_cursor_move(struct drm_crtc *crtc,
- int x, int y)
+static int dce_v11_0_cursor_move_locked(struct drm_crtc *crtc,
+ int x, int y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
struct amdgpu_device *adev = crtc->dev->dev_private;
y = 0;
}
- dce_v11_0_lock_cursor(crtc, true);
WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
- dce_v11_0_lock_cursor(crtc, false);
+
+ amdgpu_crtc->cursor_x = x;
+ amdgpu_crtc->cursor_y = y;
return 0;
}
-static int dce_v11_0_crtc_cursor_set(struct drm_crtc *crtc,
- struct drm_file *file_priv,
- uint32_t handle,
- uint32_t width,
- uint32_t height)
+static int dce_v11_0_crtc_cursor_move(struct drm_crtc *crtc,
+ int x, int y)
+{
+ int ret;
+
+ dce_v11_0_lock_cursor(crtc, true);
+ ret = dce_v11_0_cursor_move_locked(crtc, x, y);
+ dce_v11_0_lock_cursor(crtc, false);
+
+ return ret;
+}
+
+static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc,
+ struct drm_file *file_priv,
+ uint32_t handle,
+ uint32_t width,
+ uint32_t height,
+ int32_t hot_x,
+ int32_t hot_y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
struct drm_gem_object *obj;
- struct amdgpu_bo *robj;
- uint64_t gpu_addr;
+ struct amdgpu_bo *aobj;
int ret;
if (!handle) {
return -ENOENT;
}
- robj = gem_to_amdgpu_bo(obj);
- ret = amdgpu_bo_reserve(robj, false);
- if (unlikely(ret != 0))
- goto fail;
- ret = amdgpu_bo_pin_restricted(robj, AMDGPU_GEM_DOMAIN_VRAM,
- 0, 0, &gpu_addr);
- amdgpu_bo_unreserve(robj);
- if (ret)
- goto fail;
+ aobj = gem_to_amdgpu_bo(obj);
+ ret = amdgpu_bo_reserve(aobj, false);
+ if (ret != 0) {
+ drm_gem_object_unreference_unlocked(obj);
+ return ret;
+ }
+
+ ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+ amdgpu_bo_unreserve(aobj);
+ if (ret) {
+ DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
+ drm_gem_object_unreference_unlocked(obj);
+ return ret;
+ }
amdgpu_crtc->cursor_width = width;
amdgpu_crtc->cursor_height = height;
dce_v11_0_lock_cursor(crtc, true);
- dce_v11_0_set_cursor(crtc, obj, gpu_addr);
+
+ if (hot_x != amdgpu_crtc->cursor_hot_x ||
+ hot_y != amdgpu_crtc->cursor_hot_y) {
+ int x, y;
+
+ x = amdgpu_crtc->cursor_x + amdgpu_crtc->cursor_hot_x - hot_x;
+ y = amdgpu_crtc->cursor_y + amdgpu_crtc->cursor_hot_y - hot_y;
+
+ dce_v11_0_cursor_move_locked(crtc, x, y);
+
+ amdgpu_crtc->cursor_hot_x = hot_x;
+ amdgpu_crtc->cursor_hot_y = hot_y;
+ }
+
dce_v11_0_show_cursor(crtc);
dce_v11_0_lock_cursor(crtc, false);
unpin:
if (amdgpu_crtc->cursor_bo) {
- robj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
- ret = amdgpu_bo_reserve(robj, false);
+ struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+ ret = amdgpu_bo_reserve(aobj, false);
if (likely(ret == 0)) {
- amdgpu_bo_unpin(robj);
- amdgpu_bo_unreserve(robj);
+ amdgpu_bo_unpin(aobj);
+ amdgpu_bo_unreserve(aobj);
}
drm_gem_object_unreference_unlocked(amdgpu_crtc->cursor_bo);
}
amdgpu_crtc->cursor_bo = obj;
return 0;
-fail:
- drm_gem_object_unreference_unlocked(obj);
+}
- return ret;
+static void dce_v11_0_cursor_reset(struct drm_crtc *crtc)
+{
+ struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+
+ if (amdgpu_crtc->cursor_bo) {
+ dce_v11_0_lock_cursor(crtc, true);
+
+ dce_v11_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
+ amdgpu_crtc->cursor_y);
+
+ dce_v11_0_show_cursor(crtc);
+
+ dce_v11_0_lock_cursor(crtc, false);
+ }
}
static void dce_v11_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
}
static const struct drm_crtc_funcs dce_v11_0_crtc_funcs = {
- .cursor_set = dce_v11_0_crtc_cursor_set,
+ .cursor_set2 = dce_v11_0_crtc_cursor_set2,
.cursor_move = dce_v11_0_crtc_cursor_move,
.gamma_set = dce_v11_0_crtc_gamma_set,
.set_config = amdgpu_crtc_set_config,
dce_v11_0_crtc_do_set_base(crtc, old_fb, x, y, 0);
amdgpu_atombios_crtc_overscan_setup(crtc, mode, adjusted_mode);
amdgpu_atombios_crtc_scaler_setup(crtc);
+ dce_v11_0_cursor_reset(crtc);
/* update the hw version fpr dpm */
amdgpu_crtc->hw_mode = *adjusted_mode;
unsigned type,
enum amdgpu_interrupt_state state)
{
- u32 reg, reg_block;
- /* now deal with page flip IRQ */
- switch (type) {
- case AMDGPU_PAGEFLIP_IRQ_D1:
- reg_block = CRTC0_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D2:
- reg_block = CRTC1_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D3:
- reg_block = CRTC2_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D4:
- reg_block = CRTC3_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D5:
- reg_block = CRTC4_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D6:
- reg_block = CRTC5_REGISTER_OFFSET;
- break;
- default:
- DRM_ERROR("invalid pageflip crtc %d\n", type);
- return -EINVAL;
+ u32 reg;
+
+ if (type >= adev->mode_info.num_crtc) {
+ DRM_ERROR("invalid pageflip crtc %d\n", type);
+ return -EINVAL;
}
- reg = RREG32(mmGRPH_INTERRUPT_CONTROL + reg_block);
+ reg = RREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type]);
if (state == AMDGPU_IRQ_STATE_DISABLE)
- WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
+ WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type],
+ reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
else
- WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
+ WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type],
+ reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
return 0;
}
struct amdgpu_irq_src *source,
struct amdgpu_iv_entry *entry)
{
- int reg_block;
unsigned long flags;
unsigned crtc_id;
struct amdgpu_crtc *amdgpu_crtc;
crtc_id = (entry->src_id - 8) >> 1;
amdgpu_crtc = adev->mode_info.crtcs[crtc_id];
- /* ack the interrupt */
- switch(crtc_id){
- case AMDGPU_PAGEFLIP_IRQ_D1:
- reg_block = CRTC0_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D2:
- reg_block = CRTC1_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D3:
- reg_block = CRTC2_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D4:
- reg_block = CRTC3_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D5:
- reg_block = CRTC4_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D6:
- reg_block = CRTC5_REGISTER_OFFSET;
- break;
- default:
- DRM_ERROR("invalid pageflip crtc %d\n", crtc_id);
- return -EINVAL;
+ if (crtc_id >= adev->mode_info.num_crtc) {
+ DRM_ERROR("invalid pageflip crtc %d\n", crtc_id);
+ return -EINVAL;
}
- if (RREG32(mmGRPH_INTERRUPT_STATUS + reg_block) & GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK)
- WREG32(mmGRPH_INTERRUPT_STATUS + reg_block, GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK);
+ if (RREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id]) &
+ GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK)
+ WREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id],
+ GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK);
/* IRQ could occur when in initial stage */
if(amdgpu_crtc == NULL)
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
struct amdgpu_device *adev = crtc->dev->dev_private;
+ WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
+ upper_32_bits(amdgpu_crtc->cursor_addr));
+ WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset,
+ lower_32_bits(amdgpu_crtc->cursor_addr));
+
WREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset,
CUR_CONTROL__CURSOR_EN_MASK |
(CURSOR_24_8_PRE_MULT << CUR_CONTROL__CURSOR_MODE__SHIFT) |
(CURSOR_URGENT_1_2 << CUR_CONTROL__CURSOR_URGENT_CONTROL__SHIFT));
}
-static void dce_v8_0_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj,
- uint64_t gpu_addr)
-{
- struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct amdgpu_device *adev = crtc->dev->dev_private;
-
- WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
- upper_32_bits(gpu_addr));
- WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset,
- gpu_addr & 0xffffffff);
-}
-
-static int dce_v8_0_crtc_cursor_move(struct drm_crtc *crtc,
- int x, int y)
+static int dce_v8_0_cursor_move_locked(struct drm_crtc *crtc,
+ int x, int y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
struct amdgpu_device *adev = crtc->dev->dev_private;
y = 0;
}
- dce_v8_0_lock_cursor(crtc, true);
WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
- dce_v8_0_lock_cursor(crtc, false);
+
+ amdgpu_crtc->cursor_x = x;
+ amdgpu_crtc->cursor_y = y;
return 0;
}
-static int dce_v8_0_crtc_cursor_set(struct drm_crtc *crtc,
- struct drm_file *file_priv,
- uint32_t handle,
- uint32_t width,
- uint32_t height)
+static int dce_v8_0_crtc_cursor_move(struct drm_crtc *crtc,
+ int x, int y)
+{
+ int ret;
+
+ dce_v8_0_lock_cursor(crtc, true);
+ ret = dce_v8_0_cursor_move_locked(crtc, x, y);
+ dce_v8_0_lock_cursor(crtc, false);
+
+ return ret;
+}
+
+static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc,
+ struct drm_file *file_priv,
+ uint32_t handle,
+ uint32_t width,
+ uint32_t height,
+ int32_t hot_x,
+ int32_t hot_y)
{
struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
struct drm_gem_object *obj;
- struct amdgpu_bo *robj;
- uint64_t gpu_addr;
+ struct amdgpu_bo *aobj;
int ret;
if (!handle) {
return -ENOENT;
}
- robj = gem_to_amdgpu_bo(obj);
- ret = amdgpu_bo_reserve(robj, false);
- if (unlikely(ret != 0))
- goto fail;
- ret = amdgpu_bo_pin_restricted(robj, AMDGPU_GEM_DOMAIN_VRAM,
- 0, 0, &gpu_addr);
- amdgpu_bo_unreserve(robj);
- if (ret)
- goto fail;
+ aobj = gem_to_amdgpu_bo(obj);
+ ret = amdgpu_bo_reserve(aobj, false);
+ if (ret != 0) {
+ drm_gem_object_unreference_unlocked(obj);
+ return ret;
+ }
+
+ ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+ amdgpu_bo_unreserve(aobj);
+ if (ret) {
+ DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
+ drm_gem_object_unreference_unlocked(obj);
+ return ret;
+ }
amdgpu_crtc->cursor_width = width;
amdgpu_crtc->cursor_height = height;
dce_v8_0_lock_cursor(crtc, true);
- dce_v8_0_set_cursor(crtc, obj, gpu_addr);
+
+ if (hot_x != amdgpu_crtc->cursor_hot_x ||
+ hot_y != amdgpu_crtc->cursor_hot_y) {
+ int x, y;
+
+ x = amdgpu_crtc->cursor_x + amdgpu_crtc->cursor_hot_x - hot_x;
+ y = amdgpu_crtc->cursor_y + amdgpu_crtc->cursor_hot_y - hot_y;
+
+ dce_v8_0_cursor_move_locked(crtc, x, y);
+
+ amdgpu_crtc->cursor_hot_x = hot_x;
+ amdgpu_crtc->cursor_hot_y = hot_y;
+ }
+
dce_v8_0_show_cursor(crtc);
dce_v8_0_lock_cursor(crtc, false);
unpin:
if (amdgpu_crtc->cursor_bo) {
- robj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
- ret = amdgpu_bo_reserve(robj, false);
+ struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+ ret = amdgpu_bo_reserve(aobj, false);
if (likely(ret == 0)) {
- amdgpu_bo_unpin(robj);
- amdgpu_bo_unreserve(robj);
+ amdgpu_bo_unpin(aobj);
+ amdgpu_bo_unreserve(aobj);
}
drm_gem_object_unreference_unlocked(amdgpu_crtc->cursor_bo);
}
amdgpu_crtc->cursor_bo = obj;
return 0;
-fail:
- drm_gem_object_unreference_unlocked(obj);
+}
- return ret;
+static void dce_v8_0_cursor_reset(struct drm_crtc *crtc)
+{
+ struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+
+ if (amdgpu_crtc->cursor_bo) {
+ dce_v8_0_lock_cursor(crtc, true);
+
+ dce_v8_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
+ amdgpu_crtc->cursor_y);
+
+ dce_v8_0_show_cursor(crtc);
+
+ dce_v8_0_lock_cursor(crtc, false);
+ }
}
static void dce_v8_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
}
static const struct drm_crtc_funcs dce_v8_0_crtc_funcs = {
- .cursor_set = dce_v8_0_crtc_cursor_set,
+ .cursor_set2 = dce_v8_0_crtc_cursor_set2,
.cursor_move = dce_v8_0_crtc_cursor_move,
.gamma_set = dce_v8_0_crtc_gamma_set,
.set_config = amdgpu_crtc_set_config,
dce_v8_0_crtc_do_set_base(crtc, old_fb, x, y, 0);
amdgpu_atombios_crtc_overscan_setup(crtc, mode, adjusted_mode);
amdgpu_atombios_crtc_scaler_setup(crtc);
+ dce_v8_0_cursor_reset(crtc);
/* update the hw version fpr dpm */
amdgpu_crtc->hw_mode = *adjusted_mode;
unsigned type,
enum amdgpu_interrupt_state state)
{
- u32 reg, reg_block;
- /* now deal with page flip IRQ */
- switch (type) {
- case AMDGPU_PAGEFLIP_IRQ_D1:
- reg_block = CRTC0_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D2:
- reg_block = CRTC1_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D3:
- reg_block = CRTC2_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D4:
- reg_block = CRTC3_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D5:
- reg_block = CRTC4_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D6:
- reg_block = CRTC5_REGISTER_OFFSET;
- break;
- default:
- DRM_ERROR("invalid pageflip crtc %d\n", type);
- return -EINVAL;
+ u32 reg;
+
+ if (type >= adev->mode_info.num_crtc) {
+ DRM_ERROR("invalid pageflip crtc %d\n", type);
+ return -EINVAL;
}
- reg = RREG32(mmGRPH_INTERRUPT_CONTROL + reg_block);
+ reg = RREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type]);
if (state == AMDGPU_IRQ_STATE_DISABLE)
- WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
+ WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type],
+ reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
else
- WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
+ WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type],
+ reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK);
return 0;
}
struct amdgpu_irq_src *source,
struct amdgpu_iv_entry *entry)
{
- int reg_block;
unsigned long flags;
unsigned crtc_id;
struct amdgpu_crtc *amdgpu_crtc;
crtc_id = (entry->src_id - 8) >> 1;
amdgpu_crtc = adev->mode_info.crtcs[crtc_id];
- /* ack the interrupt */
- switch(crtc_id){
- case AMDGPU_PAGEFLIP_IRQ_D1:
- reg_block = CRTC0_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D2:
- reg_block = CRTC1_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D3:
- reg_block = CRTC2_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D4:
- reg_block = CRTC3_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D5:
- reg_block = CRTC4_REGISTER_OFFSET;
- break;
- case AMDGPU_PAGEFLIP_IRQ_D6:
- reg_block = CRTC5_REGISTER_OFFSET;
- break;
- default:
- DRM_ERROR("invalid pageflip crtc %d\n", crtc_id);
- return -EINVAL;
+ if (crtc_id >= adev->mode_info.num_crtc) {
+ DRM_ERROR("invalid pageflip crtc %d\n", crtc_id);
+ return -EINVAL;
}
- if (RREG32(mmGRPH_INTERRUPT_STATUS + reg_block) & GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK)
- WREG32(mmGRPH_INTERRUPT_STATUS + reg_block, GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK);
+ if (RREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id]) &
+ GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK)
+ WREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id],
+ GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK);
/* IRQ could occur when in initial stage */
if (amdgpu_crtc == NULL)
return 0;
}
+static void gfx_v8_0_gpu_early_init(struct amdgpu_device *adev)
+{
+ u32 gb_addr_config;
+ u32 mc_shared_chmap, mc_arb_ramcfg;
+ u32 dimm00_addr_map, dimm01_addr_map, dimm10_addr_map, dimm11_addr_map;
+ u32 tmp;
+
+ switch (adev->asic_type) {
+ case CHIP_TOPAZ:
+ adev->gfx.config.max_shader_engines = 1;
+ adev->gfx.config.max_tile_pipes = 2;
+ adev->gfx.config.max_cu_per_sh = 6;
+ adev->gfx.config.max_sh_per_se = 1;
+ adev->gfx.config.max_backends_per_se = 2;
+ adev->gfx.config.max_texture_channel_caches = 2;
+ adev->gfx.config.max_gprs = 256;
+ adev->gfx.config.max_gs_threads = 32;
+ adev->gfx.config.max_hw_contexts = 8;
+
+ adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
+ adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
+ adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
+ adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = TOPAZ_GB_ADDR_CONFIG_GOLDEN;
+ break;
+ case CHIP_FIJI:
+ adev->gfx.config.max_shader_engines = 4;
+ adev->gfx.config.max_tile_pipes = 16;
+ adev->gfx.config.max_cu_per_sh = 16;
+ adev->gfx.config.max_sh_per_se = 1;
+ adev->gfx.config.max_backends_per_se = 4;
+ adev->gfx.config.max_texture_channel_caches = 8;
+ adev->gfx.config.max_gprs = 256;
+ adev->gfx.config.max_gs_threads = 32;
+ adev->gfx.config.max_hw_contexts = 8;
+
+ adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
+ adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
+ adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
+ adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN;
+ break;
+ case CHIP_TONGA:
+ adev->gfx.config.max_shader_engines = 4;
+ adev->gfx.config.max_tile_pipes = 8;
+ adev->gfx.config.max_cu_per_sh = 8;
+ adev->gfx.config.max_sh_per_se = 1;
+ adev->gfx.config.max_backends_per_se = 2;
+ adev->gfx.config.max_texture_channel_caches = 8;
+ adev->gfx.config.max_gprs = 256;
+ adev->gfx.config.max_gs_threads = 32;
+ adev->gfx.config.max_hw_contexts = 8;
+
+ adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
+ adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
+ adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
+ adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN;
+ break;
+ case CHIP_CARRIZO:
+ adev->gfx.config.max_shader_engines = 1;
+ adev->gfx.config.max_tile_pipes = 2;
+ adev->gfx.config.max_sh_per_se = 1;
+ adev->gfx.config.max_backends_per_se = 2;
+
+ switch (adev->pdev->revision) {
+ case 0xc4:
+ case 0x84:
+ case 0xc8:
+ case 0xcc:
+ /* B10 */
+ adev->gfx.config.max_cu_per_sh = 8;
+ break;
+ case 0xc5:
+ case 0x81:
+ case 0x85:
+ case 0xc9:
+ case 0xcd:
+ /* B8 */
+ adev->gfx.config.max_cu_per_sh = 6;
+ break;
+ case 0xc6:
+ case 0xca:
+ case 0xce:
+ /* B6 */
+ adev->gfx.config.max_cu_per_sh = 6;
+ break;
+ case 0xc7:
+ case 0x87:
+ case 0xcb:
+ default:
+ /* B4 */
+ adev->gfx.config.max_cu_per_sh = 4;
+ break;
+ }
+
+ adev->gfx.config.max_texture_channel_caches = 2;
+ adev->gfx.config.max_gprs = 256;
+ adev->gfx.config.max_gs_threads = 32;
+ adev->gfx.config.max_hw_contexts = 8;
+
+ adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
+ adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
+ adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
+ adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = CARRIZO_GB_ADDR_CONFIG_GOLDEN;
+ break;
+ default:
+ adev->gfx.config.max_shader_engines = 2;
+ adev->gfx.config.max_tile_pipes = 4;
+ adev->gfx.config.max_cu_per_sh = 2;
+ adev->gfx.config.max_sh_per_se = 1;
+ adev->gfx.config.max_backends_per_se = 2;
+ adev->gfx.config.max_texture_channel_caches = 4;
+ adev->gfx.config.max_gprs = 256;
+ adev->gfx.config.max_gs_threads = 32;
+ adev->gfx.config.max_hw_contexts = 8;
+
+ adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
+ adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
+ adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
+ adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN;
+ break;
+ }
+
+ mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP);
+ adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG);
+ mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg;
+
+ adev->gfx.config.num_tile_pipes = adev->gfx.config.max_tile_pipes;
+ adev->gfx.config.mem_max_burst_length_bytes = 256;
+ if (adev->flags & AMD_IS_APU) {
+ /* Get memory bank mapping mode. */
+ tmp = RREG32(mmMC_FUS_DRAM0_BANK_ADDR_MAPPING);
+ dimm00_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM0_BANK_ADDR_MAPPING, DIMM0ADDRMAP);
+ dimm01_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM0_BANK_ADDR_MAPPING, DIMM1ADDRMAP);
+
+ tmp = RREG32(mmMC_FUS_DRAM1_BANK_ADDR_MAPPING);
+ dimm10_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM1_BANK_ADDR_MAPPING, DIMM0ADDRMAP);
+ dimm11_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM1_BANK_ADDR_MAPPING, DIMM1ADDRMAP);
+
+ /* Validate settings in case only one DIMM installed. */
+ if ((dimm00_addr_map == 0) || (dimm00_addr_map == 3) || (dimm00_addr_map == 4) || (dimm00_addr_map > 12))
+ dimm00_addr_map = 0;
+ if ((dimm01_addr_map == 0) || (dimm01_addr_map == 3) || (dimm01_addr_map == 4) || (dimm01_addr_map > 12))
+ dimm01_addr_map = 0;
+ if ((dimm10_addr_map == 0) || (dimm10_addr_map == 3) || (dimm10_addr_map == 4) || (dimm10_addr_map > 12))
+ dimm10_addr_map = 0;
+ if ((dimm11_addr_map == 0) || (dimm11_addr_map == 3) || (dimm11_addr_map == 4) || (dimm11_addr_map > 12))
+ dimm11_addr_map = 0;
+
+ /* If DIMM Addr map is 8GB, ROW size should be 2KB. Otherwise 1KB. */
+ /* If ROW size(DIMM1) != ROW size(DMIMM0), ROW size should be larger one. */
+ if ((dimm00_addr_map == 11) || (dimm01_addr_map == 11) || (dimm10_addr_map == 11) || (dimm11_addr_map == 11))
+ adev->gfx.config.mem_row_size_in_kb = 2;
+ else
+ adev->gfx.config.mem_row_size_in_kb = 1;
+ } else {
+ tmp = REG_GET_FIELD(mc_arb_ramcfg, MC_ARB_RAMCFG, NOOFCOLS);
+ adev->gfx.config.mem_row_size_in_kb = (4 * (1 << (8 + tmp))) / 1024;
+ if (adev->gfx.config.mem_row_size_in_kb > 4)
+ adev->gfx.config.mem_row_size_in_kb = 4;
+ }
+
+ adev->gfx.config.shader_engine_tile_size = 32;
+ adev->gfx.config.num_gpus = 1;
+ adev->gfx.config.multi_gpu_tile_size = 64;
+
+ /* fix up row size */
+ switch (adev->gfx.config.mem_row_size_in_kb) {
+ case 1:
+ default:
+ gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 0);
+ break;
+ case 2:
+ gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 1);
+ break;
+ case 4:
+ gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 2);
+ break;
+ }
+ adev->gfx.config.gb_addr_config = gb_addr_config;
+}
+
static int gfx_v8_0_sw_init(void *handle)
{
int i, r;
adev->gfx.ce_ram_size = 0x8000;
+ gfx_v8_0_gpu_early_init(adev);
+
return 0;
}
static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
{
- u32 gb_addr_config;
- u32 mc_shared_chmap, mc_arb_ramcfg;
- u32 dimm00_addr_map, dimm01_addr_map, dimm10_addr_map, dimm11_addr_map;
u32 tmp;
int i;
- switch (adev->asic_type) {
- case CHIP_TOPAZ:
- adev->gfx.config.max_shader_engines = 1;
- adev->gfx.config.max_tile_pipes = 2;
- adev->gfx.config.max_cu_per_sh = 6;
- adev->gfx.config.max_sh_per_se = 1;
- adev->gfx.config.max_backends_per_se = 2;
- adev->gfx.config.max_texture_channel_caches = 2;
- adev->gfx.config.max_gprs = 256;
- adev->gfx.config.max_gs_threads = 32;
- adev->gfx.config.max_hw_contexts = 8;
-
- adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
- adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
- adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
- adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
- gb_addr_config = TOPAZ_GB_ADDR_CONFIG_GOLDEN;
- break;
- case CHIP_FIJI:
- adev->gfx.config.max_shader_engines = 4;
- adev->gfx.config.max_tile_pipes = 16;
- adev->gfx.config.max_cu_per_sh = 16;
- adev->gfx.config.max_sh_per_se = 1;
- adev->gfx.config.max_backends_per_se = 4;
- adev->gfx.config.max_texture_channel_caches = 8;
- adev->gfx.config.max_gprs = 256;
- adev->gfx.config.max_gs_threads = 32;
- adev->gfx.config.max_hw_contexts = 8;
-
- adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
- adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
- adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
- adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
- gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN;
- break;
- case CHIP_TONGA:
- adev->gfx.config.max_shader_engines = 4;
- adev->gfx.config.max_tile_pipes = 8;
- adev->gfx.config.max_cu_per_sh = 8;
- adev->gfx.config.max_sh_per_se = 1;
- adev->gfx.config.max_backends_per_se = 2;
- adev->gfx.config.max_texture_channel_caches = 8;
- adev->gfx.config.max_gprs = 256;
- adev->gfx.config.max_gs_threads = 32;
- adev->gfx.config.max_hw_contexts = 8;
-
- adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
- adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
- adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
- adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
- gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN;
- break;
- case CHIP_CARRIZO:
- adev->gfx.config.max_shader_engines = 1;
- adev->gfx.config.max_tile_pipes = 2;
- adev->gfx.config.max_sh_per_se = 1;
- adev->gfx.config.max_backends_per_se = 2;
-
- switch (adev->pdev->revision) {
- case 0xc4:
- case 0x84:
- case 0xc8:
- case 0xcc:
- /* B10 */
- adev->gfx.config.max_cu_per_sh = 8;
- break;
- case 0xc5:
- case 0x81:
- case 0x85:
- case 0xc9:
- case 0xcd:
- /* B8 */
- adev->gfx.config.max_cu_per_sh = 6;
- break;
- case 0xc6:
- case 0xca:
- case 0xce:
- /* B6 */
- adev->gfx.config.max_cu_per_sh = 6;
- break;
- case 0xc7:
- case 0x87:
- case 0xcb:
- default:
- /* B4 */
- adev->gfx.config.max_cu_per_sh = 4;
- break;
- }
-
- adev->gfx.config.max_texture_channel_caches = 2;
- adev->gfx.config.max_gprs = 256;
- adev->gfx.config.max_gs_threads = 32;
- adev->gfx.config.max_hw_contexts = 8;
-
- adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
- adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
- adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
- adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
- gb_addr_config = CARRIZO_GB_ADDR_CONFIG_GOLDEN;
- break;
- default:
- adev->gfx.config.max_shader_engines = 2;
- adev->gfx.config.max_tile_pipes = 4;
- adev->gfx.config.max_cu_per_sh = 2;
- adev->gfx.config.max_sh_per_se = 1;
- adev->gfx.config.max_backends_per_se = 2;
- adev->gfx.config.max_texture_channel_caches = 4;
- adev->gfx.config.max_gprs = 256;
- adev->gfx.config.max_gs_threads = 32;
- adev->gfx.config.max_hw_contexts = 8;
-
- adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
- adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
- adev->gfx.config.sc_hiz_tile_fifo_size = 0x30;
- adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130;
- gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN;
- break;
- }
-
tmp = RREG32(mmGRBM_CNTL);
tmp = REG_SET_FIELD(tmp, GRBM_CNTL, READ_TIMEOUT, 0xff);
WREG32(mmGRBM_CNTL, tmp);
- mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP);
- adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG);
- mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg;
-
- adev->gfx.config.num_tile_pipes = adev->gfx.config.max_tile_pipes;
- adev->gfx.config.mem_max_burst_length_bytes = 256;
- if (adev->flags & AMD_IS_APU) {
- /* Get memory bank mapping mode. */
- tmp = RREG32(mmMC_FUS_DRAM0_BANK_ADDR_MAPPING);
- dimm00_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM0_BANK_ADDR_MAPPING, DIMM0ADDRMAP);
- dimm01_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM0_BANK_ADDR_MAPPING, DIMM1ADDRMAP);
-
- tmp = RREG32(mmMC_FUS_DRAM1_BANK_ADDR_MAPPING);
- dimm10_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM1_BANK_ADDR_MAPPING, DIMM0ADDRMAP);
- dimm11_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM1_BANK_ADDR_MAPPING, DIMM1ADDRMAP);
-
- /* Validate settings in case only one DIMM installed. */
- if ((dimm00_addr_map == 0) || (dimm00_addr_map == 3) || (dimm00_addr_map == 4) || (dimm00_addr_map > 12))
- dimm00_addr_map = 0;
- if ((dimm01_addr_map == 0) || (dimm01_addr_map == 3) || (dimm01_addr_map == 4) || (dimm01_addr_map > 12))
- dimm01_addr_map = 0;
- if ((dimm10_addr_map == 0) || (dimm10_addr_map == 3) || (dimm10_addr_map == 4) || (dimm10_addr_map > 12))
- dimm10_addr_map = 0;
- if ((dimm11_addr_map == 0) || (dimm11_addr_map == 3) || (dimm11_addr_map == 4) || (dimm11_addr_map > 12))
- dimm11_addr_map = 0;
-
- /* If DIMM Addr map is 8GB, ROW size should be 2KB. Otherwise 1KB. */
- /* If ROW size(DIMM1) != ROW size(DMIMM0), ROW size should be larger one. */
- if ((dimm00_addr_map == 11) || (dimm01_addr_map == 11) || (dimm10_addr_map == 11) || (dimm11_addr_map == 11))
- adev->gfx.config.mem_row_size_in_kb = 2;
- else
- adev->gfx.config.mem_row_size_in_kb = 1;
- } else {
- tmp = REG_GET_FIELD(mc_arb_ramcfg, MC_ARB_RAMCFG, NOOFCOLS);
- adev->gfx.config.mem_row_size_in_kb = (4 * (1 << (8 + tmp))) / 1024;
- if (adev->gfx.config.mem_row_size_in_kb > 4)
- adev->gfx.config.mem_row_size_in_kb = 4;
- }
-
- adev->gfx.config.shader_engine_tile_size = 32;
- adev->gfx.config.num_gpus = 1;
- adev->gfx.config.multi_gpu_tile_size = 64;
-
- /* fix up row size */
- switch (adev->gfx.config.mem_row_size_in_kb) {
- case 1:
- default:
- gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 0);
- break;
- case 2:
- gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 1);
- break;
- case 4:
- gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 2);
- break;
- }
- adev->gfx.config.gb_addr_config = gb_addr_config;
-
- WREG32(mmGB_ADDR_CONFIG, gb_addr_config);
- WREG32(mmHDP_ADDR_CONFIG, gb_addr_config);
- WREG32(mmDMIF_ADDR_CALC, gb_addr_config);
+ WREG32(mmGB_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
+ WREG32(mmHDP_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
+ WREG32(mmDMIF_ADDR_CALC, adev->gfx.config.gb_addr_config);
WREG32(mmSDMA0_TILING_CONFIG + SDMA0_REGISTER_OFFSET,
- gb_addr_config & 0x70);
+ adev->gfx.config.gb_addr_config & 0x70);
WREG32(mmSDMA0_TILING_CONFIG + SDMA1_REGISTER_OFFSET,
- gb_addr_config & 0x70);
- WREG32(mmUVD_UDEC_ADDR_CONFIG, gb_addr_config);
- WREG32(mmUVD_UDEC_DB_ADDR_CONFIG, gb_addr_config);
- WREG32(mmUVD_UDEC_DBW_ADDR_CONFIG, gb_addr_config);
+ adev->gfx.config.gb_addr_config & 0x70);
+ WREG32(mmUVD_UDEC_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
+ WREG32(mmUVD_UDEC_DB_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
+ WREG32(mmUVD_UDEC_DBW_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
gfx_v8_0_tiling_mode_table_init(adev);
if (i == 0) {
tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, DEFAULT_MTYPE, MTYPE_UC);
tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, APE1_MTYPE, MTYPE_UC);
- tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
+ tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
SH_MEM_ALIGNMENT_MODE_UNALIGNED);
WREG32(mmSH_MEM_CONFIG, tmp);
} else {
tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, DEFAULT_MTYPE, MTYPE_NC);
tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, APE1_MTYPE, MTYPE_NC);
- tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
+ tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE,
SH_MEM_ALIGNMENT_MODE_UNALIGNED);
WREG32(mmSH_MEM_CONFIG, tmp);
}
return 0;
}
+/**
+ * gmc_v8_0_set_fault_enable_default - update VM fault handling
+ *
+ * @adev: amdgpu_device pointer
+ * @value: true redirects VM faults to the default page
+ */
+static void gmc_v7_0_set_fault_enable_default(struct amdgpu_device *adev,
+ bool value)
+{
+ u32 tmp;
+
+ tmp = RREG32(mmVM_CONTEXT1_CNTL);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ VALID_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ READ_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ WREG32(mmVM_CONTEXT1_CNTL, tmp);
+}
+
/**
* gmc_v7_0_gart_enable - gart enable
*
tmp = RREG32(mmVM_CONTEXT1_CNTL);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, ENABLE_CONTEXT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_DEPTH, 1);
- tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
- tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
- tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
- tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
- tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
- tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_BLOCK_SIZE,
amdgpu_vm_block_size - 9);
WREG32(mmVM_CONTEXT1_CNTL, tmp);
+ if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
+ gmc_v7_0_set_fault_enable_default(adev, false);
+ else
+ gmc_v7_0_set_fault_enable_default(adev, true);
if (adev->asic_type == CHIP_KAVERI) {
tmp = RREG32(mmCHUB_CONTROL);
addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT);
+ /* reset addr and status */
+ WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1);
+
+ if (!addr && !status)
+ return 0;
+
+ if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST)
+ gmc_v7_0_set_fault_enable_default(adev, false);
+
dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
entry->src_id, entry->src_data);
dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
status);
gmc_v7_0_vm_decode_fault(adev, status, addr, mc_client);
- /* reset addr and status */
- WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1);
return 0;
}
return 0;
}
+/**
+ * gmc_v8_0_set_fault_enable_default - update VM fault handling
+ *
+ * @adev: amdgpu_device pointer
+ * @value: true redirects VM faults to the default page
+ */
+static void gmc_v8_0_set_fault_enable_default(struct amdgpu_device *adev,
+ bool value)
+{
+ u32 tmp;
+
+ tmp = RREG32(mmVM_CONTEXT1_CNTL);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ VALID_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ READ_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
+ EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, value);
+ WREG32(mmVM_CONTEXT1_CNTL, tmp);
+}
+
/**
* gmc_v8_0_gart_enable - gart enable
*
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_BLOCK_SIZE,
amdgpu_vm_block_size - 9);
WREG32(mmVM_CONTEXT1_CNTL, tmp);
+ if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
+ gmc_v8_0_set_fault_enable_default(adev, false);
+ else
+ gmc_v8_0_set_fault_enable_default(adev, true);
gmc_v8_0_gart_flush_gpu_tlb(adev, 0);
DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT);
+ /* reset addr and status */
+ WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1);
+
+ if (!addr && !status)
+ return 0;
+
+ if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST)
+ gmc_v8_0_set_fault_enable_default(adev, false);
+
dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
entry->src_id, entry->src_data);
dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
status);
gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client);
- /* reset addr and status */
- WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1);
return 0;
}
{
const char *chip_name;
char fw_name[30];
- int err, i;
+ int err = 0, i;
struct amdgpu_firmware_info *info = NULL;
const struct common_firmware_header *header = NULL;
const struct sdma_firmware_header_v1_0 *hdr;
default: BUG();
}
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
if (i == 0)
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name);
else
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name);
- err = request_firmware(&adev->sdma[i].fw, fw_name, adev->dev);
+ err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev);
if (err)
goto out;
- err = amdgpu_ucode_validate(adev->sdma[i].fw);
+ err = amdgpu_ucode_validate(adev->sdma.instance[i].fw);
if (err)
goto out;
- hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
- adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
- adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
- if (adev->sdma[i].feature_version >= 20)
- adev->sdma[i].burst_nop = true;
+ hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
+ adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
+ adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
+ if (adev->sdma.instance[i].feature_version >= 20)
+ adev->sdma.instance[i].burst_nop = true;
if (adev->firmware.smu_load) {
info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i;
- info->fw = adev->sdma[i].fw;
+ info->fw = adev->sdma.instance[i].fw;
header = (const struct common_firmware_header *)info->fw->data;
adev->firmware.fw_size +=
ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
printk(KERN_ERR
"sdma_v2_4: Failed to load firmware \"%s\"\n",
fw_name);
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
- release_firmware(adev->sdma[i].fw);
- adev->sdma[i].fw = NULL;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ release_firmware(adev->sdma.instance[i].fw);
+ adev->sdma.instance[i].fw = NULL;
}
}
return err;
static uint32_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1;
+ int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
u32 wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
return wptr;
static void sdma_v2_4_ring_set_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1;
+ int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], ring->wptr << 2);
}
static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
{
- struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ring);
+ struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring);
int i;
for (i = 0; i < count; i++)
{
u32 ref_and_mask = 0;
- if (ring == &ring->adev->sdma[0].ring)
+ if (ring == &ring->adev->sdma.instance[0].ring)
ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
else
ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
*/
static void sdma_v2_4_gfx_stop(struct amdgpu_device *adev)
{
- struct amdgpu_ring *sdma0 = &adev->sdma[0].ring;
- struct amdgpu_ring *sdma1 = &adev->sdma[1].ring;
+ struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring;
+ struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring;
u32 rb_cntl, ib_cntl;
int i;
(adev->mman.buffer_funcs_ring == sdma1))
amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size);
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i], rb_cntl);
sdma_v2_4_rlc_stop(adev);
}
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
f32_cntl = RREG32(mmSDMA0_F32_CNTL + sdma_offsets[i]);
if (enable)
f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, 0);
u32 wb_offset;
int i, j, r;
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
- ring = &adev->sdma[i].ring;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
wb_offset = (ring->rptr_offs * 4);
mutex_lock(&adev->srbm_mutex);
const __le32 *fw_data;
u32 fw_size;
int i, j;
- bool smc_loads_fw = false; /* XXX fix me */
-
- if (!adev->sdma[0].fw || !adev->sdma[1].fw)
- return -EINVAL;
/* halt the MEs */
sdma_v2_4_enable(adev, false);
- if (smc_loads_fw) {
- /* XXX query SMC for fw load complete */
- } else {
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
- hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
- amdgpu_ucode_print_sdma_hdr(&hdr->header);
- fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
- fw_data = (const __le32 *)
- (adev->sdma[i].fw->data +
- le32_to_cpu(hdr->header.ucode_array_offset_bytes));
- WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
- for (j = 0; j < fw_size; j++)
- WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
- WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma[i].fw_version);
- }
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ if (!adev->sdma.instance[i].fw)
+ return -EINVAL;
+ hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
+ amdgpu_ucode_print_sdma_hdr(&hdr->header);
+ fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
+ fw_data = (const __le32 *)
+ (adev->sdma.instance[i].fw->data +
+ le32_to_cpu(hdr->header.ucode_array_offset_bytes));
+ WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
+ for (j = 0; j < fw_size; j++)
+ WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
+ WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version);
}
return 0;
*/
static void sdma_v2_4_vm_pad_ib(struct amdgpu_ib *ib)
{
- struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ib->ring);
+ struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ib->ring);
u32 pad_count;
int i;
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ adev->sdma.num_instances = SDMA_MAX_INSTANCE;
+
sdma_v2_4_set_ring_funcs(adev);
sdma_v2_4_set_buffer_funcs(adev);
sdma_v2_4_set_vm_pte_funcs(adev);
static int sdma_v2_4_sw_init(void *handle)
{
struct amdgpu_ring *ring;
- int r;
+ int r, i;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* SDMA trap event */
- r = amdgpu_irq_add_id(adev, 224, &adev->sdma_trap_irq);
+ r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq);
if (r)
return r;
/* SDMA Privileged inst */
- r = amdgpu_irq_add_id(adev, 241, &adev->sdma_illegal_inst_irq);
+ r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq);
if (r)
return r;
/* SDMA Privileged inst */
- r = amdgpu_irq_add_id(adev, 247, &adev->sdma_illegal_inst_irq);
+ r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq);
if (r)
return r;
return r;
}
- ring = &adev->sdma[0].ring;
- ring->ring_obj = NULL;
- ring->use_doorbell = false;
-
- ring = &adev->sdma[1].ring;
- ring->ring_obj = NULL;
- ring->use_doorbell = false;
-
- ring = &adev->sdma[0].ring;
- sprintf(ring->name, "sdma0");
- r = amdgpu_ring_init(adev, ring, 256 * 1024,
- SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
- &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP0,
- AMDGPU_RING_TYPE_SDMA);
- if (r)
- return r;
-
- ring = &adev->sdma[1].ring;
- sprintf(ring->name, "sdma1");
- r = amdgpu_ring_init(adev, ring, 256 * 1024,
- SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
- &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP1,
- AMDGPU_RING_TYPE_SDMA);
- if (r)
- return r;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
+ ring->ring_obj = NULL;
+ ring->use_doorbell = false;
+ sprintf(ring->name, "sdma%d", i);
+ r = amdgpu_ring_init(adev, ring, 256 * 1024,
+ SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
+ &adev->sdma.trap_irq,
+ (i == 0) ?
+ AMDGPU_SDMA_IRQ_TRAP0 : AMDGPU_SDMA_IRQ_TRAP1,
+ AMDGPU_RING_TYPE_SDMA);
+ if (r)
+ return r;
+ }
return r;
}
static int sdma_v2_4_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int i;
- amdgpu_ring_fini(&adev->sdma[0].ring);
- amdgpu_ring_fini(&adev->sdma[1].ring);
+ for (i = 0; i < adev->sdma.num_instances; i++)
+ amdgpu_ring_fini(&adev->sdma.instance[i].ring);
return 0;
}
dev_info(adev->dev, "VI SDMA registers\n");
dev_info(adev->dev, " SRBM_STATUS2=0x%08X\n",
RREG32(mmSRBM_STATUS2));
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
dev_info(adev->dev, " SDMA%d_STATUS_REG=0x%08X\n",
i, RREG32(mmSDMA0_STATUS_REG + sdma_offsets[i]));
dev_info(adev->dev, " SDMA%d_F32_CNTL=0x%08X\n",
case 0:
switch (queue_id) {
case 0:
- amdgpu_fence_process(&adev->sdma[0].ring);
+ amdgpu_fence_process(&adev->sdma.instance[0].ring);
break;
case 1:
/* XXX compute */
case 1:
switch (queue_id) {
case 0:
- amdgpu_fence_process(&adev->sdma[1].ring);
+ amdgpu_fence_process(&adev->sdma.instance[1].ring);
break;
case 1:
/* XXX compute */
static void sdma_v2_4_set_ring_funcs(struct amdgpu_device *adev)
{
- adev->sdma[0].ring.funcs = &sdma_v2_4_ring_funcs;
- adev->sdma[1].ring.funcs = &sdma_v2_4_ring_funcs;
+ int i;
+
+ for (i = 0; i < adev->sdma.num_instances; i++)
+ adev->sdma.instance[i].ring.funcs = &sdma_v2_4_ring_funcs;
}
static const struct amdgpu_irq_src_funcs sdma_v2_4_trap_irq_funcs = {
static void sdma_v2_4_set_irq_funcs(struct amdgpu_device *adev)
{
- adev->sdma_trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
- adev->sdma_trap_irq.funcs = &sdma_v2_4_trap_irq_funcs;
- adev->sdma_illegal_inst_irq.funcs = &sdma_v2_4_illegal_inst_irq_funcs;
+ adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
+ adev->sdma.trap_irq.funcs = &sdma_v2_4_trap_irq_funcs;
+ adev->sdma.illegal_inst_irq.funcs = &sdma_v2_4_illegal_inst_irq_funcs;
}
/**
{
if (adev->mman.buffer_funcs == NULL) {
adev->mman.buffer_funcs = &sdma_v2_4_buffer_funcs;
- adev->mman.buffer_funcs_ring = &adev->sdma[0].ring;
+ adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
}
}
{
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &sdma_v2_4_vm_pte_funcs;
- adev->vm_manager.vm_pte_funcs_ring = &adev->sdma[0].ring;
+ adev->vm_manager.vm_pte_funcs_ring = &adev->sdma.instance[0].ring;
adev->vm_manager.vm_pte_funcs_ring->is_pte_ring = true;
}
}
{
const char *chip_name;
char fw_name[30];
- int err, i;
+ int err = 0, i;
struct amdgpu_firmware_info *info = NULL;
const struct common_firmware_header *header = NULL;
const struct sdma_firmware_header_v1_0 *hdr;
default: BUG();
}
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
if (i == 0)
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name);
else
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name);
- err = request_firmware(&adev->sdma[i].fw, fw_name, adev->dev);
+ err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev);
if (err)
goto out;
- err = amdgpu_ucode_validate(adev->sdma[i].fw);
+ err = amdgpu_ucode_validate(adev->sdma.instance[i].fw);
if (err)
goto out;
- hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
- adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
- adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
- if (adev->sdma[i].feature_version >= 20)
- adev->sdma[i].burst_nop = true;
+ hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
+ adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
+ adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
+ if (adev->sdma.instance[i].feature_version >= 20)
+ adev->sdma.instance[i].burst_nop = true;
if (adev->firmware.smu_load) {
info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i;
- info->fw = adev->sdma[i].fw;
+ info->fw = adev->sdma.instance[i].fw;
header = (const struct common_firmware_header *)info->fw->data;
adev->firmware.fw_size +=
ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
printk(KERN_ERR
"sdma_v3_0: Failed to load firmware \"%s\"\n",
fw_name);
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
- release_firmware(adev->sdma[i].fw);
- adev->sdma[i].fw = NULL;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ release_firmware(adev->sdma.instance[i].fw);
+ adev->sdma.instance[i].fw = NULL;
}
}
return err;
/* XXX check if swapping is necessary on BE */
wptr = ring->adev->wb.wb[ring->wptr_offs] >> 2;
} else {
- int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1;
+ int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
}
adev->wb.wb[ring->wptr_offs] = ring->wptr << 2;
WDOORBELL32(ring->doorbell_index, ring->wptr << 2);
} else {
- int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1;
+ int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], ring->wptr << 2);
}
static void sdma_v3_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
{
- struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ring);
+ struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring);
int i;
for (i = 0; i < count; i++)
{
u32 ref_and_mask = 0;
- if (ring == &ring->adev->sdma[0].ring)
+ if (ring == &ring->adev->sdma.instance[0].ring)
ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
else
ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
*/
static void sdma_v3_0_gfx_stop(struct amdgpu_device *adev)
{
- struct amdgpu_ring *sdma0 = &adev->sdma[0].ring;
- struct amdgpu_ring *sdma1 = &adev->sdma[1].ring;
+ struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring;
+ struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring;
u32 rb_cntl, ib_cntl;
int i;
(adev->mman.buffer_funcs_ring == sdma1))
amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size);
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i], rb_cntl);
u32 f32_cntl;
int i;
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
f32_cntl = RREG32(mmSDMA0_CNTL + sdma_offsets[i]);
if (enable)
f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
sdma_v3_0_rlc_stop(adev);
}
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
f32_cntl = RREG32(mmSDMA0_F32_CNTL + sdma_offsets[i]);
if (enable)
f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, 0);
u32 doorbell;
int i, j, r;
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
- ring = &adev->sdma[i].ring;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
wb_offset = (ring->rptr_offs * 4);
mutex_lock(&adev->srbm_mutex);
u32 fw_size;
int i, j;
- if (!adev->sdma[0].fw || !adev->sdma[1].fw)
- return -EINVAL;
-
/* halt the MEs */
sdma_v3_0_enable(adev, false);
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
- hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ if (!adev->sdma.instance[i].fw)
+ return -EINVAL;
+ hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
amdgpu_ucode_print_sdma_hdr(&hdr->header);
fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
fw_data = (const __le32 *)
- (adev->sdma[i].fw->data +
+ (adev->sdma.instance[i].fw->data +
le32_to_cpu(hdr->header.ucode_array_offset_bytes));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
for (j = 0; j < fw_size; j++)
WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
- WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma[i].fw_version);
+ WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version);
}
return 0;
*/
static int sdma_v3_0_start(struct amdgpu_device *adev)
{
- int r;
+ int r, i;
if (!adev->firmware.smu_load) {
r = sdma_v3_0_load_microcode(adev);
if (r)
return r;
} else {
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- AMDGPU_UCODE_ID_SDMA0);
- if (r)
- return -EINVAL;
- r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
- AMDGPU_UCODE_ID_SDMA1);
- if (r)
- return -EINVAL;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
+ (i == 0) ?
+ AMDGPU_UCODE_ID_SDMA0 :
+ AMDGPU_UCODE_ID_SDMA1);
+ if (r)
+ return -EINVAL;
+ }
}
/* unhalt the MEs */
*/
static void sdma_v3_0_vm_pad_ib(struct amdgpu_ib *ib)
{
- struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ib->ring);
+ struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ib->ring);
u32 pad_count;
int i;
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ switch (adev->asic_type) {
+ default:
+ adev->sdma.num_instances = SDMA_MAX_INSTANCE;
+ break;
+ }
+
sdma_v3_0_set_ring_funcs(adev);
sdma_v3_0_set_buffer_funcs(adev);
sdma_v3_0_set_vm_pte_funcs(adev);
static int sdma_v3_0_sw_init(void *handle)
{
struct amdgpu_ring *ring;
- int r;
+ int r, i;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* SDMA trap event */
- r = amdgpu_irq_add_id(adev, 224, &adev->sdma_trap_irq);
+ r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq);
if (r)
return r;
/* SDMA Privileged inst */
- r = amdgpu_irq_add_id(adev, 241, &adev->sdma_illegal_inst_irq);
+ r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq);
if (r)
return r;
/* SDMA Privileged inst */
- r = amdgpu_irq_add_id(adev, 247, &adev->sdma_illegal_inst_irq);
+ r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq);
if (r)
return r;
return r;
}
- ring = &adev->sdma[0].ring;
- ring->ring_obj = NULL;
- ring->use_doorbell = true;
- ring->doorbell_index = AMDGPU_DOORBELL_sDMA_ENGINE0;
-
- ring = &adev->sdma[1].ring;
- ring->ring_obj = NULL;
- ring->use_doorbell = true;
- ring->doorbell_index = AMDGPU_DOORBELL_sDMA_ENGINE1;
-
- ring = &adev->sdma[0].ring;
- sprintf(ring->name, "sdma0");
- r = amdgpu_ring_init(adev, ring, 256 * 1024,
- SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
- &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP0,
- AMDGPU_RING_TYPE_SDMA);
- if (r)
- return r;
-
- ring = &adev->sdma[1].ring;
- sprintf(ring->name, "sdma1");
- r = amdgpu_ring_init(adev, ring, 256 * 1024,
- SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
- &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP1,
- AMDGPU_RING_TYPE_SDMA);
- if (r)
- return r;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ ring = &adev->sdma.instance[i].ring;
+ ring->ring_obj = NULL;
+ ring->use_doorbell = true;
+ ring->doorbell_index = (i == 0) ?
+ AMDGPU_DOORBELL_sDMA_ENGINE0 : AMDGPU_DOORBELL_sDMA_ENGINE1;
+
+ sprintf(ring->name, "sdma%d", i);
+ r = amdgpu_ring_init(adev, ring, 256 * 1024,
+ SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
+ &adev->sdma.trap_irq,
+ (i == 0) ?
+ AMDGPU_SDMA_IRQ_TRAP0 : AMDGPU_SDMA_IRQ_TRAP1,
+ AMDGPU_RING_TYPE_SDMA);
+ if (r)
+ return r;
+ }
return r;
}
static int sdma_v3_0_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int i;
- amdgpu_ring_fini(&adev->sdma[0].ring);
- amdgpu_ring_fini(&adev->sdma[1].ring);
+ for (i = 0; i < adev->sdma.num_instances; i++)
+ amdgpu_ring_fini(&adev->sdma.instance[i].ring);
return 0;
}
dev_info(adev->dev, "VI SDMA registers\n");
dev_info(adev->dev, " SRBM_STATUS2=0x%08X\n",
RREG32(mmSRBM_STATUS2));
- for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++) {
dev_info(adev->dev, " SDMA%d_STATUS_REG=0x%08X\n",
i, RREG32(mmSDMA0_STATUS_REG + sdma_offsets[i]));
dev_info(adev->dev, " SDMA%d_F32_CNTL=0x%08X\n",
case 0:
switch (queue_id) {
case 0:
- amdgpu_fence_process(&adev->sdma[0].ring);
+ amdgpu_fence_process(&adev->sdma.instance[0].ring);
break;
case 1:
/* XXX compute */
case 1:
switch (queue_id) {
case 0:
- amdgpu_fence_process(&adev->sdma[1].ring);
+ amdgpu_fence_process(&adev->sdma.instance[1].ring);
break;
case 1:
/* XXX compute */
static void sdma_v3_0_set_ring_funcs(struct amdgpu_device *adev)
{
- adev->sdma[0].ring.funcs = &sdma_v3_0_ring_funcs;
- adev->sdma[1].ring.funcs = &sdma_v3_0_ring_funcs;
+ int i;
+
+ for (i = 0; i < adev->sdma.num_instances; i++)
+ adev->sdma.instance[i].ring.funcs = &sdma_v3_0_ring_funcs;
}
static const struct amdgpu_irq_src_funcs sdma_v3_0_trap_irq_funcs = {
static void sdma_v3_0_set_irq_funcs(struct amdgpu_device *adev)
{
- adev->sdma_trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
- adev->sdma_trap_irq.funcs = &sdma_v3_0_trap_irq_funcs;
- adev->sdma_illegal_inst_irq.funcs = &sdma_v3_0_illegal_inst_irq_funcs;
+ adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
+ adev->sdma.trap_irq.funcs = &sdma_v3_0_trap_irq_funcs;
+ adev->sdma.illegal_inst_irq.funcs = &sdma_v3_0_illegal_inst_irq_funcs;
}
/**
{
if (adev->mman.buffer_funcs == NULL) {
adev->mman.buffer_funcs = &sdma_v3_0_buffer_funcs;
- adev->mman.buffer_funcs_ring = &adev->sdma[0].ring;
+ adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
}
}
{
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &sdma_v3_0_vm_pte_funcs;
- adev->vm_manager.vm_pte_funcs_ring = &adev->sdma[0].ring;
+ adev->vm_manager.vm_pte_funcs_ring = &adev->sdma.instance[0].ring;
adev->vm_manager.vm_pte_funcs_ring->is_pte_ring = true;
}
}
struct amd_sched_fence *s_fence =
container_of(cb, struct amd_sched_fence, cb);
struct amd_gpu_scheduler *sched = s_fence->sched;
+ unsigned long flags;
atomic_dec(&sched->hw_rq_count);
amd_sched_fence_signal(s_fence);
+ if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
+ cancel_delayed_work_sync(&s_fence->dwork);
+ spin_lock_irqsave(&sched->fence_list_lock, flags);
+ list_del_init(&s_fence->list);
+ spin_unlock_irqrestore(&sched->fence_list_lock, flags);
+ }
fence_put(&s_fence->base);
wake_up_interruptible(&sched->wake_up_worker);
}
+static void amd_sched_fence_work_func(struct work_struct *work)
+{
+ struct amd_sched_fence *s_fence =
+ container_of(work, struct amd_sched_fence, dwork.work);
+ struct amd_gpu_scheduler *sched = s_fence->sched;
+ struct amd_sched_fence *entity, *tmp;
+ unsigned long flags;
+
+ DRM_ERROR("[%s] scheduler is timeout!\n", sched->name);
+
+ /* Clean all pending fences */
+ spin_lock_irqsave(&sched->fence_list_lock, flags);
+ list_for_each_entry_safe(entity, tmp, &sched->fence_list, list) {
+ DRM_ERROR(" fence no %d\n", entity->base.seqno);
+ cancel_delayed_work(&entity->dwork);
+ list_del_init(&entity->list);
+ fence_put(&entity->base);
+ }
+ spin_unlock_irqrestore(&sched->fence_list_lock, flags);
+}
+
static int amd_sched_main(void *param)
{
struct sched_param sparam = {.sched_priority = 1};
struct amd_gpu_scheduler *sched = (struct amd_gpu_scheduler *)param;
int r, count;
+ spin_lock_init(&sched->fence_list_lock);
+ INIT_LIST_HEAD(&sched->fence_list);
sched_setscheduler(current, SCHED_FIFO, &sparam);
while (!kthread_should_stop()) {
struct amd_sched_fence *s_fence;
struct amd_sched_job *sched_job;
struct fence *fence;
+ unsigned long flags;
wait_event_interruptible(sched->wake_up_worker,
kthread_should_stop() ||
entity = sched_job->s_entity;
s_fence = sched_job->s_fence;
+
+ if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
+ INIT_DELAYED_WORK(&s_fence->dwork, amd_sched_fence_work_func);
+ schedule_delayed_work(&s_fence->dwork, sched->timeout);
+ spin_lock_irqsave(&sched->fence_list_lock, flags);
+ list_add_tail(&s_fence->list, &sched->fence_list);
+ spin_unlock_irqrestore(&sched->fence_list_lock, flags);
+ }
+
atomic_inc(&sched->hw_rq_count);
fence = sched->ops->run_job(sched_job);
if (fence) {
*/
int amd_sched_init(struct amd_gpu_scheduler *sched,
struct amd_sched_backend_ops *ops,
- unsigned hw_submission, const char *name)
+ unsigned hw_submission, long timeout, const char *name)
{
sched->ops = ops;
sched->hw_submission_limit = hw_submission;
sched->name = name;
+ sched->timeout = timeout;
amd_sched_rq_init(&sched->sched_rq);
amd_sched_rq_init(&sched->kernel_rq);
struct amd_gpu_scheduler *sched;
spinlock_t lock;
void *owner;
+ struct delayed_work dwork;
+ struct list_head list;
};
struct amd_sched_job {
struct amd_gpu_scheduler {
struct amd_sched_backend_ops *ops;
uint32_t hw_submission_limit;
+ long timeout;
const char *name;
struct amd_sched_rq sched_rq;
struct amd_sched_rq kernel_rq;
wait_queue_head_t wake_up_worker;
wait_queue_head_t job_scheduled;
atomic_t hw_rq_count;
+ struct list_head fence_list;
+ spinlock_t fence_list_lock;
struct task_struct *thread;
};
int amd_sched_init(struct amd_gpu_scheduler *sched,
struct amd_sched_backend_ops *ops,
- uint32_t hw_submission, const char *name);
+ uint32_t hw_submission, long timeout, const char *name);
void amd_sched_fini(struct amd_gpu_scheduler *sched);
int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
This driver provides no built-in acceleration; acceleration is
performed by other IP found on the SoC. This driver provides
kernel mode setting and buffer management to userspace.
-
-config DRM_ARMADA_TDA1998X
- bool "Support TDA1998X HDMI output"
- depends on DRM_ARMADA != n
- depends on I2C && DRM_I2C_NXP_TDA998X = y
- default y
- help
- Support the TDA1998x HDMI output device found on the Solid-Run
- CuBox.
armada-y := armada_crtc.o armada_drv.o armada_fb.o armada_fbdev.o \
- armada_gem.o armada_output.o armada_overlay.o \
- armada_slave.o
+ armada_gem.o armada_overlay.o
armada-y += armada_510.o
armada-$(CONFIG_DEBUG_FS) += armada_debugfs.o
#include "armada_hw.h"
struct armada_frame_work {
+ struct armada_plane_work work;
struct drm_pending_vblank_event *event;
struct armada_regs regs[4];
struct drm_framebuffer *old_fb;
CSC_RGB_STUDIO = 2,
};
+static const uint32_t armada_primary_formats[] = {
+ DRM_FORMAT_UYVY,
+ DRM_FORMAT_YUYV,
+ DRM_FORMAT_VYUY,
+ DRM_FORMAT_YVYU,
+ DRM_FORMAT_ARGB8888,
+ DRM_FORMAT_ABGR8888,
+ DRM_FORMAT_XRGB8888,
+ DRM_FORMAT_XBGR8888,
+ DRM_FORMAT_RGB888,
+ DRM_FORMAT_BGR888,
+ DRM_FORMAT_ARGB1555,
+ DRM_FORMAT_ABGR1555,
+ DRM_FORMAT_RGB565,
+ DRM_FORMAT_BGR565,
+};
+
/*
* A note about interlacing. Let's consider HDMI 1920x1080i.
* The timing parameters we have from X are:
return i;
}
-static int armada_drm_crtc_queue_frame_work(struct armada_crtc *dcrtc,
- struct armada_frame_work *work)
+static void armada_drm_plane_work_run(struct armada_crtc *dcrtc,
+ struct armada_plane *plane)
+{
+ struct armada_plane_work *work = xchg(&plane->work, NULL);
+
+ /* Handle any pending frame work. */
+ if (work) {
+ work->fn(dcrtc, plane, work);
+ drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
+ }
+
+ wake_up(&plane->frame_wait);
+}
+
+int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
+ struct armada_plane *plane, struct armada_plane_work *work)
{
- struct drm_device *dev = dcrtc->crtc.dev;
- unsigned long flags;
int ret;
- ret = drm_vblank_get(dev, dcrtc->num);
+ ret = drm_vblank_get(dcrtc->crtc.dev, dcrtc->num);
if (ret) {
DRM_ERROR("failed to acquire vblank counter\n");
return ret;
}
- spin_lock_irqsave(&dev->event_lock, flags);
- if (!dcrtc->frame_work)
- dcrtc->frame_work = work;
- else
- ret = -EBUSY;
- spin_unlock_irqrestore(&dev->event_lock, flags);
-
+ ret = cmpxchg(&plane->work, NULL, work) ? -EBUSY : 0;
if (ret)
- drm_vblank_put(dev, dcrtc->num);
+ drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
return ret;
}
-static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc)
+int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout)
{
- struct drm_device *dev = dcrtc->crtc.dev;
- struct armada_frame_work *work = dcrtc->frame_work;
+ return wait_event_timeout(plane->frame_wait, !plane->work, timeout);
+}
- dcrtc->frame_work = NULL;
+struct armada_plane_work *armada_drm_plane_work_cancel(
+ struct armada_crtc *dcrtc, struct armada_plane *plane)
+{
+ struct armada_plane_work *work = xchg(&plane->work, NULL);
- armada_drm_crtc_update_regs(dcrtc, work->regs);
+ if (work)
+ drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
- if (work->event)
- drm_send_vblank_event(dev, dcrtc->num, work->event);
+ return work;
+}
- drm_vblank_put(dev, dcrtc->num);
+static int armada_drm_crtc_queue_frame_work(struct armada_crtc *dcrtc,
+ struct armada_frame_work *work)
+{
+ struct armada_plane *plane = drm_to_armada_plane(dcrtc->crtc.primary);
+
+ return armada_drm_plane_work_queue(dcrtc, plane, &work->work);
+}
+
+static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc,
+ struct armada_plane *plane, struct armada_plane_work *work)
+{
+ struct armada_frame_work *fwork = container_of(work, struct armada_frame_work, work);
+ struct drm_device *dev = dcrtc->crtc.dev;
+ unsigned long flags;
+
+ spin_lock_irqsave(&dcrtc->irq_lock, flags);
+ armada_drm_crtc_update_regs(dcrtc, fwork->regs);
+ spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
+
+ if (fwork->event) {
+ spin_lock_irqsave(&dev->event_lock, flags);
+ drm_send_vblank_event(dev, dcrtc->num, fwork->event);
+ spin_unlock_irqrestore(&dev->event_lock, flags);
+ }
/* Finally, queue the process-half of the cleanup. */
- __armada_drm_queue_unref_work(dcrtc->crtc.dev, work->old_fb);
- kfree(work);
+ __armada_drm_queue_unref_work(dcrtc->crtc.dev, fwork->old_fb);
+ kfree(fwork);
}
static void armada_drm_crtc_finish_fb(struct armada_crtc *dcrtc,
work = kmalloc(sizeof(*work), GFP_KERNEL);
if (work) {
int i = 0;
+ work->work.fn = armada_drm_crtc_complete_frame_work;
work->event = NULL;
work->old_fb = fb;
armada_reg_queue_end(work->regs, i);
static void armada_drm_vblank_off(struct armada_crtc *dcrtc)
{
- struct drm_device *dev = dcrtc->crtc.dev;
+ struct armada_plane *plane = drm_to_armada_plane(dcrtc->crtc.primary);
/*
* Tell the DRM core that vblank IRQs aren't going to happen for
* a while. This cleans up any pending vblank events for us.
*/
drm_crtc_vblank_off(&dcrtc->crtc);
-
- /* Handle any pending flip event. */
- spin_lock_irq(&dev->event_lock);
- if (dcrtc->frame_work)
- armada_drm_crtc_complete_frame_work(dcrtc);
- spin_unlock_irq(&dev->event_lock);
+ armada_drm_plane_work_run(dcrtc, plane);
}
void armada_drm_crtc_gamma_set(struct drm_crtc *crtc, u16 r, u16 g, u16 b,
if (dcrtc->dpms != dpms) {
dcrtc->dpms = dpms;
+ if (!IS_ERR(dcrtc->clk) && !dpms_blanked(dpms))
+ WARN_ON(clk_prepare_enable(dcrtc->clk));
armada_drm_crtc_update(dcrtc);
+ if (!IS_ERR(dcrtc->clk) && dpms_blanked(dpms))
+ clk_disable_unprepare(dcrtc->clk);
if (dpms_blanked(dpms))
armada_drm_vblank_off(dcrtc);
else
/*
* If we have an overlay plane associated with this CRTC, disable
* it before the modeset to avoid its coordinates being outside
- * the new mode parameters. DRM doesn't provide help with this.
+ * the new mode parameters.
*/
plane = dcrtc->plane;
- if (plane) {
- struct drm_framebuffer *fb = plane->fb;
-
- plane->funcs->disable_plane(plane);
- plane->fb = NULL;
- plane->crtc = NULL;
- drm_framebuffer_unreference(fb);
- }
+ if (plane)
+ drm_plane_force_disable(plane);
}
/* The mode_config.mutex will be held for this call */
static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
{
- struct armada_vbl_event *e, *n;
void __iomem *base = dcrtc->base;
+ struct drm_plane *ovl_plane;
if (stat & DMA_FF_UNDERFLOW)
DRM_ERROR("video underflow on crtc %u\n", dcrtc->num);
drm_handle_vblank(dcrtc->crtc.dev, dcrtc->num);
spin_lock(&dcrtc->irq_lock);
-
- list_for_each_entry_safe(e, n, &dcrtc->vbl_list, node) {
- list_del_init(&e->node);
- drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
- e->fn(dcrtc, e->data);
+ ovl_plane = dcrtc->plane;
+ if (ovl_plane) {
+ struct armada_plane *plane = drm_to_armada_plane(ovl_plane);
+ armada_drm_plane_work_run(dcrtc, plane);
}
if (stat & GRA_FRAME_IRQ && dcrtc->interlaced) {
spin_unlock(&dcrtc->irq_lock);
if (stat & GRA_FRAME_IRQ) {
- struct drm_device *dev = dcrtc->crtc.dev;
-
- spin_lock(&dev->event_lock);
- if (dcrtc->frame_work)
- armada_drm_crtc_complete_frame_work(dcrtc);
- spin_unlock(&dev->event_lock);
-
- wake_up(&dcrtc->frame_wait);
+ struct armada_plane *plane = drm_to_armada_plane(dcrtc->crtc.primary);
+ armada_drm_plane_work_run(dcrtc, plane);
}
}
adj->crtc_vtotal, tm, bm);
/* Wait for pending flips to complete */
- wait_event(dcrtc->frame_wait, !dcrtc->frame_work);
+ armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
+ MAX_SCHEDULE_TIMEOUT);
drm_crtc_vblank_off(crtc);
writel_relaxed(val, dcrtc->base + LCD_SPU_DUMB_CTRL);
}
+ /*
+ * If we are blanked, we would have disabled the clock. Re-enable
+ * it so that compute_clock() does the right thing.
+ */
+ if (!IS_ERR(dcrtc->clk) && dpms_blanked(dcrtc->dpms))
+ WARN_ON(clk_prepare_enable(dcrtc->clk));
+
/* Now compute the divider for real */
dcrtc->variant->compute_clock(dcrtc, adj, &sclk);
armada_reg_queue_end(regs, i);
/* Wait for pending flips to complete */
- wait_event(dcrtc->frame_wait, !dcrtc->frame_work);
+ armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
+ MAX_SCHEDULE_TIMEOUT);
/* Take a reference to the new fb as we're using it */
drm_framebuffer_reference(crtc->primary->fb);
return 0;
}
+void armada_drm_crtc_plane_disable(struct armada_crtc *dcrtc,
+ struct drm_plane *plane)
+{
+ u32 sram_para1, dma_ctrl0_mask;
+
+ /*
+ * Drop our reference on any framebuffer attached to this plane.
+ * We don't need to NULL this out as drm_plane_force_disable(),
+ * and __setplane_internal() will do so for an overlay plane, and
+ * __drm_helper_disable_unused_functions() will do so for the
+ * primary plane.
+ */
+ if (plane->fb)
+ drm_framebuffer_unreference(plane->fb);
+
+ /* Power down the Y/U/V FIFOs */
+ sram_para1 = CFG_PDWN16x66 | CFG_PDWN32x66;
+
+ /* Power down most RAMs and FIFOs if this is the primary plane */
+ if (plane->type == DRM_PLANE_TYPE_PRIMARY) {
+ sram_para1 |= CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 |
+ CFG_PDWN32x32 | CFG_PDWN64x66;
+ dma_ctrl0_mask = CFG_GRA_ENA;
+ } else {
+ dma_ctrl0_mask = CFG_DMA_ENA;
+ }
+
+ spin_lock_irq(&dcrtc->irq_lock);
+ armada_updatel(0, dma_ctrl0_mask, dcrtc->base + LCD_SPU_DMA_CTRL0);
+ spin_unlock_irq(&dcrtc->irq_lock);
+
+ armada_updatel(sram_para1, 0, dcrtc->base + LCD_SPU_SRAM_PARA1);
+}
+
/* The mode_config.mutex will be held for this call */
static void armada_drm_crtc_disable(struct drm_crtc *crtc)
{
struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
armada_drm_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
- armada_drm_crtc_finish_fb(dcrtc, crtc->primary->fb, true);
-
- /* Power down most RAMs and FIFOs */
- writel_relaxed(CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 |
- CFG_PDWN32x32 | CFG_PDWN16x66 | CFG_PDWN32x66 |
- CFG_PDWN64x66, dcrtc->base + LCD_SPU_SRAM_PARA1);
+ armada_drm_crtc_plane_disable(dcrtc, crtc->primary);
}
static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = {
{
struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
struct armada_frame_work *work;
- struct drm_device *dev = crtc->dev;
- unsigned long flags;
unsigned i;
int ret;
if (!work)
return -ENOMEM;
+ work->work.fn = armada_drm_crtc_complete_frame_work;
work->event = event;
work->old_fb = dcrtc->crtc.primary->fb;
* Finally, if the display is blanked, we won't receive an
* interrupt, so complete it now.
*/
- if (dpms_blanked(dcrtc->dpms)) {
- spin_lock_irqsave(&dev->event_lock, flags);
- if (dcrtc->frame_work)
- armada_drm_crtc_complete_frame_work(dcrtc);
- spin_unlock_irqrestore(&dev->event_lock, flags);
- }
+ if (dpms_blanked(dcrtc->dpms))
+ armada_drm_plane_work_run(dcrtc, drm_to_armada_plane(dcrtc->crtc.primary));
return 0;
}
.set_property = armada_drm_crtc_set_property,
};
+static const struct drm_plane_funcs armada_primary_plane_funcs = {
+ .update_plane = drm_primary_helper_update,
+ .disable_plane = drm_primary_helper_disable,
+ .destroy = drm_primary_helper_destroy,
+};
+
+int armada_drm_plane_init(struct armada_plane *plane)
+{
+ init_waitqueue_head(&plane->frame_wait);
+
+ return 0;
+}
+
static struct drm_prop_enum_list armada_drm_csc_yuv_enum_list[] = {
{ CSC_AUTO, "Auto" },
{ CSC_YUV_CCIR601, "CCIR601" },
return 0;
}
-int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
+static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
struct resource *res, int irq, const struct armada_variant *variant,
struct device_node *port)
{
struct armada_private *priv = drm->dev_private;
struct armada_crtc *dcrtc;
+ struct armada_plane *primary;
void __iomem *base;
int ret;
dcrtc->spu_iopad_ctrl = CFG_VSCALE_LN_EN | CFG_IOPAD_DUMB24;
spin_lock_init(&dcrtc->irq_lock);
dcrtc->irq_ena = CLEAN_SPU_IRQ_ISR;
- INIT_LIST_HEAD(&dcrtc->vbl_list);
- init_waitqueue_head(&dcrtc->frame_wait);
/* Initialize some registers which we don't otherwise set */
writel_relaxed(0x00000001, dcrtc->base + LCD_CFG_SCLK_DIV);
priv->dcrtc[dcrtc->num] = dcrtc;
dcrtc->crtc.port = port;
- drm_crtc_init(drm, &dcrtc->crtc, &armada_crtc_funcs);
+
+ primary = kzalloc(sizeof(*primary), GFP_KERNEL);
+ if (!primary)
+ return -ENOMEM;
+
+ ret = armada_drm_plane_init(primary);
+ if (ret) {
+ kfree(primary);
+ return ret;
+ }
+
+ ret = drm_universal_plane_init(drm, &primary->base, 0,
+ &armada_primary_plane_funcs,
+ armada_primary_formats,
+ ARRAY_SIZE(armada_primary_formats),
+ DRM_PLANE_TYPE_PRIMARY);
+ if (ret) {
+ kfree(primary);
+ return ret;
+ }
+
+ ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, &primary->base, NULL,
+ &armada_crtc_funcs);
+ if (ret)
+ goto err_crtc_init;
+
drm_crtc_helper_add(&dcrtc->crtc, &armada_crtc_helper_funcs);
drm_object_attach_property(&dcrtc->crtc.base, priv->csc_yuv_prop,
dcrtc->csc_rgb_mode);
return armada_overlay_plane_create(drm, 1 << dcrtc->num);
+
+err_crtc_init:
+ primary->base.funcs->destroy(&primary->base);
+ return ret;
}
static int
#define armada_reg_queue_end(_r, _i) \
armada_reg_queue_mod(_r, _i, 0, 0, ~0)
-struct armada_frame_work;
+struct armada_crtc;
+struct armada_plane;
struct armada_variant;
+struct armada_plane_work {
+ void (*fn)(struct armada_crtc *,
+ struct armada_plane *,
+ struct armada_plane_work *);
+};
+
+struct armada_plane {
+ struct drm_plane base;
+ wait_queue_head_t frame_wait;
+ struct armada_plane_work *work;
+};
+#define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
+
+int armada_drm_plane_init(struct armada_plane *plane);
+int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
+ struct armada_plane *plane, struct armada_plane_work *work);
+int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout);
+struct armada_plane_work *armada_drm_plane_work_cancel(
+ struct armada_crtc *dcrtc, struct armada_plane *plane);
+
struct armada_crtc {
struct drm_crtc crtc;
const struct armada_variant *variant;
uint32_t dumb_ctrl;
uint32_t spu_iopad_ctrl;
- wait_queue_head_t frame_wait;
- struct armada_frame_work *frame_work;
-
spinlock_t irq_lock;
uint32_t irq_ena;
- struct list_head vbl_list;
};
#define drm_to_armada_crtc(c) container_of(c, struct armada_crtc, crtc)
-struct device_node;
-int armada_drm_crtc_create(struct drm_device *, struct device *,
- struct resource *, int, const struct armada_variant *,
- struct device_node *);
void armada_drm_crtc_gamma_set(struct drm_crtc *, u16, u16, u16, int);
void armada_drm_crtc_gamma_get(struct drm_crtc *, u16 *, u16 *, u16 *, int);
void armada_drm_crtc_disable_irq(struct armada_crtc *, u32);
void armada_drm_crtc_enable_irq(struct armada_crtc *, u32);
void armada_drm_crtc_update_regs(struct armada_crtc *, struct armada_regs *);
+void armada_drm_crtc_plane_disable(struct armada_crtc *dcrtc,
+ struct drm_plane *plane);
+
extern struct platform_driver armada_lcd_platform_driver;
#endif
return ALIGN(pitch, 128);
}
-struct armada_vbl_event {
- struct list_head node;
- void *data;
- void (*fn)(struct armada_crtc *, void *);
-};
-void armada_drm_vbl_event_add(struct armada_crtc *,
- struct armada_vbl_event *);
-void armada_drm_vbl_event_remove(struct armada_crtc *,
- struct armada_vbl_event *);
-#define armada_drm_vbl_event_init(_e, _f, _d) do { \
- struct armada_vbl_event *__e = _e; \
- INIT_LIST_HEAD(&__e->node); \
- __e->data = _d; \
- __e->fn = _f; \
-} while (0)
-
struct armada_private;
#include <drm/armada_drm.h>
#include "armada_ioctlP.h"
-#ifdef CONFIG_DRM_ARMADA_TDA1998X
-#include <drm/i2c/tda998x.h>
-#include "armada_slave.h"
-
-static struct tda998x_encoder_params params = {
- /* With 0x24, there is no translation between vp_out and int_vp
- FB LCD out Pins VIP Int Vp
- R:23:16 R:7:0 VPC7:0 7:0 7:0[R]
- G:15:8 G:15:8 VPB7:0 23:16 23:16[G]
- B:7:0 B:23:16 VPA7:0 15:8 15:8[B]
- */
- .swap_a = 2,
- .swap_b = 3,
- .swap_c = 4,
- .swap_d = 5,
- .swap_e = 0,
- .swap_f = 1,
- .audio_cfg = BIT(2),
- .audio_frame[1] = 1,
- .audio_format = AFMT_SPDIF,
- .audio_sample_rate = 44100,
-};
-
-static const struct armada_drm_slave_config tda19988_config = {
- .i2c_adapter_id = 0,
- .crtcs = 1 << 0, /* Only LCD0 at the moment */
- .polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT,
- .interlace_allowed = true,
- .info = {
- .type = "tda998x",
- .addr = 0x70,
- .platform_data = ¶ms,
- },
-};
-#endif
-
-static bool is_componentized(struct device *dev)
-{
- return dev->of_node || dev->platform_data;
-}
-
static void armada_drm_unref_work(struct work_struct *work)
{
struct armada_private *priv =
static int armada_drm_load(struct drm_device *dev, unsigned long flags)
{
- const struct platform_device_id *id;
- const struct armada_variant *variant;
struct armada_private *priv;
- struct resource *res[ARRAY_SIZE(priv->dcrtc)];
struct resource *mem = NULL;
- int ret, n, i;
-
- memset(res, 0, sizeof(res));
+ int ret, n;
- for (n = i = 0; ; n++) {
+ for (n = 0; ; n++) {
struct resource *r = platform_get_resource(dev->platformdev,
IORESOURCE_MEM, n);
if (!r)
/* Resources above 64K are graphics memory */
if (resource_size(r) > SZ_64K)
mem = r;
- else if (i < ARRAY_SIZE(priv->dcrtc))
- res[i++] = r;
else
return -EINVAL;
}
platform_set_drvdata(dev->platformdev, dev);
dev->dev_private = priv;
- /* Get the implementation specific driver data. */
- id = platform_get_device_id(dev->platformdev);
- if (!id)
- return -ENXIO;
-
- variant = (const struct armada_variant *)id->driver_data;
-
INIT_WORK(&priv->fb_unref_work, armada_drm_unref_work);
INIT_KFIFO(priv->fb_unref);
dev->mode_config.funcs = &armada_drm_mode_config_funcs;
drm_mm_init(&priv->linear, mem->start, resource_size(mem));
- /* Create all LCD controllers */
- for (n = 0; n < ARRAY_SIZE(priv->dcrtc); n++) {
- int irq;
-
- if (!res[n])
- break;
-
- irq = platform_get_irq(dev->platformdev, n);
- if (irq < 0)
- goto err_kms;
-
- ret = armada_drm_crtc_create(dev, dev->dev, res[n], irq,
- variant, NULL);
- if (ret)
- goto err_kms;
- }
-
- if (is_componentized(dev->dev)) {
- ret = component_bind_all(dev->dev, dev);
- if (ret)
- goto err_kms;
- } else {
-#ifdef CONFIG_DRM_ARMADA_TDA1998X
- ret = armada_drm_connector_slave_create(dev, &tda19988_config);
- if (ret)
- goto err_kms;
-#endif
- }
+ ret = component_bind_all(dev->dev, dev);
+ if (ret)
+ goto err_kms;
ret = drm_vblank_init(dev, dev->mode_config.num_crtc);
if (ret)
return 0;
err_comp:
- if (is_componentized(dev->dev))
- component_unbind_all(dev->dev, dev);
+ component_unbind_all(dev->dev, dev);
err_kms:
drm_mode_config_cleanup(dev);
drm_mm_takedown(&priv->linear);
drm_kms_helper_poll_fini(dev);
armada_fbdev_fini(dev);
- if (is_componentized(dev->dev))
- component_unbind_all(dev->dev, dev);
+ component_unbind_all(dev->dev, dev);
drm_mode_config_cleanup(dev);
drm_mm_takedown(&priv->linear);
return 0;
}
-void armada_drm_vbl_event_add(struct armada_crtc *dcrtc,
- struct armada_vbl_event *evt)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&dcrtc->irq_lock, flags);
- if (list_empty(&evt->node)) {
- list_add_tail(&evt->node, &dcrtc->vbl_list);
-
- drm_vblank_get(dcrtc->crtc.dev, dcrtc->num);
- }
- spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-}
-
-void armada_drm_vbl_event_remove(struct armada_crtc *dcrtc,
- struct armada_vbl_event *evt)
-{
- if (!list_empty(&evt->node)) {
- list_del_init(&evt->node);
- drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
- }
-}
-
/* These are called under the vbl_lock. */
static int armada_drm_enable_vblank(struct drm_device *dev, unsigned int pipe)
{
static int armada_drm_probe(struct platform_device *pdev)
{
- if (is_componentized(&pdev->dev)) {
- struct component_match *match = NULL;
- int ret;
-
- ret = armada_drm_find_components(&pdev->dev, &match);
- if (ret < 0)
- return ret;
-
- return component_master_add_with_match(&pdev->dev,
- &armada_master_ops, match);
- } else {
- return drm_platform_init(&armada_drm_driver, pdev);
- }
+ struct component_match *match = NULL;
+ int ret;
+
+ ret = armada_drm_find_components(&pdev->dev, &match);
+ if (ret < 0)
+ return ret;
+
+ return component_master_add_with_match(&pdev->dev, &armada_master_ops,
+ match);
}
static int armada_drm_remove(struct platform_device *pdev)
{
- if (is_componentized(&pdev->dev))
- component_master_del(&pdev->dev, &armada_master_ops);
- else
- drm_put_dev(platform_get_drvdata(pdev));
+ component_master_del(&pdev->dev, &armada_master_ops);
return 0;
}
static const struct platform_device_id armada_drm_platform_ids[] = {
{
.name = "armada-drm",
- .driver_data = (unsigned long)&armada510_ops,
}, {
.name = "armada-510-drm",
- .driver_data = (unsigned long)&armada510_ops,
},
{ },
};
+++ /dev/null
-/*
- * Copyright (C) 2012 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <drm/drmP.h>
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_edid.h>
-#include <drm/drm_encoder_slave.h>
-#include "armada_output.h"
-#include "armada_drm.h"
-
-struct armada_connector {
- struct drm_connector conn;
- const struct armada_output_type *type;
-};
-
-#define drm_to_armada_conn(c) container_of(c, struct armada_connector, conn)
-
-struct drm_encoder *armada_drm_connector_encoder(struct drm_connector *conn)
-{
- struct drm_encoder *enc = conn->encoder;
-
- return enc ? enc : drm_encoder_find(conn->dev, conn->encoder_ids[0]);
-}
-
-static enum drm_connector_status armada_drm_connector_detect(
- struct drm_connector *conn, bool force)
-{
- struct armada_connector *dconn = drm_to_armada_conn(conn);
- enum drm_connector_status status = connector_status_disconnected;
-
- if (dconn->type->detect) {
- status = dconn->type->detect(conn, force);
- } else {
- struct drm_encoder *enc = armada_drm_connector_encoder(conn);
-
- if (enc)
- status = encoder_helper_funcs(enc)->detect(enc, conn);
- }
-
- return status;
-}
-
-static void armada_drm_connector_destroy(struct drm_connector *conn)
-{
- struct armada_connector *dconn = drm_to_armada_conn(conn);
-
- drm_connector_unregister(conn);
- drm_connector_cleanup(conn);
- kfree(dconn);
-}
-
-static int armada_drm_connector_set_property(struct drm_connector *conn,
- struct drm_property *property, uint64_t value)
-{
- struct armada_connector *dconn = drm_to_armada_conn(conn);
-
- if (!dconn->type->set_property)
- return -EINVAL;
-
- return dconn->type->set_property(conn, property, value);
-}
-
-static const struct drm_connector_funcs armada_drm_conn_funcs = {
- .dpms = drm_helper_connector_dpms,
- .fill_modes = drm_helper_probe_single_connector_modes,
- .detect = armada_drm_connector_detect,
- .destroy = armada_drm_connector_destroy,
- .set_property = armada_drm_connector_set_property,
-};
-
-/* Shouldn't this be a generic helper function? */
-int armada_drm_slave_encoder_mode_valid(struct drm_connector *conn,
- struct drm_display_mode *mode)
-{
- struct drm_encoder *encoder = armada_drm_connector_encoder(conn);
- int valid = MODE_BAD;
-
- if (encoder) {
- struct drm_encoder_slave *slave = to_encoder_slave(encoder);
-
- valid = slave->slave_funcs->mode_valid(encoder, mode);
- }
- return valid;
-}
-
-int armada_drm_slave_encoder_set_property(struct drm_connector *conn,
- struct drm_property *property, uint64_t value)
-{
- struct drm_encoder *encoder = armada_drm_connector_encoder(conn);
- int rc = -EINVAL;
-
- if (encoder) {
- struct drm_encoder_slave *slave = to_encoder_slave(encoder);
-
- rc = slave->slave_funcs->set_property(encoder, conn, property,
- value);
- }
- return rc;
-}
-
-int armada_output_create(struct drm_device *dev,
- const struct armada_output_type *type, const void *data)
-{
- struct armada_connector *dconn;
- int ret;
-
- dconn = kzalloc(sizeof(*dconn), GFP_KERNEL);
- if (!dconn)
- return -ENOMEM;
-
- dconn->type = type;
-
- ret = drm_connector_init(dev, &dconn->conn, &armada_drm_conn_funcs,
- type->connector_type);
- if (ret) {
- DRM_ERROR("unable to init connector\n");
- goto err_destroy_dconn;
- }
-
- ret = type->create(&dconn->conn, data);
- if (ret)
- goto err_conn;
-
- ret = drm_connector_register(&dconn->conn);
- if (ret)
- goto err_sysfs;
-
- return 0;
-
- err_sysfs:
- if (dconn->conn.encoder)
- dconn->conn.encoder->funcs->destroy(dconn->conn.encoder);
- err_conn:
- drm_connector_cleanup(&dconn->conn);
- err_destroy_dconn:
- kfree(dconn);
- return ret;
-}
+++ /dev/null
-/*
- * Copyright (C) 2012 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef ARMADA_CONNETOR_H
-#define ARMADA_CONNETOR_H
-
-#define encoder_helper_funcs(encoder) \
- ((const struct drm_encoder_helper_funcs *)encoder->helper_private)
-
-struct armada_output_type {
- int connector_type;
- enum drm_connector_status (*detect)(struct drm_connector *, bool);
- int (*create)(struct drm_connector *, const void *);
- int (*set_property)(struct drm_connector *, struct drm_property *,
- uint64_t);
-};
-
-struct drm_encoder *armada_drm_connector_encoder(struct drm_connector *conn);
-
-int armada_drm_slave_encoder_mode_valid(struct drm_connector *conn,
- struct drm_display_mode *mode);
-
-int armada_drm_slave_encoder_set_property(struct drm_connector *conn,
- struct drm_property *property, uint64_t value);
-
-int armada_output_create(struct drm_device *dev,
- const struct armada_output_type *type, const void *data);
-
-#endif
#include <drm/armada_drm.h>
#include "armada_ioctlP.h"
-struct armada_plane_properties {
+struct armada_ovl_plane_properties {
uint32_t colorkey_yr;
uint32_t colorkey_ug;
uint32_t colorkey_vb;
uint32_t colorkey_mode;
};
-struct armada_plane {
- struct drm_plane base;
- spinlock_t lock;
+struct armada_ovl_plane {
+ struct armada_plane base;
struct drm_framebuffer *old_fb;
uint32_t src_hw;
uint32_t dst_hw;
uint32_t dst_yx;
uint32_t ctrl0;
struct {
- struct armada_vbl_event update;
+ struct armada_plane_work work;
struct armada_regs regs[13];
- wait_queue_head_t wait;
} vbl;
- struct armada_plane_properties prop;
+ struct armada_ovl_plane_properties prop;
};
-#define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
+#define drm_to_armada_ovl_plane(p) \
+ container_of(p, struct armada_ovl_plane, base.base)
static void
-armada_ovl_update_attr(struct armada_plane_properties *prop,
+armada_ovl_update_attr(struct armada_ovl_plane_properties *prop,
struct armada_crtc *dcrtc)
{
writel_relaxed(prop->colorkey_yr, dcrtc->base + LCD_SPU_COLORKEY_Y);
spin_unlock_irq(&dcrtc->irq_lock);
}
-/* === Plane support === */
-static void armada_plane_vbl(struct armada_crtc *dcrtc, void *data)
+static void armada_ovl_retire_fb(struct armada_ovl_plane *dplane,
+ struct drm_framebuffer *fb)
{
- struct armada_plane *dplane = data;
- struct drm_framebuffer *fb;
+ struct drm_framebuffer *old_fb;
- armada_drm_crtc_update_regs(dcrtc, dplane->vbl.regs);
+ old_fb = xchg(&dplane->old_fb, fb);
- spin_lock(&dplane->lock);
- fb = dplane->old_fb;
- dplane->old_fb = NULL;
- spin_unlock(&dplane->lock);
+ if (old_fb)
+ armada_drm_queue_unref_work(dplane->base.base.dev, old_fb);
+}
- if (fb)
- armada_drm_queue_unref_work(dcrtc->crtc.dev, fb);
+/* === Plane support === */
+static void armada_ovl_plane_work(struct armada_crtc *dcrtc,
+ struct armada_plane *plane, struct armada_plane_work *work)
+{
+ struct armada_ovl_plane *dplane = container_of(plane, struct armada_ovl_plane, base);
- wake_up(&dplane->vbl.wait);
+ armada_drm_crtc_update_regs(dcrtc, dplane->vbl.regs);
+ armada_ovl_retire_fb(dplane, NULL);
}
static int
-armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
+armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
struct drm_framebuffer *fb,
int crtc_x, int crtc_y, unsigned crtc_w, unsigned crtc_h,
uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h)
{
- struct armada_plane *dplane = drm_to_armada_plane(plane);
+ struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
struct drm_rect src = {
.x1 = src_x,
dcrtc->base + LCD_SPU_SRAM_PARA1);
}
- wait_event_timeout(dplane->vbl.wait,
- list_empty(&dplane->vbl.update.node),
- HZ/25);
+ if (armada_drm_plane_work_wait(&dplane->base, HZ / 25) == 0)
+ armada_drm_plane_work_cancel(dcrtc, &dplane->base);
if (plane->fb != fb) {
struct armada_gem_object *obj = drm_fb_obj(fb);
*/
drm_framebuffer_reference(fb);
- if (plane->fb) {
- struct drm_framebuffer *older_fb;
-
- spin_lock_irq(&dplane->lock);
- older_fb = dplane->old_fb;
- dplane->old_fb = plane->fb;
- spin_unlock_irq(&dplane->lock);
- if (older_fb)
- armada_drm_queue_unref_work(dcrtc->crtc.dev,
- older_fb);
- }
+ if (plane->fb)
+ armada_ovl_retire_fb(dplane, plane->fb);
src_y = src.y1 >> 16;
src_x = src.x1 >> 16;
}
if (idx) {
armada_reg_queue_end(dplane->vbl.regs, idx);
- armada_drm_vbl_event_add(dcrtc, &dplane->vbl.update);
+ armada_drm_plane_work_queue(dcrtc, &dplane->base,
+ &dplane->vbl.work);
}
return 0;
}
-static int armada_plane_disable(struct drm_plane *plane)
+static int armada_ovl_plane_disable(struct drm_plane *plane)
{
- struct armada_plane *dplane = drm_to_armada_plane(plane);
+ struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
struct drm_framebuffer *fb;
struct armada_crtc *dcrtc;
- if (!dplane->base.crtc)
+ if (!dplane->base.base.crtc)
return 0;
- dcrtc = drm_to_armada_crtc(dplane->base.crtc);
- dcrtc->plane = NULL;
-
- spin_lock_irq(&dcrtc->irq_lock);
- armada_drm_vbl_event_remove(dcrtc, &dplane->vbl.update);
- armada_updatel(0, CFG_DMA_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0);
- dplane->ctrl0 = 0;
- spin_unlock_irq(&dcrtc->irq_lock);
+ dcrtc = drm_to_armada_crtc(dplane->base.base.crtc);
- /* Power down the Y/U/V FIFOs */
- armada_updatel(CFG_PDWN16x66 | CFG_PDWN32x66, 0,
- dcrtc->base + LCD_SPU_SRAM_PARA1);
+ armada_drm_plane_work_cancel(dcrtc, &dplane->base);
+ armada_drm_crtc_plane_disable(dcrtc, plane);
- if (plane->fb)
- drm_framebuffer_unreference(plane->fb);
+ dcrtc->plane = NULL;
+ dplane->ctrl0 = 0;
- spin_lock_irq(&dplane->lock);
- fb = dplane->old_fb;
- dplane->old_fb = NULL;
- spin_unlock_irq(&dplane->lock);
+ fb = xchg(&dplane->old_fb, NULL);
if (fb)
drm_framebuffer_unreference(fb);
return 0;
}
-static void armada_plane_destroy(struct drm_plane *plane)
+static void armada_ovl_plane_destroy(struct drm_plane *plane)
{
- struct armada_plane *dplane = drm_to_armada_plane(plane);
+ struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
drm_plane_cleanup(plane);
kfree(dplane);
}
-static int armada_plane_set_property(struct drm_plane *plane,
+static int armada_ovl_plane_set_property(struct drm_plane *plane,
struct drm_property *property, uint64_t val)
{
struct armada_private *priv = plane->dev->dev_private;
- struct armada_plane *dplane = drm_to_armada_plane(plane);
+ struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
bool update_attr = false;
if (property == priv->colorkey_prop) {
update_attr = true;
}
- if (update_attr && dplane->base.crtc)
+ if (update_attr && dplane->base.base.crtc)
armada_ovl_update_attr(&dplane->prop,
- drm_to_armada_crtc(dplane->base.crtc));
+ drm_to_armada_crtc(dplane->base.base.crtc));
return 0;
}
-static const struct drm_plane_funcs armada_plane_funcs = {
- .update_plane = armada_plane_update,
- .disable_plane = armada_plane_disable,
- .destroy = armada_plane_destroy,
- .set_property = armada_plane_set_property,
+static const struct drm_plane_funcs armada_ovl_plane_funcs = {
+ .update_plane = armada_ovl_plane_update,
+ .disable_plane = armada_ovl_plane_disable,
+ .destroy = armada_ovl_plane_destroy,
+ .set_property = armada_ovl_plane_set_property,
};
-static const uint32_t armada_formats[] = {
+static const uint32_t armada_ovl_formats[] = {
DRM_FORMAT_UYVY,
DRM_FORMAT_YUYV,
DRM_FORMAT_YUV420,
{
struct armada_private *priv = dev->dev_private;
struct drm_mode_object *mobj;
- struct armada_plane *dplane;
+ struct armada_ovl_plane *dplane;
int ret;
ret = armada_overlay_create_properties(dev);
if (!dplane)
return -ENOMEM;
- spin_lock_init(&dplane->lock);
- init_waitqueue_head(&dplane->vbl.wait);
- armada_drm_vbl_event_init(&dplane->vbl.update, armada_plane_vbl,
- dplane);
+ ret = armada_drm_plane_init(&dplane->base);
+ if (ret) {
+ kfree(dplane);
+ return ret;
+ }
+
+ dplane->vbl.work.fn = armada_ovl_plane_work;
- drm_plane_init(dev, &dplane->base, crtcs, &armada_plane_funcs,
- armada_formats, ARRAY_SIZE(armada_formats), false);
+ ret = drm_universal_plane_init(dev, &dplane->base.base, crtcs,
+ &armada_ovl_plane_funcs,
+ armada_ovl_formats,
+ ARRAY_SIZE(armada_ovl_formats),
+ DRM_PLANE_TYPE_OVERLAY);
+ if (ret) {
+ kfree(dplane);
+ return ret;
+ }
dplane->prop.colorkey_yr = 0xfefefe00;
dplane->prop.colorkey_ug = 0x01010100;
dplane->prop.contrast = 0x4000;
dplane->prop.saturation = 0x4000;
- mobj = &dplane->base.base;
+ mobj = &dplane->base.base.base;
drm_object_attach_property(mobj, priv->colorkey_prop,
0x0101fe);
drm_object_attach_property(mobj, priv->colorkey_min_prop,
+++ /dev/null
-/*
- * Copyright (C) 2012 Russell King
- * Rewritten from the dovefb driver, and Armada510 manuals.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <drm/drmP.h>
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_edid.h>
-#include <drm/drm_encoder_slave.h>
-#include "armada_drm.h"
-#include "armada_output.h"
-#include "armada_slave.h"
-
-static int armada_drm_slave_get_modes(struct drm_connector *conn)
-{
- struct drm_encoder *enc = armada_drm_connector_encoder(conn);
- int count = 0;
-
- if (enc) {
- struct drm_encoder_slave *slave = to_encoder_slave(enc);
-
- count = slave->slave_funcs->get_modes(enc, conn);
- }
-
- return count;
-}
-
-static void armada_drm_slave_destroy(struct drm_encoder *enc)
-{
- struct drm_encoder_slave *slave = to_encoder_slave(enc);
- struct i2c_client *client = drm_i2c_encoder_get_client(enc);
-
- if (slave->slave_funcs)
- slave->slave_funcs->destroy(enc);
- if (client)
- i2c_put_adapter(client->adapter);
-
- drm_encoder_cleanup(&slave->base);
- kfree(slave);
-}
-
-static const struct drm_encoder_funcs armada_drm_slave_encoder_funcs = {
- .destroy = armada_drm_slave_destroy,
-};
-
-static const struct drm_connector_helper_funcs armada_drm_slave_helper_funcs = {
- .get_modes = armada_drm_slave_get_modes,
- .mode_valid = armada_drm_slave_encoder_mode_valid,
- .best_encoder = armada_drm_connector_encoder,
-};
-
-static const struct drm_encoder_helper_funcs drm_slave_encoder_helpers = {
- .dpms = drm_i2c_encoder_dpms,
- .save = drm_i2c_encoder_save,
- .restore = drm_i2c_encoder_restore,
- .mode_fixup = drm_i2c_encoder_mode_fixup,
- .prepare = drm_i2c_encoder_prepare,
- .commit = drm_i2c_encoder_commit,
- .mode_set = drm_i2c_encoder_mode_set,
- .detect = drm_i2c_encoder_detect,
-};
-
-static int
-armada_drm_conn_slave_create(struct drm_connector *conn, const void *data)
-{
- const struct armada_drm_slave_config *config = data;
- struct drm_encoder_slave *slave;
- struct i2c_adapter *adap;
- int ret;
-
- conn->interlace_allowed = config->interlace_allowed;
- conn->doublescan_allowed = config->doublescan_allowed;
- conn->polled = config->polled;
-
- drm_connector_helper_add(conn, &armada_drm_slave_helper_funcs);
-
- slave = kzalloc(sizeof(*slave), GFP_KERNEL);
- if (!slave)
- return -ENOMEM;
-
- slave->base.possible_crtcs = config->crtcs;
-
- adap = i2c_get_adapter(config->i2c_adapter_id);
- if (!adap) {
- kfree(slave);
- return -EPROBE_DEFER;
- }
-
- ret = drm_encoder_init(conn->dev, &slave->base,
- &armada_drm_slave_encoder_funcs,
- DRM_MODE_ENCODER_TMDS);
- if (ret) {
- DRM_ERROR("unable to init encoder\n");
- i2c_put_adapter(adap);
- kfree(slave);
- return ret;
- }
-
- ret = drm_i2c_encoder_init(conn->dev, slave, adap, &config->info);
- i2c_put_adapter(adap);
- if (ret) {
- DRM_ERROR("unable to init encoder slave\n");
- armada_drm_slave_destroy(&slave->base);
- return ret;
- }
-
- drm_encoder_helper_add(&slave->base, &drm_slave_encoder_helpers);
-
- ret = slave->slave_funcs->create_resources(&slave->base, conn);
- if (ret) {
- armada_drm_slave_destroy(&slave->base);
- return ret;
- }
-
- ret = drm_mode_connector_attach_encoder(conn, &slave->base);
- if (ret) {
- armada_drm_slave_destroy(&slave->base);
- return ret;
- }
-
- conn->encoder = &slave->base;
-
- return ret;
-}
-
-static const struct armada_output_type armada_drm_conn_slave = {
- .connector_type = DRM_MODE_CONNECTOR_HDMIA,
- .create = armada_drm_conn_slave_create,
- .set_property = armada_drm_slave_encoder_set_property,
-};
-
-int armada_drm_connector_slave_create(struct drm_device *dev,
- const struct armada_drm_slave_config *config)
-{
- return armada_output_create(dev, &armada_drm_conn_slave, config);
-}
+++ /dev/null
-/*
- * Copyright (C) 2012 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef ARMADA_SLAVE_H
-#define ARMADA_SLAVE_H
-
-#include <linux/i2c.h>
-#include <drm/drmP.h>
-
-struct armada_drm_slave_config {
- int i2c_adapter_id;
- uint32_t crtcs;
- uint8_t polled;
- bool interlace_allowed;
- bool doublescan_allowed;
- struct i2c_board_info info;
-};
-
-int armada_drm_connector_slave_create(struct drm_device *dev,
- const struct armada_drm_slave_config *);
-
-#endif
#include <drm/drmP.h>
#include <drm/drm_crtc_helper.h>
-#include <drm/drm_encoder_slave.h>
#include <drm/drm_edid.h>
#include <drm/drm_of.h>
#include <drm/i2c/tda998x.h>
struct i2c_client *cec;
struct i2c_client *hdmi;
struct mutex mutex;
- struct delayed_work dwork;
- uint16_t rev;
- uint8_t current_page;
+ u16 rev;
+ u8 current_page;
int dpms;
bool is_hdmi_sink;
u8 vip_cntrl_0;
wait_queue_head_t wq_edid;
volatile int wq_edid_wait;
- struct drm_encoder *encoder;
+
+ struct work_struct detect_work;
+ struct timer_list edid_delay_timer;
+ wait_queue_head_t edid_delay_waitq;
+ bool edid_delay_active;
+
+ struct drm_encoder encoder;
+ struct drm_connector connector;
};
-#define to_tda998x_priv(x) ((struct tda998x_priv *)to_encoder_slave(x)->slave_priv)
+#define conn_to_tda998x_priv(x) \
+ container_of(x, struct tda998x_priv, connector)
+
+#define enc_to_tda998x_priv(x) \
+ container_of(x, struct tda998x_priv, encoder)
/* The TDA9988 series of devices use a paged register scheme.. to simplify
* things we encode the page # in upper bits of the register #. To read/
# define CEC_FRO_IM_CLK_CTRL_FRO_DIV (1 << 0)
#define REG_CEC_RXSHPDINTENA 0xfc /* read/write */
#define REG_CEC_RXSHPDINT 0xfd /* read */
+# define CEC_RXSHPDINT_RXSENS BIT(0)
+# define CEC_RXSHPDINT_HPD BIT(1)
#define REG_CEC_RXSHPDLEV 0xfe /* read */
# define CEC_RXSHPDLEV_RXSENS (1 << 0)
# define CEC_RXSHPDLEV_HPD (1 << 1)
#define TDA19988 0x0301
static void
-cec_write(struct tda998x_priv *priv, uint16_t addr, uint8_t val)
+cec_write(struct tda998x_priv *priv, u16 addr, u8 val)
{
struct i2c_client *client = priv->cec;
- uint8_t buf[] = {addr, val};
+ u8 buf[] = {addr, val};
int ret;
ret = i2c_master_send(client, buf, sizeof(buf));
dev_err(&client->dev, "Error %d writing to cec:0x%x\n", ret, addr);
}
-static uint8_t
-cec_read(struct tda998x_priv *priv, uint8_t addr)
+static u8
+cec_read(struct tda998x_priv *priv, u8 addr)
{
struct i2c_client *client = priv->cec;
- uint8_t val;
+ u8 val;
int ret;
ret = i2c_master_send(client, &addr, sizeof(addr));
}
static int
-set_page(struct tda998x_priv *priv, uint16_t reg)
+set_page(struct tda998x_priv *priv, u16 reg)
{
if (REG2PAGE(reg) != priv->current_page) {
struct i2c_client *client = priv->hdmi;
- uint8_t buf[] = {
+ u8 buf[] = {
REG_CURPAGE, REG2PAGE(reg)
};
int ret = i2c_master_send(client, buf, sizeof(buf));
}
static int
-reg_read_range(struct tda998x_priv *priv, uint16_t reg, char *buf, int cnt)
+reg_read_range(struct tda998x_priv *priv, u16 reg, char *buf, int cnt)
{
struct i2c_client *client = priv->hdmi;
- uint8_t addr = REG2ADDR(reg);
+ u8 addr = REG2ADDR(reg);
int ret;
mutex_lock(&priv->mutex);
}
static void
-reg_write_range(struct tda998x_priv *priv, uint16_t reg, uint8_t *p, int cnt)
+reg_write_range(struct tda998x_priv *priv, u16 reg, u8 *p, int cnt)
{
struct i2c_client *client = priv->hdmi;
- uint8_t buf[cnt+1];
+ u8 buf[cnt+1];
int ret;
buf[0] = REG2ADDR(reg);
}
static int
-reg_read(struct tda998x_priv *priv, uint16_t reg)
+reg_read(struct tda998x_priv *priv, u16 reg)
{
- uint8_t val = 0;
+ u8 val = 0;
int ret;
ret = reg_read_range(priv, reg, &val, sizeof(val));
}
static void
-reg_write(struct tda998x_priv *priv, uint16_t reg, uint8_t val)
+reg_write(struct tda998x_priv *priv, u16 reg, u8 val)
{
struct i2c_client *client = priv->hdmi;
- uint8_t buf[] = {REG2ADDR(reg), val};
+ u8 buf[] = {REG2ADDR(reg), val};
int ret;
mutex_lock(&priv->mutex);
}
static void
-reg_write16(struct tda998x_priv *priv, uint16_t reg, uint16_t val)
+reg_write16(struct tda998x_priv *priv, u16 reg, u16 val)
{
struct i2c_client *client = priv->hdmi;
- uint8_t buf[] = {REG2ADDR(reg), val >> 8, val};
+ u8 buf[] = {REG2ADDR(reg), val >> 8, val};
int ret;
mutex_lock(&priv->mutex);
}
static void
-reg_set(struct tda998x_priv *priv, uint16_t reg, uint8_t val)
+reg_set(struct tda998x_priv *priv, u16 reg, u8 val)
{
int old_val;
}
static void
-reg_clear(struct tda998x_priv *priv, uint16_t reg, uint8_t val)
+reg_clear(struct tda998x_priv *priv, u16 reg, u8 val)
{
int old_val;
reg_write(priv, REG_MUX_VP_VIP_OUT, 0x24);
}
-/* handle HDMI connect/disconnect */
-static void tda998x_hpd(struct work_struct *work)
+/*
+ * The TDA998x has a problem when trying to read the EDID close to a
+ * HPD assertion: it needs a delay of 100ms to avoid timing out while
+ * trying to read EDID data.
+ *
+ * However, tda998x_encoder_get_modes() may be called at any moment
+ * after tda998x_connector_detect() indicates that we are connected, so
+ * we need to delay probing modes in tda998x_encoder_get_modes() after
+ * we have seen a HPD inactive->active transition. This code implements
+ * that delay.
+ */
+static void tda998x_edid_delay_done(unsigned long data)
+{
+ struct tda998x_priv *priv = (struct tda998x_priv *)data;
+
+ priv->edid_delay_active = false;
+ wake_up(&priv->edid_delay_waitq);
+ schedule_work(&priv->detect_work);
+}
+
+static void tda998x_edid_delay_start(struct tda998x_priv *priv)
+{
+ priv->edid_delay_active = true;
+ mod_timer(&priv->edid_delay_timer, jiffies + HZ/10);
+}
+
+static int tda998x_edid_delay_wait(struct tda998x_priv *priv)
+{
+ return wait_event_killable(priv->edid_delay_waitq, !priv->edid_delay_active);
+}
+
+/*
+ * We need to run the KMS hotplug event helper outside of our threaded
+ * interrupt routine as this can call back into our get_modes method,
+ * which will want to make use of interrupts.
+ */
+static void tda998x_detect_work(struct work_struct *work)
{
- struct delayed_work *dwork = to_delayed_work(work);
struct tda998x_priv *priv =
- container_of(dwork, struct tda998x_priv, dwork);
+ container_of(work, struct tda998x_priv, detect_work);
+ struct drm_device *dev = priv->encoder.dev;
- if (priv->encoder && priv->encoder->dev)
- drm_kms_helper_hotplug_event(priv->encoder->dev);
+ if (dev)
+ drm_kms_helper_hotplug_event(dev);
}
/*
{
struct tda998x_priv *priv = data;
u8 sta, cec, lvl, flag0, flag1, flag2;
+ bool handled = false;
- if (!priv)
- return IRQ_HANDLED;
sta = cec_read(priv, REG_CEC_INTSTATUS);
cec = cec_read(priv, REG_CEC_RXSHPDINT);
lvl = cec_read(priv, REG_CEC_RXSHPDLEV);
DRM_DEBUG_DRIVER(
"tda irq sta %02x cec %02x lvl %02x f0 %02x f1 %02x f2 %02x\n",
sta, cec, lvl, flag0, flag1, flag2);
+
+ if (cec & CEC_RXSHPDINT_HPD) {
+ if (lvl & CEC_RXSHPDLEV_HPD)
+ tda998x_edid_delay_start(priv);
+ else
+ schedule_work(&priv->detect_work);
+
+ handled = true;
+ }
+
if ((flag2 & INT_FLAGS_2_EDID_BLK_RD) && priv->wq_edid_wait) {
priv->wq_edid_wait = 0;
wake_up(&priv->wq_edid);
- } else if (cec != 0) { /* HPD change */
- schedule_delayed_work(&priv->dwork, HZ/10);
+ handled = true;
}
- return IRQ_HANDLED;
-}
-static uint8_t tda998x_cksum(uint8_t *buf, size_t bytes)
-{
- int sum = 0;
-
- while (bytes--)
- sum -= *buf++;
- return sum;
+ return IRQ_RETVAL(handled);
}
-#define HB(x) (x)
-#define PB(x) (HB(2) + 1 + (x))
-
static void
-tda998x_write_if(struct tda998x_priv *priv, uint8_t bit, uint16_t addr,
- uint8_t *buf, size_t size)
+tda998x_write_if(struct tda998x_priv *priv, u8 bit, u16 addr,
+ union hdmi_infoframe *frame)
{
+ u8 buf[32];
+ ssize_t len;
+
+ len = hdmi_infoframe_pack(frame, buf, sizeof(buf));
+ if (len < 0) {
+ dev_err(&priv->hdmi->dev,
+ "hdmi_infoframe_pack() type=0x%02x failed: %zd\n",
+ frame->any.type, len);
+ return;
+ }
+
reg_clear(priv, REG_DIP_IF_FLAGS, bit);
- reg_write_range(priv, addr, buf, size);
+ reg_write_range(priv, addr, buf, len);
reg_set(priv, REG_DIP_IF_FLAGS, bit);
}
static void
tda998x_write_aif(struct tda998x_priv *priv, struct tda998x_encoder_params *p)
{
- u8 buf[PB(HDMI_AUDIO_INFOFRAME_SIZE) + 1];
+ union hdmi_infoframe frame;
+
+ hdmi_audio_infoframe_init(&frame.audio);
- memset(buf, 0, sizeof(buf));
- buf[HB(0)] = HDMI_INFOFRAME_TYPE_AUDIO;
- buf[HB(1)] = 0x01;
- buf[HB(2)] = HDMI_AUDIO_INFOFRAME_SIZE;
- buf[PB(1)] = p->audio_frame[1] & 0x07; /* CC */
- buf[PB(2)] = p->audio_frame[2] & 0x1c; /* SF */
- buf[PB(4)] = p->audio_frame[4];
- buf[PB(5)] = p->audio_frame[5] & 0xf8; /* DM_INH + LSV */
+ frame.audio.channels = p->audio_frame[1] & 0x07;
+ frame.audio.channel_allocation = p->audio_frame[4];
+ frame.audio.level_shift_value = (p->audio_frame[5] & 0x78) >> 3;
+ frame.audio.downmix_inhibit = (p->audio_frame[5] & 0x80) >> 7;
- buf[PB(0)] = tda998x_cksum(buf, sizeof(buf));
+ /*
+ * L-PCM and IEC61937 compressed audio shall always set sample
+ * frequency to "refer to stream". For others, see the HDMI
+ * specification.
+ */
+ frame.audio.sample_frequency = (p->audio_frame[2] & 0x1c) >> 2;
- tda998x_write_if(priv, DIP_IF_FLAGS_IF4, REG_IF4_HB0, buf,
- sizeof(buf));
+ tda998x_write_if(priv, DIP_IF_FLAGS_IF4, REG_IF4_HB0, &frame);
}
static void
tda998x_write_avi(struct tda998x_priv *priv, struct drm_display_mode *mode)
{
- struct hdmi_avi_infoframe frame;
- u8 buf[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE];
- ssize_t len;
+ union hdmi_infoframe frame;
- drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
+ drm_hdmi_avi_infoframe_from_display_mode(&frame.avi, mode);
+ frame.avi.quantization_range = HDMI_QUANTIZATION_RANGE_FULL;
- frame.quantization_range = HDMI_QUANTIZATION_RANGE_FULL;
-
- len = hdmi_avi_infoframe_pack(&frame, buf, sizeof(buf));
- if (len < 0) {
- dev_err(&priv->hdmi->dev,
- "hdmi_avi_infoframe_pack() failed: %zd\n", len);
- return;
- }
-
- tda998x_write_if(priv, DIP_IF_FLAGS_IF2, REG_IF2_HB0, buf, len);
+ tda998x_write_if(priv, DIP_IF_FLAGS_IF2, REG_IF2_HB0, &frame);
}
static void tda998x_audio_mute(struct tda998x_priv *priv, bool on)
tda998x_configure_audio(struct tda998x_priv *priv,
struct drm_display_mode *mode, struct tda998x_encoder_params *p)
{
- uint8_t buf[6], clksel_aip, clksel_fs, cts_n, adiv;
- uint32_t n;
+ u8 buf[6], clksel_aip, clksel_fs, cts_n, adiv;
+ u32 n;
/* Enable audio ports */
reg_write(priv, REG_ENA_AP, p->audio_cfg);
priv->params = *p;
}
-static void tda998x_encoder_dpms(struct tda998x_priv *priv, int mode)
+static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
{
+ struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
+
/* we only care about on or off: */
if (mode != DRM_MODE_DPMS_ON)
mode = DRM_MODE_DPMS_OFF;
return true;
}
-static int tda998x_encoder_mode_valid(struct tda998x_priv *priv,
- struct drm_display_mode *mode)
+static int tda998x_connector_mode_valid(struct drm_connector *connector,
+ struct drm_display_mode *mode)
{
if (mode->clock > 150000)
return MODE_CLOCK_HIGH;
}
static void
-tda998x_encoder_mode_set(struct tda998x_priv *priv,
+tda998x_encoder_mode_set(struct drm_encoder *encoder,
struct drm_display_mode *mode,
struct drm_display_mode *adjusted_mode)
{
- uint16_t ref_pix, ref_line, n_pix, n_line;
- uint16_t hs_pix_s, hs_pix_e;
- uint16_t vs1_pix_s, vs1_pix_e, vs1_line_s, vs1_line_e;
- uint16_t vs2_pix_s, vs2_pix_e, vs2_line_s, vs2_line_e;
- uint16_t vwin1_line_s, vwin1_line_e;
- uint16_t vwin2_line_s, vwin2_line_e;
- uint16_t de_pix_s, de_pix_e;
- uint8_t reg, div, rep;
+ struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
+ u16 ref_pix, ref_line, n_pix, n_line;
+ u16 hs_pix_s, hs_pix_e;
+ u16 vs1_pix_s, vs1_pix_e, vs1_line_s, vs1_line_e;
+ u16 vs2_pix_s, vs2_pix_e, vs2_line_s, vs2_line_e;
+ u16 vwin1_line_s, vwin1_line_e;
+ u16 vwin2_line_s, vwin2_line_e;
+ u16 de_pix_s, de_pix_e;
+ u8 reg, div, rep;
/*
* Internally TDA998x is using ITU-R BT.656 style sync but
}
static enum drm_connector_status
-tda998x_encoder_detect(struct tda998x_priv *priv)
+tda998x_connector_detect(struct drm_connector *connector, bool force)
{
- uint8_t val = cec_read(priv, REG_CEC_RXSHPDLEV);
+ struct tda998x_priv *priv = conn_to_tda998x_priv(connector);
+ u8 val = cec_read(priv, REG_CEC_RXSHPDLEV);
return (val & CEC_RXSHPDLEV_HPD) ? connector_status_connected :
connector_status_disconnected;
static int read_edid_block(void *data, u8 *buf, unsigned int blk, size_t length)
{
struct tda998x_priv *priv = data;
- uint8_t offset, segptr;
+ u8 offset, segptr;
int ret, i;
offset = (blk & 1) ? 128 : 0;
return 0;
}
-static int
-tda998x_encoder_get_modes(struct tda998x_priv *priv,
- struct drm_connector *connector)
+static int tda998x_connector_get_modes(struct drm_connector *connector)
{
+ struct tda998x_priv *priv = conn_to_tda998x_priv(connector);
struct edid *edid;
int n;
+ /*
+ * If we get killed while waiting for the HPD timeout, return
+ * no modes found: we are not in a restartable path, so we
+ * can't handle signals gracefully.
+ */
+ if (tda998x_edid_delay_wait(priv))
+ return 0;
+
if (priv->rev == TDA19988)
reg_clear(priv, REG_TX4, TX4_PD_RAM);
DRM_CONNECTOR_POLL_DISCONNECT;
}
-static int
-tda998x_encoder_set_property(struct drm_encoder *encoder,
- struct drm_connector *connector,
- struct drm_property *property,
- uint64_t val)
-{
- DBG("");
- return 0;
-}
-
static void tda998x_destroy(struct tda998x_priv *priv)
{
/* disable all IRQs and free the IRQ handler */
cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
- if (priv->hdmi->irq) {
- free_irq(priv->hdmi->irq, priv);
- cancel_delayed_work_sync(&priv->dwork);
- }
-
- i2c_unregister_device(priv->cec);
-}
-
-/* Slave encoder support */
-
-static void
-tda998x_encoder_slave_set_config(struct drm_encoder *encoder, void *params)
-{
- tda998x_encoder_set_config(to_tda998x_priv(encoder), params);
-}
-static void tda998x_encoder_slave_destroy(struct drm_encoder *encoder)
-{
- struct tda998x_priv *priv = to_tda998x_priv(encoder);
-
- tda998x_destroy(priv);
- drm_i2c_encoder_destroy(encoder);
- kfree(priv);
-}
-
-static void tda998x_encoder_slave_dpms(struct drm_encoder *encoder, int mode)
-{
- tda998x_encoder_dpms(to_tda998x_priv(encoder), mode);
-}
-
-static int tda998x_encoder_slave_mode_valid(struct drm_encoder *encoder,
- struct drm_display_mode *mode)
-{
- return tda998x_encoder_mode_valid(to_tda998x_priv(encoder), mode);
-}
+ if (priv->hdmi->irq)
+ free_irq(priv->hdmi->irq, priv);
-static void
-tda998x_encoder_slave_mode_set(struct drm_encoder *encoder,
- struct drm_display_mode *mode,
- struct drm_display_mode *adjusted_mode)
-{
- tda998x_encoder_mode_set(to_tda998x_priv(encoder), mode, adjusted_mode);
-}
+ del_timer_sync(&priv->edid_delay_timer);
+ cancel_work_sync(&priv->detect_work);
-static enum drm_connector_status
-tda998x_encoder_slave_detect(struct drm_encoder *encoder,
- struct drm_connector *connector)
-{
- return tda998x_encoder_detect(to_tda998x_priv(encoder));
-}
-
-static int tda998x_encoder_slave_get_modes(struct drm_encoder *encoder,
- struct drm_connector *connector)
-{
- return tda998x_encoder_get_modes(to_tda998x_priv(encoder), connector);
-}
-
-static int
-tda998x_encoder_slave_create_resources(struct drm_encoder *encoder,
- struct drm_connector *connector)
-{
- tda998x_encoder_set_polling(to_tda998x_priv(encoder), connector);
- return 0;
+ i2c_unregister_device(priv->cec);
}
-static struct drm_encoder_slave_funcs tda998x_encoder_slave_funcs = {
- .set_config = tda998x_encoder_slave_set_config,
- .destroy = tda998x_encoder_slave_destroy,
- .dpms = tda998x_encoder_slave_dpms,
- .save = tda998x_encoder_save,
- .restore = tda998x_encoder_restore,
- .mode_fixup = tda998x_encoder_mode_fixup,
- .mode_valid = tda998x_encoder_slave_mode_valid,
- .mode_set = tda998x_encoder_slave_mode_set,
- .detect = tda998x_encoder_slave_detect,
- .get_modes = tda998x_encoder_slave_get_modes,
- .create_resources = tda998x_encoder_slave_create_resources,
- .set_property = tda998x_encoder_set_property,
-};
-
/* I2C driver functions */
static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
priv->dpms = DRM_MODE_DPMS_OFF;
mutex_init(&priv->mutex); /* protect the page access */
+ init_waitqueue_head(&priv->edid_delay_waitq);
+ setup_timer(&priv->edid_delay_timer, tda998x_edid_delay_done,
+ (unsigned long)priv);
+ INIT_WORK(&priv->detect_work, tda998x_detect_work);
/* wake up the device: */
cec_write(priv, REG_CEC_ENAMODS,
/* init read EDID waitqueue and HDP work */
init_waitqueue_head(&priv->wq_edid);
- INIT_DELAYED_WORK(&priv->dwork, tda998x_hpd);
/* clear pending interrupts */
reg_read(priv, REG_INT_FLAGS_0);
return -ENXIO;
}
-static int tda998x_encoder_init(struct i2c_client *client,
- struct drm_device *dev,
- struct drm_encoder_slave *encoder_slave)
-{
- struct tda998x_priv *priv;
- int ret;
-
- priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (!priv)
- return -ENOMEM;
-
- priv->encoder = &encoder_slave->base;
-
- ret = tda998x_create(client, priv);
- if (ret) {
- kfree(priv);
- return ret;
- }
-
- encoder_slave->slave_priv = priv;
- encoder_slave->slave_funcs = &tda998x_encoder_slave_funcs;
-
- return 0;
-}
-
-struct tda998x_priv2 {
- struct tda998x_priv base;
- struct drm_encoder encoder;
- struct drm_connector connector;
-};
-
-#define conn_to_tda998x_priv2(x) \
- container_of(x, struct tda998x_priv2, connector);
-
-#define enc_to_tda998x_priv2(x) \
- container_of(x, struct tda998x_priv2, encoder);
-
-static void tda998x_encoder2_dpms(struct drm_encoder *encoder, int mode)
-{
- struct tda998x_priv2 *priv = enc_to_tda998x_priv2(encoder);
-
- tda998x_encoder_dpms(&priv->base, mode);
-}
-
static void tda998x_encoder_prepare(struct drm_encoder *encoder)
{
- tda998x_encoder2_dpms(encoder, DRM_MODE_DPMS_OFF);
+ tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_OFF);
}
static void tda998x_encoder_commit(struct drm_encoder *encoder)
{
- tda998x_encoder2_dpms(encoder, DRM_MODE_DPMS_ON);
-}
-
-static void tda998x_encoder2_mode_set(struct drm_encoder *encoder,
- struct drm_display_mode *mode,
- struct drm_display_mode *adjusted_mode)
-{
- struct tda998x_priv2 *priv = enc_to_tda998x_priv2(encoder);
-
- tda998x_encoder_mode_set(&priv->base, mode, adjusted_mode);
+ tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
}
static const struct drm_encoder_helper_funcs tda998x_encoder_helper_funcs = {
- .dpms = tda998x_encoder2_dpms,
+ .dpms = tda998x_encoder_dpms,
.save = tda998x_encoder_save,
.restore = tda998x_encoder_restore,
.mode_fixup = tda998x_encoder_mode_fixup,
.prepare = tda998x_encoder_prepare,
.commit = tda998x_encoder_commit,
- .mode_set = tda998x_encoder2_mode_set,
+ .mode_set = tda998x_encoder_mode_set,
};
static void tda998x_encoder_destroy(struct drm_encoder *encoder)
{
- struct tda998x_priv2 *priv = enc_to_tda998x_priv2(encoder);
+ struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
- tda998x_destroy(&priv->base);
+ tda998x_destroy(priv);
drm_encoder_cleanup(encoder);
}
.destroy = tda998x_encoder_destroy,
};
-static int tda998x_connector_get_modes(struct drm_connector *connector)
-{
- struct tda998x_priv2 *priv = conn_to_tda998x_priv2(connector);
-
- return tda998x_encoder_get_modes(&priv->base, connector);
-}
-
-static int tda998x_connector_mode_valid(struct drm_connector *connector,
- struct drm_display_mode *mode)
-{
- struct tda998x_priv2 *priv = conn_to_tda998x_priv2(connector);
-
- return tda998x_encoder_mode_valid(&priv->base, mode);
-}
-
static struct drm_encoder *
tda998x_connector_best_encoder(struct drm_connector *connector)
{
- struct tda998x_priv2 *priv = conn_to_tda998x_priv2(connector);
+ struct tda998x_priv *priv = conn_to_tda998x_priv(connector);
return &priv->encoder;
}
.best_encoder = tda998x_connector_best_encoder,
};
-static enum drm_connector_status
-tda998x_connector_detect(struct drm_connector *connector, bool force)
-{
- struct tda998x_priv2 *priv = conn_to_tda998x_priv2(connector);
-
- return tda998x_encoder_detect(&priv->base);
-}
-
static void tda998x_connector_destroy(struct drm_connector *connector)
{
drm_connector_unregister(connector);
struct tda998x_encoder_params *params = dev->platform_data;
struct i2c_client *client = to_i2c_client(dev);
struct drm_device *drm = data;
- struct tda998x_priv2 *priv;
- uint32_t crtcs = 0;
+ struct tda998x_priv *priv;
+ u32 crtcs = 0;
int ret;
priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
crtcs = 1 << 0;
}
- priv->base.encoder = &priv->encoder;
priv->connector.interlace_allowed = 1;
priv->encoder.possible_crtcs = crtcs;
- ret = tda998x_create(client, &priv->base);
+ ret = tda998x_create(client, priv);
if (ret)
return ret;
if (!dev->of_node && params)
- tda998x_encoder_set_config(&priv->base, params);
+ tda998x_encoder_set_config(priv, params);
- tda998x_encoder_set_polling(&priv->base, &priv->connector);
+ tda998x_encoder_set_polling(priv, &priv->connector);
drm_encoder_helper_add(&priv->encoder, &tda998x_encoder_helper_funcs);
ret = drm_encoder_init(drm, &priv->encoder, &tda998x_encoder_funcs,
err_connector:
drm_encoder_cleanup(&priv->encoder);
err_encoder:
- tda998x_destroy(&priv->base);
+ tda998x_destroy(priv);
return ret;
}
static void tda998x_unbind(struct device *dev, struct device *master,
void *data)
{
- struct tda998x_priv2 *priv = dev_get_drvdata(dev);
+ struct tda998x_priv *priv = dev_get_drvdata(dev);
drm_connector_cleanup(&priv->connector);
drm_encoder_cleanup(&priv->encoder);
- tda998x_destroy(&priv->base);
+ tda998x_destroy(priv);
}
static const struct component_ops tda998x_ops = {
};
MODULE_DEVICE_TABLE(i2c, tda998x_ids);
-static struct drm_i2c_encoder_driver tda998x_driver = {
- .i2c_driver = {
- .probe = tda998x_probe,
- .remove = tda998x_remove,
- .driver = {
- .name = "tda998x",
- .of_match_table = of_match_ptr(tda998x_dt_ids),
- },
- .id_table = tda998x_ids,
+static struct i2c_driver tda998x_driver = {
+ .probe = tda998x_probe,
+ .remove = tda998x_remove,
+ .driver = {
+ .name = "tda998x",
+ .of_match_table = of_match_ptr(tda998x_dt_ids),
},
- .encoder_init = tda998x_encoder_init,
+ .id_table = tda998x_ids,
};
-/* Module initialization */
-
-static int __init
-tda998x_init(void)
-{
- DBG("");
- return drm_i2c_encoder_register(THIS_MODULE, &tda998x_driver);
-}
-
-static void __exit
-tda998x_exit(void)
-{
- DBG("");
- drm_i2c_encoder_unregister(&tda998x_driver);
-}
+module_i2c_driver(tda998x_driver);
MODULE_AUTHOR("Rob Clark <robdclark@gmail.com");
MODULE_DESCRIPTION("NXP Semiconductors TDA998X HDMI Encoder");
MODULE_LICENSE("GPL");
-
-module_init(tda998x_init);
-module_exit(tda998x_exit);
intel_ringbuffer.o \
intel_uncore.o
+# general-purpose microcontroller (GuC) support
+i915-y += intel_guc_loader.o \
+ i915_guc_submission.o
+
# autogenerated null render state
i915-y += intel_renderstate_gen6.o \
intel_renderstate_gen7.o \
#define CMD(op, opm, f, lm, fl, ...) \
{ \
.flags = (fl) | ((f) ? CMD_DESC_FIXED : 0), \
- .cmd = { (op), (opm) }, \
+ .cmd = { (op), (opm) }, \
.length = { (lm) }, \
__VA_ARGS__ \
}
CMD( MI_STORE_DWORD_INDEX, SMI, !F, 0xFF, R ),
CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W,
.reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ),
- CMD( MI_STORE_REGISTER_MEM(1), SMI, !F, 0xFF, W | B,
+ CMD( MI_STORE_REGISTER_MEM, SMI, F, 3, W | B,
.reg = { .offset = 1, .mask = 0x007FFFFC },
.bits = {{
.offset = 0,
.mask = MI_GLOBAL_GTT,
.expected = 0,
}}, ),
- CMD( MI_LOAD_REGISTER_MEM(1), SMI, !F, 0xFF, W | B,
+ CMD( MI_LOAD_REGISTER_MEM, SMI, F, 3, W | B,
.reg = { .offset = 1, .mask = 0x007FFFFC },
.bits = {{
.offset = 0,
* only MI_LOAD_REGISTER_IMM commands.
*/
if (reg_addr == OACONTROL) {
- if (desc->cmd.value == MI_LOAD_REGISTER_MEM(1)) {
+ if (desc->cmd.value == MI_LOAD_REGISTER_MEM) {
DRM_DEBUG_DRIVER("CMD: Rejected LRM to OACONTROL\n");
return false;
}
* allowed mask/value pair given in the whitelist entry.
*/
if (reg->mask) {
- if (desc->cmd.value == MI_LOAD_REGISTER_MEM(1)) {
+ if (desc->cmd.value == MI_LOAD_REGISTER_MEM) {
DRM_DEBUG_DRIVER("CMD: Rejected LRM to masked register 0x%08X\n",
reg_addr);
return false;
* 2. Allow access to the MI_PREDICATE_SRC0 and
* MI_PREDICATE_SRC1 registers.
* 3. Allow access to the GPGPU_THREADS_DISPATCHED register.
+ * 4. L3 atomic chicken bits of HSW_SCRATCH1 and HSW_ROW_CHICKEN3.
*/
- return 3;
+ return 4;
}
PINNED_LIST,
};
-static const char *yesno(int v)
-{
- return v ? "yes" : "no";
-}
-
/* As the drm_debugfs_init() routines are called before dev->dev_private is
* allocated we need to hook into the minor for release. */
static int
intel_runtime_pm_put(dev_priv);
mutex_unlock(&dev->struct_mutex);
- seq_printf(m, "HD boost: %s\n", (rgvmodectl & MEMMODE_BOOST_EN) ?
- "yes" : "no");
+ seq_printf(m, "HD boost: %s\n", yesno(rgvmodectl & MEMMODE_BOOST_EN));
seq_printf(m, "Boost freq: %d\n",
(rgvmodectl & MEMMODE_BOOST_FREQ_MASK) >>
MEMMODE_BOOST_FREQ_SHIFT);
seq_printf(m, "HW control enabled: %s\n",
- rgvmodectl & MEMMODE_HWIDLE_EN ? "yes" : "no");
+ yesno(rgvmodectl & MEMMODE_HWIDLE_EN));
seq_printf(m, "SW control enabled: %s\n",
- rgvmodectl & MEMMODE_SWMODE_EN ? "yes" : "no");
+ yesno(rgvmodectl & MEMMODE_SWMODE_EN));
seq_printf(m, "Gated voltage change: %s\n",
- rgvmodectl & MEMMODE_RCLK_GATE ? "yes" : "no");
+ yesno(rgvmodectl & MEMMODE_RCLK_GATE));
seq_printf(m, "Starting frequency: P%d\n",
(rgvmodectl & MEMMODE_FSTART_MASK) >> MEMMODE_FSTART_SHIFT);
seq_printf(m, "Max P-state: P%d\n",
seq_printf(m, "RS1 VID: %d\n", (crstandvid & 0x3f));
seq_printf(m, "RS2 VID: %d\n", ((crstandvid >> 8) & 0x3f));
seq_printf(m, "Render standby enabled: %s\n",
- (rstdbyctl & RCX_SW_EXIT) ? "no" : "yes");
+ yesno(!(rstdbyctl & RCX_SW_EXIT)));
seq_puts(m, "Current RS state: ");
switch (rstdbyctl & RSX_STATUS_MASK) {
case RSX_STATUS_ON:
return;
}
- page = i915_gem_object_get_page(ctx_obj, 1);
+ page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
if (!WARN_ON(page == NULL)) {
reg_state = kmap_atomic(page);
seq_printf(m, "%s\n", ring->name);
- status = I915_READ(RING_EXECLIST_STATUS(ring));
- ctx_id = I915_READ(RING_EXECLIST_STATUS(ring) + 4);
+ status = I915_READ(RING_EXECLIST_STATUS_LO(ring));
+ ctx_id = I915_READ(RING_EXECLIST_STATUS_HI(ring));
seq_printf(m, "\tExeclist status: 0x%08X, context: %u\n",
status, ctx_id);
read_pointer, write_pointer);
for (i = 0; i < 6; i++) {
- status = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + 8*i);
- ctx_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + 8*i + 4);
+ status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, i));
+ ctx_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, i));
seq_printf(m, "\tStatus buffer %d: 0x%08X, context: %u\n",
i, status, ctx_id);
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring;
- struct drm_file *file;
int i;
if (INTEL_INFO(dev)->gen == 6)
ppgtt->debug_dump(ppgtt, m);
}
- list_for_each_entry_reverse(file, &dev->filelist, lhead) {
- struct drm_i915_file_private *file_priv = file->driver_priv;
-
- seq_printf(m, "proc: %s\n",
- get_pid_task(file->pid, PIDTYPE_PID)->comm);
- idr_for_each(&file_priv->context_idr, per_file_ctx, m);
- }
seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK));
}
struct drm_info_node *node = m->private;
struct drm_device *dev = node->minor->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_file *file;
int ret = mutex_lock_interruptible(&dev->struct_mutex);
if (ret)
else if (INTEL_INFO(dev)->gen >= 6)
gen6_ppgtt_info(m, dev);
+ list_for_each_entry_reverse(file, &dev->filelist, lhead) {
+ struct drm_i915_file_private *file_priv = file->driver_priv;
+ struct task_struct *task;
+
+ task = get_pid_task(file->pid, PIDTYPE_PID);
+ if (!task)
+ return -ESRCH;
+ seq_printf(m, "\nproc: %s\n", task->comm);
+ put_task_struct(task);
+ idr_for_each(&file_priv->context_idr, per_file_ctx,
+ (void *)(unsigned long)m);
+ }
+
intel_runtime_pm_put(dev_priv);
mutex_unlock(&dev->struct_mutex);
return 0;
}
+static int i915_guc_load_status_info(struct seq_file *m, void *data)
+{
+ struct drm_info_node *node = m->private;
+ struct drm_i915_private *dev_priv = node->minor->dev->dev_private;
+ struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
+ u32 tmp, i;
+
+ if (!HAS_GUC_UCODE(dev_priv->dev))
+ return 0;
+
+ seq_printf(m, "GuC firmware status:\n");
+ seq_printf(m, "\tpath: %s\n",
+ guc_fw->guc_fw_path);
+ seq_printf(m, "\tfetch: %s\n",
+ intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status));
+ seq_printf(m, "\tload: %s\n",
+ intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
+ seq_printf(m, "\tversion wanted: %d.%d\n",
+ guc_fw->guc_fw_major_wanted, guc_fw->guc_fw_minor_wanted);
+ seq_printf(m, "\tversion found: %d.%d\n",
+ guc_fw->guc_fw_major_found, guc_fw->guc_fw_minor_found);
+
+ tmp = I915_READ(GUC_STATUS);
+
+ seq_printf(m, "\nGuC status 0x%08x:\n", tmp);
+ seq_printf(m, "\tBootrom status = 0x%x\n",
+ (tmp & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT);
+ seq_printf(m, "\tuKernel status = 0x%x\n",
+ (tmp & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT);
+ seq_printf(m, "\tMIA Core status = 0x%x\n",
+ (tmp & GS_MIA_MASK) >> GS_MIA_SHIFT);
+ seq_puts(m, "\nScratch registers:\n");
+ for (i = 0; i < 16; i++)
+ seq_printf(m, "\t%2d: \t0x%x\n", i, I915_READ(SOFT_SCRATCH(i)));
+
+ return 0;
+}
+
+static void i915_guc_client_info(struct seq_file *m,
+ struct drm_i915_private *dev_priv,
+ struct i915_guc_client *client)
+{
+ struct intel_engine_cs *ring;
+ uint64_t tot = 0;
+ uint32_t i;
+
+ seq_printf(m, "\tPriority %d, GuC ctx index: %u, PD offset 0x%x\n",
+ client->priority, client->ctx_index, client->proc_desc_offset);
+ seq_printf(m, "\tDoorbell id %d, offset: 0x%x, cookie 0x%x\n",
+ client->doorbell_id, client->doorbell_offset, client->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, "\tFailed to queue: %u\n", client->q_fail);
+ seq_printf(m, "\tFailed doorbell: %u\n", client->b_fail);
+ seq_printf(m, "\tLast submission result: %d\n", client->retcode);
+
+ for_each_ring(ring, dev_priv, i) {
+ seq_printf(m, "\tSubmissions: %llu %s\n",
+ client->submissions[i],
+ ring->name);
+ tot += client->submissions[i];
+ }
+ seq_printf(m, "\tTotal: %llu\n", tot);
+}
+
+static int i915_guc_info(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;
+ struct intel_guc guc;
+ struct i915_guc_client client = {};
+ struct intel_engine_cs *ring;
+ enum intel_ring_id i;
+ u64 total = 0;
+
+ if (!HAS_GUC_SCHED(dev_priv->dev))
+ return 0;
+
+ /* Take a local copy of the GuC data, so we can dump it at leisure */
+ spin_lock(&dev_priv->guc.host2guc_lock);
+ guc = dev_priv->guc;
+ if (guc.execbuf_client) {
+ spin_lock(&guc.execbuf_client->wq_lock);
+ client = *guc.execbuf_client;
+ spin_unlock(&guc.execbuf_client->wq_lock);
+ }
+ spin_unlock(&dev_priv->guc.host2guc_lock);
+
+ seq_printf(m, "GuC total action count: %llu\n", guc.action_count);
+ seq_printf(m, "GuC action failure count: %u\n", guc.action_fail);
+ seq_printf(m, "GuC last action command: 0x%x\n", guc.action_cmd);
+ seq_printf(m, "GuC last action status: 0x%x\n", guc.action_status);
+ seq_printf(m, "GuC last action error code: %d\n", guc.action_err);
+
+ seq_printf(m, "\nGuC submissions:\n");
+ for_each_ring(ring, dev_priv, i) {
+ seq_printf(m, "\t%-24s: %10llu, last seqno 0x%08x %9d\n",
+ ring->name, guc.submissions[i],
+ guc.last_seqno[i], guc.last_seqno[i]);
+ total += guc.submissions[i];
+ }
+ seq_printf(m, "\t%s: %llu\n", "Total", total);
+
+ seq_printf(m, "\nGuC execbuf client @ %p:\n", guc.execbuf_client);
+ i915_guc_client_info(m, dev_priv, &client);
+
+ /* Add more as required ... */
+
+ return 0;
+}
+
+static int i915_guc_log_dump(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;
+ struct drm_i915_gem_object *log_obj = dev_priv->guc.log_obj;
+ u32 *log;
+ int i = 0, pg;
+
+ if (!log_obj)
+ return 0;
+
+ for (pg = 0; pg < log_obj->base.size / PAGE_SIZE; pg++) {
+ log = kmap_atomic(i915_gem_object_get_page(log_obj, pg));
+
+ for (i = 0; i < PAGE_SIZE / sizeof(u32); i += 4)
+ seq_printf(m, "0x%08x 0x%08x 0x%08x 0x%08x\n",
+ *(log + i), *(log + i + 1),
+ *(log + i + 2), *(log + i + 3));
+
+ kunmap_atomic(log);
+ }
+
+ seq_putc(m, '\n');
+
+ 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_crtc *crtc = &intel_crtc->base;
struct intel_encoder *intel_encoder;
+ struct drm_plane_state *plane_state = crtc->primary->state;
+ struct drm_framebuffer *fb = plane_state->fb;
- if (crtc->primary->fb)
+ if (fb)
seq_printf(m, "\tfb: %d, pos: %dx%d, size: %dx%d\n",
- crtc->primary->fb->base.id, crtc->x, crtc->y,
- crtc->primary->fb->width, crtc->primary->fb->height);
+ fb->base.id, plane_state->src_x >> 16,
+ plane_state->src_y >> 16, fb->width, fb->height);
else
seq_puts(m, "\tprimary plane disabled\n");
for_each_encoder_on_crtc(dev, crtc, intel_encoder)
struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base);
seq_printf(m, "\tDPCD rev: %x\n", intel_dp->dpcd[DP_DPCD_REV]);
- seq_printf(m, "\taudio support: %s\n", intel_dp->has_audio ? "yes" :
- "no");
+ seq_printf(m, "\taudio support: %s\n", yesno(intel_dp->has_audio));
if (intel_encoder->type == INTEL_OUTPUT_EDP)
intel_panel_info(m, &intel_connector->panel);
}
struct intel_encoder *intel_encoder = intel_connector->encoder;
struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&intel_encoder->base);
- seq_printf(m, "\taudio support: %s\n", intel_hdmi->has_audio ? "yes" :
- "no");
+ seq_printf(m, "\taudio support: %s\n", yesno(intel_hdmi->has_audio));
}
static void intel_lvds_info(struct seq_file *m,
struct sseu_dev_status *stat)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- const int ss_max = 2;
+ int ss_max = 2;
int ss;
u32 sig1[ss_max], sig2[ss_max];
{"i915_gem_hws_bsd", i915_hws_info, 0, (void *)VCS},
{"i915_gem_hws_vebox", i915_hws_info, 0, (void *)VECS},
{"i915_gem_batch_pool", i915_gem_batch_pool_info, 0},
+ {"i915_guc_info", i915_guc_info, 0},
+ {"i915_guc_load_status", i915_guc_load_status_info, 0},
+ {"i915_guc_log_dump", i915_guc_log_dump, 0},
{"i915_frequency_info", i915_frequency_info, 0},
{"i915_hangcheck_info", i915_hangcheck_info, 0},
{"i915_drpc_info", i915_drpc_info, 0},
dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
/* i915 resume handler doesn't set to D0 */
pci_set_power_state(dev->pdev, PCI_D0);
- i915_resume_legacy(dev);
+ i915_resume_switcheroo(dev);
dev->switch_power_state = DRM_SWITCH_POWER_ON;
} else {
pr_err("switched off\n");
dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
- i915_suspend_legacy(dev, pmm);
+ i915_suspend_switcheroo(dev, pmm);
dev->switch_power_state = DRM_SWITCH_POWER_OFF;
}
}
* working irqs for e.g. gmbus and dp aux transfers. */
intel_modeset_init(dev);
+ /* intel_guc_ucode_init() needs the mutex to allocate GEM objects */
+ mutex_lock(&dev->struct_mutex);
+ intel_guc_ucode_init(dev);
+ mutex_unlock(&dev->struct_mutex);
+
ret = i915_gem_init(dev);
if (ret)
goto cleanup_irq;
i915_gem_context_fini(dev);
mutex_unlock(&dev->struct_mutex);
cleanup_irq:
+ mutex_lock(&dev->struct_mutex);
+ intel_guc_ucode_fini(dev);
+ mutex_unlock(&dev->struct_mutex);
drm_irq_uninstall(dev);
cleanup_gem_stolen:
i915_gem_cleanup_stolen(dev);
u32 fuse2, s_enable, ss_disable, eu_disable;
u8 eu_mask = 0xff;
- /*
- * BXT has a single slice. BXT also has at most 6 EU per subslice,
- * and therefore only the lowest 6 bits of the 8-bit EU disable
- * fields are valid.
- */
- if (IS_BROXTON(dev)) {
- s_max = 1;
- eu_max = 6;
- eu_mask = 0x3f;
- }
-
info = (struct intel_device_info *)&dev_priv->info;
fuse2 = I915_READ(GEN8_FUSE2);
s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >>
info->has_eu_pg ? "y" : "n");
}
+static void intel_init_dpio(struct drm_i915_private *dev_priv)
+{
+ if (!IS_VALLEYVIEW(dev_priv))
+ return;
+
+ /*
+ * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C),
+ * CHV x1 PHY (DP/HDMI D)
+ * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C)
+ */
+ if (IS_CHERRYVIEW(dev_priv)) {
+ DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2;
+ DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO;
+ } else {
+ DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO;
+ }
+}
+
/**
* i915_driver_load - setup chip and create an initial config
* @dev: DRM device
intel_setup_gmbus(dev);
intel_opregion_setup(dev);
- intel_setup_bios(dev);
-
i915_gem_load(dev);
/* On the 945G/GM, the chipset reports the MSI capability on the
intel_device_info_runtime_init(dev);
+ intel_init_dpio(dev_priv);
+
if (INTEL_INFO(dev)->num_pipes) {
ret = drm_vblank_init(dev, INTEL_INFO(dev)->num_pipes);
if (ret)
dev_priv->vbt.child_dev = NULL;
dev_priv->vbt.child_dev_num = 0;
}
+ kfree(dev_priv->vbt.sdvo_lvds_vbt_mode);
+ dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
+ kfree(dev_priv->vbt.lfp_lvds_vbt_mode);
+ dev_priv->vbt.lfp_lvds_vbt_mode = NULL;
vga_switcheroo_unregister_client(dev->pdev);
vga_client_register(dev->pdev, NULL, NULL, NULL);
flush_workqueue(dev_priv->wq);
mutex_lock(&dev->struct_mutex);
+ intel_guc_ucode_fini(dev);
i915_gem_cleanup_ringbuffer(dev);
i915_gem_context_fini(dev);
mutex_unlock(&dev->struct_mutex);
.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
.has_llc = 1,
.has_ddi = 1,
+ .has_fpga_dbg = 1,
.has_fbc = 1,
GEN_DEFAULT_PIPEOFFSETS,
IVB_CURSOR_OFFSETS,
.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
.has_llc = 1,
.has_ddi = 1,
+ .has_fpga_dbg = 1,
.has_fbc = 1,
GEN_DEFAULT_PIPEOFFSETS,
IVB_CURSOR_OFFSETS,
.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
.num_pipes = 3,
.has_ddi = 1,
+ .has_fpga_dbg = 1,
.has_fbc = 1,
GEN_DEFAULT_PIPEOFFSETS,
IVB_CURSOR_OFFSETS,
return 0;
}
-int i915_suspend_legacy(struct drm_device *dev, pm_message_t state)
+int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state)
{
int error;
return ret;
}
-int i915_resume_legacy(struct drm_device *dev)
+int i915_resume_switcheroo(struct drm_device *dev)
{
int ret;
s->gfx_pend_tlb1 = I915_READ(GEN7_GFX_PEND_TLB1);
for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++)
- s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS_BASE + i * 4);
+ s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS(i));
s->media_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT);
s->gfx_max_req_count = I915_READ(GEN7_GFX_MAX_REQ_COUNT);
s->pm_ier = I915_READ(GEN6_PMIER);
for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++)
- s->gt_scratch[i] = I915_READ(GEN7_GT_SCRATCH_BASE + i * 4);
+ s->gt_scratch[i] = I915_READ(GEN7_GT_SCRATCH(i));
/* GT SA CZ domain, 0x100000-0x138124 */
s->tilectl = I915_READ(TILECTL);
I915_WRITE(GEN7_GFX_PEND_TLB1, s->gfx_pend_tlb1);
for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++)
- I915_WRITE(GEN7_LRA_LIMITS_BASE + i * 4, s->lra_limits[i]);
+ I915_WRITE(GEN7_LRA_LIMITS(i), s->lra_limits[i]);
I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->media_max_req_count);
I915_WRITE(GEN7_GFX_MAX_REQ_COUNT, s->gfx_max_req_count);
I915_WRITE(GEN6_PMIER, s->pm_ier);
for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++)
- I915_WRITE(GEN7_GT_SCRATCH_BASE + i * 4, s->gt_scratch[i]);
+ I915_WRITE(GEN7_GT_SCRATCH(i), s->gt_scratch[i]);
/* GT SA CZ domain, 0x100000-0x138124 */
I915_WRITE(TILECTL, s->tilectl);
gen6_update_ring_freq(dev);
intel_runtime_pm_enable_interrupts(dev_priv);
+
+ /*
+ * On VLV/CHV display interrupts are part of the display
+ * power well, so hpd is reinitialized from there. For
+ * everyone else do it here.
+ */
+ if (!IS_VALLEYVIEW(dev_priv))
+ intel_hpd_init(dev_priv);
+
intel_enable_gt_powersave(dev);
if (ret)
*/
.driver_features =
DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | DRIVER_PRIME |
- DRIVER_RENDER,
+ DRIVER_RENDER | DRIVER_MODESET,
.load = i915_driver_load,
.unload = i915_driver_unload,
.open = i915_driver_open,
.postclose = i915_driver_postclose,
.set_busid = drm_pci_set_busid,
- /* Used in place of i915_pm_ops for non-DRIVER_MODESET */
- .suspend = i915_suspend_legacy,
- .resume = i915_resume_legacy,
-
#if defined(CONFIG_DEBUG_FS)
.debugfs_init = i915_debugfs_init,
.debugfs_cleanup = i915_debugfs_cleanup,
* either the i915.modeset prarameter or by the
* vga_text_mode_force boot option.
*/
- driver.driver_features |= DRIVER_MODESET;
if (i915.modeset == 0)
driver.driver_features &= ~DRIVER_MODESET;
#endif
if (!(driver.driver_features & DRIVER_MODESET)) {
- driver.get_vblank_timestamp = NULL;
/* Silently fail loading to not upset userspace. */
DRM_DEBUG_DRIVER("KMS and UMS disabled.\n");
return 0;
}
- /*
- * FIXME: Note that we're lying to the DRM core here so that we can get access
- * to the atomic ioctl and the atomic properties. Only plane operations on
- * a single CRTC will actually work.
- */
- if (driver.driver_features & DRIVER_MODESET)
+ if (i915.nuclear_pageflip)
driver.driver_features |= DRIVER_ATOMIC;
return drm_pci_init(&driver, &i915_pci_driver);
#include <linux/intel-iommu.h>
#include <linux/kref.h>
#include <linux/pm_qos.h>
+#include "intel_guc.h"
/* General customization:
*/
#define DRIVER_NAME "i915"
#define DRIVER_DESC "Intel Graphics"
-#define DRIVER_DATE "20150731"
+#define DRIVER_DATE "20150928"
#undef WARN_ON
/* Many gcc seem to no see through this and fall over :( */
BUILD_BUG_ON(__i915_warn_cond); \
WARN(__i915_warn_cond, "WARN_ON(" #x ")"); })
#else
-#define WARN_ON(x) WARN((x), "WARN_ON(" #x ")")
+#define WARN_ON(x) WARN((x), "WARN_ON(%s)", #x )
#endif
#undef WARN_ON_ONCE
-#define WARN_ON_ONCE(x) WARN_ONCE((x), "WARN_ON_ONCE(" #x ")")
+#define WARN_ON_ONCE(x) WARN_ONCE((x), "WARN_ON_ONCE(%s)", #x )
#define MISSING_CASE(x) WARN(1, "Missing switch case (%lu) in %s\n", \
(long) (x), __func__);
unlikely(__ret_warn_on); \
})
+static inline const char *yesno(bool v)
+{
+ return v ? "yes" : "no";
+}
+
enum pipe {
INVALID_PIPE = -1,
PIPE_A = 0,
struct drm_i915_error_object {
int page_count;
- u32 gtt_offset;
+ u64 gtt_offset;
u32 *pages[0];
} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
u32 size;
u32 name;
u32 rseqno[I915_NUM_RINGS], wseqno;
- u32 gtt_offset;
+ u64 gtt_offset;
u32 read_domains;
u32 write_domain;
s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
uint32_t level);
void (*disable_backlight)(struct intel_connector *connector);
void (*enable_backlight)(struct intel_connector *connector);
+ uint32_t (*backlight_hz_to_pwm)(struct intel_connector *connector,
+ uint32_t hz);
};
enum forcewake_domain_id {
} legacy_hw_ctx;
/* Execlists */
- bool rcs_initialized;
struct {
struct drm_i915_gem_object *state;
struct intel_ringbuffer *ringbuf;
FBC_CHIP_DEFAULT, /* disabled by default on this chip */
FBC_ROTATION, /* rotation is not supported */
FBC_IN_DBG_MASTER, /* kernel debugger is active */
+ FBC_BAD_STRIDE, /* stride is not supported */
+ FBC_PIXEL_RATE, /* pixel rate is too big */
+ FBC_PIXEL_FORMAT /* pixel format is invalid */
} no_fbc_reason;
bool (*fbc_enabled)(struct drm_i915_private *dev_priv);
struct drm_file *file;
uint32_t dispatch_flags;
uint32_t args_batch_start_offset;
- uint32_t batch_obj_vm_offset;
+ uint64_t batch_obj_vm_offset;
struct intel_engine_cs *ring;
struct drm_i915_gem_object *batch_obj;
struct intel_context *ctx;
struct i915_virtual_gpu vgpu;
+ struct intel_guc guc;
+
struct intel_csr csr;
/* Display CSR-related protection */
unsigned int fsb_freq, mem_freq, is_ddr3;
unsigned int skl_boot_cdclk;
unsigned int cdclk_freq, max_cdclk_freq;
+ unsigned int max_dotclk_freq;
unsigned int hpll_freq;
/**
return to_i915(dev_get_drvdata(dev));
}
+static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc)
+{
+ return container_of(guc, struct drm_i915_private, guc);
+}
+
/* Iterate over initialised rings */
#define for_each_ring(ring__, dev_priv__, i__) \
for ((i__) = 0; (i__) < I915_NUM_RINGS; (i__)++) \
/*
* Frontbuffer tracking bits. Set in obj->frontbuffer_bits while a gem bo is
- * considered to be the frontbuffer for the given plane interface-vise. This
+ * considered to be the frontbuffer for the given plane interface-wise. This
* doesn't mean that the hw necessarily already scans it out, but that any
* rendering (by the cpu or gpu) will land in the frontbuffer eventually.
*
* We have one bit per pipe and per scanout plane type.
*/
-#define INTEL_FRONTBUFFER_BITS_PER_PIPE 4
+#define INTEL_MAX_SPRITE_BITS_PER_PIPE 5
+#define INTEL_FRONTBUFFER_BITS_PER_PIPE 8
#define INTEL_FRONTBUFFER_BITS \
(INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES)
#define INTEL_FRONTBUFFER_PRIMARY(pipe) \
(1 << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
#define INTEL_FRONTBUFFER_CURSOR(pipe) \
- (1 << (1 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
-#define INTEL_FRONTBUFFER_SPRITE(pipe) \
- (1 << (2 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+ (1 << (1 + (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+#define INTEL_FRONTBUFFER_SPRITE(pipe, plane) \
+ (1 << (2 + plane + (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
#define INTEL_FRONTBUFFER_OVERLAY(pipe) \
- (1 << (3 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+ (1 << (2 + INTEL_MAX_SPRITE_BITS_PER_PIPE + (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
#define INTEL_FRONTBUFFER_ALL_MASK(pipe) \
- (0xf << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
+ (0xff << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
struct drm_i915_gem_object {
struct drm_gem_object base;
#define IS_SKL_ULX(dev) (INTEL_DEVID(dev) == 0x190E || \
INTEL_DEVID(dev) == 0x1915 || \
INTEL_DEVID(dev) == 0x191E)
+#define IS_SKL_GT3(dev) (IS_SKYLAKE(dev) && \
+ (INTEL_DEVID(dev) & 0x00F0) == 0x0020)
+#define IS_SKL_GT4(dev) (IS_SKYLAKE(dev) && \
+ (INTEL_DEVID(dev) & 0x00F0) == 0x0030)
+
#define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary)
#define SKL_REVID_A0 (0x0)
#define BXT_REVID_A0 (0x0)
#define BXT_REVID_B0 (0x3)
-#define BXT_REVID_C0 (0x6)
+#define BXT_REVID_C0 (0x9)
/*
* The genX designation typically refers to the render engine, so render
#define HAS_HW_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 6)
#define HAS_LOGICAL_RING_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 8)
#define USES_PPGTT(dev) (i915.enable_ppgtt)
-#define USES_FULL_PPGTT(dev) (i915.enable_ppgtt == 2)
+#define USES_FULL_PPGTT(dev) (i915.enable_ppgtt >= 2)
+#define USES_FULL_48BIT_PPGTT(dev) (i915.enable_ppgtt == 3)
#define HAS_OVERLAY(dev) (INTEL_INFO(dev)->has_overlay)
#define OVERLAY_NEEDS_PHYSICAL(dev) (INTEL_INFO(dev)->overlay_needs_physical)
#define HAS_RC6(dev) (INTEL_INFO(dev)->gen >= 6)
#define HAS_RC6p(dev) (INTEL_INFO(dev)->gen == 6 || IS_IVYBRIDGE(dev))
-#define HAS_CSR(dev) (IS_SKYLAKE(dev))
+#define HAS_CSR(dev) (IS_GEN9(dev))
+
+#define HAS_GUC_UCODE(dev) (IS_GEN9(dev))
+#define HAS_GUC_SCHED(dev) (IS_GEN9(dev))
#define HAS_RESOURCE_STREAMER(dev) (IS_HASWELL(dev) || \
INTEL_INFO(dev)->gen >= 8)
#define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type)
#define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT)
#define HAS_PCH_LPT(dev) (INTEL_PCH_TYPE(dev) == PCH_LPT)
+#define HAS_PCH_LPT_LP(dev) (__I915__(dev)->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE)
#define HAS_PCH_CPT(dev) (INTEL_PCH_TYPE(dev) == PCH_CPT)
#define HAS_PCH_IBX(dev) (INTEL_PCH_TYPE(dev) == PCH_IBX)
#define HAS_PCH_NOP(dev) (INTEL_PCH_TYPE(dev) == PCH_NOP)
extern const struct drm_ioctl_desc i915_ioctls[];
extern int i915_max_ioctl;
-extern int i915_suspend_legacy(struct drm_device *dev, pm_message_t state);
-extern int i915_resume_legacy(struct drm_device *dev);
+extern int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state);
+extern int i915_resume_switcheroo(struct drm_device *dev);
/* i915_params.c */
struct i915_params {
int enable_cmd_parser;
/* leave bools at the end to not create holes */
bool enable_hangcheck;
- bool fastboot;
bool prefault_disable;
bool load_detect_test;
bool reset;
int use_mmio_flip;
int mmio_debug;
bool verbose_state_checks;
+ bool nuclear_pageflip;
int edp_vswing;
};
extern struct i915_params i915 __read_mostly;
void valleyview_enable_display_irqs(struct drm_i915_private *dev_priv);
void valleyview_disable_display_irqs(struct drm_i915_private *dev_priv);
+void i915_hotplug_interrupt_update(struct drm_i915_private *dev_priv,
+ uint32_t mask,
+ uint32_t bits);
void
ironlake_enable_display_irq(struct drm_i915_private *dev_priv, u32 mask);
void
size_t size);
struct drm_i915_gem_object *i915_gem_object_create_from_data(
struct drm_device *dev, const void *data, size_t size);
-void i915_init_vm(struct drm_i915_private *dev_priv,
- struct i915_address_space *vm);
void i915_gem_free_object(struct drm_gem_object *obj);
void i915_gem_vma_destroy(struct i915_vma *vma);
struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
struct drm_gem_object *gem_obj, int flags);
-unsigned long
-i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
- const struct i915_ggtt_view *view);
-unsigned long
-i915_gem_obj_offset(struct drm_i915_gem_object *o,
- struct i915_address_space *vm);
-static inline unsigned long
+u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
+ const struct i915_ggtt_view *view);
+u64 i915_gem_obj_offset(struct drm_i915_gem_object *o,
+ struct i915_address_space *vm);
+static inline u64
i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o)
{
return i915_gem_obj_ggtt_offset_view(o, &i915_ggtt_view_normal);
int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv,
struct drm_mm_node *node, u64 size,
unsigned alignment);
+int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
+ struct drm_mm_node *node, u64 size,
+ unsigned alignment, u64 start,
+ u64 end);
void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv,
struct drm_mm_node *node);
int i915_gem_init_stolen(struct drm_device *dev);
if (!needs_clflush_after &&
obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
if (i915_gem_clflush_object(obj, obj->pin_display))
- i915_gem_chipset_flush(dev);
+ needs_clflush_after = true;
}
}
if (needs_clflush_after)
i915_gem_chipset_flush(dev);
+ else
+ obj->cache_dirty = true;
intel_fb_obj_flush(obj, false, ORIGIN_CPU);
return ret;
/**
* i915_gem_fault - fault a page into the GTT
- * vma: VMA in question
- * vmf: fault info
+ * @vma: VMA in question
+ * @vmf: fault info
*
* The fault handler is set up by drm_gem_mmap() when a object is GTT mapped
* from userspace. The fault handler takes care of binding the object to
ret = i915_gem_object_wait_rendering(obj, false);
if (ret)
return ret;
- /* Continue on if we fail due to EIO, the GPU is hung so we
- * should be safe and we need to cleanup or else we might
- * cause memory corruption through use-after-free.
- */
if (i915_is_ggtt(vma->vm) &&
vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL) {
{
struct drm_device *dev = obj->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 size, fence_size, fence_alignment, unfenced_alignment;
+ u32 fence_alignment, unfenced_alignment;
+ u64 size, fence_size;
u64 start =
flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0;
u64 end =
* attempt to find space.
*/
if (size > end) {
- DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%u > %s aperture=%llu\n",
+ DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%llu > %s aperture=%llu\n",
ggtt_view ? ggtt_view->type : 0,
size,
flags & PIN_MAPPABLE ? "mappable" : "total",
{
struct drm_device *dev = obj->base.dev;
struct i915_vma *vma, *next;
- int ret;
+ int ret = 0;
if (obj->cache_level == cache_level)
- return 0;
+ goto out;
if (i915_gem_obj_is_pinned(obj)) {
DRM_DEBUG("can not change the cache level of pinned objects\n");
vma->node.color = cache_level;
obj->cache_level = cache_level;
+out:
if (obj->cache_dirty &&
obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
cpu_write_needs_clflush(obj)) {
level = I915_CACHE_NONE;
break;
case I915_CACHING_CACHED:
+ /*
+ * Due to a HW issue on BXT A stepping, GPU stores via a
+ * snooped mapping may leave stale data in a corresponding CPU
+ * cacheline, whereas normally such cachelines would get
+ * invalidated.
+ */
+ if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0)
+ return -ENODEV;
+
level = I915_CACHE_LLC;
break;
case I915_CACHING_DISPLAY:
return -EBUSY;
if (i915_vma_misplaced(vma, alignment, flags)) {
- unsigned long offset;
- offset = ggtt_view ? i915_gem_obj_ggtt_offset_view(obj, ggtt_view) :
- i915_gem_obj_offset(obj, vm);
WARN(vma->pin_count,
"bo is already pinned in %s with incorrect alignment:"
- " offset=%lx, req.alignment=%x, req.map_and_fenceable=%d,"
+ " offset=%08x %08x, req.alignment=%x, req.map_and_fenceable=%d,"
" obj->map_and_fenceable=%d\n",
ggtt_view ? "ggtt" : "ppgtt",
- offset,
+ upper_32_bits(vma->node.start),
+ lower_32_bits(vma->node.start),
alignment,
!!(flags & PIN_MAPPABLE),
obj->map_and_fenceable);
goto cleanup_vebox_ring;
}
- ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
- if (ret)
- goto cleanup_bsd2_ring;
-
return 0;
-cleanup_bsd2_ring:
- intel_cleanup_ring_buffer(&dev_priv->ring[VCS2]);
cleanup_vebox_ring:
intel_cleanup_ring_buffer(&dev_priv->ring[VECS]);
cleanup_blt_ring:
goto out;
}
+ /* We can't enable contexts until all firmware is loaded */
+ if (HAS_GUC_UCODE(dev)) {
+ ret = intel_guc_ucode_load(dev);
+ if (ret) {
+ /*
+ * If we got an error and GuC submission is enabled, map
+ * the error to -EIO so the GPU will be declared wedged.
+ * OTOH, if we didn't intend to use the GuC anyway, just
+ * discard the error and carry on.
+ */
+ DRM_ERROR("Failed to initialize GuC, error %d%s\n", ret,
+ i915.enable_guc_submission ? "" :
+ " (ignored)");
+ ret = i915.enable_guc_submission ? -EIO : 0;
+ if (ret)
+ goto out;
+ }
+ }
+
+ /*
+ * Increment the next seqno by 0x100 so we have a visible break
+ * on re-initialisation
+ */
+ ret = i915_gem_set_seqno(dev, dev_priv->next_seqno+0x100);
+ if (ret)
+ goto out;
+
/* Now it is safe to go back round and do everything else: */
for_each_ring(ring, dev_priv, i) {
struct drm_i915_gem_request *req;
INIT_LIST_HEAD(&ring->request_list);
}
-void i915_init_vm(struct drm_i915_private *dev_priv,
- struct i915_address_space *vm)
-{
- if (!i915_is_ggtt(vm))
- drm_mm_init(&vm->mm, vm->start, vm->total);
- vm->dev = dev_priv->dev;
- INIT_LIST_HEAD(&vm->active_list);
- INIT_LIST_HEAD(&vm->inactive_list);
- INIT_LIST_HEAD(&vm->global_link);
- list_add_tail(&vm->global_link, &dev_priv->vm_list);
-}
-
void
i915_gem_load(struct drm_device *dev)
{
NULL);
INIT_LIST_HEAD(&dev_priv->vm_list);
- i915_init_vm(dev_priv, &dev_priv->gtt.base);
-
INIT_LIST_HEAD(&dev_priv->context_list);
INIT_LIST_HEAD(&dev_priv->mm.unbound_list);
INIT_LIST_HEAD(&dev_priv->mm.bound_list);
dev_priv->num_fence_regs =
I915_READ(vgtif_reg(avail_rs.fence_num));
+ /*
+ * Set initial sequence number for requests.
+ * Using this number allows the wraparound to happen early,
+ * catching any obvious problems.
+ */
+ dev_priv->next_seqno = ((u32)~0 - 0x1100);
+ dev_priv->last_seqno = ((u32)~0 - 0x1101);
+
/* Initialize fence registers to zero */
INIT_LIST_HEAD(&dev_priv->mm.fence_list);
i915_gem_restore_fences(dev);
/**
* i915_gem_track_fb - update frontbuffer tracking
- * old: current GEM buffer for the frontbuffer slots
- * new: new GEM buffer for the frontbuffer slots
- * frontbuffer_bits: bitmask of frontbuffer slots
+ * @old: current GEM buffer for the frontbuffer slots
+ * @new: new GEM buffer for the frontbuffer slots
+ * @frontbuffer_bits: bitmask of frontbuffer slots
*
* This updates the frontbuffer tracking bits @frontbuffer_bits by clearing them
* from @old and setting them in @new. Both @old and @new can be NULL.
}
/* All the new VM stuff */
-unsigned long
-i915_gem_obj_offset(struct drm_i915_gem_object *o,
- struct i915_address_space *vm)
+u64 i915_gem_obj_offset(struct drm_i915_gem_object *o,
+ struct i915_address_space *vm)
{
struct drm_i915_private *dev_priv = o->base.dev->dev_private;
struct i915_vma *vma;
return -1;
}
-unsigned long
-i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
- const struct i915_ggtt_view *view)
+u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
+ const struct i915_ggtt_view *view)
{
struct i915_address_space *ggtt = i915_obj_to_ggtt(o);
struct i915_vma *vma;
if (WARN_ON(dev_priv->ring[RCS].default_context))
return 0;
+ if (intel_vgpu_active(dev) && HAS_LOGICAL_RING_CONTEXTS(dev)) {
+ if (!i915.enable_execlists) {
+ DRM_INFO("Only EXECLIST mode is supported in vgpu.\n");
+ return -EINVAL;
+ }
+ }
+
if (i915.enable_execlists) {
/* NB: intentionally left blank. We will allocate our own
* backing objects as we need them, thank you very much */
}
if (i915.enable_execlists && !ctx->engine[ring->id].state) {
- int ret = intel_lr_context_deferred_create(ctx, ring);
+ int ret = intel_lr_context_deferred_alloc(ctx, ring);
if (ret) {
DRM_DEBUG("Could not create LRC %u: %d\n", ctx_id, ret);
return ERR_PTR(ret);
WARN((i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK) ||
(size & -size) != size ||
(i915_gem_obj_ggtt_offset(obj) & (size - 1)),
- "object 0x%08lx [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n",
+ "object 0x%08llx [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))
WARN((i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK) ||
(size & -size) != size ||
(i915_gem_obj_ggtt_offset(obj) & (size - 1)),
- "object 0x%08lx not 512K or pot-size 0x%08x aligned\n",
+ "object 0x%08llx not 512K or pot-size 0x%08x aligned\n",
i915_gem_obj_ggtt_offset(obj), size);
pitch_val = obj->stride / 128;
return pde;
}
+#define gen8_pdpe_encode gen8_pde_encode
+#define gen8_pml4e_encode gen8_pde_encode
+
static gen6_pte_t snb_pte_encode(dma_addr_t addr,
enum i915_cache_level level,
bool valid, u32 unused)
fill_px(vm->dev, pd, scratch_pde);
}
+static int __pdp_init(struct drm_device *dev,
+ struct i915_page_directory_pointer *pdp)
+{
+ size_t pdpes = I915_PDPES_PER_PDP(dev);
+
+ pdp->used_pdpes = kcalloc(BITS_TO_LONGS(pdpes),
+ sizeof(unsigned long),
+ GFP_KERNEL);
+ if (!pdp->used_pdpes)
+ return -ENOMEM;
+
+ pdp->page_directory = kcalloc(pdpes, sizeof(*pdp->page_directory),
+ GFP_KERNEL);
+ if (!pdp->page_directory) {
+ kfree(pdp->used_pdpes);
+ /* the PDP might be the statically allocated top level. Keep it
+ * as clean as possible */
+ pdp->used_pdpes = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void __pdp_fini(struct i915_page_directory_pointer *pdp)
+{
+ kfree(pdp->used_pdpes);
+ kfree(pdp->page_directory);
+ pdp->page_directory = NULL;
+}
+
+static struct
+i915_page_directory_pointer *alloc_pdp(struct drm_device *dev)
+{
+ struct i915_page_directory_pointer *pdp;
+ int ret = -ENOMEM;
+
+ WARN_ON(!USES_FULL_48BIT_PPGTT(dev));
+
+ pdp = kzalloc(sizeof(*pdp), GFP_KERNEL);
+ if (!pdp)
+ return ERR_PTR(-ENOMEM);
+
+ ret = __pdp_init(dev, pdp);
+ if (ret)
+ goto fail_bitmap;
+
+ ret = setup_px(dev, pdp);
+ if (ret)
+ goto fail_page_m;
+
+ return pdp;
+
+fail_page_m:
+ __pdp_fini(pdp);
+fail_bitmap:
+ kfree(pdp);
+
+ return ERR_PTR(ret);
+}
+
+static void free_pdp(struct drm_device *dev,
+ struct i915_page_directory_pointer *pdp)
+{
+ __pdp_fini(pdp);
+ if (USES_FULL_48BIT_PPGTT(dev)) {
+ cleanup_px(dev, pdp);
+ kfree(pdp);
+ }
+}
+
+static void gen8_initialize_pdp(struct i915_address_space *vm,
+ struct i915_page_directory_pointer *pdp)
+{
+ gen8_ppgtt_pdpe_t scratch_pdpe;
+
+ scratch_pdpe = gen8_pdpe_encode(px_dma(vm->scratch_pd), I915_CACHE_LLC);
+
+ fill_px(vm->dev, pdp, scratch_pdpe);
+}
+
+static void gen8_initialize_pml4(struct i915_address_space *vm,
+ struct i915_pml4 *pml4)
+{
+ gen8_ppgtt_pml4e_t scratch_pml4e;
+
+ scratch_pml4e = gen8_pml4e_encode(px_dma(vm->scratch_pdp),
+ I915_CACHE_LLC);
+
+ fill_px(vm->dev, pml4, scratch_pml4e);
+}
+
+static void
+gen8_setup_page_directory(struct i915_hw_ppgtt *ppgtt,
+ struct i915_page_directory_pointer *pdp,
+ struct i915_page_directory *pd,
+ int index)
+{
+ gen8_ppgtt_pdpe_t *page_directorypo;
+
+ if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev))
+ return;
+
+ page_directorypo = kmap_px(pdp);
+ page_directorypo[index] = gen8_pdpe_encode(px_dma(pd), I915_CACHE_LLC);
+ kunmap_px(ppgtt, page_directorypo);
+}
+
+static void
+gen8_setup_page_directory_pointer(struct i915_hw_ppgtt *ppgtt,
+ struct i915_pml4 *pml4,
+ struct i915_page_directory_pointer *pdp,
+ int index)
+{
+ gen8_ppgtt_pml4e_t *pagemap = kmap_px(pml4);
+
+ WARN_ON(!USES_FULL_48BIT_PPGTT(ppgtt->base.dev));
+ pagemap[index] = gen8_pml4e_encode(px_dma(pdp), I915_CACHE_LLC);
+ kunmap_px(ppgtt, pagemap);
+}
+
/* Broadwell Page Directory Pointer Descriptors */
static int gen8_write_pdp(struct drm_i915_gem_request *req,
unsigned entry,
return 0;
}
-static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct drm_i915_gem_request *req)
+static int gen8_legacy_mm_switch(struct i915_hw_ppgtt *ppgtt,
+ struct drm_i915_gem_request *req)
{
int i, ret;
return 0;
}
-static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
- uint64_t start,
- uint64_t length,
- bool use_scratch)
+static int gen8_48b_mm_switch(struct i915_hw_ppgtt *ppgtt,
+ struct drm_i915_gem_request *req)
+{
+ return gen8_write_pdp(req, 0, px_dma(&ppgtt->pml4));
+}
+
+static void gen8_ppgtt_clear_pte_range(struct i915_address_space *vm,
+ struct i915_page_directory_pointer *pdp,
+ uint64_t start,
+ uint64_t length,
+ gen8_pte_t scratch_pte)
{
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
- gen8_pte_t *pt_vaddr, scratch_pte;
- unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
- unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
- unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
+ gen8_pte_t *pt_vaddr;
+ unsigned pdpe = gen8_pdpe_index(start);
+ unsigned pde = gen8_pde_index(start);
+ unsigned pte = gen8_pte_index(start);
unsigned num_entries = length >> PAGE_SHIFT;
unsigned last_pte, i;
- scratch_pte = gen8_pte_encode(px_dma(ppgtt->base.scratch_page),
- I915_CACHE_LLC, use_scratch);
+ if (WARN_ON(!pdp))
+ return;
while (num_entries) {
struct i915_page_directory *pd;
struct i915_page_table *pt;
- if (WARN_ON(!ppgtt->pdp.page_directory[pdpe]))
+ if (WARN_ON(!pdp->page_directory[pdpe]))
break;
- pd = ppgtt->pdp.page_directory[pdpe];
+ pd = pdp->page_directory[pdpe];
if (WARN_ON(!pd->page_table[pde]))
break;
pte = 0;
if (++pde == I915_PDES) {
- pdpe++;
+ if (++pdpe == I915_PDPES_PER_PDP(vm->dev))
+ break;
pde = 0;
}
}
}
-static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
- struct sg_table *pages,
- uint64_t start,
- enum i915_cache_level cache_level, u32 unused)
+static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
+ uint64_t start,
+ uint64_t length,
+ bool use_scratch)
+{
+ struct i915_hw_ppgtt *ppgtt =
+ container_of(vm, struct i915_hw_ppgtt, base);
+ gen8_pte_t scratch_pte = gen8_pte_encode(px_dma(vm->scratch_page),
+ I915_CACHE_LLC, use_scratch);
+
+ if (!USES_FULL_48BIT_PPGTT(vm->dev)) {
+ gen8_ppgtt_clear_pte_range(vm, &ppgtt->pdp, start, length,
+ scratch_pte);
+ } else {
+ uint64_t templ4, pml4e;
+ struct i915_page_directory_pointer *pdp;
+
+ gen8_for_each_pml4e(pdp, &ppgtt->pml4, start, length, templ4, pml4e) {
+ gen8_ppgtt_clear_pte_range(vm, pdp, start, length,
+ scratch_pte);
+ }
+ }
+}
+
+static void
+gen8_ppgtt_insert_pte_entries(struct i915_address_space *vm,
+ struct i915_page_directory_pointer *pdp,
+ struct sg_page_iter *sg_iter,
+ uint64_t start,
+ enum i915_cache_level cache_level)
{
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
gen8_pte_t *pt_vaddr;
- unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
- unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
- unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
- struct sg_page_iter sg_iter;
+ unsigned pdpe = gen8_pdpe_index(start);
+ unsigned pde = gen8_pde_index(start);
+ unsigned pte = gen8_pte_index(start);
pt_vaddr = NULL;
- for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
- if (WARN_ON(pdpe >= GEN8_LEGACY_PDPES))
- break;
-
+ while (__sg_page_iter_next(sg_iter)) {
if (pt_vaddr == NULL) {
- struct i915_page_directory *pd = ppgtt->pdp.page_directory[pdpe];
+ struct i915_page_directory *pd = pdp->page_directory[pdpe];
struct i915_page_table *pt = pd->page_table[pde];
pt_vaddr = kmap_px(pt);
}
pt_vaddr[pte] =
- gen8_pte_encode(sg_page_iter_dma_address(&sg_iter),
+ gen8_pte_encode(sg_page_iter_dma_address(sg_iter),
cache_level, true);
if (++pte == GEN8_PTES) {
kunmap_px(ppgtt, pt_vaddr);
pt_vaddr = NULL;
if (++pde == I915_PDES) {
- pdpe++;
+ if (++pdpe == I915_PDPES_PER_PDP(vm->dev))
+ break;
pde = 0;
}
pte = 0;
kunmap_px(ppgtt, pt_vaddr);
}
+static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
+ struct sg_table *pages,
+ uint64_t start,
+ enum i915_cache_level cache_level,
+ u32 unused)
+{
+ struct i915_hw_ppgtt *ppgtt =
+ container_of(vm, struct i915_hw_ppgtt, base);
+ struct sg_page_iter sg_iter;
+
+ __sg_page_iter_start(&sg_iter, pages->sgl, sg_nents(pages->sgl), 0);
+
+ if (!USES_FULL_48BIT_PPGTT(vm->dev)) {
+ gen8_ppgtt_insert_pte_entries(vm, &ppgtt->pdp, &sg_iter, start,
+ cache_level);
+ } else {
+ struct i915_page_directory_pointer *pdp;
+ uint64_t templ4, pml4e;
+ uint64_t length = (uint64_t)pages->orig_nents << PAGE_SHIFT;
+
+ gen8_for_each_pml4e(pdp, &ppgtt->pml4, start, length, templ4, pml4e) {
+ gen8_ppgtt_insert_pte_entries(vm, pdp, &sg_iter,
+ start, cache_level);
+ }
+ }
+}
+
static void gen8_free_page_tables(struct drm_device *dev,
struct i915_page_directory *pd)
{
return PTR_ERR(vm->scratch_pd);
}
+ if (USES_FULL_48BIT_PPGTT(dev)) {
+ vm->scratch_pdp = alloc_pdp(dev);
+ if (IS_ERR(vm->scratch_pdp)) {
+ free_pd(dev, vm->scratch_pd);
+ free_pt(dev, vm->scratch_pt);
+ free_scratch_page(dev, vm->scratch_page);
+ return PTR_ERR(vm->scratch_pdp);
+ }
+ }
+
gen8_initialize_pt(vm, vm->scratch_pt);
gen8_initialize_pd(vm, vm->scratch_pd);
+ if (USES_FULL_48BIT_PPGTT(dev))
+ gen8_initialize_pdp(vm, vm->scratch_pdp);
+
+ return 0;
+}
+
+static int gen8_ppgtt_notify_vgt(struct i915_hw_ppgtt *ppgtt, bool create)
+{
+ enum vgt_g2v_type msg;
+ struct drm_device *dev = ppgtt->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned int offset = vgtif_reg(pdp0_lo);
+ int i;
+
+ if (USES_FULL_48BIT_PPGTT(dev)) {
+ u64 daddr = px_dma(&ppgtt->pml4);
+
+ I915_WRITE(offset, lower_32_bits(daddr));
+ I915_WRITE(offset + 4, upper_32_bits(daddr));
+
+ msg = (create ? VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE :
+ VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY);
+ } else {
+ for (i = 0; i < GEN8_LEGACY_PDPES; i++) {
+ u64 daddr = i915_page_dir_dma_addr(ppgtt, i);
+
+ I915_WRITE(offset, lower_32_bits(daddr));
+ I915_WRITE(offset + 4, upper_32_bits(daddr));
+
+ offset += 8;
+ }
+
+ msg = (create ? VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE :
+ VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY);
+ }
+
+ I915_WRITE(vgtif_reg(g2v_notify), msg);
return 0;
}
{
struct drm_device *dev = vm->dev;
+ if (USES_FULL_48BIT_PPGTT(dev))
+ free_pdp(dev, vm->scratch_pdp);
free_pd(dev, vm->scratch_pd);
free_pt(dev, vm->scratch_pt);
free_scratch_page(dev, vm->scratch_page);
}
-static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
+static void gen8_ppgtt_cleanup_3lvl(struct drm_device *dev,
+ struct i915_page_directory_pointer *pdp)
+{
+ int i;
+
+ for_each_set_bit(i, pdp->used_pdpes, I915_PDPES_PER_PDP(dev)) {
+ if (WARN_ON(!pdp->page_directory[i]))
+ continue;
+
+ gen8_free_page_tables(dev, pdp->page_directory[i]);
+ free_pd(dev, pdp->page_directory[i]);
+ }
+
+ free_pdp(dev, pdp);
+}
+
+static void gen8_ppgtt_cleanup_4lvl(struct i915_hw_ppgtt *ppgtt)
{
- struct i915_hw_ppgtt *ppgtt =
- container_of(vm, struct i915_hw_ppgtt, base);
int i;
- for_each_set_bit(i, ppgtt->pdp.used_pdpes, GEN8_LEGACY_PDPES) {
- if (WARN_ON(!ppgtt->pdp.page_directory[i]))
+ for_each_set_bit(i, ppgtt->pml4.used_pml4es, GEN8_PML4ES_PER_PML4) {
+ if (WARN_ON(!ppgtt->pml4.pdps[i]))
continue;
- gen8_free_page_tables(ppgtt->base.dev,
- ppgtt->pdp.page_directory[i]);
- free_pd(ppgtt->base.dev, ppgtt->pdp.page_directory[i]);
+ gen8_ppgtt_cleanup_3lvl(ppgtt->base.dev, ppgtt->pml4.pdps[i]);
}
+ cleanup_px(ppgtt->base.dev, &ppgtt->pml4);
+}
+
+static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
+{
+ struct i915_hw_ppgtt *ppgtt =
+ container_of(vm, struct i915_hw_ppgtt, base);
+
+ if (intel_vgpu_active(vm->dev))
+ gen8_ppgtt_notify_vgt(ppgtt, false);
+
+ if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev))
+ gen8_ppgtt_cleanup_3lvl(ppgtt->base.dev, &ppgtt->pdp);
+ else
+ gen8_ppgtt_cleanup_4lvl(ppgtt);
+
gen8_free_scratch(vm);
}
/**
* gen8_ppgtt_alloc_pagetabs() - Allocate page tables for VA range.
- * @ppgtt: Master ppgtt structure.
- * @pd: Page directory for this address range.
+ * @vm: Master vm structure.
+ * @pd: Page directory for this address range.
* @start: Starting virtual address to begin allocations.
- * @length Size of the allocations.
+ * @length: Size of the allocations.
* @new_pts: Bitmap set by function with new allocations. Likely used by the
* caller to free on error.
*
*
* Return: 0 if success; negative error code otherwise.
*/
-static int gen8_ppgtt_alloc_pagetabs(struct i915_hw_ppgtt *ppgtt,
+static int gen8_ppgtt_alloc_pagetabs(struct i915_address_space *vm,
struct i915_page_directory *pd,
uint64_t start,
uint64_t length,
unsigned long *new_pts)
{
- struct drm_device *dev = ppgtt->base.dev;
+ struct drm_device *dev = vm->dev;
struct i915_page_table *pt;
uint64_t temp;
uint32_t pde;
gen8_for_each_pde(pt, pd, start, length, temp, pde) {
/* Don't reallocate page tables */
- if (pt) {
+ if (test_bit(pde, pd->used_pdes)) {
/* Scratch is never allocated this way */
- WARN_ON(pt == ppgtt->base.scratch_pt);
+ WARN_ON(pt == vm->scratch_pt);
continue;
}
if (IS_ERR(pt))
goto unwind_out;
- gen8_initialize_pt(&ppgtt->base, pt);
+ gen8_initialize_pt(vm, pt);
pd->page_table[pde] = pt;
__set_bit(pde, new_pts);
+ trace_i915_page_table_entry_alloc(vm, pde, start, GEN8_PDE_SHIFT);
}
return 0;
/**
* gen8_ppgtt_alloc_page_directories() - Allocate page directories for VA range.
- * @ppgtt: Master ppgtt structure.
+ * @vm: Master vm structure.
* @pdp: Page directory pointer for this address range.
* @start: Starting virtual address to begin allocations.
- * @length Size of the allocations.
- * @new_pds Bitmap set by function with new allocations. Likely used by the
+ * @length: Size of the allocations.
+ * @new_pds: Bitmap set by function with new allocations. Likely used by the
* caller to free on error.
*
* Allocate the required number of page directories starting at the pde index of
*
* Return: 0 if success; negative error code otherwise.
*/
-static int gen8_ppgtt_alloc_page_directories(struct i915_hw_ppgtt *ppgtt,
- struct i915_page_directory_pointer *pdp,
- uint64_t start,
- uint64_t length,
- unsigned long *new_pds)
+static int
+gen8_ppgtt_alloc_page_directories(struct i915_address_space *vm,
+ struct i915_page_directory_pointer *pdp,
+ uint64_t start,
+ uint64_t length,
+ unsigned long *new_pds)
{
- struct drm_device *dev = ppgtt->base.dev;
+ struct drm_device *dev = vm->dev;
struct i915_page_directory *pd;
uint64_t temp;
uint32_t pdpe;
+ uint32_t pdpes = I915_PDPES_PER_PDP(dev);
- WARN_ON(!bitmap_empty(new_pds, GEN8_LEGACY_PDPES));
+ WARN_ON(!bitmap_empty(new_pds, pdpes));
gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) {
- if (pd)
+ if (test_bit(pdpe, pdp->used_pdpes))
continue;
pd = alloc_pd(dev);
if (IS_ERR(pd))
goto unwind_out;
- gen8_initialize_pd(&ppgtt->base, pd);
+ gen8_initialize_pd(vm, pd);
pdp->page_directory[pdpe] = pd;
__set_bit(pdpe, new_pds);
+ trace_i915_page_directory_entry_alloc(vm, pdpe, start, GEN8_PDPE_SHIFT);
}
return 0;
unwind_out:
- for_each_set_bit(pdpe, new_pds, GEN8_LEGACY_PDPES)
+ for_each_set_bit(pdpe, new_pds, pdpes)
free_pd(dev, pdp->page_directory[pdpe]);
return -ENOMEM;
}
-static void
-free_gen8_temp_bitmaps(unsigned long *new_pds, unsigned long **new_pts)
+/**
+ * gen8_ppgtt_alloc_page_dirpointers() - Allocate pdps for VA range.
+ * @vm: Master vm structure.
+ * @pml4: Page map level 4 for this address range.
+ * @start: Starting virtual address to begin allocations.
+ * @length: Size of the allocations.
+ * @new_pdps: Bitmap set by function with new allocations. Likely used by the
+ * caller to free on error.
+ *
+ * Allocate the required number of page directory pointers. Extremely similar to
+ * gen8_ppgtt_alloc_page_directories() and gen8_ppgtt_alloc_pagetabs().
+ * The main difference is here we are limited by the pml4 boundary (instead of
+ * the page directory pointer).
+ *
+ * Return: 0 if success; negative error code otherwise.
+ */
+static int
+gen8_ppgtt_alloc_page_dirpointers(struct i915_address_space *vm,
+ struct i915_pml4 *pml4,
+ uint64_t start,
+ uint64_t length,
+ unsigned long *new_pdps)
{
- int i;
+ struct drm_device *dev = vm->dev;
+ struct i915_page_directory_pointer *pdp;
+ uint64_t temp;
+ uint32_t pml4e;
+
+ WARN_ON(!bitmap_empty(new_pdps, GEN8_PML4ES_PER_PML4));
+
+ gen8_for_each_pml4e(pdp, pml4, start, length, temp, pml4e) {
+ if (!test_bit(pml4e, pml4->used_pml4es)) {
+ pdp = alloc_pdp(dev);
+ if (IS_ERR(pdp))
+ goto unwind_out;
+
+ gen8_initialize_pdp(vm, pdp);
+ pml4->pdps[pml4e] = pdp;
+ __set_bit(pml4e, new_pdps);
+ trace_i915_page_directory_pointer_entry_alloc(vm,
+ pml4e,
+ start,
+ GEN8_PML4E_SHIFT);
+ }
+ }
+
+ return 0;
+
+unwind_out:
+ for_each_set_bit(pml4e, new_pdps, GEN8_PML4ES_PER_PML4)
+ free_pdp(dev, pml4->pdps[pml4e]);
+
+ return -ENOMEM;
+}
- for (i = 0; i < GEN8_LEGACY_PDPES; i++)
- kfree(new_pts[i]);
+static void
+free_gen8_temp_bitmaps(unsigned long *new_pds, unsigned long *new_pts)
+{
kfree(new_pts);
kfree(new_pds);
}
*/
static
int __must_check alloc_gen8_temp_bitmaps(unsigned long **new_pds,
- unsigned long ***new_pts)
+ unsigned long **new_pts,
+ uint32_t pdpes)
{
- int i;
unsigned long *pds;
- unsigned long **pts;
+ unsigned long *pts;
- pds = kcalloc(BITS_TO_LONGS(GEN8_LEGACY_PDPES), sizeof(unsigned long), GFP_KERNEL);
+ pds = kcalloc(BITS_TO_LONGS(pdpes), sizeof(unsigned long), GFP_TEMPORARY);
if (!pds)
return -ENOMEM;
- pts = kcalloc(GEN8_LEGACY_PDPES, sizeof(unsigned long *), GFP_KERNEL);
- if (!pts) {
- kfree(pds);
- return -ENOMEM;
- }
-
- for (i = 0; i < GEN8_LEGACY_PDPES; i++) {
- pts[i] = kcalloc(BITS_TO_LONGS(I915_PDES),
- sizeof(unsigned long), GFP_KERNEL);
- if (!pts[i])
- goto err_out;
- }
+ pts = kcalloc(pdpes, BITS_TO_LONGS(I915_PDES) * sizeof(unsigned long),
+ GFP_TEMPORARY);
+ if (!pts)
+ goto err_out;
*new_pds = pds;
*new_pts = pts;
ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->base.dev)->ring_mask;
}
-static int gen8_alloc_va_range(struct i915_address_space *vm,
- uint64_t start,
- uint64_t length)
+static int gen8_alloc_va_range_3lvl(struct i915_address_space *vm,
+ struct i915_page_directory_pointer *pdp,
+ uint64_t start,
+ uint64_t length)
{
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
- unsigned long *new_page_dirs, **new_page_tables;
+ unsigned long *new_page_dirs, *new_page_tables;
+ struct drm_device *dev = vm->dev;
struct i915_page_directory *pd;
const uint64_t orig_start = start;
const uint64_t orig_length = length;
uint64_t temp;
uint32_t pdpe;
+ uint32_t pdpes = I915_PDPES_PER_PDP(dev);
int ret;
/* Wrap is never okay since we can only represent 48b, and we don't
if (WARN_ON(start + length < start))
return -ENODEV;
- if (WARN_ON(start + length > ppgtt->base.total))
+ if (WARN_ON(start + length > vm->total))
return -ENODEV;
- ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables);
+ ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables, pdpes);
if (ret)
return ret;
/* Do the allocations first so we can easily bail out */
- ret = gen8_ppgtt_alloc_page_directories(ppgtt, &ppgtt->pdp, start, length,
- new_page_dirs);
+ ret = gen8_ppgtt_alloc_page_directories(vm, pdp, start, length,
+ new_page_dirs);
if (ret) {
free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
return ret;
}
/* For every page directory referenced, allocate page tables */
- gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
- ret = gen8_ppgtt_alloc_pagetabs(ppgtt, pd, start, length,
- new_page_tables[pdpe]);
+ gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) {
+ ret = gen8_ppgtt_alloc_pagetabs(vm, pd, start, length,
+ new_page_tables + pdpe * BITS_TO_LONGS(I915_PDES));
if (ret)
goto err_out;
}
/* Allocations have completed successfully, so set the bitmaps, and do
* the mappings. */
- gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
+ gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) {
gen8_pde_t *const page_directory = kmap_px(pd);
struct i915_page_table *pt;
- uint64_t pd_len = gen8_clamp_pd(start, length);
+ uint64_t pd_len = length;
uint64_t pd_start = start;
uint32_t pde;
/* Map the PDE to the page table */
page_directory[pde] = gen8_pde_encode(px_dma(pt),
I915_CACHE_LLC);
+ trace_i915_page_table_entry_map(&ppgtt->base, pde, pt,
+ gen8_pte_index(start),
+ gen8_pte_count(start, length),
+ GEN8_PTES);
/* NB: We haven't yet mapped ptes to pages. At this
* point we're still relying on insert_entries() */
}
kunmap_px(ppgtt, page_directory);
-
- __set_bit(pdpe, ppgtt->pdp.used_pdpes);
+ __set_bit(pdpe, pdp->used_pdpes);
+ gen8_setup_page_directory(ppgtt, pdp, pd, pdpe);
}
free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
err_out:
while (pdpe--) {
- for_each_set_bit(temp, new_page_tables[pdpe], I915_PDES)
- free_pt(vm->dev, ppgtt->pdp.page_directory[pdpe]->page_table[temp]);
+ for_each_set_bit(temp, new_page_tables + pdpe *
+ BITS_TO_LONGS(I915_PDES), I915_PDES)
+ free_pt(dev, pdp->page_directory[pdpe]->page_table[temp]);
}
- for_each_set_bit(pdpe, new_page_dirs, GEN8_LEGACY_PDPES)
- free_pd(vm->dev, ppgtt->pdp.page_directory[pdpe]);
+ for_each_set_bit(pdpe, new_page_dirs, pdpes)
+ free_pd(dev, pdp->page_directory[pdpe]);
free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
mark_tlbs_dirty(ppgtt);
return ret;
}
+static int gen8_alloc_va_range_4lvl(struct i915_address_space *vm,
+ struct i915_pml4 *pml4,
+ uint64_t start,
+ uint64_t length)
+{
+ DECLARE_BITMAP(new_pdps, GEN8_PML4ES_PER_PML4);
+ struct i915_hw_ppgtt *ppgtt =
+ container_of(vm, struct i915_hw_ppgtt, base);
+ struct i915_page_directory_pointer *pdp;
+ uint64_t temp, pml4e;
+ int ret = 0;
+
+ /* Do the pml4 allocations first, so we don't need to track the newly
+ * allocated tables below the pdp */
+ bitmap_zero(new_pdps, GEN8_PML4ES_PER_PML4);
+
+ /* The pagedirectory and pagetable allocations are done in the shared 3
+ * and 4 level code. Just allocate the pdps.
+ */
+ ret = gen8_ppgtt_alloc_page_dirpointers(vm, pml4, start, length,
+ new_pdps);
+ if (ret)
+ return ret;
+
+ WARN(bitmap_weight(new_pdps, GEN8_PML4ES_PER_PML4) > 2,
+ "The allocation has spanned more than 512GB. "
+ "It is highly likely this is incorrect.");
+
+ gen8_for_each_pml4e(pdp, pml4, start, length, temp, pml4e) {
+ WARN_ON(!pdp);
+
+ ret = gen8_alloc_va_range_3lvl(vm, pdp, start, length);
+ if (ret)
+ goto err_out;
+
+ gen8_setup_page_directory_pointer(ppgtt, pml4, pdp, pml4e);
+ }
+
+ bitmap_or(pml4->used_pml4es, new_pdps, pml4->used_pml4es,
+ GEN8_PML4ES_PER_PML4);
+
+ return 0;
+
+err_out:
+ for_each_set_bit(pml4e, new_pdps, GEN8_PML4ES_PER_PML4)
+ gen8_ppgtt_cleanup_3lvl(vm->dev, pml4->pdps[pml4e]);
+
+ return ret;
+}
+
+static int gen8_alloc_va_range(struct i915_address_space *vm,
+ uint64_t start, uint64_t length)
+{
+ struct i915_hw_ppgtt *ppgtt =
+ container_of(vm, struct i915_hw_ppgtt, base);
+
+ if (USES_FULL_48BIT_PPGTT(vm->dev))
+ return gen8_alloc_va_range_4lvl(vm, &ppgtt->pml4, start, length);
+ else
+ return gen8_alloc_va_range_3lvl(vm, &ppgtt->pdp, start, length);
+}
+
+static void gen8_dump_pdp(struct i915_page_directory_pointer *pdp,
+ uint64_t start, uint64_t length,
+ gen8_pte_t scratch_pte,
+ struct seq_file *m)
+{
+ struct i915_page_directory *pd;
+ uint64_t temp;
+ uint32_t pdpe;
+
+ gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) {
+ struct i915_page_table *pt;
+ uint64_t pd_len = length;
+ uint64_t pd_start = start;
+ uint32_t pde;
+
+ if (!test_bit(pdpe, pdp->used_pdpes))
+ continue;
+
+ seq_printf(m, "\tPDPE #%d\n", pdpe);
+ gen8_for_each_pde(pt, pd, pd_start, pd_len, temp, pde) {
+ uint32_t pte;
+ gen8_pte_t *pt_vaddr;
+
+ if (!test_bit(pde, pd->used_pdes))
+ continue;
+
+ pt_vaddr = kmap_px(pt);
+ for (pte = 0; pte < GEN8_PTES; pte += 4) {
+ uint64_t va =
+ (pdpe << GEN8_PDPE_SHIFT) |
+ (pde << GEN8_PDE_SHIFT) |
+ (pte << GEN8_PTE_SHIFT);
+ int i;
+ bool found = false;
+
+ for (i = 0; i < 4; i++)
+ if (pt_vaddr[pte + i] != scratch_pte)
+ found = true;
+ if (!found)
+ continue;
+
+ seq_printf(m, "\t\t0x%llx [%03d,%03d,%04d]: =", va, pdpe, pde, pte);
+ for (i = 0; i < 4; i++) {
+ if (pt_vaddr[pte + i] != scratch_pte)
+ seq_printf(m, " %llx", pt_vaddr[pte + i]);
+ else
+ seq_puts(m, " SCRATCH ");
+ }
+ seq_puts(m, "\n");
+ }
+ /* don't use kunmap_px, it could trigger
+ * an unnecessary flush.
+ */
+ kunmap_atomic(pt_vaddr);
+ }
+ }
+}
+
+static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
+{
+ struct i915_address_space *vm = &ppgtt->base;
+ uint64_t start = ppgtt->base.start;
+ uint64_t length = ppgtt->base.total;
+ gen8_pte_t scratch_pte = gen8_pte_encode(px_dma(vm->scratch_page),
+ I915_CACHE_LLC, true);
+
+ if (!USES_FULL_48BIT_PPGTT(vm->dev)) {
+ gen8_dump_pdp(&ppgtt->pdp, start, length, scratch_pte, m);
+ } else {
+ uint64_t templ4, pml4e;
+ struct i915_pml4 *pml4 = &ppgtt->pml4;
+ struct i915_page_directory_pointer *pdp;
+
+ gen8_for_each_pml4e(pdp, pml4, start, length, templ4, pml4e) {
+ if (!test_bit(pml4e, pml4->used_pml4es))
+ continue;
+
+ seq_printf(m, " PML4E #%llu\n", pml4e);
+ gen8_dump_pdp(pdp, start, length, scratch_pte, m);
+ }
+ }
+}
+
+static int gen8_preallocate_top_level_pdps(struct i915_hw_ppgtt *ppgtt)
+{
+ unsigned long *new_page_dirs, *new_page_tables;
+ uint32_t pdpes = I915_PDPES_PER_PDP(dev);
+ int ret;
+
+ /* We allocate temp bitmap for page tables for no gain
+ * but as this is for init only, lets keep the things simple
+ */
+ ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables, pdpes);
+ if (ret)
+ return ret;
+
+ /* Allocate for all pdps regardless of how the ppgtt
+ * was defined.
+ */
+ ret = gen8_ppgtt_alloc_page_directories(&ppgtt->base, &ppgtt->pdp,
+ 0, 1ULL << 32,
+ new_page_dirs);
+ if (!ret)
+ *ppgtt->pdp.used_pdpes = *new_page_dirs;
+
+ free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
+
+ return ret;
+}
+
/*
* GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
* with a net effect resembling a 2-level page table in normal x86 terms. Each
return ret;
ppgtt->base.start = 0;
- ppgtt->base.total = 1ULL << 32;
- if (IS_ENABLED(CONFIG_X86_32))
- /* While we have a proliferation of size_t variables
- * we cannot represent the full ppgtt size on 32bit,
- * so limit it to the same size as the GGTT (currently
- * 2GiB).
- */
- ppgtt->base.total = to_i915(ppgtt->base.dev)->gtt.base.total;
ppgtt->base.cleanup = gen8_ppgtt_cleanup;
ppgtt->base.allocate_va_range = gen8_alloc_va_range;
ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
ppgtt->base.clear_range = gen8_ppgtt_clear_range;
ppgtt->base.unbind_vma = ppgtt_unbind_vma;
ppgtt->base.bind_vma = ppgtt_bind_vma;
+ ppgtt->debug_dump = gen8_dump_ppgtt;
+
+ if (USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
+ ret = setup_px(ppgtt->base.dev, &ppgtt->pml4);
+ if (ret)
+ goto free_scratch;
+
+ gen8_initialize_pml4(&ppgtt->base, &ppgtt->pml4);
+
+ ppgtt->base.total = 1ULL << 48;
+ ppgtt->switch_mm = gen8_48b_mm_switch;
+ } else {
+ ret = __pdp_init(ppgtt->base.dev, &ppgtt->pdp);
+ if (ret)
+ goto free_scratch;
+
+ ppgtt->base.total = 1ULL << 32;
+ ppgtt->switch_mm = gen8_legacy_mm_switch;
+ trace_i915_page_directory_pointer_entry_alloc(&ppgtt->base,
+ 0, 0,
+ GEN8_PML4E_SHIFT);
+
+ if (intel_vgpu_active(ppgtt->base.dev)) {
+ ret = gen8_preallocate_top_level_pdps(ppgtt);
+ if (ret)
+ goto free_scratch;
+ }
+ }
- ppgtt->switch_mm = gen8_mm_switch;
+ if (intel_vgpu_active(ppgtt->base.dev))
+ gen8_ppgtt_notify_vgt(ppgtt, true);
return 0;
+
+free_scratch:
+ gen8_free_scratch(&ppgtt->base);
+ return ret;
}
static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
int j;
for_each_ring(ring, dev_priv, j) {
+ u32 four_level = USES_FULL_48BIT_PPGTT(dev) ? GEN8_GFX_PPGTT_48B : 0;
I915_WRITE(RING_MODE_GEN7(ring),
- _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+ _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE | four_level));
}
}
return gen8_ppgtt_init(ppgtt);
}
+static void i915_address_space_init(struct i915_address_space *vm,
+ struct drm_i915_private *dev_priv)
+{
+ drm_mm_init(&vm->mm, vm->start, vm->total);
+ vm->dev = dev_priv->dev;
+ INIT_LIST_HEAD(&vm->active_list);
+ INIT_LIST_HEAD(&vm->inactive_list);
+ list_add_tail(&vm->global_link, &dev_priv->vm_list);
+}
+
int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
{
struct drm_i915_private *dev_priv = dev->dev_private;
ret = __hw_ppgtt_init(dev, ppgtt);
if (ret == 0) {
kref_init(&ppgtt->ref);
- drm_mm_init(&ppgtt->base.mm, ppgtt->base.start,
- ppgtt->base.total);
- i915_init_vm(dev_priv, &ppgtt->base);
+ i915_address_space_init(&ppgtt->base, dev_priv);
}
return ret;
* the bound flag ourselves.
*/
vma->bound |= GLOBAL_BIND;
-
}
if (dev_priv->mm.aliasing_ppgtt && flags & LOCAL_BIND) {
}
static int i915_gem_setup_global_gtt(struct drm_device *dev,
- unsigned long start,
- unsigned long mappable_end,
- unsigned long end)
+ u64 start,
+ u64 mappable_end,
+ u64 end)
{
/* Let GEM Manage all of the aperture.
*
BUG_ON(mappable_end > end);
- /* Subtract the guard page ... */
- drm_mm_init(&ggtt_vm->mm, start, end - start - PAGE_SIZE);
+ ggtt_vm->start = start;
- dev_priv->gtt.base.start = start;
- dev_priv->gtt.base.total = end - start;
+ /* Subtract the guard page before address space initialization to
+ * shrink the range used by drm_mm */
+ ggtt_vm->total = end - start - PAGE_SIZE;
+ i915_address_space_init(ggtt_vm, dev_priv);
+ ggtt_vm->total += PAGE_SIZE;
if (intel_vgpu_active(dev)) {
ret = intel_vgt_balloon(dev);
}
if (!HAS_LLC(dev))
- dev_priv->gtt.base.mm.color_adjust = i915_gtt_color_adjust;
+ ggtt_vm->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) {
struct i915_vma *vma = i915_gem_obj_to_vma(obj, ggtt_vm);
- DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n",
+ DRM_DEBUG_KMS("reserving preallocated space: %llx + %zx\n",
i915_gem_obj_ggtt_offset(obj), obj->base.size);
WARN_ON(i915_gem_obj_ggtt_bound(obj));
return ret;
}
vma->bound |= GLOBAL_BIND;
+ list_add_tail(&vma->mm_list, &ggtt_vm->inactive_list);
}
/* Clear any non-preallocated blocks */
}
-static void
-rotate_pages(dma_addr_t *in, unsigned int width, unsigned int height,
- struct sg_table *st)
+static struct scatterlist *
+rotate_pages(dma_addr_t *in, unsigned int offset,
+ unsigned int width, unsigned int height,
+ struct sg_table *st, struct scatterlist *sg)
{
unsigned int column, row;
unsigned int src_idx;
- struct scatterlist *sg = st->sgl;
- st->nents = 0;
+ if (!sg) {
+ st->nents = 0;
+ sg = st->sgl;
+ }
for (column = 0; column < width; column++) {
src_idx = width * (height - 1) + column;
* The only thing we need are DMA addresses.
*/
sg_set_page(sg, NULL, PAGE_SIZE, 0);
- sg_dma_address(sg) = in[src_idx];
+ sg_dma_address(sg) = in[offset + src_idx];
sg_dma_len(sg) = PAGE_SIZE;
sg = sg_next(sg);
src_idx -= width;
}
}
+
+ return sg;
}
static struct sg_table *
{
struct intel_rotation_info *rot_info = &ggtt_view->rotation_info;
unsigned int size_pages = rot_info->size >> PAGE_SHIFT;
+ unsigned int size_pages_uv;
struct sg_page_iter sg_iter;
unsigned long i;
dma_addr_t *page_addr_list;
struct sg_table *st;
+ unsigned int uv_start_page;
+ struct scatterlist *sg;
int ret = -ENOMEM;
/* Allocate a temporary list of source pages for random access. */
if (!page_addr_list)
return ERR_PTR(ret);
+ /* Account for UV plane with NV12. */
+ if (rot_info->pixel_format == DRM_FORMAT_NV12)
+ size_pages_uv = rot_info->size_uv >> PAGE_SHIFT;
+ else
+ size_pages_uv = 0;
+
/* Allocate target SG list. */
st = kmalloc(sizeof(*st), GFP_KERNEL);
if (!st)
goto err_st_alloc;
- ret = sg_alloc_table(st, size_pages, GFP_KERNEL);
+ ret = sg_alloc_table(st, size_pages + size_pages_uv, GFP_KERNEL);
if (ret)
goto err_sg_alloc;
}
/* Rotate the pages. */
- rotate_pages(page_addr_list,
+ sg = rotate_pages(page_addr_list, 0,
rot_info->width_pages, rot_info->height_pages,
- st);
+ st, NULL);
+
+ /* Append the UV plane if NV12. */
+ if (rot_info->pixel_format == DRM_FORMAT_NV12) {
+ uv_start_page = size_pages;
+
+ /* Check for tile-row un-alignment. */
+ if (offset_in_page(rot_info->uv_offset))
+ uv_start_page--;
+
+ rot_info->uv_start_page = uv_start_page;
+
+ rotate_pages(page_addr_list, uv_start_page,
+ rot_info->width_pages_uv,
+ rot_info->height_pages_uv,
+ st, sg);
+ }
DRM_DEBUG_KMS(
- "Created rotated page mapping for object size %zu (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages).\n",
+ "Created rotated page mapping for object size %zu (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages (%u plane 0)).\n",
obj->base.size, rot_info->pitch, rot_info->height,
rot_info->pixel_format, rot_info->width_pages,
- rot_info->height_pages, size_pages);
+ rot_info->height_pages, size_pages + size_pages_uv,
+ size_pages);
drm_free_large(page_addr_list);
drm_free_large(page_addr_list);
DRM_DEBUG_KMS(
- "Failed to create rotated mapping for object size %zu! (%d) (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages)\n",
+ "Failed to create rotated mapping for object size %zu! (%d) (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages (%u plane 0))\n",
obj->base.size, ret, rot_info->pitch, rot_info->height,
rot_info->pixel_format, rot_info->width_pages,
- rot_info->height_pages, size_pages);
+ rot_info->height_pages, size_pages + size_pages_uv,
+ size_pages);
return ERR_PTR(ret);
}
typedef uint32_t gen6_pte_t;
typedef uint64_t gen8_pte_t;
typedef uint64_t gen8_pde_t;
+typedef uint64_t gen8_ppgtt_pdpe_t;
+typedef uint64_t gen8_ppgtt_pml4e_t;
#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT)
* PDPE | PDE | PTE | offset
* The difference as compared to normal x86 3 level page table is the PDPEs are
* programmed via register.
+ *
+ * GEN8 48b legacy style address is defined as a 4 level page table:
+ * 47:39 | 38:30 | 29:21 | 20:12 | 11:0
+ * PML4E | PDPE | PDE | PTE | offset
*/
+#define GEN8_PML4ES_PER_PML4 512
+#define GEN8_PML4E_SHIFT 39
+#define GEN8_PML4E_MASK (GEN8_PML4ES_PER_PML4 - 1)
#define GEN8_PDPE_SHIFT 30
-#define GEN8_PDPE_MASK 0x3
+/* NB: GEN8_PDPE_MASK is untrue for 32b platforms, but it has no impact on 32b page
+ * tables */
+#define GEN8_PDPE_MASK 0x1ff
#define GEN8_PDE_SHIFT 21
#define GEN8_PDE_MASK 0x1ff
#define GEN8_PTE_SHIFT 12
#define GEN8_LEGACY_PDPES 4
#define GEN8_PTES I915_PTES(sizeof(gen8_pte_t))
+#define I915_PDPES_PER_PDP(dev) (USES_FULL_48BIT_PPGTT(dev) ?\
+ GEN8_PML4ES_PER_PML4 : GEN8_LEGACY_PDPES)
+
#define PPAT_UNCACHED_INDEX (_PAGE_PWT | _PAGE_PCD)
#define PPAT_CACHED_PDE_INDEX 0 /* WB LLC */
#define PPAT_CACHED_INDEX _PAGE_PAT /* WB LLCeLLC */
struct intel_rotation_info {
unsigned int height;
unsigned int pitch;
+ unsigned int uv_offset;
uint32_t pixel_format;
uint64_t fb_modifier;
unsigned int width_pages, height_pages;
uint64_t size;
+ unsigned int width_pages_uv, height_pages_uv;
+ uint64_t size_uv;
+ unsigned int uv_start_page;
};
struct i915_ggtt_view {
union {
struct {
- unsigned long offset;
+ u64 offset;
unsigned int size;
} partial;
} params;
};
struct i915_page_directory_pointer {
- /* struct page *page; */
- DECLARE_BITMAP(used_pdpes, GEN8_LEGACY_PDPES);
- struct i915_page_directory *page_directory[GEN8_LEGACY_PDPES];
+ struct i915_page_dma base;
+
+ unsigned long *used_pdpes;
+ struct i915_page_directory **page_directory;
+};
+
+struct i915_pml4 {
+ struct i915_page_dma base;
+
+ DECLARE_BITMAP(used_pml4es, GEN8_PML4ES_PER_PML4);
+ struct i915_page_directory_pointer *pdps[GEN8_PML4ES_PER_PML4];
};
struct i915_address_space {
struct i915_page_scratch *scratch_page;
struct i915_page_table *scratch_pt;
struct i915_page_directory *scratch_pd;
+ struct i915_page_directory_pointer *scratch_pdp; /* GEN8+ & 48b PPGTT */
/**
* List of objects currently involved in rendering.
struct i915_address_space base;
size_t stolen_size; /* Total size of stolen memory */
+ size_t stolen_usable_size; /* Total size minus BIOS reserved */
u64 mappable_end; /* End offset that we can CPU map */
struct io_mapping *mappable; /* Mapping to our CPU mappable region */
phys_addr_t mappable_base; /* PA of our GMADR */
struct drm_mm_node node;
unsigned long pd_dirty_rings;
union {
- struct i915_page_directory_pointer pdp;
- struct i915_page_directory pd;
+ struct i915_pml4 pml4; /* GEN8+ & 48b PPGTT */
+ struct i915_page_directory_pointer pdp; /* GEN8+ */
+ struct i915_page_directory pd; /* GEN6-7 */
};
struct drm_i915_file_private *file_priv;
temp = min(temp, length), \
start += temp, length -= temp)
-#define gen8_for_each_pdpe(pd, pdp, start, length, temp, iter) \
- for (iter = gen8_pdpe_index(start); \
- pd = (pdp)->page_directory[iter], length > 0 && iter < GEN8_LEGACY_PDPES; \
+#define gen8_for_each_pdpe(pd, pdp, start, length, temp, iter) \
+ for (iter = gen8_pdpe_index(start); \
+ pd = (pdp)->page_directory[iter], \
+ length > 0 && (iter < I915_PDPES_PER_PDP(dev)); \
iter++, \
temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT) - start, \
temp = min(temp, length), \
start += temp, length -= temp)
-/* Clamp length to the next page_directory boundary */
-static inline uint64_t gen8_clamp_pd(uint64_t start, uint64_t length)
-{
- uint64_t next_pd = ALIGN(start + 1, 1 << GEN8_PDPE_SHIFT);
-
- if (next_pd > (start + length))
- return length;
-
- return next_pd - start;
-}
+#define gen8_for_each_pml4e(pdp, pml4, start, length, temp, iter) \
+ for (iter = gen8_pml4e_index(start); \
+ pdp = (pml4)->pdps[iter], \
+ length > 0 && iter < GEN8_PML4ES_PER_PML4; \
+ iter++, \
+ temp = ALIGN(start+1, 1ULL << GEN8_PML4E_SHIFT) - start, \
+ temp = min(temp, length), \
+ start += temp, length -= temp)
static inline uint32_t gen8_pte_index(uint64_t address)
{
static inline uint32_t gen8_pml4e_index(uint64_t address)
{
- WARN_ON(1); /* For 64B */
- return 0;
+ return (address >> GEN8_PML4E_SHIFT) & GEN8_PML4E_MASK;
}
static inline size_t gen8_pte_count(uint64_t address, uint64_t length)
* for is a boon.
*/
-int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv,
- struct drm_mm_node *node, u64 size,
- unsigned alignment)
+int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
+ struct drm_mm_node *node, u64 size,
+ unsigned alignment, u64 start, u64 end)
{
int ret;
return -ENODEV;
mutex_lock(&dev_priv->mm.stolen_lock);
- ret = drm_mm_insert_node(&dev_priv->mm.stolen, node, size, alignment,
- DRM_MM_SEARCH_DEFAULT);
+ ret = drm_mm_insert_node_in_range(&dev_priv->mm.stolen, node, size,
+ alignment, start, end,
+ DRM_MM_SEARCH_DEFAULT);
mutex_unlock(&dev_priv->mm.stolen_lock);
return ret;
}
+int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv,
+ struct drm_mm_node *node, u64 size,
+ unsigned alignment)
+{
+ return i915_gem_stolen_insert_node_in_range(dev_priv, node, size,
+ alignment, 0,
+ dev_priv->gtt.stolen_usable_size);
+}
+
void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv,
struct drm_mm_node *node)
{
drm_mm_takedown(&dev_priv->mm.stolen);
}
+static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv,
+ unsigned long *base, unsigned long *size)
+{
+ uint32_t reg_val = I915_READ(IS_GM45(dev_priv) ?
+ CTG_STOLEN_RESERVED :
+ ELK_STOLEN_RESERVED);
+ unsigned long stolen_top = dev_priv->mm.stolen_base +
+ dev_priv->gtt.stolen_size;
+
+ *base = (reg_val & G4X_STOLEN_RESERVED_ADDR2_MASK) << 16;
+
+ WARN_ON((reg_val & G4X_STOLEN_RESERVED_ADDR1_MASK) < *base);
+
+ /* On these platforms, the register doesn't have a size field, so the
+ * size is the distance between the base and the top of the stolen
+ * memory. We also have the genuine case where base is zero and there's
+ * nothing reserved. */
+ if (*base == 0)
+ *size = 0;
+ else
+ *size = stolen_top - *base;
+}
+
static void gen6_get_stolen_reserved(struct drm_i915_private *dev_priv,
unsigned long *base, unsigned long *size)
{
int i915_gem_init_stolen(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- unsigned long reserved_total, reserved_base, reserved_size;
+ unsigned long reserved_total, reserved_base = 0, reserved_size;
unsigned long stolen_top;
mutex_init(&dev_priv->mm.stolen_lock);
switch (INTEL_INFO(dev_priv)->gen) {
case 2:
case 3:
+ break;
case 4:
+ if (IS_G4X(dev))
+ g4x_get_stolen_reserved(dev_priv, &reserved_base,
+ &reserved_size);
+ break;
case 5:
/* Assume the gen6 maximum for the older platforms. */
reserved_size = 1024 * 1024;
dev_priv->gtt.stolen_size >> 10,
(dev_priv->gtt.stolen_size - reserved_total) >> 10);
+ dev_priv->gtt.stolen_usable_size = dev_priv->gtt.stolen_size -
+ reserved_total;
+
/* Basic memrange allocator for stolen space */
- drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->gtt.stolen_size -
- reserved_total);
+ drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->gtt.stolen_usable_size);
return 0;
}
vma = i915_gem_obj_lookup_or_create_vma(obj, ggtt);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
- goto err_out;
+ goto err;
}
/* To simplify the initialisation sequence between KMS and GTT,
ret = drm_mm_reserve_node(&ggtt->mm, &vma->node);
if (ret) {
DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
- goto err_vma;
+ goto err;
}
- }
- vma->bound |= GLOBAL_BIND;
+ vma->bound |= GLOBAL_BIND;
+ list_add_tail(&vma->mm_list, &ggtt->inactive_list);
+ }
list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
- list_add_tail(&vma->mm_list, &ggtt->inactive_list);
i915_gem_object_pin_pages(obj);
return obj;
-err_vma:
- i915_gem_vma_destroy(vma);
-err_out:
- i915_gem_stolen_remove_node(dev_priv, stolen);
- kfree(stolen);
+err:
drm_gem_object_unreference(&obj->base);
return NULL;
}
int
i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_userptr *args = data;
struct drm_i915_gem_object *obj;
int ret;
if (offset_in_page(args->user_ptr | args->user_size))
return -EINVAL;
- if (args->user_size > dev_priv->gtt.base.total)
- return -E2BIG;
-
if (!access_ok(args->flags & I915_USERPTR_READ_ONLY ? VERIFY_READ : VERIFY_WRITE,
(char __user *)(unsigned long)args->user_ptr, args->user_size))
return -EFAULT;
#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) {
err_printf(m, " %s [%d]:\n", name, count);
while (count--) {
- err_printf(m, " %08x %8u %02x %02x [ ",
- err->gtt_offset,
+ err_printf(m, " %08x_%08x %8u %02x %02x [ ",
+ upper_32_bits(err->gtt_offset),
+ lower_32_bits(err->gtt_offset),
err->size,
err->read_domains,
err->write_domain);
err_printf(m, " (submitted by %s [%d])",
error->ring[i].comm,
error->ring[i].pid);
- err_printf(m, " --- gtt_offset = 0x%08x\n",
- obj->gtt_offset);
+ err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
+ upper_32_bits(obj->gtt_offset),
+ lower_32_bits(obj->gtt_offset));
print_error_obj(m, obj);
}
obj = error->ring[i].wa_batchbuffer;
if (obj) {
err_printf(m, "%s (w/a) --- gtt_offset = 0x%08x\n",
- dev_priv->ring[i].name, obj->gtt_offset);
+ dev_priv->ring[i].name,
+ lower_32_bits(obj->gtt_offset));
print_error_obj(m, obj);
}
if ((obj = error->ring[i].ringbuffer)) {
err_printf(m, "%s --- ringbuffer = 0x%08x\n",
dev_priv->ring[i].name,
- obj->gtt_offset);
+ lower_32_bits(obj->gtt_offset));
print_error_obj(m, obj);
}
if ((obj = error->ring[i].hws_page)) {
- err_printf(m, "%s --- HW Status = 0x%08x\n",
- dev_priv->ring[i].name,
- obj->gtt_offset);
+ u64 hws_offset = obj->gtt_offset;
+ u32 *hws_page = &obj->pages[0][0];
+
+ if (i915.enable_execlists) {
+ hws_offset += LRC_PPHWSP_PN * PAGE_SIZE;
+ hws_page = &obj->pages[LRC_PPHWSP_PN][0];
+ }
+ err_printf(m, "%s --- HW Status = 0x%08llx\n",
+ dev_priv->ring[i].name, hws_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]);
+ hws_page[elt],
+ hws_page[elt+1],
+ hws_page[elt+2],
+ hws_page[elt+3]);
offset += 16;
}
}
if ((obj = error->ring[i].ctx)) {
err_printf(m, "%s --- HW Context = 0x%08x\n",
dev_priv->ring[i].name,
- obj->gtt_offset);
+ lower_32_bits(obj->gtt_offset));
print_error_obj(m, obj);
}
}
if ((obj = error->semaphore_obj)) {
- err_printf(m, "Semaphore page = 0x%08x\n", obj->gtt_offset);
+ err_printf(m, "Semaphore page = 0x%08x\n",
+ lower_32_bits(obj->gtt_offset));
for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
err_printf(m, "[%04x] %08x %08x %08x %08x\n",
elt * 4,
int num_pages;
bool use_ggtt;
int i = 0;
- u32 reloc_offset;
+ u64 reloc_offset;
if (src == NULL || src->pages == NULL)
return NULL;
#define GS_MIA_SHIFT 16
#define GS_MIA_MASK (0x07 << GS_MIA_SHIFT)
-#define GUC_WOPCM_SIZE 0xc050
-#define GUC_WOPCM_SIZE_VALUE (0x80 << 12) /* 512KB */
-#define GUC_WOPCM_OFFSET 0x80000 /* 512KB */
-
#define SOFT_SCRATCH(n) (0xc180 + ((n) * 4))
#define UOS_RSA_SCRATCH_0 0xc200
#define UOS_MOVE (1<<4)
#define START_DMA (1<<0)
#define DMA_GUC_WOPCM_OFFSET 0xc340
+#define GUC_WOPCM_OFFSET_VALUE 0x80000 /* 512KB */
+#define GUC_MAX_IDLE_COUNT 0xC3E4
+
+#define GUC_WOPCM_SIZE 0xc050
+#define GUC_WOPCM_SIZE_VALUE (0x80 << 12) /* 512KB */
+
+/* GuC addresses below GUC_WOPCM_TOP don't map through the GTT */
+#define GUC_WOPCM_TOP (GUC_WOPCM_SIZE_VALUE)
#define GEN8_GT_PM_CONFIG 0x138140
+#define GEN9LP_GT_PM_CONFIG 0x138140
#define GEN9_GT_PM_CONFIG 0x13816c
-#define GEN8_GT_DOORBELL_ENABLE (1<<0)
+#define GT_DOORBELL_ENABLE (1<<0)
#define GEN8_GTCR 0x4274
#define GEN8_GTCR_INVALIDATE (1<<0)
GUC_ENABLE_READ_CACHE_LOGIC | \
GUC_ENABLE_MIA_CACHING | \
GUC_ENABLE_READ_CACHE_FOR_SRAM_DATA | \
- GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA)
+ GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA | \
+ GUC_ENABLE_MIA_CLOCK_GATING)
#define HOST2GUC_INTERRUPT 0xc4c8
#define HOST2GUC_TRIGGER (1<<0)
--- /dev/null
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+#include <linux/firmware.h>
+#include <linux/circ_buf.h>
+#include "i915_drv.h"
+#include "intel_guc.h"
+
+/**
+ * DOC: GuC Client
+ *
+ * i915_guc_client:
+ * We use the term client to avoid confusion with contexts. A i915_guc_client is
+ * equivalent to GuC object guc_context_desc. This context descriptor is
+ * allocated from a pool of 1024 entries. Kernel driver will allocate doorbell
+ * and workqueue for it. Also the process descriptor (guc_process_desc), which
+ * is mapped to client space. So the client can write Work Item then ring the
+ * doorbell.
+ *
+ * To simplify the implementation, we allocate one gem object that contains all
+ * pages for doorbell, process descriptor and workqueue.
+ *
+ * The Scratch registers:
+ * There are 16 MMIO-based registers start from 0xC180. The kernel driver writes
+ * a value to the action register (SOFT_SCRATCH_0) along with any data. It then
+ * triggers an interrupt on the GuC via another register write (0xC4C8).
+ * Firmware writes a success/fail code back to the action register after
+ * processes the request. The kernel driver polls waiting for this update and
+ * then proceeds.
+ * See host2guc_action()
+ *
+ * Doorbells:
+ * Doorbells are interrupts to uKernel. A doorbell is a single cache line (QW)
+ * mapped into process space.
+ *
+ * Work Items:
+ * There are several types of work items that the host may place into a
+ * workqueue, each with its own requirements and limitations. Currently only
+ * WQ_TYPE_INORDER is needed to support legacy submission via GuC, which
+ * represents in-order queue. The kernel driver packs ring tail pointer and an
+ * ELSP context descriptor dword into Work Item.
+ * See guc_add_workqueue_item()
+ *
+ */
+
+/*
+ * Read GuC command/status register (SOFT_SCRATCH_0)
+ * Return true if it contains a response rather than a command
+ */
+static inline bool host2guc_action_response(struct drm_i915_private *dev_priv,
+ u32 *status)
+{
+ u32 val = I915_READ(SOFT_SCRATCH(0));
+ *status = val;
+ return GUC2HOST_IS_RESPONSE(val);
+}
+
+static int host2guc_action(struct intel_guc *guc, u32 *data, u32 len)
+{
+ struct drm_i915_private *dev_priv = guc_to_i915(guc);
+ u32 status;
+ int i;
+ int ret;
+
+ if (WARN_ON(len < 1 || len > 15))
+ return -EINVAL;
+
+ intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+ spin_lock(&dev_priv->guc.host2guc_lock);
+
+ dev_priv->guc.action_count += 1;
+ dev_priv->guc.action_cmd = data[0];
+
+ for (i = 0; i < len; i++)
+ I915_WRITE(SOFT_SCRATCH(i), data[i]);
+
+ POSTING_READ(SOFT_SCRATCH(i - 1));
+
+ I915_WRITE(HOST2GUC_INTERRUPT, HOST2GUC_TRIGGER);
+
+ /* No HOST2GUC command should take longer than 10ms */
+ ret = wait_for_atomic(host2guc_action_response(dev_priv, &status), 10);
+ if (status != GUC2HOST_STATUS_SUCCESS) {
+ /*
+ * Either the GuC explicitly returned an error (which
+ * we convert to -EIO here) or no response at all was
+ * received within the timeout limit (-ETIMEDOUT)
+ */
+ if (ret != -ETIMEDOUT)
+ ret = -EIO;
+
+ DRM_ERROR("GUC: host2guc action 0x%X failed. ret=%d "
+ "status=0x%08X response=0x%08X\n",
+ data[0], ret, status,
+ I915_READ(SOFT_SCRATCH(15)));
+
+ dev_priv->guc.action_fail += 1;
+ dev_priv->guc.action_err = ret;
+ }
+ dev_priv->guc.action_status = status;
+
+ spin_unlock(&dev_priv->guc.host2guc_lock);
+ intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+
+ return ret;
+}
+
+/*
+ * Tell the GuC to allocate or deallocate a specific doorbell
+ */
+
+static int host2guc_allocate_doorbell(struct intel_guc *guc,
+ struct i915_guc_client *client)
+{
+ u32 data[2];
+
+ data[0] = HOST2GUC_ACTION_ALLOCATE_DOORBELL;
+ data[1] = client->ctx_index;
+
+ return host2guc_action(guc, data, 2);
+}
+
+static int host2guc_release_doorbell(struct intel_guc *guc,
+ struct i915_guc_client *client)
+{
+ u32 data[2];
+
+ data[0] = HOST2GUC_ACTION_DEALLOCATE_DOORBELL;
+ data[1] = client->ctx_index;
+
+ return host2guc_action(guc, data, 2);
+}
+
+static int host2guc_sample_forcewake(struct intel_guc *guc,
+ struct i915_guc_client *client)
+{
+ struct drm_i915_private *dev_priv = guc_to_i915(guc);
+ u32 data[2];
+
+ data[0] = HOST2GUC_ACTION_SAMPLE_FORCEWAKE;
+ data[1] = (intel_enable_rc6(dev_priv->dev)) ? 1 : 0;
+
+ return host2guc_action(guc, data, 2);
+}
+
+/*
+ * Initialise, update, or clear doorbell data shared with the GuC
+ *
+ * These functions modify shared data and so need access to the mapped
+ * client object which contains the page being used for the doorbell
+ */
+
+static void guc_init_doorbell(struct intel_guc *guc,
+ struct i915_guc_client *client)
+{
+ struct guc_doorbell_info *doorbell;
+ void *base;
+
+ base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0));
+ doorbell = base + client->doorbell_offset;
+
+ doorbell->db_status = 1;
+ doorbell->cookie = 0;
+
+ kunmap_atomic(base);
+}
+
+static int guc_ring_doorbell(struct i915_guc_client *gc)
+{
+ struct guc_process_desc *desc;
+ union guc_doorbell_qw db_cmp, db_exc, db_ret;
+ union guc_doorbell_qw *db;
+ void *base;
+ int attempt = 2, ret = -EAGAIN;
+
+ base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, 0));
+ desc = base + gc->proc_desc_offset;
+
+ /* Update the tail so it is visible to GuC */
+ desc->tail = gc->wq_tail;
+
+ /* current cookie */
+ db_cmp.db_status = GUC_DOORBELL_ENABLED;
+ db_cmp.cookie = gc->cookie;
+
+ /* cookie to be updated */
+ db_exc.db_status = GUC_DOORBELL_ENABLED;
+ db_exc.cookie = gc->cookie + 1;
+ if (db_exc.cookie == 0)
+ db_exc.cookie = 1;
+
+ /* pointer of current doorbell cacheline */
+ db = base + gc->doorbell_offset;
+
+ while (attempt--) {
+ /* lets ring the doorbell */
+ db_ret.value_qw = atomic64_cmpxchg((atomic64_t *)db,
+ db_cmp.value_qw, db_exc.value_qw);
+
+ /* if the exchange was successfully executed */
+ if (db_ret.value_qw == db_cmp.value_qw) {
+ /* db was successfully rung */
+ gc->cookie = db_exc.cookie;
+ ret = 0;
+ break;
+ }
+
+ /* XXX: doorbell was lost and need to acquire it again */
+ if (db_ret.db_status == GUC_DOORBELL_DISABLED)
+ break;
+
+ DRM_ERROR("Cookie mismatch. Expected %d, returned %d\n",
+ db_cmp.cookie, db_ret.cookie);
+
+ /* update the cookie to newly read cookie from GuC */
+ db_cmp.cookie = db_ret.cookie;
+ db_exc.cookie = db_ret.cookie + 1;
+ if (db_exc.cookie == 0)
+ db_exc.cookie = 1;
+ }
+
+ kunmap_atomic(base);
+ return ret;
+}
+
+static void guc_disable_doorbell(struct intel_guc *guc,
+ struct i915_guc_client *client)
+{
+ struct drm_i915_private *dev_priv = guc_to_i915(guc);
+ struct guc_doorbell_info *doorbell;
+ void *base;
+ int drbreg = GEN8_DRBREGL(client->doorbell_id);
+ int value;
+
+ base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0));
+ doorbell = base + client->doorbell_offset;
+
+ doorbell->db_status = 0;
+
+ kunmap_atomic(base);
+
+ I915_WRITE(drbreg, I915_READ(drbreg) & ~GEN8_DRB_VALID);
+
+ value = I915_READ(drbreg);
+ WARN_ON((value & GEN8_DRB_VALID) != 0);
+
+ I915_WRITE(GEN8_DRBREGU(client->doorbell_id), 0);
+ I915_WRITE(drbreg, 0);
+
+ /* XXX: wait for any interrupts */
+ /* XXX: wait for workqueue to drain */
+}
+
+/*
+ * Select, assign and relase doorbell cachelines
+ *
+ * These functions track which doorbell cachelines are in use.
+ * The data they manipulate is protected by the host2guc lock.
+ */
+
+static uint32_t select_doorbell_cacheline(struct intel_guc *guc)
+{
+ const uint32_t cacheline_size = cache_line_size();
+ uint32_t offset;
+
+ spin_lock(&guc->host2guc_lock);
+
+ /* Doorbell uses a single cache line within a page */
+ offset = offset_in_page(guc->db_cacheline);
+
+ /* Moving to next cache line to reduce contention */
+ guc->db_cacheline += cacheline_size;
+
+ spin_unlock(&guc->host2guc_lock);
+
+ DRM_DEBUG_DRIVER("selected doorbell cacheline 0x%x, next 0x%x, linesize %u\n",
+ offset, guc->db_cacheline, cacheline_size);
+
+ return offset;
+}
+
+static uint16_t assign_doorbell(struct intel_guc *guc, uint32_t priority)
+{
+ /*
+ * The bitmap is split into two halves; the first half is used for
+ * normal priority contexts, the second half for high-priority ones.
+ * Note that logically higher priorities are numerically less than
+ * normal ones, so the test below means "is it high-priority?"
+ */
+ const bool hi_pri = (priority <= GUC_CTX_PRIORITY_HIGH);
+ const uint16_t half = GUC_MAX_DOORBELLS / 2;
+ const uint16_t start = hi_pri ? half : 0;
+ const uint16_t end = start + half;
+ uint16_t id;
+
+ spin_lock(&guc->host2guc_lock);
+ id = find_next_zero_bit(guc->doorbell_bitmap, end, start);
+ if (id == end)
+ id = GUC_INVALID_DOORBELL_ID;
+ else
+ bitmap_set(guc->doorbell_bitmap, id, 1);
+ spin_unlock(&guc->host2guc_lock);
+
+ DRM_DEBUG_DRIVER("assigned %s priority doorbell id 0x%x\n",
+ hi_pri ? "high" : "normal", id);
+
+ return id;
+}
+
+static void release_doorbell(struct intel_guc *guc, uint16_t id)
+{
+ spin_lock(&guc->host2guc_lock);
+ bitmap_clear(guc->doorbell_bitmap, id, 1);
+ spin_unlock(&guc->host2guc_lock);
+}
+
+/*
+ * Initialise the process descriptor shared with the GuC firmware.
+ */
+static void guc_init_proc_desc(struct intel_guc *guc,
+ struct i915_guc_client *client)
+{
+ struct guc_process_desc *desc;
+ void *base;
+
+ base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0));
+ desc = base + client->proc_desc_offset;
+
+ memset(desc, 0, sizeof(*desc));
+
+ /*
+ * XXX: pDoorbell and WQVBaseAddress are pointers in process address
+ * space for ring3 clients (set them as in mmap_ioctl) or kernel
+ * space for kernel clients (map on demand instead? May make debug
+ * easier to have it mapped).
+ */
+ desc->wq_base_addr = 0;
+ desc->db_base_addr = 0;
+
+ desc->context_id = client->ctx_index;
+ desc->wq_size_bytes = client->wq_size;
+ desc->wq_status = WQ_STATUS_ACTIVE;
+ desc->priority = client->priority;
+
+ kunmap_atomic(base);
+}
+
+/*
+ * Initialise/clear the context descriptor shared with the GuC firmware.
+ *
+ * This descriptor tells the GuC where (in GGTT space) to find the important
+ * data structures relating to this client (doorbell, process descriptor,
+ * write queue, etc).
+ */
+
+static void guc_init_ctx_desc(struct intel_guc *guc,
+ struct i915_guc_client *client)
+{
+ struct intel_context *ctx = client->owner;
+ struct guc_context_desc desc;
+ struct sg_table *sg;
+ int i;
+
+ memset(&desc, 0, sizeof(desc));
+
+ desc.attribute = GUC_CTX_DESC_ATTR_ACTIVE | GUC_CTX_DESC_ATTR_KERNEL;
+ desc.context_id = client->ctx_index;
+ desc.priority = client->priority;
+ desc.db_id = client->doorbell_id;
+
+ for (i = 0; i < I915_NUM_RINGS; i++) {
+ struct guc_execlist_context *lrc = &desc.lrc[i];
+ struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf;
+ struct intel_engine_cs *ring;
+ struct drm_i915_gem_object *obj;
+ uint64_t ctx_desc;
+
+ /* TODO: We have a design issue to be solved here. Only when we
+ * receive the first batch, we know which engine is used by the
+ * user. But here GuC expects the lrc and ring to be pinned. It
+ * is not an issue for default context, which is the only one
+ * for now who owns a GuC client. But for future owner of GuC
+ * client, need to make sure lrc is pinned prior to enter here.
+ */
+ obj = ctx->engine[i].state;
+ if (!obj)
+ break; /* XXX: continue? */
+
+ ring = ringbuf->ring;
+ ctx_desc = intel_lr_context_descriptor(ctx, ring);
+ lrc->context_desc = (u32)ctx_desc;
+
+ /* The state page is after PPHWSP */
+ lrc->ring_lcra = i915_gem_obj_ggtt_offset(obj) +
+ LRC_STATE_PN * PAGE_SIZE;
+ lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) |
+ (ring->id << GUC_ELC_ENGINE_OFFSET);
+
+ obj = ringbuf->obj;
+
+ lrc->ring_begin = i915_gem_obj_ggtt_offset(obj);
+ lrc->ring_end = lrc->ring_begin + obj->base.size - 1;
+ lrc->ring_next_free_location = lrc->ring_begin;
+ lrc->ring_current_tail_pointer_value = 0;
+
+ desc.engines_used |= (1 << ring->id);
+ }
+
+ WARN_ON(desc.engines_used == 0);
+
+ /*
+ * The CPU address is only needed at certain points, so kmap_atomic on
+ * demand instead of storing it in the ctx descriptor.
+ * XXX: May make debug easier to have it mapped
+ */
+ desc.db_trigger_cpu = 0;
+ desc.db_trigger_uk = client->doorbell_offset +
+ i915_gem_obj_ggtt_offset(client->client_obj);
+ desc.db_trigger_phy = client->doorbell_offset +
+ sg_dma_address(client->client_obj->pages->sgl);
+
+ desc.process_desc = client->proc_desc_offset +
+ i915_gem_obj_ggtt_offset(client->client_obj);
+
+ desc.wq_addr = client->wq_offset +
+ i915_gem_obj_ggtt_offset(client->client_obj);
+
+ desc.wq_size = client->wq_size;
+
+ /*
+ * XXX: Take LRCs from an existing intel_context if this is not an
+ * IsKMDCreatedContext client
+ */
+ desc.desc_private = (uintptr_t)client;
+
+ /* Pool context is pinned already */
+ sg = guc->ctx_pool_obj->pages;
+ sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc),
+ sizeof(desc) * client->ctx_index);
+}
+
+static void guc_fini_ctx_desc(struct intel_guc *guc,
+ struct i915_guc_client *client)
+{
+ struct guc_context_desc desc;
+ struct sg_table *sg;
+
+ memset(&desc, 0, sizeof(desc));
+
+ sg = guc->ctx_pool_obj->pages;
+ sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc),
+ sizeof(desc) * client->ctx_index);
+}
+
+/* Get valid workqueue item and return it back to offset */
+static int guc_get_workqueue_space(struct i915_guc_client *gc, u32 *offset)
+{
+ struct guc_process_desc *desc;
+ void *base;
+ u32 size = sizeof(struct guc_wq_item);
+ int ret = 0, timeout_counter = 200;
+
+ base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, 0));
+ desc = base + gc->proc_desc_offset;
+
+ while (timeout_counter-- > 0) {
+ ret = wait_for_atomic(CIRC_SPACE(gc->wq_tail, desc->head,
+ gc->wq_size) >= size, 1);
+
+ if (!ret) {
+ *offset = gc->wq_tail;
+
+ /* advance the tail for next workqueue item */
+ gc->wq_tail += size;
+ gc->wq_tail &= gc->wq_size - 1;
+
+ /* this will break the loop */
+ timeout_counter = 0;
+ }
+ };
+
+ kunmap_atomic(base);
+
+ return ret;
+}
+
+static int guc_add_workqueue_item(struct i915_guc_client *gc,
+ struct drm_i915_gem_request *rq)
+{
+ enum intel_ring_id ring_id = rq->ring->id;
+ struct guc_wq_item *wqi;
+ void *base;
+ u32 tail, wq_len, wq_off = 0;
+ int ret;
+
+ ret = guc_get_workqueue_space(gc, &wq_off);
+ if (ret)
+ return ret;
+
+ /* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we
+ * should not have the case where structure wqi is across page, neither
+ * wrapped to the beginning. This simplifies the implementation below.
+ *
+ * XXX: if not the case, we need save data to a temp wqi and copy it to
+ * workqueue buffer dw by dw.
+ */
+ WARN_ON(sizeof(struct guc_wq_item) != 16);
+ WARN_ON(wq_off & 3);
+
+ /* wq starts from the page after doorbell / process_desc */
+ base = kmap_atomic(i915_gem_object_get_page(gc->client_obj,
+ (wq_off + GUC_DB_SIZE) >> PAGE_SHIFT));
+ wq_off &= PAGE_SIZE - 1;
+ wqi = (struct guc_wq_item *)((char *)base + wq_off);
+
+ /* len does not include the header */
+ wq_len = sizeof(struct guc_wq_item) / sizeof(u32) - 1;
+ wqi->header = WQ_TYPE_INORDER |
+ (wq_len << WQ_LEN_SHIFT) |
+ (ring_id << WQ_TARGET_SHIFT) |
+ WQ_NO_WCFLUSH_WAIT;
+
+ /* The GuC wants only the low-order word of the context descriptor */
+ wqi->context_desc = (u32)intel_lr_context_descriptor(rq->ctx, rq->ring);
+
+ /* The GuC firmware wants the tail index in QWords, not bytes */
+ tail = rq->ringbuf->tail >> 3;
+ wqi->ring_tail = tail << WQ_RING_TAIL_SHIFT;
+ wqi->fence_id = 0; /*XXX: what fence to be here */
+
+ kunmap_atomic(base);
+
+ return 0;
+}
+
+#define CTX_RING_BUFFER_START 0x08
+
+/* Update the ringbuffer pointer in a saved context image */
+static void lr_context_update(struct drm_i915_gem_request *rq)
+{
+ enum intel_ring_id ring_id = rq->ring->id;
+ struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring_id].state;
+ struct drm_i915_gem_object *rb_obj = rq->ringbuf->obj;
+ struct page *page;
+ uint32_t *reg_state;
+
+ BUG_ON(!ctx_obj);
+ WARN_ON(!i915_gem_obj_is_pinned(ctx_obj));
+ WARN_ON(!i915_gem_obj_is_pinned(rb_obj));
+
+ page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
+ reg_state = kmap_atomic(page);
+
+ reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj);
+
+ kunmap_atomic(reg_state);
+}
+
+/**
+ * i915_guc_submit() - Submit commands through GuC
+ * @client: the guc client where commands will go through
+ * @ctx: LRC where commands come from
+ * @ring: HW engine that will excute the commands
+ *
+ * Return: 0 if succeed
+ */
+int i915_guc_submit(struct i915_guc_client *client,
+ struct drm_i915_gem_request *rq)
+{
+ struct intel_guc *guc = client->guc;
+ enum intel_ring_id ring_id = rq->ring->id;
+ unsigned long flags;
+ int q_ret, b_ret;
+
+ /* Need this because of the deferred pin ctx and ring */
+ /* Shall we move this right after ring is pinned? */
+ lr_context_update(rq);
+
+ spin_lock_irqsave(&client->wq_lock, flags);
+
+ q_ret = guc_add_workqueue_item(client, rq);
+ if (q_ret == 0)
+ b_ret = guc_ring_doorbell(client);
+
+ client->submissions[ring_id] += 1;
+ if (q_ret) {
+ client->q_fail += 1;
+ client->retcode = q_ret;
+ } else if (b_ret) {
+ client->b_fail += 1;
+ client->retcode = q_ret = b_ret;
+ } else {
+ client->retcode = 0;
+ }
+ spin_unlock_irqrestore(&client->wq_lock, flags);
+
+ spin_lock(&guc->host2guc_lock);
+ guc->submissions[ring_id] += 1;
+ guc->last_seqno[ring_id] = rq->seqno;
+ spin_unlock(&guc->host2guc_lock);
+
+ return q_ret;
+}
+
+/*
+ * Everything below here is concerned with setup & teardown, and is
+ * therefore not part of the somewhat time-critical batch-submission
+ * path of i915_guc_submit() above.
+ */
+
+/**
+ * gem_allocate_guc_obj() - Allocate gem object for GuC usage
+ * @dev: drm device
+ * @size: size of object
+ *
+ * This is a wrapper to create a gem obj. In order to use it inside GuC, the
+ * object needs to be pinned lifetime. Also we must pin it to gtt space other
+ * than [0, GUC_WOPCM_TOP) because this range is reserved inside GuC.
+ *
+ * Return: A drm_i915_gem_object if successful, otherwise NULL.
+ */
+static struct drm_i915_gem_object *gem_allocate_guc_obj(struct drm_device *dev,
+ u32 size)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_i915_gem_object *obj;
+
+ obj = i915_gem_alloc_object(dev, size);
+ if (!obj)
+ return NULL;
+
+ if (i915_gem_object_get_pages(obj)) {
+ drm_gem_object_unreference(&obj->base);
+ return NULL;
+ }
+
+ if (i915_gem_obj_ggtt_pin(obj, PAGE_SIZE,
+ PIN_OFFSET_BIAS | GUC_WOPCM_TOP)) {
+ drm_gem_object_unreference(&obj->base);
+ return NULL;
+ }
+
+ /* Invalidate GuC TLB to let GuC take the latest updates to GTT. */
+ I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+
+ return obj;
+}
+
+/**
+ * gem_release_guc_obj() - Release gem object allocated for GuC usage
+ * @obj: gem obj to be released
+ */
+static void gem_release_guc_obj(struct drm_i915_gem_object *obj)
+{
+ if (!obj)
+ return;
+
+ if (i915_gem_obj_is_pinned(obj))
+ i915_gem_object_ggtt_unpin(obj);
+
+ drm_gem_object_unreference(&obj->base);
+}
+
+static void guc_client_free(struct drm_device *dev,
+ struct i915_guc_client *client)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_guc *guc = &dev_priv->guc;
+
+ if (!client)
+ return;
+
+ if (client->doorbell_id != GUC_INVALID_DOORBELL_ID) {
+ /*
+ * First disable the doorbell, then tell the GuC we've
+ * finished with it, finally deallocate it in our bitmap
+ */
+ guc_disable_doorbell(guc, client);
+ host2guc_release_doorbell(guc, client);
+ release_doorbell(guc, client->doorbell_id);
+ }
+
+ /*
+ * XXX: wait for any outstanding submissions before freeing memory.
+ * Be sure to drop any locks
+ */
+
+ gem_release_guc_obj(client->client_obj);
+
+ if (client->ctx_index != GUC_INVALID_CTX_ID) {
+ guc_fini_ctx_desc(guc, client);
+ ida_simple_remove(&guc->ctx_ids, client->ctx_index);
+ }
+
+ kfree(client);
+}
+
+/**
+ * guc_client_alloc() - Allocate an i915_guc_client
+ * @dev: drm device
+ * @priority: four levels priority _CRITICAL, _HIGH, _NORMAL and _LOW
+ * The kernel client to replace ExecList submission is created with
+ * NORMAL priority. Priority of a client for scheduler can be HIGH,
+ * while a preemption context can use CRITICAL.
+ * @ctx the context to own the client (we use the default render context)
+ *
+ * Return: An i915_guc_client object if success.
+ */
+static struct i915_guc_client *guc_client_alloc(struct drm_device *dev,
+ uint32_t priority,
+ struct intel_context *ctx)
+{
+ struct i915_guc_client *client;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_guc *guc = &dev_priv->guc;
+ struct drm_i915_gem_object *obj;
+
+ client = kzalloc(sizeof(*client), GFP_KERNEL);
+ if (!client)
+ return NULL;
+
+ client->doorbell_id = GUC_INVALID_DOORBELL_ID;
+ client->priority = priority;
+ client->owner = ctx;
+ client->guc = guc;
+
+ client->ctx_index = (uint32_t)ida_simple_get(&guc->ctx_ids, 0,
+ GUC_MAX_GPU_CONTEXTS, GFP_KERNEL);
+ if (client->ctx_index >= GUC_MAX_GPU_CONTEXTS) {
+ client->ctx_index = GUC_INVALID_CTX_ID;
+ goto err;
+ }
+
+ /* The first page is doorbell/proc_desc. Two followed pages are wq. */
+ obj = gem_allocate_guc_obj(dev, GUC_DB_SIZE + GUC_WQ_SIZE);
+ if (!obj)
+ goto err;
+
+ client->client_obj = obj;
+ client->wq_offset = GUC_DB_SIZE;
+ client->wq_size = GUC_WQ_SIZE;
+ spin_lock_init(&client->wq_lock);
+
+ client->doorbell_offset = select_doorbell_cacheline(guc);
+
+ /*
+ * Since the doorbell only requires a single cacheline, we can save
+ * space by putting the application process descriptor in the same
+ * page. Use the half of the page that doesn't include the doorbell.
+ */
+ if (client->doorbell_offset >= (GUC_DB_SIZE / 2))
+ client->proc_desc_offset = 0;
+ else
+ client->proc_desc_offset = (GUC_DB_SIZE / 2);
+
+ client->doorbell_id = assign_doorbell(guc, client->priority);
+ if (client->doorbell_id == GUC_INVALID_DOORBELL_ID)
+ /* XXX: evict a doorbell instead */
+ goto err;
+
+ guc_init_proc_desc(guc, client);
+ guc_init_ctx_desc(guc, client);
+ guc_init_doorbell(guc, client);
+
+ /* XXX: Any cache flushes needed? General domain mgmt calls? */
+
+ if (host2guc_allocate_doorbell(guc, client))
+ goto err;
+
+ DRM_DEBUG_DRIVER("new priority %u client %p: ctx_index %u db_id %u\n",
+ priority, client, client->ctx_index, client->doorbell_id);
+
+ return client;
+
+err:
+ DRM_ERROR("FAILED to create priority %u GuC client!\n", priority);
+
+ guc_client_free(dev, client);
+ return NULL;
+}
+
+static void guc_create_log(struct intel_guc *guc)
+{
+ struct drm_i915_private *dev_priv = guc_to_i915(guc);
+ struct drm_i915_gem_object *obj;
+ unsigned long offset;
+ uint32_t size, flags;
+
+ if (i915.guc_log_level < GUC_LOG_VERBOSITY_MIN)
+ return;
+
+ if (i915.guc_log_level > GUC_LOG_VERBOSITY_MAX)
+ i915.guc_log_level = GUC_LOG_VERBOSITY_MAX;
+
+ /* The first page is to save log buffer state. Allocate one
+ * extra page for others in case for overlap */
+ size = (1 + GUC_LOG_DPC_PAGES + 1 +
+ GUC_LOG_ISR_PAGES + 1 +
+ GUC_LOG_CRASH_PAGES + 1) << PAGE_SHIFT;
+
+ obj = guc->log_obj;
+ if (!obj) {
+ obj = gem_allocate_guc_obj(dev_priv->dev, size);
+ if (!obj) {
+ /* logging will be off */
+ i915.guc_log_level = -1;
+ return;
+ }
+
+ guc->log_obj = obj;
+ }
+
+ /* each allocated unit is a page */
+ flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL |
+ (GUC_LOG_DPC_PAGES << GUC_LOG_DPC_SHIFT) |
+ (GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
+ (GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT);
+
+ offset = i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT; /* in pages */
+ guc->log_flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
+}
+
+/*
+ * Set up the memory resources to be shared with the GuC. At this point,
+ * we require just one object that can be mapped through the GGTT.
+ */
+int i915_guc_submission_init(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ const size_t ctxsize = sizeof(struct guc_context_desc);
+ const size_t poolsize = GUC_MAX_GPU_CONTEXTS * ctxsize;
+ const size_t gemsize = round_up(poolsize, PAGE_SIZE);
+ struct intel_guc *guc = &dev_priv->guc;
+
+ if (!i915.enable_guc_submission)
+ return 0; /* not enabled */
+
+ if (guc->ctx_pool_obj)
+ return 0; /* already allocated */
+
+ guc->ctx_pool_obj = gem_allocate_guc_obj(dev_priv->dev, gemsize);
+ if (!guc->ctx_pool_obj)
+ return -ENOMEM;
+
+ spin_lock_init(&dev_priv->guc.host2guc_lock);
+
+ ida_init(&guc->ctx_ids);
+
+ guc_create_log(guc);
+
+ return 0;
+}
+
+int i915_guc_submission_enable(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_guc *guc = &dev_priv->guc;
+ struct intel_context *ctx = dev_priv->ring[RCS].default_context;
+ struct i915_guc_client *client;
+
+ /* client for execbuf submission */
+ client = guc_client_alloc(dev, GUC_CTX_PRIORITY_KMD_NORMAL, ctx);
+ if (!client) {
+ DRM_ERROR("Failed to create execbuf guc_client\n");
+ return -ENOMEM;
+ }
+
+ guc->execbuf_client = client;
+
+ host2guc_sample_forcewake(guc, client);
+
+ return 0;
+}
+
+void i915_guc_submission_disable(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_guc *guc = &dev_priv->guc;
+
+ guc_client_free(dev, guc->execbuf_client);
+ guc->execbuf_client = NULL;
+}
+
+void i915_guc_submission_fini(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_guc *guc = &dev_priv->guc;
+
+ gem_release_guc_obj(dev_priv->guc.log_obj);
+ guc->log_obj = NULL;
+
+ if (guc->ctx_pool_obj)
+ ida_destroy(&guc->ctx_ids);
+ gem_release_guc_obj(guc->ctx_pool_obj);
+ guc->ctx_pool_obj = NULL;
+}
* and related files, but that will be described in separate chapters.
*/
+static const u32 hpd_ilk[HPD_NUM_PINS] = {
+ [HPD_PORT_A] = DE_DP_A_HOTPLUG,
+};
+
+static const u32 hpd_ivb[HPD_NUM_PINS] = {
+ [HPD_PORT_A] = DE_DP_A_HOTPLUG_IVB,
+};
+
+static const u32 hpd_bdw[HPD_NUM_PINS] = {
+ [HPD_PORT_A] = GEN8_PORT_DP_A_HOTPLUG,
+};
+
static const u32 hpd_ibx[HPD_NUM_PINS] = {
[HPD_CRT] = SDE_CRT_HOTPLUG,
[HPD_SDVO_B] = SDE_SDVOB_HOTPLUG,
};
static const u32 hpd_spt[HPD_NUM_PINS] = {
+ [HPD_PORT_A] = SDE_PORTA_HOTPLUG_SPT,
[HPD_PORT_B] = SDE_PORTB_HOTPLUG_CPT,
[HPD_PORT_C] = SDE_PORTC_HOTPLUG_CPT,
[HPD_PORT_D] = SDE_PORTD_HOTPLUG_CPT,
/* BXT hpd list */
static const u32 hpd_bxt[HPD_NUM_PINS] = {
+ [HPD_PORT_A] = BXT_DE_PORT_HP_DDIA,
[HPD_PORT_B] = BXT_DE_PORT_HP_DDIB,
[HPD_PORT_C] = BXT_DE_PORT_HP_DDIC
};
static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir);
/* For display hotplug interrupt */
-void
-ironlake_enable_display_irq(struct drm_i915_private *dev_priv, u32 mask)
+static inline void
+i915_hotplug_interrupt_update_locked(struct drm_i915_private *dev_priv,
+ uint32_t mask,
+ uint32_t bits)
{
+ uint32_t val;
+
assert_spin_locked(&dev_priv->irq_lock);
+ WARN_ON(bits & ~mask);
- if (WARN_ON(!intel_irqs_enabled(dev_priv)))
- return;
+ val = I915_READ(PORT_HOTPLUG_EN);
+ val &= ~mask;
+ val |= bits;
+ I915_WRITE(PORT_HOTPLUG_EN, val);
+}
- if ((dev_priv->irq_mask & mask) != 0) {
- dev_priv->irq_mask &= ~mask;
- I915_WRITE(DEIMR, dev_priv->irq_mask);
- POSTING_READ(DEIMR);
- }
+/**
+ * i915_hotplug_interrupt_update - update hotplug interrupt enable
+ * @dev_priv: driver private
+ * @mask: bits to update
+ * @bits: bits to enable
+ * NOTE: the HPD enable bits are modified both inside and outside
+ * of an interrupt context. To avoid that read-modify-write cycles
+ * interfer, these bits are protected by a spinlock. Since this
+ * function is usually not called from a context where the lock is
+ * held already, this function acquires the lock itself. A non-locking
+ * version is also available.
+ */
+void i915_hotplug_interrupt_update(struct drm_i915_private *dev_priv,
+ uint32_t mask,
+ uint32_t bits)
+{
+ spin_lock_irq(&dev_priv->irq_lock);
+ i915_hotplug_interrupt_update_locked(dev_priv, mask, bits);
+ spin_unlock_irq(&dev_priv->irq_lock);
}
-void
-ironlake_disable_display_irq(struct drm_i915_private *dev_priv, u32 mask)
+/**
+ * ilk_update_display_irq - update DEIMR
+ * @dev_priv: driver private
+ * @interrupt_mask: mask of interrupt bits to update
+ * @enabled_irq_mask: mask of interrupt bits to enable
+ */
+static void ilk_update_display_irq(struct drm_i915_private *dev_priv,
+ uint32_t interrupt_mask,
+ uint32_t enabled_irq_mask)
{
+ uint32_t new_val;
+
assert_spin_locked(&dev_priv->irq_lock);
+ WARN_ON(enabled_irq_mask & ~interrupt_mask);
+
if (WARN_ON(!intel_irqs_enabled(dev_priv)))
return;
- if ((dev_priv->irq_mask & mask) != mask) {
- dev_priv->irq_mask |= mask;
+ new_val = dev_priv->irq_mask;
+ new_val &= ~interrupt_mask;
+ new_val |= (~enabled_irq_mask & interrupt_mask);
+
+ if (new_val != dev_priv->irq_mask) {
+ dev_priv->irq_mask = new_val;
I915_WRITE(DEIMR, dev_priv->irq_mask);
POSTING_READ(DEIMR);
}
}
+void
+ironlake_enable_display_irq(struct drm_i915_private *dev_priv, u32 mask)
+{
+ ilk_update_display_irq(dev_priv, mask, mask);
+}
+
+void
+ironlake_disable_display_irq(struct drm_i915_private *dev_priv, u32 mask)
+{
+ ilk_update_display_irq(dev_priv, mask, 0);
+}
+
/**
* ilk_update_gt_irq - update GTIMR
* @dev_priv: driver private
synchronize_irq(dev->irq);
}
+/**
+ * bdw_update_port_irq - update DE port interrupt
+ * @dev_priv: driver private
+ * @interrupt_mask: mask of interrupt bits to update
+ * @enabled_irq_mask: mask of interrupt bits to enable
+ */
+static void bdw_update_port_irq(struct drm_i915_private *dev_priv,
+ uint32_t interrupt_mask,
+ uint32_t enabled_irq_mask)
+{
+ uint32_t new_val;
+ uint32_t old_val;
+
+ assert_spin_locked(&dev_priv->irq_lock);
+
+ WARN_ON(enabled_irq_mask & ~interrupt_mask);
+
+ if (WARN_ON(!intel_irqs_enabled(dev_priv)))
+ return;
+
+ old_val = I915_READ(GEN8_DE_PORT_IMR);
+
+ new_val = old_val;
+ new_val &= ~interrupt_mask;
+ new_val |= (~enabled_irq_mask & interrupt_mask);
+
+ if (new_val != old_val) {
+ I915_WRITE(GEN8_DE_PORT_IMR, new_val);
+ POSTING_READ(GEN8_DE_PORT_IMR);
+ }
+}
+
/**
* ibx_display_interrupt_update - update SDEIMR
* @dev_priv: driver private
{
switch (port) {
case PORT_A:
- return val & BXT_PORTA_HOTPLUG_LONG_DETECT;
+ return val & PORTA_HOTPLUG_LONG_DETECT;
+ case PORT_B:
+ return val & PORTB_HOTPLUG_LONG_DETECT;
+ case PORT_C:
+ return val & PORTC_HOTPLUG_LONG_DETECT;
+ default:
+ return false;
+ }
+}
+
+static bool spt_port_hotplug2_long_detect(enum port port, u32 val)
+{
+ switch (port) {
+ case PORT_E:
+ return val & PORTE_HOTPLUG_LONG_DETECT;
+ default:
+ return false;
+ }
+}
+
+static bool spt_port_hotplug_long_detect(enum port port, u32 val)
+{
+ switch (port) {
+ case PORT_A:
+ return val & PORTA_HOTPLUG_LONG_DETECT;
case PORT_B:
return val & PORTB_HOTPLUG_LONG_DETECT;
case PORT_C:
}
}
+static bool ilk_port_hotplug_long_detect(enum port port, u32 val)
+{
+ switch (port) {
+ case PORT_A:
+ return val & DIGITAL_PORTA_HOTPLUG_LONG_DETECT;
+ default:
+ return false;
+ }
+}
+
static bool pch_port_hotplug_long_detect(enum port port, u32 val)
{
switch (port) {
return val & PORTC_HOTPLUG_LONG_DETECT;
case PORT_D:
return val & PORTD_HOTPLUG_LONG_DETECT;
- case PORT_E:
- return val & PORTE_HOTPLUG_LONG_DETECT;
default:
return false;
}
}
}
-/* Get a bit mask of pins that have triggered, and which ones may be long. */
+/*
+ * Get a bit mask of pins that have triggered, and which ones may be long.
+ * This can be called multiple times with the same masks to accumulate
+ * hotplug detection results from several registers.
+ *
+ * Note that the caller is expected to zero out the masks initially.
+ */
static void intel_get_hpd_pins(u32 *pin_mask, u32 *long_mask,
u32 hotplug_trigger, u32 dig_hotplug_reg,
const u32 hpd[HPD_NUM_PINS],
enum port port;
int i;
- *pin_mask = 0;
- *long_mask = 0;
-
for_each_hpd_pin(i) {
if ((hpd[i] & hotplug_trigger) == 0)
continue;
{
struct drm_i915_private *dev_priv = dev->dev_private;
u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
- u32 pin_mask, long_mask;
+ u32 pin_mask = 0, long_mask = 0;
if (!hotplug_status)
return;
if (IS_G4X(dev) || IS_VALLEYVIEW(dev)) {
u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
- intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
- hotplug_trigger, hpd_status_g4x,
- i9xx_port_hotplug_long_detect);
- intel_hpd_irq_handler(dev, pin_mask, long_mask);
+ if (hotplug_trigger) {
+ intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+ hotplug_trigger, hpd_status_g4x,
+ i9xx_port_hotplug_long_detect);
+
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
+ }
if (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
dp_aux_irq_handler(dev);
} else {
u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
- intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
- hotplug_trigger, hpd_status_i915,
- i9xx_port_hotplug_long_detect);
- intel_hpd_irq_handler(dev, pin_mask, long_mask);
+ if (hotplug_trigger) {
+ intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+ hotplug_trigger, hpd_status_i915,
+ i9xx_port_hotplug_long_detect);
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
+ }
}
}
return ret;
}
+static void ibx_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
+ const u32 hpd[HPD_NUM_PINS])
+{
+ struct drm_i915_private *dev_priv = to_i915(dev);
+ u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
+
+ dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
+ I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
+
+ intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+ dig_hotplug_reg, hpd,
+ pch_port_hotplug_long_detect);
+
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
+}
+
static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir)
{
struct drm_i915_private *dev_priv = dev->dev_private;
int pipe;
u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK;
- if (hotplug_trigger) {
- u32 dig_hotplug_reg, pin_mask, long_mask;
-
- dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
- I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
-
- intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
- dig_hotplug_reg, hpd_ibx,
- pch_port_hotplug_long_detect);
- intel_hpd_irq_handler(dev, pin_mask, long_mask);
- }
+ if (hotplug_trigger)
+ ibx_hpd_irq_handler(dev, hotplug_trigger, hpd_ibx);
if (pch_iir & SDE_AUDIO_POWER_MASK) {
int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK) >>
{
struct drm_i915_private *dev_priv = dev->dev_private;
int pipe;
- u32 hotplug_trigger;
-
- if (HAS_PCH_SPT(dev))
- hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_SPT;
- else
- hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_CPT;
-
- if (hotplug_trigger) {
- u32 dig_hotplug_reg, pin_mask, long_mask;
-
- dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
- I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
-
- if (HAS_PCH_SPT(dev)) {
- intel_get_hpd_pins(&pin_mask, &long_mask,
- hotplug_trigger,
- dig_hotplug_reg, hpd_spt,
- pch_port_hotplug_long_detect);
-
- /* detect PORTE HP event */
- dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG2);
- if (pch_port_hotplug_long_detect(PORT_E,
- dig_hotplug_reg))
- long_mask |= 1 << HPD_PORT_E;
- } else
- intel_get_hpd_pins(&pin_mask, &long_mask,
- hotplug_trigger,
- dig_hotplug_reg, hpd_cpt,
- pch_port_hotplug_long_detect);
+ u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_CPT;
- intel_hpd_irq_handler(dev, pin_mask, long_mask);
- }
+ if (hotplug_trigger)
+ ibx_hpd_irq_handler(dev, hotplug_trigger, hpd_cpt);
if (pch_iir & SDE_AUDIO_POWER_MASK_CPT) {
int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK_CPT) >>
cpt_serr_int_handler(dev);
}
+static void spt_irq_handler(struct drm_device *dev, u32 pch_iir)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_SPT &
+ ~SDE_PORTE_HOTPLUG_SPT;
+ u32 hotplug2_trigger = pch_iir & SDE_PORTE_HOTPLUG_SPT;
+ u32 pin_mask = 0, long_mask = 0;
+
+ if (hotplug_trigger) {
+ u32 dig_hotplug_reg;
+
+ dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
+ I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
+
+ intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+ dig_hotplug_reg, hpd_spt,
+ spt_port_hotplug_long_detect);
+ }
+
+ if (hotplug2_trigger) {
+ u32 dig_hotplug_reg;
+
+ dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG2);
+ I915_WRITE(PCH_PORT_HOTPLUG2, dig_hotplug_reg);
+
+ intel_get_hpd_pins(&pin_mask, &long_mask, hotplug2_trigger,
+ dig_hotplug_reg, hpd_spt,
+ spt_port_hotplug2_long_detect);
+ }
+
+ if (pin_mask)
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
+
+ if (pch_iir & SDE_GMBUS_CPT)
+ gmbus_irq_handler(dev);
+}
+
+static void ilk_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
+ const u32 hpd[HPD_NUM_PINS])
+{
+ struct drm_i915_private *dev_priv = to_i915(dev);
+ u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
+
+ dig_hotplug_reg = I915_READ(DIGITAL_PORT_HOTPLUG_CNTRL);
+ I915_WRITE(DIGITAL_PORT_HOTPLUG_CNTRL, dig_hotplug_reg);
+
+ intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+ dig_hotplug_reg, hpd,
+ ilk_port_hotplug_long_detect);
+
+ intel_hpd_irq_handler(dev, pin_mask, long_mask);
+}
+
static void ilk_display_irq_handler(struct drm_device *dev, u32 de_iir)
{
struct drm_i915_private *dev_priv = dev->dev_private;
enum pipe pipe;
+ u32 hotplug_trigger = de_iir & DE_DP_A_HOTPLUG;
+
+ if (hotplug_trigger)
+ ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_ilk);
if (de_iir & DE_AUX_CHANNEL_A)
dp_aux_irq_handler(dev);
{
struct drm_i915_private *dev_priv = dev->dev_private;
enum pipe pipe;
+ u32 hotplug_trigger = de_iir & DE_DP_A_HOTPLUG_IVB;
+
+ if (hotplug_trigger)
+ ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_ivb);
if (de_iir & DE_ERR_INT_IVB)
ivb_err_int_handler(dev);
return ret;
}
-static void bxt_hpd_handler(struct drm_device *dev, uint32_t iir_status)
+static void bxt_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
+ const u32 hpd[HPD_NUM_PINS])
{
- struct drm_i915_private *dev_priv = dev->dev_private;
- u32 hp_control, hp_trigger;
- u32 pin_mask, long_mask;
-
- /* Get the status */
- hp_trigger = iir_status & BXT_DE_PORT_HOTPLUG_MASK;
- hp_control = I915_READ(BXT_HOTPLUG_CTL);
+ struct drm_i915_private *dev_priv = to_i915(dev);
+ u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
- /* Hotplug not enabled ? */
- if (!(hp_control & BXT_HOTPLUG_CTL_MASK)) {
- DRM_ERROR("Interrupt when HPD disabled\n");
- return;
- }
+ dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
+ I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg);
- /* Clear sticky bits in hpd status */
- I915_WRITE(BXT_HOTPLUG_CTL, hp_control);
+ intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
+ dig_hotplug_reg, hpd,
+ bxt_port_hotplug_long_detect);
- intel_get_hpd_pins(&pin_mask, &long_mask, hp_trigger, hp_control,
- hpd_bxt, bxt_port_hotplug_long_detect);
intel_hpd_irq_handler(dev, pin_mask, long_mask);
}
if (!intel_irqs_enabled(dev_priv))
return IRQ_NONE;
- if (IS_GEN9(dev))
+ if (INTEL_INFO(dev_priv)->gen >= 9)
aux_mask |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
GEN9_AUX_CHANNEL_D;
tmp = I915_READ(GEN8_DE_PORT_IIR);
if (tmp) {
bool found = false;
+ u32 hotplug_trigger = 0;
+
+ if (IS_BROXTON(dev_priv))
+ hotplug_trigger = tmp & BXT_DE_PORT_HOTPLUG_MASK;
+ else if (IS_BROADWELL(dev_priv))
+ hotplug_trigger = tmp & GEN8_PORT_DP_A_HOTPLUG;
I915_WRITE(GEN8_DE_PORT_IIR, tmp);
ret = IRQ_HANDLED;
found = true;
}
- if (IS_BROXTON(dev) && tmp & BXT_DE_PORT_HOTPLUG_MASK) {
- bxt_hpd_handler(dev, tmp);
+ if (hotplug_trigger) {
+ if (IS_BROXTON(dev))
+ bxt_hpd_irq_handler(dev, hotplug_trigger, hpd_bxt);
+ else
+ ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_bdw);
found = true;
}
intel_pipe_handle_vblank(dev, pipe))
intel_check_page_flip(dev, pipe);
- if (IS_GEN9(dev))
+ if (INTEL_INFO(dev_priv)->gen >= 9)
flip_done = pipe_iir & GEN9_PIPE_PLANE1_FLIP_DONE;
else
flip_done = pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE;
pipe);
- if (IS_GEN9(dev))
+ if (INTEL_INFO(dev_priv)->gen >= 9)
fault_errors = pipe_iir & GEN9_DE_PIPE_IRQ_FAULT_ERRORS;
else
fault_errors = pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
if (pch_iir) {
I915_WRITE(SDEIIR, pch_iir);
ret = IRQ_HANDLED;
- cpt_irq_handler(dev, pch_iir);
+
+ if (HAS_PCH_SPT(dev_priv))
+ spt_irq_handler(dev, pch_iir);
+ else
+ cpt_irq_handler(dev, pch_iir);
} else
DRM_ERROR("The master control interrupt lied (SDE)!\n");
{
enum pipe pipe;
- I915_WRITE(PORT_HOTPLUG_EN, 0);
+ i915_hotplug_interrupt_update(dev_priv, 0xFFFFFFFF, 0);
I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
for_each_pipe(dev_priv, pipe)
vlv_display_irq_reset(dev_priv);
}
+static u32 intel_hpd_enabled_irqs(struct drm_device *dev,
+ const u32 hpd[HPD_NUM_PINS])
+{
+ struct drm_i915_private *dev_priv = to_i915(dev);
+ struct intel_encoder *encoder;
+ u32 enabled_irqs = 0;
+
+ for_each_intel_encoder(dev, encoder)
+ if (dev_priv->hotplug.stats[encoder->hpd_pin].state == HPD_ENABLED)
+ enabled_irqs |= hpd[encoder->hpd_pin];
+
+ return enabled_irqs;
+}
+
static void ibx_hpd_irq_setup(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_encoder *intel_encoder;
- u32 hotplug_irqs, hotplug, enabled_irqs = 0;
+ u32 hotplug_irqs, hotplug, enabled_irqs;
if (HAS_PCH_IBX(dev)) {
hotplug_irqs = SDE_HOTPLUG_MASK;
- for_each_intel_encoder(dev, intel_encoder)
- if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED)
- enabled_irqs |= hpd_ibx[intel_encoder->hpd_pin];
- } else if (HAS_PCH_SPT(dev)) {
- hotplug_irqs = SDE_HOTPLUG_MASK_SPT;
- for_each_intel_encoder(dev, intel_encoder)
- if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED)
- enabled_irqs |= hpd_spt[intel_encoder->hpd_pin];
+ enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_ibx);
} else {
hotplug_irqs = SDE_HOTPLUG_MASK_CPT;
- for_each_intel_encoder(dev, intel_encoder)
- if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED)
- enabled_irqs |= hpd_cpt[intel_encoder->hpd_pin];
+ enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_cpt);
}
ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
/*
* Enable digital hotplug on the PCH, and configure the DP short pulse
- * duration to 2ms (which is the minimum in the Display Port spec)
- *
- * This register is the same on all known PCH chips.
+ * duration to 2ms (which is the minimum in the Display Port spec).
+ * The pulse duration bits are reserved on LPT+.
*/
hotplug = I915_READ(PCH_PORT_HOTPLUG);
hotplug &= ~(PORTD_PULSE_DURATION_MASK|PORTC_PULSE_DURATION_MASK|PORTB_PULSE_DURATION_MASK);
hotplug |= PORTD_HOTPLUG_ENABLE | PORTD_PULSE_DURATION_2ms;
hotplug |= PORTC_HOTPLUG_ENABLE | PORTC_PULSE_DURATION_2ms;
hotplug |= PORTB_HOTPLUG_ENABLE | PORTB_PULSE_DURATION_2ms;
+ /*
+ * When CPU and PCH are on the same package, port A
+ * HPD must be enabled in both north and south.
+ */
+ if (HAS_PCH_LPT_LP(dev))
+ hotplug |= PORTA_HOTPLUG_ENABLE;
I915_WRITE(PCH_PORT_HOTPLUG, hotplug);
+}
- /* enable SPT PORTE hot plug */
- if (HAS_PCH_SPT(dev)) {
- hotplug = I915_READ(PCH_PORT_HOTPLUG2);
- hotplug |= PORTE_HOTPLUG_ENABLE;
- I915_WRITE(PCH_PORT_HOTPLUG2, hotplug);
- }
+static void spt_hpd_irq_setup(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 hotplug_irqs, hotplug, enabled_irqs;
+
+ hotplug_irqs = SDE_HOTPLUG_MASK_SPT;
+ enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_spt);
+
+ ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
+
+ /* Enable digital hotplug on the PCH */
+ hotplug = I915_READ(PCH_PORT_HOTPLUG);
+ hotplug |= PORTD_HOTPLUG_ENABLE | PORTC_HOTPLUG_ENABLE |
+ PORTB_HOTPLUG_ENABLE | PORTA_HOTPLUG_ENABLE;
+ I915_WRITE(PCH_PORT_HOTPLUG, hotplug);
+
+ hotplug = I915_READ(PCH_PORT_HOTPLUG2);
+ hotplug |= PORTE_HOTPLUG_ENABLE;
+ I915_WRITE(PCH_PORT_HOTPLUG2, hotplug);
}
-static void bxt_hpd_irq_setup(struct drm_device *dev)
+static void ilk_hpd_irq_setup(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_encoder *intel_encoder;
- u32 hotplug_port = 0;
- u32 hotplug_ctrl;
-
- /* Now, enable HPD */
- for_each_intel_encoder(dev, intel_encoder) {
- if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state
- == HPD_ENABLED)
- hotplug_port |= hpd_bxt[intel_encoder->hpd_pin];
+ u32 hotplug_irqs, hotplug, enabled_irqs;
+
+ if (INTEL_INFO(dev)->gen >= 8) {
+ hotplug_irqs = GEN8_PORT_DP_A_HOTPLUG;
+ enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_bdw);
+
+ bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs);
+ } else if (INTEL_INFO(dev)->gen >= 7) {
+ hotplug_irqs = DE_DP_A_HOTPLUG_IVB;
+ enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_ivb);
+
+ ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs);
+ } else {
+ hotplug_irqs = DE_DP_A_HOTPLUG;
+ enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_ilk);
+
+ ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs);
}
- /* Mask all HPD control bits */
- hotplug_ctrl = I915_READ(BXT_HOTPLUG_CTL) & ~BXT_HOTPLUG_CTL_MASK;
+ /*
+ * Enable digital hotplug on the CPU, and configure the DP short pulse
+ * duration to 2ms (which is the minimum in the Display Port spec)
+ * The pulse duration bits are reserved on HSW+.
+ */
+ hotplug = I915_READ(DIGITAL_PORT_HOTPLUG_CNTRL);
+ hotplug &= ~DIGITAL_PORTA_PULSE_DURATION_MASK;
+ hotplug |= DIGITAL_PORTA_HOTPLUG_ENABLE | DIGITAL_PORTA_PULSE_DURATION_2ms;
+ I915_WRITE(DIGITAL_PORT_HOTPLUG_CNTRL, hotplug);
+
+ ibx_hpd_irq_setup(dev);
+}
+
+static void bxt_hpd_irq_setup(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 hotplug_irqs, hotplug, enabled_irqs;
- /* Enable requested port in hotplug control */
- /* TODO: implement (short) HPD support on port A */
- WARN_ON_ONCE(hotplug_port & BXT_DE_PORT_HP_DDIA);
- if (hotplug_port & BXT_DE_PORT_HP_DDIB)
- hotplug_ctrl |= BXT_DDIB_HPD_ENABLE;
- if (hotplug_port & BXT_DE_PORT_HP_DDIC)
- hotplug_ctrl |= BXT_DDIC_HPD_ENABLE;
- I915_WRITE(BXT_HOTPLUG_CTL, hotplug_ctrl);
+ enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_bxt);
+ hotplug_irqs = BXT_DE_PORT_HOTPLUG_MASK;
- /* Unmask DDI hotplug in IMR */
- hotplug_ctrl = I915_READ(GEN8_DE_PORT_IMR) & ~hotplug_port;
- I915_WRITE(GEN8_DE_PORT_IMR, hotplug_ctrl);
+ bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs);
- /* Enable DDI hotplug in IER */
- hotplug_ctrl = I915_READ(GEN8_DE_PORT_IER) | hotplug_port;
- I915_WRITE(GEN8_DE_PORT_IER, hotplug_ctrl);
- POSTING_READ(GEN8_DE_PORT_IER);
+ hotplug = I915_READ(PCH_PORT_HOTPLUG);
+ hotplug |= PORTC_HOTPLUG_ENABLE | PORTB_HOTPLUG_ENABLE |
+ PORTA_HOTPLUG_ENABLE;
+ I915_WRITE(PCH_PORT_HOTPLUG, hotplug);
}
static void ibx_irq_postinstall(struct drm_device *dev)
DE_PLANEB_FLIP_DONE_IVB |
DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB);
extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB |
- DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB);
+ DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB |
+ DE_DP_A_HOTPLUG_IVB);
} 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_CRC_DONE | DE_PIPEA_CRC_DONE |
DE_POISON);
- extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT |
- DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN;
+ extra_mask = (DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT |
+ DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN |
+ DE_DP_A_HOTPLUG);
}
dev_priv->irq_mask = ~display_mask;
{
dev_priv->irq_mask = ~0;
- I915_WRITE(PORT_HOTPLUG_EN, 0);
+ i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
POSTING_READ(PORT_HOTPLUG_EN);
I915_WRITE(VLV_IIR, 0xffffffff);
{
uint32_t de_pipe_masked = GEN8_PIPE_CDCLK_CRC_DONE;
uint32_t de_pipe_enables;
- int pipe;
- u32 de_port_en = GEN8_AUX_CHANNEL_A;
+ u32 de_port_masked = GEN8_AUX_CHANNEL_A;
+ u32 de_port_enables;
+ enum pipe pipe;
- if (IS_GEN9(dev_priv)) {
+ if (INTEL_INFO(dev_priv)->gen >= 9) {
de_pipe_masked |= GEN9_PIPE_PLANE1_FLIP_DONE |
GEN9_DE_PIPE_IRQ_FAULT_ERRORS;
- de_port_en |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
- GEN9_AUX_CHANNEL_D;
-
+ de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
+ GEN9_AUX_CHANNEL_D;
if (IS_BROXTON(dev_priv))
- de_port_en |= BXT_DE_PORT_GMBUS;
- } else
+ de_port_masked |= BXT_DE_PORT_GMBUS;
+ } else {
de_pipe_masked |= GEN8_PIPE_PRIMARY_FLIP_DONE |
GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
+ }
de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
GEN8_PIPE_FIFO_UNDERRUN;
+ de_port_enables = de_port_masked;
+ if (IS_BROXTON(dev_priv))
+ de_port_enables |= BXT_DE_PORT_HOTPLUG_MASK;
+ else if (IS_BROADWELL(dev_priv))
+ de_port_enables |= GEN8_PORT_DP_A_HOTPLUG;
+
dev_priv->de_irq_mask[PIPE_A] = ~de_pipe_masked;
dev_priv->de_irq_mask[PIPE_B] = ~de_pipe_masked;
dev_priv->de_irq_mask[PIPE_C] = ~de_pipe_masked;
dev_priv->de_irq_mask[pipe],
de_pipe_enables);
- GEN5_IRQ_INIT(GEN8_DE_PORT_, ~de_port_en, de_port_en);
+ GEN5_IRQ_INIT(GEN8_DE_PORT_, ~de_port_masked, de_port_enables);
}
static int gen8_irq_postinstall(struct drm_device *dev)
int pipe;
if (I915_HAS_HOTPLUG(dev)) {
- I915_WRITE(PORT_HOTPLUG_EN, 0);
+ i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
}
I915_USER_INTERRUPT;
if (I915_HAS_HOTPLUG(dev)) {
- I915_WRITE(PORT_HOTPLUG_EN, 0);
+ i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
POSTING_READ(PORT_HOTPLUG_EN);
/* Enable in IER... */
int pipe;
if (I915_HAS_HOTPLUG(dev)) {
- I915_WRITE(PORT_HOTPLUG_EN, 0);
+ i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
}
struct drm_i915_private *dev_priv = dev->dev_private;
int pipe;
- I915_WRITE(PORT_HOTPLUG_EN, 0);
+ i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
I915_WRITE(HWSTAM, 0xeffe);
I915_WRITE(IER, enable_mask);
POSTING_READ(IER);
- I915_WRITE(PORT_HOTPLUG_EN, 0);
+ i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
POSTING_READ(PORT_HOTPLUG_EN);
i915_enable_asle_pipestat(dev);
static void i915_hpd_irq_setup(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_encoder *intel_encoder;
u32 hotplug_en;
assert_spin_locked(&dev_priv->irq_lock);
- hotplug_en = I915_READ(PORT_HOTPLUG_EN);
- hotplug_en &= ~HOTPLUG_INT_EN_MASK;
/* Note HDMI and DP share hotplug bits */
/* enable bits are the same for all generations */
- for_each_intel_encoder(dev, intel_encoder)
- if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED)
- hotplug_en |= hpd_mask_i915[intel_encoder->hpd_pin];
+ hotplug_en = intel_hpd_enabled_irqs(dev, hpd_mask_i915);
/* Programming the CRT detection parameters tends
to generate a spurious hotplug event about three
seconds later. So just do it once.
*/
if (IS_G4X(dev))
hotplug_en |= CRT_HOTPLUG_ACTIVATION_PERIOD_64;
- hotplug_en &= ~CRT_HOTPLUG_VOLTAGE_COMPARE_MASK;
hotplug_en |= CRT_HOTPLUG_VOLTAGE_COMPARE_50;
/* Ignore TV since it's buggy */
- I915_WRITE(PORT_HOTPLUG_EN, hotplug_en);
+ i915_hotplug_interrupt_update_locked(dev_priv,
+ (HOTPLUG_INT_EN_MASK
+ | CRT_HOTPLUG_VOLTAGE_COMPARE_MASK),
+ hotplug_en);
}
static irqreturn_t i965_irq_handler(int irq, void *arg)
if (!dev_priv)
return;
- I915_WRITE(PORT_HOTPLUG_EN, 0);
+ i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
I915_WRITE(HWSTAM, 0xffffffff);
dev->driver->irq_uninstall = gen8_irq_uninstall;
dev->driver->enable_vblank = gen8_enable_vblank;
dev->driver->disable_vblank = gen8_disable_vblank;
- if (HAS_PCH_SPLIT(dev))
- dev_priv->display.hpd_irq_setup = ibx_hpd_irq_setup;
- else
+ if (IS_BROXTON(dev))
dev_priv->display.hpd_irq_setup = bxt_hpd_irq_setup;
+ else if (HAS_PCH_SPT(dev))
+ dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup;
+ else
+ dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup;
} else if (HAS_PCH_SPLIT(dev)) {
dev->driver->irq_handler = ironlake_irq_handler;
dev->driver->irq_preinstall = ironlake_irq_reset;
dev->driver->irq_uninstall = ironlake_irq_uninstall;
dev->driver->enable_vblank = ironlake_enable_vblank;
dev->driver->disable_vblank = ironlake_disable_vblank;
- dev_priv->display.hpd_irq_setup = ibx_hpd_irq_setup;
+ dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup;
} else {
if (INTEL_INFO(dev_priv)->gen == 2) {
dev->driver->irq_preinstall = i8xx_irq_preinstall;
.preliminary_hw_support = IS_ENABLED(CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT),
.disable_power_well = 1,
.enable_ips = 1,
- .fastboot = 0,
.prefault_disable = 0,
.load_detect_test = 0,
.reset = true,
.use_mmio_flip = 0,
.mmio_debug = 0,
.verbose_state_checks = 1,
+ .nuclear_pageflip = 0,
.edp_vswing = 0,
.enable_guc_submission = false,
.guc_log_level = -1,
"Use kernel modesetting [KMS] (0=disable, "
"1=on, -1=force vga console preference [default])");
-module_param_named(panel_ignore_lid, i915.panel_ignore_lid, int, 0600);
+module_param_named_unsafe(panel_ignore_lid, i915.panel_ignore_lid, int, 0600);
MODULE_PARM_DESC(panel_ignore_lid,
"Override lid status (0=autodetect, 1=autodetect disabled [default], "
"-1=force lid closed, -2=force lid open)");
"Enable frame buffer compression for power savings "
"(default: -1 (use per-chip default))");
-module_param_named(lvds_channel_mode, i915.lvds_channel_mode, int, 0600);
+module_param_named_unsafe(lvds_channel_mode, i915.lvds_channel_mode, int, 0600);
MODULE_PARM_DESC(lvds_channel_mode,
"Specify LVDS channel mode "
"(0=probe BIOS [default], 1=single-channel, 2=dual-channel)");
-module_param_named(lvds_use_ssc, i915.panel_use_ssc, int, 0600);
+module_param_named_unsafe(lvds_use_ssc, i915.panel_use_ssc, int, 0600);
MODULE_PARM_DESC(lvds_use_ssc,
"Use Spread Spectrum Clock with panels [LVDS/eDP] "
"(default: auto from VBT)");
-module_param_named(vbt_sdvo_panel_type, i915.vbt_sdvo_panel_type, int, 0600);
+module_param_named_unsafe(vbt_sdvo_panel_type, i915.vbt_sdvo_panel_type, int, 0600);
MODULE_PARM_DESC(vbt_sdvo_panel_type,
"Override/Ignore selection of SDVO panel mode in the VBT "
"(-2=ignore, -1=auto [default], index in VBT BIOS table)");
module_param_named_unsafe(reset, i915.reset, bool, 0600);
MODULE_PARM_DESC(reset, "Attempt GPU resets (default: true)");
-module_param_named(enable_hangcheck, i915.enable_hangcheck, bool, 0644);
+module_param_named_unsafe(enable_hangcheck, i915.enable_hangcheck, bool, 0644);
MODULE_PARM_DESC(enable_hangcheck,
"Periodically check GPU activity for detecting hangs. "
"WARNING: Disabling this can cause system wide hangs. "
"Override PPGTT usage. "
"(-1=auto [default], 0=disabled, 1=aliasing, 2=full)");
-module_param_named(enable_execlists, i915.enable_execlists, int, 0400);
+module_param_named_unsafe(enable_execlists, i915.enable_execlists, int, 0400);
MODULE_PARM_DESC(enable_execlists,
"Override execlists usage. "
"(-1=auto [default], 0=disabled, 1=enabled)");
-module_param_named(enable_psr, i915.enable_psr, int, 0600);
+module_param_named_unsafe(enable_psr, i915.enable_psr, int, 0600);
MODULE_PARM_DESC(enable_psr, "Enable PSR (default: false)");
-module_param_named(preliminary_hw_support, i915.preliminary_hw_support, int, 0600);
+module_param_named_unsafe(preliminary_hw_support, i915.preliminary_hw_support, int, 0600);
MODULE_PARM_DESC(preliminary_hw_support,
"Enable preliminary hardware support.");
-module_param_named(disable_power_well, i915.disable_power_well, int, 0600);
+module_param_named_unsafe(disable_power_well, i915.disable_power_well, int, 0600);
MODULE_PARM_DESC(disable_power_well,
"Disable the power well when possible (default: true)");
-module_param_named(enable_ips, i915.enable_ips, int, 0600);
+module_param_named_unsafe(enable_ips, i915.enable_ips, int, 0600);
MODULE_PARM_DESC(enable_ips, "Enable IPS (default: true)");
-module_param_named(fastboot, i915.fastboot, bool, 0600);
-MODULE_PARM_DESC(fastboot,
- "Try to skip unnecessary mode sets at boot time (default: false)");
-
module_param_named_unsafe(prefault_disable, i915.prefault_disable, bool, 0600);
MODULE_PARM_DESC(prefault_disable,
"Disable page prefaulting for pread/pwrite/reloc (default:false). "
"Force-enable the VGA load detect code for testing (default:false). "
"For developers only.");
-module_param_named(invert_brightness, i915.invert_brightness, int, 0600);
+module_param_named_unsafe(invert_brightness, i915.invert_brightness, int, 0600);
MODULE_PARM_DESC(invert_brightness,
"Invert backlight brightness "
"(-1 force normal, 0 machine defaults, 1 force inversion), please "
module_param_named(disable_display, i915.disable_display, bool, 0600);
MODULE_PARM_DESC(disable_display, "Disable display (default: false)");
-module_param_named(disable_vtd_wa, i915.disable_vtd_wa, bool, 0600);
+module_param_named_unsafe(disable_vtd_wa, i915.disable_vtd_wa, bool, 0600);
MODULE_PARM_DESC(disable_vtd_wa, "Disable all VT-d workarounds (default: false)");
-module_param_named(enable_cmd_parser, i915.enable_cmd_parser, int, 0600);
+module_param_named_unsafe(enable_cmd_parser, i915.enable_cmd_parser, int, 0600);
MODULE_PARM_DESC(enable_cmd_parser,
"Enable command parsing (1=enabled [default], 0=disabled)");
-module_param_named(use_mmio_flip, i915.use_mmio_flip, int, 0600);
+module_param_named_unsafe(use_mmio_flip, i915.use_mmio_flip, int, 0600);
MODULE_PARM_DESC(use_mmio_flip,
"use MMIO flips (-1=never, 0=driver discretion [default], 1=always)");
MODULE_PARM_DESC(verbose_state_checks,
"Enable verbose logs (ie. WARN_ON()) in case of unexpected hw state conditions.");
+module_param_named_unsafe(nuclear_pageflip, i915.nuclear_pageflip, bool, 0600);
+MODULE_PARM_DESC(nuclear_pageflip,
+ "Force atomic modeset functionality; asynchronous mode is not yet supported. (default: false).");
+
/* WA to get away with the default setting in VBT for early platforms.Will be removed */
module_param_named_unsafe(edp_vswing, i915.edp_vswing, int, 0400);
MODULE_PARM_DESC(edp_vswing,
*/
#define MI_LOAD_REGISTER_IMM(x) MI_INSTR(0x22, 2*(x)-1)
#define MI_LRI_FORCE_POSTED (1<<12)
-#define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*(x)-1)
-#define MI_STORE_REGISTER_MEM_GEN8(x) MI_INSTR(0x24, 3*(x)-1)
+#define MI_STORE_REGISTER_MEM MI_INSTR(0x24, 1)
+#define MI_STORE_REGISTER_MEM_GEN8 MI_INSTR(0x24, 2)
#define MI_SRM_LRM_GLOBAL_GTT (1<<22)
#define MI_FLUSH_DW MI_INSTR(0x26, 1) /* for GEN6 */
#define MI_FLUSH_DW_STORE_INDEX (1<<21)
#define MI_INVALIDATE_BSD (1<<7)
#define MI_FLUSH_DW_USE_GTT (1<<2)
#define MI_FLUSH_DW_USE_PPGTT (0<<2)
-#define MI_LOAD_REGISTER_MEM(x) MI_INSTR(0x29, 2*(x)-1)
-#define MI_LOAD_REGISTER_MEM_GEN8(x) MI_INSTR(0x29, 3*(x)-1)
+#define MI_LOAD_REGISTER_MEM MI_INSTR(0x29, 1)
+#define MI_LOAD_REGISTER_MEM_GEN8 MI_INSTR(0x29, 2)
#define MI_BATCH_BUFFER MI_INSTR(0x30, 1)
#define MI_BATCH_NON_SECURE (1)
/* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
#define DPIO_CHV_INT_LOCK_THRESHOLD_SEL_COARSE 1 /* 1: coarse & 0 : fine */
#define CHV_PLL_DW9(ch) _PIPE(ch, _CHV_PLL_DW9_CH0, _CHV_PLL_DW9_CH1)
+#define _CHV_CMN_DW0_CH0 0x8100
+#define DPIO_ALLDL_POWERDOWN_SHIFT_CH0 19
+#define DPIO_ANYDL_POWERDOWN_SHIFT_CH0 18
+#define DPIO_ALLDL_POWERDOWN (1 << 1)
+#define DPIO_ANYDL_POWERDOWN (1 << 0)
+
#define _CHV_CMN_DW5_CH0 0x8114
#define CHV_BUFRIGHTENA1_DISABLE (0 << 20)
#define CHV_BUFRIGHTENA1_NORMAL (1 << 20)
#define _CHV_CMN_DW19_CH0 0x814c
#define _CHV_CMN_DW6_CH1 0x8098
+#define DPIO_ALLDL_POWERDOWN_SHIFT_CH1 30 /* CL2 DW6 only */
+#define DPIO_ANYDL_POWERDOWN_SHIFT_CH1 29 /* CL2 DW6 only */
+#define DPIO_DYNPWRDOWNEN_CH1 (1 << 28) /* CL2 DW6 only */
#define CHV_CMN_USEDCLKCHANNEL (1 << 13)
+
#define CHV_CMN_DW19(ch) _PIPE(ch, _CHV_CMN_DW19_CH0, _CHV_CMN_DW6_CH1)
+#define CHV_CMN_DW28 0x8170
+#define DPIO_CL1POWERDOWNEN (1 << 23)
+#define DPIO_DYNPWRDOWNEN_CH0 (1 << 22)
+#define DPIO_SUS_CLK_CONFIG_ON (0 << 0)
+#define DPIO_SUS_CLK_CONFIG_CLKREQ (1 << 0)
+#define DPIO_SUS_CLK_CONFIG_GATE (2 << 0)
+#define DPIO_SUS_CLK_CONFIG_GATE_CLKREQ (3 << 0)
+
#define CHV_CMN_DW30 0x8178
+#define DPIO_CL2_LDOFUSE_PWRENB (1 << 6)
#define DPIO_LRC_BYPASS (1 << 3)
#define _TXLANE(ch, lane, offset) ((ch ? 0x2400 : 0) + \
#define GEN7_GFX_PEND_TLB0 0x4034
#define GEN7_GFX_PEND_TLB1 0x4038
/* L3, CVS, ZTLB, RCC, CASC LRA min, max values */
-#define GEN7_LRA_LIMITS_BASE 0x403C
+#define GEN7_LRA_LIMITS(i) (0x403C + (i) * 4)
#define GEN7_LRA_LIMITS_REG_NUM 13
#define GEN7_MEDIA_MAX_REQ_COUNT 0x4070
#define GEN7_GFX_MAX_REQ_COUNT 0x4074
#define GFX_MODE_GEN7 0x0229c
#define RING_MODE_GEN7(ring) ((ring)->mmio_base+0x29c)
#define GFX_RUN_LIST_ENABLE (1<<15)
+#define GFX_INTERRUPT_STEERING (1<<14)
#define GFX_TLB_INVALIDATE_EXPLICIT (1<<13)
#define GFX_SURFACE_FAULT_ENABLE (1<<12)
#define GFX_REPLAY_MODE (1<<11)
#define GFX_PSMI_GRANULARITY (1<<10)
#define GFX_PPGTT_ENABLE (1<<9)
+#define GEN8_GFX_PPGTT_48B (1<<7)
+
+#define GFX_FORWARD_VBLANK_MASK (3<<5)
+#define GFX_FORWARD_VBLANK_NEVER (0<<5)
+#define GFX_FORWARD_VBLANK_ALWAYS (1<<5)
+#define GFX_FORWARD_VBLANK_COND (2<<5)
#define VLV_DISPLAY_BASE 0x180000
#define VLV_MIPI_BASE VLV_DISPLAY_BASE
#define FBC_CTL_CPU_FENCE (1<<1)
#define FBC_CTL_PLANE(plane) ((plane)<<0)
#define FBC_FENCE_OFF 0x03218 /* BSpec typo has 321Bh */
-#define FBC_TAG 0x03300
+#define FBC_TAG(i) (0x03300 + (i) * 4)
#define FBC_STATUS2 0x43214
#define FBC_COMPRESSION_MASK 0x7ff
#define DPIO_PHY_STATUS (VLV_DISPLAY_BASE + 0x6240)
#define DPLL_PORTD_READY_MASK (0xf)
#define DISPLAY_PHY_CONTROL (VLV_DISPLAY_BASE + 0x60100)
+#define PHY_CH_POWER_DOWN_OVRD_EN(phy, ch) (1 << (2*(phy)+(ch)+27))
#define PHY_LDO_DELAY_0NS 0x0
#define PHY_LDO_DELAY_200NS 0x1
#define PHY_LDO_DELAY_600NS 0x2
#define PHY_LDO_SEQ_DELAY(delay, phy) ((delay) << (2*(phy)+23))
+#define PHY_CH_POWER_DOWN_OVRD(mask, phy, ch) ((mask) << (8*(phy)+4*(ch)+11))
#define PHY_CH_SU_PSR 0x1
#define PHY_CH_DEEP_PSR 0x7
#define PHY_CH_POWER_MODE(mode, phy, ch) ((mode) << (6*(phy)+3*(ch)+2))
#define PHY_COM_LANE_RESET_DEASSERT(phy) (1 << (phy))
#define DISPLAY_PHY_STATUS (VLV_DISPLAY_BASE + 0x60104)
#define PHY_POWERGOOD(phy) (((phy) == DPIO_PHY0) ? (1<<31) : (1<<30))
+#define PHY_STATUS_CMN_LDO(phy, ch) (1 << (6-(6*(phy)+3*(ch))))
+#define PHY_STATUS_SPLINE_LDO(phy, ch, spline) (1 << (8-(6*(phy)+3*(ch)+(spline))))
/*
* The i830 generation, in LVDS mode, defines P1 as the bit number set within
#define MCHBAR_MIRROR_BASE_SNB 0x140000
+#define CTG_STOLEN_RESERVED (MCHBAR_MIRROR_BASE + 0x34)
+#define ELK_STOLEN_RESERVED (MCHBAR_MIRROR_BASE + 0x48)
+#define G4X_STOLEN_RESERVED_ADDR1_MASK (0xFFFF << 16)
+#define G4X_STOLEN_RESERVED_ADDR2_MASK (0xFFF << 4)
+
/* Memory controller frequency in MCHBAR for Haswell (possible SNB+) */
#define DCLK (MCHBAR_MIRROR_BASE_SNB + 0x5e04)
#define TSFS_INTR_MASK 0x000000ff
#define CRSTANDVID 0x11100
-#define PXVFREQ_BASE 0x11110 /* P[0-15]VIDFREQ (0x1114c) (Ironlake) */
+#define PXVFREQ(i) (0x11110 + (i) * 4) /* P[0-15]VIDFREQ (0x1114c) (Ironlake) */
#define PXVFREQ_PX_MASK 0x7f000000
#define PXVFREQ_PX_SHIFT 24
#define VIDFREQ_BASE 0x11110
#define CSIEW0 0x11250
#define CSIEW1 0x11254
#define CSIEW2 0x11258
-#define PEW 0x1125c
-#define DEW 0x11270
+#define PEW(i) (0x1125c + (i) * 4) /* 5 registers */
+#define DEW(i) (0x11270 + (i) * 4) /* 3 registers */
#define MCHAFE 0x112c0
#define CSIEC 0x112e0
#define DMIEC 0x112e4
#define EG5 0x11624
#define EG6 0x11628
#define EG7 0x1162c
-#define PXW 0x11664
-#define PXWL 0x11680
+#define PXW(i) (0x11664 + (i) * 4) /* 4 registers */
+#define PXWL(i) (0x11680 + (i) * 4) /* 8 registers */
#define LCFUSE02 0x116c0
#define LCFUSE_HIV_MASK 0x000000ff
#define CSIPLL0 0x12c10
# define TV_CC_DATA_1_MASK 0x0000007f
# define TV_CC_DATA_1_SHIFT 0
-#define TV_H_LUMA_0 0x68100
-#define TV_H_LUMA_59 0x681ec
-#define TV_H_CHROMA_0 0x68200
-#define TV_H_CHROMA_59 0x682ec
-#define TV_V_LUMA_0 0x68300
-#define TV_V_LUMA_42 0x683a8
-#define TV_V_CHROMA_0 0x68400
-#define TV_V_CHROMA_42 0x684a8
+#define TV_H_LUMA(i) (0x68100 + (i) * 4) /* 60 registers */
+#define TV_H_CHROMA(i) (0x68200 + (i) * 4) /* 60 registers */
+#define TV_V_LUMA(i) (0x68300 + (i) * 4) /* 43 registers */
+#define TV_V_CHROMA(i) (0x68400 + (i) * 4) /* 43 registers */
/* Display Port */
#define DP_A 0x64000 /* eDP */
/* How many wires to use. I guess 3 was too hard */
#define DP_PORT_WIDTH(width) (((width) - 1) << 19)
#define DP_PORT_WIDTH_MASK (7 << 19)
+#define DP_PORT_WIDTH_SHIFT 19
/* Mystic DPCD version 1.1 special mode */
#define DP_ENHANCED_FRAMING (1 << 18)
#define CBR1_VLV (VLV_DISPLAY_BASE + 0x70400)
#define CBR_PND_DEADLINE_DISABLE (1<<31)
+#define CBR_PWM_CLOCK_MUX_SELECT (1<<30)
/* FIFO watermark sizes etc */
#define G4X_FIFO_LINE_SIZE 64
#define CPU_VGACNTRL 0x41000
-#define DIGITAL_PORT_HOTPLUG_CNTRL 0x44030
-#define DIGITAL_PORTA_HOTPLUG_ENABLE (1 << 4)
-#define DIGITAL_PORTA_SHORT_PULSE_2MS (0 << 2)
-#define DIGITAL_PORTA_SHORT_PULSE_4_5MS (1 << 2)
-#define DIGITAL_PORTA_SHORT_PULSE_6MS (2 << 2)
-#define DIGITAL_PORTA_SHORT_PULSE_100MS (3 << 2)
-#define DIGITAL_PORTA_NO_DETECT (0 << 0)
-#define DIGITAL_PORTA_LONG_PULSE_DETECT_MASK (1 << 1)
-#define DIGITAL_PORTA_SHORT_PULSE_DETECT_MASK (1 << 0)
+#define DIGITAL_PORT_HOTPLUG_CNTRL 0x44030
+#define DIGITAL_PORTA_HOTPLUG_ENABLE (1 << 4)
+#define DIGITAL_PORTA_PULSE_DURATION_2ms (0 << 2) /* pre-HSW */
+#define DIGITAL_PORTA_PULSE_DURATION_4_5ms (1 << 2) /* pre-HSW */
+#define DIGITAL_PORTA_PULSE_DURATION_6ms (2 << 2) /* pre-HSW */
+#define DIGITAL_PORTA_PULSE_DURATION_100ms (3 << 2) /* pre-HSW */
+#define DIGITAL_PORTA_PULSE_DURATION_MASK (3 << 2) /* pre-HSW */
+#define DIGITAL_PORTA_HOTPLUG_STATUS_MASK (3 << 0)
+#define DIGITAL_PORTA_HOTPLUG_NO_DETECT (0 << 0)
+#define DIGITAL_PORTA_HOTPLUG_SHORT_DETECT (1 << 0)
+#define DIGITAL_PORTA_HOTPLUG_LONG_DETECT (2 << 0)
/* refresh rate hardware control */
#define RR_HW_CTL 0x45300
#define GEN8_GT_IIR(which) (0x44308 + (0x10 * (which)))
#define GEN8_GT_IER(which) (0x4430c + (0x10 * (which)))
-#define GEN8_BCS_IRQ_SHIFT 16
#define GEN8_RCS_IRQ_SHIFT 0
-#define GEN8_VCS2_IRQ_SHIFT 16
+#define GEN8_BCS_IRQ_SHIFT 16
#define GEN8_VCS1_IRQ_SHIFT 0
+#define GEN8_VCS2_IRQ_SHIFT 16
#define GEN8_VECS_IRQ_SHIFT 0
+#define GEN8_WD_IRQ_SHIFT 16
#define GEN8_DE_PIPE_ISR(pipe) (0x44400 + (0x10 * (pipe)))
#define GEN8_DE_PIPE_IMR(pipe) (0x44404 + (0x10 * (pipe)))
#define GEN8_PCU_IIR 0x444e8
#define GEN8_PCU_IER 0x444ec
-/* BXT hotplug control */
-#define BXT_HOTPLUG_CTL 0xC4030
-#define BXT_DDIA_HPD_ENABLE (1 << 28)
-#define BXT_DDIA_HPD_STATUS (3 << 24)
-#define BXT_DDIC_HPD_ENABLE (1 << 12)
-#define BXT_DDIC_HPD_STATUS (3 << 8)
-#define BXT_DDIB_HPD_ENABLE (1 << 4)
-#define BXT_DDIB_HPD_STATUS (3 << 0)
-#define BXT_HOTPLUG_CTL_MASK (BXT_DDIA_HPD_ENABLE | \
- BXT_DDIB_HPD_ENABLE | \
- BXT_DDIC_HPD_ENABLE)
-#define BXT_HPD_STATUS_MASK (BXT_DDIA_HPD_STATUS | \
- BXT_DDIB_HPD_STATUS | \
- BXT_DDIC_HPD_STATUS)
-
#define ILK_DISPLAY_CHICKEN2 0x42004
/* Required on all Ironlake and Sandybridge according to the B-Spec. */
#define ILK_ELPIN_409_SELECT (1 << 25)
#define SDE_AUXB_CPT (1 << 25)
#define SDE_AUX_MASK_CPT (7 << 25)
#define SDE_PORTE_HOTPLUG_SPT (1 << 25)
+#define SDE_PORTA_HOTPLUG_SPT (1 << 24)
#define SDE_PORTD_HOTPLUG_CPT (1 << 23)
#define SDE_PORTC_HOTPLUG_CPT (1 << 22)
#define SDE_PORTB_HOTPLUG_CPT (1 << 21)
#define SDE_HOTPLUG_MASK_SPT (SDE_PORTE_HOTPLUG_SPT | \
SDE_PORTD_HOTPLUG_CPT | \
SDE_PORTC_HOTPLUG_CPT | \
- SDE_PORTB_HOTPLUG_CPT)
+ SDE_PORTB_HOTPLUG_CPT | \
+ SDE_PORTA_HOTPLUG_SPT)
#define SDE_GMBUS_CPT (1 << 17)
#define SDE_ERROR_CPT (1 << 16)
#define SDE_AUDIO_CP_REQ_C_CPT (1 << 10)
#define SERR_INT_TRANS_FIFO_UNDERRUN(pipe) (1<<(pipe*3))
/* digital port hotplug */
-#define PCH_PORT_HOTPLUG 0xc4030 /* SHOTPLUG_CTL */
-#define BXT_PORTA_HOTPLUG_ENABLE (1 << 28)
-#define BXT_PORTA_HOTPLUG_STATUS_MASK (0x3 << 24)
-#define BXT_PORTA_HOTPLUG_NO_DETECT (0 << 24)
-#define BXT_PORTA_HOTPLUG_SHORT_DETECT (1 << 24)
-#define BXT_PORTA_HOTPLUG_LONG_DETECT (2 << 24)
-#define PORTD_HOTPLUG_ENABLE (1 << 20)
-#define PORTD_PULSE_DURATION_2ms (0)
-#define PORTD_PULSE_DURATION_4_5ms (1 << 18)
-#define PORTD_PULSE_DURATION_6ms (2 << 18)
-#define PORTD_PULSE_DURATION_100ms (3 << 18)
-#define PORTD_PULSE_DURATION_MASK (3 << 18)
-#define PORTD_HOTPLUG_STATUS_MASK (0x3 << 16)
+#define PCH_PORT_HOTPLUG 0xc4030 /* SHOTPLUG_CTL */
+#define PORTA_HOTPLUG_ENABLE (1 << 28) /* LPT:LP+ & BXT */
+#define PORTA_HOTPLUG_STATUS_MASK (3 << 24) /* SPT+ & BXT */
+#define PORTA_HOTPLUG_NO_DETECT (0 << 24) /* SPT+ & BXT */
+#define PORTA_HOTPLUG_SHORT_DETECT (1 << 24) /* SPT+ & BXT */
+#define PORTA_HOTPLUG_LONG_DETECT (2 << 24) /* SPT+ & BXT */
+#define PORTD_HOTPLUG_ENABLE (1 << 20)
+#define PORTD_PULSE_DURATION_2ms (0 << 18) /* pre-LPT */
+#define PORTD_PULSE_DURATION_4_5ms (1 << 18) /* pre-LPT */
+#define PORTD_PULSE_DURATION_6ms (2 << 18) /* pre-LPT */
+#define PORTD_PULSE_DURATION_100ms (3 << 18) /* pre-LPT */
+#define PORTD_PULSE_DURATION_MASK (3 << 18) /* pre-LPT */
+#define PORTD_HOTPLUG_STATUS_MASK (3 << 16)
#define PORTD_HOTPLUG_NO_DETECT (0 << 16)
#define PORTD_HOTPLUG_SHORT_DETECT (1 << 16)
#define PORTD_HOTPLUG_LONG_DETECT (2 << 16)
-#define PORTC_HOTPLUG_ENABLE (1 << 12)
-#define PORTC_PULSE_DURATION_2ms (0)
-#define PORTC_PULSE_DURATION_4_5ms (1 << 10)
-#define PORTC_PULSE_DURATION_6ms (2 << 10)
-#define PORTC_PULSE_DURATION_100ms (3 << 10)
-#define PORTC_PULSE_DURATION_MASK (3 << 10)
-#define PORTC_HOTPLUG_STATUS_MASK (0x3 << 8)
+#define PORTC_HOTPLUG_ENABLE (1 << 12)
+#define PORTC_PULSE_DURATION_2ms (0 << 10) /* pre-LPT */
+#define PORTC_PULSE_DURATION_4_5ms (1 << 10) /* pre-LPT */
+#define PORTC_PULSE_DURATION_6ms (2 << 10) /* pre-LPT */
+#define PORTC_PULSE_DURATION_100ms (3 << 10) /* pre-LPT */
+#define PORTC_PULSE_DURATION_MASK (3 << 10) /* pre-LPT */
+#define PORTC_HOTPLUG_STATUS_MASK (3 << 8)
#define PORTC_HOTPLUG_NO_DETECT (0 << 8)
#define PORTC_HOTPLUG_SHORT_DETECT (1 << 8)
#define PORTC_HOTPLUG_LONG_DETECT (2 << 8)
-#define PORTB_HOTPLUG_ENABLE (1 << 4)
-#define PORTB_PULSE_DURATION_2ms (0)
-#define PORTB_PULSE_DURATION_4_5ms (1 << 2)
-#define PORTB_PULSE_DURATION_6ms (2 << 2)
-#define PORTB_PULSE_DURATION_100ms (3 << 2)
-#define PORTB_PULSE_DURATION_MASK (3 << 2)
-#define PORTB_HOTPLUG_STATUS_MASK (0x3 << 0)
+#define PORTB_HOTPLUG_ENABLE (1 << 4)
+#define PORTB_PULSE_DURATION_2ms (0 << 2) /* pre-LPT */
+#define PORTB_PULSE_DURATION_4_5ms (1 << 2) /* pre-LPT */
+#define PORTB_PULSE_DURATION_6ms (2 << 2) /* pre-LPT */
+#define PORTB_PULSE_DURATION_100ms (3 << 2) /* pre-LPT */
+#define PORTB_PULSE_DURATION_MASK (3 << 2) /* pre-LPT */
+#define PORTB_HOTPLUG_STATUS_MASK (3 << 0)
#define PORTB_HOTPLUG_NO_DETECT (0 << 0)
#define PORTB_HOTPLUG_SHORT_DETECT (1 << 0)
#define PORTB_HOTPLUG_LONG_DETECT (2 << 0)
-#define PCH_PORT_HOTPLUG2 0xc403C /* SHOTPLUG_CTL2 */
-#define PORTE_HOTPLUG_ENABLE (1 << 4)
-#define PORTE_HOTPLUG_STATUS_MASK (0x3 << 0)
+#define PCH_PORT_HOTPLUG2 0xc403C /* SHOTPLUG_CTL2 SPT+ */
+#define PORTE_HOTPLUG_ENABLE (1 << 4)
+#define PORTE_HOTPLUG_STATUS_MASK (3 << 0)
#define PORTE_HOTPLUG_NO_DETECT (0 << 0)
#define PORTE_HOTPLUG_SHORT_DETECT (1 << 0)
#define PORTE_HOTPLUG_LONG_DETECT (2 << 0)
#define FDI_PHASE_SYNC_OVR(pipe) (1<<(FDIA_PHASE_SYNC_SHIFT_OVR - ((pipe) * 2)))
#define FDI_PHASE_SYNC_EN(pipe) (1<<(FDIA_PHASE_SYNC_SHIFT_EN - ((pipe) * 2)))
#define FDI_BC_BIFURCATION_SELECT (1 << 12)
+#define SPT_PWM_GRANULARITY (1<<0)
#define SOUTH_CHICKEN2 0xc2004
#define FDI_MPHY_IOSFSB_RESET_STATUS (1<<13)
#define FDI_MPHY_IOSFSB_RESET_CTL (1<<12)
+#define LPT_PWM_GRANULARITY (1<<5)
#define DPLS_EDP_PPS_FIX_DIS (1<<0)
#define _FDI_RXA_CHICKEN 0xc200c
GEN6_PM_RP_DOWN_THRESHOLD | \
GEN6_PM_RP_DOWN_TIMEOUT)
-#define GEN7_GT_SCRATCH_BASE 0x4F100
+#define GEN7_GT_SCRATCH(i) (0x4F100 + (i) * 4)
#define GEN7_GT_SCRATCH_REG_NUM 8
#define VLV_GTLC_SURVIVABILITY_REG 0x130098
#define GEN9_PGCTL_SSB_EU311_ACK (1 << 14)
#define GEN7_MISCCPCTL (0x9424)
-#define GEN7_DOP_CLOCK_GATE_ENABLE (1<<0)
+#define GEN7_DOP_CLOCK_GATE_ENABLE (1<<0)
+#define GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE (1<<2)
+#define GEN8_DOP_CLOCK_GATE_GUC_ENABLE (1<<4)
+#define GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE (1<<6)
#define GEN8_GARBCNTL 0xB004
#define GEN9_GAPS_TSV_CREDIT_DISABLE (1<<7)
#define HSW_ROW_CHICKEN3 0xe49c
#define HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE (1 << 6)
+#define HALF_SLICE_CHICKEN2 0xe180
+#define GEN8_ST_PO_DISABLE (1<<13)
+
#define HALF_SLICE_CHICKEN3 0xe184
#define HSW_SAMPLE_C_PERFORMANCE (1<<9)
#define GEN8_CENTROID_PIXEL_OPT_DIS (1<<8)
#define DDI_BUF_IS_IDLE (1<<7)
#define DDI_A_4_LANES (1<<4)
#define DDI_PORT_WIDTH(width) (((width) - 1) << 1)
+#define DDI_PORT_WIDTH_MASK (7 << 1)
+#define DDI_PORT_WIDTH_SHIFT 1
#define DDI_INIT_DISPLAY_DETECTED (1<<0)
/* DDI Buffer Translations */
#define DDI_BUF_TRANS_A 0x64E00
#define DDI_BUF_TRANS_B 0x64E60
-#define DDI_BUF_TRANS(port) _PORT(port, DDI_BUF_TRANS_A, DDI_BUF_TRANS_B)
+#define DDI_BUF_TRANS_LO(port, i) (_PORT(port, DDI_BUF_TRANS_A, DDI_BUF_TRANS_B) + (i) * 8)
+#define DDI_BUF_TRANS_HI(port, i) (_PORT(port, DDI_BUF_TRANS_A, DDI_BUF_TRANS_B) + (i) * 8 + 4)
/* Sideband Interface (SBI) is programmed indirectly, via
* SBI_ADDR, which contains the register offset; and SBI_DATA,
#define _MIPI_PORT(port, a, c) _PORT3(port, a, 0, c) /* ports A and C only */
+/* BXT MIPI mode configure */
+#define _BXT_MIPIA_TRANS_HACTIVE 0x6B0F8
+#define _BXT_MIPIC_TRANS_HACTIVE 0x6B8F8
+#define BXT_MIPI_TRANS_HACTIVE(tc) _MIPI_PORT(tc, \
+ _BXT_MIPIA_TRANS_HACTIVE, _BXT_MIPIC_TRANS_HACTIVE)
+
+#define _BXT_MIPIA_TRANS_VACTIVE 0x6B0FC
+#define _BXT_MIPIC_TRANS_VACTIVE 0x6B8FC
+#define BXT_MIPI_TRANS_VACTIVE(tc) _MIPI_PORT(tc, \
+ _BXT_MIPIA_TRANS_VACTIVE, _BXT_MIPIC_TRANS_VACTIVE)
+
+#define _BXT_MIPIA_TRANS_VTOTAL 0x6B100
+#define _BXT_MIPIC_TRANS_VTOTAL 0x6B900
+#define BXT_MIPI_TRANS_VTOTAL(tc) _MIPI_PORT(tc, \
+ _BXT_MIPIA_TRANS_VTOTAL, _BXT_MIPIC_TRANS_VTOTAL)
+
+#define BXT_DSI_PLL_CTL 0x161000
+#define BXT_DSI_PLL_PVD_RATIO_SHIFT 16
+#define BXT_DSI_PLL_PVD_RATIO_MASK (3 << BXT_DSI_PLL_PVD_RATIO_SHIFT)
+#define BXT_DSI_PLL_PVD_RATIO_1 (1 << BXT_DSI_PLL_PVD_RATIO_SHIFT)
+#define BXT_DSIC_16X_BY2 (1 << 10)
+#define BXT_DSIC_16X_BY3 (2 << 10)
+#define BXT_DSIC_16X_BY4 (3 << 10)
+#define BXT_DSIA_16X_BY2 (1 << 8)
+#define BXT_DSIA_16X_BY3 (2 << 8)
+#define BXT_DSIA_16X_BY4 (3 << 8)
+#define BXT_DSI_FREQ_SEL_SHIFT 8
+#define BXT_DSI_FREQ_SEL_MASK (0xF << BXT_DSI_FREQ_SEL_SHIFT)
+
+#define BXT_DSI_PLL_RATIO_MAX 0x7D
+#define BXT_DSI_PLL_RATIO_MIN 0x22
+#define BXT_DSI_PLL_RATIO_MASK 0xFF
+#define BXT_REF_CLOCK_KHZ 19500
+
+#define BXT_DSI_PLL_ENABLE 0x46080
+#define BXT_DSI_PLL_DO_ENABLE (1 << 31)
+#define BXT_DSI_PLL_LOCKED (1 << 30)
+
#define _MIPIA_PORT_CTRL (VLV_DISPLAY_BASE + 0x61190)
#define _MIPIC_PORT_CTRL (VLV_DISPLAY_BASE + 0x61700)
#define MIPI_PORT_CTRL(port) _MIPI_PORT(port, _MIPIA_PORT_CTRL, _MIPIC_PORT_CTRL)
#define READ_REQUEST_PRIORITY_HIGH (3 << 3)
#define RGB_FLIP_TO_BGR (1 << 2)
+#define BXT_PIPE_SELECT_MASK (7 << 7)
+#define BXT_PIPE_SELECT_C (2 << 7)
+#define BXT_PIPE_SELECT_B (1 << 7)
+#define BXT_PIPE_SELECT_A (0 << 7)
+
#define _MIPIA_DATA_ADDRESS (dev_priv->mipi_mmio_base + 0xb108)
#define _MIPIC_DATA_ADDRESS (dev_priv->mipi_mmio_base + 0xb908)
#define MIPI_DATA_ADDRESS(port) _MIPI_PORT(port, _MIPIA_DATA_ADDRESS, \
/* pipe updates */
TRACE_EVENT(i915_pipe_update_start,
- TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max),
- TP_ARGS(crtc, min, max),
+ TP_PROTO(struct intel_crtc *crtc),
+ TP_ARGS(crtc),
TP_STRUCT__entry(
__field(enum pipe, pipe)
__entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
crtc->pipe);
__entry->scanline = intel_get_crtc_scanline(crtc);
- __entry->min = min;
- __entry->max = max;
+ __entry->min = crtc->debug.min_vbl;
+ __entry->max = crtc->debug.max_vbl;
),
TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u",
);
TRACE_EVENT(i915_pipe_update_vblank_evaded,
- TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max, u32 frame),
- TP_ARGS(crtc, min, max, frame),
+ TP_PROTO(struct intel_crtc *crtc),
+ TP_ARGS(crtc),
TP_STRUCT__entry(
__field(enum pipe, pipe)
TP_fast_assign(
__entry->pipe = crtc->pipe;
- __entry->frame = frame;
- __entry->scanline = intel_get_crtc_scanline(crtc);
- __entry->min = min;
- __entry->max = max;
+ __entry->frame = crtc->debug.start_vbl_count;
+ __entry->scanline = crtc->debug.scanline_start;
+ __entry->min = crtc->debug.min_vbl;
+ __entry->max = crtc->debug.max_vbl;
),
TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u",
);
TRACE_EVENT(i915_pipe_update_end,
- TP_PROTO(struct intel_crtc *crtc, u32 frame),
- TP_ARGS(crtc, frame),
+ TP_PROTO(struct intel_crtc *crtc, u32 frame, int scanline_end),
+ TP_ARGS(crtc, frame, scanline_end),
TP_STRUCT__entry(
__field(enum pipe, pipe)
TP_fast_assign(
__entry->pipe = crtc->pipe;
__entry->frame = frame;
- __entry->scanline = intel_get_crtc_scanline(crtc);
+ __entry->scanline = scanline_end;
),
TP_printk("pipe %c, frame=%u, scanline=%u",
TP_ARGS(vm, start, length, name)
);
-DECLARE_EVENT_CLASS(i915_page_table_entry,
- TP_PROTO(struct i915_address_space *vm, u32 pde, u64 start, u64 pde_shift),
- TP_ARGS(vm, pde, start, pde_shift),
+DECLARE_EVENT_CLASS(i915_px_entry,
+ TP_PROTO(struct i915_address_space *vm, u32 px, u64 start, u64 px_shift),
+ TP_ARGS(vm, px, start, px_shift),
TP_STRUCT__entry(
__field(struct i915_address_space *, vm)
- __field(u32, pde)
+ __field(u32, px)
__field(u64, start)
__field(u64, end)
),
TP_fast_assign(
__entry->vm = vm;
- __entry->pde = pde;
+ __entry->px = px;
__entry->start = start;
- __entry->end = ((start + (1ULL << pde_shift)) & ~((1ULL << pde_shift)-1)) - 1;
+ __entry->end = ((start + (1ULL << px_shift)) & ~((1ULL << px_shift)-1)) - 1;
),
TP_printk("vm=%p, pde=%d (0x%llx-0x%llx)",
- __entry->vm, __entry->pde, __entry->start, __entry->end)
+ __entry->vm, __entry->px, __entry->start, __entry->end)
);
-DEFINE_EVENT(i915_page_table_entry, i915_page_table_entry_alloc,
+DEFINE_EVENT(i915_px_entry, i915_page_table_entry_alloc,
TP_PROTO(struct i915_address_space *vm, u32 pde, u64 start, u64 pde_shift),
TP_ARGS(vm, pde, start, pde_shift)
);
+DEFINE_EVENT_PRINT(i915_px_entry, i915_page_directory_entry_alloc,
+ TP_PROTO(struct i915_address_space *vm, u32 pdpe, u64 start, u64 pdpe_shift),
+ TP_ARGS(vm, pdpe, start, pdpe_shift),
+
+ TP_printk("vm=%p, pdpe=%d (0x%llx-0x%llx)",
+ __entry->vm, __entry->px, __entry->start, __entry->end)
+);
+
+DEFINE_EVENT_PRINT(i915_px_entry, i915_page_directory_pointer_entry_alloc,
+ TP_PROTO(struct i915_address_space *vm, u32 pml4e, u64 start, u64 pml4e_shift),
+ TP_ARGS(vm, pml4e, start, pml4e_shift),
+
+ TP_printk("vm=%p, pml4e=%d (0x%llx-0x%llx)",
+ __entry->vm, __entry->px, __entry->start, __entry->end)
+);
+
/* Avoid extra math because we only support two sizes. The format is defined by
* bitmap_scnprintf. Each 32 bits is 8 HEX digits followed by comma */
#define TRACE_PT_SIZE(bits) \
#define INTEL_VGT_IF_VERSION \
INTEL_VGT_IF_VERSION_ENCODE(VGT_VERSION_MAJOR, VGT_VERSION_MINOR)
+/*
+ * notifications from guest to vgpu device model
+ */
+enum vgt_g2v_type {
+ VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE = 2,
+ VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY,
+ VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE,
+ VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY,
+ VGT_G2V_EXECLIST_CONTEXT_CREATE,
+ VGT_G2V_EXECLIST_CONTEXT_DESTROY,
+ VGT_G2V_MAX,
+};
+
struct vgt_if {
uint64_t magic; /* VGT_MAGIC */
uint16_t version_major;
uint32_t rsv3[0x200 - 24]; /* pad to half page */
/*
* The bottom half page is for response from Gfx driver to hypervisor.
- * Set to reserved fields temporarily by now.
*/
uint32_t rsv4;
uint32_t display_ready; /* ready for display owner switch */
- uint32_t rsv5[0x200 - 2]; /* pad to one page */
+
+ uint32_t rsv5[4];
+
+ uint32_t g2v_notify;
+ uint32_t rsv6[7];
+
+ uint32_t pdp0_lo;
+ uint32_t pdp0_hi;
+ uint32_t pdp1_lo;
+ uint32_t pdp1_hi;
+ uint32_t pdp2_lo;
+ uint32_t pdp2_hi;
+ uint32_t pdp3_lo;
+ uint32_t pdp3_hi;
+
+ uint32_t execlist_context_descriptor_lo;
+ uint32_t execlist_context_descriptor_hi;
+
+ uint32_t rsv7[0x200 - 24]; /* pad to one page */
} __packed;
#define vgtif_reg(x) \
if (vga_count == 2 && has_dsm) {
acpi_get_name(intel_dsm_priv.dhandle, ACPI_FULL_PATHNAME, &buffer);
- DRM_DEBUG_DRIVER("VGA switcheroo: detected DSM switching method %s handle\n",
+ DRM_DEBUG_DRIVER("vga_switcheroo: detected DSM switching method %s handle\n",
acpi_method_name);
return true;
}
struct drm_crtc_state *
intel_crtc_duplicate_state(struct drm_crtc *crtc)
{
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
struct intel_crtc_state *crtc_state;
- if (WARN_ON(!intel_crtc->config))
- crtc_state = kzalloc(sizeof(*crtc_state), GFP_KERNEL);
- else
- crtc_state = kmemdup(intel_crtc->config,
- sizeof(*intel_crtc->config), GFP_KERNEL);
-
+ crtc_state = kmemdup(crtc->state, sizeof(*crtc_state), GFP_KERNEL);
if (!crtc_state)
return NULL;
__drm_atomic_helper_crtc_duplicate_state(crtc, &crtc_state->base);
- crtc_state->base.crtc = crtc;
+ crtc_state->update_pipe = false;
return &crtc_state->base;
}
int i, j;
num_scalers_need = hweight32(scaler_state->scaler_users);
- DRM_DEBUG_KMS("crtc_state = %p need = %d avail = %d scaler_users = 0x%x\n",
- crtc_state, num_scalers_need, intel_crtc->num_scalers,
- scaler_state->scaler_users);
/*
* High level flow:
struct drm_plane_state *state;
struct intel_plane_state *intel_state;
- if (WARN_ON(!plane->state))
- intel_state = intel_create_plane_state(plane);
- else
- intel_state = kmemdup(plane->state, sizeof(*intel_state),
- GFP_KERNEL);
+ intel_state = kmemdup(plane->state, sizeof(*intel_state), GFP_KERNEL);
if (!intel_state)
return NULL;
return 0;
}
-
-/* Ensure that vital registers have been initialised, even if the BIOS
- * is absent or just failing to do its job.
- */
-void intel_setup_bios(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- /* Set the Panel Power On/Off timings if uninitialized. */
- if (!HAS_PCH_SPLIT(dev) &&
- I915_READ(PP_ON_DELAYS) == 0 && I915_READ(PP_OFF_DELAYS) == 0) {
- /* Set T2 to 40ms and T5 to 200ms */
- I915_WRITE(PP_ON_DELAYS, 0x019007d0);
-
- /* Set T3 to 35ms and Tx to 200ms */
- I915_WRITE(PP_OFF_DELAYS, 0x015e07d0);
- }
-}
struct psr_table psr_table[16];
} __packed;
-void intel_setup_bios(struct drm_device *dev);
int intel_parse_bios(struct drm_device *dev);
/*
*/
#define DEVICE_TYPE_eDP_BITS \
(DEVICE_TYPE_INTERNAL_CONNECTOR | \
- DEVICE_TYPE_NOT_HDMI_OUTPUT | \
DEVICE_TYPE_MIPI_OUTPUT | \
DEVICE_TYPE_COMPOSITE_OUTPUT | \
DEVICE_TYPE_DUAL_CHANNEL | \
DEVICE_TYPE_TMDS_DVI_SIGNALING | \
DEVICE_TYPE_VIDEO_SIGNALING | \
DEVICE_TYPE_DISPLAYPORT_OUTPUT | \
- DEVICE_TYPE_DIGITAL_OUTPUT | \
DEVICE_TYPE_ANALOG_OUTPUT)
/* define the DVO port for HDMI output type */
{
struct drm_device *dev = connector->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 hotplug_en, orig, stat;
+ u32 stat;
bool ret = false;
int i, tries = 0;
tries = 2;
else
tries = 1;
- hotplug_en = orig = I915_READ(PORT_HOTPLUG_EN);
- hotplug_en |= CRT_HOTPLUG_FORCE_DETECT;
for (i = 0; i < tries ; i++) {
/* turn on the FORCE_DETECT */
- I915_WRITE(PORT_HOTPLUG_EN, hotplug_en);
+ i915_hotplug_interrupt_update(dev_priv,
+ CRT_HOTPLUG_FORCE_DETECT,
+ CRT_HOTPLUG_FORCE_DETECT);
/* wait for FORCE_DETECT to go off */
if (wait_for((I915_READ(PORT_HOTPLUG_EN) &
CRT_HOTPLUG_FORCE_DETECT) == 0,
/* clear the interrupt we just generated, if any */
I915_WRITE(PORT_HOTPLUG_STAT, CRT_HOTPLUG_INT_STATUS);
- /* and put the bits back */
- I915_WRITE(PORT_HOTPLUG_EN, orig);
+ i915_hotplug_interrupt_update(dev_priv, CRT_HOTPLUG_FORCE_DETECT, 0);
return ret;
}
*/
#define I915_CSR_SKL "i915/skl_dmc_ver1.bin"
+#define I915_CSR_BXT "i915/bxt_dmc_ver1.bin"
MODULE_FIRMWARE(I915_CSR_SKL);
+MODULE_FIRMWARE(I915_CSR_BXT);
/*
* SKL CSR registers for DC5 and DC6
*/
-#define CSR_PROGRAM_BASE 0x80000
+#define CSR_PROGRAM(i) (0x80000 + (i) * 4)
#define CSR_SSP_BASE_ADDR_GEN9 0x00002FC0
#define CSR_HTP_ADDR_SKL 0x00500034
#define CSR_SSP_BASE 0x8F074
{'G', '0'}, {'H', '0'}, {'I', '0'}
};
+static struct stepping_info bxt_stepping_info[] = {
+ {'A', '0'}, {'A', '1'}, {'A', '2'},
+ {'B', '0'}, {'B', '1'}, {'B', '2'}
+};
+
static char intel_get_stepping(struct drm_device *dev)
{
if (IS_SKYLAKE(dev) && (dev->pdev->revision <
ARRAY_SIZE(skl_stepping_info)))
return skl_stepping_info[dev->pdev->revision].stepping;
+ else if (IS_BROXTON(dev) && (dev->pdev->revision <
+ ARRAY_SIZE(bxt_stepping_info)))
+ return bxt_stepping_info[dev->pdev->revision].stepping;
else
return -ENODATA;
}
if (IS_SKYLAKE(dev) && (dev->pdev->revision <
ARRAY_SIZE(skl_stepping_info)))
return skl_stepping_info[dev->pdev->revision].substepping;
+ else if (IS_BROXTON(dev) && (dev->pdev->revision <
+ ARRAY_SIZE(bxt_stepping_info)))
+ return bxt_stepping_info[dev->pdev->revision].substepping;
else
return -ENODATA;
}
mutex_lock(&dev_priv->csr_lock);
fw_size = dev_priv->csr.dmc_fw_size;
for (i = 0; i < fw_size; i++)
- I915_WRITE(CSR_PROGRAM_BASE + i * 4,
- payload[i]);
+ I915_WRITE(CSR_PROGRAM(i), payload[i]);
for (i = 0; i < dev_priv->csr.mmio_count; i++) {
I915_WRITE(dev_priv->csr.mmioaddr[i],
if (IS_SKYLAKE(dev))
csr->fw_path = I915_CSR_SKL;
+ else if (IS_BROXTON(dev_priv))
+ csr->fw_path = I915_CSR_BXT;
else {
DRM_ERROR("Unexpected: no known CSR firmware for platform\n");
intel_csr_load_status_set(dev_priv, FW_FAILED);
void assert_csr_loaded(struct drm_i915_private *dev_priv)
{
- WARN(intel_csr_load_status_get(dev_priv) != FW_LOADED,
- "CSR is not loaded.\n");
- WARN(!I915_READ(CSR_PROGRAM_BASE),
- "CSR program storage start is NULL\n");
- WARN(!I915_READ(CSR_SSP_BASE), "CSR SSP Base Not fine\n");
- WARN(!I915_READ(CSR_HTP_SKL), "CSR HTP Not fine\n");
+ WARN_ONCE(intel_csr_load_status_get(dev_priv) != FW_LOADED,
+ "CSR is not loaded.\n");
+ WARN_ONCE(!I915_READ(CSR_PROGRAM(0)),
+ "CSR program storage start is NULL\n");
+ WARN_ONCE(!I915_READ(CSR_SSP_BASE), "CSR SSP Base Not fine\n");
+ WARN_ONCE(!I915_READ(CSR_HTP_SKL), "CSR HTP Not fine\n");
}
bool supports_hdmi)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 reg;
u32 iboost_bit = 0;
int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_default_entry,
size;
BUG();
}
- for (i = 0, reg = DDI_BUF_TRANS(port); i < size; i++) {
- I915_WRITE(reg, ddi_translations[i].trans1 | iboost_bit);
- reg += 4;
- I915_WRITE(reg, ddi_translations[i].trans2);
- reg += 4;
+ for (i = 0; i < size; i++) {
+ I915_WRITE(DDI_BUF_TRANS_LO(port, i),
+ ddi_translations[i].trans1 | iboost_bit);
+ I915_WRITE(DDI_BUF_TRANS_HI(port, i),
+ ddi_translations[i].trans2);
}
if (!supports_hdmi)
hdmi_level = hdmi_default_entry;
/* Entry 9 is for HDMI: */
- I915_WRITE(reg, ddi_translations_hdmi[hdmi_level].trans1 | iboost_bit);
- reg += 4;
- I915_WRITE(reg, ddi_translations_hdmi[hdmi_level].trans2);
- reg += 4;
+ I915_WRITE(DDI_BUF_TRANS_LO(port, i),
+ ddi_translations_hdmi[hdmi_level].trans1 | iboost_bit);
+ I915_WRITE(DDI_BUF_TRANS_HI(port, i),
+ ddi_translations_hdmi[hdmi_level].trans2);
}
/* Program DDI buffers translations for DP. By default, program ports A-D in DP
intel_dp->DP = intel_dig_port->saved_port_bits |
DDI_BUF_CTL_ENABLE | DDI_BUF_TRANS_SELECT(0);
intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count);
-
}
static struct intel_encoder *
static bool
hsw_ddi_pll_select(struct intel_crtc *intel_crtc,
struct intel_crtc_state *crtc_state,
- struct intel_encoder *intel_encoder,
- int clock)
+ struct intel_encoder *intel_encoder)
{
+ int clock = crtc_state->port_clock;
+
if (intel_encoder->type == INTEL_OUTPUT_HDMI) {
struct intel_shared_dpll *pll;
uint32_t val;
static bool
skl_ddi_pll_select(struct intel_crtc *intel_crtc,
struct intel_crtc_state *crtc_state,
- struct intel_encoder *intel_encoder,
- int clock)
+ struct intel_encoder *intel_encoder)
{
struct intel_shared_dpll *pll;
uint32_t ctrl1, cfgcr1, cfgcr2;
+ int clock = crtc_state->port_clock;
/*
* See comment in intel_dpll_hw_state to understand why we always use 0
static bool
bxt_ddi_pll_select(struct intel_crtc *intel_crtc,
struct intel_crtc_state *crtc_state,
- struct intel_encoder *intel_encoder,
- int clock)
+ struct intel_encoder *intel_encoder)
{
struct intel_shared_dpll *pll;
struct bxt_clk_div clk_div = {0};
int vco = 0;
uint32_t prop_coef, int_coef, gain_ctl, targ_cnt;
uint32_t lanestagger;
+ int clock = crtc_state->port_clock;
if (intel_encoder->type == INTEL_OUTPUT_HDMI) {
intel_clock_t best_clock;
struct drm_device *dev = intel_crtc->base.dev;
struct intel_encoder *intel_encoder =
intel_ddi_get_crtc_new_encoder(crtc_state);
- int clock = crtc_state->port_clock;
if (IS_SKYLAKE(dev))
return skl_ddi_pll_select(intel_crtc, crtc_state,
- intel_encoder, clock);
+ intel_encoder);
else if (IS_BROXTON(dev))
return bxt_ddi_pll_select(intel_crtc, crtc_state,
- intel_encoder, clock);
+ intel_encoder);
else
return hsw_ddi_pll_select(intel_crtc, crtc_state,
- intel_encoder, clock);
+ intel_encoder);
}
void intel_ddi_set_pipe_settings(struct drm_crtc *crtc)
} else
temp |= TRANS_DDI_MODE_SELECT_DP_SST;
- temp |= DDI_PORT_WIDTH(intel_dp->lane_count);
+ temp |= DDI_PORT_WIDTH(intel_crtc->config->lane_count);
} else if (type == INTEL_OUTPUT_DP_MST) {
struct intel_dp *intel_dp = &enc_to_mst(encoder)->primary->dp;
} else
temp |= TRANS_DDI_MODE_SELECT_DP_SST;
- temp |= DDI_PORT_WIDTH(intel_dp->lane_count);
+ temp |= DDI_PORT_WIDTH(intel_crtc->config->lane_count);
} else {
WARN(1, "Invalid encoder type %d for pipe %c\n",
intel_encoder->type, pipe_name(pipe));
if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+ intel_dp_set_link_params(intel_dp, crtc->config);
+
intel_ddi_init_dp_buf_reg(intel_encoder);
intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
* here just read out lanes 0/1 and output a note if lanes 2/3 differ.
*/
hw_state->pcsdw12 = I915_READ(BXT_PORT_PCS_DW12_LN01(port));
- if (I915_READ(BXT_PORT_PCS_DW12_LN23(port) != hw_state->pcsdw12))
+ if (I915_READ(BXT_PORT_PCS_DW12_LN23(port)) != hw_state->pcsdw12)
DRM_DEBUG_DRIVER("lane stagger config different for lane 01 (%08x) and 23 (%08x)\n",
hw_state->pcsdw12,
I915_READ(BXT_PORT_PCS_DW12_LN23(port)));
case TRANS_DDI_MODE_SELECT_DP_SST:
case TRANS_DDI_MODE_SELECT_DP_MST:
pipe_config->has_dp_encoder = true;
+ pipe_config->lane_count =
+ ((temp & DDI_PORT_WIDTH_MASK) >> DDI_PORT_WIDTH_SHIFT) + 1;
intel_dp_get_m_n(intel_crtc, pipe_config);
break;
default:
goto err;
intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
- dev_priv->hotplug.irq_port[port] = intel_dig_port;
+ /*
+ * On BXT A0/A1, sw needs to activate DDIA HPD logic and
+ * interrupts to check the external panel connection.
+ */
+ if (IS_BROXTON(dev_priv) && (INTEL_REVID(dev) < BXT_REVID_B0)
+ && port == PORT_B)
+ dev_priv->hotplug.irq_port[PORT_A] = intel_dig_port;
+ else
+ dev_priv->hotplug.irq_port[port] = intel_dig_port;
}
/* In theory we don't need the encoder->type check, but leave it just in
DRM_FORMAT_ABGR8888,
DRM_FORMAT_XRGB2101010,
DRM_FORMAT_XBGR2101010,
+ DRM_FORMAT_YUYV,
+ DRM_FORMAT_YVYU,
+ DRM_FORMAT_UYVY,
+ DRM_FORMAT_VYUY,
};
/* Cursor formats */
struct intel_crtc_state *crtc_state);
static int i9xx_get_refclk(const struct intel_crtc_state *crtc_state,
int num_connectors);
+static void skylake_pfit_enable(struct intel_crtc *crtc);
+static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force);
+static void ironlake_pfit_enable(struct intel_crtc *crtc);
static void intel_modeset_setup_hw_state(struct drm_device *dev);
typedef struct {
return I915_READ(PCH_RAWCLK_FREQ) & RAWCLK_FREQ_MASK;
}
+/* hrawclock is 1/4 the FSB frequency */
+int intel_hrawclk(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ uint32_t clkcfg;
+
+ /* There is no CLKCFG reg in Valleyview. VLV hrawclk is 200 MHz */
+ if (IS_VALLEYVIEW(dev))
+ return 200;
+
+ clkcfg = I915_READ(CLKCFG);
+ switch (clkcfg & CLKCFG_FSB_MASK) {
+ case CLKCFG_FSB_400:
+ return 100;
+ case CLKCFG_FSB_533:
+ return 133;
+ case CLKCFG_FSB_667:
+ return 166;
+ case CLKCFG_FSB_800:
+ return 200;
+ case CLKCFG_FSB_1067:
+ return 266;
+ case CLKCFG_FSB_1333:
+ return 333;
+ /* these two are just a guess; one of them might be right */
+ case CLKCFG_FSB_1600:
+ case CLKCFG_FSB_1600_ALT:
+ return 400;
+ default:
+ return 133;
+ }
+}
+
static inline u32 /* units of 100MHz */
intel_fdi_link_freq(struct drm_device *dev)
{
}
}
-/*
- * ibx_digital_port_connected - is the specified port connected?
- * @dev_priv: i915 private structure
- * @port: the port to test
- *
- * Returns true if @port is connected, false otherwise.
- */
-bool ibx_digital_port_connected(struct drm_i915_private *dev_priv,
- struct intel_digital_port *port)
-{
- u32 bit;
-
- if (HAS_PCH_IBX(dev_priv->dev)) {
- switch (port->port) {
- case PORT_B:
- bit = SDE_PORTB_HOTPLUG;
- break;
- case PORT_C:
- bit = SDE_PORTC_HOTPLUG;
- break;
- case PORT_D:
- bit = SDE_PORTD_HOTPLUG;
- break;
- default:
- return true;
- }
- } else {
- switch (port->port) {
- case PORT_B:
- bit = SDE_PORTB_HOTPLUG_CPT;
- break;
- case PORT_C:
- bit = SDE_PORTC_HOTPLUG_CPT;
- break;
- case PORT_D:
- bit = SDE_PORTD_HOTPLUG_CPT;
- break;
- case PORT_E:
- bit = SDE_PORTE_HOTPLUG_SPT;
- break;
- default:
- return true;
- }
- }
-
- return I915_READ(SDEISR) & bit;
-}
-
static const char *state_string(bool enabled)
{
return enabled ? "on" : "off";
assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMID);
}
-static void intel_init_dpio(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- if (!IS_VALLEYVIEW(dev))
- return;
-
- /*
- * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C),
- * CHV x1 PHY (DP/HDMI D)
- * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C)
- */
- if (IS_CHERRYVIEW(dev)) {
- DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2;
- DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO;
- } else {
- DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO;
- }
-}
-
static void vlv_enable_pll(struct intel_crtc *crtc,
const struct intel_crtc_state *pipe_config)
{
val &= ~DPIO_DCLKP_EN;
vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), val);
- /* disable left/right clock distribution */
- if (pipe != PIPE_B) {
- val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
- val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
- vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
- } else {
- val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
- val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
- vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
- }
-
mutex_unlock(&dev_priv->sb_lock);
}
unsigned int
intel_tile_height(struct drm_device *dev, uint32_t pixel_format,
- uint64_t fb_format_modifier)
+ uint64_t fb_format_modifier, unsigned int plane)
{
unsigned int tile_height;
uint32_t pixel_bytes;
tile_height = 32;
break;
case I915_FORMAT_MOD_Yf_TILED:
- pixel_bytes = drm_format_plane_cpp(pixel_format, 0);
+ pixel_bytes = drm_format_plane_cpp(pixel_format, plane);
switch (pixel_bytes) {
default:
case 1:
uint32_t pixel_format, uint64_t fb_format_modifier)
{
return ALIGN(height, intel_tile_height(dev, pixel_format,
- fb_format_modifier));
+ fb_format_modifier, 0));
}
static int
info->height = fb->height;
info->pixel_format = fb->pixel_format;
info->pitch = fb->pitches[0];
+ info->uv_offset = fb->offsets[1];
info->fb_modifier = fb->modifier[0];
tile_height = intel_tile_height(fb->dev, fb->pixel_format,
- fb->modifier[0]);
+ fb->modifier[0], 0);
tile_pitch = PAGE_SIZE / tile_height;
info->width_pages = DIV_ROUND_UP(fb->pitches[0], tile_pitch);
info->height_pages = DIV_ROUND_UP(fb->height, tile_height);
info->size = info->width_pages * info->height_pages * PAGE_SIZE;
+ if (info->pixel_format == DRM_FORMAT_NV12) {
+ tile_height = intel_tile_height(fb->dev, fb->pixel_format,
+ fb->modifier[0], 1);
+ tile_pitch = PAGE_SIZE / tile_height;
+ info->width_pages_uv = DIV_ROUND_UP(fb->pitches[0], tile_pitch);
+ info->height_pages_uv = DIV_ROUND_UP(fb->height / 2,
+ tile_height);
+ info->size_uv = info->width_pages_uv * info->height_pages_uv *
+ PAGE_SIZE;
+ }
+
return 0;
}
(intel_crtc->config->pipe_src_w - 1) * pixel_size;
}
+ intel_crtc->adjusted_x = x;
+ intel_crtc->adjusted_y = y;
+
I915_WRITE(reg, dspcntr);
I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
}
}
+ intel_crtc->adjusted_x = x;
+ intel_crtc->adjusted_y = y;
+
I915_WRITE(reg, dspcntr);
I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
}
unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane,
- struct drm_i915_gem_object *obj)
+ struct drm_i915_gem_object *obj,
+ unsigned int plane)
{
const struct i915_ggtt_view *view = &i915_ggtt_view_normal;
+ struct i915_vma *vma;
+ unsigned char *offset;
if (intel_rotation_90_or_270(intel_plane->base.state->rotation))
view = &i915_ggtt_view_rotated;
- return i915_gem_obj_ggtt_offset_view(obj, view);
+ vma = i915_gem_obj_to_ggtt_view(obj, view);
+ if (WARN(!vma, "ggtt vma for display object not found! (view=%u)\n",
+ view->type))
+ return -1;
+
+ offset = (unsigned char *)vma->node.start;
+
+ if (plane == 1) {
+ offset += vma->ggtt_view.rotation_info.uv_start_page *
+ PAGE_SIZE;
+ }
+
+ return (unsigned long)offset;
}
static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
I915_WRITE(SKL_PS_CTRL(intel_crtc->pipe, id), 0);
I915_WRITE(SKL_PS_WIN_POS(intel_crtc->pipe, id), 0);
I915_WRITE(SKL_PS_WIN_SZ(intel_crtc->pipe, id), 0);
- DRM_DEBUG_KMS("CRTC:%d Disabled scaler id %u.%u\n",
- intel_crtc->base.base.id, intel_crtc->pipe, id);
}
/*
obj = intel_fb_obj(fb);
stride_div = intel_fb_stride_alignment(dev, fb->modifier[0],
fb->pixel_format);
- surf_addr = intel_plane_obj_offset(to_intel_plane(plane), obj);
+ surf_addr = intel_plane_obj_offset(to_intel_plane(plane), obj, 0);
/*
* FIXME: intel_plane_state->src, dst aren't set when transitional
if (intel_rotation_90_or_270(rotation)) {
/* stride = Surface height in tiles */
tile_height = intel_tile_height(dev, fb->pixel_format,
- fb->modifier[0]);
+ fb->modifier[0], 0);
stride = DIV_ROUND_UP(fb->height, tile_height);
x_offset = stride * tile_height - y - src_h;
y_offset = x;
}
plane_offset = y_offset << 16 | x_offset;
+ intel_crtc->adjusted_x = x_offset;
+ intel_crtc->adjusted_y = y_offset;
+
I915_WRITE(PLANE_CTL(pipe, 0), plane_ctl);
I915_WRITE(PLANE_OFFSET(pipe, 0), plane_offset);
I915_WRITE(PLANE_SIZE(pipe, 0), plane_size);
static void intel_update_primary_planes(struct drm_device *dev)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_crtc *crtc;
for_each_crtc(dev, crtc) {
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ struct intel_plane *plane = to_intel_plane(crtc->primary);
+ struct intel_plane_state *plane_state;
- drm_modeset_lock(&crtc->mutex, NULL);
- /*
- * FIXME: Once we have proper support for primary planes (and
- * disabling them without disabling the entire crtc) allow again
- * a NULL crtc->primary->fb.
- */
- if (intel_crtc->active && crtc->primary->fb)
- dev_priv->display.update_primary_plane(crtc,
- crtc->primary->fb,
- crtc->x,
- crtc->y);
- drm_modeset_unlock(&crtc->mutex);
+ drm_modeset_lock_crtc(crtc, &plane->base);
+
+ plane_state = to_intel_plane_state(plane->base.state);
+
+ if (plane_state->base.fb)
+ plane->commit_plane(&plane->base, plane_state);
+
+ drm_modeset_unlock_crtc(crtc);
}
}
* so update the base address of all primary
* planes to the the last fb to make sure we're
* showing the correct fb after a reset.
+ *
+ * FIXME: Atomic will make this obsolete since we won't schedule
+ * CS-based flips (which might get lost in gpu resets) any more.
*/
intel_update_primary_planes(dev);
return;
return pending;
}
-static void intel_update_pipe_size(struct intel_crtc *crtc)
+static void intel_update_pipe_config(struct intel_crtc *crtc,
+ struct intel_crtc_state *old_crtc_state)
{
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- const struct drm_display_mode *adjusted_mode;
+ struct intel_crtc_state *pipe_config =
+ to_intel_crtc_state(crtc->base.state);
- if (!i915.fastboot)
- return;
+ /* drm_atomic_helper_update_legacy_modeset_state might not be called. */
+ crtc->base.mode = crtc->base.state->mode;
+
+ DRM_DEBUG_KMS("Updating pipe size %ix%i -> %ix%i\n",
+ old_crtc_state->pipe_src_w, old_crtc_state->pipe_src_h,
+ pipe_config->pipe_src_w, pipe_config->pipe_src_h);
+
+ if (HAS_DDI(dev))
+ intel_set_pipe_csc(&crtc->base);
/*
* Update pipe size and adjust fitter if needed: the reason for this is
* fastboot case, we'll flip, but if we don't update the pipesrc and
* pfit state, we'll end up with a big fb scanned out into the wrong
* sized surface.
- *
- * To fix this properly, we need to hoist the checks up into
- * compute_mode_changes (or above), check the actual pfit state and
- * whether the platform allows pfit disable with pipe active, and only
- * then update the pipesrc and pfit state, even on the flip path.
*/
- adjusted_mode = &crtc->config->base.adjusted_mode;
-
I915_WRITE(PIPESRC(crtc->pipe),
- ((adjusted_mode->crtc_hdisplay - 1) << 16) |
- (adjusted_mode->crtc_vdisplay - 1));
- if (!crtc->config->pch_pfit.enabled &&
- (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) ||
- intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))) {
- I915_WRITE(PF_CTL(crtc->pipe), 0);
- I915_WRITE(PF_WIN_POS(crtc->pipe), 0);
- I915_WRITE(PF_WIN_SZ(crtc->pipe), 0);
+ ((pipe_config->pipe_src_w - 1) << 16) |
+ (pipe_config->pipe_src_h - 1));
+
+ /* on skylake this is done by detaching scalers */
+ if (INTEL_INFO(dev)->gen >= 9) {
+ skl_detach_scalers(crtc);
+
+ if (pipe_config->pch_pfit.enabled)
+ skylake_pfit_enable(crtc);
+ } else if (HAS_PCH_SPLIT(dev)) {
+ if (pipe_config->pch_pfit.enabled)
+ ironlake_pfit_enable(crtc);
+ else if (old_crtc_state->pch_pfit.enabled)
+ ironlake_pfit_disable(crtc, true);
}
- crtc->config->pipe_src_w = adjusted_mode->crtc_hdisplay;
- crtc->config->pipe_src_h = adjusted_mode->crtc_vdisplay;
}
static void intel_fdi_normal_train(struct drm_crtc *crtc)
intel_ddi_enable_pipe_clock(intel_crtc);
- if (INTEL_INFO(dev)->gen == 9)
+ if (INTEL_INFO(dev)->gen >= 9)
skylake_pfit_enable(intel_crtc);
- else if (INTEL_INFO(dev)->gen < 9)
- ironlake_pfit_enable(intel_crtc);
else
- MISSING_CASE(INTEL_INFO(dev)->gen);
+ ironlake_pfit_enable(intel_crtc);
/*
* On ILK+ LUT must be loaded before the pipe is running but with
}
}
-static void ironlake_pfit_disable(struct intel_crtc *crtc)
+static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force)
{
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
/* To avoid upsetting the power well on haswell only disable the pfit if
* it's in use. The hw state code will make sure we get this right. */
- if (crtc->config->pch_pfit.enabled) {
+ if (force || crtc->config->pch_pfit.enabled) {
I915_WRITE(PF_CTL(pipe), 0);
I915_WRITE(PF_WIN_POS(pipe), 0);
I915_WRITE(PF_WIN_SZ(pipe), 0);
intel_disable_pipe(intel_crtc);
- ironlake_pfit_disable(intel_crtc);
+ ironlake_pfit_disable(intel_crtc, false);
if (intel_crtc->config->has_pch_encoder)
ironlake_fdi_disable(crtc);
intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
- if (INTEL_INFO(dev)->gen == 9)
+ if (INTEL_INFO(dev)->gen >= 9)
skylake_scaler_disable(intel_crtc);
- else if (INTEL_INFO(dev)->gen < 9)
- ironlake_pfit_disable(intel_crtc);
else
- MISSING_CASE(INTEL_INFO(dev)->gen);
+ ironlake_pfit_disable(intel_crtc, false);
intel_ddi_disable_pipe_clock(intel_crtc);
modeset_put_power_domains(dev_priv, put_domains[i]);
}
+static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv)
+{
+ int max_cdclk_freq = dev_priv->max_cdclk_freq;
+
+ if (INTEL_INFO(dev_priv)->gen >= 9 ||
+ IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
+ return max_cdclk_freq;
+ else if (IS_CHERRYVIEW(dev_priv))
+ return max_cdclk_freq*95/100;
+ else if (INTEL_INFO(dev_priv)->gen < 4)
+ return 2*max_cdclk_freq*90/100;
+ else
+ return max_cdclk_freq*90/100;
+}
+
static void intel_update_max_cdclk(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
dev_priv->max_cdclk_freq = dev_priv->cdclk_freq;
}
+ dev_priv->max_dotclk_freq = intel_compute_max_dotclk(dev_priv);
+
DRM_DEBUG_DRIVER("Max CD clock rate: %d kHz\n",
dev_priv->max_cdclk_freq);
+
+ DRM_DEBUG_DRIVER("Max dotclock rate: %d kHz\n",
+ dev_priv->max_dotclk_freq);
}
static void intel_update_cdclk(struct drm_device *dev)
is_dsi = intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DSI);
- if (!is_dsi) {
- if (IS_CHERRYVIEW(dev))
- chv_prepare_pll(intel_crtc, intel_crtc->config);
- else
- vlv_prepare_pll(intel_crtc, intel_crtc->config);
- }
-
if (intel_crtc->config->has_dp_encoder)
intel_dp_set_m_n(intel_crtc, M1_N1);
encoder->pre_pll_enable(encoder);
if (!is_dsi) {
- if (IS_CHERRYVIEW(dev))
+ if (IS_CHERRYVIEW(dev)) {
+ chv_prepare_pll(intel_crtc, intel_crtc->config);
chv_enable_pll(intel_crtc, intel_crtc->config);
- else
+ } else {
+ vlv_prepare_pll(intel_crtc, intel_crtc->config);
vlv_enable_pll(intel_crtc, intel_crtc->config);
+ }
}
for_each_encoder_on_crtc(dev, crtc, encoder)
i9xx_disable_pll(intel_crtc);
}
+ for_each_encoder_on_crtc(dev, crtc, encoder)
+ if (encoder->post_pll_disable)
+ encoder->post_pll_disable(encoder);
+
if (!IS_GEN2(dev))
intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
1 << DPIO_CHV_N_DIV_SHIFT);
/* M2 fraction division */
- if (bestm2_frac)
- vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW2(port), bestm2_frac);
+ vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW2(port), bestm2_frac);
/* M2 fraction division enable */
dpio_val = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW3(port));
else
i9xx_crtc_clock_get(crtc, pipe_config);
+ /*
+ * Normally the dotclock is filled in by the encoder .get_config()
+ * but in case the pipe is enabled w/o any ports we need a sane
+ * default.
+ */
+ pipe_config->base.adjusted_mode.crtc_clock =
+ pipe_config->port_clock / pipe_config->pixel_multiplier;
+
return true;
}
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"))
+ if (WARN(HAS_PCH_LPT_LP(dev) && with_fdi, "LP PCH doesn't have FDI\n"))
with_fdi = false;
mutex_lock(&dev_priv->sb_lock);
}
}
- reg = (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) ?
- SBI_GEN0 : SBI_DBUFF0;
+ reg = HAS_PCH_LPT_LP(dev) ? 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_lock(&dev_priv->sb_lock);
- reg = (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) ?
- SBI_GEN0 : SBI_DBUFF0;
+ reg = HAS_PCH_LPT_LP(dev) ? 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);
DRM_DEBUG_KMS("Enabling package C8+\n");
- if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+ if (HAS_PCH_LPT_LP(dev)) {
val = I915_READ(SOUTH_DSPCLK_GATE_D);
val &= ~PCH_LP_PARTITION_LEVEL_DISABLE;
I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
hsw_restore_lcpll(dev_priv);
lpt_init_pch_refclk(dev);
- if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+ if (HAS_PCH_LPT_LP(dev)) {
val = I915_READ(SOUTH_DSPCLK_GATE_D);
val |= PCH_LP_PARTITION_LEVEL_DISABLE;
I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
}
if (intel_display_power_is_enabled(dev_priv, pfit_domain)) {
- if (INTEL_INFO(dev)->gen == 9)
+ if (INTEL_INFO(dev)->gen >= 9)
skylake_get_pfit_config(crtc, pipe_config);
- else if (INTEL_INFO(dev)->gen < 9)
- ironlake_get_pfit_config(crtc, pipe_config);
else
- MISSING_CASE(INTEL_INFO(dev)->gen);
+ ironlake_get_pfit_config(crtc, pipe_config);
}
if (IS_HASWELL(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 x = crtc->cursor_x;
- int y = crtc->cursor_y;
+ struct drm_plane_state *cursor_state = crtc->cursor->state;
+ int x = cursor_state->crtc_x;
+ int y = cursor_state->crtc_y;
u32 base = 0, pos = 0;
if (on)
base = 0;
if (x < 0) {
- if (x + intel_crtc->base.cursor->state->crtc_w <= 0)
+ if (x + cursor_state->crtc_w <= 0)
base = 0;
pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT;
pos |= x << CURSOR_X_SHIFT;
if (y < 0) {
- if (y + intel_crtc->base.cursor->state->crtc_h <= 0)
+ if (y + cursor_state->crtc_h <= 0)
base = 0;
pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT;
/* ILK+ do this automagically */
if (HAS_GMCH_DISPLAY(dev) &&
crtc->cursor->state->rotation == BIT(DRM_ROTATE_180)) {
- base += (intel_crtc->base.cursor->state->crtc_h *
- intel_crtc->base.cursor->state->crtc_w - 1) * 4;
+ base += (cursor_state->crtc_h *
+ cursor_state->crtc_w - 1) * 4;
}
if (IS_845G(dev) || IS_I865G(dev))
DERRMR_PIPEB_PRI_FLIP_DONE |
DERRMR_PIPEC_PRI_FLIP_DONE));
if (IS_GEN8(dev))
- intel_ring_emit(ring, MI_STORE_REGISTER_MEM_GEN8(1) |
+ intel_ring_emit(ring, MI_STORE_REGISTER_MEM_GEN8 |
MI_SRM_LRM_GLOBAL_GTT);
else
- intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1) |
+ intel_ring_emit(ring, MI_STORE_REGISTER_MEM |
MI_SRM_LRM_GLOBAL_GTT);
intel_ring_emit(ring, DERRMR);
intel_ring_emit(ring, ring->scratch.gtt_offset + 256);
static void intel_do_mmio_flip(struct intel_crtc *intel_crtc)
{
struct drm_device *dev = intel_crtc->base.dev;
- u32 start_vbl_count;
intel_mark_page_flip_active(intel_crtc);
- intel_pipe_update_start(intel_crtc, &start_vbl_count);
+ intel_pipe_update_start(intel_crtc);
if (INTEL_INFO(dev)->gen >= 9)
skl_do_mmio_flip(intel_crtc);
/* use_mmio_flip() retricts MMIO flips to ilk+ */
ilk_do_mmio_flip(intel_crtc);
- intel_pipe_update_end(intel_crtc, start_vbl_count);
+ intel_pipe_update_end(intel_crtc);
}
static void intel_mmio_flip_work_func(struct work_struct *work)
if (atomic_read(&work->pending) >= INTEL_FLIP_COMPLETE)
return true;
+ if (atomic_read(&work->pending) < INTEL_FLIP_PENDING)
+ return false;
+
if (!work->enable_stall_check)
return false;
if (ret)
goto cleanup_pending;
- work->gtt_offset = intel_plane_obj_offset(to_intel_plane(primary), obj)
- + intel_crtc->dspaddr_offset;
+ work->gtt_offset = intel_plane_obj_offset(to_intel_plane(primary),
+ obj, 0);
+ work->gtt_offset += intel_crtc->dspaddr_offset;
if (mmio_flip) {
ret = intel_queue_mmio_flip(dev, crtc, fb, obj, ring,
intel_crtc->atomic.update_wm_pre = true;
}
- if (visible)
+ if (visible || was_visible)
intel_crtc->atomic.fb_bits |=
to_intel_plane(plane)->frontbuffer_bit;
pipe_config->fdi_m_n.gmch_m, pipe_config->fdi_m_n.gmch_n,
pipe_config->fdi_m_n.link_m, pipe_config->fdi_m_n.link_n,
pipe_config->fdi_m_n.tu);
- DRM_DEBUG_KMS("dp: %i, gmch_m: %u, gmch_n: %u, link_m: %u, link_n: %u, tu: %u\n",
+ DRM_DEBUG_KMS("dp: %i, lanes: %i, gmch_m: %u, gmch_n: %u, link_m: %u, link_n: %u, tu: %u\n",
pipe_config->has_dp_encoder,
+ pipe_config->lane_count,
pipe_config->dp_m_n.gmch_m, pipe_config->dp_m_n.gmch_n,
pipe_config->dp_m_n.link_m, pipe_config->dp_m_n.link_n,
pipe_config->dp_m_n.tu);
- DRM_DEBUG_KMS("dp: %i, gmch_m2: %u, gmch_n2: %u, link_m2: %u, link_n2: %u, tu2: %u\n",
+ DRM_DEBUG_KMS("dp: %i, lanes: %i, gmch_m2: %u, gmch_n2: %u, link_m2: %u, link_n2: %u, tu2: %u\n",
pipe_config->has_dp_encoder,
+ pipe_config->lane_count,
pipe_config->dp_m2_n2.gmch_m,
pipe_config->dp_m2_n2.gmch_n,
pipe_config->dp_m2_n2.link_m,
(DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC)))
pipe_config->base.adjusted_mode.flags |= DRM_MODE_FLAG_NVSYNC;
- /* Compute a starting value for pipe_config->pipe_bpp taking the source
- * plane pixel format and any sink constraints into account. Returns the
- * source plane bpp so that dithering can be selected on mismatches
- * after encoders and crtc also have had their say. */
base_bpp = compute_baseline_pipe_bpp(to_intel_crtc(crtc),
pipe_config);
if (base_bpp < 0)
/* Dithering seems to not pass-through bits correctly when it should, so
* only enable it on 6bpc panels. */
pipe_config->dither = pipe_config->pipe_bpp == 6*3;
- DRM_DEBUG_KMS("plane bpp: %i, pipe bpp: %i, dithering: %i\n",
+ DRM_DEBUG_KMS("hw max bpp: %i, pipe bpp: %i, dithering: %i\n",
base_bpp, pipe_config->pipe_bpp, pipe_config->dither);
fail:
base.head) \
if (mask & (1 <<(intel_crtc)->pipe))
-
static bool
intel_compare_m_n(unsigned int m, unsigned int n,
unsigned int m2, unsigned int n2,
PIPE_CONF_CHECK_M_N(fdi_m_n);
PIPE_CONF_CHECK_I(has_dp_encoder);
+ PIPE_CONF_CHECK_I(lane_count);
if (INTEL_INFO(dev)->gen < 8) {
PIPE_CONF_CHECK_M_N(dp_m_n);
DRM_MODE_FLAG_NVSYNC);
}
- PIPE_CONF_CHECK_I(pipe_src_w);
- PIPE_CONF_CHECK_I(pipe_src_h);
-
- PIPE_CONF_CHECK_I(gmch_pfit.control);
+ PIPE_CONF_CHECK_X(gmch_pfit.control);
/* pfit ratios are autocomputed by the hw on gen4+ */
if (INTEL_INFO(dev)->gen < 4)
PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios);
- PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits);
+ PIPE_CONF_CHECK_X(gmch_pfit.lvds_border_bits);
- PIPE_CONF_CHECK_I(pch_pfit.enabled);
- if (current_config->pch_pfit.enabled) {
- PIPE_CONF_CHECK_I(pch_pfit.pos);
- PIPE_CONF_CHECK_I(pch_pfit.size);
- }
+ if (!adjust) {
+ PIPE_CONF_CHECK_I(pipe_src_w);
+ PIPE_CONF_CHECK_I(pipe_src_h);
+
+ PIPE_CONF_CHECK_I(pch_pfit.enabled);
+ if (current_config->pch_pfit.enabled) {
+ PIPE_CONF_CHECK_X(pch_pfit.pos);
+ PIPE_CONF_CHECK_X(pch_pfit.size);
+ }
- PIPE_CONF_CHECK_I(scaler_state.scaler_id);
+ PIPE_CONF_CHECK_I(scaler_state.scaler_id);
+ }
/* BDW+ don't expose a synchronous way to read the state */
if (IS_HASWELL(dev))
struct intel_crtc_state *pipe_config, *sw_config;
bool active;
- if (!needs_modeset(crtc->state))
+ if (!needs_modeset(crtc->state) &&
+ !to_intel_crtc_state(crtc->state)->update_pipe)
continue;
__drm_atomic_helper_crtc_destroy_state(crtc, old_crtc_state);
return ret;
}
-
static int intel_modeset_checks(struct drm_atomic_state *state)
{
struct drm_device *dev = state->dev;
if (ret)
return ret;
- if (i915.fastboot &&
- intel_pipe_config_compare(state->dev,
+ if (intel_pipe_config_compare(state->dev,
to_intel_crtc_state(crtc->state),
pipe_config, true)) {
crtc_state->mode_changed = false;
+ to_intel_crtc_state(crtc_state)->update_pipe = true;
}
if (needs_modeset(crtc_state)) {
for_each_crtc_in_state(state, crtc, crtc_state, i) {
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
bool modeset = needs_modeset(crtc->state);
+ bool update_pipe = !modeset &&
+ to_intel_crtc_state(crtc->state)->update_pipe;
+ unsigned long put_domains = 0;
if (modeset && crtc->state->active) {
update_scanline_offset(to_intel_crtc(crtc));
dev_priv->display.crtc_enable(crtc);
}
+ if (update_pipe) {
+ put_domains = modeset_get_crtc_power_domains(crtc);
+
+ /* make sure intel_modeset_check_state runs */
+ any_ms = true;
+ }
+
if (!modeset)
intel_pre_plane_update(intel_crtc);
drm_atomic_helper_commit_planes_on_crtc(crtc_state);
+
+ if (put_domains)
+ modeset_put_power_domains(dev_priv, put_domains);
+
intel_post_plane_update(intel_crtc);
}
if (!crtc->state->active)
return;
- if (state->visible)
- /* FIXME: kill this fastboot hack */
- intel_update_pipe_size(intel_crtc);
-
- dev_priv->display.update_primary_plane(crtc, fb, crtc->x, crtc->y);
+ dev_priv->display.update_primary_plane(crtc, fb,
+ state->src.x1 >> 16,
+ state->src.y1 >> 16);
}
static void
{
struct drm_device *dev = crtc->dev;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+ struct intel_crtc_state *old_intel_state =
+ to_intel_crtc_state(old_crtc_state);
+ bool modeset = needs_modeset(crtc->state);
if (intel_crtc->atomic.update_wm_pre)
intel_update_watermarks(crtc);
/* Perform vblank evasion around commit operation */
if (crtc->state->active)
- intel_pipe_update_start(intel_crtc, &intel_crtc->start_vbl_count);
+ intel_pipe_update_start(intel_crtc);
+
+ if (modeset)
+ return;
- if (!needs_modeset(crtc->state) && INTEL_INFO(dev)->gen >= 9)
+ if (to_intel_crtc_state(crtc->state)->update_pipe)
+ intel_update_pipe_config(intel_crtc, old_intel_state);
+ else if (INTEL_INFO(dev)->gen >= 9)
skl_detach_scalers(intel_crtc);
}
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
if (crtc->state->active)
- intel_pipe_update_end(intel_crtc, intel_crtc->start_vbl_count);
+ intel_pipe_update_end(intel_crtc);
}
/**
crtc = crtc ? crtc : plane->crtc;
intel_crtc = to_intel_crtc(crtc);
- plane->fb = state->base.fb;
- crtc->cursor_x = state->base.crtc_x;
- crtc->cursor_y = state->base.crtc_y;
-
if (intel_crtc->cursor_bo == obj)
goto update;
}
}
- intel_init_dpio(dev);
-
intel_shared_dpll_init(dev);
/* Just disable it once at startup */
return true;
}
+static bool intel_crtc_has_encoders(struct intel_crtc *crtc)
+{
+ struct drm_device *dev = crtc->base.dev;
+ struct intel_encoder *encoder;
+
+ for_each_encoder_on_crtc(dev, &crtc->base, encoder)
+ return true;
+
+ return false;
+}
+
static void intel_sanitize_crtc(struct intel_crtc *crtc)
{
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_encoder *encoder;
u32 reg;
- bool enable;
/* Clear any frame start delays used for debugging left by the BIOS */
reg = PIPECONF(crtc->config->cpu_transcoder);
/* restore vblank interrupts to correct state */
drm_crtc_vblank_reset(&crtc->base);
if (crtc->active) {
- drm_calc_timestamping_constants(&crtc->base, &crtc->base.hwmode);
- update_scanline_offset(crtc);
+ struct intel_plane *plane;
+
drm_crtc_vblank_on(&crtc->base);
+
+ /* Disable everything but the primary plane */
+ for_each_intel_plane_on_crtc(dev, crtc, plane) {
+ if (plane->base.type == DRM_PLANE_TYPE_PRIMARY)
+ continue;
+
+ plane->disable_plane(&plane->base, &crtc->base);
+ }
}
/* We need to sanitize the plane -> pipe mapping first because this will
/* Adjust the state of the output pipe according to whether we
* have active connectors/encoders. */
- enable = false;
- for_each_encoder_on_crtc(dev, &crtc->base, encoder) {
- enable = true;
- break;
- }
-
- if (!enable)
+ if (!intel_crtc_has_encoders(crtc))
intel_crtc_disable_noatomic(&crtc->base);
if (crtc->active != crtc->base.state->active) {
+ struct intel_encoder *encoder;
/* This can happen either due to bugs in the get_hw_state
* functions or because of calls to intel_crtc_disable_noatomic,
i915_redisable_vga_power_on(dev);
}
-static bool primary_get_hw_state(struct intel_crtc *crtc)
+static bool primary_get_hw_state(struct intel_plane *plane)
{
- struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+ struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
- return !!(I915_READ(DSPCNTR(crtc->plane)) & DISPLAY_PLANE_ENABLE);
+ return I915_READ(DSPCNTR(plane->plane)) & DISPLAY_PLANE_ENABLE;
}
-static void readout_plane_state(struct intel_crtc *crtc,
- struct intel_crtc_state *crtc_state)
+/* FIXME read out full plane state for all planes */
+static void readout_plane_state(struct intel_crtc *crtc)
{
- struct intel_plane *p;
- struct intel_plane_state *plane_state;
- bool active = crtc_state->base.active;
-
- for_each_intel_plane(crtc->base.dev, p) {
- if (crtc->pipe != p->pipe)
- continue;
-
- plane_state = to_intel_plane_state(p->base.state);
-
- if (p->base.type == DRM_PLANE_TYPE_PRIMARY) {
- plane_state->visible = primary_get_hw_state(crtc);
- if (plane_state->visible)
- crtc->base.state->plane_mask |=
- 1 << drm_plane_index(&p->base);
- } else {
- if (active)
- p->disable_plane(&p->base, &crtc->base);
+ struct intel_plane_state *plane_state =
+ to_intel_plane_state(crtc->base.primary->state);
- plane_state->visible = false;
- }
- }
+ plane_state->visible =
+ primary_get_hw_state(to_intel_plane(crtc->base.primary));
}
static void intel_modeset_readout_hw_state(struct drm_device *dev)
crtc->base.state->active = crtc->active;
crtc->base.enabled = crtc->active;
- memset(&crtc->base.mode, 0, sizeof(crtc->base.mode));
- if (crtc->base.state->active) {
- intel_mode_from_pipe_config(&crtc->base.mode, crtc->config);
- intel_mode_from_pipe_config(&crtc->base.state->adjusted_mode, crtc->config);
- WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode));
-
- /*
- * The initial mode needs to be set in order to keep
- * the atomic core happy. It wants a valid mode if the
- * crtc's enabled, so we do the above call.
- *
- * At this point some state updated by the connectors
- * in their ->detect() callback has not run yet, so
- * no recalculation can be done yet.
- *
- * Even if we could do a recalculation and modeset
- * right now it would cause a double modeset if
- * fbdev or userspace chooses a different initial mode.
- *
- * If that happens, someone indicated they wanted a
- * mode change, which means it's safe to do a full
- * recalculation.
- */
- crtc->base.state->mode.private_flags = I915_MODE_FLAG_INHERITED;
- }
-
- crtc->base.hwmode = crtc->config->base.adjusted_mode;
- readout_plane_state(crtc, to_intel_crtc_state(crtc->base.state));
+ readout_plane_state(crtc);
DRM_DEBUG_KMS("[CRTC:%d] hw state readout: %s\n",
crtc->base.base.id,
connector->base.name,
connector->base.encoder ? "enabled" : "disabled");
}
+
+ for_each_intel_crtc(dev, crtc) {
+ crtc->base.hwmode = crtc->config->base.adjusted_mode;
+
+ memset(&crtc->base.mode, 0, sizeof(crtc->base.mode));
+ if (crtc->base.state->active) {
+ intel_mode_from_pipe_config(&crtc->base.mode, crtc->config);
+ intel_mode_from_pipe_config(&crtc->base.state->adjusted_mode, crtc->config);
+ WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode));
+
+ /*
+ * The initial mode needs to be set in order to keep
+ * the atomic core happy. It wants a valid mode if the
+ * crtc's enabled, so we do the above call.
+ *
+ * At this point some state updated by the connectors
+ * in their ->detect() callback has not run yet, so
+ * no recalculation can be done yet.
+ *
+ * Even if we could do a recalculation and modeset
+ * right now it would cause a double modeset if
+ * fbdev or userspace chooses a different initial mode.
+ *
+ * If that happens, someone indicated they wanted a
+ * mode change, which means it's safe to do a full
+ * recalculation.
+ */
+ crtc->base.state->mode.private_flags = I915_MODE_FLAG_INHERITED;
+
+ drm_calc_timestamping_constants(&crtc->base, &crtc->base.hwmode);
+ update_scanline_offset(crtc);
+ }
+ }
}
/* Scan out the current hw modeset state,
static void vlv_steal_power_sequencer(struct drm_device *dev,
enum pipe pipe);
+static unsigned int intel_dp_unused_lane_mask(int lane_count)
+{
+ return ~((1 << lane_count) - 1) & 0xf;
+}
+
static int
intel_dp_max_link_bw(struct intel_dp *intel_dp)
{
dst[i] = src >> ((3-i) * 8);
}
-/* hrawclock is 1/4 the FSB frequency */
-static int
-intel_hrawclk(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
- uint32_t clkcfg;
-
- /* There is no CLKCFG reg in Valleyview. VLV hrawclk is 200 MHz */
- if (IS_VALLEYVIEW(dev))
- return 200;
-
- clkcfg = I915_READ(CLKCFG);
- switch (clkcfg & CLKCFG_FSB_MASK) {
- case CLKCFG_FSB_400:
- return 100;
- case CLKCFG_FSB_533:
- return 133;
- case CLKCFG_FSB_667:
- return 166;
- case CLKCFG_FSB_800:
- return 200;
- case CLKCFG_FSB_1067:
- return 266;
- case CLKCFG_FSB_1333:
- return 333;
- /* these two are just a guess; one of them might be right */
- case CLKCFG_FSB_1600:
- case CLKCFG_FSB_1600_ALT:
- return 400;
- default:
- return 133;
- }
-}
-
static void
intel_dp_init_panel_power_sequencer(struct drm_device *dev,
struct intel_dp *intel_dp);
struct drm_device *dev = intel_dig_port->base.base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
enum pipe pipe = intel_dp->pps_pipe;
- bool pll_enabled;
+ bool pll_enabled, release_cl_override = false;
+ enum dpio_phy phy = DPIO_PHY(pipe);
+ enum dpio_channel ch = vlv_pipe_to_channel(pipe);
uint32_t DP;
if (WARN(I915_READ(intel_dp->output_reg) & DP_PORT_EN,
* The DPLL for the pipe must be enabled for this to work.
* So enable temporarily it if it's not already enabled.
*/
- if (!pll_enabled)
+ if (!pll_enabled) {
+ release_cl_override = IS_CHERRYVIEW(dev) &&
+ !chv_phy_powergate_ch(dev_priv, phy, ch, true);
+
vlv_force_pll_on(dev, pipe, IS_CHERRYVIEW(dev) ?
&chv_dpll[0].dpll : &vlv_dpll[0].dpll);
+ }
/*
* Similar magic as in intel_dp_enable_port().
I915_WRITE(intel_dp->output_reg, DP & ~DP_PORT_EN);
POSTING_READ(intel_dp->output_reg);
- if (!pll_enabled)
+ if (!pll_enabled) {
vlv_force_pll_off(dev, pipe);
+
+ if (release_cl_override)
+ chv_phy_powergate_ch(dev_priv, phy, ch, false);
+ }
}
static enum pipe
return rate_to_index(rate, intel_dp->sink_rates);
}
+static void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock,
+ uint8_t *link_bw, uint8_t *rate_select)
+{
+ if (intel_dp->num_sink_rates) {
+ *link_bw = 0;
+ *rate_select =
+ intel_dp_rate_select(intel_dp, port_clock);
+ } else {
+ *link_bw = drm_dp_link_rate_to_bw_code(port_clock);
+ *rate_select = 0;
+ }
+}
+
bool
intel_dp_compute_config(struct intel_encoder *encoder,
struct intel_crtc_state *pipe_config)
int link_avail, link_clock;
int common_rates[DP_MAX_SUPPORTED_RATES] = {};
int common_len;
+ uint8_t link_bw, rate_select;
common_len = intel_dp_common_rates(intel_dp, common_rates);
* CEA-861-E - 5.1 Default Encoding Parameters
* VESA DisplayPort Ver.1.2a - 5.1.1.1 Video Colorimetry
*/
- if (bpp != 18 && drm_match_cea_mode(adjusted_mode) > 1)
- intel_dp->color_range = DP_COLOR_RANGE_16_235;
- else
- intel_dp->color_range = 0;
- }
-
- if (intel_dp->color_range)
- pipe_config->limited_color_range = true;
-
- intel_dp->lane_count = lane_count;
-
- if (intel_dp->num_sink_rates) {
- intel_dp->link_bw = 0;
- intel_dp->rate_select =
- intel_dp_rate_select(intel_dp, common_rates[clock]);
+ pipe_config->limited_color_range =
+ bpp != 18 && drm_match_cea_mode(adjusted_mode) > 1;
} else {
- intel_dp->link_bw =
- drm_dp_link_rate_to_bw_code(common_rates[clock]);
- intel_dp->rate_select = 0;
+ pipe_config->limited_color_range =
+ intel_dp->limited_color_range;
}
+ pipe_config->lane_count = lane_count;
+
pipe_config->pipe_bpp = bpp;
pipe_config->port_clock = common_rates[clock];
- DRM_DEBUG_KMS("DP link bw %02x lane count %d clock %d bpp %d\n",
- intel_dp->link_bw, intel_dp->lane_count,
+ intel_dp_compute_rate(intel_dp, pipe_config->port_clock,
+ &link_bw, &rate_select);
+
+ DRM_DEBUG_KMS("DP link bw %02x rate select %02x lane count %d clock %d bpp %d\n",
+ link_bw, rate_select, pipe_config->lane_count,
pipe_config->port_clock, bpp);
DRM_DEBUG_KMS("DP link bw required %i available %i\n",
mode_rate, link_avail);
udelay(500);
}
+void intel_dp_set_link_params(struct intel_dp *intel_dp,
+ const struct intel_crtc_state *pipe_config)
+{
+ intel_dp->link_rate = pipe_config->port_clock;
+ intel_dp->lane_count = pipe_config->lane_count;
+}
+
static void intel_dp_prepare(struct intel_encoder *encoder)
{
struct drm_device *dev = encoder->base.dev;
struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
+ intel_dp_set_link_params(intel_dp, crtc->config);
+
/*
* There are four kinds of DP registers:
*
/* Handle DP bits in common between all three register formats */
intel_dp->DP |= DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
- intel_dp->DP |= DP_PORT_WIDTH(intel_dp->lane_count);
+ intel_dp->DP |= DP_PORT_WIDTH(crtc->config->lane_count);
if (crtc->config->has_audio)
intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE;
trans_dp &= ~TRANS_DP_ENH_FRAMING;
I915_WRITE(TRANS_DP_CTL(crtc->pipe), trans_dp);
} else {
- if (!HAS_PCH_SPLIT(dev) && !IS_VALLEYVIEW(dev))
- intel_dp->DP |= intel_dp->color_range;
+ if (!HAS_PCH_SPLIT(dev) && !IS_VALLEYVIEW(dev) &&
+ crtc->config->limited_color_range)
+ intel_dp->DP |= DP_COLOR_RANGE_16_235;
if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
intel_dp->DP |= DP_SYNC_HS_HIGH;
pipe_config->has_audio = tmp & DP_AUDIO_OUTPUT_ENABLE && port != PORT_A;
if (HAS_PCH_CPT(dev) && port != PORT_A) {
- tmp = I915_READ(TRANS_DP_CTL(crtc->pipe));
- if (tmp & TRANS_DP_HSYNC_ACTIVE_HIGH)
+ u32 trans_dp = I915_READ(TRANS_DP_CTL(crtc->pipe));
+
+ if (trans_dp & TRANS_DP_HSYNC_ACTIVE_HIGH)
flags |= DRM_MODE_FLAG_PHSYNC;
else
flags |= DRM_MODE_FLAG_NHSYNC;
- if (tmp & TRANS_DP_VSYNC_ACTIVE_HIGH)
+ if (trans_dp & TRANS_DP_VSYNC_ACTIVE_HIGH)
flags |= DRM_MODE_FLAG_PVSYNC;
else
flags |= DRM_MODE_FLAG_NVSYNC;
pipe_config->has_dp_encoder = true;
+ pipe_config->lane_count =
+ ((tmp & DP_PORT_WIDTH_MASK) >> DP_PORT_WIDTH_SHIFT) + 1;
+
intel_dp_get_m_n(crtc, pipe_config);
if (port == PORT_A) {
intel_dp_link_down(intel_dp);
}
-static void chv_post_disable_dp(struct intel_encoder *encoder)
+static void chv_data_lane_soft_reset(struct intel_encoder *encoder,
+ bool reset)
{
- struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
- struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
- 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);
- enum dpio_channel ch = vlv_dport_to_channel(dport);
- enum pipe pipe = intel_crtc->pipe;
- u32 val;
+ struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+ enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
+ struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+ enum pipe pipe = crtc->pipe;
+ uint32_t val;
- intel_dp_link_down(intel_dp);
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
+ if (reset)
+ val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+ else
+ val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
- mutex_lock(&dev_priv->sb_lock);
+ if (crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
+ if (reset)
+ val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+ else
+ val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+ }
- /* Propagate soft reset to data lane reset */
val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
val |= CHV_PCS_REQ_SOFTRESET_EN;
+ if (reset)
+ val &= ~DPIO_PCS_CLK_SOFT_RESET;
+ else
+ val |= DPIO_PCS_CLK_SOFT_RESET;
vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
- val |= CHV_PCS_REQ_SOFTRESET_EN;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
+ if (crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
+ val |= CHV_PCS_REQ_SOFTRESET_EN;
+ if (reset)
+ val &= ~DPIO_PCS_CLK_SOFT_RESET;
+ else
+ val |= DPIO_PCS_CLK_SOFT_RESET;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
+ }
+}
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
- val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
- vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
+static void chv_post_disable_dp(struct intel_encoder *encoder)
+{
+ struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+ struct drm_device *dev = encoder->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
- val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+ intel_dp_link_down(intel_dp);
+
+ mutex_lock(&dev_priv->sb_lock);
+
+ /* Assert data lane reset */
+ chv_data_lane_soft_reset(encoder, true);
mutex_unlock(&dev_priv->sb_lock);
}
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
uint32_t dp_reg = I915_READ(intel_dp->output_reg);
- unsigned int lane_mask = 0x0;
if (WARN_ON(dp_reg & DP_PORT_EN))
return;
pps_unlock(intel_dp);
- if (IS_VALLEYVIEW(dev))
+ if (IS_VALLEYVIEW(dev)) {
+ unsigned int lane_mask = 0x0;
+
+ if (IS_CHERRYVIEW(dev))
+ lane_mask = intel_dp_unused_lane_mask(crtc->config->lane_count);
+
vlv_wait_port_ready(dev_priv, dp_to_dig_port(intel_dp),
lane_mask);
+ }
intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
intel_dp_start_link_train(intel_dp);
val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val);
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
- val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
-
- /* Deassert soft data lane reset*/
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
- val |= CHV_PCS_REQ_SOFTRESET_EN;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
-
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
- val |= CHV_PCS_REQ_SOFTRESET_EN;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
-
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
- val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
- vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
-
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
- val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+ if (intel_crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
+ val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
+ }
/* Program Tx lane latency optimal setting*/
- for (i = 0; i < 4; i++) {
+ for (i = 0; i < intel_crtc->config->lane_count; i++) {
/* Set the upar bit */
- data = (i == 1) ? 0x0 : 0x1;
+ if (intel_crtc->config->lane_count == 1)
+ data = 0x0;
+ else
+ data = (i == 1) ? 0x0 : 0x1;
vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i),
data << DPIO_UPAR_SHIFT);
}
val |= DPIO_TX2_STAGGER_MASK(0x1f);
vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val);
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
- val |= DPIO_TX2_STAGGER_MASK(0x1f);
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
+ if (intel_crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
+ val |= DPIO_TX2_STAGGER_MASK(0x1f);
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
+ }
vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW12(ch),
DPIO_LANESTAGGER_STRAP(stagger) |
DPIO_TX1_STAGGER_MULT(6) |
DPIO_TX2_STAGGER_MULT(0));
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW12(ch),
- DPIO_LANESTAGGER_STRAP(stagger) |
- DPIO_LANESTAGGER_STRAP_OVRD |
- DPIO_TX1_STAGGER_MASK(0x1f) |
- DPIO_TX1_STAGGER_MULT(7) |
- DPIO_TX2_STAGGER_MULT(5));
+ if (intel_crtc->config->lane_count > 2) {
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW12(ch),
+ DPIO_LANESTAGGER_STRAP(stagger) |
+ DPIO_LANESTAGGER_STRAP_OVRD |
+ DPIO_TX1_STAGGER_MASK(0x1f) |
+ DPIO_TX1_STAGGER_MULT(7) |
+ DPIO_TX2_STAGGER_MULT(5));
+ }
+
+ /* Deassert data lane reset */
+ chv_data_lane_soft_reset(encoder, false);
mutex_unlock(&dev_priv->sb_lock);
intel_enable_dp(encoder);
+
+ /* Second common lane will stay alive on its own now */
+ if (dport->release_cl2_override) {
+ chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, false);
+ dport->release_cl2_override = false;
+ }
}
static void chv_dp_pre_pll_enable(struct intel_encoder *encoder)
to_intel_crtc(encoder->base.crtc);
enum dpio_channel ch = vlv_dport_to_channel(dport);
enum pipe pipe = intel_crtc->pipe;
+ unsigned int lane_mask =
+ intel_dp_unused_lane_mask(intel_crtc->config->lane_count);
u32 val;
intel_dp_prepare(encoder);
+ /*
+ * Must trick the second common lane into life.
+ * Otherwise we can't even access the PLL.
+ */
+ if (ch == DPIO_CH0 && pipe == PIPE_B)
+ dport->release_cl2_override =
+ !chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, true);
+
+ chv_phy_powergate_lanes(encoder, true, lane_mask);
+
mutex_lock(&dev_priv->sb_lock);
+ /* Assert data lane reset */
+ chv_data_lane_soft_reset(encoder, true);
+
/* program left/right clock distribution */
if (pipe != PIPE_B) {
val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
val |= CHV_PCS_USEDCLKCHANNEL;
vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW8(ch), val);
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch));
- val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
- if (pipe != PIPE_B)
- val &= ~CHV_PCS_USEDCLKCHANNEL;
- else
- val |= CHV_PCS_USEDCLKCHANNEL;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val);
+ if (intel_crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch));
+ val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
+ if (pipe != PIPE_B)
+ val &= ~CHV_PCS_USEDCLKCHANNEL;
+ else
+ val |= CHV_PCS_USEDCLKCHANNEL;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val);
+ }
/*
* This a a bit weird since generally CL
mutex_unlock(&dev_priv->sb_lock);
}
+static void chv_dp_post_pll_disable(struct intel_encoder *encoder)
+{
+ struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+ enum pipe pipe = to_intel_crtc(encoder->base.crtc)->pipe;
+ u32 val;
+
+ mutex_lock(&dev_priv->sb_lock);
+
+ /* disable left/right clock distribution */
+ if (pipe != PIPE_B) {
+ val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
+ val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
+ vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
+ } else {
+ val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
+ val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
+ vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
+ }
+
+ mutex_unlock(&dev_priv->sb_lock);
+
+ /*
+ * Leave the power down bit cleared for at least one
+ * lane so that chv_powergate_phy_ch() will power
+ * on something when the channel is otherwise unused.
+ * When the port is off and the override is removed
+ * the lanes power down anyway, so otherwise it doesn't
+ * really matter what the state of power down bits is
+ * after this.
+ */
+ chv_phy_powergate_lanes(encoder, false, 0x0);
+}
+
/*
* Native read with retry for link status and receiver capability reads for
* cases where the sink may still be asleep.
return 0;
}
+static bool chv_need_uniq_trans_scale(uint8_t train_set)
+{
+ return (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) == DP_TRAIN_PRE_EMPH_LEVEL_0 &&
+ (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) == DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
+}
+
static uint32_t chv_signal_levels(struct intel_dp *intel_dp)
{
struct drm_device *dev = intel_dp_to_dev(intel_dp);
val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5;
vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
- val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
- val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK);
- val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+ if (intel_crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
+ val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
+ val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK);
+ val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+ }
val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW9(ch));
val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK);
val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000;
vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW9(ch), val);
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW9(ch));
- val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK);
- val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW9(ch), val);
+ if (intel_crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW9(ch));
+ val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK);
+ val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW9(ch), val);
+ }
/* Program swing deemph */
- for (i = 0; i < 4; i++) {
+ for (i = 0; i < intel_crtc->config->lane_count; i++) {
val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i));
val &= ~DPIO_SWING_DEEMPH9P5_MASK;
val |= deemph_reg_value << DPIO_SWING_DEEMPH9P5_SHIFT;
}
/* Program swing margin */
- for (i = 0; i < 4; i++) {
+ for (i = 0; i < intel_crtc->config->lane_count; i++) {
val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
+
val &= ~DPIO_SWING_MARGIN000_MASK;
val |= margin_reg_value << DPIO_SWING_MARGIN000_SHIFT;
+
+ /*
+ * Supposedly this value shouldn't matter when unique transition
+ * scale is disabled, but in fact it does matter. Let's just
+ * always program the same value and hope it's OK.
+ */
+ val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT);
+ val |= 0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT;
+
vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
}
- /* Disable unique transition scale */
- for (i = 0; i < 4; i++) {
+ /*
+ * The document said it needs to set bit 27 for ch0 and bit 26
+ * for ch1. Might be a typo in the doc.
+ * For now, for this unique transition scale selection, set bit
+ * 27 for ch0 and ch1.
+ */
+ for (i = 0; i < intel_crtc->config->lane_count; i++) {
val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i));
- val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN;
- vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
- }
-
- if (((train_set & DP_TRAIN_PRE_EMPHASIS_MASK)
- == DP_TRAIN_PRE_EMPH_LEVEL_0) &&
- ((train_set & DP_TRAIN_VOLTAGE_SWING_MASK)
- == DP_TRAIN_VOLTAGE_SWING_LEVEL_3)) {
-
- /*
- * The document said it needs to set bit 27 for ch0 and bit 26
- * for ch1. Might be a typo in the doc.
- * For now, for this unique transition scale selection, set bit
- * 27 for ch0 and ch1.
- */
- for (i = 0; i < 4; i++) {
- val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i));
+ if (chv_need_uniq_trans_scale(train_set))
val |= DPIO_TX_UNIQ_TRANS_SCALE_EN;
- vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
- }
-
- for (i = 0; i < 4; i++) {
- val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
- val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT);
- val |= (0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT);
- vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
- }
+ else
+ val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN;
+ vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
}
/* Start swing calculation */
val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
- val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+ if (intel_crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
+ val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+ }
/* LRC Bypass */
val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30);
uint8_t dp_train_pat)
{
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;
+ struct drm_i915_private *dev_priv =
+ to_i915(intel_dig_port->base.base.dev);
uint8_t buf[sizeof(intel_dp->train_set) + 1];
int ret, len;
const uint8_t link_status[DP_LINK_STATUS_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;
+ struct drm_i915_private *dev_priv =
+ to_i915(intel_dig_port->base.base.dev);
int ret;
intel_get_adjust_train(intel_dp, link_status);
int voltage_tries, loop_tries;
uint32_t DP = intel_dp->DP;
uint8_t link_config[2];
+ uint8_t link_bw, rate_select;
if (HAS_DDI(dev))
intel_ddi_prepare_link_retrain(encoder);
+ intel_dp_compute_rate(intel_dp, intel_dp->link_rate,
+ &link_bw, &rate_select);
+
/* Write the link configuration data */
- link_config[0] = intel_dp->link_bw;
+ link_config[0] = link_bw;
link_config[1] = intel_dp->lane_count;
if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2);
if (intel_dp->num_sink_rates)
drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET,
- &intel_dp->rate_select, 1);
+ &rate_select, 1);
link_config[0] = 0;
link_config[1] = DP_SET_ANSI_8B10B;
void
intel_dp_complete_link_train(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;
bool channel_eq = false;
int tries, cr_tries;
uint32_t DP = intel_dp->DP;
uint32_t training_pattern = DP_TRAINING_PATTERN_2;
- /* Training Pattern 3 for HBR2 ot 1.2 devices that support it*/
- if (intel_dp->link_bw == DP_LINK_BW_5_4 || intel_dp->use_tps3)
+ /*
+ * Training Pattern 3 for HBR2 or 1.2 devices that support it.
+ *
+ * Intel platforms that support HBR2 also support TPS3. TPS3 support is
+ * also mandatory for downstream devices that support HBR2.
+ *
+ * Due to WaDisableHBR2 SKL < B0 is the only exception where TPS3 is
+ * supported but still not enabled.
+ */
+ if (intel_dp_source_supports_hbr2(dev) &&
+ drm_dp_tps3_supported(intel_dp->dpcd))
training_pattern = DP_TRAINING_PATTERN_3;
+ else if (intel_dp->link_rate == 540000)
+ DRM_ERROR("5.4 Gbps link rate without HBR2/TPS3 support\n");
/* channel equalization */
if (!intel_dp_set_link_train(intel_dp, &DP,
}
/* Make sure clock is still ok */
- if (!drm_dp_clock_recovery_ok(link_status, intel_dp->lane_count)) {
+ if (!drm_dp_clock_recovery_ok(link_status,
+ intel_dp->lane_count)) {
intel_dp->train_set_valid = false;
intel_dp_start_link_train(intel_dp);
intel_dp_set_link_train(intel_dp, &DP,
continue;
}
- if (drm_dp_channel_eq_ok(link_status, intel_dp->lane_count)) {
+ if (drm_dp_channel_eq_ok(link_status,
+ intel_dp->lane_count)) {
channel_eq = true;
break;
}
}
}
- /* Training Pattern 3 support, Intel platforms that support HBR2 alone
- * have support for TP3 hence that check is used along with dpcd check
- * to ensure TP3 can be enabled.
- * SKL < B0: due it's WaDisableHBR2 is the only exception where TP3 is
- * supported but still not enabled.
- */
- if (intel_dp->dpcd[DP_DPCD_REV] >= 0x12 &&
- intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED &&
- intel_dp_source_supports_hbr2(dev)) {
- intel_dp->use_tps3 = true;
- DRM_DEBUG_KMS("Displayport TPS3 supported\n");
- } else
- intel_dp->use_tps3 = false;
+ DRM_DEBUG_KMS("Display Port TPS3 support: source %s, sink %s\n",
+ yesno(intel_dp_source_supports_hbr2(dev)),
+ yesno(drm_dp_tps3_supported(intel_dp->dpcd)));
/* Intermediate frequency support */
if (is_edp(intel_dp) &&
return intel_dp->is_mst;
}
-static void intel_dp_sink_crc_stop(struct intel_dp *intel_dp)
+static int intel_dp_sink_crc_stop(struct intel_dp *intel_dp)
{
struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
struct intel_crtc *intel_crtc = to_intel_crtc(dig_port->base.base.crtc);
u8 buf;
+ int ret = 0;
if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0) {
DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n");
- return;
+ ret = -EIO;
+ goto out;
}
if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
- buf & ~DP_TEST_SINK_START) < 0)
+ buf & ~DP_TEST_SINK_START) < 0) {
DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n");
+ ret = -EIO;
+ goto out;
+ }
+ intel_dp->sink_crc.started = false;
+ out:
hsw_enable_ips(intel_crtc);
+ return ret;
}
static int intel_dp_sink_crc_start(struct intel_dp *intel_dp)
struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
struct intel_crtc *intel_crtc = to_intel_crtc(dig_port->base.base.crtc);
u8 buf;
+ int ret;
+
+ if (intel_dp->sink_crc.started) {
+ ret = intel_dp_sink_crc_stop(intel_dp);
+ if (ret)
+ return ret;
+ }
if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0)
return -EIO;
if (!(buf & DP_TEST_CRC_SUPPORTED))
return -ENOTTY;
+ intel_dp->sink_crc.last_count = buf & DP_TEST_COUNT_MASK;
+
if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0)
return -EIO;
return -EIO;
}
+ intel_dp->sink_crc.started = true;
return 0;
}
struct drm_device *dev = dig_port->base.base.dev;
struct intel_crtc *intel_crtc = to_intel_crtc(dig_port->base.base.crtc);
u8 buf;
- int test_crc_count;
+ int count, ret;
int attempts = 6;
- int ret;
+ bool old_equal_new;
ret = intel_dp_sink_crc_start(intel_dp);
if (ret)
return ret;
- if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0) {
- ret = -EIO;
- goto stop;
- }
-
- test_crc_count = buf & DP_TEST_COUNT_MASK;
-
do {
+ intel_wait_for_vblank(dev, intel_crtc->pipe);
+
if (drm_dp_dpcd_readb(&intel_dp->aux,
DP_TEST_SINK_MISC, &buf) < 0) {
ret = -EIO;
goto stop;
}
- intel_wait_for_vblank(dev, intel_crtc->pipe);
- } while (--attempts && (buf & DP_TEST_COUNT_MASK) == test_crc_count);
+ count = buf & DP_TEST_COUNT_MASK;
+
+ /*
+ * Count might be reset during the loop. In this case
+ * last known count needs to be reset as well.
+ */
+ if (count == 0)
+ intel_dp->sink_crc.last_count = 0;
+
+ if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0) {
+ ret = -EIO;
+ goto stop;
+ }
+
+ old_equal_new = (count == intel_dp->sink_crc.last_count &&
+ !memcmp(intel_dp->sink_crc.last_crc, crc,
+ 6 * sizeof(u8)));
+
+ } while (--attempts && (count == 0 || old_equal_new));
+
+ intel_dp->sink_crc.last_count = buf & DP_TEST_COUNT_MASK;
+ memcpy(intel_dp->sink_crc.last_crc, crc, 6 * sizeof(u8));
if (attempts == 0) {
- DRM_DEBUG_KMS("Panel is unable to calculate CRC after 6 vblanks\n");
- ret = -ETIMEDOUT;
- goto stop;
+ if (old_equal_new) {
+ DRM_DEBUG_KMS("Unreliable Sink CRC counter: Current returned CRC is identical to the previous one\n");
+ } else {
+ DRM_ERROR("Panel is unable to calculate any CRC after 6 vblanks\n");
+ ret = -ETIMEDOUT;
+ goto stop;
+ }
}
- if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0)
- ret = -EIO;
stop:
intel_dp_sink_crc_stop(intel_dp);
return ret;
if (bret == true) {
/* check link status - esi[10] = 0x200c */
- if (intel_dp->active_mst_links && !drm_dp_channel_eq_ok(&esi[10], intel_dp->lane_count)) {
+ if (intel_dp->active_mst_links &&
+ !drm_dp_channel_eq_ok(&esi[10], intel_dp->lane_count)) {
DRM_DEBUG_KMS("channel EQ not ok, retraining\n");
intel_dp_start_link_train(intel_dp);
intel_dp_complete_link_train(intel_dp);
return status;
}
-static enum drm_connector_status
-ironlake_dp_detect(struct intel_dp *intel_dp)
+static bool ibx_digital_port_connected(struct drm_i915_private *dev_priv,
+ struct intel_digital_port *port)
{
- struct drm_device *dev = intel_dp_to_dev(intel_dp);
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+ u32 bit;
- if (!ibx_digital_port_connected(dev_priv, intel_dig_port))
- return connector_status_disconnected;
+ switch (port->port) {
+ case PORT_A:
+ return true;
+ case PORT_B:
+ bit = SDE_PORTB_HOTPLUG;
+ break;
+ case PORT_C:
+ bit = SDE_PORTC_HOTPLUG;
+ break;
+ case PORT_D:
+ bit = SDE_PORTD_HOTPLUG;
+ break;
+ default:
+ MISSING_CASE(port->port);
+ return false;
+ }
- return intel_dp_detect_dpcd(intel_dp);
+ return I915_READ(SDEISR) & bit;
+}
+
+static bool cpt_digital_port_connected(struct drm_i915_private *dev_priv,
+ struct intel_digital_port *port)
+{
+ u32 bit;
+
+ switch (port->port) {
+ case PORT_A:
+ return true;
+ case PORT_B:
+ bit = SDE_PORTB_HOTPLUG_CPT;
+ break;
+ case PORT_C:
+ bit = SDE_PORTC_HOTPLUG_CPT;
+ break;
+ case PORT_D:
+ bit = SDE_PORTD_HOTPLUG_CPT;
+ break;
+ case PORT_E:
+ bit = SDE_PORTE_HOTPLUG_SPT;
+ break;
+ default:
+ MISSING_CASE(port->port);
+ return false;
+ }
+
+ return I915_READ(SDEISR) & bit;
}
-static int g4x_digital_port_connected(struct drm_device *dev,
+static bool g4x_digital_port_connected(struct drm_i915_private *dev_priv,
+ struct intel_digital_port *port)
+{
+ u32 bit;
+
+ switch (port->port) {
+ case PORT_B:
+ bit = PORTB_HOTPLUG_LIVE_STATUS_G4X;
+ break;
+ case PORT_C:
+ bit = PORTC_HOTPLUG_LIVE_STATUS_G4X;
+ break;
+ case PORT_D:
+ bit = PORTD_HOTPLUG_LIVE_STATUS_G4X;
+ break;
+ default:
+ MISSING_CASE(port->port);
+ return false;
+ }
+
+ return I915_READ(PORT_HOTPLUG_STAT) & bit;
+}
+
+static bool vlv_digital_port_connected(struct drm_i915_private *dev_priv,
+ struct intel_digital_port *port)
+{
+ u32 bit;
+
+ switch (port->port) {
+ case PORT_B:
+ bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
+ break;
+ case PORT_C:
+ bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
+ break;
+ case PORT_D:
+ bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
+ break;
+ default:
+ MISSING_CASE(port->port);
+ return false;
+ }
+
+ return I915_READ(PORT_HOTPLUG_STAT) & bit;
+}
+
+static bool bxt_digital_port_connected(struct drm_i915_private *dev_priv,
struct intel_digital_port *intel_dig_port)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
- uint32_t bit;
+ struct intel_encoder *intel_encoder = &intel_dig_port->base;
+ enum port port;
+ u32 bit;
- if (IS_VALLEYVIEW(dev)) {
- switch (intel_dig_port->port) {
- case PORT_B:
- bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
- break;
- case PORT_C:
- bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
- break;
- case PORT_D:
- bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
- break;
- default:
- return -EINVAL;
- }
- } else {
- switch (intel_dig_port->port) {
- case PORT_B:
- bit = PORTB_HOTPLUG_LIVE_STATUS_G4X;
- break;
- case PORT_C:
- bit = PORTC_HOTPLUG_LIVE_STATUS_G4X;
- break;
- case PORT_D:
- bit = PORTD_HOTPLUG_LIVE_STATUS_G4X;
- break;
- default:
- return -EINVAL;
- }
+ intel_hpd_pin_to_port(intel_encoder->hpd_pin, &port);
+ switch (port) {
+ case PORT_A:
+ bit = BXT_DE_PORT_HP_DDIA;
+ break;
+ case PORT_B:
+ bit = BXT_DE_PORT_HP_DDIB;
+ break;
+ case PORT_C:
+ bit = BXT_DE_PORT_HP_DDIC;
+ break;
+ default:
+ MISSING_CASE(port);
+ return false;
}
- if ((I915_READ(PORT_HOTPLUG_STAT) & bit) == 0)
- return 0;
- return 1;
+ return I915_READ(GEN8_DE_PORT_ISR) & bit;
+}
+
+/*
+ * intel_digital_port_connected - is the specified port connected?
+ * @dev_priv: i915 private structure
+ * @port: the port to test
+ *
+ * Return %true if @port is connected, %false otherwise.
+ */
+bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
+ struct intel_digital_port *port)
+{
+ if (HAS_PCH_IBX(dev_priv))
+ return ibx_digital_port_connected(dev_priv, port);
+ if (HAS_PCH_SPLIT(dev_priv))
+ return cpt_digital_port_connected(dev_priv, port);
+ else if (IS_BROXTON(dev_priv))
+ return bxt_digital_port_connected(dev_priv, port);
+ else if (IS_VALLEYVIEW(dev_priv))
+ return vlv_digital_port_connected(dev_priv, port);
+ else
+ return g4x_digital_port_connected(dev_priv, port);
+}
+
+static enum drm_connector_status
+ironlake_dp_detect(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 intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+
+ if (!intel_digital_port_connected(dev_priv, intel_dig_port))
+ return connector_status_disconnected;
+
+ return intel_dp_detect_dpcd(intel_dp);
}
static enum drm_connector_status
{
struct drm_device *dev = intel_dp_to_dev(intel_dp);
struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
- int ret;
/* Can't disconnect eDP, but you can close the lid... */
if (is_edp(intel_dp)) {
return status;
}
- ret = g4x_digital_port_connected(dev, intel_dig_port);
- if (ret == -EINVAL)
- return connector_status_unknown;
- else if (ret == 0)
+ if (!intel_digital_port_connected(dev->dev_private, intel_dig_port))
return connector_status_disconnected;
return intel_dp_detect_dpcd(intel_dp);
if (property == dev_priv->broadcast_rgb_property) {
bool old_auto = intel_dp->color_range_auto;
- uint32_t old_range = intel_dp->color_range;
+ bool old_range = intel_dp->limited_color_range;
switch (val) {
case INTEL_BROADCAST_RGB_AUTO:
break;
case INTEL_BROADCAST_RGB_FULL:
intel_dp->color_range_auto = false;
- intel_dp->color_range = 0;
+ intel_dp->limited_color_range = false;
break;
case INTEL_BROADCAST_RGB_LIMITED:
intel_dp->color_range_auto = false;
- intel_dp->color_range = DP_COLOR_RANGE_16_235;
+ intel_dp->limited_color_range = true;
break;
default:
return -EINVAL;
}
if (old_auto == intel_dp->color_range_auto &&
- old_range == intel_dp->color_range)
+ old_range == intel_dp->limited_color_range)
return 0;
goto done;
/* indicate that we need to restart link training */
intel_dp->train_set_valid = false;
- if (HAS_PCH_SPLIT(dev)) {
- if (!ibx_digital_port_connected(dev_priv, intel_dig_port))
- goto mst_fail;
- } else {
- if (g4x_digital_port_connected(dev, intel_dig_port) != 1)
- goto mst_fail;
- }
+ if (!intel_digital_port_connected(dev_priv, intel_dig_port))
+ goto mst_fail;
if (!intel_dp_get_dpcd(intel_dp)) {
goto mst_fail;
[PORT_E] = DVO_PORT_DPE,
};
+ /*
+ * eDP not supported on g4x. so bail out early just
+ * for a bit extra safety in case the VBT is bonkers.
+ */
+ if (INTEL_INFO(dev)->gen < 5)
+ return false;
+
if (port == PORT_A)
return true;
break;
case PORT_B:
intel_encoder->hpd_pin = HPD_PORT_B;
+ if (IS_BROXTON(dev_priv) && (INTEL_REVID(dev) < BXT_REVID_B0))
+ intel_encoder->hpd_pin = HPD_PORT_A;
break;
case PORT_C:
intel_encoder->hpd_pin = HPD_PORT_C;
intel_encoder->pre_enable = chv_pre_enable_dp;
intel_encoder->enable = vlv_enable_dp;
intel_encoder->post_disable = chv_post_disable_dp;
+ intel_encoder->post_pll_disable = chv_dp_post_pll_disable;
} else if (IS_VALLEYVIEW(dev)) {
intel_encoder->pre_pll_enable = vlv_dp_pre_pll_enable;
intel_encoder->pre_enable = vlv_pre_enable_dp;
struct intel_dp *intel_dp = &intel_dig_port->dp;
struct drm_atomic_state *state;
int bpp, i;
- int lane_count, slots, rate;
+ int lane_count, slots;
struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
struct drm_connector *drm_connector;
struct intel_connector *connector, *found = NULL;
*/
lane_count = drm_dp_max_lane_count(intel_dp->dpcd);
- rate = intel_dp_max_link_rate(intel_dp);
- if (intel_dp->num_sink_rates) {
- intel_dp->link_bw = 0;
- intel_dp->rate_select = intel_dp_rate_select(intel_dp, rate);
- } else {
- intel_dp->link_bw = drm_dp_link_rate_to_bw_code(rate);
- intel_dp->rate_select = 0;
- }
-
- intel_dp->lane_count = lane_count;
+ pipe_config->lane_count = lane_count;
pipe_config->pipe_bpp = 24;
- pipe_config->port_clock = rate;
+ pipe_config->port_clock = intel_dp_max_link_rate(intel_dp);
state = pipe_config->base.state;
if (intel_dp->active_mst_links == 0) {
enum port port = intel_ddi_get_encoder_port(encoder);
+ intel_dp_set_link_params(intel_dp, intel_crtc->config);
+
/* FIXME: add support for SKL */
if (INTEL_INFO(dev)->gen < 9)
I915_WRITE(PORT_CLK_SEL(port),
break;
}
pipe_config->base.adjusted_mode.flags |= flags;
+
+ pipe_config->lane_count =
+ ((temp & DDI_PORT_WIDTH_MASK) >> DDI_PORT_WIDTH_SHIFT) + 1;
+
intel_dp_get_m_n(crtc, pipe_config);
intel_ddi_clock_get(&intel_dig_port->base, pipe_config);
void (*mode_set)(struct intel_encoder *intel_encoder);
void (*disable)(struct intel_encoder *);
void (*post_disable)(struct intel_encoder *);
+ void (*post_pll_disable)(struct intel_encoder *);
/* Read out the current hw state of this connector, returning true if
* the encoder is active. If the encoder is enabled it also set the pipe
* it is connected to in the pipe parameter. */
#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */
unsigned long quirks;
+ bool update_pipe;
+
/* Pipe source size (ie. panel fitter input size)
* All planes will be positioned inside this space,
* and get clipped at the edges. */
/* Used by SDVO (and if we ever fix it, HDMI). */
unsigned pixel_multiplier;
+ uint8_t lane_count;
+
/* Panel fitter controls for gen2-gen4 + VLV */
struct {
u32 control;
* gen4+ this only adjusts up to a tile, offsets within a tile are
* handled in the hw itself (with the TILEOFF register). */
unsigned long dspaddr_offset;
+ int adjusted_x;
+ int adjusted_y;
struct drm_i915_gem_object *cursor_bo;
uint32_t cursor_addr;
int scanline_offset;
- unsigned start_vbl_count;
+ struct {
+ unsigned start_vbl_count;
+ ktime_t start_vbl_time;
+ int min_vbl, max_vbl;
+ int scanline_start;
+ } debug;
+
struct intel_crtc_atomic_commit atomic;
/* scalers available on this crtc */
struct intel_hdmi {
u32 hdmi_reg;
int ddc_bus;
- uint32_t color_range;
+ bool limited_color_range;
bool color_range_auto;
bool has_hdmi_sink;
bool has_audio;
enum hdmi_force_audio force_audio;
bool rgb_quant_range_selectable;
enum hdmi_picture_aspect aspect_ratio;
+ struct intel_connector *attached_connector;
void (*write_infoframe)(struct drm_encoder *encoder,
enum hdmi_infoframe_type type,
const void *frame, ssize_t len);
M2_N2
};
+struct sink_crc {
+ bool started;
+ u8 last_crc[6];
+ int last_count;
+};
+
struct intel_dp {
uint32_t output_reg;
uint32_t aux_ch_ctl_reg;
uint32_t DP;
+ int link_rate;
+ uint8_t lane_count;
bool has_audio;
enum hdmi_force_audio force_audio;
- uint32_t color_range;
+ bool limited_color_range;
bool color_range_auto;
- uint8_t link_bw;
- uint8_t rate_select;
- 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];
/* sink rates as reported by DP_SUPPORTED_LINK_RATES */
uint8_t num_sink_rates;
int sink_rates[DP_MAX_SUPPORTED_RATES];
+ struct sink_crc sink_crc;
struct drm_dp_aux aux;
uint8_t train_set[4];
int panel_power_up_delay;
enum pipe pps_pipe;
struct edp_power_seq pps_delays;
- bool use_tps3;
bool can_mst; /* this port supports mst */
bool is_mst;
int active_mst_links;
struct intel_dp dp;
struct intel_hdmi hdmi;
enum irqreturn (*hpd_pulse)(struct intel_digital_port *, bool);
+ bool release_cl2_override;
};
struct intel_dp_mst_encoder {
void *port; /* store this opaque as its illegal to dereference it */
};
-static inline int
+static inline enum dpio_channel
vlv_dport_to_channel(struct intel_digital_port *dport)
{
switch (dport->port) {
}
}
-static inline int
+static inline enum dpio_phy
+vlv_dport_to_phy(struct intel_digital_port *dport)
+{
+ switch (dport->port) {
+ case PORT_B:
+ case PORT_C:
+ return DPIO_PHY0;
+ case PORT_D:
+ return DPIO_PHY1;
+ default:
+ BUG();
+ }
+}
+
+static inline enum dpio_channel
vlv_pipe_to_channel(enum pipe pipe)
{
switch (pipe) {
extern const struct drm_plane_funcs intel_plane_funcs;
bool intel_has_pending_fb_unpin(struct drm_device *dev);
int intel_pch_rawclk(struct drm_device *dev);
+int intel_hrawclk(struct drm_device *dev);
void intel_mark_busy(struct drm_device *dev);
void intel_mark_idle(struct drm_device *dev);
void intel_crtc_restore_mode(struct drm_crtc *crtc);
int intel_connector_init(struct intel_connector *);
struct intel_connector *intel_connector_alloc(void);
bool intel_connector_get_hw_state(struct intel_connector *connector);
-bool ibx_digital_port_connected(struct drm_i915_private *dev_priv,
- struct intel_digital_port *port);
void intel_connector_attach_encoder(struct intel_connector *connector,
struct intel_encoder *encoder);
struct drm_encoder *intel_best_encoder(struct drm_connector *connector);
unsigned int
intel_tile_height(struct drm_device *dev, uint32_t pixel_format,
- uint64_t fb_format_modifier);
+ uint64_t fb_format_modifier, unsigned int plane);
static inline bool
intel_rotation_90_or_270(unsigned int rotation)
int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state);
unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane,
- struct drm_i915_gem_object *obj);
+ struct drm_i915_gem_object *obj,
+ unsigned int plane);
+
u32 skl_plane_ctl_format(uint32_t pixel_format);
u32 skl_plane_ctl_tiling(uint64_t fb_modifier);
u32 skl_plane_ctl_rotation(unsigned int rotation);
void intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
struct intel_connector *intel_connector);
+void intel_dp_set_link_params(struct intel_dp *intel_dp,
+ const struct intel_crtc_state *pipe_config);
void intel_dp_start_link_train(struct intel_dp *intel_dp);
void intel_dp_complete_link_train(struct intel_dp *intel_dp);
void intel_dp_stop_link_train(struct intel_dp *intel_dp);
void intel_edp_drrs_invalidate(struct drm_device *dev,
unsigned frontbuffer_bits);
void intel_edp_drrs_flush(struct drm_device *dev, unsigned frontbuffer_bits);
+bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
+ struct intel_digital_port *port);
void hsw_dp_set_ddi_pll_sel(struct intel_crtc_state *pipe_config);
/* intel_dp_mst.c */
void intel_display_set_init_power(struct drm_i915_private *dev, bool enable);
+void chv_phy_powergate_lanes(struct intel_encoder *encoder,
+ bool override, unsigned int mask);
+bool chv_phy_powergate_ch(struct drm_i915_private *dev_priv, enum dpio_phy phy,
+ enum dpio_channel ch, bool override);
+
+
/* intel_pm.c */
void intel_init_clock_gating(struct drm_device *dev);
void intel_suspend_hw(struct drm_device *dev);
int intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane);
int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
struct drm_file *file_priv);
-void intel_pipe_update_start(struct intel_crtc *crtc,
- uint32_t *start_vbl_count);
-void intel_pipe_update_end(struct intel_crtc *crtc, u32 start_vbl_count);
+void intel_pipe_update_start(struct intel_crtc *crtc);
+void intel_pipe_update_end(struct intel_crtc *crtc);
/* intel_tv.c */
void intel_tv_init(struct drm_device *dev);
usleep_range(2000, 2500);
}
- vlv_disable_dsi_pll(encoder);
+ intel_disable_dsi_pll(encoder);
}
static void intel_dsi_post_disable(struct intel_encoder *encoder)
{
struct intel_connector *intel_connector = to_intel_connector(connector);
struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
+ int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
DRM_DEBUG_KMS("\n");
return MODE_PANEL;
if (mode->vdisplay > fixed_mode->vdisplay)
return MODE_PANEL;
+ if (fixed_mode->clock > max_dotclk)
+ return MODE_CLOCK_HIGH;
}
return MODE_OK;
hbp = txbyteclkhs(hbp, bpp, lane_count, intel_dsi->burst_mode_ratio);
for_each_dsi_port(port, intel_dsi->ports) {
+ if (IS_BROXTON(dev)) {
+ /*
+ * Program hdisplay and vdisplay on MIPI transcoder.
+ * This is different from calculated hactive and
+ * vactive, as they are calculated per channel basis,
+ * whereas these values should be based on resolution.
+ */
+ I915_WRITE(BXT_MIPI_TRANS_HACTIVE(port),
+ mode->hdisplay);
+ I915_WRITE(BXT_MIPI_TRANS_VACTIVE(port),
+ mode->vdisplay);
+ I915_WRITE(BXT_MIPI_TRANS_VTOTAL(port),
+ mode->vtotal);
+ }
+
I915_WRITE(MIPI_HACTIVE_AREA_COUNT(port), hactive);
I915_WRITE(MIPI_HFP_COUNT(port), hfp);
}
for_each_dsi_port(port, intel_dsi->ports) {
- /* escape clock divider, 20MHz, shared for A and C.
- * device ready must be off when doing this! txclkesc? */
- tmp = I915_READ(MIPI_CTRL(PORT_A));
- tmp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
- I915_WRITE(MIPI_CTRL(PORT_A), tmp | ESCAPE_CLOCK_DIVIDER_1);
-
- /* read request priority is per pipe */
- tmp = I915_READ(MIPI_CTRL(port));
- tmp &= ~READ_REQUEST_PRIORITY_MASK;
- I915_WRITE(MIPI_CTRL(port), tmp | READ_REQUEST_PRIORITY_HIGH);
+ if (IS_VALLEYVIEW(dev)) {
+ /*
+ * escape clock divider, 20MHz, shared for A and C.
+ * device ready must be off when doing this! txclkesc?
+ */
+ tmp = I915_READ(MIPI_CTRL(PORT_A));
+ tmp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
+ I915_WRITE(MIPI_CTRL(PORT_A), tmp |
+ ESCAPE_CLOCK_DIVIDER_1);
+
+ /* read request priority is per pipe */
+ tmp = I915_READ(MIPI_CTRL(port));
+ tmp &= ~READ_REQUEST_PRIORITY_MASK;
+ I915_WRITE(MIPI_CTRL(port), tmp |
+ READ_REQUEST_PRIORITY_HIGH);
+ } else if (IS_BROXTON(dev)) {
+ /*
+ * FIXME:
+ * BXT can connect any PIPE to any MIPI port.
+ * Select the pipe based on the MIPI port read from
+ * VBT for now. Pick PIPE A for MIPI port A and C
+ * for port C.
+ */
+ tmp = I915_READ(MIPI_CTRL(port));
+ tmp &= ~BXT_PIPE_SELECT_MASK;
+
+ if (port == PORT_A)
+ tmp |= BXT_PIPE_SELECT_A;
+ else if (port == PORT_C)
+ tmp |= BXT_PIPE_SELECT_C;
+
+ I915_WRITE(MIPI_CTRL(port), tmp);
+ }
/* XXX: why here, why like this? handling in irq handler?! */
I915_WRITE(MIPI_INTR_STAT(port), 0xffffffff);
I915_WRITE(MIPI_INIT_COUNT(port),
txclkesc(intel_dsi->escape_clk_div, 100));
+ if (IS_BROXTON(dev) && (!intel_dsi->dual_link)) {
+ /*
+ * BXT spec says write MIPI_INIT_COUNT for
+ * both the ports, even if only one is
+ * getting used. So write the other port
+ * if not in dual link mode.
+ */
+ I915_WRITE(MIPI_INIT_COUNT(port ==
+ PORT_A ? PORT_C : PORT_A),
+ intel_dsi->init_count);
+ }
/* recovery disables */
I915_WRITE(MIPI_EOT_DISABLE(port), tmp);
DRM_DEBUG_KMS("\n");
intel_dsi_prepare(encoder);
+ intel_enable_dsi_pll(encoder);
- vlv_enable_dsi_pll(encoder);
}
static enum drm_connector_status
return container_of(encoder, struct intel_dsi, base.base);
}
-extern void vlv_enable_dsi_pll(struct intel_encoder *encoder);
-extern void vlv_disable_dsi_pll(struct intel_encoder *encoder);
+extern void intel_enable_dsi_pll(struct intel_encoder *encoder);
+extern void intel_disable_dsi_pll(struct intel_encoder *encoder);
extern u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp);
struct drm_panel *vbt_panel_init(struct intel_dsi *intel_dsi, u16 panel_id);
vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL, dsi_mnp.dsi_pll_ctrl);
}
-void vlv_enable_dsi_pll(struct intel_encoder *encoder)
+static void vlv_enable_dsi_pll(struct intel_encoder *encoder)
{
struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
u32 tmp;
DRM_DEBUG_KMS("DSI PLL locked\n");
}
-void vlv_disable_dsi_pll(struct intel_encoder *encoder)
+static void vlv_disable_dsi_pll(struct intel_encoder *encoder)
{
struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
u32 tmp;
mutex_unlock(&dev_priv->sb_lock);
}
+static void bxt_disable_dsi_pll(struct intel_encoder *encoder)
+{
+ struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+ u32 val;
+
+ DRM_DEBUG_KMS("\n");
+
+ val = I915_READ(BXT_DSI_PLL_ENABLE);
+ val &= ~BXT_DSI_PLL_DO_ENABLE;
+ I915_WRITE(BXT_DSI_PLL_ENABLE, val);
+
+ /*
+ * PLL lock should deassert within 200us.
+ * Wait up to 1ms before timing out.
+ */
+ if (wait_for((I915_READ(BXT_DSI_PLL_ENABLE)
+ & BXT_DSI_PLL_LOCKED) == 0, 1))
+ DRM_ERROR("Timeout waiting for PLL lock deassertion\n");
+}
+
static void assert_bpp_mismatch(int pixel_format, int pipe_bpp)
{
int bpp = dsi_pixel_format_bpp(pixel_format);
return pclk;
}
+
+static bool bxt_configure_dsi_pll(struct intel_encoder *encoder)
+{
+ struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+ struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+ u8 dsi_ratio;
+ u32 dsi_clk;
+ u32 val;
+
+ dsi_clk = dsi_clk_from_pclk(intel_dsi->pclk, intel_dsi->pixel_format,
+ intel_dsi->lane_count);
+
+ /*
+ * From clock diagram, to get PLL ratio divider, divide double of DSI
+ * link rate (i.e., 2*8x=16x frequency value) by ref clock. Make sure to
+ * round 'up' the result
+ */
+ dsi_ratio = DIV_ROUND_UP(dsi_clk * 2, BXT_REF_CLOCK_KHZ);
+ if (dsi_ratio < BXT_DSI_PLL_RATIO_MIN ||
+ dsi_ratio > BXT_DSI_PLL_RATIO_MAX) {
+ DRM_ERROR("Cant get a suitable ratio from DSI PLL ratios\n");
+ return false;
+ }
+
+ /*
+ * Program DSI ratio and Select MIPIC and MIPIA PLL output as 8x
+ * Spec says both have to be programmed, even if one is not getting
+ * used. Configure MIPI_CLOCK_CTL dividers in modeset
+ */
+ val = I915_READ(BXT_DSI_PLL_CTL);
+ val &= ~BXT_DSI_PLL_PVD_RATIO_MASK;
+ val &= ~BXT_DSI_FREQ_SEL_MASK;
+ val &= ~BXT_DSI_PLL_RATIO_MASK;
+ val |= (dsi_ratio | BXT_DSIA_16X_BY2 | BXT_DSIC_16X_BY2);
+
+ /* As per recommendation from hardware team,
+ * Prog PVD ratio =1 if dsi ratio <= 50
+ */
+ if (dsi_ratio <= 50) {
+ val &= ~BXT_DSI_PLL_PVD_RATIO_MASK;
+ val |= BXT_DSI_PLL_PVD_RATIO_1;
+ }
+
+ I915_WRITE(BXT_DSI_PLL_CTL, val);
+ POSTING_READ(BXT_DSI_PLL_CTL);
+
+ return true;
+}
+
+static void bxt_enable_dsi_pll(struct intel_encoder *encoder)
+{
+ struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+ u32 val;
+
+ DRM_DEBUG_KMS("\n");
+
+ val = I915_READ(BXT_DSI_PLL_ENABLE);
+
+ if (val & BXT_DSI_PLL_DO_ENABLE) {
+ WARN(1, "DSI PLL already enabled. Disabling it.\n");
+ val &= ~BXT_DSI_PLL_DO_ENABLE;
+ I915_WRITE(BXT_DSI_PLL_ENABLE, val);
+ }
+
+ /* Configure PLL vales */
+ if (!bxt_configure_dsi_pll(encoder)) {
+ DRM_ERROR("Configure DSI PLL failed, abort PLL enable\n");
+ return;
+ }
+
+ /* Enable DSI PLL */
+ val = I915_READ(BXT_DSI_PLL_ENABLE);
+ val |= BXT_DSI_PLL_DO_ENABLE;
+ I915_WRITE(BXT_DSI_PLL_ENABLE, val);
+
+ /* Timeout and fail if PLL not locked */
+ if (wait_for(I915_READ(BXT_DSI_PLL_ENABLE) & BXT_DSI_PLL_LOCKED, 1)) {
+ DRM_ERROR("Timed out waiting for DSI PLL to lock\n");
+ return;
+ }
+
+ DRM_DEBUG_KMS("DSI PLL locked\n");
+}
+
+void intel_enable_dsi_pll(struct intel_encoder *encoder)
+{
+ struct drm_device *dev = encoder->base.dev;
+
+ if (IS_VALLEYVIEW(dev))
+ vlv_enable_dsi_pll(encoder);
+ else if (IS_BROXTON(dev))
+ bxt_enable_dsi_pll(encoder);
+}
+
+void intel_disable_dsi_pll(struct intel_encoder *encoder)
+{
+ struct drm_device *dev = encoder->base.dev;
+
+ if (IS_VALLEYVIEW(dev))
+ vlv_disable_dsi_pll(encoder);
+ else if (IS_BROXTON(dev))
+ bxt_disable_dsi_pll(encoder);
+}
struct drm_display_mode *mode)
{
struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
+ int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+ int target_clock = mode->clock;
if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
return MODE_NO_DBLESCAN;
return MODE_PANEL;
if (mode->vdisplay > intel_dvo->panel_fixed_mode->vdisplay)
return MODE_PANEL;
+
+ target_clock = intel_dvo->panel_fixed_mode->clock;
}
+ if (target_clock > max_dotclk)
+ return MODE_CLOCK_HIGH;
+
return intel_dvo->dev.dev_ops->mode_valid(&intel_dvo->dev, mode);
}
#include "intel_drv.h"
#include "i915_drv.h"
+/*
+ * In some platforms where the CRTC's x:0/y:0 coordinates doesn't match the
+ * frontbuffer's x:0/y:0 coordinates we lie to the hardware about the plane's
+ * origin so the x and y offsets can actually fit the registers. As a
+ * consequence, the fence doesn't really start exactly at the display plane
+ * address we program because it starts at the real start of the buffer, so we
+ * have to take this into consideration here.
+ */
+static unsigned int get_crtc_fence_y_offset(struct intel_crtc *crtc)
+{
+ return crtc->base.y - crtc->adjusted_y;
+}
+
static void i8xx_fbc_disable(struct drm_i915_private *dev_priv)
{
u32 fbc_ctl;
/* Clear old tags */
for (i = 0; i < (FBC_LL_SIZE / 32) + 1; i++)
- I915_WRITE(FBC_TAG + (i * 4), 0);
+ I915_WRITE(FBC_TAG(i), 0);
if (IS_GEN4(dev_priv)) {
u32 fbc_ctl2;
fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM | FBC_CTL_CPU_FENCE;
fbc_ctl2 |= FBC_CTL_PLANE(crtc->plane);
I915_WRITE(FBC_CONTROL2, fbc_ctl2);
- I915_WRITE(FBC_FENCE_OFF, crtc->base.y);
+ I915_WRITE(FBC_FENCE_OFF, get_crtc_fence_y_offset(crtc));
}
/* enable it... */
dpfc_ctl |= DPFC_CTL_LIMIT_1X;
dpfc_ctl |= DPFC_CTL_FENCE_EN | obj->fence_reg;
- I915_WRITE(DPFC_FENCE_YOFF, crtc->base.y);
+ I915_WRITE(DPFC_FENCE_YOFF, get_crtc_fence_y_offset(crtc));
/* enable it... */
I915_WRITE(DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
struct drm_i915_gem_object *obj = intel_fb_obj(fb);
u32 dpfc_ctl;
int threshold = dev_priv->fbc.threshold;
+ unsigned int y_offset;
dev_priv->fbc.enabled = true;
if (IS_GEN5(dev_priv))
dpfc_ctl |= obj->fence_reg;
- I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->base.y);
+ y_offset = get_crtc_fence_y_offset(crtc);
+ I915_WRITE(ILK_DPFC_FENCE_YOFF, y_offset);
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);
if (IS_GEN6(dev_priv)) {
I915_WRITE(SNB_DPFC_CTL_SA,
SNB_CPU_FENCE_ENABLE | obj->fence_reg);
- I915_WRITE(DPFC_CPU_FENCE_OFFSET, crtc->base.y);
+ I915_WRITE(DPFC_CPU_FENCE_OFFSET, y_offset);
}
intel_fbc_nuke(dev_priv);
if (dev_priv->fbc.false_color)
dpfc_ctl |= FBC_CTL_FALSE_COLOR;
- I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
-
if (IS_IVYBRIDGE(dev_priv)) {
/* WaFbcAsynchFlipDisableFbcQueue:ivb */
I915_WRITE(ILK_DISPLAY_CHICKEN1,
I915_READ(ILK_DISPLAY_CHICKEN1) |
ILK_FBCQ_DIS);
- } else {
+ } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
I915_WRITE(CHICKEN_PIPESL_1(crtc->pipe),
I915_READ(CHICKEN_PIPESL_1(crtc->pipe)) |
HSW_FBCQ_DIS);
}
+ I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
+
I915_WRITE(SNB_DPFC_CTL_SA,
SNB_CPU_FENCE_ENABLE | obj->fence_reg);
- I915_WRITE(DPFC_CPU_FENCE_OFFSET, crtc->base.y);
+ I915_WRITE(DPFC_CPU_FENCE_OFFSET, get_crtc_fence_y_offset(crtc));
intel_fbc_nuke(dev_priv);
return dev_priv->fbc.enabled;
}
+static void intel_fbc_enable(struct intel_crtc *crtc,
+ const struct drm_framebuffer *fb)
+{
+ struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+
+ dev_priv->fbc.enable_fbc(crtc);
+
+ dev_priv->fbc.crtc = crtc;
+ dev_priv->fbc.fb_id = fb->base.id;
+ dev_priv->fbc.y = crtc->base.y;
+}
+
static void intel_fbc_work_fn(struct work_struct *__work)
{
struct intel_fbc_work *work =
/* Double check that we haven't switched fb without cancelling
* the prior work.
*/
- if (crtc_fb == work->fb) {
- dev_priv->fbc.enable_fbc(work->crtc);
-
- dev_priv->fbc.crtc = work->crtc;
- dev_priv->fbc.fb_id = crtc_fb->base.id;
- dev_priv->fbc.y = work->crtc->base.y;
- }
+ if (crtc_fb == work->fb)
+ intel_fbc_enable(work->crtc, work->fb);
dev_priv->fbc.fbc_work = NULL;
}
dev_priv->fbc.fbc_work = NULL;
}
-static void intel_fbc_enable(struct intel_crtc *crtc)
+static void intel_fbc_schedule_enable(struct intel_crtc *crtc)
{
struct intel_fbc_work *work;
struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
work = kzalloc(sizeof(*work), GFP_KERNEL);
if (work == NULL) {
DRM_ERROR("Failed to allocate FBC work structure\n");
- dev_priv->fbc.enable_fbc(crtc);
+ intel_fbc_enable(crtc, crtc->base.primary->fb);
return;
}
return "rotation unsupported";
case FBC_IN_DBG_MASTER:
return "Kernel debugger is active";
+ case FBC_BAD_STRIDE:
+ return "framebuffer stride not supported";
+ case FBC_PIXEL_RATE:
+ return "pixel rate is too big";
+ case FBC_PIXEL_FORMAT:
+ return "pixel format is invalid";
default:
MISSING_CASE(reason);
return "unknown reason";
{
int compression_threshold = 1;
int ret;
+ u64 end;
+
+ /* The FBC hardware for BDW/SKL doesn't have access to the stolen
+ * reserved range size, so it always assumes the maximum (8mb) is used.
+ * If we enable FBC using a CFB on that memory range we'll get FIFO
+ * underruns, even if that range is not reserved by the BIOS. */
+ if (IS_BROADWELL(dev_priv) || IS_SKYLAKE(dev_priv))
+ end = dev_priv->gtt.stolen_size - 8 * 1024 * 1024;
+ else
+ end = dev_priv->gtt.stolen_usable_size;
/* HACK: This code depends on what we will do in *_enable_fbc. If that
* code changes, this code needs to change as well.
*/
/* Try to over-allocate to reduce reallocations and fragmentation. */
- ret = i915_gem_stolen_insert_node(dev_priv, node, size <<= 1, 4096);
+ ret = i915_gem_stolen_insert_node_in_range(dev_priv, node, size <<= 1,
+ 4096, 0, end);
if (ret == 0)
return compression_threshold;
(fb_cpp == 2 && compression_threshold == 2))
return 0;
- ret = i915_gem_stolen_insert_node(dev_priv, node, size >>= 1, 4096);
+ ret = i915_gem_stolen_insert_node_in_range(dev_priv, node, size >>= 1,
+ 4096, 0, end);
if (ret && INTEL_INFO(dev_priv)->gen <= 4) {
return 0;
} else if (ret) {
dev_priv->fbc.uncompressed_size = size;
- DRM_DEBUG_KMS("reserved %d bytes of contiguous stolen space for FBC\n",
- size);
+ DRM_DEBUG_KMS("reserved %llu bytes of contiguous stolen space for FBC, threshold: %d\n",
+ dev_priv->fbc.compressed_fb.size,
+ dev_priv->fbc.threshold);
return 0;
return intel_fbc_alloc_cfb(dev_priv, size, fb_cpp);
}
+static bool stride_is_valid(struct drm_i915_private *dev_priv,
+ unsigned int stride)
+{
+ /* These should have been caught earlier. */
+ WARN_ON(stride < 512);
+ WARN_ON((stride & (64 - 1)) != 0);
+
+ /* Below are the additional FBC restrictions. */
+
+ if (IS_GEN2(dev_priv) || IS_GEN3(dev_priv))
+ return stride == 4096 || stride == 8192;
+
+ if (IS_GEN4(dev_priv) && !IS_G4X(dev_priv) && stride < 2048)
+ return false;
+
+ if (stride > 16384)
+ return false;
+
+ return true;
+}
+
+static bool pixel_format_is_valid(struct drm_framebuffer *fb)
+{
+ struct drm_device *dev = fb->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ switch (fb->pixel_format) {
+ case DRM_FORMAT_XRGB8888:
+ case DRM_FORMAT_XBGR8888:
+ return true;
+ case DRM_FORMAT_XRGB1555:
+ case DRM_FORMAT_RGB565:
+ /* 16bpp not supported on gen2 */
+ if (IS_GEN2(dev))
+ return false;
+ /* WaFbcOnly1to1Ratio:ctg */
+ if (IS_G4X(dev_priv))
+ return false;
+ return true;
+ default:
+ return false;
+ }
+}
+
/**
* __intel_fbc_update - enable/disable FBC as needed, unlocked
* @dev_priv: i915 device instance
goto out_disable;
}
+ if (!stride_is_valid(dev_priv, fb->pitches[0])) {
+ set_no_fbc_reason(dev_priv, FBC_BAD_STRIDE);
+ goto out_disable;
+ }
+
+ if (!pixel_format_is_valid(fb)) {
+ set_no_fbc_reason(dev_priv, FBC_PIXEL_FORMAT);
+ goto out_disable;
+ }
+
/* If the kernel debugger is active, always disable compression */
if (in_dbg_master()) {
set_no_fbc_reason(dev_priv, FBC_IN_DBG_MASTER);
goto out_disable;
}
+ /* WaFbcExceedCdClockThreshold:hsw,bdw */
+ if ((IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) &&
+ ilk_pipe_pixel_rate(intel_crtc->config) >=
+ dev_priv->cdclk_freq * 95 / 100) {
+ set_no_fbc_reason(dev_priv, FBC_PIXEL_RATE);
+ goto out_disable;
+ }
+
if (intel_fbc_setup_cfb(dev_priv, obj->base.size,
drm_format_plane_cpp(fb->pixel_format, 0))) {
set_no_fbc_reason(dev_priv, FBC_STOLEN_TOO_SMALL);
__intel_fbc_disable(dev_priv);
}
- intel_fbc_enable(intel_crtc);
+ intel_fbc_schedule_enable(intel_crtc);
dev_priv->fbc.no_fbc_reason = FBC_OK;
return;
/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
- DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08lx, bo %p\n",
+ DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08llx, bo %p\n",
fb->width, fb->height,
i915_gem_obj_ggtt_offset(obj), obj);
struct intel_crtc *intel_crtc;
unsigned int max_size = 0;
- if (!i915.fastboot)
- return false;
-
/* Find the largest fb */
for_each_crtc(dev, crtc) {
struct drm_i915_gem_object *obj =
intel_fb_obj(crtc->primary->state->fb);
intel_crtc = to_intel_crtc(crtc);
- if (!intel_crtc->active || !obj) {
+ if (!crtc->state->active || !obj) {
DRM_DEBUG_KMS("pipe %c not active or no fb, skipping\n",
pipe_name(intel_crtc->pipe));
continue;
intel_crtc = to_intel_crtc(crtc);
- if (!intel_crtc->active) {
+ if (!crtc->state->active) {
DRM_DEBUG_KMS("pipe %c not active, skipping\n",
pipe_name(intel_crtc->pipe));
continue;
for_each_crtc(dev, crtc) {
intel_crtc = to_intel_crtc(crtc);
- if (!intel_crtc->active)
+ if (!crtc->state->active)
continue;
WARN(!crtc->primary->fb,
--- /dev/null
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+#ifndef _INTEL_GUC_H_
+#define _INTEL_GUC_H_
+
+#include "intel_guc_fwif.h"
+#include "i915_guc_reg.h"
+
+struct i915_guc_client {
+ struct drm_i915_gem_object *client_obj;
+ struct intel_context *owner;
+ struct intel_guc *guc;
+ uint32_t priority;
+ uint32_t ctx_index;
+
+ uint32_t proc_desc_offset;
+ uint32_t doorbell_offset;
+ uint32_t cookie;
+ uint16_t doorbell_id;
+ uint16_t padding; /* Maintain alignment */
+
+ uint32_t wq_offset;
+ uint32_t wq_size;
+
+ spinlock_t wq_lock; /* Protects all data below */
+ uint32_t wq_tail;
+
+ /* GuC submission statistics & status */
+ uint64_t submissions[I915_NUM_RINGS];
+ uint32_t q_fail;
+ uint32_t b_fail;
+ int retcode;
+};
+
+enum intel_guc_fw_status {
+ GUC_FIRMWARE_FAIL = -1,
+ GUC_FIRMWARE_NONE = 0,
+ GUC_FIRMWARE_PENDING,
+ GUC_FIRMWARE_SUCCESS
+};
+
+/*
+ * This structure encapsulates all the data needed during the process
+ * of fetching, caching, and loading the firmware image into the GuC.
+ */
+struct intel_guc_fw {
+ struct drm_device * guc_dev;
+ const char * guc_fw_path;
+ size_t guc_fw_size;
+ struct drm_i915_gem_object * guc_fw_obj;
+ enum intel_guc_fw_status guc_fw_fetch_status;
+ enum intel_guc_fw_status guc_fw_load_status;
+
+ uint16_t guc_fw_major_wanted;
+ uint16_t guc_fw_minor_wanted;
+ uint16_t guc_fw_major_found;
+ uint16_t guc_fw_minor_found;
+};
+
+struct intel_guc {
+ struct intel_guc_fw guc_fw;
+
+ uint32_t log_flags;
+ struct drm_i915_gem_object *log_obj;
+
+ struct drm_i915_gem_object *ctx_pool_obj;
+ struct ida ctx_ids;
+
+ struct i915_guc_client *execbuf_client;
+
+ spinlock_t host2guc_lock; /* Protects all data below */
+
+ DECLARE_BITMAP(doorbell_bitmap, GUC_MAX_DOORBELLS);
+ uint32_t db_cacheline; /* Cyclic counter mod pagesize */
+
+ /* Action status & statistics */
+ uint64_t action_count; /* Total commands issued */
+ uint32_t action_cmd; /* Last command word */
+ uint32_t action_status; /* Last return status */
+ uint32_t action_fail; /* Total number of failures */
+ int32_t action_err; /* Last error code */
+
+ uint64_t submissions[I915_NUM_RINGS];
+ uint32_t last_seqno[I915_NUM_RINGS];
+};
+
+/* intel_guc_loader.c */
+extern void intel_guc_ucode_init(struct drm_device *dev);
+extern int intel_guc_ucode_load(struct drm_device *dev);
+extern void intel_guc_ucode_fini(struct drm_device *dev);
+extern const char *intel_guc_fw_status_repr(enum intel_guc_fw_status status);
+
+/* i915_guc_submission.c */
+int i915_guc_submission_init(struct drm_device *dev);
+int i915_guc_submission_enable(struct drm_device *dev);
+int i915_guc_submit(struct i915_guc_client *client,
+ struct drm_i915_gem_request *rq);
+void i915_guc_submission_disable(struct drm_device *dev);
+void i915_guc_submission_fini(struct drm_device *dev);
+
+#endif
* EDITING THIS FILE IS THEREFORE NOT RECOMMENDED - YOUR CHANGES MAY BE LOST.
*/
-#define GFXCORE_FAMILY_GEN8 11
#define GFXCORE_FAMILY_GEN9 12
-#define GFXCORE_FAMILY_FORCE_ULONG 0x7fffffff
+#define GFXCORE_FAMILY_UNKNOWN 0x7fffffff
-#define GUC_CTX_PRIORITY_CRITICAL 0
+#define GUC_CTX_PRIORITY_KMD_HIGH 0
#define GUC_CTX_PRIORITY_HIGH 1
-#define GUC_CTX_PRIORITY_NORMAL 2
-#define GUC_CTX_PRIORITY_LOW 3
+#define GUC_CTX_PRIORITY_KMD_NORMAL 2
+#define GUC_CTX_PRIORITY_NORMAL 3
#define GUC_MAX_GPU_CONTEXTS 1024
-#define GUC_INVALID_CTX_ID (GUC_MAX_GPU_CONTEXTS + 1)
+#define GUC_INVALID_CTX_ID GUC_MAX_GPU_CONTEXTS
/* Work queue item header definitions */
#define WQ_STATUS_ACTIVE 1
#define GUC_CTX_DESC_ATTR_RESET (1 << 4)
#define GUC_CTX_DESC_ATTR_WQLOCKED (1 << 5)
#define GUC_CTX_DESC_ATTR_PCH (1 << 6)
+#define GUC_CTX_DESC_ATTR_TERMINATED (1 << 7)
/* The guc control data is 10 DWORDs */
#define GUC_CTL_CTXINFO 0
#define GUC_CTL_DISABLE_SCHEDULER (1 << 4)
#define GUC_CTL_PREEMPTION_LOG (1 << 5)
#define GUC_CTL_ENABLE_SLPC (1 << 7)
+#define GUC_CTL_RESET_ON_PREMPT_FAILURE (1 << 8)
#define GUC_CTL_DEBUG 8
#define GUC_LOG_VERBOSITY_SHIFT 0
#define GUC_LOG_VERBOSITY_LOW (0 << GUC_LOG_VERBOSITY_SHIFT)
/* Verbosity range-check limits, without the shift */
#define GUC_LOG_VERBOSITY_MIN 0
#define GUC_LOG_VERBOSITY_MAX 3
+#define GUC_CTL_RSRVD 9
-#define GUC_CTL_MAX_DWORDS (GUC_CTL_DEBUG + 1)
+#define GUC_CTL_MAX_DWORDS (GUC_CTL_RSRVD + 1)
struct guc_doorbell_info {
u32 db_status;
u32 engine_presence;
- u32 reserved0[1];
+ u8 engine_suspended;
+
+ u8 reserved0[3];
u64 reserved1[1];
u64 desc_private;
--- /dev/null
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ * Vinit Azad <vinit.azad@intel.com>
+ * Ben Widawsky <ben@bwidawsk.net>
+ * Dave Gordon <david.s.gordon@intel.com>
+ * Alex Dai <yu.dai@intel.com>
+ */
+#include <linux/firmware.h>
+#include "i915_drv.h"
+#include "intel_guc.h"
+
+/**
+ * DOC: GuC
+ *
+ * intel_guc:
+ * Top level structure of guc. It handles firmware loading and manages client
+ * pool and doorbells. intel_guc owns a i915_guc_client to replace the legacy
+ * ExecList submission.
+ *
+ * Firmware versioning:
+ * The firmware build process will generate a version header file with major and
+ * minor version defined. The versions are built into CSS header of firmware.
+ * i915 kernel driver set the minimal firmware version required per platform.
+ * The firmware installation package will install (symbolic link) proper version
+ * of firmware.
+ *
+ * GuC address space:
+ * GuC does not allow any gfx GGTT address that falls into range [0, WOPCM_TOP),
+ * which is reserved for Boot ROM, SRAM and WOPCM. Currently this top address is
+ * 512K. In order to exclude 0-512K address space from GGTT, all gfx objects
+ * used by GuC is pinned with PIN_OFFSET_BIAS along with size of WOPCM.
+ *
+ * Firmware log:
+ * Firmware log is enabled by setting i915.guc_log_level to non-negative level.
+ * Log data is printed out via reading debugfs i915_guc_log_dump. Reading from
+ * i915_guc_load_status will print out firmware loading status and scratch
+ * registers value.
+ *
+ */
+
+#define I915_SKL_GUC_UCODE "i915/skl_guc_ver4.bin"
+MODULE_FIRMWARE(I915_SKL_GUC_UCODE);
+
+/* User-friendly representation of an enum */
+const char *intel_guc_fw_status_repr(enum intel_guc_fw_status status)
+{
+ switch (status) {
+ case GUC_FIRMWARE_FAIL:
+ return "FAIL";
+ case GUC_FIRMWARE_NONE:
+ return "NONE";
+ case GUC_FIRMWARE_PENDING:
+ return "PENDING";
+ case GUC_FIRMWARE_SUCCESS:
+ return "SUCCESS";
+ default:
+ return "UNKNOWN!";
+ }
+};
+
+static void direct_interrupts_to_host(struct drm_i915_private *dev_priv)
+{
+ struct intel_engine_cs *ring;
+ int i, irqs;
+
+ /* tell all command streamers NOT to forward interrupts and vblank to GuC */
+ irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_NEVER);
+ irqs |= _MASKED_BIT_DISABLE(GFX_INTERRUPT_STEERING);
+ for_each_ring(ring, dev_priv, i)
+ I915_WRITE(RING_MODE_GEN7(ring), irqs);
+
+ /* tell DE to send nothing to GuC */
+ I915_WRITE(DE_GUCRMR, ~0);
+
+ /* route all GT interrupts to the host */
+ I915_WRITE(GUC_BCS_RCS_IER, 0);
+ I915_WRITE(GUC_VCS2_VCS1_IER, 0);
+ I915_WRITE(GUC_WD_VECS_IER, 0);
+}
+
+static void direct_interrupts_to_guc(struct drm_i915_private *dev_priv)
+{
+ struct intel_engine_cs *ring;
+ int i, irqs;
+
+ /* tell all command streamers to forward interrupts and vblank to GuC */
+ irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_ALWAYS);
+ irqs |= _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
+ for_each_ring(ring, dev_priv, i)
+ I915_WRITE(RING_MODE_GEN7(ring), irqs);
+
+ /* tell DE to send (all) flip_done to GuC */
+ irqs = DERRMR_PIPEA_PRI_FLIP_DONE | DERRMR_PIPEA_SPR_FLIP_DONE |
+ DERRMR_PIPEB_PRI_FLIP_DONE | DERRMR_PIPEB_SPR_FLIP_DONE |
+ DERRMR_PIPEC_PRI_FLIP_DONE | DERRMR_PIPEC_SPR_FLIP_DONE;
+ /* Unmasked bits will cause GuC response message to be sent */
+ I915_WRITE(DE_GUCRMR, ~irqs);
+
+ /* route USER_INTERRUPT to Host, all others are sent to GuC. */
+ irqs = GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
+ GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
+ /* These three registers have the same bit definitions */
+ I915_WRITE(GUC_BCS_RCS_IER, ~irqs);
+ I915_WRITE(GUC_VCS2_VCS1_IER, ~irqs);
+ I915_WRITE(GUC_WD_VECS_IER, ~irqs);
+}
+
+static u32 get_gttype(struct drm_i915_private *dev_priv)
+{
+ /* XXX: GT type based on PCI device ID? field seems unused by fw */
+ return 0;
+}
+
+static u32 get_core_family(struct drm_i915_private *dev_priv)
+{
+ switch (INTEL_INFO(dev_priv)->gen) {
+ case 9:
+ return GFXCORE_FAMILY_GEN9;
+
+ default:
+ DRM_ERROR("GUC: unsupported core family\n");
+ return GFXCORE_FAMILY_UNKNOWN;
+ }
+}
+
+static void set_guc_init_params(struct drm_i915_private *dev_priv)
+{
+ struct intel_guc *guc = &dev_priv->guc;
+ u32 params[GUC_CTL_MAX_DWORDS];
+ int i;
+
+ memset(¶ms, 0, sizeof(params));
+
+ params[GUC_CTL_DEVICE_INFO] |=
+ (get_gttype(dev_priv) << GUC_CTL_GTTYPE_SHIFT) |
+ (get_core_family(dev_priv) << GUC_CTL_COREFAMILY_SHIFT);
+
+ /*
+ * GuC ARAT increment is 10 ns. GuC default scheduler quantum is one
+ * second. This ARAR is calculated by:
+ * Scheduler-Quantum-in-ns / ARAT-increment-in-ns = 1000000000 / 10
+ */
+ params[GUC_CTL_ARAT_HIGH] = 0;
+ params[GUC_CTL_ARAT_LOW] = 100000000;
+
+ params[GUC_CTL_WA] |= GUC_CTL_WA_UK_BY_DRIVER;
+
+ params[GUC_CTL_FEATURE] |= GUC_CTL_DISABLE_SCHEDULER |
+ GUC_CTL_VCS2_ENABLED;
+
+ if (i915.guc_log_level >= 0) {
+ params[GUC_CTL_LOG_PARAMS] = guc->log_flags;
+ params[GUC_CTL_DEBUG] =
+ i915.guc_log_level << GUC_LOG_VERBOSITY_SHIFT;
+ }
+
+ /* If GuC submission is enabled, set up additional parameters here */
+ if (i915.enable_guc_submission) {
+ u32 pgs = i915_gem_obj_ggtt_offset(dev_priv->guc.ctx_pool_obj);
+ u32 ctx_in_16 = GUC_MAX_GPU_CONTEXTS / 16;
+
+ pgs >>= PAGE_SHIFT;
+ params[GUC_CTL_CTXINFO] = (pgs << GUC_CTL_BASE_ADDR_SHIFT) |
+ (ctx_in_16 << GUC_CTL_CTXNUM_IN16_SHIFT);
+
+ params[GUC_CTL_FEATURE] |= GUC_CTL_KERNEL_SUBMISSIONS;
+
+ /* Unmask this bit to enable the GuC's internal scheduler */
+ params[GUC_CTL_FEATURE] &= ~GUC_CTL_DISABLE_SCHEDULER;
+ }
+
+ I915_WRITE(SOFT_SCRATCH(0), 0);
+
+ for (i = 0; i < GUC_CTL_MAX_DWORDS; i++)
+ I915_WRITE(SOFT_SCRATCH(1 + i), params[i]);
+}
+
+/*
+ * Read the GuC status register (GUC_STATUS) and store it in the
+ * specified location; then return a boolean indicating whether
+ * the value matches either of two values representing completion
+ * of the GuC boot process.
+ *
+ * This is used for polling the GuC status in a wait_for_atomic()
+ * loop below.
+ */
+static inline bool guc_ucode_response(struct drm_i915_private *dev_priv,
+ u32 *status)
+{
+ u32 val = I915_READ(GUC_STATUS);
+ *status = val;
+ return ((val & GS_UKERNEL_MASK) == GS_UKERNEL_READY ||
+ (val & GS_UKERNEL_MASK) == GS_UKERNEL_LAPIC_DONE);
+}
+
+/*
+ * Transfer the firmware image to RAM for execution by the microcontroller.
+ *
+ * GuC Firmware layout:
+ * +-------------------------------+ ----
+ * | CSS header | 128B
+ * | contains major/minor version |
+ * +-------------------------------+ ----
+ * | uCode |
+ * +-------------------------------+ ----
+ * | RSA signature | 256B
+ * +-------------------------------+ ----
+ *
+ * Architecturally, the DMA engine is bidirectional, and can potentially even
+ * transfer between GTT locations. This functionality is left out of the API
+ * for now as there is no need for it.
+ *
+ * Note that GuC needs the CSS header plus uKernel code to be copied by the
+ * DMA engine in one operation, whereas the RSA signature is loaded via MMIO.
+ */
+
+#define UOS_CSS_HEADER_OFFSET 0
+#define UOS_VER_MINOR_OFFSET 0x44
+#define UOS_VER_MAJOR_OFFSET 0x46
+#define UOS_CSS_HEADER_SIZE 0x80
+#define UOS_RSA_SIG_SIZE 0x100
+
+static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv)
+{
+ struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
+ struct drm_i915_gem_object *fw_obj = guc_fw->guc_fw_obj;
+ unsigned long offset;
+ struct sg_table *sg = fw_obj->pages;
+ u32 status, ucode_size, rsa[UOS_RSA_SIG_SIZE / sizeof(u32)];
+ int i, ret = 0;
+
+ /* uCode size, also is where RSA signature starts */
+ offset = ucode_size = guc_fw->guc_fw_size - UOS_RSA_SIG_SIZE;
+ I915_WRITE(DMA_COPY_SIZE, ucode_size);
+
+ /* Copy RSA signature from the fw image to HW for verification */
+ sg_pcopy_to_buffer(sg->sgl, sg->nents, rsa, UOS_RSA_SIG_SIZE, offset);
+ for (i = 0; i < UOS_RSA_SIG_SIZE / sizeof(u32); i++)
+ I915_WRITE(UOS_RSA_SCRATCH_0 + i * sizeof(u32), rsa[i]);
+
+ /* Set the source address for the new blob */
+ offset = i915_gem_obj_ggtt_offset(fw_obj);
+ I915_WRITE(DMA_ADDR_0_LOW, lower_32_bits(offset));
+ I915_WRITE(DMA_ADDR_0_HIGH, upper_32_bits(offset) & 0xFFFF);
+
+ /*
+ * Set the DMA destination. Current uCode expects the code to be
+ * loaded at 8k; locations below this are used for the stack.
+ */
+ I915_WRITE(DMA_ADDR_1_LOW, 0x2000);
+ I915_WRITE(DMA_ADDR_1_HIGH, DMA_ADDRESS_SPACE_WOPCM);
+
+ /* Finally start the DMA */
+ I915_WRITE(DMA_CTRL, _MASKED_BIT_ENABLE(UOS_MOVE | START_DMA));
+
+ /*
+ * Spin-wait for the DMA to complete & the GuC to start up.
+ * NB: Docs recommend not using the interrupt for completion.
+ * Measurements indicate this should take no more than 20ms, so a
+ * timeout here indicates that the GuC has failed and is unusable.
+ * (Higher levels of the driver will attempt to fall back to
+ * execlist mode if this happens.)
+ */
+ ret = wait_for_atomic(guc_ucode_response(dev_priv, &status), 100);
+
+ DRM_DEBUG_DRIVER("DMA status 0x%x, GuC status 0x%x\n",
+ I915_READ(DMA_CTRL), status);
+
+ if ((status & GS_BOOTROM_MASK) == GS_BOOTROM_RSA_FAILED) {
+ DRM_ERROR("GuC firmware signature verification failed\n");
+ ret = -ENOEXEC;
+ }
+
+ DRM_DEBUG_DRIVER("returning %d\n", ret);
+
+ return ret;
+}
+
+/*
+ * Load the GuC firmware blob into the MinuteIA.
+ */
+static int guc_ucode_xfer(struct drm_i915_private *dev_priv)
+{
+ struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
+ struct drm_device *dev = dev_priv->dev;
+ int ret;
+
+ ret = i915_gem_object_set_to_gtt_domain(guc_fw->guc_fw_obj, false);
+ if (ret) {
+ DRM_DEBUG_DRIVER("set-domain failed %d\n", ret);
+ return ret;
+ }
+
+ ret = i915_gem_obj_ggtt_pin(guc_fw->guc_fw_obj, 0, 0);
+ if (ret) {
+ DRM_DEBUG_DRIVER("pin failed %d\n", ret);
+ return ret;
+ }
+
+ /* Invalidate GuC TLB to let GuC take the latest updates to GTT. */
+ I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+
+ intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+
+ /* init WOPCM */
+ I915_WRITE(GUC_WOPCM_SIZE, GUC_WOPCM_SIZE_VALUE);
+ I915_WRITE(DMA_GUC_WOPCM_OFFSET, GUC_WOPCM_OFFSET_VALUE);
+
+ /* Enable MIA caching. GuC clock gating is disabled. */
+ I915_WRITE(GUC_SHIM_CONTROL, GUC_SHIM_CONTROL_VALUE);
+
+ /* WaDisableMinuteIaClockGating:skl,bxt */
+ if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0) ||
+ (IS_BROXTON(dev) && INTEL_REVID(dev) == BXT_REVID_A0)) {
+ I915_WRITE(GUC_SHIM_CONTROL, (I915_READ(GUC_SHIM_CONTROL) &
+ ~GUC_ENABLE_MIA_CLOCK_GATING));
+ }
+
+ /* WaC6DisallowByGfxPause*/
+ I915_WRITE(GEN6_GFXPAUSE, 0x30FFF);
+
+ if (IS_BROXTON(dev))
+ I915_WRITE(GEN9LP_GT_PM_CONFIG, GT_DOORBELL_ENABLE);
+ else
+ I915_WRITE(GEN9_GT_PM_CONFIG, GT_DOORBELL_ENABLE);
+
+ if (IS_GEN9(dev)) {
+ /* DOP Clock Gating Enable for GuC clocks */
+ I915_WRITE(GEN7_MISCCPCTL, (GEN8_DOP_CLOCK_GATE_GUC_ENABLE |
+ I915_READ(GEN7_MISCCPCTL)));
+
+ /* allows for 5us before GT can go to RC6 */
+ I915_WRITE(GUC_ARAT_C6DIS, 0x1FF);
+ }
+
+ set_guc_init_params(dev_priv);
+
+ ret = guc_ucode_xfer_dma(dev_priv);
+
+ intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+
+ /*
+ * We keep the object pages for reuse during resume. But we can unpin it
+ * now that DMA has completed, so it doesn't continue to take up space.
+ */
+ i915_gem_object_ggtt_unpin(guc_fw->guc_fw_obj);
+
+ return ret;
+}
+
+/**
+ * intel_guc_ucode_load() - load GuC uCode into the device
+ * @dev: drm device
+ *
+ * Called from gem_init_hw() during driver loading and also after a GPU reset.
+ *
+ * The firmware image should have already been fetched into memory by the
+ * earlier call to intel_guc_ucode_init(), so here we need only check that
+ * is succeeded, and then transfer the image to the h/w.
+ *
+ * Return: non-zero code on error
+ */
+int intel_guc_ucode_load(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
+ int err = 0;
+
+ DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n",
+ intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
+ intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
+
+ direct_interrupts_to_host(dev_priv);
+ i915_guc_submission_disable(dev);
+
+ if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_NONE)
+ return 0;
+
+ if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_SUCCESS &&
+ guc_fw->guc_fw_load_status == GUC_FIRMWARE_FAIL)
+ return -ENOEXEC;
+
+ guc_fw->guc_fw_load_status = GUC_FIRMWARE_PENDING;
+
+ DRM_DEBUG_DRIVER("GuC fw fetch status %s\n",
+ intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status));
+
+ switch (guc_fw->guc_fw_fetch_status) {
+ case GUC_FIRMWARE_FAIL:
+ /* something went wrong :( */
+ err = -EIO;
+ goto fail;
+
+ case GUC_FIRMWARE_NONE:
+ case GUC_FIRMWARE_PENDING:
+ default:
+ /* "can't happen" */
+ WARN_ONCE(1, "GuC fw %s invalid guc_fw_fetch_status %s [%d]\n",
+ guc_fw->guc_fw_path,
+ intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
+ guc_fw->guc_fw_fetch_status);
+ err = -ENXIO;
+ goto fail;
+
+ case GUC_FIRMWARE_SUCCESS:
+ break;
+ }
+
+ err = i915_guc_submission_init(dev);
+ if (err)
+ goto fail;
+
+ err = guc_ucode_xfer(dev_priv);
+ if (err)
+ goto fail;
+
+ guc_fw->guc_fw_load_status = GUC_FIRMWARE_SUCCESS;
+
+ DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n",
+ intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
+ intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
+
+ if (i915.enable_guc_submission) {
+ err = i915_guc_submission_enable(dev);
+ if (err)
+ goto fail;
+ direct_interrupts_to_guc(dev_priv);
+ }
+
+ return 0;
+
+fail:
+ if (guc_fw->guc_fw_load_status == GUC_FIRMWARE_PENDING)
+ guc_fw->guc_fw_load_status = GUC_FIRMWARE_FAIL;
+
+ direct_interrupts_to_host(dev_priv);
+ i915_guc_submission_disable(dev);
+
+ return err;
+}
+
+static void guc_fw_fetch(struct drm_device *dev, struct intel_guc_fw *guc_fw)
+{
+ struct drm_i915_gem_object *obj;
+ const struct firmware *fw;
+ const u8 *css_header;
+ const size_t minsize = UOS_CSS_HEADER_SIZE + UOS_RSA_SIG_SIZE;
+ const size_t maxsize = GUC_WOPCM_SIZE_VALUE + UOS_RSA_SIG_SIZE
+ - 0x8000; /* 32k reserved (8K stack + 24k context) */
+ int err;
+
+ DRM_DEBUG_DRIVER("before requesting firmware: GuC fw fetch status %s\n",
+ intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status));
+
+ err = request_firmware(&fw, guc_fw->guc_fw_path, &dev->pdev->dev);
+ if (err)
+ goto fail;
+ if (!fw)
+ goto fail;
+
+ DRM_DEBUG_DRIVER("fetch GuC fw from %s succeeded, fw %p\n",
+ guc_fw->guc_fw_path, fw);
+ DRM_DEBUG_DRIVER("firmware file size %zu (minimum %zu, maximum %zu)\n",
+ fw->size, minsize, maxsize);
+
+ /* Check the size of the blob befoe examining buffer contents */
+ if (fw->size < minsize || fw->size > maxsize)
+ goto fail;
+
+ /*
+ * The GuC firmware image has the version number embedded at a well-known
+ * offset within the firmware blob; note that major / minor version are
+ * TWO bytes each (i.e. u16), although all pointers and offsets are defined
+ * in terms of bytes (u8).
+ */
+ css_header = fw->data + UOS_CSS_HEADER_OFFSET;
+ guc_fw->guc_fw_major_found = *(u16 *)(css_header + UOS_VER_MAJOR_OFFSET);
+ guc_fw->guc_fw_minor_found = *(u16 *)(css_header + UOS_VER_MINOR_OFFSET);
+
+ if (guc_fw->guc_fw_major_found != guc_fw->guc_fw_major_wanted ||
+ guc_fw->guc_fw_minor_found < guc_fw->guc_fw_minor_wanted) {
+ DRM_ERROR("GuC firmware version %d.%d, required %d.%d\n",
+ guc_fw->guc_fw_major_found, guc_fw->guc_fw_minor_found,
+ guc_fw->guc_fw_major_wanted, guc_fw->guc_fw_minor_wanted);
+ err = -ENOEXEC;
+ goto fail;
+ }
+
+ DRM_DEBUG_DRIVER("firmware version %d.%d OK (minimum %d.%d)\n",
+ guc_fw->guc_fw_major_found, guc_fw->guc_fw_minor_found,
+ guc_fw->guc_fw_major_wanted, guc_fw->guc_fw_minor_wanted);
+
+ obj = i915_gem_object_create_from_data(dev, fw->data, fw->size);
+ if (IS_ERR_OR_NULL(obj)) {
+ err = obj ? PTR_ERR(obj) : -ENOMEM;
+ goto fail;
+ }
+
+ guc_fw->guc_fw_obj = obj;
+ guc_fw->guc_fw_size = fw->size;
+
+ DRM_DEBUG_DRIVER("GuC fw fetch status SUCCESS, obj %p\n",
+ guc_fw->guc_fw_obj);
+
+ release_firmware(fw);
+ guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_SUCCESS;
+ return;
+
+fail:
+ DRM_DEBUG_DRIVER("GuC fw fetch status FAIL; err %d, fw %p, obj %p\n",
+ err, fw, guc_fw->guc_fw_obj);
+ DRM_ERROR("Failed to fetch GuC firmware from %s (error %d)\n",
+ guc_fw->guc_fw_path, err);
+
+ obj = guc_fw->guc_fw_obj;
+ if (obj)
+ drm_gem_object_unreference(&obj->base);
+ guc_fw->guc_fw_obj = NULL;
+
+ release_firmware(fw); /* OK even if fw is NULL */
+ guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL;
+}
+
+/**
+ * intel_guc_ucode_init() - define parameters and fetch firmware
+ * @dev: drm device
+ *
+ * Called early during driver load, but after GEM is initialised.
+ * The device struct_mutex must be held by the caller, as we're
+ * going to allocate a GEM object to hold the firmware image.
+ *
+ * The firmware will be transferred to the GuC's memory later,
+ * when intel_guc_ucode_load() is called.
+ */
+void intel_guc_ucode_init(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
+ const char *fw_path;
+
+ if (!HAS_GUC_SCHED(dev))
+ i915.enable_guc_submission = false;
+
+ if (!HAS_GUC_UCODE(dev)) {
+ fw_path = NULL;
+ } else if (IS_SKYLAKE(dev)) {
+ fw_path = I915_SKL_GUC_UCODE;
+ guc_fw->guc_fw_major_wanted = 4;
+ guc_fw->guc_fw_minor_wanted = 3;
+ } else {
+ i915.enable_guc_submission = false;
+ fw_path = ""; /* unknown device */
+ }
+
+ guc_fw->guc_dev = dev;
+ guc_fw->guc_fw_path = fw_path;
+ guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_NONE;
+ guc_fw->guc_fw_load_status = GUC_FIRMWARE_NONE;
+
+ if (fw_path == NULL)
+ return;
+
+ if (*fw_path == '\0') {
+ DRM_ERROR("No GuC firmware known for this platform\n");
+ guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL;
+ return;
+ }
+
+ guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_PENDING;
+ DRM_DEBUG_DRIVER("GuC firmware pending, path %s\n", fw_path);
+ guc_fw_fetch(dev, guc_fw);
+ /* status must now be FAIL or SUCCESS */
+}
+
+/**
+ * intel_guc_ucode_fini() - clean up all allocated resources
+ * @dev: drm device
+ */
+void intel_guc_ucode_fini(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
+
+ direct_interrupts_to_host(dev_priv);
+ i915_guc_submission_fini(dev);
+
+ if (guc_fw->guc_fw_obj)
+ drm_gem_object_unreference(&guc_fw->guc_fw_obj->base);
+ guc_fw->guc_fw_obj = NULL;
+
+ guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_NONE;
+}
u32 hdmi_val;
hdmi_val = SDVO_ENCODING_HDMI;
- if (!HAS_PCH_SPLIT(dev))
- hdmi_val |= intel_hdmi->color_range;
+ if (!HAS_PCH_SPLIT(dev) && crtc->config->limited_color_range)
+ hdmi_val |= HDMI_COLOR_RANGE_16_235;
if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
hdmi_val |= SDVO_VSYNC_ACTIVE_HIGH;
if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
if (intel_hdmi->color_range_auto) {
/* See CEA-861-E - 5.1 Default Encoding Parameters */
- if (pipe_config->has_hdmi_sink &&
- drm_match_cea_mode(adjusted_mode) > 1)
- intel_hdmi->color_range = HDMI_COLOR_RANGE_16_235;
- else
- intel_hdmi->color_range = 0;
+ pipe_config->limited_color_range =
+ pipe_config->has_hdmi_sink &&
+ drm_match_cea_mode(adjusted_mode) > 1;
+ } else {
+ pipe_config->limited_color_range =
+ intel_hdmi->limited_color_range;
}
if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) {
clock_12bpc *= 2;
}
- if (intel_hdmi->color_range)
- pipe_config->limited_color_range = true;
-
if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev))
pipe_config->has_pch_encoder = true;
}
static bool
-intel_hdmi_set_edid(struct drm_connector *connector)
+intel_hdmi_set_edid(struct drm_connector *connector, bool force)
{
struct drm_i915_private *dev_priv = to_i915(connector->dev);
struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
struct intel_encoder *intel_encoder =
&hdmi_to_dig_port(intel_hdmi)->base;
enum intel_display_power_domain power_domain;
- struct edid *edid;
+ struct edid *edid = NULL;
bool connected = false;
power_domain = intel_display_port_power_domain(intel_encoder);
intel_display_power_get(dev_priv, power_domain);
- edid = drm_get_edid(connector,
- intel_gmbus_get_adapter(dev_priv,
- intel_hdmi->ddc_bus));
+ if (force)
+ edid = drm_get_edid(connector,
+ intel_gmbus_get_adapter(dev_priv,
+ intel_hdmi->ddc_bus));
intel_display_power_put(dev_priv, power_domain);
intel_hdmi_detect(struct drm_connector *connector, bool force)
{
enum drm_connector_status status;
+ struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+ struct drm_i915_private *dev_priv = to_i915(connector->dev);
+ bool live_status = false;
+ unsigned int retry = 3;
DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
connector->base.id, connector->name);
+ while (!live_status && --retry) {
+ live_status = intel_digital_port_connected(dev_priv,
+ hdmi_to_dig_port(intel_hdmi));
+ mdelay(10);
+ }
+
+ if (!live_status)
+ DRM_DEBUG_KMS("Live status not up!");
+
intel_hdmi_unset_edid(connector);
- if (intel_hdmi_set_edid(connector)) {
+ if (intel_hdmi_set_edid(connector, live_status)) {
struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
hdmi_to_dig_port(intel_hdmi)->base.type = INTEL_OUTPUT_HDMI;
if (connector->status != connector_status_connected)
return;
- intel_hdmi_set_edid(connector);
+ intel_hdmi_set_edid(connector, true);
hdmi_to_dig_port(intel_hdmi)->base.type = INTEL_OUTPUT_HDMI;
}
if (property == dev_priv->broadcast_rgb_property) {
bool old_auto = intel_hdmi->color_range_auto;
- uint32_t old_range = intel_hdmi->color_range;
+ bool old_range = intel_hdmi->limited_color_range;
switch (val) {
case INTEL_BROADCAST_RGB_AUTO:
break;
case INTEL_BROADCAST_RGB_FULL:
intel_hdmi->color_range_auto = false;
- intel_hdmi->color_range = 0;
+ intel_hdmi->limited_color_range = false;
break;
case INTEL_BROADCAST_RGB_LIMITED:
intel_hdmi->color_range_auto = false;
- intel_hdmi->color_range = HDMI_COLOR_RANGE_16_235;
+ intel_hdmi->limited_color_range = true;
break;
default:
return -EINVAL;
}
if (old_auto == intel_hdmi->color_range_auto &&
- old_range == intel_hdmi->color_range)
+ old_range == intel_hdmi->limited_color_range)
return 0;
goto done;
mutex_unlock(&dev_priv->sb_lock);
}
+static void chv_data_lane_soft_reset(struct intel_encoder *encoder,
+ bool reset)
+{
+ struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+ enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
+ struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+ enum pipe pipe = crtc->pipe;
+ uint32_t val;
+
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
+ if (reset)
+ val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+ else
+ val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
+
+ if (crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
+ if (reset)
+ val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+ else
+ val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+ }
+
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
+ val |= CHV_PCS_REQ_SOFTRESET_EN;
+ if (reset)
+ val &= ~DPIO_PCS_CLK_SOFT_RESET;
+ else
+ val |= DPIO_PCS_CLK_SOFT_RESET;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
+
+ if (crtc->config->lane_count > 2) {
+ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
+ val |= CHV_PCS_REQ_SOFTRESET_EN;
+ if (reset)
+ val &= ~DPIO_PCS_CLK_SOFT_RESET;
+ else
+ val |= DPIO_PCS_CLK_SOFT_RESET;
+ vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
+ }
+}
+
static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
{
struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
intel_hdmi_prepare(encoder);
+ /*
+ * Must trick the second common lane into life.
+ * Otherwise we can't even access the PLL.
+ */
+ if (ch == DPIO_CH0 && pipe == PIPE_B)
+ dport->release_cl2_override =
+ !chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, true);
+
+ chv_phy_powergate_lanes(encoder, true, 0x0);
+
mutex_lock(&dev_priv->sb_lock);
+ /* Assert data lane reset */
+ chv_data_lane_soft_reset(encoder, true);
+
/* program left/right clock distribution */
if (pipe != PIPE_B) {
val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
mutex_unlock(&dev_priv->sb_lock);
}
+static void chv_hdmi_post_pll_disable(struct intel_encoder *encoder)
+{
+ struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+ enum pipe pipe = to_intel_crtc(encoder->base.crtc)->pipe;
+ u32 val;
+
+ mutex_lock(&dev_priv->sb_lock);
+
+ /* disable left/right clock distribution */
+ if (pipe != PIPE_B) {
+ val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
+ val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
+ vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
+ } else {
+ val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
+ val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
+ vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
+ }
+
+ mutex_unlock(&dev_priv->sb_lock);
+
+ /*
+ * Leave the power down bit cleared for at least one
+ * lane so that chv_powergate_phy_ch() will power
+ * on something when the channel is otherwise unused.
+ * When the port is off and the override is removed
+ * the lanes power down anyway, so otherwise it doesn't
+ * really matter what the state of power down bits is
+ * after this.
+ */
+ chv_phy_powergate_lanes(encoder, false, 0x0);
+}
+
static void vlv_hdmi_post_disable(struct intel_encoder *encoder)
{
struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
static void chv_hdmi_post_disable(struct intel_encoder *encoder)
{
- struct intel_digital_port *dport = enc_to_dig_port(&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);
- enum dpio_channel ch = vlv_dport_to_channel(dport);
- enum pipe pipe = intel_crtc->pipe;
- u32 val;
mutex_lock(&dev_priv->sb_lock);
- /* Propagate soft reset to data lane reset */
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
- val |= CHV_PCS_REQ_SOFTRESET_EN;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
-
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
- val |= CHV_PCS_REQ_SOFTRESET_EN;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
-
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
- val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
- vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
-
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
- val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+ /* Assert data lane reset */
+ chv_data_lane_soft_reset(encoder, true);
mutex_unlock(&dev_priv->sb_lock);
}
val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
- /* Deassert soft data lane reset*/
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
- val |= CHV_PCS_REQ_SOFTRESET_EN;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
-
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
- val |= CHV_PCS_REQ_SOFTRESET_EN;
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
-
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
- val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
- vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
-
- val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
- val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
- vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
-
/* Program Tx latency optimal setting */
for (i = 0; i < 4; i++) {
/* Set the upar bit */
DPIO_TX1_STAGGER_MULT(7) |
DPIO_TX2_STAGGER_MULT(5));
+ /* Deassert data lane reset */
+ chv_data_lane_soft_reset(encoder, false);
+
/* Clear calc init */
val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
for (i = 0; i < 4; i++) {
val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
+
val &= ~DPIO_SWING_MARGIN000_MASK;
val |= 102 << DPIO_SWING_MARGIN000_SHIFT;
+
+ /*
+ * Supposedly this value shouldn't matter when unique transition
+ * scale is disabled, but in fact it does matter. Let's just
+ * always program the same value and hope it's OK.
+ */
+ val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT);
+ val |= 0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT;
+
vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
}
- /* Disable unique transition scale */
+ /*
+ * The document said it needs to set bit 27 for ch0 and bit 26
+ * for ch1. Might be a typo in the doc.
+ * For now, for this unique transition scale selection, set bit
+ * 27 for ch0 and ch1.
+ */
for (i = 0; i < 4; i++) {
val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i));
val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN;
vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
}
- /* Additional steps for 1200mV-0dB */
-#if 0
- val = vlv_dpio_read(dev_priv, pipe, VLV_TX_DW3(ch));
- if (ch)
- val |= DPIO_TX_UNIQ_TRANS_SCALE_CH1;
- else
- val |= DPIO_TX_UNIQ_TRANS_SCALE_CH0;
- vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(ch), val);
-
- vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(ch),
- vlv_dpio_read(dev_priv, pipe, VLV_TX_DW2(ch)) |
- (0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT));
-#endif
/* Start swing calculation */
val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
g4x_enable_hdmi(encoder);
vlv_wait_port_ready(dev_priv, dport, 0x0);
+
+ /* Second common lane will stay alive on its own now */
+ if (dport->release_cl2_override) {
+ chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, false);
+ dport->release_cl2_override = false;
+ }
}
static void intel_hdmi_destroy(struct drm_connector *connector)
intel_hdmi->ddc_bus = GMBUS_PIN_1_BXT;
else
intel_hdmi->ddc_bus = GMBUS_PIN_DPB;
- intel_encoder->hpd_pin = HPD_PORT_B;
+ /*
+ * On BXT A0/A1, sw needs to activate DDIA HPD logic and
+ * interrupts to check the external panel connection.
+ */
+ if (IS_BROXTON(dev_priv) && (INTEL_REVID(dev) < BXT_REVID_B0))
+ intel_encoder->hpd_pin = HPD_PORT_A;
+ else
+ intel_encoder->hpd_pin = HPD_PORT_B;
break;
case PORT_C:
if (IS_BROXTON(dev_priv))
intel_connector_attach_encoder(intel_connector, intel_encoder);
drm_connector_register(connector);
+ intel_hdmi->attached_connector = intel_connector;
/* For G4X desktop chip, PEG_BAND_GAP_DATA 3:0 must first be written
* 0xd. Failure to do so will result in spurious interrupts being
intel_encoder->pre_enable = chv_hdmi_pre_enable;
intel_encoder->enable = vlv_enable_hdmi;
intel_encoder->post_disable = chv_hdmi_post_disable;
+ intel_encoder->post_pll_disable = chv_hdmi_post_pll_disable;
} else if (IS_VALLEYVIEW(dev)) {
intel_encoder->pre_pll_enable = vlv_hdmi_pre_pll_enable;
intel_encoder->pre_enable = vlv_hdmi_pre_enable;
reg_state[CTX_PDP ## n ## _LDW+1] = lower_32_bits(_addr); \
}
+#define ASSIGN_CTX_PML4(ppgtt, reg_state) { \
+ reg_state[CTX_PDP0_UDW + 1] = upper_32_bits(px_dma(&ppgtt->pml4)); \
+ reg_state[CTX_PDP0_LDW + 1] = lower_32_bits(px_dma(&ppgtt->pml4)); \
+}
+
enum {
ADVANCED_CONTEXT = 0,
- LEGACY_CONTEXT,
+ LEGACY_32B_CONTEXT,
ADVANCED_AD_CONTEXT,
LEGACY_64B_CONTEXT
};
-#define GEN8_CTX_MODE_SHIFT 3
+#define GEN8_CTX_ADDRESSING_MODE_SHIFT 3
+#define GEN8_CTX_ADDRESSING_MODE(dev) (USES_FULL_48BIT_PPGTT(dev) ?\
+ LEGACY_64B_CONTEXT :\
+ LEGACY_32B_CONTEXT)
enum {
FAULT_AND_HANG = 0,
FAULT_AND_HALT, /* Debug only */
#define CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT 0x17
static int intel_lr_context_pin(struct drm_i915_gem_request *rq);
+static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring,
+ struct drm_i915_gem_object *default_ctx_obj);
+
/**
* intel_sanitize_enable_execlists() - sanitize i915.enable_execlists
{
WARN_ON(i915.enable_ppgtt == -1);
+ /* On platforms with execlist available, vGPU will only
+ * support execlist mode, no ring buffer mode.
+ */
+ if (HAS_LOGICAL_RING_CONTEXTS(dev) && intel_vgpu_active(dev))
+ return 1;
+
if (INTEL_INFO(dev)->gen >= 9)
return 1;
*/
u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj)
{
- u32 lrca = i915_gem_obj_ggtt_offset(ctx_obj);
+ u32 lrca = i915_gem_obj_ggtt_offset(ctx_obj) +
+ LRC_PPHWSP_PN * PAGE_SIZE;
/* LRCA is required to be 4K aligned so the more significant 20 bits
* are globally unique */
return lrca >> 12;
}
-static uint64_t execlists_ctx_descriptor(struct drm_i915_gem_request *rq)
+static bool disable_lite_restore_wa(struct intel_engine_cs *ring)
{
- struct intel_engine_cs *ring = rq->ring;
struct drm_device *dev = ring->dev;
- struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state;
+
+ return ((IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0) ||
+ (IS_BROXTON(dev) && INTEL_REVID(dev) == BXT_REVID_A0)) &&
+ (ring->id == VCS || ring->id == VCS2);
+}
+
+uint64_t intel_lr_context_descriptor(struct intel_context *ctx,
+ struct intel_engine_cs *ring)
+{
+ struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
uint64_t desc;
- uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj);
+ uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj) +
+ LRC_PPHWSP_PN * PAGE_SIZE;
WARN_ON(lrca & 0xFFFFFFFF00000FFFULL);
desc = GEN8_CTX_VALID;
- desc |= LEGACY_CONTEXT << GEN8_CTX_MODE_SHIFT;
+ desc |= GEN8_CTX_ADDRESSING_MODE(dev) << GEN8_CTX_ADDRESSING_MODE_SHIFT;
if (IS_GEN8(ctx_obj->base.dev))
desc |= GEN8_CTX_L3LLC_COHERENT;
desc |= GEN8_CTX_PRIVILEGE;
/* desc |= GEN8_CTX_FORCE_RESTORE; */
/* WaEnableForceRestoreInCtxtDescForVCS:skl */
- if (IS_GEN9(dev) &&
- INTEL_REVID(dev) <= SKL_REVID_B0 &&
- (ring->id == BCS || ring->id == VCS ||
- ring->id == VECS || ring->id == VCS2))
+ /* WaEnableForceRestoreInCtxtDescForVCS:bxt */
+ if (disable_lite_restore_wa(ring))
desc |= GEN8_CTX_FORCE_RESTORE;
return desc;
uint64_t desc[2];
if (rq1) {
- desc[1] = execlists_ctx_descriptor(rq1);
+ desc[1] = intel_lr_context_descriptor(rq1->ctx, rq1->ring);
rq1->elsp_submitted++;
} else {
desc[1] = 0;
}
- desc[0] = execlists_ctx_descriptor(rq0);
+ desc[0] = intel_lr_context_descriptor(rq0->ctx, rq0->ring);
rq0->elsp_submitted++;
/* You must always write both descriptors in the order below. */
I915_WRITE_FW(RING_ELSP(ring), lower_32_bits(desc[0]));
/* ELSP is a wo register, use another nearby reg for posting */
- POSTING_READ_FW(RING_EXECLIST_STATUS(ring));
+ POSTING_READ_FW(RING_EXECLIST_STATUS_LO(ring));
intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
spin_unlock(&dev_priv->uncore.lock);
}
WARN_ON(!i915_gem_obj_is_pinned(ctx_obj));
WARN_ON(!i915_gem_obj_is_pinned(rb_obj));
- page = i915_gem_object_get_page(ctx_obj, 1);
+ page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
reg_state = kmap_atomic(page);
reg_state[CTX_RING_TAIL+1] = rq->tail;
reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj);
- /* True PPGTT with dynamic page allocation: update PDP registers and
- * point the unallocated PDPs to the scratch page
- */
- if (ppgtt) {
+ if (ppgtt && !USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
+ /* True 32b PPGTT with dynamic page allocation: update PDP
+ * registers and point the unallocated PDPs to scratch page.
+ * PML4 is allocated during ppgtt init, so this is not needed
+ * in 48-bit mode.
+ */
ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
u32 status_pointer;
u8 read_pointer;
u8 write_pointer;
- u32 status;
+ u32 status = 0;
u32 status_id;
u32 submit_contexts = 0;
while (read_pointer < write_pointer) {
read_pointer++;
- status = I915_READ(RING_CONTEXT_STATUS_BUF(ring) +
- (read_pointer % 6) * 8);
- status_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) +
- (read_pointer % 6) * 8 + 4);
+ status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, read_pointer % 6));
+ status_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, read_pointer % 6));
if (status & GEN8_CTX_STATUS_IDLE_ACTIVE)
continue;
}
}
- if (submit_contexts != 0)
+ if (disable_lite_restore_wa(ring)) {
+ /* Prevent a ctx to preempt itself */
+ if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) &&
+ (submit_contexts != 0))
+ execlists_context_unqueue(ring);
+ } else if (submit_contexts != 0) {
execlists_context_unqueue(ring);
+ }
spin_unlock(&ring->execlist_lock);
i915_gem_request_reference(request);
- request->tail = request->ringbuf->tail;
-
spin_lock_irq(&ring->execlist_lock);
list_for_each_entry(cursor, &ring->execlist_queue, execlist_link)
intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
{
struct intel_engine_cs *ring = request->ring;
+ struct drm_i915_private *dev_priv = request->i915;
intel_logical_ring_advance(request->ringbuf);
+ request->tail = request->ringbuf->tail;
+
if (intel_ring_stopped(ring))
return;
- execlists_context_queue(request);
+ if (dev_priv->guc.execbuf_client)
+ i915_guc_submit(dev_priv->guc.execbuf_client, request);
+ else
+ execlists_context_queue(request);
}
static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf)
/**
* intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
*
- * @request: The request to start some new work for
- * @ctx: Logical ring context whose ringbuffer is being prepared.
+ * @req: The request to start some new work for
* @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
*
* The ringbuffer might not be ready to accept the commands right away (maybe it needs to
return 0;
}
+static int intel_lr_context_do_pin(struct intel_engine_cs *ring,
+ struct drm_i915_gem_object *ctx_obj,
+ struct intel_ringbuffer *ringbuf)
+{
+ struct drm_device *dev = ring->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int ret = 0;
+
+ WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
+ ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN,
+ PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+ if (ret)
+ return ret;
+
+ ret = intel_pin_and_map_ringbuffer_obj(ring->dev, ringbuf);
+ if (ret)
+ goto unpin_ctx_obj;
+
+ ctx_obj->dirty = true;
+
+ /* Invalidate GuC TLB. */
+ if (i915.enable_guc_submission)
+ I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+
+ return ret;
+
+unpin_ctx_obj:
+ i915_gem_object_ggtt_unpin(ctx_obj);
+
+ return ret;
+}
+
static int intel_lr_context_pin(struct drm_i915_gem_request *rq)
{
+ int ret = 0;
struct intel_engine_cs *ring = rq->ring;
struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state;
struct intel_ringbuffer *ringbuf = rq->ringbuf;
- int ret = 0;
- WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
if (rq->ctx->engine[ring->id].pin_count++ == 0) {
- ret = i915_gem_obj_ggtt_pin(ctx_obj,
- GEN8_LR_CONTEXT_ALIGN, 0);
+ ret = intel_lr_context_do_pin(ring, ctx_obj, ringbuf);
if (ret)
goto reset_pin_count;
-
- ret = intel_pin_and_map_ringbuffer_obj(ring->dev, ringbuf);
- if (ret)
- goto unpin_ctx_obj;
-
- ctx_obj->dirty = true;
}
-
return ret;
-unpin_ctx_obj:
- i915_gem_object_ggtt_unpin(ctx_obj);
reset_pin_count:
rq->ctx->engine[ring->id].pin_count = 0;
-
return ret;
}
if (IS_SKYLAKE(ring->dev) && INTEL_REVID(ring->dev) <= SKL_REVID_E0)
l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS;
- wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8(1) |
+ wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
MI_SRM_LRM_GLOBAL_GTT));
wa_ctx_emit(batch, index, GEN8_L3SQCREG4);
wa_ctx_emit(batch, index, ring->scratch.gtt_offset + 256);
wa_ctx_emit(batch, index, 0);
wa_ctx_emit(batch, index, 0);
- wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8(1) |
+ wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8 |
MI_SRM_LRM_GLOBAL_GTT));
wa_ctx_emit(batch, index, GEN8_L3SQCREG4);
wa_ctx_emit(batch, index, ring->scratch.gtt_offset + 256);
/* WaFlushCoherentL3CacheLinesAtContextSwitch:bdw */
if (IS_BROADWELL(ring->dev)) {
- index = gen8_emit_flush_coherentl3_wa(ring, batch, index);
- if (index < 0)
- return index;
+ int rc = gen8_emit_flush_coherentl3_wa(ring, batch, index);
+ if (rc < 0)
+ return rc;
+ index = rc;
}
/* WaClearSlmSpaceAtContextSwitch:bdw,chv */
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ lrc_setup_hardware_status_page(ring,
+ ring->default_context->engine[ring->id].state);
+
I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask));
I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff);
* Ideally, we should set Force PD Restore in ctx descriptor,
* but we can't. Force Restore would be a second option, but
* it is unsafe in case of lite-restore (because the ctx is
- * not idle). */
+ * not idle). PML4 is allocated during ppgtt init so this is
+ * not needed in 48-bit.*/
if (req->ctx->ppgtt &&
(intel_ring_flag(req->ring) & req->ctx->ppgtt->pd_dirty_rings)) {
- ret = intel_logical_ring_emit_pdps(req);
- if (ret)
- return ret;
+ if (!USES_FULL_48BIT_PPGTT(req->i915) &&
+ !intel_vgpu_active(req->i915->dev)) {
+ ret = intel_logical_ring_emit_pdps(req);
+ if (ret)
+ return ret;
+ }
req->ctx->ppgtt->pd_dirty_rings &= ~intel_ring_flag(req->ring);
}
intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
}
+static u32 bxt_a_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency)
+{
+
+ /*
+ * On BXT A steppings there is a HW coherency issue whereby the
+ * MI_STORE_DATA_IMM storing the completed request's seqno
+ * occasionally doesn't invalidate the CPU cache. Work around this by
+ * clflushing the corresponding cacheline whenever the caller wants
+ * the coherency to be guaranteed. Note that this cacheline is known
+ * to be clean at this point, since we only write it in
+ * bxt_a_set_seqno(), where we also do a clflush after the write. So
+ * this clflush in practice becomes an invalidate operation.
+ */
+
+ if (!lazy_coherency)
+ intel_flush_status_page(ring, I915_GEM_HWS_INDEX);
+
+ return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
+}
+
+static void bxt_a_set_seqno(struct intel_engine_cs *ring, u32 seqno)
+{
+ intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
+
+ /* See bxt_a_get_seqno() explaining the reason for the clflush. */
+ intel_flush_status_page(ring, I915_GEM_HWS_INDEX);
+}
+
static int gen8_emit_request(struct drm_i915_gem_request *request)
{
struct intel_ringbuffer *ringbuf = request->ringbuf;
if (ret)
return ret;
- ret = intel_lr_context_deferred_create(ring->default_context, ring);
+ ret = intel_lr_context_deferred_alloc(ring->default_context, ring);
+ if (ret)
+ return ret;
+
+ /* As this is the default context, always pin it */
+ ret = intel_lr_context_do_pin(
+ ring,
+ ring->default_context->engine[ring->id].state,
+ ring->default_context->engine[ring->id].ringbuf);
+ if (ret) {
+ DRM_ERROR(
+ "Failed to pin and map ringbuffer %s: %d\n",
+ ring->name, ret);
+ return ret;
+ }
return ret;
}
ring->init_hw = gen8_init_render_ring;
ring->init_context = gen8_init_rcs_context;
ring->cleanup = intel_fini_pipe_control;
- ring->get_seqno = gen8_get_seqno;
- ring->set_seqno = gen8_set_seqno;
+ if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0) {
+ ring->get_seqno = bxt_a_get_seqno;
+ ring->set_seqno = bxt_a_set_seqno;
+ } else {
+ ring->get_seqno = gen8_get_seqno;
+ ring->set_seqno = gen8_set_seqno;
+ }
ring->emit_request = gen8_emit_request;
ring->emit_flush = gen8_emit_flush_render;
ring->irq_get = gen8_logical_ring_get_irq;
GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS1_IRQ_SHIFT;
ring->init_hw = gen8_init_common_ring;
- ring->get_seqno = gen8_get_seqno;
- ring->set_seqno = gen8_set_seqno;
+ if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0) {
+ ring->get_seqno = bxt_a_get_seqno;
+ ring->set_seqno = bxt_a_set_seqno;
+ } else {
+ ring->get_seqno = gen8_get_seqno;
+ ring->set_seqno = gen8_set_seqno;
+ }
ring->emit_request = gen8_emit_request;
ring->emit_flush = gen8_emit_flush;
ring->irq_get = gen8_logical_ring_get_irq;
GT_CONTEXT_SWITCH_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
ring->init_hw = gen8_init_common_ring;
- ring->get_seqno = gen8_get_seqno;
- ring->set_seqno = gen8_set_seqno;
+ if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0) {
+ ring->get_seqno = bxt_a_get_seqno;
+ ring->set_seqno = bxt_a_set_seqno;
+ } else {
+ ring->get_seqno = gen8_get_seqno;
+ ring->set_seqno = gen8_set_seqno;
+ }
ring->emit_request = gen8_emit_request;
ring->emit_flush = gen8_emit_flush;
ring->irq_get = gen8_logical_ring_get_irq;
GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VECS_IRQ_SHIFT;
ring->init_hw = gen8_init_common_ring;
- ring->get_seqno = gen8_get_seqno;
- ring->set_seqno = gen8_set_seqno;
+ if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0) {
+ ring->get_seqno = bxt_a_get_seqno;
+ ring->set_seqno = bxt_a_set_seqno;
+ } else {
+ ring->get_seqno = gen8_get_seqno;
+ ring->set_seqno = gen8_set_seqno;
+ }
ring->emit_request = gen8_emit_request;
ring->emit_flush = gen8_emit_flush;
ring->irq_get = gen8_logical_ring_get_irq;
goto cleanup_vebox_ring;
}
- ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
- if (ret)
- goto cleanup_bsd2_ring;
-
return 0;
-cleanup_bsd2_ring:
- intel_logical_ring_cleanup(&dev_priv->ring[VCS2]);
cleanup_vebox_ring:
intel_logical_ring_cleanup(&dev_priv->ring[VECS]);
cleanup_blt_ring:
/* The second page of the context object contains some fields which must
* be set up prior to the first execution. */
- page = i915_gem_object_get_page(ctx_obj, 1);
+ page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
reg_state = kmap_atomic(page);
/* A context is actually a big batch buffer with several MI_LOAD_REGISTER_IMM
reg_state[CTX_PDP0_UDW] = GEN8_RING_PDP_UDW(ring, 0);
reg_state[CTX_PDP0_LDW] = GEN8_RING_PDP_LDW(ring, 0);
- /* With dynamic page allocation, PDPs may not be allocated at this point,
- * Point the unallocated PDPs to the scratch page
- */
- ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
- ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
- ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
- ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
+ if (USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
+ /* 64b PPGTT (48bit canonical)
+ * PDP0_DESCRIPTOR contains the base address to PML4 and
+ * other PDP Descriptors are ignored.
+ */
+ ASSIGN_CTX_PML4(ppgtt, reg_state);
+ } else {
+ /* 32b PPGTT
+ * PDP*_DESCRIPTOR contains the base address of space supported.
+ * With dynamic page allocation, PDPs may not be allocated at
+ * this point. Point the unallocated PDPs to the scratch page
+ */
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 3);
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 2);
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 1);
+ ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
+ }
+
if (ring->id == RCS) {
reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
reg_state[CTX_R_PWR_CLK_STATE] = GEN8_R_PWR_CLK_STATE;
i915_gem_object_ggtt_unpin(ctx_obj);
}
WARN_ON(ctx->engine[ring->id].pin_count);
- intel_destroy_ringbuffer_obj(ringbuf);
- kfree(ringbuf);
+ intel_ringbuffer_free(ringbuf);
drm_gem_object_unreference(&ctx_obj->base);
}
}
struct drm_i915_gem_object *default_ctx_obj)
{
struct drm_i915_private *dev_priv = ring->dev->dev_private;
+ struct page *page;
- /* The status page is offset 0 from the default context object
- * in LRC mode. */
- ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(default_ctx_obj);
- ring->status_page.page_addr =
- kmap(sg_page(default_ctx_obj->pages->sgl));
+ /* The HWSP is part of the default context object in LRC mode. */
+ ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(default_ctx_obj)
+ + LRC_PPHWSP_PN * PAGE_SIZE;
+ page = i915_gem_object_get_page(default_ctx_obj, LRC_PPHWSP_PN);
+ ring->status_page.page_addr = kmap(page);
ring->status_page.obj = default_ctx_obj;
I915_WRITE(RING_HWS_PGA(ring->mmio_base),
}
/**
- * intel_lr_context_deferred_create() - create the LRC specific bits of a context
+ * intel_lr_context_deferred_alloc() - create the LRC specific bits of a context
* @ctx: LR context to create.
* @ring: engine to be used with the context.
*
*
* Return: non-zero on error.
*/
-int intel_lr_context_deferred_create(struct intel_context *ctx,
+
+int intel_lr_context_deferred_alloc(struct intel_context *ctx,
struct intel_engine_cs *ring)
{
- const bool is_global_default_ctx = (ctx == ring->default_context);
struct drm_device *dev = ring->dev;
struct drm_i915_gem_object *ctx_obj;
uint32_t context_size;
context_size = round_up(get_lr_context_size(ring), 4096);
+ /* One extra page as the sharing data between driver and GuC */
+ context_size += PAGE_SIZE * LRC_PPHWSP_PN;
+
ctx_obj = i915_gem_alloc_object(dev, context_size);
if (!ctx_obj) {
DRM_DEBUG_DRIVER("Alloc LRC backing obj failed.\n");
return -ENOMEM;
}
- if (is_global_default_ctx) {
- ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN, 0);
- if (ret) {
- DRM_DEBUG_DRIVER("Pin LRC backing obj failed: %d\n",
- ret);
- drm_gem_object_unreference(&ctx_obj->base);
- return ret;
- }
- }
-
- ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);
- if (!ringbuf) {
- DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s\n",
- ring->name);
- ret = -ENOMEM;
- goto error_unpin_ctx;
- }
-
- ringbuf->ring = ring;
-
- ringbuf->size = 32 * PAGE_SIZE;
- ringbuf->effective_size = ringbuf->size;
- ringbuf->head = 0;
- ringbuf->tail = 0;
- ringbuf->last_retired_head = -1;
- intel_ring_update_space(ringbuf);
-
- if (ringbuf->obj == NULL) {
- ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
- if (ret) {
- DRM_DEBUG_DRIVER(
- "Failed to allocate ringbuffer obj %s: %d\n",
- ring->name, ret);
- goto error_free_rbuf;
- }
-
- if (is_global_default_ctx) {
- ret = intel_pin_and_map_ringbuffer_obj(dev, ringbuf);
- if (ret) {
- DRM_ERROR(
- "Failed to pin and map ringbuffer %s: %d\n",
- ring->name, ret);
- goto error_destroy_rbuf;
- }
- }
-
+ ringbuf = intel_engine_create_ringbuffer(ring, 4 * PAGE_SIZE);
+ if (IS_ERR(ringbuf)) {
+ ret = PTR_ERR(ringbuf);
+ goto error_deref_obj;
}
ret = populate_lr_context(ctx, ctx_obj, ring, ringbuf);
if (ret) {
DRM_DEBUG_DRIVER("Failed to populate LRC: %d\n", ret);
- goto error;
+ goto error_ringbuf;
}
ctx->engine[ring->id].ringbuf = ringbuf;
ctx->engine[ring->id].state = ctx_obj;
- if (ctx == ring->default_context)
- lrc_setup_hardware_status_page(ring, ctx_obj);
- else if (ring->id == RCS && !ctx->rcs_initialized) {
- if (ring->init_context) {
- struct drm_i915_gem_request *req;
+ if (ctx != ring->default_context && ring->init_context) {
+ struct drm_i915_gem_request *req;
- ret = i915_gem_request_alloc(ring, ctx, &req);
- if (ret)
- return ret;
-
- ret = ring->init_context(req);
- if (ret) {
- DRM_ERROR("ring init context: %d\n", ret);
- i915_gem_request_cancel(req);
- ctx->engine[ring->id].ringbuf = NULL;
- ctx->engine[ring->id].state = NULL;
- goto error;
- }
-
- i915_add_request_no_flush(req);
+ ret = i915_gem_request_alloc(ring,
+ ctx, &req);
+ if (ret) {
+ DRM_ERROR("ring create req: %d\n",
+ ret);
+ goto error_ringbuf;
}
- ctx->rcs_initialized = true;
+ ret = ring->init_context(req);
+ if (ret) {
+ DRM_ERROR("ring init context: %d\n",
+ ret);
+ i915_gem_request_cancel(req);
+ goto error_ringbuf;
+ }
+ i915_add_request_no_flush(req);
}
-
return 0;
-error:
- if (is_global_default_ctx)
- intel_unpin_ringbuffer_obj(ringbuf);
-error_destroy_rbuf:
- intel_destroy_ringbuffer_obj(ringbuf);
-error_free_rbuf:
- kfree(ringbuf);
-error_unpin_ctx:
- if (is_global_default_ctx)
- i915_gem_object_ggtt_unpin(ctx_obj);
+error_ringbuf:
+ intel_ringbuffer_free(ringbuf);
+error_deref_obj:
drm_gem_object_unreference(&ctx_obj->base);
+ ctx->engine[ring->id].ringbuf = NULL;
+ ctx->engine[ring->id].state = NULL;
return ret;
}
WARN(1, "Failed get_pages for context obj\n");
continue;
}
- page = i915_gem_object_get_page(ctx_obj, 1);
+ page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
reg_state = kmap_atomic(page);
reg_state[CTX_RING_HEAD+1] = 0;
/* Execlists regs */
#define RING_ELSP(ring) ((ring)->mmio_base+0x230)
-#define RING_EXECLIST_STATUS(ring) ((ring)->mmio_base+0x234)
+#define RING_EXECLIST_STATUS_LO(ring) ((ring)->mmio_base+0x234)
+#define RING_EXECLIST_STATUS_HI(ring) ((ring)->mmio_base+0x234 + 4)
#define RING_CONTEXT_CONTROL(ring) ((ring)->mmio_base+0x244)
#define CTX_CTRL_INHIBIT_SYN_CTX_SWITCH (1 << 3)
#define CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT (1 << 0)
#define CTX_CTRL_RS_CTX_ENABLE (1 << 1)
-#define RING_CONTEXT_STATUS_BUF(ring) ((ring)->mmio_base+0x370)
+#define RING_CONTEXT_STATUS_BUF_LO(ring, i) ((ring)->mmio_base+0x370 + (i) * 8)
+#define RING_CONTEXT_STATUS_BUF_HI(ring, i) ((ring)->mmio_base+0x370 + (i) * 8 + 4)
#define RING_CONTEXT_STATUS_PTR(ring) ((ring)->mmio_base+0x3a0)
/* Logical Rings */
}
/* Logical Ring Contexts */
+
+/* One extra page is added before LRC for GuC as shared data */
+#define LRC_GUCSHR_PN (0)
+#define LRC_PPHWSP_PN (LRC_GUCSHR_PN + 1)
+#define LRC_STATE_PN (LRC_PPHWSP_PN + 1)
+
void intel_lr_context_free(struct intel_context *ctx);
-int intel_lr_context_deferred_create(struct intel_context *ctx,
- struct intel_engine_cs *ring);
+int intel_lr_context_deferred_alloc(struct intel_context *ctx,
+ struct intel_engine_cs *ring);
void intel_lr_context_unpin(struct drm_i915_gem_request *req);
void intel_lr_context_reset(struct drm_device *dev,
struct intel_context *ctx);
+uint64_t intel_lr_context_descriptor(struct intel_context *ctx,
+ struct intel_engine_cs *ring);
/* Execlists */
int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);
{
struct intel_connector *intel_connector = to_intel_connector(connector);
struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
+ int max_pixclk = to_i915(connector->dev)->max_dotclk_freq;
if (mode->hdisplay > fixed_mode->hdisplay)
return MODE_PANEL;
if (mode->vdisplay > fixed_mode->vdisplay)
return MODE_PANEL;
+ if (fixed_mode->clock > max_pixclk)
+ return MODE_CLOCK_HIGH;
return MODE_OK;
}
if (HAS_PCH_SPLIT(dev)) {
I915_WRITE(PCH_PP_CONTROL,
I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS);
- } else {
+ } else if (INTEL_INFO(dev_priv)->gen < 5) {
I915_WRITE(PP_CONTROL,
I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS);
}
DRM_DEBUG_KMS("LVDS is not present in VBT, but enabled anyway\n");
}
+ /* Set the Panel Power On/Off timings if uninitialized. */
+ if (INTEL_INFO(dev_priv)->gen < 5 &&
+ I915_READ(PP_ON_DELAYS) == 0 && I915_READ(PP_OFF_DELAYS) == 0) {
+ /* Set T2 to 40ms and T5 to 200ms */
+ I915_WRITE(PP_ON_DELAYS, 0x019007d0);
+
+ /* Set T3 to 35ms and Tx to 200ms */
+ I915_WRITE(PP_OFF_DELAYS, 0x015e07d0);
+
+ DRM_DEBUG_KMS("Panel power timings uninitialized, setting defaults\n");
+ }
+
lvds_encoder = kzalloc(sizeof(*lvds_encoder), GFP_KERNEL);
if (!lvds_encoder)
return;
return val;
}
-static u32 bdw_get_backlight(struct intel_connector *connector)
+static u32 lpt_get_backlight(struct intel_connector *connector)
{
struct drm_device *dev = connector->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
return val;
}
-static void bdw_set_backlight(struct intel_connector *connector, u32 level)
+static void lpt_set_backlight(struct intel_connector *connector, u32 level)
{
struct drm_device *dev = connector->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
mutex_unlock(&dev_priv->backlight_lock);
}
+static void lpt_disable_backlight(struct intel_connector *connector)
+{
+ struct drm_device *dev = connector->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 tmp;
+
+ intel_panel_actually_set_backlight(connector, 0);
+
+ tmp = I915_READ(BLC_PWM_PCH_CTL1);
+ I915_WRITE(BLC_PWM_PCH_CTL1, tmp & ~BLM_PCH_PWM_ENABLE);
+}
+
static void pch_disable_backlight(struct intel_connector *connector)
{
struct drm_device *dev = connector->base.dev;
return;
/*
- * Do not disable backlight on the vgaswitcheroo path. When switching
+ * Do not disable backlight on the vga_switcheroo path. When switching
* away from i915, the other client may depend on i915 to handle the
* backlight. This will leave the backlight on unnecessarily when
* another client is not activated.
mutex_unlock(&dev_priv->backlight_lock);
}
-static void bdw_enable_backlight(struct intel_connector *connector)
+static void lpt_enable_backlight(struct intel_connector *connector)
{
struct drm_device *dev = connector->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
#endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */
/*
- * Note: The setup hooks can't assume pipe is set!
+ * SPT: This value represents the period of the PWM stream in clock periods
+ * multiplied by 16 (default increment) or 128 (alternate increment selected in
+ * SCHICKEN_1 bit 0). PWM clock is 24 MHz.
+ */
+static u32 spt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+ struct drm_device *dev = connector->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 mul, clock;
+
+ if (I915_READ(SOUTH_CHICKEN1) & SPT_PWM_GRANULARITY)
+ mul = 128;
+ else
+ mul = 16;
+
+ clock = MHz(24);
+
+ return clock / (pwm_freq_hz * mul);
+}
+
+/*
+ * LPT: This value represents the period of the PWM stream in clock periods
+ * multiplied by 128 (default increment) or 16 (alternate increment, selected in
+ * LPT SOUTH_CHICKEN2 register bit 5).
+ */
+static u32 lpt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+ struct drm_device *dev = connector->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 mul, clock;
+
+ if (I915_READ(SOUTH_CHICKEN2) & LPT_PWM_GRANULARITY)
+ mul = 16;
+ else
+ mul = 128;
+
+ if (dev_priv->pch_id == INTEL_PCH_LPT_DEVICE_ID_TYPE)
+ clock = MHz(135); /* LPT:H */
+ else
+ clock = MHz(24); /* LPT:LP */
+
+ return clock / (pwm_freq_hz * mul);
+}
+
+/*
+ * ILK/SNB/IVB: This value represents the period of the PWM stream in PCH
+ * display raw clocks multiplied by 128.
+ */
+static u32 pch_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+ struct drm_device *dev = connector->base.dev;
+ int clock = MHz(intel_pch_rawclk(dev));
+
+ return clock / (pwm_freq_hz * 128);
+}
+
+/*
+ * Gen2: This field determines the number of time base events (display core
+ * clock frequency/32) in total for a complete cycle of modulated backlight
+ * control.
*
- * XXX: Query mode clock or hardware clock and program PWM modulation frequency
- * appropriately when it's 0. Use VBT and/or sane defaults.
+ * Gen3: A time base event equals the display core clock ([DevPNV] HRAW clock)
+ * divided by 32.
+ */
+static u32 i9xx_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+ struct drm_device *dev = connector->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int clock;
+
+ if (IS_PINEVIEW(dev))
+ clock = intel_hrawclk(dev);
+ else
+ clock = 1000 * dev_priv->display.get_display_clock_speed(dev);
+
+ return clock / (pwm_freq_hz * 32);
+}
+
+/*
+ * Gen4: This value represents the period of the PWM stream in display core
+ * clocks multiplied by 128.
+ */
+static u32 i965_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+ struct drm_device *dev = connector->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int clock = 1000 * dev_priv->display.get_display_clock_speed(dev);
+
+ return clock / (pwm_freq_hz * 128);
+}
+
+/*
+ * VLV: This value represents the period of the PWM stream in display core
+ * clocks ([DevCTG] 200MHz HRAW clocks) multiplied by 128 or 25MHz S0IX clocks
+ * multiplied by 16. CHV uses a 19.2MHz S0IX clock.
+ */
+static u32 vlv_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
+{
+ struct drm_device *dev = connector->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int clock;
+
+ if ((I915_READ(CBR1_VLV) & CBR_PWM_CLOCK_MUX_SELECT) == 0) {
+ if (IS_CHERRYVIEW(dev))
+ return KHz(19200) / (pwm_freq_hz * 16);
+ else
+ return MHz(25) / (pwm_freq_hz * 16);
+ } else {
+ clock = intel_hrawclk(dev);
+ return MHz(clock) / (pwm_freq_hz * 128);
+ }
+}
+
+static u32 get_backlight_max_vbt(struct intel_connector *connector)
+{
+ struct drm_device *dev = connector->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u16 pwm_freq_hz = dev_priv->vbt.backlight.pwm_freq_hz;
+ u32 pwm;
+
+ if (!pwm_freq_hz) {
+ DRM_DEBUG_KMS("backlight frequency not specified in VBT\n");
+ return 0;
+ }
+
+ if (!dev_priv->display.backlight_hz_to_pwm) {
+ DRM_DEBUG_KMS("backlight frequency setting from VBT currently not supported on this platform\n");
+ return 0;
+ }
+
+ pwm = dev_priv->display.backlight_hz_to_pwm(connector, pwm_freq_hz);
+ if (!pwm) {
+ DRM_DEBUG_KMS("backlight frequency conversion failed\n");
+ return 0;
+ }
+
+ DRM_DEBUG_KMS("backlight frequency %u Hz from VBT\n", pwm_freq_hz);
+
+ return pwm;
+}
+
+/*
+ * Note: The setup hooks can't assume pipe is set!
*/
static u32 get_backlight_min_vbt(struct intel_connector *connector)
{
return scale(min, 0, 255, 0, panel->backlight.max);
}
-static int bdw_setup_backlight(struct intel_connector *connector, enum pipe unused)
+static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unused)
{
struct drm_device *dev = connector->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
pch_ctl2 = I915_READ(BLC_PWM_PCH_CTL2);
panel->backlight.max = pch_ctl2 >> 16;
+
+ if (!panel->backlight.max)
+ panel->backlight.max = get_backlight_max_vbt(connector);
+
if (!panel->backlight.max)
return -ENODEV;
panel->backlight.min = get_backlight_min_vbt(connector);
- val = bdw_get_backlight(connector);
+ val = lpt_get_backlight(connector);
panel->backlight.level = intel_panel_compute_brightness(connector, val);
panel->backlight.enabled = (pch_ctl1 & BLM_PCH_PWM_ENABLE) &&
pch_ctl2 = I915_READ(BLC_PWM_PCH_CTL2);
panel->backlight.max = pch_ctl2 >> 16;
+
+ if (!panel->backlight.max)
+ panel->backlight.max = get_backlight_max_vbt(connector);
+
if (!panel->backlight.max)
return -ENODEV;
panel->backlight.active_low_pwm = ctl & BLM_POLARITY_PNV;
panel->backlight.max = ctl >> 17;
- if (panel->backlight.combination_mode)
- panel->backlight.max *= 0xff;
+
+ if (!panel->backlight.max) {
+ panel->backlight.max = get_backlight_max_vbt(connector);
+ panel->backlight.max >>= 1;
+ }
if (!panel->backlight.max)
return -ENODEV;
+ if (panel->backlight.combination_mode)
+ panel->backlight.max *= 0xff;
+
panel->backlight.min = get_backlight_min_vbt(connector);
val = i9xx_get_backlight(connector);
ctl = I915_READ(BLC_PWM_CTL);
panel->backlight.max = ctl >> 16;
- if (panel->backlight.combination_mode)
- panel->backlight.max *= 0xff;
+
+ if (!panel->backlight.max)
+ panel->backlight.max = get_backlight_max_vbt(connector);
if (!panel->backlight.max)
return -ENODEV;
+ if (panel->backlight.combination_mode)
+ panel->backlight.max *= 0xff;
+
panel->backlight.min = get_backlight_min_vbt(connector);
val = i9xx_get_backlight(connector);
struct drm_device *dev = connector->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_panel *panel = &connector->panel;
- enum pipe p;
u32 ctl, ctl2, val;
- for_each_pipe(dev_priv, p) {
- u32 cur_val = I915_READ(VLV_BLC_PWM_CTL(p));
-
- /* Skip if the modulation freq is already set */
- if (cur_val & ~BACKLIGHT_DUTY_CYCLE_MASK)
- continue;
-
- cur_val &= BACKLIGHT_DUTY_CYCLE_MASK;
- I915_WRITE(VLV_BLC_PWM_CTL(p), (0xf42 << 16) |
- cur_val);
- }
-
if (WARN_ON(pipe != PIPE_A && pipe != PIPE_B))
return -ENODEV;
ctl = I915_READ(VLV_BLC_PWM_CTL(pipe));
panel->backlight.max = ctl >> 16;
+
+ if (!panel->backlight.max)
+ panel->backlight.max = get_backlight_max_vbt(connector);
+
if (!panel->backlight.max)
return -ENODEV;
panel->backlight.active_low_pwm = pwm_ctl & BXT_BLC_PWM_POLARITY;
panel->backlight.max = I915_READ(BXT_BLC_PWM_FREQ1);
+
+ if (!panel->backlight.max)
+ panel->backlight.max = get_backlight_max_vbt(connector);
+
if (!panel->backlight.max)
return -ENODEV;
dev_priv->display.disable_backlight = bxt_disable_backlight;
dev_priv->display.set_backlight = bxt_set_backlight;
dev_priv->display.get_backlight = bxt_get_backlight;
- } else if (IS_BROADWELL(dev) || IS_SKYLAKE(dev)) {
- dev_priv->display.setup_backlight = bdw_setup_backlight;
- dev_priv->display.enable_backlight = bdw_enable_backlight;
- dev_priv->display.disable_backlight = pch_disable_backlight;
- dev_priv->display.set_backlight = bdw_set_backlight;
- dev_priv->display.get_backlight = bdw_get_backlight;
+ } else if (HAS_PCH_LPT(dev) || HAS_PCH_SPT(dev)) {
+ dev_priv->display.setup_backlight = lpt_setup_backlight;
+ dev_priv->display.enable_backlight = lpt_enable_backlight;
+ dev_priv->display.disable_backlight = lpt_disable_backlight;
+ dev_priv->display.set_backlight = lpt_set_backlight;
+ dev_priv->display.get_backlight = lpt_get_backlight;
+ if (HAS_PCH_LPT(dev))
+ dev_priv->display.backlight_hz_to_pwm = lpt_hz_to_pwm;
+ else
+ dev_priv->display.backlight_hz_to_pwm = spt_hz_to_pwm;
} else if (HAS_PCH_SPLIT(dev)) {
dev_priv->display.setup_backlight = pch_setup_backlight;
dev_priv->display.enable_backlight = pch_enable_backlight;
dev_priv->display.disable_backlight = pch_disable_backlight;
dev_priv->display.set_backlight = pch_set_backlight;
dev_priv->display.get_backlight = pch_get_backlight;
+ dev_priv->display.backlight_hz_to_pwm = pch_hz_to_pwm;
} else if (IS_VALLEYVIEW(dev)) {
if (dev_priv->vbt.has_mipi) {
dev_priv->display.setup_backlight = pwm_setup_backlight;
dev_priv->display.disable_backlight = vlv_disable_backlight;
dev_priv->display.set_backlight = vlv_set_backlight;
dev_priv->display.get_backlight = vlv_get_backlight;
+ dev_priv->display.backlight_hz_to_pwm = vlv_hz_to_pwm;
}
} else if (IS_GEN4(dev)) {
dev_priv->display.setup_backlight = i965_setup_backlight;
dev_priv->display.disable_backlight = i965_disable_backlight;
dev_priv->display.set_backlight = i9xx_set_backlight;
dev_priv->display.get_backlight = i9xx_get_backlight;
+ dev_priv->display.backlight_hz_to_pwm = i965_hz_to_pwm;
} else {
dev_priv->display.setup_backlight = i9xx_setup_backlight;
dev_priv->display.enable_backlight = i9xx_enable_backlight;
dev_priv->display.disable_backlight = i9xx_disable_backlight;
dev_priv->display.set_backlight = i9xx_set_backlight;
dev_priv->display.get_backlight = i9xx_get_backlight;
+ dev_priv->display.backlight_hz_to_pwm = i9xx_hz_to_pwm;
}
}
gen9_init_clock_gating(dev);
+ /* WaDisableSDEUnitClockGating:bxt */
+ I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
+ GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+
/*
* FIXME:
- * GEN8_SDEUNIT_CLOCK_GATE_DISABLE applies on A0 only.
* GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ applies on 3x6 GT SKUs only.
*/
- /* WaDisableSDEUnitClockGating:bxt */
I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
- GEN8_SDEUNIT_CLOCK_GATE_DISABLE |
GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ);
- /* FIXME: apply on A0 only */
- I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_TLBPF);
+ if (INTEL_REVID(dev) == BXT_REVID_A0) {
+ /*
+ * Hardware specification requires this bit to be
+ * set to 1 for A0
+ */
+ I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_TLBPF);
+ }
+
+ /* WaSetClckGatingDisableMedia:bxt */
+ if (INTEL_REVID(dev) == BXT_REVID_A0) {
+ I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) &
+ ~GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE));
+ }
}
static void i915_pineview_get_mem_freq(struct drm_device *dev)
if (fb) {
p->plane[0].enabled = true;
p->plane[0].bytes_per_pixel = fb->pixel_format == DRM_FORMAT_NV12 ?
- drm_format_plane_cpp(fb->pixel_format, 1) : fb->bits_per_pixel / 8;
+ drm_format_plane_cpp(fb->pixel_format, 1) :
+ drm_format_plane_cpp(fb->pixel_format, 0);
p->plane[0].y_bytes_per_pixel = fb->pixel_format == DRM_FORMAT_NV12 ?
drm_format_plane_cpp(fb->pixel_format, 0) : 0;
p->plane[0].tiling = fb->modifier[0];
}
}
+static void skl_clear_wm(struct skl_wm_values *watermarks, enum pipe pipe)
+{
+ watermarks->wm_linetime[pipe] = 0;
+ memset(watermarks->plane[pipe], 0,
+ sizeof(uint32_t) * 8 * I915_MAX_PLANES);
+ memset(watermarks->cursor[pipe], 0, sizeof(uint32_t) * 8);
+ memset(watermarks->plane_trans[pipe],
+ 0, sizeof(uint32_t) * I915_MAX_PLANES);
+ watermarks->cursor_trans[pipe] = 0;
+
+ /* Clear ddb entries for pipe */
+ memset(&watermarks->ddb.pipe[pipe], 0, sizeof(struct skl_ddb_entry));
+ memset(&watermarks->ddb.plane[pipe], 0,
+ sizeof(struct skl_ddb_entry) * I915_MAX_PLANES);
+ memset(&watermarks->ddb.y_plane[pipe], 0,
+ sizeof(struct skl_ddb_entry) * I915_MAX_PLANES);
+ memset(&watermarks->ddb.cursor[pipe], 0, sizeof(struct skl_ddb_entry));
+
+}
+
static void skl_update_wm(struct drm_crtc *crtc)
{
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
struct skl_pipe_wm pipe_wm = {};
struct intel_wm_config config = {};
- memset(results, 0, sizeof(*results));
+
+ /* Clear all dirty flags */
+ memset(results->dirty, 0, sizeof(bool) * I915_MAX_PIPES);
+
+ skl_clear_wm(results, intel_crtc->pipe);
skl_compute_wm_global_parameters(dev, &config);
fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >>
MEMMODE_FSTART_SHIFT;
- vstart = (I915_READ(PXVFREQ_BASE + (fstart * 4)) & PXVFREQ_PX_MASK) >>
+ vstart = (I915_READ(PXVFREQ(fstart)) & PXVFREQ_PX_MASK) >>
PXVFREQ_PX_SHIFT;
dev_priv->ips.fmax = fmax; /* IPS callback will increase this */
ironlake_set_drps(dev, fstart);
- dev_priv->ips.last_count1 = I915_READ(0x112e4) + I915_READ(0x112e8) +
- I915_READ(0x112e0);
+ dev_priv->ips.last_count1 = I915_READ(DMIEC) +
+ I915_READ(DDREC) + I915_READ(CSIEC);
dev_priv->ips.last_time1 = jiffies_to_msecs(jiffies);
- dev_priv->ips.last_count2 = I915_READ(0x112f4);
+ dev_priv->ips.last_count2 = I915_READ(GFXEC);
dev_priv->ips.last_time2 = ktime_get_raw_ns();
spin_unlock_irq(&mchdev_lock);
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ /* WaGsvDisableTurbo: Workaround to disable turbo on BXT A* */
+ if (IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0))
+ return;
+
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
WARN_ON(val > dev_priv->rps.max_freq);
WARN_ON(val < dev_priv->rps.min_freq);
gen6_init_rps_frequencies(dev);
+ /* WaGsvDisableTurbo: Workaround to disable turbo on BXT A* */
+ if (IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) {
+ intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+ return;
+ }
+
/* Program defaults and thresholds for RPS*/
I915_WRITE(GEN6_RC_VIDEO_FREQ,
GEN9_FREQUENCY(dev_priv->rps.rp1_freq));
I915_WRITE(GEN6_RC_CONTROL, 0);
/* 2b: Program RC6 thresholds.*/
- I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
+
+ /* WaRsDoubleRc6WrlWithCoarsePowerGating: Doubling WRL only when CPG is enabled */
+ if (IS_SKYLAKE(dev) && !((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) &&
+ (INTEL_REVID(dev) <= SKL_REVID_E0)))
+ I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16);
+ else
+ I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
for_each_ring(ring, dev_priv, unused)
I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+
+ if (HAS_GUC_UCODE(dev))
+ I915_WRITE(GUC_MAX_IDLE_COUNT, 0xA);
+
I915_WRITE(GEN6_RC_SLEEP, 0);
I915_WRITE(GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */
rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
DRM_INFO("RC6 %s\n", (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ?
"on" : "off");
- I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
- GEN6_RC_CTL_EI_MODE(1) |
- rc6_mask);
+
+ if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_D0) ||
+ (IS_BROXTON(dev) && INTEL_REVID(dev) <= BXT_REVID_A0))
+ I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
+ GEN7_RC_CTL_TO_MODE |
+ rc6_mask);
+ else
+ I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
+ GEN6_RC_CTL_EI_MODE(1) |
+ rc6_mask);
/*
* 3b: Enable Coarse Power Gating only when RC6 is enabled.
- * WaDisableRenderPowerGating:skl,bxt - Render PG need to be disabled with RC6.
+ * WaRsDisableCoarsePowerGating:skl,bxt - Render/Media PG need to be disabled with RC6.
*/
- I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ?
- GEN9_MEDIA_PG_ENABLE : 0);
-
+ if ((IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) ||
+ ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && (INTEL_REVID(dev) <= SKL_REVID_E0)))
+ I915_WRITE(GEN9_PG_ENABLE, 0);
+ else
+ I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ?
+ (GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE) : 0);
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
/* RPS code assumes GPLL is used */
WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n");
- DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & GPLLENABLE ? "yes" : "no");
+ DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
dev_priv->rps.cur_freq = (val >> 8) & 0xff;
/* RPS code assumes GPLL is used */
WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n");
- DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & GPLLENABLE ? "yes" : "no");
+ DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
dev_priv->rps.cur_freq = (val >> 8) & 0xff;
assert_spin_locked(&mchdev_lock);
- pxvid = I915_READ(PXVFREQ_BASE + (dev_priv->rps.cur_freq * 4));
+ pxvid = I915_READ(PXVFREQ(dev_priv->rps.cur_freq));
pxvid = (pxvid >> 24) & 0x7f;
ext_v = pvid_to_extvid(dev_priv, pxvid);
I915_WRITE(CSIEW2, 0x04000004);
for (i = 0; i < 5; i++)
- I915_WRITE(PEW + (i * 4), 0);
+ I915_WRITE(PEW(i), 0);
for (i = 0; i < 3; i++)
- I915_WRITE(DEW + (i * 4), 0);
+ I915_WRITE(DEW(i), 0);
/* Program P-state weights to account for frequency power adjustment */
for (i = 0; i < 16; i++) {
- u32 pxvidfreq = I915_READ(PXVFREQ_BASE + (i * 4));
+ u32 pxvidfreq = I915_READ(PXVFREQ(i));
unsigned long freq = intel_pxfreq(pxvidfreq);
unsigned long vid = (pxvidfreq & PXVFREQ_PX_MASK) >>
PXVFREQ_PX_SHIFT;
for (i = 0; i < 4; i++) {
u32 val = (pxw[i*4] << 24) | (pxw[(i*4)+1] << 16) |
(pxw[(i*4)+2] << 8) | (pxw[(i*4)+3]);
- I915_WRITE(PXW + (i * 4), val);
+ I915_WRITE(PXW(i), val);
}
/* Adjust magic regs to magic values (more experimental results) */
I915_WRITE(EG7, 0);
for (i = 0; i < 8; i++)
- I915_WRITE(PXWL + (i * 4), 0);
+ I915_WRITE(PXWL(i), 0);
/* Enable PMON + select events */
I915_WRITE(ECR, 0x80000019);
* TODO: this bit should only be enabled when really needed, then
* disabled when not needed anymore in order to save power.
*/
- if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE)
+ if (HAS_PCH_LPT_LP(dev))
I915_WRITE(SOUTH_DSPCLK_GATE_D,
I915_READ(SOUTH_DSPCLK_GATE_D) |
PCH_LP_PARTITION_LEVEL_DISABLE);
{
struct drm_i915_private *dev_priv = dev->dev_private;
- if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+ if (HAS_PCH_LPT_LP(dev)) {
uint32_t val = I915_READ(SOUTH_DSPCLK_GATE_D);
val &= ~PCH_LP_PARTITION_LEVEL_DISABLE;
tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE;
WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp);
+ /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt */
+ if (IS_SKYLAKE(dev) ||
+ (IS_BROXTON(dev) && INTEL_REVID(dev) <= BXT_REVID_B0)) {
+ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
+ GEN8_SAMPLER_POWER_BYPASS_DIS);
+ }
+
+ /* WaDisableSTUnitPowerOptimization:skl,bxt */
+ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
+
return 0;
}
return 0;
}
-void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
+static void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
{
drm_gem_object_unreference(&ringbuf->obj->base);
ringbuf->obj = NULL;
}
-int intel_alloc_ringbuffer_obj(struct drm_device *dev,
- struct intel_ringbuffer *ringbuf)
+static int intel_alloc_ringbuffer_obj(struct drm_device *dev,
+ struct intel_ringbuffer *ringbuf)
{
struct drm_i915_gem_object *obj;
return 0;
}
+struct intel_ringbuffer *
+intel_engine_create_ringbuffer(struct intel_engine_cs *engine, int size)
+{
+ struct intel_ringbuffer *ring;
+ int ret;
+
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+ if (ring == NULL)
+ return ERR_PTR(-ENOMEM);
+
+ ring->ring = engine;
+
+ ring->size = size;
+ /* Workaround an erratum on the i830 which causes a hang if
+ * the TAIL pointer points to within the last 2 cachelines
+ * of the buffer.
+ */
+ ring->effective_size = size;
+ if (IS_I830(engine->dev) || IS_845G(engine->dev))
+ ring->effective_size -= 2 * CACHELINE_BYTES;
+
+ ring->last_retired_head = -1;
+ intel_ring_update_space(ring);
+
+ ret = intel_alloc_ringbuffer_obj(engine->dev, ring);
+ if (ret) {
+ DRM_ERROR("Failed to allocate ringbuffer %s: %d\n",
+ engine->name, ret);
+ kfree(ring);
+ return ERR_PTR(ret);
+ }
+
+ return ring;
+}
+
+void
+intel_ringbuffer_free(struct intel_ringbuffer *ring)
+{
+ intel_destroy_ringbuffer_obj(ring);
+ kfree(ring);
+}
+
static int intel_init_ring_buffer(struct drm_device *dev,
struct intel_engine_cs *ring)
{
WARN_ON(ring->buffer);
- ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);
- if (!ringbuf)
- return -ENOMEM;
- ring->buffer = ringbuf;
-
ring->dev = dev;
INIT_LIST_HEAD(&ring->active_list);
INIT_LIST_HEAD(&ring->request_list);
INIT_LIST_HEAD(&ring->execlist_queue);
i915_gem_batch_pool_init(dev, &ring->batch_pool);
- ringbuf->size = 32 * PAGE_SIZE;
- ringbuf->ring = ring;
memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno));
init_waitqueue_head(&ring->irq_queue);
+ ringbuf = intel_engine_create_ringbuffer(ring, 32 * PAGE_SIZE);
+ if (IS_ERR(ringbuf))
+ return PTR_ERR(ringbuf);
+ ring->buffer = ringbuf;
+
if (I915_NEED_GFX_HWS(dev)) {
ret = init_status_page(ring);
if (ret)
goto error;
}
- WARN_ON(ringbuf->obj);
-
- ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
- if (ret) {
- DRM_ERROR("Failed to allocate ringbuffer %s: %d\n",
- ring->name, ret);
- goto error;
- }
-
ret = intel_pin_and_map_ringbuffer_obj(dev, ringbuf);
if (ret) {
DRM_ERROR("Failed to pin and map ringbuffer %s: %d\n",
goto error;
}
- /* Workaround an erratum on the i830 which causes a hang if
- * the TAIL pointer points to within the last 2 cachelines
- * of the buffer.
- */
- ringbuf->effective_size = ringbuf->size;
- if (IS_I830(dev) || IS_845G(dev))
- ringbuf->effective_size -= 2 * CACHELINE_BYTES;
-
ret = i915_cmd_parser_init_ring(ring);
if (ret)
goto error;
return 0;
error:
- kfree(ringbuf);
+ intel_ringbuffer_free(ringbuf);
ring->buffer = NULL;
return ret;
}
void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
{
struct drm_i915_private *dev_priv;
- struct intel_ringbuffer *ringbuf;
if (!intel_ring_initialized(ring))
return;
dev_priv = to_i915(ring->dev);
- ringbuf = ring->buffer;
intel_stop_ring_buffer(ring);
WARN_ON(!IS_GEN2(ring->dev) && (I915_READ_MODE(ring) & MODE_IDLE) == 0);
- intel_unpin_ringbuffer_obj(ringbuf);
- intel_destroy_ringbuffer_obj(ringbuf);
+ intel_unpin_ringbuffer_obj(ring->buffer);
+ intel_ringbuffer_free(ring->buffer);
+ ring->buffer = NULL;
if (ring->cleanup)
ring->cleanup(ring);
i915_cmd_parser_fini_ring(ring);
i915_gem_batch_pool_fini(&ring->batch_pool);
-
- kfree(ringbuf);
- ring->buffer = NULL;
}
static int ring_wait_for_space(struct intel_engine_cs *ring, int n)
return idx;
}
+static inline void
+intel_flush_status_page(struct intel_engine_cs *ring, int reg)
+{
+ drm_clflush_virt_range(&ring->status_page.page_addr[reg],
+ sizeof(uint32_t));
+}
+
static inline u32
intel_read_status_page(struct intel_engine_cs *ring,
int reg)
#define I915_GEM_HWS_SCRATCH_INDEX 0x40
#define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
-void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf);
+struct intel_ringbuffer *
+intel_engine_create_ringbuffer(struct intel_engine_cs *engine, int size);
int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
struct intel_ringbuffer *ringbuf);
-void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf);
-int intel_alloc_ringbuffer_obj(struct drm_device *dev,
- struct intel_ringbuffer *ringbuf);
+void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf);
+void intel_ringbuffer_free(struct intel_ringbuffer *ring);
void intel_stop_ring_buffer(struct intel_engine_cs *ring);
void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
bool pg2_enabled = intel_display_power_well_is_enabled(dev_priv,
SKL_DISP_PW_2);
- WARN(!IS_SKYLAKE(dev), "Platform doesn't support DC5.\n");
- WARN(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n");
- WARN(pg2_enabled, "PG2 not disabled to enable DC5.\n");
+ WARN_ONCE(!IS_SKYLAKE(dev), "Platform doesn't support DC5.\n");
+ WARN_ONCE(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n");
+ WARN_ONCE(pg2_enabled, "PG2 not disabled to enable DC5.\n");
- WARN((I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC5),
- "DC5 already programmed to be enabled.\n");
- WARN(dev_priv->pm.suspended,
- "DC5 cannot be enabled, if platform is runtime-suspended.\n");
+ WARN_ONCE((I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC5),
+ "DC5 already programmed to be enabled.\n");
+ WARN_ONCE(dev_priv->pm.suspended,
+ "DC5 cannot be enabled, if platform is runtime-suspended.\n");
assert_csr_loaded(dev_priv);
}
if (dev_priv->power_domains.initializing)
return;
- WARN(!pg2_enabled, "PG2 not enabled to disable DC5.\n");
- WARN(dev_priv->pm.suspended,
+ WARN_ONCE(!pg2_enabled, "PG2 not enabled to disable DC5.\n");
+ WARN_ONCE(dev_priv->pm.suspended,
"Disabling of DC5 while platform is runtime-suspended should never happen.\n");
}
{
struct drm_device *dev = dev_priv->dev;
- WARN(!IS_SKYLAKE(dev), "Platform doesn't support DC6.\n");
- WARN(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n");
- WARN(I915_READ(UTIL_PIN_CTL) & UTIL_PIN_ENABLE,
- "Backlight is not disabled.\n");
- WARN((I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC6),
- "DC6 already programmed to be enabled.\n");
+ WARN_ONCE(!IS_SKYLAKE(dev), "Platform doesn't support DC6.\n");
+ WARN_ONCE(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n");
+ WARN_ONCE(I915_READ(UTIL_PIN_CTL) & UTIL_PIN_ENABLE,
+ "Backlight is not disabled.\n");
+ WARN_ONCE((I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC6),
+ "DC6 already programmed to be enabled.\n");
assert_csr_loaded(dev_priv);
}
return;
assert_csr_loaded(dev_priv);
- WARN(!(I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC6),
- "DC6 already programmed to be disabled.\n");
+ WARN_ONCE(!(I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC6),
+ "DC6 already programmed to be disabled.\n");
}
static void skl_enable_dc6(struct drm_i915_private *dev_priv)
wait_for((state = intel_csr_load_status_get(dev_priv)) !=
FW_UNINITIALIZED, 1000);
if (state != FW_LOADED)
- DRM_ERROR("CSR firmware not ready (%d)\n",
+ DRM_DEBUG("CSR firmware not ready (%d)\n",
state);
else
if (SKL_ENABLE_DC6(dev))
static void vlv_display_power_well_init(struct drm_i915_private *dev_priv)
{
+ enum pipe pipe;
+
+ /*
+ * Enable the CRI clock source so we can get at the
+ * display and the reference clock for VGA
+ * hotplug / manual detection. Supposedly DSI also
+ * needs the ref clock up and running.
+ *
+ * CHV DPLL B/C have some issues if VGA mode is enabled.
+ */
+ for_each_pipe(dev_priv->dev, pipe) {
+ u32 val = I915_READ(DPLL(pipe));
+
+ val |= DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS;
+ if (pipe != PIPE_A)
+ val |= DPLL_INTEGRATED_CRI_CLK_VLV;
+
+ I915_WRITE(DPLL(pipe), val);
+ }
spin_lock_irq(&dev_priv->irq_lock);
valleyview_enable_display_irqs(dev_priv);
{
WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC);
- /*
- * Enable the CRI clock source so we can get at the
- * display and the reference clock for VGA
- * hotplug / manual detection.
- */
- I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) | DPLL_VGA_MODE_DIS |
- DPLL_REF_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV);
+ /* since ref/cri clock was enabled */
udelay(1); /* >10ns for cmnreset, >0ns for sidereset */
vlv_set_power_well(dev_priv, power_well, true);
vlv_set_power_well(dev_priv, power_well, false);
}
+#define POWER_DOMAIN_MASK (BIT(POWER_DOMAIN_NUM) - 1)
+
+static struct i915_power_well *lookup_power_well(struct drm_i915_private *dev_priv,
+ int power_well_id)
+{
+ struct i915_power_domains *power_domains = &dev_priv->power_domains;
+ struct i915_power_well *power_well;
+ int i;
+
+ for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) {
+ if (power_well->data == power_well_id)
+ return power_well;
+ }
+
+ return NULL;
+}
+
+#define BITS_SET(val, bits) (((val) & (bits)) == (bits))
+
+static void assert_chv_phy_status(struct drm_i915_private *dev_priv)
+{
+ struct i915_power_well *cmn_bc =
+ lookup_power_well(dev_priv, PUNIT_POWER_WELL_DPIO_CMN_BC);
+ struct i915_power_well *cmn_d =
+ lookup_power_well(dev_priv, PUNIT_POWER_WELL_DPIO_CMN_D);
+ u32 phy_control = dev_priv->chv_phy_control;
+ u32 phy_status = 0;
+ u32 tmp;
+
+ if (cmn_bc->ops->is_enabled(dev_priv, cmn_bc)) {
+ phy_status |= PHY_POWERGOOD(DPIO_PHY0);
+
+ /* this assumes override is only used to enable lanes */
+ if ((phy_control & PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH0)) == 0)
+ phy_control |= PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH0);
+
+ if ((phy_control & PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH1)) == 0)
+ phy_control |= PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH1);
+
+ /* CL1 is on whenever anything is on in either channel */
+ if (BITS_SET(phy_control,
+ PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH0) |
+ PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH1)))
+ phy_status |= PHY_STATUS_CMN_LDO(DPIO_PHY0, DPIO_CH0);
+
+ /*
+ * The DPLLB check accounts for the pipe B + port A usage
+ * with CL2 powered up but all the lanes in the second channel
+ * powered down.
+ */
+ if (BITS_SET(phy_control,
+ PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH1)) &&
+ (I915_READ(DPLL(PIPE_B)) & DPLL_VCO_ENABLE) == 0)
+ phy_status |= PHY_STATUS_CMN_LDO(DPIO_PHY0, DPIO_CH1);
+
+ if (BITS_SET(phy_control,
+ PHY_CH_POWER_DOWN_OVRD(0x3, DPIO_PHY0, DPIO_CH0)))
+ phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH0, 0);
+ if (BITS_SET(phy_control,
+ PHY_CH_POWER_DOWN_OVRD(0xc, DPIO_PHY0, DPIO_CH0)))
+ phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH0, 1);
+
+ if (BITS_SET(phy_control,
+ PHY_CH_POWER_DOWN_OVRD(0x3, DPIO_PHY0, DPIO_CH1)))
+ phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH1, 0);
+ if (BITS_SET(phy_control,
+ PHY_CH_POWER_DOWN_OVRD(0xc, DPIO_PHY0, DPIO_CH1)))
+ phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH1, 1);
+ }
+
+ if (cmn_d->ops->is_enabled(dev_priv, cmn_d)) {
+ phy_status |= PHY_POWERGOOD(DPIO_PHY1);
+
+ /* this assumes override is only used to enable lanes */
+ if ((phy_control & PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY1, DPIO_CH0)) == 0)
+ phy_control |= PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY1, DPIO_CH0);
+
+ if (BITS_SET(phy_control,
+ PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY1, DPIO_CH0)))
+ phy_status |= PHY_STATUS_CMN_LDO(DPIO_PHY1, DPIO_CH0);
+
+ if (BITS_SET(phy_control,
+ PHY_CH_POWER_DOWN_OVRD(0x3, DPIO_PHY1, DPIO_CH0)))
+ phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY1, DPIO_CH0, 0);
+ if (BITS_SET(phy_control,
+ PHY_CH_POWER_DOWN_OVRD(0xc, DPIO_PHY1, DPIO_CH0)))
+ phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY1, DPIO_CH0, 1);
+ }
+
+ /*
+ * The PHY may be busy with some initial calibration and whatnot,
+ * so the power state can take a while to actually change.
+ */
+ if (wait_for((tmp = I915_READ(DISPLAY_PHY_STATUS)) == phy_status, 10))
+ WARN(phy_status != tmp,
+ "Unexpected PHY_STATUS 0x%08x, expected 0x%08x (PHY_CONTROL=0x%08x)\n",
+ tmp, phy_status, dev_priv->chv_phy_control);
+}
+
+#undef BITS_SET
+
static void chv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
struct i915_power_well *power_well)
{
enum dpio_phy phy;
+ enum pipe pipe;
+ uint32_t tmp;
WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC &&
power_well->data != PUNIT_POWER_WELL_DPIO_CMN_D);
- /*
- * Enable the CRI clock source so we can get at the
- * display and the reference clock for VGA
- * hotplug / manual detection.
- */
if (power_well->data == PUNIT_POWER_WELL_DPIO_CMN_BC) {
+ pipe = PIPE_A;
phy = DPIO_PHY0;
- I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) | DPLL_VGA_MODE_DIS |
- DPLL_REF_CLK_ENABLE_VLV);
- I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) | DPLL_VGA_MODE_DIS |
- DPLL_REF_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV);
} else {
+ pipe = PIPE_C;
phy = DPIO_PHY1;
- I915_WRITE(DPLL(PIPE_C), I915_READ(DPLL(PIPE_C)) | DPLL_VGA_MODE_DIS |
- DPLL_REF_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV);
}
+
+ /* since ref/cri clock was enabled */
udelay(1); /* >10ns for cmnreset, >0ns for sidereset */
vlv_set_power_well(dev_priv, power_well, true);
if (wait_for(I915_READ(DISPLAY_PHY_STATUS) & PHY_POWERGOOD(phy), 1))
DRM_ERROR("Display PHY %d is not power up\n", phy);
+ mutex_lock(&dev_priv->sb_lock);
+
+ /* Enable dynamic power down */
+ tmp = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW28);
+ tmp |= DPIO_DYNPWRDOWNEN_CH0 | DPIO_CL1POWERDOWNEN |
+ DPIO_SUS_CLK_CONFIG_GATE_CLKREQ;
+ vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW28, tmp);
+
+ if (power_well->data == PUNIT_POWER_WELL_DPIO_CMN_BC) {
+ tmp = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW6_CH1);
+ tmp |= DPIO_DYNPWRDOWNEN_CH1;
+ vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW6_CH1, tmp);
+ } else {
+ /*
+ * Force the non-existing CL2 off. BXT does this
+ * too, so maybe it saves some power even though
+ * CL2 doesn't exist?
+ */
+ tmp = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30);
+ tmp |= DPIO_CL2_LDOFUSE_PWRENB;
+ vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, tmp);
+ }
+
+ mutex_unlock(&dev_priv->sb_lock);
+
dev_priv->chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(phy);
I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control);
+
+ DRM_DEBUG_KMS("Enabled DPIO PHY%d (PHY_CONTROL=0x%08x)\n",
+ phy, dev_priv->chv_phy_control);
+
+ assert_chv_phy_status(dev_priv);
}
static void chv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv,
I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control);
vlv_set_power_well(dev_priv, power_well, false);
+
+ DRM_DEBUG_KMS("Disabled DPIO PHY%d (PHY_CONTROL=0x%08x)\n",
+ phy, dev_priv->chv_phy_control);
+
+ assert_chv_phy_status(dev_priv);
+}
+
+static void assert_chv_phy_powergate(struct drm_i915_private *dev_priv, enum dpio_phy phy,
+ enum dpio_channel ch, bool override, unsigned int mask)
+{
+ enum pipe pipe = phy == DPIO_PHY0 ? PIPE_A : PIPE_C;
+ u32 reg, val, expected, actual;
+
+ if (ch == DPIO_CH0)
+ reg = _CHV_CMN_DW0_CH0;
+ else
+ reg = _CHV_CMN_DW6_CH1;
+
+ mutex_lock(&dev_priv->sb_lock);
+ val = vlv_dpio_read(dev_priv, pipe, reg);
+ mutex_unlock(&dev_priv->sb_lock);
+
+ /*
+ * This assumes !override is only used when the port is disabled.
+ * All lanes should power down even without the override when
+ * the port is disabled.
+ */
+ if (!override || mask == 0xf) {
+ expected = DPIO_ALLDL_POWERDOWN | DPIO_ANYDL_POWERDOWN;
+ /*
+ * If CH1 common lane is not active anymore
+ * (eg. for pipe B DPLL) the entire channel will
+ * shut down, which causes the common lane registers
+ * to read as 0. That means we can't actually check
+ * the lane power down status bits, but as the entire
+ * register reads as 0 it's a good indication that the
+ * channel is indeed entirely powered down.
+ */
+ if (ch == DPIO_CH1 && val == 0)
+ expected = 0;
+ } else if (mask != 0x0) {
+ expected = DPIO_ANYDL_POWERDOWN;
+ } else {
+ expected = 0;
+ }
+
+ if (ch == DPIO_CH0)
+ actual = val >> DPIO_ANYDL_POWERDOWN_SHIFT_CH0;
+ else
+ actual = val >> DPIO_ANYDL_POWERDOWN_SHIFT_CH1;
+ actual &= DPIO_ALLDL_POWERDOWN | DPIO_ANYDL_POWERDOWN;
+
+ WARN(actual != expected,
+ "Unexpected DPIO lane power down: all %d, any %d. Expected: all %d, any %d. (0x%x = 0x%08x)\n",
+ !!(actual & DPIO_ALLDL_POWERDOWN), !!(actual & DPIO_ANYDL_POWERDOWN),
+ !!(expected & DPIO_ALLDL_POWERDOWN), !!(expected & DPIO_ANYDL_POWERDOWN),
+ reg, val);
+}
+
+bool chv_phy_powergate_ch(struct drm_i915_private *dev_priv, enum dpio_phy phy,
+ enum dpio_channel ch, bool override)
+{
+ struct i915_power_domains *power_domains = &dev_priv->power_domains;
+ bool was_override;
+
+ mutex_lock(&power_domains->lock);
+
+ was_override = dev_priv->chv_phy_control & PHY_CH_POWER_DOWN_OVRD_EN(phy, ch);
+
+ if (override == was_override)
+ goto out;
+
+ if (override)
+ dev_priv->chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(phy, ch);
+ else
+ dev_priv->chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD_EN(phy, ch);
+
+ I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control);
+
+ DRM_DEBUG_KMS("Power gating DPIO PHY%d CH%d (DPIO_PHY_CONTROL=0x%08x)\n",
+ phy, ch, dev_priv->chv_phy_control);
+
+ assert_chv_phy_status(dev_priv);
+
+out:
+ mutex_unlock(&power_domains->lock);
+
+ return was_override;
+}
+
+void chv_phy_powergate_lanes(struct intel_encoder *encoder,
+ bool override, unsigned int mask)
+{
+ struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+ struct i915_power_domains *power_domains = &dev_priv->power_domains;
+ enum dpio_phy phy = vlv_dport_to_phy(enc_to_dig_port(&encoder->base));
+ enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
+
+ mutex_lock(&power_domains->lock);
+
+ dev_priv->chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD(0xf, phy, ch);
+ dev_priv->chv_phy_control |= PHY_CH_POWER_DOWN_OVRD(mask, phy, ch);
+
+ if (override)
+ dev_priv->chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(phy, ch);
+ else
+ dev_priv->chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD_EN(phy, ch);
+
+ I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control);
+
+ DRM_DEBUG_KMS("Power gating DPIO PHY%d CH%d lanes 0x%x (PHY_CONTROL=0x%08x)\n",
+ phy, ch, mask, dev_priv->chv_phy_control);
+
+ assert_chv_phy_status(dev_priv);
+
+ assert_chv_phy_powergate(dev_priv, phy, ch, override, mask);
+
+ mutex_unlock(&power_domains->lock);
}
static bool chv_pipe_power_well_enabled(struct drm_i915_private *dev_priv,
intel_runtime_pm_put(dev_priv);
}
-#define POWER_DOMAIN_MASK (BIT(POWER_DOMAIN_NUM) - 1)
-
#define HSW_ALWAYS_ON_POWER_DOMAINS ( \
BIT(POWER_DOMAIN_PIPE_A) | \
BIT(POWER_DOMAIN_TRANSCODER_EDP) | \
},
};
-static struct i915_power_well *lookup_power_well(struct drm_i915_private *dev_priv,
- int power_well_id)
-{
- struct i915_power_domains *power_domains = &dev_priv->power_domains;
- struct i915_power_well *power_well;
- int i;
-
- for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) {
- if (power_well->data == power_well_id)
- return power_well;
- }
-
- return NULL;
-}
-
bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv,
int power_well_id)
{
* DISPLAY_PHY_CONTROL can get corrupted if read. As a
* workaround never ever read DISPLAY_PHY_CONTROL, and
* instead maintain a shadow copy ourselves. Use the actual
- * power well state to reconstruct the expected initial
- * value.
+ * power well state and lane status to reconstruct the
+ * expected initial value.
*/
dev_priv->chv_phy_control =
PHY_LDO_SEQ_DELAY(PHY_LDO_DELAY_600NS, DPIO_PHY0) |
PHY_LDO_SEQ_DELAY(PHY_LDO_DELAY_600NS, DPIO_PHY1) |
- PHY_CH_POWER_MODE(PHY_CH_SU_PSR, DPIO_PHY0, DPIO_CH0) |
- PHY_CH_POWER_MODE(PHY_CH_SU_PSR, DPIO_PHY0, DPIO_CH1) |
- PHY_CH_POWER_MODE(PHY_CH_SU_PSR, DPIO_PHY1, DPIO_CH0);
- if (cmn_bc->ops->is_enabled(dev_priv, cmn_bc))
+ PHY_CH_POWER_MODE(PHY_CH_DEEP_PSR, DPIO_PHY0, DPIO_CH0) |
+ PHY_CH_POWER_MODE(PHY_CH_DEEP_PSR, DPIO_PHY0, DPIO_CH1) |
+ PHY_CH_POWER_MODE(PHY_CH_DEEP_PSR, DPIO_PHY1, DPIO_CH0);
+
+ /*
+ * If all lanes are disabled we leave the override disabled
+ * with all power down bits cleared to match the state we
+ * would use after disabling the port. Otherwise enable the
+ * override and set the lane powerdown bits accding to the
+ * current lane status.
+ */
+ if (cmn_bc->ops->is_enabled(dev_priv, cmn_bc)) {
+ uint32_t status = I915_READ(DPLL(PIPE_A));
+ unsigned int mask;
+
+ mask = status & DPLL_PORTB_READY_MASK;
+ if (mask == 0xf)
+ mask = 0x0;
+ else
+ dev_priv->chv_phy_control |=
+ PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH0);
+
+ dev_priv->chv_phy_control |=
+ PHY_CH_POWER_DOWN_OVRD(mask, DPIO_PHY0, DPIO_CH0);
+
+ mask = (status & DPLL_PORTC_READY_MASK) >> 4;
+ if (mask == 0xf)
+ mask = 0x0;
+ else
+ dev_priv->chv_phy_control |=
+ PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH1);
+
+ dev_priv->chv_phy_control |=
+ PHY_CH_POWER_DOWN_OVRD(mask, DPIO_PHY0, DPIO_CH1);
+
dev_priv->chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(DPIO_PHY0);
- if (cmn_d->ops->is_enabled(dev_priv, cmn_d))
+ }
+
+ if (cmn_d->ops->is_enabled(dev_priv, cmn_d)) {
+ uint32_t status = I915_READ(DPIO_PHY_STATUS);
+ unsigned int mask;
+
+ mask = status & DPLL_PORTD_READY_MASK;
+
+ if (mask == 0xf)
+ mask = 0x0;
+ else
+ dev_priv->chv_phy_control |=
+ PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY1, DPIO_CH0);
+
+ dev_priv->chv_phy_control |=
+ PHY_CH_POWER_DOWN_OVRD(mask, DPIO_PHY1, DPIO_CH0);
+
dev_priv->chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(DPIO_PHY1);
+ }
+
+ I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control);
+
+ DRM_DEBUG_KMS("Initial PHY_CONTROL=0x%08x\n",
+ dev_priv->chv_phy_control);
}
static void vlv_cmnlane_wa(struct drm_i915_private *dev_priv)
power_domains->initializing = true;
if (IS_CHERRYVIEW(dev)) {
+ mutex_lock(&power_domains->lock);
chv_phy_control_init(dev_priv);
+ mutex_unlock(&power_domains->lock);
} else if (IS_VALLEYVIEW(dev)) {
mutex_lock(&power_domains->lock);
vlv_cmnlane_wa(dev_priv);
#define IS_DIGITAL(c) (c->output_flag & (SDVO_TMDS_MASK | SDVO_LVDS_MASK))
-static const char *tv_format_names[] = {
+static const char * const tv_format_names[] = {
"NTSC_M" , "NTSC_J" , "NTSC_443",
"PAL_B" , "PAL_D" , "PAL_G" ,
"PAL_H" , "PAL_I" , "PAL_M" ,
"SECAM_60"
};
-#define TV_FORMAT_NUM (sizeof(tv_format_names) / sizeof(*tv_format_names))
+#define TV_FORMAT_NUM ARRAY_SIZE(tv_format_names)
struct intel_sdvo {
struct intel_encoder base;
DRM_DEBUG_KMS("%s: W: %02X %s\n", SDVO_NAME(intel_sdvo), cmd, buffer);
}
-static const char *cmd_status_names[] = {
+static const char * const cmd_status_names[] = {
"Power on",
"Success",
"Not supported",
*/
static void
intel_sdvo_select_ddc_bus(struct drm_i915_private *dev_priv,
- struct intel_sdvo *sdvo, u32 reg)
+ struct intel_sdvo *sdvo)
{
struct sdvo_device_mapping *mapping;
static void
intel_sdvo_select_i2c_bus(struct drm_i915_private *dev_priv,
- struct intel_sdvo *sdvo, u32 reg)
+ struct intel_sdvo *sdvo)
{
struct sdvo_device_mapping *mapping;
u8 pin;
intel_sdvo->sdvo_reg = sdvo_reg;
intel_sdvo->is_sdvob = is_sdvob;
intel_sdvo->slave_addr = intel_sdvo_get_slave_addr(dev, intel_sdvo) >> 1;
- intel_sdvo_select_i2c_bus(dev_priv, intel_sdvo, sdvo_reg);
+ intel_sdvo_select_i2c_bus(dev_priv, intel_sdvo);
if (!intel_sdvo_init_ddc_proxy(intel_sdvo, dev))
goto err_i2c_bus;
*/
intel_sdvo->base.cloneable = 0;
- intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo, sdvo_reg);
+ intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo);
/* Set the input timing to the screen. Assume always input 0. */
if (!intel_sdvo_set_target_input(intel_sdvo))
* avoid random delays. The value written to @start_vbl_count should be
* supplied to intel_pipe_update_end() for error checking.
*/
-void intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl_count)
+void intel_pipe_update_start(struct intel_crtc *crtc)
{
struct drm_device *dev = crtc->base.dev;
const struct drm_display_mode *mode = &crtc->config->base.adjusted_mode;
max = vblank_start - 1;
local_irq_disable();
- *start_vbl_count = 0;
if (min <= 0 || max <= 0)
return;
if (WARN_ON(drm_crtc_vblank_get(&crtc->base)))
return;
- trace_i915_pipe_update_start(crtc, min, max);
+ crtc->debug.min_vbl = min;
+ crtc->debug.max_vbl = max;
+ trace_i915_pipe_update_start(crtc);
for (;;) {
/*
drm_crtc_vblank_put(&crtc->base);
- *start_vbl_count = dev->driver->get_vblank_counter(dev, pipe);
+ crtc->debug.scanline_start = scanline;
+ crtc->debug.start_vbl_time = ktime_get();
+ crtc->debug.start_vbl_count =
+ dev->driver->get_vblank_counter(dev, pipe);
- trace_i915_pipe_update_vblank_evaded(crtc, min, max, *start_vbl_count);
+ trace_i915_pipe_update_vblank_evaded(crtc);
}
/**
* re-enables interrupts and verifies the update was actually completed
* before a vblank using the value of @start_vbl_count.
*/
-void intel_pipe_update_end(struct intel_crtc *crtc, u32 start_vbl_count)
+void intel_pipe_update_end(struct intel_crtc *crtc)
{
struct drm_device *dev = crtc->base.dev;
enum pipe pipe = crtc->pipe;
+ int scanline_end = intel_get_crtc_scanline(crtc);
u32 end_vbl_count = dev->driver->get_vblank_counter(dev, pipe);
+ ktime_t end_vbl_time = ktime_get();
- trace_i915_pipe_update_end(crtc, end_vbl_count);
+ trace_i915_pipe_update_end(crtc, end_vbl_count, scanline_end);
local_irq_enable();
- if (start_vbl_count && start_vbl_count != end_vbl_count)
- DRM_ERROR("Atomic update failure on pipe %c (start=%u end=%u)\n",
- pipe_name(pipe), start_vbl_count, end_vbl_count);
+ if (crtc->debug.start_vbl_count &&
+ crtc->debug.start_vbl_count != end_vbl_count) {
+ DRM_ERROR("Atomic update failure on pipe %c (start=%u end=%u) time %lld us, min %d, max %d, scanline start %d, end %d\n",
+ pipe_name(pipe), crtc->debug.start_vbl_count,
+ end_vbl_count,
+ ktime_us_delta(end_vbl_time, crtc->debug.start_vbl_time),
+ crtc->debug.min_vbl, crtc->debug.max_vbl,
+ crtc->debug.scanline_start, scanline_end);
+ }
}
static void
else if (key->flags & I915_SET_COLORKEY_SOURCE)
plane_ctl |= PLANE_CTL_KEY_ENABLE_SOURCE;
- surf_addr = intel_plane_obj_offset(intel_plane, obj);
+ surf_addr = intel_plane_obj_offset(intel_plane, obj, 0);
if (intel_rotation_90_or_270(rotation)) {
/* stride: Surface height in tiles */
tile_height = intel_tile_height(dev, fb->pixel_format,
- fb->modifier[0]);
+ fb->modifier[0], 0);
stride = DIV_ROUND_UP(fb->height, tile_height);
plane_size = (src_w << 16) | src_h;
x_offset = stride * tile_height - y - (src_h + 1);
crtc = crtc ? crtc : plane->crtc;
- plane->fb = fb;
-
if (!crtc->state->active)
return;
intel_plane->pipe = pipe;
intel_plane->plane = plane;
- intel_plane->frontbuffer_bit = INTEL_FRONTBUFFER_SPRITE(pipe);
+ intel_plane->frontbuffer_bit = INTEL_FRONTBUFFER_SPRITE(pipe, plane);
intel_plane->check_plane = intel_check_sprite_plane;
intel_plane->commit_plane = intel_commit_sprite_plane;
possible_crtcs = (1 << pipe);
j = 0;
for (i = 0; i < 60; i++)
- I915_WRITE(TV_H_LUMA_0 + (i<<2), tv_mode->filter_table[j++]);
+ I915_WRITE(TV_H_LUMA(i), tv_mode->filter_table[j++]);
for (i = 0; i < 60; i++)
- I915_WRITE(TV_H_CHROMA_0 + (i<<2), tv_mode->filter_table[j++]);
+ I915_WRITE(TV_H_CHROMA(i), tv_mode->filter_table[j++]);
for (i = 0; i < 43; i++)
- I915_WRITE(TV_V_LUMA_0 + (i<<2), tv_mode->filter_table[j++]);
+ I915_WRITE(TV_V_LUMA(i), tv_mode->filter_table[j++]);
for (i = 0; i < 43; i++)
- I915_WRITE(TV_V_CHROMA_0 + (i<<2), tv_mode->filter_table[j++]);
+ I915_WRITE(TV_V_CHROMA(i), tv_mode->filter_table[j++]);
I915_WRITE(TV_DAC, I915_READ(TV_DAC) & TV_DAC_SAVE);
I915_WRITE(TV_CTL, tv_ctl);
}
return;
- for (i = 0; i < sizeof(tv_modes) / sizeof(*tv_modes); i++) {
+ for (i = 0; i < ARRAY_SIZE(tv_modes); i++) {
tv_mode = tv_modes + i;
if ((intel_tv->type == DRM_MODE_CONNECTOR_Component) ==
#include <linux/pm_runtime.h>
-#define FORCEWAKE_ACK_TIMEOUT_MS 2
+#define FORCEWAKE_ACK_TIMEOUT_MS 50
#define __raw_i915_read8(dev_priv__, reg__) readb((dev_priv__)->regs + (reg__))
#define __raw_i915_write8(dev_priv__, reg__, val__) writeb(val__, (dev_priv__)->regs + (reg__))
const char *
intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id)
{
- BUILD_BUG_ON((sizeof(forcewake_domain_names)/sizeof(const char *)) !=
- FW_DOMAIN_ID_COUNT);
+ BUILD_BUG_ON(ARRAY_SIZE(forcewake_domain_names) != FW_DOMAIN_ID_COUNT);
if (id >= 0 && id < FW_DOMAIN_ID_COUNT)
return forcewake_domain_names[id];
gen9_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
enum forcewake_domains fw_engine; \
GEN6_READ_HEADER(x); \
+ hsw_unclaimed_reg_debug(dev_priv, reg, true, true); \
if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg))) \
fw_engine = 0; \
else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg)) \
if (fw_engine) \
__force_wake_get(dev_priv, fw_engine); \
val = __raw_i915_read##x(dev_priv, reg); \
+ hsw_unclaimed_reg_debug(dev_priv, reg, true, false); \
GEN6_READ_FOOTER; \
}
bool trace) { \
enum forcewake_domains fw_engine; \
GEN6_WRITE_HEADER; \
+ hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \
if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg)) || \
is_gen9_shadowed(dev_priv, reg)) \
fw_engine = 0; \
if (fw_engine) \
__force_wake_get(dev_priv, fw_engine); \
__raw_i915_write##x(dev_priv, reg, val); \
+ hsw_unclaimed_reg_debug(dev_priv, reg, false, false); \
+ hsw_unclaimed_reg_detect(dev_priv); \
GEN6_WRITE_FOOTER; \
}
switch (INTEL_INFO(dev)->gen) {
default:
- MISSING_CASE(INTEL_INFO(dev)->gen);
- return;
case 9:
ASSIGN_WRITE_MMIO_VFUNCS(gen9);
ASSIGN_READ_MMIO_VFUNCS(gen9);
#define MAX(a,b) (((a)>(b))?(a):(b))
#define MIN(a,b) (((a)<(b))?(a):(b))
+#define REG_SAFE_BM_SIZE ARRAY_SIZE(evergreen_reg_safe_bm)
+
int r600_dma_cs_next_reloc(struct radeon_cs_parser *p,
struct radeon_bo_list **cs_reloc);
struct evergreen_cs_track {
u32 htile_surface;
struct radeon_bo *htile_bo;
unsigned long indirect_draw_buffer_size;
+ const unsigned *reg_safe_bm;
};
static u32 evergreen_cs_get_aray_mode(u32 tiling_flags)
* command stream.
*/
if (!surf.mode) {
- volatile u32 *ib = p->ib.ptr;
+ uint32_t *ib = p->ib.ptr;
unsigned long tmp, nby, bsize, size, min = 0;
/* find the height the ddx wants */
}
/**
- * evergreen_cs_check_reg() - check if register is authorized or not
+ * evergreen_cs_handle_reg() - process registers that need special handling.
* @parser: parser structure holding parsing context
* @reg: register we are testing
* @idx: index into the cs buffer
- *
- * This function will test against evergreen_reg_safe_bm and return 0
- * if register is safe. If register is not flag as safe this function
- * will test it against a list of register needind special handling.
*/
-static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
+static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
{
struct evergreen_cs_track *track = (struct evergreen_cs_track *)p->track;
struct radeon_bo_list *reloc;
- u32 last_reg;
- u32 m, i, tmp, *ib;
+ u32 tmp, *ib;
int r;
- if (p->rdev->family >= CHIP_CAYMAN)
- last_reg = ARRAY_SIZE(cayman_reg_safe_bm);
- else
- last_reg = ARRAY_SIZE(evergreen_reg_safe_bm);
-
- i = (reg >> 7);
- if (i >= last_reg) {
- dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
- return -EINVAL;
- }
- m = 1 << ((reg >> 2) & 31);
- if (p->rdev->family >= CHIP_CAYMAN) {
- if (!(cayman_reg_safe_bm[i] & m))
- return 0;
- } else {
- if (!(evergreen_reg_safe_bm[i] & m))
- return 0;
- }
ib = p->ib.ptr;
switch (reg) {
/* force following reg to 0 in an attempt to disable out buffer
return 0;
}
-static bool evergreen_is_safe_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
+/**
+ * evergreen_is_safe_reg() - check if register is authorized or not
+ * @parser: parser structure holding parsing context
+ * @reg: register we are testing
+ *
+ * This function will test against reg_safe_bm and return true
+ * if register is safe or false otherwise.
+ */
+static inline bool evergreen_is_safe_reg(struct radeon_cs_parser *p, u32 reg)
{
- u32 last_reg, m, i;
-
- if (p->rdev->family >= CHIP_CAYMAN)
- last_reg = ARRAY_SIZE(cayman_reg_safe_bm);
- else
- last_reg = ARRAY_SIZE(evergreen_reg_safe_bm);
+ struct evergreen_cs_track *track = p->track;
+ u32 m, i;
i = (reg >> 7);
- if (i >= last_reg) {
- dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
+ if (unlikely(i >= REG_SAFE_BM_SIZE)) {
return false;
}
m = 1 << ((reg >> 2) & 31);
- if (p->rdev->family >= CHIP_CAYMAN) {
- if (!(cayman_reg_safe_bm[i] & m))
- return true;
- } else {
- if (!(evergreen_reg_safe_bm[i] & m))
- return true;
- }
- dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
+ if (!(track->reg_safe_bm[i] & m))
+ return true;
+
return false;
}
{
struct radeon_bo_list *reloc;
struct evergreen_cs_track *track;
- volatile u32 *ib;
+ uint32_t *ib;
unsigned idx;
unsigned i;
unsigned start_reg, end_reg, reg;
DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n");
return -EINVAL;
}
- for (i = 0; i < pkt->count; i++) {
- reg = start_reg + (4 * i);
- r = evergreen_cs_check_reg(p, reg, idx+1+i);
+ for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) {
+ if (evergreen_is_safe_reg(p, reg))
+ continue;
+ r = evergreen_cs_handle_reg(p, reg, idx);
if (r)
return r;
}
DRM_ERROR("bad PACKET3_SET_CONTEXT_REG\n");
return -EINVAL;
}
- for (i = 0; i < pkt->count; i++) {
- reg = start_reg + (4 * i);
- r = evergreen_cs_check_reg(p, reg, idx+1+i);
+ for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) {
+ if (evergreen_is_safe_reg(p, reg))
+ continue;
+ r = evergreen_cs_handle_reg(p, reg, idx);
if (r)
return r;
}
} else {
/* SRC is a reg. */
reg = radeon_get_ib_value(p, idx+1) << 2;
- if (!evergreen_is_safe_reg(p, reg, idx+1))
+ if (!evergreen_is_safe_reg(p, reg)) {
+ dev_warn(p->dev, "forbidden register 0x%08x at %d\n",
+ reg, idx + 1);
return -EINVAL;
+ }
}
if (idx_value & 0x2) {
u64 offset;
} else {
/* DST is a reg. */
reg = radeon_get_ib_value(p, idx+3) << 2;
- if (!evergreen_is_safe_reg(p, reg, idx+3))
+ if (!evergreen_is_safe_reg(p, reg)) {
+ dev_warn(p->dev, "forbidden register 0x%08x at %d\n",
+ reg, idx + 3);
return -EINVAL;
+ }
}
break;
case PACKET3_NOP:
if (track == NULL)
return -ENOMEM;
evergreen_cs_track_init(track);
- if (p->rdev->family >= CHIP_CAYMAN)
+ if (p->rdev->family >= CHIP_CAYMAN) {
tmp = p->rdev->config.cayman.tile_config;
- else
+ track->reg_safe_bm = cayman_reg_safe_bm;
+ } else {
tmp = p->rdev->config.evergreen.tile_config;
-
+ track->reg_safe_bm = evergreen_reg_safe_bm;
+ }
+ BUILD_BUG_ON(ARRAY_SIZE(cayman_reg_safe_bm) != REG_SAFE_BM_SIZE);
+ BUILD_BUG_ON(ARRAY_SIZE(evergreen_reg_safe_bm) != REG_SAFE_BM_SIZE);
switch (tmp & 0xf) {
case 0:
track->npipes = 1;
struct radeon_cs_chunk *ib_chunk = p->chunk_ib;
struct radeon_bo_list *src_reloc, *dst_reloc, *dst2_reloc;
u32 header, cmd, count, sub_cmd;
- volatile u32 *ib = p->ib.ptr;
+ uint32_t *ib = p->ib.ptr;
u32 idx;
u64 src_offset, dst_offset, dst2_offset;
int r;
#include <linux/acpi.h>
#include <linux/slab.h>
#include <linux/power_supply.h>
-#include <linux/vga_switcheroo.h>
#include <acpi/video.h>
#include <drm/drmP.h>
#include <drm/drm_crtc_helper.h>
#include <drm/drm_crtc_helper.h>
#include <drm/radeon_drm.h>
#include <linux/vgaarb.h>
-#include <linux/vga_switcheroo.h>
#include "radeon_reg.h"
#include "radeon.h"
#include "radeon_asic.h"
if (has_atpx && vga_count == 2) {
acpi_get_name(radeon_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer);
- printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
+ printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n",
acpi_method_name);
radeon_atpx_priv.atpx_detected = true;
return true;
#include "radeon.h"
#include "atom.h"
-#include <linux/vga_switcheroo.h>
#include <linux/slab.h>
#include <linux/acpi.h>
/*
* radeon_switcheroo_set_state - set switcheroo state
*
* @pdev: pci dev pointer
- * @state: vga switcheroo state
+ * @state: vga_switcheroo state
*
* Callback for the switcheroo driver. Suspends or resumes the
* the asics before or after it is powered up using ACPI methods.
*
* @dev: drm dev pointer
*
- * Switch vga switcheroo state after last close (all asics).
+ * Switch vga_switcheroo state after last close (all asics).
*/
void radeon_driver_lastclose_kms(struct drm_device *dev)
{
(dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP);
}
+static inline bool
+drm_dp_tps3_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+ return dpcd[DP_DPCD_REV] >= 0x12 &&
+ dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED;
+}
+
/*
* DisplayPort AUX channel
*/
projects / linux-drm-fsl-dcu.git / commitdiff