diff options
| author | Zhi Wang <zhi.a.wang@intel.com> | 2018-05-14 05:19:07 +0800 |
|---|---|---|
| committer | Zhi Wang <zhi.a.wang@intel.com> | 2018-05-14 05:22:01 +0800 |
| commit | bba9525520b6028ecbe7486e13216e9ede8636be (patch) | |
| tree | f82f4f2adecf6f97933c88050682d44336db783e /drivers/gpu | |
| parent | cb8ba171ae6c1e4f5fa027162c06d50fc2b43055 (diff) | |
| parent | 0c79f9cb77eae28d48a4f9fc1b3341aacbbd260c (diff) | |
| download | op-kernel-dev-bba9525520b6028ecbe7486e13216e9ede8636be.zip op-kernel-dev-bba9525520b6028ecbe7486e13216e9ede8636be.tar.gz | |
Merge branch 'drm-intel-next-queued' into gvt-next
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Diffstat (limited to 'drivers/gpu')
305 files changed, 13274 insertions, 4823 deletions
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index deeefa7..757825a 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -289,6 +289,8 @@ source "drivers/gpu/drm/pl111/Kconfig" source "drivers/gpu/drm/tve200/Kconfig" +source "drivers/gpu/drm/xen/Kconfig" + # Keep legacy drivers last menuconfig DRM_LEGACY diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 50093ff..9d66657 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -103,3 +103,4 @@ obj-$(CONFIG_DRM_MXSFB) += mxsfb/ obj-$(CONFIG_DRM_TINYDRM) += tinydrm/ obj-$(CONFIG_DRM_PL111) += pl111/ obj-$(CONFIG_DRM_TVE200) += tve200/ +obj-$(CONFIG_DRM_XEN) += xen/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index f44a83a..c8b605f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -890,6 +890,7 @@ struct amdgpu_gfx_funcs { void (*read_wave_data)(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t *dst, int *no_fields); void (*read_wave_vgprs)(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t thread, uint32_t start, uint32_t size, uint32_t *dst); void (*read_wave_sgprs)(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t start, uint32_t size, uint32_t *dst); + void (*select_me_pipe_q)(struct amdgpu_device *adev, u32 me, u32 pipe, u32 queue); }; struct amdgpu_ngg_buf { @@ -1378,6 +1379,7 @@ enum amd_hw_ip_block_type { ATHUB_HWIP, NBIO_HWIP, MP0_HWIP, + MP1_HWIP, UVD_HWIP, VCN_HWIP = UVD_HWIP, VCE_HWIP, @@ -1387,6 +1389,7 @@ enum amd_hw_ip_block_type { SMUIO_HWIP, PWR_HWIP, NBIF_HWIP, + THM_HWIP, MAX_HWIP }; @@ -1812,6 +1815,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring) #define amdgpu_gfx_select_se_sh(adev, se, sh, instance) (adev)->gfx.funcs->select_se_sh((adev), (se), (sh), (instance)) #define amdgpu_gds_switch(adev, r, v, d, w, a) (adev)->gds.funcs->patch_gds_switch((r), (v), (d), (w), (a)) #define amdgpu_psp_check_fw_loading_status(adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i)) +#define amdgpu_gfx_select_me_pipe_q(adev, me, pipe, q) (adev)->gfx.funcs->select_me_pipe_q((adev), (me), (pipe), (q)) /* Common functions */ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 369beb5..448d69f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -64,16 +64,21 @@ int amdgpu_debugfs_add_files(struct amdgpu_device *adev, #if defined(CONFIG_DEBUG_FS) -static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf, - size_t size, loff_t *pos) + +static int amdgpu_debugfs_process_reg_op(bool read, struct file *f, + char __user *buf, size_t size, loff_t *pos) { struct amdgpu_device *adev = file_inode(f)->i_private; ssize_t result = 0; int r; - bool pm_pg_lock, use_bank; - unsigned instance_bank, sh_bank, se_bank; + bool pm_pg_lock, use_bank, use_ring; + unsigned instance_bank, sh_bank, se_bank, me, pipe, queue; - if (size & 0x3 || *pos & 0x3) + pm_pg_lock = use_bank = use_ring = false; + instance_bank = sh_bank = se_bank = me = pipe = queue = 0; + + if (size & 0x3 || *pos & 0x3 || + ((*pos & (1ULL << 62)) && (*pos & (1ULL << 61)))) return -EINVAL; /* are we reading registers for which a PG lock is necessary? */ @@ -91,8 +96,15 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf, if (instance_bank == 0x3FF) instance_bank = 0xFFFFFFFF; use_bank = 1; + } else if (*pos & (1ULL << 61)) { + + me = (*pos & GENMASK_ULL(33, 24)) >> 24; + pipe = (*pos & GENMASK_ULL(43, 34)) >> 34; + queue = (*pos & GENMASK_ULL(53, 44)) >> 44; + + use_ring = 1; } else { - use_bank = 0; + use_bank = use_ring = 0; } *pos &= (1UL << 22) - 1; @@ -104,6 +116,9 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf, mutex_lock(&adev->grbm_idx_mutex); amdgpu_gfx_select_se_sh(adev, se_bank, sh_bank, instance_bank); + } else if (use_ring) { + mutex_lock(&adev->srbm_mutex); + amdgpu_gfx_select_me_pipe_q(adev, me, pipe, queue); } if (pm_pg_lock) @@ -115,8 +130,14 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf, if (*pos > adev->rmmio_size) goto end; - value = RREG32(*pos >> 2); - r = put_user(value, (uint32_t *)buf); + if (read) { + value = RREG32(*pos >> 2); + r = put_user(value, (uint32_t *)buf); + } else { + r = get_user(value, (uint32_t *)buf); + if (!r) + WREG32(*pos >> 2, value); + } if (r) { result = r; goto end; @@ -132,6 +153,9 @@ end: if (use_bank) { amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); + } else if (use_ring) { + amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0); + mutex_unlock(&adev->srbm_mutex); } if (pm_pg_lock) @@ -140,78 +164,17 @@ end: return result; } + +static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf, + size_t size, loff_t *pos) +{ + return amdgpu_debugfs_process_reg_op(true, f, buf, size, pos); +} + static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf, size_t size, loff_t *pos) { - struct amdgpu_device *adev = file_inode(f)->i_private; - ssize_t result = 0; - int r; - bool pm_pg_lock, use_bank; - unsigned instance_bank, sh_bank, se_bank; - - if (size & 0x3 || *pos & 0x3) - return -EINVAL; - - /* are we reading registers for which a PG lock is necessary? */ - pm_pg_lock = (*pos >> 23) & 1; - - if (*pos & (1ULL << 62)) { - se_bank = (*pos & GENMASK_ULL(33, 24)) >> 24; - sh_bank = (*pos & GENMASK_ULL(43, 34)) >> 34; - instance_bank = (*pos & GENMASK_ULL(53, 44)) >> 44; - - if (se_bank == 0x3FF) - se_bank = 0xFFFFFFFF; - if (sh_bank == 0x3FF) - sh_bank = 0xFFFFFFFF; - if (instance_bank == 0x3FF) - instance_bank = 0xFFFFFFFF; - use_bank = 1; - } else { - use_bank = 0; - } - - *pos &= (1UL << 22) - 1; - - if (use_bank) { - if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) || - (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines)) - return -EINVAL; - mutex_lock(&adev->grbm_idx_mutex); - amdgpu_gfx_select_se_sh(adev, se_bank, - sh_bank, instance_bank); - } - - if (pm_pg_lock) - mutex_lock(&adev->pm.mutex); - - while (size) { - uint32_t value; - - if (*pos > adev->rmmio_size) - return result; - - r = get_user(value, (uint32_t *)buf); - if (r) - return r; - - WREG32(*pos >> 2, value); - - result += 4; - buf += 4; - *pos += 4; - size -= 4; - } - - if (use_bank) { - amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); - mutex_unlock(&adev->grbm_idx_mutex); - } - - if (pm_pg_lock) - mutex_unlock(&adev->pm.mutex); - - return result; + return amdgpu_debugfs_process_reg_op(false, f, (char __user *)buf, size, pos); } static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 7379aa5..0b19482 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -922,6 +922,11 @@ static int __init amdgpu_init(void) { int r; + if (vgacon_text_force()) { + DRM_ERROR("VGACON disables amdgpu kernel modesetting.\n"); + return -EINVAL; + } + r = amdgpu_sync_init(); if (r) goto error_sync; @@ -930,10 +935,6 @@ static int __init amdgpu_init(void) if (r) goto error_fence; - if (vgacon_text_force()) { - DRM_ERROR("VGACON disables amdgpu kernel modesetting.\n"); - return -EINVAL; - } DRM_INFO("amdgpu kernel modesetting enabled.\n"); driver = &kms_driver; pdriver = &amdgpu_kms_pci_driver; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 455a81e..97449e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -410,6 +410,7 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring, int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring, unsigned num_hw_submission) { + long timeout; int r; /* Check that num_hw_submission is a power of two */ @@ -433,11 +434,16 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring, /* No need to setup the GPU scheduler for KIQ ring */ if (ring->funcs->type != AMDGPU_RING_TYPE_KIQ) { + /* for non-sriov case, no timeout enforce on compute ring */ + if ((ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) + && !amdgpu_sriov_vf(ring->adev)) + timeout = MAX_SCHEDULE_TIMEOUT; + else + timeout = msecs_to_jiffies(amdgpu_lockup_timeout); + r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, num_hw_submission, amdgpu_job_hang_limit, - (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) ? - MAX_SCHEDULE_TIMEOUT : msecs_to_jiffies(amdgpu_lockup_timeout), - ring->name); + timeout, ring->name); if (r) { DRM_ERROR("Failed to create scheduler on ring %s.\n", ring->name); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 28c2706..46b9ea4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -56,11 +56,23 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, alignment = PAGE_SIZE; } +retry: r = amdgpu_bo_create(adev, size, alignment, initial_domain, flags, type, resv, &bo); if (r) { - DRM_DEBUG("Failed to allocate GEM object (%ld, %d, %u, %d)\n", - size, initial_domain, alignment, r); + if (r != -ERESTARTSYS) { + if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) { + flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; + goto retry; + } + + if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) { + initial_domain |= AMDGPU_GEM_DOMAIN_GTT; + goto retry; + } + DRM_DEBUG("Failed to allocate GEM object (%ld, %d, %u, %d)\n", + size, initial_domain, alignment, r); + } return r; } *obj = &bo->gem_base; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index fac4b60..6d08cde 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -356,7 +356,6 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size, struct amdgpu_bo *bo; unsigned long page_align; size_t acc_size; - u32 domains; int r; page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT; @@ -418,23 +417,12 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, unsigned long size, #endif bo->tbo.bdev = &adev->mman.bdev; - domains = bo->preferred_domains; -retry: - amdgpu_ttm_placement_from_domain(bo, domains); + amdgpu_ttm_placement_from_domain(bo, domain); + r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type, &bo->placement, page_align, &ctx, acc_size, NULL, resv, &amdgpu_ttm_bo_destroy); - - if (unlikely(r && r != -ERESTARTSYS)) { - if (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) { - bo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - goto retry; - } else if (domains != bo->preferred_domains) { - domains = bo->allowed_domains; - goto retry; - } - } - if (unlikely(r)) + if (unlikely(r != 0)) return r; if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 19e71f4..c7d43e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -505,6 +505,9 @@ failed: int psp_gpu_reset(struct amdgpu_device *adev) { + if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) + return 0; + return psp_mode1_reset(&adev->psp); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index dd6f989..5916cc2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -277,7 +277,7 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type) else return AMDGPU_FW_LOAD_PSP; default: - DRM_ERROR("Unknow firmware load type\n"); + DRM_ERROR("Unknown firmware load type\n"); } return AMDGPU_FW_LOAD_DIRECT; diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index f48ea0d..a757625 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -859,7 +859,7 @@ static void cik_sdma_ring_emit_pipeline_sync(struct amdgpu_ring *ring) amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); /* reference */ - amdgpu_ring_write(ring, 0xfffffff); /* mask */ + amdgpu_ring_write(ring, 0xffffffff); /* mask */ amdgpu_ring_write(ring, (0xfff << 16) | 4); /* retry count, poll interval */ } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index 0fff5b8..cd6bf29 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -3061,11 +3061,18 @@ static void gfx_v6_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd, start + SQIND_WAVE_SGPRS_OFFSET, size, dst); } +static void gfx_v6_0_select_me_pipe_q(struct amdgpu_device *adev, + u32 me, u32 pipe, u32 q) +{ + DRM_INFO("Not implemented\n"); +} + static const struct amdgpu_gfx_funcs gfx_v6_0_gfx_funcs = { .get_gpu_clock_counter = &gfx_v6_0_get_gpu_clock_counter, .select_se_sh = &gfx_v6_0_select_se_sh, .read_wave_data = &gfx_v6_0_read_wave_data, .read_wave_sgprs = &gfx_v6_0_read_wave_sgprs, + .select_me_pipe_q = &gfx_v6_0_select_me_pipe_q }; static int gfx_v6_0_early_init(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index e13d9d8..42b6144 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -4270,11 +4270,18 @@ static void gfx_v7_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd, start + SQIND_WAVE_SGPRS_OFFSET, size, dst); } +static void gfx_v7_0_select_me_pipe_q(struct amdgpu_device *adev, + u32 me, u32 pipe, u32 q) +{ + cik_srbm_select(adev, me, pipe, q, 0); +} + static const struct amdgpu_gfx_funcs gfx_v7_0_gfx_funcs = { .get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter, .select_se_sh = &gfx_v7_0_select_se_sh, .read_wave_data = &gfx_v7_0_read_wave_data, .read_wave_sgprs = &gfx_v7_0_read_wave_sgprs, + .select_me_pipe_q = &gfx_v7_0_select_me_pipe_q }; static const struct amdgpu_rlc_funcs gfx_v7_0_rlc_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 27943e5..e14263f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -1459,10 +1459,11 @@ static const u32 sgpr_init_compute_shader[] = static const u32 vgpr_init_regs[] = { mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0xffffffff, - mmCOMPUTE_RESOURCE_LIMITS, 0, + mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */ mmCOMPUTE_NUM_THREAD_X, 256*4, mmCOMPUTE_NUM_THREAD_Y, 1, mmCOMPUTE_NUM_THREAD_Z, 1, + mmCOMPUTE_PGM_RSRC1, 0x100004f, /* VGPRS=15 (64 logical VGPRs), SGPRS=1 (16 SGPRs), BULKY=1 */ mmCOMPUTE_PGM_RSRC2, 20, mmCOMPUTE_USER_DATA_0, 0xedcedc00, mmCOMPUTE_USER_DATA_1, 0xedcedc01, @@ -1479,10 +1480,11 @@ static const u32 vgpr_init_regs[] = static const u32 sgpr1_init_regs[] = { mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0x0f, - mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, + mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */ mmCOMPUTE_NUM_THREAD_X, 256*5, mmCOMPUTE_NUM_THREAD_Y, 1, mmCOMPUTE_NUM_THREAD_Z, 1, + mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */ mmCOMPUTE_PGM_RSRC2, 20, mmCOMPUTE_USER_DATA_0, 0xedcedc00, mmCOMPUTE_USER_DATA_1, 0xedcedc01, @@ -1503,6 +1505,7 @@ static const u32 sgpr2_init_regs[] = mmCOMPUTE_NUM_THREAD_X, 256*5, mmCOMPUTE_NUM_THREAD_Y, 1, mmCOMPUTE_NUM_THREAD_Z, 1, + mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */ mmCOMPUTE_PGM_RSRC2, 20, mmCOMPUTE_USER_DATA_0, 0xedcedc00, mmCOMPUTE_USER_DATA_1, 0xedcedc01, @@ -3475,6 +3478,12 @@ static void gfx_v8_0_select_se_sh(struct amdgpu_device *adev, WREG32(mmGRBM_GFX_INDEX, data); } +static void gfx_v8_0_select_me_pipe_q(struct amdgpu_device *adev, + u32 me, u32 pipe, u32 q) +{ + vi_srbm_select(adev, me, pipe, q, 0); +} + static u32 gfx_v8_0_get_rb_active_bitmap(struct amdgpu_device *adev) { u32 data, mask; @@ -5442,6 +5451,7 @@ static const struct amdgpu_gfx_funcs gfx_v8_0_gfx_funcs = { .select_se_sh = &gfx_v8_0_select_se_sh, .read_wave_data = &gfx_v8_0_read_wave_data, .read_wave_sgprs = &gfx_v8_0_read_wave_sgprs, + .select_me_pipe_q = &gfx_v8_0_select_me_pipe_q }; static int gfx_v8_0_early_init(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 1ae3de1..9d39fd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -998,12 +998,19 @@ static void gfx_v9_0_read_wave_vgprs(struct amdgpu_device *adev, uint32_t simd, start + SQIND_WAVE_VGPRS_OFFSET, size, dst); } +static void gfx_v9_0_select_me_pipe_q(struct amdgpu_device *adev, + u32 me, u32 pipe, u32 q) +{ + soc15_grbm_select(adev, me, pipe, q, 0); +} + static const struct amdgpu_gfx_funcs gfx_v9_0_gfx_funcs = { .get_gpu_clock_counter = &gfx_v9_0_get_gpu_clock_counter, .select_se_sh = &gfx_v9_0_select_se_sh, .read_wave_data = &gfx_v9_0_read_wave_data, .read_wave_sgprs = &gfx_v9_0_read_wave_sgprs, .read_wave_vgprs = &gfx_v9_0_read_wave_vgprs, + .select_me_pipe_q = &gfx_v9_0_select_me_pipe_q }; static void gfx_v9_0_gpu_early_init(struct amdgpu_device *adev) @@ -2757,6 +2764,45 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring) return 0; } +static int gfx_v9_0_kiq_fini_register(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + int j; + + /* disable the queue if it's active */ + if (RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE) & 1) { + + WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, 1); + + for (j = 0; j < adev->usec_timeout; j++) { + if (!(RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE) & 1)) + break; + udelay(1); + } + + if (j == AMDGPU_MAX_USEC_TIMEOUT) { + DRM_DEBUG("KIQ dequeue request failed.\n"); + + /* Manual disable if dequeue request times out */ + WREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE, 0); + } + + WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, + 0); + } + + WREG32_SOC15(GC, 0, mmCP_HQD_IQ_TIMER, 0); + WREG32_SOC15(GC, 0, mmCP_HQD_IB_CONTROL, 0); + WREG32_SOC15(GC, 0, mmCP_HQD_PERSISTENT_STATE, 0); + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL, 0x40000000); + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL, 0); + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_RPTR, 0); + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_HI, 0); + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_LO, 0); + + return 0; +} + static int gfx_v9_0_kiq_init_queue(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; @@ -3010,7 +3056,6 @@ static int gfx_v9_0_kcq_disable(struct amdgpu_ring *kiq_ring,struct amdgpu_ring return r; } - static int gfx_v9_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -3033,6 +3078,20 @@ static int gfx_v9_0_hw_fini(void *handle) WREG32_FIELD15(GC, 0, CP_PQ_WPTR_POLL_CNTL, EN, 0); return 0; } + + /* Use deinitialize sequence from CAIL when unbinding device from driver, + * otherwise KIQ is hanging when binding back + */ + if (!adev->in_gpu_reset && !adev->gfx.in_suspend) { + mutex_lock(&adev->srbm_mutex); + soc15_grbm_select(adev, adev->gfx.kiq.ring.me, + adev->gfx.kiq.ring.pipe, + adev->gfx.kiq.ring.queue, 0); + gfx_v9_0_kiq_fini_register(&adev->gfx.kiq.ring); + soc15_grbm_select(adev, 0, 0, 0, 0); + mutex_unlock(&adev->srbm_mutex); + } + gfx_v9_0_cp_enable(adev, false); gfx_v9_0_rlc_stop(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 6452101..c7190c3 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -837,7 +837,7 @@ static void sdma_v2_4_ring_emit_pipeline_sync(struct amdgpu_ring *ring) amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); /* reference */ - amdgpu_ring_write(ring, 0xfffffff); /* mask */ + amdgpu_ring_write(ring, 0xffffffff); /* mask */ amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */ } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index ecaef08..be20a38 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -1105,7 +1105,7 @@ static void sdma_v3_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring) amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); /* reference */ - amdgpu_ring_write(ring, 0xfffffff); /* mask */ + amdgpu_ring_write(ring, 0xffffffff); /* mask */ amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */ } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 2a81840..399f876 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1121,7 +1121,7 @@ static void sdma_v4_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring) amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); /* reference */ - amdgpu_ring_write(ring, 0xfffffff); /* mask */ + amdgpu_ring_write(ring, 0xffffffff); /* mask */ amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */ } diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c index b154667..a675ec6 100644 --- a/drivers/gpu/drm/amd/amdgpu/si.c +++ b/drivers/gpu/drm/amd/amdgpu/si.c @@ -1252,6 +1252,71 @@ static void si_invalidate_hdp(struct amdgpu_device *adev, } } +static int si_get_pcie_lanes(struct amdgpu_device *adev) +{ + u32 link_width_cntl; + + if (adev->flags & AMD_IS_APU) + return 0; + + link_width_cntl = RREG32_PCIE_PORT(PCIE_LC_LINK_WIDTH_CNTL); + + switch ((link_width_cntl & LC_LINK_WIDTH_RD_MASK) >> LC_LINK_WIDTH_RD_SHIFT) { + case LC_LINK_WIDTH_X1: + return 1; + case LC_LINK_WIDTH_X2: + return 2; + case LC_LINK_WIDTH_X4: + return 4; + case LC_LINK_WIDTH_X8: + return 8; + case LC_LINK_WIDTH_X0: + case LC_LINK_WIDTH_X16: + default: + return 16; + } +} + +static void si_set_pcie_lanes(struct amdgpu_device *adev, int lanes) +{ + u32 link_width_cntl, mask; + + if (adev->flags & AMD_IS_APU) + return; + + switch (lanes) { + case 0: + mask = LC_LINK_WIDTH_X0; + break; + case 1: + mask = LC_LINK_WIDTH_X1; + break; + case 2: + mask = LC_LINK_WIDTH_X2; + break; + case 4: + mask = LC_LINK_WIDTH_X4; + break; + case 8: + mask = LC_LINK_WIDTH_X8; + break; + case 16: + mask = LC_LINK_WIDTH_X16; + break; + default: + DRM_ERROR("invalid pcie lane request: %d\n", lanes); + return; + } + + link_width_cntl = RREG32_PCIE_PORT(PCIE_LC_LINK_WIDTH_CNTL); + link_width_cntl &= ~LC_LINK_WIDTH_MASK; + link_width_cntl |= mask << LC_LINK_WIDTH_SHIFT; + link_width_cntl |= (LC_RECONFIG_NOW | + LC_RECONFIG_ARC_MISSING_ESCAPE); + + WREG32_PCIE_PORT(PCIE_LC_LINK_WIDTH_CNTL, link_width_cntl); +} + static const struct amdgpu_asic_funcs si_asic_funcs = { .read_disabled_bios = &si_read_disabled_bios, @@ -1262,6 +1327,8 @@ static const struct amdgpu_asic_funcs si_asic_funcs = .get_xclk = &si_get_xclk, .set_uvd_clocks = &si_set_uvd_clocks, .set_vce_clocks = NULL, + .get_pcie_lanes = &si_get_pcie_lanes, + .set_pcie_lanes = &si_set_pcie_lanes, .get_config_memsize = &si_get_config_memsize, .flush_hdp = &si_flush_hdp, .invalidate_hdp = &si_invalidate_hdp, diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index 672eaff..797d505 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -6372,9 +6372,9 @@ static void si_set_pcie_lane_width_in_smc(struct amdgpu_device *adev, { u32 lane_width; u32 new_lane_width = - (amdgpu_new_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT; + ((amdgpu_new_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT) + 1; u32 current_lane_width = - (amdgpu_current_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT; + ((amdgpu_current_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT) + 1; if (new_lane_width != current_lane_width) { amdgpu_set_pcie_lanes(adev, new_lane_width); diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c index 73fd48d..73fd48d 100755..100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c index 4c45db7..45aafca 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c @@ -38,6 +38,7 @@ int vega10_reg_base_init(struct amdgpu_device *adev) adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); + adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); adev->reg_offset[UVD_HWIP][i] = (uint32_t *)(&(UVD_BASE.instance[i])); adev->reg_offset[VCE_HWIP][i] = (uint32_t *)(&(VCE_BASE.instance[i])); adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(VCN_BASE.instance[i])); @@ -49,7 +50,7 @@ int vega10_reg_base_init(struct amdgpu_device *adev) adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); adev->reg_offset[PWR_HWIP][i] = (uint32_t *)(&(PWR_BASE.instance[i])); adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIF_BASE.instance[i])); - + adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); } return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/Kconfig b/drivers/gpu/drm/amd/amdkfd/Kconfig index ed2f06c..3858820 100644 --- a/drivers/gpu/drm/amd/amdkfd/Kconfig +++ b/drivers/gpu/drm/amd/amdkfd/Kconfig @@ -6,5 +6,6 @@ config HSA_AMD tristate "HSA kernel driver for AMD GPU devices" depends on DRM_AMDGPU && X86_64 imply AMD_IOMMU_V2 + select MMU_NOTIFIER help Enable this if you want to use HSA features on AMD GPU devices. diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index cd679cf..59808a3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -749,12 +749,13 @@ static int kfd_ioctl_get_clock_counters(struct file *filep, struct timespec64 time; dev = kfd_device_by_id(args->gpu_id); - if (dev == NULL) - return -EINVAL; - - /* Reading GPU clock counter from KGD */ - args->gpu_clock_counter = - dev->kfd2kgd->get_gpu_clock_counter(dev->kgd); + if (dev) + /* Reading GPU clock counter from KGD */ + args->gpu_clock_counter = + dev->kfd2kgd->get_gpu_clock_counter(dev->kgd); + else + /* Node without GPU resource */ + args->gpu_clock_counter = 0; /* No access to rdtsc. Using raw monotonic time */ getrawmonotonic64(&time); @@ -1147,7 +1148,7 @@ err_unlock: return ret; } -bool kfd_dev_is_large_bar(struct kfd_dev *dev) +static bool kfd_dev_is_large_bar(struct kfd_dev *dev) { struct kfd_local_mem_info mem_info; @@ -1421,7 +1422,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, pdd = kfd_get_process_device_data(dev, p); if (!pdd) { - err = PTR_ERR(pdd); + err = -EINVAL; goto bind_process_to_device_failed; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index c18e048..d55d29d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1058,13 +1058,13 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, pr_warn("Can't create new usermode queue because %d queues were already created\n", dqm->total_queue_count); retval = -EPERM; - goto out; + goto out_unlock; } if (q->properties.type == KFD_QUEUE_TYPE_SDMA) { retval = allocate_sdma_queue(dqm, &q->sdma_id); if (retval) - goto out; + goto out_unlock; q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE; q->properties.sdma_engine_id = @@ -1075,7 +1075,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, if (!mqd) { retval = -ENOMEM; - goto out; + goto out_deallocate_sdma_queue; } /* * Eviction state logic: we only mark active queues as evicted @@ -1093,7 +1093,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj, &q->gart_mqd_addr, &q->properties); if (retval) - goto out; + goto out_deallocate_sdma_queue; list_add(&q->list, &qpd->queues_list); qpd->queue_count++; @@ -1114,7 +1114,13 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, pr_debug("Total of %d queues are accountable so far\n", dqm->total_queue_count); -out: + mutex_unlock(&dqm->lock); + return retval; + +out_deallocate_sdma_queue: + if (q->properties.type == KFD_QUEUE_TYPE_SDMA) + deallocate_sdma_queue(dqm, q->sdma_id); +out_unlock: mutex_unlock(&dqm->lock); return retval; } @@ -1433,8 +1439,10 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, /* Clear all user mode queues */ list_for_each_entry(q, &qpd->queues_list, list) { - if (q->properties.type == KFD_QUEUE_TYPE_SDMA) + if (q->properties.type == KFD_QUEUE_TYPE_SDMA) { dqm->sdma_queue_count--; + deallocate_sdma_queue(dqm, q->sdma_id); + } if (q->properties.is_active) dqm->queue_count--; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c index 7614375..89ba4c6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c @@ -188,8 +188,7 @@ static int pm_create_map_process(struct packet_manager *pm, uint32_t *buffer, packet->sh_mem_ape1_base = qpd->sh_mem_ape1_base; packet->sh_mem_ape1_limit = qpd->sh_mem_ape1_limit; - /* TODO: scratch support */ - packet->sh_hidden_private_base_vmid = 0; + packet->sh_hidden_private_base_vmid = qpd->sh_hidden_private_base; packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area); packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index e42a28e..1dd1142 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1403,6 +1403,28 @@ static int initialize_plane(struct amdgpu_display_manager *dm, return ret; } + +static void register_backlight_device(struct amdgpu_display_manager *dm, + struct dc_link *link) +{ +#if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\ + defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) + + if ((link->connector_signal & (SIGNAL_TYPE_EDP | SIGNAL_TYPE_LVDS)) && + link->type != dc_connection_none) { + /* Event if registration failed, we should continue with + * DM initialization because not having a backlight control + * is better then a black screen. + */ + amdgpu_dm_register_backlight_device(dm); + + if (dm->backlight_dev) + dm->backlight_link = link; + } +#endif +} + + /* In this architecture, the association * connector -> encoder -> crtc * id not really requried. The crtc and connector will hold the @@ -1456,6 +1478,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) /* loops over all connectors on the board */ for (i = 0; i < link_cnt; i++) { + struct dc_link *link = NULL; if (i > AMDGPU_DM_MAX_DISPLAY_INDEX) { DRM_ERROR( @@ -1482,9 +1505,14 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) goto fail; } - if (dc_link_detect(dc_get_link_at_index(dm->dc, i), - DETECT_REASON_BOOT)) + link = dc_get_link_at_index(dm->dc, i); + + if (dc_link_detect(link, DETECT_REASON_BOOT)) { amdgpu_dm_update_connector_after_detect(aconnector); + register_backlight_device(dm, link); + } + + } /* Software is initialized. Now we can register interrupt handlers. */ @@ -2685,7 +2713,8 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\ defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) - if (link->connector_signal & (SIGNAL_TYPE_EDP | SIGNAL_TYPE_LVDS)) { + if ((link->connector_signal & (SIGNAL_TYPE_EDP | SIGNAL_TYPE_LVDS)) && + link->type != dc_connection_none) { amdgpu_dm_register_backlight_device(dm); if (dm->backlight_dev) { @@ -3561,6 +3590,7 @@ create_i2c(struct ddc_service *ddc_service, return i2c; } + /* Note: this function assumes that dc_link_detect() was called for the * dc_link which will be represented by this aconnector. */ @@ -3630,28 +3660,6 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm, || connector_type == DRM_MODE_CONNECTOR_eDP) amdgpu_dm_initialize_dp_connector(dm, aconnector); -#if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\ - defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) - - /* NOTE: this currently will create backlight device even if a panel - * is not connected to the eDP/LVDS connector. - * - * This is less than ideal but we don't have sink information at this - * stage since detection happens after. We can't do detection earlier - * since MST detection needs connectors to be created first. - */ - if (link->connector_signal & (SIGNAL_TYPE_EDP | SIGNAL_TYPE_LVDS)) { - /* Event if registration failed, we should continue with - * DM initialization because not having a backlight control - * is better then a black screen. - */ - amdgpu_dm_register_backlight_device(dm); - - if (dm->backlight_dev) - dm->backlight_link = link; - } -#endif - out_free: if (res) { kfree(i2c); @@ -4549,6 +4557,7 @@ static int dm_update_crtcs_state(struct dc *dc, struct amdgpu_dm_connector *aconnector = NULL; struct drm_connector_state *new_con_state = NULL; struct dm_connector_state *dm_conn_state = NULL; + struct drm_plane_state *new_plane_state = NULL; new_stream = NULL; @@ -4556,6 +4565,13 @@ static int dm_update_crtcs_state(struct dc *dc, dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); acrtc = to_amdgpu_crtc(crtc); + new_plane_state = drm_atomic_get_new_plane_state(state, new_crtc_state->crtc->primary); + + if (new_crtc_state->enable && new_plane_state && !new_plane_state->fb) { + ret = -EINVAL; + goto fail; + } + aconnector = amdgpu_dm_find_first_crtc_matching_connector(state, crtc); /* TODO This hack should go away */ @@ -4752,7 +4768,7 @@ static int dm_update_planes_state(struct dc *dc, if (!dm_old_crtc_state->stream) continue; - DRM_DEBUG_DRIVER("Disabling DRM plane: %d on DRM crtc %d\n", + DRM_DEBUG_ATOMIC("Disabling DRM plane: %d on DRM crtc %d\n", plane->base.id, old_plane_crtc->base.id); if (!dc_remove_plane_from_context( @@ -4840,33 +4856,6 @@ static int dm_update_planes_state(struct dc *dc, return ret; } -static int dm_atomic_check_plane_state_fb(struct drm_atomic_state *state, - struct drm_crtc *crtc) -{ - struct drm_plane *plane; - struct drm_crtc_state *crtc_state; - - WARN_ON(!drm_atomic_get_new_crtc_state(state, crtc)); - - drm_for_each_plane_mask(plane, state->dev, crtc->state->plane_mask) { - struct drm_plane_state *plane_state = - drm_atomic_get_plane_state(state, plane); - - if (IS_ERR(plane_state)) - return -EDEADLK; - - crtc_state = drm_atomic_get_crtc_state(plane_state->state, crtc); - if (IS_ERR(crtc_state)) - return PTR_ERR(crtc_state); - - if (crtc->primary == plane && crtc_state->active) { - if (!plane_state->fb) - return -EINVAL; - } - } - return 0; -} - static int amdgpu_dm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { @@ -4890,10 +4879,6 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { - ret = dm_atomic_check_plane_state_fb(state, crtc); - if (ret) - goto fail; - if (!drm_atomic_crtc_needs_modeset(new_crtc_state) && !new_crtc_state->color_mgmt_changed) continue; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c index f6cb502..25f064c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c @@ -138,13 +138,6 @@ int amdgpu_dm_set_regamma_lut(struct dm_crtc_state *crtc) lut = (struct drm_color_lut *)blob->data; lut_size = blob->length / sizeof(struct drm_color_lut); - if (__is_lut_linear(lut, lut_size)) { - /* Set to bypass if lut is set to linear */ - stream->out_transfer_func->type = TF_TYPE_BYPASS; - stream->out_transfer_func->tf = TRANSFER_FUNCTION_LINEAR; - return 0; - } - gamma = dc_create_gamma(); if (!gamma) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index 490017d..4be21bf 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -329,14 +329,15 @@ void amdgpu_dm_irq_fini(struct amdgpu_device *adev) { int src; struct irq_list_head *lh; + unsigned long irq_table_flags; DRM_DEBUG_KMS("DM_IRQ: releasing resources.\n"); - for (src = 0; src < DAL_IRQ_SOURCES_NUMBER; src++) { - + DM_IRQ_TABLE_LOCK(adev, irq_table_flags); /* The handler was removed from the table, * it means it is safe to flush all the 'work' * (because no code can schedule a new one). */ lh = &adev->dm.irq_handler_list_low_tab[src]; + DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags); flush_work(&lh->work); } } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 8291d74..ace9ad5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -161,6 +161,11 @@ dm_dp_mst_connector_destroy(struct drm_connector *connector) struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); struct amdgpu_encoder *amdgpu_encoder = amdgpu_dm_connector->mst_encoder; + if (amdgpu_dm_connector->edid) { + kfree(amdgpu_dm_connector->edid); + amdgpu_dm_connector->edid = NULL; + } + drm_encoder_cleanup(&amdgpu_encoder->base); kfree(amdgpu_encoder); drm_connector_cleanup(connector); @@ -181,28 +186,22 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = { void dm_dp_mst_dc_sink_create(struct drm_connector *connector) { struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); - struct edid *edid; struct dc_sink *dc_sink; struct dc_sink_init_data init_params = { .link = aconnector->dc_link, .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; + /* FIXME none of this is safe. we shouldn't touch aconnector here in + * atomic_check + */ + /* * TODO: Need to further figure out why ddc.algo is NULL while MST port exists */ if (!aconnector->port || !aconnector->port->aux.ddc.algo) return; - edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port); - - if (!edid) { - drm_mode_connector_update_edid_property( - &aconnector->base, - NULL); - return; - } - - aconnector->edid = edid; + ASSERT(aconnector->edid); dc_sink = dc_link_add_remote_sink( aconnector->dc_link, @@ -215,9 +214,6 @@ void dm_dp_mst_dc_sink_create(struct drm_connector *connector) amdgpu_dm_add_sink_to_freesync_module( connector, aconnector->edid); - - drm_mode_connector_update_edid_property( - &aconnector->base, aconnector->edid); } static int dm_dp_mst_get_modes(struct drm_connector *connector) @@ -230,10 +226,6 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) if (!aconnector->edid) { struct edid *edid; - struct dc_sink *dc_sink; - struct dc_sink_init_data init_params = { - .link = aconnector->dc_link, - .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port); if (!edid) { @@ -244,11 +236,17 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) } aconnector->edid = edid; + } + if (!aconnector->dc_sink) { + struct dc_sink *dc_sink; + struct dc_sink_init_data init_params = { + .link = aconnector->dc_link, + .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; dc_sink = dc_link_add_remote_sink( aconnector->dc_link, - (uint8_t *)edid, - (edid->extensions + 1) * EDID_LENGTH, + (uint8_t *)aconnector->edid, + (aconnector->edid->extensions + 1) * EDID_LENGTH, &init_params); dc_sink->priv = aconnector; @@ -256,12 +254,12 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) if (aconnector->dc_sink) amdgpu_dm_add_sink_to_freesync_module( - connector, edid); - - drm_mode_connector_update_edid_property( - &aconnector->base, edid); + connector, aconnector->edid); } + drm_mode_connector_update_edid_property( + &aconnector->base, aconnector->edid); + ret = drm_add_edid_modes(connector, aconnector->edid); return ret; @@ -424,14 +422,6 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, dc_sink_release(aconnector->dc_sink); aconnector->dc_sink = NULL; } - if (aconnector->edid) { - kfree(aconnector->edid); - aconnector->edid = NULL; - } - - drm_mode_connector_update_edid_property( - &aconnector->base, - NULL); aconnector->mst_connected = false; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 63a3d46..9cd3566 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -589,7 +589,7 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) ******************************************************************************/ struct dc *dc_create(const struct dc_init_data *init_params) - { +{ struct dc *dc = kzalloc(sizeof(*dc), GFP_KERNEL); unsigned int full_pipe_count; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index eeb0447..6d1c498 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1997,6 +1997,19 @@ bool dc_link_set_backlight_level(const struct dc_link *link, uint32_t level, return true; } +bool dc_link_set_abm_disable(const struct dc_link *link) +{ + struct dc *core_dc = link->ctx->dc; + struct abm *abm = core_dc->res_pool->abm; + + if ((abm == NULL) || (abm->funcs->set_backlight_level == NULL)) + return false; + + abm->funcs->set_abm_immediate_disable(abm); + + return true; +} + bool dc_link_set_psr_enable(const struct dc_link *link, bool enable, bool wait) { struct dc *core_dc = link->ctx->dc; diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index fb4d9ea..dc34515 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -132,6 +132,8 @@ static inline struct dc_link *dc_get_link_at_index(struct dc *dc, uint32_t link_ bool dc_link_set_backlight_level(const struct dc_link *dc_link, uint32_t level, uint32_t frame_ramp, const struct dc_stream_state *stream); +bool dc_link_set_abm_disable(const struct dc_link *dc_link); + bool dc_link_set_psr_enable(const struct dc_link *dc_link, bool enable, bool wait); bool dc_link_get_psr_state(const struct dc_link *dc_link, uint32_t *psr_state); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c index 444558c..162f6a6 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c @@ -735,6 +735,8 @@ static void dce110_stream_encoder_update_hdmi_info_packets( if (info_frame->avi.valid) { const uint32_t *content = (const uint32_t *) &info_frame->avi.sb[0]; + /*we need turn on clock before programming AFMT block*/ + REG_UPDATE(AFMT_CNTL, AFMT_AUDIO_CLOCK_EN, 1); REG_WRITE(AFMT_AVI_INFO0, content[0]); diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c index 775d3bf..9150d26 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c @@ -102,6 +102,43 @@ static uint32_t align_to_chunks_number_per_line(uint32_t pixels) return 256 * ((pixels + 255) / 256); } +static void reset_lb_on_vblank(struct dc_context *ctx) +{ + uint32_t value, frame_count; + uint32_t retry = 0; + uint32_t status_pos = + dm_read_reg(ctx, mmCRTC_STATUS_POSITION); + + + /* Only if CRTC is enabled and counter is moving we wait for one frame. */ + if (status_pos != dm_read_reg(ctx, mmCRTC_STATUS_POSITION)) { + /* Resetting LB on VBlank */ + value = dm_read_reg(ctx, mmLB_SYNC_RESET_SEL); + set_reg_field_value(value, 3, LB_SYNC_RESET_SEL, LB_SYNC_RESET_SEL); + set_reg_field_value(value, 1, LB_SYNC_RESET_SEL, LB_SYNC_RESET_SEL2); + dm_write_reg(ctx, mmLB_SYNC_RESET_SEL, value); + + frame_count = dm_read_reg(ctx, mmCRTC_STATUS_FRAME_COUNT); + + + for (retry = 100; retry > 0; retry--) { + if (frame_count != dm_read_reg(ctx, mmCRTC_STATUS_FRAME_COUNT)) + break; + msleep(1); + } + if (!retry) + dm_error("Frame count did not increase for 100ms.\n"); + + /* Resetting LB on VBlank */ + value = dm_read_reg(ctx, mmLB_SYNC_RESET_SEL); + set_reg_field_value(value, 2, LB_SYNC_RESET_SEL, LB_SYNC_RESET_SEL); + set_reg_field_value(value, 0, LB_SYNC_RESET_SEL, LB_SYNC_RESET_SEL2); + dm_write_reg(ctx, mmLB_SYNC_RESET_SEL, value); + + } + +} + static void wait_for_fbc_state_changed( struct dce110_compressor *cp110, bool enabled) @@ -232,19 +269,23 @@ void dce110_compressor_disable_fbc(struct compressor *compressor) { struct dce110_compressor *cp110 = TO_DCE110_COMPRESSOR(compressor); - if (compressor->options.bits.FBC_SUPPORT && - dce110_compressor_is_fbc_enabled_in_hw(compressor, NULL)) { - uint32_t reg_data; - /* Turn off compression */ - reg_data = dm_read_reg(compressor->ctx, mmFBC_CNTL); - set_reg_field_value(reg_data, 0, FBC_CNTL, FBC_GRPH_COMP_EN); - dm_write_reg(compressor->ctx, mmFBC_CNTL, reg_data); - - /* Reset enum controller_id to undefined */ - compressor->attached_inst = 0; - compressor->is_enabled = false; - - wait_for_fbc_state_changed(cp110, false); + if (compressor->options.bits.FBC_SUPPORT) { + if (dce110_compressor_is_fbc_enabled_in_hw(compressor, NULL)) { + uint32_t reg_data; + /* Turn off compression */ + reg_data = dm_read_reg(compressor->ctx, mmFBC_CNTL); + set_reg_field_value(reg_data, 0, FBC_CNTL, FBC_GRPH_COMP_EN); + dm_write_reg(compressor->ctx, mmFBC_CNTL, reg_data); + + /* Reset enum controller_id to undefined */ + compressor->attached_inst = 0; + compressor->is_enabled = false; + + wait_for_fbc_state_changed(cp110, false); + } + + /* Sync line buffer - dce100/110 only*/ + reset_lb_on_vblank(compressor->ctx); } } diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 30dd62f..d057599 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -453,10 +453,13 @@ dce110_translate_regamma_to_hw_format(const struct dc_transfer_func *output_tf, } else { /* 10 segments - * segment is from 2^-10 to 2^0 + * segment is from 2^-10 to 2^1 + * We include an extra segment for range [2^0, 2^1). This is to + * ensure that colors with normalized values of 1 don't miss the + * LUT. */ region_start = -10; - region_end = 0; + region_end = 1; seg_distr[0] = 4; seg_distr[1] = 4; @@ -468,7 +471,7 @@ dce110_translate_regamma_to_hw_format(const struct dc_transfer_func *output_tf, seg_distr[7] = 4; seg_distr[8] = 4; seg_distr[9] = 4; - seg_distr[10] = -1; + seg_distr[10] = 0; seg_distr[11] = -1; seg_distr[12] = -1; seg_distr[13] = -1; @@ -1016,8 +1019,10 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx) struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->sink->link; - if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) + if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) { link->dc->hwss.edp_backlight_control(link, false); + dc_link_set_abm_disable(link); + } if (dc_is_dp_signal(pipe_ctx->stream->signal)) pipe_ctx->stream_res.stream_enc->funcs->dp_blank(pipe_ctx->stream_res.stream_enc); diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index 3ae3da4..0f5ad54 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -1264,9 +1264,9 @@ struct atom_smc_dpm_info_v4_1 uint8_t ledpin2; uint8_t padding8_4; - uint8_t gfxclkspreadenabled; - uint8_t gfxclkspreadpercent; - uint16_t gfxclkspreadfreq; + uint8_t pllgfxclkspreadenabled; + uint8_t pllgfxclkspreadpercent; + uint16_t pllgfxclkspreadfreq; uint8_t uclkspreadenabled; uint8_t uclkspreadpercent; @@ -1276,7 +1276,11 @@ struct atom_smc_dpm_info_v4_1 uint8_t socclkspreadpercent; uint16_t socclkspreadfreq; - uint32_t boardreserved[3]; + uint8_t acggfxclkspreadenabled; + uint8_t acggfxclkspreadpercent; + uint16_t acggfxclkspreadfreq; + + uint32_t boardreserved[10]; }; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile b/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile index faf9c88..210fb3e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile @@ -32,7 +32,7 @@ HARDWARE_MGR = hwmgr.o processpptables.o \ vega10_processpptables.o vega10_hwmgr.o vega10_powertune.o \ vega10_thermal.o smu10_hwmgr.o pp_psm.o\ vega12_processpptables.o vega12_hwmgr.o \ - vega12_powertune.o vega12_thermal.o \ + vega12_thermal.o \ pp_overdriver.o smu_helper.o AMD_PP_HWMGR = $(addprefix $(AMD_PP_PATH)/hwmgr/,$(HARDWARE_MGR)) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c index 55f9b30..ad42caa 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c @@ -616,9 +616,9 @@ int pp_atomfwctrl_get_smc_dpm_information(struct pp_hwmgr *hwmgr, param->ledpin1 = info->ledpin1; param->ledpin2 = info->ledpin2; - param->gfxclkspreadenabled = info->gfxclkspreadenabled; - param->gfxclkspreadpercent = info->gfxclkspreadpercent; - param->gfxclkspreadfreq = info->gfxclkspreadfreq; + param->pllgfxclkspreadenabled = info->pllgfxclkspreadenabled; + param->pllgfxclkspreadpercent = info->pllgfxclkspreadpercent; + param->pllgfxclkspreadfreq = info->pllgfxclkspreadfreq; param->uclkspreadenabled = info->uclkspreadenabled; param->uclkspreadpercent = info->uclkspreadpercent; @@ -628,5 +628,9 @@ int pp_atomfwctrl_get_smc_dpm_information(struct pp_hwmgr *hwmgr, param->socclkspreadpercent = info->socclkspreadpercent; param->socclkspreadfreq = info->socclkspreadfreq; + param->acggfxclkspreadenabled = info->acggfxclkspreadenabled; + param->acggfxclkspreadpercent = info->acggfxclkspreadpercent; + param->acggfxclkspreadfreq = info->acggfxclkspreadfreq; + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h index a957d8f..8df1e84f 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h @@ -192,9 +192,9 @@ struct pp_atomfwctrl_smc_dpm_parameters uint8_t ledpin1; uint8_t ledpin2; - uint8_t gfxclkspreadenabled; - uint8_t gfxclkspreadpercent; - uint16_t gfxclkspreadfreq; + uint8_t pllgfxclkspreadenabled; + uint8_t pllgfxclkspreadpercent; + uint16_t pllgfxclkspreadfreq; uint8_t uclkspreadenabled; uint8_t uclkspreadpercent; @@ -203,6 +203,10 @@ struct pp_atomfwctrl_smc_dpm_parameters uint8_t socclkspreadenabled; uint8_t socclkspreadpercent; uint16_t socclkspreadfreq; + + uint8_t acggfxclkspreadenabled; + uint8_t acggfxclkspreadpercent; + uint16_t acggfxclkspreadfreq; }; int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 2b0c366..26fbeaf 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3374,7 +3374,8 @@ static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, "Failed to start pm status log!", return -1); - msleep_interruptible(20); + /* Sampling period from 50ms to 4sec */ + msleep_interruptible(200); PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogSample), @@ -4742,23 +4743,27 @@ static void smu7_check_dpm_table_updated(struct pp_hwmgr *hwmgr) for (i=0; i < dep_table->count; i++) { if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) { - data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC; - break; + data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK; + return; } } - if (i == dep_table->count) + if (i == dep_table->count && data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) { data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC; + data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK; + } dep_table = table_info->vdd_dep_on_sclk; odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_sclk); for (i=0; i < dep_table->count; i++) { if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) { - data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC; - break; + data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK; + return; } } - if (i == dep_table->count) + if (i == dep_table->count && data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) { data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC; + data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK; + } } static int smu7_odn_edit_dpm_table(struct pp_hwmgr *hwmgr, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c index 75a465f..7b26607 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c @@ -319,13 +319,13 @@ static int smu8_get_system_info_data(struct pp_hwmgr *hwmgr) GetIndexIntoMasterTable(DATA, IntegratedSystemInfo), &size, &frev, &crev); - if (crev != 9) { - pr_err("Unsupported IGP table: %d %d\n", frev, crev); + if (info == NULL) { + pr_err("Could not retrieve the Integrated System Info Table!\n"); return -EINVAL; } - if (info == NULL) { - pr_err("Could not retrieve the Integrated System Info Table!\n"); + if (crev != 9) { + pr_err("Unsupported IGP table: %d %d\n", frev, crev); return -EINVAL; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c index 15ce1e8..200de46 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c @@ -33,7 +33,6 @@ #include "ppatomfwctrl.h" #include "atomfirmware.h" #include "cgs_common.h" -#include "vega12_powertune.h" #include "vega12_inc.h" #include "pp_soc15.h" #include "pppcielanes.h" @@ -893,6 +892,28 @@ static int vega12_odn_initialize_default_settings( return 0; } +static int vega12_set_overdrive_target_percentage(struct pp_hwmgr *hwmgr, + uint32_t adjust_percent) +{ + return smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_OverDriveSetPercentage, adjust_percent); +} + +static int vega12_power_control_set_level(struct pp_hwmgr *hwmgr) +{ + int adjust_percent, result = 0; + + if (PP_CAP(PHM_PlatformCaps_PowerContainment)) { + adjust_percent = + hwmgr->platform_descriptor.TDPAdjustmentPolarity ? + hwmgr->platform_descriptor.TDPAdjustment : + (-1 * hwmgr->platform_descriptor.TDPAdjustment); + result = vega12_set_overdrive_target_percentage(hwmgr, + (uint32_t)adjust_percent); + } + return result; +} + static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr) { int tmp_result, result = 0; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_powertune.c deleted file mode 100644 index 76e60c0..0000000 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_powertune.c +++ /dev/null @@ -1,1364 +0,0 @@ -/* - * Copyright 2017 Advanced Micro Devices, Inc. - * - * 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 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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 "hwmgr.h" -#include "vega12_hwmgr.h" -#include "vega12_powertune.h" -#include "vega12_smumgr.h" -#include "vega12_ppsmc.h" -#include "vega12_inc.h" -#include "pp_debug.h" -#include "pp_soc15.h" - -static const struct vega12_didt_config_reg SEDiDtTuningCtrlConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* DIDT_SQ */ - { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x3853 }, - { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x3153 }, - - /* DIDT_TD */ - { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x0dde }, - { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x0dde }, - - /* DIDT_TCP */ - { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x3dde }, - { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x3dde }, - - /* DIDT_DB */ - { ixDIDT_DB_TUNING_CTRL, DIDT_DB_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_DB_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x3dde }, - { ixDIDT_DB_TUNING_CTRL, DIDT_DB_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_DB_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x3dde }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEDiDtCtrl3Config_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /*DIDT_SQ_CTRL3 */ - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__GC_DIDT_ENABLE_MASK, DIDT_SQ_CTRL3__GC_DIDT_ENABLE__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__GC_DIDT_CLK_EN_OVERRIDE_MASK, DIDT_SQ_CTRL3__GC_DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__THROTTLE_POLICY_MASK, DIDT_SQ_CTRL3__THROTTLE_POLICY__SHIFT, 0x0003 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__DIDT_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_SQ_CTRL3__DIDT_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__DIDT_POWER_LEVEL_LOWBIT_MASK, DIDT_SQ_CTRL3__DIDT_POWER_LEVEL_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__DIDT_STALL_PATTERN_BIT_NUMS_MASK, DIDT_SQ_CTRL3__DIDT_STALL_PATTERN_BIT_NUMS__SHIFT, 0x0003 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__GC_DIDT_LEVEL_COMB_EN_MASK, DIDT_SQ_CTRL3__GC_DIDT_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__SE_DIDT_LEVEL_COMB_EN_MASK, DIDT_SQ_CTRL3__SE_DIDT_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__QUALIFY_STALL_EN_MASK, DIDT_SQ_CTRL3__QUALIFY_STALL_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__DIDT_STALL_SEL_MASK, DIDT_SQ_CTRL3__DIDT_STALL_SEL__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__DIDT_FORCE_STALL_MASK, DIDT_SQ_CTRL3__DIDT_FORCE_STALL__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL3, DIDT_SQ_CTRL3__DIDT_STALL_DELAY_EN_MASK, DIDT_SQ_CTRL3__DIDT_STALL_DELAY_EN__SHIFT, 0x0000 }, - - /*DIDT_TCP_CTRL3 */ - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__GC_DIDT_ENABLE_MASK, DIDT_TCP_CTRL3__GC_DIDT_ENABLE__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__GC_DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TCP_CTRL3__GC_DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__THROTTLE_POLICY_MASK, DIDT_TCP_CTRL3__THROTTLE_POLICY__SHIFT, 0x0003 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__DIDT_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_TCP_CTRL3__DIDT_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__DIDT_POWER_LEVEL_LOWBIT_MASK, DIDT_TCP_CTRL3__DIDT_POWER_LEVEL_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__DIDT_STALL_PATTERN_BIT_NUMS_MASK, DIDT_TCP_CTRL3__DIDT_STALL_PATTERN_BIT_NUMS__SHIFT, 0x0003 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__GC_DIDT_LEVEL_COMB_EN_MASK, DIDT_TCP_CTRL3__GC_DIDT_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__SE_DIDT_LEVEL_COMB_EN_MASK, DIDT_TCP_CTRL3__SE_DIDT_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__QUALIFY_STALL_EN_MASK, DIDT_TCP_CTRL3__QUALIFY_STALL_EN__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__DIDT_STALL_SEL_MASK, DIDT_TCP_CTRL3__DIDT_STALL_SEL__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__DIDT_FORCE_STALL_MASK, DIDT_TCP_CTRL3__DIDT_FORCE_STALL__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL3, DIDT_TCP_CTRL3__DIDT_STALL_DELAY_EN_MASK, DIDT_TCP_CTRL3__DIDT_STALL_DELAY_EN__SHIFT, 0x0000 }, - - /*DIDT_TD_CTRL3 */ - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__GC_DIDT_ENABLE_MASK, DIDT_TD_CTRL3__GC_DIDT_ENABLE__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__GC_DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TD_CTRL3__GC_DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__THROTTLE_POLICY_MASK, DIDT_TD_CTRL3__THROTTLE_POLICY__SHIFT, 0x0003 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__DIDT_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_TD_CTRL3__DIDT_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__DIDT_POWER_LEVEL_LOWBIT_MASK, DIDT_TD_CTRL3__DIDT_POWER_LEVEL_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__DIDT_STALL_PATTERN_BIT_NUMS_MASK, DIDT_TD_CTRL3__DIDT_STALL_PATTERN_BIT_NUMS__SHIFT, 0x0003 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__GC_DIDT_LEVEL_COMB_EN_MASK, DIDT_TD_CTRL3__GC_DIDT_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__SE_DIDT_LEVEL_COMB_EN_MASK, DIDT_TD_CTRL3__SE_DIDT_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__QUALIFY_STALL_EN_MASK, DIDT_TD_CTRL3__QUALIFY_STALL_EN__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__DIDT_STALL_SEL_MASK, DIDT_TD_CTRL3__DIDT_STALL_SEL__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__DIDT_FORCE_STALL_MASK, DIDT_TD_CTRL3__DIDT_FORCE_STALL__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL3, DIDT_TD_CTRL3__DIDT_STALL_DELAY_EN_MASK, DIDT_TD_CTRL3__DIDT_STALL_DELAY_EN__SHIFT, 0x0000 }, - - /*DIDT_DB_CTRL3 */ - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__GC_DIDT_ENABLE_MASK, DIDT_DB_CTRL3__GC_DIDT_ENABLE__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__GC_DIDT_CLK_EN_OVERRIDE_MASK, DIDT_DB_CTRL3__GC_DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__THROTTLE_POLICY_MASK, DIDT_DB_CTRL3__THROTTLE_POLICY__SHIFT, 0x0003 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__DIDT_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_DB_CTRL3__DIDT_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__DIDT_POWER_LEVEL_LOWBIT_MASK, DIDT_DB_CTRL3__DIDT_POWER_LEVEL_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__DIDT_STALL_PATTERN_BIT_NUMS_MASK, DIDT_DB_CTRL3__DIDT_STALL_PATTERN_BIT_NUMS__SHIFT, 0x0003 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__GC_DIDT_LEVEL_COMB_EN_MASK, DIDT_DB_CTRL3__GC_DIDT_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__SE_DIDT_LEVEL_COMB_EN_MASK, DIDT_DB_CTRL3__SE_DIDT_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__QUALIFY_STALL_EN_MASK, DIDT_DB_CTRL3__QUALIFY_STALL_EN__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__DIDT_STALL_SEL_MASK, DIDT_DB_CTRL3__DIDT_STALL_SEL__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__DIDT_FORCE_STALL_MASK, DIDT_DB_CTRL3__DIDT_FORCE_STALL__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL3, DIDT_DB_CTRL3__DIDT_STALL_DELAY_EN_MASK, DIDT_DB_CTRL3__DIDT_STALL_DELAY_EN__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEDiDtCtrl2Config_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* DIDT_SQ */ - { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__MAX_POWER_DELTA_MASK, DIDT_SQ_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3853 }, - { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x00c0 }, - { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000 }, - - /* DIDT_TD */ - { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__MAX_POWER_DELTA_MASK, DIDT_TD_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3fff }, - { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x00c0 }, - { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0001 }, - - /* DIDT_TCP */ - { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__MAX_POWER_DELTA_MASK, DIDT_TCP_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3dde }, - { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x00c0 }, - { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0001 }, - - /* DIDT_DB */ - { ixDIDT_DB_CTRL2, DIDT_DB_CTRL2__MAX_POWER_DELTA_MASK, DIDT_DB_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3dde }, - { ixDIDT_DB_CTRL2, DIDT_DB_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_DB_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x00c0 }, - { ixDIDT_DB_CTRL2, DIDT_DB_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_DB_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0001 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEDiDtCtrl1Config_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* DIDT_SQ */ - { ixDIDT_SQ_CTRL1, DIDT_SQ_CTRL1__MIN_POWER_MASK, DIDT_SQ_CTRL1__MIN_POWER__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL1, DIDT_SQ_CTRL1__MAX_POWER_MASK, DIDT_SQ_CTRL1__MAX_POWER__SHIFT, 0xffff }, - /* DIDT_TD */ - { ixDIDT_TD_CTRL1, DIDT_TD_CTRL1__MIN_POWER_MASK, DIDT_TD_CTRL1__MIN_POWER__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL1, DIDT_TD_CTRL1__MAX_POWER_MASK, DIDT_TD_CTRL1__MAX_POWER__SHIFT, 0xffff }, - /* DIDT_TCP */ - { ixDIDT_TCP_CTRL1, DIDT_TCP_CTRL1__MIN_POWER_MASK, DIDT_TCP_CTRL1__MIN_POWER__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL1, DIDT_TCP_CTRL1__MAX_POWER_MASK, DIDT_TCP_CTRL1__MAX_POWER__SHIFT, 0xffff }, - /* DIDT_DB */ - { ixDIDT_DB_CTRL1, DIDT_DB_CTRL1__MIN_POWER_MASK, DIDT_DB_CTRL1__MIN_POWER__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL1, DIDT_DB_CTRL1__MAX_POWER_MASK, DIDT_DB_CTRL1__MAX_POWER__SHIFT, 0xffff }, - - { 0xFFFFFFFF } /* End of list */ -}; - - -static const struct vega12_didt_config_reg SEDiDtWeightConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* DIDT_SQ */ - { ixDIDT_SQ_WEIGHT0_3, 0xFFFFFFFF, 0, 0x2B363B1A }, - { ixDIDT_SQ_WEIGHT4_7, 0xFFFFFFFF, 0, 0x270B2432 }, - { ixDIDT_SQ_WEIGHT8_11, 0xFFFFFFFF, 0, 0x00000018 }, - - /* DIDT_TD */ - { ixDIDT_TD_WEIGHT0_3, 0xFFFFFFFF, 0, 0x2B1D220F }, - { ixDIDT_TD_WEIGHT4_7, 0xFFFFFFFF, 0, 0x00007558 }, - { ixDIDT_TD_WEIGHT8_11, 0xFFFFFFFF, 0, 0x00000000 }, - - /* DIDT_TCP */ - { ixDIDT_TCP_WEIGHT0_3, 0xFFFFFFFF, 0, 0x5ACE160D }, - { ixDIDT_TCP_WEIGHT4_7, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TCP_WEIGHT8_11, 0xFFFFFFFF, 0, 0x00000000 }, - - /* DIDT_DB */ - { ixDIDT_DB_WEIGHT0_3, 0xFFFFFFFF, 0, 0x0E152A0F }, - { ixDIDT_DB_WEIGHT4_7, 0xFFFFFFFF, 0, 0x09061813 }, - { ixDIDT_DB_WEIGHT8_11, 0xFFFFFFFF, 0, 0x00000013 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEDiDtCtrl0Config_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* DIDT_SQ */ - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK, DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__PHASE_OFFSET_MASK, DIDT_SQ_CTRL0__PHASE_OFFSET__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CTRL_RST_MASK, DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_STALL_CTRL_EN_MASK, DIDT_SQ_CTRL0__DIDT_STALL_CTRL_EN__SHIFT, 0x0001 }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_TUNING_CTRL_EN_MASK, DIDT_SQ_CTRL0__DIDT_TUNING_CTRL_EN__SHIFT, 0x0001 }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_STALL_AUTO_RELEASE_EN_MASK, DIDT_SQ_CTRL0__DIDT_STALL_AUTO_RELEASE_EN__SHIFT, 0x0001 }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_SQ_CTRL0__DIDT_HI_POWER_THRESHOLD__SHIFT, 0xffff }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_AUTO_MPD_EN_MASK, DIDT_SQ_CTRL0__DIDT_AUTO_MPD_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_STALL_EVENT_EN_MASK, DIDT_SQ_CTRL0__DIDT_STALL_EVENT_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_STALL_EVENT_COUNTER_CLEAR_MASK, DIDT_SQ_CTRL0__DIDT_STALL_EVENT_COUNTER_CLEAR__SHIFT, 0x0000 }, - /* DIDT_TD */ - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK, DIDT_TD_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__PHASE_OFFSET_MASK, DIDT_TD_CTRL0__PHASE_OFFSET__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CTRL_RST_MASK, DIDT_TD_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_STALL_CTRL_EN_MASK, DIDT_TD_CTRL0__DIDT_STALL_CTRL_EN__SHIFT, 0x0001 }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_TUNING_CTRL_EN_MASK, DIDT_TD_CTRL0__DIDT_TUNING_CTRL_EN__SHIFT, 0x0001 }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_STALL_AUTO_RELEASE_EN_MASK, DIDT_TD_CTRL0__DIDT_STALL_AUTO_RELEASE_EN__SHIFT, 0x0001 }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_TD_CTRL0__DIDT_HI_POWER_THRESHOLD__SHIFT, 0xffff }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_AUTO_MPD_EN_MASK, DIDT_TD_CTRL0__DIDT_AUTO_MPD_EN__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_STALL_EVENT_EN_MASK, DIDT_TD_CTRL0__DIDT_STALL_EVENT_EN__SHIFT, 0x0000 }, - { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_STALL_EVENT_COUNTER_CLEAR_MASK, DIDT_TD_CTRL0__DIDT_STALL_EVENT_COUNTER_CLEAR__SHIFT, 0x0000 }, - /* DIDT_TCP */ - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK, DIDT_TCP_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__PHASE_OFFSET_MASK, DIDT_TCP_CTRL0__PHASE_OFFSET__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CTRL_RST_MASK, DIDT_TCP_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_STALL_CTRL_EN_MASK, DIDT_TCP_CTRL0__DIDT_STALL_CTRL_EN__SHIFT, 0x0001 }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_TUNING_CTRL_EN_MASK, DIDT_TCP_CTRL0__DIDT_TUNING_CTRL_EN__SHIFT, 0x0001 }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_STALL_AUTO_RELEASE_EN_MASK, DIDT_TCP_CTRL0__DIDT_STALL_AUTO_RELEASE_EN__SHIFT, 0x0001 }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_TCP_CTRL0__DIDT_HI_POWER_THRESHOLD__SHIFT, 0xffff }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_AUTO_MPD_EN_MASK, DIDT_TCP_CTRL0__DIDT_AUTO_MPD_EN__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_STALL_EVENT_EN_MASK, DIDT_TCP_CTRL0__DIDT_STALL_EVENT_EN__SHIFT, 0x0000 }, - { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_STALL_EVENT_COUNTER_CLEAR_MASK, DIDT_TCP_CTRL0__DIDT_STALL_EVENT_COUNTER_CLEAR__SHIFT, 0x0000 }, - /* DIDT_DB */ - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_CTRL_EN_MASK, DIDT_DB_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__PHASE_OFFSET_MASK, DIDT_DB_CTRL0__PHASE_OFFSET__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_CTRL_RST_MASK, DIDT_DB_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_DB_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_STALL_CTRL_EN_MASK, DIDT_DB_CTRL0__DIDT_STALL_CTRL_EN__SHIFT, 0x0001 }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_TUNING_CTRL_EN_MASK, DIDT_DB_CTRL0__DIDT_TUNING_CTRL_EN__SHIFT, 0x0001 }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_STALL_AUTO_RELEASE_EN_MASK, DIDT_DB_CTRL0__DIDT_STALL_AUTO_RELEASE_EN__SHIFT, 0x0001 }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_DB_CTRL0__DIDT_HI_POWER_THRESHOLD__SHIFT, 0xffff }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_AUTO_MPD_EN_MASK, DIDT_DB_CTRL0__DIDT_AUTO_MPD_EN__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_STALL_EVENT_EN_MASK, DIDT_DB_CTRL0__DIDT_STALL_EVENT_EN__SHIFT, 0x0000 }, - { ixDIDT_DB_CTRL0, DIDT_DB_CTRL0__DIDT_STALL_EVENT_COUNTER_CLEAR_MASK, DIDT_DB_CTRL0__DIDT_STALL_EVENT_COUNTER_CLEAR__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - - -static const struct vega12_didt_config_reg SEDiDtStallCtrlConfig_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* DIDT_SQ */ - { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0004 }, - { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0004 }, - { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_SQ_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x000a }, - { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_SQ_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x000a }, - - /* DIDT_TD */ - { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001 }, - { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001 }, - { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_TD_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x000a }, - { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_TD_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x000a }, - - /* DIDT_TCP */ - { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001 }, - { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001 }, - { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_TCP_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x000a }, - { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_TCP_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x000a }, - - /* DIDT_DB */ - { ixDIDT_DB_STALL_CTRL, DIDT_DB_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_DB_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0004 }, - { ixDIDT_DB_STALL_CTRL, DIDT_DB_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_DB_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0004 }, - { ixDIDT_DB_STALL_CTRL, DIDT_DB_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_DB_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x000a }, - { ixDIDT_DB_STALL_CTRL, DIDT_DB_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_DB_STALL_CTRL__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x000a }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEDiDtStallPatternConfig_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* DIDT_SQ_STALL_PATTERN_1_2 */ - { ixDIDT_SQ_STALL_PATTERN_1_2, DIDT_SQ_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_1_MASK, DIDT_SQ_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_1__SHIFT, 0x0001 }, - { ixDIDT_SQ_STALL_PATTERN_1_2, DIDT_SQ_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_2_MASK, DIDT_SQ_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_2__SHIFT, 0x0001 }, - - /* DIDT_SQ_STALL_PATTERN_3_4 */ - { ixDIDT_SQ_STALL_PATTERN_3_4, DIDT_SQ_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_3_MASK, DIDT_SQ_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_3__SHIFT, 0x0001 }, - { ixDIDT_SQ_STALL_PATTERN_3_4, DIDT_SQ_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_4_MASK, DIDT_SQ_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_4__SHIFT, 0x0001 }, - - /* DIDT_SQ_STALL_PATTERN_5_6 */ - { ixDIDT_SQ_STALL_PATTERN_5_6, DIDT_SQ_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_5_MASK, DIDT_SQ_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_5__SHIFT, 0x0000 }, - { ixDIDT_SQ_STALL_PATTERN_5_6, DIDT_SQ_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_6_MASK, DIDT_SQ_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_6__SHIFT, 0x0000 }, - - /* DIDT_SQ_STALL_PATTERN_7 */ - { ixDIDT_SQ_STALL_PATTERN_7, DIDT_SQ_STALL_PATTERN_7__DIDT_STALL_PATTERN_7_MASK, DIDT_SQ_STALL_PATTERN_7__DIDT_STALL_PATTERN_7__SHIFT, 0x0000 }, - - /* DIDT_TCP_STALL_PATTERN_1_2 */ - { ixDIDT_TCP_STALL_PATTERN_1_2, DIDT_TCP_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_1_MASK, DIDT_TCP_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_1__SHIFT, 0x0001 }, - { ixDIDT_TCP_STALL_PATTERN_1_2, DIDT_TCP_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_2_MASK, DIDT_TCP_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_2__SHIFT, 0x0001 }, - - /* DIDT_TCP_STALL_PATTERN_3_4 */ - { ixDIDT_TCP_STALL_PATTERN_3_4, DIDT_TCP_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_3_MASK, DIDT_TCP_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_3__SHIFT, 0x0001 }, - { ixDIDT_TCP_STALL_PATTERN_3_4, DIDT_TCP_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_4_MASK, DIDT_TCP_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_4__SHIFT, 0x0001 }, - - /* DIDT_TCP_STALL_PATTERN_5_6 */ - { ixDIDT_TCP_STALL_PATTERN_5_6, DIDT_TCP_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_5_MASK, DIDT_TCP_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_5__SHIFT, 0x0000 }, - { ixDIDT_TCP_STALL_PATTERN_5_6, DIDT_TCP_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_6_MASK, DIDT_TCP_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_6__SHIFT, 0x0000 }, - - /* DIDT_TCP_STALL_PATTERN_7 */ - { ixDIDT_TCP_STALL_PATTERN_7, DIDT_TCP_STALL_PATTERN_7__DIDT_STALL_PATTERN_7_MASK, DIDT_TCP_STALL_PATTERN_7__DIDT_STALL_PATTERN_7__SHIFT, 0x0000 }, - - /* DIDT_TD_STALL_PATTERN_1_2 */ - { ixDIDT_TD_STALL_PATTERN_1_2, DIDT_TD_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_1_MASK, DIDT_TD_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_1__SHIFT, 0x0001 }, - { ixDIDT_TD_STALL_PATTERN_1_2, DIDT_TD_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_2_MASK, DIDT_TD_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_2__SHIFT, 0x0001 }, - - /* DIDT_TD_STALL_PATTERN_3_4 */ - { ixDIDT_TD_STALL_PATTERN_3_4, DIDT_TD_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_3_MASK, DIDT_TD_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_3__SHIFT, 0x0001 }, - { ixDIDT_TD_STALL_PATTERN_3_4, DIDT_TD_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_4_MASK, DIDT_TD_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_4__SHIFT, 0x0001 }, - - /* DIDT_TD_STALL_PATTERN_5_6 */ - { ixDIDT_TD_STALL_PATTERN_5_6, DIDT_TD_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_5_MASK, DIDT_TD_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_5__SHIFT, 0x0000 }, - { ixDIDT_TD_STALL_PATTERN_5_6, DIDT_TD_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_6_MASK, DIDT_TD_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_6__SHIFT, 0x0000 }, - - /* DIDT_TD_STALL_PATTERN_7 */ - { ixDIDT_TD_STALL_PATTERN_7, DIDT_TD_STALL_PATTERN_7__DIDT_STALL_PATTERN_7_MASK, DIDT_TD_STALL_PATTERN_7__DIDT_STALL_PATTERN_7__SHIFT, 0x0000 }, - - /* DIDT_DB_STALL_PATTERN_1_2 */ - { ixDIDT_DB_STALL_PATTERN_1_2, DIDT_DB_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_1_MASK, DIDT_DB_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_1__SHIFT, 0x0001 }, - { ixDIDT_DB_STALL_PATTERN_1_2, DIDT_DB_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_2_MASK, DIDT_DB_STALL_PATTERN_1_2__DIDT_STALL_PATTERN_2__SHIFT, 0x0001 }, - - /* DIDT_DB_STALL_PATTERN_3_4 */ - { ixDIDT_DB_STALL_PATTERN_3_4, DIDT_DB_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_3_MASK, DIDT_DB_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_3__SHIFT, 0x0001 }, - { ixDIDT_DB_STALL_PATTERN_3_4, DIDT_DB_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_4_MASK, DIDT_DB_STALL_PATTERN_3_4__DIDT_STALL_PATTERN_4__SHIFT, 0x0001 }, - - /* DIDT_DB_STALL_PATTERN_5_6 */ - { ixDIDT_DB_STALL_PATTERN_5_6, DIDT_DB_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_5_MASK, DIDT_DB_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_5__SHIFT, 0x0000 }, - { ixDIDT_DB_STALL_PATTERN_5_6, DIDT_DB_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_6_MASK, DIDT_DB_STALL_PATTERN_5_6__DIDT_STALL_PATTERN_6__SHIFT, 0x0000 }, - - /* DIDT_DB_STALL_PATTERN_7 */ - { ixDIDT_DB_STALL_PATTERN_7, DIDT_DB_STALL_PATTERN_7__DIDT_STALL_PATTERN_7_MASK, DIDT_DB_STALL_PATTERN_7__DIDT_STALL_PATTERN_7__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SELCacConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ */ - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x00060021 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x00860021 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x01060021 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x01860021 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x02060021 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x02860021 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x03060021 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x03860021 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x04060021 }, - /* TD */ - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x000E0020 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x008E0020 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x010E0020 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x018E0020 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x020E0020 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x028E0020 }, - /* TCP */ - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x001c0020 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x009c0020 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x011c0020 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x019c0020 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x021c0020 }, - /* DB */ - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x00200008 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x00820008 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x01020008 }, - { ixSE_CAC_CNTL, 0xFFFFFFFF, 0, 0x01820008 }, - - { 0xFFFFFFFF } /* End of list */ -}; - - -static const struct vega12_didt_config_reg SEEDCStallPatternConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ */ - { ixDIDT_SQ_EDC_STALL_PATTERN_1_2, 0xFFFFFFFF, 0, 0x00030001 }, - { ixDIDT_SQ_EDC_STALL_PATTERN_3_4, 0xFFFFFFFF, 0, 0x000F0007 }, - { ixDIDT_SQ_EDC_STALL_PATTERN_5_6, 0xFFFFFFFF, 0, 0x003F001F }, - { ixDIDT_SQ_EDC_STALL_PATTERN_7, 0xFFFFFFFF, 0, 0x0000007F }, - /* TD */ - { ixDIDT_TD_EDC_STALL_PATTERN_1_2, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TD_EDC_STALL_PATTERN_3_4, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TD_EDC_STALL_PATTERN_5_6, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TD_EDC_STALL_PATTERN_7, 0xFFFFFFFF, 0, 0x00000000 }, - /* TCP */ - { ixDIDT_TCP_EDC_STALL_PATTERN_1_2, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TCP_EDC_STALL_PATTERN_3_4, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TCP_EDC_STALL_PATTERN_5_6, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TCP_EDC_STALL_PATTERN_7, 0xFFFFFFFF, 0, 0x00000000 }, - /* DB */ - { ixDIDT_DB_EDC_STALL_PATTERN_1_2, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_DB_EDC_STALL_PATTERN_3_4, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_DB_EDC_STALL_PATTERN_5_6, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_DB_EDC_STALL_PATTERN_7, 0xFFFFFFFF, 0, 0x00000000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEEDCForceStallPatternConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ */ - { ixDIDT_SQ_EDC_STALL_PATTERN_1_2, 0xFFFFFFFF, 0, 0x00000015 }, - { ixDIDT_SQ_EDC_STALL_PATTERN_3_4, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_SQ_EDC_STALL_PATTERN_5_6, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_SQ_EDC_STALL_PATTERN_7, 0xFFFFFFFF, 0, 0x00000000 }, - /* TD */ - { ixDIDT_TD_EDC_STALL_PATTERN_1_2, 0xFFFFFFFF, 0, 0x00000015 }, - { ixDIDT_TD_EDC_STALL_PATTERN_3_4, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TD_EDC_STALL_PATTERN_5_6, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TD_EDC_STALL_PATTERN_7, 0xFFFFFFFF, 0, 0x00000000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEEDCStallDelayConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ */ - { ixDIDT_SQ_EDC_STALL_DELAY_1, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_SQ_EDC_STALL_DELAY_2, 0xFFFFFFFF, 0, 0x00000000 }, - /* TD */ - { ixDIDT_TD_EDC_STALL_DELAY_1, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TD_EDC_STALL_DELAY_2, 0xFFFFFFFF, 0, 0x00000000 }, - /* TCP */ - { ixDIDT_TCP_EDC_STALL_DELAY_1, 0xFFFFFFFF, 0, 0x00000000 }, - { ixDIDT_TCP_EDC_STALL_DELAY_2, 0xFFFFFFFF, 0, 0x00000000 }, - /* DB */ - { ixDIDT_DB_EDC_STALL_DELAY_1, 0xFFFFFFFF, 0, 0x00000000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEEDCThresholdConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - { ixDIDT_SQ_EDC_THRESHOLD, 0xFFFFFFFF, 0, 0x0000010E }, - { ixDIDT_TD_EDC_THRESHOLD, 0xFFFFFFFF, 0, 0xFFFFFFFF }, - { ixDIDT_TCP_EDC_THRESHOLD, 0xFFFFFFFF, 0, 0xFFFFFFFF }, - { ixDIDT_DB_EDC_THRESHOLD, 0xFFFFFFFF, 0, 0xFFFFFFFF }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEEDCCtrlResetConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ */ - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_EN_MASK, DIDT_SQ_EDC_CTRL__EDC_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_SW_RST_MASK, DIDT_SQ_EDC_CTRL__EDC_SW_RST__SHIFT, 0x0001 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE_MASK, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL_MASK, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS_MASK, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA_MASK, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEEDCCtrlConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ */ - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_EN_MASK, DIDT_SQ_EDC_CTRL__EDC_EN__SHIFT, 0x0001 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_SW_RST_MASK, DIDT_SQ_EDC_CTRL__EDC_SW_RST__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE_MASK, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL_MASK, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0004 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS_MASK, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS__SHIFT, 0x0006 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA_MASK, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN__SHIFT, 0x0001 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg SEEDCCtrlForceStallConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ */ - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_EN_MASK, DIDT_SQ_EDC_CTRL__EDC_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_SW_RST_MASK, DIDT_SQ_EDC_CTRL__EDC_SW_RST__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE_MASK, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL_MASK, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL__SHIFT, 0x0001 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0001 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS_MASK, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS__SHIFT, 0x000C }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA_MASK, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN__SHIFT, 0x0001 }, - - /* TD */ - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__EDC_EN_MASK, DIDT_TD_EDC_CTRL__EDC_EN__SHIFT, 0x0000 }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__EDC_SW_RST_MASK, DIDT_TD_EDC_CTRL__EDC_SW_RST__SHIFT, 0x0000 }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__EDC_CLK_EN_OVERRIDE_MASK, DIDT_TD_EDC_CTRL__EDC_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__EDC_FORCE_STALL_MASK, DIDT_TD_EDC_CTRL__EDC_FORCE_STALL__SHIFT, 0x0001 }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_TD_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0001 }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS_MASK, DIDT_TD_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS__SHIFT, 0x000E }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA_MASK, DIDT_TD_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA__SHIFT, 0x0000 }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__GC_EDC_EN_MASK, DIDT_TD_EDC_CTRL__GC_EDC_EN__SHIFT, 0x0000 }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__GC_EDC_STALL_POLICY_MASK, DIDT_TD_EDC_CTRL__GC_EDC_STALL_POLICY__SHIFT, 0x0000 }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__GC_EDC_LEVEL_COMB_EN_MASK, DIDT_TD_EDC_CTRL__GC_EDC_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_TD_EDC_CTRL, DIDT_TD_EDC_CTRL__SE_EDC_LEVEL_COMB_EN_MASK, DIDT_TD_EDC_CTRL__SE_EDC_LEVEL_COMB_EN__SHIFT, 0x0001 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg GCDiDtDroopCtrlConfig_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - { mmGC_DIDT_DROOP_CTRL, GC_DIDT_DROOP_CTRL__DIDT_DROOP_LEVEL_EN_MASK, GC_DIDT_DROOP_CTRL__DIDT_DROOP_LEVEL_EN__SHIFT, 0x0000 }, - { mmGC_DIDT_DROOP_CTRL, GC_DIDT_DROOP_CTRL__DIDT_DROOP_THRESHOLD_MASK, GC_DIDT_DROOP_CTRL__DIDT_DROOP_THRESHOLD__SHIFT, 0x0000 }, - { mmGC_DIDT_DROOP_CTRL, GC_DIDT_DROOP_CTRL__DIDT_DROOP_LEVEL_INDEX_MASK, GC_DIDT_DROOP_CTRL__DIDT_DROOP_LEVEL_INDEX__SHIFT, 0x0000 }, - { mmGC_DIDT_DROOP_CTRL, GC_DIDT_DROOP_CTRL__DIDT_LEVEL_SEL_MASK, GC_DIDT_DROOP_CTRL__DIDT_LEVEL_SEL__SHIFT, 0x0000 }, - { mmGC_DIDT_DROOP_CTRL, GC_DIDT_DROOP_CTRL__DIDT_DROOP_LEVEL_OVERFLOW_MASK, GC_DIDT_DROOP_CTRL__DIDT_DROOP_LEVEL_OVERFLOW__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg GCDiDtCtrl0Config_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - { mmGC_DIDT_CTRL0, GC_DIDT_CTRL0__DIDT_CTRL_EN_MASK, GC_DIDT_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0000 }, - { mmGC_DIDT_CTRL0, GC_DIDT_CTRL0__PHASE_OFFSET_MASK, GC_DIDT_CTRL0__PHASE_OFFSET__SHIFT, 0x0000 }, - { mmGC_DIDT_CTRL0, GC_DIDT_CTRL0__DIDT_SW_RST_MASK, GC_DIDT_CTRL0__DIDT_SW_RST__SHIFT, 0x0000 }, - { mmGC_DIDT_CTRL0, GC_DIDT_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, GC_DIDT_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { mmGC_DIDT_CTRL0, GC_DIDT_CTRL0__DIDT_TRIGGER_THROTTLE_LOWBIT_MASK, GC_DIDT_CTRL0__DIDT_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { 0xFFFFFFFF } /* End of list */ -}; - - -static const struct vega12_didt_config_reg PSMSEEDCStallPatternConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ EDC STALL PATTERNs */ - { ixDIDT_SQ_EDC_STALL_PATTERN_1_2, DIDT_SQ_EDC_STALL_PATTERN_1_2__EDC_STALL_PATTERN_1_MASK, DIDT_SQ_EDC_STALL_PATTERN_1_2__EDC_STALL_PATTERN_1__SHIFT, 0x0101 }, - { ixDIDT_SQ_EDC_STALL_PATTERN_1_2, DIDT_SQ_EDC_STALL_PATTERN_1_2__EDC_STALL_PATTERN_2_MASK, DIDT_SQ_EDC_STALL_PATTERN_1_2__EDC_STALL_PATTERN_2__SHIFT, 0x0101 }, - { ixDIDT_SQ_EDC_STALL_PATTERN_3_4, DIDT_SQ_EDC_STALL_PATTERN_3_4__EDC_STALL_PATTERN_3_MASK, DIDT_SQ_EDC_STALL_PATTERN_3_4__EDC_STALL_PATTERN_3__SHIFT, 0x1111 }, - { ixDIDT_SQ_EDC_STALL_PATTERN_3_4, DIDT_SQ_EDC_STALL_PATTERN_3_4__EDC_STALL_PATTERN_4_MASK, DIDT_SQ_EDC_STALL_PATTERN_3_4__EDC_STALL_PATTERN_4__SHIFT, 0x1111 }, - - { ixDIDT_SQ_EDC_STALL_PATTERN_5_6, DIDT_SQ_EDC_STALL_PATTERN_5_6__EDC_STALL_PATTERN_5_MASK, DIDT_SQ_EDC_STALL_PATTERN_5_6__EDC_STALL_PATTERN_5__SHIFT, 0x1515 }, - { ixDIDT_SQ_EDC_STALL_PATTERN_5_6, DIDT_SQ_EDC_STALL_PATTERN_5_6__EDC_STALL_PATTERN_6_MASK, DIDT_SQ_EDC_STALL_PATTERN_5_6__EDC_STALL_PATTERN_6__SHIFT, 0x1515 }, - - { ixDIDT_SQ_EDC_STALL_PATTERN_7, DIDT_SQ_EDC_STALL_PATTERN_7__EDC_STALL_PATTERN_7_MASK, DIDT_SQ_EDC_STALL_PATTERN_7__EDC_STALL_PATTERN_7__SHIFT, 0x5555 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg PSMSEEDCStallDelayConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ EDC STALL DELAYs */ - { ixDIDT_SQ_EDC_STALL_DELAY_1, DIDT_SQ_EDC_STALL_DELAY_1__EDC_STALL_DELAY_SQ0_MASK, DIDT_SQ_EDC_STALL_DELAY_1__EDC_STALL_DELAY_SQ0__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_STALL_DELAY_1, DIDT_SQ_EDC_STALL_DELAY_1__EDC_STALL_DELAY_SQ1_MASK, DIDT_SQ_EDC_STALL_DELAY_1__EDC_STALL_DELAY_SQ1__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_STALL_DELAY_1, DIDT_SQ_EDC_STALL_DELAY_1__EDC_STALL_DELAY_SQ2_MASK, DIDT_SQ_EDC_STALL_DELAY_1__EDC_STALL_DELAY_SQ2__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_STALL_DELAY_1, DIDT_SQ_EDC_STALL_DELAY_1__EDC_STALL_DELAY_SQ3_MASK, DIDT_SQ_EDC_STALL_DELAY_1__EDC_STALL_DELAY_SQ3__SHIFT, 0x0000 }, - - { ixDIDT_SQ_EDC_STALL_DELAY_2, DIDT_SQ_EDC_STALL_DELAY_2__EDC_STALL_DELAY_SQ4_MASK, DIDT_SQ_EDC_STALL_DELAY_2__EDC_STALL_DELAY_SQ4__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg PSMSEEDCThresholdConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ EDC THRESHOLD */ - { ixDIDT_SQ_EDC_THRESHOLD, DIDT_SQ_EDC_THRESHOLD__EDC_THRESHOLD_MASK, DIDT_SQ_EDC_THRESHOLD__EDC_THRESHOLD__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg PSMSEEDCCtrlResetConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ EDC CTRL */ - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_EN_MASK, DIDT_SQ_EDC_CTRL__EDC_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_SW_RST_MASK, DIDT_SQ_EDC_CTRL__EDC_SW_RST__SHIFT, 0x0001 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE_MASK, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL_MASK, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS_MASK, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA_MASK, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg PSMSEEDCCtrlConfig_Vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - /* SQ EDC CTRL */ - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_EN_MASK, DIDT_SQ_EDC_CTRL__EDC_EN__SHIFT, 0x0001 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_SW_RST_MASK, DIDT_SQ_EDC_CTRL__EDC_SW_RST__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE_MASK, DIDT_SQ_EDC_CTRL__EDC_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL_MASK, DIDT_SQ_EDC_CTRL__EDC_FORCE_STALL__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT_MASK, DIDT_SQ_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS_MASK, DIDT_SQ_EDC_CTRL__EDC_STALL_PATTERN_BIT_NUMS__SHIFT, 0x000E }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA_MASK, DIDT_SQ_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA__SHIFT, 0x0000 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_EN__SHIFT, 0x0001 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_STALL_POLICY__SHIFT, 0x0003 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__GC_EDC_LEVEL_COMB_EN__SHIFT, 0x0001 }, - { ixDIDT_SQ_EDC_CTRL, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN_MASK, DIDT_SQ_EDC_CTRL__SE_EDC_LEVEL_COMB_EN__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg PSMGCEDCThresholdConfig_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - { mmGC_EDC_THRESHOLD, GC_EDC_THRESHOLD__EDC_THRESHOLD_MASK, GC_EDC_THRESHOLD__EDC_THRESHOLD__SHIFT, 0x0000000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg PSMGCEDCDroopCtrlConfig_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - { mmGC_EDC_DROOP_CTRL, GC_EDC_DROOP_CTRL__EDC_DROOP_LEVEL_EN_MASK, GC_EDC_DROOP_CTRL__EDC_DROOP_LEVEL_EN__SHIFT, 0x0001 }, - { mmGC_EDC_DROOP_CTRL, GC_EDC_DROOP_CTRL__EDC_DROOP_THRESHOLD_MASK, GC_EDC_DROOP_CTRL__EDC_DROOP_THRESHOLD__SHIFT, 0x0384 }, - { mmGC_EDC_DROOP_CTRL, GC_EDC_DROOP_CTRL__EDC_DROOP_LEVEL_INDEX_MASK, GC_EDC_DROOP_CTRL__EDC_DROOP_LEVEL_INDEX__SHIFT, 0x0001 }, - { mmGC_EDC_DROOP_CTRL, GC_EDC_DROOP_CTRL__AVG_PSM_SEL_MASK, GC_EDC_DROOP_CTRL__AVG_PSM_SEL__SHIFT, 0x0001 }, - { mmGC_EDC_DROOP_CTRL, GC_EDC_DROOP_CTRL__EDC_LEVEL_SEL_MASK, GC_EDC_DROOP_CTRL__EDC_LEVEL_SEL__SHIFT, 0x0001 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg PSMGCEDCCtrlResetConfig_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_EN_MASK, GC_EDC_CTRL__EDC_EN__SHIFT, 0x0000 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_SW_RST_MASK, GC_EDC_CTRL__EDC_SW_RST__SHIFT, 0x0001 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_CLK_EN_OVERRIDE_MASK, GC_EDC_CTRL__EDC_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_FORCE_STALL_MASK, GC_EDC_CTRL__EDC_FORCE_STALL__SHIFT, 0x0000 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT_MASK, GC_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA_MASK, GC_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg PSMGCEDCCtrlConfig_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_EN_MASK, GC_EDC_CTRL__EDC_EN__SHIFT, 0x0001 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_SW_RST_MASK, GC_EDC_CTRL__EDC_SW_RST__SHIFT, 0x0000 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_CLK_EN_OVERRIDE_MASK, GC_EDC_CTRL__EDC_CLK_EN_OVERRIDE__SHIFT, 0x0000 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_FORCE_STALL_MASK, GC_EDC_CTRL__EDC_FORCE_STALL__SHIFT, 0x0000 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT_MASK, GC_EDC_CTRL__EDC_TRIGGER_THROTTLE_LOWBIT__SHIFT, 0x0000 }, - { mmGC_EDC_CTRL, GC_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA_MASK, GC_EDC_CTRL__EDC_ALLOW_WRITE_PWRDELTA__SHIFT, 0x0000 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg AvfsPSMResetConfig_vega12[]= -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - { 0x16A02, 0xFFFFFFFF, 0x0, 0x0000005F }, - { 0x16A05, 0xFFFFFFFF, 0x0, 0x00000001 }, - { 0x16A06, 0x00000001, 0x0, 0x02000000 }, - { 0x16A01, 0xFFFFFFFF, 0x0, 0x00003027 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static const struct vega12_didt_config_reg AvfsPSMInitConfig_vega12[] = -{ -/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - * Offset Mask Shift Value - * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - */ - { 0x16A05, 0xFFFFFFFF, 0x18, 0x00000001 }, - { 0x16A05, 0xFFFFFFFF, 0x8, 0x00000003 }, - { 0x16A05, 0xFFFFFFFF, 0xa, 0x00000006 }, - { 0x16A05, 0xFFFFFFFF, 0x7, 0x00000000 }, - { 0x16A06, 0xFFFFFFFF, 0x18, 0x00000001 }, - { 0x16A06, 0xFFFFFFFF, 0x19, 0x00000001 }, - { 0x16A01, 0xFFFFFFFF, 0x0, 0x00003027 }, - - { 0xFFFFFFFF } /* End of list */ -}; - -static int vega12_program_didt_config_registers(struct pp_hwmgr *hwmgr, const struct vega12_didt_config_reg *config_regs, enum vega12_didt_config_reg_type reg_type) -{ - uint32_t data; - - PP_ASSERT_WITH_CODE((config_regs != NULL), "[vega12_program_didt_config_registers] Invalid config register table!", return -EINVAL); - - while (config_regs->offset != 0xFFFFFFFF) { - switch (reg_type) { - case VEGA12_CONFIGREG_DIDT: - data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, config_regs->offset); - data &= ~config_regs->mask; - data |= ((config_regs->value << config_regs->shift) & config_regs->mask); - cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, config_regs->offset, data); - break; - case VEGA12_CONFIGREG_GCCAC: - data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG_GC_CAC, config_regs->offset); - data &= ~config_regs->mask; - data |= ((config_regs->value << config_regs->shift) & config_regs->mask); - cgs_write_ind_register(hwmgr->device, CGS_IND_REG_GC_CAC, config_regs->offset, data); - break; - case VEGA12_CONFIGREG_SECAC: - data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG_SE_CAC, config_regs->offset); - data &= ~config_regs->mask; - data |= ((config_regs->value << config_regs->shift) & config_regs->mask); - cgs_write_ind_register(hwmgr->device, CGS_IND_REG_SE_CAC, config_regs->offset, data); - break; - default: - return -EINVAL; - } - - config_regs++; - } - - return 0; -} - -static int vega12_program_gc_didt_config_registers(struct pp_hwmgr *hwmgr, const struct vega12_didt_config_reg *config_regs) -{ - uint32_t data; - - while (config_regs->offset != 0xFFFFFFFF) { - data = cgs_read_register(hwmgr->device, config_regs->offset); - data &= ~config_regs->mask; - data |= ((config_regs->value << config_regs->shift) & config_regs->mask); - cgs_write_register(hwmgr->device, config_regs->offset, data); - config_regs++; - } - - return 0; -} - -static void vega12_didt_set_mask(struct pp_hwmgr *hwmgr, const bool enable) -{ - uint32_t data; - int result; - uint32_t en = (enable ? 1 : 0); - uint32_t didt_block_info = SQ_IR_MASK | TCP_IR_MASK | TD_PCC_MASK; - - if (PP_CAP(PHM_PlatformCaps_SQRamping)) { - CGS_WREG32_FIELD_IND(hwmgr->device, CGS_IND_REG__DIDT, - DIDT_SQ_CTRL0, DIDT_CTRL_EN, en); - didt_block_info &= ~SQ_Enable_MASK; - didt_block_info |= en << SQ_Enable_SHIFT; - } - - if (PP_CAP(PHM_PlatformCaps_DBRamping)) { - CGS_WREG32_FIELD_IND(hwmgr->device, CGS_IND_REG__DIDT, - DIDT_DB_CTRL0, DIDT_CTRL_EN, en); - didt_block_info &= ~DB_Enable_MASK; - didt_block_info |= en << DB_Enable_SHIFT; - } - - if (PP_CAP(PHM_PlatformCaps_TDRamping)) { - CGS_WREG32_FIELD_IND(hwmgr->device, CGS_IND_REG__DIDT, - DIDT_TD_CTRL0, DIDT_CTRL_EN, en); - didt_block_info &= ~TD_Enable_MASK; - didt_block_info |= en << TD_Enable_SHIFT; - } - - if (PP_CAP(PHM_PlatformCaps_TCPRamping)) { - CGS_WREG32_FIELD_IND(hwmgr->device, CGS_IND_REG__DIDT, - DIDT_TCP_CTRL0, DIDT_CTRL_EN, en); - didt_block_info &= ~TCP_Enable_MASK; - didt_block_info |= en << TCP_Enable_SHIFT; - } - -#if 0 - if (PP_CAP(PHM_PlatformCaps_DBRRamping)) { - CGS_WREG32_FIELD_IND(hwmgr->device, CGS_IND_REG__DIDT, - DIDT_DBR_CTRL0, DIDT_CTRL_EN, en); - } -#endif - - if (PP_CAP(PHM_PlatformCaps_DiDtEDCEnable)) { - if (PP_CAP(PHM_PlatformCaps_SQRamping)) { - data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_SQ_EDC_CTRL); - data = CGS_REG_SET_FIELD(data, DIDT_SQ_EDC_CTRL, EDC_EN, en); - data = CGS_REG_SET_FIELD(data, DIDT_SQ_EDC_CTRL, EDC_SW_RST, ~en); - cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_SQ_EDC_CTRL, data); - } - - if (PP_CAP(PHM_PlatformCaps_DBRamping)) { - data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DB_EDC_CTRL); - data = CGS_REG_SET_FIELD(data, DIDT_DB_EDC_CTRL, EDC_EN, en); - data = CGS_REG_SET_FIELD(data, DIDT_DB_EDC_CTRL, EDC_SW_RST, ~en); - cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DB_EDC_CTRL, data); - } - - if (PP_CAP(PHM_PlatformCaps_TDRamping)) { - data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TD_EDC_CTRL); - data = CGS_REG_SET_FIELD(data, DIDT_TD_EDC_CTRL, EDC_EN, en); - data = CGS_REG_SET_FIELD(data, DIDT_TD_EDC_CTRL, EDC_SW_RST, ~en); - cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TD_EDC_CTRL, data); - } - - if (PP_CAP(PHM_PlatformCaps_TCPRamping)) { - data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TCP_EDC_CTRL); - data = CGS_REG_SET_FIELD(data, DIDT_TCP_EDC_CTRL, EDC_EN, en); - data = CGS_REG_SET_FIELD(data, DIDT_TCP_EDC_CTRL, EDC_SW_RST, ~en); - cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TCP_EDC_CTRL, data); - } - -#if 0 - if (PP_CAP(PHM_PlatformCaps_DBRRamping)) { - data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DBR_EDC_CTRL); - data = CGS_REG_SET_FIELD(data, DIDT_DBR_EDC_CTRL, EDC_EN, en); - data = CGS_REG_SET_FIELD(data, DIDT_DBR_EDC_CTRL, EDC_SW_RST, ~en); - cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DBR_EDC_CTRL, data); - } -#endif - } - - if (enable) { - /* For Vega12, SMC does not support any mask yet. */ - result = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_ConfigureGfxDidt, didt_block_info); - PP_ASSERT((0 == result), "[EnableDiDtConfig] SMC Configure Gfx Didt Failed!"); - } -} - -static int vega12_enable_cac_driving_se_didt_config(struct pp_hwmgr *hwmgr) -{ - int result; - uint32_t num_se = 0, count, data; - struct amdgpu_device *adev = hwmgr->adev; - uint32_t reg; - - num_se = adev->gfx.config.max_shader_engines; - - cgs_enter_safe_mode(hwmgr->device, true); - - cgs_lock_grbm_idx(hwmgr->device, true); - reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX); - for (count = 0; count < num_se; count++) { - data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK | GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | ( count << GRBM_GFX_INDEX__SE_INDEX__SHIFT); - cgs_write_register(hwmgr->device, reg, data); - - result = vega12_program_didt_config_registers(hwmgr, SEDiDtStallCtrlConfig_vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtStallPatternConfig_vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtWeightConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtCtrl1Config_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtCtrl2Config_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtCtrl3Config_vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtTuningCtrlConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SELCacConfig_Vega12, VEGA12_CONFIGREG_SECAC); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtCtrl0Config_Vega12, VEGA12_CONFIGREG_DIDT); - - if (0 != result) - break; - } - cgs_write_register(hwmgr->device, reg, 0xE0000000); - cgs_lock_grbm_idx(hwmgr->device, false); - - vega12_didt_set_mask(hwmgr, true); - - cgs_enter_safe_mode(hwmgr->device, false); - - return 0; -} - -static int vega12_disable_cac_driving_se_didt_config(struct pp_hwmgr *hwmgr) -{ - cgs_enter_safe_mode(hwmgr->device, true); - - vega12_didt_set_mask(hwmgr, false); - - cgs_enter_safe_mode(hwmgr->device, false); - - return 0; -} - -static int vega12_enable_psm_gc_didt_config(struct pp_hwmgr *hwmgr) -{ - int result; - uint32_t num_se = 0, count, data; - struct amdgpu_device *adev = hwmgr->adev; - uint32_t reg; - - num_se = adev->gfx.config.max_shader_engines; - - cgs_enter_safe_mode(hwmgr->device, true); - - cgs_lock_grbm_idx(hwmgr->device, true); - reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX); - for (count = 0; count < num_se; count++) { - data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK | GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | ( count << GRBM_GFX_INDEX__SE_INDEX__SHIFT); - cgs_write_register(hwmgr->device, reg, data); - - result = vega12_program_didt_config_registers(hwmgr, SEDiDtStallCtrlConfig_vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtStallPatternConfig_vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtCtrl3Config_vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEDiDtCtrl0Config_Vega12, VEGA12_CONFIGREG_DIDT); - if (0 != result) - break; - } - cgs_write_register(hwmgr->device, reg, 0xE0000000); - cgs_lock_grbm_idx(hwmgr->device, false); - - vega12_didt_set_mask(hwmgr, true); - - cgs_enter_safe_mode(hwmgr->device, false); - - vega12_program_gc_didt_config_registers(hwmgr, GCDiDtDroopCtrlConfig_vega12); - if (PP_CAP(PHM_PlatformCaps_GCEDC)) - vega12_program_gc_didt_config_registers(hwmgr, GCDiDtCtrl0Config_vega12); - - if (PP_CAP(PHM_PlatformCaps_PSM)) - vega12_program_gc_didt_config_registers(hwmgr, AvfsPSMInitConfig_vega12); - - return 0; -} - -static int vega12_disable_psm_gc_didt_config(struct pp_hwmgr *hwmgr) -{ - uint32_t data; - - cgs_enter_safe_mode(hwmgr->device, true); - - vega12_didt_set_mask(hwmgr, false); - - cgs_enter_safe_mode(hwmgr->device, false); - - if (PP_CAP(PHM_PlatformCaps_GCEDC)) { - data = 0x00000000; - cgs_write_register(hwmgr->device, mmGC_DIDT_CTRL0, data); - } - - if (PP_CAP(PHM_PlatformCaps_PSM)) - vega12_program_gc_didt_config_registers(hwmgr, AvfsPSMResetConfig_vega12); - - return 0; -} - -static int vega12_enable_se_edc_config(struct pp_hwmgr *hwmgr) -{ - int result; - uint32_t num_se = 0, count, data; - struct amdgpu_device *adev = hwmgr->adev; - uint32_t reg; - - num_se = adev->gfx.config.max_shader_engines; - - cgs_enter_safe_mode(hwmgr->device, true); - - cgs_lock_grbm_idx(hwmgr->device, true); - reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX); - for (count = 0; count < num_se; count++) { - data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK | GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | ( count << GRBM_GFX_INDEX__SE_INDEX__SHIFT); - cgs_write_register(hwmgr->device, reg, data); - result = vega12_program_didt_config_registers(hwmgr, SEDiDtWeightConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEEDCStallPatternConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEEDCStallDelayConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEEDCThresholdConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEEDCCtrlResetConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEEDCCtrlConfig_Vega12, VEGA12_CONFIGREG_DIDT); - - if (0 != result) - break; - } - cgs_write_register(hwmgr->device, reg, 0xE0000000); - cgs_lock_grbm_idx(hwmgr->device, false); - - vega12_didt_set_mask(hwmgr, true); - - cgs_enter_safe_mode(hwmgr->device, false); - - return 0; -} - -static int vega12_disable_se_edc_config(struct pp_hwmgr *hwmgr) -{ - cgs_enter_safe_mode(hwmgr->device, true); - - vega12_didt_set_mask(hwmgr, false); - - cgs_enter_safe_mode(hwmgr->device, false); - - return 0; -} - -static int vega12_enable_psm_gc_edc_config(struct pp_hwmgr *hwmgr) -{ - int result; - uint32_t num_se = 0; - uint32_t count, data; - struct amdgpu_device *adev = hwmgr->adev; - uint32_t reg; - - num_se = adev->gfx.config.max_shader_engines; - - cgs_enter_safe_mode(hwmgr->device, true); - - vega12_program_gc_didt_config_registers(hwmgr, AvfsPSMResetConfig_vega12); - - cgs_lock_grbm_idx(hwmgr->device, true); - reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX); - for (count = 0; count < num_se; count++) { - data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK | GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | ( count << GRBM_GFX_INDEX__SE_INDEX__SHIFT); - cgs_write_register(hwmgr->device, reg, data); - result |= vega12_program_didt_config_registers(hwmgr, PSMSEEDCStallPatternConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, PSMSEEDCStallDelayConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, PSMSEEDCCtrlResetConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, PSMSEEDCCtrlConfig_Vega12, VEGA12_CONFIGREG_DIDT); - - if (0 != result) - break; - } - cgs_write_register(hwmgr->device, reg, 0xE0000000); - cgs_lock_grbm_idx(hwmgr->device, false); - - vega12_didt_set_mask(hwmgr, true); - - cgs_enter_safe_mode(hwmgr->device, false); - - vega12_program_gc_didt_config_registers(hwmgr, PSMGCEDCDroopCtrlConfig_vega12); - - if (PP_CAP(PHM_PlatformCaps_GCEDC)) { - vega12_program_gc_didt_config_registers(hwmgr, PSMGCEDCCtrlResetConfig_vega12); - vega12_program_gc_didt_config_registers(hwmgr, PSMGCEDCCtrlConfig_vega12); - } - - if (PP_CAP(PHM_PlatformCaps_PSM)) - vega12_program_gc_didt_config_registers(hwmgr, AvfsPSMInitConfig_vega12); - - return 0; -} - -static int vega12_disable_psm_gc_edc_config(struct pp_hwmgr *hwmgr) -{ - uint32_t data; - - cgs_enter_safe_mode(hwmgr->device, true); - - vega12_didt_set_mask(hwmgr, false); - - cgs_enter_safe_mode(hwmgr->device, false); - - if (PP_CAP(PHM_PlatformCaps_GCEDC)) { - data = 0x00000000; - cgs_write_register(hwmgr->device, mmGC_EDC_CTRL, data); - } - - if (PP_CAP(PHM_PlatformCaps_PSM)) - vega12_program_gc_didt_config_registers(hwmgr, AvfsPSMResetConfig_vega12); - - return 0; -} - -static int vega12_enable_se_edc_force_stall_config(struct pp_hwmgr *hwmgr) -{ - uint32_t reg; - int result; - - cgs_enter_safe_mode(hwmgr->device, true); - - cgs_lock_grbm_idx(hwmgr->device, true); - reg = soc15_get_register_offset(GC_HWID, 0, mmGRBM_GFX_INDEX_BASE_IDX, mmGRBM_GFX_INDEX); - cgs_write_register(hwmgr->device, reg, 0xE0000000); - cgs_lock_grbm_idx(hwmgr->device, false); - - result = vega12_program_didt_config_registers(hwmgr, SEEDCForceStallPatternConfig_Vega12, VEGA12_CONFIGREG_DIDT); - result |= vega12_program_didt_config_registers(hwmgr, SEEDCCtrlForceStallConfig_Vega12, VEGA12_CONFIGREG_DIDT); - if (0 != result) - return result; - - vega12_didt_set_mask(hwmgr, false); - - cgs_enter_safe_mode(hwmgr->device, false); - - return 0; -} - -static int vega12_disable_se_edc_force_stall_config(struct pp_hwmgr *hwmgr) -{ - int result; - - result = vega12_disable_se_edc_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[DisableDiDtConfig] Pre DIDT disable clock gating failed!", return result); - - return 0; -} - -int vega12_enable_didt_config(struct pp_hwmgr *hwmgr) -{ - int result = 0; - struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend); - - if (data->smu_features[GNLD_DIDT].supported) { - if (data->smu_features[GNLD_DIDT].enabled) - PP_DBG_LOG("[EnableDiDtConfig] Feature DiDt Already enabled!\n"); - - switch (data->registry_data.didt_mode) { - case 0: - result = vega12_enable_cac_driving_se_didt_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[EnableDiDt] Attempt to enable DiDt Mode 0 Failed!", return result); - break; - case 2: - result = vega12_enable_psm_gc_didt_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[EnableDiDt] Attempt to enable DiDt Mode 2 Failed!", return result); - break; - case 3: - result = vega12_enable_se_edc_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[EnableDiDt] Attempt to enable DiDt Mode 3 Failed!", return result); - break; - case 1: - case 4: - case 5: - result = vega12_enable_psm_gc_edc_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[EnableDiDt] Attempt to enable DiDt Mode 5 Failed!", return result); - break; - case 6: - result = vega12_enable_se_edc_force_stall_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[EnableDiDt] Attempt to enable DiDt Mode 6 Failed!", return result); - break; - default: - result = -EINVAL; - break; - } - -#if 0 - if (0 == result) { - result = vega12_enable_smc_features(hwmgr, true, data->smu_features[GNLD_DIDT].smu_feature_bitmap); - PP_ASSERT_WITH_CODE((0 == result), "[EnableDiDtConfig] Attempt to Enable DiDt feature Failed!", return result); - data->smu_features[GNLD_DIDT].enabled = true; - } -#endif - } - - return result; -} - -int vega12_disable_didt_config(struct pp_hwmgr *hwmgr) -{ - int result = 0; - struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend); - - if (data->smu_features[GNLD_DIDT].supported) { - if (!data->smu_features[GNLD_DIDT].enabled) - PP_DBG_LOG("[DisableDiDtConfig] Feature DiDt Already Disabled!\n"); - - switch (data->registry_data.didt_mode) { - case 0: - result = vega12_disable_cac_driving_se_didt_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[DisableDiDt] Attempt to disable DiDt Mode 0 Failed!", return result); - break; - case 2: - result = vega12_disable_psm_gc_didt_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[DisableDiDt] Attempt to disable DiDt Mode 2 Failed!", return result); - break; - case 3: - result = vega12_disable_se_edc_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[DisableDiDt] Attempt to disable DiDt Mode 3 Failed!", return result); - break; - case 1: - case 4: - case 5: - result = vega12_disable_psm_gc_edc_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[DisableDiDt] Attempt to disable DiDt Mode 5 Failed!", return result); - break; - case 6: - result = vega12_disable_se_edc_force_stall_config(hwmgr); - PP_ASSERT_WITH_CODE((0 == result), "[DisableDiDt] Attempt to disable DiDt Mode 6 Failed!", return result); - break; - default: - result = -EINVAL; - break; - } - - if (0 == result) { - result = vega12_enable_smc_features(hwmgr, false, data->smu_features[GNLD_DIDT].smu_feature_bitmap); - PP_ASSERT_WITH_CODE((0 == result), "[DisableDiDtConfig] Attempt to Disable DiDt feature Failed!", return result); - data->smu_features[GNLD_DIDT].enabled = false; - } - } - - return result; -} - -int vega12_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n) -{ - struct vega12_hwmgr *data = - (struct vega12_hwmgr *)(hwmgr->backend); - - if (data->smu_features[GNLD_PPT].enabled) - return smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_SetPptLimit, n); - - return 0; -} - -int vega12_enable_power_containment(struct pp_hwmgr *hwmgr) -{ - struct vega12_hwmgr *data = - (struct vega12_hwmgr *)(hwmgr->backend); - struct phm_ppt_v2_information *table_info = - (struct phm_ppt_v2_information *)(hwmgr->pptable); - struct phm_tdp_table *tdp_table = table_info->tdp_table; - uint32_t default_pwr_limit = - (uint32_t)(tdp_table->usMaximumPowerDeliveryLimit); - int result = 0; - - if (PP_CAP(PHM_PlatformCaps_PowerContainment)) { - if (data->smu_features[GNLD_PPT].supported) - PP_ASSERT_WITH_CODE(!vega12_enable_smc_features(hwmgr, - true, data->smu_features[GNLD_PPT].smu_feature_bitmap), - "Attempt to enable PPT feature Failed!", - data->smu_features[GNLD_PPT].supported = false); - - if (data->smu_features[GNLD_TDC].supported) - PP_ASSERT_WITH_CODE(!vega12_enable_smc_features(hwmgr, - true, data->smu_features[GNLD_TDC].smu_feature_bitmap), - "Attempt to enable PPT feature Failed!", - data->smu_features[GNLD_TDC].supported = false); - - result = vega12_set_power_limit(hwmgr, default_pwr_limit); - PP_ASSERT_WITH_CODE(!result, - "Failed to set Default Power Limit in SMC!", - return result); - } - - return result; -} - -int vega12_disable_power_containment(struct pp_hwmgr *hwmgr) -{ - struct vega12_hwmgr *data = - (struct vega12_hwmgr *)(hwmgr->backend); - - if (PP_CAP(PHM_PlatformCaps_PowerContainment)) { - if (data->smu_features[GNLD_PPT].supported) - PP_ASSERT_WITH_CODE(!vega12_enable_smc_features(hwmgr, - false, data->smu_features[GNLD_PPT].smu_feature_bitmap), - "Attempt to disable PPT feature Failed!", - data->smu_features[GNLD_PPT].supported = false); - - if (data->smu_features[GNLD_TDC].supported) - PP_ASSERT_WITH_CODE(!vega12_enable_smc_features(hwmgr, - false, data->smu_features[GNLD_TDC].smu_feature_bitmap), - "Attempt to disable PPT feature Failed!", - data->smu_features[GNLD_TDC].supported = false); - } - - return 0; -} - -static int vega12_set_overdrive_target_percentage(struct pp_hwmgr *hwmgr, - uint32_t adjust_percent) -{ - return smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_OverDriveSetPercentage, adjust_percent); -} - -int vega12_power_control_set_level(struct pp_hwmgr *hwmgr) -{ - int adjust_percent, result = 0; - - if (PP_CAP(PHM_PlatformCaps_PowerContainment)) { - adjust_percent = - hwmgr->platform_descriptor.TDPAdjustmentPolarity ? - hwmgr->platform_descriptor.TDPAdjustment : - (-1 * hwmgr->platform_descriptor.TDPAdjustment); - result = vega12_set_overdrive_target_percentage(hwmgr, - (uint32_t)adjust_percent); - } - return result; -} diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_powertune.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_powertune.h deleted file mode 100644 index 78d31a6..0000000 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_powertune.h +++ /dev/null @@ -1,53 +0,0 @@ -/* - * Copyright 2017 Advanced Micro Devices, Inc. - * - * 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 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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 _VEGA12_POWERTUNE_H_ -#define _VEGA12_POWERTUNE_H_ - -enum vega12_didt_config_reg_type { - VEGA12_CONFIGREG_DIDT = 0, - VEGA12_CONFIGREG_GCCAC, - VEGA12_CONFIGREG_SECAC -}; - -/* PowerContainment Features */ -#define POWERCONTAINMENT_FEATURE_DTE 0x00000001 -#define POWERCONTAINMENT_FEATURE_TDCLimit 0x00000002 -#define POWERCONTAINMENT_FEATURE_PkgPwrLimit 0x00000004 - -struct vega12_didt_config_reg { - uint32_t offset; - uint32_t mask; - uint32_t shift; - uint32_t value; -}; - -int vega12_enable_power_containment(struct pp_hwmgr *hwmgr); -int vega12_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n); -int vega12_power_control_set_level(struct pp_hwmgr *hwmgr); -int vega12_disable_power_containment(struct pp_hwmgr *hwmgr); - -int vega12_enable_didt_config(struct pp_hwmgr *hwmgr); -int vega12_disable_didt_config(struct pp_hwmgr *hwmgr); - -#endif /* _VEGA12_POWERTUNE_H_ */ - diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c index e7d7949..b34113f 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c @@ -208,9 +208,9 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable ppsmc_pptable->LedPin1 = smc_dpm_table.ledpin1; ppsmc_pptable->LedPin2 = smc_dpm_table.ledpin2; - ppsmc_pptable->GfxclkSpreadEnabled = smc_dpm_table.gfxclkspreadenabled; - ppsmc_pptable->GfxclkSpreadPercent = smc_dpm_table.gfxclkspreadpercent; - ppsmc_pptable->GfxclkSpreadFreq = smc_dpm_table.gfxclkspreadfreq; + ppsmc_pptable->PllGfxclkSpreadEnabled = smc_dpm_table.pllgfxclkspreadenabled; + ppsmc_pptable->PllGfxclkSpreadPercent = smc_dpm_table.pllgfxclkspreadpercent; + ppsmc_pptable->PllGfxclkSpreadFreq = smc_dpm_table.pllgfxclkspreadfreq; ppsmc_pptable->UclkSpreadEnabled = 0; ppsmc_pptable->UclkSpreadPercent = smc_dpm_table.uclkspreadpercent; @@ -220,6 +220,11 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable ppsmc_pptable->SocclkSpreadPercent = smc_dpm_table.socclkspreadpercent; ppsmc_pptable->SocclkSpreadFreq = smc_dpm_table.socclkspreadfreq; + ppsmc_pptable->AcgGfxclkSpreadEnabled = smc_dpm_table.acggfxclkspreadenabled; + ppsmc_pptable->AcgGfxclkSpreadPercent = smc_dpm_table.acggfxclkspreadpercent; + ppsmc_pptable->AcgGfxclkSpreadFreq = smc_dpm_table.acggfxclkspreadfreq; + + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h index cd2e503..2f8a3b9 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h +++ b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h @@ -127,7 +127,7 @@ #define FEATURE_GFX_EDC_MASK (1 << FEATURE_GFX_EDC_BIT ) #define FEATURE_GFXOFF_MASK (1 << FEATURE_GFXOFF_BIT ) #define FEATURE_CG_MASK (1 << FEATURE_CG_BIT ) -#define FEATURE_ACG_MASK (1 << FEATURE_ACG_BIT ) +#define FEATURE_ACG_MASK (1 << FEATURE_ACG_BIT) #define FEATURE_SPARE_29_MASK (1 << FEATURE_SPARE_29_BIT ) #define FEATURE_SPARE_30_MASK (1 << FEATURE_SPARE_30_BIT ) #define FEATURE_SPARE_31_MASK (1 << FEATURE_SPARE_31_BIT ) @@ -412,8 +412,10 @@ typedef struct { QuadraticInt_t ReservedEquation2; QuadraticInt_t ReservedEquation3; + uint16_t MinVoltageUlvGfx; + uint16_t MinVoltageUlvSoc; - uint32_t Reserved[15]; + uint32_t Reserved[14]; @@ -481,9 +483,9 @@ typedef struct { uint8_t padding8_4; - uint8_t GfxclkSpreadEnabled; - uint8_t GfxclkSpreadPercent; - uint16_t GfxclkSpreadFreq; + uint8_t PllGfxclkSpreadEnabled; + uint8_t PllGfxclkSpreadPercent; + uint16_t PllGfxclkSpreadFreq; uint8_t UclkSpreadEnabled; uint8_t UclkSpreadPercent; @@ -493,7 +495,11 @@ typedef struct { uint8_t SocclkSpreadPercent; uint16_t SocclkSpreadFreq; - uint32_t BoardReserved[3]; + uint8_t AcgGfxclkSpreadEnabled; + uint8_t AcgGfxclkSpreadPercent; + uint16_t AcgGfxclkSpreadFreq; + + uint32_t BoardReserved[10]; uint32_t MmHubPadding[7]; diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c index 55cd204..651a3f2 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c @@ -30,8 +30,7 @@ #include "ppatomctrl.h" #include "pp_debug.h" -#include "smu_ucode_xfer_vi.h" -#include "smu7_smumgr.h" + /* MP Apertures */ #define MP0_Public 0x03800000 @@ -392,8 +391,7 @@ static int vega12_smu_init(struct pp_hwmgr *hwmgr) struct cgs_firmware_info info = {0}; int ret; - ret = cgs_get_firmware_info(hwmgr->device, - smu7_convert_fw_type_to_cgs(UCODE_ID_SMU), + ret = cgs_get_firmware_info(hwmgr->device, CGS_UCODE_ID_SMU, &info); if (ret || !info.kptr) return -EINVAL; diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 831b733..036dff8 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -799,7 +799,7 @@ static int ast_get_modes(struct drm_connector *connector) return 0; } -static int ast_mode_valid(struct drm_connector *connector, +static enum drm_mode_status ast_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct ast_private *ast = connector->dev->dev_private; diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.h b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.h index ab32d5b..60c937f 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.h +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.h @@ -299,7 +299,6 @@ struct atmel_hlcdc_layer { struct atmel_hlcdc_plane { struct drm_plane base; struct atmel_hlcdc_layer layer; - struct atmel_hlcdc_plane_properties *properties; }; static inline struct atmel_hlcdc_plane * @@ -346,18 +345,6 @@ struct atmel_hlcdc_dc_desc { }; /** - * Atmel HLCDC Plane properties. - * - * This structure stores plane property definitions. - * - * @alpha: alpha blending (or transparency) property - * @rotation: rotation property - */ -struct atmel_hlcdc_plane_properties { - struct drm_property *alpha; -}; - -/** * Atmel HLCDC Display Controller. * * @desc: HLCDC Display Controller description diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c index e18800e..73c875d 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c @@ -31,7 +31,6 @@ * @src_y: y buffer position * @src_w: buffer width * @src_h: buffer height - * @alpha: alpha blending of the plane * @disc_x: x discard position * @disc_y: y discard position * @disc_w: discard width @@ -54,8 +53,6 @@ struct atmel_hlcdc_plane_state { uint32_t src_w; uint32_t src_h; - u8 alpha; - int disc_x; int disc_y; int disc_w; @@ -385,7 +382,7 @@ atmel_hlcdc_plane_update_general_settings(struct atmel_hlcdc_plane *plane, cfg |= ATMEL_HLCDC_LAYER_LAEN; else cfg |= ATMEL_HLCDC_LAYER_GAEN | - ATMEL_HLCDC_LAYER_GA(state->alpha); + ATMEL_HLCDC_LAYER_GA(state->base.alpha >> 8); } if (state->disc_h && state->disc_w) @@ -553,7 +550,7 @@ atmel_hlcdc_plane_prepare_disc_area(struct drm_crtc_state *c_state) if (!ovl_s->fb || ovl_s->fb->format->has_alpha || - ovl_state->alpha != 255) + ovl_s->alpha != DRM_BLEND_ALPHA_OPAQUE) continue; /* TODO: implement a smarter hidden area detection */ @@ -829,51 +826,18 @@ static void atmel_hlcdc_plane_destroy(struct drm_plane *p) drm_plane_cleanup(p); } -static int atmel_hlcdc_plane_atomic_set_property(struct drm_plane *p, - struct drm_plane_state *s, - struct drm_property *property, - uint64_t val) -{ - struct atmel_hlcdc_plane *plane = drm_plane_to_atmel_hlcdc_plane(p); - struct atmel_hlcdc_plane_properties *props = plane->properties; - struct atmel_hlcdc_plane_state *state = - drm_plane_state_to_atmel_hlcdc_plane_state(s); - - if (property == props->alpha) - state->alpha = val; - else - return -EINVAL; - - return 0; -} - -static int atmel_hlcdc_plane_atomic_get_property(struct drm_plane *p, - const struct drm_plane_state *s, - struct drm_property *property, - uint64_t *val) -{ - struct atmel_hlcdc_plane *plane = drm_plane_to_atmel_hlcdc_plane(p); - struct atmel_hlcdc_plane_properties *props = plane->properties; - const struct atmel_hlcdc_plane_state *state = - container_of(s, const struct atmel_hlcdc_plane_state, base); - - if (property == props->alpha) - *val = state->alpha; - else - return -EINVAL; - - return 0; -} - -static int atmel_hlcdc_plane_init_properties(struct atmel_hlcdc_plane *plane, - struct atmel_hlcdc_plane_properties *props) +static int atmel_hlcdc_plane_init_properties(struct atmel_hlcdc_plane *plane) { const struct atmel_hlcdc_layer_desc *desc = plane->layer.desc; if (desc->type == ATMEL_HLCDC_OVERLAY_LAYER || - desc->type == ATMEL_HLCDC_CURSOR_LAYER) - drm_object_attach_property(&plane->base.base, - props->alpha, 255); + desc->type == ATMEL_HLCDC_CURSOR_LAYER) { + int ret; + + ret = drm_plane_create_alpha_property(&plane->base); + if (ret) + return ret; + } if (desc->layout.xstride && desc->layout.pstride) { int ret; @@ -988,8 +952,8 @@ static void atmel_hlcdc_plane_reset(struct drm_plane *p) return; } - state->alpha = 255; p->state = &state->base; + p->state->alpha = DRM_BLEND_ALPHA_OPAQUE; p->state->plane = p; } } @@ -1042,13 +1006,10 @@ static const struct drm_plane_funcs layer_plane_funcs = { .reset = atmel_hlcdc_plane_reset, .atomic_duplicate_state = atmel_hlcdc_plane_atomic_duplicate_state, .atomic_destroy_state = atmel_hlcdc_plane_atomic_destroy_state, - .atomic_set_property = atmel_hlcdc_plane_atomic_set_property, - .atomic_get_property = atmel_hlcdc_plane_atomic_get_property, }; static int atmel_hlcdc_plane_create(struct drm_device *dev, - const struct atmel_hlcdc_layer_desc *desc, - struct atmel_hlcdc_plane_properties *props) + const struct atmel_hlcdc_layer_desc *desc) { struct atmel_hlcdc_dc *dc = dev->dev_private; struct atmel_hlcdc_plane *plane; @@ -1060,7 +1021,6 @@ static int atmel_hlcdc_plane_create(struct drm_device *dev, return -ENOMEM; atmel_hlcdc_layer_init(&plane->layer, desc, dc->hlcdc->regmap); - plane->properties = props; if (desc->type == ATMEL_HLCDC_BASE_LAYER) type = DRM_PLANE_TYPE_PRIMARY; @@ -1081,7 +1041,7 @@ static int atmel_hlcdc_plane_create(struct drm_device *dev, &atmel_hlcdc_layer_plane_helper_funcs); /* Set default property values*/ - ret = atmel_hlcdc_plane_init_properties(plane, props); + ret = atmel_hlcdc_plane_init_properties(plane); if (ret) return ret; @@ -1090,34 +1050,13 @@ static int atmel_hlcdc_plane_create(struct drm_device *dev, return 0; } -static struct atmel_hlcdc_plane_properties * -atmel_hlcdc_plane_create_properties(struct drm_device *dev) -{ - struct atmel_hlcdc_plane_properties *props; - - props = devm_kzalloc(dev->dev, sizeof(*props), GFP_KERNEL); - if (!props) - return ERR_PTR(-ENOMEM); - - props->alpha = drm_property_create_range(dev, 0, "alpha", 0, 255); - if (!props->alpha) - return ERR_PTR(-ENOMEM); - - return props; -} - int atmel_hlcdc_create_planes(struct drm_device *dev) { struct atmel_hlcdc_dc *dc = dev->dev_private; - struct atmel_hlcdc_plane_properties *props; const struct atmel_hlcdc_layer_desc *descs = dc->desc->layers; int nlayers = dc->desc->nlayers; int i, ret; - props = atmel_hlcdc_plane_create_properties(dev); - if (IS_ERR(props)) - return PTR_ERR(props); - dc->dscrpool = dmam_pool_create("atmel-hlcdc-dscr", dev->dev, sizeof(struct atmel_hlcdc_dma_channel_dscr), sizeof(u64), 0); @@ -1130,7 +1069,7 @@ int atmel_hlcdc_create_planes(struct drm_device *dev) descs[i].type != ATMEL_HLCDC_CURSOR_LAYER) continue; - ret = atmel_hlcdc_plane_create(dev, &descs[i], props); + ret = atmel_hlcdc_plane_create(dev, &descs[i]); if (ret) return ret; } diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index a24a18f..233980a 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -188,7 +188,7 @@ static int bochs_connector_get_modes(struct drm_connector *connector) return count; } -static int bochs_connector_mode_valid(struct drm_connector *connector, +static enum drm_mode_status bochs_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct bochs_device *bochs = diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 3aa65bd..1d75d3a 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -25,6 +25,16 @@ config DRM_ANALOGIX_ANX78XX the HDMI output of an application processor to MyDP or DisplayPort. +config DRM_CDNS_DSI + tristate "Cadence DPI/DSI bridge" + select DRM_KMS_HELPER + select DRM_MIPI_DSI + select DRM_PANEL_BRIDGE + depends on OF + help + Support Cadence DPI to DSI bridge. This is an internal + bridge and is meant to be directly embedded in a SoC. + config DRM_DUMB_VGA_DAC tristate "Dumb VGA DAC Bridge support" depends on OF @@ -93,6 +103,12 @@ config DRM_SII9234 It is an I2C driver, that detects connection of MHL bridge and starts encapsulation of HDMI signal. +config DRM_THINE_THC63LVD1024 + tristate "Thine THC63LVD1024 LVDS decoder bridge" + depends on OF + ---help--- + Thine THC63LVD1024 LVDS/parallel converter driver. + config DRM_TOSHIBA_TC358767 tristate "Toshiba TC358767 eDP bridge" depends on OF diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile index 373eb28..35f88d4 100644 --- a/drivers/gpu/drm/bridge/Makefile +++ b/drivers/gpu/drm/bridge/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DRM_ANALOGIX_ANX78XX) += analogix-anx78xx.o +obj-$(CONFIG_DRM_CDNS_DSI) += cdns-dsi.o obj-$(CONFIG_DRM_DUMB_VGA_DAC) += dumb-vga-dac.o obj-$(CONFIG_DRM_LVDS_ENCODER) += lvds-encoder.o obj-$(CONFIG_DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW) += megachips-stdpxxxx-ge-b850v3-fw.o @@ -8,6 +9,7 @@ obj-$(CONFIG_DRM_PARADE_PS8622) += parade-ps8622.o obj-$(CONFIG_DRM_SIL_SII8620) += sil-sii8620.o obj-$(CONFIG_DRM_SII902X) += sii902x.o obj-$(CONFIG_DRM_SII9234) += sii9234.o +obj-$(CONFIG_DRM_THINE_THC63LVD1024) += thc63lvd1024.o obj-$(CONFIG_DRM_TOSHIBA_TC358767) += tc358767.o obj-$(CONFIG_DRM_ANALOGIX_DP) += analogix/ obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511/ diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511.h b/drivers/gpu/drm/bridge/adv7511/adv7511.h index d034b2c..73d8ccb 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511.h +++ b/drivers/gpu/drm/bridge/adv7511/adv7511.h @@ -93,6 +93,11 @@ #define ADV7511_REG_CHIP_ID_HIGH 0xf5 #define ADV7511_REG_CHIP_ID_LOW 0xf6 +/* Hardware defined default addresses for I2C register maps */ +#define ADV7511_CEC_I2C_ADDR_DEFAULT 0x3c +#define ADV7511_EDID_I2C_ADDR_DEFAULT 0x3f +#define ADV7511_PACKET_I2C_ADDR_DEFAULT 0x38 + #define ADV7511_CSC_ENABLE BIT(7) #define ADV7511_CSC_UPDATE_MODE BIT(5) @@ -321,6 +326,7 @@ enum adv7511_type { struct adv7511 { struct i2c_client *i2c_main; struct i2c_client *i2c_edid; + struct i2c_client *i2c_packet; struct i2c_client *i2c_cec; struct regmap *regmap; diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index efa29db..2614cea 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -586,7 +586,7 @@ static int adv7511_get_modes(struct adv7511 *adv7511, /* Reading the EDID only works if the device is powered */ if (!adv7511->powered) { unsigned int edid_i2c_addr = - (adv7511->i2c_main->addr << 1) + 4; + (adv7511->i2c_edid->addr << 1); __adv7511_power_on(adv7511); @@ -654,7 +654,7 @@ adv7511_detect(struct adv7511 *adv7511, struct drm_connector *connector) return status; } -static int adv7511_mode_valid(struct adv7511 *adv7511, +static enum drm_mode_status adv7511_mode_valid(struct adv7511 *adv7511, struct drm_display_mode *mode) { if (mode->clock > 165000) @@ -969,10 +969,10 @@ static int adv7511_init_cec_regmap(struct adv7511 *adv) { int ret; - adv->i2c_cec = i2c_new_dummy(adv->i2c_main->adapter, - adv->i2c_main->addr - 1); + adv->i2c_cec = i2c_new_secondary_device(adv->i2c_main, "cec", + ADV7511_CEC_I2C_ADDR_DEFAULT); if (!adv->i2c_cec) - return -ENOMEM; + return -EINVAL; i2c_set_clientdata(adv->i2c_cec, adv); adv->regmap_cec = devm_regmap_init_i2c(adv->i2c_cec, @@ -1082,8 +1082,6 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) struct adv7511_link_config link_config; struct adv7511 *adv7511; struct device *dev = &i2c->dev; - unsigned int main_i2c_addr = i2c->addr << 1; - unsigned int edid_i2c_addr = main_i2c_addr + 4; unsigned int val; int ret; @@ -1153,23 +1151,34 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) if (ret) goto uninit_regulators; - regmap_write(adv7511->regmap, ADV7511_REG_EDID_I2C_ADDR, edid_i2c_addr); - regmap_write(adv7511->regmap, ADV7511_REG_PACKET_I2C_ADDR, - main_i2c_addr - 0xa); - regmap_write(adv7511->regmap, ADV7511_REG_CEC_I2C_ADDR, - main_i2c_addr - 2); - adv7511_packet_disable(adv7511, 0xffff); - adv7511->i2c_edid = i2c_new_dummy(i2c->adapter, edid_i2c_addr >> 1); + adv7511->i2c_edid = i2c_new_secondary_device(i2c, "edid", + ADV7511_EDID_I2C_ADDR_DEFAULT); if (!adv7511->i2c_edid) { - ret = -ENOMEM; + ret = -EINVAL; goto uninit_regulators; } + regmap_write(adv7511->regmap, ADV7511_REG_EDID_I2C_ADDR, + adv7511->i2c_edid->addr << 1); + + adv7511->i2c_packet = i2c_new_secondary_device(i2c, "packet", + ADV7511_PACKET_I2C_ADDR_DEFAULT); + if (!adv7511->i2c_packet) { + ret = -EINVAL; + goto err_i2c_unregister_edid; + } + + regmap_write(adv7511->regmap, ADV7511_REG_PACKET_I2C_ADDR, + adv7511->i2c_packet->addr << 1); + ret = adv7511_init_cec_regmap(adv7511); if (ret) - goto err_i2c_unregister_edid; + goto err_i2c_unregister_packet; + + regmap_write(adv7511->regmap, ADV7511_REG_CEC_I2C_ADDR, + adv7511->i2c_cec->addr << 1); INIT_WORK(&adv7511->hpd_work, adv7511_hpd_work); @@ -1207,6 +1216,8 @@ err_unregister_cec: i2c_unregister_device(adv7511->i2c_cec); if (adv7511->cec_clk) clk_disable_unprepare(adv7511->cec_clk); +err_i2c_unregister_packet: + i2c_unregister_device(adv7511->i2c_packet); err_i2c_unregister_edid: i2c_unregister_device(adv7511->i2c_edid); uninit_regulators: @@ -1233,6 +1244,7 @@ static int adv7511_remove(struct i2c_client *i2c) cec_unregister_adapter(adv7511->cec_adap); + i2c_unregister_device(adv7511->i2c_packet); i2c_unregister_device(adv7511->i2c_edid); return 0; diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index 5c52307..2bcbfad 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -43,8 +43,10 @@ struct bridge_init { struct device_node *node; }; -static void analogix_dp_init_dp(struct analogix_dp_device *dp) +static int analogix_dp_init_dp(struct analogix_dp_device *dp) { + int ret; + analogix_dp_reset(dp); analogix_dp_swreset(dp); @@ -56,10 +58,13 @@ static void analogix_dp_init_dp(struct analogix_dp_device *dp) analogix_dp_enable_sw_function(dp); analogix_dp_config_interrupt(dp); - analogix_dp_init_analog_func(dp); + ret = analogix_dp_init_analog_func(dp); + if (ret) + return ret; analogix_dp_init_hpd(dp); analogix_dp_init_aux(dp); + return 0; } static int analogix_dp_detect_hpd(struct analogix_dp_device *dp) @@ -71,7 +76,7 @@ static int analogix_dp_detect_hpd(struct analogix_dp_device *dp) return 0; timeout_loop++; - usleep_range(10, 11); + usleep_range(1000, 1100); } /* @@ -148,87 +153,146 @@ int analogix_dp_disable_psr(struct analogix_dp_device *dp) psr_vsc.DB1 = 0; ret = drm_dp_dpcd_writeb(&dp->aux, DP_SET_POWER, DP_SET_POWER_D0); - if (ret != 1) + if (ret != 1) { dev_err(dp->dev, "Failed to set DP Power0 %d\n", ret); + return ret; + } return analogix_dp_send_psr_spd(dp, &psr_vsc, false); } EXPORT_SYMBOL_GPL(analogix_dp_disable_psr); -static bool analogix_dp_detect_sink_psr(struct analogix_dp_device *dp) +static int analogix_dp_detect_sink_psr(struct analogix_dp_device *dp) { unsigned char psr_version; + int ret; + + ret = drm_dp_dpcd_readb(&dp->aux, DP_PSR_SUPPORT, &psr_version); + if (ret != 1) { + dev_err(dp->dev, "failed to get PSR version, disable it\n"); + return ret; + } - drm_dp_dpcd_readb(&dp->aux, DP_PSR_SUPPORT, &psr_version); dev_dbg(dp->dev, "Panel PSR version : %x\n", psr_version); - return (psr_version & DP_PSR_IS_SUPPORTED) ? true : false; + dp->psr_enable = (psr_version & DP_PSR_IS_SUPPORTED) ? true : false; + + return 0; } -static void analogix_dp_enable_sink_psr(struct analogix_dp_device *dp) +static int analogix_dp_enable_sink_psr(struct analogix_dp_device *dp) { unsigned char psr_en; + int ret; /* Disable psr function */ - drm_dp_dpcd_readb(&dp->aux, DP_PSR_EN_CFG, &psr_en); + ret = drm_dp_dpcd_readb(&dp->aux, DP_PSR_EN_CFG, &psr_en); + if (ret != 1) { + dev_err(dp->dev, "failed to get psr config\n"); + goto end; + } + psr_en &= ~DP_PSR_ENABLE; - drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en); + ret = drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en); + if (ret != 1) { + dev_err(dp->dev, "failed to disable panel psr\n"); + goto end; + } /* Main-Link transmitter remains active during PSR active states */ psr_en = DP_PSR_MAIN_LINK_ACTIVE | DP_PSR_CRC_VERIFICATION; - drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en); + ret = drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en); + if (ret != 1) { + dev_err(dp->dev, "failed to set panel psr\n"); + goto end; + } /* Enable psr function */ psr_en = DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE | DP_PSR_CRC_VERIFICATION; - drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en); + ret = drm_dp_dpcd_writeb(&dp->aux, DP_PSR_EN_CFG, psr_en); + if (ret != 1) { + dev_err(dp->dev, "failed to set panel psr\n"); + goto end; + } analogix_dp_enable_psr_crc(dp); + + return 0; +end: + dev_err(dp->dev, "enable psr fail, force to disable psr\n"); + dp->psr_enable = false; + + return ret; } -static void +static int analogix_dp_enable_rx_to_enhanced_mode(struct analogix_dp_device *dp, bool enable) { u8 data; + int ret; - drm_dp_dpcd_readb(&dp->aux, DP_LANE_COUNT_SET, &data); + ret = drm_dp_dpcd_readb(&dp->aux, DP_LANE_COUNT_SET, &data); + if (ret != 1) + return ret; if (enable) - drm_dp_dpcd_writeb(&dp->aux, DP_LANE_COUNT_SET, - DP_LANE_COUNT_ENHANCED_FRAME_EN | - DPCD_LANE_COUNT_SET(data)); + ret = drm_dp_dpcd_writeb(&dp->aux, DP_LANE_COUNT_SET, + DP_LANE_COUNT_ENHANCED_FRAME_EN | + DPCD_LANE_COUNT_SET(data)); else - drm_dp_dpcd_writeb(&dp->aux, DP_LANE_COUNT_SET, - DPCD_LANE_COUNT_SET(data)); + ret = drm_dp_dpcd_writeb(&dp->aux, DP_LANE_COUNT_SET, + DPCD_LANE_COUNT_SET(data)); + + return ret < 0 ? ret : 0; } -static int analogix_dp_is_enhanced_mode_available(struct analogix_dp_device *dp) +static int analogix_dp_is_enhanced_mode_available(struct analogix_dp_device *dp, + u8 *enhanced_mode_support) { u8 data; - int retval; + int ret; - drm_dp_dpcd_readb(&dp->aux, DP_MAX_LANE_COUNT, &data); - retval = DPCD_ENHANCED_FRAME_CAP(data); + ret = drm_dp_dpcd_readb(&dp->aux, DP_MAX_LANE_COUNT, &data); + if (ret != 1) { + *enhanced_mode_support = 0; + return ret; + } - return retval; + *enhanced_mode_support = DPCD_ENHANCED_FRAME_CAP(data); + + return 0; } -static void analogix_dp_set_enhanced_mode(struct analogix_dp_device *dp) +static int analogix_dp_set_enhanced_mode(struct analogix_dp_device *dp) { u8 data; + int ret; + + ret = analogix_dp_is_enhanced_mode_available(dp, &data); + if (ret < 0) + return ret; + + ret = analogix_dp_enable_rx_to_enhanced_mode(dp, data); + if (ret < 0) + return ret; - data = analogix_dp_is_enhanced_mode_available(dp); - analogix_dp_enable_rx_to_enhanced_mode(dp, data); analogix_dp_enable_enhanced_mode(dp, data); + + return 0; } -static void analogix_dp_training_pattern_dis(struct analogix_dp_device *dp) +static int analogix_dp_training_pattern_dis(struct analogix_dp_device *dp) { + int ret; + analogix_dp_set_training_pattern(dp, DP_NONE); - drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET, - DP_TRAINING_PATTERN_DISABLE); + ret = drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET, + DP_TRAINING_PATTERN_DISABLE); + + return ret < 0 ? ret : 0; } static void @@ -276,6 +340,12 @@ static int analogix_dp_link_start(struct analogix_dp_device *dp) retval = drm_dp_dpcd_write(&dp->aux, DP_LINK_BW_SET, buf, 2); if (retval < 0) return retval; + /* set enhanced mode if available */ + retval = analogix_dp_set_enhanced_mode(dp); + if (retval < 0) { + dev_err(dp->dev, "failed to set enhance mode\n"); + return retval; + } /* Set TX pre-emphasis to minimum */ for (lane = 0; lane < lane_count; lane++) @@ -531,7 +601,7 @@ static int analogix_dp_process_equalizer_training(struct analogix_dp_device *dp) { int lane, lane_count, retval; u32 reg; - u8 link_align, link_status[2], adjust_request[2], spread; + u8 link_align, link_status[2], adjust_request[2]; usleep_range(400, 401); @@ -560,10 +630,11 @@ static int analogix_dp_process_equalizer_training(struct analogix_dp_device *dp) if (!analogix_dp_channel_eq_ok(link_status, link_align, lane_count)) { /* traing pattern Set to Normal */ - analogix_dp_training_pattern_dis(dp); + retval = analogix_dp_training_pattern_dis(dp); + if (retval < 0) + return retval; dev_info(dp->dev, "Link Training success!\n"); - analogix_dp_get_link_bandwidth(dp, ®); dp->link_train.link_rate = reg; dev_dbg(dp->dev, "final bandwidth = %.2x\n", @@ -574,22 +645,6 @@ static int analogix_dp_process_equalizer_training(struct analogix_dp_device *dp) dev_dbg(dp->dev, "final lane count = %.2x\n", dp->link_train.lane_count); - retval = drm_dp_dpcd_readb(&dp->aux, DP_MAX_DOWNSPREAD, - &spread); - if (retval != 1) { - dev_err(dp->dev, "failed to read downspread %d\n", - retval); - dp->fast_train_support = false; - } else { - dp->fast_train_support = - (spread & DP_NO_AUX_HANDSHAKE_LINK_TRAINING) ? - true : false; - } - dev_dbg(dp->dev, "fast link training %s\n", - dp->fast_train_support ? "supported" : "unsupported"); - - /* set enhanced mode if available */ - analogix_dp_set_enhanced_mode(dp); dp->link_train.lt_state = FINISHED; return 0; @@ -793,7 +848,7 @@ static int analogix_dp_fast_link_train(struct analogix_dp_device *dp) static int analogix_dp_train_link(struct analogix_dp_device *dp) { - if (dp->fast_train_support) + if (dp->fast_train_enable) return analogix_dp_fast_link_train(dp); return analogix_dp_full_link_train(dp, dp->video_info.max_lane_count, @@ -819,11 +874,10 @@ static int analogix_dp_config_video(struct analogix_dp_device *dp) if (analogix_dp_is_slave_video_stream_clock_on(dp) == 0) break; if (timeout_loop > DP_TIMEOUT_LOOP_COUNT) { - dev_err(dp->dev, "Timeout of video streamclk ok\n"); + dev_err(dp->dev, "Timeout of slave video streamclk ok\n"); return -ETIMEDOUT; } - - usleep_range(1, 2); + usleep_range(1000, 1001); } /* Set to use the register calculated M/N video */ @@ -838,6 +892,9 @@ static int analogix_dp_config_video(struct analogix_dp_device *dp) /* Configure video slave mode */ analogix_dp_enable_video_master(dp, 0); + /* Enable video */ + analogix_dp_start_video(dp); + timeout_loop = 0; for (;;) { @@ -850,8 +907,9 @@ static int analogix_dp_config_video(struct analogix_dp_device *dp) done_count = 0; } if (timeout_loop > DP_TIMEOUT_LOOP_COUNT) { - dev_err(dp->dev, "Timeout of video streamclk ok\n"); - return -ETIMEDOUT; + dev_warn(dp->dev, + "Ignoring timeout of video streamclk ok\n"); + break; } usleep_range(1000, 1001); @@ -860,24 +918,32 @@ static int analogix_dp_config_video(struct analogix_dp_device *dp) return 0; } -static void analogix_dp_enable_scramble(struct analogix_dp_device *dp, - bool enable) +static int analogix_dp_enable_scramble(struct analogix_dp_device *dp, + bool enable) { u8 data; + int ret; if (enable) { analogix_dp_enable_scrambling(dp); - drm_dp_dpcd_readb(&dp->aux, DP_TRAINING_PATTERN_SET, &data); - drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET, + ret = drm_dp_dpcd_readb(&dp->aux, DP_TRAINING_PATTERN_SET, + &data); + if (ret != 1) + return ret; + ret = drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET, (u8)(data & ~DP_LINK_SCRAMBLING_DISABLE)); } else { analogix_dp_disable_scrambling(dp); - drm_dp_dpcd_readb(&dp->aux, DP_TRAINING_PATTERN_SET, &data); - drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET, + ret = drm_dp_dpcd_readb(&dp->aux, DP_TRAINING_PATTERN_SET, + &data); + if (ret != 1) + return ret; + ret = drm_dp_dpcd_writeb(&dp->aux, DP_TRAINING_PATTERN_SET, (u8)(data | DP_LINK_SCRAMBLING_DISABLE)); } + return ret < 0 ? ret : 0; } static irqreturn_t analogix_dp_hardirq(int irq, void *arg) @@ -916,7 +982,23 @@ static irqreturn_t analogix_dp_irq_thread(int irq, void *arg) return IRQ_HANDLED; } -static void analogix_dp_commit(struct analogix_dp_device *dp) +static int analogix_dp_fast_link_train_detection(struct analogix_dp_device *dp) +{ + int ret; + u8 spread; + + ret = drm_dp_dpcd_readb(&dp->aux, DP_MAX_DOWNSPREAD, &spread); + if (ret != 1) { + dev_err(dp->dev, "failed to read downspread %d\n", ret); + return ret; + } + dp->fast_train_enable = !!(spread & DP_NO_AUX_HANDSHAKE_LINK_TRAINING); + dev_dbg(dp->dev, "fast link training %s\n", + dp->fast_train_enable ? "supported" : "unsupported"); + return 0; +} + +static int analogix_dp_commit(struct analogix_dp_device *dp) { int ret; @@ -926,34 +1008,50 @@ static void analogix_dp_commit(struct analogix_dp_device *dp) DRM_ERROR("failed to disable the panel\n"); } - ret = readx_poll_timeout(analogix_dp_train_link, dp, ret, !ret, 100, - DP_TIMEOUT_TRAINING_US * 5); + ret = analogix_dp_train_link(dp); if (ret) { dev_err(dp->dev, "unable to do link train, ret=%d\n", ret); - return; + return ret; } - analogix_dp_enable_scramble(dp, 1); - analogix_dp_enable_rx_to_enhanced_mode(dp, 1); - analogix_dp_enable_enhanced_mode(dp, 1); + ret = analogix_dp_enable_scramble(dp, 1); + if (ret < 0) { + dev_err(dp->dev, "can not enable scramble\n"); + return ret; + } analogix_dp_init_video(dp); ret = analogix_dp_config_video(dp); - if (ret) + if (ret) { dev_err(dp->dev, "unable to config video\n"); + return ret; + } /* Safe to enable the panel now */ if (dp->plat_data->panel) { - if (drm_panel_enable(dp->plat_data->panel)) + ret = drm_panel_enable(dp->plat_data->panel); + if (ret) { DRM_ERROR("failed to enable the panel\n"); + return ret; + } } - /* Enable video */ - analogix_dp_start_video(dp); + ret = analogix_dp_detect_sink_psr(dp); + if (ret) + return ret; - dp->psr_enable = analogix_dp_detect_sink_psr(dp); - if (dp->psr_enable) - analogix_dp_enable_sink_psr(dp); + if (dp->psr_enable) { + ret = analogix_dp_enable_sink_psr(dp); + if (ret) + return ret; + } + + /* Check whether panel supports fast training */ + ret = analogix_dp_fast_link_train_detection(dp); + if (ret) + dp->psr_enable = false; + + return ret; } /* @@ -1150,24 +1248,80 @@ static void analogix_dp_bridge_pre_enable(struct drm_bridge *bridge) DRM_ERROR("failed to setup the panel ret = %d\n", ret); } -static void analogix_dp_bridge_enable(struct drm_bridge *bridge) +static int analogix_dp_set_bridge(struct analogix_dp_device *dp) { - struct analogix_dp_device *dp = bridge->driver_private; - - if (dp->dpms_mode == DRM_MODE_DPMS_ON) - return; + int ret; pm_runtime_get_sync(dp->dev); - if (dp->plat_data->power_on) - dp->plat_data->power_on(dp->plat_data); + ret = clk_prepare_enable(dp->clock); + if (ret < 0) { + DRM_ERROR("Failed to prepare_enable the clock clk [%d]\n", ret); + goto out_dp_clk_pre; + } + + if (dp->plat_data->power_on_start) + dp->plat_data->power_on_start(dp->plat_data); phy_power_on(dp->phy); - analogix_dp_init_dp(dp); + + ret = analogix_dp_init_dp(dp); + if (ret) + goto out_dp_init; + + /* + * According to DP spec v1.3 chap 3.5.1.2 Link Training, + * We should first make sure the HPD signal is asserted high by device + * when we want to establish a link with it. + */ + ret = analogix_dp_detect_hpd(dp); + if (ret) { + DRM_ERROR("failed to get hpd single ret = %d\n", ret); + goto out_dp_init; + } + + ret = analogix_dp_commit(dp); + if (ret) { + DRM_ERROR("dp commit error, ret = %d\n", ret); + goto out_dp_init; + } + + if (dp->plat_data->power_on_end) + dp->plat_data->power_on_end(dp->plat_data); + enable_irq(dp->irq); - analogix_dp_commit(dp); + return 0; - dp->dpms_mode = DRM_MODE_DPMS_ON; +out_dp_init: + phy_power_off(dp->phy); + if (dp->plat_data->power_off) + dp->plat_data->power_off(dp->plat_data); + clk_disable_unprepare(dp->clock); +out_dp_clk_pre: + pm_runtime_put_sync(dp->dev); + + return ret; +} + +static void analogix_dp_bridge_enable(struct drm_bridge *bridge) +{ + struct analogix_dp_device *dp = bridge->driver_private; + int timeout_loop = 0; + + if (dp->dpms_mode == DRM_MODE_DPMS_ON) + return; + + while (timeout_loop < MAX_PLL_LOCK_LOOP) { + if (analogix_dp_set_bridge(dp) == 0) { + dp->dpms_mode = DRM_MODE_DPMS_ON; + return; + } + dev_err(dp->dev, "failed to set bridge, retry: %d\n", + timeout_loop); + timeout_loop++; + usleep_range(10, 11); + } + dev_err(dp->dev, "too many times retry set bridge, give it up\n"); } static void analogix_dp_bridge_disable(struct drm_bridge *bridge) @@ -1186,11 +1340,15 @@ static void analogix_dp_bridge_disable(struct drm_bridge *bridge) } disable_irq(dp->irq); - phy_power_off(dp->phy); if (dp->plat_data->power_off) dp->plat_data->power_off(dp->plat_data); + analogix_dp_set_analog_power_down(dp, POWER_ALL, 1); + phy_power_off(dp->phy); + + clk_disable_unprepare(dp->clock); + pm_runtime_put_sync(dp->dev); ret = analogix_dp_prepare_panel(dp, false, true); @@ -1198,6 +1356,7 @@ static void analogix_dp_bridge_disable(struct drm_bridge *bridge) DRM_ERROR("failed to setup the panel ret = %d\n", ret); dp->psr_enable = false; + dp->fast_train_enable = false; dp->dpms_mode = DRM_MODE_DPMS_OFF; } diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h index 6a96ef7..769255d 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h @@ -19,6 +19,7 @@ #define DP_TIMEOUT_LOOP_COUNT 100 #define MAX_CR_LOOP 5 #define MAX_EQ_LOOP 5 +#define MAX_PLL_LOCK_LOOP 5 /* Training takes 22ms if AUX channel comm fails. Use this as retry interval */ #define DP_TIMEOUT_TRAINING_US 22000 @@ -173,7 +174,7 @@ struct analogix_dp_device { int hpd_gpio; bool force_hpd; bool psr_enable; - bool fast_train_support; + bool fast_train_enable; struct mutex panel_lock; bool panel_is_modeset; @@ -197,7 +198,7 @@ void analogix_dp_set_pll_power_down(struct analogix_dp_device *dp, bool enable); void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp, enum analog_power_block block, bool enable); -void analogix_dp_init_analog_func(struct analogix_dp_device *dp); +int analogix_dp_init_analog_func(struct analogix_dp_device *dp); void analogix_dp_init_hpd(struct analogix_dp_device *dp); void analogix_dp_force_hpd(struct analogix_dp_device *dp); enum dp_irq_type analogix_dp_get_irq_type(struct analogix_dp_device *dp); diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c index 9df2f3e..a5f2763 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c @@ -126,9 +126,14 @@ void analogix_dp_reset(struct analogix_dp_device *dp) analogix_dp_stop_video(dp); analogix_dp_enable_video_mute(dp, 0); - reg = MASTER_VID_FUNC_EN_N | SLAVE_VID_FUNC_EN_N | - AUD_FIFO_FUNC_EN_N | AUD_FUNC_EN_N | - HDCP_FUNC_EN_N | SW_FUNC_EN_N; + if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) + reg = RK_VID_CAP_FUNC_EN_N | RK_VID_FIFO_FUNC_EN_N | + SW_FUNC_EN_N; + else + reg = MASTER_VID_FUNC_EN_N | SLAVE_VID_FUNC_EN_N | + AUD_FIFO_FUNC_EN_N | AUD_FUNC_EN_N | + HDCP_FUNC_EN_N | SW_FUNC_EN_N; + writel(reg, dp->reg_base + ANALOGIX_DP_FUNC_EN_1); reg = SSC_FUNC_EN_N | AUX_FUNC_EN_N | @@ -230,16 +235,20 @@ enum pll_status analogix_dp_get_pll_lock_status(struct analogix_dp_device *dp) void analogix_dp_set_pll_power_down(struct analogix_dp_device *dp, bool enable) { u32 reg; + u32 mask = DP_PLL_PD; + u32 pd_addr = ANALOGIX_DP_PLL_CTL; - if (enable) { - reg = readl(dp->reg_base + ANALOGIX_DP_PLL_CTL); - reg |= DP_PLL_PD; - writel(reg, dp->reg_base + ANALOGIX_DP_PLL_CTL); - } else { - reg = readl(dp->reg_base + ANALOGIX_DP_PLL_CTL); - reg &= ~DP_PLL_PD; - writel(reg, dp->reg_base + ANALOGIX_DP_PLL_CTL); + if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) { + pd_addr = ANALOGIX_DP_PD; + mask = RK_PLL_PD; } + + reg = readl(dp->reg_base + pd_addr); + if (enable) + reg |= mask; + else + reg &= ~mask; + writel(reg, dp->reg_base + pd_addr); } void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp, @@ -248,83 +257,98 @@ void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp, { u32 reg; u32 phy_pd_addr = ANALOGIX_DP_PHY_PD; + u32 mask; if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) phy_pd_addr = ANALOGIX_DP_PD; switch (block) { case AUX_BLOCK: - if (enable) { - reg = readl(dp->reg_base + phy_pd_addr); - reg |= AUX_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } else { - reg = readl(dp->reg_base + phy_pd_addr); - reg &= ~AUX_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } + if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) + mask = RK_AUX_PD; + else + mask = AUX_PD; + + reg = readl(dp->reg_base + phy_pd_addr); + if (enable) + reg |= mask; + else + reg &= ~mask; + writel(reg, dp->reg_base + phy_pd_addr); break; case CH0_BLOCK: - if (enable) { - reg = readl(dp->reg_base + phy_pd_addr); - reg |= CH0_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } else { - reg = readl(dp->reg_base + phy_pd_addr); - reg &= ~CH0_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } + mask = CH0_PD; + reg = readl(dp->reg_base + phy_pd_addr); + + if (enable) + reg |= mask; + else + reg &= ~mask; + writel(reg, dp->reg_base + phy_pd_addr); break; case CH1_BLOCK: - if (enable) { - reg = readl(dp->reg_base + phy_pd_addr); - reg |= CH1_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } else { - reg = readl(dp->reg_base + phy_pd_addr); - reg &= ~CH1_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } + mask = CH1_PD; + reg = readl(dp->reg_base + phy_pd_addr); + + if (enable) + reg |= mask; + else + reg &= ~mask; + writel(reg, dp->reg_base + phy_pd_addr); break; case CH2_BLOCK: - if (enable) { - reg = readl(dp->reg_base + phy_pd_addr); - reg |= CH2_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } else { - reg = readl(dp->reg_base + phy_pd_addr); - reg &= ~CH2_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } + mask = CH2_PD; + reg = readl(dp->reg_base + phy_pd_addr); + + if (enable) + reg |= mask; + else + reg &= ~mask; + writel(reg, dp->reg_base + phy_pd_addr); break; case CH3_BLOCK: - if (enable) { - reg = readl(dp->reg_base + phy_pd_addr); - reg |= CH3_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } else { - reg = readl(dp->reg_base + phy_pd_addr); - reg &= ~CH3_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } + mask = CH3_PD; + reg = readl(dp->reg_base + phy_pd_addr); + + if (enable) + reg |= mask; + else + reg &= ~mask; + writel(reg, dp->reg_base + phy_pd_addr); break; case ANALOG_TOTAL: - if (enable) { - reg = readl(dp->reg_base + phy_pd_addr); - reg |= DP_PHY_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } else { - reg = readl(dp->reg_base + phy_pd_addr); - reg &= ~DP_PHY_PD; - writel(reg, dp->reg_base + phy_pd_addr); - } + /* + * There is no bit named DP_PHY_PD, so We used DP_INC_BG + * to power off everything instead of DP_PHY_PD in + * Rockchip + */ + if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) + mask = DP_INC_BG; + else + mask = DP_PHY_PD; + + reg = readl(dp->reg_base + phy_pd_addr); + if (enable) + reg |= mask; + else + reg &= ~mask; + + writel(reg, dp->reg_base + phy_pd_addr); + if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) + usleep_range(10, 15); break; case POWER_ALL: if (enable) { - reg = DP_PHY_PD | AUX_PD | CH3_PD | CH2_PD | - CH1_PD | CH0_PD; + reg = DP_ALL_PD; writel(reg, dp->reg_base + phy_pd_addr); } else { + reg = DP_ALL_PD; + writel(reg, dp->reg_base + phy_pd_addr); + usleep_range(10, 15); + reg &= ~DP_INC_BG; + writel(reg, dp->reg_base + phy_pd_addr); + usleep_range(10, 15); + writel(0x00, dp->reg_base + phy_pd_addr); } break; @@ -333,7 +357,7 @@ void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp, } } -void analogix_dp_init_analog_func(struct analogix_dp_device *dp) +int analogix_dp_init_analog_func(struct analogix_dp_device *dp) { u32 reg; int timeout_loop = 0; @@ -355,7 +379,7 @@ void analogix_dp_init_analog_func(struct analogix_dp_device *dp) timeout_loop++; if (DP_TIMEOUT_LOOP_COUNT < timeout_loop) { dev_err(dp->dev, "failed to get pll lock status\n"); - return; + return -ETIMEDOUT; } usleep_range(10, 20); } @@ -366,6 +390,7 @@ void analogix_dp_init_analog_func(struct analogix_dp_device *dp) reg &= ~(SERDES_FIFO_FUNC_EN_N | LS_CLK_DOMAIN_FUNC_EN_N | AUX_FUNC_EN_N); writel(reg, dp->reg_base + ANALOGIX_DP_FUNC_EN_2); + return 0; } void analogix_dp_clear_hotplug_interrupts(struct analogix_dp_device *dp) @@ -450,17 +475,22 @@ void analogix_dp_init_aux(struct analogix_dp_device *dp) reg = RPLY_RECEIV | AUX_ERR; writel(reg, dp->reg_base + ANALOGIX_DP_INT_STA); + analogix_dp_set_analog_power_down(dp, AUX_BLOCK, true); + usleep_range(10, 11); + analogix_dp_set_analog_power_down(dp, AUX_BLOCK, false); + analogix_dp_reset_aux(dp); - /* Disable AUX transaction H/W retry */ + /* AUX_BIT_PERIOD_EXPECTED_DELAY doesn't apply to Rockchip IP */ if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) - reg = AUX_BIT_PERIOD_EXPECTED_DELAY(0) | - AUX_HW_RETRY_COUNT_SEL(3) | - AUX_HW_RETRY_INTERVAL_600_MICROSECONDS; + reg = 0; else - reg = AUX_BIT_PERIOD_EXPECTED_DELAY(3) | - AUX_HW_RETRY_COUNT_SEL(0) | - AUX_HW_RETRY_INTERVAL_600_MICROSECONDS; + reg = AUX_BIT_PERIOD_EXPECTED_DELAY(3); + + /* Disable AUX transaction H/W retry */ + reg |= AUX_HW_RETRY_COUNT_SEL(0) | + AUX_HW_RETRY_INTERVAL_600_MICROSECONDS; + writel(reg, dp->reg_base + ANALOGIX_DP_AUX_HW_RETRY_CTL); /* Receive AUX Channel DEFER commands equal to DEFFER_COUNT*64 */ @@ -947,8 +977,12 @@ void analogix_dp_config_video_slave_mode(struct analogix_dp_device *dp) u32 reg; reg = readl(dp->reg_base + ANALOGIX_DP_FUNC_EN_1); - reg &= ~(MASTER_VID_FUNC_EN_N | SLAVE_VID_FUNC_EN_N); - reg |= MASTER_VID_FUNC_EN_N; + if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) { + reg &= ~(RK_VID_CAP_FUNC_EN_N | RK_VID_FIFO_FUNC_EN_N); + } else { + reg &= ~(MASTER_VID_FUNC_EN_N | SLAVE_VID_FUNC_EN_N); + reg |= MASTER_VID_FUNC_EN_N; + } writel(reg, dp->reg_base + ANALOGIX_DP_FUNC_EN_1); reg = readl(dp->reg_base + ANALOGIX_DP_VIDEO_CTL_10); @@ -1072,10 +1106,11 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, struct drm_dp_aux_msg *msg) { u32 reg; + u32 status_reg; u8 *buffer = msg->buffer; - int timeout_loop = 0; unsigned int i; int num_transferred = 0; + int ret; /* Buffer size of AUX CH is 16 bytes */ if (WARN_ON(msg->size > 16)) @@ -1139,17 +1174,20 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, writel(reg, dp->reg_base + ANALOGIX_DP_AUX_CH_CTL_2); - /* Is AUX CH command reply received? */ + ret = readx_poll_timeout(readl, dp->reg_base + ANALOGIX_DP_AUX_CH_CTL_2, + reg, !(reg & AUX_EN), 25, 500 * 1000); + if (ret) { + dev_err(dp->dev, "AUX CH enable timeout!\n"); + goto aux_error; + } + /* TODO: Wait for an interrupt instead of looping? */ - reg = readl(dp->reg_base + ANALOGIX_DP_INT_STA); - while (!(reg & RPLY_RECEIV)) { - timeout_loop++; - if (timeout_loop > DP_TIMEOUT_LOOP_COUNT) { - dev_err(dp->dev, "AUX CH command reply failed!\n"); - return -ETIMEDOUT; - } - reg = readl(dp->reg_base + ANALOGIX_DP_INT_STA); - usleep_range(10, 11); + /* Is AUX CH command reply received? */ + ret = readx_poll_timeout(readl, dp->reg_base + ANALOGIX_DP_INT_STA, + reg, reg & RPLY_RECEIV, 10, 20 * 1000); + if (ret) { + dev_err(dp->dev, "AUX CH cmd reply timeout!\n"); + goto aux_error; } /* Clear interrupt source for AUX CH command reply */ @@ -1157,17 +1195,13 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, /* Clear interrupt source for AUX CH access error */ reg = readl(dp->reg_base + ANALOGIX_DP_INT_STA); - if (reg & AUX_ERR) { + status_reg = readl(dp->reg_base + ANALOGIX_DP_AUX_CH_STA); + if ((reg & AUX_ERR) || (status_reg & AUX_STATUS_MASK)) { writel(AUX_ERR, dp->reg_base + ANALOGIX_DP_INT_STA); - return -EREMOTEIO; - } - /* Check AUX CH error access status */ - reg = readl(dp->reg_base + ANALOGIX_DP_AUX_CH_STA); - if ((reg & AUX_STATUS_MASK)) { - dev_err(dp->dev, "AUX CH error happened: %d\n\n", - reg & AUX_STATUS_MASK); - return -EREMOTEIO; + dev_warn(dp->dev, "AUX CH error happened: %#x (%d)\n", + status_reg & AUX_STATUS_MASK, !!(reg & AUX_ERR)); + goto aux_error; } if (msg->request & DP_AUX_I2C_READ) { @@ -1193,4 +1227,10 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, msg->reply = DP_AUX_NATIVE_REPLY_ACK; return num_transferred > 0 ? num_transferred : -EBUSY; + +aux_error: + /* if aux err happen, reset aux */ + analogix_dp_init_aux(dp); + + return -EREMOTEIO; } diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h index 40200c6..0cf27c7 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h @@ -127,7 +127,9 @@ /* ANALOGIX_DP_FUNC_EN_1 */ #define MASTER_VID_FUNC_EN_N (0x1 << 7) +#define RK_VID_CAP_FUNC_EN_N (0x1 << 6) #define SLAVE_VID_FUNC_EN_N (0x1 << 5) +#define RK_VID_FIFO_FUNC_EN_N (0x1 << 5) #define AUD_FIFO_FUNC_EN_N (0x1 << 4) #define AUD_FUNC_EN_N (0x1 << 3) #define HDCP_FUNC_EN_N (0x1 << 2) @@ -342,12 +344,17 @@ #define DP_PLL_REF_BIT_1_2500V (0x7 << 0) /* ANALOGIX_DP_PHY_PD */ +#define DP_INC_BG (0x1 << 7) +#define DP_EXP_BG (0x1 << 6) #define DP_PHY_PD (0x1 << 5) +#define RK_AUX_PD (0x1 << 5) #define AUX_PD (0x1 << 4) +#define RK_PLL_PD (0x1 << 4) #define CH3_PD (0x1 << 3) #define CH2_PD (0x1 << 2) #define CH1_PD (0x1 << 1) #define CH0_PD (0x1 << 0) +#define DP_ALL_PD (0xff) /* ANALOGIX_DP_PHY_TEST */ #define MACRO_RST (0x1 << 5) diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c new file mode 100644 index 0000000..c255fc3 --- /dev/null +++ b/drivers/gpu/drm/bridge/cdns-dsi.c @@ -0,0 +1,1623 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright: 2017 Cadence Design Systems, Inc. + * + * Author: Boris Brezillon <boris.brezillon@bootlin.com> + */ + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_bridge.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_panel.h> +#include <video/mipi_display.h> + +#include <linux/clk.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_graph.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/reset.h> + +#define IP_CONF 0x0 +#define SP_HS_FIFO_DEPTH(x) (((x) & GENMASK(30, 26)) >> 26) +#define SP_LP_FIFO_DEPTH(x) (((x) & GENMASK(25, 21)) >> 21) +#define VRS_FIFO_DEPTH(x) (((x) & GENMASK(20, 16)) >> 16) +#define DIRCMD_FIFO_DEPTH(x) (((x) & GENMASK(15, 13)) >> 13) +#define SDI_IFACE_32 BIT(12) +#define INTERNAL_DATAPATH_32 (0 << 10) +#define INTERNAL_DATAPATH_16 (1 << 10) +#define INTERNAL_DATAPATH_8 (3 << 10) +#define INTERNAL_DATAPATH_SIZE ((x) & GENMASK(11, 10)) +#define NUM_IFACE(x) ((((x) & GENMASK(9, 8)) >> 8) + 1) +#define MAX_LANE_NB(x) (((x) & GENMASK(7, 6)) >> 6) +#define RX_FIFO_DEPTH(x) ((x) & GENMASK(5, 0)) + +#define MCTL_MAIN_DATA_CTL 0x4 +#define TE_MIPI_POLLING_EN BIT(25) +#define TE_HW_POLLING_EN BIT(24) +#define DISP_EOT_GEN BIT(18) +#define HOST_EOT_GEN BIT(17) +#define DISP_GEN_CHECKSUM BIT(16) +#define DISP_GEN_ECC BIT(15) +#define BTA_EN BIT(14) +#define READ_EN BIT(13) +#define REG_TE_EN BIT(12) +#define IF_TE_EN(x) BIT(8 + (x)) +#define TVG_SEL BIT(6) +#define VID_EN BIT(5) +#define IF_VID_SELECT(x) ((x) << 2) +#define IF_VID_SELECT_MASK GENMASK(3, 2) +#define IF_VID_MODE BIT(1) +#define LINK_EN BIT(0) + +#define MCTL_MAIN_PHY_CTL 0x8 +#define HS_INVERT_DAT(x) BIT(19 + ((x) * 2)) +#define SWAP_PINS_DAT(x) BIT(18 + ((x) * 2)) +#define HS_INVERT_CLK BIT(17) +#define SWAP_PINS_CLK BIT(16) +#define HS_SKEWCAL_EN BIT(15) +#define WAIT_BURST_TIME(x) ((x) << 10) +#define DATA_ULPM_EN(x) BIT(6 + (x)) +#define CLK_ULPM_EN BIT(5) +#define CLK_CONTINUOUS BIT(4) +#define DATA_LANE_EN(x) BIT((x) - 1) + +#define MCTL_MAIN_EN 0xc +#define DATA_FORCE_STOP BIT(17) +#define CLK_FORCE_STOP BIT(16) +#define IF_EN(x) BIT(13 + (x)) +#define DATA_LANE_ULPM_REQ(l) BIT(9 + (l)) +#define CLK_LANE_ULPM_REQ BIT(8) +#define DATA_LANE_START(x) BIT(4 + (x)) +#define CLK_LANE_EN BIT(3) +#define PLL_START BIT(0) + +#define MCTL_DPHY_CFG0 0x10 +#define DPHY_C_RSTB BIT(20) +#define DPHY_D_RSTB(x) GENMASK(15 + (x), 16) +#define DPHY_PLL_PDN BIT(10) +#define DPHY_CMN_PDN BIT(9) +#define DPHY_C_PDN BIT(8) +#define DPHY_D_PDN(x) GENMASK(3 + (x), 4) +#define DPHY_ALL_D_PDN GENMASK(7, 4) +#define DPHY_PLL_PSO BIT(1) +#define DPHY_CMN_PSO BIT(0) + +#define MCTL_DPHY_TIMEOUT1 0x14 +#define HSTX_TIMEOUT(x) ((x) << 4) +#define HSTX_TIMEOUT_MAX GENMASK(17, 0) +#define CLK_DIV(x) (x) +#define CLK_DIV_MAX GENMASK(3, 0) + +#define MCTL_DPHY_TIMEOUT2 0x18 +#define LPRX_TIMEOUT(x) (x) + +#define MCTL_ULPOUT_TIME 0x1c +#define DATA_LANE_ULPOUT_TIME(x) ((x) << 9) +#define CLK_LANE_ULPOUT_TIME(x) (x) + +#define MCTL_3DVIDEO_CTL 0x20 +#define VID_VSYNC_3D_EN BIT(7) +#define VID_VSYNC_3D_LR BIT(5) +#define VID_VSYNC_3D_SECOND_EN BIT(4) +#define VID_VSYNC_3DFORMAT_LINE (0 << 2) +#define VID_VSYNC_3DFORMAT_FRAME (1 << 2) +#define VID_VSYNC_3DFORMAT_PIXEL (2 << 2) +#define VID_VSYNC_3DMODE_OFF 0 +#define VID_VSYNC_3DMODE_PORTRAIT 1 +#define VID_VSYNC_3DMODE_LANDSCAPE 2 + +#define MCTL_MAIN_STS 0x24 +#define MCTL_MAIN_STS_CTL 0x130 +#define MCTL_MAIN_STS_CLR 0x150 +#define MCTL_MAIN_STS_FLAG 0x170 +#define HS_SKEWCAL_DONE BIT(11) +#define IF_UNTERM_PKT_ERR(x) BIT(8 + (x)) +#define LPRX_TIMEOUT_ERR BIT(7) +#define HSTX_TIMEOUT_ERR BIT(6) +#define DATA_LANE_RDY(l) BIT(2 + (l)) +#define CLK_LANE_RDY BIT(1) +#define PLL_LOCKED BIT(0) + +#define MCTL_DPHY_ERR 0x28 +#define MCTL_DPHY_ERR_CTL1 0x148 +#define MCTL_DPHY_ERR_CLR 0x168 +#define MCTL_DPHY_ERR_FLAG 0x188 +#define ERR_CONT_LP(x, l) BIT(18 + ((x) * 4) + (l)) +#define ERR_CONTROL(l) BIT(14 + (l)) +#define ERR_SYNESC(l) BIT(10 + (l)) +#define ERR_ESC(l) BIT(6 + (l)) + +#define MCTL_DPHY_ERR_CTL2 0x14c +#define ERR_CONT_LP_EDGE(x, l) BIT(12 + ((x) * 4) + (l)) +#define ERR_CONTROL_EDGE(l) BIT(8 + (l)) +#define ERR_SYN_ESC_EDGE(l) BIT(4 + (l)) +#define ERR_ESC_EDGE(l) BIT(0 + (l)) + +#define MCTL_LANE_STS 0x2c +#define PPI_C_TX_READY_HS BIT(18) +#define DPHY_PLL_LOCK BIT(17) +#define PPI_D_RX_ULPS_ESC(x) (((x) & GENMASK(15, 12)) >> 12) +#define LANE_STATE_START 0 +#define LANE_STATE_IDLE 1 +#define LANE_STATE_WRITE 2 +#define LANE_STATE_ULPM 3 +#define LANE_STATE_READ 4 +#define DATA_LANE_STATE(l, val) \ + (((val) >> (2 + 2 * (l) + ((l) ? 1 : 0))) & GENMASK((l) ? 1 : 2, 0)) +#define CLK_LANE_STATE_HS 2 +#define CLK_LANE_STATE(val) ((val) & GENMASK(1, 0)) + +#define DSC_MODE_CTL 0x30 +#define DSC_MODE_EN BIT(0) + +#define DSC_CMD_SEND 0x34 +#define DSC_SEND_PPS BIT(0) +#define DSC_EXECUTE_QUEUE BIT(1) + +#define DSC_PPS_WRDAT 0x38 + +#define DSC_MODE_STS 0x3c +#define DSC_PPS_DONE BIT(1) +#define DSC_EXEC_DONE BIT(2) + +#define CMD_MODE_CTL 0x70 +#define IF_LP_EN(x) BIT(9 + (x)) +#define IF_VCHAN_ID(x, c) ((c) << ((x) * 2)) + +#define CMD_MODE_CTL2 0x74 +#define TE_TIMEOUT(x) ((x) << 11) +#define FILL_VALUE(x) ((x) << 3) +#define ARB_IF_WITH_HIGHEST_PRIORITY(x) ((x) << 1) +#define ARB_ROUND_ROBIN_MODE BIT(0) + +#define CMD_MODE_STS 0x78 +#define CMD_MODE_STS_CTL 0x134 +#define CMD_MODE_STS_CLR 0x154 +#define CMD_MODE_STS_FLAG 0x174 +#define ERR_IF_UNDERRUN(x) BIT(4 + (x)) +#define ERR_UNWANTED_READ BIT(3) +#define ERR_TE_MISS BIT(2) +#define ERR_NO_TE BIT(1) +#define CSM_RUNNING BIT(0) + +#define DIRECT_CMD_SEND 0x80 + +#define DIRECT_CMD_MAIN_SETTINGS 0x84 +#define TRIGGER_VAL(x) ((x) << 25) +#define CMD_LP_EN BIT(24) +#define CMD_SIZE(x) ((x) << 16) +#define CMD_VCHAN_ID(x) ((x) << 14) +#define CMD_DATATYPE(x) ((x) << 8) +#define CMD_LONG BIT(3) +#define WRITE_CMD 0 +#define READ_CMD 1 +#define TE_REQ 4 +#define TRIGGER_REQ 5 +#define BTA_REQ 6 + +#define DIRECT_CMD_STS 0x88 +#define DIRECT_CMD_STS_CTL 0x138 +#define DIRECT_CMD_STS_CLR 0x158 +#define DIRECT_CMD_STS_FLAG 0x178 +#define RCVD_ACK_VAL(val) ((val) >> 16) +#define RCVD_TRIGGER_VAL(val) (((val) & GENMASK(14, 11)) >> 11) +#define READ_COMPLETED_WITH_ERR BIT(10) +#define BTA_FINISHED BIT(9) +#define BTA_COMPLETED BIT(8) +#define TE_RCVD BIT(7) +#define TRIGGER_RCVD BIT(6) +#define ACK_WITH_ERR_RCVD BIT(5) +#define ACK_RCVD BIT(4) +#define READ_COMPLETED BIT(3) +#define TRIGGER_COMPLETED BIT(2) +#define WRITE_COMPLETED BIT(1) +#define SENDING_CMD BIT(0) + +#define DIRECT_CMD_STOP_READ 0x8c + +#define DIRECT_CMD_WRDATA 0x90 + +#define DIRECT_CMD_FIFO_RST 0x94 + +#define DIRECT_CMD_RDDATA 0xa0 + +#define DIRECT_CMD_RD_PROPS 0xa4 +#define RD_DCS BIT(18) +#define RD_VCHAN_ID(val) (((val) >> 16) & GENMASK(1, 0)) +#define RD_SIZE(val) ((val) & GENMASK(15, 0)) + +#define DIRECT_CMD_RD_STS 0xa8 +#define DIRECT_CMD_RD_STS_CTL 0x13c +#define DIRECT_CMD_RD_STS_CLR 0x15c +#define DIRECT_CMD_RD_STS_FLAG 0x17c +#define ERR_EOT_WITH_ERR BIT(8) +#define ERR_MISSING_EOT BIT(7) +#define ERR_WRONG_LENGTH BIT(6) +#define ERR_OVERSIZE BIT(5) +#define ERR_RECEIVE BIT(4) +#define ERR_UNDECODABLE BIT(3) +#define ERR_CHECKSUM BIT(2) +#define ERR_UNCORRECTABLE BIT(1) +#define ERR_FIXED BIT(0) + +#define VID_MAIN_CTL 0xb0 +#define VID_IGNORE_MISS_VSYNC BIT(31) +#define VID_FIELD_SW BIT(28) +#define VID_INTERLACED_EN BIT(27) +#define RECOVERY_MODE(x) ((x) << 25) +#define RECOVERY_MODE_NEXT_HSYNC 0 +#define RECOVERY_MODE_NEXT_STOP_POINT 2 +#define RECOVERY_MODE_NEXT_VSYNC 3 +#define REG_BLKEOL_MODE(x) ((x) << 23) +#define REG_BLKLINE_MODE(x) ((x) << 21) +#define REG_BLK_MODE_NULL_PKT 0 +#define REG_BLK_MODE_BLANKING_PKT 1 +#define REG_BLK_MODE_LP 2 +#define SYNC_PULSE_HORIZONTAL BIT(20) +#define SYNC_PULSE_ACTIVE BIT(19) +#define BURST_MODE BIT(18) +#define VID_PIXEL_MODE_MASK GENMASK(17, 14) +#define VID_PIXEL_MODE_RGB565 (0 << 14) +#define VID_PIXEL_MODE_RGB666_PACKED (1 << 14) +#define VID_PIXEL_MODE_RGB666 (2 << 14) +#define VID_PIXEL_MODE_RGB888 (3 << 14) +#define VID_PIXEL_MODE_RGB101010 (4 << 14) +#define VID_PIXEL_MODE_RGB121212 (5 << 14) +#define VID_PIXEL_MODE_YUV420 (8 << 14) +#define VID_PIXEL_MODE_YUV422_PACKED (9 << 14) +#define VID_PIXEL_MODE_YUV422 (10 << 14) +#define VID_PIXEL_MODE_YUV422_24B (11 << 14) +#define VID_PIXEL_MODE_DSC_COMP (12 << 14) +#define VID_DATATYPE(x) ((x) << 8) +#define VID_VIRTCHAN_ID(iface, x) ((x) << (4 + (iface) * 2)) +#define STOP_MODE(x) ((x) << 2) +#define START_MODE(x) (x) + +#define VID_VSIZE1 0xb4 +#define VFP_LEN(x) ((x) << 12) +#define VBP_LEN(x) ((x) << 6) +#define VSA_LEN(x) (x) + +#define VID_VSIZE2 0xb8 +#define VACT_LEN(x) (x) + +#define VID_HSIZE1 0xc0 +#define HBP_LEN(x) ((x) << 16) +#define HSA_LEN(x) (x) + +#define VID_HSIZE2 0xc4 +#define HFP_LEN(x) ((x) << 16) +#define HACT_LEN(x) (x) + +#define VID_BLKSIZE1 0xcc +#define BLK_EOL_PKT_LEN(x) ((x) << 15) +#define BLK_LINE_EVENT_PKT_LEN(x) (x) + +#define VID_BLKSIZE2 0xd0 +#define BLK_LINE_PULSE_PKT_LEN(x) (x) + +#define VID_PKT_TIME 0xd8 +#define BLK_EOL_DURATION(x) (x) + +#define VID_DPHY_TIME 0xdc +#define REG_WAKEUP_TIME(x) ((x) << 17) +#define REG_LINE_DURATION(x) (x) + +#define VID_ERR_COLOR1 0xe0 +#define COL_GREEN(x) ((x) << 12) +#define COL_RED(x) (x) + +#define VID_ERR_COLOR2 0xe4 +#define PAD_VAL(x) ((x) << 12) +#define COL_BLUE(x) (x) + +#define VID_VPOS 0xe8 +#define LINE_VAL(val) (((val) & GENMASK(14, 2)) >> 2) +#define LINE_POS(val) ((val) & GENMASK(1, 0)) + +#define VID_HPOS 0xec +#define HORIZ_VAL(val) (((val) & GENMASK(17, 3)) >> 3) +#define HORIZ_POS(val) ((val) & GENMASK(2, 0)) + +#define VID_MODE_STS 0xf0 +#define VID_MODE_STS_CTL 0x140 +#define VID_MODE_STS_CLR 0x160 +#define VID_MODE_STS_FLAG 0x180 +#define VSG_RECOVERY BIT(10) +#define ERR_VRS_WRONG_LEN BIT(9) +#define ERR_LONG_READ BIT(8) +#define ERR_LINE_WRITE BIT(7) +#define ERR_BURST_WRITE BIT(6) +#define ERR_SMALL_HEIGHT BIT(5) +#define ERR_SMALL_LEN BIT(4) +#define ERR_MISSING_VSYNC BIT(3) +#define ERR_MISSING_HSYNC BIT(2) +#define ERR_MISSING_DATA BIT(1) +#define VSG_RUNNING BIT(0) + +#define VID_VCA_SETTING1 0xf4 +#define BURST_LP BIT(16) +#define MAX_BURST_LIMIT(x) (x) + +#define VID_VCA_SETTING2 0xf8 +#define MAX_LINE_LIMIT(x) ((x) << 16) +#define EXACT_BURST_LIMIT(x) (x) + +#define TVG_CTL 0xfc +#define TVG_STRIPE_SIZE(x) ((x) << 5) +#define TVG_MODE_MASK GENMASK(4, 3) +#define TVG_MODE_SINGLE_COLOR (0 << 3) +#define TVG_MODE_VSTRIPES (2 << 3) +#define TVG_MODE_HSTRIPES (3 << 3) +#define TVG_STOPMODE_MASK GENMASK(2, 1) +#define TVG_STOPMODE_EOF (0 << 1) +#define TVG_STOPMODE_EOL (1 << 1) +#define TVG_STOPMODE_NOW (2 << 1) +#define TVG_RUN BIT(0) + +#define TVG_IMG_SIZE 0x100 +#define TVG_NBLINES(x) ((x) << 16) +#define TVG_LINE_SIZE(x) (x) + +#define TVG_COLOR1 0x104 +#define TVG_COL1_GREEN(x) ((x) << 12) +#define TVG_COL1_RED(x) (x) + +#define TVG_COLOR1_BIS 0x108 +#define TVG_COL1_BLUE(x) (x) + +#define TVG_COLOR2 0x10c +#define TVG_COL2_GREEN(x) ((x) << 12) +#define TVG_COL2_RED(x) (x) + +#define TVG_COLOR2_BIS 0x110 +#define TVG_COL2_BLUE(x) (x) + +#define TVG_STS 0x114 +#define TVG_STS_CTL 0x144 +#define TVG_STS_CLR 0x164 +#define TVG_STS_FLAG 0x184 +#define TVG_STS_RUNNING BIT(0) + +#define STS_CTL_EDGE(e) ((e) << 16) + +#define DPHY_LANES_MAP 0x198 +#define DAT_REMAP_CFG(b, l) ((l) << ((b) * 8)) + +#define DPI_IRQ_EN 0x1a0 +#define DPI_IRQ_CLR 0x1a4 +#define DPI_IRQ_STS 0x1a8 +#define PIXEL_BUF_OVERFLOW BIT(0) + +#define DPI_CFG 0x1ac +#define DPI_CFG_FIFO_DEPTH(x) ((x) >> 16) +#define DPI_CFG_FIFO_LEVEL(x) ((x) & GENMASK(15, 0)) + +#define TEST_GENERIC 0x1f0 +#define TEST_STATUS(x) ((x) >> 16) +#define TEST_CTRL(x) (x) + +#define ID_REG 0x1fc +#define REV_VENDOR_ID(x) (((x) & GENMASK(31, 20)) >> 20) +#define REV_PRODUCT_ID(x) (((x) & GENMASK(19, 12)) >> 12) +#define REV_HW(x) (((x) & GENMASK(11, 8)) >> 8) +#define REV_MAJOR(x) (((x) & GENMASK(7, 4)) >> 4) +#define REV_MINOR(x) ((x) & GENMASK(3, 0)) + +#define DSI_OUTPUT_PORT 0 +#define DSI_INPUT_PORT(inputid) (1 + (inputid)) + +#define DSI_HBP_FRAME_OVERHEAD 12 +#define DSI_HSA_FRAME_OVERHEAD 14 +#define DSI_HFP_FRAME_OVERHEAD 6 +#define DSI_HSS_VSS_VSE_FRAME_OVERHEAD 4 +#define DSI_BLANKING_FRAME_OVERHEAD 6 +#define DSI_NULL_FRAME_OVERHEAD 6 +#define DSI_EOT_PKT_SIZE 4 + +#define REG_WAKEUP_TIME_NS 800 +#define DPHY_PLL_RATE_HZ 108000000 + +/* DPHY registers */ +#define DPHY_PMA_CMN(reg) (reg) +#define DPHY_PMA_LCLK(reg) (0x100 + (reg)) +#define DPHY_PMA_LDATA(lane, reg) (0x200 + ((lane) * 0x100) + (reg)) +#define DPHY_PMA_RCLK(reg) (0x600 + (reg)) +#define DPHY_PMA_RDATA(lane, reg) (0x700 + ((lane) * 0x100) + (reg)) +#define DPHY_PCS(reg) (0xb00 + (reg)) + +#define DPHY_CMN_SSM DPHY_PMA_CMN(0x20) +#define DPHY_CMN_SSM_EN BIT(0) +#define DPHY_CMN_TX_MODE_EN BIT(9) + +#define DPHY_CMN_PWM DPHY_PMA_CMN(0x40) +#define DPHY_CMN_PWM_DIV(x) ((x) << 20) +#define DPHY_CMN_PWM_LOW(x) ((x) << 10) +#define DPHY_CMN_PWM_HIGH(x) (x) + +#define DPHY_CMN_FBDIV DPHY_PMA_CMN(0x4c) +#define DPHY_CMN_FBDIV_VAL(low, high) (((high) << 11) | ((low) << 22)) +#define DPHY_CMN_FBDIV_FROM_REG (BIT(10) | BIT(21)) + +#define DPHY_CMN_OPIPDIV DPHY_PMA_CMN(0x50) +#define DPHY_CMN_IPDIV_FROM_REG BIT(0) +#define DPHY_CMN_IPDIV(x) ((x) << 1) +#define DPHY_CMN_OPDIV_FROM_REG BIT(6) +#define DPHY_CMN_OPDIV(x) ((x) << 7) + +#define DPHY_PSM_CFG DPHY_PCS(0x4) +#define DPHY_PSM_CFG_FROM_REG BIT(0) +#define DPHY_PSM_CLK_DIV(x) ((x) << 1) + +struct cdns_dsi_output { + struct mipi_dsi_device *dev; + struct drm_panel *panel; + struct drm_bridge *bridge; +}; + +enum cdns_dsi_input_id { + CDNS_SDI_INPUT, + CDNS_DPI_INPUT, + CDNS_DSC_INPUT, +}; + +struct cdns_dphy_cfg { + u8 pll_ipdiv; + u8 pll_opdiv; + u16 pll_fbdiv; + unsigned long lane_bps; + unsigned int nlanes; +}; + +struct cdns_dsi_cfg { + unsigned int hfp; + unsigned int hsa; + unsigned int hbp; + unsigned int hact; + unsigned int htotal; +}; + +struct cdns_dphy; + +enum cdns_dphy_clk_lane_cfg { + DPHY_CLK_CFG_LEFT_DRIVES_ALL = 0, + DPHY_CLK_CFG_LEFT_DRIVES_RIGHT = 1, + DPHY_CLK_CFG_LEFT_DRIVES_LEFT = 2, + DPHY_CLK_CFG_RIGHT_DRIVES_ALL = 3, +}; + +struct cdns_dphy_ops { + int (*probe)(struct cdns_dphy *dphy); + void (*remove)(struct cdns_dphy *dphy); + void (*set_psm_div)(struct cdns_dphy *dphy, u8 div); + void (*set_clk_lane_cfg)(struct cdns_dphy *dphy, + enum cdns_dphy_clk_lane_cfg cfg); + void (*set_pll_cfg)(struct cdns_dphy *dphy, + const struct cdns_dphy_cfg *cfg); + unsigned long (*get_wakeup_time_ns)(struct cdns_dphy *dphy); +}; + +struct cdns_dphy { + struct cdns_dphy_cfg cfg; + void __iomem *regs; + struct clk *psm_clk; + struct clk *pll_ref_clk; + const struct cdns_dphy_ops *ops; +}; + +struct cdns_dsi_input { + enum cdns_dsi_input_id id; + struct drm_bridge bridge; +}; + +struct cdns_dsi { + struct mipi_dsi_host base; + void __iomem *regs; + struct cdns_dsi_input input; + struct cdns_dsi_output output; + unsigned int direct_cmd_fifo_depth; + unsigned int rx_fifo_depth; + struct completion direct_cmd_comp; + struct clk *dsi_p_clk; + struct reset_control *dsi_p_rst; + struct clk *dsi_sys_clk; + bool link_initialized; + struct cdns_dphy *dphy; +}; + +static inline struct cdns_dsi *input_to_dsi(struct cdns_dsi_input *input) +{ + return container_of(input, struct cdns_dsi, input); +} + +static inline struct cdns_dsi *to_cdns_dsi(struct mipi_dsi_host *host) +{ + return container_of(host, struct cdns_dsi, base); +} + +static inline struct cdns_dsi_input * +bridge_to_cdns_dsi_input(struct drm_bridge *bridge) +{ + return container_of(bridge, struct cdns_dsi_input, bridge); +} + +static int cdns_dsi_get_dphy_pll_cfg(struct cdns_dphy *dphy, + struct cdns_dphy_cfg *cfg, + unsigned int dpi_htotal, + unsigned int dpi_bpp, + unsigned int dpi_hz, + unsigned int dsi_htotal, + unsigned int dsi_nlanes, + unsigned int *dsi_hfp_ext) +{ + u64 dlane_bps, dlane_bps_max, fbdiv, fbdiv_max, adj_dsi_htotal; + unsigned long pll_ref_hz = clk_get_rate(dphy->pll_ref_clk); + + memset(cfg, 0, sizeof(*cfg)); + + cfg->nlanes = dsi_nlanes; + + if (pll_ref_hz < 9600000 || pll_ref_hz >= 150000000) + return -EINVAL; + else if (pll_ref_hz < 19200000) + cfg->pll_ipdiv = 1; + else if (pll_ref_hz < 38400000) + cfg->pll_ipdiv = 2; + else if (pll_ref_hz < 76800000) + cfg->pll_ipdiv = 4; + else + cfg->pll_ipdiv = 8; + + /* + * Make sure DSI htotal is aligned on a lane boundary when calculating + * the expected data rate. This is done by extending HFP in case of + * misalignment. + */ + adj_dsi_htotal = dsi_htotal; + if (dsi_htotal % dsi_nlanes) + adj_dsi_htotal += dsi_nlanes - (dsi_htotal % dsi_nlanes); + + dlane_bps = (u64)dpi_hz * adj_dsi_htotal; + + /* data rate in bytes/sec is not an integer, refuse the mode. */ + if (do_div(dlane_bps, dsi_nlanes * dpi_htotal)) + return -EINVAL; + + /* data rate was in bytes/sec, convert to bits/sec. */ + dlane_bps *= 8; + + if (dlane_bps > 2500000000UL || dlane_bps < 160000000UL) + return -EINVAL; + else if (dlane_bps >= 1250000000) + cfg->pll_opdiv = 1; + else if (dlane_bps >= 630000000) + cfg->pll_opdiv = 2; + else if (dlane_bps >= 320000000) + cfg->pll_opdiv = 4; + else if (dlane_bps >= 160000000) + cfg->pll_opdiv = 8; + + /* + * Allow a deviation of 0.2% on the per-lane data rate to try to + * recover a potential mismatch between DPI and PPI clks. + */ + dlane_bps_max = dlane_bps + DIV_ROUND_DOWN_ULL(dlane_bps, 500); + fbdiv_max = DIV_ROUND_DOWN_ULL(dlane_bps_max * 2 * + cfg->pll_opdiv * cfg->pll_ipdiv, + pll_ref_hz); + fbdiv = DIV_ROUND_UP_ULL(dlane_bps * 2 * cfg->pll_opdiv * + cfg->pll_ipdiv, + pll_ref_hz); + + /* + * Iterate over all acceptable fbdiv and try to find an adjusted DSI + * htotal length providing an exact match. + * + * Note that we could do something even trickier by relying on the fact + * that a new line is not necessarily aligned on a lane boundary, so, + * by making adj_dsi_htotal non aligned on a dsi_lanes we can improve a + * bit the precision. With this, the step would be + * + * pll_ref_hz / (2 * opdiv * ipdiv * nlanes) + * + * instead of + * + * pll_ref_hz / (2 * opdiv * ipdiv) + * + * The drawback of this approach is that we would need to make sure the + * number or lines is a multiple of the realignment periodicity which is + * a function of the number of lanes and the original misalignment. For + * example, for NLANES = 4 and HTOTAL % NLANES = 3, it takes 4 lines + * to realign on a lane: + * LINE 0: expected number of bytes, starts emitting first byte of + * LINE 1 on LANE 3 + * LINE 1: expected number of bytes, starts emitting first 2 bytes of + * LINE 2 on LANES 2 and 3 + * LINE 2: expected number of bytes, starts emitting first 3 bytes of + * of LINE 3 on LANES 1, 2 and 3 + * LINE 3: one byte less, now things are realigned on LANE 0 for LINE 4 + * + * I figured this extra complexity was not worth the benefit, but if + * someone really has unfixable mismatch, that would be something to + * investigate. + */ + for (; fbdiv <= fbdiv_max; fbdiv++) { + u32 rem; + + adj_dsi_htotal = (u64)fbdiv * pll_ref_hz * dsi_nlanes * + dpi_htotal; + + /* + * Do the division in 2 steps to avoid an overflow on the + * divider. + */ + rem = do_div(adj_dsi_htotal, dpi_hz); + if (rem) + continue; + + rem = do_div(adj_dsi_htotal, + cfg->pll_opdiv * cfg->pll_ipdiv * 2 * 8); + if (rem) + continue; + + cfg->pll_fbdiv = fbdiv; + *dsi_hfp_ext = adj_dsi_htotal - dsi_htotal; + break; + } + + /* No match, let's just reject the display mode. */ + if (!cfg->pll_fbdiv) + return -EINVAL; + + dlane_bps = DIV_ROUND_DOWN_ULL((u64)dpi_hz * adj_dsi_htotal * 8, + dsi_nlanes * dpi_htotal); + cfg->lane_bps = dlane_bps; + + return 0; +} + +static int cdns_dphy_setup_psm(struct cdns_dphy *dphy) +{ + unsigned long psm_clk_hz = clk_get_rate(dphy->psm_clk); + unsigned long psm_div; + + if (!psm_clk_hz || psm_clk_hz > 100000000) + return -EINVAL; + + psm_div = DIV_ROUND_CLOSEST(psm_clk_hz, 1000000); + if (dphy->ops->set_psm_div) + dphy->ops->set_psm_div(dphy, psm_div); + + return 0; +} + +static void cdns_dphy_set_clk_lane_cfg(struct cdns_dphy *dphy, + enum cdns_dphy_clk_lane_cfg cfg) +{ + if (dphy->ops->set_clk_lane_cfg) + dphy->ops->set_clk_lane_cfg(dphy, cfg); +} + +static void cdns_dphy_set_pll_cfg(struct cdns_dphy *dphy, + const struct cdns_dphy_cfg *cfg) +{ + if (dphy->ops->set_pll_cfg) + dphy->ops->set_pll_cfg(dphy, cfg); +} + +static unsigned long cdns_dphy_get_wakeup_time_ns(struct cdns_dphy *dphy) +{ + return dphy->ops->get_wakeup_time_ns(dphy); +} + +static unsigned int dpi_to_dsi_timing(unsigned int dpi_timing, + unsigned int dpi_bpp, + unsigned int dsi_pkt_overhead) +{ + unsigned int dsi_timing = DIV_ROUND_UP(dpi_timing * dpi_bpp, 8); + + if (dsi_timing < dsi_pkt_overhead) + dsi_timing = 0; + else + dsi_timing -= dsi_pkt_overhead; + + return dsi_timing; +} + +static int cdns_dsi_mode2cfg(struct cdns_dsi *dsi, + const struct drm_display_mode *mode, + struct cdns_dsi_cfg *dsi_cfg, + struct cdns_dphy_cfg *dphy_cfg, + bool mode_valid_check) +{ + unsigned long dsi_htotal = 0, dsi_hss_hsa_hse_hbp = 0; + struct cdns_dsi_output *output = &dsi->output; + unsigned int dsi_hfp_ext = 0, dpi_hfp, tmp; + bool sync_pulse = false; + int bpp, nlanes, ret; + + memset(dsi_cfg, 0, sizeof(*dsi_cfg)); + + if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) + sync_pulse = true; + + bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format); + nlanes = output->dev->lanes; + + if (mode_valid_check) + tmp = mode->htotal - + (sync_pulse ? mode->hsync_end : mode->hsync_start); + else + tmp = mode->crtc_htotal - + (sync_pulse ? + mode->crtc_hsync_end : mode->crtc_hsync_start); + + dsi_cfg->hbp = dpi_to_dsi_timing(tmp, bpp, DSI_HBP_FRAME_OVERHEAD); + dsi_htotal += dsi_cfg->hbp + DSI_HBP_FRAME_OVERHEAD; + dsi_hss_hsa_hse_hbp += dsi_cfg->hbp + DSI_HBP_FRAME_OVERHEAD; + + if (sync_pulse) { + if (mode_valid_check) + tmp = mode->hsync_end - mode->hsync_start; + else + tmp = mode->crtc_hsync_end - mode->crtc_hsync_start; + + dsi_cfg->hsa = dpi_to_dsi_timing(tmp, bpp, + DSI_HSA_FRAME_OVERHEAD); + dsi_htotal += dsi_cfg->hsa + DSI_HSA_FRAME_OVERHEAD; + dsi_hss_hsa_hse_hbp += dsi_cfg->hsa + DSI_HSA_FRAME_OVERHEAD; + } + + dsi_cfg->hact = dpi_to_dsi_timing(mode_valid_check ? + mode->hdisplay : mode->crtc_hdisplay, + bpp, 0); + dsi_htotal += dsi_cfg->hact; + + if (mode_valid_check) + dpi_hfp = mode->hsync_start - mode->hdisplay; + else + dpi_hfp = mode->crtc_hsync_start - mode->crtc_hdisplay; + + dsi_cfg->hfp = dpi_to_dsi_timing(dpi_hfp, bpp, DSI_HFP_FRAME_OVERHEAD); + dsi_htotal += dsi_cfg->hfp + DSI_HFP_FRAME_OVERHEAD; + + if (mode_valid_check) + ret = cdns_dsi_get_dphy_pll_cfg(dsi->dphy, dphy_cfg, + mode->htotal, bpp, + mode->clock * 1000, + dsi_htotal, nlanes, + &dsi_hfp_ext); + else + ret = cdns_dsi_get_dphy_pll_cfg(dsi->dphy, dphy_cfg, + mode->crtc_htotal, bpp, + mode->crtc_clock * 1000, + dsi_htotal, nlanes, + &dsi_hfp_ext); + + if (ret) + return ret; + + dsi_cfg->hfp += dsi_hfp_ext; + dsi_htotal += dsi_hfp_ext; + dsi_cfg->htotal = dsi_htotal; + + /* + * Make sure DPI(HFP) > DSI(HSS+HSA+HSE+HBP) to guarantee that the FIFO + * is empty before we start a receiving a new line on the DPI + * interface. + */ + if ((u64)dphy_cfg->lane_bps * dpi_hfp * nlanes < + (u64)dsi_hss_hsa_hse_hbp * + (mode_valid_check ? mode->clock : mode->crtc_clock) * 1000) + return -EINVAL; + + return 0; +} + +static int cdns_dsi_bridge_attach(struct drm_bridge *bridge) +{ + struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge); + struct cdns_dsi *dsi = input_to_dsi(input); + struct cdns_dsi_output *output = &dsi->output; + + if (!drm_core_check_feature(bridge->dev, DRIVER_ATOMIC)) { + dev_err(dsi->base.dev, + "cdns-dsi driver is only compatible with DRM devices supporting atomic updates"); + return -ENOTSUPP; + } + + return drm_bridge_attach(bridge->encoder, output->bridge, bridge); +} + +static enum drm_mode_status +cdns_dsi_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_mode *mode) +{ + struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge); + struct cdns_dsi *dsi = input_to_dsi(input); + struct cdns_dsi_output *output = &dsi->output; + struct cdns_dphy_cfg dphy_cfg; + struct cdns_dsi_cfg dsi_cfg; + int bpp, nlanes, ret; + + /* + * VFP_DSI should be less than VFP_DPI and VFP_DSI should be at + * least 1. + */ + if (mode->vtotal - mode->vsync_end < 2) + return MODE_V_ILLEGAL; + + /* VSA_DSI = VSA_DPI and must be at least 2. */ + if (mode->vsync_end - mode->vsync_start < 2) + return MODE_V_ILLEGAL; + + /* HACT must be 32-bits aligned. */ + bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format); + if ((mode->hdisplay * bpp) % 32) + return MODE_H_ILLEGAL; + + nlanes = output->dev->lanes; + + ret = cdns_dsi_mode2cfg(dsi, mode, &dsi_cfg, &dphy_cfg, true); + if (ret) + return MODE_CLOCK_RANGE; + + return MODE_OK; +} + +static void cdns_dsi_bridge_disable(struct drm_bridge *bridge) +{ + struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge); + struct cdns_dsi *dsi = input_to_dsi(input); + u32 val; + + val = readl(dsi->regs + MCTL_MAIN_DATA_CTL); + val &= ~(IF_VID_SELECT_MASK | IF_VID_MODE | VID_EN | HOST_EOT_GEN | + DISP_EOT_GEN); + writel(val, dsi->regs + MCTL_MAIN_DATA_CTL); + + val = readl(dsi->regs + MCTL_MAIN_EN) & ~IF_EN(input->id); + writel(val, dsi->regs + MCTL_MAIN_EN); + pm_runtime_put(dsi->base.dev); +} + +static void cdns_dsi_hs_init(struct cdns_dsi *dsi, + const struct cdns_dphy_cfg *dphy_cfg) +{ + u32 status; + + /* + * Power all internal DPHY blocks down and maintain their reset line + * asserted before changing the DPHY config. + */ + writel(DPHY_CMN_PSO | DPHY_PLL_PSO | DPHY_ALL_D_PDN | DPHY_C_PDN | + DPHY_CMN_PDN | DPHY_PLL_PDN, + dsi->regs + MCTL_DPHY_CFG0); + + /* + * Configure the internal PSM clk divider so that the DPHY has a + * 1MHz clk (or something close). + */ + WARN_ON_ONCE(cdns_dphy_setup_psm(dsi->dphy)); + + /* + * Configure attach clk lanes to data lanes: the DPHY has 2 clk lanes + * and 8 data lanes, each clk lane can be attache different set of + * data lanes. The 2 groups are named 'left' and 'right', so here we + * just say that we want the 'left' clk lane to drive the 'left' data + * lanes. + */ + cdns_dphy_set_clk_lane_cfg(dsi->dphy, DPHY_CLK_CFG_LEFT_DRIVES_LEFT); + + /* + * Configure the DPHY PLL that will be used to generate the TX byte + * clk. + */ + cdns_dphy_set_pll_cfg(dsi->dphy, dphy_cfg); + + /* Start TX state machine. */ + writel(DPHY_CMN_SSM_EN | DPHY_CMN_TX_MODE_EN, + dsi->dphy->regs + DPHY_CMN_SSM); + + /* Activate the PLL and wait until it's locked. */ + writel(PLL_LOCKED, dsi->regs + MCTL_MAIN_STS_CLR); + writel(DPHY_CMN_PSO | DPHY_ALL_D_PDN | DPHY_C_PDN | DPHY_CMN_PDN, + dsi->regs + MCTL_DPHY_CFG0); + WARN_ON_ONCE(readl_poll_timeout(dsi->regs + MCTL_MAIN_STS, status, + status & PLL_LOCKED, 100, 100)); + /* De-assert data and clock reset lines. */ + writel(DPHY_CMN_PSO | DPHY_ALL_D_PDN | DPHY_C_PDN | DPHY_CMN_PDN | + DPHY_D_RSTB(dphy_cfg->nlanes) | DPHY_C_RSTB, + dsi->regs + MCTL_DPHY_CFG0); +} + +static void cdns_dsi_init_link(struct cdns_dsi *dsi) +{ + struct cdns_dsi_output *output = &dsi->output; + unsigned long sysclk_period, ulpout; + u32 val; + int i; + + if (dsi->link_initialized) + return; + + val = 0; + for (i = 1; i < output->dev->lanes; i++) + val |= DATA_LANE_EN(i); + + if (!(output->dev->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS)) + val |= CLK_CONTINUOUS; + + writel(val, dsi->regs + MCTL_MAIN_PHY_CTL); + + /* ULPOUT should be set to 1ms and is expressed in sysclk cycles. */ + sysclk_period = NSEC_PER_SEC / clk_get_rate(dsi->dsi_sys_clk); + ulpout = DIV_ROUND_UP(NSEC_PER_MSEC, sysclk_period); + writel(CLK_LANE_ULPOUT_TIME(ulpout) | DATA_LANE_ULPOUT_TIME(ulpout), + dsi->regs + MCTL_ULPOUT_TIME); + + writel(LINK_EN, dsi->regs + MCTL_MAIN_DATA_CTL); + + val = CLK_LANE_EN | PLL_START; + for (i = 0; i < output->dev->lanes; i++) + val |= DATA_LANE_START(i); + + writel(val, dsi->regs + MCTL_MAIN_EN); + + dsi->link_initialized = true; +} + +static void cdns_dsi_bridge_enable(struct drm_bridge *bridge) +{ + struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge); + struct cdns_dsi *dsi = input_to_dsi(input); + struct cdns_dsi_output *output = &dsi->output; + struct drm_display_mode *mode; + struct cdns_dphy_cfg dphy_cfg; + unsigned long tx_byte_period; + struct cdns_dsi_cfg dsi_cfg; + u32 tmp, reg_wakeup, div; + int bpp, nlanes; + + if (WARN_ON(pm_runtime_get_sync(dsi->base.dev) < 0)) + return; + + mode = &bridge->encoder->crtc->state->adjusted_mode; + bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format); + nlanes = output->dev->lanes; + + WARN_ON_ONCE(cdns_dsi_mode2cfg(dsi, mode, &dsi_cfg, &dphy_cfg, false)); + + cdns_dsi_hs_init(dsi, &dphy_cfg); + cdns_dsi_init_link(dsi); + + writel(HBP_LEN(dsi_cfg.hbp) | HSA_LEN(dsi_cfg.hsa), + dsi->regs + VID_HSIZE1); + writel(HFP_LEN(dsi_cfg.hfp) | HACT_LEN(dsi_cfg.hact), + dsi->regs + VID_HSIZE2); + + writel(VBP_LEN(mode->crtc_vtotal - mode->crtc_vsync_end - 1) | + VFP_LEN(mode->crtc_vsync_start - mode->crtc_vdisplay) | + VSA_LEN(mode->crtc_vsync_end - mode->crtc_vsync_start + 1), + dsi->regs + VID_VSIZE1); + writel(mode->crtc_vdisplay, dsi->regs + VID_VSIZE2); + + tmp = dsi_cfg.htotal - + (dsi_cfg.hsa + DSI_BLANKING_FRAME_OVERHEAD + + DSI_HSA_FRAME_OVERHEAD); + writel(BLK_LINE_PULSE_PKT_LEN(tmp), dsi->regs + VID_BLKSIZE2); + if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) + writel(MAX_LINE_LIMIT(tmp - DSI_NULL_FRAME_OVERHEAD), + dsi->regs + VID_VCA_SETTING2); + + tmp = dsi_cfg.htotal - + (DSI_HSS_VSS_VSE_FRAME_OVERHEAD + DSI_BLANKING_FRAME_OVERHEAD); + writel(BLK_LINE_EVENT_PKT_LEN(tmp), dsi->regs + VID_BLKSIZE1); + if (!(output->dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE)) + writel(MAX_LINE_LIMIT(tmp - DSI_NULL_FRAME_OVERHEAD), + dsi->regs + VID_VCA_SETTING2); + + tmp = DIV_ROUND_UP(dsi_cfg.htotal, nlanes) - + DIV_ROUND_UP(dsi_cfg.hsa, nlanes); + + if (!(output->dev->mode_flags & MIPI_DSI_MODE_EOT_PACKET)) + tmp -= DIV_ROUND_UP(DSI_EOT_PKT_SIZE, nlanes); + + tx_byte_period = DIV_ROUND_DOWN_ULL((u64)NSEC_PER_SEC * 8, + dphy_cfg.lane_bps); + reg_wakeup = cdns_dphy_get_wakeup_time_ns(dsi->dphy) / + tx_byte_period; + writel(REG_WAKEUP_TIME(reg_wakeup) | REG_LINE_DURATION(tmp), + dsi->regs + VID_DPHY_TIME); + + /* + * HSTX and LPRX timeouts are both expressed in TX byte clk cycles and + * both should be set to at least the time it takes to transmit a + * frame. + */ + tmp = NSEC_PER_SEC / drm_mode_vrefresh(mode); + tmp /= tx_byte_period; + + for (div = 0; div <= CLK_DIV_MAX; div++) { + if (tmp <= HSTX_TIMEOUT_MAX) + break; + + tmp >>= 1; + } + + if (tmp > HSTX_TIMEOUT_MAX) + tmp = HSTX_TIMEOUT_MAX; + + writel(CLK_DIV(div) | HSTX_TIMEOUT(tmp), + dsi->regs + MCTL_DPHY_TIMEOUT1); + + writel(LPRX_TIMEOUT(tmp), dsi->regs + MCTL_DPHY_TIMEOUT2); + + if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO) { + switch (output->dev->format) { + case MIPI_DSI_FMT_RGB888: + tmp = VID_PIXEL_MODE_RGB888 | + VID_DATATYPE(MIPI_DSI_PACKED_PIXEL_STREAM_24); + break; + + case MIPI_DSI_FMT_RGB666: + tmp = VID_PIXEL_MODE_RGB666 | + VID_DATATYPE(MIPI_DSI_PIXEL_STREAM_3BYTE_18); + break; + + case MIPI_DSI_FMT_RGB666_PACKED: + tmp = VID_PIXEL_MODE_RGB666_PACKED | + VID_DATATYPE(MIPI_DSI_PACKED_PIXEL_STREAM_18); + break; + + case MIPI_DSI_FMT_RGB565: + tmp = VID_PIXEL_MODE_RGB565 | + VID_DATATYPE(MIPI_DSI_PACKED_PIXEL_STREAM_16); + break; + + default: + dev_err(dsi->base.dev, "Unsupported DSI format\n"); + return; + } + + if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) + tmp |= SYNC_PULSE_ACTIVE | SYNC_PULSE_HORIZONTAL; + + tmp |= REG_BLKLINE_MODE(REG_BLK_MODE_BLANKING_PKT) | + REG_BLKEOL_MODE(REG_BLK_MODE_BLANKING_PKT) | + RECOVERY_MODE(RECOVERY_MODE_NEXT_HSYNC) | + VID_IGNORE_MISS_VSYNC; + + writel(tmp, dsi->regs + VID_MAIN_CTL); + } + + tmp = readl(dsi->regs + MCTL_MAIN_DATA_CTL); + tmp &= ~(IF_VID_SELECT_MASK | HOST_EOT_GEN | IF_VID_MODE); + + if (!(output->dev->mode_flags & MIPI_DSI_MODE_EOT_PACKET)) + tmp |= HOST_EOT_GEN; + + if (output->dev->mode_flags & MIPI_DSI_MODE_VIDEO) + tmp |= IF_VID_MODE | IF_VID_SELECT(input->id) | VID_EN; + + writel(tmp, dsi->regs + MCTL_MAIN_DATA_CTL); + + tmp = readl(dsi->regs + MCTL_MAIN_EN) | IF_EN(input->id); + writel(tmp, dsi->regs + MCTL_MAIN_EN); +} + +static const struct drm_bridge_funcs cdns_dsi_bridge_funcs = { + .attach = cdns_dsi_bridge_attach, + .mode_valid = cdns_dsi_bridge_mode_valid, + .disable = cdns_dsi_bridge_disable, + .enable = cdns_dsi_bridge_enable, +}; + +static int cdns_dsi_attach(struct mipi_dsi_host *host, + struct mipi_dsi_device *dev) +{ + struct cdns_dsi *dsi = to_cdns_dsi(host); + struct cdns_dsi_output *output = &dsi->output; + struct cdns_dsi_input *input = &dsi->input; + struct drm_bridge *bridge; + struct drm_panel *panel; + struct device_node *np; + int ret; + + /* + * We currently do not support connecting several DSI devices to the + * same host. In order to support that we'd need the DRM bridge + * framework to allow dynamic reconfiguration of the bridge chain. + */ + if (output->dev) + return -EBUSY; + + /* We do not support burst mode yet. */ + if (dev->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) + return -ENOTSUPP; + + /* + * The host <-> device link might be described using an OF-graph + * representation, in this case we extract the device of_node from + * this representation, otherwise we use dsidev->dev.of_node which + * should have been filled by the core. + */ + np = of_graph_get_remote_node(dsi->base.dev->of_node, DSI_OUTPUT_PORT, + dev->channel); + if (!np) + np = of_node_get(dev->dev.of_node); + + panel = of_drm_find_panel(np); + if (panel) { + bridge = drm_panel_bridge_add(panel, DRM_MODE_CONNECTOR_DSI); + } else { + bridge = of_drm_find_bridge(dev->dev.of_node); + if (!bridge) + bridge = ERR_PTR(-EINVAL); + } + + of_node_put(np); + + if (IS_ERR(bridge)) { + ret = PTR_ERR(bridge); + dev_err(host->dev, "failed to add DSI device %s (err = %d)", + dev->name, ret); + return ret; + } + + output->dev = dev; + output->bridge = bridge; + output->panel = panel; + + /* + * The DSI output has been properly configured, we can now safely + * register the input to the bridge framework so that it can take place + * in a display pipeline. + */ + drm_bridge_add(&input->bridge); + + return 0; +} + +static int cdns_dsi_detach(struct mipi_dsi_host *host, + struct mipi_dsi_device *dev) +{ + struct cdns_dsi *dsi = to_cdns_dsi(host); + struct cdns_dsi_output *output = &dsi->output; + struct cdns_dsi_input *input = &dsi->input; + + drm_bridge_remove(&input->bridge); + if (output->panel) + drm_panel_bridge_remove(output->bridge); + + return 0; +} + +static irqreturn_t cdns_dsi_interrupt(int irq, void *data) +{ + struct cdns_dsi *dsi = data; + irqreturn_t ret = IRQ_NONE; + u32 flag, ctl; + + flag = readl(dsi->regs + DIRECT_CMD_STS_FLAG); + if (flag) { + ctl = readl(dsi->regs + DIRECT_CMD_STS_CTL); + ctl &= ~flag; + writel(ctl, dsi->regs + DIRECT_CMD_STS_CTL); + complete(&dsi->direct_cmd_comp); + ret = IRQ_HANDLED; + } + + return ret; +} + +static ssize_t cdns_dsi_transfer(struct mipi_dsi_host *host, + const struct mipi_dsi_msg *msg) +{ + struct cdns_dsi *dsi = to_cdns_dsi(host); + u32 cmd, sts, val, wait = WRITE_COMPLETED, ctl = 0; + struct mipi_dsi_packet packet; + int ret, i, tx_len, rx_len; + + ret = pm_runtime_get_sync(host->dev); + if (ret < 0) + return ret; + + cdns_dsi_init_link(dsi); + + ret = mipi_dsi_create_packet(&packet, msg); + if (ret) + goto out; + + tx_len = msg->tx_buf ? msg->tx_len : 0; + rx_len = msg->rx_buf ? msg->rx_len : 0; + + /* For read operations, the maximum TX len is 2. */ + if (rx_len && tx_len > 2) { + ret = -ENOTSUPP; + goto out; + } + + /* TX len is limited by the CMD FIFO depth. */ + if (tx_len > dsi->direct_cmd_fifo_depth) { + ret = -ENOTSUPP; + goto out; + } + + /* RX len is limited by the RX FIFO depth. */ + if (rx_len > dsi->rx_fifo_depth) { + ret = -ENOTSUPP; + goto out; + } + + cmd = CMD_SIZE(tx_len) | CMD_VCHAN_ID(msg->channel) | + CMD_DATATYPE(msg->type); + + if (msg->flags & MIPI_DSI_MSG_USE_LPM) + cmd |= CMD_LP_EN; + + if (mipi_dsi_packet_format_is_long(msg->type)) + cmd |= CMD_LONG; + + if (rx_len) { + cmd |= READ_CMD; + wait = READ_COMPLETED_WITH_ERR | READ_COMPLETED; + ctl = READ_EN | BTA_EN; + } else if (msg->flags & MIPI_DSI_MSG_REQ_ACK) { + cmd |= BTA_REQ; + wait = ACK_WITH_ERR_RCVD | ACK_RCVD; + ctl = BTA_EN; + } + + writel(readl(dsi->regs + MCTL_MAIN_DATA_CTL) | ctl, + dsi->regs + MCTL_MAIN_DATA_CTL); + + writel(cmd, dsi->regs + DIRECT_CMD_MAIN_SETTINGS); + + for (i = 0; i < tx_len; i += 4) { + const u8 *buf = msg->tx_buf; + int j; + + val = 0; + for (j = 0; j < 4 && j + i < tx_len; j++) + val |= (u32)buf[i + j] << (8 * j); + + writel(val, dsi->regs + DIRECT_CMD_WRDATA); + } + + /* Clear status flags before sending the command. */ + writel(wait, dsi->regs + DIRECT_CMD_STS_CLR); + writel(wait, dsi->regs + DIRECT_CMD_STS_CTL); + reinit_completion(&dsi->direct_cmd_comp); + writel(0, dsi->regs + DIRECT_CMD_SEND); + + wait_for_completion_timeout(&dsi->direct_cmd_comp, + msecs_to_jiffies(1000)); + + sts = readl(dsi->regs + DIRECT_CMD_STS); + writel(wait, dsi->regs + DIRECT_CMD_STS_CLR); + writel(0, dsi->regs + DIRECT_CMD_STS_CTL); + + writel(readl(dsi->regs + MCTL_MAIN_DATA_CTL) & ~ctl, + dsi->regs + MCTL_MAIN_DATA_CTL); + + /* We did not receive the events we were waiting for. */ + if (!(sts & wait)) { + ret = -ETIMEDOUT; + goto out; + } + + /* 'READ' or 'WRITE with ACK' failed. */ + if (sts & (READ_COMPLETED_WITH_ERR | ACK_WITH_ERR_RCVD)) { + ret = -EIO; + goto out; + } + + for (i = 0; i < rx_len; i += 4) { + u8 *buf = msg->rx_buf; + int j; + + val = readl(dsi->regs + DIRECT_CMD_RDDATA); + for (j = 0; j < 4 && j + i < rx_len; j++) + buf[i + j] = val >> (8 * j); + } + +out: + pm_runtime_put(host->dev); + return ret; +} + +static const struct mipi_dsi_host_ops cdns_dsi_ops = { + .attach = cdns_dsi_attach, + .detach = cdns_dsi_detach, + .transfer = cdns_dsi_transfer, +}; + +static int cdns_dsi_resume(struct device *dev) +{ + struct cdns_dsi *dsi = dev_get_drvdata(dev); + + reset_control_deassert(dsi->dsi_p_rst); + clk_prepare_enable(dsi->dsi_p_clk); + clk_prepare_enable(dsi->dsi_sys_clk); + clk_prepare_enable(dsi->dphy->psm_clk); + clk_prepare_enable(dsi->dphy->pll_ref_clk); + + return 0; +} + +static int cdns_dsi_suspend(struct device *dev) +{ + struct cdns_dsi *dsi = dev_get_drvdata(dev); + + clk_disable_unprepare(dsi->dphy->pll_ref_clk); + clk_disable_unprepare(dsi->dphy->psm_clk); + clk_disable_unprepare(dsi->dsi_sys_clk); + clk_disable_unprepare(dsi->dsi_p_clk); + reset_control_assert(dsi->dsi_p_rst); + dsi->link_initialized = false; + return 0; +} + +static UNIVERSAL_DEV_PM_OPS(cdns_dsi_pm_ops, cdns_dsi_suspend, cdns_dsi_resume, + NULL); + +static unsigned long cdns_dphy_ref_get_wakeup_time_ns(struct cdns_dphy *dphy) +{ + /* Default wakeup time is 800 ns (in a simulated environment). */ + return 800; +} + +static void cdns_dphy_ref_set_pll_cfg(struct cdns_dphy *dphy, + const struct cdns_dphy_cfg *cfg) +{ + u32 fbdiv_low, fbdiv_high; + + fbdiv_low = (cfg->pll_fbdiv / 4) - 2; + fbdiv_high = cfg->pll_fbdiv - fbdiv_low - 2; + + writel(DPHY_CMN_IPDIV_FROM_REG | DPHY_CMN_OPDIV_FROM_REG | + DPHY_CMN_IPDIV(cfg->pll_ipdiv) | + DPHY_CMN_OPDIV(cfg->pll_opdiv), + dphy->regs + DPHY_CMN_OPIPDIV); + writel(DPHY_CMN_FBDIV_FROM_REG | + DPHY_CMN_FBDIV_VAL(fbdiv_low, fbdiv_high), + dphy->regs + DPHY_CMN_FBDIV); + writel(DPHY_CMN_PWM_HIGH(6) | DPHY_CMN_PWM_LOW(0x101) | + DPHY_CMN_PWM_DIV(0x8), + dphy->regs + DPHY_CMN_PWM); +} + +static void cdns_dphy_ref_set_psm_div(struct cdns_dphy *dphy, u8 div) +{ + writel(DPHY_PSM_CFG_FROM_REG | DPHY_PSM_CLK_DIV(div), + dphy->regs + DPHY_PSM_CFG); +} + +/* + * This is the reference implementation of DPHY hooks. Specific integration of + * this IP may have to re-implement some of them depending on how they decided + * to wire things in the SoC. + */ +static const struct cdns_dphy_ops ref_dphy_ops = { + .get_wakeup_time_ns = cdns_dphy_ref_get_wakeup_time_ns, + .set_pll_cfg = cdns_dphy_ref_set_pll_cfg, + .set_psm_div = cdns_dphy_ref_set_psm_div, +}; + +static const struct of_device_id cdns_dphy_of_match[] = { + { .compatible = "cdns,dphy", .data = &ref_dphy_ops }, + { /* sentinel */ }, +}; + +static struct cdns_dphy *cdns_dphy_probe(struct platform_device *pdev) +{ + const struct of_device_id *match; + struct cdns_dphy *dphy; + struct of_phandle_args args; + struct resource res; + int ret; + + ret = of_parse_phandle_with_args(pdev->dev.of_node, "phys", + "#phy-cells", 0, &args); + if (ret) + return ERR_PTR(-ENOENT); + + match = of_match_node(cdns_dphy_of_match, args.np); + if (!match || !match->data) + return ERR_PTR(-EINVAL); + + dphy = devm_kzalloc(&pdev->dev, sizeof(*dphy), GFP_KERNEL); + if (!dphy) + return ERR_PTR(-ENOMEM); + + dphy->ops = match->data; + + ret = of_address_to_resource(args.np, 0, &res); + if (ret) + return ERR_PTR(ret); + + dphy->regs = devm_ioremap_resource(&pdev->dev, &res); + if (IS_ERR(dphy->regs)) + return ERR_CAST(dphy->regs); + + dphy->psm_clk = of_clk_get_by_name(args.np, "psm"); + if (IS_ERR(dphy->psm_clk)) + return ERR_CAST(dphy->psm_clk); + + dphy->pll_ref_clk = of_clk_get_by_name(args.np, "pll_ref"); + if (IS_ERR(dphy->pll_ref_clk)) { + ret = PTR_ERR(dphy->pll_ref_clk); + goto err_put_psm_clk; + } + + if (dphy->ops->probe) { + ret = dphy->ops->probe(dphy); + if (ret) + goto err_put_pll_ref_clk; + } + + return dphy; + +err_put_pll_ref_clk: + clk_put(dphy->pll_ref_clk); + +err_put_psm_clk: + clk_put(dphy->psm_clk); + + return ERR_PTR(ret); +} + +static void cdns_dphy_remove(struct cdns_dphy *dphy) +{ + if (dphy->ops->remove) + dphy->ops->remove(dphy); + + clk_put(dphy->pll_ref_clk); + clk_put(dphy->psm_clk); +} + +static int cdns_dsi_drm_probe(struct platform_device *pdev) +{ + struct cdns_dsi *dsi; + struct cdns_dsi_input *input; + struct resource *res; + int ret, irq; + u32 val; + + dsi = devm_kzalloc(&pdev->dev, sizeof(*dsi), GFP_KERNEL); + if (!dsi) + return -ENOMEM; + + platform_set_drvdata(pdev, dsi); + + input = &dsi->input; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + dsi->regs = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(dsi->regs)) + return PTR_ERR(dsi->regs); + + dsi->dsi_p_clk = devm_clk_get(&pdev->dev, "dsi_p_clk"); + if (IS_ERR(dsi->dsi_p_clk)) + return PTR_ERR(dsi->dsi_p_clk); + + dsi->dsi_p_rst = devm_reset_control_get_optional_exclusive(&pdev->dev, + "dsi_p_rst"); + if (IS_ERR(dsi->dsi_p_rst)) + return PTR_ERR(dsi->dsi_p_rst); + + dsi->dsi_sys_clk = devm_clk_get(&pdev->dev, "dsi_sys_clk"); + if (IS_ERR(dsi->dsi_sys_clk)) + return PTR_ERR(dsi->dsi_sys_clk); + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + dsi->dphy = cdns_dphy_probe(pdev); + if (IS_ERR(dsi->dphy)) + return PTR_ERR(dsi->dphy); + + ret = clk_prepare_enable(dsi->dsi_p_clk); + if (ret) + goto err_remove_dphy; + + val = readl(dsi->regs + ID_REG); + if (REV_VENDOR_ID(val) != 0xcad) { + dev_err(&pdev->dev, "invalid vendor id\n"); + ret = -EINVAL; + goto err_disable_pclk; + } + + val = readl(dsi->regs + IP_CONF); + dsi->direct_cmd_fifo_depth = 1 << (DIRCMD_FIFO_DEPTH(val) + 2); + dsi->rx_fifo_depth = RX_FIFO_DEPTH(val); + init_completion(&dsi->direct_cmd_comp); + + writel(0, dsi->regs + MCTL_MAIN_DATA_CTL); + writel(0, dsi->regs + MCTL_MAIN_EN); + writel(0, dsi->regs + MCTL_MAIN_PHY_CTL); + + /* + * We only support the DPI input, so force input->id to + * CDNS_DPI_INPUT. + */ + input->id = CDNS_DPI_INPUT; + input->bridge.funcs = &cdns_dsi_bridge_funcs; + input->bridge.of_node = pdev->dev.of_node; + + /* Mask all interrupts before registering the IRQ handler. */ + writel(0, dsi->regs + MCTL_MAIN_STS_CTL); + writel(0, dsi->regs + MCTL_DPHY_ERR_CTL1); + writel(0, dsi->regs + CMD_MODE_STS_CTL); + writel(0, dsi->regs + DIRECT_CMD_STS_CTL); + writel(0, dsi->regs + DIRECT_CMD_RD_STS_CTL); + writel(0, dsi->regs + VID_MODE_STS_CTL); + writel(0, dsi->regs + TVG_STS_CTL); + writel(0, dsi->regs + DPI_IRQ_EN); + ret = devm_request_irq(&pdev->dev, irq, cdns_dsi_interrupt, 0, + dev_name(&pdev->dev), dsi); + if (ret) + goto err_disable_pclk; + + pm_runtime_enable(&pdev->dev); + dsi->base.dev = &pdev->dev; + dsi->base.ops = &cdns_dsi_ops; + + ret = mipi_dsi_host_register(&dsi->base); + if (ret) + goto err_disable_runtime_pm; + + clk_disable_unprepare(dsi->dsi_p_clk); + + return 0; + +err_disable_runtime_pm: + pm_runtime_disable(&pdev->dev); + +err_disable_pclk: + clk_disable_unprepare(dsi->dsi_p_clk); + +err_remove_dphy: + cdns_dphy_remove(dsi->dphy); + + return ret; +} + +static int cdns_dsi_drm_remove(struct platform_device *pdev) +{ + struct cdns_dsi *dsi = platform_get_drvdata(pdev); + + mipi_dsi_host_unregister(&dsi->base); + pm_runtime_disable(&pdev->dev); + cdns_dphy_remove(dsi->dphy); + + return 0; +} + +static const struct of_device_id cdns_dsi_of_match[] = { + { .compatible = "cdns,dsi" }, + { }, +}; + +static struct platform_driver cdns_dsi_platform_driver = { + .probe = cdns_dsi_drm_probe, + .remove = cdns_dsi_drm_remove, + .driver = { + .name = "cdns-dsi", + .of_match_table = cdns_dsi_of_match, + .pm = &cdns_dsi_pm_ops, + }, +}; +module_platform_driver(cdns_dsi_platform_driver); + +MODULE_AUTHOR("Boris Brezillon <boris.brezillon@bootlin.com>"); +MODULE_DESCRIPTION("Cadence DSI driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:cdns-dsi"); + diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c index 86789f8..7ab3604 100644 --- a/drivers/gpu/drm/bridge/sil-sii8620.c +++ b/drivers/gpu/drm/bridge/sil-sii8620.c @@ -17,6 +17,7 @@ #include <linux/clk.h> #include <linux/delay.h> +#include <linux/extcon.h> #include <linux/gpio/consumer.h> #include <linux/i2c.h> #include <linux/interrupt.h> @@ -25,6 +26,7 @@ #include <linux/list.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/of_graph.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> @@ -81,6 +83,10 @@ struct sii8620 { struct edid *edid; unsigned int gen2_write_burst:1; enum sii8620_mt_state mt_state; + struct extcon_dev *extcon; + struct notifier_block extcon_nb; + struct work_struct extcon_wq; + int cable_state; struct list_head mt_queue; struct { int r_size; @@ -2170,6 +2176,77 @@ static void sii8620_init_rcp_input_dev(struct sii8620 *ctx) ctx->rc_dev = rc_dev; } +static void sii8620_cable_out(struct sii8620 *ctx) +{ + disable_irq(to_i2c_client(ctx->dev)->irq); + sii8620_hw_off(ctx); +} + +static void sii8620_extcon_work(struct work_struct *work) +{ + struct sii8620 *ctx = + container_of(work, struct sii8620, extcon_wq); + int state = extcon_get_state(ctx->extcon, EXTCON_DISP_MHL); + + if (state == ctx->cable_state) + return; + + ctx->cable_state = state; + + if (state > 0) + sii8620_cable_in(ctx); + else + sii8620_cable_out(ctx); +} + +static int sii8620_extcon_notifier(struct notifier_block *self, + unsigned long event, void *ptr) +{ + struct sii8620 *ctx = + container_of(self, struct sii8620, extcon_nb); + + schedule_work(&ctx->extcon_wq); + + return NOTIFY_DONE; +} + +static int sii8620_extcon_init(struct sii8620 *ctx) +{ + struct extcon_dev *edev; + struct device_node *musb, *muic; + int ret; + + /* get micro-USB connector node */ + musb = of_graph_get_remote_node(ctx->dev->of_node, 1, -1); + /* next get micro-USB Interface Controller node */ + muic = of_get_next_parent(musb); + + if (!muic) { + dev_info(ctx->dev, "no extcon found, switching to 'always on' mode\n"); + return 0; + } + + edev = extcon_find_edev_by_node(muic); + of_node_put(muic); + if (IS_ERR(edev)) { + if (PTR_ERR(edev) == -EPROBE_DEFER) + return -EPROBE_DEFER; + dev_err(ctx->dev, "Invalid or missing extcon\n"); + return PTR_ERR(edev); + } + + ctx->extcon = edev; + ctx->extcon_nb.notifier_call = sii8620_extcon_notifier; + INIT_WORK(&ctx->extcon_wq, sii8620_extcon_work); + ret = extcon_register_notifier(edev, EXTCON_DISP_MHL, &ctx->extcon_nb); + if (ret) { + dev_err(ctx->dev, "failed to register notifier for MHL\n"); + return ret; + } + + return 0; +} + static inline struct sii8620 *bridge_to_sii8620(struct drm_bridge *bridge) { return container_of(bridge, struct sii8620, bridge); @@ -2302,13 +2379,20 @@ static int sii8620_probe(struct i2c_client *client, if (ret) return ret; + ret = sii8620_extcon_init(ctx); + if (ret < 0) { + dev_err(ctx->dev, "failed to initialize EXTCON\n"); + return ret; + } + i2c_set_clientdata(client, ctx); ctx->bridge.funcs = &sii8620_bridge_funcs; ctx->bridge.of_node = dev->of_node; drm_bridge_add(&ctx->bridge); - sii8620_cable_in(ctx); + if (!ctx->extcon) + sii8620_cable_in(ctx); return 0; } @@ -2317,8 +2401,15 @@ static int sii8620_remove(struct i2c_client *client) { struct sii8620 *ctx = i2c_get_clientdata(client); - disable_irq(to_i2c_client(ctx->dev)->irq); - sii8620_hw_off(ctx); + if (ctx->extcon) { + extcon_unregister_notifier(ctx->extcon, EXTCON_DISP_MHL, + &ctx->extcon_nb); + flush_work(&ctx->extcon_wq); + if (ctx->cable_state > 0) + sii8620_cable_out(ctx); + } else { + sii8620_cable_out(ctx); + } drm_bridge_remove(&ctx->bridge); return 0; diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c index 3b7e5c5..8f9c8a6 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c @@ -152,7 +152,6 @@ static struct platform_driver snd_dw_hdmi_driver = { .remove = snd_dw_hdmi_remove, .driver = { .name = DRIVER_NAME, - .owner = THIS_MODULE, }, }; module_platform_driver(snd_dw_hdmi_driver); diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c index 226171a..fd79996 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Copyright (c) 2016, Fuzhou Rockchip Electronics Co., Ltd * Copyright (C) STMicroelectronics SA 2017 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * * Modified by Philippe Cornu <philippe.cornu@st.com> * This generic Synopsys DesignWare MIPI DSI host driver is based on the * Rockchip version from rockchip/dw-mipi-dsi.c with phy & bridge APIs. @@ -775,20 +771,20 @@ static void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge, clk_prepare_enable(dsi->pclk); - ret = phy_ops->get_lane_mbps(priv_data, mode, dsi->mode_flags, + ret = phy_ops->get_lane_mbps(priv_data, adjusted_mode, dsi->mode_flags, dsi->lanes, dsi->format, &dsi->lane_mbps); if (ret) DRM_DEBUG_DRIVER("Phy get_lane_mbps() failed\n"); pm_runtime_get_sync(dsi->dev); dw_mipi_dsi_init(dsi); - dw_mipi_dsi_dpi_config(dsi, mode); + dw_mipi_dsi_dpi_config(dsi, adjusted_mode); dw_mipi_dsi_packet_handler_config(dsi); dw_mipi_dsi_video_mode_config(dsi); - dw_mipi_dsi_video_packet_config(dsi, mode); + dw_mipi_dsi_video_packet_config(dsi, adjusted_mode); dw_mipi_dsi_command_mode_config(dsi); - dw_mipi_dsi_line_timer_config(dsi, mode); - dw_mipi_dsi_vertical_timing_config(dsi, mode); + dw_mipi_dsi_line_timer_config(dsi, adjusted_mode); + dw_mipi_dsi_vertical_timing_config(dsi, adjusted_mode); dw_mipi_dsi_dphy_init(dsi); dw_mipi_dsi_dphy_timing_config(dsi); @@ -802,7 +798,7 @@ static void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge, dw_mipi_dsi_dphy_enable(dsi); - dw_mipi_dsi_wait_for_two_frames(mode); + dw_mipi_dsi_wait_for_two_frames(adjusted_mode); /* Switch to cmd mode for panel-bridge pre_enable & panel prepare */ dw_mipi_dsi_set_mode(dsi, 0); diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index 08ab7d6a..0fd9cf2 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -1102,7 +1102,7 @@ static bool tc_bridge_mode_fixup(struct drm_bridge *bridge, return true; } -static int tc_connector_mode_valid(struct drm_connector *connector, +static enum drm_mode_status tc_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { /* DPI interface clock limitation: upto 154 MHz */ diff --git a/drivers/gpu/drm/bridge/thc63lvd1024.c b/drivers/gpu/drm/bridge/thc63lvd1024.c new file mode 100644 index 0000000..c8b9edd --- /dev/null +++ b/drivers/gpu/drm/bridge/thc63lvd1024.c @@ -0,0 +1,206 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * THC63LVD1024 LVDS to parallel data DRM bridge driver. + * + * Copyright (C) 2018 Jacopo Mondi <jacopo+renesas@jmondi.org> + */ + +#include <drm/drmP.h> +#include <drm/drm_bridge.h> +#include <drm/drm_panel.h> + +#include <linux/gpio/consumer.h> +#include <linux/of_graph.h> +#include <linux/regulator/consumer.h> +#include <linux/slab.h> + +enum thc63_ports { + THC63_LVDS_IN0, + THC63_LVDS_IN1, + THC63_RGB_OUT0, + THC63_RGB_OUT1, +}; + +struct thc63_dev { + struct device *dev; + + struct regulator *vcc; + + struct gpio_desc *pdwn; + struct gpio_desc *oe; + + struct drm_bridge bridge; + struct drm_bridge *next; +}; + +static inline struct thc63_dev *to_thc63(struct drm_bridge *bridge) +{ + return container_of(bridge, struct thc63_dev, bridge); +} + +static int thc63_attach(struct drm_bridge *bridge) +{ + struct thc63_dev *thc63 = to_thc63(bridge); + + return drm_bridge_attach(bridge->encoder, thc63->next, bridge); +} + +static void thc63_enable(struct drm_bridge *bridge) +{ + struct thc63_dev *thc63 = to_thc63(bridge); + int ret; + + ret = regulator_enable(thc63->vcc); + if (ret) { + dev_err(thc63->dev, + "Failed to enable regulator \"vcc\": %d\n", ret); + return; + } + + gpiod_set_value(thc63->pdwn, 0); + gpiod_set_value(thc63->oe, 1); +} + +static void thc63_disable(struct drm_bridge *bridge) +{ + struct thc63_dev *thc63 = to_thc63(bridge); + int ret; + + gpiod_set_value(thc63->oe, 0); + gpiod_set_value(thc63->pdwn, 1); + + ret = regulator_disable(thc63->vcc); + if (ret) + dev_err(thc63->dev, + "Failed to disable regulator \"vcc\": %d\n", ret); +} + +static const struct drm_bridge_funcs thc63_bridge_func = { + .attach = thc63_attach, + .enable = thc63_enable, + .disable = thc63_disable, +}; + +static int thc63_parse_dt(struct thc63_dev *thc63) +{ + struct device_node *thc63_out; + struct device_node *remote; + + thc63_out = of_graph_get_endpoint_by_regs(thc63->dev->of_node, + THC63_RGB_OUT0, -1); + if (!thc63_out) { + dev_err(thc63->dev, "Missing endpoint in port@%u\n", + THC63_RGB_OUT0); + return -ENODEV; + } + + remote = of_graph_get_remote_port_parent(thc63_out); + of_node_put(thc63_out); + if (!remote) { + dev_err(thc63->dev, "Endpoint in port@%u unconnected\n", + THC63_RGB_OUT0); + return -ENODEV; + } + + if (!of_device_is_available(remote)) { + dev_err(thc63->dev, "port@%u remote endpoint is disabled\n", + THC63_RGB_OUT0); + of_node_put(remote); + return -ENODEV; + } + + thc63->next = of_drm_find_bridge(remote); + of_node_put(remote); + if (!thc63->next) + return -EPROBE_DEFER; + + return 0; +} + +static int thc63_gpio_init(struct thc63_dev *thc63) +{ + thc63->oe = devm_gpiod_get_optional(thc63->dev, "oe", GPIOD_OUT_LOW); + if (IS_ERR(thc63->oe)) { + dev_err(thc63->dev, "Unable to get \"oe-gpios\": %ld\n", + PTR_ERR(thc63->oe)); + return PTR_ERR(thc63->oe); + } + + thc63->pdwn = devm_gpiod_get_optional(thc63->dev, "powerdown", + GPIOD_OUT_HIGH); + if (IS_ERR(thc63->pdwn)) { + dev_err(thc63->dev, "Unable to get \"powerdown-gpios\": %ld\n", + PTR_ERR(thc63->pdwn)); + return PTR_ERR(thc63->pdwn); + } + + return 0; +} + +static int thc63_probe(struct platform_device *pdev) +{ + struct thc63_dev *thc63; + int ret; + + thc63 = devm_kzalloc(&pdev->dev, sizeof(*thc63), GFP_KERNEL); + if (!thc63) + return -ENOMEM; + + thc63->dev = &pdev->dev; + platform_set_drvdata(pdev, thc63); + + thc63->vcc = devm_regulator_get_optional(thc63->dev, "vcc"); + if (IS_ERR(thc63->vcc)) { + if (PTR_ERR(thc63->vcc) == -EPROBE_DEFER) + return -EPROBE_DEFER; + + dev_err(thc63->dev, "Unable to get \"vcc\" supply: %ld\n", + PTR_ERR(thc63->vcc)); + return PTR_ERR(thc63->vcc); + } + + ret = thc63_gpio_init(thc63); + if (ret) + return ret; + + ret = thc63_parse_dt(thc63); + if (ret) + return ret; + + thc63->bridge.driver_private = thc63; + thc63->bridge.of_node = pdev->dev.of_node; + thc63->bridge.funcs = &thc63_bridge_func; + + drm_bridge_add(&thc63->bridge); + + return 0; +} + +static int thc63_remove(struct platform_device *pdev) +{ + struct thc63_dev *thc63 = platform_get_drvdata(pdev); + + drm_bridge_remove(&thc63->bridge); + + return 0; +} + +static const struct of_device_id thc63_match[] = { + { .compatible = "thine,thc63lvd1024", }, + { }, +}; +MODULE_DEVICE_TABLE(of, thc63_match); + +static struct platform_driver thc63_driver = { + .probe = thc63_probe, + .remove = thc63_remove, + .driver = { + .name = "thc63lvd1024", + .of_match_table = thc63_match, + }, +}; +module_platform_driver(thc63_driver); + +MODULE_AUTHOR("Jacopo Mondi <jacopo@jmondi.org>"); +MODULE_DESCRIPTION("Thine THC63LVD1024 LVDS decoder DRM bridge driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 7d25c42..3c181d2 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -783,6 +783,8 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane, state->src_w = val; } else if (property == config->prop_src_h) { state->src_h = val; + } else if (property == plane->alpha_property) { + state->alpha = val; } else if (property == plane->rotation_property) { if (!is_power_of_2(val & DRM_MODE_ROTATE_MASK)) return -EINVAL; @@ -848,6 +850,8 @@ drm_atomic_plane_get_property(struct drm_plane *plane, *val = state->src_w; } else if (property == config->prop_src_h) { *val = state->src_h; + } else if (property == plane->alpha_property) { + *val = state->alpha; } else if (property == plane->rotation_property) { *val = state->rotation; } else if (property == plane->zpos_property) { @@ -1492,6 +1496,14 @@ EXPORT_SYMBOL(drm_atomic_set_fb_for_plane); * Otherwise, if &drm_plane_state.fence is not set this function we just set it * with the received implicit fence. In both cases this function consumes a * reference for @fence. + * + * This way explicit fencing can be used to overrule implicit fencing, which is + * important to make explicit fencing use-cases work: One example is using one + * buffer for 2 screens with different refresh rates. Implicit fencing will + * clamp rendering to the refresh rate of the slower screen, whereas explicit + * fence allows 2 independent render and display loops on a single buffer. If a + * driver allows obeys both implicit and explicit fences for plane updates, then + * it will break all the benefits of explicit fencing. */ void drm_atomic_set_fence_for_plane(struct drm_plane_state *plane_state, @@ -1702,11 +1714,15 @@ int drm_atomic_check_only(struct drm_atomic_state *state) } } - if (config->funcs->atomic_check) + if (config->funcs->atomic_check) { ret = config->funcs->atomic_check(state->dev, state); - if (ret) - return ret; + if (ret) { + DRM_DEBUG_ATOMIC("atomic driver check for %p failed: %d\n", + state, ret); + return ret; + } + } if (!state->allow_modeset) { for_each_new_crtc_in_state(state, crtc, crtc_state, i) { diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index c356545..9cb2209 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -875,6 +875,11 @@ EXPORT_SYMBOL(drm_atomic_helper_check_planes); * functions depend upon an updated adjusted_mode.clock to e.g. properly compute * watermarks. * + * Note that zpos normalization will add all enable planes to the state which + * might not desired for some drivers. + * For example enable/disable of a cursor plane which have fixed zpos value + * would trigger all other enabled planes to be forced to the state change. + * * RETURNS: * Zero for success or -errno */ @@ -887,6 +892,12 @@ int drm_atomic_helper_check(struct drm_device *dev, if (ret) return ret; + if (dev->mode_config.normalize_zpos) { + ret = drm_atomic_normalize_zpos(dev, state); + if (ret) + return ret; + } + ret = drm_atomic_helper_check_planes(dev, state); if (ret) return ret; @@ -1561,6 +1572,17 @@ void drm_atomic_helper_async_commit(struct drm_device *dev, for_each_new_plane_in_state(state, plane, plane_state, i) { funcs = plane->helper_private; funcs->atomic_async_update(plane, plane_state); + + /* + * ->atomic_async_update() is supposed to update the + * plane->state in-place, make sure at least common + * properties have been properly updated. + */ + WARN_ON_ONCE(plane->state->fb != plane_state->fb); + WARN_ON_ONCE(plane->state->crtc_x != plane_state->crtc_x); + WARN_ON_ONCE(plane->state->crtc_y != plane_state->crtc_y); + WARN_ON_ONCE(plane->state->src_x != plane_state->src_x); + WARN_ON_ONCE(plane->state->src_y != plane_state->src_y); } } EXPORT_SYMBOL(drm_atomic_helper_async_commit); @@ -2659,7 +2681,7 @@ int drm_atomic_helper_disable_plane(struct drm_plane *plane, goto fail; } - if (plane_state->crtc && (plane == plane->crtc->cursor)) + if (plane_state->crtc && plane_state->crtc->cursor == plane) plane_state->state->legacy_cursor_update = true; ret = __drm_atomic_helper_disable_plane(plane, plane_state); @@ -2881,31 +2903,9 @@ commit: return 0; } -/** - * drm_atomic_helper_disable_all - disable all currently active outputs - * @dev: DRM device - * @ctx: lock acquisition context - * - * Loops through all connectors, finding those that aren't turned off and then - * turns them off by setting their DPMS mode to OFF and deactivating the CRTC - * that they are connected to. - * - * This is used for example in suspend/resume to disable all currently active - * functions when suspending. If you just want to shut down everything at e.g. - * driver unload, look at drm_atomic_helper_shutdown(). - * - * Note that if callers haven't already acquired all modeset locks this might - * return -EDEADLK, which must be handled by calling drm_modeset_backoff(). - * - * Returns: - * 0 on success or a negative error code on failure. - * - * See also: - * drm_atomic_helper_suspend(), drm_atomic_helper_resume() and - * drm_atomic_helper_shutdown(). - */ -int drm_atomic_helper_disable_all(struct drm_device *dev, - struct drm_modeset_acquire_ctx *ctx) +static int __drm_atomic_helper_disable_all(struct drm_device *dev, + struct drm_modeset_acquire_ctx *ctx, + bool clean_old_fbs) { struct drm_atomic_state *state; struct drm_connector_state *conn_state; @@ -2957,8 +2957,11 @@ int drm_atomic_helper_disable_all(struct drm_device *dev, goto free; drm_atomic_set_fb_for_plane(plane_state, NULL); - plane_mask |= BIT(drm_plane_index(plane)); - plane->old_fb = plane->fb; + + if (clean_old_fbs) { + plane->old_fb = plane->fb; + plane_mask |= BIT(drm_plane_index(plane)); + } } ret = drm_atomic_commit(state); @@ -2969,6 +2972,34 @@ free: return ret; } +/** + * drm_atomic_helper_disable_all - disable all currently active outputs + * @dev: DRM device + * @ctx: lock acquisition context + * + * Loops through all connectors, finding those that aren't turned off and then + * turns them off by setting their DPMS mode to OFF and deactivating the CRTC + * that they are connected to. + * + * This is used for example in suspend/resume to disable all currently active + * functions when suspending. If you just want to shut down everything at e.g. + * driver unload, look at drm_atomic_helper_shutdown(). + * + * Note that if callers haven't already acquired all modeset locks this might + * return -EDEADLK, which must be handled by calling drm_modeset_backoff(). + * + * Returns: + * 0 on success or a negative error code on failure. + * + * See also: + * drm_atomic_helper_suspend(), drm_atomic_helper_resume() and + * drm_atomic_helper_shutdown(). + */ +int drm_atomic_helper_disable_all(struct drm_device *dev, + struct drm_modeset_acquire_ctx *ctx) +{ + return __drm_atomic_helper_disable_all(dev, ctx, false); +} EXPORT_SYMBOL(drm_atomic_helper_disable_all); /** @@ -2991,7 +3022,7 @@ void drm_atomic_helper_shutdown(struct drm_device *dev) while (1) { ret = drm_modeset_lock_all_ctx(dev, &ctx); if (!ret) - ret = drm_atomic_helper_disable_all(dev, &ctx); + ret = __drm_atomic_helper_disable_all(dev, &ctx, true); if (ret != -EDEADLK) break; @@ -3095,14 +3126,14 @@ int drm_atomic_helper_commit_duplicated_state(struct drm_atomic_state *state, struct drm_connector_state *new_conn_state; struct drm_crtc *crtc; struct drm_crtc_state *new_crtc_state; - unsigned plane_mask = 0; - struct drm_device *dev = state->dev; - int ret; state->acquire_ctx = ctx; for_each_new_plane_in_state(state, plane, new_plane_state, i) { - plane_mask |= BIT(drm_plane_index(plane)); + WARN_ON(plane->crtc != new_plane_state->crtc); + WARN_ON(plane->fb != new_plane_state->fb); + WARN_ON(plane->old_fb); + state->planes[i].old_state = plane->state; } @@ -3112,11 +3143,7 @@ int drm_atomic_helper_commit_duplicated_state(struct drm_atomic_state *state, for_each_new_connector_in_state(state, connector, new_conn_state, i) state->connectors[i].old_state = connector->state; - ret = drm_atomic_commit(state); - if (plane_mask) - drm_atomic_clean_old_fb(dev, plane_mask, ret); - - return ret; + return drm_atomic_commit(state); } EXPORT_SYMBOL(drm_atomic_helper_commit_duplicated_state); @@ -3484,6 +3511,10 @@ void drm_atomic_helper_plane_reset(struct drm_plane *plane) if (plane->state) { plane->state->plane = plane; plane->state->rotation = DRM_MODE_ROTATE_0; + + /* Reset the alpha value to fully opaque if it matters */ + if (plane->alpha_property) + plane->state->alpha = plane->alpha_property->values[1]; } } EXPORT_SYMBOL(drm_atomic_helper_plane_reset); diff --git a/drivers/gpu/drm/drm_blend.c b/drivers/gpu/drm/drm_blend.c index 5a81e1b..a16a74d 100644 --- a/drivers/gpu/drm/drm_blend.c +++ b/drivers/gpu/drm/drm_blend.c @@ -88,6 +88,13 @@ * On top of this basic transformation additional properties can be exposed by * the driver: * + * alpha: + * Alpha is setup with drm_plane_create_alpha_property(). It controls the + * plane-wide opacity, from transparent (0) to opaque (0xffff). It can be + * combined with pixel alpha. + * The pixel values in the framebuffers are expected to not be + * pre-multiplied by the global alpha associated to the plane. + * * rotation: * Rotation is set up with drm_plane_create_rotation_property(). It adds a * rotation and reflection step between the source and destination rectangles. @@ -106,6 +113,38 @@ */ /** + * drm_plane_create_alpha_property - create a new alpha property + * @plane: drm plane + * + * This function creates a generic, mutable, alpha property and enables support + * for it in the DRM core. It is attached to @plane. + * + * The alpha property will be allowed to be within the bounds of 0 + * (transparent) to 0xffff (opaque). + * + * Returns: + * 0 on success, negative error code on failure. + */ +int drm_plane_create_alpha_property(struct drm_plane *plane) +{ + struct drm_property *prop; + + prop = drm_property_create_range(plane->dev, 0, "alpha", + 0, DRM_BLEND_ALPHA_OPAQUE); + if (!prop) + return -ENOMEM; + + drm_object_attach_property(&plane->base, prop, DRM_BLEND_ALPHA_OPAQUE); + plane->alpha_property = prop; + + if (plane->state) + plane->state->alpha = DRM_BLEND_ALPHA_OPAQUE; + + return 0; +} +EXPORT_SYMBOL(drm_plane_create_alpha_property); + +/** * drm_plane_create_rotation_property - create a new rotation property * @plane: drm plane * @rotation: initial value of the rotation property diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index 4ff0646..b97e2de 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -417,8 +417,8 @@ int drm_plane_create_color_properties(struct drm_plane *plane, { struct drm_device *dev = plane->dev; struct drm_property *prop; - struct drm_prop_enum_list enum_list[max(DRM_COLOR_ENCODING_MAX, - DRM_COLOR_RANGE_MAX)]; + struct drm_prop_enum_list enum_list[max_t(int, DRM_COLOR_ENCODING_MAX, + DRM_COLOR_RANGE_MAX)]; int i, len; if (WARN_ON(supported_encodings == 0 || diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 0358388..a231dd5 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -402,6 +402,7 @@ int drm_mode_getcrtc(struct drm_device *dev, { struct drm_mode_crtc *crtc_resp = data; struct drm_crtc *crtc; + struct drm_plane *plane; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; @@ -410,34 +411,36 @@ int drm_mode_getcrtc(struct drm_device *dev, if (!crtc) return -ENOENT; + plane = crtc->primary; + crtc_resp->gamma_size = crtc->gamma_size; - drm_modeset_lock(&crtc->primary->mutex, NULL); - if (crtc->primary->state && crtc->primary->state->fb) - crtc_resp->fb_id = crtc->primary->state->fb->base.id; - else if (!crtc->primary->state && crtc->primary->fb) - crtc_resp->fb_id = crtc->primary->fb->base.id; + drm_modeset_lock(&plane->mutex, NULL); + if (plane->state && plane->state->fb) + crtc_resp->fb_id = plane->state->fb->base.id; + else if (!plane->state && plane->fb) + crtc_resp->fb_id = plane->fb->base.id; else crtc_resp->fb_id = 0; - if (crtc->primary->state) { - crtc_resp->x = crtc->primary->state->src_x >> 16; - crtc_resp->y = crtc->primary->state->src_y >> 16; + if (plane->state) { + crtc_resp->x = plane->state->src_x >> 16; + crtc_resp->y = plane->state->src_y >> 16; } - drm_modeset_unlock(&crtc->primary->mutex); + drm_modeset_unlock(&plane->mutex); drm_modeset_lock(&crtc->mutex, NULL); if (crtc->state) { if (crtc->state->enable) { drm_mode_convert_to_umode(&crtc_resp->mode, &crtc->state->mode); crtc_resp->mode_valid = 1; - } else { crtc_resp->mode_valid = 0; } } else { crtc_resp->x = crtc->x; crtc_resp->y = crtc->y; + if (crtc->enabled) { drm_mode_convert_to_umode(&crtc_resp->mode, &crtc->mode); crtc_resp->mode_valid = 1; @@ -471,7 +474,7 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set, ret = crtc->funcs->set_config(set, ctx); if (ret == 0) { - crtc->primary->crtc = crtc; + crtc->primary->crtc = fb ? crtc : NULL; crtc->primary->fb = fb; } @@ -554,6 +557,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, struct drm_mode_config *config = &dev->mode_config; struct drm_mode_crtc *crtc_req = data; struct drm_crtc *crtc; + struct drm_plane *plane; struct drm_connector **connector_set = NULL, *connector; struct drm_framebuffer *fb = NULL; struct drm_display_mode *mode = NULL; @@ -580,22 +584,33 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, } DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name); + plane = crtc->primary; + mutex_lock(&crtc->dev->mode_config.mutex); drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE); retry: ret = drm_modeset_lock_all_ctx(crtc->dev, &ctx); if (ret) goto out; + if (crtc_req->mode_valid) { /* If we have a mode we need a framebuffer. */ /* If we pass -1, set the mode with the currently bound fb */ if (crtc_req->fb_id == -1) { - if (!crtc->primary->fb) { + struct drm_framebuffer *old_fb; + + if (plane->state) + old_fb = plane->state->fb; + else + old_fb = plane->fb; + + if (!old_fb) { DRM_DEBUG_KMS("CRTC doesn't have current FB\n"); ret = -EINVAL; goto out; } - fb = crtc->primary->fb; + + fb = old_fb; /* Make refcounting symmetric with the lookup path. */ drm_framebuffer_get(fb); } else { @@ -627,8 +642,8 @@ retry: * match real hardware capabilities. Skip the check in that * case. */ - if (!crtc->primary->format_default) { - ret = drm_plane_check_pixel_format(crtc->primary, + if (!plane->format_default) { + ret = drm_plane_check_pixel_format(plane, fb->format->format, fb->modifier); if (ret) { diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h index 3c2b828..5d307b2 100644 --- a/drivers/gpu/drm/drm_crtc_internal.h +++ b/drivers/gpu/drm/drm_crtc_internal.h @@ -220,3 +220,5 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, /* drm_edid.c */ void drm_mode_fixup_1366x768(struct drm_display_mode *mode); +void drm_reset_display_info(struct drm_connector *connector); +u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edid); diff --git a/drivers/gpu/drm/drm_dp_aux_dev.c b/drivers/gpu/drm/drm_dp_aux_dev.c index 0530442..0e4f25d 100644 --- a/drivers/gpu/drm/drm_dp_aux_dev.c +++ b/drivers/gpu/drm/drm_dp_aux_dev.c @@ -177,8 +177,9 @@ static ssize_t auxdev_read_iter(struct kiocb *iocb, struct iov_iter *to) res = pos - iocb->ki_pos; iocb->ki_pos = pos; - atomic_dec(&aux_dev->usecount); - wake_up_atomic_t(&aux_dev->usecount); + if (atomic_dec_and_test(&aux_dev->usecount)) + wake_up_var(&aux_dev->usecount); + return res; } @@ -218,8 +219,9 @@ static ssize_t auxdev_write_iter(struct kiocb *iocb, struct iov_iter *from) res = pos - iocb->ki_pos; iocb->ki_pos = pos; - atomic_dec(&aux_dev->usecount); - wake_up_atomic_t(&aux_dev->usecount); + if (atomic_dec_and_test(&aux_dev->usecount)) + wake_up_var(&aux_dev->usecount); + return res; } @@ -277,8 +279,7 @@ void drm_dp_aux_unregister_devnode(struct drm_dp_aux *aux) mutex_unlock(&aux_idr_mutex); atomic_dec(&aux_dev->usecount); - wait_on_atomic_t(&aux_dev->usecount, atomic_t_wait, - TASK_UNINTERRUPTIBLE); + wait_var_event(&aux_dev->usecount, !atomic_read(&aux_dev->usecount)); minor = aux_dev->index; if (aux_dev->dev) diff --git a/drivers/gpu/drm/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/drm_dp_dual_mode_helper.c index 02a5092..e7f4fe2 100644 --- a/drivers/gpu/drm/drm_dp_dual_mode_helper.c +++ b/drivers/gpu/drm/drm_dp_dual_mode_helper.c @@ -350,19 +350,44 @@ int drm_dp_dual_mode_set_tmds_output(enum drm_dp_dual_mode_type type, { uint8_t tmds_oen = enable ? 0 : DP_DUAL_MODE_TMDS_DISABLE; ssize_t ret; + int retry; if (type < DRM_DP_DUAL_MODE_TYPE2_DVI) return 0; - ret = drm_dp_dual_mode_write(adapter, DP_DUAL_MODE_TMDS_OEN, - &tmds_oen, sizeof(tmds_oen)); - if (ret) { - DRM_DEBUG_KMS("Failed to %s TMDS output buffers\n", - enable ? "enable" : "disable"); - return ret; + /* + * LSPCON adapters in low-power state may ignore the first write, so + * read back and verify the written value a few times. + */ + for (retry = 0; retry < 3; retry++) { + uint8_t tmp; + + ret = drm_dp_dual_mode_write(adapter, DP_DUAL_MODE_TMDS_OEN, + &tmds_oen, sizeof(tmds_oen)); + if (ret) { + DRM_DEBUG_KMS("Failed to %s TMDS output buffers (%d attempts)\n", + enable ? "enable" : "disable", + retry + 1); + return ret; + } + + ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_TMDS_OEN, + &tmp, sizeof(tmp)); + if (ret) { + DRM_DEBUG_KMS("I2C read failed during TMDS output buffer %s (%d attempts)\n", + enable ? "enabling" : "disabling", + retry + 1); + return ret; + } + + if (tmp == tmds_oen) + return 0; } - return 0; + DRM_DEBUG_KMS("I2C write value mismatch during TMDS output buffer %s\n", + enable ? "enabling" : "disabling"); + + return -EIO; } EXPORT_SYMBOL(drm_dp_dual_mode_set_tmds_output); diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 6fac412..6588306 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -2941,12 +2941,14 @@ static void drm_dp_mst_dump_mstb(struct seq_file *m, } } +#define DP_PAYLOAD_TABLE_SIZE 64 + static bool dump_dp_payload_table(struct drm_dp_mst_topology_mgr *mgr, char *buf) { int i; - for (i = 0; i < 64; i += 16) { + for (i = 0; i < DP_PAYLOAD_TABLE_SIZE; i += 16) { if (drm_dp_dpcd_read(mgr->aux, DP_PAYLOAD_TABLE_UPDATE_STATUS + i, &buf[i], 16) != 16) @@ -3015,7 +3017,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m, mutex_lock(&mgr->lock); if (mgr->mst_primary) { - u8 buf[64]; + u8 buf[DP_PAYLOAD_TABLE_SIZE]; int ret; ret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, buf, DP_RECEIVER_CAP_SIZE); @@ -3033,8 +3035,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m, seq_printf(m, " revision: hw: %x.%x sw: %x.%x\n", buf[0x9] >> 4, buf[0x9] & 0xf, buf[0xa], buf[0xb]); if (dump_dp_payload_table(mgr, buf)) - seq_printf(m, "payload table: %*ph\n", 63, buf); - + seq_printf(m, "payload table: %*ph\n", DP_PAYLOAD_TABLE_SIZE, buf); } mutex_unlock(&mgr->lock); diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index a1b9338..32a83b4 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -32,6 +32,7 @@ #include <linux/moduleparam.h> #include <linux/mount.h> #include <linux/slab.h> +#include <linux/srcu.h> #include <drm/drm_drv.h> #include <drm/drmP.h> @@ -75,6 +76,8 @@ static bool drm_core_init_complete = false; static struct dentry *drm_debugfs_root; +DEFINE_STATIC_SRCU(drm_unplug_srcu); + /* * DRM Minors * A DRM device can provide several char-dev interfaces on the DRM-Major. Each @@ -318,18 +321,51 @@ void drm_put_dev(struct drm_device *dev) } EXPORT_SYMBOL(drm_put_dev); -static void drm_device_set_unplugged(struct drm_device *dev) +/** + * drm_dev_enter - Enter device critical section + * @dev: DRM device + * @idx: Pointer to index that will be passed to the matching drm_dev_exit() + * + * This function marks and protects the beginning of a section that should not + * be entered after the device has been unplugged. The section end is marked + * with drm_dev_exit(). Calls to this function can be nested. + * + * Returns: + * True if it is OK to enter the section, false otherwise. + */ +bool drm_dev_enter(struct drm_device *dev, int *idx) +{ + *idx = srcu_read_lock(&drm_unplug_srcu); + + if (dev->unplugged) { + srcu_read_unlock(&drm_unplug_srcu, *idx); + return false; + } + + return true; +} +EXPORT_SYMBOL(drm_dev_enter); + +/** + * drm_dev_exit - Exit device critical section + * @idx: index returned from drm_dev_enter() + * + * This function marks the end of a section that should not be entered after + * the device has been unplugged. + */ +void drm_dev_exit(int idx) { - smp_wmb(); - atomic_set(&dev->unplugged, 1); + srcu_read_unlock(&drm_unplug_srcu, idx); } +EXPORT_SYMBOL(drm_dev_exit); /** * drm_dev_unplug - unplug a DRM device * @dev: DRM device * * This unplugs a hotpluggable DRM device, which makes it inaccessible to - * userspace operations. Entry-points can use drm_dev_is_unplugged(). This + * userspace operations. Entry-points can use drm_dev_enter() and + * drm_dev_exit() to protect device resources in a race free manner. This * essentially unregisters the device like drm_dev_unregister(), but can be * called while there are still open users of @dev. */ @@ -338,10 +374,18 @@ void drm_dev_unplug(struct drm_device *dev) drm_dev_unregister(dev); mutex_lock(&drm_global_mutex); - drm_device_set_unplugged(dev); if (dev->open_count == 0) drm_dev_put(dev); mutex_unlock(&drm_global_mutex); + + /* + * After synchronizing any critical read section is guaranteed to see + * the new value of ->unplugged, and any critical section which might + * still have seen the old value of ->unplugged is guaranteed to have + * finished. + */ + dev->unplugged = true; + synchronize_srcu(&drm_unplug_srcu); } EXPORT_SYMBOL(drm_dev_unplug); diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 134069f..08d33b4 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -4451,10 +4451,10 @@ drm_reset_display_info(struct drm_connector *connector) info->max_tmds_clock = 0; info->dvi_dual = false; info->has_hdmi_infoframe = false; + memset(&info->hdmi, 0, sizeof(info->hdmi)); info->non_desktop = 0; } -EXPORT_SYMBOL_GPL(drm_reset_display_info); u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edid) { @@ -4462,17 +4462,11 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi u32 quirks = edid_get_quirks(edid); + drm_reset_display_info(connector); + info->width_mm = edid->width_cm * 10; info->height_mm = edid->height_cm * 10; - /* driver figures it out in this case */ - info->bpc = 0; - info->color_formats = 0; - info->cea_rev = 0; - info->max_tmds_clock = 0; - info->dvi_dual = false; - info->has_hdmi_infoframe = false; - info->non_desktop = !!(quirks & EDID_QUIRK_NON_DESKTOP); DRM_DEBUG_KMS("non_desktop set to %d\n", info->non_desktop); @@ -4538,7 +4532,6 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi info->color_formats |= DRM_COLOR_FORMAT_YCRCB422; return quirks; } -EXPORT_SYMBOL_GPL(drm_add_display_info); static int validate_displayid(u8 *displayid, int length, int idx) { diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index ad67203..8c4d32a 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -468,29 +468,31 @@ int drm_mode_getfb(struct drm_device *dev, goto out; } + if (!fb->funcs->create_handle) { + ret = -ENODEV; + goto out; + } + r->height = fb->height; r->width = fb->width; r->depth = fb->format->depth; r->bpp = fb->format->cpp[0] * 8; r->pitch = fb->pitches[0]; - if (fb->funcs->create_handle) { - if (drm_is_current_master(file_priv) || capable(CAP_SYS_ADMIN) || - drm_is_control_client(file_priv)) { - ret = fb->funcs->create_handle(fb, file_priv, - &r->handle); - } else { - /* GET_FB() is an unprivileged ioctl so we must not - * return a buffer-handle to non-master processes! For - * backwards-compatibility reasons, we cannot make - * GET_FB() privileged, so just return an invalid handle - * for non-masters. */ - r->handle = 0; - ret = 0; - } - } else { - ret = -ENODEV; + + /* GET_FB() is an unprivileged ioctl so we must not return a + * buffer-handle to non-master processes! For + * backwards-compatibility reasons, we cannot make GET_FB() privileged, + * so just return an invalid handle for non-masters. + */ + if (!drm_is_current_master(file_priv) && !capable(CAP_SYS_ADMIN) && + !drm_is_control_client(file_priv)) { + r->handle = 0; + ret = 0; + goto out; } + ret = fb->funcs->create_handle(fb, file_priv, &r->handle); + out: drm_framebuffer_put(fb); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 4975ba9..4a16d7b 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -436,9 +436,12 @@ err_unref: * @obj: object to register * @handlep: pionter to return the created handle to the caller * - * Create a handle for this object. This adds a handle reference - * to the object, which includes a regular reference count. Callers - * will likely want to dereference the object afterwards. + * Create a handle for this object. This adds a handle reference to the object, + * which includes a regular reference count. Callers will likely want to + * dereference the object afterwards. + * + * Since this publishes @obj to userspace it must be fully set up by this point, + * drivers must call this last in their buffer object creation callbacks. */ int drm_gem_handle_create(struct drm_file *file_priv, struct drm_gem_object *obj, diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index 4d682a6..acfbc06 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -22,6 +22,7 @@ #include <drm/drm_gem.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_modeset_helper.h> +#include <drm/drm_simple_kms_helper.h> /** * DOC: overview @@ -266,6 +267,24 @@ int drm_gem_fb_prepare_fb(struct drm_plane *plane, EXPORT_SYMBOL_GPL(drm_gem_fb_prepare_fb); /** + * drm_gem_fb_simple_display_pipe_prepare_fb - prepare_fb helper for + * &drm_simple_display_pipe + * @pipe: Simple display pipe + * @plane_state: Plane state + * + * This function uses drm_gem_fb_prepare_fb() to check if the plane FB has a + * &dma_buf attached, extracts the exclusive fence and attaches it to plane + * state for the atomic helper to wait on. Drivers can use this as their + * &drm_simple_display_pipe_funcs.prepare_fb callback. + */ +int drm_gem_fb_simple_display_pipe_prepare_fb(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *plane_state) +{ + return drm_gem_fb_prepare_fb(&pipe->plane, plane_state); +} +EXPORT_SYMBOL(drm_gem_fb_simple_display_pipe_prepare_fb); + +/** * drm_gem_fbdev_fb_create - Create a GEM backed &drm_framebuffer for fbdev * emulation * @dev: DRM device diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index d345563..50c73c0 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -340,7 +340,7 @@ static void _drm_lease_revoke(struct drm_master *top) break; /* Over */ - master = list_entry(master->lessee_list.next, struct drm_master, lessee_list); + master = list_next_entry(master, lessee_list); } } } diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 902cc1a..caebddd 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -60,7 +60,7 @@ static const struct drm_dmi_panel_orientation_data itworks_tw891 = { .orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP, }; -static const struct drm_dmi_panel_orientation_data vios_lth17 = { +static const struct drm_dmi_panel_orientation_data lcd800x1280_rightside_up = { .width = 800, .height = 1280, .orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP, @@ -102,12 +102,30 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "TW891"), }, .driver_data = (void *)&itworks_tw891, + }, { /* + * Lenovo Ideapad Miix 310 laptop, only some production batches + * have a portrait screen, the resolution checks makes the quirk + * apply only to those batches. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80SG"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* Lenovo Ideapad Miix 320 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80XF"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 320-10ICR"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* VIOS LTH17 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "VIOS"), DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "LTH17"), }, - .driver_data = (void *)&vios_lth17, + .driver_data = (void *)&lcd800x1280_rightside_up, }, {} }; diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 6d2a6e4..0350544 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -756,6 +756,7 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc, struct drm_modeset_acquire_ctx *ctx) { struct drm_device *dev = crtc->dev; + struct drm_plane *plane = crtc->cursor; struct drm_framebuffer *fb = NULL; struct drm_mode_fb_cmd2 fbreq = { .width = req->width, @@ -769,8 +770,8 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc, uint32_t src_w = 0, src_h = 0; int ret = 0; - BUG_ON(!crtc->cursor); - WARN_ON(crtc->cursor->crtc != crtc && crtc->cursor->crtc != NULL); + BUG_ON(!plane); + WARN_ON(plane->crtc != crtc && plane->crtc != NULL); /* * Obtain fb we'll be using (either new or existing) and take an extra @@ -784,13 +785,18 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc, DRM_DEBUG_KMS("failed to wrap cursor buffer in drm framebuffer\n"); return PTR_ERR(fb); } + fb->hot_x = req->hot_x; fb->hot_y = req->hot_y; } else { fb = NULL; } } else { - fb = crtc->cursor->fb; + if (plane->state) + fb = plane->state->fb; + else + fb = plane->fb; + if (fb) drm_framebuffer_get(fb); } @@ -810,7 +816,7 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc, src_h = fb->height << 16; } - ret = __setplane_internal(crtc->cursor, crtc, fb, + ret = __setplane_internal(plane, crtc, fb, crtc_x, crtc_y, crtc_w, crtc_h, 0, 0, src_w, src_h, ctx); @@ -931,7 +937,8 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, { struct drm_mode_crtc_page_flip_target *page_flip = data; struct drm_crtc *crtc; - struct drm_framebuffer *fb = NULL; + struct drm_plane *plane; + struct drm_framebuffer *fb = NULL, *old_fb; struct drm_pending_vblank_event *e = NULL; u32 target_vblank = page_flip->sequence; struct drm_modeset_acquire_ctx ctx; @@ -959,6 +966,8 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, if (!crtc) return -ENOENT; + plane = crtc->primary; + if (crtc->funcs->page_flip_target) { u32 current_vblank; int r; @@ -1003,11 +1012,16 @@ retry: ret = drm_modeset_lock(&crtc->mutex, &ctx); if (ret) goto out; - ret = drm_modeset_lock(&crtc->primary->mutex, &ctx); + ret = drm_modeset_lock(&plane->mutex, &ctx); if (ret) goto out; - if (crtc->primary->fb == NULL) { + if (plane->state) + old_fb = plane->state->fb; + else + old_fb = plane->fb; + + if (old_fb == NULL) { /* The framebuffer is currently unbound, presumably * due to a hotplug event, that userspace has not * yet discovered. @@ -1022,8 +1036,8 @@ retry: goto out; } - if (crtc->state) { - const struct drm_plane_state *state = crtc->primary->state; + if (plane->state) { + const struct drm_plane_state *state = plane->state; ret = drm_framebuffer_check_src_coords(state->src_x, state->src_y, @@ -1031,12 +1045,13 @@ retry: state->src_h, fb); } else { - ret = drm_crtc_check_viewport(crtc, crtc->x, crtc->y, &crtc->mode, fb); + ret = drm_crtc_check_viewport(crtc, crtc->x, crtc->y, + &crtc->mode, fb); } if (ret) goto out; - if (crtc->primary->fb->format != fb->format) { + if (old_fb->format != fb->format) { DRM_DEBUG_KMS("Page flip is not allowed to change frame buffer format.\n"); ret = -EINVAL; goto out; @@ -1048,10 +1063,12 @@ retry: ret = -ENOMEM; goto out; } + e->event.base.type = DRM_EVENT_FLIP_COMPLETE; e->event.base.length = sizeof(e->event); e->event.vbl.user_data = page_flip->user_data; e->event.vbl.crtc_id = crtc->base.id; + ret = drm_event_reserve_init(dev, file_priv, &e->base, &e->event.base); if (ret) { kfree(e); @@ -1060,7 +1077,7 @@ retry: } } - crtc->primary->old_fb = crtc->primary->fb; + plane->old_fb = plane->fb; if (crtc->funcs->page_flip_target) ret = crtc->funcs->page_flip_target(crtc, fb, e, page_flip->flags, @@ -1073,19 +1090,18 @@ retry: if (page_flip->flags & DRM_MODE_PAGE_FLIP_EVENT) drm_event_cancel_free(dev, &e->base); /* Keep the old fb, don't unref it. */ - crtc->primary->old_fb = NULL; + plane->old_fb = NULL; } else { - crtc->primary->fb = fb; - /* Unref only the old framebuffer. */ - fb = NULL; + plane->fb = fb; + drm_framebuffer_get(fb); } out: if (fb) drm_framebuffer_put(fb); - if (crtc->primary->old_fb) - drm_framebuffer_put(crtc->primary->old_fb); - crtc->primary->old_fb = NULL; + if (plane->old_fb) + drm_framebuffer_put(plane->old_fb); + plane->old_fb = NULL; if (ret == -EDEADLK) { ret = drm_modeset_backoff(&ctx); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 7856a9b..caf675e 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -331,6 +331,9 @@ EXPORT_SYMBOL(drm_gem_map_dma_buf); /** * drm_gem_unmap_dma_buf - unmap_dma_buf implementation for GEM + * @attach: attachment to unmap buffer from + * @sgt: scatterlist info of the buffer to unmap + * @dir: direction of DMA transfer * * Not implemented. The unmap is done at drm_gem_map_detach(). This can be * used as the &dma_buf_ops.unmap_dma_buf callback. @@ -429,6 +432,8 @@ EXPORT_SYMBOL(drm_gem_dmabuf_vunmap); /** * drm_gem_dmabuf_kmap_atomic - map_atomic implementation for GEM + * @dma_buf: buffer to be mapped + * @page_num: page number within the buffer * * Not implemented. This can be used as the &dma_buf_ops.map_atomic callback. */ @@ -441,6 +446,9 @@ EXPORT_SYMBOL(drm_gem_dmabuf_kmap_atomic); /** * drm_gem_dmabuf_kunmap_atomic - unmap_atomic implementation for GEM + * @dma_buf: buffer to be unmapped + * @page_num: page number within the buffer + * @addr: virtual address of the buffer * * Not implemented. This can be used as the &dma_buf_ops.unmap_atomic callback. */ @@ -453,6 +461,8 @@ EXPORT_SYMBOL(drm_gem_dmabuf_kunmap_atomic); /** * drm_gem_dmabuf_kmap - map implementation for GEM + * @dma_buf: buffer to be mapped + * @page_num: page number within the buffer * * Not implemented. This can be used as the &dma_buf_ops.map callback. */ @@ -464,6 +474,9 @@ EXPORT_SYMBOL(drm_gem_dmabuf_kmap); /** * drm_gem_dmabuf_kunmap - unmap implementation for GEM + * @dma_buf: buffer to be unmapped + * @page_num: page number within the buffer + * @addr: virtual address of the buffer * * Not implemented. This can be used as the &dma_buf_ops.unmap callback. */ diff --git a/drivers/gpu/drm/drm_scdc_helper.c b/drivers/gpu/drm/drm_scdc_helper.c index 657ea5a..870e25f 100644 --- a/drivers/gpu/drm/drm_scdc_helper.c +++ b/drivers/gpu/drm/drm_scdc_helper.c @@ -141,7 +141,7 @@ bool drm_scdc_get_scrambling_status(struct i2c_adapter *adapter) ret = drm_scdc_readb(adapter, SCDC_SCRAMBLER_STATUS, &status); if (ret < 0) { - DRM_ERROR("Failed to read scrambling status: %d\n", ret); + DRM_DEBUG_KMS("Failed to read scrambling status: %d\n", ret); return false; } @@ -168,7 +168,7 @@ bool drm_scdc_set_scrambling(struct i2c_adapter *adapter, bool enable) ret = drm_scdc_readb(adapter, SCDC_TMDS_CONFIG, &config); if (ret < 0) { - DRM_ERROR("Failed to read TMDS config: %d\n", ret); + DRM_DEBUG_KMS("Failed to read TMDS config: %d\n", ret); return false; } @@ -179,7 +179,7 @@ bool drm_scdc_set_scrambling(struct i2c_adapter *adapter, bool enable) ret = drm_scdc_writeb(adapter, SCDC_TMDS_CONFIG, config); if (ret < 0) { - DRM_ERROR("Failed to enable scrambling: %d\n", ret); + DRM_DEBUG_KMS("Failed to enable scrambling: %d\n", ret); return false; } @@ -223,7 +223,7 @@ bool drm_scdc_set_high_tmds_clock_ratio(struct i2c_adapter *adapter, bool set) ret = drm_scdc_readb(adapter, SCDC_TMDS_CONFIG, &config); if (ret < 0) { - DRM_ERROR("Failed to read TMDS config: %d\n", ret); + DRM_DEBUG_KMS("Failed to read TMDS config: %d\n", ret); return false; } @@ -234,7 +234,7 @@ bool drm_scdc_set_high_tmds_clock_ratio(struct i2c_adapter *adapter, bool set) ret = drm_scdc_writeb(adapter, SCDC_TMDS_CONFIG, config); if (ret < 0) { - DRM_ERROR("Failed to set TMDS clock ratio: %d\n", ret); + DRM_DEBUG_KMS("Failed to set TMDS clock ratio: %d\n", ret); return false; } diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c index 987a353..7a00455 100644 --- a/drivers/gpu/drm/drm_simple_kms_helper.c +++ b/drivers/gpu/drm/drm_simple_kms_helper.c @@ -64,13 +64,15 @@ static int drm_simple_kms_crtc_check(struct drm_crtc *crtc, static void drm_simple_kms_crtc_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { + struct drm_plane *plane; struct drm_simple_display_pipe *pipe; pipe = container_of(crtc, struct drm_simple_display_pipe, crtc); if (!pipe->funcs || !pipe->funcs->enable) return; - pipe->funcs->enable(pipe, crtc->state); + plane = &pipe->plane; + pipe->funcs->enable(pipe, crtc->state, plane->state); } static void drm_simple_kms_crtc_disable(struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c index 964831d..86330f3 100644 --- a/drivers/gpu/drm/exynos/exynos_dp.c +++ b/drivers/gpu/drm/exynos/exynos_dp.c @@ -162,7 +162,7 @@ static int exynos_dp_bind(struct device *dev, struct device *master, void *data) dp->drm_dev = drm_dev; dp->plat_data.dev_type = EXYNOS_DP; - dp->plat_data.power_on = exynos_dp_poweron; + dp->plat_data.power_on_start = exynos_dp_poweron; dp->plat_data.power_off = exynos_dp_poweroff; dp->plat_data.attach = exynos_dp_bridge_attach; dp->plat_data.get_modes = exynos_dp_get_modes; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index a518e9c..39284bb 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -37,26 +37,6 @@ #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 -int exynos_atomic_check(struct drm_device *dev, - struct drm_atomic_state *state) -{ - int ret; - - ret = drm_atomic_helper_check_modeset(dev, state); - if (ret) - return ret; - - ret = drm_atomic_normalize_zpos(dev, state); - if (ret) - return ret; - - ret = drm_atomic_helper_check_planes(dev, state); - if (ret) - return ret; - - return ret; -} - static int exynos_drm_open(struct drm_device *dev, struct drm_file *file) { struct drm_exynos_file_private *file_priv; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index df2262f..075957c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -275,7 +275,6 @@ static inline int exynos_dpi_bind(struct drm_device *dev, int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state, bool nonblock); -int exynos_atomic_check(struct drm_device *dev, struct drm_atomic_state *state); extern struct platform_driver fimd_driver; diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c index 0faaf82..7fcc1a7 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fb.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c @@ -18,6 +18,7 @@ #include <drm/drm_fb_helper.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> #include <uapi/drm/exynos_drm.h> #include "exynos_drm_drv.h" @@ -26,20 +27,6 @@ #include "exynos_drm_iommu.h" #include "exynos_drm_crtc.h" -#define to_exynos_fb(x) container_of(x, struct exynos_drm_fb, fb) - -/* - * exynos specific framebuffer structure. - * - * @fb: drm framebuffer obejct. - * @exynos_gem: array of exynos specific gem object containing a gem object. - */ -struct exynos_drm_fb { - struct drm_framebuffer fb; - struct exynos_drm_gem *exynos_gem[MAX_FB_BUFFER]; - dma_addr_t dma_addr[MAX_FB_BUFFER]; -}; - static int check_fb_gem_memory_type(struct drm_device *drm_dev, struct exynos_drm_gem *exynos_gem) { @@ -66,40 +53,9 @@ static int check_fb_gem_memory_type(struct drm_device *drm_dev, return 0; } -static void exynos_drm_fb_destroy(struct drm_framebuffer *fb) -{ - struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb); - unsigned int i; - - drm_framebuffer_cleanup(fb); - - for (i = 0; i < ARRAY_SIZE(exynos_fb->exynos_gem); i++) { - struct drm_gem_object *obj; - - if (exynos_fb->exynos_gem[i] == NULL) - continue; - - obj = &exynos_fb->exynos_gem[i]->base; - drm_gem_object_unreference_unlocked(obj); - } - - kfree(exynos_fb); - exynos_fb = NULL; -} - -static int exynos_drm_fb_create_handle(struct drm_framebuffer *fb, - struct drm_file *file_priv, - unsigned int *handle) -{ - struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb); - - return drm_gem_handle_create(file_priv, - &exynos_fb->exynos_gem[0]->base, handle); -} - static const struct drm_framebuffer_funcs exynos_drm_fb_funcs = { - .destroy = exynos_drm_fb_destroy, - .create_handle = exynos_drm_fb_create_handle, + .destroy = drm_gem_fb_destroy, + .create_handle = drm_gem_fb_create_handle, }; struct drm_framebuffer * @@ -108,12 +64,12 @@ exynos_drm_framebuffer_init(struct drm_device *dev, struct exynos_drm_gem **exynos_gem, int count) { - struct exynos_drm_fb *exynos_fb; + struct drm_framebuffer *fb; int i; int ret; - exynos_fb = kzalloc(sizeof(*exynos_fb), GFP_KERNEL); - if (!exynos_fb) + fb = kzalloc(sizeof(*fb), GFP_KERNEL); + if (!fb) return ERR_PTR(-ENOMEM); for (i = 0; i < count; i++) { @@ -121,23 +77,21 @@ exynos_drm_framebuffer_init(struct drm_device *dev, if (ret < 0) goto err; - exynos_fb->exynos_gem[i] = exynos_gem[i]; - exynos_fb->dma_addr[i] = exynos_gem[i]->dma_addr - + mode_cmd->offsets[i]; + fb->obj[i] = &exynos_gem[i]->base; } - drm_helper_mode_fill_fb_struct(dev, &exynos_fb->fb, mode_cmd); + drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd); - ret = drm_framebuffer_init(dev, &exynos_fb->fb, &exynos_drm_fb_funcs); + ret = drm_framebuffer_init(dev, fb, &exynos_drm_fb_funcs); if (ret < 0) { DRM_ERROR("failed to initialize framebuffer\n"); goto err; } - return &exynos_fb->fb; + return fb; err: - kfree(exynos_fb); + kfree(fb); return ERR_PTR(ret); } @@ -191,12 +145,13 @@ err: dma_addr_t exynos_drm_fb_dma_addr(struct drm_framebuffer *fb, int index) { - struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb); + struct exynos_drm_gem *exynos_gem; if (WARN_ON_ONCE(index >= MAX_FB_BUFFER)) return 0; - return exynos_fb->dma_addr[index]; + exynos_gem = to_exynos_gem(fb->obj[index]); + return exynos_gem->dma_addr + fb->offsets[index]; } static struct drm_mode_config_helper_funcs exynos_drm_mode_config_helpers = { @@ -206,7 +161,7 @@ static struct drm_mode_config_helper_funcs exynos_drm_mode_config_helpers = { static const struct drm_mode_config_funcs exynos_drm_mode_config_funcs = { .fb_create = exynos_user_fb_create, .output_poll_changed = drm_fb_helper_output_poll_changed, - .atomic_check = exynos_atomic_check, + .atomic_check = drm_atomic_helper_check, .atomic_commit = drm_atomic_helper_commit, }; @@ -227,4 +182,6 @@ void exynos_drm_mode_config_init(struct drm_device *dev) dev->mode_config.helper_private = &exynos_drm_mode_config_helpers; dev->mode_config.allow_fb_modifiers = true; + + dev->mode_config.normalize_zpos = true; } diff --git a/drivers/gpu/drm/gma500/cdv_intel_crt.c b/drivers/gpu/drm/gma500/cdv_intel_crt.c index b837e7a..cb5a14b 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_crt.c +++ b/drivers/gpu/drm/gma500/cdv_intel_crt.c @@ -64,7 +64,7 @@ static void cdv_intel_crt_dpms(struct drm_encoder *encoder, int mode) REG_WRITE(reg, temp); } -static int cdv_intel_crt_mode_valid(struct drm_connector *connector, +static enum drm_mode_status cdv_intel_crt_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { if (mode->flags & DRM_MODE_FLAG_DBLSCAN) diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c index a4bb89b..5ea785f 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_dp.c +++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c @@ -505,7 +505,7 @@ static void cdv_intel_edp_backlight_off (struct gma_encoder *intel_encoder) msleep(intel_dp->backlight_off_delay); } -static int +static enum drm_mode_status cdv_intel_dp_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c index 563f193..f087899 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c +++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c @@ -223,7 +223,7 @@ static int cdv_hdmi_get_modes(struct drm_connector *connector) return ret; } -static int cdv_hdmi_mode_valid(struct drm_connector *connector, +static enum drm_mode_status cdv_hdmi_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { if (mode->clock > 165000) diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c index e64960d..de9531c 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c +++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c @@ -244,7 +244,7 @@ static void cdv_intel_lvds_restore(struct drm_connector *connector) { } -static int cdv_intel_lvds_mode_valid(struct drm_connector *connector, +static enum drm_mode_status cdv_intel_lvds_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct drm_device *dev = connector->dev; diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_output.c b/drivers/gpu/drm/gma500/mdfld_dsi_output.c index acb3848..fe02092 100644 --- a/drivers/gpu/drm/gma500/mdfld_dsi_output.c +++ b/drivers/gpu/drm/gma500/mdfld_dsi_output.c @@ -346,7 +346,7 @@ static int mdfld_dsi_connector_get_modes(struct drm_connector *connector) return 0; } -static int mdfld_dsi_connector_mode_valid(struct drm_connector *connector, +static enum drm_mode_status mdfld_dsi_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct mdfld_dsi_connector *dsi_connector = diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c index 8b2eb32..78566a8 100644 --- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c +++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c @@ -509,7 +509,7 @@ static void oaktrail_hdmi_dpms(struct drm_encoder *encoder, int mode) HDMI_WRITE(HDMI_VIDEO_REG, temp); } -static int oaktrail_hdmi_mode_valid(struct drm_connector *connector, +static enum drm_mode_status oaktrail_hdmi_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { if (mode->clock > 165000) diff --git a/drivers/gpu/drm/gma500/psb_intel_drv.h b/drivers/gpu/drm/gma500/psb_intel_drv.h index e8e4ea1..e05e539 100644 --- a/drivers/gpu/drm/gma500/psb_intel_drv.h +++ b/drivers/gpu/drm/gma500/psb_intel_drv.h @@ -255,7 +255,7 @@ extern int intelfb_remove(struct drm_device *dev, extern bool psb_intel_lvds_mode_fixup(struct drm_encoder *encoder, const struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode); -extern int psb_intel_lvds_mode_valid(struct drm_connector *connector, +extern enum drm_mode_status psb_intel_lvds_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode); extern int psb_intel_lvds_set_property(struct drm_connector *connector, struct drm_property *property, diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c index be3eefe..8baf632 100644 --- a/drivers/gpu/drm/gma500/psb_intel_lvds.c +++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c @@ -343,7 +343,7 @@ static void psb_intel_lvds_restore(struct drm_connector *connector) } } -int psb_intel_lvds_mode_valid(struct drm_connector *connector, +enum drm_mode_status psb_intel_lvds_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct drm_psb_private *dev_priv = connector->dev->dev_private; diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c index 8450791..8dc2b19 100644 --- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c +++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c @@ -1157,7 +1157,7 @@ static void psb_intel_sdvo_dpms(struct drm_encoder *encoder, int mode) return; } -static int psb_intel_sdvo_mode_valid(struct drm_connector *connector, +static enum drm_mode_status psb_intel_sdvo_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct psb_intel_sdvo *psb_intel_sdvo = intel_attached_sdvo(connector); diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index f4eba87..d2f4749 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -27,7 +27,7 @@ static int hibmc_connector_get_modes(struct drm_connector *connector) return drm_add_modes_noedid(connector, 800, 600); } -static int hibmc_connector_mode_valid(struct drm_connector *connector, +static enum drm_mode_status hibmc_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { return MODE_OK; diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index 9e67a7b..421c8a7 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -1106,7 +1106,7 @@ static int tda998x_connector_get_modes(struct drm_connector *connector) return n; } -static int tda998x_connector_mode_valid(struct drm_connector *connector, +static enum drm_mode_status tda998x_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { /* TDA19988 dotclock can go up to 165MHz */ diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 9bee52a9..4c6adae 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -18,6 +18,10 @@ subdir-ccflags-y += $(call cc-disable-warning, type-limits) subdir-ccflags-y += $(call cc-disable-warning, missing-field-initializers) subdir-ccflags-y += $(call cc-disable-warning, implicit-fallthrough) subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable) +# clang warnings +subdir-ccflags-y += $(call cc-disable-warning, sign-compare) +subdir-ccflags-y += $(call cc-disable-warning, sometimes-uninitialized) +subdir-ccflags-y += $(call cc-disable-warning, initializer-overrides) subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror # Fine grained warnings disable @@ -67,11 +71,11 @@ i915-y += i915_cmd_parser.o \ i915_gem_shrinker.o \ i915_gem_stolen.o \ i915_gem_tiling.o \ - i915_gem_timeline.o \ i915_gem_userptr.o \ i915_gemfs.o \ i915_query.o \ i915_request.o \ + i915_timeline.o \ i915_trace_points.o \ i915_vma.o \ intel_breadcrumbs.o \ @@ -154,7 +158,8 @@ i915-y += dvo_ch7017.o \ i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o i915-$(CONFIG_DRM_I915_SELFTEST) += \ selftests/i915_random.o \ - selftests/i915_selftest.o + selftests/i915_selftest.o \ + selftests/igt_flush_test.o # virtual gpu code i915-y += i915_vgpu.o diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 36c6180..718ca08 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -1096,6 +1096,7 @@ static int cmd_handler_mi_user_interrupt(struct parser_exec_state *s) { set_bit(cmd_interrupt_events[s->ring_id].mi_user_interrupt, s->workload->pending_events); + patch_value(s, cmd_ptr(s, 0), MI_NOOP); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index dd96ffc..6d8180e 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -169,6 +169,8 @@ static u8 dpcd_fix_data[DPCD_HEADER_SIZE] = { static void emulate_monitor_status_change(struct intel_vgpu *vgpu) { struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; + int pipe; + vgpu_vreg_t(vgpu, SDEISR) &= ~(SDE_PORTB_HOTPLUG_CPT | SDE_PORTC_HOTPLUG_CPT | SDE_PORTD_HOTPLUG_CPT); @@ -267,6 +269,14 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) if (IS_BROADWELL(dev_priv)) vgpu_vreg_t(vgpu, PCH_ADPA) &= ~ADPA_CRT_HOTPLUG_MONITOR_MASK; + /* Disable Primary/Sprite/Cursor plane */ + for_each_pipe(dev_priv, pipe) { + vgpu_vreg_t(vgpu, DSPCNTR(pipe)) &= ~DISPLAY_PLANE_ENABLE; + vgpu_vreg_t(vgpu, SPRCTL(pipe)) &= ~SPRITE_ENABLE; + vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~CURSOR_MODE; + vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= CURSOR_MODE_DISABLE; + } + vgpu_vreg_t(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE; } diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index b555eb2..6f4f8e9 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -323,6 +323,7 @@ static void update_fb_info(struct vfio_device_gfx_plane_info *gvt_dmabuf, struct intel_vgpu_fb_info *fb_info) { gvt_dmabuf->drm_format = fb_info->drm_format; + gvt_dmabuf->drm_format_mod = fb_info->drm_format_mod; gvt_dmabuf->width = fb_info->width; gvt_dmabuf->height = fb_info->height; gvt_dmabuf->stride = fb_info->stride; diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index 6b50fe7..1c12068 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -245,16 +245,13 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, plane->hw_format = fmt; plane->base = vgpu_vreg_t(vgpu, DSPSURF(pipe)) & I915_GTT_PAGE_MASK; - if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) { - gvt_vgpu_err("invalid gma address: %lx\n", - (unsigned long)plane->base); + if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) return -EINVAL; - } plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base); if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) { - gvt_vgpu_err("invalid gma address: %lx\n", - (unsigned long)plane->base); + gvt_vgpu_err("Translate primary plane gma 0x%x to gpa fail\n", + plane->base); return -EINVAL; } @@ -371,16 +368,13 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu, alpha_plane, alpha_force); plane->base = vgpu_vreg_t(vgpu, CURBASE(pipe)) & I915_GTT_PAGE_MASK; - if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) { - gvt_vgpu_err("invalid gma address: %lx\n", - (unsigned long)plane->base); + if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) return -EINVAL; - } plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base); if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) { - gvt_vgpu_err("invalid gma address: %lx\n", - (unsigned long)plane->base); + gvt_vgpu_err("Translate cursor plane gma 0x%x to gpa fail\n", + plane->base); return -EINVAL; } @@ -476,16 +470,13 @@ int intel_vgpu_decode_sprite_plane(struct intel_vgpu *vgpu, plane->drm_format = drm_format; plane->base = vgpu_vreg_t(vgpu, SPRSURF(pipe)) & I915_GTT_PAGE_MASK; - if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) { - gvt_vgpu_err("invalid gma address: %lx\n", - (unsigned long)plane->base); + if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) return -EINVAL; - } plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base); if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) { - gvt_vgpu_err("invalid gma address: %lx\n", - (unsigned long)plane->base); + gvt_vgpu_err("Translate sprite plane gma 0x%x to gpa fail\n", + plane->base); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index d292812..78e55aa 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -530,6 +530,16 @@ static void ggtt_set_guest_entry(struct intel_vgpu_mm *mm, false, 0, mm->vgpu); } +static void ggtt_get_host_entry(struct intel_vgpu_mm *mm, + struct intel_gvt_gtt_entry *entry, unsigned long index) +{ + struct intel_gvt_gtt_pte_ops *pte_ops = mm->vgpu->gvt->gtt.pte_ops; + + GEM_BUG_ON(mm->type != INTEL_GVT_MM_GGTT); + + pte_ops->get_entry(NULL, entry, index, false, 0, mm->vgpu); +} + static void ggtt_set_host_entry(struct intel_vgpu_mm *mm, struct intel_gvt_gtt_entry *entry, unsigned long index) { @@ -1818,6 +1828,18 @@ int intel_vgpu_emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, unsigned int off, return ret; } +static void ggtt_invalidate_pte(struct intel_vgpu *vgpu, + struct intel_gvt_gtt_entry *entry) +{ + struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops; + unsigned long pfn; + + pfn = pte_ops->get_pfn(entry); + if (pfn != vgpu->gvt->gtt.scratch_mfn) + intel_gvt_hypervisor_dma_unmap_guest_page(vgpu, + pfn << PAGE_SHIFT); +} + static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, void *p_data, unsigned int bytes) { @@ -1844,10 +1866,10 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data, bytes); - m = e; if (ops->test_present(&e)) { gfn = ops->get_pfn(&e); + m = e; /* one PTE update may be issued in multiple writes and the * first write may not construct a valid gfn @@ -1868,8 +1890,12 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, ops->set_pfn(&m, gvt->gtt.scratch_mfn); } else ops->set_pfn(&m, dma_addr >> PAGE_SHIFT); - } else + } else { + ggtt_get_host_entry(ggtt_mm, &m, g_gtt_index); + ggtt_invalidate_pte(vgpu, &m); ops->set_pfn(&m, gvt->gtt.scratch_mfn); + ops->clear_present(&m); + } out: ggtt_set_host_entry(ggtt_mm, &m, g_gtt_index); @@ -2030,7 +2056,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) return PTR_ERR(gtt->ggtt_mm); } - intel_vgpu_reset_ggtt(vgpu); + intel_vgpu_reset_ggtt(vgpu, false); return create_scratch_page_tree(vgpu); } @@ -2315,17 +2341,19 @@ void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu) /** * intel_vgpu_reset_ggtt - reset the GGTT entry * @vgpu: a vGPU + * @invalidate_old: invalidate old entries * * This function is called at the vGPU create stage * to reset all the GGTT entries. * */ -void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu) +void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old) { struct intel_gvt *gvt = vgpu->gvt; struct drm_i915_private *dev_priv = gvt->dev_priv; struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops; struct intel_gvt_gtt_entry entry = {.type = GTT_TYPE_GGTT_PTE}; + struct intel_gvt_gtt_entry old_entry; u32 index; u32 num_entries; @@ -2334,13 +2362,23 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu) index = vgpu_aperture_gmadr_base(vgpu) >> PAGE_SHIFT; num_entries = vgpu_aperture_sz(vgpu) >> PAGE_SHIFT; - while (num_entries--) + while (num_entries--) { + if (invalidate_old) { + ggtt_get_host_entry(vgpu->gtt.ggtt_mm, &old_entry, index); + ggtt_invalidate_pte(vgpu, &old_entry); + } ggtt_set_host_entry(vgpu->gtt.ggtt_mm, &entry, index++); + } index = vgpu_hidden_gmadr_base(vgpu) >> PAGE_SHIFT; num_entries = vgpu_hidden_sz(vgpu) >> PAGE_SHIFT; - while (num_entries--) + while (num_entries--) { + if (invalidate_old) { + ggtt_get_host_entry(vgpu->gtt.ggtt_mm, &old_entry, index); + ggtt_invalidate_pte(vgpu, &old_entry); + } ggtt_set_host_entry(vgpu->gtt.ggtt_mm, &entry, index++); + } ggtt_invalidate(dev_priv); } @@ -2360,5 +2398,5 @@ void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu) * removing the shadow pages. */ intel_vgpu_destroy_all_ppgtt_mm(vgpu); - intel_vgpu_reset_ggtt(vgpu); + intel_vgpu_reset_ggtt(vgpu, true); } diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index a8b369c..3792f2b 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -193,7 +193,7 @@ struct intel_vgpu_gtt { extern int intel_vgpu_init_gtt(struct intel_vgpu *vgpu); extern void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu); -void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu); +void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old); void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu); extern int intel_gvt_init_gtt(struct intel_gvt *gvt); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index c16a492..1466d87 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -1301,7 +1301,7 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd, } - return 0; + return -ENOTTY; } static ssize_t diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index a5bac83..0f94955 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -448,7 +448,7 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next, bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id) { - u32 *reg_state = ctx->engine[ring_id].lrc_reg_state; + u32 *reg_state = ctx->__engine[ring_id].lrc_reg_state; u32 inhibit_mask = _MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT); diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index d1a8fd8..ffb45a9 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -58,7 +58,7 @@ static void update_shadow_pdps(struct intel_vgpu_workload *workload) int ring_id = workload->ring_id; struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx; struct drm_i915_gem_object *ctx_obj = - shadow_ctx->engine[ring_id].state->obj; + shadow_ctx->__engine[ring_id].state->obj; struct execlist_ring_context *shadow_ring_context; struct page *page; @@ -130,7 +130,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload) int ring_id = workload->ring_id; struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx; struct drm_i915_gem_object *ctx_obj = - shadow_ctx->engine[ring_id].state->obj; + shadow_ctx->__engine[ring_id].state->obj; struct execlist_ring_context *shadow_ring_context; struct page *page; void *dst; @@ -283,7 +283,7 @@ static int shadow_context_status_change(struct notifier_block *nb, static void shadow_context_descriptor_update(struct i915_gem_context *ctx, struct intel_engine_cs *engine) { - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = to_intel_context(ctx, engine); u64 desc = 0; desc = ce->lrc_desc; @@ -389,7 +389,7 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload) * shadow_ctx pages invalid. So gvt need to pin itself. After update * the guest context, gvt can unpin the shadow_ctx safely. */ - ring = engine->context_pin(engine, shadow_ctx); + ring = intel_context_pin(shadow_ctx, engine); if (IS_ERR(ring)) { ret = PTR_ERR(ring); gvt_vgpu_err("fail to pin shadow context\n"); @@ -403,7 +403,7 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload) return 0; err_unpin: - engine->context_unpin(engine, shadow_ctx); + intel_context_unpin(shadow_ctx, engine); err_shadow: release_shadow_wa_ctx(&workload->wa_ctx); err_scan: @@ -437,7 +437,7 @@ static int intel_gvt_generate_request(struct intel_vgpu_workload *workload) return 0; err_unpin: - engine->context_unpin(engine, shadow_ctx); + intel_context_unpin(shadow_ctx, engine); release_shadow_wa_ctx(&workload->wa_ctx); return ret; } @@ -526,7 +526,7 @@ static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx) struct intel_vgpu_submission *s = &workload->vgpu->submission; struct i915_gem_context *shadow_ctx = s->shadow_ctx; struct drm_i915_gem_object *ctx_obj = - shadow_ctx->engine[ring_id].state->obj; + shadow_ctx->__engine[ring_id].state->obj; struct execlist_ring_context *shadow_ring_context; struct page *page; @@ -688,7 +688,7 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) ret = prepare_workload(workload); if (ret) { - engine->context_unpin(engine, shadow_ctx); + intel_context_unpin(shadow_ctx, engine); goto out; } @@ -771,7 +771,7 @@ static void update_guest_context(struct intel_vgpu_workload *workload) struct i915_gem_context *shadow_ctx = s->shadow_ctx; int ring_id = workload->ring_id; struct drm_i915_gem_object *ctx_obj = - shadow_ctx->engine[ring_id].state->obj; + shadow_ctx->__engine[ring_id].state->obj; struct execlist_ring_context *shadow_ring_context; struct page *page; void *src; @@ -898,7 +898,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) } mutex_lock(&dev_priv->drm.struct_mutex); /* unpin shadow ctx as the shadow_ctx update is done */ - engine->context_unpin(engine, s->shadow_ctx); + intel_context_unpin(s->shadow_ctx, engine); mutex_unlock(&dev_priv->drm.struct_mutex); } @@ -1157,7 +1157,7 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) return PTR_ERR(s->shadow_ctx); if (HAS_LOGICAL_RING_PREEMPTION(vgpu->gvt->dev_priv)) - s->shadow_ctx->priority = INT_MAX; + s->shadow_ctx->sched.priority = INT_MAX; bitmap_zero(s->shadow_ctx_desc_updated, I915_NUM_ENGINES); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 2e6652a..13e7b9e 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -377,16 +377,19 @@ static void print_batch_pool_stats(struct seq_file *m, print_file_stats(m, "[k]batch pool", stats); } -static int per_file_ctx_stats(int id, void *ptr, void *data) +static int per_file_ctx_stats(int idx, void *ptr, void *data) { struct i915_gem_context *ctx = ptr; - int n; + struct intel_engine_cs *engine; + enum intel_engine_id id; + + for_each_engine(engine, ctx->i915, id) { + struct intel_context *ce = to_intel_context(ctx, engine); - for (n = 0; n < ARRAY_SIZE(ctx->engine); n++) { - if (ctx->engine[n].state) - per_file_stats(0, ctx->engine[n].state->obj, data); - if (ctx->engine[n].ring) - per_file_stats(0, ctx->engine[n].ring->vma->obj, data); + if (ce->state) + per_file_stats(0, ce->state->obj, data); + if (ce->ring) + per_file_stats(0, ce->ring->vma->obj, data); } return 0; @@ -1340,10 +1343,9 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused) struct rb_node *rb; seq_printf(m, "%s:\n", engine->name); - seq_printf(m, "\tseqno = %x [current %x, last %x], inflight %d\n", + seq_printf(m, "\tseqno = %x [current %x, last %x]\n", engine->hangcheck.seqno, seqno[id], - intel_engine_last_submit(engine), - engine->timeline->inflight_seqnos); + intel_engine_last_submit(engine)); seq_printf(m, "\twaiters? %s, fake irq active? %s, stalled? %s\n", yesno(intel_engine_has_waiter(engine)), yesno(test_bit(engine->id, @@ -1960,7 +1962,8 @@ static int i915_context_status(struct seq_file *m, void *unused) seq_putc(m, '\n'); for_each_engine(engine, dev_priv, id) { - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = + to_intel_context(ctx, engine); seq_printf(m, "%s: ", engine->name); if (ce->state) @@ -2603,6 +2606,26 @@ static const char *psr2_live_status(u32 val) return "unknown"; } +static const char *psr_sink_status(u8 val) +{ + static const char * const sink_status[] = { + "inactive", + "transition to active, capture and display", + "active, display from RFB", + "active, capture and display on sink device timings", + "transition to inactive, capture and display, timing re-sync", + "reserved", + "reserved", + "sink internal error" + }; + + val &= DP_PSR_SINK_STATE_MASK; + if (val < ARRAY_SIZE(sink_status)) + return sink_status[val]; + + return "unknown"; +} + static int i915_edp_psr_status(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -2684,12 +2707,61 @@ static int i915_edp_psr_status(struct seq_file *m, void *data) seq_printf(m, "EDP_PSR2_STATUS: %x [%s]\n", psr2, psr2_live_status(psr2)); } + + if (dev_priv->psr.enabled) { + struct drm_dp_aux *aux = &dev_priv->psr.enabled->aux; + u8 val; + + if (drm_dp_dpcd_readb(aux, DP_PSR_STATUS, &val) == 1) + seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val, + psr_sink_status(val)); + } mutex_unlock(&dev_priv->psr.lock); + if (READ_ONCE(dev_priv->psr.debug)) { + seq_printf(m, "Last attempted entry at: %lld\n", + dev_priv->psr.last_entry_attempt); + seq_printf(m, "Last exit at: %lld\n", + dev_priv->psr.last_exit); + } + + intel_runtime_pm_put(dev_priv); + return 0; +} + +static int +i915_edp_psr_debug_set(void *data, u64 val) +{ + struct drm_i915_private *dev_priv = data; + + if (!CAN_PSR(dev_priv)) + return -ENODEV; + + DRM_DEBUG_KMS("PSR debug %s\n", enableddisabled(val)); + + intel_runtime_pm_get(dev_priv); + intel_psr_irq_control(dev_priv, !!val); intel_runtime_pm_put(dev_priv); + return 0; } +static int +i915_edp_psr_debug_get(void *data, u64 *val) +{ + struct drm_i915_private *dev_priv = data; + + if (!CAN_PSR(dev_priv)) + return -ENODEV; + + *val = READ_ONCE(dev_priv->psr.debug); + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(i915_edp_psr_debug_fops, + i915_edp_psr_debug_get, i915_edp_psr_debug_set, + "%llu\n"); + static int i915_sink_crc(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -3296,6 +3368,28 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused) seq_printf(m, " fp0: 0x%08x\n", pll->state.hw_state.fp0); seq_printf(m, " fp1: 0x%08x\n", pll->state.hw_state.fp1); seq_printf(m, " wrpll: 0x%08x\n", pll->state.hw_state.wrpll); + seq_printf(m, " cfgcr0: 0x%08x\n", pll->state.hw_state.cfgcr0); + seq_printf(m, " cfgcr1: 0x%08x\n", pll->state.hw_state.cfgcr1); + seq_printf(m, " mg_refclkin_ctl: 0x%08x\n", + pll->state.hw_state.mg_refclkin_ctl); + seq_printf(m, " mg_clktop2_coreclkctl1: 0x%08x\n", + pll->state.hw_state.mg_clktop2_coreclkctl1); + seq_printf(m, " mg_clktop2_hsclkctl: 0x%08x\n", + pll->state.hw_state.mg_clktop2_hsclkctl); + seq_printf(m, " mg_pll_div0: 0x%08x\n", + pll->state.hw_state.mg_pll_div0); + seq_printf(m, " mg_pll_div1: 0x%08x\n", + pll->state.hw_state.mg_pll_div1); + seq_printf(m, " mg_pll_lf: 0x%08x\n", + pll->state.hw_state.mg_pll_lf); + seq_printf(m, " mg_pll_frac_lock: 0x%08x\n", + pll->state.hw_state.mg_pll_frac_lock); + seq_printf(m, " mg_pll_ssc: 0x%08x\n", + pll->state.hw_state.mg_pll_ssc); + seq_printf(m, " mg_pll_bias: 0x%08x\n", + pll->state.hw_state.mg_pll_bias); + seq_printf(m, " mg_pll_tdc_coldst_bias: 0x%08x\n", + pll->state.hw_state.mg_pll_tdc_coldst_bias); } drm_modeset_unlock_all(dev); @@ -3304,24 +3398,13 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused) static int i915_wa_registers(struct seq_file *m, void *unused) { - int i; - int ret; - struct intel_engine_cs *engine; struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_device *dev = &dev_priv->drm; struct i915_workarounds *workarounds = &dev_priv->workarounds; - enum intel_engine_id id; - - ret = mutex_lock_interruptible(&dev->struct_mutex); - if (ret) - return ret; + int i; intel_runtime_pm_get(dev_priv); seq_printf(m, "Workarounds applied: %d\n", workarounds->count); - for_each_engine(engine, dev_priv, id) - seq_printf(m, "HW whitelist count for %s: %d\n", - engine->name, workarounds->hw_whitelist_count[id]); for (i = 0; i < workarounds->count; ++i) { i915_reg_t addr; u32 mask, value, read; @@ -3337,7 +3420,6 @@ static int i915_wa_registers(struct seq_file *m, void *unused) } intel_runtime_pm_put(dev_priv); - mutex_unlock(&dev->struct_mutex); return 0; } @@ -4177,119 +4259,6 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_drop_caches_fops, "0x%08llx\n"); static int -i915_max_freq_get(void *data, u64 *val) -{ - struct drm_i915_private *dev_priv = data; - - if (INTEL_GEN(dev_priv) < 6) - return -ENODEV; - - *val = intel_gpu_freq(dev_priv, dev_priv->gt_pm.rps.max_freq_softlimit); - return 0; -} - -static int -i915_max_freq_set(void *data, u64 val) -{ - struct drm_i915_private *dev_priv = data; - struct intel_rps *rps = &dev_priv->gt_pm.rps; - u32 hw_max, hw_min; - int ret; - - if (INTEL_GEN(dev_priv) < 6) - return -ENODEV; - - DRM_DEBUG_DRIVER("Manually setting max freq to %llu\n", val); - - ret = mutex_lock_interruptible(&dev_priv->pcu_lock); - if (ret) - return ret; - - /* - * Turbo will still be enabled, but won't go above the set value. - */ - val = intel_freq_opcode(dev_priv, val); - - hw_max = rps->max_freq; - hw_min = rps->min_freq; - - if (val < hw_min || val > hw_max || val < rps->min_freq_softlimit) { - mutex_unlock(&dev_priv->pcu_lock); - return -EINVAL; - } - - rps->max_freq_softlimit = val; - - if (intel_set_rps(dev_priv, val)) - DRM_DEBUG_DRIVER("failed to update RPS to new softlimit\n"); - - mutex_unlock(&dev_priv->pcu_lock); - - return 0; -} - -DEFINE_SIMPLE_ATTRIBUTE(i915_max_freq_fops, - i915_max_freq_get, i915_max_freq_set, - "%llu\n"); - -static int -i915_min_freq_get(void *data, u64 *val) -{ - struct drm_i915_private *dev_priv = data; - - if (INTEL_GEN(dev_priv) < 6) - return -ENODEV; - - *val = intel_gpu_freq(dev_priv, dev_priv->gt_pm.rps.min_freq_softlimit); - return 0; -} - -static int -i915_min_freq_set(void *data, u64 val) -{ - struct drm_i915_private *dev_priv = data; - struct intel_rps *rps = &dev_priv->gt_pm.rps; - u32 hw_max, hw_min; - int ret; - - if (INTEL_GEN(dev_priv) < 6) - return -ENODEV; - - DRM_DEBUG_DRIVER("Manually setting min freq to %llu\n", val); - - ret = mutex_lock_interruptible(&dev_priv->pcu_lock); - if (ret) - return ret; - - /* - * Turbo will still be enabled, but won't go below the set value. - */ - val = intel_freq_opcode(dev_priv, val); - - hw_max = rps->max_freq; - hw_min = rps->min_freq; - - if (val < hw_min || - val > hw_max || val > rps->max_freq_softlimit) { - mutex_unlock(&dev_priv->pcu_lock); - return -EINVAL; - } - - rps->min_freq_softlimit = val; - - if (intel_set_rps(dev_priv, val)) - DRM_DEBUG_DRIVER("failed to update RPS to new softlimit\n"); - - mutex_unlock(&dev_priv->pcu_lock); - - return 0; -} - -DEFINE_SIMPLE_ATTRIBUTE(i915_min_freq_fops, - i915_min_freq_get, i915_min_freq_set, - "%llu\n"); - -static int i915_cache_sharing_get(void *data, u64 *val) { struct drm_i915_private *dev_priv = data; @@ -4850,8 +4819,6 @@ static const struct i915_debugfs_files { const struct file_operations *fops; } i915_debugfs_files[] = { {"i915_wedged", &i915_wedged_fops}, - {"i915_max_freq", &i915_max_freq_fops}, - {"i915_min_freq", &i915_min_freq_fops}, {"i915_cache_sharing", &i915_cache_sharing_fops}, {"i915_ring_missed_irq", &i915_ring_missed_irq_fops}, {"i915_ring_test_irq", &i915_ring_test_irq_fops}, @@ -4874,7 +4841,8 @@ static const struct i915_debugfs_files { {"i915_guc_log_relay", &i915_guc_log_relay_fops}, {"i915_hpd_storm_ctl", &i915_hpd_storm_ctl_fops}, {"i915_ipc_status", &i915_ipc_status_fops}, - {"i915_drrs_ctl", &i915_drrs_ctl_fops} + {"i915_drrs_ctl", &i915_drrs_ctl_fops}, + {"i915_edp_psr_debug", &i915_edp_psr_debug_fops} }; int i915_debugfs_register(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f770be1..2a96d08 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -101,7 +101,13 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level, __builtin_return_address(0), &vaf); if (is_error && !shown_bug_once) { - dev_notice(kdev, "%s", FDO_BUG_MSG); + /* + * Ask the user to file a bug report for the error, except + * if they may have caused the bug by fiddling with unsafe + * module parameters. + */ + if (!test_taint(TAINT_USER)) + dev_notice(kdev, "%s", FDO_BUG_MSG); shown_bug_once = true; } @@ -449,7 +455,10 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data, static int i915_get_bridge_dev(struct drm_i915_private *dev_priv) { - dev_priv->bridge_dev = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0)); + int domain = pci_domain_nr(dev_priv->drm.pdev->bus); + + dev_priv->bridge_dev = + pci_get_domain_bus_and_slot(domain, 0, PCI_DEVFN(0, 0)); if (!dev_priv->bridge_dev) { DRM_ERROR("bridge device not found\n"); return -1; @@ -1101,30 +1110,32 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) ret = i915_ggtt_probe_hw(dev_priv); if (ret) - return ret; + goto err_perf; - /* WARNING: Apparently we must kick fbdev drivers before vgacon, - * otherwise the vga fbdev driver falls over. */ + /* + * WARNING: Apparently we must kick fbdev drivers before vgacon, + * otherwise the vga fbdev driver falls over. + */ ret = i915_kick_out_firmware_fb(dev_priv); if (ret) { DRM_ERROR("failed to remove conflicting framebuffer drivers\n"); - goto out_ggtt; + goto err_ggtt; } ret = i915_kick_out_vgacon(dev_priv); if (ret) { DRM_ERROR("failed to remove conflicting VGA console\n"); - goto out_ggtt; + goto err_ggtt; } ret = i915_ggtt_init_hw(dev_priv); if (ret) - return ret; + goto err_ggtt; ret = i915_ggtt_enable_hw(dev_priv); if (ret) { DRM_ERROR("failed to enable GGTT\n"); - goto out_ggtt; + goto err_ggtt; } pci_set_master(pdev); @@ -1135,7 +1146,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) if (ret) { DRM_ERROR("failed to set DMA mask\n"); - goto out_ggtt; + goto err_ggtt; } } @@ -1153,7 +1164,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) if (ret) { DRM_ERROR("failed to set DMA mask\n"); - goto out_ggtt; + goto err_ggtt; } } @@ -1186,13 +1197,14 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) ret = intel_gvt_init(dev_priv); if (ret) - goto out_ggtt; + goto err_ggtt; return 0; -out_ggtt: +err_ggtt: i915_ggtt_cleanup_hw(dev_priv); - +err_perf: + i915_perf_fini(dev_priv); return ret; } @@ -2462,10 +2474,13 @@ static void vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv, /* * RC6 transitioning can be delayed up to 2 msec (see * valleyview_enable_rps), use 3 msec for safety. + * + * This can fail to turn off the rc6 if the GPU is stuck after a failed + * reset and we are trying to force the machine to sleep. */ if (vlv_wait_for_pw_status(dev_priv, mask, val)) - DRM_ERROR("timeout waiting for GT wells to go %s\n", - onoff(wait_for_on)); + DRM_DEBUG_DRIVER("timeout waiting for GT wells to go %s\n", + onoff(wait_for_on)); } static void vlv_check_no_gt_access(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index e50d958..57fb3aa 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -72,9 +72,10 @@ #include "i915_gem_fence_reg.h" #include "i915_gem_object.h" #include "i915_gem_gtt.h" -#include "i915_gem_timeline.h" #include "i915_gpu_error.h" #include "i915_request.h" +#include "i915_scheduler.h" +#include "i915_timeline.h" #include "i915_vma.h" #include "intel_gvt.h" @@ -609,6 +610,9 @@ struct i915_psr { bool has_hw_tracking; bool psr2_enabled; u8 sink_sync_latency; + bool debug; + ktime_t last_entry_attempt; + ktime_t last_exit; void (*enable_source)(struct intel_dp *, const struct intel_crtc_state *); @@ -1069,6 +1073,7 @@ struct intel_vbt_data { } edp; struct { + bool enable; bool full_link; bool require_aux_wakeup; int idle_frames; @@ -1185,6 +1190,7 @@ struct skl_ddb_allocation { /* packed/y */ struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES]; struct skl_ddb_entry uv_plane[I915_MAX_PIPES][I915_MAX_PLANES]; + u8 enabled_slices; /* GEN11 has configurable 2 slices */ }; struct skl_ddb_values { @@ -1297,7 +1303,6 @@ struct i915_wa_reg { struct i915_workarounds { struct i915_wa_reg reg[I915_MAX_WA_REGS]; u32 count; - u32 hw_whitelist_count[I915_NUM_ENGINES]; }; struct i915_virtual_gpu { @@ -2056,8 +2061,11 @@ struct drm_i915_private { void (*cleanup_engine)(struct intel_engine_cs *engine); struct list_head timelines; - struct i915_gem_timeline global_timeline; + + struct list_head active_rings; + struct list_head closed_vma; u32 active_requests; + u32 request_serial; /** * Is the GPU currently considered idle, or busy executing @@ -2462,6 +2470,15 @@ intel_info(const struct drm_i915_private *dev_priv) #define IS_CNL_REVID(p, since, until) \ (IS_CANNONLAKE(p) && IS_REVID(p, since, until)) +#define ICL_REVID_A0 0x0 +#define ICL_REVID_A2 0x1 +#define ICL_REVID_B0 0x3 +#define ICL_REVID_B2 0x4 +#define ICL_REVID_C0 0x5 + +#define IS_ICL_REVID(p, since, until) \ + (IS_ICELAKE(p) && IS_REVID(p, since, until)) + /* * The genX designation typically refers to the render engine, so render * capability related checks should use IS_GEN, while display and other checks @@ -3159,7 +3176,7 @@ int i915_gem_object_wait(struct drm_i915_gem_object *obj, struct intel_rps_client *rps); int i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, unsigned int flags, - int priority); + const struct i915_sched_attr *attr); #define I915_PRIORITY_DISPLAY I915_PRIORITY_MAX int __must_check @@ -3228,16 +3245,6 @@ i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id) return ctx; } -static inline struct intel_timeline * -i915_gem_context_lookup_timeline(struct i915_gem_context *ctx, - struct intel_engine_cs *engine) -{ - struct i915_address_space *vm; - - vm = ctx->ppgtt ? &ctx->ppgtt->base : &ctx->i915->ggtt.base; - return &vm->timeline.engine[engine->id]; -} - int i915_perf_open_ioctl(struct drm_device *dev, void *data, struct drm_file *file); int i915_perf_add_config_ioctl(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 4c9d2a6..89bf5d6 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -141,6 +141,7 @@ static u32 __i915_gem_park(struct drm_i915_private *i915) { lockdep_assert_held(&i915->drm.struct_mutex); GEM_BUG_ON(i915->gt.active_requests); + GEM_BUG_ON(!list_empty(&i915->gt.active_rings)); if (!i915->gt.awake) return I915_EPOCH_INVALID; @@ -161,9 +162,10 @@ static u32 __i915_gem_park(struct drm_i915_private *i915) synchronize_irq(i915->drm.irq); intel_engines_park(i915); - i915_gem_timelines_park(i915); + i915_timelines_park(i915); i915_pmu_gt_parked(i915); + i915_vma_parked(i915); i915->gt.awake = false; @@ -564,7 +566,8 @@ i915_gem_object_wait_reservation(struct reservation_object *resv, return timeout; } -static void __fence_set_priority(struct dma_fence *fence, int prio) +static void __fence_set_priority(struct dma_fence *fence, + const struct i915_sched_attr *attr) { struct i915_request *rq; struct intel_engine_cs *engine; @@ -575,13 +578,16 @@ static void __fence_set_priority(struct dma_fence *fence, int prio) rq = to_request(fence); engine = rq->engine; - rcu_read_lock(); + local_bh_disable(); + rcu_read_lock(); /* RCU serialisation for set-wedged protection */ if (engine->schedule) - engine->schedule(rq, prio); + engine->schedule(rq, attr); rcu_read_unlock(); + local_bh_enable(); /* kick the tasklets if queues were reprioritised */ } -static void fence_set_priority(struct dma_fence *fence, int prio) +static void fence_set_priority(struct dma_fence *fence, + const struct i915_sched_attr *attr) { /* Recurse once into a fence-array */ if (dma_fence_is_array(fence)) { @@ -589,16 +595,16 @@ static void fence_set_priority(struct dma_fence *fence, int prio) int i; for (i = 0; i < array->num_fences; i++) - __fence_set_priority(array->fences[i], prio); + __fence_set_priority(array->fences[i], attr); } else { - __fence_set_priority(fence, prio); + __fence_set_priority(fence, attr); } } int i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, unsigned int flags, - int prio) + const struct i915_sched_attr *attr) { struct dma_fence *excl; @@ -613,7 +619,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, return ret; for (i = 0; i < count; i++) { - fence_set_priority(shared[i], prio); + fence_set_priority(shared[i], attr); dma_fence_put(shared[i]); } @@ -623,7 +629,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, } if (excl) { - fence_set_priority(excl, prio); + fence_set_priority(excl, attr); dma_fence_put(excl); } return 0; @@ -2974,8 +2980,8 @@ i915_gem_find_active_request(struct intel_engine_cs *engine) * extra delay for a recent interrupt is pointless. Hence, we do * not need an engine->irq_seqno_barrier() before the seqno reads. */ - spin_lock_irqsave(&engine->timeline->lock, flags); - list_for_each_entry(request, &engine->timeline->requests, link) { + spin_lock_irqsave(&engine->timeline.lock, flags); + list_for_each_entry(request, &engine->timeline.requests, link) { if (__i915_request_completed(request, request->global_seqno)) continue; @@ -2986,7 +2992,7 @@ i915_gem_find_active_request(struct intel_engine_cs *engine) active = request; break; } - spin_unlock_irqrestore(&engine->timeline->lock, flags); + spin_unlock_irqrestore(&engine->timeline.lock, flags); return active; } @@ -3107,15 +3113,15 @@ static void engine_skip_context(struct i915_request *request) { struct intel_engine_cs *engine = request->engine; struct i915_gem_context *hung_ctx = request->ctx; - struct intel_timeline *timeline; + struct i915_timeline *timeline = request->timeline; unsigned long flags; - timeline = i915_gem_context_lookup_timeline(hung_ctx, engine); + GEM_BUG_ON(timeline == &engine->timeline); - spin_lock_irqsave(&engine->timeline->lock, flags); + spin_lock_irqsave(&engine->timeline.lock, flags); spin_lock(&timeline->lock); - list_for_each_entry_continue(request, &engine->timeline->requests, link) + list_for_each_entry_continue(request, &engine->timeline.requests, link) if (request->ctx == hung_ctx) skip_request(request); @@ -3123,7 +3129,7 @@ static void engine_skip_context(struct i915_request *request) skip_request(request); spin_unlock(&timeline->lock); - spin_unlock_irqrestore(&engine->timeline->lock, flags); + spin_unlock_irqrestore(&engine->timeline.lock, flags); } /* Returns the request if it was guilty of the hang */ @@ -3180,11 +3186,11 @@ i915_gem_reset_request(struct intel_engine_cs *engine, dma_fence_set_error(&request->fence, -EAGAIN); /* Rewind the engine to replay the incomplete rq */ - spin_lock_irq(&engine->timeline->lock); + spin_lock_irq(&engine->timeline.lock); request = list_prev_entry(request, link); - if (&request->link == &engine->timeline->requests) + if (&request->link == &engine->timeline.requests) request = NULL; - spin_unlock_irq(&engine->timeline->lock); + spin_unlock_irq(&engine->timeline.lock); } } @@ -3232,7 +3238,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv, stalled_mask & ENGINE_MASK(id)); ctx = fetch_and_zero(&engine->last_retired_context); if (ctx) - engine->context_unpin(engine, ctx); + intel_context_unpin(ctx, engine); /* * Ostensibily, we always want a context loaded for powersaving, @@ -3297,10 +3303,10 @@ static void nop_complete_submit_request(struct i915_request *request) request->fence.context, request->fence.seqno); dma_fence_set_error(&request->fence, -EIO); - spin_lock_irqsave(&request->engine->timeline->lock, flags); + spin_lock_irqsave(&request->engine->timeline.lock, flags); __i915_request_submit(request); intel_engine_init_global_seqno(request->engine, request->global_seqno); - spin_unlock_irqrestore(&request->engine->timeline->lock, flags); + spin_unlock_irqrestore(&request->engine->timeline.lock, flags); } void i915_gem_set_wedged(struct drm_i915_private *i915) @@ -3310,7 +3316,7 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) GEM_TRACE("start\n"); - if (drm_debug & DRM_UT_DRIVER) { + if (GEM_SHOW_DEBUG()) { struct drm_printer p = drm_debug_printer(__func__); for_each_engine(engine, i915, id) @@ -3369,10 +3375,10 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) * (lockless) lookup doesn't try and wait upon the request as we * reset it. */ - spin_lock_irqsave(&engine->timeline->lock, flags); + spin_lock_irqsave(&engine->timeline.lock, flags); intel_engine_init_global_seqno(engine, intel_engine_last_submit(engine)); - spin_unlock_irqrestore(&engine->timeline->lock, flags); + spin_unlock_irqrestore(&engine->timeline.lock, flags); i915_gem_reset_finish_engine(engine); } @@ -3384,8 +3390,7 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) bool i915_gem_unset_wedged(struct drm_i915_private *i915) { - struct i915_gem_timeline *tl; - int i; + struct i915_timeline *tl; lockdep_assert_held(&i915->drm.struct_mutex); if (!test_bit(I915_WEDGED, &i915->gpu_error.flags)) @@ -3404,29 +3409,27 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915) * No more can be submitted until we reset the wedged bit. */ list_for_each_entry(tl, &i915->gt.timelines, link) { - for (i = 0; i < ARRAY_SIZE(tl->engine); i++) { - struct i915_request *rq; + struct i915_request *rq; - rq = i915_gem_active_peek(&tl->engine[i].last_request, - &i915->drm.struct_mutex); - if (!rq) - continue; + rq = i915_gem_active_peek(&tl->last_request, + &i915->drm.struct_mutex); + if (!rq) + continue; - /* - * We can't use our normal waiter as we want to - * avoid recursively trying to handle the current - * reset. The basic dma_fence_default_wait() installs - * a callback for dma_fence_signal(), which is - * triggered by our nop handler (indirectly, the - * callback enables the signaler thread which is - * woken by the nop_submit_request() advancing the seqno - * and when the seqno passes the fence, the signaler - * then signals the fence waking us up). - */ - if (dma_fence_default_wait(&rq->fence, true, - MAX_SCHEDULE_TIMEOUT) < 0) - return false; - } + /* + * We can't use our normal waiter as we want to + * avoid recursively trying to handle the current + * reset. The basic dma_fence_default_wait() installs + * a callback for dma_fence_signal(), which is + * triggered by our nop handler (indirectly, the + * callback enables the signaler thread which is + * woken by the nop_submit_request() advancing the seqno + * and when the seqno passes the fence, the signaler + * then signals the fence waking us up). + */ + if (dma_fence_default_wait(&rq->fence, true, + MAX_SCHEDULE_TIMEOUT) < 0) + return false; } i915_retire_requests(i915); GEM_BUG_ON(i915->gt.active_requests); @@ -3731,17 +3734,9 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) return ret; } -static int wait_for_timeline(struct i915_gem_timeline *tl, unsigned int flags) +static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags) { - int ret, i; - - for (i = 0; i < ARRAY_SIZE(tl->engine); i++) { - ret = i915_gem_active_wait(&tl->engine[i].last_request, flags); - if (ret) - return ret; - } - - return 0; + return i915_gem_active_wait(&tl->last_request, flags); } static int wait_for_engines(struct drm_i915_private *i915) @@ -3759,30 +3754,37 @@ static int wait_for_engines(struct drm_i915_private *i915) int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags) { - int ret; - /* If the device is asleep, we have no requests outstanding */ if (!READ_ONCE(i915->gt.awake)) return 0; if (flags & I915_WAIT_LOCKED) { - struct i915_gem_timeline *tl; + struct i915_timeline *tl; + int err; lockdep_assert_held(&i915->drm.struct_mutex); list_for_each_entry(tl, &i915->gt.timelines, link) { - ret = wait_for_timeline(tl, flags); - if (ret) - return ret; + err = wait_for_timeline(tl, flags); + if (err) + return err; } i915_retire_requests(i915); - ret = wait_for_engines(i915); + return wait_for_engines(i915); } else { - ret = wait_for_timeline(&i915->gt.global_timeline, flags); - } + struct intel_engine_cs *engine; + enum intel_engine_id id; + int err; - return ret; + for_each_engine(engine, i915, id) { + err = wait_for_timeline(&engine->timeline, flags); + if (err) + return err; + } + + return 0; + } } static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj) @@ -4796,7 +4798,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, &obj->vma_list, obj_link) { GEM_BUG_ON(i915_vma_is_active(vma)); vma->flags &= ~I915_VMA_PIN_MASK; - i915_vma_close(vma); + i915_vma_destroy(vma); } GEM_BUG_ON(!list_empty(&obj->vma_list)); GEM_BUG_ON(!RB_EMPTY_ROOT(&obj->vma_tree)); @@ -4951,7 +4953,7 @@ static void assert_kernel_context_is_current(struct drm_i915_private *i915) enum intel_engine_id id; for_each_engine(engine, i915, id) { - GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline->last_request)); + GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request)); GEM_BUG_ON(engine->last_retired_context != kernel_context); } } @@ -5289,7 +5291,7 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915) for_each_engine(engine, i915, id) { struct i915_vma *state; - state = ctx->engine[id].state; + state = to_intel_context(ctx, engine)->state; if (!state) continue; @@ -5597,12 +5599,9 @@ int i915_gem_init_early(struct drm_i915_private *dev_priv) if (!dev_priv->priorities) goto err_dependencies; - mutex_lock(&dev_priv->drm.struct_mutex); INIT_LIST_HEAD(&dev_priv->gt.timelines); - err = i915_gem_timeline_init__global(dev_priv); - mutex_unlock(&dev_priv->drm.struct_mutex); - if (err) - goto err_priorities; + INIT_LIST_HEAD(&dev_priv->gt.active_rings); + INIT_LIST_HEAD(&dev_priv->gt.closed_vma); i915_gem_init__mm(dev_priv); @@ -5623,8 +5622,6 @@ int i915_gem_init_early(struct drm_i915_private *dev_priv) return 0; -err_priorities: - kmem_cache_destroy(dev_priv->priorities); err_dependencies: kmem_cache_destroy(dev_priv->dependencies); err_requests: @@ -5645,11 +5642,7 @@ void i915_gem_cleanup_early(struct drm_i915_private *dev_priv) GEM_BUG_ON(!llist_empty(&dev_priv->mm.free_list)); GEM_BUG_ON(atomic_read(&dev_priv->mm.free_count)); WARN_ON(dev_priv->mm.object_count); - - mutex_lock(&dev_priv->drm.struct_mutex); - i915_gem_timeline_fini(&dev_priv->gt.global_timeline); WARN_ON(!list_empty(&dev_priv->gt.timelines)); - mutex_unlock(&dev_priv->drm.struct_mutex); kmem_cache_destroy(dev_priv->priorities); kmem_cache_destroy(dev_priv->dependencies); diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h index deaf78d..5259204 100644 --- a/drivers/gpu/drm/i915/i915_gem.h +++ b/drivers/gpu/drm/i915/i915_gem.h @@ -30,6 +30,9 @@ struct drm_i915_private; #ifdef CONFIG_DRM_I915_DEBUG_GEM + +#define GEM_SHOW_DEBUG() (drm_debug & DRM_UT_DRIVER) + #define GEM_BUG_ON(condition) do { if (unlikely((condition))) { \ pr_err("%s:%d GEM_BUG_ON(%s)\n", \ __func__, __LINE__, __stringify(condition)); \ @@ -45,6 +48,9 @@ struct drm_i915_private; #define GEM_DEBUG_BUG_ON(expr) GEM_BUG_ON(expr) #else + +#define GEM_SHOW_DEBUG() (0) + #define GEM_BUG_ON(expr) BUILD_BUG_ON_INVALID(expr) #define GEM_WARN_ON(expr) (BUILD_BUG_ON_INVALID(expr), 0) diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 9b3834a..33f8a4b 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -117,15 +117,15 @@ static void lut_close(struct i915_gem_context *ctx) static void i915_gem_context_free(struct i915_gem_context *ctx) { - int i; + unsigned int n; lockdep_assert_held(&ctx->i915->drm.struct_mutex); GEM_BUG_ON(!i915_gem_context_is_closed(ctx)); i915_ppgtt_put(ctx->ppgtt); - for (i = 0; i < I915_NUM_ENGINES; i++) { - struct intel_context *ce = &ctx->engine[i]; + for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) { + struct intel_context *ce = &ctx->__engine[n]; if (!ce->state) continue; @@ -281,7 +281,7 @@ __create_hw_context(struct drm_i915_private *dev_priv, kref_init(&ctx->ref); list_add_tail(&ctx->link, &dev_priv->contexts.list); ctx->i915 = dev_priv; - ctx->priority = I915_PRIORITY_NORMAL; + ctx->sched.priority = I915_PRIORITY_NORMAL; INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL); INIT_LIST_HEAD(&ctx->handles_list); @@ -431,7 +431,7 @@ i915_gem_context_create_kernel(struct drm_i915_private *i915, int prio) return ctx; i915_gem_context_clear_bannable(ctx); - ctx->priority = prio; + ctx->sched.priority = prio; ctx->ring_size = PAGE_SIZE; GEM_BUG_ON(!i915_gem_context_is_kernel(ctx)); @@ -521,7 +521,7 @@ void i915_gem_contexts_lost(struct drm_i915_private *dev_priv) if (!engine->last_retired_context) continue; - engine->context_unpin(engine, engine->last_retired_context); + intel_context_unpin(engine->last_retired_context, engine); engine->last_retired_context = NULL; } } @@ -577,19 +577,29 @@ void i915_gem_context_close(struct drm_file *file) idr_destroy(&file_priv->context_idr); } -static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine) +static struct i915_request * +last_request_on_engine(struct i915_timeline *timeline, + struct intel_engine_cs *engine) { - struct i915_gem_timeline *timeline; + struct i915_request *rq; - list_for_each_entry(timeline, &engine->i915->gt.timelines, link) { - struct intel_timeline *tl; + if (timeline == &engine->timeline) + return NULL; - if (timeline == &engine->i915->gt.global_timeline) - continue; + rq = i915_gem_active_raw(&timeline->last_request, + &engine->i915->drm.struct_mutex); + if (rq && rq->engine == engine) + return rq; + + return NULL; +} - tl = &timeline->engine[engine->id]; - if (i915_gem_active_peek(&tl->last_request, - &engine->i915->drm.struct_mutex)) +static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine) +{ + struct i915_timeline *timeline; + + list_for_each_entry(timeline, &engine->i915->gt.timelines, link) { + if (last_request_on_engine(timeline, engine)) return false; } @@ -599,7 +609,7 @@ static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine) int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv) { struct intel_engine_cs *engine; - struct i915_gem_timeline *timeline; + struct i915_timeline *timeline; enum intel_engine_id id; lockdep_assert_held(&dev_priv->drm.struct_mutex); @@ -619,11 +629,8 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv) /* Queue this switch after all other activity */ list_for_each_entry(timeline, &dev_priv->gt.timelines, link) { struct i915_request *prev; - struct intel_timeline *tl; - tl = &timeline->engine[engine->id]; - prev = i915_gem_active_raw(&tl->last_request, - &dev_priv->drm.struct_mutex); + prev = last_request_on_engine(timeline, engine); if (prev) i915_sw_fence_await_sw_fence_gfp(&rq->submit, &prev->submit, @@ -753,7 +760,7 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, args->value = i915_gem_context_is_bannable(ctx); break; case I915_CONTEXT_PARAM_PRIORITY: - args->value = ctx->priority; + args->value = ctx->sched.priority; break; default: ret = -EINVAL; @@ -826,7 +833,7 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data, !capable(CAP_SYS_NICE)) ret = -EPERM; else - ctx->priority = priority; + ctx->sched.priority = priority; } break; diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h index 7854262..ace3b12 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.h +++ b/drivers/gpu/drm/i915/i915_gem_context.h @@ -137,18 +137,7 @@ struct i915_gem_context { */ u32 user_handle; - /** - * @priority: execution and service priority - * - * All clients are equal, but some are more equal than others! - * - * Requests from a context with a greater (more positive) value of - * @priority will be executed before those with a lower @priority - * value, forming a simple QoS. - * - * The &drm_i915_private.kernel_context is assigned the lowest priority. - */ - int priority; + struct i915_sched_attr sched; /** ggtt_offset_bias: placement restriction for context objects */ u32 ggtt_offset_bias; @@ -160,7 +149,7 @@ struct i915_gem_context { u32 *lrc_reg_state; u64 lrc_desc; int pin_count; - } engine[I915_NUM_ENGINES]; + } __engine[I915_NUM_ENGINES]; /** ring_size: size for allocating the per-engine ring buffer */ u32 ring_size; @@ -267,6 +256,34 @@ static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx) return !ctx->file_priv; } +static inline struct intel_context * +to_intel_context(struct i915_gem_context *ctx, + const struct intel_engine_cs *engine) +{ + return &ctx->__engine[engine->id]; +} + +static inline struct intel_ring * +intel_context_pin(struct i915_gem_context *ctx, struct intel_engine_cs *engine) +{ + return engine->context_pin(engine, ctx); +} + +static inline void __intel_context_pin(struct i915_gem_context *ctx, + const struct intel_engine_cs *engine) +{ + struct intel_context *ce = to_intel_context(ctx, engine); + + GEM_BUG_ON(!ce->pin_count); + ce->pin_count++; +} + +static inline void intel_context_unpin(struct i915_gem_context *ctx, + struct intel_engine_cs *engine) +{ + engine->context_unpin(engine, ctx); +} + /* i915_gem_context.c */ int __must_check i915_gem_contexts_init(struct drm_i915_private *dev_priv); void i915_gem_contexts_lost(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index c74f5df..f627a8c 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -762,7 +762,8 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) } /* transfer ref to ctx */ - vma->open_count++; + if (!vma->open_count++) + i915_vma_reopen(vma); list_add(&lut->obj_link, &obj->lut_list); list_add(&lut->ctx_link, &eb->ctx->handles_list); lut->ctx = eb->ctx; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 21d72f6..996ab2a 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -110,7 +110,8 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma); static void gen6_ggtt_invalidate(struct drm_i915_private *dev_priv) { - /* Note that as an uncached mmio write, this should flush the + /* + * Note that as an uncached mmio write, this will flush the * WCB of the writes into the GGTT before it triggers the invalidate. */ I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); @@ -1161,6 +1162,27 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma, vaddr[idx.pde] |= GEN8_PDE_IPS_64K; kunmap_atomic(vaddr); page_size = I915_GTT_PAGE_SIZE_64K; + + /* + * We write all 4K page entries, even when using 64K + * pages. In order to verify that the HW isn't cheating + * by using the 4K PTE instead of the 64K PTE, we want + * to remove all the surplus entries. If the HW skipped + * the 64K PTE, it will read/write into the scratch page + * instead - which we detect as missing results during + * selftests. + */ + if (I915_SELFTEST_ONLY(vma->vm->scrub_64K)) { + u16 i; + + encode = pte_encode | vma->vm->scratch_page.daddr; + vaddr = kmap_atomic_px(pd->page_table[idx.pde]); + + for (i = 1; i < index; i += 16) + memset64(vaddr + i, encode, 15); + + kunmap_atomic(vaddr); + } } vma->page_sizes.gtt |= page_size; @@ -2111,8 +2133,6 @@ static void i915_address_space_init(struct i915_address_space *vm, struct drm_i915_private *dev_priv, const char *name) { - i915_gem_timeline_init(dev_priv, &vm->timeline, name); - drm_mm_init(&vm->mm, 0, vm->total); vm->mm.head_node.color = I915_COLOR_UNEVICTABLE; @@ -2129,7 +2149,6 @@ static void i915_address_space_fini(struct i915_address_space *vm) if (pagevec_count(&vm->free_pages)) vm_free_pages_release(vm, true); - i915_gem_timeline_fini(&vm->timeline); drm_mm_takedown(&vm->mm); list_del(&vm->global_link); } @@ -2140,15 +2159,15 @@ static void gtt_write_workarounds(struct drm_i915_private *dev_priv) * called on driver load and after a GPU reset, so you can place * workarounds here even if they get overwritten by GPU reset. */ - /* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt,kbl,glk,cfl,cnl */ + /* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt,kbl,glk,cfl,cnl,icl */ if (IS_BROADWELL(dev_priv)) I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW); else if (IS_CHERRYVIEW(dev_priv)) I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV); - else if (IS_GEN9_BC(dev_priv) || IS_GEN10(dev_priv)) - I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL); else if (IS_GEN9_LP(dev_priv)) I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT); + else if (INTEL_GEN(dev_priv) >= 9) + I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL); /* * To support 64K PTEs we need to first enable the use of the @@ -2222,6 +2241,12 @@ i915_ppgtt_create(struct drm_i915_private *dev_priv, void i915_ppgtt_close(struct i915_address_space *vm) { + GEM_BUG_ON(vm->closed); + vm->closed = true; +} + +static void ppgtt_destroy_vma(struct i915_address_space *vm) +{ struct list_head *phases[] = { &vm->active_list, &vm->inactive_list, @@ -2229,15 +2254,12 @@ void i915_ppgtt_close(struct i915_address_space *vm) NULL, }, **phase; - GEM_BUG_ON(vm->closed); vm->closed = true; - for (phase = phases; *phase; phase++) { struct i915_vma *vma, *vn; list_for_each_entry_safe(vma, vn, *phase, vm_link) - if (!i915_vma_is_closed(vma)) - i915_vma_close(vma); + i915_vma_destroy(vma); } } @@ -2248,7 +2270,8 @@ void i915_ppgtt_release(struct kref *kref) trace_i915_ppgtt_release(&ppgtt->base); - /* vmas should already be unbound and destroyed */ + ppgtt_destroy_vma(&ppgtt->base); + GEM_BUG_ON(!list_empty(&ppgtt->base.active_list)); GEM_BUG_ON(!list_empty(&ppgtt->base.inactive_list)); GEM_BUG_ON(!list_empty(&ppgtt->base.unbound_list)); @@ -2417,11 +2440,9 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, for_each_sgt_dma(addr, sgt_iter, vma->pages) gen8_set_pte(gtt_entries++, pte_encode | addr); - wmb(); - - /* This next bit makes the above posting read even more important. We - * want to flush the TLBs only after we're certain all the PTE updates - * have finished. + /* + * We want to flush the TLBs only after we're certain all the PTE + * updates have finished. */ ggtt->invalidate(vm->i915); } @@ -2459,11 +2480,10 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm, dma_addr_t addr; for_each_sgt_dma(addr, iter, vma->pages) iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]); - wmb(); - /* This next bit makes the above posting read even more important. We - * want to flush the TLBs only after we're certain all the PTE updates - * have finished. + /* + * We want to flush the TLBs only after we're certain all the PTE + * updates have finished. */ ggtt->invalidate(vm->i915); } @@ -3325,14 +3345,10 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err); pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); - - if (INTEL_GEN(dev_priv) >= 9) { - size = gen8_get_total_gtt_size(snb_gmch_ctl); - } else if (IS_CHERRYVIEW(dev_priv)) { + if (IS_CHERRYVIEW(dev_priv)) size = chv_get_total_gtt_size(snb_gmch_ctl); - } else { + else size = gen8_get_total_gtt_size(snb_gmch_ctl); - } ggtt->base.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT; ggtt->base.cleanup = gen6_gmch_remove; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index 6efc017..aec4f73 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -38,10 +38,9 @@ #include <linux/mm.h> #include <linux/pagevec.h> -#include "i915_gem_timeline.h" - #include "i915_request.h" #include "i915_selftest.h" +#include "i915_timeline.h" #define I915_GTT_PAGE_SIZE_4K BIT(12) #define I915_GTT_PAGE_SIZE_64K BIT(16) @@ -257,7 +256,6 @@ struct i915_pml4 { struct i915_address_space { struct drm_mm mm; - struct i915_gem_timeline timeline; struct drm_i915_private *i915; struct device *dma; /* Every address space belongs to a struct file - except for the global @@ -344,6 +342,7 @@ struct i915_address_space { void (*clear_pages)(struct i915_vma *vma); I915_SELFTEST_DECLARE(struct fault_attr fault_attr); + I915_SELFTEST_DECLARE(bool scrub_64K); }; #define i915_is_ggtt(V) (!(V)->file) diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index af915d0..ad949cc 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -51,6 +51,10 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, if (!drm_mm_initialized(&dev_priv->mm.stolen)) return -ENODEV; + /* WaSkipStolenMemoryFirstPage:bdw+ */ + if (INTEL_GEN(dev_priv) >= 8 && start < 4096) + start = 4096; + mutex_lock(&dev_priv->mm.stolen_lock); ret = drm_mm_insert_node_in_range(&dev_priv->mm.stolen, node, size, alignment, 0, @@ -343,7 +347,6 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv) { resource_size_t reserved_base, stolen_top; resource_size_t reserved_total, reserved_size; - resource_size_t stolen_usable_start; mutex_init(&dev_priv->mm.stolen_lock); @@ -435,17 +438,11 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv) (u64)resource_size(&dev_priv->dsm) >> 10, ((u64)resource_size(&dev_priv->dsm) - reserved_total) >> 10); - stolen_usable_start = 0; - /* WaSkipStolenMemoryFirstPage:bdw+ */ - if (INTEL_GEN(dev_priv) >= 8) - stolen_usable_start = 4096; - dev_priv->stolen_usable_size = - resource_size(&dev_priv->dsm) - reserved_total - stolen_usable_start; + resource_size(&dev_priv->dsm) - reserved_total; /* Basic memrange allocator for stolen space. */ - drm_mm_init(&dev_priv->mm.stolen, stolen_usable_start, - dev_priv->stolen_usable_size); + drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->stolen_usable_size); return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem_timeline.c b/drivers/gpu/drm/i915/i915_gem_timeline.c deleted file mode 100644 index e9fd876..0000000 --- a/drivers/gpu/drm/i915/i915_gem_timeline.c +++ /dev/null @@ -1,154 +0,0 @@ -/* - * Copyright © 2016 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 "i915_drv.h" -#include "i915_syncmap.h" - -static void __intel_timeline_init(struct intel_timeline *tl, - struct i915_gem_timeline *parent, - u64 context, - struct lock_class_key *lockclass, - const char *lockname) -{ - tl->fence_context = context; - tl->common = parent; - spin_lock_init(&tl->lock); - lockdep_set_class_and_name(&tl->lock, lockclass, lockname); - init_request_active(&tl->last_request, NULL); - INIT_LIST_HEAD(&tl->requests); - i915_syncmap_init(&tl->sync); -} - -static void __intel_timeline_fini(struct intel_timeline *tl) -{ - GEM_BUG_ON(!list_empty(&tl->requests)); - - i915_syncmap_free(&tl->sync); -} - -static int __i915_gem_timeline_init(struct drm_i915_private *i915, - struct i915_gem_timeline *timeline, - const char *name, - struct lock_class_key *lockclass, - const char *lockname) -{ - unsigned int i; - u64 fences; - - lockdep_assert_held(&i915->drm.struct_mutex); - - /* - * Ideally we want a set of engines on a single leaf as we expect - * to mostly be tracking synchronisation between engines. It is not - * a huge issue if this is not the case, but we may want to mitigate - * any page crossing penalties if they become an issue. - */ - BUILD_BUG_ON(KSYNCMAP < I915_NUM_ENGINES); - - timeline->i915 = i915; - timeline->name = kstrdup(name ?: "[kernel]", GFP_KERNEL); - if (!timeline->name) - return -ENOMEM; - - list_add(&timeline->link, &i915->gt.timelines); - - /* Called during early_init before we know how many engines there are */ - fences = dma_fence_context_alloc(ARRAY_SIZE(timeline->engine)); - for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) - __intel_timeline_init(&timeline->engine[i], - timeline, fences++, - lockclass, lockname); - - return 0; -} - -int i915_gem_timeline_init(struct drm_i915_private *i915, - struct i915_gem_timeline *timeline, - const char *name) -{ - static struct lock_class_key class; - - return __i915_gem_timeline_init(i915, timeline, name, - &class, "&timeline->lock"); -} - -int i915_gem_timeline_init__global(struct drm_i915_private *i915) -{ - static struct lock_class_key class; - - return __i915_gem_timeline_init(i915, - &i915->gt.global_timeline, - "[execution]", - &class, "&global_timeline->lock"); -} - -/** - * i915_gem_timelines_park - called when the driver idles - * @i915: the drm_i915_private device - * - * When the driver is completely idle, we know that all of our sync points - * have been signaled and our tracking is then entirely redundant. Any request - * to wait upon an older sync point will be completed instantly as we know - * the fence is signaled and therefore we will not even look them up in the - * sync point map. - */ -void i915_gem_timelines_park(struct drm_i915_private *i915) -{ - struct i915_gem_timeline *timeline; - int i; - - lockdep_assert_held(&i915->drm.struct_mutex); - - list_for_each_entry(timeline, &i915->gt.timelines, link) { - for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) { - struct intel_timeline *tl = &timeline->engine[i]; - - /* - * All known fences are completed so we can scrap - * the current sync point tracking and start afresh, - * any attempt to wait upon a previous sync point - * will be skipped as the fence was signaled. - */ - i915_syncmap_free(&tl->sync); - } - } -} - -void i915_gem_timeline_fini(struct i915_gem_timeline *timeline) -{ - int i; - - lockdep_assert_held(&timeline->i915->drm.struct_mutex); - - for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) - __intel_timeline_fini(&timeline->engine[i]); - - list_del(&timeline->link); - kfree(timeline->name); -} - -#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) -#include "selftests/mock_timeline.c" -#include "selftests/i915_gem_timeline.c" -#endif diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index d596a83..854bd51 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -778,6 +778,9 @@ i915_gem_userptr_ioctl(struct drm_device *dev, I915_USERPTR_UNSYNCHRONIZED)) return -EINVAL; + if (!args->user_size) + return -EINVAL; + if (offset_in_page(args->user_ptr | args->user_size)) return -EINVAL; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index effaf98..df234dc 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -404,16 +404,17 @@ static const char *bannable(const struct drm_i915_error_context *ctx) static void error_print_request(struct drm_i915_error_state_buf *m, const char *prefix, - const struct drm_i915_error_request *erq) + const struct drm_i915_error_request *erq, + const unsigned long epoch) { if (!erq->seqno) return; - err_printf(m, "%s pid %d, ban score %d, seqno %8x:%08x, prio %d, emitted %dms ago, head %08x, tail %08x\n", + err_printf(m, "%s pid %d, ban score %d, seqno %8x:%08x, prio %d, emitted %dms, start %08x, head %08x, tail %08x\n", prefix, erq->pid, erq->ban_score, - erq->context, erq->seqno, erq->priority, - jiffies_to_msecs(jiffies - erq->jiffies), - erq->head, erq->tail); + erq->context, erq->seqno, erq->sched_attr.priority, + jiffies_to_msecs(erq->jiffies - epoch), + erq->start, erq->head, erq->tail); } static void error_print_context(struct drm_i915_error_state_buf *m, @@ -422,12 +423,13 @@ static void error_print_context(struct drm_i915_error_state_buf *m, { err_printf(m, "%s%s[%d] user_handle %d hw_id %d, prio %d, ban score %d%s guilty %d active %d\n", header, ctx->comm, ctx->pid, ctx->handle, ctx->hw_id, - ctx->priority, ctx->ban_score, bannable(ctx), + ctx->sched_attr.priority, ctx->ban_score, bannable(ctx), ctx->guilty, ctx->active); } static void error_print_engine(struct drm_i915_error_state_buf *m, - const struct drm_i915_error_engine *ee) + const struct drm_i915_error_engine *ee, + const unsigned long epoch) { int n; @@ -497,14 +499,15 @@ static void error_print_engine(struct drm_i915_error_state_buf *m, err_printf(m, " hangcheck stall: %s\n", yesno(ee->hangcheck_stalled)); err_printf(m, " hangcheck action: %s\n", hangcheck_action_to_str(ee->hangcheck_action)); - err_printf(m, " hangcheck action timestamp: %lu, %u ms ago\n", + err_printf(m, " hangcheck action timestamp: %dms (%lu%s)\n", + jiffies_to_msecs(ee->hangcheck_timestamp - epoch), ee->hangcheck_timestamp, - jiffies_to_msecs(jiffies - ee->hangcheck_timestamp)); + ee->hangcheck_timestamp == epoch ? "; epoch" : ""); err_printf(m, " engine reset count: %u\n", ee->reset_count); for (n = 0; n < ee->num_ports; n++) { err_printf(m, " ELSP[%d]:", n); - error_print_request(m, " ", &ee->execlist[n]); + error_print_request(m, " ", &ee->execlist[n], epoch); } error_print_context(m, " Active context: ", &ee->context); @@ -650,6 +653,11 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, ts = ktime_to_timespec64(error->uptime); err_printf(m, "Uptime: %lld s %ld us\n", (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC); + err_printf(m, "Epoch: %lu jiffies (%u HZ)\n", error->epoch, HZ); + err_printf(m, "Capture: %lu jiffies; %d ms ago, %d ms after epoch\n", + error->capture, + jiffies_to_msecs(jiffies - error->capture), + jiffies_to_msecs(error->capture - error->epoch)); for (i = 0; i < ARRAY_SIZE(error->engine); i++) { if (error->engine[i].hangcheck_stalled && @@ -710,7 +718,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, for (i = 0; i < ARRAY_SIZE(error->engine); i++) { if (error->engine[i].engine_id != -1) - error_print_engine(m, &error->engine[i]); + error_print_engine(m, &error->engine[i], error->epoch); } for (i = 0; i < ARRAY_SIZE(error->active_vm); i++) { @@ -769,7 +777,9 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, dev_priv->engine[i]->name, ee->num_requests); for (j = 0; j < ee->num_requests; j++) - error_print_request(m, " ", &ee->requests[j]); + error_print_request(m, " ", + &ee->requests[j], + error->epoch); } if (IS_ERR(ee->waiters)) { @@ -1278,10 +1288,11 @@ static void record_request(struct i915_request *request, struct drm_i915_error_request *erq) { erq->context = request->ctx->hw_id; - erq->priority = request->priotree.priority; + erq->sched_attr = request->sched.attr; erq->ban_score = atomic_read(&request->ctx->ban_score); erq->seqno = request->global_seqno; erq->jiffies = request->emitted_jiffies; + erq->start = i915_ggtt_offset(request->ring->vma); erq->head = request->head; erq->tail = request->tail; @@ -1299,7 +1310,7 @@ static void engine_record_requests(struct intel_engine_cs *engine, count = 0; request = first; - list_for_each_entry_from(request, &engine->timeline->requests, link) + list_for_each_entry_from(request, &engine->timeline.requests, link) count++; if (!count) return; @@ -1312,7 +1323,7 @@ static void engine_record_requests(struct intel_engine_cs *engine, count = 0; request = first; - list_for_each_entry_from(request, &engine->timeline->requests, link) { + list_for_each_entry_from(request, &engine->timeline.requests, link) { if (count >= ee->num_requests) { /* * If the ring request list was changed in @@ -1372,7 +1383,7 @@ static void record_context(struct drm_i915_error_context *e, e->handle = ctx->user_handle; e->hw_id = ctx->hw_id; - e->priority = ctx->priority; + e->sched_attr = ctx->sched; e->ban_score = atomic_read(&ctx->ban_score); e->bannable = i915_gem_context_is_bannable(ctx); e->guilty = atomic_read(&ctx->guilty_count); @@ -1472,7 +1483,8 @@ static void gem_record_rings(struct i915_gpu_state *error) ee->ctx = i915_error_object_create(i915, - request->ctx->engine[i].state); + to_intel_context(request->ctx, + engine)->state); error->simulated |= i915_gem_context_no_error_capture(request->ctx); @@ -1735,6 +1747,22 @@ static void capture_params(struct i915_gpu_state *error) #undef DUP } +static unsigned long capture_find_epoch(const struct i915_gpu_state *error) +{ + unsigned long epoch = error->capture; + int i; + + for (i = 0; i < ARRAY_SIZE(error->engine); i++) { + const struct drm_i915_error_engine *ee = &error->engine[i]; + + if (ee->hangcheck_stalled && + time_before(ee->hangcheck_timestamp, epoch)) + epoch = ee->hangcheck_timestamp; + } + + return epoch; +} + static int capture(void *data) { struct i915_gpu_state *error = data; @@ -1743,6 +1771,7 @@ static int capture(void *data) error->boottime = ktime_get_boottime(); error->uptime = ktime_sub(ktime_get(), error->i915->gt.last_init_time); + error->capture = jiffies; capture_params(error); capture_gen_state(error); @@ -1756,6 +1785,8 @@ static int capture(void *data) error->overlay = intel_overlay_capture_error_state(error->i915); error->display = intel_display_capture_error_state(error->i915); + error->epoch = capture_find_epoch(error); + return 0; } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index c05b603..dac0f8c 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -20,6 +20,7 @@ #include "i915_gem.h" #include "i915_gem_gtt.h" #include "i915_params.h" +#include "i915_scheduler.h" struct drm_i915_private; struct intel_overlay_error_state; @@ -30,6 +31,8 @@ struct i915_gpu_state { ktime_t time; ktime_t boottime; ktime_t uptime; + unsigned long capture; + unsigned long epoch; struct drm_i915_private *i915; @@ -122,11 +125,11 @@ struct i915_gpu_state { pid_t pid; u32 handle; u32 hw_id; - int priority; int ban_score; int active; int guilty; bool bannable; + struct i915_sched_attr sched_attr; } context; struct drm_i915_error_object { @@ -147,11 +150,12 @@ struct i915_gpu_state { long jiffies; pid_t pid; u32 context; - int priority; int ban_score; u32 seqno; + u32 start; u32 head; u32 tail; + struct i915_sched_attr sched_attr; } *requests, execlist[EXECLIST_MAX_PORTS]; unsigned int num_ports; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index b03d185..f9bc3aa 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -247,9 +247,9 @@ static u32 gen11_gt_engine_identity(struct drm_i915_private * const i915, const unsigned int bank, const unsigned int bit); -static bool gen11_reset_one_iir(struct drm_i915_private * const i915, - const unsigned int bank, - const unsigned int bit) +bool gen11_reset_one_iir(struct drm_i915_private * const i915, + const unsigned int bank, + const unsigned int bit) { void __iomem * const regs = i915->regs; u32 dw; @@ -2464,6 +2464,13 @@ static void ivb_display_irq_handler(struct drm_i915_private *dev_priv, if (de_iir & DE_ERR_INT_IVB) ivb_err_int_handler(dev_priv); + if (de_iir & DE_EDP_PSR_INT_HSW) { + u32 psr_iir = I915_READ(EDP_PSR_IIR); + + intel_psr_irq_handler(dev_priv, psr_iir); + I915_WRITE(EDP_PSR_IIR, psr_iir); + } + if (de_iir & DE_AUX_CHANNEL_A_IVB) dp_aux_irq_handler(dev_priv); @@ -2593,11 +2600,25 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl) if (master_ctl & GEN8_DE_MISC_IRQ) { iir = I915_READ(GEN8_DE_MISC_IIR); if (iir) { + bool found = false; + I915_WRITE(GEN8_DE_MISC_IIR, iir); ret = IRQ_HANDLED; - if (iir & GEN8_DE_MISC_GSE) + + if (iir & GEN8_DE_MISC_GSE) { intel_opregion_asle_intr(dev_priv); - else + found = true; + } + + if (iir & GEN8_DE_EDP_PSR) { + u32 psr_iir = I915_READ(EDP_PSR_IIR); + + intel_psr_irq_handler(dev_priv, psr_iir); + I915_WRITE(EDP_PSR_IIR, psr_iir); + found = true; + } + + if (!found) DRM_ERROR("Unexpected DE Misc interrupt\n"); } else @@ -3348,6 +3369,11 @@ static void ironlake_irq_reset(struct drm_device *dev) if (IS_GEN7(dev_priv)) I915_WRITE(GEN7_ERR_INT, 0xffffffff); + if (IS_HASWELL(dev_priv)) { + I915_WRITE(EDP_PSR_IMR, 0xffffffff); + I915_WRITE(EDP_PSR_IIR, 0xffffffff); + } + gen5_gt_irq_reset(dev_priv); ibx_irq_reset(dev_priv); @@ -3386,6 +3412,9 @@ static void gen8_irq_reset(struct drm_device *dev) gen8_gt_irq_reset(dev_priv); + I915_WRITE(EDP_PSR_IMR, 0xffffffff); + I915_WRITE(EDP_PSR_IIR, 0xffffffff); + for_each_pipe(dev_priv, pipe) if (intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) @@ -3762,6 +3791,12 @@ static int ironlake_irq_postinstall(struct drm_device *dev) DE_DP_A_HOTPLUG); } + if (IS_HASWELL(dev_priv)) { + gen3_assert_iir_is_zero(dev_priv, EDP_PSR_IIR); + intel_psr_irq_control(dev_priv, dev_priv->psr.debug); + display_mask |= DE_EDP_PSR_INT_HSW; + } + dev_priv->irq_mask = ~display_mask; ibx_irq_pre_postinstall(dev); @@ -3872,7 +3907,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) uint32_t de_pipe_enables; u32 de_port_masked = GEN8_AUX_CHANNEL_A; u32 de_port_enables; - u32 de_misc_masked = GEN8_DE_MISC_GSE; + u32 de_misc_masked = GEN8_DE_MISC_GSE | GEN8_DE_EDP_PSR; enum pipe pipe; if (INTEL_GEN(dev_priv) >= 9) { @@ -3897,6 +3932,9 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) else if (IS_BROADWELL(dev_priv)) de_port_enables |= GEN8_PORT_DP_A_HOTPLUG; + gen3_assert_iir_is_zero(dev_priv, EDP_PSR_IIR); + intel_psr_irq_control(dev_priv, dev_priv->psr.debug); + for_each_pipe(dev_priv, pipe) { dev_priv->de_irq_mask[pipe] = ~de_pipe_masked; diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 08108ce..66ea355 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -164,6 +164,9 @@ i915_param_named_unsafe(guc_firmware_path, charp, 0400, i915_param_named_unsafe(huc_firmware_path, charp, 0400, "HuC firmware path to use instead of the default one"); +i915_param_named_unsafe(dmc_firmware_path, charp, 0400, + "DMC firmware path to use instead of the default one"); + i915_param_named_unsafe(enable_dp_mst, bool, 0600, "Enable multi-stream transport (MST) for new DisplayPort sinks. (default: true)"); diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h index c963603..6684025 100644 --- a/drivers/gpu/drm/i915/i915_params.h +++ b/drivers/gpu/drm/i915/i915_params.h @@ -51,6 +51,7 @@ struct drm_printer; param(int, guc_log_level, -1) \ param(char *, guc_firmware_path, NULL) \ param(char *, huc_firmware_path, NULL) \ + param(char *, dmc_firmware_path, NULL) \ param(int, mmio_debug, 0) \ param(int, edp_vswing, 0) \ param(int, reset, 2) \ diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index bfc906c..019bd2d 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1234,7 +1234,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) * * NB: implied RCS engine... */ - ring = engine->context_pin(engine, stream->ctx); + ring = intel_context_pin(stream->ctx, engine); mutex_unlock(&dev_priv->drm.struct_mutex); if (IS_ERR(ring)) return PTR_ERR(ring); @@ -1246,7 +1246,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) * with gen8+ and execlists */ dev_priv->perf.oa.specific_ctx_id = - i915_ggtt_offset(stream->ctx->engine[engine->id].state); + i915_ggtt_offset(to_intel_context(stream->ctx, engine)->state); } return 0; @@ -1271,7 +1271,7 @@ static void oa_put_render_ctx_id(struct i915_perf_stream *stream) mutex_lock(&dev_priv->drm.struct_mutex); dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID; - engine->context_unpin(engine, stream->ctx); + intel_context_unpin(stream->ctx, engine); mutex_unlock(&dev_priv->drm.struct_mutex); } @@ -1695,7 +1695,7 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr const struct i915_oa_config *oa_config) { struct intel_engine_cs *engine = dev_priv->engine[RCS]; - struct i915_gem_timeline *timeline; + struct i915_timeline *timeline; struct i915_request *rq; int ret; @@ -1716,15 +1716,11 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr /* Queue this switch after all other activity */ list_for_each_entry(timeline, &dev_priv->gt.timelines, link) { struct i915_request *prev; - struct intel_timeline *tl; - tl = &timeline->engine[engine->id]; - prev = i915_gem_active_raw(&tl->last_request, + prev = i915_gem_active_raw(&timeline->last_request, &dev_priv->drm.struct_mutex); if (prev) - i915_sw_fence_await_sw_fence_gfp(&rq->submit, - &prev->submit, - GFP_KERNEL); + i915_request_await_dma_fence(rq, &prev->fence); } i915_request_add(rq); @@ -1759,6 +1755,7 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, const struct i915_oa_config *oa_config) { + struct intel_engine_cs *engine = dev_priv->engine[RCS]; struct i915_gem_context *ctx; int ret; unsigned int wait_flags = I915_WAIT_LOCKED; @@ -1789,7 +1786,7 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, /* Update all contexts now that we've stalled the submission. */ list_for_each_entry(ctx, &dev_priv->contexts.list, link) { - struct intel_context *ce = &ctx->engine[RCS]; + struct intel_context *ce = to_intel_context(ctx, engine); u32 *regs; /* OA settings will be set upon first use */ @@ -1963,11 +1960,19 @@ static void i915_oa_stream_enable(struct i915_perf_stream *stream) static void gen7_oa_disable(struct drm_i915_private *dev_priv) { I915_WRITE(GEN7_OACONTROL, 0); + if (intel_wait_for_register(dev_priv, + GEN7_OACONTROL, GEN7_OACONTROL_ENABLE, 0, + 50)) + DRM_ERROR("wait for OA to be disabled timed out\n"); } static void gen8_oa_disable(struct drm_i915_private *dev_priv) { I915_WRITE(GEN8_OACONTROL, 0); + if (intel_wait_for_register(dev_priv, + GEN8_OACONTROL, GEN8_OA_COUNTER_ENABLE, 0, + 50)) + DRM_ERROR("wait for OA to be disabled timed out\n"); } /** diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index fb10602..f11bb21 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3840,6 +3840,7 @@ enum { #define SLICE_UNIT_LEVEL_CLKGATE _MMIO(0x94d4) #define SARBUNIT_CLKGATE_DIS (1 << 5) #define RCCUNIT_CLKGATE_DIS (1 << 7) +#define MSCUNIT_CLKGATE_DIS (1 << 10) #define SUBSLICE_UNIT_LEVEL_CLKGATE _MMIO(0x9524) #define GWUNIT_CLKGATE_DIS (1 << 16) @@ -3847,6 +3848,9 @@ enum { #define UNSLICE_UNIT_LEVEL_CLKGATE _MMIO(0x9434) #define VFUNIT_CLKGATE_DIS (1 << 20) +#define INF_UNIT_LEVEL_CLKGATE _MMIO(0x9560) +#define CGPSF_CLKGATE_DIS (1 << 3) + /* * Display engine regs */ @@ -4026,6 +4030,13 @@ enum { #define EDP_PSR_TP1_TIME_0us (3<<4) #define EDP_PSR_IDLE_FRAME_SHIFT 0 +/* Bspec claims those aren't shifted but stay at 0x64800 */ +#define EDP_PSR_IMR _MMIO(0x64834) +#define EDP_PSR_IIR _MMIO(0x64838) +#define EDP_PSR_ERROR(trans) (1 << (((trans) * 8 + 10) & 31)) +#define EDP_PSR_POST_EXIT(trans) (1 << (((trans) * 8 + 9) & 31)) +#define EDP_PSR_PRE_ENTRY(trans) (1 << (((trans) * 8 + 8) & 31)) + #define EDP_PSR_AUX_CTL _MMIO(dev_priv->psr_mmio_base + 0x10) #define EDP_PSR_AUX_CTL_TIME_OUT_MASK (3 << 26) #define EDP_PSR_AUX_CTL_MESSAGE_SIZE_MASK (0x1f << 20) @@ -4088,6 +4099,29 @@ enum { #define EDP_PSR2_IDLE_FRAME_MASK 0xf #define EDP_PSR2_IDLE_FRAME_SHIFT 0 +#define _PSR_EVENT_TRANS_A 0x60848 +#define _PSR_EVENT_TRANS_B 0x61848 +#define _PSR_EVENT_TRANS_C 0x62848 +#define _PSR_EVENT_TRANS_D 0x63848 +#define _PSR_EVENT_TRANS_EDP 0x6F848 +#define PSR_EVENT(trans) _MMIO_TRANS2(trans, _PSR_EVENT_TRANS_A) +#define PSR_EVENT_PSR2_WD_TIMER_EXPIRE (1 << 17) +#define PSR_EVENT_PSR2_DISABLED (1 << 16) +#define PSR_EVENT_SU_DIRTY_FIFO_UNDERRUN (1 << 15) +#define PSR_EVENT_SU_CRC_FIFO_UNDERRUN (1 << 14) +#define PSR_EVENT_GRAPHICS_RESET (1 << 12) +#define PSR_EVENT_PCH_INTERRUPT (1 << 11) +#define PSR_EVENT_MEMORY_UP (1 << 10) +#define PSR_EVENT_FRONT_BUFFER_MODIFY (1 << 9) +#define PSR_EVENT_WD_TIMER_EXPIRE (1 << 8) +#define PSR_EVENT_PIPE_REGISTERS_UPDATE (1 << 6) +#define PSR_EVENT_REGISTER_UPDATE (1 << 5) +#define PSR_EVENT_HDCP_ENABLE (1 << 4) +#define PSR_EVENT_KVMR_SESSION_ENABLE (1 << 3) +#define PSR_EVENT_VBI_ENABLE (1 << 2) +#define PSR_EVENT_LPSP_MODE_EXIT (1 << 1) +#define PSR_EVENT_PSR_DISABLE (1 << 0) + #define EDP_PSR2_STATUS _MMIO(0x6f940) #define EDP_PSR2_STATUS_STATE_MASK (0xf<<28) #define EDP_PSR2_STATUS_STATE_SHIFT 28 @@ -6377,9 +6411,9 @@ enum { #define _PLANE_COLOR_CTL_1_A 0x701CC /* GLK+ */ #define _PLANE_COLOR_CTL_2_A 0x702CC /* GLK+ */ #define _PLANE_COLOR_CTL_3_A 0x703CC /* GLK+ */ -#define PLANE_COLOR_PIPE_GAMMA_ENABLE (1 << 30) +#define PLANE_COLOR_PIPE_GAMMA_ENABLE (1 << 30) /* Pre-ICL */ #define PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE (1 << 28) -#define PLANE_COLOR_PIPE_CSC_ENABLE (1 << 23) +#define PLANE_COLOR_PIPE_CSC_ENABLE (1 << 23) /* Pre-ICL */ #define PLANE_COLOR_CSC_MODE_BYPASS (0 << 17) #define PLANE_COLOR_CSC_MODE_YUV601_TO_RGB709 (1 << 17) #define PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709 (2 << 17) @@ -6474,6 +6508,9 @@ enum { #define _PLANE_BUF_CFG_1_B 0x7127c #define _PLANE_BUF_CFG_2_B 0x7137c +#define SKL_DDB_ENTRY_MASK 0x3FF +#define ICL_DDB_ENTRY_MASK 0x7FF +#define DDB_ENTRY_END_SHIFT 16 #define _PLANE_BUF_CFG_1(pipe) \ _PIPE(pipe, _PLANE_BUF_CFG_1_A, _PLANE_BUF_CFG_1_B) #define _PLANE_BUF_CFG_2(pipe) \ @@ -6837,6 +6874,7 @@ enum { #define DE_PCH_EVENT_IVB (1<<28) #define DE_DP_A_HOTPLUG_IVB (1<<27) #define DE_AUX_CHANNEL_A_IVB (1<<26) +#define DE_EDP_PSR_INT_HSW (1<<19) #define DE_SPRITEC_FLIP_DONE_IVB (1<<14) #define DE_PLANEC_FLIP_DONE_IVB (1<<13) #define DE_PIPEC_VBLANK_IVB (1<<10) @@ -6961,6 +6999,7 @@ enum { #define GEN8_DE_MISC_IIR _MMIO(0x44468) #define GEN8_DE_MISC_IER _MMIO(0x4446c) #define GEN8_DE_MISC_GSE (1 << 27) +#define GEN8_DE_EDP_PSR (1 << 19) #define GEN8_PCU_ISR _MMIO(0x444e0) #define GEN8_PCU_IMR _MMIO(0x444e4) @@ -7191,18 +7230,22 @@ enum { #define GEN7_L3CNTLREG3 _MMIO(0xB024) #define GEN7_L3_CHICKEN_MODE_REGISTER _MMIO(0xB030) -#define GEN7_WA_L3_CHICKEN_MODE 0x20000000 +#define GEN7_WA_L3_CHICKEN_MODE 0x20000000 +#define GEN10_L3_CHICKEN_MODE_REGISTER _MMIO(0xB114) +#define GEN11_I2M_WRITE_DISABLE (1 << 28) #define GEN7_L3SQCREG4 _MMIO(0xb034) #define L3SQ_URB_READ_CAM_MATCH_DISABLE (1<<27) #define GEN8_L3SQCREG4 _MMIO(0xb118) -#define GEN8_LQSC_RO_PERF_DIS (1<<27) -#define GEN8_LQSC_FLUSH_COHERENT_LINES (1<<21) +#define GEN11_LQSC_CLEAN_EVICT_DISABLE (1 << 6) +#define GEN8_LQSC_RO_PERF_DIS (1 << 27) +#define GEN8_LQSC_FLUSH_COHERENT_LINES (1 << 21) /* GEN8 chicken */ #define HDC_CHICKEN0 _MMIO(0x7300) #define CNL_HDC_CHICKEN0 _MMIO(0xE5F0) +#define ICL_HDC_MODE _MMIO(0xE5F4) #define HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE (1<<15) #define HDC_FENCE_DEST_SLM_DISABLE (1<<14) #define HDC_DONOT_FETCH_MEM_WHEN_MASKED (1<<11) @@ -7216,6 +7259,9 @@ enum { #define SLICE_ECO_CHICKEN0 _MMIO(0x7308) #define PIXEL_MASK_CAMMING_DISABLE (1 << 14) +#define GEN9_WM_CHICKEN3 _MMIO(0x5588) +#define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9) + /* WaCatErrorRejectionIssue */ #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG _MMIO(0x9030) #define GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB (1<<11) @@ -8214,8 +8260,30 @@ enum { #define GEN8_DOP_CLOCK_GATE_GUC_ENABLE (1<<4) #define GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE (1<<6) -#define GEN8_GARBCNTL _MMIO(0xB004) -#define GEN9_GAPS_TSV_CREDIT_DISABLE (1<<7) +#define GEN8_GARBCNTL _MMIO(0xB004) +#define GEN9_GAPS_TSV_CREDIT_DISABLE (1 << 7) +#define GEN11_ARBITRATION_PRIO_ORDER_MASK (0x3f << 22) +#define GEN11_HASH_CTRL_EXCL_MASK (0x7f << 0) +#define GEN11_HASH_CTRL_EXCL_BIT0 (1 << 0) + +#define GEN11_GLBLINVL _MMIO(0xB404) +#define GEN11_BANK_HASH_ADDR_EXCL_MASK (0x7f << 5) +#define GEN11_BANK_HASH_ADDR_EXCL_BIT0 (1 << 5) + +#define GEN10_DFR_RATIO_EN_AND_CHICKEN _MMIO(0x9550) +#define DFR_DISABLE (1 << 9) + +#define GEN11_GACB_PERF_CTRL _MMIO(0x4B80) +#define GEN11_HASH_CTRL_MASK (0x3 << 12 | 0xf << 0) +#define GEN11_HASH_CTRL_BIT0 (1 << 0) +#define GEN11_HASH_CTRL_BIT4 (1 << 12) + +#define GEN11_LSN_UNSLCVC _MMIO(0xB43C) +#define GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC (1 << 9) +#define GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC (1 << 7) + +#define GAMW_ECO_DEV_RW_IA_REG _MMIO(0x4080) +#define GAMW_ECO_DEV_CTX_RELOAD_DISABLE (1 << 7) /* IVYBRIDGE DPF */ #define GEN7_L3CDERRST1(slice) _MMIO(0xB008 + (slice) * 0x200) /* L3CD Error Status 1 */ @@ -8724,6 +8792,12 @@ enum skl_power_gate { #define PORT_CLK_SEL_NONE (7<<29) #define PORT_CLK_SEL_MASK (7<<29) +/* On ICL+ this is the same as PORT_CLK_SEL, but all bits change. */ +#define DDI_CLK_SEL(port) PORT_CLK_SEL(port) +#define DDI_CLK_SEL_NONE (0x0 << 28) +#define DDI_CLK_SEL_MG (0x8 << 28) +#define DDI_CLK_SEL_MASK (0xF << 28) + /* Transcoder clock selection */ #define _TRANS_CLK_SEL_A 0x46140 #define _TRANS_CLK_SEL_B 0x46144 @@ -8854,6 +8928,7 @@ enum skl_power_gate { * CNL Clocks */ #define DPCLKA_CFGCR0 _MMIO(0x6C200) +#define DPCLKA_CFGCR0_ICL _MMIO(0x164280) #define DPCLKA_CFGCR0_DDI_CLK_OFF(port) (1 << ((port) == PORT_F ? 23 : \ (port)+10)) #define DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port) ((port) == PORT_F ? 21 : \ @@ -8870,10 +8945,141 @@ enum skl_power_gate { #define PLL_POWER_STATE (1 << 26) #define CNL_DPLL_ENABLE(pll) _MMIO_PLL(pll, DPLL0_ENABLE, DPLL1_ENABLE) +#define _MG_PLL1_ENABLE 0x46030 +#define _MG_PLL2_ENABLE 0x46034 +#define _MG_PLL3_ENABLE 0x46038 +#define _MG_PLL4_ENABLE 0x4603C +/* Bits are the same as DPLL0_ENABLE */ +#define MG_PLL_ENABLE(port) _MMIO_PORT((port) - PORT_C, _MG_PLL1_ENABLE, \ + _MG_PLL2_ENABLE) + +#define _MG_REFCLKIN_CTL_PORT1 0x16892C +#define _MG_REFCLKIN_CTL_PORT2 0x16992C +#define _MG_REFCLKIN_CTL_PORT3 0x16A92C +#define _MG_REFCLKIN_CTL_PORT4 0x16B92C +#define MG_REFCLKIN_CTL_OD_2_MUX(x) ((x) << 8) +#define MG_REFCLKIN_CTL(port) _MMIO_PORT((port) - PORT_C, \ + _MG_REFCLKIN_CTL_PORT1, \ + _MG_REFCLKIN_CTL_PORT2) + +#define _MG_CLKTOP2_CORECLKCTL1_PORT1 0x1688D8 +#define _MG_CLKTOP2_CORECLKCTL1_PORT2 0x1698D8 +#define _MG_CLKTOP2_CORECLKCTL1_PORT3 0x16A8D8 +#define _MG_CLKTOP2_CORECLKCTL1_PORT4 0x16B8D8 +#define MG_CLKTOP2_CORECLKCTL1_B_DIVRATIO(x) ((x) << 16) +#define MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO(x) ((x) << 8) +#define MG_CLKTOP2_CORECLKCTL1(port) _MMIO_PORT((port) - PORT_C, \ + _MG_CLKTOP2_CORECLKCTL1_PORT1, \ + _MG_CLKTOP2_CORECLKCTL1_PORT2) + +#define _MG_CLKTOP2_HSCLKCTL_PORT1 0x1688D4 +#define _MG_CLKTOP2_HSCLKCTL_PORT2 0x1698D4 +#define _MG_CLKTOP2_HSCLKCTL_PORT3 0x16A8D4 +#define _MG_CLKTOP2_HSCLKCTL_PORT4 0x16B8D4 +#define MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL(x) ((x) << 16) +#define MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL(x) ((x) << 14) +#define MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO(x) ((x) << 12) +#define MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO(x) ((x) << 8) +#define MG_CLKTOP2_HSCLKCTL(port) _MMIO_PORT((port) - PORT_C, \ + _MG_CLKTOP2_HSCLKCTL_PORT1, \ + _MG_CLKTOP2_HSCLKCTL_PORT2) + +#define _MG_PLL_DIV0_PORT1 0x168A00 +#define _MG_PLL_DIV0_PORT2 0x169A00 +#define _MG_PLL_DIV0_PORT3 0x16AA00 +#define _MG_PLL_DIV0_PORT4 0x16BA00 +#define MG_PLL_DIV0_FRACNEN_H (1 << 30) +#define MG_PLL_DIV0_FBDIV_FRAC(x) ((x) << 8) +#define MG_PLL_DIV0_FBDIV_INT(x) ((x) << 0) +#define MG_PLL_DIV0(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_DIV0_PORT1, \ + _MG_PLL_DIV0_PORT2) + +#define _MG_PLL_DIV1_PORT1 0x168A04 +#define _MG_PLL_DIV1_PORT2 0x169A04 +#define _MG_PLL_DIV1_PORT3 0x16AA04 +#define _MG_PLL_DIV1_PORT4 0x16BA04 +#define MG_PLL_DIV1_IREF_NDIVRATIO(x) ((x) << 16) +#define MG_PLL_DIV1_DITHER_DIV_1 (0 << 12) +#define MG_PLL_DIV1_DITHER_DIV_2 (1 << 12) +#define MG_PLL_DIV1_DITHER_DIV_4 (2 << 12) +#define MG_PLL_DIV1_DITHER_DIV_8 (3 << 12) +#define MG_PLL_DIV1_NDIVRATIO(x) ((x) << 4) +#define MG_PLL_DIV1_FBPREDIV(x) ((x) << 0) +#define MG_PLL_DIV1(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_DIV1_PORT1, \ + _MG_PLL_DIV1_PORT2) + +#define _MG_PLL_LF_PORT1 0x168A08 +#define _MG_PLL_LF_PORT2 0x169A08 +#define _MG_PLL_LF_PORT3 0x16AA08 +#define _MG_PLL_LF_PORT4 0x16BA08 +#define MG_PLL_LF_TDCTARGETCNT(x) ((x) << 24) +#define MG_PLL_LF_AFCCNTSEL_256 (0 << 20) +#define MG_PLL_LF_AFCCNTSEL_512 (1 << 20) +#define MG_PLL_LF_GAINCTRL(x) ((x) << 16) +#define MG_PLL_LF_INT_COEFF(x) ((x) << 8) +#define MG_PLL_LF_PROP_COEFF(x) ((x) << 0) +#define MG_PLL_LF(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_LF_PORT1, \ + _MG_PLL_LF_PORT2) + +#define _MG_PLL_FRAC_LOCK_PORT1 0x168A0C +#define _MG_PLL_FRAC_LOCK_PORT2 0x169A0C +#define _MG_PLL_FRAC_LOCK_PORT3 0x16AA0C +#define _MG_PLL_FRAC_LOCK_PORT4 0x16BA0C +#define MG_PLL_FRAC_LOCK_TRUELOCK_CRIT_32 (1 << 18) +#define MG_PLL_FRAC_LOCK_EARLYLOCK_CRIT_32 (1 << 16) +#define MG_PLL_FRAC_LOCK_LOCKTHRESH(x) ((x) << 11) +#define MG_PLL_FRAC_LOCK_DCODITHEREN (1 << 10) +#define MG_PLL_FRAC_LOCK_FEEDFWRDCAL_EN (1 << 8) +#define MG_PLL_FRAC_LOCK_FEEDFWRDGAIN(x) ((x) << 0) +#define MG_PLL_FRAC_LOCK(port) _MMIO_PORT((port) - PORT_C, \ + _MG_PLL_FRAC_LOCK_PORT1, \ + _MG_PLL_FRAC_LOCK_PORT2) + +#define _MG_PLL_SSC_PORT1 0x168A10 +#define _MG_PLL_SSC_PORT2 0x169A10 +#define _MG_PLL_SSC_PORT3 0x16AA10 +#define _MG_PLL_SSC_PORT4 0x16BA10 +#define MG_PLL_SSC_EN (1 << 28) +#define MG_PLL_SSC_TYPE(x) ((x) << 26) +#define MG_PLL_SSC_STEPLENGTH(x) ((x) << 16) +#define MG_PLL_SSC_STEPNUM(x) ((x) << 10) +#define MG_PLL_SSC_FLLEN (1 << 9) +#define MG_PLL_SSC_STEPSIZE(x) ((x) << 0) +#define MG_PLL_SSC(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_SSC_PORT1, \ + _MG_PLL_SSC_PORT2) + +#define _MG_PLL_BIAS_PORT1 0x168A14 +#define _MG_PLL_BIAS_PORT2 0x169A14 +#define _MG_PLL_BIAS_PORT3 0x16AA14 +#define _MG_PLL_BIAS_PORT4 0x16BA14 +#define MG_PLL_BIAS_BIAS_GB_SEL(x) ((x) << 30) +#define MG_PLL_BIAS_INIT_DCOAMP(x) ((x) << 24) +#define MG_PLL_BIAS_BIAS_BONUS(x) ((x) << 16) +#define MG_PLL_BIAS_BIASCAL_EN (1 << 15) +#define MG_PLL_BIAS_CTRIM(x) ((x) << 8) +#define MG_PLL_BIAS_VREF_RDAC(x) ((x) << 5) +#define MG_PLL_BIAS_IREFTRIM(x) ((x) << 0) +#define MG_PLL_BIAS(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_BIAS_PORT1, \ + _MG_PLL_BIAS_PORT2) + +#define _MG_PLL_TDC_COLDST_BIAS_PORT1 0x168A18 +#define _MG_PLL_TDC_COLDST_BIAS_PORT2 0x169A18 +#define _MG_PLL_TDC_COLDST_BIAS_PORT3 0x16AA18 +#define _MG_PLL_TDC_COLDST_BIAS_PORT4 0x16BA18 +#define MG_PLL_TDC_COLDST_IREFINT_EN (1 << 27) +#define MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(x) ((x) << 17) +#define MG_PLL_TDC_COLDST_COLDSTART (1 << 16) +#define MG_PLL_TDC_TDCOVCCORR_EN (1 << 2) +#define MG_PLL_TDC_TDCSEL(x) ((x) << 0) +#define MG_PLL_TDC_COLDST_BIAS(port) _MMIO_PORT((port) - PORT_C, \ + _MG_PLL_TDC_COLDST_BIAS_PORT1, \ + _MG_PLL_TDC_COLDST_BIAS_PORT2) + #define _CNL_DPLL0_CFGCR0 0x6C000 #define _CNL_DPLL1_CFGCR0 0x6C080 #define DPLL_CFGCR0_HDMI_MODE (1 << 30) #define DPLL_CFGCR0_SSC_ENABLE (1 << 29) +#define DPLL_CFGCR0_SSC_ENABLE_ICL (1 << 25) #define DPLL_CFGCR0_LINK_RATE_MASK (0xf << 25) #define DPLL_CFGCR0_LINK_RATE_2700 (0 << 25) #define DPLL_CFGCR0_LINK_RATE_1350 (1 << 25) @@ -8907,8 +9113,19 @@ enum skl_power_gate { #define DPLL_CFGCR1_PDIV_5 (4 << 2) #define DPLL_CFGCR1_PDIV_7 (8 << 2) #define DPLL_CFGCR1_CENTRAL_FREQ (3 << 0) +#define DPLL_CFGCR1_CENTRAL_FREQ_8400 (3 << 0) #define CNL_DPLL_CFGCR1(pll) _MMIO_PLL(pll, _CNL_DPLL0_CFGCR1, _CNL_DPLL1_CFGCR1) +#define _ICL_DPLL0_CFGCR0 0x164000 +#define _ICL_DPLL1_CFGCR0 0x164080 +#define ICL_DPLL_CFGCR0(pll) _MMIO_PLL(pll, _ICL_DPLL0_CFGCR0, \ + _ICL_DPLL1_CFGCR0) + +#define _ICL_DPLL0_CFGCR1 0x164004 +#define _ICL_DPLL1_CFGCR1 0x164084 +#define ICL_DPLL_CFGCR1(pll) _MMIO_PLL(pll, _ICL_DPLL0_CFGCR1, \ + _ICL_DPLL1_CFGCR1) + /* BXT display engine PLL */ #define BXT_DE_PLL_CTL _MMIO(0x6d000) #define BXT_DE_PLL_RATIO(x) (x) /* {60,65,100} * 19.2MHz */ @@ -9680,6 +9897,13 @@ enum skl_power_gate { #define GEN9_MFX1_MOCS(i) _MMIO(0xca00 + (i) * 4) /* Media 1 MOCS registers */ #define GEN9_VEBOX_MOCS(i) _MMIO(0xcb00 + (i) * 4) /* Video MOCS registers */ #define GEN9_BLT_MOCS(i) _MMIO(0xcc00 + (i) * 4) /* Blitter MOCS registers */ +/* Media decoder 2 MOCS registers */ +#define GEN11_MFX2_MOCS(i) _MMIO(0x10000 + (i) * 4) + +#define GEN10_SCRATCH_LNCF2 _MMIO(0xb0a0) +#define PMFLUSHDONE_LNICRSDROP (1 << 20) +#define PMFLUSH_GAPL3UNBLOCK (1 << 21) +#define PMFLUSHDONE_LNEBLK (1 << 22) /* gamt regs */ #define GEN8_L3_LRA_1_GPGPU _MMIO(0x4dd4) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 9ca9c24..8928894 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -49,7 +49,7 @@ static const char *i915_fence_get_timeline_name(struct dma_fence *fence) if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) return "signaled"; - return to_request(fence)->timeline->common->name; + return to_request(fence)->timeline->name; } static bool i915_fence_signaled(struct dma_fence *fence) @@ -125,22 +125,22 @@ i915_dependency_free(struct drm_i915_private *i915, } static void -__i915_priotree_add_dependency(struct i915_priotree *pt, - struct i915_priotree *signal, - struct i915_dependency *dep, - unsigned long flags) +__i915_sched_node_add_dependency(struct i915_sched_node *node, + struct i915_sched_node *signal, + struct i915_dependency *dep, + unsigned long flags) { INIT_LIST_HEAD(&dep->dfs_link); list_add(&dep->wait_link, &signal->waiters_list); - list_add(&dep->signal_link, &pt->signalers_list); + list_add(&dep->signal_link, &node->signalers_list); dep->signaler = signal; dep->flags = flags; } static int -i915_priotree_add_dependency(struct drm_i915_private *i915, - struct i915_priotree *pt, - struct i915_priotree *signal) +i915_sched_node_add_dependency(struct drm_i915_private *i915, + struct i915_sched_node *node, + struct i915_sched_node *signal) { struct i915_dependency *dep; @@ -148,16 +148,18 @@ i915_priotree_add_dependency(struct drm_i915_private *i915, if (!dep) return -ENOMEM; - __i915_priotree_add_dependency(pt, signal, dep, I915_DEPENDENCY_ALLOC); + __i915_sched_node_add_dependency(node, signal, dep, + I915_DEPENDENCY_ALLOC); return 0; } static void -i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt) +i915_sched_node_fini(struct drm_i915_private *i915, + struct i915_sched_node *node) { - struct i915_dependency *dep, *next; + struct i915_dependency *dep, *tmp; - GEM_BUG_ON(!list_empty(&pt->link)); + GEM_BUG_ON(!list_empty(&node->link)); /* * Everyone we depended upon (the fences we wait to be signaled) @@ -165,8 +167,8 @@ i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt) * However, retirement is run independently on each timeline and * so we may be called out-of-order. */ - list_for_each_entry_safe(dep, next, &pt->signalers_list, signal_link) { - GEM_BUG_ON(!i915_priotree_signaled(dep->signaler)); + list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) { + GEM_BUG_ON(!i915_sched_node_signaled(dep->signaler)); GEM_BUG_ON(!list_empty(&dep->dfs_link)); list_del(&dep->wait_link); @@ -175,8 +177,8 @@ i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt) } /* Remove ourselves from everyone who depends upon us */ - list_for_each_entry_safe(dep, next, &pt->waiters_list, wait_link) { - GEM_BUG_ON(dep->signaler != pt); + list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) { + GEM_BUG_ON(dep->signaler != node); GEM_BUG_ON(!list_empty(&dep->dfs_link)); list_del(&dep->signal_link); @@ -186,17 +188,18 @@ i915_priotree_fini(struct drm_i915_private *i915, struct i915_priotree *pt) } static void -i915_priotree_init(struct i915_priotree *pt) +i915_sched_node_init(struct i915_sched_node *node) { - INIT_LIST_HEAD(&pt->signalers_list); - INIT_LIST_HEAD(&pt->waiters_list); - INIT_LIST_HEAD(&pt->link); - pt->priority = I915_PRIORITY_INVALID; + INIT_LIST_HEAD(&node->signalers_list); + INIT_LIST_HEAD(&node->waiters_list); + INIT_LIST_HEAD(&node->link); + node->attr.priority = I915_PRIORITY_INVALID; } static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno) { struct intel_engine_cs *engine; + struct i915_timeline *timeline; enum intel_engine_id id; int ret; @@ -211,34 +214,33 @@ static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno) /* If the seqno wraps around, we need to clear the breadcrumb rbtree */ for_each_engine(engine, i915, id) { - struct i915_gem_timeline *timeline; - struct intel_timeline *tl = engine->timeline; - GEM_TRACE("%s seqno %d (current %d) -> %d\n", engine->name, - tl->seqno, + engine->timeline.seqno, intel_engine_get_seqno(engine), seqno); - if (!i915_seqno_passed(seqno, tl->seqno)) { + if (!i915_seqno_passed(seqno, engine->timeline.seqno)) { /* Flush any waiters before we reuse the seqno */ intel_engine_disarm_breadcrumbs(engine); + intel_engine_init_hangcheck(engine); GEM_BUG_ON(!list_empty(&engine->breadcrumbs.signals)); } /* Check we are idle before we fiddle with hw state! */ GEM_BUG_ON(!intel_engine_is_idle(engine)); - GEM_BUG_ON(i915_gem_active_isset(&engine->timeline->last_request)); + GEM_BUG_ON(i915_gem_active_isset(&engine->timeline.last_request)); /* Finally reset hw state */ intel_engine_init_global_seqno(engine, seqno); - tl->seqno = seqno; - - list_for_each_entry(timeline, &i915->gt.timelines, link) - memset(timeline->engine[id].global_sync, 0, - sizeof(timeline->engine[id].global_sync)); + engine->timeline.seqno = seqno; } + list_for_each_entry(timeline, &i915->gt.timelines, link) + memset(timeline->global_sync, 0, sizeof(timeline->global_sync)); + + i915->gt.request_serial = seqno; + return 0; } @@ -255,18 +257,22 @@ int i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno) return reset_all_global_seqno(i915, seqno - 1); } -static int reserve_engine(struct intel_engine_cs *engine) +static int reserve_gt(struct drm_i915_private *i915) { - struct drm_i915_private *i915 = engine->i915; - u32 active = ++engine->timeline->inflight_seqnos; - u32 seqno = engine->timeline->seqno; int ret; - /* Reservation is fine until we need to wrap around */ - if (unlikely(add_overflows(seqno, active))) { + /* + * Reservation is fine until we may need to wrap around + * + * By incrementing the serial for every request, we know that no + * individual engine may exceed that serial (as each is reset to 0 + * on any wrap). This protects even the most pessimistic of migrations + * of every request from all engines onto just one. + */ + while (unlikely(++i915->gt.request_serial == 0)) { ret = reset_all_global_seqno(i915, 0); if (ret) { - engine->timeline->inflight_seqnos--; + i915->gt.request_serial--; return ret; } } @@ -277,15 +283,11 @@ static int reserve_engine(struct intel_engine_cs *engine) return 0; } -static void unreserve_engine(struct intel_engine_cs *engine) +static void unreserve_gt(struct drm_i915_private *i915) { - struct drm_i915_private *i915 = engine->i915; - + GEM_BUG_ON(!i915->gt.active_requests); if (!--i915->gt.active_requests) i915_gem_park(i915); - - GEM_BUG_ON(!engine->timeline->inflight_seqnos); - engine->timeline->inflight_seqnos--; } void i915_gem_retire_noop(struct i915_gem_active *active, @@ -296,6 +298,7 @@ void i915_gem_retire_noop(struct i915_gem_active *active, static void advance_ring(struct i915_request *request) { + struct intel_ring *ring = request->ring; unsigned int tail; /* @@ -307,7 +310,8 @@ static void advance_ring(struct i915_request *request) * Note this requires that we are always called in request * completion order. */ - if (list_is_last(&request->ring_link, &request->ring->request_list)) { + GEM_BUG_ON(!list_is_first(&request->ring_link, &ring->request_list)); + if (list_is_last(&request->ring_link, &ring->request_list)) { /* * We may race here with execlists resubmitting this request * as we retire it. The resubmission will move the ring->tail @@ -317,12 +321,13 @@ static void advance_ring(struct i915_request *request) * noops - they are safe to be replayed on a reset. */ tail = READ_ONCE(request->tail); + list_del(&ring->active_link); } else { tail = request->postfix; } - list_del(&request->ring_link); + list_del_init(&request->ring_link); - request->ring->head = tail; + ring->head = tail; } static void free_capture_list(struct i915_request *request) @@ -338,31 +343,84 @@ static void free_capture_list(struct i915_request *request) } } +static void __retire_engine_request(struct intel_engine_cs *engine, + struct i915_request *rq) +{ + GEM_TRACE("%s(%s) fence %llx:%d, global=%d, current %d\n", + __func__, engine->name, + rq->fence.context, rq->fence.seqno, + rq->global_seqno, + intel_engine_get_seqno(engine)); + + GEM_BUG_ON(!i915_request_completed(rq)); + + local_irq_disable(); + + spin_lock(&engine->timeline.lock); + GEM_BUG_ON(!list_is_first(&rq->link, &engine->timeline.requests)); + list_del_init(&rq->link); + spin_unlock(&engine->timeline.lock); + + spin_lock(&rq->lock); + if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)) + dma_fence_signal_locked(&rq->fence); + if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags)) + intel_engine_cancel_signaling(rq); + if (rq->waitboost) { + GEM_BUG_ON(!atomic_read(&rq->i915->gt_pm.rps.num_waiters)); + atomic_dec(&rq->i915->gt_pm.rps.num_waiters); + } + spin_unlock(&rq->lock); + + local_irq_enable(); + + /* + * The backing object for the context is done after switching to the + * *next* context. Therefore we cannot retire the previous context until + * the next context has already started running. However, since we + * cannot take the required locks at i915_request_submit() we + * defer the unpinning of the active context to now, retirement of + * the subsequent request. + */ + if (engine->last_retired_context) + intel_context_unpin(engine->last_retired_context, engine); + engine->last_retired_context = rq->ctx; +} + +static void __retire_engine_upto(struct intel_engine_cs *engine, + struct i915_request *rq) +{ + struct i915_request *tmp; + + if (list_empty(&rq->link)) + return; + + do { + tmp = list_first_entry(&engine->timeline.requests, + typeof(*tmp), link); + + GEM_BUG_ON(tmp->engine != engine); + __retire_engine_request(engine, tmp); + } while (tmp != rq); +} + static void i915_request_retire(struct i915_request *request) { - struct intel_engine_cs *engine = request->engine; struct i915_gem_active *active, *next; GEM_TRACE("%s fence %llx:%d, global=%d, current %d\n", - engine->name, + request->engine->name, request->fence.context, request->fence.seqno, request->global_seqno, - intel_engine_get_seqno(engine)); + intel_engine_get_seqno(request->engine)); lockdep_assert_held(&request->i915->drm.struct_mutex); GEM_BUG_ON(!i915_sw_fence_signaled(&request->submit)); GEM_BUG_ON(!i915_request_completed(request)); - GEM_BUG_ON(!request->i915->gt.active_requests); trace_i915_request_retire(request); - spin_lock_irq(&engine->timeline->lock); - list_del_init(&request->link); - spin_unlock_irq(&engine->timeline->lock); - - unreserve_engine(request->engine); advance_ring(request); - free_capture_list(request); /* @@ -398,65 +456,53 @@ static void i915_request_retire(struct i915_request *request) /* Retirement decays the ban score as it is a sign of ctx progress */ atomic_dec_if_positive(&request->ctx->ban_score); + intel_context_unpin(request->ctx, request->engine); - /* - * The backing object for the context is done after switching to the - * *next* context. Therefore we cannot retire the previous context until - * the next context has already started running. However, since we - * cannot take the required locks at i915_request_submit() we - * defer the unpinning of the active context to now, retirement of - * the subsequent request. - */ - if (engine->last_retired_context) - engine->context_unpin(engine, engine->last_retired_context); - engine->last_retired_context = request->ctx; + __retire_engine_upto(request->engine, request); - spin_lock_irq(&request->lock); - if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags)) - dma_fence_signal_locked(&request->fence); - if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags)) - intel_engine_cancel_signaling(request); - if (request->waitboost) { - GEM_BUG_ON(!atomic_read(&request->i915->gt_pm.rps.num_waiters)); - atomic_dec(&request->i915->gt_pm.rps.num_waiters); - } - spin_unlock_irq(&request->lock); + unreserve_gt(request->i915); - i915_priotree_fini(request->i915, &request->priotree); + i915_sched_node_fini(request->i915, &request->sched); i915_request_put(request); } void i915_request_retire_upto(struct i915_request *rq) { - struct intel_engine_cs *engine = rq->engine; + struct intel_ring *ring = rq->ring; struct i915_request *tmp; + GEM_TRACE("%s fence %llx:%d, global=%d, current %d\n", + rq->engine->name, + rq->fence.context, rq->fence.seqno, + rq->global_seqno, + intel_engine_get_seqno(rq->engine)); + lockdep_assert_held(&rq->i915->drm.struct_mutex); GEM_BUG_ON(!i915_request_completed(rq)); - if (list_empty(&rq->link)) + if (list_empty(&rq->ring_link)) return; do { - tmp = list_first_entry(&engine->timeline->requests, - typeof(*tmp), link); + tmp = list_first_entry(&ring->request_list, + typeof(*tmp), ring_link); i915_request_retire(tmp); } while (tmp != rq); } -static u32 timeline_get_seqno(struct intel_timeline *tl) +static u32 timeline_get_seqno(struct i915_timeline *tl) { return ++tl->seqno; } static void move_to_timeline(struct i915_request *request, - struct intel_timeline *timeline) + struct i915_timeline *timeline) { - GEM_BUG_ON(request->timeline == request->engine->timeline); - lockdep_assert_held(&request->engine->timeline->lock); + GEM_BUG_ON(request->timeline == &request->engine->timeline); + lockdep_assert_held(&request->engine->timeline.lock); - spin_lock(&request->timeline->lock); + spin_lock_nested(&request->timeline->lock, SINGLE_DEPTH_NESTING); list_move_tail(&request->link, &timeline->requests); spin_unlock(&request->timeline->lock); } @@ -469,15 +515,15 @@ void __i915_request_submit(struct i915_request *request) GEM_TRACE("%s fence %llx:%d -> global=%d, current %d\n", engine->name, request->fence.context, request->fence.seqno, - engine->timeline->seqno + 1, + engine->timeline.seqno + 1, intel_engine_get_seqno(engine)); GEM_BUG_ON(!irqs_disabled()); - lockdep_assert_held(&engine->timeline->lock); + lockdep_assert_held(&engine->timeline.lock); GEM_BUG_ON(request->global_seqno); - seqno = timeline_get_seqno(engine->timeline); + seqno = timeline_get_seqno(&engine->timeline); GEM_BUG_ON(!seqno); GEM_BUG_ON(i915_seqno_passed(intel_engine_get_seqno(engine), seqno)); @@ -492,7 +538,7 @@ void __i915_request_submit(struct i915_request *request) request->ring->vaddr + request->postfix); /* Transfer from per-context onto the global per-engine timeline */ - move_to_timeline(request, engine->timeline); + move_to_timeline(request, &engine->timeline); trace_i915_request_execute(request); @@ -505,11 +551,11 @@ void i915_request_submit(struct i915_request *request) unsigned long flags; /* Will be called from irq-context when using foreign fences. */ - spin_lock_irqsave(&engine->timeline->lock, flags); + spin_lock_irqsave(&engine->timeline.lock, flags); __i915_request_submit(request); - spin_unlock_irqrestore(&engine->timeline->lock, flags); + spin_unlock_irqrestore(&engine->timeline.lock, flags); } void __i915_request_unsubmit(struct i915_request *request) @@ -523,17 +569,17 @@ void __i915_request_unsubmit(struct i915_request *request) intel_engine_get_seqno(engine)); GEM_BUG_ON(!irqs_disabled()); - lockdep_assert_held(&engine->timeline->lock); + lockdep_assert_held(&engine->timeline.lock); /* * Only unwind in reverse order, required so that the per-context list * is kept in seqno/ring order. */ GEM_BUG_ON(!request->global_seqno); - GEM_BUG_ON(request->global_seqno != engine->timeline->seqno); + GEM_BUG_ON(request->global_seqno != engine->timeline.seqno); GEM_BUG_ON(i915_seqno_passed(intel_engine_get_seqno(engine), request->global_seqno)); - engine->timeline->seqno--; + engine->timeline.seqno--; /* We may be recursing from the signal callback of another i915 fence */ spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); @@ -560,11 +606,11 @@ void i915_request_unsubmit(struct i915_request *request) unsigned long flags; /* Will be called from irq-context when using foreign fences. */ - spin_lock_irqsave(&engine->timeline->lock, flags); + spin_lock_irqsave(&engine->timeline.lock, flags); __i915_request_unsubmit(request); - spin_unlock_irqrestore(&engine->timeline->lock, flags); + spin_unlock_irqrestore(&engine->timeline.lock, flags); } static int __i915_sw_fence_call @@ -635,12 +681,12 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) * GGTT space, so do this first before we reserve a seqno for * ourselves. */ - ring = engine->context_pin(engine, ctx); + ring = intel_context_pin(ctx, engine); if (IS_ERR(ring)) return ERR_CAST(ring); GEM_BUG_ON(!ring); - ret = reserve_engine(engine); + ret = reserve_gt(i915); if (ret) goto err_unpin; @@ -648,10 +694,10 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) if (ret) goto err_unreserve; - /* Move the oldest request to the slab-cache (if not in use!) */ - rq = list_first_entry_or_null(&engine->timeline->requests, - typeof(*rq), link); - if (rq && i915_request_completed(rq)) + /* Move our oldest request to the slab-cache (if not in use!) */ + rq = list_first_entry(&ring->request_list, typeof(*rq), ring_link); + if (!list_is_last(&rq->ring_link, &ring->request_list) && + i915_request_completed(rq)) i915_request_retire(rq); /* @@ -711,8 +757,13 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) } } - rq->timeline = i915_gem_context_lookup_timeline(ctx, engine); - GEM_BUG_ON(rq->timeline == engine->timeline); + INIT_LIST_HEAD(&rq->active_list); + rq->i915 = i915; + rq->engine = engine; + rq->ctx = ctx; + rq->ring = ring; + rq->timeline = ring->timeline; + GEM_BUG_ON(rq->timeline == &engine->timeline); spin_lock_init(&rq->lock); dma_fence_init(&rq->fence, @@ -725,13 +776,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) i915_sw_fence_init(&i915_request_get(rq)->submit, submit_notify); init_waitqueue_head(&rq->execute); - i915_priotree_init(&rq->priotree); - - INIT_LIST_HEAD(&rq->active_list); - rq->i915 = i915; - rq->engine = engine; - rq->ctx = ctx; - rq->ring = ring; + i915_sched_node_init(&rq->sched); /* No zalloc, must clear what we need by hand */ rq->global_seqno = 0; @@ -768,6 +813,9 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) if (ret) goto err_unwind; + /* Keep a second pin for the dual retirement along engine and ring */ + __intel_context_pin(rq->ctx, engine); + /* Check that we didn't interrupt ourselves with a new request */ GEM_BUG_ON(rq->timeline->seqno != rq->fence.seqno); return rq; @@ -777,14 +825,14 @@ err_unwind: /* Make sure we didn't add ourselves to external state before freeing */ GEM_BUG_ON(!list_empty(&rq->active_list)); - GEM_BUG_ON(!list_empty(&rq->priotree.signalers_list)); - GEM_BUG_ON(!list_empty(&rq->priotree.waiters_list)); + GEM_BUG_ON(!list_empty(&rq->sched.signalers_list)); + GEM_BUG_ON(!list_empty(&rq->sched.waiters_list)); kmem_cache_free(i915->requests, rq); err_unreserve: - unreserve_engine(engine); + unreserve_gt(i915); err_unpin: - engine->context_unpin(engine, ctx); + intel_context_unpin(ctx, engine); return ERR_PTR(ret); } @@ -800,9 +848,9 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) return 0; if (to->engine->schedule) { - ret = i915_priotree_add_dependency(to->i915, - &to->priotree, - &from->priotree); + ret = i915_sched_node_add_dependency(to->i915, + &to->sched, + &from->sched); if (ret < 0) return ret; } @@ -880,7 +928,7 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence) /* Squash repeated waits to the same timelines */ if (fence->context != rq->i915->mm.unordered_timeline && - intel_timeline_sync_is_later(rq->timeline, fence)) + i915_timeline_sync_is_later(rq->timeline, fence)) continue; if (dma_fence_is_i915(fence)) @@ -894,7 +942,7 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence) /* Record the latest fence used against each timeline */ if (fence->context != rq->i915->mm.unordered_timeline) - intel_timeline_sync_set(rq->timeline, fence); + i915_timeline_sync_set(rq->timeline, fence); } while (--nchild); return 0; @@ -971,7 +1019,7 @@ void __i915_request_add(struct i915_request *request, bool flush_caches) { struct intel_engine_cs *engine = request->engine; struct intel_ring *ring = request->ring; - struct intel_timeline *timeline = request->timeline; + struct i915_timeline *timeline = request->timeline; struct i915_request *prev; u32 *cs; int err; @@ -1033,10 +1081,10 @@ void __i915_request_add(struct i915_request *request, bool flush_caches) i915_sw_fence_await_sw_fence(&request->submit, &prev->submit, &request->submitq); if (engine->schedule) - __i915_priotree_add_dependency(&request->priotree, - &prev->priotree, - &request->dep, - 0); + __i915_sched_node_add_dependency(&request->sched, + &prev->sched, + &request->dep, + 0); } spin_lock_irq(&timeline->lock); @@ -1047,6 +1095,8 @@ void __i915_request_add(struct i915_request *request, bool flush_caches) i915_gem_active_set(&timeline->last_request, request); list_add_tail(&request->ring_link, &ring->request_list); + if (list_is_first(&request->ring_link, &ring->request_list)) + list_add(&ring->active_link, &request->i915->gt.active_rings); request->emitted_jiffies = jiffies; /* @@ -1060,12 +1110,11 @@ void __i915_request_add(struct i915_request *request, bool flush_caches) * decide whether to preempt the entire chain so that it is ready to * run at the earliest possible convenience. */ - rcu_read_lock(); + local_bh_disable(); + rcu_read_lock(); /* RCU serialisation for set-wedged protection */ if (engine->schedule) - engine->schedule(request, request->ctx->priority); + engine->schedule(request, &request->ctx->sched); rcu_read_unlock(); - - local_bh_disable(); i915_sw_fence_commit(&request->submit); local_bh_enable(); /* Kick the execlists tasklet if just scheduled */ @@ -1354,38 +1403,30 @@ complete: return timeout; } -static void engine_retire_requests(struct intel_engine_cs *engine) +static void ring_retire_requests(struct intel_ring *ring) { struct i915_request *request, *next; - u32 seqno = intel_engine_get_seqno(engine); - LIST_HEAD(retire); - spin_lock_irq(&engine->timeline->lock); list_for_each_entry_safe(request, next, - &engine->timeline->requests, link) { - if (!i915_seqno_passed(seqno, request->global_seqno)) + &ring->request_list, ring_link) { + if (!i915_request_completed(request)) break; - list_move_tail(&request->link, &retire); - } - spin_unlock_irq(&engine->timeline->lock); - - list_for_each_entry_safe(request, next, &retire, link) i915_request_retire(request); + } } void i915_retire_requests(struct drm_i915_private *i915) { - struct intel_engine_cs *engine; - enum intel_engine_id id; + struct intel_ring *ring, *tmp; lockdep_assert_held(&i915->drm.struct_mutex); if (!i915->gt.active_requests) return; - for_each_engine(engine, i915, id) - engine_retire_requests(engine); + list_for_each_entry_safe(ring, tmp, &i915->gt.active_rings, active_link) + ring_retire_requests(ring); } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 7d6eb82..eddbd424 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -28,13 +28,16 @@ #include <linux/dma-fence.h> #include "i915_gem.h" +#include "i915_scheduler.h" #include "i915_sw_fence.h" +#include "i915_scheduler.h" #include <uapi/drm/i915_drm.h> struct drm_file; struct drm_i915_gem_object; struct i915_request; +struct i915_timeline; struct intel_wait { struct rb_node node; @@ -48,44 +51,6 @@ struct intel_signal_node { struct list_head link; }; -struct i915_dependency { - struct i915_priotree *signaler; - struct list_head signal_link; - struct list_head wait_link; - struct list_head dfs_link; - unsigned long flags; -#define I915_DEPENDENCY_ALLOC BIT(0) -}; - -/* - * "People assume that time is a strict progression of cause to effect, but - * actually, from a nonlinear, non-subjective viewpoint, it's more like a big - * ball of wibbly-wobbly, timey-wimey ... stuff." -The Doctor, 2015 - * - * Requests exist in a complex web of interdependencies. Each request - * has to wait for some other request to complete before it is ready to be run - * (e.g. we have to wait until the pixels have been rendering into a texture - * before we can copy from it). We track the readiness of a request in terms - * of fences, but we also need to keep the dependency tree for the lifetime - * of the request (beyond the life of an individual fence). We use the tree - * at various points to reorder the requests whilst keeping the requests - * in order with respect to their various dependencies. - */ -struct i915_priotree { - struct list_head signalers_list; /* those before us, we depend upon */ - struct list_head waiters_list; /* those after us, they depend upon us */ - struct list_head link; - int priority; -}; - -enum { - I915_PRIORITY_MIN = I915_CONTEXT_MIN_USER_PRIORITY - 1, - I915_PRIORITY_NORMAL = I915_CONTEXT_DEFAULT_PRIORITY, - I915_PRIORITY_MAX = I915_CONTEXT_MAX_USER_PRIORITY + 1, - - I915_PRIORITY_INVALID = INT_MIN -}; - struct i915_capture_list { struct i915_capture_list *next; struct i915_vma *vma; @@ -131,7 +96,7 @@ struct i915_request { struct i915_gem_context *ctx; struct intel_engine_cs *engine; struct intel_ring *ring; - struct intel_timeline *timeline; + struct i915_timeline *timeline; struct intel_signal_node signaling; /* @@ -154,7 +119,7 @@ struct i915_request { * to retirement), i.e. bidirectional dependency information for the * request not tied to individual fences. */ - struct i915_priotree priotree; + struct i915_sched_node sched; struct i915_dependency dep; /** @@ -343,10 +308,10 @@ static inline bool i915_request_started(const struct i915_request *rq) seqno - 1); } -static inline bool i915_priotree_signaled(const struct i915_priotree *pt) +static inline bool i915_sched_node_signaled(const struct i915_sched_node *node) { const struct i915_request *rq = - container_of(pt, const struct i915_request, priotree); + container_of(node, const struct i915_request, sched); return i915_request_completed(rq); } diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h new file mode 100644 index 0000000..70a4222 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_scheduler.h @@ -0,0 +1,72 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#ifndef _I915_SCHEDULER_H_ +#define _I915_SCHEDULER_H_ + +#include <linux/bitops.h> + +#include <uapi/drm/i915_drm.h> + +enum { + I915_PRIORITY_MIN = I915_CONTEXT_MIN_USER_PRIORITY - 1, + I915_PRIORITY_NORMAL = I915_CONTEXT_DEFAULT_PRIORITY, + I915_PRIORITY_MAX = I915_CONTEXT_MAX_USER_PRIORITY + 1, + + I915_PRIORITY_INVALID = INT_MIN +}; + +struct i915_sched_attr { + /** + * @priority: execution and service priority + * + * All clients are equal, but some are more equal than others! + * + * Requests from a context with a greater (more positive) value of + * @priority will be executed before those with a lower @priority + * value, forming a simple QoS. + * + * The &drm_i915_private.kernel_context is assigned the lowest priority. + */ + int priority; +}; + +/* + * "People assume that time is a strict progression of cause to effect, but + * actually, from a nonlinear, non-subjective viewpoint, it's more like a big + * ball of wibbly-wobbly, timey-wimey ... stuff." -The Doctor, 2015 + * + * Requests exist in a complex web of interdependencies. Each request + * has to wait for some other request to complete before it is ready to be run + * (e.g. we have to wait until the pixels have been rendering into a texture + * before we can copy from it). We track the readiness of a request in terms + * of fences, but we also need to keep the dependency tree for the lifetime + * of the request (beyond the life of an individual fence). We use the tree + * at various points to reorder the requests whilst keeping the requests + * in order with respect to their various dependencies. + * + * There is no active component to the "scheduler". As we know the dependency + * DAG of each request, we are able to insert it into a sorted queue when it + * is ready, and are able to reorder its portion of the graph to accommodate + * dynamic priority changes. + */ +struct i915_sched_node { + struct list_head signalers_list; /* those before us, we depend upon */ + struct list_head waiters_list; /* those after us, they depend upon us */ + struct list_head link; + struct i915_sched_attr attr; +}; + +struct i915_dependency { + struct i915_sched_node *signaler; + struct list_head signal_link; + struct list_head wait_link; + struct list_head dfs_link; + unsigned long flags; +#define I915_DEPENDENCY_ALLOC BIT(0) +}; + +#endif /* _I915_SCHEDULER_H_ */ diff --git a/drivers/gpu/drm/i915/i915_timeline.c b/drivers/gpu/drm/i915/i915_timeline.c new file mode 100644 index 0000000..4667cc0 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_timeline.c @@ -0,0 +1,105 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2016-2018 Intel Corporation + */ + +#include "i915_drv.h" + +#include "i915_timeline.h" +#include "i915_syncmap.h" + +void i915_timeline_init(struct drm_i915_private *i915, + struct i915_timeline *timeline, + const char *name) +{ + lockdep_assert_held(&i915->drm.struct_mutex); + + /* + * Ideally we want a set of engines on a single leaf as we expect + * to mostly be tracking synchronisation between engines. It is not + * a huge issue if this is not the case, but we may want to mitigate + * any page crossing penalties if they become an issue. + */ + BUILD_BUG_ON(KSYNCMAP < I915_NUM_ENGINES); + + timeline->name = name; + + list_add(&timeline->link, &i915->gt.timelines); + + /* Called during early_init before we know how many engines there are */ + + timeline->fence_context = dma_fence_context_alloc(1); + + spin_lock_init(&timeline->lock); + + init_request_active(&timeline->last_request, NULL); + INIT_LIST_HEAD(&timeline->requests); + + i915_syncmap_init(&timeline->sync); +} + +/** + * i915_timelines_park - called when the driver idles + * @i915: the drm_i915_private device + * + * When the driver is completely idle, we know that all of our sync points + * have been signaled and our tracking is then entirely redundant. Any request + * to wait upon an older sync point will be completed instantly as we know + * the fence is signaled and therefore we will not even look them up in the + * sync point map. + */ +void i915_timelines_park(struct drm_i915_private *i915) +{ + struct i915_timeline *timeline; + + lockdep_assert_held(&i915->drm.struct_mutex); + + list_for_each_entry(timeline, &i915->gt.timelines, link) { + /* + * All known fences are completed so we can scrap + * the current sync point tracking and start afresh, + * any attempt to wait upon a previous sync point + * will be skipped as the fence was signaled. + */ + i915_syncmap_free(&timeline->sync); + } +} + +void i915_timeline_fini(struct i915_timeline *timeline) +{ + GEM_BUG_ON(!list_empty(&timeline->requests)); + + i915_syncmap_free(&timeline->sync); + + list_del(&timeline->link); +} + +struct i915_timeline * +i915_timeline_create(struct drm_i915_private *i915, const char *name) +{ + struct i915_timeline *timeline; + + timeline = kzalloc(sizeof(*timeline), GFP_KERNEL); + if (!timeline) + return ERR_PTR(-ENOMEM); + + i915_timeline_init(i915, timeline, name); + kref_init(&timeline->kref); + + return timeline; +} + +void __i915_timeline_free(struct kref *kref) +{ + struct i915_timeline *timeline = + container_of(kref, typeof(*timeline), kref); + + i915_timeline_fini(timeline); + kfree(timeline); +} + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#include "selftests/mock_timeline.c" +#include "selftests/i915_timeline.c" +#endif diff --git a/drivers/gpu/drm/i915/i915_gem_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h index 33e01bf..dc2a463 100644 --- a/drivers/gpu/drm/i915/i915_gem_timeline.h +++ b/drivers/gpu/drm/i915/i915_timeline.h @@ -22,27 +22,20 @@ * */ -#ifndef I915_GEM_TIMELINE_H -#define I915_GEM_TIMELINE_H +#ifndef I915_TIMELINE_H +#define I915_TIMELINE_H #include <linux/list.h> +#include <linux/kref.h> #include "i915_request.h" #include "i915_syncmap.h" #include "i915_utils.h" -struct i915_gem_timeline; - -struct intel_timeline { +struct i915_timeline { u64 fence_context; u32 seqno; - /** - * Count of outstanding requests, from the time they are constructed - * to the moment they are retired. Loosely coupled to hardware. - */ - u32 inflight_seqnos; - spinlock_t lock; /** @@ -77,47 +70,57 @@ struct intel_timeline { */ u32 global_sync[I915_NUM_ENGINES]; - struct i915_gem_timeline *common; -}; - -struct i915_gem_timeline { struct list_head link; - - struct drm_i915_private *i915; const char *name; - struct intel_timeline engine[I915_NUM_ENGINES]; + struct kref kref; }; -int i915_gem_timeline_init(struct drm_i915_private *i915, - struct i915_gem_timeline *tl, - const char *name); -int i915_gem_timeline_init__global(struct drm_i915_private *i915); -void i915_gem_timelines_park(struct drm_i915_private *i915); -void i915_gem_timeline_fini(struct i915_gem_timeline *tl); +void i915_timeline_init(struct drm_i915_private *i915, + struct i915_timeline *tl, + const char *name); +void i915_timeline_fini(struct i915_timeline *tl); + +struct i915_timeline * +i915_timeline_create(struct drm_i915_private *i915, const char *name); -static inline int __intel_timeline_sync_set(struct intel_timeline *tl, - u64 context, u32 seqno) +static inline struct i915_timeline * +i915_timeline_get(struct i915_timeline *timeline) +{ + kref_get(&timeline->kref); + return timeline; +} + +void __i915_timeline_free(struct kref *kref); +static inline void i915_timeline_put(struct i915_timeline *timeline) +{ + kref_put(&timeline->kref, __i915_timeline_free); +} + +static inline int __i915_timeline_sync_set(struct i915_timeline *tl, + u64 context, u32 seqno) { return i915_syncmap_set(&tl->sync, context, seqno); } -static inline int intel_timeline_sync_set(struct intel_timeline *tl, - const struct dma_fence *fence) +static inline int i915_timeline_sync_set(struct i915_timeline *tl, + const struct dma_fence *fence) { - return __intel_timeline_sync_set(tl, fence->context, fence->seqno); + return __i915_timeline_sync_set(tl, fence->context, fence->seqno); } -static inline bool __intel_timeline_sync_is_later(struct intel_timeline *tl, - u64 context, u32 seqno) +static inline bool __i915_timeline_sync_is_later(struct i915_timeline *tl, + u64 context, u32 seqno) { return i915_syncmap_is_later(&tl->sync, context, seqno); } -static inline bool intel_timeline_sync_is_later(struct intel_timeline *tl, - const struct dma_fence *fence) +static inline bool i915_timeline_sync_is_later(struct i915_timeline *tl, + const struct dma_fence *fence) { - return __intel_timeline_sync_is_later(tl, fence->context, fence->seqno); + return __i915_timeline_sync_is_later(tl, fence->context, fence->seqno); } +void i915_timelines_park(struct drm_i915_private *i915); + #endif diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 408827b..8cc3a25 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -679,45 +679,68 @@ DEFINE_EVENT(i915_request, i915_request_execute, TP_ARGS(rq) ); -DECLARE_EVENT_CLASS(i915_request_hw, - TP_PROTO(struct i915_request *rq, unsigned int port), - TP_ARGS(rq, port), - - TP_STRUCT__entry( - __field(u32, dev) - __field(u32, hw_id) - __field(u32, ring) - __field(u32, ctx) - __field(u32, seqno) - __field(u32, global_seqno) - __field(u32, port) - ), - - TP_fast_assign( - __entry->dev = rq->i915->drm.primary->index; - __entry->hw_id = rq->ctx->hw_id; - __entry->ring = rq->engine->id; - __entry->ctx = rq->fence.context; - __entry->seqno = rq->fence.seqno; - __entry->global_seqno = rq->global_seqno; - __entry->port = port; - ), - - TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, port=%u", - __entry->dev, __entry->hw_id, __entry->ring, - __entry->ctx, __entry->seqno, - __entry->global_seqno, __entry->port) -); +TRACE_EVENT(i915_request_in, + TP_PROTO(struct i915_request *rq, unsigned int port), + TP_ARGS(rq, port), + + TP_STRUCT__entry( + __field(u32, dev) + __field(u32, hw_id) + __field(u32, ring) + __field(u32, ctx) + __field(u32, seqno) + __field(u32, global_seqno) + __field(u32, port) + __field(u32, prio) + ), + + TP_fast_assign( + __entry->dev = rq->i915->drm.primary->index; + __entry->hw_id = rq->ctx->hw_id; + __entry->ring = rq->engine->id; + __entry->ctx = rq->fence.context; + __entry->seqno = rq->fence.seqno; + __entry->global_seqno = rq->global_seqno; + __entry->prio = rq->sched.attr.priority; + __entry->port = port; + ), -DEFINE_EVENT(i915_request_hw, i915_request_in, - TP_PROTO(struct i915_request *rq, unsigned int port), - TP_ARGS(rq, port) + TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u", + __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx, + __entry->seqno, __entry->prio, __entry->global_seqno, + __entry->port) ); -DEFINE_EVENT(i915_request, i915_request_out, - TP_PROTO(struct i915_request *rq), - TP_ARGS(rq) +TRACE_EVENT(i915_request_out, + TP_PROTO(struct i915_request *rq), + TP_ARGS(rq), + + TP_STRUCT__entry( + __field(u32, dev) + __field(u32, hw_id) + __field(u32, ring) + __field(u32, ctx) + __field(u32, seqno) + __field(u32, global_seqno) + __field(u32, completed) + ), + + TP_fast_assign( + __entry->dev = rq->i915->drm.primary->index; + __entry->hw_id = rq->ctx->hw_id; + __entry->ring = rq->engine->id; + __entry->ctx = rq->fence.context; + __entry->seqno = rq->fence.seqno; + __entry->global_seqno = rq->global_seqno; + __entry->completed = i915_request_completed(rq); + ), + + TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, completed?=%u", + __entry->dev, __entry->hw_id, __entry->ring, + __entry->ctx, __entry->seqno, + __entry->global_seqno, __entry->completed) ); + #else #if !defined(TRACE_HEADER_MULTI_READ) static inline void @@ -811,42 +834,6 @@ DEFINE_EVENT(i915_request, i915_request_wait_end, TP_ARGS(rq) ); -TRACE_EVENT(i915_flip_request, - TP_PROTO(int plane, struct drm_i915_gem_object *obj), - - TP_ARGS(plane, obj), - - TP_STRUCT__entry( - __field(int, plane) - __field(struct drm_i915_gem_object *, obj) - ), - - TP_fast_assign( - __entry->plane = plane; - __entry->obj = obj; - ), - - TP_printk("plane=%d, obj=%p", __entry->plane, __entry->obj) -); - -TRACE_EVENT(i915_flip_complete, - TP_PROTO(int plane, struct drm_i915_gem_object *obj), - - TP_ARGS(plane, obj), - - TP_STRUCT__entry( - __field(int, plane) - __field(struct drm_i915_gem_object *, obj) - ), - - TP_fast_assign( - __entry->plane = plane; - __entry->obj = obj; - ), - - TP_printk("plane=%d, obj=%p", __entry->plane, __entry->obj) -); - TRACE_EVENT_CONDITION(i915_reg_rw, TP_PROTO(bool write, i915_reg_t reg, u64 val, int len, bool trace), diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index 0695717..00165ad 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -120,6 +120,12 @@ static inline u64 ptr_to_u64(const void *ptr) #include <linux/list.h> +static inline int list_is_first(const struct list_head *list, + const struct list_head *head) +{ + return head->next == list; +} + static inline void __list_del_many(struct list_head *head, struct list_head *first) { diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 4bda3bd..9324d47 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -46,8 +46,6 @@ i915_vma_retire(struct i915_gem_active *active, struct i915_request *rq) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); list_move_tail(&vma->vm_link, &vma->vm->inactive_list); - if (unlikely(i915_vma_is_closed(vma) && !i915_vma_is_pinned(vma))) - WARN_ON(i915_vma_unbind(vma)); GEM_BUG_ON(!i915_gem_object_is_active(obj)); if (--obj->active_count) @@ -232,7 +230,6 @@ i915_vma_instance(struct drm_i915_gem_object *obj, if (!vma) vma = vma_create(obj, vm, view); - GEM_BUG_ON(!IS_ERR(vma) && i915_vma_is_closed(vma)); GEM_BUG_ON(!IS_ERR(vma) && i915_vma_compare(vma, vm, view)); GEM_BUG_ON(!IS_ERR(vma) && vma_lookup(obj, vm, view) != vma); return vma; @@ -684,13 +681,43 @@ err_unpin: return ret; } -static void i915_vma_destroy(struct i915_vma *vma) +void i915_vma_close(struct i915_vma *vma) +{ + lockdep_assert_held(&vma->vm->i915->drm.struct_mutex); + + GEM_BUG_ON(i915_vma_is_closed(vma)); + vma->flags |= I915_VMA_CLOSED; + + /* + * We defer actually closing, unbinding and destroying the VMA until + * the next idle point, or if the object is freed in the meantime. By + * postponing the unbind, we allow for it to be resurrected by the + * client, avoiding the work required to rebind the VMA. This is + * advantageous for DRI, where the client/server pass objects + * between themselves, temporarily opening a local VMA to the + * object, and then closing it again. The same object is then reused + * on the next frame (or two, depending on the depth of the swap queue) + * causing us to rebind the VMA once more. This ends up being a lot + * of wasted work for the steady state. + */ + list_add_tail(&vma->closed_link, &vma->vm->i915->gt.closed_vma); +} + +void i915_vma_reopen(struct i915_vma *vma) +{ + lockdep_assert_held(&vma->vm->i915->drm.struct_mutex); + + if (vma->flags & I915_VMA_CLOSED) { + vma->flags &= ~I915_VMA_CLOSED; + list_del(&vma->closed_link); + } +} + +static void __i915_vma_destroy(struct i915_vma *vma) { int i; GEM_BUG_ON(vma->node.allocated); - GEM_BUG_ON(i915_vma_is_active(vma)); - GEM_BUG_ON(!i915_vma_is_closed(vma)); GEM_BUG_ON(vma->fence); for (i = 0; i < ARRAY_SIZE(vma->last_read); i++) @@ -699,6 +726,7 @@ static void i915_vma_destroy(struct i915_vma *vma) list_del(&vma->obj_link); list_del(&vma->vm_link); + rb_erase(&vma->obj_node, &vma->obj->vma_tree); if (!i915_vma_is_ggtt(vma)) i915_ppgtt_put(i915_vm_to_ppgtt(vma->vm)); @@ -706,15 +734,30 @@ static void i915_vma_destroy(struct i915_vma *vma) kmem_cache_free(to_i915(vma->obj->base.dev)->vmas, vma); } -void i915_vma_close(struct i915_vma *vma) +void i915_vma_destroy(struct i915_vma *vma) { - GEM_BUG_ON(i915_vma_is_closed(vma)); - vma->flags |= I915_VMA_CLOSED; + lockdep_assert_held(&vma->vm->i915->drm.struct_mutex); - rb_erase(&vma->obj_node, &vma->obj->vma_tree); + GEM_BUG_ON(i915_vma_is_active(vma)); + GEM_BUG_ON(i915_vma_is_pinned(vma)); + + if (i915_vma_is_closed(vma)) + list_del(&vma->closed_link); + + WARN_ON(i915_vma_unbind(vma)); + __i915_vma_destroy(vma); +} + +void i915_vma_parked(struct drm_i915_private *i915) +{ + struct i915_vma *vma, *next; - if (!i915_vma_is_active(vma) && !i915_vma_is_pinned(vma)) - WARN_ON(i915_vma_unbind(vma)); + list_for_each_entry_safe(vma, next, &i915->gt.closed_vma, closed_link) { + GEM_BUG_ON(!i915_vma_is_closed(vma)); + i915_vma_destroy(vma); + } + + GEM_BUG_ON(!list_empty(&i915->gt.closed_vma)); } static void __i915_vma_iounmap(struct i915_vma *vma) @@ -804,7 +847,7 @@ int i915_vma_unbind(struct i915_vma *vma) return -EBUSY; if (!drm_mm_node_allocated(&vma->node)) - goto destroy; + return 0; GEM_BUG_ON(obj->bind_count == 0); GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); @@ -841,10 +884,6 @@ int i915_vma_unbind(struct i915_vma *vma) i915_vma_remove(vma); -destroy: - if (unlikely(i915_vma_is_closed(vma))) - i915_vma_destroy(vma); - return 0; } diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 8c50220..fc4294c 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -119,6 +119,8 @@ struct i915_vma { /** This vma's place in the eviction list */ struct list_head evict_link; + struct list_head closed_link; + /** * Used for performing relocations during execbuffer insertion. */ @@ -285,6 +287,8 @@ void i915_vma_revoke_mmap(struct i915_vma *vma); int __must_check i915_vma_unbind(struct i915_vma *vma); void i915_vma_unlink_ctx(struct i915_vma *vma); void i915_vma_close(struct i915_vma *vma); +void i915_vma_reopen(struct i915_vma *vma); +void i915_vma_destroy(struct i915_vma *vma); int __i915_vma_do_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags); @@ -408,6 +412,8 @@ i915_vma_unpin_fence(struct i915_vma *vma) __i915_vma_unpin_fence(vma); } +void i915_vma_parked(struct drm_i915_private *i915); + #define for_each_until(cond) if (cond) break; else /** diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c index 7481ce8..6d06878 100644 --- a/drivers/gpu/drm/i915/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/intel_atomic_plane.c @@ -183,11 +183,16 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_ } /* FIXME pre-g4x don't work like this */ - if (intel_state->base.visible) + if (state->visible) crtc_state->active_planes |= BIT(intel_plane->id); else crtc_state->active_planes &= ~BIT(intel_plane->id); + if (state->visible && state->fb->format->format == DRM_FORMAT_NV12) + crtc_state->nv12_planes |= BIT(intel_plane->id); + else + crtc_state->nv12_planes &= ~BIT(intel_plane->id); + return intel_plane_atomic_calc_changes(old_crtc_state, &crtc_state->base, old_plane_state, diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 656f6c9..3ea566f 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -729,7 +729,7 @@ static void i915_audio_component_codec_wake_override(struct device *kdev, struct drm_i915_private *dev_priv = kdev_to_i915(kdev); u32 tmp; - if (!IS_GEN9_BC(dev_priv) && !IS_BROXTON(dev_priv)) + if (!IS_GEN9(dev_priv)) return; i915_audio_component_get_power(kdev); diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 702d3fa..54270bd 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -530,6 +530,7 @@ parse_driver_features(struct drm_i915_private *dev_priv, */ if (!driver->drrs_enabled) dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED; + dev_priv->vbt.psr.enable = driver->psr_enabled; } static void diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c index 671a6d6..18e643d 100644 --- a/drivers/gpu/drm/i915/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c @@ -82,7 +82,7 @@ static unsigned long wait_timeout(void) static noinline void missed_breadcrumb(struct intel_engine_cs *engine) { - if (drm_debug & DRM_UT_DRIVER) { + if (GEM_SHOW_DEBUG()) { struct drm_printer p = drm_debug_printer(__func__); intel_engine_dump(engine, &p, @@ -130,11 +130,12 @@ static void intel_breadcrumbs_hangcheck(struct timer_list *t) static void intel_breadcrumbs_fake_irq(struct timer_list *t) { - struct intel_engine_cs *engine = from_timer(engine, t, - breadcrumbs.fake_irq); + struct intel_engine_cs *engine = + from_timer(engine, t, breadcrumbs.fake_irq); struct intel_breadcrumbs *b = &engine->breadcrumbs; - /* The timer persists in case we cannot enable interrupts, + /* + * The timer persists in case we cannot enable interrupts, * or if we have previously seen seqno/interrupt incoherency * ("missed interrupt" syndrome, better known as a "missed breadcrumb"). * Here the worker will wake up every jiffie in order to kick the @@ -148,6 +149,12 @@ static void intel_breadcrumbs_fake_irq(struct timer_list *t) if (!b->irq_armed) return; + /* If the user has disabled the fake-irq, restore the hangchecking */ + if (!test_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings)) { + mod_timer(&b->hangcheck, wait_timeout()); + return; + } + mod_timer(&b->fake_irq, jiffies + 1); } @@ -831,8 +838,8 @@ static void cancel_fake_irq(struct intel_engine_cs *engine) { struct intel_breadcrumbs *b = &engine->breadcrumbs; + del_timer_sync(&b->fake_irq); /* may queue b->hangcheck */ del_timer_sync(&b->hangcheck); - del_timer_sync(&b->fake_irq); clear_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings); } @@ -840,15 +847,22 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine) { struct intel_breadcrumbs *b = &engine->breadcrumbs; - cancel_fake_irq(engine); spin_lock_irq(&b->irq_lock); + /* + * Leave the fake_irq timer enabled (if it is running), but clear the + * bit so that it turns itself off on its next wake up and goes back + * to the long hangcheck interval if still required. + */ + clear_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings); + if (b->irq_enabled) irq_enable(engine); else irq_disable(engine); - /* We set the IRQ_BREADCRUMB bit when we enable the irq presuming the + /* + * We set the IRQ_BREADCRUMB bit when we enable the irq presuming the * GPU is active and may have already executed the MI_USER_INTERRUPT * before the CPU is ready to receive. However, the engine is currently * idle (we haven't started it yet), there is no possibility for a @@ -857,9 +871,6 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine) */ clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted); - if (b->irq_armed) - enable_fake_irq(b); - spin_unlock_irq(&b->irq_lock); } diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index dc7db8a..704ddb4 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -1626,7 +1626,7 @@ static void cnl_cdclk_pll_disable(struct drm_i915_private *dev_priv) /* Timeout 200us */ if (wait_for((I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK) == 0, 1)) - DRM_ERROR("timout waiting for CDCLK PLL unlock\n"); + DRM_ERROR("timeout waiting for CDCLK PLL unlock\n"); dev_priv->cdclk.hw.vco = 0; } @@ -1644,7 +1644,7 @@ static void cnl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco) /* Timeout 200us */ if (wait_for((I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK) != 0, 1)) - DRM_ERROR("timout waiting for CDCLK PLL lock\n"); + DRM_ERROR("timeout waiting for CDCLK PLL lock\n"); dev_priv->cdclk.hw.vco = vco; } @@ -2140,10 +2140,22 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) } } - /* According to BSpec, "The CD clock frequency must be at least twice + /* + * According to BSpec, "The CD clock frequency must be at least twice * the frequency of the Azalia BCLK." and BCLK is 96 MHz by default. + * + * FIXME: Check the actual, not default, BCLK being used. + * + * FIXME: This does not depend on ->has_audio because the higher CDCLK + * is required for audio probe, also when there are no audio capable + * displays connected at probe time. This leads to unnecessarily high + * CDCLK when audio is not required. + * + * FIXME: This limit is only applied when there are displays connected + * at probe time. If we probe without displays, we'll still end up using + * the platform minimum CDCLK, failing audio probe. */ - if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9) + if (INTEL_GEN(dev_priv) >= 9) min_cdclk = max(2 * 96000, min_cdclk); /* @@ -2290,9 +2302,44 @@ static int bdw_modeset_calc_cdclk(struct drm_atomic_state *state) return 0; } +static int skl_dpll0_vco(struct intel_atomic_state *intel_state) +{ + struct drm_i915_private *dev_priv = to_i915(intel_state->base.dev); + struct intel_crtc *crtc; + struct intel_crtc_state *crtc_state; + int vco, i; + + vco = intel_state->cdclk.logical.vco; + if (!vco) + vco = dev_priv->skl_preferred_vco_freq; + + for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) { + if (!crtc_state->base.enable) + continue; + + if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) + continue; + + /* + * DPLL0 VCO may need to be adjusted to get the correct + * clock for eDP. This will affect cdclk as well. + */ + switch (crtc_state->port_clock / 2) { + case 108000: + case 216000: + vco = 8640000; + break; + default: + vco = 8100000; + break; + } + } + + return vco; +} + static int skl_modeset_calc_cdclk(struct drm_atomic_state *state) { - struct drm_i915_private *dev_priv = to_i915(state->dev); struct intel_atomic_state *intel_state = to_intel_atomic_state(state); int min_cdclk, cdclk, vco; @@ -2300,9 +2347,7 @@ static int skl_modeset_calc_cdclk(struct drm_atomic_state *state) if (min_cdclk < 0) return min_cdclk; - vco = intel_state->cdclk.logical.vco; - if (!vco) - vco = dev_priv->skl_preferred_vco_freq; + vco = skl_dpll0_vco(intel_state); /* * FIXME should also account for plane ratio diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index c0a8805..de0e223 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -748,6 +748,11 @@ intel_crt_detect(struct drm_connector *connector, connector->base.id, connector->name, force); + if (i915_modparams.load_detect_test) { + intel_display_power_get(dev_priv, intel_encoder->power_domain); + goto load_detect; + } + /* Skip machines without VGA that falsely report hotplug events */ if (dmi_check_system(intel_spurious_crt_detect)) return connector_status_disconnected; @@ -776,11 +781,12 @@ intel_crt_detect(struct drm_connector *connector, * broken monitor (without edid) to work behind a broken kvm (that fails * to have the right resistors for HP detection) needs to fix this up. * For now just bail out. */ - if (I915_HAS_HOTPLUG(dev_priv) && !i915_modparams.load_detect_test) { + if (I915_HAS_HOTPLUG(dev_priv)) { status = connector_status_disconnected; goto out; } +load_detect: if (!force) { status = connector->status; goto out; diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 41e6c75..cf9b600 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -35,6 +35,7 @@ */ #define I915_CSR_GLK "i915/glk_dmc_ver1_04.bin" +MODULE_FIRMWARE(I915_CSR_GLK); #define GLK_CSR_VERSION_REQUIRED CSR_VERSION(1, 4) #define I915_CSR_CNL "i915/cnl_dmc_ver1_07.bin" @@ -297,7 +298,10 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, csr->version = css_header->version; - if (IS_CANNONLAKE(dev_priv)) { + if (csr->fw_path == i915_modparams.dmc_firmware_path) { + /* Bypass version check for firmware override. */ + required_version = csr->version; + } else if (IS_CANNONLAKE(dev_priv)) { required_version = CNL_CSR_VERSION_REQUIRED; } else if (IS_GEMINILAKE(dev_priv)) { required_version = GLK_CSR_VERSION_REQUIRED; @@ -452,7 +456,9 @@ void intel_csr_ucode_init(struct drm_i915_private *dev_priv) if (!HAS_CSR(dev_priv)) return; - if (IS_CANNONLAKE(dev_priv)) + if (i915_modparams.dmc_firmware_path) + csr->fw_path = i915_modparams.dmc_firmware_path; + else if (IS_CANNONLAKE(dev_priv)) csr->fw_path = I915_CSR_CNL; else if (IS_GEMINILAKE(dev_priv)) csr->fw_path = I915_CSR_GLK; diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 92cb26b..b98ac054 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -870,6 +870,45 @@ cnl_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries) } } +static const struct icl_combo_phy_ddi_buf_trans * +icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, enum port port, + int type, int *n_entries) +{ + u32 voltage = I915_READ(ICL_PORT_COMP_DW3(port)) & VOLTAGE_INFO_MASK; + + if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) { + switch (voltage) { + case VOLTAGE_INFO_0_85V: + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_85V); + return icl_combo_phy_ddi_translations_edp_0_85V; + case VOLTAGE_INFO_0_95V: + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_95V); + return icl_combo_phy_ddi_translations_edp_0_95V; + case VOLTAGE_INFO_1_05V: + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_1_05V); + return icl_combo_phy_ddi_translations_edp_1_05V; + default: + MISSING_CASE(voltage); + return NULL; + } + } else { + switch (voltage) { + case VOLTAGE_INFO_0_85V: + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_85V); + return icl_combo_phy_ddi_translations_dp_hdmi_0_85V; + case VOLTAGE_INFO_0_95V: + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_95V); + return icl_combo_phy_ddi_translations_dp_hdmi_0_95V; + case VOLTAGE_INFO_1_05V: + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_1_05V); + return icl_combo_phy_ddi_translations_dp_hdmi_1_05V; + default: + MISSING_CASE(voltage); + return NULL; + } + } +} + static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port) { int n_entries, level, default_entry; @@ -1013,6 +1052,25 @@ static uint32_t hsw_pll_to_ddi_pll_sel(const struct intel_shared_dpll *pll) } } +static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder, + const struct intel_shared_dpll *pll) +{ + const enum intel_dpll_id id = pll->info->id; + + switch (id) { + default: + MISSING_CASE(id); + case DPLL_ID_ICL_DPLL0: + case DPLL_ID_ICL_DPLL1: + return DDI_CLK_SEL_NONE; + case DPLL_ID_ICL_MGPLL1: + case DPLL_ID_ICL_MGPLL2: + case DPLL_ID_ICL_MGPLL3: + case DPLL_ID_ICL_MGPLL4: + return DDI_CLK_SEL_MG; + } +} + /* Starting with Haswell, different DDI ports can work in FDI mode for * connection to the PCH-located connectors. For this, it is necessary to train * both the DDI port and PCH receiver for the desired DDI buffer settings. @@ -2025,7 +2083,13 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder) enum port port = encoder->port; int n_entries; - if (IS_CANNONLAKE(dev_priv)) { + if (IS_ICELAKE(dev_priv)) { + if (port == PORT_A || port == PORT_B) + icl_get_combo_buf_trans(dev_priv, port, encoder->type, + &n_entries); + else + n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); + } else if (IS_CANNONLAKE(dev_priv)) { if (encoder->type == INTEL_OUTPUT_EDP) cnl_get_buf_trans_edp(dev_priv, &n_entries); else @@ -2182,6 +2246,146 @@ static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder, I915_WRITE(CNL_PORT_TX_DW5_GRP(port), val); } +static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, + u32 level, enum port port, int type) +{ + const struct icl_combo_phy_ddi_buf_trans *ddi_translations = NULL; + u32 n_entries, val; + int ln; + + ddi_translations = icl_get_combo_buf_trans(dev_priv, port, type, + &n_entries); + if (!ddi_translations) + return; + + if (level >= n_entries) { + DRM_DEBUG_KMS("DDI translation not found for level %d. Using %d instead.", level, n_entries - 1); + level = n_entries - 1; + } + + /* Set PORT_TX_DW5 Rterm Sel to 110b. */ + val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); + val &= ~RTERM_SELECT_MASK; + val |= RTERM_SELECT(0x6); + I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); + + /* Program PORT_TX_DW5 */ + val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); + /* Set DisableTap2 and DisableTap3 if MIPI DSI + * Clear DisableTap2 and DisableTap3 for all other Ports + */ + if (type == INTEL_OUTPUT_DSI) { + val |= TAP2_DISABLE; + val |= TAP3_DISABLE; + } else { + val &= ~TAP2_DISABLE; + val &= ~TAP3_DISABLE; + } + I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); + + /* Program PORT_TX_DW2 */ + val = I915_READ(ICL_PORT_TX_DW2_LN0(port)); + val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK | + RCOMP_SCALAR_MASK); + val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_select); + val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_select); + /* Program Rcomp scalar for every table entry */ + val |= RCOMP_SCALAR(ddi_translations[level].dw2_swing_scalar); + I915_WRITE(ICL_PORT_TX_DW2_GRP(port), val); + + /* Program PORT_TX_DW4 */ + /* We cannot write to GRP. It would overwrite individual loadgen. */ + for (ln = 0; ln <= 3; ln++) { + val = I915_READ(ICL_PORT_TX_DW4_LN(port, ln)); + val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK | + CURSOR_COEFF_MASK); + val |= ddi_translations[level].dw4_scaling; + I915_WRITE(ICL_PORT_TX_DW4_LN(port, ln), val); + } +} + +static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, + u32 level, + enum intel_output_type type) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum port port = encoder->port; + int width = 0; + int rate = 0; + u32 val; + int ln = 0; + + if (type == INTEL_OUTPUT_HDMI) { + width = 4; + /* Rate is always < than 6GHz for HDMI */ + } else { + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + + width = intel_dp->lane_count; + rate = intel_dp->link_rate; + } + + /* + * 1. If port type is eDP or DP, + * set PORT_PCS_DW1 cmnkeeper_enable to 1b, + * else clear to 0b. + */ + val = I915_READ(ICL_PORT_PCS_DW1_LN0(port)); + if (type == INTEL_OUTPUT_HDMI) + val &= ~COMMON_KEEPER_EN; + else + val |= COMMON_KEEPER_EN; + I915_WRITE(ICL_PORT_PCS_DW1_GRP(port), val); + + /* 2. Program loadgen select */ + /* + * Program PORT_TX_DW4_LN depending on Bit rate and used lanes + * <= 6 GHz and 4 lanes (LN0=0, LN1=1, LN2=1, LN3=1) + * <= 6 GHz and 1,2 lanes (LN0=0, LN1=1, LN2=1, LN3=0) + * > 6 GHz (LN0=0, LN1=0, LN2=0, LN3=0) + */ + for (ln = 0; ln <= 3; ln++) { + val = I915_READ(ICL_PORT_TX_DW4_LN(port, ln)); + val &= ~LOADGEN_SELECT; + + if ((rate <= 600000 && width == 4 && ln >= 1) || + (rate <= 600000 && width < 4 && (ln == 1 || ln == 2))) { + val |= LOADGEN_SELECT; + } + I915_WRITE(ICL_PORT_TX_DW4_LN(port, ln), val); + } + + /* 3. Set PORT_CL_DW5 SUS Clock Config to 11b */ + val = I915_READ(ICL_PORT_CL_DW5(port)); + val |= SUS_CLOCK_CONFIG; + I915_WRITE(ICL_PORT_CL_DW5(port), val); + + /* 4. Clear training enable to change swing values */ + val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); + val &= ~TX_TRAINING_EN; + I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); + + /* 5. Program swing and de-emphasis */ + icl_ddi_combo_vswing_program(dev_priv, level, port, type); + + /* 6. Set training enable to trigger update */ + val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); + val |= TX_TRAINING_EN; + I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); +} + +static void icl_ddi_vswing_sequence(struct intel_encoder *encoder, u32 level, + enum intel_output_type type) +{ + enum port port = encoder->port; + + if (port == PORT_A || port == PORT_B) + icl_combo_phy_ddi_vswing_sequence(encoder, level, type); + else + /* Not Implemented Yet */ + WARN_ON(1); +} + static uint32_t translate_signal_level(int signal_levels) { int i; @@ -2213,7 +2417,9 @@ u32 bxt_signal_levels(struct intel_dp *intel_dp) struct intel_encoder *encoder = &dport->base; int level = intel_ddi_dp_level(intel_dp); - if (IS_CANNONLAKE(dev_priv)) + if (IS_ICELAKE(dev_priv)) + icl_ddi_vswing_sequence(encoder, level, encoder->type); + else if (IS_CANNONLAKE(dev_priv)) cnl_ddi_vswing_sequence(encoder, level, encoder->type); else bxt_ddi_vswing_sequence(encoder, level, encoder->type); @@ -2234,6 +2440,69 @@ uint32_t ddi_signal_levels(struct intel_dp *intel_dp) return DDI_BUF_TRANS_SELECT(level); } +void icl_map_plls_to_ports(struct drm_crtc *crtc, + struct intel_crtc_state *crtc_state, + struct drm_atomic_state *old_state) +{ + struct intel_shared_dpll *pll = crtc_state->shared_dpll; + struct drm_i915_private *dev_priv = to_i915(crtc->dev); + struct drm_connector_state *conn_state; + struct drm_connector *conn; + int i; + + for_each_new_connector_in_state(old_state, conn, conn_state, i) { + struct intel_encoder *encoder = + to_intel_encoder(conn_state->best_encoder); + enum port port = encoder->port; + uint32_t val; + + if (conn_state->crtc != crtc) + continue; + + mutex_lock(&dev_priv->dpll_lock); + + val = I915_READ(DPCLKA_CFGCR0_ICL); + WARN_ON((val & DPCLKA_CFGCR0_DDI_CLK_OFF(port)) == 0); + + if (port == PORT_A || port == PORT_B) { + val &= ~DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port); + val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port); + I915_WRITE(DPCLKA_CFGCR0_ICL, val); + POSTING_READ(DPCLKA_CFGCR0_ICL); + } + + val &= ~DPCLKA_CFGCR0_DDI_CLK_OFF(port); + I915_WRITE(DPCLKA_CFGCR0_ICL, val); + + mutex_unlock(&dev_priv->dpll_lock); + } +} + +void icl_unmap_plls_to_ports(struct drm_crtc *crtc, + struct intel_crtc_state *crtc_state, + struct drm_atomic_state *old_state) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->dev); + struct drm_connector_state *old_conn_state; + struct drm_connector *conn; + int i; + + for_each_old_connector_in_state(old_state, conn, old_conn_state, i) { + struct intel_encoder *encoder = + to_intel_encoder(old_conn_state->best_encoder); + enum port port = encoder->port; + + if (old_conn_state->crtc != crtc) + continue; + + mutex_lock(&dev_priv->dpll_lock); + I915_WRITE(DPCLKA_CFGCR0_ICL, + I915_READ(DPCLKA_CFGCR0_ICL) | + DPCLKA_CFGCR0_DDI_CLK_OFF(port)); + mutex_unlock(&dev_priv->dpll_lock); + } +} + static void intel_ddi_clk_select(struct intel_encoder *encoder, const struct intel_shared_dpll *pll) { @@ -2246,7 +2515,11 @@ static void intel_ddi_clk_select(struct intel_encoder *encoder, mutex_lock(&dev_priv->dpll_lock); - if (IS_CANNONLAKE(dev_priv)) { + if (IS_ICELAKE(dev_priv)) { + if (port >= PORT_C) + I915_WRITE(DDI_CLK_SEL(port), + icl_pll_to_ddi_pll_sel(encoder, pll)); + } else if (IS_CANNONLAKE(dev_priv)) { /* Configure DPCLKA_CFGCR0 to map the DPLL to the DDI. */ val = I915_READ(DPCLKA_CFGCR0); val &= ~DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port); @@ -2284,14 +2557,18 @@ static void intel_ddi_clk_disable(struct intel_encoder *encoder) struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum port port = encoder->port; - if (IS_CANNONLAKE(dev_priv)) + if (IS_ICELAKE(dev_priv)) { + if (port >= PORT_C) + I915_WRITE(DDI_CLK_SEL(port), DDI_CLK_SEL_NONE); + } else if (IS_CANNONLAKE(dev_priv)) { I915_WRITE(DPCLKA_CFGCR0, I915_READ(DPCLKA_CFGCR0) | DPCLKA_CFGCR0_DDI_CLK_OFF(port)); - else if (IS_GEN9_BC(dev_priv)) + } else if (IS_GEN9_BC(dev_priv)) { I915_WRITE(DPLL_CTRL2, I915_READ(DPLL_CTRL2) | DPLL_CTRL2_DDI_CLK_OFF(port)); - else if (INTEL_GEN(dev_priv) < 9) + } else if (INTEL_GEN(dev_priv) < 9) { I915_WRITE(PORT_CLK_SEL(port), PORT_CLK_SEL_NONE); + } } static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder, @@ -2316,7 +2593,9 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder, intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain); - if (IS_CANNONLAKE(dev_priv)) + if (IS_ICELAKE(dev_priv)) + icl_ddi_vswing_sequence(encoder, level, encoder->type); + else if (IS_CANNONLAKE(dev_priv)) cnl_ddi_vswing_sequence(encoder, level, encoder->type); else if (IS_GEN9_LP(dev_priv)) bxt_ddi_vswing_sequence(encoder, level, encoder->type); @@ -2347,7 +2626,9 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder, intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain); - if (IS_CANNONLAKE(dev_priv)) + if (IS_ICELAKE(dev_priv)) + icl_ddi_vswing_sequence(encoder, level, INTEL_OUTPUT_HDMI); + else if (IS_CANNONLAKE(dev_priv)) cnl_ddi_vswing_sequence(encoder, level, INTEL_OUTPUT_HDMI); else if (IS_GEN9_LP(dev_priv)) bxt_ddi_vswing_sequence(encoder, level, INTEL_OUTPUT_HDMI); diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index a32ba72..0fd13df 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -848,7 +848,7 @@ void intel_device_info_runtime_init(struct intel_device_info *info) gen9_sseu_info_init(dev_priv); else if (INTEL_GEN(dev_priv) == 10) gen10_sseu_info_init(dev_priv); - else if (INTEL_INFO(dev_priv)->gen >= 11) + else if (INTEL_GEN(dev_priv) >= 11) gen11_sseu_info_init(dev_priv); /* Initialize command stream timestamp frequency */ diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index e04050e..ad588d5 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -88,6 +88,22 @@ static const uint32_t skl_primary_formats[] = { DRM_FORMAT_VYUY, }; +static const uint32_t skl_pri_planar_formats[] = { + DRM_FORMAT_C8, + DRM_FORMAT_RGB565, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_XRGB2101010, + DRM_FORMAT_XBGR2101010, + DRM_FORMAT_YUYV, + DRM_FORMAT_YVYU, + DRM_FORMAT_UYVY, + DRM_FORMAT_VYUY, + DRM_FORMAT_NV12, +}; + static const uint64_t skl_format_modifiers_noccs[] = { I915_FORMAT_MOD_Yf_TILED, I915_FORMAT_MOD_Y_TILED, @@ -489,9 +505,21 @@ static const struct intel_limit intel_limits_bxt = { }; static void +skl_wa_528(struct drm_i915_private *dev_priv, int pipe, bool enable) +{ + if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv)) + return; + + if (enable) + I915_WRITE(CHICKEN_PIPESL_1(pipe), HSW_FBCQ_DIS); + else + I915_WRITE(CHICKEN_PIPESL_1(pipe), 0); +} + +static void skl_wa_clkgate(struct drm_i915_private *dev_priv, int pipe, bool enable) { - if (IS_SKYLAKE(dev_priv)) + if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv)) return; if (enable) @@ -2841,7 +2869,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, continue; if (intel_plane_ggtt_offset(state) == plane_config->base) { - fb = c->primary->fb; + fb = state->base.fb; drm_framebuffer_get(fb); goto valid_fb; } @@ -3090,6 +3118,29 @@ static int skl_check_main_surface(const struct intel_crtc_state *crtc_state, return 0; } +static int +skl_check_nv12_surface(const struct intel_crtc_state *crtc_state, + struct intel_plane_state *plane_state) +{ + /* Display WA #1106 */ + if (plane_state->base.rotation != + (DRM_MODE_REFLECT_X | DRM_MODE_ROTATE_90) && + plane_state->base.rotation != DRM_MODE_ROTATE_270) + return 0; + + /* + * src coordinates are rotated here. + * We check height but report it as width + */ + if (((drm_rect_height(&plane_state->base.src) >> 16) % 4) != 0) { + DRM_DEBUG_KMS("src width must be multiple " + "of 4 for rotated NV12\n"); + return -EINVAL; + } + + return 0; +} + static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state) { const struct drm_framebuffer *fb = plane_state->base.fb; @@ -3173,6 +3224,9 @@ int skl_check_plane_surface(const struct intel_crtc_state *crtc_state, * the main surface setup depends on it. */ if (fb->format->format == DRM_FORMAT_NV12) { + ret = skl_check_nv12_surface(crtc_state, plane_state); + if (ret) + return ret; ret = skl_check_nv12_aux_surface(plane_state); if (ret) return ret; @@ -3623,11 +3677,15 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state, u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { + struct drm_i915_private *dev_priv = + to_i915(plane_state->base.plane->dev); const struct drm_framebuffer *fb = plane_state->base.fb; u32 plane_color_ctl = 0; - plane_color_ctl |= PLANE_COLOR_PIPE_GAMMA_ENABLE; - plane_color_ctl |= PLANE_COLOR_PIPE_CSC_ENABLE; + if (INTEL_GEN(dev_priv) < 11) { + plane_color_ctl |= PLANE_COLOR_PIPE_GAMMA_ENABLE; + plane_color_ctl |= PLANE_COLOR_PIPE_CSC_ENABLE; + } plane_color_ctl |= PLANE_COLOR_PLANE_GAMMA_DISABLE; plane_color_ctl |= glk_plane_color_ctl_alpha(fb->format->format); @@ -4790,8 +4848,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach, } if (plane_scaler_check && pixel_format == DRM_FORMAT_NV12 && - (src_h < SKL_MIN_YUV_420_SRC_H || (src_w % 4) != 0 || - (src_h % 4) != 0)) { + (src_h < SKL_MIN_YUV_420_SRC_H || src_w < SKL_MIN_YUV_420_SRC_W)) { DRM_DEBUG_KMS("NV12: src dimensions not met\n"); return -EINVAL; } @@ -5138,6 +5195,22 @@ static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_s return !old_crtc_state->ips_enabled; } +static bool needs_nv12_wa(struct drm_i915_private *dev_priv, + const struct intel_crtc_state *crtc_state) +{ + if (!crtc_state->nv12_planes) + return false; + + if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv)) + return false; + + if ((INTEL_GEN(dev_priv) == 9 && !IS_GEMINILAKE(dev_priv)) || + IS_CANNONLAKE(dev_priv)) + return true; + + return false; +} + static void intel_post_plane_update(struct intel_crtc_state *old_crtc_state) { struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc); @@ -5162,7 +5235,6 @@ static void intel_post_plane_update(struct intel_crtc_state *old_crtc_state) if (old_primary_state) { struct drm_plane_state *new_primary_state = drm_atomic_get_new_plane_state(old_state, primary); - struct drm_framebuffer *fb = new_primary_state->fb; intel_fbc_post_update(crtc); @@ -5170,14 +5242,13 @@ static void intel_post_plane_update(struct intel_crtc_state *old_crtc_state) (needs_modeset(&pipe_config->base) || !old_primary_state->visible)) intel_post_enable_primary(&crtc->base, pipe_config); + } - /* Display WA 827 */ - if ((INTEL_GEN(dev_priv) == 9 && !IS_GEMINILAKE(dev_priv)) || - IS_CANNONLAKE(dev_priv)) { - if (fb && fb->format->format == DRM_FORMAT_NV12) - skl_wa_clkgate(dev_priv, crtc->pipe, false); - } - + /* Display WA 827 */ + if (needs_nv12_wa(dev_priv, old_crtc_state) && + !needs_nv12_wa(dev_priv, pipe_config)) { + skl_wa_clkgate(dev_priv, crtc->pipe, false); + skl_wa_528(dev_priv, crtc->pipe, false); } } @@ -5202,14 +5273,6 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state, struct intel_plane_state *new_primary_state = intel_atomic_get_new_plane_state(old_intel_state, to_intel_plane(primary)); - struct drm_framebuffer *fb = new_primary_state->base.fb; - - /* Display WA 827 */ - if ((INTEL_GEN(dev_priv) == 9 && !IS_GEMINILAKE(dev_priv)) || - IS_CANNONLAKE(dev_priv)) { - if (fb && fb->format->format == DRM_FORMAT_NV12) - skl_wa_clkgate(dev_priv, crtc->pipe, true); - } intel_fbc_pre_update(crtc, pipe_config, new_primary_state); /* @@ -5221,6 +5284,13 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state, intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false); } + /* Display WA 827 */ + if (!needs_nv12_wa(dev_priv, old_crtc_state) && + needs_nv12_wa(dev_priv, pipe_config)) { + skl_wa_clkgate(dev_priv, crtc->pipe, true); + skl_wa_528(dev_priv, crtc->pipe, true); + } + /* * Vblank time updates from the shadow to live plane control register * are blocked if the memory self-refresh mode is active at that @@ -5555,6 +5625,9 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config, if (intel_crtc->config->shared_dpll) intel_enable_shared_dpll(intel_crtc); + if (INTEL_GEN(dev_priv) >= 11) + icl_map_plls_to_ports(crtc, pipe_config, old_state); + if (intel_crtc_has_dp_encoder(intel_crtc->config)) intel_dp_set_m_n(intel_crtc, M1_N1); @@ -5752,6 +5825,9 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state, intel_ddi_disable_pipe_clock(intel_crtc->config); intel_encoders_post_disable(crtc, old_crtc_state, old_state); + + if (INTEL_GEN(dev_priv) >= 11) + icl_unmap_plls_to_ports(crtc, old_crtc_state, old_state); } static void i9xx_pfit_enable(struct intel_crtc *crtc) @@ -10030,6 +10106,8 @@ found: ret = PTR_ERR_OR_ZERO(drm_atomic_get_connector_state(restore_state, connector)); if (!ret) ret = PTR_ERR_OR_ZERO(drm_atomic_get_crtc_state(restore_state, crtc)); + if (!ret) + ret = drm_atomic_add_affected_planes(restore_state, crtc); if (ret) { DRM_DEBUG_KMS("Failed to create a copy of old state to restore: %i\n", ret); goto fail; @@ -11141,39 +11219,42 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv, (current_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED) && !(pipe_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED); -#define PIPE_CONF_CHECK_X(name) \ +#define PIPE_CONF_CHECK_X(name) do { \ if (current_config->name != pipe_config->name) { \ pipe_config_err(adjust, __stringify(name), \ "(expected 0x%08x, found 0x%08x)\n", \ current_config->name, \ pipe_config->name); \ ret = false; \ - } + } \ +} while (0) -#define PIPE_CONF_CHECK_I(name) \ +#define PIPE_CONF_CHECK_I(name) do { \ if (current_config->name != pipe_config->name) { \ pipe_config_err(adjust, __stringify(name), \ "(expected %i, found %i)\n", \ current_config->name, \ pipe_config->name); \ ret = false; \ - } + } \ +} while (0) -#define PIPE_CONF_CHECK_BOOL(name) \ +#define PIPE_CONF_CHECK_BOOL(name) do { \ if (current_config->name != pipe_config->name) { \ pipe_config_err(adjust, __stringify(name), \ "(expected %s, found %s)\n", \ yesno(current_config->name), \ yesno(pipe_config->name)); \ ret = false; \ - } + } \ +} while (0) /* * Checks state where we only read out the enabling, but not the entire * state itself (like full infoframes or ELD for audio). These states * require a full modeset on bootup to fix up. */ -#define PIPE_CONF_CHECK_BOOL_INCOMPLETE(name) \ +#define PIPE_CONF_CHECK_BOOL_INCOMPLETE(name) do { \ if (!fixup_inherited || (!current_config->name && !pipe_config->name)) { \ PIPE_CONF_CHECK_BOOL(name); \ } else { \ @@ -11182,18 +11263,20 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv, yesno(current_config->name), \ yesno(pipe_config->name)); \ ret = false; \ - } + } \ +} while (0) -#define PIPE_CONF_CHECK_P(name) \ +#define PIPE_CONF_CHECK_P(name) do { \ if (current_config->name != pipe_config->name) { \ pipe_config_err(adjust, __stringify(name), \ "(expected %p, found %p)\n", \ current_config->name, \ pipe_config->name); \ ret = false; \ - } + } \ +} while (0) -#define PIPE_CONF_CHECK_M_N(name) \ +#define PIPE_CONF_CHECK_M_N(name) do { \ if (!intel_compare_link_m_n(¤t_config->name, \ &pipe_config->name,\ adjust)) { \ @@ -11211,14 +11294,15 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv, pipe_config->name.link_m, \ pipe_config->name.link_n); \ ret = false; \ - } + } \ +} while (0) /* This is required for BDW+ where there is only one set of registers for * switching between high and low RR. * This macro can be used whenever a comparison has to be made between one * hw state and multiple sw state variables. */ -#define PIPE_CONF_CHECK_M_N_ALT(name, alt_name) \ +#define PIPE_CONF_CHECK_M_N_ALT(name, alt_name) do { \ if (!intel_compare_link_m_n(¤t_config->name, \ &pipe_config->name, adjust) && \ !intel_compare_link_m_n(¤t_config->alt_name, \ @@ -11243,9 +11327,10 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv, pipe_config->name.link_m, \ pipe_config->name.link_n); \ ret = false; \ - } + } \ +} while (0) -#define PIPE_CONF_CHECK_FLAGS(name, mask) \ +#define PIPE_CONF_CHECK_FLAGS(name, mask) do { \ if ((current_config->name ^ pipe_config->name) & (mask)) { \ pipe_config_err(adjust, __stringify(name), \ "(%x) (expected %i, found %i)\n", \ @@ -11253,16 +11338,18 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv, current_config->name & (mask), \ pipe_config->name & (mask)); \ ret = false; \ - } + } \ +} while (0) -#define PIPE_CONF_CHECK_CLOCK_FUZZY(name) \ +#define PIPE_CONF_CHECK_CLOCK_FUZZY(name) do { \ if (!intel_fuzzy_clock_check(current_config->name, pipe_config->name)) { \ pipe_config_err(adjust, __stringify(name), \ "(expected %i, found %i)\n", \ current_config->name, \ pipe_config->name); \ ret = false; \ - } + } \ +} while (0) #define PIPE_CONF_QUIRK(quirk) \ ((current_config->quirks | pipe_config->quirks) & (quirk)) @@ -11371,6 +11458,16 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv, PIPE_CONF_CHECK_X(dpll_hw_state.pll9); PIPE_CONF_CHECK_X(dpll_hw_state.pll10); PIPE_CONF_CHECK_X(dpll_hw_state.pcsdw12); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_refclkin_ctl); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_clktop2_coreclkctl1); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_clktop2_hsclkctl); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_div0); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_div1); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_lf); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_frac_lock); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_ssc); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_bias); + PIPE_CONF_CHECK_X(dpll_hw_state.mg_pll_tdc_coldst_bias); PIPE_CONF_CHECK_X(dsi_pll.ctrl); PIPE_CONF_CHECK_X(dsi_pll.div); @@ -11434,6 +11531,11 @@ static void verify_wm_state(struct drm_crtc *crtc, skl_ddb_get_hw_state(dev_priv, &hw_ddb); sw_ddb = &dev_priv->wm.skl_hw.ddb; + if (INTEL_GEN(dev_priv) >= 11) + if (hw_ddb.enabled_slices != sw_ddb->enabled_slices) + DRM_ERROR("mismatch in DBUF Slices (expected %u, got %u)\n", + sw_ddb->enabled_slices, + hw_ddb.enabled_slices); /* planes */ for_each_universal_plane(dev_priv, pipe, plane) { hw_plane_wm = &hw_wm.planes[plane]; @@ -12240,6 +12342,8 @@ static void skl_update_crtcs(struct drm_atomic_state *state) bool progress; enum pipe pipe; int i; + u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices; + u8 required_slices = intel_state->wm_results.ddb.enabled_slices; const struct skl_ddb_entry *entries[I915_MAX_PIPES] = {}; @@ -12248,6 +12352,10 @@ static void skl_update_crtcs(struct drm_atomic_state *state) if (new_crtc_state->active) entries[i] = &to_intel_crtc_state(old_crtc_state)->wm.skl.ddb; + /* If 2nd DBuf slice required, enable it here */ + if (INTEL_GEN(dev_priv) >= 11 && required_slices > hw_enabled_slices) + icl_dbuf_slices_update(dev_priv, required_slices); + /* * Whenever the number of active pipes changes, we need to make sure we * update the pipes in the right order so that their ddb allocations @@ -12298,6 +12406,10 @@ static void skl_update_crtcs(struct drm_atomic_state *state) progress = true; } } while (progress); + + /* If 2nd DBuf slice is no more required disable it */ + if (INTEL_GEN(dev_priv) >= 11 && required_slices < hw_enabled_slices) + icl_dbuf_slices_update(dev_priv, required_slices); } static void intel_atomic_helper_free_state(struct drm_i915_private *dev_priv) @@ -12761,6 +12873,15 @@ static void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state) intel_unpin_fb_vma(vma, old_plane_state->flags); } +static void fb_obj_bump_render_priority(struct drm_i915_gem_object *obj) +{ + struct i915_sched_attr attr = { + .priority = I915_PRIORITY_DISPLAY, + }; + + i915_gem_object_wait_priority(obj, 0, &attr); +} + /** * intel_prepare_plane_fb - Prepare fb for usage on plane * @plane: drm plane to prepare for @@ -12837,7 +12958,7 @@ intel_prepare_plane_fb(struct drm_plane *plane, ret = intel_plane_pin_fb(to_intel_plane_state(new_state)); - i915_gem_object_wait_priority(obj, 0, I915_PRIORITY_DISPLAY); + fb_obj_bump_render_priority(obj); mutex_unlock(&dev_priv->drm.struct_mutex); i915_gem_object_unpin_pages(obj); @@ -13113,6 +13234,7 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier) case DRM_FORMAT_YVYU: case DRM_FORMAT_UYVY: case DRM_FORMAT_VYUY: + case DRM_FORMAT_NV12: if (modifier == I915_FORMAT_MOD_Yf_TILED) return true; /* fall through */ @@ -13320,6 +13442,30 @@ static bool skl_plane_has_fbc(struct drm_i915_private *dev_priv, return pipe == PIPE_A && plane_id == PLANE_PRIMARY; } +bool skl_plane_has_planar(struct drm_i915_private *dev_priv, + enum pipe pipe, enum plane_id plane_id) +{ + if (plane_id == PLANE_PRIMARY) { + if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv)) + return false; + else if ((INTEL_GEN(dev_priv) == 9 && pipe == PIPE_C) && + !IS_GEMINILAKE(dev_priv)) + return false; + } else if (plane_id >= PLANE_SPRITE0) { + if (plane_id == PLANE_CURSOR) + return false; + if (IS_GEMINILAKE(dev_priv) || INTEL_GEN(dev_priv) == 10) { + if (plane_id != PLANE_SPRITE0) + return false; + } else { + if (plane_id != PLANE_SPRITE0 || pipe == PIPE_C || + IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv)) + return false; + } + } + return true; +} + static struct intel_plane * intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) { @@ -13380,8 +13526,13 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) primary->check_plane = intel_check_primary_plane; if (INTEL_GEN(dev_priv) >= 9) { - intel_primary_formats = skl_primary_formats; - num_formats = ARRAY_SIZE(skl_primary_formats); + if (skl_plane_has_planar(dev_priv, pipe, PLANE_PRIMARY)) { + intel_primary_formats = skl_pri_planar_formats; + num_formats = ARRAY_SIZE(skl_pri_planar_formats); + } else { + intel_primary_formats = skl_primary_formats; + num_formats = ARRAY_SIZE(skl_primary_formats); + } if (skl_plane_has_ccs(dev_priv, pipe, PLANE_PRIMARY)) modifiers = skl_format_modifiers_ccs; @@ -14202,6 +14353,20 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, goto err; } break; + case DRM_FORMAT_NV12: + if (mode_cmd->modifier[0] == I915_FORMAT_MOD_Y_TILED_CCS || + mode_cmd->modifier[0] == I915_FORMAT_MOD_Yf_TILED_CCS) { + DRM_DEBUG_KMS("RC not to be enabled with NV12\n"); + goto err; + } + if (INTEL_GEN(dev_priv) < 9 || IS_SKYLAKE(dev_priv) || + IS_BROXTON(dev_priv)) { + DRM_DEBUG_KMS("unsupported pixel format: %s\n", + drm_get_format_name(mode_cmd->pixel_format, + &format_name)); + goto err; + } + break; default: DRM_DEBUG_KMS("unsupported pixel format: %s\n", drm_get_format_name(mode_cmd->pixel_format, &format_name)); @@ -14214,6 +14379,14 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, drm_helper_mode_fill_fb_struct(&dev_priv->drm, fb, mode_cmd); + if (fb->format->format == DRM_FORMAT_NV12 && + (fb->width < SKL_MIN_YUV_420_SRC_W || + fb->height < SKL_MIN_YUV_420_SRC_H || + (fb->width % 4) != 0 || (fb->height % 4) != 0)) { + DRM_DEBUG_KMS("src dimensions not correct for NV12\n"); + return -EINVAL; + } + for (i = 0; i < fb->format->num_planes; i++) { u32 stride_alignment; @@ -15268,6 +15441,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) memset(&crtc->base.mode, 0, sizeof(crtc->base.mode)); if (crtc_state->base.active) { intel_mode_from_pipe_config(&crtc->base.mode, crtc_state); + crtc->base.mode.hdisplay = crtc_state->pipe_src_w; + crtc->base.mode.vdisplay = crtc_state->pipe_src_h; intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode, crtc_state); WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode)); diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h index 4e7418b..2ef3161 100644 --- a/drivers/gpu/drm/i915/intel_display.h +++ b/drivers/gpu/drm/i915/intel_display.h @@ -218,6 +218,10 @@ struct intel_link_m_n { for ((__p) = 0; (__p) < INTEL_INFO(__dev_priv)->num_pipes; (__p)++) \ for_each_if((__mask) & BIT(__p)) +#define for_each_cpu_transcoder_masked(__dev_priv, __t, __mask) \ + for ((__t) = 0; (__t) < I915_MAX_TRANSCODERS; (__t)++) \ + for_each_if ((__mask) & (1 << (__t))) + #define for_each_universal_plane(__dev_priv, __pipe, __p) \ for ((__p) = 0; \ (__p) < INTEL_INFO(__dev_priv)->num_sprites[(__pipe)] + 1; \ diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 62f82c4..dde92e4 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1647,9 +1647,17 @@ void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock, } } +struct link_config_limits { + int min_clock, max_clock; + int min_lane_count, max_lane_count; + int min_bpp, max_bpp; +}; + static int intel_dp_compute_bpp(struct intel_dp *intel_dp, struct intel_crtc_state *pipe_config) { + struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp)); + struct intel_connector *intel_connector = intel_dp->attached_connector; int bpp, bpc; bpp = pipe_config->pipe_bpp; @@ -1658,13 +1666,16 @@ static int intel_dp_compute_bpp(struct intel_dp *intel_dp, if (bpc > 0) bpp = min(bpp, 3*bpc); - /* For DP Compliance we override the computed bpp for the pipe */ - if (intel_dp->compliance.test_data.bpc != 0) { - pipe_config->pipe_bpp = 3*intel_dp->compliance.test_data.bpc; - pipe_config->dither_force_disable = pipe_config->pipe_bpp == 6*3; - DRM_DEBUG_KMS("Setting pipe_bpp to %d\n", - pipe_config->pipe_bpp); + if (intel_dp_is_edp(intel_dp)) { + /* Get bpp from vbt only for panels that dont have bpp in edid */ + if (intel_connector->base.display_info.bpc == 0 && + dev_priv->vbt.edp.bpp && dev_priv->vbt.edp.bpp < bpp) { + DRM_DEBUG_KMS("clamping bpp for eDP panel to BIOS-provided %i\n", + dev_priv->vbt.edp.bpp); + bpp = dev_priv->vbt.edp.bpp; + } } + return bpp; } @@ -1685,6 +1696,142 @@ static bool intel_edp_compare_alt_mode(struct drm_display_mode *m1, return bres; } +/* Adjust link config limits based on compliance test requests. */ +static void +intel_dp_adjust_compliance_config(struct intel_dp *intel_dp, + struct intel_crtc_state *pipe_config, + struct link_config_limits *limits) +{ + /* For DP Compliance we override the computed bpp for the pipe */ + if (intel_dp->compliance.test_data.bpc != 0) { + int bpp = 3 * intel_dp->compliance.test_data.bpc; + + limits->min_bpp = limits->max_bpp = bpp; + pipe_config->dither_force_disable = bpp == 6 * 3; + + DRM_DEBUG_KMS("Setting pipe_bpp to %d\n", bpp); + } + + /* Use values requested by Compliance Test Request */ + if (intel_dp->compliance.test_type == DP_TEST_LINK_TRAINING) { + int index; + + /* Validate the compliance test data since max values + * might have changed due to link train fallback. + */ + if (intel_dp_link_params_valid(intel_dp, intel_dp->compliance.test_link_rate, + intel_dp->compliance.test_lane_count)) { + index = intel_dp_rate_index(intel_dp->common_rates, + intel_dp->num_common_rates, + intel_dp->compliance.test_link_rate); + if (index >= 0) + limits->min_clock = limits->max_clock = index; + limits->min_lane_count = limits->max_lane_count = + intel_dp->compliance.test_lane_count; + } + } +} + +/* Optimize link config in order: max bpp, min clock, min lanes */ +static bool +intel_dp_compute_link_config_wide(struct intel_dp *intel_dp, + struct intel_crtc_state *pipe_config, + const struct link_config_limits *limits) +{ + struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; + int bpp, clock, lane_count; + int mode_rate, link_clock, link_avail; + + for (bpp = limits->max_bpp; bpp >= limits->min_bpp; bpp -= 2 * 3) { + mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock, + bpp); + + for (clock = limits->min_clock; clock <= limits->max_clock; clock++) { + for (lane_count = limits->min_lane_count; + lane_count <= limits->max_lane_count; + lane_count <<= 1) { + link_clock = intel_dp->common_rates[clock]; + link_avail = intel_dp_max_data_rate(link_clock, + lane_count); + + if (mode_rate <= link_avail) { + pipe_config->lane_count = lane_count; + pipe_config->pipe_bpp = bpp; + pipe_config->port_clock = link_clock; + + return true; + } + } + } + } + + return false; +} + +static bool +intel_dp_compute_link_config(struct intel_encoder *encoder, + struct intel_crtc_state *pipe_config) +{ + struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + struct link_config_limits limits; + int common_len; + + common_len = intel_dp_common_len_rate_limit(intel_dp, + intel_dp->max_link_rate); + + /* No common link rates between source and sink */ + WARN_ON(common_len <= 0); + + limits.min_clock = 0; + limits.max_clock = common_len - 1; + + limits.min_lane_count = 1; + limits.max_lane_count = intel_dp_max_lane_count(intel_dp); + + limits.min_bpp = 6 * 3; + limits.max_bpp = intel_dp_compute_bpp(intel_dp, pipe_config); + + if (intel_dp_is_edp(intel_dp)) { + /* + * Use the maximum clock and number of lanes the eDP panel + * advertizes being capable of. The panels are generally + * designed to support only a single clock and lane + * configuration, and typically these values correspond to the + * native resolution of the panel. + */ + limits.min_lane_count = limits.max_lane_count; + limits.min_clock = limits.max_clock; + } + + intel_dp_adjust_compliance_config(intel_dp, pipe_config, &limits); + + DRM_DEBUG_KMS("DP link computation with max lane count %i " + "max rate %d max bpp %d pixel clock %iKHz\n", + limits.max_lane_count, + intel_dp->common_rates[limits.max_clock], + limits.max_bpp, adjusted_mode->crtc_clock); + + /* + * Optimize for slow and wide. This is the place to add alternative + * optimization policy. + */ + if (!intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits)) + return false; + + DRM_DEBUG_KMS("DP lane count %d clock %d bpp %d\n", + pipe_config->lane_count, pipe_config->port_clock, + pipe_config->pipe_bpp); + + DRM_DEBUG_KMS("DP link rate required %i available %i\n", + intel_dp_link_required(adjusted_mode->crtc_clock, + pipe_config->pipe_bpp), + intel_dp_max_data_rate(pipe_config->port_clock, + pipe_config->lane_count)); + + return true; +} + bool intel_dp_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, @@ -1698,27 +1845,9 @@ intel_dp_compute_config(struct intel_encoder *encoder, struct intel_connector *intel_connector = intel_dp->attached_connector; struct intel_digital_connector_state *intel_conn_state = to_intel_digital_connector_state(conn_state); - int lane_count, clock; - int min_lane_count = 1; - int max_lane_count = intel_dp_max_lane_count(intel_dp); - /* Conveniently, the link BW constants become indices with a shift...*/ - int min_clock = 0; - int max_clock; - int bpp, mode_rate; - int link_avail, link_clock; - int common_len; - uint8_t link_bw, rate_select; bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc, DP_DPCD_QUIRK_LIMITED_M_N); - common_len = intel_dp_common_len_rate_limit(intel_dp, - intel_dp->max_link_rate); - - /* No common link rates between source and sink */ - WARN_ON(common_len <= 0); - - max_clock = common_len - 1; - if (HAS_PCH_SPLIT(dev_priv) && !HAS_DDI(dev_priv) && port != PORT_A) pipe_config->has_pch_encoder = true; @@ -1744,6 +1873,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, if (INTEL_GEN(dev_priv) >= 9) { int ret; + ret = skl_update_scaler_crtc(pipe_config); if (ret) return ret; @@ -1764,75 +1894,9 @@ intel_dp_compute_config(struct intel_encoder *encoder, if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) return false; - /* Use values requested by Compliance Test Request */ - if (intel_dp->compliance.test_type == DP_TEST_LINK_TRAINING) { - int index; - - /* Validate the compliance test data since max values - * might have changed due to link train fallback. - */ - if (intel_dp_link_params_valid(intel_dp, intel_dp->compliance.test_link_rate, - intel_dp->compliance.test_lane_count)) { - index = intel_dp_rate_index(intel_dp->common_rates, - intel_dp->num_common_rates, - intel_dp->compliance.test_link_rate); - if (index >= 0) - min_clock = max_clock = index; - min_lane_count = max_lane_count = intel_dp->compliance.test_lane_count; - } - } - DRM_DEBUG_KMS("DP link computation with max lane count %i " - "max bw %d pixel clock %iKHz\n", - max_lane_count, intel_dp->common_rates[max_clock], - adjusted_mode->crtc_clock); - - /* Walk through all bpp values. Luckily they're all nicely spaced with 2 - * bpc in between. */ - bpp = intel_dp_compute_bpp(intel_dp, pipe_config); - if (intel_dp_is_edp(intel_dp)) { - - /* Get bpp from vbt only for panels that dont have bpp in edid */ - if (intel_connector->base.display_info.bpc == 0 && - (dev_priv->vbt.edp.bpp && dev_priv->vbt.edp.bpp < bpp)) { - DRM_DEBUG_KMS("clamping bpp for eDP panel to BIOS-provided %i\n", - dev_priv->vbt.edp.bpp); - bpp = dev_priv->vbt.edp.bpp; - } - - /* - * Use the maximum clock and number of lanes the eDP panel - * advertizes being capable of. The panels are generally - * designed to support only a single clock and lane - * configuration, and typically these values correspond to the - * native resolution of the panel. - */ - min_lane_count = max_lane_count; - min_clock = max_clock; - } - - for (; bpp >= 6*3; bpp -= 2*3) { - mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock, - bpp); - - for (clock = min_clock; clock <= max_clock; clock++) { - for (lane_count = min_lane_count; - lane_count <= max_lane_count; - lane_count <<= 1) { - - link_clock = intel_dp->common_rates[clock]; - link_avail = intel_dp_max_data_rate(link_clock, - lane_count); - - if (mode_rate <= link_avail) { - goto found; - } - } - } - } - - return false; + if (!intel_dp_compute_link_config(encoder, pipe_config)) + return false; -found: if (intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) { /* * See: @@ -1840,7 +1904,7 @@ found: * VESA DisplayPort Ver.1.2a - 5.1.1.1 Video Colorimetry */ pipe_config->limited_color_range = - bpp != 18 && + pipe_config->pipe_bpp != 18 && drm_default_rgb_quant_range(adjusted_mode) == HDMI_QUANTIZATION_RANGE_LIMITED; } else { @@ -1848,21 +1912,7 @@ found: intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_LIMITED; } - pipe_config->lane_count = lane_count; - - pipe_config->pipe_bpp = bpp; - pipe_config->port_clock = intel_dp->common_rates[clock]; - - 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); - - intel_link_compute_m_n(bpp, lane_count, + intel_link_compute_m_n(pipe_config->pipe_bpp, pipe_config->lane_count, adjusted_mode->crtc_clock, pipe_config->port_clock, &pipe_config->dp_m_n, @@ -1871,31 +1921,12 @@ found: if (intel_connector->panel.downclock_mode != NULL && dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) { pipe_config->has_drrs = true; - intel_link_compute_m_n(bpp, lane_count, - intel_connector->panel.downclock_mode->clock, - pipe_config->port_clock, - &pipe_config->dp_m2_n2, - reduce_m_n); - } - - /* - * DPLL0 VCO may need to be adjusted to get the correct - * clock for eDP. This will affect cdclk as well. - */ - if (intel_dp_is_edp(intel_dp) && IS_GEN9_BC(dev_priv)) { - int vco; - - switch (pipe_config->port_clock / 2) { - case 108000: - case 216000: - vco = 8640000; - break; - default: - vco = 8100000; - break; - } - - to_intel_atomic_state(pipe_config->base.state)->cdclk.logical.vco = vco; + intel_link_compute_m_n(pipe_config->pipe_bpp, + pipe_config->lane_count, + intel_connector->panel.downclock_mode->clock, + pipe_config->port_clock, + &pipe_config->dp_m2_n2, + reduce_m_n); } if (!HAS_DDI(dev_priv)) diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c index f59b59b..3fcaa98 100644 --- a/drivers/gpu/drm/i915/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/intel_dp_link_training.c @@ -139,6 +139,11 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp) intel_dp_compute_rate(intel_dp, intel_dp->link_rate, &link_bw, &rate_select); + if (link_bw) + DRM_DEBUG_KMS("Using LINK_BW_SET value %02x\n", link_bw); + else + DRM_DEBUG_KMS("Using LINK_RATE_SET value %02x\n", rate_select); + /* Write the link configuration data */ link_config[0] = link_bw; link_config[1] = intel_dp->lane_count; diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c index d5e114e..383fbc1 100644 --- a/drivers/gpu/drm/i915/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c @@ -2218,6 +2218,7 @@ cnl_ddi_calculate_wrpll(int clock, struct skl_wrpll_params *wrpll_params) { u32 afe_clock = clock * 5; + uint32_t ref_clock; u32 dco_min = 7998000; u32 dco_max = 10000000; u32 dco_mid = (dco_min + dco_max) / 2; @@ -2250,8 +2251,17 @@ cnl_ddi_calculate_wrpll(int clock, cnl_wrpll_get_multipliers(best_div, &pdiv, &qdiv, &kdiv); - cnl_wrpll_params_populate(wrpll_params, best_dco, - dev_priv->cdclk.hw.ref, pdiv, qdiv, kdiv); + ref_clock = dev_priv->cdclk.hw.ref; + + /* + * For ICL, the spec states: if reference frequency is 38.4, use 19.2 + * because the DPLL automatically divides that by 2. + */ + if (IS_ICELAKE(dev_priv) && ref_clock == 38400) + ref_clock = 19200; + + cnl_wrpll_params_populate(wrpll_params, best_dco, ref_clock, pdiv, qdiv, + kdiv); return true; } @@ -2399,6 +2409,644 @@ static const struct intel_dpll_mgr cnl_pll_mgr = { .dump_hw_state = cnl_dump_hw_state, }; +/* + * These values alrea already adjusted: they're the bits we write to the + * registers, not the logical values. + */ +static const struct skl_wrpll_params icl_dp_combo_pll_24MHz_values[] = { + { .dco_integer = 0x151, .dco_fraction = 0x4000, /* [0]: 5.4 */ + .pdiv = 0x2 /* 3 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x151, .dco_fraction = 0x4000, /* [1]: 2.7 */ + .pdiv = 0x2 /* 3 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x151, .dco_fraction = 0x4000, /* [2]: 1.62 */ + .pdiv = 0x4 /* 5 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x151, .dco_fraction = 0x4000, /* [3]: 3.24 */ + .pdiv = 0x4 /* 5 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x168, .dco_fraction = 0x0000, /* [4]: 2.16 */ + .pdiv = 0x1 /* 2 */, .kdiv = 2, .qdiv_mode = 1, .qdiv_ratio = 2}, + { .dco_integer = 0x168, .dco_fraction = 0x0000, /* [5]: 4.32 */ + .pdiv = 0x1 /* 2 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x195, .dco_fraction = 0x0000, /* [6]: 6.48 */ + .pdiv = 0x2 /* 3 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x151, .dco_fraction = 0x4000, /* [7]: 8.1 */ + .pdiv = 0x1 /* 2 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0}, +}; + +/* Also used for 38.4 MHz values. */ +static const struct skl_wrpll_params icl_dp_combo_pll_19_2MHz_values[] = { + { .dco_integer = 0x1A5, .dco_fraction = 0x7000, /* [0]: 5.4 */ + .pdiv = 0x2 /* 3 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x1A5, .dco_fraction = 0x7000, /* [1]: 2.7 */ + .pdiv = 0x2 /* 3 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x1A5, .dco_fraction = 0x7000, /* [2]: 1.62 */ + .pdiv = 0x4 /* 5 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x1A5, .dco_fraction = 0x7000, /* [3]: 3.24 */ + .pdiv = 0x4 /* 5 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x1C2, .dco_fraction = 0x0000, /* [4]: 2.16 */ + .pdiv = 0x1 /* 2 */, .kdiv = 2, .qdiv_mode = 1, .qdiv_ratio = 2}, + { .dco_integer = 0x1C2, .dco_fraction = 0x0000, /* [5]: 4.32 */ + .pdiv = 0x1 /* 2 */, .kdiv = 2, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x1FA, .dco_fraction = 0x2000, /* [6]: 6.48 */ + .pdiv = 0x2 /* 3 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0}, + { .dco_integer = 0x1A5, .dco_fraction = 0x7000, /* [7]: 8.1 */ + .pdiv = 0x1 /* 2 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0}, +}; + +static bool icl_calc_dp_combo_pll(struct drm_i915_private *dev_priv, int clock, + struct skl_wrpll_params *pll_params) +{ + const struct skl_wrpll_params *params; + + params = dev_priv->cdclk.hw.ref == 24000 ? + icl_dp_combo_pll_24MHz_values : + icl_dp_combo_pll_19_2MHz_values; + + switch (clock) { + case 540000: + *pll_params = params[0]; + break; + case 270000: + *pll_params = params[1]; + break; + case 162000: + *pll_params = params[2]; + break; + case 324000: + *pll_params = params[3]; + break; + case 216000: + *pll_params = params[4]; + break; + case 432000: + *pll_params = params[5]; + break; + case 648000: + *pll_params = params[6]; + break; + case 810000: + *pll_params = params[7]; + break; + default: + MISSING_CASE(clock); + return false; + } + + return true; +} + +static bool icl_calc_dpll_state(struct intel_crtc_state *crtc_state, + struct intel_encoder *encoder, int clock, + struct intel_dpll_hw_state *pll_state) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + uint32_t cfgcr0, cfgcr1; + struct skl_wrpll_params pll_params = { 0 }; + bool ret; + + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) + ret = cnl_ddi_calculate_wrpll(clock, dev_priv, &pll_params); + else + ret = icl_calc_dp_combo_pll(dev_priv, clock, &pll_params); + + if (!ret) + return false; + + cfgcr0 = DPLL_CFGCR0_DCO_FRACTION(pll_params.dco_fraction) | + pll_params.dco_integer; + + cfgcr1 = DPLL_CFGCR1_QDIV_RATIO(pll_params.qdiv_ratio) | + DPLL_CFGCR1_QDIV_MODE(pll_params.qdiv_mode) | + DPLL_CFGCR1_KDIV(pll_params.kdiv) | + DPLL_CFGCR1_PDIV(pll_params.pdiv) | + DPLL_CFGCR1_CENTRAL_FREQ_8400; + + pll_state->cfgcr0 = cfgcr0; + pll_state->cfgcr1 = cfgcr1; + return true; +} + +static enum port icl_mg_pll_id_to_port(enum intel_dpll_id id) +{ + return id - DPLL_ID_ICL_MGPLL1 + PORT_C; +} + +static enum intel_dpll_id icl_port_to_mg_pll_id(enum port port) +{ + return port - PORT_C + DPLL_ID_ICL_MGPLL1; +} + +static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc, + uint32_t *target_dco_khz, + struct intel_dpll_hw_state *state) +{ + uint32_t dco_min_freq, dco_max_freq; + int div1_vals[] = {7, 5, 3, 2}; + unsigned int i; + int div2; + + dco_min_freq = is_dp ? 8100000 : use_ssc ? 8000000 : 7992000; + dco_max_freq = is_dp ? 8100000 : 10000000; + + for (i = 0; i < ARRAY_SIZE(div1_vals); i++) { + int div1 = div1_vals[i]; + + for (div2 = 10; div2 > 0; div2--) { + int dco = div1 * div2 * clock_khz * 5; + int a_divratio, tlinedrv, inputsel, hsdiv; + + if (dco < dco_min_freq || dco > dco_max_freq) + continue; + + if (div2 >= 2) { + a_divratio = is_dp ? 10 : 5; + tlinedrv = 2; + } else { + a_divratio = 5; + tlinedrv = 0; + } + inputsel = is_dp ? 0 : 1; + + switch (div1) { + default: + MISSING_CASE(div1); + case 2: + hsdiv = 0; + break; + case 3: + hsdiv = 1; + break; + case 5: + hsdiv = 2; + break; + case 7: + hsdiv = 3; + break; + } + + *target_dco_khz = dco; + + state->mg_refclkin_ctl = MG_REFCLKIN_CTL_OD_2_MUX(1); + + state->mg_clktop2_coreclkctl1 = + MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO(a_divratio); + + state->mg_clktop2_hsclkctl = + MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL(tlinedrv) | + MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL(inputsel) | + MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO(hsdiv) | + MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO(div2); + + return true; + } + } + + return false; +} + +/* + * The specification for this function uses real numbers, so the math had to be + * adapted to integer-only calculation, that's why it looks so different. + */ +static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state, + struct intel_encoder *encoder, int clock, + struct intel_dpll_hw_state *pll_state) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + int refclk_khz = dev_priv->cdclk.hw.ref; + uint32_t dco_khz, m1div, m2div_int, m2div_rem, m2div_frac; + uint32_t iref_ndiv, iref_trim, iref_pulse_w; + uint32_t prop_coeff, int_coeff; + uint32_t tdc_targetcnt, feedfwgain; + uint64_t ssc_stepsize, ssc_steplen, ssc_steplog; + uint64_t tmp; + bool use_ssc = false; + bool is_dp = !intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI); + + if (!icl_mg_pll_find_divisors(clock, is_dp, use_ssc, &dco_khz, + pll_state)) { + DRM_DEBUG_KMS("Failed to find divisors for clock %d\n", clock); + return false; + } + + m1div = 2; + m2div_int = dco_khz / (refclk_khz * m1div); + if (m2div_int > 255) { + m1div = 4; + m2div_int = dco_khz / (refclk_khz * m1div); + if (m2div_int > 255) { + DRM_DEBUG_KMS("Failed to find mdiv for clock %d\n", + clock); + return false; + } + } + m2div_rem = dco_khz % (refclk_khz * m1div); + + tmp = (uint64_t)m2div_rem * (1 << 22); + do_div(tmp, refclk_khz * m1div); + m2div_frac = tmp; + + switch (refclk_khz) { + case 19200: + iref_ndiv = 1; + iref_trim = 28; + iref_pulse_w = 1; + break; + case 24000: + iref_ndiv = 1; + iref_trim = 25; + iref_pulse_w = 2; + break; + case 38400: + iref_ndiv = 2; + iref_trim = 28; + iref_pulse_w = 1; + break; + default: + MISSING_CASE(refclk_khz); + return false; + } + + /* + * tdc_res = 0.000003 + * tdc_targetcnt = int(2 / (tdc_res * 8 * 50 * 1.1) / refclk_mhz + 0.5) + * + * The multiplication by 1000 is due to refclk MHz to KHz conversion. It + * was supposed to be a division, but we rearranged the operations of + * the formula to avoid early divisions so we don't multiply the + * rounding errors. + * + * 0.000003 * 8 * 50 * 1.1 = 0.00132, also known as 132 / 100000, which + * we also rearrange to work with integers. + * + * The 0.5 transformed to 5 results in a multiplication by 10 and the + * last division by 10. + */ + tdc_targetcnt = (2 * 1000 * 100000 * 10 / (132 * refclk_khz) + 5) / 10; + + /* + * Here we divide dco_khz by 10 in order to allow the dividend to fit in + * 32 bits. That's not a problem since we round the division down + * anyway. + */ + feedfwgain = (use_ssc || m2div_rem > 0) ? + m1div * 1000000 * 100 / (dco_khz * 3 / 10) : 0; + + if (dco_khz >= 9000000) { + prop_coeff = 5; + int_coeff = 10; + } else { + prop_coeff = 4; + int_coeff = 8; + } + + if (use_ssc) { + tmp = (uint64_t)dco_khz * 47 * 32; + do_div(tmp, refclk_khz * m1div * 10000); + ssc_stepsize = tmp; + + tmp = (uint64_t)dco_khz * 1000; + ssc_steplen = DIV_ROUND_UP_ULL(tmp, 32 * 2 * 32); + } else { + ssc_stepsize = 0; + ssc_steplen = 0; + } + ssc_steplog = 4; + + pll_state->mg_pll_div0 = (m2div_rem > 0 ? MG_PLL_DIV0_FRACNEN_H : 0) | + MG_PLL_DIV0_FBDIV_FRAC(m2div_frac) | + MG_PLL_DIV0_FBDIV_INT(m2div_int); + + pll_state->mg_pll_div1 = MG_PLL_DIV1_IREF_NDIVRATIO(iref_ndiv) | + MG_PLL_DIV1_DITHER_DIV_2 | + MG_PLL_DIV1_NDIVRATIO(1) | + MG_PLL_DIV1_FBPREDIV(m1div); + + pll_state->mg_pll_lf = MG_PLL_LF_TDCTARGETCNT(tdc_targetcnt) | + MG_PLL_LF_AFCCNTSEL_512 | + MG_PLL_LF_GAINCTRL(1) | + MG_PLL_LF_INT_COEFF(int_coeff) | + MG_PLL_LF_PROP_COEFF(prop_coeff); + + pll_state->mg_pll_frac_lock = MG_PLL_FRAC_LOCK_TRUELOCK_CRIT_32 | + MG_PLL_FRAC_LOCK_EARLYLOCK_CRIT_32 | + MG_PLL_FRAC_LOCK_LOCKTHRESH(10) | + MG_PLL_FRAC_LOCK_DCODITHEREN | + MG_PLL_FRAC_LOCK_FEEDFWRDGAIN(feedfwgain); + if (use_ssc || m2div_rem > 0) + pll_state->mg_pll_frac_lock |= MG_PLL_FRAC_LOCK_FEEDFWRDCAL_EN; + + pll_state->mg_pll_ssc = (use_ssc ? MG_PLL_SSC_EN : 0) | + MG_PLL_SSC_TYPE(2) | + MG_PLL_SSC_STEPLENGTH(ssc_steplen) | + MG_PLL_SSC_STEPNUM(ssc_steplog) | + MG_PLL_SSC_FLLEN | + MG_PLL_SSC_STEPSIZE(ssc_stepsize); + + pll_state->mg_pll_tdc_coldst_bias = MG_PLL_TDC_COLDST_COLDSTART; + + if (refclk_khz != 38400) { + pll_state->mg_pll_tdc_coldst_bias |= + MG_PLL_TDC_COLDST_IREFINT_EN | + MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) | + MG_PLL_TDC_COLDST_COLDSTART | + MG_PLL_TDC_TDCOVCCORR_EN | + MG_PLL_TDC_TDCSEL(3); + + pll_state->mg_pll_bias = MG_PLL_BIAS_BIAS_GB_SEL(3) | + MG_PLL_BIAS_INIT_DCOAMP(0x3F) | + MG_PLL_BIAS_BIAS_BONUS(10) | + MG_PLL_BIAS_BIASCAL_EN | + MG_PLL_BIAS_CTRIM(12) | + MG_PLL_BIAS_VREF_RDAC(4) | + MG_PLL_BIAS_IREFTRIM(iref_trim); + } + + return true; +} + +static struct intel_shared_dpll * +icl_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state, + struct intel_encoder *encoder) +{ + struct intel_shared_dpll *pll; + struct intel_dpll_hw_state pll_state = {}; + enum port port = encoder->port; + enum intel_dpll_id min, max; + int clock = crtc_state->port_clock; + bool ret; + + switch (port) { + case PORT_A: + case PORT_B: + min = DPLL_ID_ICL_DPLL0; + max = DPLL_ID_ICL_DPLL1; + ret = icl_calc_dpll_state(crtc_state, encoder, clock, + &pll_state); + break; + case PORT_C: + case PORT_D: + case PORT_E: + case PORT_F: + min = icl_port_to_mg_pll_id(port); + max = min; + ret = icl_calc_mg_pll_state(crtc_state, encoder, clock, + &pll_state); + break; + default: + MISSING_CASE(port); + return NULL; + } + + if (!ret) { + DRM_DEBUG_KMS("Could not calculate PLL state.\n"); + return NULL; + } + + crtc_state->dpll_hw_state = pll_state; + + pll = intel_find_shared_dpll(crtc, crtc_state, min, max); + if (!pll) { + DRM_DEBUG_KMS("No PLL selected\n"); + return NULL; + } + + intel_reference_shared_dpll(pll, crtc_state); + + return pll; +} + +static i915_reg_t icl_pll_id_to_enable_reg(enum intel_dpll_id id) +{ + switch (id) { + default: + MISSING_CASE(id); + case DPLL_ID_ICL_DPLL0: + case DPLL_ID_ICL_DPLL1: + return CNL_DPLL_ENABLE(id); + case DPLL_ID_ICL_MGPLL1: + case DPLL_ID_ICL_MGPLL2: + case DPLL_ID_ICL_MGPLL3: + case DPLL_ID_ICL_MGPLL4: + return MG_PLL_ENABLE(icl_mg_pll_id_to_port(id)); + } +} + +static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll, + struct intel_dpll_hw_state *hw_state) +{ + const enum intel_dpll_id id = pll->info->id; + uint32_t val; + enum port port; + bool ret = false; + + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) + return false; + + val = I915_READ(icl_pll_id_to_enable_reg(id)); + if (!(val & PLL_ENABLE)) + goto out; + + switch (id) { + case DPLL_ID_ICL_DPLL0: + case DPLL_ID_ICL_DPLL1: + hw_state->cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(id)); + hw_state->cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(id)); + break; + case DPLL_ID_ICL_MGPLL1: + case DPLL_ID_ICL_MGPLL2: + case DPLL_ID_ICL_MGPLL3: + case DPLL_ID_ICL_MGPLL4: + port = icl_mg_pll_id_to_port(id); + hw_state->mg_refclkin_ctl = I915_READ(MG_REFCLKIN_CTL(port)); + hw_state->mg_clktop2_coreclkctl1 = + I915_READ(MG_CLKTOP2_CORECLKCTL1(port)); + hw_state->mg_clktop2_hsclkctl = + I915_READ(MG_CLKTOP2_HSCLKCTL(port)); + hw_state->mg_pll_div0 = I915_READ(MG_PLL_DIV0(port)); + hw_state->mg_pll_div1 = I915_READ(MG_PLL_DIV1(port)); + hw_state->mg_pll_lf = I915_READ(MG_PLL_LF(port)); + hw_state->mg_pll_frac_lock = I915_READ(MG_PLL_FRAC_LOCK(port)); + hw_state->mg_pll_ssc = I915_READ(MG_PLL_SSC(port)); + hw_state->mg_pll_bias = I915_READ(MG_PLL_BIAS(port)); + hw_state->mg_pll_tdc_coldst_bias = + I915_READ(MG_PLL_TDC_COLDST_BIAS(port)); + break; + default: + MISSING_CASE(id); + } + + ret = true; +out: + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return ret; +} + +static void icl_dpll_write(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll) +{ + struct intel_dpll_hw_state *hw_state = &pll->state.hw_state; + const enum intel_dpll_id id = pll->info->id; + + I915_WRITE(ICL_DPLL_CFGCR0(id), hw_state->cfgcr0); + I915_WRITE(ICL_DPLL_CFGCR1(id), hw_state->cfgcr1); + POSTING_READ(ICL_DPLL_CFGCR1(id)); +} + +static void icl_mg_pll_write(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll) +{ + struct intel_dpll_hw_state *hw_state = &pll->state.hw_state; + enum port port = icl_mg_pll_id_to_port(pll->info->id); + + I915_WRITE(MG_REFCLKIN_CTL(port), hw_state->mg_refclkin_ctl); + I915_WRITE(MG_CLKTOP2_CORECLKCTL1(port), + hw_state->mg_clktop2_coreclkctl1); + I915_WRITE(MG_CLKTOP2_HSCLKCTL(port), hw_state->mg_clktop2_hsclkctl); + I915_WRITE(MG_PLL_DIV0(port), hw_state->mg_pll_div0); + I915_WRITE(MG_PLL_DIV1(port), hw_state->mg_pll_div1); + I915_WRITE(MG_PLL_LF(port), hw_state->mg_pll_lf); + I915_WRITE(MG_PLL_FRAC_LOCK(port), hw_state->mg_pll_frac_lock); + I915_WRITE(MG_PLL_SSC(port), hw_state->mg_pll_ssc); + I915_WRITE(MG_PLL_BIAS(port), hw_state->mg_pll_bias); + I915_WRITE(MG_PLL_TDC_COLDST_BIAS(port), + hw_state->mg_pll_tdc_coldst_bias); + POSTING_READ(MG_PLL_TDC_COLDST_BIAS(port)); +} + +static void icl_pll_enable(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll) +{ + const enum intel_dpll_id id = pll->info->id; + i915_reg_t enable_reg = icl_pll_id_to_enable_reg(id); + uint32_t val; + + val = I915_READ(enable_reg); + val |= PLL_POWER_ENABLE; + I915_WRITE(enable_reg, val); + + /* + * The spec says we need to "wait" but it also says it should be + * immediate. + */ + if (intel_wait_for_register(dev_priv, enable_reg, PLL_POWER_STATE, + PLL_POWER_STATE, 1)) + DRM_ERROR("PLL %d Power not enabled\n", id); + + switch (id) { + case DPLL_ID_ICL_DPLL0: + case DPLL_ID_ICL_DPLL1: + icl_dpll_write(dev_priv, pll); + break; + case DPLL_ID_ICL_MGPLL1: + case DPLL_ID_ICL_MGPLL2: + case DPLL_ID_ICL_MGPLL3: + case DPLL_ID_ICL_MGPLL4: + icl_mg_pll_write(dev_priv, pll); + break; + default: + MISSING_CASE(id); + } + + /* + * DVFS pre sequence would be here, but in our driver the cdclk code + * paths should already be setting the appropriate voltage, hence we do + * nothign here. + */ + + val = I915_READ(enable_reg); + val |= PLL_ENABLE; + I915_WRITE(enable_reg, val); + + if (intel_wait_for_register(dev_priv, enable_reg, PLL_LOCK, PLL_LOCK, + 1)) /* 600us actually. */ + DRM_ERROR("PLL %d not locked\n", id); + + /* DVFS post sequence would be here. See the comment above. */ +} + +static void icl_pll_disable(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll) +{ + const enum intel_dpll_id id = pll->info->id; + i915_reg_t enable_reg = icl_pll_id_to_enable_reg(id); + uint32_t val; + + /* The first steps are done by intel_ddi_post_disable(). */ + + /* + * DVFS pre sequence would be here, but in our driver the cdclk code + * paths should already be setting the appropriate voltage, hence we do + * nothign here. + */ + + val = I915_READ(enable_reg); + val &= ~PLL_ENABLE; + I915_WRITE(enable_reg, val); + + /* Timeout is actually 1us. */ + if (intel_wait_for_register(dev_priv, enable_reg, PLL_LOCK, 0, 1)) + DRM_ERROR("PLL %d locked\n", id); + + /* DVFS post sequence would be here. See the comment above. */ + + val = I915_READ(enable_reg); + val &= ~PLL_POWER_ENABLE; + I915_WRITE(enable_reg, val); + + /* + * The spec says we need to "wait" but it also says it should be + * immediate. + */ + if (intel_wait_for_register(dev_priv, enable_reg, PLL_POWER_STATE, 0, + 1)) + DRM_ERROR("PLL %d Power not disabled\n", id); +} + +static void icl_dump_hw_state(struct drm_i915_private *dev_priv, + struct intel_dpll_hw_state *hw_state) +{ + DRM_DEBUG_KMS("dpll_hw_state: cfgcr0: 0x%x, cfgcr1: 0x%x, " + "mg_refclkin_ctl: 0x%x, hg_clktop2_coreclkctl1: 0x%x, " + "mg_clktop2_hsclkctl: 0x%x, mg_pll_div0: 0x%x, " + "mg_pll_div2: 0x%x, mg_pll_lf: 0x%x, " + "mg_pll_frac_lock: 0x%x, mg_pll_ssc: 0x%x, " + "mg_pll_bias: 0x%x, mg_pll_tdc_coldst_bias: 0x%x\n", + hw_state->cfgcr0, hw_state->cfgcr1, + hw_state->mg_refclkin_ctl, + hw_state->mg_clktop2_coreclkctl1, + hw_state->mg_clktop2_hsclkctl, + hw_state->mg_pll_div0, + hw_state->mg_pll_div1, + hw_state->mg_pll_lf, + hw_state->mg_pll_frac_lock, + hw_state->mg_pll_ssc, + hw_state->mg_pll_bias, + hw_state->mg_pll_tdc_coldst_bias); +} + +static const struct intel_shared_dpll_funcs icl_pll_funcs = { + .enable = icl_pll_enable, + .disable = icl_pll_disable, + .get_hw_state = icl_pll_get_hw_state, +}; + +static const struct dpll_info icl_plls[] = { + { "DPLL 0", &icl_pll_funcs, DPLL_ID_ICL_DPLL0, 0 }, + { "DPLL 1", &icl_pll_funcs, DPLL_ID_ICL_DPLL1, 0 }, + { "MG PLL 1", &icl_pll_funcs, DPLL_ID_ICL_MGPLL1, 0 }, + { "MG PLL 2", &icl_pll_funcs, DPLL_ID_ICL_MGPLL2, 0 }, + { "MG PLL 3", &icl_pll_funcs, DPLL_ID_ICL_MGPLL3, 0 }, + { "MG PLL 4", &icl_pll_funcs, DPLL_ID_ICL_MGPLL4, 0 }, + { }, +}; + +static const struct intel_dpll_mgr icl_pll_mgr = { + .dpll_info = icl_plls, + .get_dpll = icl_get_dpll, + .dump_hw_state = icl_dump_hw_state, +}; + /** * intel_shared_dpll_init - Initialize shared DPLLs * @dev: drm device @@ -2412,7 +3060,9 @@ void intel_shared_dpll_init(struct drm_device *dev) const struct dpll_info *dpll_info; int i; - if (IS_CANNONLAKE(dev_priv)) + if (IS_ICELAKE(dev_priv)) + dpll_mgr = &icl_pll_mgr; + else if (IS_CANNONLAKE(dev_priv)) dpll_mgr = &cnl_pll_mgr; else if (IS_GEN9_BC(dev_priv)) dpll_mgr = &skl_pll_mgr; diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.h b/drivers/gpu/drm/i915/intel_dpll_mgr.h index 4febfaa..7a0cd56 100644 --- a/drivers/gpu/drm/i915/intel_dpll_mgr.h +++ b/drivers/gpu/drm/i915/intel_dpll_mgr.h @@ -103,6 +103,32 @@ enum intel_dpll_id { * @DPLL_ID_SKL_DPLL3: SKL and later DPLL3 */ DPLL_ID_SKL_DPLL3 = 3, + + + /** + * @DPLL_ID_ICL_DPLL0: ICL combo PHY DPLL0 + */ + DPLL_ID_ICL_DPLL0 = 0, + /** + * @DPLL_ID_ICL_DPLL1: ICL combo PHY DPLL1 + */ + DPLL_ID_ICL_DPLL1 = 1, + /** + * @DPLL_ID_ICL_MGPLL1: ICL MG PLL 1 port 1 (C) + */ + DPLL_ID_ICL_MGPLL1 = 2, + /** + * @DPLL_ID_ICL_MGPLL2: ICL MG PLL 1 port 2 (D) + */ + DPLL_ID_ICL_MGPLL2 = 3, + /** + * @DPLL_ID_ICL_MGPLL3: ICL MG PLL 1 port 3 (E) + */ + DPLL_ID_ICL_MGPLL3 = 4, + /** + * @DPLL_ID_ICL_MGPLL4: ICL MG PLL 1 port 4 (F) + */ + DPLL_ID_ICL_MGPLL4 = 5, }; #define I915_NUM_PLLS 6 @@ -135,6 +161,21 @@ struct intel_dpll_hw_state { /* bxt */ uint32_t ebb0, ebb4, pll0, pll1, pll2, pll3, pll6, pll8, pll9, pll10, pcsdw12; + + /* + * ICL uses the following, already defined: + * uint32_t cfgcr0, cfgcr1; + */ + uint32_t mg_refclkin_ctl; + uint32_t mg_clktop2_coreclkctl1; + uint32_t mg_clktop2_hsclkctl; + uint32_t mg_pll_div0; + uint32_t mg_pll_div1; + uint32_t mg_pll_lf; + uint32_t mg_pll_frac_lock; + uint32_t mg_pll_ssc; + uint32_t mg_pll_bias; + uint32_t mg_pll_tdc_coldst_bias; }; /** diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 5bd2263..d7dbca1 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -49,13 +49,15 @@ * check the condition before the timeout. */ #define __wait_for(OP, COND, US, Wmin, Wmax) ({ \ - unsigned long timeout__ = jiffies + usecs_to_jiffies(US) + 1; \ + const ktime_t end__ = ktime_add_ns(ktime_get_raw(), 1000ll * (US)); \ long wait__ = (Wmin); /* recommended min for usleep is 10 us */ \ int ret__; \ might_sleep(); \ for (;;) { \ - bool expired__ = time_after(jiffies, timeout__); \ + const bool expired__ = ktime_after(ktime_get_raw(), end__); \ OP; \ + /* Guarantee COND check prior to timeout */ \ + barrier(); \ if (COND) { \ ret__ = 0; \ break; \ @@ -96,6 +98,8 @@ u64 now = local_clock(); \ if (!(ATOMIC)) \ preempt_enable(); \ + /* Guarantee COND check prior to timeout */ \ + barrier(); \ if (COND) { \ ret = 0; \ break; \ @@ -140,6 +144,10 @@ #define KHz(x) (1000 * (x)) #define MHz(x) KHz(1000 * (x)) +#define KBps(x) (1000 * (x)) +#define MBps(x) KBps(1000 * (x)) +#define GBps(x) ((u64)1000 * MBps((x))) + /* * Display related stuff */ @@ -882,6 +890,7 @@ struct intel_crtc_state { /* bitmask of visible planes (enum plane_id) */ u8 active_planes; + u8 nv12_planes; /* HDMI scrambling status */ bool hdmi_scrambling; @@ -1329,6 +1338,9 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv); void intel_check_pch_fifo_underruns(struct drm_i915_private *dev_priv); /* i915_irq.c */ +bool gen11_reset_one_iir(struct drm_i915_private * const i915, + const unsigned int bank, + const unsigned int bit); void gen5_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask); void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask); void gen6_mask_pm_irq(struct drm_i915_private *dev_priv, u32 mask); @@ -1398,6 +1410,12 @@ uint32_t ddi_signal_levels(struct intel_dp *intel_dp); u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder); int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, bool enable); +void icl_map_plls_to_ports(struct drm_crtc *crtc, + struct intel_crtc_state *crtc_state, + struct drm_atomic_state *old_state); +void icl_unmap_plls_to_ports(struct drm_crtc *crtc, + struct intel_crtc_state *crtc_state, + struct drm_atomic_state *old_state); unsigned int intel_fb_align_height(const struct drm_framebuffer *fb, int plane, unsigned int height); @@ -1580,8 +1598,6 @@ void bxt_enable_dc9(struct drm_i915_private *dev_priv); void bxt_disable_dc9(struct drm_i915_private *dev_priv); void gen9_enable_dc5(struct drm_i915_private *dev_priv); unsigned int skl_cdclk_get_vco(unsigned int freq); -void skl_enable_dc6(struct drm_i915_private *dev_priv); -void skl_disable_dc6(struct drm_i915_private *dev_priv); void intel_dp_get_m_n(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config); void intel_dp_set_m_n(struct intel_crtc *crtc, enum link_m_n_set m_n); @@ -1901,6 +1917,8 @@ void intel_psr_single_frame_update(struct drm_i915_private *dev_priv, unsigned frontbuffer_bits); void intel_psr_compute_config(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state); +void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug); +void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir); /* intel_runtime_pm.c */ int intel_power_domains_init(struct drm_i915_private *); @@ -1924,6 +1942,8 @@ bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); void intel_display_power_put(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); +void icl_dbuf_slices_update(struct drm_i915_private *dev_priv, + u8 req_slices); static inline void assert_rpm_device_not_suspended(struct drm_i915_private *dev_priv) @@ -2062,6 +2082,8 @@ bool skl_plane_get_hw_state(struct intel_plane *plane); bool skl_plane_has_ccs(struct drm_i915_private *dev_priv, enum pipe pipe, enum plane_id plane_id); bool intel_format_is_yuv(uint32_t format); +bool skl_plane_has_planar(struct drm_i915_private *dev_priv, + enum pipe pipe, enum plane_id plane_id); /* intel_tv.c */ void intel_tv_init(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_dsi_vbt.c b/drivers/gpu/drm/i915/intel_dsi_vbt.c index 91c07b0..4d6ffa7 100644 --- a/drivers/gpu/drm/i915/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_vbt.c @@ -647,6 +647,11 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id) /* prepare count */ prepare_cnt = DIV_ROUND_UP(ths_prepare_ns * ui_den, ui_num * mul); + if (prepare_cnt > PREPARE_CNT_MAX) { + DRM_DEBUG_KMS("prepare count too high %u\n", prepare_cnt); + prepare_cnt = PREPARE_CNT_MAX; + } + /* exit zero count */ exit_zero_cnt = DIV_ROUND_UP( (ths_prepare_hszero - ths_prepare_ns) * ui_den, @@ -662,32 +667,29 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id) if (exit_zero_cnt < (55 * ui_den / ui_num) && (55 * ui_den) % ui_num) exit_zero_cnt += 1; + if (exit_zero_cnt > EXIT_ZERO_CNT_MAX) { + DRM_DEBUG_KMS("exit zero count too high %u\n", exit_zero_cnt); + exit_zero_cnt = EXIT_ZERO_CNT_MAX; + } + /* clk zero count */ clk_zero_cnt = DIV_ROUND_UP( (tclk_prepare_clkzero - ths_prepare_ns) * ui_den, ui_num * mul); + if (clk_zero_cnt > CLK_ZERO_CNT_MAX) { + DRM_DEBUG_KMS("clock zero count too high %u\n", clk_zero_cnt); + clk_zero_cnt = CLK_ZERO_CNT_MAX; + } + /* trail count */ tclk_trail_ns = max(mipi_config->tclk_trail, mipi_config->ths_trail); trail_cnt = DIV_ROUND_UP(tclk_trail_ns * ui_den, ui_num * mul); - if (prepare_cnt > PREPARE_CNT_MAX || - exit_zero_cnt > EXIT_ZERO_CNT_MAX || - clk_zero_cnt > CLK_ZERO_CNT_MAX || - trail_cnt > TRAIL_CNT_MAX) - DRM_DEBUG_DRIVER("Values crossing maximum limits, restricting to max values\n"); - - if (prepare_cnt > PREPARE_CNT_MAX) - prepare_cnt = PREPARE_CNT_MAX; - - if (exit_zero_cnt > EXIT_ZERO_CNT_MAX) - exit_zero_cnt = EXIT_ZERO_CNT_MAX; - - if (clk_zero_cnt > CLK_ZERO_CNT_MAX) - clk_zero_cnt = CLK_ZERO_CNT_MAX; - - if (trail_cnt > TRAIL_CNT_MAX) + if (trail_cnt > TRAIL_CNT_MAX) { + DRM_DEBUG_KMS("trail count too high %u\n", trail_cnt); trail_cnt = TRAIL_CNT_MAX; + } /* B080 */ intel_dsi->dphy_reg = exit_zero_cnt << 24 | trail_cnt << 16 | diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 1a83707..8303e05 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -306,7 +306,7 @@ intel_engine_setup(struct drm_i915_private *dev_priv, /* Nothing to do here, execute in order of dependencies */ engine->schedule = NULL; - spin_lock_init(&engine->stats.lock); + seqlock_init(&engine->stats.lock); ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier); @@ -451,11 +451,6 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno) GEM_BUG_ON(intel_engine_get_seqno(engine) != seqno); } -static void intel_engine_init_timeline(struct intel_engine_cs *engine) -{ - engine->timeline = &engine->i915->gt.global_timeline.engine[engine->id]; -} - static void intel_engine_init_batch_pool(struct intel_engine_cs *engine) { i915_gem_batch_pool_init(&engine->batch_pool, engine); @@ -475,9 +470,6 @@ static bool csb_force_mmio(struct drm_i915_private *i915) if (intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915)) return true; - if (IS_CANNONLAKE(i915)) - return true; - return false; } @@ -507,8 +499,9 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine) */ void intel_engine_setup_common(struct intel_engine_cs *engine) { + i915_timeline_init(engine->i915, &engine->timeline, engine->name); + intel_engine_init_execlist(engine); - intel_engine_init_timeline(engine); intel_engine_init_hangcheck(engine); intel_engine_init_batch_pool(engine); intel_engine_init_cmd_parser(engine); @@ -541,8 +534,6 @@ int intel_engine_create_scratch(struct intel_engine_cs *engine, int size) goto err_unref; engine->scratch = vma; - DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n", - engine->name, i915_ggtt_offset(vma)); return 0; err_unref: @@ -636,9 +627,6 @@ static int init_status_page(struct intel_engine_cs *engine) engine->status_page.vma = vma; engine->status_page.ggtt_offset = i915_ggtt_offset(vma); engine->status_page.page_addr = memset(vaddr, 0, PAGE_SIZE); - - DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n", - engine->name, i915_ggtt_offset(vma)); return 0; err_unpin: @@ -690,7 +678,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine) * be available. To avoid this we always pin the default * context. */ - ring = engine->context_pin(engine, engine->i915->kernel_context); + ring = intel_context_pin(engine->i915->kernel_context, engine); if (IS_ERR(ring)) return PTR_ERR(ring); @@ -699,8 +687,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine) * we can interrupt the engine at any time. */ if (engine->i915->preempt_context) { - ring = engine->context_pin(engine, - engine->i915->preempt_context); + ring = intel_context_pin(engine->i915->preempt_context, engine); if (IS_ERR(ring)) { ret = PTR_ERR(ring); goto err_unpin_kernel; @@ -724,9 +711,9 @@ err_breadcrumbs: intel_engine_fini_breadcrumbs(engine); err_unpin_preempt: if (engine->i915->preempt_context) - engine->context_unpin(engine, engine->i915->preempt_context); + intel_context_unpin(engine->i915->preempt_context, engine); err_unpin_kernel: - engine->context_unpin(engine, engine->i915->kernel_context); + intel_context_unpin(engine->i915->kernel_context, engine); return ret; } @@ -754,8 +741,10 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) i915_gem_object_put(engine->default_state); if (engine->i915->preempt_context) - engine->context_unpin(engine, engine->i915->preempt_context); - engine->context_unpin(engine, engine->i915->kernel_context); + intel_context_unpin(engine->i915->preempt_context, engine); + intel_context_unpin(engine->i915->kernel_context, engine); + + i915_timeline_fini(&engine->timeline); } u64 intel_engine_get_active_head(const struct intel_engine_cs *engine) @@ -1008,7 +997,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine) * the last request that remains in the timeline. When idle, it is * the last executed context as tracked by retirement. */ - rq = __i915_gem_active_peek(&engine->timeline->last_request); + rq = __i915_gem_active_peek(&engine->timeline.last_request); if (rq) return rq->ctx == kernel_context; else @@ -1081,6 +1070,8 @@ void intel_engines_unpark(struct drm_i915_private *i915) for_each_engine(engine, i915, id) { if (engine->unpark) engine->unpark(engine); + + intel_engine_init_hangcheck(engine); } } @@ -1113,17 +1104,35 @@ unsigned int intel_engines_has_context_isolation(struct drm_i915_private *i915) return which; } +static int print_sched_attr(struct drm_i915_private *i915, + const struct i915_sched_attr *attr, + char *buf, int x, int len) +{ + if (attr->priority == I915_PRIORITY_INVALID) + return x; + + x += snprintf(buf + x, len - x, + " prio=%d", attr->priority); + + return x; +} + static void print_request(struct drm_printer *m, struct i915_request *rq, const char *prefix) { const char *name = rq->fence.ops->get_timeline_name(&rq->fence); + char buf[80]; + int x = 0; - drm_printf(m, "%s%x%s [%llx:%x] prio=%d @ %dms: %s\n", prefix, + x = print_sched_attr(rq->i915, &rq->sched.attr, buf, x, sizeof(buf)); + + drm_printf(m, "%s%x%s [%llx:%x]%s @ %dms: %s\n", + prefix, rq->global_seqno, i915_request_completed(rq) ? "!" : "", rq->fence.context, rq->fence.seqno, - rq->priotree.priority, + buf, jiffies_to_msecs(jiffies - rq->emitted_jiffies), name); } @@ -1266,8 +1275,9 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine, char hdr[80]; snprintf(hdr, sizeof(hdr), - "\t\tELSP[%d] count=%d, rq: ", - idx, count); + "\t\tELSP[%d] count=%d, ring->start=%08x, rq: ", + idx, count, + i915_ggtt_offset(rq->ring->vma)); print_request(m, rq, hdr); } else { drm_printf(m, "\t\tELSP[%d] idle\n", idx); @@ -1289,11 +1299,13 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m, const char *header, ...) { + const int MAX_REQUESTS_TO_SHOW = 8; struct intel_breadcrumbs * const b = &engine->breadcrumbs; const struct intel_engine_execlists * const execlists = &engine->execlists; struct i915_gpu_error * const error = &engine->i915->gpu_error; - struct i915_request *rq; + struct i915_request *rq, *last; struct rb_node *rb; + int count; if (header) { va_list ap; @@ -1306,12 +1318,11 @@ void intel_engine_dump(struct intel_engine_cs *engine, if (i915_terminally_wedged(&engine->i915->gpu_error)) drm_printf(m, "*** WEDGED ***\n"); - drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], inflight %d\n", + drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms]\n", intel_engine_get_seqno(engine), intel_engine_last_submit(engine), engine->hangcheck.seqno, - jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp), - engine->timeline->inflight_seqnos); + jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp)); drm_printf(m, "\tReset count: %d (global %d)\n", i915_reset_engine_count(error, engine), i915_reset_count(error)); @@ -1320,14 +1331,14 @@ void intel_engine_dump(struct intel_engine_cs *engine, drm_printf(m, "\tRequests:\n"); - rq = list_first_entry(&engine->timeline->requests, + rq = list_first_entry(&engine->timeline.requests, struct i915_request, link); - if (&rq->link != &engine->timeline->requests) + if (&rq->link != &engine->timeline.requests) print_request(m, rq, "\t\tfirst "); - rq = list_last_entry(&engine->timeline->requests, + rq = list_last_entry(&engine->timeline.requests, struct i915_request, link); - if (&rq->link != &engine->timeline->requests) + if (&rq->link != &engine->timeline.requests) print_request(m, rq, "\t\tlast "); rq = i915_gem_find_active_request(engine); @@ -1359,18 +1370,49 @@ void intel_engine_dump(struct intel_engine_cs *engine, drm_printf(m, "\tDevice is asleep; skipping register dump\n"); } - spin_lock_irq(&engine->timeline->lock); - list_for_each_entry(rq, &engine->timeline->requests, link) - print_request(m, rq, "\t\tE "); + spin_lock_irq(&engine->timeline.lock); + + last = NULL; + count = 0; + list_for_each_entry(rq, &engine->timeline.requests, link) { + if (count++ < MAX_REQUESTS_TO_SHOW - 1) + print_request(m, rq, "\t\tE "); + else + last = rq; + } + if (last) { + if (count > MAX_REQUESTS_TO_SHOW) { + drm_printf(m, + "\t\t...skipping %d executing requests...\n", + count - MAX_REQUESTS_TO_SHOW); + } + print_request(m, last, "\t\tE "); + } + + last = NULL; + count = 0; drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority); for (rb = execlists->first; rb; rb = rb_next(rb)) { struct i915_priolist *p = rb_entry(rb, typeof(*p), node); - list_for_each_entry(rq, &p->requests, priotree.link) - print_request(m, rq, "\t\tQ "); + list_for_each_entry(rq, &p->requests, sched.link) { + if (count++ < MAX_REQUESTS_TO_SHOW - 1) + print_request(m, rq, "\t\tQ "); + else + last = rq; + } + } + if (last) { + if (count > MAX_REQUESTS_TO_SHOW) { + drm_printf(m, + "\t\t...skipping %d queued requests...\n", + count - MAX_REQUESTS_TO_SHOW); + } + print_request(m, last, "\t\tQ "); } - spin_unlock_irq(&engine->timeline->lock); + + spin_unlock_irq(&engine->timeline.lock); spin_lock_irq(&b->rb_lock); for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) { @@ -1435,7 +1477,7 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine) return -ENODEV; tasklet_disable(&execlists->tasklet); - spin_lock_irqsave(&engine->stats.lock, flags); + write_seqlock_irqsave(&engine->stats.lock, flags); if (unlikely(engine->stats.enabled == ~0)) { err = -EBUSY; @@ -1459,7 +1501,7 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine) } unlock: - spin_unlock_irqrestore(&engine->stats.lock, flags); + write_sequnlock_irqrestore(&engine->stats.lock, flags); tasklet_enable(&execlists->tasklet); return err; @@ -1488,12 +1530,13 @@ static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine) */ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine) { + unsigned int seq; ktime_t total; - unsigned long flags; - spin_lock_irqsave(&engine->stats.lock, flags); - total = __intel_engine_get_busy_time(engine); - spin_unlock_irqrestore(&engine->stats.lock, flags); + do { + seq = read_seqbegin(&engine->stats.lock); + total = __intel_engine_get_busy_time(engine); + } while (read_seqretry(&engine->stats.lock, seq)); return total; } @@ -1511,13 +1554,13 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine) if (!intel_engine_supports_stats(engine)) return; - spin_lock_irqsave(&engine->stats.lock, flags); + write_seqlock_irqsave(&engine->stats.lock, flags); WARN_ON_ONCE(engine->stats.enabled == 0); if (--engine->stats.enabled == 0) { engine->stats.total = __intel_engine_get_busy_time(engine); engine->stats.active = 0; } - spin_unlock_irqrestore(&engine->stats.lock, flags); + write_sequnlock_irqrestore(&engine->stats.lock, flags); } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 65a3313..e9e02b5 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -641,7 +641,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, if (!crtc->state->active) continue; - WARN(!crtc->primary->fb, + WARN(!crtc->primary->state->fb, "re-used BIOS config but lost an fb on crtc %d\n", crtc->base.id); } @@ -807,7 +807,7 @@ void intel_fbdev_output_poll_changed(struct drm_device *dev) return; intel_fbdev_sync(ifbdev); - if (ifbdev->vma) + if (ifbdev->vma || ifbdev->helper.deferred_setup) drm_fb_helper_hotplug_event(&ifbdev->helper); } diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c index a00a59a..116f4cc 100644 --- a/drivers/gpu/drm/i915/intel_guc.c +++ b/drivers/gpu/drm/i915/intel_guc.c @@ -203,26 +203,6 @@ void intel_guc_fini(struct intel_guc *guc) guc_shared_data_destroy(guc); } -static u32 get_gt_type(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) -{ - u32 gen = INTEL_GEN(dev_priv); - - switch (gen) { - case 9: - return GUC_CORE_FAMILY_GEN9; - - default: - MISSING_CASE(gen); - return GUC_CORE_FAMILY_UNKNOWN; - } -} - static u32 get_log_control_flags(void) { u32 level = i915_modparams.guc_log_level; @@ -255,10 +235,6 @@ void intel_guc_init_params(struct intel_guc *guc) memset(params, 0, sizeof(params)); - params[GUC_CTL_DEVICE_INFO] |= - (get_gt_type(dev_priv) << GUC_CTL_GT_TYPE_SHIFT) | - (get_core_family(dev_priv) << GUC_CTL_CORE_FAMILY_SHIFT); - /* * GuC ARAT increment is 10 ns. GuC default scheduler quantum is one * second. This ARAR is calculated by: diff --git a/drivers/gpu/drm/i915/intel_guc_ads.c b/drivers/gpu/drm/i915/intel_guc_ads.c index 334cb52..dcaa3fb7 100644 --- a/drivers/gpu/drm/i915/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/intel_guc_ads.c @@ -121,7 +121,8 @@ int intel_guc_ads_create(struct intel_guc *guc) * to find it. Note that we have to skip our header (1 page), * because our GuC shared data is there. */ - kernel_ctx_vma = dev_priv->kernel_context->engine[RCS].state; + kernel_ctx_vma = to_intel_context(dev_priv->kernel_context, + dev_priv->engine[RCS])->state; blob->ads.golden_context_lrca = intel_guc_ggtt_offset(guc, kernel_ctx_vma) + skipped_offset; diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h index d73673f..0867ba7 100644 --- a/drivers/gpu/drm/i915/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/intel_guc_fwif.h @@ -23,9 +23,6 @@ #ifndef _INTEL_GUC_FWIF_H #define _INTEL_GUC_FWIF_H -#define GUC_CORE_FAMILY_GEN9 12 -#define GUC_CORE_FAMILY_UNKNOWN 0x7fffffff - #define GUC_CLIENT_PRIORITY_KMD_HIGH 0 #define GUC_CLIENT_PRIORITY_HIGH 1 #define GUC_CLIENT_PRIORITY_KMD_NORMAL 2 @@ -82,8 +79,6 @@ #define GUC_CTL_ARAT_LOW 2 #define GUC_CTL_DEVICE_INFO 3 -#define GUC_CTL_GT_TYPE_SHIFT 0 -#define GUC_CTL_CORE_FAMILY_SHIFT 7 #define GUC_CTL_LOG_PARAMS 4 #define GUC_LOG_VALID (1 << 0) diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c index 9712123..2feb650 100644 --- a/drivers/gpu/drm/i915/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/intel_guc_submission.c @@ -124,9 +124,17 @@ static int reserve_doorbell(struct intel_guc_client *client) return 0; } +static bool has_doorbell(struct intel_guc_client *client) +{ + if (client->doorbell_id == GUC_DOORBELL_INVALID) + return false; + + return test_bit(client->doorbell_id, client->guc->doorbell_bitmap); +} + static void unreserve_doorbell(struct intel_guc_client *client) { - GEM_BUG_ON(client->doorbell_id == GUC_DOORBELL_INVALID); + GEM_BUG_ON(!has_doorbell(client)); __clear_bit(client->doorbell_id, client->guc->doorbell_bitmap); client->doorbell_id = GUC_DOORBELL_INVALID; @@ -184,14 +192,6 @@ static struct guc_doorbell_info *__get_doorbell(struct intel_guc_client *client) return client->vaddr + client->doorbell_offset; } -static bool has_doorbell(struct intel_guc_client *client) -{ - if (client->doorbell_id == GUC_DOORBELL_INVALID) - return false; - - return test_bit(client->doorbell_id, client->guc->doorbell_bitmap); -} - static void __create_doorbell(struct intel_guc_client *client) { struct guc_doorbell_info *doorbell; @@ -207,7 +207,6 @@ static void __destroy_doorbell(struct intel_guc_client *client) struct guc_doorbell_info *doorbell; u16 db_id = client->doorbell_id; - doorbell = __get_doorbell(client); doorbell->db_status = GUC_DOORBELL_DISABLED; doorbell->cookie = 0; @@ -224,6 +223,9 @@ static int create_doorbell(struct intel_guc_client *client) { int ret; + if (WARN_ON(!has_doorbell(client))) + return -ENODEV; /* internal setup error, should never happen */ + __update_doorbell_desc(client, client->doorbell_id); __create_doorbell(client); @@ -362,7 +364,7 @@ static void guc_stage_desc_init(struct intel_guc *guc, desc->db_id = client->doorbell_id; for_each_engine_masked(engine, dev_priv, client->engines, tmp) { - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = to_intel_context(ctx, engine); u32 guc_engine_id = engine->guc_id; struct guc_execlist_context *lrc = &desc->lrc[guc_engine_id]; @@ -659,7 +661,7 @@ static void port_assign(struct execlist_port *port, struct i915_request *rq) static inline int rq_prio(const struct i915_request *rq) { - return rq->priotree.priority; + return rq->sched.attr.priority; } static inline int port_prio(const struct execlist_port *port) @@ -667,7 +669,7 @@ static inline int port_prio(const struct execlist_port *port) return rq_prio(port_request(port)); } -static void guc_dequeue(struct intel_engine_cs *engine) +static bool __guc_dequeue(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; struct execlist_port *port = execlists->port; @@ -677,7 +679,8 @@ static void guc_dequeue(struct intel_engine_cs *engine) bool submit = false; struct rb_node *rb; - spin_lock_irq(&engine->timeline->lock); + lockdep_assert_held(&engine->timeline.lock); + rb = execlists->first; GEM_BUG_ON(rb_first(&execlists->queue) != rb); @@ -692,13 +695,13 @@ static void guc_dequeue(struct intel_engine_cs *engine) EXECLISTS_ACTIVE_PREEMPT); queue_work(engine->i915->guc.preempt_wq, &preempt_work->work); - goto unlock; + return false; } } port++; if (port_isset(port)) - goto unlock; + return false; } GEM_BUG_ON(port_isset(port)); @@ -706,11 +709,11 @@ static void guc_dequeue(struct intel_engine_cs *engine) struct i915_priolist *p = to_priolist(rb); struct i915_request *rq, *rn; - list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) { + list_for_each_entry_safe(rq, rn, &p->requests, sched.link) { if (last && rq->ctx != last->ctx) { if (port == last_port) { __list_del_many(&p->requests, - &rq->priotree.link); + &rq->sched.link); goto done; } @@ -719,7 +722,7 @@ static void guc_dequeue(struct intel_engine_cs *engine) port++; } - INIT_LIST_HEAD(&rq->priotree.link); + INIT_LIST_HEAD(&rq->sched.link); __i915_request_submit(rq); trace_i915_request_in(rq, port_index(port, execlists)); @@ -736,19 +739,34 @@ static void guc_dequeue(struct intel_engine_cs *engine) done: execlists->queue_priority = rb ? to_priolist(rb)->priority : INT_MIN; execlists->first = rb; - if (submit) { + if (submit) port_assign(port, last); + if (last) execlists_user_begin(execlists, execlists->port); - guc_submit(engine); - } /* We must always keep the beast fed if we have work piled up */ GEM_BUG_ON(port_isset(execlists->port) && !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER)); GEM_BUG_ON(execlists->first && !port_isset(execlists->port)); -unlock: - spin_unlock_irq(&engine->timeline->lock); + return submit; +} + +static void guc_dequeue(struct intel_engine_cs *engine) +{ + unsigned long flags; + bool submit; + + local_irq_save(flags); + + spin_lock(&engine->timeline.lock); + submit = __guc_dequeue(engine); + spin_unlock(&engine->timeline.lock); + + if (submit) + guc_submit(engine); + + local_irq_restore(flags); } static void guc_submission_tasklet(unsigned long data) @@ -990,7 +1008,8 @@ static void guc_fill_preempt_context(struct intel_guc *guc) enum intel_engine_id id; for_each_engine(engine, dev_priv, id) { - struct intel_context *ce = &client->owner->engine[id]; + struct intel_context *ce = + to_intel_context(client->owner, engine); u32 addr = intel_hws_preempt_done_address(engine); u32 *cs; diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c index fd0ffb8..d47e346 100644 --- a/drivers/gpu/drm/i915/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/intel_hangcheck.c @@ -356,7 +356,7 @@ static void hangcheck_accumulate_sample(struct intel_engine_cs *engine, break; case ENGINE_DEAD: - if (drm_debug & DRM_UT_DRIVER) { + if (GEM_SHOW_DEBUG()) { struct drm_printer p = drm_debug_printer("hangcheck"); intel_engine_dump(engine, &p, "%s\n", engine->name); } @@ -452,6 +452,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work) void intel_engine_init_hangcheck(struct intel_engine_cs *engine) { memset(&engine->hangcheck, 0, sizeof(engine->hangcheck)); + engine->hangcheck.action_timestamp = jiffies; } void intel_hangcheck_init(struct drm_i915_private *i915) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index c7c8513..7c6164d 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -177,7 +177,7 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb) static inline int rq_prio(const struct i915_request *rq) { - return rq->priotree.priority; + return rq->sched.attr.priority; } static inline bool need_preempt(const struct intel_engine_cs *engine, @@ -185,7 +185,8 @@ static inline bool need_preempt(const struct intel_engine_cs *engine, int prio) { return (intel_engine_has_preemption(engine) && - __execlists_need_preempt(prio, rq_prio(last))); + __execlists_need_preempt(prio, rq_prio(last)) && + !i915_request_completed(last)); } /** @@ -223,7 +224,7 @@ static void intel_lr_context_descriptor_update(struct i915_gem_context *ctx, struct intel_engine_cs *engine) { - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = to_intel_context(ctx, engine); u64 desc; BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (BIT(GEN8_CTX_ID_WIDTH))); @@ -257,9 +258,7 @@ intel_lr_context_descriptor_update(struct i915_gem_context *ctx, } static struct i915_priolist * -lookup_priolist(struct intel_engine_cs *engine, - struct i915_priotree *pt, - int prio) +lookup_priolist(struct intel_engine_cs *engine, int prio) { struct intel_engine_execlists * const execlists = &engine->execlists; struct i915_priolist *p; @@ -330,10 +329,10 @@ static void __unwind_incomplete_requests(struct intel_engine_cs *engine) struct i915_priolist *uninitialized_var(p); int last_prio = I915_PRIORITY_INVALID; - lockdep_assert_held(&engine->timeline->lock); + lockdep_assert_held(&engine->timeline.lock); list_for_each_entry_safe_reverse(rq, rn, - &engine->timeline->requests, + &engine->timeline.requests, link) { if (i915_request_completed(rq)) return; @@ -344,10 +343,11 @@ static void __unwind_incomplete_requests(struct intel_engine_cs *engine) GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID); if (rq_prio(rq) != last_prio) { last_prio = rq_prio(rq); - p = lookup_priolist(engine, &rq->priotree, last_prio); + p = lookup_priolist(engine, last_prio); } - list_add(&rq->priotree.link, &p->requests); + GEM_BUG_ON(p->priority != rq_prio(rq)); + list_add(&rq->sched.link, &p->requests); } } @@ -356,10 +356,13 @@ execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists) { struct intel_engine_cs *engine = container_of(execlists, typeof(*engine), execlists); + unsigned long flags; + + spin_lock_irqsave(&engine->timeline.lock, flags); - spin_lock_irq(&engine->timeline->lock); __unwind_incomplete_requests(engine); - spin_unlock_irq(&engine->timeline->lock); + + spin_unlock_irqrestore(&engine->timeline.lock, flags); } static inline void @@ -397,10 +400,11 @@ execlists_context_schedule_in(struct i915_request *rq) } static inline void -execlists_context_schedule_out(struct i915_request *rq) +execlists_context_schedule_out(struct i915_request *rq, unsigned long status) { intel_engine_context_out(rq->engine); - execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT); + execlists_context_status_change(rq, status); + trace_i915_request_out(rq); } static void @@ -414,7 +418,7 @@ execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state) static u64 execlists_update_context(struct i915_request *rq) { - struct intel_context *ce = &rq->ctx->engine[rq->engine->id]; + struct intel_context *ce = to_intel_context(rq->ctx, rq->engine); struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt; u32 *reg_state = ce->lrc_reg_state; @@ -523,7 +527,7 @@ static void inject_preempt_context(struct intel_engine_cs *engine) { struct intel_engine_execlists *execlists = &engine->execlists; struct intel_context *ce = - &engine->i915->preempt_context->engine[engine->id]; + to_intel_context(engine->i915->preempt_context, engine); unsigned int n; GEM_BUG_ON(execlists->preempt_complete_status != @@ -552,7 +556,7 @@ static void inject_preempt_context(struct intel_engine_cs *engine) execlists_set_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT); } -static void execlists_dequeue(struct intel_engine_cs *engine) +static bool __execlists_dequeue(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; struct execlist_port *port = execlists->port; @@ -562,6 +566,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine) struct rb_node *rb; bool submit = false; + lockdep_assert_held(&engine->timeline.lock); + /* Hardware submission is through 2 ports. Conceptually each port * has a (RING_START, RING_HEAD, RING_TAIL) tuple. RING_START is * static for a context, and unique to each, so we only execute @@ -583,7 +589,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * and context switches) submission. */ - spin_lock_irq(&engine->timeline->lock); rb = execlists->first; GEM_BUG_ON(rb_first(&execlists->queue) != rb); @@ -598,7 +603,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) EXECLISTS_ACTIVE_USER)); GEM_BUG_ON(!port_count(&port[0])); if (port_count(&port[0]) > 1) - goto unlock; + return false; /* * If we write to ELSP a second time before the HW has had @@ -608,11 +613,11 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * the HW to indicate that it has had a chance to respond. */ if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_HWACK)) - goto unlock; + return false; if (need_preempt(engine, last, execlists->queue_priority)) { inject_preempt_context(engine); - goto unlock; + return false; } /* @@ -637,7 +642,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * priorities of the ports haven't been switch. */ if (port_count(&port[1])) - goto unlock; + return false; /* * WaIdleLiteRestore:bdw,skl @@ -654,7 +659,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) struct i915_priolist *p = to_priolist(rb); struct i915_request *rq, *rn; - list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) { + list_for_each_entry_safe(rq, rn, &p->requests, sched.link) { /* * Can we combine this request with the current port? * It has to be the same context/ringbuffer and not @@ -674,7 +679,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) */ if (port == last_port) { __list_del_many(&p->requests, - &rq->priotree.link); + &rq->sched.link); goto done; } @@ -688,7 +693,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) if (ctx_single_port_submission(last->ctx) || ctx_single_port_submission(rq->ctx)) { __list_del_many(&p->requests, - &rq->priotree.link); + &rq->sched.link); goto done; } @@ -701,7 +706,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) GEM_BUG_ON(port_isset(port)); } - INIT_LIST_HEAD(&rq->priotree.link); + INIT_LIST_HEAD(&rq->sched.link); __i915_request_submit(rq); trace_i915_request_in(rq, port_index(port, execlists)); last = rq; @@ -742,13 +747,25 @@ done: /* We must always keep the beast fed if we have work piled up */ GEM_BUG_ON(execlists->first && !port_isset(execlists->port)); -unlock: - spin_unlock_irq(&engine->timeline->lock); - - if (submit) { + /* Re-evaluate the executing context setup after each preemptive kick */ + if (last) execlists_user_begin(execlists, execlists->port); + + return submit; +} + +static void execlists_dequeue(struct intel_engine_cs *engine) +{ + struct intel_engine_execlists * const execlists = &engine->execlists; + unsigned long flags; + bool submit; + + spin_lock_irqsave(&engine->timeline.lock, flags); + submit = __execlists_dequeue(engine); + spin_unlock_irqrestore(&engine->timeline.lock, flags); + + if (submit) execlists_submit_ports(engine); - } GEM_BUG_ON(port_isset(execlists->port) && !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER)); @@ -771,12 +788,10 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists) intel_engine_get_seqno(rq->engine)); GEM_BUG_ON(!execlists->active); - intel_engine_context_out(rq->engine); - - execlists_context_status_change(rq, - i915_request_completed(rq) ? - INTEL_CONTEXT_SCHEDULE_OUT : - INTEL_CONTEXT_SCHEDULE_PREEMPTED); + execlists_context_schedule_out(rq, + i915_request_completed(rq) ? + INTEL_CONTEXT_SCHEDULE_OUT : + INTEL_CONTEXT_SCHEDULE_PREEMPTED); i915_request_put(rq); @@ -784,27 +799,15 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists) port++; } + execlists_clear_active(execlists, EXECLISTS_ACTIVE_USER); execlists_user_end(execlists); } static void clear_gtiir(struct intel_engine_cs *engine) { - static const u8 gtiir[] = { - [RCS] = 0, - [BCS] = 0, - [VCS] = 1, - [VCS2] = 1, - [VECS] = 3, - }; struct drm_i915_private *dev_priv = engine->i915; int i; - /* TODO: correctly reset irqs for gen11 */ - if (WARN_ON_ONCE(INTEL_GEN(engine->i915) >= 11)) - return; - - GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir)); - /* * Clear any pending interrupt state. * @@ -812,13 +815,50 @@ static void clear_gtiir(struct intel_engine_cs *engine) * double buffered, and so if we only reset it once there may * still be an interrupt pending. */ - for (i = 0; i < 2; i++) { - I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]), + if (INTEL_GEN(dev_priv) >= 11) { + static const struct { + u8 bank; + u8 bit; + } gen11_gtiir[] = { + [RCS] = {0, GEN11_RCS0}, + [BCS] = {0, GEN11_BCS}, + [_VCS(0)] = {1, GEN11_VCS(0)}, + [_VCS(1)] = {1, GEN11_VCS(1)}, + [_VCS(2)] = {1, GEN11_VCS(2)}, + [_VCS(3)] = {1, GEN11_VCS(3)}, + [_VECS(0)] = {1, GEN11_VECS(0)}, + [_VECS(1)] = {1, GEN11_VECS(1)}, + }; + unsigned long irqflags; + + GEM_BUG_ON(engine->id >= ARRAY_SIZE(gen11_gtiir)); + + spin_lock_irqsave(&dev_priv->irq_lock, irqflags); + for (i = 0; i < 2; i++) { + gen11_reset_one_iir(dev_priv, + gen11_gtiir[engine->id].bank, + gen11_gtiir[engine->id].bit); + } + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + } else { + static const u8 gtiir[] = { + [RCS] = 0, + [BCS] = 0, + [VCS] = 1, + [VCS2] = 1, + [VECS] = 3, + }; + + GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir)); + + for (i = 0; i < 2; i++) { + I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]), + engine->irq_keep_mask); + POSTING_READ(GEN8_GT_IIR(gtiir[engine->id])); + } + GEM_BUG_ON(I915_READ(GEN8_GT_IIR(gtiir[engine->id])) & engine->irq_keep_mask); - POSTING_READ(GEN8_GT_IIR(gtiir[engine->id])); } - GEM_BUG_ON(I915_READ(GEN8_GT_IIR(gtiir[engine->id])) & - engine->irq_keep_mask); } static void reset_irq(struct intel_engine_cs *engine) @@ -868,10 +908,10 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) execlists_cancel_port_requests(execlists); reset_irq(engine); - spin_lock(&engine->timeline->lock); + spin_lock(&engine->timeline.lock); /* Mark all executing requests as skipped. */ - list_for_each_entry(rq, &engine->timeline->requests, link) { + list_for_each_entry(rq, &engine->timeline.requests, link) { GEM_BUG_ON(!rq->global_seqno); if (!i915_request_completed(rq)) dma_fence_set_error(&rq->fence, -EIO); @@ -882,8 +922,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) while (rb) { struct i915_priolist *p = to_priolist(rb); - list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) { - INIT_LIST_HEAD(&rq->priotree.link); + list_for_each_entry_safe(rq, rn, &p->requests, sched.link) { + INIT_LIST_HEAD(&rq->sched.link); dma_fence_set_error(&rq->fence, -EIO); __i915_request_submit(rq); @@ -903,7 +943,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) execlists->first = NULL; GEM_BUG_ON(port_isset(execlists->port)); - spin_unlock(&engine->timeline->lock); + spin_unlock(&engine->timeline.lock); local_irq_restore(flags); } @@ -969,6 +1009,7 @@ static void execlists_submission_tasklet(unsigned long data) head = execlists->csb_head; tail = READ_ONCE(buf[write_idx]); + rmb(); /* Hopefully paired with a wmb() in HW */ } GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n", engine->name, @@ -1079,8 +1120,8 @@ static void execlists_submission_tasklet(unsigned long data) */ GEM_BUG_ON(!i915_request_completed(rq)); - execlists_context_schedule_out(rq); - trace_i915_request_out(rq); + execlists_context_schedule_out(rq, + INTEL_CONTEXT_SCHEDULE_OUT); i915_request_put(rq); GEM_TRACE("%s completed ctx=%d\n", @@ -1116,10 +1157,11 @@ static void execlists_submission_tasklet(unsigned long data) } static void queue_request(struct intel_engine_cs *engine, - struct i915_priotree *pt, + struct i915_sched_node *node, int prio) { - list_add_tail(&pt->link, &lookup_priolist(engine, pt, prio)->requests); + list_add_tail(&node->link, + &lookup_priolist(engine, prio)->requests); } static void __submit_queue(struct intel_engine_cs *engine, int prio) @@ -1140,42 +1182,45 @@ static void execlists_submit_request(struct i915_request *request) unsigned long flags; /* Will be called from irq-context when using foreign fences. */ - spin_lock_irqsave(&engine->timeline->lock, flags); + spin_lock_irqsave(&engine->timeline.lock, flags); - queue_request(engine, &request->priotree, rq_prio(request)); + queue_request(engine, &request->sched, rq_prio(request)); submit_queue(engine, rq_prio(request)); GEM_BUG_ON(!engine->execlists.first); - GEM_BUG_ON(list_empty(&request->priotree.link)); + GEM_BUG_ON(list_empty(&request->sched.link)); - spin_unlock_irqrestore(&engine->timeline->lock, flags); + spin_unlock_irqrestore(&engine->timeline.lock, flags); } -static struct i915_request *pt_to_request(struct i915_priotree *pt) +static struct i915_request *sched_to_request(struct i915_sched_node *node) { - return container_of(pt, struct i915_request, priotree); + return container_of(node, struct i915_request, sched); } static struct intel_engine_cs * -pt_lock_engine(struct i915_priotree *pt, struct intel_engine_cs *locked) +sched_lock_engine(struct i915_sched_node *node, struct intel_engine_cs *locked) { - struct intel_engine_cs *engine = pt_to_request(pt)->engine; + struct intel_engine_cs *engine = sched_to_request(node)->engine; GEM_BUG_ON(!locked); if (engine != locked) { - spin_unlock(&locked->timeline->lock); - spin_lock(&engine->timeline->lock); + spin_unlock(&locked->timeline.lock); + spin_lock(&engine->timeline.lock); } return engine; } -static void execlists_schedule(struct i915_request *request, int prio) +static void execlists_schedule(struct i915_request *request, + const struct i915_sched_attr *attr) { - struct intel_engine_cs *engine; + struct i915_priolist *uninitialized_var(pl); + struct intel_engine_cs *engine, *last; struct i915_dependency *dep, *p; struct i915_dependency stack; + const int prio = attr->priority; LIST_HEAD(dfs); GEM_BUG_ON(prio == I915_PRIORITY_INVALID); @@ -1183,23 +1228,23 @@ static void execlists_schedule(struct i915_request *request, int prio) if (i915_request_completed(request)) return; - if (prio <= READ_ONCE(request->priotree.priority)) + if (prio <= READ_ONCE(request->sched.attr.priority)) return; /* Need BKL in order to use the temporary link inside i915_dependency */ lockdep_assert_held(&request->i915->drm.struct_mutex); - stack.signaler = &request->priotree; + stack.signaler = &request->sched; list_add(&stack.dfs_link, &dfs); /* * Recursively bump all dependent priorities to match the new request. * * A naive approach would be to use recursion: - * static void update_priorities(struct i915_priotree *pt, prio) { - * list_for_each_entry(dep, &pt->signalers_list, signal_link) + * static void update_priorities(struct i915_sched_node *node, prio) { + * list_for_each_entry(dep, &node->signalers_list, signal_link) * update_priorities(dep->signal, prio) - * queue_request(pt); + * queue_request(node); * } * but that may have unlimited recursion depth and so runs a very * real risk of overunning the kernel stack. Instead, we build @@ -1211,7 +1256,7 @@ static void execlists_schedule(struct i915_request *request, int prio) * last element in the list is the request we must execute first. */ list_for_each_entry(dep, &dfs, dfs_link) { - struct i915_priotree *pt = dep->signaler; + struct i915_sched_node *node = dep->signaler; /* * Within an engine, there can be no cycle, but we may @@ -1219,14 +1264,14 @@ static void execlists_schedule(struct i915_request *request, int prio) * (redundant dependencies are not eliminated) and across * engines. */ - list_for_each_entry(p, &pt->signalers_list, signal_link) { + list_for_each_entry(p, &node->signalers_list, signal_link) { GEM_BUG_ON(p == dep); /* no cycles! */ - if (i915_priotree_signaled(p->signaler)) + if (i915_sched_node_signaled(p->signaler)) continue; - GEM_BUG_ON(p->signaler->priority < pt->priority); - if (prio > READ_ONCE(p->signaler->priority)) + GEM_BUG_ON(p->signaler->attr.priority < node->attr.priority); + if (prio > READ_ONCE(p->signaler->attr.priority)) list_move_tail(&p->dfs_link, &dfs); } } @@ -1237,40 +1282,45 @@ static void execlists_schedule(struct i915_request *request, int prio) * execlists_submit_request()), we can set our own priority and skip * acquiring the engine locks. */ - if (request->priotree.priority == I915_PRIORITY_INVALID) { - GEM_BUG_ON(!list_empty(&request->priotree.link)); - request->priotree.priority = prio; + if (request->sched.attr.priority == I915_PRIORITY_INVALID) { + GEM_BUG_ON(!list_empty(&request->sched.link)); + request->sched.attr = *attr; if (stack.dfs_link.next == stack.dfs_link.prev) return; __list_del_entry(&stack.dfs_link); } + last = NULL; engine = request->engine; - spin_lock_irq(&engine->timeline->lock); + spin_lock_irq(&engine->timeline.lock); /* Fifo and depth-first replacement ensure our deps execute before us */ list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) { - struct i915_priotree *pt = dep->signaler; + struct i915_sched_node *node = dep->signaler; INIT_LIST_HEAD(&dep->dfs_link); - engine = pt_lock_engine(pt, engine); + engine = sched_lock_engine(node, engine); - if (prio <= pt->priority) + if (prio <= node->attr.priority) continue; - pt->priority = prio; - if (!list_empty(&pt->link)) { - __list_del_entry(&pt->link); - queue_request(engine, pt, prio); + node->attr.priority = prio; + if (!list_empty(&node->link)) { + if (last != engine) { + pl = lookup_priolist(engine, prio); + last = engine; + } + GEM_BUG_ON(pl->priority != prio); + list_move_tail(&node->link, &pl->requests); } if (prio > engine->execlists.queue_priority && - i915_sw_fence_done(&pt_to_request(pt)->submit)) + i915_sw_fence_done(&sched_to_request(node)->submit)) __submit_queue(engine, prio); } - spin_unlock_irq(&engine->timeline->lock); + spin_unlock_irq(&engine->timeline.lock); } static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma) @@ -1300,7 +1350,7 @@ static struct intel_ring * execlists_context_pin(struct intel_engine_cs *engine, struct i915_gem_context *ctx) { - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = to_intel_context(ctx, engine); void *vaddr; int ret; @@ -1353,7 +1403,7 @@ err: static void execlists_context_unpin(struct intel_engine_cs *engine, struct i915_gem_context *ctx) { - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = to_intel_context(ctx, engine); lockdep_assert_held(&ctx->i915->drm.struct_mutex); GEM_BUG_ON(ce->pin_count == 0); @@ -1372,8 +1422,8 @@ static void execlists_context_unpin(struct intel_engine_cs *engine, static int execlists_request_alloc(struct i915_request *request) { - struct intel_engine_cs *engine = request->engine; - struct intel_context *ce = &request->ctx->engine[engine->id]; + struct intel_context *ce = + to_intel_context(request->ctx, request->engine); int ret; GEM_BUG_ON(!ce->pin_count); @@ -1633,6 +1683,8 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine) return -EINVAL; switch (INTEL_GEN(engine->i915)) { + case 11: + return 0; case 10: wa_bb_fn[0] = gen10_init_indirectctx_bb; wa_bb_fn[1] = NULL; @@ -1744,9 +1796,7 @@ static int gen8_init_render_ring(struct intel_engine_cs *engine) if (ret) return ret; - ret = intel_whitelist_workarounds_apply(engine); - if (ret) - return ret; + intel_whitelist_workarounds_apply(engine); /* We need to disable the AsyncFlip performance optimisations in order * to use MI_WAIT_FOR_EVENT within the CS. It should already be @@ -1769,9 +1819,7 @@ static int gen9_init_render_ring(struct intel_engine_cs *engine) if (ret) return ret; - ret = intel_whitelist_workarounds_apply(engine); - if (ret) - return ret; + intel_whitelist_workarounds_apply(engine); return 0; } @@ -1780,8 +1828,8 @@ static void reset_common_ring(struct intel_engine_cs *engine, struct i915_request *request) { struct intel_engine_execlists * const execlists = &engine->execlists; - struct intel_context *ce; unsigned long flags; + u32 *regs; GEM_TRACE("%s request global=%x, current=%d\n", engine->name, request ? request->global_seqno : 0, @@ -1803,9 +1851,9 @@ static void reset_common_ring(struct intel_engine_cs *engine, reset_irq(engine); /* Push back any incomplete requests for replay after the reset. */ - spin_lock(&engine->timeline->lock); + spin_lock(&engine->timeline.lock); __unwind_incomplete_requests(engine); - spin_unlock(&engine->timeline->lock); + spin_unlock(&engine->timeline.lock); local_irq_restore(flags); @@ -1831,14 +1879,24 @@ static void reset_common_ring(struct intel_engine_cs *engine, * future request will be after userspace has had the opportunity * to recreate its own state. */ - ce = &request->ctx->engine[engine->id]; - execlists_init_reg_state(ce->lrc_reg_state, - request->ctx, engine, ce->ring); + regs = to_intel_context(request->ctx, engine)->lrc_reg_state; + if (engine->default_state) { + void *defaults; + + defaults = i915_gem_object_pin_map(engine->default_state, + I915_MAP_WB); + if (!IS_ERR(defaults)) { + memcpy(regs, /* skip restoring the vanilla PPHWSP */ + defaults + LRC_STATE_PN * PAGE_SIZE, + engine->context_size - PAGE_SIZE); + i915_gem_object_unpin_map(engine->default_state); + } + } + execlists_init_reg_state(regs, request->ctx, engine, request->ring); /* Move the RING_HEAD onto the breadcrumb, past the hanging batch */ - ce->lrc_reg_state[CTX_RING_BUFFER_START+1] = - i915_ggtt_offset(ce->ring->vma); - ce->lrc_reg_state[CTX_RING_HEAD+1] = request->postfix; + regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(request->ring->vma); + regs[CTX_RING_HEAD + 1] = request->postfix; request->ring->head = request->postfix; intel_ring_update_space(request->ring); @@ -1899,7 +1957,7 @@ static int gen8_emit_bb_start(struct i915_request *rq, rq->ctx->ppgtt->pd_dirty_rings &= ~intel_engine_flag(rq->engine); } - cs = intel_ring_begin(rq, 4); + cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) return PTR_ERR(cs); @@ -1928,6 +1986,9 @@ static int gen8_emit_bb_start(struct i915_request *rq, (flags & I915_DISPATCH_RS ? MI_BATCH_RESOURCE_STREAMER : 0); *cs++ = lower_32_bits(offset); *cs++ = upper_32_bits(offset); + + *cs++ = MI_ARB_ON_OFF | MI_ARB_DISABLE; + *cs++ = MI_NOOP; intel_ring_advance(rq, cs); return 0; @@ -2070,7 +2131,7 @@ static void gen8_emit_breadcrumb(struct i915_request *request, u32 *cs) cs = gen8_emit_ggtt_write(cs, request->global_seqno, intel_hws_seqno_address(request->engine)); *cs++ = MI_USER_INTERRUPT; - *cs++ = MI_NOOP; + *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; request->tail = intel_ring_offset(request, cs); assert_ring_tail_valid(request->ring, request->tail); @@ -2086,7 +2147,7 @@ static void gen8_emit_breadcrumb_rcs(struct i915_request *request, u32 *cs) cs = gen8_emit_ggtt_write_rcs(cs, request->global_seqno, intel_hws_seqno_address(request->engine)); *cs++ = MI_USER_INTERRUPT; - *cs++ = MI_NOOP; + *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; request->tail = intel_ring_offset(request, cs); assert_ring_tail_valid(request->ring, request->tail); @@ -2272,9 +2333,13 @@ static int logical_ring_init(struct intel_engine_cs *engine) } engine->execlists.preempt_complete_status = ~0u; - if (engine->i915->preempt_context) + if (engine->i915->preempt_context) { + struct intel_context *ce = + to_intel_context(engine->i915->preempt_context, engine); + engine->execlists.preempt_complete_status = - upper_32_bits(engine->i915->preempt_context->engine[engine->id].lrc_desc); + upper_32_bits(ce->lrc_desc); + } return 0; @@ -2528,8 +2593,10 @@ populate_lr_context(struct i915_gem_context *ctx, defaults = i915_gem_object_pin_map(engine->default_state, I915_MAP_WB); - if (IS_ERR(defaults)) - return PTR_ERR(defaults); + if (IS_ERR(defaults)) { + ret = PTR_ERR(defaults); + goto err_unpin_ctx; + } memcpy(vaddr + start, defaults + start, engine->context_size); i915_gem_object_unpin_map(engine->default_state); @@ -2547,19 +2614,20 @@ populate_lr_context(struct i915_gem_context *ctx, _MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT | CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT); +err_unpin_ctx: i915_gem_object_unpin_map(ctx_obj); - - return 0; + return ret; } static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, struct intel_engine_cs *engine) { struct drm_i915_gem_object *ctx_obj; - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = to_intel_context(ctx, engine); struct i915_vma *vma; uint32_t context_size; struct intel_ring *ring; + struct i915_timeline *timeline; int ret; if (ce->state) @@ -2575,8 +2643,8 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, ctx_obj = i915_gem_object_create(ctx->i915, context_size); if (IS_ERR(ctx_obj)) { - DRM_DEBUG_DRIVER("Alloc LRC backing obj failed.\n"); - return PTR_ERR(ctx_obj); + ret = PTR_ERR(ctx_obj); + goto error_deref_obj; } vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.base, NULL); @@ -2585,7 +2653,14 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, goto error_deref_obj; } - ring = intel_engine_create_ring(engine, ctx->ring_size); + timeline = i915_timeline_create(ctx->i915, ctx->name); + if (IS_ERR(timeline)) { + ret = PTR_ERR(timeline); + goto error_deref_obj; + } + + ring = intel_engine_create_ring(engine, timeline, ctx->ring_size); + i915_timeline_put(timeline); if (IS_ERR(ring)) { ret = PTR_ERR(ring); goto error_deref_obj; @@ -2627,7 +2702,8 @@ void intel_lr_context_resume(struct drm_i915_private *dev_priv) */ list_for_each_entry(ctx, &dev_priv->contexts.list, link) { for_each_engine(engine, dev_priv, id) { - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = + to_intel_context(ctx, engine); u32 *reg; if (!ce->state) diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h index 59d7b86..4ec7d8d 100644 --- a/drivers/gpu/drm/i915/intel_lrc.h +++ b/drivers/gpu/drm/i915/intel_lrc.h @@ -108,7 +108,7 @@ static inline uint64_t intel_lr_context_descriptor(struct i915_gem_context *ctx, struct intel_engine_cs *engine) { - return ctx->engine[engine->id].lrc_desc; + return to_intel_context(ctx, engine)->lrc_desc; } #endif /* _INTEL_LRC_H_ */ diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index d35d2d5..8691c86 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -326,7 +326,8 @@ static void intel_enable_lvds(struct intel_encoder *encoder, I915_WRITE(PP_CONTROL(0), I915_READ(PP_CONTROL(0)) | PANEL_POWER_ON); POSTING_READ(lvds_encoder->reg); - if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 1000)) + + if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 5000)) DRM_ERROR("timed out waiting for panel to power on\n"); intel_panel_enable_backlight(pipe_config, conn_state); diff --git a/drivers/gpu/drm/i915/intel_mocs.c b/drivers/gpu/drm/i915/intel_mocs.c index c0b34b7..9f0bd6a4 100644 --- a/drivers/gpu/drm/i915/intel_mocs.c +++ b/drivers/gpu/drm/i915/intel_mocs.c @@ -178,7 +178,8 @@ static bool get_mocs_settings(struct drm_i915_private *dev_priv, { bool result = false; - if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) { + if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv) || + IS_ICELAKE(dev_priv)) { table->size = ARRAY_SIZE(skylake_mocs_table); table->table = skylake_mocs_table; result = true; @@ -217,6 +218,8 @@ static i915_reg_t mocs_register(enum intel_engine_id engine_id, int index) return GEN9_VEBOX_MOCS(index); case VCS2: return GEN9_MFX1_MOCS(index); + case VCS3: + return GEN11_MFX2_MOCS(index); default: MISSING_CASE(engine_id); return INVALID_MMIO_REG; diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c index 4f367c1..39a4e4e 100644 --- a/drivers/gpu/drm/i915/intel_pipe_crc.c +++ b/drivers/gpu/drm/i915/intel_pipe_crc.c @@ -766,13 +766,12 @@ display_crc_ctl_parse_object(const char *buf, enum intel_pipe_crc_object *o) { int i; - for (i = 0; i < ARRAY_SIZE(pipe_crc_objects); i++) - if (!strcmp(buf, pipe_crc_objects[i])) { - *o = i; - return 0; - } + i = match_string(pipe_crc_objects, ARRAY_SIZE(pipe_crc_objects), buf); + if (i < 0) + return i; - return -EINVAL; + *o = i; + return 0; } static int display_crc_ctl_parse_pipe(struct drm_i915_private *dev_priv, @@ -798,13 +797,12 @@ display_crc_ctl_parse_source(const char *buf, enum intel_pipe_crc_source *s) return 0; } - for (i = 0; i < ARRAY_SIZE(pipe_crc_sources); i++) - if (!strcmp(buf, pipe_crc_sources[i])) { - *s = i; - return 0; - } + i = match_string(pipe_crc_sources, ARRAY_SIZE(pipe_crc_sources), buf); + if (i < 0) + return i; - return -EINVAL; + *s = i; + return 0; } static int display_crc_ctl_parse(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 4baab85..b85229e 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3567,6 +3567,23 @@ bool ilk_disable_lp_wm(struct drm_device *dev) return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL); } +static u8 intel_enabled_dbuf_slices_num(struct drm_i915_private *dev_priv) +{ + u8 enabled_slices; + + /* Slice 1 will always be enabled */ + enabled_slices = 1; + + /* Gen prior to GEN11 have only one DBuf slice */ + if (INTEL_GEN(dev_priv) < 11) + return enabled_slices; + + if (I915_READ(DBUF_CTL_S2) & DBUF_POWER_STATE) + enabled_slices++; + + return enabled_slices; +} + /* * FIXME: We still don't have the proper code detect if we need to apply the WA, * so assume we'll always need it in order to avoid underruns. @@ -3754,9 +3771,42 @@ bool intel_can_enable_sagv(struct drm_atomic_state *state) return true; } +static unsigned int intel_get_ddb_size(struct drm_i915_private *dev_priv, + const struct intel_crtc_state *cstate, + const unsigned int total_data_rate, + const int num_active, + struct skl_ddb_allocation *ddb) +{ + const struct drm_display_mode *adjusted_mode; + u64 total_data_bw; + u16 ddb_size = INTEL_INFO(dev_priv)->ddb_size; + + WARN_ON(ddb_size == 0); + + if (INTEL_GEN(dev_priv) < 11) + return ddb_size - 4; /* 4 blocks for bypass path allocation */ + + adjusted_mode = &cstate->base.adjusted_mode; + total_data_bw = (u64)total_data_rate * drm_mode_vrefresh(adjusted_mode); + + /* + * 12GB/s is maximum BW supported by single DBuf slice. + */ + if (total_data_bw >= GBps(12) || num_active > 1) { + ddb->enabled_slices = 2; + } else { + ddb->enabled_slices = 1; + ddb_size /= 2; + } + + return ddb_size; +} + static void skl_ddb_get_pipe_allocation_limits(struct drm_device *dev, const struct intel_crtc_state *cstate, + const unsigned int total_data_rate, + struct skl_ddb_allocation *ddb, struct skl_ddb_entry *alloc, /* out */ int *num_active /* out */) { @@ -3779,11 +3829,8 @@ skl_ddb_get_pipe_allocation_limits(struct drm_device *dev, else *num_active = hweight32(dev_priv->active_crtcs); - ddb_size = INTEL_INFO(dev_priv)->ddb_size; - WARN_ON(ddb_size == 0); - - if (INTEL_GEN(dev_priv) < 11) - ddb_size -= 4; /* 4 blocks for bypass path allocation */ + ddb_size = intel_get_ddb_size(dev_priv, cstate, total_data_rate, + *num_active, ddb); /* * If the state doesn't change the active CRTC's, then there's @@ -3817,10 +3864,18 @@ static unsigned int skl_cursor_allocation(int num_active) return 8; } -static void skl_ddb_entry_init_from_hw(struct skl_ddb_entry *entry, u32 reg) +static void skl_ddb_entry_init_from_hw(struct drm_i915_private *dev_priv, + struct skl_ddb_entry *entry, u32 reg) { - entry->start = reg & 0x3ff; - entry->end = (reg >> 16) & 0x3ff; + u16 mask; + + if (INTEL_GEN(dev_priv) >= 11) + mask = ICL_DDB_ENTRY_MASK; + else + mask = SKL_DDB_ENTRY_MASK; + entry->start = reg & mask; + entry->end = (reg >> DDB_ENTRY_END_SHIFT) & mask; + if (entry->end) entry->end += 1; } @@ -3837,7 +3892,8 @@ skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv, /* Cursor doesn't support NV12/planar, so no extra calculation needed */ if (plane_id == PLANE_CURSOR) { val = I915_READ(CUR_BUF_CFG(pipe)); - skl_ddb_entry_init_from_hw(&ddb->plane[pipe][plane_id], val); + skl_ddb_entry_init_from_hw(dev_priv, + &ddb->plane[pipe][plane_id], val); return; } @@ -3856,10 +3912,13 @@ skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv, val2 = I915_READ(PLANE_NV12_BUF_CFG(pipe, plane_id)); if (fourcc == DRM_FORMAT_NV12) { - skl_ddb_entry_init_from_hw(&ddb->plane[pipe][plane_id], val2); - skl_ddb_entry_init_from_hw(&ddb->uv_plane[pipe][plane_id], val); + skl_ddb_entry_init_from_hw(dev_priv, + &ddb->plane[pipe][plane_id], val2); + skl_ddb_entry_init_from_hw(dev_priv, + &ddb->uv_plane[pipe][plane_id], val); } else { - skl_ddb_entry_init_from_hw(&ddb->plane[pipe][plane_id], val); + skl_ddb_entry_init_from_hw(dev_priv, + &ddb->plane[pipe][plane_id], val); } } @@ -3870,6 +3929,8 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, memset(ddb, 0, sizeof(*ddb)); + ddb->enabled_slices = intel_enabled_dbuf_slices_num(dev_priv); + for_each_intel_crtc(&dev_priv->drm, crtc) { enum intel_display_power_domain power_domain; enum plane_id plane_id; @@ -4242,7 +4303,11 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, return 0; } - skl_ddb_get_pipe_allocation_limits(dev, cstate, alloc, &num_active); + total_data_rate = skl_get_total_relative_data_rate(cstate, + plane_data_rate, + uv_plane_data_rate); + skl_ddb_get_pipe_allocation_limits(dev, cstate, total_data_rate, ddb, + alloc, &num_active); alloc_size = skl_ddb_entry_size(alloc); if (alloc_size == 0) return 0; @@ -4277,9 +4342,6 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, * * FIXME: we may not allocate every single block here. */ - total_data_rate = skl_get_total_relative_data_rate(cstate, - plane_data_rate, - uv_plane_data_rate); if (total_data_rate == 0) return 0; @@ -5088,6 +5150,7 @@ skl_copy_ddb_for_pipe(struct skl_ddb_values *dst, sizeof(dst->ddb.uv_plane[pipe])); memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe], sizeof(dst->ddb.plane[pipe])); + dst->ddb.enabled_slices = src->ddb.enabled_slices; } static void @@ -5472,8 +5535,12 @@ void skl_wm_get_hw_state(struct drm_device *dev) /* Fully recompute DDB on first atomic commit */ dev_priv->wm.distrust_bios_wm = true; } else { - /* Easy/common case; just sanitize DDB now if everything off */ - memset(ddb, 0, sizeof(*ddb)); + /* + * Easy/common case; just sanitize DDB now if everything off + * Keep dbuf slice info intact + */ + memset(ddb->plane, 0, sizeof(ddb->plane)); + memset(ddb->uv_plane, 0, sizeof(ddb->uv_plane)); } } @@ -8597,6 +8664,13 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv, I915_WRITE(GEN7_MISCCPCTL, misccpctl); } +static void icl_init_clock_gating(struct drm_i915_private *dev_priv) +{ + /* This is not an Wa. Enable to reduce Sampler power */ + I915_WRITE(GEN10_DFR_RATIO_EN_AND_CHICKEN, + I915_READ(GEN10_DFR_RATIO_EN_AND_CHICKEN) & ~DFR_DISABLE); +} + static void cnp_init_clock_gating(struct drm_i915_private *dev_priv) { if (!HAS_PCH_CNP(dev_priv)) @@ -9123,7 +9197,9 @@ static void nop_init_clock_gating(struct drm_i915_private *dev_priv) */ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) { - if (IS_CANNONLAKE(dev_priv)) + if (IS_ICELAKE(dev_priv)) + dev_priv->display.init_clock_gating = icl_init_clock_gating; + else if (IS_CANNONLAKE(dev_priv)) dev_priv->display.init_clock_gating = cnl_init_clock_gating; else if (IS_COFFEELAKE(dev_priv)) dev_priv->display.init_clock_gating = cfl_init_clock_gating; diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c index 69a5b27..db27f2f 100644 --- a/drivers/gpu/drm/i915/intel_psr.c +++ b/drivers/gpu/drm/i915/intel_psr.c @@ -93,6 +93,114 @@ static void psr_aux_io_power_put(struct intel_dp *intel_dp) intel_display_power_put(dev_priv, psr_aux_domain(intel_dp)); } +void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug) +{ + u32 debug_mask, mask; + + /* No PSR interrupts on VLV/CHV */ + if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + return; + + mask = EDP_PSR_ERROR(TRANSCODER_EDP); + debug_mask = EDP_PSR_POST_EXIT(TRANSCODER_EDP) | + EDP_PSR_PRE_ENTRY(TRANSCODER_EDP); + + if (INTEL_GEN(dev_priv) >= 8) { + mask |= EDP_PSR_ERROR(TRANSCODER_A) | + EDP_PSR_ERROR(TRANSCODER_B) | + EDP_PSR_ERROR(TRANSCODER_C); + + debug_mask |= EDP_PSR_POST_EXIT(TRANSCODER_A) | + EDP_PSR_PRE_ENTRY(TRANSCODER_A) | + EDP_PSR_POST_EXIT(TRANSCODER_B) | + EDP_PSR_PRE_ENTRY(TRANSCODER_B) | + EDP_PSR_POST_EXIT(TRANSCODER_C) | + EDP_PSR_PRE_ENTRY(TRANSCODER_C); + } + + if (debug) + mask |= debug_mask; + + WRITE_ONCE(dev_priv->psr.debug, debug); + I915_WRITE(EDP_PSR_IMR, ~mask); +} + +static void psr_event_print(u32 val, bool psr2_enabled) +{ + DRM_DEBUG_KMS("PSR exit events: 0x%x\n", val); + if (val & PSR_EVENT_PSR2_WD_TIMER_EXPIRE) + DRM_DEBUG_KMS("\tPSR2 watchdog timer expired\n"); + if ((val & PSR_EVENT_PSR2_DISABLED) && psr2_enabled) + DRM_DEBUG_KMS("\tPSR2 disabled\n"); + if (val & PSR_EVENT_SU_DIRTY_FIFO_UNDERRUN) + DRM_DEBUG_KMS("\tSU dirty FIFO underrun\n"); + if (val & PSR_EVENT_SU_CRC_FIFO_UNDERRUN) + DRM_DEBUG_KMS("\tSU CRC FIFO underrun\n"); + if (val & PSR_EVENT_GRAPHICS_RESET) + DRM_DEBUG_KMS("\tGraphics reset\n"); + if (val & PSR_EVENT_PCH_INTERRUPT) + DRM_DEBUG_KMS("\tPCH interrupt\n"); + if (val & PSR_EVENT_MEMORY_UP) + DRM_DEBUG_KMS("\tMemory up\n"); + if (val & PSR_EVENT_FRONT_BUFFER_MODIFY) + DRM_DEBUG_KMS("\tFront buffer modification\n"); + if (val & PSR_EVENT_WD_TIMER_EXPIRE) + DRM_DEBUG_KMS("\tPSR watchdog timer expired\n"); + if (val & PSR_EVENT_PIPE_REGISTERS_UPDATE) + DRM_DEBUG_KMS("\tPIPE registers updated\n"); + if (val & PSR_EVENT_REGISTER_UPDATE) + DRM_DEBUG_KMS("\tRegister updated\n"); + if (val & PSR_EVENT_HDCP_ENABLE) + DRM_DEBUG_KMS("\tHDCP enabled\n"); + if (val & PSR_EVENT_KVMR_SESSION_ENABLE) + DRM_DEBUG_KMS("\tKVMR session enabled\n"); + if (val & PSR_EVENT_VBI_ENABLE) + DRM_DEBUG_KMS("\tVBI enabled\n"); + if (val & PSR_EVENT_LPSP_MODE_EXIT) + DRM_DEBUG_KMS("\tLPSP mode exited\n"); + if ((val & PSR_EVENT_PSR_DISABLE) && !psr2_enabled) + DRM_DEBUG_KMS("\tPSR disabled\n"); +} + +void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir) +{ + u32 transcoders = BIT(TRANSCODER_EDP); + enum transcoder cpu_transcoder; + ktime_t time_ns = ktime_get(); + + if (INTEL_GEN(dev_priv) >= 8) + transcoders |= BIT(TRANSCODER_A) | + BIT(TRANSCODER_B) | + BIT(TRANSCODER_C); + + for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, transcoders) { + /* FIXME: Exit PSR and link train manually when this happens. */ + if (psr_iir & EDP_PSR_ERROR(cpu_transcoder)) + DRM_DEBUG_KMS("[transcoder %s] PSR aux error\n", + transcoder_name(cpu_transcoder)); + + if (psr_iir & EDP_PSR_PRE_ENTRY(cpu_transcoder)) { + dev_priv->psr.last_entry_attempt = time_ns; + DRM_DEBUG_KMS("[transcoder %s] PSR entry attempt in 2 vblanks\n", + transcoder_name(cpu_transcoder)); + } + + if (psr_iir & EDP_PSR_POST_EXIT(cpu_transcoder)) { + dev_priv->psr.last_exit = time_ns; + DRM_DEBUG_KMS("[transcoder %s] PSR exit completed\n", + transcoder_name(cpu_transcoder)); + + if (INTEL_GEN(dev_priv) >= 9) { + u32 val = I915_READ(PSR_EVENT(cpu_transcoder)); + bool psr2_enabled = dev_priv->psr.psr2_enabled; + + I915_WRITE(PSR_EVENT(cpu_transcoder), val); + psr_event_print(val, psr2_enabled); + } + } + } +} + static bool intel_dp_get_y_coord_required(struct intel_dp *intel_dp) { uint8_t psr_caps = 0; @@ -400,9 +508,8 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) * mesh at all with our frontbuffer tracking. And the hw alone isn't * good enough. */ val |= EDP_PSR2_ENABLE | EDP_SU_TRACK_ENABLE; - if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) { - val |= EDP_Y_COORDINATE_VALID | EDP_Y_COORDINATE_ENABLE; - } + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) + val |= EDP_Y_COORDINATE_ENABLE; val |= EDP_PSR2_FRAME_BEFORE_SU(dev_priv->psr.sink_sync_latency + 1); @@ -604,7 +711,8 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp, I915_WRITE(EDP_PSR_DEBUG, EDP_PSR_DEBUG_MASK_MEMUP | EDP_PSR_DEBUG_MASK_HPD | - EDP_PSR_DEBUG_MASK_LPSP); + EDP_PSR_DEBUG_MASK_LPSP | + EDP_PSR_DEBUG_MASK_DISP_REG_WRITE); } } @@ -1065,9 +1173,12 @@ void intel_psr_init(struct drm_i915_private *dev_priv) if (!dev_priv->psr.sink_support) return; - /* Per platform default: all disabled. */ - if (i915_modparams.enable_psr == -1) + if (i915_modparams.enable_psr == -1) { + i915_modparams.enable_psr = dev_priv->vbt.psr.enable; + + /* Per platform default: all disabled. */ i915_modparams.enable_psr = 0; + } /* Set link_standby x link_off defaults */ if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 757bb09..8f19349 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -558,7 +558,8 @@ static void reset_ring_common(struct intel_engine_cs *engine, */ if (request) { struct drm_i915_private *dev_priv = request->i915; - struct intel_context *ce = &request->ctx->engine[engine->id]; + struct intel_context *ce = to_intel_context(request->ctx, + engine); struct i915_hw_ppgtt *ppgtt; if (ce->state) { @@ -618,9 +619,7 @@ static int init_render_ring(struct intel_engine_cs *engine) if (ret) return ret; - ret = intel_whitelist_workarounds_apply(engine); - if (ret) - return ret; + intel_whitelist_workarounds_apply(engine); /* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */ if (IS_GEN(dev_priv, 4, 6)) @@ -698,17 +697,17 @@ static void cancel_requests(struct intel_engine_cs *engine) struct i915_request *request; unsigned long flags; - spin_lock_irqsave(&engine->timeline->lock, flags); + spin_lock_irqsave(&engine->timeline.lock, flags); /* Mark all submitted requests as skipped. */ - list_for_each_entry(request, &engine->timeline->requests, link) { + list_for_each_entry(request, &engine->timeline.requests, link) { GEM_BUG_ON(!request->global_seqno); if (!i915_request_completed(request)) dma_fence_set_error(&request->fence, -EIO); } /* Remaining _unready_ requests will be nop'ed when submitted */ - spin_unlock_irqrestore(&engine->timeline->lock, flags); + spin_unlock_irqrestore(&engine->timeline.lock, flags); } static void i9xx_submit_request(struct i915_request *request) @@ -1067,7 +1066,6 @@ err: void intel_ring_reset(struct intel_ring *ring, u32 tail) { - GEM_BUG_ON(!list_empty(&ring->request_list)); ring->tail = tail; ring->head = tail; ring->emit = tail; @@ -1119,19 +1117,24 @@ err: } struct intel_ring * -intel_engine_create_ring(struct intel_engine_cs *engine, int size) +intel_engine_create_ring(struct intel_engine_cs *engine, + struct i915_timeline *timeline, + int size) { struct intel_ring *ring; struct i915_vma *vma; GEM_BUG_ON(!is_power_of_2(size)); GEM_BUG_ON(RING_CTL_SIZE(size) & ~RING_NR_PAGES); + GEM_BUG_ON(timeline == &engine->timeline); + lockdep_assert_held(&engine->i915->drm.struct_mutex); ring = kzalloc(sizeof(*ring), GFP_KERNEL); if (!ring) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&ring->request_list); + ring->timeline = i915_timeline_get(timeline); ring->size = size; /* Workaround an erratum on the i830 which causes a hang if @@ -1162,12 +1165,13 @@ intel_ring_free(struct intel_ring *ring) i915_vma_close(ring->vma); __i915_gem_object_release_unless_active(obj); + i915_timeline_put(ring->timeline); kfree(ring); } -static int context_pin(struct i915_gem_context *ctx) +static int context_pin(struct intel_context *ce) { - struct i915_vma *vma = ctx->engine[RCS].state; + struct i915_vma *vma = ce->state; int ret; /* @@ -1258,7 +1262,7 @@ static struct intel_ring * intel_ring_context_pin(struct intel_engine_cs *engine, struct i915_gem_context *ctx) { - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = to_intel_context(ctx, engine); int ret; lockdep_assert_held(&ctx->i915->drm.struct_mutex); @@ -1280,7 +1284,7 @@ intel_ring_context_pin(struct intel_engine_cs *engine, } if (ce->state) { - ret = context_pin(ctx); + ret = context_pin(ce); if (ret) goto err; @@ -1301,7 +1305,7 @@ err: static void intel_ring_context_unpin(struct intel_engine_cs *engine, struct i915_gem_context *ctx) { - struct intel_context *ce = &ctx->engine[engine->id]; + struct intel_context *ce = to_intel_context(ctx, engine); lockdep_assert_held(&ctx->i915->drm.struct_mutex); GEM_BUG_ON(ce->pin_count == 0); @@ -1320,6 +1324,7 @@ static void intel_ring_context_unpin(struct intel_engine_cs *engine, static int intel_init_ring_buffer(struct intel_engine_cs *engine) { struct intel_ring *ring; + struct i915_timeline *timeline; int err; intel_engine_setup_common(engine); @@ -1328,7 +1333,14 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) if (err) goto err; - ring = intel_engine_create_ring(engine, 32 * PAGE_SIZE); + timeline = i915_timeline_create(engine->i915, engine->name); + if (IS_ERR(timeline)) { + err = PTR_ERR(timeline); + goto err; + } + + ring = intel_engine_create_ring(engine, timeline, 32 * PAGE_SIZE); + i915_timeline_put(timeline); if (IS_ERR(ring)) { err = PTR_ERR(ring); goto err; @@ -1429,7 +1441,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) *cs++ = MI_NOOP; *cs++ = MI_SET_CONTEXT; - *cs++ = i915_ggtt_offset(rq->ctx->engine[RCS].state) | flags; + *cs++ = i915_ggtt_offset(to_intel_context(rq->ctx, engine)->state) | flags; /* * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP * WaMiSetContext_Hang:snb,ivb,vlv @@ -1520,7 +1532,7 @@ static int switch_context(struct i915_request *rq) hw_flags = MI_FORCE_RESTORE; } - if (to_ctx->engine[engine->id].state && + if (to_intel_context(to_ctx, engine)->state && (to_ctx != from_ctx || hw_flags & MI_FORCE_RESTORE)) { GEM_BUG_ON(engine->id != RCS); @@ -1568,7 +1580,7 @@ static int ring_request_alloc(struct i915_request *request) { int ret; - GEM_BUG_ON(!request->ctx->engine[request->engine->id].pin_count); + GEM_BUG_ON(!to_intel_context(request->ctx, request->engine)->pin_count); /* Flush enough space to reduce the likelihood of waiting after * we start building the request - in which case we will just @@ -1719,22 +1731,24 @@ u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords) /* Align the ring tail to a cacheline boundary */ int intel_ring_cacheline_align(struct i915_request *rq) { - int num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32); - u32 *cs; + int num_dwords; + void *cs; + num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32); if (num_dwords == 0) return 0; - num_dwords = CACHELINE_BYTES / sizeof(u32) - num_dwords; + num_dwords = CACHELINE_DWORDS - num_dwords; + GEM_BUG_ON(num_dwords & 1); + cs = intel_ring_begin(rq, num_dwords); if (IS_ERR(cs)) return PTR_ERR(cs); - while (num_dwords--) - *cs++ = MI_NOOP; - + memset64(cs, (u64)MI_NOOP << 32 | MI_NOOP, num_dwords / 2); intel_ring_advance(rq, cs); + GEM_BUG_ON(rq->ring->emit & (CACHELINE_BYTES - 1)); return 0; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 7170416..010750e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -3,17 +3,19 @@ #define _INTEL_RINGBUFFER_H_ #include <linux/hashtable.h> +#include <linux/seqlock.h> #include "i915_gem_batch_pool.h" -#include "i915_gem_timeline.h" #include "i915_reg.h" #include "i915_pmu.h" #include "i915_request.h" #include "i915_selftest.h" +#include "i915_timeline.h" #include "intel_gpu_commands.h" struct drm_printer; +struct i915_sched_attr; #define I915_CMD_HASH_ORDER 9 @@ -127,7 +129,9 @@ struct intel_ring { struct i915_vma *vma; void *vaddr; + struct i915_timeline *timeline; struct list_head request_list; + struct list_head active_link; u32 head; u32 tail; @@ -334,7 +338,8 @@ struct intel_engine_cs { u32 mmio_base; struct intel_ring *buffer; - struct intel_timeline *timeline; + + struct i915_timeline timeline; struct drm_i915_gem_object *default_state; @@ -460,7 +465,8 @@ struct intel_engine_cs { * * Called under the struct_mutex. */ - void (*schedule)(struct i915_request *request, int priority); + void (*schedule)(struct i915_request *request, + const struct i915_sched_attr *attr); /* * Cancel all requests on the hardware, or queued for execution. @@ -593,7 +599,7 @@ struct intel_engine_cs { /** * @lock: Lock protecting the below fields. */ - spinlock_t lock; + seqlock_t lock; /** * @enabled: Reference count indicating number of listeners. */ @@ -764,7 +770,9 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value) #define CNL_HWS_CSB_WRITE_INDEX 0x2f struct intel_ring * -intel_engine_create_ring(struct intel_engine_cs *engine, int size); +intel_engine_create_ring(struct intel_engine_cs *engine, + struct i915_timeline *timeline, + int size); int intel_ring_pin(struct intel_ring *ring, struct drm_i915_private *i915, unsigned int offset_bias); @@ -882,7 +890,7 @@ static inline u32 intel_engine_last_submit(struct intel_engine_cs *engine) * wtih serialising this hint with anything, so document it as * a hint and nothing more. */ - return READ_ONCE(engine->timeline->seqno); + return READ_ONCE(engine->timeline.seqno); } void intel_engine_get_instdone(struct intel_engine_cs *engine, @@ -1062,7 +1070,7 @@ static inline void intel_engine_context_in(struct intel_engine_cs *engine) if (READ_ONCE(engine->stats.enabled) == 0) return; - spin_lock_irqsave(&engine->stats.lock, flags); + write_seqlock_irqsave(&engine->stats.lock, flags); if (engine->stats.enabled > 0) { if (engine->stats.active++ == 0) @@ -1070,7 +1078,7 @@ static inline void intel_engine_context_in(struct intel_engine_cs *engine) GEM_BUG_ON(engine->stats.active == 0); } - spin_unlock_irqrestore(&engine->stats.lock, flags); + write_sequnlock_irqrestore(&engine->stats.lock, flags); } static inline void intel_engine_context_out(struct intel_engine_cs *engine) @@ -1080,7 +1088,7 @@ static inline void intel_engine_context_out(struct intel_engine_cs *engine) if (READ_ONCE(engine->stats.enabled) == 0) return; - spin_lock_irqsave(&engine->stats.lock, flags); + write_seqlock_irqsave(&engine->stats.lock, flags); if (engine->stats.enabled > 0) { ktime_t last; @@ -1107,7 +1115,7 @@ static inline void intel_engine_context_out(struct intel_engine_cs *engine) } } - spin_unlock_irqrestore(&engine->stats.lock, flags); + write_sequnlock_irqrestore(&engine->stats.lock, flags); } int intel_enable_engine_stats(struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 53ea564..53a6eaa 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -542,6 +542,29 @@ void gen9_sanitize_dc_state(struct drm_i915_private *dev_priv) dev_priv->csr.dc_state = val; } +/** + * gen9_set_dc_state - set target display C power state + * @dev_priv: i915 device instance + * @state: target DC power state + * - DC_STATE_DISABLE + * - DC_STATE_EN_UPTO_DC5 + * - DC_STATE_EN_UPTO_DC6 + * - DC_STATE_EN_DC9 + * + * Signal to DMC firmware/HW the target DC power state passed in @state. + * DMC/HW can turn off individual display clocks and power rails when entering + * a deeper DC power state (higher in number) and turns these back when exiting + * that state to a shallower power state (lower in number). The HW will decide + * when to actually enter a given state on an on-demand basis, for instance + * depending on the active state of display pipes. The state of display + * registers backed by affected power rails are saved/restored as needed. + * + * Based on the above enabling a deeper DC power state is asynchronous wrt. + * enabling it. Disabling a deeper power state is synchronous: for instance + * setting %DC_STATE_DISABLE won't complete until all HW resources are turned + * back on and register state is restored. This is guaranteed by the MMIO write + * to DC_STATE_EN blocking until the state is restored. + */ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state) { uint32_t val; @@ -635,26 +658,18 @@ static void assert_can_enable_dc6(struct drm_i915_private *dev_priv) assert_csr_loaded(dev_priv); } -void skl_enable_dc6(struct drm_i915_private *dev_priv) +static void skl_enable_dc6(struct drm_i915_private *dev_priv) { assert_can_enable_dc6(dev_priv); DRM_DEBUG_KMS("Enabling DC6\n"); - gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6); - -} - -void skl_disable_dc6(struct drm_i915_private *dev_priv) -{ - DRM_DEBUG_KMS("Disabling DC6\n"); - /* Wa Display #1183: skl,kbl,cfl */ if (IS_GEN9_BC(dev_priv)) I915_WRITE(GEN8_CHICKEN_DCPR_1, I915_READ(GEN8_CHICKEN_DCPR_1) | SKL_SELECT_ALTERNATE_DC_EXIT); - gen9_set_dc_state(dev_priv, DC_STATE_DISABLE); + gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6); } static void hsw_power_well_sync_hw(struct drm_i915_private *dev_priv, @@ -2627,32 +2642,69 @@ static void intel_power_domains_sync_hw(struct drm_i915_private *dev_priv) mutex_unlock(&power_domains->lock); } -static void gen9_dbuf_enable(struct drm_i915_private *dev_priv) +static inline +bool intel_dbuf_slice_set(struct drm_i915_private *dev_priv, + i915_reg_t reg, bool enable) { - I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) | DBUF_POWER_REQUEST); - POSTING_READ(DBUF_CTL); + u32 val, status; + val = I915_READ(reg); + val = enable ? (val | DBUF_POWER_REQUEST) : (val & ~DBUF_POWER_REQUEST); + I915_WRITE(reg, val); + POSTING_READ(reg); udelay(10); - if (!(I915_READ(DBUF_CTL) & DBUF_POWER_STATE)) - DRM_ERROR("DBuf power enable timeout\n"); + status = I915_READ(reg) & DBUF_POWER_STATE; + if ((enable && !status) || (!enable && status)) { + DRM_ERROR("DBus power %s timeout!\n", + enable ? "enable" : "disable"); + return false; + } + return true; +} + +static void gen9_dbuf_enable(struct drm_i915_private *dev_priv) +{ + intel_dbuf_slice_set(dev_priv, DBUF_CTL, true); } static void gen9_dbuf_disable(struct drm_i915_private *dev_priv) { - I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) & ~DBUF_POWER_REQUEST); - POSTING_READ(DBUF_CTL); + intel_dbuf_slice_set(dev_priv, DBUF_CTL, false); +} - udelay(10); +static u8 intel_dbuf_max_slices(struct drm_i915_private *dev_priv) +{ + if (INTEL_GEN(dev_priv) < 11) + return 1; + return 2; +} - if (I915_READ(DBUF_CTL) & DBUF_POWER_STATE) - DRM_ERROR("DBuf power disable timeout!\n"); +void icl_dbuf_slices_update(struct drm_i915_private *dev_priv, + u8 req_slices) +{ + u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices; + u32 val; + bool ret; + + if (req_slices > intel_dbuf_max_slices(dev_priv)) { + DRM_ERROR("Invalid number of dbuf slices requested\n"); + return; + } + + if (req_slices == hw_enabled_slices || req_slices == 0) + return; + + val = I915_READ(DBUF_CTL_S2); + if (req_slices > hw_enabled_slices) + ret = intel_dbuf_slice_set(dev_priv, DBUF_CTL_S2, true); + else + ret = intel_dbuf_slice_set(dev_priv, DBUF_CTL_S2, false); + + if (ret) + dev_priv->wm.skl_hw.ddb.enabled_slices = req_slices; } -/* - * TODO: we shouldn't always enable DBUF_CTL_S2, we should only enable it when - * needed and keep it disabled as much as possible. - */ static void icl_dbuf_enable(struct drm_i915_private *dev_priv) { I915_WRITE(DBUF_CTL_S1, I915_READ(DBUF_CTL_S1) | DBUF_POWER_REQUEST); @@ -2664,6 +2716,8 @@ static void icl_dbuf_enable(struct drm_i915_private *dev_priv) if (!(I915_READ(DBUF_CTL_S1) & DBUF_POWER_STATE) || !(I915_READ(DBUF_CTL_S2) & DBUF_POWER_STATE)) DRM_ERROR("DBuf power enable timeout\n"); + else + dev_priv->wm.skl_hw.ddb.enabled_slices = 2; } static void icl_dbuf_disable(struct drm_i915_private *dev_priv) @@ -2677,6 +2731,8 @@ static void icl_dbuf_disable(struct drm_i915_private *dev_priv) if ((I915_READ(DBUF_CTL_S1) & DBUF_POWER_STATE) || (I915_READ(DBUF_CTL_S2) & DBUF_POWER_STATE)) DRM_ERROR("DBuf power disable timeout!\n"); + else + dev_priv->wm.skl_hw.ddb.enabled_slices = 0; } static void icl_mbus_init(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index aa1dfaa..1597938 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -131,7 +131,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state) if (scanline < min || scanline > max) break; - if (timeout <= 0) { + if (!timeout) { DRM_ERROR("Potential atomic update failure on pipe %c\n", pipe_name(crtc->pipe)); break; @@ -1060,7 +1060,8 @@ intel_check_sprite_plane(struct intel_plane *plane, src_y = src->y1 >> 16; src_h = drm_rect_height(src) >> 16; - if (intel_format_is_yuv(fb->format->format)) { + if (intel_format_is_yuv(fb->format->format) && + fb->format->format != DRM_FORMAT_NV12) { src_x &= ~1; src_w &= ~1; @@ -1253,6 +1254,19 @@ static uint32_t skl_plane_formats[] = { DRM_FORMAT_VYUY, }; +static uint32_t skl_planar_formats[] = { + DRM_FORMAT_RGB565, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_YUYV, + DRM_FORMAT_YVYU, + DRM_FORMAT_UYVY, + DRM_FORMAT_VYUY, + DRM_FORMAT_NV12, +}; + static const uint64_t skl_plane_format_modifiers_noccs[] = { I915_FORMAT_MOD_Yf_TILED, I915_FORMAT_MOD_Y_TILED, @@ -1347,6 +1361,7 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier) case DRM_FORMAT_YVYU: case DRM_FORMAT_UYVY: case DRM_FORMAT_VYUY: + case DRM_FORMAT_NV12: if (modifier == I915_FORMAT_MOD_Yf_TILED) return true; /* fall through */ @@ -1446,8 +1461,14 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv, intel_plane->disable_plane = skl_disable_plane; intel_plane->get_hw_state = skl_plane_get_hw_state; - plane_formats = skl_plane_formats; - num_plane_formats = ARRAY_SIZE(skl_plane_formats); + if (skl_plane_has_planar(dev_priv, pipe, + PLANE_SPRITE0 + plane)) { + plane_formats = skl_planar_formats; + num_plane_formats = ARRAY_SIZE(skl_planar_formats); + } else { + plane_formats = skl_plane_formats; + num_plane_formats = ARRAY_SIZE(skl_plane_formats); + } if (skl_plane_has_ccs(dev_priv, pipe, PLANE_SPRITE0 + plane)) modifiers = skl_plane_format_modifiers_ccs; diff --git a/drivers/gpu/drm/i915/intel_uc_fw.h b/drivers/gpu/drm/i915/intel_uc_fw.h index dc33b12..87910aa 100644 --- a/drivers/gpu/drm/i915/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/intel_uc_fw.h @@ -30,7 +30,7 @@ struct drm_i915_private; struct i915_vma; /* Home of GuC, HuC and DMC firmwares */ -#define INTEL_UC_FIRMWARE_URL "https://01.org/linuxgraphics/downloads/firmware" +#define INTEL_UC_FIRMWARE_URL "https://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git/tree/i915" enum intel_uc_fw_status { INTEL_UC_FIRMWARE_FAIL = -1, diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index d6e20f0..448293e 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -139,7 +139,9 @@ fw_domain_wait_ack_with_fallback(const struct drm_i915_private *i915, * in the hope that the original ack will be delivered along with * the fallback ack. * - * This workaround is described in HSDES #1604254524 + * This workaround is described in HSDES #1604254524 and it's known as: + * WaRsForcewakeAddDelayForAck:skl,bxt,kbl,glk,cfl,cnl,icl + * although the name is a bit misleading. */ pass = 1; @@ -1394,7 +1396,8 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) if (INTEL_GEN(dev_priv) >= 11) { int i; - dev_priv->uncore.funcs.force_wake_get = fw_domains_get; + dev_priv->uncore.funcs.force_wake_get = + fw_domains_get_with_fallback; dev_priv->uncore.funcs.force_wake_put = fw_domains_put; fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE_RENDER_GEN9, diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c index bbbf4ed..2df3538 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.c +++ b/drivers/gpu/drm/i915/intel_workarounds.c @@ -270,6 +270,10 @@ static int gen9_ctx_workarounds_init(struct drm_i915_private *dev_priv) GEN9_PREEMPT_GPGPU_LEVEL_MASK, GEN9_PREEMPT_GPGPU_COMMAND_LEVEL); + /* WaClearHIZ_WM_CHICKEN3:bxt,glk */ + if (IS_GEN9_LP(dev_priv)) + WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ); + return 0; } @@ -441,6 +445,27 @@ static int cnl_ctx_workarounds_init(struct drm_i915_private *dev_priv) return 0; } +static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv) +{ + /* Wa_1604370585:icl (pre-prod) + * Formerly known as WaPushConstantDereferenceHoldDisable + */ + if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_B0)) + WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, + PUSH_CONSTANT_DEREF_DISABLE); + + /* WaForceEnableNonCoherent:icl + * This is not the same workaround as in early Gen9 platforms, where + * lacking this could cause system hangs, but coherency performance + * overhead is high and only a few compute workloads really need it + * (the register is whitelisted in hardware now, so UMDs can opt in + * for coherency if they have a good reason). + */ + WA_SET_BIT_MASKED(ICL_HDC_MODE, HDC_FORCE_NON_COHERENT); + + return 0; +} + int intel_ctx_workarounds_init(struct drm_i915_private *dev_priv) { int err = 0; @@ -465,6 +490,8 @@ int intel_ctx_workarounds_init(struct drm_i915_private *dev_priv) err = cfl_ctx_workarounds_init(dev_priv); else if (IS_CANNONLAKE(dev_priv)) err = cnl_ctx_workarounds_init(dev_priv); + else if (IS_ICELAKE(dev_priv)) + err = icl_ctx_workarounds_init(dev_priv); else MISSING_CASE(INTEL_GEN(dev_priv)); if (err) @@ -663,6 +690,90 @@ static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv) _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); } +static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +{ + /* This is not an Wa. Enable for better image quality */ + I915_WRITE(_3D_CHICKEN3, + _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE)); + + /* WaInPlaceDecompressionHang:icl */ + I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + + /* WaPipelineFlushCoherentLines:icl */ + I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | + GEN8_LQSC_FLUSH_COHERENT_LINES); + + /* Wa_1405543622:icl + * Formerly known as WaGAPZPriorityScheme + */ + I915_WRITE(GEN8_GARBCNTL, I915_READ(GEN8_GARBCNTL) | + GEN11_ARBITRATION_PRIO_ORDER_MASK); + + /* Wa_1604223664:icl + * Formerly known as WaL3BankAddressHashing + */ + I915_WRITE(GEN8_GARBCNTL, + (I915_READ(GEN8_GARBCNTL) & ~GEN11_HASH_CTRL_EXCL_MASK) | + GEN11_HASH_CTRL_EXCL_BIT0); + I915_WRITE(GEN11_GLBLINVL, + (I915_READ(GEN11_GLBLINVL) & ~GEN11_BANK_HASH_ADDR_EXCL_MASK) | + GEN11_BANK_HASH_ADDR_EXCL_BIT0); + + /* WaModifyGamTlbPartitioning:icl */ + I915_WRITE(GEN11_GACB_PERF_CTRL, + (I915_READ(GEN11_GACB_PERF_CTRL) & ~GEN11_HASH_CTRL_MASK) | + GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4); + + /* Wa_1405733216:icl + * Formerly known as WaDisableCleanEvicts + */ + I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | + GEN11_LQSC_CLEAN_EVICT_DISABLE); + + /* Wa_1405766107:icl + * Formerly known as WaCL2SFHalfMaxAlloc + */ + I915_WRITE(GEN11_LSN_UNSLCVC, I915_READ(GEN11_LSN_UNSLCVC) | + GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC | + GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC); + + /* Wa_220166154:icl + * Formerly known as WaDisCtxReload + */ + I915_WRITE(GAMW_ECO_DEV_RW_IA_REG, I915_READ(GAMW_ECO_DEV_RW_IA_REG) | + GAMW_ECO_DEV_CTX_RELOAD_DISABLE); + + /* Wa_1405779004:icl (pre-prod) */ + if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0)) + I915_WRITE(SLICE_UNIT_LEVEL_CLKGATE, + I915_READ(SLICE_UNIT_LEVEL_CLKGATE) | + MSCUNIT_CLKGATE_DIS); + + /* Wa_1406680159:icl */ + I915_WRITE(SUBSLICE_UNIT_LEVEL_CLKGATE, + I915_READ(SUBSLICE_UNIT_LEVEL_CLKGATE) | + GWUNIT_CLKGATE_DIS); + + /* Wa_1604302699:icl */ + I915_WRITE(GEN10_L3_CHICKEN_MODE_REGISTER, + I915_READ(GEN10_L3_CHICKEN_MODE_REGISTER) | + GEN11_I2M_WRITE_DISABLE); + + /* Wa_1406838659:icl (pre-prod) */ + if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_B0)) + I915_WRITE(INF_UNIT_LEVEL_CLKGATE, + I915_READ(INF_UNIT_LEVEL_CLKGATE) | + CGPSF_CLKGATE_DIS); + + /* WaForwardProgressSoftReset:icl */ + I915_WRITE(GEN10_SCRATCH_LNCF2, + I915_READ(GEN10_SCRATCH_LNCF2) | + PMFLUSHDONE_LNICRSDROP | + PMFLUSH_GAPL3UNBLOCK | + PMFLUSHDONE_LNEBLK); +} + void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv) { if (INTEL_GEN(dev_priv) < 8) @@ -683,174 +794,156 @@ void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv) cfl_gt_workarounds_apply(dev_priv); else if (IS_CANNONLAKE(dev_priv)) cnl_gt_workarounds_apply(dev_priv); + else if (IS_ICELAKE(dev_priv)) + icl_gt_workarounds_apply(dev_priv); else MISSING_CASE(INTEL_GEN(dev_priv)); } -static int wa_ring_whitelist_reg(struct intel_engine_cs *engine, - i915_reg_t reg) -{ - struct drm_i915_private *dev_priv = engine->i915; - struct i915_workarounds *wa = &dev_priv->workarounds; - const unsigned int index = wa->hw_whitelist_count[engine->id]; +struct whitelist { + i915_reg_t reg[RING_MAX_NONPRIV_SLOTS]; + unsigned int count; + u32 nopid; +}; - if (WARN_ON(index >= RING_MAX_NONPRIV_SLOTS)) - return -EINVAL; - - I915_WRITE(RING_FORCE_TO_NONPRIV(engine->mmio_base, index), - i915_mmio_reg_offset(reg)); - wa->hw_whitelist_count[engine->id]++; +static void whitelist_reg(struct whitelist *w, i915_reg_t reg) +{ + if (GEM_WARN_ON(w->count >= RING_MAX_NONPRIV_SLOTS)) + return; - return 0; + w->reg[w->count++] = reg; } -static int bdw_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void bdw_whitelist_build(struct whitelist *w) { - return 0; } -static int chv_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void chv_whitelist_build(struct whitelist *w) { - return 0; } -static int gen9_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void gen9_whitelist_build(struct whitelist *w) { - int ret; - /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */ - ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG); - if (ret) - return ret; + whitelist_reg(w, GEN9_CTX_PREEMPT_REG); /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */ - ret = wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); - if (ret) - return ret; + whitelist_reg(w, GEN8_CS_CHICKEN1); /* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */ - ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1); - if (ret) - return ret; - - return 0; + whitelist_reg(w, GEN8_HDC_CHICKEN1); } -static int skl_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void skl_whitelist_build(struct whitelist *w) { - int ret; - - ret = gen9_whitelist_workarounds_apply(engine); - if (ret) - return ret; + gen9_whitelist_build(w); /* WaDisableLSQCROPERFforOCL:skl */ - ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); - if (ret) - return ret; - - return 0; + whitelist_reg(w, GEN8_L3SQCREG4); } -static int bxt_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void bxt_whitelist_build(struct whitelist *w) { - int ret; - - ret = gen9_whitelist_workarounds_apply(engine); - if (ret) - return ret; - - return 0; + gen9_whitelist_build(w); } -static int kbl_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void kbl_whitelist_build(struct whitelist *w) { - int ret; - - ret = gen9_whitelist_workarounds_apply(engine); - if (ret) - return ret; + gen9_whitelist_build(w); /* WaDisableLSQCROPERFforOCL:kbl */ - ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); - if (ret) - return ret; - - return 0; + whitelist_reg(w, GEN8_L3SQCREG4); } -static int glk_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void glk_whitelist_build(struct whitelist *w) { - int ret; - - ret = gen9_whitelist_workarounds_apply(engine); - if (ret) - return ret; + gen9_whitelist_build(w); /* WA #0862: Userspace has to set "Barrier Mode" to avoid hangs. */ - ret = wa_ring_whitelist_reg(engine, GEN9_SLICE_COMMON_ECO_CHICKEN1); - if (ret) - return ret; - - return 0; + whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1); } -static int cfl_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void cfl_whitelist_build(struct whitelist *w) { - int ret; + gen9_whitelist_build(w); +} - ret = gen9_whitelist_workarounds_apply(engine); - if (ret) - return ret; +static void cnl_whitelist_build(struct whitelist *w) +{ + /* WaEnablePreemptionGranularityControlByUMD:cnl */ + whitelist_reg(w, GEN8_CS_CHICKEN1); +} - return 0; +static void icl_whitelist_build(struct whitelist *w) +{ } -static int cnl_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static struct whitelist *whitelist_build(struct intel_engine_cs *engine, + struct whitelist *w) { - int ret; + struct drm_i915_private *i915 = engine->i915; - /* WaEnablePreemptionGranularityControlByUMD:cnl */ - ret = wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); - if (ret) - return ret; + GEM_BUG_ON(engine->id != RCS); - return 0; + w->count = 0; + w->nopid = i915_mmio_reg_offset(RING_NOPID(engine->mmio_base)); + + if (INTEL_GEN(i915) < 8) + return NULL; + else if (IS_BROADWELL(i915)) + bdw_whitelist_build(w); + else if (IS_CHERRYVIEW(i915)) + chv_whitelist_build(w); + else if (IS_SKYLAKE(i915)) + skl_whitelist_build(w); + else if (IS_BROXTON(i915)) + bxt_whitelist_build(w); + else if (IS_KABYLAKE(i915)) + kbl_whitelist_build(w); + else if (IS_GEMINILAKE(i915)) + glk_whitelist_build(w); + else if (IS_COFFEELAKE(i915)) + cfl_whitelist_build(w); + else if (IS_CANNONLAKE(i915)) + cnl_whitelist_build(w); + else if (IS_ICELAKE(i915)) + icl_whitelist_build(w); + else + MISSING_CASE(INTEL_GEN(i915)); + + return w; } -int intel_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void whitelist_apply(struct intel_engine_cs *engine, + const struct whitelist *w) { struct drm_i915_private *dev_priv = engine->i915; - int err = 0; + const u32 base = engine->mmio_base; + unsigned int i; - WARN_ON(engine->id != RCS); + if (!w) + return; - dev_priv->workarounds.hw_whitelist_count[engine->id] = 0; + intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL); - if (INTEL_GEN(dev_priv) < 8) - err = 0; - else if (IS_BROADWELL(dev_priv)) - err = bdw_whitelist_workarounds_apply(engine); - else if (IS_CHERRYVIEW(dev_priv)) - err = chv_whitelist_workarounds_apply(engine); - else if (IS_SKYLAKE(dev_priv)) - err = skl_whitelist_workarounds_apply(engine); - else if (IS_BROXTON(dev_priv)) - err = bxt_whitelist_workarounds_apply(engine); - else if (IS_KABYLAKE(dev_priv)) - err = kbl_whitelist_workarounds_apply(engine); - else if (IS_GEMINILAKE(dev_priv)) - err = glk_whitelist_workarounds_apply(engine); - else if (IS_COFFEELAKE(dev_priv)) - err = cfl_whitelist_workarounds_apply(engine); - else if (IS_CANNONLAKE(dev_priv)) - err = cnl_whitelist_workarounds_apply(engine); - else - MISSING_CASE(INTEL_GEN(dev_priv)); - if (err) - return err; + for (i = 0; i < w->count; i++) + I915_WRITE_FW(RING_FORCE_TO_NONPRIV(base, i), + i915_mmio_reg_offset(w->reg[i])); - DRM_DEBUG_DRIVER("%s: Number of whitelist w/a: %d\n", engine->name, - dev_priv->workarounds.hw_whitelist_count[engine->id]); - return 0; + /* And clear the rest just in case of garbage */ + for (; i < RING_MAX_NONPRIV_SLOTS; i++) + I915_WRITE_FW(RING_FORCE_TO_NONPRIV(base, i), w->nopid); + + intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL); } + +void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine) +{ + struct whitelist w; + + whitelist_apply(engine, whitelist_build(engine, &w)); +} + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#include "selftests/intel_workarounds.c" +#endif diff --git a/drivers/gpu/drm/i915/intel_workarounds.h b/drivers/gpu/drm/i915/intel_workarounds.h index d9b0cc5..b11d0623 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.h +++ b/drivers/gpu/drm/i915/intel_workarounds.h @@ -12,6 +12,6 @@ int intel_ctx_workarounds_emit(struct i915_request *rq); void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv); -int intel_whitelist_workarounds_apply(struct intel_engine_cs *engine); +void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine); #endif diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c index 05bbef3..91c7291 100644 --- a/drivers/gpu/drm/i915/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/selftests/huge_pages.c @@ -1091,7 +1091,7 @@ static int __igt_write_huge(struct i915_gem_context *ctx, out_vma_unpin: i915_vma_unpin(vma); out_vma_close: - i915_vma_close(vma); + i915_vma_destroy(vma); return err; } @@ -1757,6 +1757,9 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv) goto out_unlock; } + if (ctx->ppgtt) + ctx->ppgtt->base.scrub_64K = true; + err = i915_subtests(tests, ctx); out_unlock: diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c index 7ecaed5..ddb03f0 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c @@ -23,6 +23,7 @@ */ #include "../i915_selftest.h" +#include "igt_flush_test.h" #include "mock_drm.h" #include "huge_gem_object.h" @@ -411,6 +412,8 @@ static int igt_ctx_exec(void *arg) } out_unlock: + if (igt_flush_test(i915, I915_WAIT_LOCKED)) + err = -EIO; mutex_unlock(&i915->drm.struct_mutex); mock_file_free(i915, file); diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h index 8bf6aa5..a00e2bd 100644 --- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h +++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h @@ -11,6 +11,7 @@ */ selftest(sanitycheck, i915_live_sanitycheck) /* keep first (igt selfcheck) */ selftest(uncore, intel_uncore_live_selftests) +selftest(workarounds, intel_workarounds_live_selftests) selftest(requests, i915_request_live_selftests) selftest(objects, i915_gem_object_live_selftests) selftest(dmabuf, i915_gem_dmabuf_live_selftests) diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c b/drivers/gpu/drm/i915/selftests/i915_timeline.c index 3000e6a..19f1c6a 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c +++ b/drivers/gpu/drm/i915/selftests/i915_timeline.c @@ -1,25 +1,7 @@ /* - * Copyright © 2017 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. + * SPDX-License-Identifier: MIT * + * Copyright © 2017-2018 Intel Corporation */ #include "../i915_selftest.h" @@ -35,21 +17,21 @@ struct __igt_sync { bool set; }; -static int __igt_sync(struct intel_timeline *tl, +static int __igt_sync(struct i915_timeline *tl, u64 ctx, const struct __igt_sync *p, const char *name) { int ret; - if (__intel_timeline_sync_is_later(tl, ctx, p->seqno) != p->expected) { + if (__i915_timeline_sync_is_later(tl, ctx, p->seqno) != p->expected) { pr_err("%s: %s(ctx=%llu, seqno=%u) expected passed %s but failed\n", name, p->name, ctx, p->seqno, yesno(p->expected)); return -EINVAL; } if (p->set) { - ret = __intel_timeline_sync_set(tl, ctx, p->seqno); + ret = __i915_timeline_sync_set(tl, ctx, p->seqno); if (ret) return ret; } @@ -77,37 +59,31 @@ static int igt_sync(void *arg) { "unwrap", UINT_MAX, true, false }, {}, }, *p; - struct intel_timeline *tl; + struct i915_timeline tl; int order, offset; int ret = -ENODEV; - tl = mock_timeline(0); - if (!tl) - return -ENOMEM; - + mock_timeline_init(&tl, 0); for (p = pass; p->name; p++) { for (order = 1; order < 64; order++) { for (offset = -1; offset <= (order > 1); offset++) { u64 ctx = BIT_ULL(order) + offset; - ret = __igt_sync(tl, ctx, p, "1"); + ret = __igt_sync(&tl, ctx, p, "1"); if (ret) goto out; } } } - mock_timeline_destroy(tl); - - tl = mock_timeline(0); - if (!tl) - return -ENOMEM; + mock_timeline_fini(&tl); + mock_timeline_init(&tl, 0); for (order = 1; order < 64; order++) { for (offset = -1; offset <= (order > 1); offset++) { u64 ctx = BIT_ULL(order) + offset; for (p = pass; p->name; p++) { - ret = __igt_sync(tl, ctx, p, "2"); + ret = __igt_sync(&tl, ctx, p, "2"); if (ret) goto out; } @@ -115,7 +91,7 @@ static int igt_sync(void *arg) } out: - mock_timeline_destroy(tl); + mock_timeline_fini(&tl); return ret; } @@ -127,15 +103,13 @@ static unsigned int random_engine(struct rnd_state *rnd) static int bench_sync(void *arg) { struct rnd_state prng; - struct intel_timeline *tl; + struct i915_timeline tl; unsigned long end_time, count; u64 prng32_1M; ktime_t kt; int order, last_order; - tl = mock_timeline(0); - if (!tl) - return -ENOMEM; + mock_timeline_init(&tl, 0); /* Lookups from cache are very fast and so the random number generation * and the loop itself becomes a significant factor in the per-iteration @@ -167,7 +141,7 @@ static int bench_sync(void *arg) do { u64 id = i915_prandom_u64_state(&prng); - __intel_timeline_sync_set(tl, id, 0); + __i915_timeline_sync_set(&tl, id, 0); count++; } while (!time_after(jiffies, end_time)); kt = ktime_sub(ktime_get(), kt); @@ -182,8 +156,8 @@ static int bench_sync(void *arg) while (end_time--) { u64 id = i915_prandom_u64_state(&prng); - if (!__intel_timeline_sync_is_later(tl, id, 0)) { - mock_timeline_destroy(tl); + if (!__i915_timeline_sync_is_later(&tl, id, 0)) { + mock_timeline_fini(&tl); pr_err("Lookup of %llu failed\n", id); return -EINVAL; } @@ -193,19 +167,17 @@ static int bench_sync(void *arg) pr_info("%s: %lu random lookups, %lluns/lookup\n", __func__, count, (long long)div64_ul(ktime_to_ns(kt), count)); - mock_timeline_destroy(tl); + mock_timeline_fini(&tl); cond_resched(); - tl = mock_timeline(0); - if (!tl) - return -ENOMEM; + mock_timeline_init(&tl, 0); /* Benchmark setting the first N (in order) contexts */ count = 0; kt = ktime_get(); end_time = jiffies + HZ/10; do { - __intel_timeline_sync_set(tl, count++, 0); + __i915_timeline_sync_set(&tl, count++, 0); } while (!time_after(jiffies, end_time)); kt = ktime_sub(ktime_get(), kt); pr_info("%s: %lu in-order insertions, %lluns/insert\n", @@ -215,9 +187,9 @@ static int bench_sync(void *arg) end_time = count; kt = ktime_get(); while (end_time--) { - if (!__intel_timeline_sync_is_later(tl, end_time, 0)) { + if (!__i915_timeline_sync_is_later(&tl, end_time, 0)) { pr_err("Lookup of %lu failed\n", end_time); - mock_timeline_destroy(tl); + mock_timeline_fini(&tl); return -EINVAL; } } @@ -225,12 +197,10 @@ static int bench_sync(void *arg) pr_info("%s: %lu in-order lookups, %lluns/lookup\n", __func__, count, (long long)div64_ul(ktime_to_ns(kt), count)); - mock_timeline_destroy(tl); + mock_timeline_fini(&tl); cond_resched(); - tl = mock_timeline(0); - if (!tl) - return -ENOMEM; + mock_timeline_init(&tl, 0); /* Benchmark searching for a random context id and maybe changing it */ prandom_seed_state(&prng, i915_selftest.random_seed); @@ -241,8 +211,8 @@ static int bench_sync(void *arg) u32 id = random_engine(&prng); u32 seqno = prandom_u32_state(&prng); - if (!__intel_timeline_sync_is_later(tl, id, seqno)) - __intel_timeline_sync_set(tl, id, seqno); + if (!__i915_timeline_sync_is_later(&tl, id, seqno)) + __i915_timeline_sync_set(&tl, id, seqno); count++; } while (!time_after(jiffies, end_time)); @@ -250,7 +220,7 @@ static int bench_sync(void *arg) kt = ktime_sub_ns(kt, (count * prng32_1M * 2) >> 20); pr_info("%s: %lu repeated insert/lookups, %lluns/op\n", __func__, count, (long long)div64_ul(ktime_to_ns(kt), count)); - mock_timeline_destroy(tl); + mock_timeline_fini(&tl); cond_resched(); /* Benchmark searching for a known context id and changing the seqno */ @@ -258,9 +228,7 @@ static int bench_sync(void *arg) ({ int tmp = last_order; last_order = order; order += tmp; })) { unsigned int mask = BIT(order) - 1; - tl = mock_timeline(0); - if (!tl) - return -ENOMEM; + mock_timeline_init(&tl, 0); count = 0; kt = ktime_get(); @@ -272,8 +240,8 @@ static int bench_sync(void *arg) */ u64 id = (u64)(count & mask) << order; - __intel_timeline_sync_is_later(tl, id, 0); - __intel_timeline_sync_set(tl, id, 0); + __i915_timeline_sync_is_later(&tl, id, 0); + __i915_timeline_sync_set(&tl, id, 0); count++; } while (!time_after(jiffies, end_time)); @@ -281,7 +249,7 @@ static int bench_sync(void *arg) pr_info("%s: %lu cyclic/%d insert/lookups, %lluns/op\n", __func__, count, order, (long long)div64_ul(ktime_to_ns(kt), count)); - mock_timeline_destroy(tl); + mock_timeline_fini(&tl); cond_resched(); } diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c index eb89e30..e90f972 100644 --- a/drivers/gpu/drm/i915/selftests/i915_vma.c +++ b/drivers/gpu/drm/i915/selftests/i915_vma.c @@ -81,7 +81,7 @@ checked_vma_instance(struct drm_i915_gem_object *obj, } if (i915_vma_compare(vma, vm, view)) { - pr_err("i915_vma_compare failed with create parmaters!\n"); + pr_err("i915_vma_compare failed with create parameters!\n"); return ERR_PTR(-EINVAL); } diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c new file mode 100644 index 0000000..0d06f55 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c @@ -0,0 +1,70 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#include "../i915_drv.h" + +#include "../i915_selftest.h" +#include "igt_flush_test.h" + +struct wedge_me { + struct delayed_work work; + struct drm_i915_private *i915; + const void *symbol; +}; + +static void wedge_me(struct work_struct *work) +{ + struct wedge_me *w = container_of(work, typeof(*w), work.work); + + pr_err("%pS timed out, cancelling all further testing.\n", w->symbol); + + GEM_TRACE("%pS timed out.\n", w->symbol); + GEM_TRACE_DUMP(); + + i915_gem_set_wedged(w->i915); +} + +static void __init_wedge(struct wedge_me *w, + struct drm_i915_private *i915, + long timeout, + const void *symbol) +{ + w->i915 = i915; + w->symbol = symbol; + + INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me); + schedule_delayed_work(&w->work, timeout); +} + +static void __fini_wedge(struct wedge_me *w) +{ + cancel_delayed_work_sync(&w->work); + destroy_delayed_work_on_stack(&w->work); + w->i915 = NULL; +} + +#define wedge_on_timeout(W, DEV, TIMEOUT) \ + for (__init_wedge((W), (DEV), (TIMEOUT), __builtin_return_address(0)); \ + (W)->i915; \ + __fini_wedge((W))) + +int igt_flush_test(struct drm_i915_private *i915, unsigned int flags) +{ + struct wedge_me w; + + cond_resched(); + + if (flags & I915_WAIT_LOCKED && + i915_gem_switch_to_kernel_context(i915)) { + pr_err("Failed to switch back to kernel context; declaring wedged\n"); + i915_gem_set_wedged(i915); + } + + wedge_on_timeout(&w, i915, HZ) + i915_gem_wait_for_idle(i915, flags); + + return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0; +} diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.h b/drivers/gpu/drm/i915/selftests/igt_flush_test.h new file mode 100644 index 0000000..63e0099 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.h @@ -0,0 +1,14 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#ifndef IGT_FLUSH_TEST_H +#define IGT_FLUSH_TEST_H + +struct drm_i915_private; + +int igt_flush_test(struct drm_i915_private *i915, unsigned int flags); + +#endif /* IGT_FLUSH_TEST_H */ diff --git a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c index 54fc571..d6926e7 100644 --- a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c @@ -271,18 +271,13 @@ struct igt_wakeup { u32 seqno; }; -static int wait_atomic_timeout(atomic_t *p, unsigned int mode) -{ - return schedule_timeout(10 * HZ) ? 0 : -ETIMEDOUT; -} - static bool wait_for_ready(struct igt_wakeup *w) { DEFINE_WAIT(ready); set_bit(IDLE, &w->flags); if (atomic_dec_and_test(w->done)) - wake_up_atomic_t(w->done); + wake_up_var(w->done); if (test_bit(STOP, &w->flags)) goto out; @@ -299,7 +294,7 @@ static bool wait_for_ready(struct igt_wakeup *w) out: clear_bit(IDLE, &w->flags); if (atomic_dec_and_test(w->set)) - wake_up_atomic_t(w->set); + wake_up_var(w->set); return !test_bit(STOP, &w->flags); } @@ -342,7 +337,7 @@ static void igt_wake_all_sync(atomic_t *ready, atomic_set(ready, 0); wake_up_all(wq); - wait_on_atomic_t(set, atomic_t_wait, TASK_UNINTERRUPTIBLE); + wait_var_event(set, !atomic_read(set)); atomic_set(ready, count); atomic_set(done, count); } @@ -350,7 +345,6 @@ static void igt_wake_all_sync(atomic_t *ready, static int igt_wakeup(void *arg) { I915_RND_STATE(prng); - const int state = TASK_UNINTERRUPTIBLE; struct intel_engine_cs *engine = arg; struct igt_wakeup *waiters; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); @@ -418,10 +412,11 @@ static int igt_wakeup(void *arg) * that they are ready for the next test. We wait until all * threads are complete and waiting for us (i.e. not a seqno). */ - err = wait_on_atomic_t(&done, wait_atomic_timeout, state); - if (err) { + if (!wait_var_event_timeout(&done, + !atomic_read(&done), 10 * HZ)) { pr_err("Timed out waiting for %d remaining waiters\n", atomic_read(&done)); + err = -ETIMEDOUT; break; } diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c index 24f913f..438e0b0 100644 --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c @@ -26,10 +26,13 @@ #include "../i915_selftest.h" #include "i915_random.h" +#include "igt_flush_test.h" #include "mock_context.h" #include "mock_drm.h" +#define IGT_IDLE_TIMEOUT 50 /* ms; time to wait after flushing between tests */ + struct hang { struct drm_i915_private *i915; struct drm_i915_gem_object *hws; @@ -251,61 +254,6 @@ static u32 hws_seqno(const struct hang *h, const struct i915_request *rq) return READ_ONCE(h->seqno[rq->fence.context % (PAGE_SIZE/sizeof(u32))]); } -struct wedge_me { - struct delayed_work work; - struct drm_i915_private *i915; - const void *symbol; -}; - -static void wedge_me(struct work_struct *work) -{ - struct wedge_me *w = container_of(work, typeof(*w), work.work); - - pr_err("%pS timed out, cancelling all further testing.\n", w->symbol); - - GEM_TRACE("%pS timed out.\n", w->symbol); - GEM_TRACE_DUMP(); - - i915_gem_set_wedged(w->i915); -} - -static void __init_wedge(struct wedge_me *w, - struct drm_i915_private *i915, - long timeout, - const void *symbol) -{ - w->i915 = i915; - w->symbol = symbol; - - INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me); - schedule_delayed_work(&w->work, timeout); -} - -static void __fini_wedge(struct wedge_me *w) -{ - cancel_delayed_work_sync(&w->work); - destroy_delayed_work_on_stack(&w->work); - w->i915 = NULL; -} - -#define wedge_on_timeout(W, DEV, TIMEOUT) \ - for (__init_wedge((W), (DEV), (TIMEOUT), __builtin_return_address(0)); \ - (W)->i915; \ - __fini_wedge((W))) - -static noinline int -flush_test(struct drm_i915_private *i915, unsigned int flags) -{ - struct wedge_me w; - - cond_resched(); - - wedge_on_timeout(&w, i915, HZ) - i915_gem_wait_for_idle(i915, flags); - - return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0; -} - static void hang_fini(struct hang *h) { *h->batch = MI_BATCH_BUFFER_END; @@ -319,7 +267,7 @@ static void hang_fini(struct hang *h) kernel_context_close(h->ctx); - flush_test(h->i915, I915_WAIT_LOCKED); + igt_flush_test(h->i915, I915_WAIT_LOCKED); } static bool wait_until_running(struct hang *h, struct i915_request *rq) @@ -454,6 +402,11 @@ static int igt_global_reset(void *arg) return err; } +static bool wait_for_idle(struct intel_engine_cs *engine) +{ + return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0; +} + static int __igt_reset_engine(struct drm_i915_private *i915, bool active) { struct intel_engine_cs *engine; @@ -481,6 +434,13 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active) if (active && !intel_engine_can_store_dword(engine)) continue; + if (!wait_for_idle(engine)) { + pr_err("%s failed to idle before reset\n", + engine->name); + err = -EIO; + break; + } + reset_count = i915_reset_count(&i915->gpu_error); reset_engine_count = i915_reset_engine_count(&i915->gpu_error, engine); @@ -542,13 +502,26 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active) err = -EINVAL; break; } + + if (!wait_for_idle(engine)) { + struct drm_printer p = + drm_info_printer(i915->drm.dev); + + pr_err("%s failed to idle after reset\n", + engine->name); + intel_engine_dump(engine, &p, + "%s\n", engine->name); + + err = -EIO; + break; + } } while (time_before(jiffies, end_time)); clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); if (err) break; - err = flush_test(i915, 0); + err = igt_flush_test(i915, 0); if (err) break; } @@ -628,7 +601,7 @@ static int active_engine(void *data) } if (arg->flags & TEST_PRIORITY) - ctx[idx]->priority = + ctx[idx]->sched.priority = i915_prandom_u32_max_state(512, &prng); rq[idx] = i915_request_get(new); @@ -683,7 +656,7 @@ static int __igt_reset_engines(struct drm_i915_private *i915, return err; if (flags & TEST_PRIORITY) - h.ctx->priority = 1024; + h.ctx->sched.priority = 1024; } for_each_engine(engine, i915, id) { @@ -696,6 +669,13 @@ static int __igt_reset_engines(struct drm_i915_private *i915, !intel_engine_can_store_dword(engine)) continue; + if (!wait_for_idle(engine)) { + pr_err("i915_reset_engine(%s:%s): failed to idle before reset\n", + engine->name, test_name); + err = -EIO; + break; + } + memset(threads, 0, sizeof(threads)); for_each_engine(other, i915, tmp) { struct task_struct *tsk; @@ -772,6 +752,20 @@ static int __igt_reset_engines(struct drm_i915_private *i915, i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT); i915_request_put(rq); } + + if (!(flags & TEST_SELF) && !wait_for_idle(engine)) { + struct drm_printer p = + drm_info_printer(i915->drm.dev); + + pr_err("i915_reset_engine(%s:%s):" + " failed to idle after reset\n", + engine->name, test_name); + intel_engine_dump(engine, &p, + "%s\n", engine->name); + + err = -EIO; + break; + } } while (time_before(jiffies, end_time)); clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); pr_info("i915_reset_engine(%s:%s): %lu resets\n", @@ -826,7 +820,7 @@ unwind: if (err) break; - err = flush_test(i915, 0); + err = igt_flush_test(i915, 0); if (err) break; } @@ -981,7 +975,7 @@ static int wait_for_others(struct drm_i915_private *i915, if (engine == exclude) continue; - if (wait_for(intel_engine_is_idle(engine), 10)) + if (!wait_for_idle(engine)) return -EIO; } @@ -1120,7 +1114,7 @@ static int igt_reset_queue(void *arg) i915_request_put(prev); - err = flush_test(i915, I915_WAIT_LOCKED); + err = igt_flush_test(i915, I915_WAIT_LOCKED); if (err) break; } @@ -1232,7 +1226,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915) err = i915_subtests(tests, i915); mutex_lock(&i915->drm.struct_mutex); - flush_test(i915, I915_WAIT_LOCKED); + igt_flush_test(i915, I915_WAIT_LOCKED); mutex_unlock(&i915->drm.struct_mutex); i915_modparams.enable_hangcheck = saved_hangcheck; diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c index 0481e2e..1b8a071 100644 --- a/drivers/gpu/drm/i915/selftests/intel_lrc.c +++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c @@ -5,6 +5,7 @@ */ #include "../i915_selftest.h" +#include "igt_flush_test.h" #include "mock_context.h" @@ -168,61 +169,6 @@ static u32 hws_seqno(const struct spinner *spin, const struct i915_request *rq) return READ_ONCE(*seqno); } -struct wedge_me { - struct delayed_work work; - struct drm_i915_private *i915; - const void *symbol; -}; - -static void wedge_me(struct work_struct *work) -{ - struct wedge_me *w = container_of(work, typeof(*w), work.work); - - pr_err("%pS timed out, cancelling all further testing.\n", w->symbol); - - GEM_TRACE("%pS timed out.\n", w->symbol); - GEM_TRACE_DUMP(); - - i915_gem_set_wedged(w->i915); -} - -static void __init_wedge(struct wedge_me *w, - struct drm_i915_private *i915, - long timeout, - const void *symbol) -{ - w->i915 = i915; - w->symbol = symbol; - - INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me); - schedule_delayed_work(&w->work, timeout); -} - -static void __fini_wedge(struct wedge_me *w) -{ - cancel_delayed_work_sync(&w->work); - destroy_delayed_work_on_stack(&w->work); - w->i915 = NULL; -} - -#define wedge_on_timeout(W, DEV, TIMEOUT) \ - for (__init_wedge((W), (DEV), (TIMEOUT), __builtin_return_address(0)); \ - (W)->i915; \ - __fini_wedge((W))) - -static noinline int -flush_test(struct drm_i915_private *i915, unsigned int flags) -{ - struct wedge_me w; - - cond_resched(); - - wedge_on_timeout(&w, i915, HZ) - i915_gem_wait_for_idle(i915, flags); - - return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0; -} - static void spinner_end(struct spinner *spin) { *spin->batch = MI_BATCH_BUFFER_END; @@ -295,7 +241,7 @@ static int live_sanitycheck(void *arg) } spinner_end(&spin); - if (flush_test(i915, I915_WAIT_LOCKED)) { + if (igt_flush_test(i915, I915_WAIT_LOCKED)) { err = -EIO; goto err_ctx; } @@ -307,7 +253,7 @@ err_ctx: err_spin: spinner_fini(&spin); err_unlock: - flush_test(i915, I915_WAIT_LOCKED); + igt_flush_test(i915, I915_WAIT_LOCKED); mutex_unlock(&i915->drm.struct_mutex); return err; } @@ -335,12 +281,12 @@ static int live_preempt(void *arg) ctx_hi = kernel_context(i915); if (!ctx_hi) goto err_spin_lo; - ctx_hi->priority = I915_CONTEXT_MAX_USER_PRIORITY; + ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY; ctx_lo = kernel_context(i915); if (!ctx_lo) goto err_ctx_hi; - ctx_lo->priority = I915_CONTEXT_MIN_USER_PRIORITY; + ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY; for_each_engine(engine, i915, id) { struct i915_request *rq; @@ -380,7 +326,7 @@ static int live_preempt(void *arg) spinner_end(&spin_hi); spinner_end(&spin_lo); - if (flush_test(i915, I915_WAIT_LOCKED)) { + if (igt_flush_test(i915, I915_WAIT_LOCKED)) { err = -EIO; goto err_ctx_lo; } @@ -396,7 +342,7 @@ err_spin_lo: err_spin_hi: spinner_fini(&spin_hi); err_unlock: - flush_test(i915, I915_WAIT_LOCKED); + igt_flush_test(i915, I915_WAIT_LOCKED); mutex_unlock(&i915->drm.struct_mutex); return err; } @@ -407,6 +353,7 @@ static int live_late_preempt(void *arg) struct i915_gem_context *ctx_hi, *ctx_lo; struct spinner spin_hi, spin_lo; struct intel_engine_cs *engine; + struct i915_sched_attr attr = {}; enum intel_engine_id id; int err = -ENOMEM; @@ -458,7 +405,8 @@ static int live_late_preempt(void *arg) goto err_wedged; } - engine->schedule(rq, I915_PRIORITY_MAX); + attr.priority = I915_PRIORITY_MAX; + engine->schedule(rq, &attr); if (!wait_for_spinner(&spin_hi, rq)) { pr_err("High priority context failed to preempt the low priority context\n"); @@ -468,7 +416,7 @@ static int live_late_preempt(void *arg) spinner_end(&spin_hi); spinner_end(&spin_lo); - if (flush_test(i915, I915_WAIT_LOCKED)) { + if (igt_flush_test(i915, I915_WAIT_LOCKED)) { err = -EIO; goto err_ctx_lo; } @@ -484,7 +432,7 @@ err_spin_lo: err_spin_hi: spinner_fini(&spin_hi); err_unlock: - flush_test(i915, I915_WAIT_LOCKED); + igt_flush_test(i915, I915_WAIT_LOCKED); mutex_unlock(&i915->drm.struct_mutex); return err; @@ -503,5 +451,9 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915) SUBTEST(live_preempt), SUBTEST(live_late_preempt), }; + + if (!HAS_EXECLISTS(i915)) + return 0; + return i915_subtests(tests, i915); } diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c new file mode 100644 index 0000000..17444a3 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c @@ -0,0 +1,291 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#include "../i915_selftest.h" + +#include "mock_context.h" + +static struct drm_i915_gem_object * +read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine) +{ + struct drm_i915_gem_object *result; + struct i915_request *rq; + struct i915_vma *vma; + const u32 base = engine->mmio_base; + u32 srm, *cs; + int err; + int i; + + result = i915_gem_object_create_internal(engine->i915, PAGE_SIZE); + if (IS_ERR(result)) + return result; + + i915_gem_object_set_cache_level(result, I915_CACHE_LLC); + + cs = i915_gem_object_pin_map(result, I915_MAP_WB); + if (IS_ERR(cs)) { + err = PTR_ERR(cs); + goto err_obj; + } + memset(cs, 0xc5, PAGE_SIZE); + i915_gem_object_unpin_map(result); + + vma = i915_vma_instance(result, &engine->i915->ggtt.base, NULL); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto err_obj; + } + + err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL); + if (err) + goto err_obj; + + rq = i915_request_alloc(engine, ctx); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto err_pin; + } + + srm = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; + if (INTEL_GEN(ctx->i915) >= 8) + srm++; + + cs = intel_ring_begin(rq, 4 * RING_MAX_NONPRIV_SLOTS); + if (IS_ERR(cs)) { + err = PTR_ERR(cs); + goto err_req; + } + + for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++) { + *cs++ = srm; + *cs++ = i915_mmio_reg_offset(RING_FORCE_TO_NONPRIV(base, i)); + *cs++ = i915_ggtt_offset(vma) + sizeof(u32) * i; + *cs++ = 0; + } + intel_ring_advance(rq, cs); + + i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + reservation_object_lock(vma->resv, NULL); + reservation_object_add_excl_fence(vma->resv, &rq->fence); + reservation_object_unlock(vma->resv); + + i915_gem_object_get(result); + i915_gem_object_set_active_reference(result); + + __i915_request_add(rq, true); + i915_vma_unpin(vma); + + return result; + +err_req: + i915_request_add(rq); +err_pin: + i915_vma_unpin(vma); +err_obj: + i915_gem_object_put(result); + return ERR_PTR(err); +} + +static u32 get_whitelist_reg(const struct whitelist *w, unsigned int i) +{ + return i < w->count ? i915_mmio_reg_offset(w->reg[i]) : w->nopid; +} + +static void print_results(const struct whitelist *w, const u32 *results) +{ + unsigned int i; + + for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++) { + u32 expected = get_whitelist_reg(w, i); + u32 actual = results[i]; + + pr_info("RING_NONPRIV[%d]: expected 0x%08x, found 0x%08x\n", + i, expected, actual); + } +} + +static int check_whitelist(const struct whitelist *w, + struct i915_gem_context *ctx, + struct intel_engine_cs *engine) +{ + struct drm_i915_gem_object *results; + u32 *vaddr; + int err; + int i; + + results = read_nonprivs(ctx, engine); + if (IS_ERR(results)) + return PTR_ERR(results); + + err = i915_gem_object_set_to_cpu_domain(results, false); + if (err) + goto out_put; + + vaddr = i915_gem_object_pin_map(results, I915_MAP_WB); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto out_put; + } + + for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++) { + u32 expected = get_whitelist_reg(w, i); + u32 actual = vaddr[i]; + + if (expected != actual) { + print_results(w, vaddr); + pr_err("Invalid RING_NONPRIV[%d], expected 0x%08x, found 0x%08x\n", + i, expected, actual); + + err = -EINVAL; + break; + } + } + + i915_gem_object_unpin_map(results); +out_put: + i915_gem_object_put(results); + return err; +} + +static int do_device_reset(struct intel_engine_cs *engine) +{ + i915_reset(engine->i915, ENGINE_MASK(engine->id), NULL); + return 0; +} + +static int do_engine_reset(struct intel_engine_cs *engine) +{ + return i915_reset_engine(engine, NULL); +} + +static int switch_to_scratch_context(struct intel_engine_cs *engine) +{ + struct i915_gem_context *ctx; + struct i915_request *rq; + + ctx = kernel_context(engine->i915); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + rq = i915_request_alloc(engine, ctx); + kernel_context_close(ctx); + if (IS_ERR(rq)) + return PTR_ERR(rq); + + i915_request_add(rq); + + return 0; +} + +static int check_whitelist_across_reset(struct intel_engine_cs *engine, + int (*reset)(struct intel_engine_cs *), + const struct whitelist *w, + const char *name) +{ + struct i915_gem_context *ctx; + int err; + + ctx = kernel_context(engine->i915); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + err = check_whitelist(w, ctx, engine); + if (err) { + pr_err("Invalid whitelist *before* %s reset!\n", name); + goto out; + } + + err = switch_to_scratch_context(engine); + if (err) + goto out; + + err = reset(engine); + if (err) { + pr_err("%s reset failed\n", name); + goto out; + } + + err = check_whitelist(w, ctx, engine); + if (err) { + pr_err("Whitelist not preserved in context across %s reset!\n", + name); + goto out; + } + + kernel_context_close(ctx); + + ctx = kernel_context(engine->i915); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + err = check_whitelist(w, ctx, engine); + if (err) { + pr_err("Invalid whitelist *after* %s reset in fresh context!\n", + name); + goto out; + } + +out: + kernel_context_close(ctx); + return err; +} + +static int live_reset_whitelist(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_engine_cs *engine = i915->engine[RCS]; + struct i915_gpu_error *error = &i915->gpu_error; + struct whitelist w; + int err = 0; + + /* If we reset the gpu, we should not lose the RING_NONPRIV */ + + if (!engine) + return 0; + + if (!whitelist_build(engine, &w)) + return 0; + + pr_info("Checking %d whitelisted registers (RING_NONPRIV)\n", w.count); + + set_bit(I915_RESET_BACKOFF, &error->flags); + set_bit(I915_RESET_ENGINE + engine->id, &error->flags); + + if (intel_has_reset_engine(i915)) { + err = check_whitelist_across_reset(engine, + do_engine_reset, &w, + "engine"); + if (err) + goto out; + } + + if (intel_has_gpu_reset(i915)) { + err = check_whitelist_across_reset(engine, + do_device_reset, &w, + "device"); + if (err) + goto out; + } + +out: + clear_bit(I915_RESET_ENGINE + engine->id, &error->flags); + clear_bit(I915_RESET_BACKOFF, &error->flags); + return err; +} + +int intel_workarounds_live_selftests(struct drm_i915_private *i915) +{ + static const struct i915_subtest tests[] = { + SUBTEST(live_reset_whitelist), + }; + int err; + + mutex_lock(&i915->drm.struct_mutex); + err = i915_subtests(tests, i915); + mutex_unlock(&i915->drm.struct_mutex); + + return err; +} diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c index 78a89ef..26bf29d 100644 --- a/drivers/gpu/drm/i915/selftests/mock_engine.c +++ b/drivers/gpu/drm/i915/selftests/mock_engine.c @@ -25,6 +25,11 @@ #include "mock_engine.h" #include "mock_request.h" +struct mock_ring { + struct intel_ring base; + struct i915_timeline timeline; +}; + static struct mock_request *first_request(struct mock_engine *engine) { return list_first_entry_or_null(&engine->hw_queue, @@ -71,14 +76,21 @@ static struct intel_ring * mock_context_pin(struct intel_engine_cs *engine, struct i915_gem_context *ctx) { - i915_gem_context_get(ctx); + struct intel_context *ce = to_intel_context(ctx, engine); + + if (!ce->pin_count++) + i915_gem_context_get(ctx); + return engine->buffer; } static void mock_context_unpin(struct intel_engine_cs *engine, struct i915_gem_context *ctx) { - i915_gem_context_put(ctx); + struct intel_context *ce = to_intel_context(ctx, engine); + + if (!--ce->pin_count) + i915_gem_context_put(ctx); } static int mock_request_alloc(struct i915_request *request) @@ -125,7 +137,7 @@ static void mock_submit_request(struct i915_request *request) static struct intel_ring *mock_ring(struct intel_engine_cs *engine) { const unsigned long sz = PAGE_SIZE / 2; - struct intel_ring *ring; + struct mock_ring *ring; BUILD_BUG_ON(MIN_SPACE_FOR_ADD_REQUEST > sz); @@ -133,14 +145,25 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) if (!ring) return NULL; - ring->size = sz; - ring->effective_size = sz; - ring->vaddr = (void *)(ring + 1); + i915_timeline_init(engine->i915, &ring->timeline, engine->name); + + ring->base.size = sz; + ring->base.effective_size = sz; + ring->base.vaddr = (void *)(ring + 1); + ring->base.timeline = &ring->timeline; - INIT_LIST_HEAD(&ring->request_list); - intel_ring_update_space(ring); + INIT_LIST_HEAD(&ring->base.request_list); + intel_ring_update_space(&ring->base); - return ring; + return &ring->base; +} + +static void mock_ring_free(struct intel_ring *base) +{ + struct mock_ring *ring = container_of(base, typeof(*ring), base); + + i915_timeline_fini(&ring->timeline); + kfree(ring); } struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, @@ -155,12 +178,6 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, if (!engine) return NULL; - engine->base.buffer = mock_ring(&engine->base); - if (!engine->base.buffer) { - kfree(engine); - return NULL; - } - /* minimal engine setup for requests */ engine->base.i915 = i915; snprintf(engine->base.name, sizeof(engine->base.name), "%s", name); @@ -174,9 +191,7 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, engine->base.emit_breadcrumb = mock_emit_breadcrumb; engine->base.submit_request = mock_submit_request; - engine->base.timeline = - &i915->gt.global_timeline.engine[engine->base.id]; - + i915_timeline_init(i915, &engine->base.timeline, engine->base.name); intel_engine_init_breadcrumbs(&engine->base); engine->base.breadcrumbs.mock = true; /* prevent touching HW for irqs */ @@ -185,7 +200,17 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915, timer_setup(&engine->hw_delay, hw_delay_complete, 0); INIT_LIST_HEAD(&engine->hw_queue); + engine->base.buffer = mock_ring(&engine->base); + if (!engine->base.buffer) + goto err_breadcrumbs; + return &engine->base; + +err_breadcrumbs: + intel_engine_fini_breadcrumbs(&engine->base); + i915_timeline_fini(&engine->base.timeline); + kfree(engine); + return NULL; } void mock_engine_flush(struct intel_engine_cs *engine) @@ -217,10 +242,12 @@ void mock_engine_free(struct intel_engine_cs *engine) GEM_BUG_ON(timer_pending(&mock->hw_delay)); if (engine->last_retired_context) - engine->context_unpin(engine, engine->last_retired_context); + intel_context_unpin(engine->last_retired_context, engine); + + mock_ring_free(engine->buffer); intel_engine_fini_breadcrumbs(engine); + i915_timeline_fini(&engine->timeline); - kfree(engine->buffer); kfree(engine); } diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index e6d4b88..94baedf 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -44,6 +44,7 @@ void mock_device_flush(struct drm_i915_private *i915) mock_engine_flush(engine); i915_retire_requests(i915); + GEM_BUG_ON(i915->gt.active_requests); } static void mock_device_release(struct drm_device *dev) @@ -72,8 +73,8 @@ static void mock_device_release(struct drm_device *dev) mutex_lock(&i915->drm.struct_mutex); mock_fini_ggtt(i915); - i915_gem_timeline_fini(&i915->gt.global_timeline); mutex_unlock(&i915->drm.struct_mutex); + WARN_ON(!list_empty(&i915->gt.timelines)); destroy_workqueue(i915->wq); @@ -223,26 +224,25 @@ struct drm_i915_private *mock_gem_device(void) if (!i915->priorities) goto err_dependencies; - mutex_lock(&i915->drm.struct_mutex); INIT_LIST_HEAD(&i915->gt.timelines); - err = i915_gem_timeline_init__global(i915); - if (err) { - mutex_unlock(&i915->drm.struct_mutex); - goto err_priorities; - } + INIT_LIST_HEAD(&i915->gt.active_rings); + INIT_LIST_HEAD(&i915->gt.closed_vma); + + mutex_lock(&i915->drm.struct_mutex); mock_init_ggtt(i915); - mutex_unlock(&i915->drm.struct_mutex); mkwrite_device_info(i915)->ring_mask = BIT(0); i915->engine[RCS] = mock_engine(i915, "mock", RCS); if (!i915->engine[RCS]) - goto err_priorities; + goto err_unlock; i915->kernel_context = mock_context(i915, NULL); if (!i915->kernel_context) goto err_engine; + mutex_unlock(&i915->drm.struct_mutex); + WARN_ON(i915_gemfs_init(i915)); return i915; @@ -250,7 +250,8 @@ struct drm_i915_private *mock_gem_device(void) err_engine: for_each_engine(engine, i915, id) mock_engine_free(engine); -err_priorities: +err_unlock: + mutex_unlock(&i915->drm.struct_mutex); kmem_cache_destroy(i915->priorities); err_dependencies: kmem_cache_destroy(i915->dependencies); diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c index e96873f..36c1120 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gtt.c +++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c @@ -76,7 +76,6 @@ mock_ppgtt(struct drm_i915_private *i915, INIT_LIST_HEAD(&ppgtt->base.global_link); drm_mm_init(&ppgtt->base.mm, 0, ppgtt->base.total); - i915_gem_timeline_init(i915, &ppgtt->base.timeline, name); ppgtt->base.clear_range = nop_clear_range; ppgtt->base.insert_page = mock_insert_page; diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.c b/drivers/gpu/drm/i915/selftests/mock_timeline.c index 47b1f47..dcf3b16 100644 --- a/drivers/gpu/drm/i915/selftests/mock_timeline.c +++ b/drivers/gpu/drm/i915/selftests/mock_timeline.c @@ -1,45 +1,28 @@ /* - * Copyright © 2017 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. + * SPDX-License-Identifier: MIT * + * Copyright © 2017-2018 Intel Corporation */ +#include "../i915_timeline.h" + #include "mock_timeline.h" -struct intel_timeline *mock_timeline(u64 context) +void mock_timeline_init(struct i915_timeline *timeline, u64 context) { - static struct lock_class_key class; - struct intel_timeline *tl; + timeline->fence_context = context; + + spin_lock_init(&timeline->lock); - tl = kzalloc(sizeof(*tl), GFP_KERNEL); - if (!tl) - return NULL; + init_request_active(&timeline->last_request, NULL); + INIT_LIST_HEAD(&timeline->requests); - __intel_timeline_init(tl, NULL, context, &class, "mock"); + i915_syncmap_init(&timeline->sync); - return tl; + INIT_LIST_HEAD(&timeline->link); } -void mock_timeline_destroy(struct intel_timeline *tl) +void mock_timeline_fini(struct i915_timeline *timeline) { - __intel_timeline_fini(tl); - kfree(tl); + i915_timeline_fini(timeline); } diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.h b/drivers/gpu/drm/i915/selftests/mock_timeline.h index c27ff46..b6deaa6 100644 --- a/drivers/gpu/drm/i915/selftests/mock_timeline.h +++ b/drivers/gpu/drm/i915/selftests/mock_timeline.h @@ -1,33 +1,15 @@ /* - * Copyright © 2017 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. + * SPDX-License-Identifier: MIT * + * Copyright © 2017-2018 Intel Corporation */ #ifndef __MOCK_TIMELINE__ #define __MOCK_TIMELINE__ -#include "../i915_gem_timeline.h" +struct i915_timeline; -struct intel_timeline *mock_timeline(u64 context); -void mock_timeline_destroy(struct intel_timeline *tl); +void mock_timeline_init(struct i915_timeline *timeline, u64 context); +void mock_timeline_fini(struct i915_timeline *timeline); #endif /* !__MOCK_TIMELINE__ */ diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index fb50a9d..8918539 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -1586,7 +1586,7 @@ static uint32_t mga_vga_calculate_mode_bandwidth(struct drm_display_mode *mode, #define MODE_BANDWIDTH MODE_BAD -static int mga_vga_mode_valid(struct drm_connector *connector, +static enum drm_mode_status mga_vga_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct drm_device *dev = connector->dev; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index a4f68af..d39400e 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -89,14 +89,14 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname) */ if (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY) { ret = qcom_mdt_load(dev, fw, fwname, GPU_PAS_ID, - mem_region, mem_phys, mem_size); + mem_region, mem_phys, mem_size, NULL); } else { char newname[strlen("qcom/") + strlen(fwname) + 1]; sprintf(newname, "qcom/%s", fwname); ret = qcom_mdt_load(dev, fw, newname, GPU_PAS_ID, - mem_region, mem_phys, mem_size); + mem_region, mem_phys, mem_size, NULL); } if (ret) goto out; diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c index 6e5e1aa..b001699 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c @@ -351,6 +351,7 @@ static void mdp4_crtc_atomic_flush(struct drm_crtc *crtc, spin_lock_irqsave(&dev->event_lock, flags); mdp4_crtc->event = crtc->state->event; + crtc->state->event = NULL; spin_unlock_irqrestore(&dev->event_lock, flags); blend_setup(crtc); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index 9893e43..76b9608 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -708,6 +708,7 @@ static void mdp5_crtc_atomic_flush(struct drm_crtc *crtc, spin_lock_irqsave(&dev->event_lock, flags); mdp5_crtc->event = crtc->state->event; + crtc->state->event = NULL; spin_unlock_irqrestore(&dev->event_lock, flags); /* diff --git a/drivers/gpu/drm/msm/disp/mdp_format.c b/drivers/gpu/drm/msm/disp/mdp_format.c index b4a8aa4..005760b 100644 --- a/drivers/gpu/drm/msm/disp/mdp_format.c +++ b/drivers/gpu/drm/msm/disp/mdp_format.c @@ -171,7 +171,8 @@ uint32_t mdp_get_formats(uint32_t *pixel_formats, uint32_t max_formats, return i; } -const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format) +const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, + uint64_t modifier) { int i; for (i = 0; i < ARRAY_SIZE(formats); i++) { diff --git a/drivers/gpu/drm/msm/disp/mdp_kms.h b/drivers/gpu/drm/msm/disp/mdp_kms.h index 1185487..4fa8dbe 100644 --- a/drivers/gpu/drm/msm/disp/mdp_kms.h +++ b/drivers/gpu/drm/msm/disp/mdp_kms.h @@ -98,7 +98,7 @@ struct mdp_format { #define MDP_FORMAT_IS_YUV(mdp_format) ((mdp_format)->is_yuv) uint32_t mdp_get_formats(uint32_t *formats, uint32_t max_formats, bool rgb_only); -const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format); +const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, uint64_t modifier); /* MDP capabilities */ #define MDP_CAP_SMP BIT(0) /* Shared Memory Pool */ diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 7a03a94..8baba30 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -173,6 +173,7 @@ struct msm_dsi_host { bool registered; bool power_on; + bool enabled; int irq; }; @@ -775,7 +776,7 @@ static inline enum dsi_cmd_dst_format dsi_get_cmd_fmt( switch (mipi_fmt) { case MIPI_DSI_FMT_RGB888: return CMD_DST_FORMAT_RGB888; case MIPI_DSI_FMT_RGB666_PACKED: - case MIPI_DSI_FMT_RGB666: return VID_DST_FORMAT_RGB666; + case MIPI_DSI_FMT_RGB666: return CMD_DST_FORMAT_RGB666; case MIPI_DSI_FMT_RGB565: return CMD_DST_FORMAT_RGB565; default: return CMD_DST_FORMAT_RGB888; } @@ -986,13 +987,19 @@ static void dsi_set_tx_power_mode(int mode, struct msm_dsi_host *msm_host) static void dsi_wait4video_done(struct msm_dsi_host *msm_host) { + u32 ret = 0; + struct device *dev = &msm_host->pdev->dev; + dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_VIDEO_DONE, 1); reinit_completion(&msm_host->video_comp); - wait_for_completion_timeout(&msm_host->video_comp, + ret = wait_for_completion_timeout(&msm_host->video_comp, msecs_to_jiffies(70)); + if (ret <= 0) + dev_err(dev, "wait for video done timed out\n"); + dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_VIDEO_DONE, 0); } @@ -1001,7 +1008,7 @@ static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host) if (!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO)) return; - if (msm_host->power_on) { + if (msm_host->power_on && msm_host->enabled) { dsi_wait4video_done(msm_host); /* delay 4 ms to skip BLLP */ usleep_range(2000, 4000); @@ -2203,7 +2210,7 @@ int msm_dsi_host_enable(struct mipi_dsi_host *host) * pm_runtime_put_autosuspend(&msm_host->pdev->dev); * } */ - + msm_host->enabled = true; return 0; } @@ -2211,6 +2218,7 @@ int msm_dsi_host_disable(struct mipi_dsi_host *host) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + msm_host->enabled = false; dsi_op_mode_config(msm_host, !!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO), false); diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 8e9d5c2..9a9fa0c 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -265,6 +265,115 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing, return 0; } +int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing, + struct msm_dsi_phy_clk_request *clk_req) +{ + const unsigned long bit_rate = clk_req->bitclk_rate; + const unsigned long esc_rate = clk_req->escclk_rate; + s32 ui, ui_x8, lpx; + s32 tmax, tmin; + s32 pcnt0 = 50; + s32 pcnt1 = 50; + s32 pcnt2 = 10; + s32 pcnt3 = 30; + s32 pcnt4 = 10; + s32 pcnt5 = 2; + s32 coeff = 1000; /* Precision, should avoid overflow */ + s32 hb_en, hb_en_ckln; + s32 temp; + + if (!bit_rate || !esc_rate) + return -EINVAL; + + timing->hs_halfbyte_en = 0; + hb_en = 0; + timing->hs_halfbyte_en_ckln = 0; + hb_en_ckln = 0; + + ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000); + ui_x8 = ui << 3; + lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000); + + temp = S_DIV_ROUND_UP(38 * coeff, ui_x8); + tmin = max_t(s32, temp, 0); + temp = (95 * coeff) / ui_x8; + tmax = max_t(s32, temp, 0); + timing->clk_prepare = linear_inter(tmax, tmin, pcnt0, 0, false); + + temp = 300 * coeff - (timing->clk_prepare << 3) * ui; + tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1; + tmax = (tmin > 255) ? 511 : 255; + timing->clk_zero = linear_inter(tmax, tmin, pcnt5, 0, false); + + tmin = DIV_ROUND_UP(60 * coeff + 3 * ui, ui_x8); + temp = 105 * coeff + 12 * ui - 20 * coeff; + tmax = (temp + 3 * ui) / ui_x8; + timing->clk_trail = linear_inter(tmax, tmin, pcnt3, 0, false); + + temp = S_DIV_ROUND_UP(40 * coeff + 4 * ui, ui_x8); + tmin = max_t(s32, temp, 0); + temp = (85 * coeff + 6 * ui) / ui_x8; + tmax = max_t(s32, temp, 0); + timing->hs_prepare = linear_inter(tmax, tmin, pcnt1, 0, false); + + temp = 145 * coeff + 10 * ui - (timing->hs_prepare << 3) * ui; + tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1; + tmax = 255; + timing->hs_zero = linear_inter(tmax, tmin, pcnt4, 0, false); + + tmin = DIV_ROUND_UP(60 * coeff + 4 * ui, ui_x8) - 1; + temp = 105 * coeff + 12 * ui - 20 * coeff; + tmax = (temp / ui_x8) - 1; + timing->hs_trail = linear_inter(tmax, tmin, pcnt3, 0, false); + + temp = 50 * coeff + ((hb_en << 2) - 8) * ui; + timing->hs_rqst = S_DIV_ROUND_UP(temp, ui_x8); + + tmin = DIV_ROUND_UP(100 * coeff, ui_x8) - 1; + tmax = 255; + timing->hs_exit = linear_inter(tmax, tmin, pcnt2, 0, false); + + temp = 50 * coeff + ((hb_en_ckln << 2) - 8) * ui; + timing->hs_rqst_ckln = S_DIV_ROUND_UP(temp, ui_x8); + + temp = 60 * coeff + 52 * ui - 43 * ui; + tmin = DIV_ROUND_UP(temp, ui_x8) - 1; + tmax = 63; + timing->shared_timings.clk_post = + linear_inter(tmax, tmin, pcnt2, 0, false); + + temp = 8 * ui + (timing->clk_prepare << 3) * ui; + temp += (((timing->clk_zero + 3) << 3) + 11) * ui; + temp += hb_en_ckln ? (((timing->hs_rqst_ckln << 3) + 4) * ui) : + (((timing->hs_rqst_ckln << 3) + 8) * ui); + tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1; + tmax = 63; + if (tmin > tmax) { + temp = linear_inter(tmax << 1, tmin, pcnt2, 0, false); + timing->shared_timings.clk_pre = temp >> 1; + timing->shared_timings.clk_pre_inc_by_2 = 1; + } else { + timing->shared_timings.clk_pre = + linear_inter(tmax, tmin, pcnt2, 0, false); + timing->shared_timings.clk_pre_inc_by_2 = 0; + } + + timing->ta_go = 3; + timing->ta_sure = 0; + timing->ta_get = 4; + + DBG("%d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d", + timing->shared_timings.clk_pre, timing->shared_timings.clk_post, + timing->shared_timings.clk_pre_inc_by_2, timing->clk_zero, + timing->clk_trail, timing->clk_prepare, timing->hs_exit, + timing->hs_zero, timing->hs_prepare, timing->hs_trail, + timing->hs_rqst, timing->hs_rqst_ckln, timing->hs_halfbyte_en, + timing->hs_halfbyte_en_ckln, timing->hs_prep_dly, + timing->hs_prep_dly_ckln); + + return 0; +} + void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg, u32 bit_mask) { diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index c56268c..a24ab80 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -101,6 +101,8 @@ int msm_dsi_dphy_timing_calc(struct msm_dsi_dphy_timing *timing, struct msm_dsi_phy_clk_request *clk_req); int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing, struct msm_dsi_phy_clk_request *clk_req); +int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing, + struct msm_dsi_phy_clk_request *clk_req); void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg, u32 bit_mask); int msm_dsi_phy_init_common(struct msm_dsi_phy *phy); diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index 0af951a..b3fffc8 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -79,34 +79,6 @@ static void dsi_phy_hw_v3_0_lane_settings(struct msm_dsi_phy *phy) dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_TX_DCTRL(3), 0x04); } -static int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing, - struct msm_dsi_phy_clk_request *clk_req) -{ - /* - * TODO: These params need to be computed, they're currently hardcoded - * for a 1440x2560@60Hz panel with a byteclk of 100.618 Mhz, and a - * default escape clock of 19.2 Mhz. - */ - - timing->hs_halfbyte_en = 0; - timing->clk_zero = 0x1c; - timing->clk_prepare = 0x07; - timing->clk_trail = 0x07; - timing->hs_exit = 0x23; - timing->hs_zero = 0x21; - timing->hs_prepare = 0x07; - timing->hs_trail = 0x07; - timing->hs_rqst = 0x05; - timing->ta_sure = 0x00; - timing->ta_go = 0x03; - timing->ta_get = 0x04; - - timing->shared_timings.clk_pre = 0x2d; - timing->shared_timings.clk_post = 0x0d; - - return 0; -} - static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, struct msm_dsi_phy_clk_request *clk_req) { diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c index 0e0c872..7a16242 100644 --- a/drivers/gpu/drm/msm/msm_fb.c +++ b/drivers/gpu/drm/msm/msm_fb.c @@ -183,7 +183,8 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, hsub = drm_format_horz_chroma_subsampling(mode_cmd->pixel_format); vsub = drm_format_vert_chroma_subsampling(mode_cmd->pixel_format); - format = kms->funcs->get_format(kms, mode_cmd->pixel_format); + format = kms->funcs->get_format(kms, mode_cmd->pixel_format, + mode_cmd->modifier[0]); if (!format) { dev_err(dev->dev, "unsupported pixel format: %4.4s\n", (char *)&mode_cmd->pixel_format); diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index c178563..456622b 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -92,8 +92,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper, if (IS_ERR(fb)) { dev_err(dev->dev, "failed to allocate fb\n"); - ret = PTR_ERR(fb); - goto fail; + return PTR_ERR(fb); } bo = msm_framebuffer_bo(fb, 0); @@ -151,13 +150,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper, fail_unlock: mutex_unlock(&dev->struct_mutex); -fail: - - if (ret) { - if (fb) - drm_framebuffer_remove(fb); - } - + drm_framebuffer_remove(fb); return ret; } diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 9519647..f583bb4 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -132,17 +132,19 @@ static void put_pages(struct drm_gem_object *obj) struct msm_gem_object *msm_obj = to_msm_bo(obj); if (msm_obj->pages) { - /* For non-cached buffers, ensure the new pages are clean - * because display controller, GPU, etc. are not coherent: - */ - if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED)) - dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + if (msm_obj->sgt) { + /* For non-cached buffers, ensure the new + * pages are clean because display controller, + * GPU, etc. are not coherent: + */ + if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED)) + dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl, + msm_obj->sgt->nents, + DMA_BIDIRECTIONAL); - if (msm_obj->sgt) sg_free_table(msm_obj->sgt); - - kfree(msm_obj->sgt); + kfree(msm_obj->sgt); + } if (use_pages(obj)) drm_gem_put_pages(obj, msm_obj->pages, true, false); diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index 17d5824..aaa329d 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -48,8 +48,11 @@ struct msm_kms_funcs { /* functions to wait for atomic commit completed on each CRTC */ void (*wait_for_crtc_commit_done)(struct msm_kms *kms, struct drm_crtc *crtc); + /* get msm_format w/ optional format modifiers from drm_mode_fb_cmd2 */ + const struct msm_format *(*get_format)(struct msm_kms *kms, + const uint32_t format, + const uint64_t modifiers); /* misc: */ - const struct msm_format *(*get_format)(struct msm_kms *kms, uint32_t format); long (*round_pixclk)(struct msm_kms *kms, unsigned long rate, struct drm_encoder *encoder); int (*set_split_display)(struct msm_kms *kms, diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c index 5cae8db..ffe5137 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c @@ -99,7 +99,8 @@ static const struct drm_mode_config_funcs mxsfb_mode_config_funcs = { }; static void mxsfb_pipe_enable(struct drm_simple_display_pipe *pipe, - struct drm_crtc_state *crtc_state) + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) { struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe); @@ -125,12 +126,6 @@ static void mxsfb_pipe_update(struct drm_simple_display_pipe *pipe, mxsfb_plane_atomic_update(mxsfb, plane_state); } -static int mxsfb_pipe_prepare_fb(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *plane_state) -{ - return drm_gem_fb_prepare_fb(&pipe->plane, plane_state); -} - static int mxsfb_pipe_enable_vblank(struct drm_simple_display_pipe *pipe) { struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe); @@ -159,7 +154,7 @@ static struct drm_simple_display_pipe_funcs mxsfb_funcs = { .enable = mxsfb_pipe_enable, .disable = mxsfb_pipe_disable, .update = mxsfb_pipe_update, - .prepare_fb = mxsfb_pipe_prepare_fb, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, .enable_vblank = mxsfb_pipe_enable_vblank, .disable_vblank = mxsfb_pipe_disable_vblank, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c index e4c8d31..81c3567 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c @@ -134,7 +134,7 @@ nvkm_cstate_find_best(struct nvkm_clk *clk, struct nvkm_pstate *pstate, nvkm_volt_map(volt, volt->max2_id, clk->temp)); for (cstate = start; &cstate->head != &pstate->list; - cstate = list_entry(cstate->head.prev, typeof(*cstate), head)) { + cstate = list_prev_entry(cstate, head)) { if (nvkm_cstate_valid(clk, cstate, max_volt, clk->temp)) break; } diff --git a/drivers/gpu/drm/omapdrm/dss/dpi.c b/drivers/gpu/drm/omapdrm/dss/dpi.c index fb1c27f..3d662e6 100644 --- a/drivers/gpu/drm/omapdrm/dss/dpi.c +++ b/drivers/gpu/drm/omapdrm/dss/dpi.c @@ -142,7 +142,7 @@ static enum dss_clk_source dpi_get_clk_src(struct dpi_data *dpi) } struct dpi_clk_calc_ctx { - struct dss_pll *pll; + struct dpi_data *dpi; unsigned int clkout_idx; /* inputs */ @@ -191,7 +191,7 @@ static bool dpi_calc_hsdiv_cb(int m_dispc, unsigned long dispc, ctx->pll_cinfo.mX[ctx->clkout_idx] = m_dispc; ctx->pll_cinfo.clkout[ctx->clkout_idx] = dispc; - return dispc_div_calc(ctx->pll->dss->dispc, dispc, + return dispc_div_calc(ctx->dpi->dss->dispc, dispc, ctx->pck_min, ctx->pck_max, dpi_calc_dispc_cb, ctx); } @@ -208,8 +208,8 @@ static bool dpi_calc_pll_cb(int n, int m, unsigned long fint, ctx->pll_cinfo.fint = fint; ctx->pll_cinfo.clkdco = clkdco; - return dss_pll_hsdiv_calc_a(ctx->pll, clkdco, - ctx->pck_min, dss_get_max_fck_rate(ctx->pll->dss), + return dss_pll_hsdiv_calc_a(ctx->dpi->pll, clkdco, + ctx->pck_min, dss_get_max_fck_rate(ctx->dpi->dss), dpi_calc_hsdiv_cb, ctx); } @@ -219,7 +219,7 @@ static bool dpi_calc_dss_cb(unsigned long fck, void *data) ctx->fck = fck; - return dispc_div_calc(ctx->pll->dss->dispc, fck, + return dispc_div_calc(ctx->dpi->dss->dispc, fck, ctx->pck_min, ctx->pck_max, dpi_calc_dispc_cb, ctx); } @@ -230,7 +230,7 @@ static bool dpi_pll_clk_calc(struct dpi_data *dpi, unsigned long pck, unsigned long clkin; memset(ctx, 0, sizeof(*ctx)); - ctx->pll = dpi->pll; + ctx->dpi = dpi; ctx->clkout_idx = dss_pll_get_clkout_idx_for_src(dpi->clk_src); clkin = clk_get_rate(dpi->pll->clkin); @@ -244,7 +244,7 @@ static bool dpi_pll_clk_calc(struct dpi_data *dpi, unsigned long pck, pll_min = 0; pll_max = 0; - return dss_pll_calc_a(ctx->pll, clkin, + return dss_pll_calc_a(ctx->dpi->pll, clkin, pll_min, pll_max, dpi_calc_pll_cb, ctx); } else { /* DSS_PLL_TYPE_B */ @@ -275,6 +275,7 @@ static bool dpi_dss_clk_calc(struct dpi_data *dpi, unsigned long pck, bool ok; memset(ctx, 0, sizeof(*ctx)); + ctx->dpi = dpi; if (pck > 1000 * i * i * i) ctx->pck_min = max(pck - 1000 * i * i * i, 0lu); else diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index 3632854..ef3b0e3 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -319,6 +319,9 @@ static int omap_modeset_init(struct drm_device *dev) dev->mode_config.max_width = 8192; dev->mode_config.max_height = 8192; + /* We want the zpos to be normalized */ + dev->mode_config.normalize_zpos = true; + dev->mode_config.funcs = &omap_mode_config_funcs; dev->mode_config.helper_private = &omap_mode_config_helper_funcs; diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c index 2899435..161233c 100644 --- a/drivers/gpu/drm/omapdrm/omap_plane.c +++ b/drivers/gpu/drm/omapdrm/omap_plane.c @@ -65,7 +65,7 @@ static void omap_plane_atomic_update(struct drm_plane *plane, info.rotation_type = OMAP_DSS_ROT_NONE; info.rotation = DRM_MODE_ROTATE_0; info.global_alpha = 0xff; - info.zorder = state->zpos; + info.zorder = state->normalized_zpos; /* update scanout: */ omap_framebuffer_update_scanout(state->fb, state, &info); diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c index 3106464..19b0d00 100644 --- a/drivers/gpu/drm/pl111/pl111_display.c +++ b/drivers/gpu/drm/pl111/pl111_display.c @@ -120,7 +120,8 @@ static int pl111_display_check(struct drm_simple_display_pipe *pipe, } static void pl111_display_enable(struct drm_simple_display_pipe *pipe, - struct drm_crtc_state *cstate) + struct drm_crtc_state *cstate, + struct drm_plane_state *plane_state) { struct drm_crtc *crtc = &pipe->crtc; struct drm_plane *plane = &pipe->plane; @@ -376,19 +377,13 @@ static void pl111_display_disable_vblank(struct drm_simple_display_pipe *pipe) writel(0, priv->regs + priv->ienb); } -static int pl111_display_prepare_fb(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *plane_state) -{ - return drm_gem_fb_prepare_fb(&pipe->plane, plane_state); -} - static struct drm_simple_display_pipe_funcs pl111_display_funcs = { .mode_valid = pl111_mode_valid, .check = pl111_display_check, .enable = pl111_display_enable, .disable = pl111_display_disable, .update = pl111_display_update, - .prepare_fb = pl111_display_prepare_fb, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, }; static int pl111_clk_div_choose_div(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c index c0fb52c..01665b9 100644 --- a/drivers/gpu/drm/qxl/qxl_cmd.c +++ b/drivers/gpu/drm/qxl/qxl_cmd.c @@ -179,10 +179,9 @@ qxl_push_command_ring_release(struct qxl_device *qdev, struct qxl_release *relea uint32_t type, bool interruptible) { struct qxl_command cmd; - struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head); cmd.type = type; - cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset); + cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset); return qxl_ring_push(qdev->command_ring, &cmd, interruptible); } @@ -192,10 +191,9 @@ qxl_push_cursor_ring_release(struct qxl_device *qdev, struct qxl_release *releas uint32_t type, bool interruptible) { struct qxl_command cmd; - struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head); cmd.type = type; - cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset); + cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset); return qxl_ring_push(qdev->cursor_ring, &cmd, interruptible); } diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index ecb35ed..820cbca 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -1037,7 +1037,7 @@ static int qxl_conn_get_modes(struct drm_connector *connector) return ret; } -static int qxl_conn_mode_valid(struct drm_connector *connector, +static enum drm_mode_status qxl_conn_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct drm_device *ddev = connector->dev; diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 00a1a66..864b456 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -167,6 +167,7 @@ struct qxl_release { int id; int type; + struct qxl_bo *release_bo; uint32_t release_offset; uint32_t surface_release_id; struct ww_acquire_ctx ticket; diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c index e238a1a..6cc9f33 100644 --- a/drivers/gpu/drm/qxl/qxl_ioctl.c +++ b/drivers/gpu/drm/qxl/qxl_ioctl.c @@ -182,9 +182,9 @@ static int qxl_process_single_command(struct qxl_device *qdev, goto out_free_reloc; /* TODO copy slow path code from i915 */ - fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_SIZE)); + fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_MASK)); unwritten = __copy_from_user_inatomic_nocache - (fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_SIZE), + (fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_MASK), u64_to_user_ptr(cmd->command), cmd->command_size); { diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c index 5d84a66..7cb2145 100644 --- a/drivers/gpu/drm/qxl/qxl_release.c +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -173,6 +173,7 @@ qxl_release_free_list(struct qxl_release *release) list_del(&entry->tv.head); kfree(entry); } + release->release_bo = NULL; } void @@ -296,7 +297,6 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev, { if (surface_cmd_type == QXL_SURFACE_CMD_DESTROY && create_rel) { int idr_ret; - struct qxl_bo_list *entry = list_first_entry(&create_rel->bos, struct qxl_bo_list, tv.head); struct qxl_bo *bo; union qxl_release_info *info; @@ -304,8 +304,9 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev, idr_ret = qxl_release_alloc(qdev, QXL_RELEASE_SURFACE_CMD, release); if (idr_ret < 0) return idr_ret; - bo = to_qxl_bo(entry->tv.bo); + bo = create_rel->release_bo; + (*release)->release_bo = bo; (*release)->release_offset = create_rel->release_offset + 64; qxl_release_list_add(*release, bo); @@ -365,6 +366,7 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size, bo = qxl_bo_ref(qdev->current_release_bo[cur_idx]); + (*release)->release_bo = bo; (*release)->release_offset = qdev->current_release_bo_offset[cur_idx] * release_size_per_bo[cur_idx]; qdev->current_release_bo_offset[cur_idx]++; @@ -408,13 +410,12 @@ union qxl_release_info *qxl_release_map(struct qxl_device *qdev, { void *ptr; union qxl_release_info *info; - struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head); - struct qxl_bo *bo = to_qxl_bo(entry->tv.bo); + struct qxl_bo *bo = release->release_bo; - ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_SIZE); + ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_MASK); if (!ptr) return NULL; - info = ptr + (release->release_offset & ~PAGE_SIZE); + info = ptr + (release->release_offset & ~PAGE_MASK); return info; } @@ -422,11 +423,10 @@ void qxl_release_unmap(struct qxl_device *qdev, struct qxl_release *release, union qxl_release_info *info) { - struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head); - struct qxl_bo *bo = to_qxl_bo(entry->tv.bo); + struct qxl_bo *bo = release->release_bo; void *ptr; - ptr = ((void *)info) - (release->release_offset & ~PAGE_SIZE); + ptr = ((void *)info) - (release->release_offset & ~PAGE_MASK); qxl_bo_kunmap_atomic_page(qdev, bo, ptr); } diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index e415d2c..48d0e6b 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -140,6 +140,10 @@ static struct radeon_px_quirk radeon_px_quirk_list[] = { * https://bugs.freedesktop.org/show_bug.cgi?id=101491 */ { PCI_VENDOR_ID_ATI, 0x6741, 0x1043, 0x2122, RADEON_PX_QUIRK_DISABLE_PX }, + /* Asus K73TK laptop with AMD A6-3420M APU and Radeon 7670m GPU + * https://bugzilla.kernel.org/show_bug.cgi?id=51381#c52 + */ + { PCI_VENDOR_ID_ATI, 0x6840, 0x1043, 0x2123, RADEON_PX_QUIRK_DISABLE_PX }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 97a0a63..90d5b41 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -5912,9 +5912,9 @@ static void si_set_pcie_lane_width_in_smc(struct radeon_device *rdev, { u32 lane_width; u32 new_lane_width = - (radeon_new_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT; + ((radeon_new_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT) + 1; u32 current_lane_width = - (radeon_current_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT; + ((radeon_current_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT) + 1; if (new_lane_width != current_lane_width) { radeon_set_pcie_lanes(rdev, new_lane_width); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.h b/drivers/gpu/drm/rcar-du/rcar_du_drv.h index 5c7ec15..131d8e8 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.h @@ -87,7 +87,6 @@ struct rcar_du_device { struct rcar_du_vsp vsps[RCAR_DU_MAX_VSPS]; struct { - struct drm_property *alpha; struct drm_property *colorkey; } props; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c index 0329b35..f4ac0f8 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c @@ -233,15 +233,7 @@ static int rcar_du_atomic_check(struct drm_device *dev, struct rcar_du_device *rcdu = dev->dev_private; int ret; - ret = drm_atomic_helper_check_modeset(dev, state); - if (ret) - return ret; - - ret = drm_atomic_normalize_zpos(dev, state); - if (ret) - return ret; - - ret = drm_atomic_helper_check_planes(dev, state); + ret = drm_atomic_helper_check(dev, state); if (ret) return ret; @@ -415,11 +407,6 @@ static int rcar_du_encoders_init(struct rcar_du_device *rcdu) static int rcar_du_properties_init(struct rcar_du_device *rcdu) { - rcdu->props.alpha = - drm_property_create_range(rcdu->ddev, 0, "alpha", 0, 255); - if (rcdu->props.alpha == NULL) - return -ENOMEM; - /* * The color key is expressed as an RGB888 triplet stored in a 32-bit * integer in XRGB8888 format. Bit 24 is used as a flag to disable (0) @@ -529,6 +516,7 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu) dev->mode_config.min_height = 0; dev->mode_config.max_width = 4095; dev->mode_config.max_height = 2047; + dev->mode_config.normalize_zpos = true; dev->mode_config.funcs = &rcar_du_mode_config_funcs; dev->mode_config.helper_private = &rcar_du_mode_config_helper; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c index 68556bd..c20f7ed 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c @@ -423,7 +423,7 @@ static void rcar_du_plane_setup_mode(struct rcar_du_group *rgrp, rcar_du_plane_write(rgrp, index, PnALPHAR, PnALPHAR_ABIT_0); else rcar_du_plane_write(rgrp, index, PnALPHAR, - PnALPHAR_ABIT_X | state->alpha); + PnALPHAR_ABIT_X | state->state.alpha >> 8); pnmr = PnMR_BM_MD | state->format->pnmr; @@ -692,11 +692,11 @@ static void rcar_du_plane_reset(struct drm_plane *plane) state->hwindex = -1; state->source = RCAR_DU_PLANE_MEMORY; - state->alpha = 255; state->colorkey = RCAR_DU_COLORKEY_NONE; state->state.zpos = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : 1; plane->state = &state->state; + plane->state->alpha = DRM_BLEND_ALPHA_OPAQUE; plane->state->plane = plane; } @@ -708,9 +708,7 @@ static int rcar_du_plane_atomic_set_property(struct drm_plane *plane, struct rcar_du_plane_state *rstate = to_rcar_plane_state(state); struct rcar_du_device *rcdu = to_rcar_plane(plane)->group->dev; - if (property == rcdu->props.alpha) - rstate->alpha = val; - else if (property == rcdu->props.colorkey) + if (property == rcdu->props.colorkey) rstate->colorkey = val; else return -EINVAL; @@ -726,9 +724,7 @@ static int rcar_du_plane_atomic_get_property(struct drm_plane *plane, container_of(state, const struct rcar_du_plane_state, state); struct rcar_du_device *rcdu = to_rcar_plane(plane)->group->dev; - if (property == rcdu->props.alpha) - *val = rstate->alpha; - else if (property == rcdu->props.colorkey) + if (property == rcdu->props.colorkey) *val = rstate->colorkey; else return -EINVAL; @@ -797,10 +793,9 @@ int rcar_du_planes_init(struct rcar_du_group *rgrp) continue; drm_object_attach_property(&plane->plane.base, - rcdu->props.alpha, 255); - drm_object_attach_property(&plane->plane.base, rcdu->props.colorkey, RCAR_DU_COLORKEY_NONE); + drm_plane_create_alpha_property(&plane->plane); drm_plane_create_zpos_property(&plane->plane, 1, 1, 7); } diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.h b/drivers/gpu/drm/rcar-du/rcar_du_plane.h index 890321b..5c19c69 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_plane.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.h @@ -50,7 +50,6 @@ static inline struct rcar_du_plane *to_rcar_plane(struct drm_plane *plane) * @state: base DRM plane state * @format: information about the pixel format used by the plane * @hwindex: 0-based hardware plane index, -1 means unused - * @alpha: value of the plane alpha property * @colorkey: value of the plane colorkey property */ struct rcar_du_plane_state { @@ -60,7 +59,6 @@ struct rcar_du_plane_state { int hwindex; enum rcar_du_plane_source source; - unsigned int alpha; unsigned int colorkey; }; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c index 2c260c3..b3bec01 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c @@ -54,6 +54,7 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc) }; struct rcar_du_plane_state state = { .state = { + .alpha = DRM_BLEND_ALPHA_OPAQUE, .crtc = &crtc->crtc, .dst.x1 = 0, .dst.y1 = 0, @@ -67,7 +68,6 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc) }, .format = rcar_du_format_info(DRM_FORMAT_ARGB8888), .source = RCAR_DU_PLANE_VSPD1, - .alpha = 255, .colorkey = 0, }; @@ -173,7 +173,7 @@ static void rcar_du_vsp_plane_setup(struct rcar_du_vsp_plane *plane) struct vsp1_du_atomic_config cfg = { .pixelformat = 0, .pitch = fb->pitches[0], - .alpha = state->alpha, + .alpha = state->state.alpha >> 8, .zpos = state->state.zpos, }; unsigned int i; @@ -335,44 +335,13 @@ static void rcar_du_vsp_plane_reset(struct drm_plane *plane) if (state == NULL) return; - state->alpha = 255; + state->state.alpha = DRM_BLEND_ALPHA_OPAQUE; state->state.zpos = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : 1; plane->state = &state->state; plane->state->plane = plane; } -static int rcar_du_vsp_plane_atomic_set_property(struct drm_plane *plane, - struct drm_plane_state *state, struct drm_property *property, - uint64_t val) -{ - struct rcar_du_vsp_plane_state *rstate = to_rcar_vsp_plane_state(state); - struct rcar_du_device *rcdu = to_rcar_vsp_plane(plane)->vsp->dev; - - if (property == rcdu->props.alpha) - rstate->alpha = val; - else - return -EINVAL; - - return 0; -} - -static int rcar_du_vsp_plane_atomic_get_property(struct drm_plane *plane, - const struct drm_plane_state *state, struct drm_property *property, - uint64_t *val) -{ - const struct rcar_du_vsp_plane_state *rstate = - container_of(state, const struct rcar_du_vsp_plane_state, state); - struct rcar_du_device *rcdu = to_rcar_vsp_plane(plane)->vsp->dev; - - if (property == rcdu->props.alpha) - *val = rstate->alpha; - else - return -EINVAL; - - return 0; -} - static const struct drm_plane_funcs rcar_du_vsp_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, @@ -380,8 +349,6 @@ static const struct drm_plane_funcs rcar_du_vsp_plane_funcs = { .destroy = drm_plane_cleanup, .atomic_duplicate_state = rcar_du_vsp_plane_atomic_duplicate_state, .atomic_destroy_state = rcar_du_vsp_plane_atomic_destroy_state, - .atomic_set_property = rcar_du_vsp_plane_atomic_set_property, - .atomic_get_property = rcar_du_vsp_plane_atomic_get_property, }; int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np, @@ -438,8 +405,7 @@ int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np, if (type == DRM_PLANE_TYPE_PRIMARY) continue; - drm_object_attach_property(&plane->plane.base, - rcdu->props.alpha, 255); + drm_plane_create_alpha_property(&plane->plane); drm_plane_create_zpos_property(&plane->plane, 1, 1, vsp->num_planes - 1); } diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.h b/drivers/gpu/drm/rcar-du/rcar_du_vsp.h index 4c5d7bb..8a8a25c 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.h @@ -44,15 +44,12 @@ static inline struct rcar_du_vsp_plane *to_rcar_vsp_plane(struct drm_plane *p) * @state: base DRM plane state * @format: information about the pixel format used by the plane * @sg_tables: scatter-gather tables for the frame buffer memory - * @alpha: value of the plane alpha property */ struct rcar_du_vsp_plane_state { struct drm_plane_state state; const struct rcar_du_format_info *format; struct sg_table sg_tables[3]; - - unsigned int alpha; }; static inline struct rcar_du_vsp_plane_state * diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index 3e8bf79..080f053 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -77,13 +77,13 @@ struct rockchip_dp_device { struct analogix_dp_plat_data plat_data; }; -static void analogix_dp_psr_set(struct drm_encoder *encoder, bool enabled) +static int analogix_dp_psr_set(struct drm_encoder *encoder, bool enabled) { struct rockchip_dp_device *dp = to_dp(encoder); int ret; if (!analogix_dp_psr_enabled(dp->adp)) - return; + return 0; DRM_DEV_DEBUG(dp->dev, "%s PSR...\n", enabled ? "Entry" : "Exit"); @@ -91,13 +91,13 @@ static void analogix_dp_psr_set(struct drm_encoder *encoder, bool enabled) PSR_WAIT_LINE_FLAG_TIMEOUT_MS); if (ret) { DRM_DEV_ERROR(dp->dev, "line flag interrupt did not arrive\n"); - return; + return -ETIMEDOUT; } if (enabled) - analogix_dp_enable_psr(dp->adp); + return analogix_dp_enable_psr(dp->adp); else - analogix_dp_disable_psr(dp->adp); + return analogix_dp_disable_psr(dp->adp); } static int rockchip_dp_pre_init(struct rockchip_dp_device *dp) @@ -109,7 +109,7 @@ static int rockchip_dp_pre_init(struct rockchip_dp_device *dp) return 0; } -static int rockchip_dp_poweron(struct analogix_dp_plat_data *plat_data) +static int rockchip_dp_poweron_start(struct analogix_dp_plat_data *plat_data) { struct rockchip_dp_device *dp = to_dp(plat_data); int ret; @@ -127,7 +127,14 @@ static int rockchip_dp_poweron(struct analogix_dp_plat_data *plat_data) return ret; } - return rockchip_drm_psr_activate(&dp->encoder); + return ret; +} + +static int rockchip_dp_poweron_end(struct analogix_dp_plat_data *plat_data) +{ + struct rockchip_dp_device *dp = to_dp(plat_data); + + return rockchip_drm_psr_inhibit_put(&dp->encoder); } static int rockchip_dp_powerdown(struct analogix_dp_plat_data *plat_data) @@ -135,7 +142,7 @@ static int rockchip_dp_powerdown(struct analogix_dp_plat_data *plat_data) struct rockchip_dp_device *dp = to_dp(plat_data); int ret; - ret = rockchip_drm_psr_deactivate(&dp->encoder); + ret = rockchip_drm_psr_inhibit_get(&dp->encoder); if (ret != 0) return ret; @@ -218,6 +225,7 @@ rockchip_dp_drm_encoder_atomic_check(struct drm_encoder *encoder, struct drm_connector_state *conn_state) { struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state); + struct drm_display_info *di = &conn_state->connector->display_info; /* * The hardware IC designed that VOP must output the RGB10 video @@ -229,6 +237,7 @@ rockchip_dp_drm_encoder_atomic_check(struct drm_encoder *encoder, s->output_mode = ROCKCHIP_OUT_MODE_AAAA; s->output_type = DRM_MODE_CONNECTOR_eDP; + s->output_bpc = di->bpc; return 0; } @@ -328,7 +337,8 @@ static int rockchip_dp_bind(struct device *dev, struct device *master, dp->plat_data.encoder = &dp->encoder; dp->plat_data.dev_type = dp->data->chip_type; - dp->plat_data.power_on = rockchip_dp_poweron; + dp->plat_data.power_on_start = rockchip_dp_poweron_start; + dp->plat_data.power_on_end = rockchip_dp_poweron_end; dp->plat_data.power_off = rockchip_dp_powerdown; dp->plat_data.get_modes = rockchip_dp_get_modes; @@ -358,6 +368,8 @@ static void rockchip_dp_unbind(struct device *dev, struct device *master, analogix_dp_unbind(dp->adp); rockchip_drm_psr_unregister(&dp->encoder); dp->encoder.funcs->destroy(&dp->encoder); + + dp->adp = ERR_PTR(-ENODEV); } static const struct component_ops rockchip_dp_component_ops = { @@ -381,6 +393,7 @@ static int rockchip_dp_probe(struct platform_device *pdev) return -ENOMEM; dp->dev = dev; + dp->adp = ERR_PTR(-ENODEV); dp->plat_data.panel = panel; ret = rockchip_dp_of_probe(dp); @@ -404,6 +417,9 @@ static int rockchip_dp_suspend(struct device *dev) { struct rockchip_dp_device *dp = dev_get_drvdata(dev); + if (IS_ERR(dp->adp)) + return 0; + return analogix_dp_suspend(dp->adp); } @@ -411,6 +427,9 @@ static int rockchip_dp_resume(struct device *dev) { struct rockchip_dp_device *dp = dev_get_drvdata(dev); + if (IS_ERR(dp->adp)) + return 0; + return analogix_dp_resume(dp->adp); } #endif diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h index 9c064a4..3a6ebfc 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h @@ -36,6 +36,7 @@ struct rockchip_crtc_state { struct drm_crtc_state base; int output_type; int output_mode; + int output_bpc; }; #define to_rockchip_crtc_state(s) \ container_of(s, struct rockchip_crtc_state, base) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index e266539..d4f4118 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -167,8 +167,67 @@ err_gem_object_unreference: return ERR_PTR(ret); } +static void +rockchip_drm_psr_inhibit_get_state(struct drm_atomic_state *state) +{ + struct drm_crtc *crtc; + struct drm_crtc_state *crtc_state; + struct drm_encoder *encoder; + u32 encoder_mask = 0; + int i; + + for_each_old_crtc_in_state(state, crtc, crtc_state, i) { + encoder_mask |= crtc_state->encoder_mask; + encoder_mask |= crtc->state->encoder_mask; + } + + drm_for_each_encoder_mask(encoder, state->dev, encoder_mask) + rockchip_drm_psr_inhibit_get(encoder); +} + +static void +rockchip_drm_psr_inhibit_put_state(struct drm_atomic_state *state) +{ + struct drm_crtc *crtc; + struct drm_crtc_state *crtc_state; + struct drm_encoder *encoder; + u32 encoder_mask = 0; + int i; + + for_each_old_crtc_in_state(state, crtc, crtc_state, i) { + encoder_mask |= crtc_state->encoder_mask; + encoder_mask |= crtc->state->encoder_mask; + } + + drm_for_each_encoder_mask(encoder, state->dev, encoder_mask) + rockchip_drm_psr_inhibit_put(encoder); +} + +static void +rockchip_atomic_helper_commit_tail_rpm(struct drm_atomic_state *old_state) +{ + struct drm_device *dev = old_state->dev; + + rockchip_drm_psr_inhibit_get_state(old_state); + + drm_atomic_helper_commit_modeset_disables(dev, old_state); + + drm_atomic_helper_commit_modeset_enables(dev, old_state); + + drm_atomic_helper_commit_planes(dev, old_state, + DRM_PLANE_COMMIT_ACTIVE_ONLY); + + rockchip_drm_psr_inhibit_put_state(old_state); + + drm_atomic_helper_commit_hw_done(old_state); + + drm_atomic_helper_wait_for_vblanks(dev, old_state); + + drm_atomic_helper_cleanup_planes(dev, old_state); +} + static const struct drm_mode_config_helper_funcs rockchip_mode_config_helpers = { - .atomic_commit_tail = drm_atomic_helper_commit_tail_rpm, + .atomic_commit_tail = rockchip_atomic_helper_commit_tail_rpm, }; static const struct drm_mode_config_funcs rockchip_drm_mode_config_funcs = { diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index 074db7a..a8db758 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -357,8 +357,8 @@ err_free_rk_obj: } /* - * rockchip_gem_free_object - (struct drm_driver)->gem_free_object callback - * function + * rockchip_gem_free_object - (struct drm_driver)->gem_free_object_unlocked + * callback function */ void rockchip_gem_free_object(struct drm_gem_object *obj) { diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_psr.c b/drivers/gpu/drm/rockchip/rockchip_drm_psr.c index b339ca9..79d00d8 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_psr.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_psr.c @@ -20,42 +20,19 @@ #define PSR_FLUSH_TIMEOUT_MS 100 -enum psr_state { - PSR_FLUSH, - PSR_ENABLE, - PSR_DISABLE, -}; - struct psr_drv { struct list_head list; struct drm_encoder *encoder; struct mutex lock; - bool active; - enum psr_state state; + int inhibit_count; + bool enabled; struct delayed_work flush_work; - void (*set)(struct drm_encoder *encoder, bool enable); + int (*set)(struct drm_encoder *encoder, bool enable); }; -static struct psr_drv *find_psr_by_crtc(struct drm_crtc *crtc) -{ - struct rockchip_drm_private *drm_drv = crtc->dev->dev_private; - struct psr_drv *psr; - - mutex_lock(&drm_drv->psr_list_lock); - list_for_each_entry(psr, &drm_drv->psr_list, list) { - if (psr->encoder->crtc == crtc) - goto out; - } - psr = ERR_PTR(-ENODEV); - -out: - mutex_unlock(&drm_drv->psr_list_lock); - return psr; -} - static struct psr_drv *find_psr_by_encoder(struct drm_encoder *encoder) { struct rockchip_drm_private *drm_drv = encoder->dev->dev_private; @@ -73,46 +50,22 @@ out: return psr; } -static void psr_set_state_locked(struct psr_drv *psr, enum psr_state state) +static int psr_set_state_locked(struct psr_drv *psr, bool enable) { - /* - * Allowed finite state machine: - * - * PSR_ENABLE < = = = = = > PSR_FLUSH - * | ^ | - * | | | - * v | | - * PSR_DISABLE < - - - - - - - - - - */ - if (state == psr->state || !psr->active) - return; - - /* Already disabled in flush, change the state, but not the hardware */ - if (state == PSR_DISABLE && psr->state == PSR_FLUSH) { - psr->state = state; - return; - } + int ret; - psr->state = state; + if (psr->inhibit_count > 0) + return -EINVAL; - /* Actually commit the state change to hardware */ - switch (psr->state) { - case PSR_ENABLE: - psr->set(psr->encoder, true); - break; + if (enable == psr->enabled) + return 0; - case PSR_DISABLE: - case PSR_FLUSH: - psr->set(psr->encoder, false); - break; - } -} + ret = psr->set(psr->encoder, enable); + if (ret) + return ret; -static void psr_set_state(struct psr_drv *psr, enum psr_state state) -{ - mutex_lock(&psr->lock); - psr_set_state_locked(psr, state); - mutex_unlock(&psr->lock); + psr->enabled = enable; + return 0; } static void psr_flush_handler(struct work_struct *work) @@ -120,21 +73,24 @@ static void psr_flush_handler(struct work_struct *work) struct psr_drv *psr = container_of(to_delayed_work(work), struct psr_drv, flush_work); - /* If the state has changed since we initiated the flush, do nothing */ mutex_lock(&psr->lock); - if (psr->state == PSR_FLUSH) - psr_set_state_locked(psr, PSR_ENABLE); + psr_set_state_locked(psr, true); mutex_unlock(&psr->lock); } /** - * rockchip_drm_psr_activate - activate PSR on the given pipe + * rockchip_drm_psr_inhibit_put - release PSR inhibit on given encoder * @encoder: encoder to obtain the PSR encoder * + * Decrements PSR inhibit count on given encoder. Should be called only + * for a PSR inhibit count increment done before. If PSR inhibit counter + * reaches zero, PSR flush work is scheduled to make the hardware enter + * PSR mode in PSR_FLUSH_TIMEOUT_MS. + * * Returns: * Zero on success, negative errno on failure. */ -int rockchip_drm_psr_activate(struct drm_encoder *encoder) +int rockchip_drm_psr_inhibit_put(struct drm_encoder *encoder) { struct psr_drv *psr = find_psr_by_encoder(encoder); @@ -142,21 +98,30 @@ int rockchip_drm_psr_activate(struct drm_encoder *encoder) return PTR_ERR(psr); mutex_lock(&psr->lock); - psr->active = true; + --psr->inhibit_count; + WARN_ON(psr->inhibit_count < 0); + if (!psr->inhibit_count) + mod_delayed_work(system_wq, &psr->flush_work, + PSR_FLUSH_TIMEOUT_MS); mutex_unlock(&psr->lock); return 0; } -EXPORT_SYMBOL(rockchip_drm_psr_activate); +EXPORT_SYMBOL(rockchip_drm_psr_inhibit_put); /** - * rockchip_drm_psr_deactivate - deactivate PSR on the given pipe + * rockchip_drm_psr_inhibit_get - acquire PSR inhibit on given encoder * @encoder: encoder to obtain the PSR encoder * + * Increments PSR inhibit count on given encoder. This function guarantees + * that after it returns PSR is turned off on given encoder and no PSR-related + * hardware state change occurs at least until a matching call to + * rockchip_drm_psr_inhibit_put() is done. + * * Returns: * Zero on success, negative errno on failure. */ -int rockchip_drm_psr_deactivate(struct drm_encoder *encoder) +int rockchip_drm_psr_inhibit_get(struct drm_encoder *encoder) { struct psr_drv *psr = find_psr_by_encoder(encoder); @@ -164,37 +129,25 @@ int rockchip_drm_psr_deactivate(struct drm_encoder *encoder) return PTR_ERR(psr); mutex_lock(&psr->lock); - psr->active = false; + psr_set_state_locked(psr, false); + ++psr->inhibit_count; mutex_unlock(&psr->lock); cancel_delayed_work_sync(&psr->flush_work); return 0; } -EXPORT_SYMBOL(rockchip_drm_psr_deactivate); +EXPORT_SYMBOL(rockchip_drm_psr_inhibit_get); static void rockchip_drm_do_flush(struct psr_drv *psr) { - psr_set_state(psr, PSR_FLUSH); - mod_delayed_work(system_wq, &psr->flush_work, PSR_FLUSH_TIMEOUT_MS); -} - -/** - * rockchip_drm_psr_flush - flush a single pipe - * @crtc: CRTC of the pipe to flush - * - * Returns: - * 0 on success, -errno on fail - */ -int rockchip_drm_psr_flush(struct drm_crtc *crtc) -{ - struct psr_drv *psr = find_psr_by_crtc(crtc); - if (IS_ERR(psr)) - return PTR_ERR(psr); + cancel_delayed_work_sync(&psr->flush_work); - rockchip_drm_do_flush(psr); - return 0; + mutex_lock(&psr->lock); + if (!psr_set_state_locked(psr, false)) + mod_delayed_work(system_wq, &psr->flush_work, + PSR_FLUSH_TIMEOUT_MS); + mutex_unlock(&psr->lock); } -EXPORT_SYMBOL(rockchip_drm_psr_flush); /** * rockchip_drm_psr_flush_all - force to flush all registered PSR encoders @@ -225,11 +178,16 @@ EXPORT_SYMBOL(rockchip_drm_psr_flush_all); * @encoder: encoder that obtain the PSR function * @psr_set: call back to set PSR state * + * The function returns with PSR inhibit counter initialized with one + * and the caller (typically encoder driver) needs to call + * rockchip_drm_psr_inhibit_put() when it becomes ready to accept PSR + * enable request. + * * Returns: * Zero on success, negative errno on failure. */ int rockchip_drm_psr_register(struct drm_encoder *encoder, - void (*psr_set)(struct drm_encoder *, bool enable)) + int (*psr_set)(struct drm_encoder *, bool enable)) { struct rockchip_drm_private *drm_drv = encoder->dev->dev_private; struct psr_drv *psr; @@ -244,8 +202,8 @@ int rockchip_drm_psr_register(struct drm_encoder *encoder, INIT_DELAYED_WORK(&psr->flush_work, psr_flush_handler); mutex_init(&psr->lock); - psr->active = true; - psr->state = PSR_DISABLE; + psr->inhibit_count = 1; + psr->enabled = false; psr->encoder = encoder; psr->set = psr_set; @@ -262,6 +220,11 @@ EXPORT_SYMBOL(rockchip_drm_psr_register); * @encoder: encoder that obtain the PSR function * @psr_set: call back to set PSR state * + * It is expected that the PSR inhibit counter is 1 when this function is + * called, which corresponds to a state when related encoder has been + * disconnected from any CRTCs and its driver called + * rockchip_drm_psr_inhibit_get() to stop the PSR logic. + * * Returns: * Zero on success, negative errno on failure. */ @@ -273,7 +236,12 @@ void rockchip_drm_psr_unregister(struct drm_encoder *encoder) mutex_lock(&drm_drv->psr_list_lock); list_for_each_entry_safe(psr, n, &drm_drv->psr_list, list) { if (psr->encoder == encoder) { - cancel_delayed_work_sync(&psr->flush_work); + /* + * Any other value would mean that the encoder + * is still in use. + */ + WARN_ON(psr->inhibit_count != 1); + list_del(&psr->list); kfree(psr); } diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_psr.h b/drivers/gpu/drm/rockchip/rockchip_drm_psr.h index b1ea015..860c624 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_psr.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_psr.h @@ -16,13 +16,12 @@ #define __ROCKCHIP_DRM_PSR___ void rockchip_drm_psr_flush_all(struct drm_device *dev); -int rockchip_drm_psr_flush(struct drm_crtc *crtc); -int rockchip_drm_psr_activate(struct drm_encoder *encoder); -int rockchip_drm_psr_deactivate(struct drm_encoder *encoder); +int rockchip_drm_psr_inhibit_put(struct drm_encoder *encoder); +int rockchip_drm_psr_inhibit_get(struct drm_encoder *encoder); int rockchip_drm_psr_register(struct drm_encoder *encoder, - void (*psr_set)(struct drm_encoder *, bool enable)); + int (*psr_set)(struct drm_encoder *, bool enable)); void rockchip_drm_psr_unregister(struct drm_encoder *encoder); #endif /* __ROCKCHIP_DRM_PSR__ */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 53d4afe..fe3faa7 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -925,6 +925,12 @@ static void vop_crtc_atomic_enable(struct drm_crtc *crtc, if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA && !(vop_data->feature & VOP_FEATURE_OUTPUT_RGB10)) s->output_mode = ROCKCHIP_OUT_MODE_P888; + + if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA && s->output_bpc == 8) + VOP_REG_SET(vop, common, pre_dither_down, 1); + else + VOP_REG_SET(vop, common, pre_dither_down, 0); + VOP_REG_SET(vop, common, out_mode, s->output_mode); VOP_REG_SET(vop, modeset, htotal_pw, (htotal << 16) | hsync_len); @@ -1017,22 +1023,15 @@ static void vop_crtc_atomic_flush(struct drm_crtc *crtc, continue; drm_framebuffer_get(old_plane_state->fb); + WARN_ON(drm_crtc_vblank_get(crtc) != 0); drm_flip_work_queue(&vop->fb_unref_work, old_plane_state->fb); set_bit(VOP_PENDING_FB_UNREF, &vop->pending); - WARN_ON(drm_crtc_vblank_get(crtc) != 0); } } -static void vop_crtc_atomic_begin(struct drm_crtc *crtc, - struct drm_crtc_state *old_crtc_state) -{ - rockchip_drm_psr_flush(crtc); -} - static const struct drm_crtc_helper_funcs vop_crtc_helper_funcs = { .mode_fixup = vop_crtc_mode_fixup, .atomic_flush = vop_crtc_atomic_flush, - .atomic_begin = vop_crtc_atomic_begin, .atomic_enable = vop_crtc_atomic_enable, .atomic_disable = vop_crtc_atomic_disable, }; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h index 56bbd2e..084acdd 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h @@ -67,6 +67,7 @@ struct vop_common { struct vop_reg cfg_done; struct vop_reg dsp_blank; struct vop_reg data_blank; + struct vop_reg pre_dither_down; struct vop_reg dither_down; struct vop_reg dither_up; struct vop_reg gate_en; diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c index 2e4eea3..08023d3 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c @@ -264,6 +264,7 @@ static const struct vop_common rk3288_common = { .standby = VOP_REG_SYNC(RK3288_SYS_CTRL, 0x1, 22), .gate_en = VOP_REG(RK3288_SYS_CTRL, 0x1, 23), .mmu_en = VOP_REG(RK3288_SYS_CTRL, 0x1, 20), + .pre_dither_down = VOP_REG(RK3288_DSP_CTRL1, 0x1, 1), .dither_down = VOP_REG(RK3288_DSP_CTRL1, 0xf, 1), .dither_up = VOP_REG(RK3288_DSP_CTRL1, 0x1, 6), .data_blank = VOP_REG(RK3288_DSP_CTRL0, 0x1, 19), diff --git a/drivers/gpu/drm/sti/Kconfig b/drivers/gpu/drm/sti/Kconfig index cca4b3c..1963cc1 100644 --- a/drivers/gpu/drm/sti/Kconfig +++ b/drivers/gpu/drm/sti/Kconfig @@ -1,6 +1,6 @@ config DRM_STI tristate "DRM Support for STMicroelectronics SoC stiH4xx Series" - depends on DRM && (ARCH_STI || ARCH_MULTIPLATFORM) + depends on OF && DRM && (ARCH_STI || ARCH_MULTIPLATFORM) select RESET_CONTROLLER select DRM_KMS_HELPER select DRM_GEM_CMA_HELPER @@ -8,6 +8,5 @@ config DRM_STI select DRM_PANEL select FW_LOADER select SND_SOC_HDMI_CODEC if SND_SOC - select OF help Choose this option to enable DRM on STM stiH4xx chipset diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c index 55b6967..90c46b4 100644 --- a/drivers/gpu/drm/sti/sti_drv.c +++ b/drivers/gpu/drm/sti/sti_drv.c @@ -119,30 +119,10 @@ err: return ret; } -static int sti_atomic_check(struct drm_device *dev, - struct drm_atomic_state *state) -{ - int ret; - - ret = drm_atomic_helper_check_modeset(dev, state); - if (ret) - return ret; - - ret = drm_atomic_normalize_zpos(dev, state); - if (ret) - return ret; - - ret = drm_atomic_helper_check_planes(dev, state); - if (ret) - return ret; - - return ret; -} - static const struct drm_mode_config_funcs sti_mode_config_funcs = { .fb_create = drm_gem_fb_create, .output_poll_changed = drm_fb_helper_output_poll_changed, - .atomic_check = sti_atomic_check, + .atomic_check = drm_atomic_helper_check, .atomic_commit = drm_atomic_helper_commit, }; @@ -160,6 +140,8 @@ static void sti_mode_config_init(struct drm_device *dev) dev->mode_config.max_height = STI_MAX_FB_HEIGHT; dev->mode_config.funcs = &sti_mode_config_funcs; + + dev->mode_config.normalize_zpos = true; } DEFINE_DRM_GEM_CMA_FOPS(sti_driver_fops); diff --git a/drivers/gpu/drm/sti/sti_plane.c b/drivers/gpu/drm/sti/sti_plane.c index b074609..b48cd86 100644 --- a/drivers/gpu/drm/sti/sti_plane.c +++ b/drivers/gpu/drm/sti/sti_plane.c @@ -40,6 +40,7 @@ void sti_plane_update_fps(struct sti_plane *plane, bool new_frame, bool new_field) { + struct drm_plane_state *state = plane->drm_plane.state; ktime_t now; struct sti_fps_info *fps; int fpks, fipks, ms_since_last, num_frames, num_fields; @@ -66,14 +67,14 @@ void sti_plane_update_fps(struct sti_plane *plane, fps->last_timestamp = now; fps->last_frame_counter = fps->curr_frame_counter; - if (plane->drm_plane.fb) { + if (state->fb) { fpks = (num_frames * 1000000) / ms_since_last; snprintf(plane->fps_info.fps_str, FPS_LENGTH, "%-8s %4dx%-4d %.4s @ %3d.%-3.3d fps (%s)", plane->drm_plane.name, - plane->drm_plane.fb->width, - plane->drm_plane.fb->height, - (char *)&plane->drm_plane.fb->format->format, + state->fb->width, + state->fb->height, + (char *)&state->fb->format->format, fpks / 1000, fpks % 1000, sti_plane_to_str(plane)); } diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index 9ab00a8..8698e08 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -72,8 +72,6 @@ static struct drm_driver drv_driver = { .gem_prime_vmap = drm_gem_cma_prime_vmap, .gem_prime_vunmap = drm_gem_cma_prime_vunmap, .gem_prime_mmap = drm_gem_cma_prime_mmap, - .enable_vblank = ltdc_crtc_enable_vblank, - .disable_vblank = ltdc_crtc_disable_vblank, }; static int drv_load(struct drm_device *ddev) diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index 1a3277e..e3121d9 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -392,9 +392,6 @@ static void ltdc_crtc_update_clut(struct drm_crtc *crtc) u32 val; int i; - if (!crtc || !crtc->state) - return; - if (!crtc->state->color_mgmt_changed || !crtc->state->gamma_lut) return; @@ -569,9 +566,9 @@ static const struct drm_crtc_helper_funcs ltdc_crtc_helper_funcs = { .atomic_disable = ltdc_crtc_atomic_disable, }; -int ltdc_crtc_enable_vblank(struct drm_device *ddev, unsigned int pipe) +static int ltdc_crtc_enable_vblank(struct drm_crtc *crtc) { - struct ltdc_device *ldev = ddev->dev_private; + struct ltdc_device *ldev = crtc_to_ltdc(crtc); DRM_DEBUG_DRIVER("\n"); reg_set(ldev->regs, LTDC_IER, IER_LIE); @@ -579,9 +576,9 @@ int ltdc_crtc_enable_vblank(struct drm_device *ddev, unsigned int pipe) return 0; } -void ltdc_crtc_disable_vblank(struct drm_device *ddev, unsigned int pipe) +static void ltdc_crtc_disable_vblank(struct drm_crtc *crtc) { - struct ltdc_device *ldev = ddev->dev_private; + struct ltdc_device *ldev = crtc_to_ltdc(crtc); DRM_DEBUG_DRIVER("\n"); reg_clear(ldev->regs, LTDC_IER, IER_LIE); @@ -594,6 +591,8 @@ static const struct drm_crtc_funcs ltdc_crtc_funcs = { .reset = drm_atomic_helper_crtc_reset, .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, + .enable_vblank = ltdc_crtc_enable_vblank, + .disable_vblank = ltdc_crtc_disable_vblank, .gamma_set = drm_atomic_helper_legacy_gamma_set, }; @@ -727,6 +726,8 @@ static void ltdc_plane_atomic_update(struct drm_plane *plane, reg_update_bits(ldev->regs, LTDC_L1CR + lofs, LXCR_LEN | LXCR_CLUTEN, val); + ldev->plane_fpsi[plane->index].counter++; + mutex_lock(&ldev->err_lock); if (ldev->error_status & ISR_FUIF) { DRM_DEBUG_DRIVER("Fifo underrun\n"); @@ -752,6 +753,25 @@ static void ltdc_plane_atomic_disable(struct drm_plane *plane, oldstate->crtc->base.id, plane->base.id); } +static void ltdc_plane_atomic_print_state(struct drm_printer *p, + const struct drm_plane_state *state) +{ + struct drm_plane *plane = state->plane; + struct ltdc_device *ldev = plane_to_ltdc(plane); + struct fps_info *fpsi = &ldev->plane_fpsi[plane->index]; + int ms_since_last; + ktime_t now; + + now = ktime_get(); + ms_since_last = ktime_to_ms(ktime_sub(now, fpsi->last_timestamp)); + + drm_printf(p, "\tuser_updates=%dfps\n", + DIV_ROUND_CLOSEST(fpsi->counter * 1000, ms_since_last)); + + fpsi->last_timestamp = now; + fpsi->counter = 0; +} + static const struct drm_plane_funcs ltdc_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, @@ -759,6 +779,7 @@ static const struct drm_plane_funcs ltdc_plane_funcs = { .reset = drm_atomic_helper_plane_reset, .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, + .atomic_print_state = ltdc_plane_atomic_print_state, }; static const struct drm_plane_helper_funcs ltdc_plane_helper_funcs = { diff --git a/drivers/gpu/drm/stm/ltdc.h b/drivers/gpu/drm/stm/ltdc.h index edb2681..1e16d6a 100644 --- a/drivers/gpu/drm/stm/ltdc.h +++ b/drivers/gpu/drm/stm/ltdc.h @@ -20,6 +20,13 @@ struct ltdc_caps { bool non_alpha_only_l1; /* non-native no-alpha formats on layer 1 */ }; +#define LTDC_MAX_LAYER 4 + +struct fps_info { + unsigned int counter; + ktime_t last_timestamp; +}; + struct ltdc_device { void __iomem *regs; struct clk *pixel_clk; /* lcd pixel clock */ @@ -27,10 +34,9 @@ struct ltdc_device { struct ltdc_caps caps; u32 error_status; u32 irq_status; + struct fps_info plane_fpsi[LTDC_MAX_LAYER]; }; -int ltdc_crtc_enable_vblank(struct drm_device *dev, unsigned int pipe); -void ltdc_crtc_disable_vblank(struct drm_device *dev, unsigned int pipe); int ltdc_load(struct drm_device *ddev); void ltdc_unload(struct drm_device *ddev); diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig index eee6bc0..156a865 100644 --- a/drivers/gpu/drm/sun4i/Kconfig +++ b/drivers/gpu/drm/sun4i/Kconfig @@ -40,6 +40,16 @@ config DRM_SUN4I_BACKEND do some alpha blending and feed graphics to TCON. If M is selected the module will be called sun4i-backend. +config DRM_SUN6I_DSI + tristate "Allwinner A31 MIPI-DSI Controller Support" + default MACH_SUN8I + select CRC_CCITT + select DRM_MIPI_DSI + help + Choose this option if you want have an Allwinner SoC with + MIPI-DSI support. If M is selected the module will be called + sun6i-dsi + config DRM_SUN8I_DW_HDMI tristate "Support for Allwinner version of DesignWare HDMI" depends on DRM_SUN4I diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile index 330843c..2589f4a 100644 --- a/drivers/gpu/drm/sun4i/Makefile +++ b/drivers/gpu/drm/sun4i/Makefile @@ -24,6 +24,9 @@ sun4i-tcon-y += sun4i_lvds.o sun4i-tcon-y += sun4i_tcon.o sun4i-tcon-y += sun4i_rgb.o +sun6i-dsi-y += sun6i_mipi_dphy.o +sun6i-dsi-y += sun6i_mipi_dsi.o + obj-$(CONFIG_DRM_SUN4I) += sun4i-drm.o obj-$(CONFIG_DRM_SUN4I) += sun4i-tcon.o obj-$(CONFIG_DRM_SUN4I) += sun4i_tv.o @@ -31,5 +34,6 @@ obj-$(CONFIG_DRM_SUN4I) += sun6i_drc.o obj-$(CONFIG_DRM_SUN4I_BACKEND) += sun4i-backend.o sun4i-frontend.o obj-$(CONFIG_DRM_SUN4I_HDMI) += sun4i-drm-hdmi.o +obj-$(CONFIG_DRM_SUN6I_DSI) += sun6i-dsi.o obj-$(CONFIG_DRM_SUN8I_DW_HDMI) += sun8i-drm-hdmi.o obj-$(CONFIG_DRM_SUN8I_MIXER) += sun8i-mixer.o diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index 9bad54f..de0a76d 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -295,6 +295,15 @@ int sun4i_backend_update_layer_formats(struct sun4i_backend *backend, DRM_DEBUG_DRIVER("Switching display backend interlaced mode %s\n", interlaced ? "on" : "off"); + val = SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA(state->alpha >> 8); + if (state->alpha != DRM_BLEND_ALPHA_OPAQUE) + val |= SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_EN; + regmap_update_bits(backend->engine.regs, + SUN4I_BACKEND_ATTCTL_REG0(layer), + SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_MASK | + SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_EN, + val); + if (sun4i_backend_format_is_yuv(fb->format->format)) return sun4i_backend_update_yuv_format(backend, layer, plane); @@ -490,7 +499,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine, DRM_DEBUG_DRIVER("Plane FB format is %s\n", drm_get_format_name(fb->format->format, &format_name)); - if (fb->format->has_alpha) + if (fb->format->has_alpha || (plane_state->alpha != DRM_BLEND_ALPHA_OPAQUE)) num_alpha_planes++; if (sun4i_backend_format_is_yuv(fb->format->format)) { @@ -548,7 +557,8 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine, } /* We can't have an alpha plane at the lowest position */ - if (plane_states[0]->fb->format->has_alpha) + if (plane_states[0]->fb->format->has_alpha || + (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE)) return -EINVAL; for (i = 1; i < num_planes; i++) { @@ -560,7 +570,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine, * The only alpha position is the lowest plane of the * second pipe. */ - if (fb->format->has_alpha) + if (fb->format->has_alpha || (p_state->alpha != DRM_BLEND_ALPHA_OPAQUE)) current_pipe++; s_state->pipe = current_pipe; diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.h b/drivers/gpu/drm/sun4i/sun4i_backend.h index 316f217..4caee03 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.h +++ b/drivers/gpu/drm/sun4i/sun4i_backend.h @@ -68,12 +68,15 @@ #define SUN4I_BACKEND_CKMIN_REG 0x884 #define SUN4I_BACKEND_CKCFG_REG 0x888 #define SUN4I_BACKEND_ATTCTL_REG0(l) (0x890 + (0x4 * (l))) +#define SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_MASK GENMASK(31, 24) +#define SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA(x) ((x) << 24) #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PIPESEL_MASK BIT(15) #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PIPESEL(x) ((x) << 15) #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PRISEL_MASK GENMASK(11, 10) #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PRISEL(x) ((x) << 10) #define SUN4I_BACKEND_ATTCTL_REG0_LAY_YUVEN BIT(2) #define SUN4I_BACKEND_ATTCTL_REG0_LAY_VDOEN BIT(1) +#define SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_EN BIT(0) #define SUN4I_BACKEND_ATTCTL_REG1(l) (0x8a0 + (0x4 * (l))) #define SUN4I_BACKEND_ATTCTL_REG1_LAY_HSCAFCT GENMASK(15, 14) diff --git a/drivers/gpu/drm/sun4i/sun4i_layer.c b/drivers/gpu/drm/sun4i/sun4i_layer.c index 2949a3c..750ad24 100644 --- a/drivers/gpu/drm/sun4i/sun4i_layer.c +++ b/drivers/gpu/drm/sun4i/sun4i_layer.c @@ -37,6 +37,7 @@ static void sun4i_backend_layer_reset(struct drm_plane *plane) if (state) { plane->state = &state->state; plane->state->plane = plane; + plane->state->alpha = DRM_BLEND_ALPHA_OPAQUE; plane->state->zpos = layer->id; } } @@ -167,6 +168,7 @@ static struct sun4i_layer *sun4i_layer_init_one(struct drm_device *drm, &sun4i_backend_layer_helper_funcs); layer->backend = backend; + drm_plane_create_alpha_property(&layer->plane); drm_plane_create_zpos_property(&layer->plane, 0, 0, SUN4I_BACKEND_NUM_LAYERS - 1); diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c index bffff4c..be3f14d 100644 --- a/drivers/gpu/drm/sun4i/sun4i_lvds.c +++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c @@ -94,64 +94,9 @@ static void sun4i_lvds_encoder_disable(struct drm_encoder *encoder) } } -static enum drm_mode_status sun4i_lvds_encoder_mode_valid(struct drm_encoder *crtc, - const struct drm_display_mode *mode) -{ - struct sun4i_lvds *lvds = drm_encoder_to_sun4i_lvds(crtc); - struct sun4i_tcon *tcon = lvds->tcon; - u32 hsync = mode->hsync_end - mode->hsync_start; - u32 vsync = mode->vsync_end - mode->vsync_start; - unsigned long rate = mode->clock * 1000; - long rounded_rate; - - DRM_DEBUG_DRIVER("Validating modes...\n"); - - if (hsync < 1) - return MODE_HSYNC_NARROW; - - if (hsync > 0x3ff) - return MODE_HSYNC_WIDE; - - if ((mode->hdisplay < 1) || (mode->htotal < 1)) - return MODE_H_ILLEGAL; - - if ((mode->hdisplay > 0x7ff) || (mode->htotal > 0xfff)) - return MODE_BAD_HVALUE; - - DRM_DEBUG_DRIVER("Horizontal parameters OK\n"); - - if (vsync < 1) - return MODE_VSYNC_NARROW; - - if (vsync > 0x3ff) - return MODE_VSYNC_WIDE; - - if ((mode->vdisplay < 1) || (mode->vtotal < 1)) - return MODE_V_ILLEGAL; - - if ((mode->vdisplay > 0x7ff) || (mode->vtotal > 0xfff)) - return MODE_BAD_VVALUE; - - DRM_DEBUG_DRIVER("Vertical parameters OK\n"); - - tcon->dclk_min_div = 7; - tcon->dclk_max_div = 7; - rounded_rate = clk_round_rate(tcon->dclk, rate); - if (rounded_rate < rate) - return MODE_CLOCK_LOW; - - if (rounded_rate > rate) - return MODE_CLOCK_HIGH; - - DRM_DEBUG_DRIVER("Clock rate OK\n"); - - return MODE_OK; -} - static const struct drm_encoder_helper_funcs sun4i_lvds_enc_helper_funcs = { .disable = sun4i_lvds_encoder_disable, .enable = sun4i_lvds_encoder_enable, - .mode_valid = sun4i_lvds_encoder_mode_valid, }; static const struct drm_encoder_funcs sun4i_lvds_enc_funcs = { diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index c3d92d5..08747fc 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -35,6 +35,7 @@ #include "sun4i_lvds.h" #include "sun4i_rgb.h" #include "sun4i_tcon.h" +#include "sun6i_mipi_dsi.h" #include "sunxi_engine.h" static struct drm_connector *sun4i_tcon_get_connector(const struct drm_encoder *encoder) @@ -169,6 +170,7 @@ void sun4i_tcon_set_status(struct sun4i_tcon *tcon, case DRM_MODE_ENCODER_LVDS: is_lvds = true; /* Fallthrough */ + case DRM_MODE_ENCODER_DSI: case DRM_MODE_ENCODER_NONE: channel = 0; break; @@ -201,7 +203,8 @@ void sun4i_tcon_enable_vblank(struct sun4i_tcon *tcon, bool enable) DRM_DEBUG_DRIVER("%sabling VBLANK interrupt\n", enable ? "En" : "Dis"); mask = SUN4I_TCON_GINT0_VBLANK_ENABLE(0) | - SUN4I_TCON_GINT0_VBLANK_ENABLE(1); + SUN4I_TCON_GINT0_VBLANK_ENABLE(1) | + SUN4I_TCON_GINT0_TCON0_TRI_FINISH_ENABLE; if (enable) val = mask; @@ -273,6 +276,71 @@ static void sun4i_tcon0_mode_set_common(struct sun4i_tcon *tcon, SUN4I_TCON0_BASIC0_Y(mode->crtc_vdisplay)); } +static void sun4i_tcon0_mode_set_cpu(struct sun4i_tcon *tcon, + struct mipi_dsi_device *device, + const struct drm_display_mode *mode) +{ + u8 bpp = mipi_dsi_pixel_format_to_bpp(device->format); + u8 lanes = device->lanes; + u32 block_space, start_delay; + u32 tcon_div; + + tcon->dclk_min_div = 4; + tcon->dclk_max_div = 127; + + sun4i_tcon0_mode_set_common(tcon, mode); + + regmap_update_bits(tcon->regs, SUN4I_TCON0_CTL_REG, + SUN4I_TCON0_CTL_IF_MASK, + SUN4I_TCON0_CTL_IF_8080); + + regmap_write(tcon->regs, SUN4I_TCON_ECC_FIFO_REG, + SUN4I_TCON_ECC_FIFO_EN); + + regmap_write(tcon->regs, SUN4I_TCON0_CPU_IF_REG, + SUN4I_TCON0_CPU_IF_MODE_DSI | + SUN4I_TCON0_CPU_IF_TRI_FIFO_FLUSH | + SUN4I_TCON0_CPU_IF_TRI_FIFO_EN | + SUN4I_TCON0_CPU_IF_TRI_EN); + + /* + * This looks suspicious, but it works... + * + * The datasheet says that this should be set higher than 20 * + * pixel cycle, but it's not clear what a pixel cycle is. + */ + regmap_read(tcon->regs, SUN4I_TCON0_DCLK_REG, &tcon_div); + tcon_div &= GENMASK(6, 0); + block_space = mode->htotal * bpp / (tcon_div * lanes); + block_space -= mode->hdisplay + 40; + + regmap_write(tcon->regs, SUN4I_TCON0_CPU_TRI0_REG, + SUN4I_TCON0_CPU_TRI0_BLOCK_SPACE(block_space) | + SUN4I_TCON0_CPU_TRI0_BLOCK_SIZE(mode->hdisplay)); + + regmap_write(tcon->regs, SUN4I_TCON0_CPU_TRI1_REG, + SUN4I_TCON0_CPU_TRI1_BLOCK_NUM(mode->vdisplay)); + + start_delay = (mode->crtc_vtotal - mode->crtc_vdisplay - 10 - 1); + start_delay = start_delay * mode->crtc_htotal * 149; + start_delay = start_delay / (mode->crtc_clock / 1000) / 8; + regmap_write(tcon->regs, SUN4I_TCON0_CPU_TRI2_REG, + SUN4I_TCON0_CPU_TRI2_TRANS_START_SET(10) | + SUN4I_TCON0_CPU_TRI2_START_DELAY(start_delay)); + + /* + * The Allwinner BSP has a comment that the period should be + * the display clock * 15, but uses an hardcoded 3000... + */ + regmap_write(tcon->regs, SUN4I_TCON_SAFE_PERIOD_REG, + SUN4I_TCON_SAFE_PERIOD_NUM(3000) | + SUN4I_TCON_SAFE_PERIOD_MODE(3)); + + /* Enable the output on the pins */ + regmap_write(tcon->regs, SUN4I_TCON0_IO_TRI_REG, + 0xe0000000); +} + static void sun4i_tcon0_mode_set_lvds(struct sun4i_tcon *tcon, const struct drm_encoder *encoder, const struct drm_display_mode *mode) @@ -538,7 +606,17 @@ void sun4i_tcon_mode_set(struct sun4i_tcon *tcon, const struct drm_encoder *encoder, const struct drm_display_mode *mode) { + struct sun6i_dsi *dsi; + switch (encoder->encoder_type) { + case DRM_MODE_ENCODER_DSI: + /* + * This is not really elegant, but it's the "cleaner" + * way I could think of... + */ + dsi = encoder_to_sun6i_dsi(encoder); + sun4i_tcon0_mode_set_cpu(tcon, dsi->device, mode); + break; case DRM_MODE_ENCODER_LVDS: sun4i_tcon0_mode_set_lvds(tcon, encoder, mode); break; @@ -582,7 +660,8 @@ static irqreturn_t sun4i_tcon_handler(int irq, void *private) regmap_read(tcon->regs, SUN4I_TCON_GINT0_REG, &status); if (!(status & (SUN4I_TCON_GINT0_VBLANK_INT(0) | - SUN4I_TCON_GINT0_VBLANK_INT(1)))) + SUN4I_TCON_GINT0_VBLANK_INT(1) | + SUN4I_TCON_GINT0_TCON0_TRI_FINISH_INT))) return IRQ_NONE; drm_crtc_handle_vblank(&scrtc->crtc); @@ -591,7 +670,8 @@ static irqreturn_t sun4i_tcon_handler(int irq, void *private) /* Acknowledge the interrupt */ regmap_update_bits(tcon->regs, SUN4I_TCON_GINT0_REG, SUN4I_TCON_GINT0_VBLANK_INT(0) | - SUN4I_TCON_GINT0_VBLANK_INT(1), + SUN4I_TCON_GINT0_VBLANK_INT(1) | + SUN4I_TCON_GINT0_TCON0_TRI_FINISH_INT, 0); if (engine->ops->vblank_quirk) diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.h b/drivers/gpu/drm/sun4i/sun4i_tcon.h index 161e094..f6a071c 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.h +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.h @@ -28,13 +28,32 @@ #define SUN4I_TCON_GINT0_REG 0x4 #define SUN4I_TCON_GINT0_VBLANK_ENABLE(pipe) BIT(31 - (pipe)) +#define SUN4I_TCON_GINT0_TCON0_TRI_FINISH_ENABLE BIT(27) +#define SUN4I_TCON_GINT0_TCON0_TRI_COUNTER_ENABLE BIT(26) #define SUN4I_TCON_GINT0_VBLANK_INT(pipe) BIT(15 - (pipe)) +#define SUN4I_TCON_GINT0_TCON0_TRI_FINISH_INT BIT(11) +#define SUN4I_TCON_GINT0_TCON0_TRI_COUNTER_INT BIT(10) #define SUN4I_TCON_GINT1_REG 0x8 + #define SUN4I_TCON_FRM_CTL_REG 0x10 +#define SUN4I_TCON_FRM_CTL_EN BIT(31) + +#define SUN4I_TCON_FRM_SEED_PR_REG 0x14 +#define SUN4I_TCON_FRM_SEED_PG_REG 0x18 +#define SUN4I_TCON_FRM_SEED_PB_REG 0x1c +#define SUN4I_TCON_FRM_SEED_LR_REG 0x20 +#define SUN4I_TCON_FRM_SEED_LG_REG 0x24 +#define SUN4I_TCON_FRM_SEED_LB_REG 0x28 +#define SUN4I_TCON_FRM_TBL0_REG 0x2c +#define SUN4I_TCON_FRM_TBL1_REG 0x30 +#define SUN4I_TCON_FRM_TBL2_REG 0x34 +#define SUN4I_TCON_FRM_TBL3_REG 0x38 #define SUN4I_TCON0_CTL_REG 0x40 #define SUN4I_TCON0_CTL_TCON_ENABLE BIT(31) +#define SUN4I_TCON0_CTL_IF_MASK GENMASK(25, 24) +#define SUN4I_TCON0_CTL_IF_8080 (1 << 24) #define SUN4I_TCON0_CTL_CLK_DELAY_MASK GENMASK(8, 4) #define SUN4I_TCON0_CTL_CLK_DELAY(delay) ((delay << 4) & SUN4I_TCON0_CTL_CLK_DELAY_MASK) #define SUN4I_TCON0_CTL_SRC_SEL_MASK GENMASK(2, 0) @@ -61,7 +80,14 @@ #define SUN4I_TCON0_BASIC3_V_SYNC(height) (((height) - 1) & 0x7ff) #define SUN4I_TCON0_HV_IF_REG 0x58 + #define SUN4I_TCON0_CPU_IF_REG 0x60 +#define SUN4I_TCON0_CPU_IF_MODE_MASK GENMASK(31, 28) +#define SUN4I_TCON0_CPU_IF_MODE_DSI (1 << 28) +#define SUN4I_TCON0_CPU_IF_TRI_FIFO_FLUSH BIT(16) +#define SUN4I_TCON0_CPU_IF_TRI_FIFO_EN BIT(2) +#define SUN4I_TCON0_CPU_IF_TRI_EN BIT(0) + #define SUN4I_TCON0_CPU_WR_REG 0x64 #define SUN4I_TCON0_CPU_RD0_REG 0x68 #define SUN4I_TCON0_CPU_RDA_REG 0x6c @@ -128,6 +154,10 @@ #define SUN4I_TCON1_IO_POL_REG 0xf0 #define SUN4I_TCON1_IO_TRI_REG 0xf4 + +#define SUN4I_TCON_ECC_FIFO_REG 0xf8 +#define SUN4I_TCON_ECC_FIFO_EN BIT(3) + #define SUN4I_TCON_CEU_CTL_REG 0x100 #define SUN4I_TCON_CEU_MUL_RR_REG 0x110 #define SUN4I_TCON_CEU_MUL_RG_REG 0x114 @@ -144,6 +174,22 @@ #define SUN4I_TCON_CEU_RANGE_R_REG 0x140 #define SUN4I_TCON_CEU_RANGE_G_REG 0x144 #define SUN4I_TCON_CEU_RANGE_B_REG 0x148 + +#define SUN4I_TCON0_CPU_TRI0_REG 0x160 +#define SUN4I_TCON0_CPU_TRI0_BLOCK_SPACE(space) ((((space) - 1) & 0xfff) << 16) +#define SUN4I_TCON0_CPU_TRI0_BLOCK_SIZE(size) (((size) - 1) & 0xfff) + +#define SUN4I_TCON0_CPU_TRI1_REG 0x164 +#define SUN4I_TCON0_CPU_TRI1_BLOCK_NUM(num) (((num) - 1) & 0xffff) + +#define SUN4I_TCON0_CPU_TRI2_REG 0x168 +#define SUN4I_TCON0_CPU_TRI2_START_DELAY(delay) (((delay) & 0xffff) << 16) +#define SUN4I_TCON0_CPU_TRI2_TRANS_START_SET(set) ((set) & 0xfff) + +#define SUN4I_TCON_SAFE_PERIOD_REG 0x1f0 +#define SUN4I_TCON_SAFE_PERIOD_NUM(num) (((num) & 0xfff) << 16) +#define SUN4I_TCON_SAFE_PERIOD_MODE(mode) ((mode) & 0x3) + #define SUN4I_TCON_MUX_CTRL_REG 0x200 #define SUN4I_TCON0_LVDS_ANA0_REG 0x220 diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dphy.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dphy.c new file mode 100644 index 0000000..e4d1943 --- /dev/null +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dphy.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2016 Allwinnertech Co., Ltd. + * Copyright (C) 2017-2018 Bootlin + * + * Maxime Ripard <maxime.ripard@free-electrons.com> + */ + +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/of_address.h> +#include <linux/regmap.h> +#include <linux/reset.h> + +#include "sun6i_mipi_dsi.h" + +#define SUN6I_DPHY_GCTL_REG 0x00 +#define SUN6I_DPHY_GCTL_LANE_NUM(n) ((((n) - 1) & 3) << 4) +#define SUN6I_DPHY_GCTL_EN BIT(0) + +#define SUN6I_DPHY_TX_CTL_REG 0x04 +#define SUN6I_DPHY_TX_CTL_HS_TX_CLK_CONT BIT(28) + +#define SUN6I_DPHY_TX_TIME0_REG 0x10 +#define SUN6I_DPHY_TX_TIME0_HS_TRAIL(n) (((n) & 0xff) << 24) +#define SUN6I_DPHY_TX_TIME0_HS_PREPARE(n) (((n) & 0xff) << 16) +#define SUN6I_DPHY_TX_TIME0_LP_CLK_DIV(n) ((n) & 0xff) + +#define SUN6I_DPHY_TX_TIME1_REG 0x14 +#define SUN6I_DPHY_TX_TIME1_CLK_POST(n) (((n) & 0xff) << 24) +#define SUN6I_DPHY_TX_TIME1_CLK_PRE(n) (((n) & 0xff) << 16) +#define SUN6I_DPHY_TX_TIME1_CLK_ZERO(n) (((n) & 0xff) << 8) +#define SUN6I_DPHY_TX_TIME1_CLK_PREPARE(n) ((n) & 0xff) + +#define SUN6I_DPHY_TX_TIME2_REG 0x18 +#define SUN6I_DPHY_TX_TIME2_CLK_TRAIL(n) ((n) & 0xff) + +#define SUN6I_DPHY_TX_TIME3_REG 0x1c + +#define SUN6I_DPHY_TX_TIME4_REG 0x20 +#define SUN6I_DPHY_TX_TIME4_HS_TX_ANA1(n) (((n) & 0xff) << 8) +#define SUN6I_DPHY_TX_TIME4_HS_TX_ANA0(n) ((n) & 0xff) + +#define SUN6I_DPHY_ANA0_REG 0x4c +#define SUN6I_DPHY_ANA0_REG_PWS BIT(31) +#define SUN6I_DPHY_ANA0_REG_DMPC BIT(28) +#define SUN6I_DPHY_ANA0_REG_DMPD(n) (((n) & 0xf) << 24) +#define SUN6I_DPHY_ANA0_REG_SLV(n) (((n) & 7) << 12) +#define SUN6I_DPHY_ANA0_REG_DEN(n) (((n) & 0xf) << 8) + +#define SUN6I_DPHY_ANA1_REG 0x50 +#define SUN6I_DPHY_ANA1_REG_VTTMODE BIT(31) +#define SUN6I_DPHY_ANA1_REG_CSMPS(n) (((n) & 3) << 28) +#define SUN6I_DPHY_ANA1_REG_SVTT(n) (((n) & 0xf) << 24) + +#define SUN6I_DPHY_ANA2_REG 0x54 +#define SUN6I_DPHY_ANA2_EN_P2S_CPU(n) (((n) & 0xf) << 24) +#define SUN6I_DPHY_ANA2_EN_P2S_CPU_MASK GENMASK(27, 24) +#define SUN6I_DPHY_ANA2_EN_CK_CPU BIT(4) +#define SUN6I_DPHY_ANA2_REG_ENIB BIT(1) + +#define SUN6I_DPHY_ANA3_REG 0x58 +#define SUN6I_DPHY_ANA3_EN_VTTD(n) (((n) & 0xf) << 28) +#define SUN6I_DPHY_ANA3_EN_VTTD_MASK GENMASK(31, 28) +#define SUN6I_DPHY_ANA3_EN_VTTC BIT(27) +#define SUN6I_DPHY_ANA3_EN_DIV BIT(26) +#define SUN6I_DPHY_ANA3_EN_LDOC BIT(25) +#define SUN6I_DPHY_ANA3_EN_LDOD BIT(24) +#define SUN6I_DPHY_ANA3_EN_LDOR BIT(18) + +#define SUN6I_DPHY_ANA4_REG 0x5c +#define SUN6I_DPHY_ANA4_REG_DMPLVC BIT(24) +#define SUN6I_DPHY_ANA4_REG_DMPLVD(n) (((n) & 0xf) << 20) +#define SUN6I_DPHY_ANA4_REG_CKDV(n) (((n) & 0x1f) << 12) +#define SUN6I_DPHY_ANA4_REG_TMSC(n) (((n) & 3) << 10) +#define SUN6I_DPHY_ANA4_REG_TMSD(n) (((n) & 3) << 8) +#define SUN6I_DPHY_ANA4_REG_TXDNSC(n) (((n) & 3) << 6) +#define SUN6I_DPHY_ANA4_REG_TXDNSD(n) (((n) & 3) << 4) +#define SUN6I_DPHY_ANA4_REG_TXPUSC(n) (((n) & 3) << 2) +#define SUN6I_DPHY_ANA4_REG_TXPUSD(n) ((n) & 3) + +#define SUN6I_DPHY_DBG5_REG 0xf4 + +int sun6i_dphy_init(struct sun6i_dphy *dphy, unsigned int lanes) +{ + reset_control_deassert(dphy->reset); + clk_prepare_enable(dphy->mod_clk); + clk_set_rate_exclusive(dphy->mod_clk, 150000000); + + regmap_write(dphy->regs, SUN6I_DPHY_TX_CTL_REG, + SUN6I_DPHY_TX_CTL_HS_TX_CLK_CONT); + + regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME0_REG, + SUN6I_DPHY_TX_TIME0_LP_CLK_DIV(14) | + SUN6I_DPHY_TX_TIME0_HS_PREPARE(6) | + SUN6I_DPHY_TX_TIME0_HS_TRAIL(10)); + + regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME1_REG, + SUN6I_DPHY_TX_TIME1_CLK_PREPARE(7) | + SUN6I_DPHY_TX_TIME1_CLK_ZERO(50) | + SUN6I_DPHY_TX_TIME1_CLK_PRE(3) | + SUN6I_DPHY_TX_TIME1_CLK_POST(10)); + + regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME2_REG, + SUN6I_DPHY_TX_TIME2_CLK_TRAIL(30)); + + regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME3_REG, 0); + + regmap_write(dphy->regs, SUN6I_DPHY_TX_TIME4_REG, + SUN6I_DPHY_TX_TIME4_HS_TX_ANA0(3) | + SUN6I_DPHY_TX_TIME4_HS_TX_ANA1(3)); + + regmap_write(dphy->regs, SUN6I_DPHY_GCTL_REG, + SUN6I_DPHY_GCTL_LANE_NUM(lanes) | + SUN6I_DPHY_GCTL_EN); + + return 0; +} + +int sun6i_dphy_power_on(struct sun6i_dphy *dphy, unsigned int lanes) +{ + u8 lanes_mask = GENMASK(lanes - 1, 0); + + regmap_write(dphy->regs, SUN6I_DPHY_ANA0_REG, + SUN6I_DPHY_ANA0_REG_PWS | + SUN6I_DPHY_ANA0_REG_DMPC | + SUN6I_DPHY_ANA0_REG_SLV(7) | + SUN6I_DPHY_ANA0_REG_DMPD(lanes_mask) | + SUN6I_DPHY_ANA0_REG_DEN(lanes_mask)); + + regmap_write(dphy->regs, SUN6I_DPHY_ANA1_REG, + SUN6I_DPHY_ANA1_REG_CSMPS(1) | + SUN6I_DPHY_ANA1_REG_SVTT(7)); + + regmap_write(dphy->regs, SUN6I_DPHY_ANA4_REG, + SUN6I_DPHY_ANA4_REG_CKDV(1) | + SUN6I_DPHY_ANA4_REG_TMSC(1) | + SUN6I_DPHY_ANA4_REG_TMSD(1) | + SUN6I_DPHY_ANA4_REG_TXDNSC(1) | + SUN6I_DPHY_ANA4_REG_TXDNSD(1) | + SUN6I_DPHY_ANA4_REG_TXPUSC(1) | + SUN6I_DPHY_ANA4_REG_TXPUSD(1) | + SUN6I_DPHY_ANA4_REG_DMPLVC | + SUN6I_DPHY_ANA4_REG_DMPLVD(lanes_mask)); + + regmap_write(dphy->regs, SUN6I_DPHY_ANA2_REG, + SUN6I_DPHY_ANA2_REG_ENIB); + udelay(5); + + regmap_write(dphy->regs, SUN6I_DPHY_ANA3_REG, + SUN6I_DPHY_ANA3_EN_LDOR | + SUN6I_DPHY_ANA3_EN_LDOC | + SUN6I_DPHY_ANA3_EN_LDOD); + udelay(1); + + regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA3_REG, + SUN6I_DPHY_ANA3_EN_VTTC | + SUN6I_DPHY_ANA3_EN_VTTD_MASK, + SUN6I_DPHY_ANA3_EN_VTTC | + SUN6I_DPHY_ANA3_EN_VTTD(lanes_mask)); + udelay(1); + + regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA3_REG, + SUN6I_DPHY_ANA3_EN_DIV, + SUN6I_DPHY_ANA3_EN_DIV); + udelay(1); + + regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA2_REG, + SUN6I_DPHY_ANA2_EN_CK_CPU, + SUN6I_DPHY_ANA2_EN_CK_CPU); + udelay(1); + + regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA1_REG, + SUN6I_DPHY_ANA1_REG_VTTMODE, + SUN6I_DPHY_ANA1_REG_VTTMODE); + + regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA2_REG, + SUN6I_DPHY_ANA2_EN_P2S_CPU_MASK, + SUN6I_DPHY_ANA2_EN_P2S_CPU(lanes_mask)); + + return 0; +} + +int sun6i_dphy_power_off(struct sun6i_dphy *dphy) +{ + regmap_update_bits(dphy->regs, SUN6I_DPHY_ANA1_REG, + SUN6I_DPHY_ANA1_REG_VTTMODE, 0); + + return 0; +} + +int sun6i_dphy_exit(struct sun6i_dphy *dphy) +{ + clk_rate_exclusive_put(dphy->mod_clk); + clk_disable_unprepare(dphy->mod_clk); + reset_control_assert(dphy->reset); + + return 0; +} + +static struct regmap_config sun6i_dphy_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + .max_register = SUN6I_DPHY_DBG5_REG, + .name = "mipi-dphy", +}; + +static const struct of_device_id sun6i_dphy_of_table[] = { + { .compatible = "allwinner,sun6i-a31-mipi-dphy" }, + { } +}; + +int sun6i_dphy_probe(struct sun6i_dsi *dsi, struct device_node *node) +{ + struct sun6i_dphy *dphy; + struct resource res; + void __iomem *regs; + int ret; + + if (!of_match_node(sun6i_dphy_of_table, node)) { + dev_err(dsi->dev, "Incompatible D-PHY\n"); + return -EINVAL; + } + + dphy = devm_kzalloc(dsi->dev, sizeof(*dphy), GFP_KERNEL); + if (!dphy) + return -ENOMEM; + + ret = of_address_to_resource(node, 0, &res); + if (ret) { + dev_err(dsi->dev, "phy: Couldn't get our resources\n"); + return ret; + } + + regs = devm_ioremap_resource(dsi->dev, &res); + if (IS_ERR(regs)) { + dev_err(dsi->dev, "Couldn't map the DPHY encoder registers\n"); + return PTR_ERR(regs); + } + + dphy->regs = devm_regmap_init_mmio(dsi->dev, regs, + &sun6i_dphy_regmap_config); + if (IS_ERR(dphy->regs)) { + dev_err(dsi->dev, "Couldn't create the DPHY encoder regmap\n"); + return PTR_ERR(dphy->regs); + } + + dphy->reset = of_reset_control_get_shared(node, NULL); + if (IS_ERR(dphy->reset)) { + dev_err(dsi->dev, "Couldn't get our reset line\n"); + return PTR_ERR(dphy->reset); + } + + dphy->bus_clk = of_clk_get_by_name(node, "bus"); + if (IS_ERR(dphy->bus_clk)) { + dev_err(dsi->dev, "Couldn't get the DPHY bus clock\n"); + ret = PTR_ERR(dphy->bus_clk); + goto err_free_reset; + } + regmap_mmio_attach_clk(dphy->regs, dphy->bus_clk); + + dphy->mod_clk = of_clk_get_by_name(node, "mod"); + if (IS_ERR(dphy->mod_clk)) { + dev_err(dsi->dev, "Couldn't get the DPHY mod clock\n"); + ret = PTR_ERR(dphy->mod_clk); + goto err_free_bus; + } + + dsi->dphy = dphy; + + return 0; + +err_free_bus: + regmap_mmio_detach_clk(dphy->regs); + clk_put(dphy->bus_clk); +err_free_reset: + reset_control_put(dphy->reset); + return ret; +} + +int sun6i_dphy_remove(struct sun6i_dsi *dsi) +{ + struct sun6i_dphy *dphy = dsi->dphy; + + regmap_mmio_detach_clk(dphy->regs); + clk_put(dphy->mod_clk); + clk_put(dphy->bus_clk); + reset_control_put(dphy->reset); + + return 0; +} diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c new file mode 100644 index 0000000..bfbf761 --- /dev/null +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -0,0 +1,1107 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2016 Allwinnertech Co., Ltd. + * Copyright (C) 2017-2018 Bootlin + * + * Maxime Ripard <maxime.ripard@bootlin.com> + */ + +#include <linux/clk.h> +#include <linux/component.h> +#include <linux/crc-ccitt.h> +#include <linux/of_address.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> +#include <linux/reset.h> + +#include <linux/phy/phy.h> + +#include <drm/drmP.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_panel.h> + +#include "sun4i_drv.h" +#include "sun6i_mipi_dsi.h" + +#include <video/mipi_display.h> + +#define SUN6I_DSI_CTL_REG 0x000 +#define SUN6I_DSI_CTL_EN BIT(0) + +#define SUN6I_DSI_BASIC_CTL_REG 0x00c +#define SUN6I_DSI_BASIC_CTL_HBP_DIS BIT(2) +#define SUN6I_DSI_BASIC_CTL_HSA_HSE_DIS BIT(1) +#define SUN6I_DSI_BASIC_CTL_VIDEO_BURST BIT(0) + +#define SUN6I_DSI_BASIC_CTL0_REG 0x010 +#define SUN6I_DSI_BASIC_CTL0_HS_EOTP_EN BIT(18) +#define SUN6I_DSI_BASIC_CTL0_CRC_EN BIT(17) +#define SUN6I_DSI_BASIC_CTL0_ECC_EN BIT(16) +#define SUN6I_DSI_BASIC_CTL0_INST_ST BIT(0) + +#define SUN6I_DSI_BASIC_CTL1_REG 0x014 +#define SUN6I_DSI_BASIC_CTL1_VIDEO_ST_DELAY(n) (((n) & 0x1fff) << 4) +#define SUN6I_DSI_BASIC_CTL1_VIDEO_FILL BIT(2) +#define SUN6I_DSI_BASIC_CTL1_VIDEO_PRECISION BIT(1) +#define SUN6I_DSI_BASIC_CTL1_VIDEO_MODE BIT(0) + +#define SUN6I_DSI_BASIC_SIZE0_REG 0x018 +#define SUN6I_DSI_BASIC_SIZE0_VBP(n) (((n) & 0xfff) << 16) +#define SUN6I_DSI_BASIC_SIZE0_VSA(n) ((n) & 0xfff) + +#define SUN6I_DSI_BASIC_SIZE1_REG 0x01c +#define SUN6I_DSI_BASIC_SIZE1_VT(n) (((n) & 0xfff) << 16) +#define SUN6I_DSI_BASIC_SIZE1_VACT(n) ((n) & 0xfff) + +#define SUN6I_DSI_INST_FUNC_REG(n) (0x020 + (n) * 0x04) +#define SUN6I_DSI_INST_FUNC_INST_MODE(n) (((n) & 0xf) << 28) +#define SUN6I_DSI_INST_FUNC_ESCAPE_ENTRY(n) (((n) & 0xf) << 24) +#define SUN6I_DSI_INST_FUNC_TRANS_PACKET(n) (((n) & 0xf) << 20) +#define SUN6I_DSI_INST_FUNC_LANE_CEN BIT(4) +#define SUN6I_DSI_INST_FUNC_LANE_DEN(n) ((n) & 0xf) + +#define SUN6I_DSI_INST_LOOP_SEL_REG 0x040 + +#define SUN6I_DSI_INST_LOOP_NUM_REG(n) (0x044 + (n) * 0x10) +#define SUN6I_DSI_INST_LOOP_NUM_N1(n) (((n) & 0xfff) << 16) +#define SUN6I_DSI_INST_LOOP_NUM_N0(n) ((n) & 0xfff) + +#define SUN6I_DSI_INST_JUMP_SEL_REG 0x048 + +#define SUN6I_DSI_INST_JUMP_CFG_REG(n) (0x04c + (n) * 0x04) +#define SUN6I_DSI_INST_JUMP_CFG_TO(n) (((n) & 0xf) << 20) +#define SUN6I_DSI_INST_JUMP_CFG_POINT(n) (((n) & 0xf) << 16) +#define SUN6I_DSI_INST_JUMP_CFG_NUM(n) ((n) & 0xffff) + +#define SUN6I_DSI_TRANS_START_REG 0x060 + +#define SUN6I_DSI_TRANS_ZERO_REG 0x078 + +#define SUN6I_DSI_TCON_DRQ_REG 0x07c +#define SUN6I_DSI_TCON_DRQ_ENABLE_MODE BIT(28) +#define SUN6I_DSI_TCON_DRQ_SET(n) ((n) & 0x3ff) + +#define SUN6I_DSI_PIXEL_CTL0_REG 0x080 +#define SUN6I_DSI_PIXEL_CTL0_PD_PLUG_DISABLE BIT(16) +#define SUN6I_DSI_PIXEL_CTL0_FORMAT(n) ((n) & 0xf) + +#define SUN6I_DSI_PIXEL_CTL1_REG 0x084 + +#define SUN6I_DSI_PIXEL_PH_REG 0x090 +#define SUN6I_DSI_PIXEL_PH_ECC(n) (((n) & 0xff) << 24) +#define SUN6I_DSI_PIXEL_PH_WC(n) (((n) & 0xffff) << 8) +#define SUN6I_DSI_PIXEL_PH_VC(n) (((n) & 3) << 6) +#define SUN6I_DSI_PIXEL_PH_DT(n) ((n) & 0x3f) + +#define SUN6I_DSI_PIXEL_PF0_REG 0x098 +#define SUN6I_DSI_PIXEL_PF0_CRC_FORCE(n) ((n) & 0xffff) + +#define SUN6I_DSI_PIXEL_PF1_REG 0x09c +#define SUN6I_DSI_PIXEL_PF1_CRC_INIT_LINEN(n) (((n) & 0xffff) << 16) +#define SUN6I_DSI_PIXEL_PF1_CRC_INIT_LINE0(n) ((n) & 0xffff) + +#define SUN6I_DSI_SYNC_HSS_REG 0x0b0 + +#define SUN6I_DSI_SYNC_HSE_REG 0x0b4 + +#define SUN6I_DSI_SYNC_VSS_REG 0x0b8 + +#define SUN6I_DSI_SYNC_VSE_REG 0x0bc + +#define SUN6I_DSI_BLK_HSA0_REG 0x0c0 + +#define SUN6I_DSI_BLK_HSA1_REG 0x0c4 +#define SUN6I_DSI_BLK_PF(n) (((n) & 0xffff) << 16) +#define SUN6I_DSI_BLK_PD(n) ((n) & 0xff) + +#define SUN6I_DSI_BLK_HBP0_REG 0x0c8 + +#define SUN6I_DSI_BLK_HBP1_REG 0x0cc + +#define SUN6I_DSI_BLK_HFP0_REG 0x0d0 + +#define SUN6I_DSI_BLK_HFP1_REG 0x0d4 + +#define SUN6I_DSI_BLK_HBLK0_REG 0x0e0 + +#define SUN6I_DSI_BLK_HBLK1_REG 0x0e4 + +#define SUN6I_DSI_BLK_VBLK0_REG 0x0e8 + +#define SUN6I_DSI_BLK_VBLK1_REG 0x0ec + +#define SUN6I_DSI_BURST_LINE_REG 0x0f0 +#define SUN6I_DSI_BURST_LINE_SYNC_POINT(n) (((n) & 0xffff) << 16) +#define SUN6I_DSI_BURST_LINE_NUM(n) ((n) & 0xffff) + +#define SUN6I_DSI_BURST_DRQ_REG 0x0f4 +#define SUN6I_DSI_BURST_DRQ_EDGE1(n) (((n) & 0xffff) << 16) +#define SUN6I_DSI_BURST_DRQ_EDGE0(n) ((n) & 0xffff) + +#define SUN6I_DSI_CMD_CTL_REG 0x200 +#define SUN6I_DSI_CMD_CTL_RX_OVERFLOW BIT(26) +#define SUN6I_DSI_CMD_CTL_RX_FLAG BIT(25) +#define SUN6I_DSI_CMD_CTL_TX_FLAG BIT(9) + +#define SUN6I_DSI_CMD_RX_REG(n) (0x240 + (n) * 0x04) + +#define SUN6I_DSI_DEBUG_DATA_REG 0x2f8 + +#define SUN6I_DSI_CMD_TX_REG(n) (0x300 + (n) * 0x04) + +enum sun6i_dsi_start_inst { + DSI_START_LPRX, + DSI_START_LPTX, + DSI_START_HSC, + DSI_START_HSD, +}; + +enum sun6i_dsi_inst_id { + DSI_INST_ID_LP11 = 0, + DSI_INST_ID_TBA, + DSI_INST_ID_HSC, + DSI_INST_ID_HSD, + DSI_INST_ID_LPDT, + DSI_INST_ID_HSCEXIT, + DSI_INST_ID_NOP, + DSI_INST_ID_DLY, + DSI_INST_ID_END = 15, +}; + +enum sun6i_dsi_inst_mode { + DSI_INST_MODE_STOP = 0, + DSI_INST_MODE_TBA, + DSI_INST_MODE_HS, + DSI_INST_MODE_ESCAPE, + DSI_INST_MODE_HSCEXIT, + DSI_INST_MODE_NOP, +}; + +enum sun6i_dsi_inst_escape { + DSI_INST_ESCA_LPDT = 0, + DSI_INST_ESCA_ULPS, + DSI_INST_ESCA_UN1, + DSI_INST_ESCA_UN2, + DSI_INST_ESCA_RESET, + DSI_INST_ESCA_UN3, + DSI_INST_ESCA_UN4, + DSI_INST_ESCA_UN5, +}; + +enum sun6i_dsi_inst_packet { + DSI_INST_PACK_PIXEL = 0, + DSI_INST_PACK_COMMAND, +}; + +static const u32 sun6i_dsi_ecc_array[] = { + [0] = (BIT(0) | BIT(1) | BIT(2) | BIT(4) | BIT(5) | BIT(7) | BIT(10) | + BIT(11) | BIT(13) | BIT(16) | BIT(20) | BIT(21) | BIT(22) | + BIT(23)), + [1] = (BIT(0) | BIT(1) | BIT(3) | BIT(4) | BIT(6) | BIT(8) | BIT(10) | + BIT(12) | BIT(14) | BIT(17) | BIT(20) | BIT(21) | BIT(22) | + BIT(23)), + [2] = (BIT(0) | BIT(2) | BIT(3) | BIT(5) | BIT(6) | BIT(9) | BIT(11) | + BIT(12) | BIT(15) | BIT(18) | BIT(20) | BIT(21) | BIT(22)), + [3] = (BIT(1) | BIT(2) | BIT(3) | BIT(7) | BIT(8) | BIT(9) | BIT(13) | + BIT(14) | BIT(15) | BIT(19) | BIT(20) | BIT(21) | BIT(23)), + [4] = (BIT(4) | BIT(5) | BIT(6) | BIT(7) | BIT(8) | BIT(9) | BIT(16) | + BIT(17) | BIT(18) | BIT(19) | BIT(20) | BIT(22) | BIT(23)), + [5] = (BIT(10) | BIT(11) | BIT(12) | BIT(13) | BIT(14) | BIT(15) | + BIT(16) | BIT(17) | BIT(18) | BIT(19) | BIT(21) | BIT(22) | + BIT(23)), +}; + +static u32 sun6i_dsi_ecc_compute(unsigned int data) +{ + int i; + u8 ecc = 0; + + for (i = 0; i < ARRAY_SIZE(sun6i_dsi_ecc_array); i++) { + u32 field = sun6i_dsi_ecc_array[i]; + bool init = false; + u8 val = 0; + int j; + + for (j = 0; j < 24; j++) { + if (!(BIT(j) & field)) + continue; + + if (!init) { + val = (BIT(j) & data) ? 1 : 0; + init = true; + } else { + val ^= (BIT(j) & data) ? 1 : 0; + } + } + + ecc |= val << i; + } + + return ecc; +} + +static u16 sun6i_dsi_crc_compute(u8 const *buffer, size_t len) +{ + return crc_ccitt(0xffff, buffer, len); +} + +static u16 sun6i_dsi_crc_repeat_compute(u8 pd, size_t len) +{ + u8 buffer[len]; + + memset(buffer, pd, len); + + return sun6i_dsi_crc_compute(buffer, len); +} + +static u32 sun6i_dsi_build_sync_pkt(u8 dt, u8 vc, u8 d0, u8 d1) +{ + u32 val = dt & 0x3f; + + val |= (vc & 3) << 6; + val |= (d0 & 0xff) << 8; + val |= (d1 & 0xff) << 16; + val |= sun6i_dsi_ecc_compute(val) << 24; + + return val; +} + +static u32 sun6i_dsi_build_blk0_pkt(u8 vc, u16 wc) +{ + return sun6i_dsi_build_sync_pkt(MIPI_DSI_BLANKING_PACKET, vc, + wc & 0xff, wc >> 8); +} + +static u32 sun6i_dsi_build_blk1_pkt(u16 pd, size_t len) +{ + u32 val = SUN6I_DSI_BLK_PD(pd); + + return val | SUN6I_DSI_BLK_PF(sun6i_dsi_crc_repeat_compute(pd, len)); +} + +static void sun6i_dsi_inst_abort(struct sun6i_dsi *dsi) +{ + regmap_update_bits(dsi->regs, SUN6I_DSI_BASIC_CTL0_REG, + SUN6I_DSI_BASIC_CTL0_INST_ST, 0); +} + +static void sun6i_dsi_inst_commit(struct sun6i_dsi *dsi) +{ + regmap_update_bits(dsi->regs, SUN6I_DSI_BASIC_CTL0_REG, + SUN6I_DSI_BASIC_CTL0_INST_ST, + SUN6I_DSI_BASIC_CTL0_INST_ST); +} + +static int sun6i_dsi_inst_wait_for_completion(struct sun6i_dsi *dsi) +{ + u32 val; + + return regmap_read_poll_timeout(dsi->regs, SUN6I_DSI_BASIC_CTL0_REG, + val, + !(val & SUN6I_DSI_BASIC_CTL0_INST_ST), + 100, 5000); +} + +static void sun6i_dsi_inst_setup(struct sun6i_dsi *dsi, + enum sun6i_dsi_inst_id id, + enum sun6i_dsi_inst_mode mode, + bool clock, u8 data, + enum sun6i_dsi_inst_packet packet, + enum sun6i_dsi_inst_escape escape) +{ + regmap_write(dsi->regs, SUN6I_DSI_INST_FUNC_REG(id), + SUN6I_DSI_INST_FUNC_INST_MODE(mode) | + SUN6I_DSI_INST_FUNC_ESCAPE_ENTRY(escape) | + SUN6I_DSI_INST_FUNC_TRANS_PACKET(packet) | + (clock ? SUN6I_DSI_INST_FUNC_LANE_CEN : 0) | + SUN6I_DSI_INST_FUNC_LANE_DEN(data)); +} + +static void sun6i_dsi_inst_init(struct sun6i_dsi *dsi, + struct mipi_dsi_device *device) +{ + u8 lanes_mask = GENMASK(device->lanes - 1, 0); + + sun6i_dsi_inst_setup(dsi, DSI_INST_ID_LP11, DSI_INST_MODE_STOP, + true, lanes_mask, 0, 0); + + sun6i_dsi_inst_setup(dsi, DSI_INST_ID_TBA, DSI_INST_MODE_TBA, + false, 1, 0, 0); + + sun6i_dsi_inst_setup(dsi, DSI_INST_ID_HSC, DSI_INST_MODE_HS, + true, 0, DSI_INST_PACK_PIXEL, 0); + + sun6i_dsi_inst_setup(dsi, DSI_INST_ID_HSD, DSI_INST_MODE_HS, + false, lanes_mask, DSI_INST_PACK_PIXEL, 0); + + sun6i_dsi_inst_setup(dsi, DSI_INST_ID_LPDT, DSI_INST_MODE_ESCAPE, + false, 1, DSI_INST_PACK_COMMAND, + DSI_INST_ESCA_LPDT); + + sun6i_dsi_inst_setup(dsi, DSI_INST_ID_HSCEXIT, DSI_INST_MODE_HSCEXIT, + true, 0, 0, 0); + + sun6i_dsi_inst_setup(dsi, DSI_INST_ID_NOP, DSI_INST_MODE_STOP, + false, lanes_mask, 0, 0); + + sun6i_dsi_inst_setup(dsi, DSI_INST_ID_DLY, DSI_INST_MODE_NOP, + true, lanes_mask, 0, 0); + + regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_CFG_REG(0), + SUN6I_DSI_INST_JUMP_CFG_POINT(DSI_INST_ID_NOP) | + SUN6I_DSI_INST_JUMP_CFG_TO(DSI_INST_ID_HSCEXIT) | + SUN6I_DSI_INST_JUMP_CFG_NUM(1)); +}; + +static u16 sun6i_dsi_get_video_start_delay(struct sun6i_dsi *dsi, + struct drm_display_mode *mode) +{ + return mode->vtotal - (mode->vsync_end - mode->vdisplay) + 1; +} + +static void sun6i_dsi_setup_burst(struct sun6i_dsi *dsi, + struct drm_display_mode *mode) +{ + struct mipi_dsi_device *device = dsi->device; + u32 val = 0; + + if ((mode->hsync_end - mode->hdisplay) > 20) { + /* Maaaaaagic */ + u16 drq = (mode->hsync_end - mode->hdisplay) - 20; + + drq *= mipi_dsi_pixel_format_to_bpp(device->format); + drq /= 32; + + val = (SUN6I_DSI_TCON_DRQ_ENABLE_MODE | + SUN6I_DSI_TCON_DRQ_SET(drq)); + } + + regmap_write(dsi->regs, SUN6I_DSI_TCON_DRQ_REG, val); +} + +static void sun6i_dsi_setup_inst_loop(struct sun6i_dsi *dsi, + struct drm_display_mode *mode) +{ + u16 delay = 50 - 1; + + regmap_write(dsi->regs, SUN6I_DSI_INST_LOOP_NUM_REG(0), + SUN6I_DSI_INST_LOOP_NUM_N0(50 - 1) | + SUN6I_DSI_INST_LOOP_NUM_N1(delay)); + regmap_write(dsi->regs, SUN6I_DSI_INST_LOOP_NUM_REG(1), + SUN6I_DSI_INST_LOOP_NUM_N0(50 - 1) | + SUN6I_DSI_INST_LOOP_NUM_N1(delay)); +} + +static void sun6i_dsi_setup_format(struct sun6i_dsi *dsi, + struct drm_display_mode *mode) +{ + struct mipi_dsi_device *device = dsi->device; + u32 val = SUN6I_DSI_PIXEL_PH_VC(device->channel); + u8 dt, fmt; + u16 wc; + + /* + * TODO: The format defines are only valid in video mode and + * change in command mode. + */ + switch (device->format) { + case MIPI_DSI_FMT_RGB888: + dt = MIPI_DSI_PACKED_PIXEL_STREAM_24; + fmt = 8; + break; + case MIPI_DSI_FMT_RGB666: + dt = MIPI_DSI_PIXEL_STREAM_3BYTE_18; + fmt = 9; + break; + case MIPI_DSI_FMT_RGB666_PACKED: + dt = MIPI_DSI_PACKED_PIXEL_STREAM_18; + fmt = 10; + break; + case MIPI_DSI_FMT_RGB565: + dt = MIPI_DSI_PACKED_PIXEL_STREAM_16; + fmt = 11; + break; + default: + return; + } + val |= SUN6I_DSI_PIXEL_PH_DT(dt); + + wc = mode->hdisplay * mipi_dsi_pixel_format_to_bpp(device->format) / 8; + val |= SUN6I_DSI_PIXEL_PH_WC(wc); + val |= SUN6I_DSI_PIXEL_PH_ECC(sun6i_dsi_ecc_compute(val)); + + regmap_write(dsi->regs, SUN6I_DSI_PIXEL_PH_REG, val); + + regmap_write(dsi->regs, SUN6I_DSI_PIXEL_PF0_REG, + SUN6I_DSI_PIXEL_PF0_CRC_FORCE(0xffff)); + + regmap_write(dsi->regs, SUN6I_DSI_PIXEL_PF1_REG, + SUN6I_DSI_PIXEL_PF1_CRC_INIT_LINE0(0xffff) | + SUN6I_DSI_PIXEL_PF1_CRC_INIT_LINEN(0xffff)); + + regmap_write(dsi->regs, SUN6I_DSI_PIXEL_CTL0_REG, + SUN6I_DSI_PIXEL_CTL0_PD_PLUG_DISABLE | + SUN6I_DSI_PIXEL_CTL0_FORMAT(fmt)); +} + +static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi, + struct drm_display_mode *mode) +{ + struct mipi_dsi_device *device = dsi->device; + unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8; + u16 hbp, hfp, hsa, hblk, vblk; + + regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL_REG, 0); + + regmap_write(dsi->regs, SUN6I_DSI_SYNC_HSS_REG, + sun6i_dsi_build_sync_pkt(MIPI_DSI_H_SYNC_START, + device->channel, + 0, 0)); + + regmap_write(dsi->regs, SUN6I_DSI_SYNC_HSE_REG, + sun6i_dsi_build_sync_pkt(MIPI_DSI_H_SYNC_END, + device->channel, + 0, 0)); + + regmap_write(dsi->regs, SUN6I_DSI_SYNC_VSS_REG, + sun6i_dsi_build_sync_pkt(MIPI_DSI_V_SYNC_START, + device->channel, + 0, 0)); + + regmap_write(dsi->regs, SUN6I_DSI_SYNC_VSE_REG, + sun6i_dsi_build_sync_pkt(MIPI_DSI_V_SYNC_END, + device->channel, + 0, 0)); + + regmap_write(dsi->regs, SUN6I_DSI_BASIC_SIZE0_REG, + SUN6I_DSI_BASIC_SIZE0_VSA(mode->vsync_end - + mode->vsync_start) | + SUN6I_DSI_BASIC_SIZE0_VBP(mode->vsync_start - + mode->vdisplay)); + + regmap_write(dsi->regs, SUN6I_DSI_BASIC_SIZE1_REG, + SUN6I_DSI_BASIC_SIZE1_VACT(mode->vdisplay) | + SUN6I_DSI_BASIC_SIZE1_VT(mode->vtotal)); + + /* + * A sync period is composed of a blanking packet (4 bytes + + * payload + 2 bytes) and a sync event packet (4 bytes). Its + * minimal size is therefore 10 bytes + */ +#define HSA_PACKET_OVERHEAD 10 + hsa = max((unsigned int)HSA_PACKET_OVERHEAD, + (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD); + regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA0_REG, + sun6i_dsi_build_blk0_pkt(device->channel, hsa)); + regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA1_REG, + sun6i_dsi_build_blk1_pkt(0, hsa)); + + /* + * The backporch is set using a blanking packet (4 bytes + + * payload + 2 bytes). Its minimal size is therefore 6 bytes + */ +#define HBP_PACKET_OVERHEAD 6 + hbp = max((unsigned int)HBP_PACKET_OVERHEAD, + (mode->hsync_start - mode->hdisplay) * Bpp - HBP_PACKET_OVERHEAD); + regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP0_REG, + sun6i_dsi_build_blk0_pkt(device->channel, hbp)); + regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP1_REG, + sun6i_dsi_build_blk1_pkt(0, hbp)); + + /* + * The frontporch is set using a blanking packet (4 bytes + + * payload + 2 bytes). Its minimal size is therefore 6 bytes + */ +#define HFP_PACKET_OVERHEAD 6 + hfp = max((unsigned int)HFP_PACKET_OVERHEAD, + (mode->htotal - mode->hsync_end) * Bpp - HFP_PACKET_OVERHEAD); + regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP0_REG, + sun6i_dsi_build_blk0_pkt(device->channel, hfp)); + regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP1_REG, + sun6i_dsi_build_blk1_pkt(0, hfp)); + + /* + * hblk seems to be the line + porches length. + */ + hblk = mode->htotal * Bpp - hsa; + regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK0_REG, + sun6i_dsi_build_blk0_pkt(device->channel, hblk)); + regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK1_REG, + sun6i_dsi_build_blk1_pkt(0, hblk)); + + /* + * And I'm not entirely sure what vblk is about. The driver in + * Allwinner BSP is using a rather convoluted calculation + * there only for 4 lanes. However, using 0 (the !4 lanes + * case) even with a 4 lanes screen seems to work... + */ + vblk = 0; + regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK0_REG, + sun6i_dsi_build_blk0_pkt(device->channel, vblk)); + regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK1_REG, + sun6i_dsi_build_blk1_pkt(0, vblk)); +} + +static int sun6i_dsi_start(struct sun6i_dsi *dsi, + enum sun6i_dsi_start_inst func) +{ + switch (func) { + case DSI_START_LPTX: + regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG, + DSI_INST_ID_LPDT << (4 * DSI_INST_ID_LP11) | + DSI_INST_ID_END << (4 * DSI_INST_ID_LPDT)); + break; + case DSI_START_LPRX: + regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG, + DSI_INST_ID_LPDT << (4 * DSI_INST_ID_LP11) | + DSI_INST_ID_DLY << (4 * DSI_INST_ID_LPDT) | + DSI_INST_ID_TBA << (4 * DSI_INST_ID_DLY) | + DSI_INST_ID_END << (4 * DSI_INST_ID_TBA)); + break; + case DSI_START_HSC: + regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG, + DSI_INST_ID_HSC << (4 * DSI_INST_ID_LP11) | + DSI_INST_ID_END << (4 * DSI_INST_ID_HSC)); + break; + case DSI_START_HSD: + regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG, + DSI_INST_ID_NOP << (4 * DSI_INST_ID_LP11) | + DSI_INST_ID_HSD << (4 * DSI_INST_ID_NOP) | + DSI_INST_ID_DLY << (4 * DSI_INST_ID_HSD) | + DSI_INST_ID_NOP << (4 * DSI_INST_ID_DLY) | + DSI_INST_ID_END << (4 * DSI_INST_ID_HSCEXIT)); + break; + default: + regmap_write(dsi->regs, SUN6I_DSI_INST_JUMP_SEL_REG, + DSI_INST_ID_END << (4 * DSI_INST_ID_LP11)); + break; + } + + sun6i_dsi_inst_abort(dsi); + sun6i_dsi_inst_commit(dsi); + + if (func == DSI_START_HSC) + regmap_write_bits(dsi->regs, + SUN6I_DSI_INST_FUNC_REG(DSI_INST_ID_LP11), + SUN6I_DSI_INST_FUNC_LANE_CEN, 0); + + return 0; +} + +static void sun6i_dsi_encoder_enable(struct drm_encoder *encoder) +{ + struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; + struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder); + struct mipi_dsi_device *device = dsi->device; + u16 delay; + + DRM_DEBUG_DRIVER("Enabling DSI output\n"); + + pm_runtime_get_sync(dsi->dev); + + delay = sun6i_dsi_get_video_start_delay(dsi, mode); + regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL1_REG, + SUN6I_DSI_BASIC_CTL1_VIDEO_ST_DELAY(delay) | + SUN6I_DSI_BASIC_CTL1_VIDEO_FILL | + SUN6I_DSI_BASIC_CTL1_VIDEO_PRECISION | + SUN6I_DSI_BASIC_CTL1_VIDEO_MODE); + + sun6i_dsi_setup_burst(dsi, mode); + sun6i_dsi_setup_inst_loop(dsi, mode); + sun6i_dsi_setup_format(dsi, mode); + sun6i_dsi_setup_timings(dsi, mode); + + sun6i_dphy_init(dsi->dphy, device->lanes); + sun6i_dphy_power_on(dsi->dphy, device->lanes); + + if (!IS_ERR(dsi->panel)) + drm_panel_prepare(dsi->panel); + + /* + * FIXME: This should be moved after the switch to HS mode. + * + * Unfortunately, once in HS mode, it seems like we're not + * able to send DCS commands anymore, which would prevent any + * panel to send any DCS command as part as their enable + * method, which is quite common. + * + * I haven't seen any artifact due to that sub-optimal + * ordering on the panels I've tested it with, so I guess this + * will do for now, until that IP is better understood. + */ + if (!IS_ERR(dsi->panel)) + drm_panel_enable(dsi->panel); + + sun6i_dsi_start(dsi, DSI_START_HSC); + + udelay(1000); + + sun6i_dsi_start(dsi, DSI_START_HSD); +} + +static void sun6i_dsi_encoder_disable(struct drm_encoder *encoder) +{ + struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder); + + DRM_DEBUG_DRIVER("Disabling DSI output\n"); + + if (!IS_ERR(dsi->panel)) { + drm_panel_disable(dsi->panel); + drm_panel_unprepare(dsi->panel); + } + + sun6i_dphy_power_off(dsi->dphy); + sun6i_dphy_exit(dsi->dphy); + + pm_runtime_put(dsi->dev); +} + +static int sun6i_dsi_get_modes(struct drm_connector *connector) +{ + struct sun6i_dsi *dsi = connector_to_sun6i_dsi(connector); + + return drm_panel_get_modes(dsi->panel); +} + +static struct drm_connector_helper_funcs sun6i_dsi_connector_helper_funcs = { + .get_modes = sun6i_dsi_get_modes, +}; + +static enum drm_connector_status +sun6i_dsi_connector_detect(struct drm_connector *connector, bool force) +{ + return connector_status_connected; +} + +static const struct drm_connector_funcs sun6i_dsi_connector_funcs = { + .detect = sun6i_dsi_connector_detect, + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = drm_connector_cleanup, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +static const struct drm_encoder_helper_funcs sun6i_dsi_enc_helper_funcs = { + .disable = sun6i_dsi_encoder_disable, + .enable = sun6i_dsi_encoder_enable, +}; + +static const struct drm_encoder_funcs sun6i_dsi_enc_funcs = { + .destroy = drm_encoder_cleanup, +}; + +static u32 sun6i_dsi_dcs_build_pkt_hdr(struct sun6i_dsi *dsi, + const struct mipi_dsi_msg *msg) +{ + u32 pkt = msg->type; + + if (msg->type == MIPI_DSI_DCS_LONG_WRITE) { + pkt |= ((msg->tx_len + 1) & 0xffff) << 8; + pkt |= (((msg->tx_len + 1) >> 8) & 0xffff) << 16; + } else { + pkt |= (((u8 *)msg->tx_buf)[0] << 8); + if (msg->tx_len > 1) + pkt |= (((u8 *)msg->tx_buf)[1] << 16); + } + + pkt |= sun6i_dsi_ecc_compute(pkt) << 24; + + return pkt; +} + +static int sun6i_dsi_dcs_write_short(struct sun6i_dsi *dsi, + const struct mipi_dsi_msg *msg) +{ + regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0), + sun6i_dsi_dcs_build_pkt_hdr(dsi, msg)); + regmap_write_bits(dsi->regs, SUN6I_DSI_CMD_CTL_REG, + 0xff, (4 - 1)); + + sun6i_dsi_start(dsi, DSI_START_LPTX); + + return msg->tx_len; +} + +static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi, + const struct mipi_dsi_msg *msg) +{ + int ret, len = 0; + u8 *bounce; + u16 crc; + + regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0), + sun6i_dsi_dcs_build_pkt_hdr(dsi, msg)); + + bounce = kzalloc(msg->tx_len + sizeof(crc), GFP_KERNEL); + if (!bounce) + return -ENOMEM; + + memcpy(bounce, msg->tx_buf, msg->tx_len); + len += msg->tx_len; + + crc = sun6i_dsi_crc_compute(bounce, msg->tx_len); + memcpy((u8 *)bounce + msg->tx_len, &crc, sizeof(crc)); + len += sizeof(crc); + + regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, len); + regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG, len + 4 - 1); + kfree(bounce); + + sun6i_dsi_start(dsi, DSI_START_LPTX); + + ret = sun6i_dsi_inst_wait_for_completion(dsi); + if (ret < 0) { + sun6i_dsi_inst_abort(dsi); + return ret; + } + + /* + * TODO: There's some bits (reg 0x200, bits 8/9) that + * apparently can be used to check whether the data have been + * sent, but I couldn't get it to work reliably. + */ + return msg->tx_len; +} + +static int sun6i_dsi_dcs_read(struct sun6i_dsi *dsi, + const struct mipi_dsi_msg *msg) +{ + u32 val; + int ret; + u8 byte0; + + regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0), + sun6i_dsi_dcs_build_pkt_hdr(dsi, msg)); + regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG, + (4 - 1)); + + sun6i_dsi_start(dsi, DSI_START_LPRX); + + ret = sun6i_dsi_inst_wait_for_completion(dsi); + if (ret < 0) { + sun6i_dsi_inst_abort(dsi); + return ret; + } + + /* + * TODO: There's some bits (reg 0x200, bits 24/25) that + * apparently can be used to check whether the data have been + * received, but I couldn't get it to work reliably. + */ + regmap_read(dsi->regs, SUN6I_DSI_CMD_CTL_REG, &val); + if (val & SUN6I_DSI_CMD_CTL_RX_OVERFLOW) + return -EIO; + + regmap_read(dsi->regs, SUN6I_DSI_CMD_RX_REG(0), &val); + byte0 = val & 0xff; + if (byte0 == MIPI_DSI_RX_ACKNOWLEDGE_AND_ERROR_REPORT) + return -EIO; + + ((u8 *)msg->rx_buf)[0] = (val >> 8); + + return 1; +} + +static int sun6i_dsi_attach(struct mipi_dsi_host *host, + struct mipi_dsi_device *device) +{ + struct sun6i_dsi *dsi = host_to_sun6i_dsi(host); + + dsi->device = device; + dsi->panel = of_drm_find_panel(device->dev.of_node); + if (!dsi->panel) + return -EINVAL; + + dev_info(host->dev, "Attached device %s\n", device->name); + + return 0; +} + +static int sun6i_dsi_detach(struct mipi_dsi_host *host, + struct mipi_dsi_device *device) +{ + struct sun6i_dsi *dsi = host_to_sun6i_dsi(host); + + dsi->panel = NULL; + dsi->device = NULL; + + return 0; +} + +static ssize_t sun6i_dsi_transfer(struct mipi_dsi_host *host, + const struct mipi_dsi_msg *msg) +{ + struct sun6i_dsi *dsi = host_to_sun6i_dsi(host); + int ret; + + ret = sun6i_dsi_inst_wait_for_completion(dsi); + if (ret < 0) + sun6i_dsi_inst_abort(dsi); + + regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG, + SUN6I_DSI_CMD_CTL_RX_OVERFLOW | + SUN6I_DSI_CMD_CTL_RX_FLAG | + SUN6I_DSI_CMD_CTL_TX_FLAG); + + switch (msg->type) { + case MIPI_DSI_DCS_SHORT_WRITE: + case MIPI_DSI_DCS_SHORT_WRITE_PARAM: + ret = sun6i_dsi_dcs_write_short(dsi, msg); + break; + + case MIPI_DSI_DCS_LONG_WRITE: + ret = sun6i_dsi_dcs_write_long(dsi, msg); + break; + + case MIPI_DSI_DCS_READ: + if (msg->rx_len == 1) { + ret = sun6i_dsi_dcs_read(dsi, msg); + break; + } + + default: + ret = -EINVAL; + } + + return ret; +} + +static const struct mipi_dsi_host_ops sun6i_dsi_host_ops = { + .attach = sun6i_dsi_attach, + .detach = sun6i_dsi_detach, + .transfer = sun6i_dsi_transfer, +}; + +static const struct regmap_config sun6i_dsi_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + .max_register = SUN6I_DSI_CMD_TX_REG(255), + .name = "mipi-dsi", +}; + +static int sun6i_dsi_bind(struct device *dev, struct device *master, + void *data) +{ + struct drm_device *drm = data; + struct sun4i_drv *drv = drm->dev_private; + struct sun6i_dsi *dsi = dev_get_drvdata(dev); + int ret; + + if (!dsi->panel) + return -EPROBE_DEFER; + + dsi->drv = drv; + + drm_encoder_helper_add(&dsi->encoder, + &sun6i_dsi_enc_helper_funcs); + ret = drm_encoder_init(drm, + &dsi->encoder, + &sun6i_dsi_enc_funcs, + DRM_MODE_ENCODER_DSI, + NULL); + if (ret) { + dev_err(dsi->dev, "Couldn't initialise the DSI encoder\n"); + return ret; + } + dsi->encoder.possible_crtcs = BIT(0); + + drm_connector_helper_add(&dsi->connector, + &sun6i_dsi_connector_helper_funcs); + ret = drm_connector_init(drm, &dsi->connector, + &sun6i_dsi_connector_funcs, + DRM_MODE_CONNECTOR_DSI); + if (ret) { + dev_err(dsi->dev, + "Couldn't initialise the DSI connector\n"); + goto err_cleanup_connector; + } + + drm_mode_connector_attach_encoder(&dsi->connector, &dsi->encoder); + drm_panel_attach(dsi->panel, &dsi->connector); + + return 0; + +err_cleanup_connector: + drm_encoder_cleanup(&dsi->encoder); + return ret; +} + +static void sun6i_dsi_unbind(struct device *dev, struct device *master, + void *data) +{ + struct sun6i_dsi *dsi = dev_get_drvdata(dev); + + drm_panel_detach(dsi->panel); +} + +static const struct component_ops sun6i_dsi_ops = { + .bind = sun6i_dsi_bind, + .unbind = sun6i_dsi_unbind, +}; + +static int sun6i_dsi_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *dphy_node; + struct sun6i_dsi *dsi; + struct resource *res; + void __iomem *base; + int ret; + + dsi = devm_kzalloc(dev, sizeof(*dsi), GFP_KERNEL); + if (!dsi) + return -ENOMEM; + dev_set_drvdata(dev, dsi); + dsi->dev = dev; + dsi->host.ops = &sun6i_dsi_host_ops; + dsi->host.dev = dev; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) { + dev_err(dev, "Couldn't map the DSI encoder registers\n"); + return PTR_ERR(base); + } + + dsi->regs = devm_regmap_init_mmio_clk(dev, "bus", base, + &sun6i_dsi_regmap_config); + if (IS_ERR(dsi->regs)) { + dev_err(dev, "Couldn't create the DSI encoder regmap\n"); + return PTR_ERR(dsi->regs); + } + + dsi->reset = devm_reset_control_get_shared(dev, NULL); + if (IS_ERR(dsi->reset)) { + dev_err(dev, "Couldn't get our reset line\n"); + return PTR_ERR(dsi->reset); + } + + dsi->mod_clk = devm_clk_get(dev, "mod"); + if (IS_ERR(dsi->mod_clk)) { + dev_err(dev, "Couldn't get the DSI mod clock\n"); + return PTR_ERR(dsi->mod_clk); + } + + /* + * In order to operate properly, that clock seems to be always + * set to 297MHz. + */ + clk_set_rate_exclusive(dsi->mod_clk, 297000000); + + dphy_node = of_parse_phandle(dev->of_node, "phys", 0); + ret = sun6i_dphy_probe(dsi, dphy_node); + of_node_put(dphy_node); + if (ret) { + dev_err(dev, "Couldn't get the MIPI D-PHY\n"); + goto err_unprotect_clk; + } + + pm_runtime_enable(dev); + + ret = mipi_dsi_host_register(&dsi->host); + if (ret) { + dev_err(dev, "Couldn't register MIPI-DSI host\n"); + goto err_remove_phy; + } + + ret = component_add(&pdev->dev, &sun6i_dsi_ops); + if (ret) { + dev_err(dev, "Couldn't register our component\n"); + goto err_remove_dsi_host; + } + + return 0; + +err_remove_dsi_host: + mipi_dsi_host_unregister(&dsi->host); +err_remove_phy: + pm_runtime_disable(dev); + sun6i_dphy_remove(dsi); +err_unprotect_clk: + clk_rate_exclusive_put(dsi->mod_clk); + return ret; +} + +static int sun6i_dsi_remove(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct sun6i_dsi *dsi = dev_get_drvdata(dev); + + component_del(&pdev->dev, &sun6i_dsi_ops); + mipi_dsi_host_unregister(&dsi->host); + pm_runtime_disable(dev); + sun6i_dphy_remove(dsi); + clk_rate_exclusive_put(dsi->mod_clk); + + return 0; +} + +static int sun6i_dsi_runtime_resume(struct device *dev) +{ + struct sun6i_dsi *dsi = dev_get_drvdata(dev); + + reset_control_deassert(dsi->reset); + clk_prepare_enable(dsi->mod_clk); + + /* + * Enable the DSI block. + * + * Some part of it can only be done once we get a number of + * lanes, see sun6i_dsi_inst_init + */ + regmap_write(dsi->regs, SUN6I_DSI_CTL_REG, SUN6I_DSI_CTL_EN); + + regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL0_REG, + SUN6I_DSI_BASIC_CTL0_ECC_EN | SUN6I_DSI_BASIC_CTL0_CRC_EN); + + regmap_write(dsi->regs, SUN6I_DSI_TRANS_START_REG, 10); + regmap_write(dsi->regs, SUN6I_DSI_TRANS_ZERO_REG, 0); + + if (dsi->device) + sun6i_dsi_inst_init(dsi, dsi->device); + + regmap_write(dsi->regs, SUN6I_DSI_DEBUG_DATA_REG, 0xff); + + return 0; +} + +static int sun6i_dsi_runtime_suspend(struct device *dev) +{ + struct sun6i_dsi *dsi = dev_get_drvdata(dev); + + clk_disable_unprepare(dsi->mod_clk); + reset_control_assert(dsi->reset); + + return 0; +} + +static const struct dev_pm_ops sun6i_dsi_pm_ops = { + SET_RUNTIME_PM_OPS(sun6i_dsi_runtime_suspend, + sun6i_dsi_runtime_resume, + NULL) +}; + +static const struct of_device_id sun6i_dsi_of_table[] = { + { .compatible = "allwinner,sun6i-a31-mipi-dsi" }, + { } +}; +MODULE_DEVICE_TABLE(of, sun6i_dsi_of_table); + +static struct platform_driver sun6i_dsi_platform_driver = { + .probe = sun6i_dsi_probe, + .remove = sun6i_dsi_remove, + .driver = { + .name = "sun6i-mipi-dsi", + .of_match_table = sun6i_dsi_of_table, + .pm = &sun6i_dsi_pm_ops, + }, +}; +module_platform_driver(sun6i_dsi_platform_driver); + +MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>"); +MODULE_DESCRIPTION("Allwinner A31 DSI Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h new file mode 100644 index 0000000..dbbc5b3 --- /dev/null +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2016 Allwinnertech Co., Ltd. + * Copyright (C) 2017-2018 Bootlin + * + * Maxime Ripard <maxime.ripard@bootlin.com> + */ + +#ifndef _SUN6I_MIPI_DSI_H_ +#define _SUN6I_MIPI_DSI_H_ + +#include <drm/drm_connector.h> +#include <drm/drm_encoder.h> +#include <drm/drm_mipi_dsi.h> + +struct sun6i_dphy { + struct clk *bus_clk; + struct clk *mod_clk; + struct regmap *regs; + struct reset_control *reset; +}; + +struct sun6i_dsi { + struct drm_connector connector; + struct drm_encoder encoder; + struct mipi_dsi_host host; + + struct clk *bus_clk; + struct clk *mod_clk; + struct regmap *regs; + struct reset_control *reset; + struct sun6i_dphy *dphy; + + struct device *dev; + struct sun4i_drv *drv; + struct mipi_dsi_device *device; + struct drm_panel *panel; +}; + +static inline struct sun6i_dsi *host_to_sun6i_dsi(struct mipi_dsi_host *host) +{ + return container_of(host, struct sun6i_dsi, host); +}; + +static inline struct sun6i_dsi *connector_to_sun6i_dsi(struct drm_connector *connector) +{ + return container_of(connector, struct sun6i_dsi, connector); +}; + +static inline struct sun6i_dsi *encoder_to_sun6i_dsi(const struct drm_encoder *encoder) +{ + return container_of(encoder, struct sun6i_dsi, encoder); +}; + +int sun6i_dphy_probe(struct sun6i_dsi *dsi, struct device_node *node); +int sun6i_dphy_remove(struct sun6i_dsi *dsi); + +int sun6i_dphy_init(struct sun6i_dphy *dphy, unsigned int lanes); +int sun6i_dphy_power_on(struct sun6i_dphy *dphy, unsigned int lanes); +int sun6i_dphy_power_off(struct sun6i_dphy *dphy); +int sun6i_dphy_exit(struct sun6i_dphy *dphy); + +#endif /* _SUN6I_MIPI_DSI_H_ */ diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 616c963..9f83a65 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -2025,9 +2025,9 @@ static const struct tegra_dc_soc_info tegra124_dc_soc_info = { .coupled_pm = false, .has_nvdisplay = false, .num_primary_formats = ARRAY_SIZE(tegra124_primary_formats), - .primary_formats = tegra114_primary_formats, + .primary_formats = tegra124_primary_formats, .num_overlay_formats = ARRAY_SIZE(tegra124_overlay_formats), - .overlay_formats = tegra114_overlay_formats, + .overlay_formats = tegra124_overlay_formats, .modifiers = tegra124_modifiers, }; @@ -2178,7 +2178,7 @@ static int tegra_dc_couple(struct tegra_dc *dc) struct device_link *link; struct device *partner; - partner = driver_find_device(dc->dev->driver, NULL, 0, + partner = driver_find_device(dc->dev->driver, NULL, NULL, tegra_dc_match_by_pipe); if (!partner) return -EPROBE_DEFER; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 7afe2f6..a051961 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -38,26 +38,11 @@ static int tegra_atomic_check(struct drm_device *drm, { int err; - err = drm_atomic_helper_check_modeset(drm, state); + err = drm_atomic_helper_check(drm, state); if (err < 0) return err; - err = tegra_display_hub_atomic_check(drm, state); - if (err < 0) - return err; - - err = drm_atomic_normalize_zpos(drm, state); - if (err < 0) - return err; - - err = drm_atomic_helper_check_planes(drm, state); - if (err < 0) - return err; - - if (state->legacy_cursor_update) - state->async_update = !drm_atomic_helper_async_check(drm, state); - - return 0; + return tegra_display_hub_atomic_check(drm, state); } static const struct drm_mode_config_funcs tegra_drm_mode_config_funcs = { @@ -151,6 +136,8 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags) drm->mode_config.allow_fb_modifiers = true; + drm->mode_config.normalize_zpos = true; + drm->mode_config.funcs = &tegra_drm_mode_config_funcs; drm->mode_config.helper_private = &tegra_drm_mode_config_helpers; diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c index 4c661627..24a33bf 100644 --- a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c +++ b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c @@ -91,7 +91,7 @@ EXPORT_SYMBOL(tinydrm_gem_cma_prime_import_sg_table); * GEM object state and frees the memory used to store the object itself using * drm_gem_cma_free_object(). It also handles PRIME buffers which has the kernel * virtual address set by tinydrm_gem_cma_prime_import_sg_table(). Drivers - * can use this as their &drm_driver->gem_free_object callback. + * can use this as their &drm_driver->gem_free_object_unlocked callback. */ void tinydrm_gem_cma_free_object(struct drm_gem_object *gem_obj) { diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-helpers.c b/drivers/gpu/drm/tinydrm/core/tinydrm-helpers.c index d1c3ce9..dcd3901 100644 --- a/drivers/gpu/drm/tinydrm/core/tinydrm-helpers.c +++ b/drivers/gpu/drm/tinydrm/core/tinydrm-helpers.c @@ -78,6 +78,36 @@ bool tinydrm_merge_clips(struct drm_clip_rect *dst, } EXPORT_SYMBOL(tinydrm_merge_clips); +int tinydrm_fb_dirty(struct drm_framebuffer *fb, + struct drm_file *file_priv, + unsigned int flags, unsigned int color, + struct drm_clip_rect *clips, + unsigned int num_clips) +{ + struct tinydrm_device *tdev = fb->dev->dev_private; + struct drm_plane *plane = &tdev->pipe.plane; + int ret = 0; + + drm_modeset_lock(&plane->mutex, NULL); + + /* fbdev can flush even when we're not interested */ + if (plane->state->fb == fb) { + mutex_lock(&tdev->dirty_lock); + ret = tdev->fb_dirty(fb, file_priv, flags, + color, clips, num_clips); + mutex_unlock(&tdev->dirty_lock); + } + + drm_modeset_unlock(&plane->mutex); + + if (ret) + dev_err_once(fb->dev->dev, + "Failed to update display %d\n", ret); + + return ret; +} +EXPORT_SYMBOL(tinydrm_fb_dirty); + /** * tinydrm_memcpy - Copy clip buffer * @dst: Destination buffer diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c b/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c index 11ae950..7e8e24d 100644 --- a/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c +++ b/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c @@ -125,9 +125,8 @@ void tinydrm_display_pipe_update(struct drm_simple_display_pipe *pipe, struct drm_crtc *crtc = &tdev->pipe.crtc; if (fb && (fb != old_state->fb)) { - pipe->plane.fb = fb; - if (fb->funcs->dirty) - fb->funcs->dirty(fb, NULL, 0, 0, NULL, 0); + if (tdev->fb_dirty) + tdev->fb_dirty(fb, NULL, 0, 0, NULL, 0); } if (crtc->state->event) { @@ -139,23 +138,6 @@ void tinydrm_display_pipe_update(struct drm_simple_display_pipe *pipe, } EXPORT_SYMBOL(tinydrm_display_pipe_update); -/** - * tinydrm_display_pipe_prepare_fb - Display pipe prepare_fb helper - * @pipe: Simple display pipe - * @plane_state: Plane state - * - * This function uses drm_gem_fb_prepare_fb() to check if the plane FB has an - * dma-buf attached, extracts the exclusive fence and attaches it to plane - * state for the atomic helper to wait on. Drivers can use this as their - * &drm_simple_display_pipe_funcs->prepare_fb callback. - */ -int tinydrm_display_pipe_prepare_fb(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *plane_state) -{ - return drm_gem_fb_prepare_fb(&pipe->plane, plane_state); -} -EXPORT_SYMBOL(tinydrm_display_pipe_prepare_fb); - static int tinydrm_rotate_mode(struct drm_display_mode *mode, unsigned int rotation) { diff --git a/drivers/gpu/drm/tinydrm/ili9225.c b/drivers/gpu/drm/tinydrm/ili9225.c index a075950..841c69a 100644 --- a/drivers/gpu/drm/tinydrm/ili9225.c +++ b/drivers/gpu/drm/tinydrm/ili9225.c @@ -88,14 +88,8 @@ static int ili9225_fb_dirty(struct drm_framebuffer *fb, bool full; void *tr; - mutex_lock(&tdev->dirty_lock); - if (!mipi->enabled) - goto out_unlock; - - /* fbdev can flush even when we're not interested */ - if (tdev->pipe.plane.fb != fb) - goto out_unlock; + return 0; full = tinydrm_merge_clips(&clip, clips, num_clips, flags, fb->width, fb->height); @@ -108,7 +102,7 @@ static int ili9225_fb_dirty(struct drm_framebuffer *fb, tr = mipi->tx_buf; ret = mipi_dbi_buf_copy(mipi->tx_buf, fb, &clip, swap); if (ret) - goto out_unlock; + return ret; } else { tr = cma_obj->vaddr; } @@ -159,24 +153,18 @@ static int ili9225_fb_dirty(struct drm_framebuffer *fb, ret = mipi_dbi_command_buf(mipi, ILI9225_WRITE_DATA_TO_GRAM, tr, (clip.x2 - clip.x1) * (clip.y2 - clip.y1) * 2); -out_unlock: - mutex_unlock(&tdev->dirty_lock); - - if (ret) - dev_err_once(fb->dev->dev, "Failed to update display %d\n", - ret); - return ret; } static const struct drm_framebuffer_funcs ili9225_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, - .dirty = ili9225_fb_dirty, + .dirty = tinydrm_fb_dirty, }; static void ili9225_pipe_enable(struct drm_simple_display_pipe *pipe, - struct drm_crtc_state *crtc_state) + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) { struct tinydrm_device *tdev = pipe_to_tinydrm(pipe); struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev); @@ -268,7 +256,7 @@ static void ili9225_pipe_enable(struct drm_simple_display_pipe *pipe, ili9225_command(mipi, ILI9225_DISPLAY_CONTROL_1, 0x1017); - mipi_dbi_enable_flush(mipi); + mipi_dbi_enable_flush(mipi, crtc_state, plane_state); } static void ili9225_pipe_disable(struct drm_simple_display_pipe *pipe) @@ -341,6 +329,8 @@ static int ili9225_init(struct device *dev, struct mipi_dbi *mipi, if (ret) return ret; + tdev->fb_dirty = ili9225_fb_dirty; + ret = tinydrm_display_pipe_init(tdev, pipe_funcs, DRM_MODE_CONNECTOR_VIRTUAL, ili9225_formats, @@ -364,7 +354,7 @@ static const struct drm_simple_display_pipe_funcs ili9225_pipe_funcs = { .enable = ili9225_pipe_enable, .disable = ili9225_pipe_disable, .update = tinydrm_display_pipe_update, - .prepare_fb = tinydrm_display_pipe_prepare_fb, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode ili9225_mode = { diff --git a/drivers/gpu/drm/tinydrm/mi0283qt.c b/drivers/gpu/drm/tinydrm/mi0283qt.c index d8ed6e6..d5ef651 100644 --- a/drivers/gpu/drm/tinydrm/mi0283qt.c +++ b/drivers/gpu/drm/tinydrm/mi0283qt.c @@ -19,6 +19,7 @@ #include <drm/drm_fb_helper.h> #include <drm/drm_modeset_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> #include <drm/tinydrm/mipi-dbi.h> #include <drm/tinydrm/tinydrm-helpers.h> #include <video/mipi_display.h> @@ -49,7 +50,8 @@ #define ILI9341_MADCTL_MY BIT(7) static void mi0283qt_enable(struct drm_simple_display_pipe *pipe, - struct drm_crtc_state *crtc_state) + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) { struct tinydrm_device *tdev = pipe_to_tinydrm(pipe); struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev); @@ -126,14 +128,14 @@ static void mi0283qt_enable(struct drm_simple_display_pipe *pipe, msleep(100); out_enable: - mipi_dbi_enable_flush(mipi); + mipi_dbi_enable_flush(mipi, crtc_state, plane_state); } static const struct drm_simple_display_pipe_funcs mi0283qt_pipe_funcs = { .enable = mi0283qt_enable, .disable = mipi_dbi_pipe_disable, .update = tinydrm_display_pipe_update, - .prepare_fb = tinydrm_display_pipe_prepare_fb, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode mi0283qt_mode = { diff --git a/drivers/gpu/drm/tinydrm/mipi-dbi.c b/drivers/gpu/drm/tinydrm/mipi-dbi.c index 9e90381..4d1fb31 100644 --- a/drivers/gpu/drm/tinydrm/mipi-dbi.c +++ b/drivers/gpu/drm/tinydrm/mipi-dbi.c @@ -219,14 +219,8 @@ static int mipi_dbi_fb_dirty(struct drm_framebuffer *fb, bool full; void *tr; - mutex_lock(&tdev->dirty_lock); - if (!mipi->enabled) - goto out_unlock; - - /* fbdev can flush even when we're not interested */ - if (tdev->pipe.plane.fb != fb) - goto out_unlock; + return 0; full = tinydrm_merge_clips(&clip, clips, num_clips, flags, fb->width, fb->height); @@ -239,7 +233,7 @@ static int mipi_dbi_fb_dirty(struct drm_framebuffer *fb, tr = mipi->tx_buf; ret = mipi_dbi_buf_copy(mipi->tx_buf, fb, &clip, swap); if (ret) - goto out_unlock; + return ret; } else { tr = cma_obj->vaddr; } @@ -254,20 +248,13 @@ static int mipi_dbi_fb_dirty(struct drm_framebuffer *fb, ret = mipi_dbi_command_buf(mipi, MIPI_DCS_WRITE_MEMORY_START, tr, (clip.x2 - clip.x1) * (clip.y2 - clip.y1) * 2); -out_unlock: - mutex_unlock(&tdev->dirty_lock); - - if (ret) - dev_err_once(fb->dev->dev, "Failed to update display %d\n", - ret); - return ret; } static const struct drm_framebuffer_funcs mipi_dbi_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, - .dirty = mipi_dbi_fb_dirty, + .dirty = tinydrm_fb_dirty, }; /** @@ -278,13 +265,16 @@ static const struct drm_framebuffer_funcs mipi_dbi_fb_funcs = { * enables the backlight. Drivers can use this in their * &drm_simple_display_pipe_funcs->enable callback. */ -void mipi_dbi_enable_flush(struct mipi_dbi *mipi) +void mipi_dbi_enable_flush(struct mipi_dbi *mipi, + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) { - struct drm_framebuffer *fb = mipi->tinydrm.pipe.plane.fb; + struct tinydrm_device *tdev = &mipi->tinydrm; + struct drm_framebuffer *fb = plane_state->fb; mipi->enabled = true; if (fb) - fb->funcs->dirty(fb, NULL, 0, 0, NULL, 0); + tdev->fb_dirty(fb, NULL, 0, 0, NULL, 0); backlight_enable(mipi->backlight); } @@ -381,6 +371,8 @@ int mipi_dbi_init(struct device *dev, struct mipi_dbi *mipi, if (ret) return ret; + tdev->fb_dirty = mipi_dbi_fb_dirty; + /* TODO: Maybe add DRM_MODE_CONNECTOR_SPI */ ret = tinydrm_display_pipe_init(tdev, pipe_funcs, DRM_MODE_CONNECTOR_VIRTUAL, diff --git a/drivers/gpu/drm/tinydrm/repaper.c b/drivers/gpu/drm/tinydrm/repaper.c index 7574063..1ee6855 100644 --- a/drivers/gpu/drm/tinydrm/repaper.c +++ b/drivers/gpu/drm/tinydrm/repaper.c @@ -540,14 +540,8 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb, clip.y1 = 0; clip.y2 = fb->height; - mutex_lock(&tdev->dirty_lock); - if (!epd->enabled) - goto out_unlock; - - /* fbdev can flush even when we're not interested */ - if (tdev->pipe.plane.fb != fb) - goto out_unlock; + return 0; repaper_get_temperature(epd); @@ -555,16 +549,14 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb, epd->factored_stage_time); buf = kmalloc(fb->width * fb->height, GFP_KERNEL); - if (!buf) { - ret = -ENOMEM; - goto out_unlock; - } + if (!buf) + return -ENOMEM; if (import_attach) { ret = dma_buf_begin_cpu_access(import_attach->dmabuf, DMA_FROM_DEVICE); if (ret) - goto out_unlock; + goto out_free; } tinydrm_xrgb8888_to_gray8(buf, cma_obj->vaddr, fb, &clip); @@ -573,7 +565,7 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb, ret = dma_buf_end_cpu_access(import_attach->dmabuf, DMA_FROM_DEVICE); if (ret) - goto out_unlock; + goto out_free; } repaper_gray8_to_mono_reversed(buf, fb->width, fb->height); @@ -625,11 +617,7 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb, } } -out_unlock: - mutex_unlock(&tdev->dirty_lock); - - if (ret) - DRM_DEV_ERROR(fb->dev->dev, "Failed to update display (%d)\n", ret); +out_free: kfree(buf); return ret; @@ -638,7 +626,7 @@ out_unlock: static const struct drm_framebuffer_funcs repaper_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, - .dirty = repaper_fb_dirty, + .dirty = tinydrm_fb_dirty, }; static void power_off(struct repaper_epd *epd) @@ -659,7 +647,8 @@ static void power_off(struct repaper_epd *epd) } static void repaper_pipe_enable(struct drm_simple_display_pipe *pipe, - struct drm_crtc_state *crtc_state) + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) { struct tinydrm_device *tdev = pipe_to_tinydrm(pipe); struct repaper_epd *epd = epd_from_tinydrm(tdev); @@ -852,7 +841,7 @@ static const struct drm_simple_display_pipe_funcs repaper_pipe_funcs = { .enable = repaper_pipe_enable, .disable = repaper_pipe_disable, .update = tinydrm_display_pipe_update, - .prepare_fb = tinydrm_display_pipe_prepare_fb, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, }; static const uint32_t repaper_formats[] = { @@ -1069,6 +1058,8 @@ static int repaper_probe(struct spi_device *spi) if (ret) return ret; + tdev->fb_dirty = repaper_fb_dirty; + ret = tinydrm_display_pipe_init(tdev, &repaper_pipe_funcs, DRM_MODE_CONNECTOR_VIRTUAL, repaper_formats, diff --git a/drivers/gpu/drm/tinydrm/st7586.c b/drivers/gpu/drm/tinydrm/st7586.c index a6396ef..5c29e38 100644 --- a/drivers/gpu/drm/tinydrm/st7586.c +++ b/drivers/gpu/drm/tinydrm/st7586.c @@ -120,14 +120,8 @@ static int st7586_fb_dirty(struct drm_framebuffer *fb, int start, end; int ret = 0; - mutex_lock(&tdev->dirty_lock); - if (!mipi->enabled) - goto out_unlock; - - /* fbdev can flush even when we're not interested */ - if (tdev->pipe.plane.fb != fb) - goto out_unlock; + return 0; tinydrm_merge_clips(&clip, clips, num_clips, flags, fb->width, fb->height); @@ -141,7 +135,7 @@ static int st7586_fb_dirty(struct drm_framebuffer *fb, ret = st7586_buf_copy(mipi->tx_buf, fb, &clip); if (ret) - goto out_unlock; + return ret; /* Pixels are packed 3 per byte */ start = clip.x1 / 3; @@ -158,24 +152,18 @@ static int st7586_fb_dirty(struct drm_framebuffer *fb, (u8 *)mipi->tx_buf, (end - start) * (clip.y2 - clip.y1)); -out_unlock: - mutex_unlock(&tdev->dirty_lock); - - if (ret) - dev_err_once(fb->dev->dev, "Failed to update display %d\n", - ret); - return ret; } static const struct drm_framebuffer_funcs st7586_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, - .dirty = st7586_fb_dirty, + .dirty = tinydrm_fb_dirty, }; static void st7586_pipe_enable(struct drm_simple_display_pipe *pipe, - struct drm_crtc_state *crtc_state) + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) { struct tinydrm_device *tdev = pipe_to_tinydrm(pipe); struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev); @@ -237,7 +225,7 @@ static void st7586_pipe_enable(struct drm_simple_display_pipe *pipe, mipi_dbi_command(mipi, MIPI_DCS_SET_DISPLAY_ON); - mipi_dbi_enable_flush(mipi); + mipi_dbi_enable_flush(mipi, crtc_state, plane_state); } static void st7586_pipe_disable(struct drm_simple_display_pipe *pipe) @@ -277,6 +265,8 @@ static int st7586_init(struct device *dev, struct mipi_dbi *mipi, if (ret) return ret; + tdev->fb_dirty = st7586_fb_dirty; + ret = tinydrm_display_pipe_init(tdev, pipe_funcs, DRM_MODE_CONNECTOR_VIRTUAL, st7586_formats, @@ -300,7 +290,7 @@ static const struct drm_simple_display_pipe_funcs st7586_pipe_funcs = { .enable = st7586_pipe_enable, .disable = st7586_pipe_disable, .update = tinydrm_display_pipe_update, - .prepare_fb = tinydrm_display_pipe_prepare_fb, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode st7586_mode = { diff --git a/drivers/gpu/drm/tinydrm/st7735r.c b/drivers/gpu/drm/tinydrm/st7735r.c index 67d197e..6c7b15c 100644 --- a/drivers/gpu/drm/tinydrm/st7735r.c +++ b/drivers/gpu/drm/tinydrm/st7735r.c @@ -37,7 +37,8 @@ #define ST7735R_MV BIT(5) static void jd_t18003_t01_pipe_enable(struct drm_simple_display_pipe *pipe, - struct drm_crtc_state *crtc_state) + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) { struct tinydrm_device *tdev = pipe_to_tinydrm(pipe); struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev); @@ -98,14 +99,14 @@ static void jd_t18003_t01_pipe_enable(struct drm_simple_display_pipe *pipe, msleep(20); - mipi_dbi_enable_flush(mipi); + mipi_dbi_enable_flush(mipi, crtc_state, plane_state); } static const struct drm_simple_display_pipe_funcs jd_t18003_t01_pipe_funcs = { .enable = jd_t18003_t01_pipe_enable, .disable = mipi_dbi_pipe_disable, .update = tinydrm_display_pipe_update, - .prepare_fb = tinydrm_display_pipe_prepare_fb, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode jd_t18003_t01_mode = { diff --git a/drivers/gpu/drm/tve200/tve200_display.c b/drivers/gpu/drm/tve200/tve200_display.c index db397fc..e8723a2 100644 --- a/drivers/gpu/drm/tve200/tve200_display.c +++ b/drivers/gpu/drm/tve200/tve200_display.c @@ -120,7 +120,8 @@ static int tve200_display_check(struct drm_simple_display_pipe *pipe, } static void tve200_display_enable(struct drm_simple_display_pipe *pipe, - struct drm_crtc_state *cstate) + struct drm_crtc_state *cstate, + struct drm_plane_state *plane_state) { struct drm_crtc *crtc = &pipe->crtc; struct drm_plane *plane = &pipe->plane; @@ -292,18 +293,12 @@ static void tve200_display_disable_vblank(struct drm_simple_display_pipe *pipe) writel(0, priv->regs + TVE200_INT_EN); } -static int tve200_display_prepare_fb(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *plane_state) -{ - return drm_gem_fb_prepare_fb(&pipe->plane, plane_state); -} - static const struct drm_simple_display_pipe_funcs tve200_display_funcs = { .check = tve200_display_check, .enable = tve200_display_enable, .disable = tve200_display_disable, .update = tve200_display_update, - .prepare_fb = tve200_display_prepare_fb, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, .enable_vblank = tve200_display_enable_vblank, .disable_vblank = tve200_display_disable_vblank, }; diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c index c3dc1fd..09dc585 100644 --- a/drivers/gpu/drm/udl/udl_connector.c +++ b/drivers/gpu/drm/udl/udl_connector.c @@ -105,7 +105,7 @@ static int udl_get_modes(struct drm_connector *connector) return 0; } -static int udl_mode_valid(struct drm_connector *connector, +static enum drm_mode_status udl_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct udl_device *udl = connector->dev->dev_private; diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c index 2867ed1..0a20695 100644 --- a/drivers/gpu/drm/udl/udl_dmabuf.c +++ b/drivers/gpu/drm/udl/udl_dmabuf.c @@ -76,6 +76,7 @@ static struct sg_table *udl_map_dma_buf(struct dma_buf_attachment *attach, struct udl_drm_dmabuf_attachment *udl_attach = attach->priv; struct udl_gem_object *obj = to_udl_bo(attach->dmabuf->priv); struct drm_device *dev = obj->base.dev; + struct udl_device *udl = dev->dev_private; struct scatterlist *rd, *wr; struct sg_table *sgt = NULL; unsigned int i; @@ -112,7 +113,7 @@ static struct sg_table *udl_map_dma_buf(struct dma_buf_attachment *attach, return ERR_PTR(-ENOMEM); } - mutex_lock(&dev->struct_mutex); + mutex_lock(&udl->gem_lock); rd = obj->sg->sgl; wr = sgt->sgl; @@ -137,7 +138,7 @@ static struct sg_table *udl_map_dma_buf(struct dma_buf_attachment *attach, attach->priv = udl_attach; err_unlock: - mutex_unlock(&dev->struct_mutex); + mutex_unlock(&udl->gem_lock); return sgt; } diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c index 3c45a30..9ef515d 100644 --- a/drivers/gpu/drm/udl/udl_drv.c +++ b/drivers/gpu/drm/udl/udl_drv.c @@ -53,7 +53,7 @@ static struct drm_driver driver = { .unload = udl_driver_unload, /* gem hooks */ - .gem_free_object = udl_gem_free_object, + .gem_free_object_unlocked = udl_gem_free_object, .gem_vm_ops = &udl_gem_vm_ops, .dumb_create = udl_dumb_create, diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h index 2a75ab8..55c0cc3 100644 --- a/drivers/gpu/drm/udl/udl_drv.h +++ b/drivers/gpu/drm/udl/udl_drv.h @@ -54,6 +54,8 @@ struct udl_device { struct usb_device *udev; struct drm_crtc *crtc; + struct mutex gem_lock; + int sku_pixel_limit; struct urb_list urbs; diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c index dee6bd9..9a15cce 100644 --- a/drivers/gpu/drm/udl/udl_gem.c +++ b/drivers/gpu/drm/udl/udl_gem.c @@ -214,9 +214,10 @@ int udl_gem_mmap(struct drm_file *file, struct drm_device *dev, { struct udl_gem_object *gobj; struct drm_gem_object *obj; + struct udl_device *udl = dev->dev_private; int ret = 0; - mutex_lock(&dev->struct_mutex); + mutex_lock(&udl->gem_lock); obj = drm_gem_object_lookup(file, handle); if (obj == NULL) { ret = -ENOENT; @@ -236,6 +237,6 @@ int udl_gem_mmap(struct drm_file *file, struct drm_device *dev, out: drm_gem_object_put(&gobj->base); unlock: - mutex_unlock(&dev->struct_mutex); + mutex_unlock(&udl->gem_lock); return ret; } diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c index f1ec452..d518de8 100644 --- a/drivers/gpu/drm/udl/udl_main.c +++ b/drivers/gpu/drm/udl/udl_main.c @@ -324,6 +324,8 @@ int udl_driver_load(struct drm_device *dev, unsigned long flags) udl->ddev = dev; dev->dev_private = udl; + mutex_init(&udl->gem_lock); + if (!udl_parse_vendor_descriptor(dev, udl->udev)) { ret = -ENODEV; DRM_ERROR("firmware not recognized. Assume incompatible device\n"); diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index 2decc8e..add9cc9 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -195,6 +195,7 @@ static void vc4_bo_destroy(struct vc4_bo *bo) vc4_bo_set_label(obj, -1); if (bo->validated_shader) { + kfree(bo->validated_shader->uniform_addr_offsets); kfree(bo->validated_shader->texture_samples); kfree(bo->validated_shader); bo->validated_shader = NULL; @@ -591,6 +592,7 @@ void vc4_free_object(struct drm_gem_object *gem_bo) } if (bo->validated_shader) { + kfree(bo->validated_shader->uniform_addr_offsets); kfree(bo->validated_shader->texture_samples); kfree(bo->validated_shader); bo->validated_shader = NULL; diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index bf46674..83d3b79 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -42,51 +42,18 @@ #include "vc4_drv.h" #include "vc4_regs.h" -struct vc4_crtc { - struct drm_crtc base; - const struct vc4_crtc_data *data; - void __iomem *regs; - - /* Timestamp at start of vblank irq - unaffected by lock delays. */ - ktime_t t_vblank; - - /* Which HVS channel we're using for our CRTC. */ - int channel; - - u8 lut_r[256]; - u8 lut_g[256]; - u8 lut_b[256]; - /* Size in pixels of the COB memory allocated to this CRTC. */ - u32 cob_size; - - struct drm_pending_vblank_event *event; -}; - struct vc4_crtc_state { struct drm_crtc_state base; /* Dlist area for this CRTC configuration. */ struct drm_mm_node mm; }; -static inline struct vc4_crtc * -to_vc4_crtc(struct drm_crtc *crtc) -{ - return (struct vc4_crtc *)crtc; -} - static inline struct vc4_crtc_state * to_vc4_crtc_state(struct drm_crtc_state *crtc_state) { return (struct vc4_crtc_state *)crtc_state; } -struct vc4_crtc_data { - /* Which channel of the HVS this pixelvalve sources from. */ - int hvs_channel; - - enum vc4_encoder_type encoder_types[4]; -}; - #define CRTC_WRITE(offset, val) writel(val, vc4_crtc->regs + (offset)) #define CRTC_READ(offset) readl(vc4_crtc->regs + (offset)) @@ -298,23 +265,21 @@ vc4_crtc_lut_load(struct drm_crtc *crtc) HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_b[i]); } -static int -vc4_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b, - uint32_t size, - struct drm_modeset_acquire_ctx *ctx) +static void +vc4_crtc_update_gamma_lut(struct drm_crtc *crtc) { struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); + struct drm_color_lut *lut = crtc->state->gamma_lut->data; + u32 length = drm_color_lut_size(crtc->state->gamma_lut); u32 i; - for (i = 0; i < size; i++) { - vc4_crtc->lut_r[i] = r[i] >> 8; - vc4_crtc->lut_g[i] = g[i] >> 8; - vc4_crtc->lut_b[i] = b[i] >> 8; + for (i = 0; i < length; i++) { + vc4_crtc->lut_r[i] = drm_color_lut_extract(lut[i].red, 8); + vc4_crtc->lut_g[i] = drm_color_lut_extract(lut[i].green, 8); + vc4_crtc->lut_b[i] = drm_color_lut_extract(lut[i].blue, 8); } vc4_crtc_lut_load(crtc); - - return 0; } static u32 vc4_get_fifo_full_level(u32 format) @@ -699,6 +664,22 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc, if (crtc->state->active && old_state->active) vc4_crtc_update_dlist(crtc); + if (crtc->state->color_mgmt_changed) { + u32 dispbkgndx = HVS_READ(SCALER_DISPBKGNDX(vc4_crtc->channel)); + + if (crtc->state->gamma_lut) { + vc4_crtc_update_gamma_lut(crtc); + dispbkgndx |= SCALER_DISPBKGND_GAMMA; + } else { + /* Unsetting DISPBKGND_GAMMA skips the gamma lut step + * in hardware, which is the same as a linear lut that + * DRM expects us to use in absence of a user lut. + */ + dispbkgndx &= ~SCALER_DISPBKGND_GAMMA; + } + HVS_WRITE(SCALER_DISPBKGNDX(vc4_crtc->channel), dispbkgndx); + } + if (debug_dump_regs) { DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc)); vc4_hvs_dump_state(dev); @@ -909,7 +890,7 @@ static const struct drm_crtc_funcs vc4_crtc_funcs = { .reset = vc4_crtc_reset, .atomic_duplicate_state = vc4_crtc_duplicate_state, .atomic_destroy_state = vc4_crtc_destroy_state, - .gamma_set = vc4_crtc_gamma_set, + .gamma_set = drm_atomic_helper_legacy_gamma_set, .enable_vblank = vc4_enable_vblank, .disable_vblank = vc4_disable_vblank, }; @@ -1035,6 +1016,12 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data) primary_plane->crtc = crtc; vc4_crtc->channel = vc4_crtc->data->hvs_channel; drm_mode_crtc_set_gamma_size(crtc, ARRAY_SIZE(vc4_crtc->lut_r)); + drm_crtc_enable_color_mgmt(crtc, 0, false, crtc->gamma_size); + + /* We support CTM, but only for one CRTC at a time. It's therefore + * implemented as private driver state in vc4_kms, not here. + */ + drm_crtc_enable_color_mgmt(crtc, 0, true, crtc->gamma_size); /* Set up some arbitrary number of planes. We're not limited * by a set number of physical registers, just the space in diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 94b99c9..40ddeaa 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -318,8 +318,8 @@ dev_unref: static void vc4_drm_unbind(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct drm_device *drm = platform_get_drvdata(pdev); + struct drm_device *drm = dev_get_drvdata(dev); + struct vc4_dev *vc4 = to_vc4_dev(drm); drm_dev_unregister(drm); @@ -327,6 +327,8 @@ static void vc4_drm_unbind(struct device *dev) drm_mode_config_cleanup(drm); + drm_atomic_private_obj_fini(&vc4->ctm_manager); + drm_dev_unref(drm); } diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 1b4cd1f..22589d3 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -10,6 +10,7 @@ #include <drm/drmP.h> #include <drm/drm_encoder.h> #include <drm/drm_gem_cma_helper.h> +#include <drm/drm_atomic.h> #include "uapi/drm/vc4_drm.h" @@ -193,6 +194,9 @@ struct vc4_dev { } hangcheck; struct semaphore async_modeset; + + struct drm_modeset_lock ctm_state_lock; + struct drm_private_obj ctm_manager; }; static inline struct vc4_dev * @@ -392,6 +396,39 @@ to_vc4_encoder(struct drm_encoder *encoder) return container_of(encoder, struct vc4_encoder, base); } +struct vc4_crtc_data { + /* Which channel of the HVS this pixelvalve sources from. */ + int hvs_channel; + + enum vc4_encoder_type encoder_types[4]; +}; + +struct vc4_crtc { + struct drm_crtc base; + const struct vc4_crtc_data *data; + void __iomem *regs; + + /* Timestamp at start of vblank irq - unaffected by lock delays. */ + ktime_t t_vblank; + + /* Which HVS channel we're using for our CRTC. */ + int channel; + + u8 lut_r[256]; + u8 lut_g[256]; + u8 lut_b[256]; + /* Size in pixels of the COB memory allocated to this CRTC. */ + u32 cob_size; + + struct drm_pending_vblank_event *event; +}; + +static inline struct vc4_crtc * +to_vc4_crtc(struct drm_crtc *crtc) +{ + return (struct vc4_crtc *)crtc; +} + #define V3D_READ(offset) readl(vc4->v3d->regs + offset) #define V3D_WRITE(offset, val) writel(val, vc4->v3d->regs + offset) #define HVS_READ(offset) readl(vc4->hvs->regs + offset) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 1a6db29..b8d5053 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -995,15 +995,17 @@ static const struct snd_soc_dapm_route vc4_hdmi_audio_routes[] = { { "TX", NULL, "Playback" }, }; -static const struct snd_soc_codec_driver vc4_hdmi_audio_codec_drv = { - .component_driver = { - .controls = vc4_hdmi_audio_controls, - .num_controls = ARRAY_SIZE(vc4_hdmi_audio_controls), - .dapm_widgets = vc4_hdmi_audio_widgets, - .num_dapm_widgets = ARRAY_SIZE(vc4_hdmi_audio_widgets), - .dapm_routes = vc4_hdmi_audio_routes, - .num_dapm_routes = ARRAY_SIZE(vc4_hdmi_audio_routes), - }, +static const struct snd_soc_component_driver vc4_hdmi_audio_component_drv = { + .controls = vc4_hdmi_audio_controls, + .num_controls = ARRAY_SIZE(vc4_hdmi_audio_controls), + .dapm_widgets = vc4_hdmi_audio_widgets, + .num_dapm_widgets = ARRAY_SIZE(vc4_hdmi_audio_widgets), + .dapm_routes = vc4_hdmi_audio_routes, + .num_dapm_routes = ARRAY_SIZE(vc4_hdmi_audio_routes), + .idle_bias_on = 1, + .use_pmdown_time = 1, + .endianness = 1, + .non_legacy_dai_naming = 1, }; static const struct snd_soc_dai_ops vc4_hdmi_audio_dai_ops = { @@ -1101,11 +1103,11 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *hdmi) return ret; } - /* register codec and codec dai */ - ret = snd_soc_register_codec(dev, &vc4_hdmi_audio_codec_drv, + /* register component and codec dai */ + ret = devm_snd_soc_register_component(dev, &vc4_hdmi_audio_component_drv, &vc4_hdmi_audio_codec_dai_drv, 1); if (ret) { - dev_err(dev, "Could not register codec: %d\n", ret); + dev_err(dev, "Could not register component: %d\n", ret); return ret; } @@ -1130,29 +1132,11 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *hdmi) */ snd_soc_card_set_drvdata(card, hdmi); ret = devm_snd_soc_register_card(dev, card); - if (ret) { + if (ret) dev_err(dev, "Could not register sound card: %d\n", ret); - goto unregister_codec; - } - - return 0; - -unregister_codec: - snd_soc_unregister_codec(dev); return ret; -} - -static void vc4_hdmi_audio_cleanup(struct vc4_hdmi *hdmi) -{ - struct device *dev = &hdmi->pdev->dev; - /* - * If drvdata is not set this means the audio card was not - * registered, just skip codec unregistration in this case. - */ - if (dev_get_drvdata(dev)) - snd_soc_unregister_codec(dev); } #ifdef CONFIG_DRM_VC4_HDMI_CEC @@ -1480,7 +1464,6 @@ static void vc4_hdmi_unbind(struct device *dev, struct device *master, struct vc4_dev *vc4 = drm->dev_private; struct vc4_hdmi *hdmi = vc4->hdmi; - vc4_hdmi_audio_cleanup(hdmi); cec_unregister_adapter(hdmi->cec_adap); vc4_hdmi_connector_destroy(hdmi->connector); vc4_hdmi_encoder_destroy(hdmi->encoder); diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c index 2b62fc5..5d8c749 100644 --- a/drivers/gpu/drm/vc4/vc4_hvs.c +++ b/drivers/gpu/drm/vc4/vc4_hvs.c @@ -58,6 +58,10 @@ static const struct { HVS_REG(SCALER_DISPSTAT2), HVS_REG(SCALER_DISPBASE2), HVS_REG(SCALER_DISPALPHA2), + HVS_REG(SCALER_OLEDOFFS), + HVS_REG(SCALER_OLEDCOEF0), + HVS_REG(SCALER_OLEDCOEF1), + HVS_REG(SCALER_OLEDCOEF2), }; void vc4_hvs_dump_state(struct drm_device *dev) diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index ba60153..8a411e5 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -23,6 +23,117 @@ #include <drm/drm_fb_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include "vc4_drv.h" +#include "vc4_regs.h" + +struct vc4_ctm_state { + struct drm_private_state base; + struct drm_color_ctm *ctm; + int fifo; +}; + +static struct vc4_ctm_state *to_vc4_ctm_state(struct drm_private_state *priv) +{ + return container_of(priv, struct vc4_ctm_state, base); +} + +static struct vc4_ctm_state *vc4_get_ctm_state(struct drm_atomic_state *state, + struct drm_private_obj *manager) +{ + struct drm_device *dev = state->dev; + struct vc4_dev *vc4 = dev->dev_private; + struct drm_private_state *priv_state; + int ret; + + ret = drm_modeset_lock(&vc4->ctm_state_lock, state->acquire_ctx); + if (ret) + return ERR_PTR(ret); + + priv_state = drm_atomic_get_private_obj_state(state, manager); + if (IS_ERR(priv_state)) + return ERR_CAST(priv_state); + + return to_vc4_ctm_state(priv_state); +} + +static struct drm_private_state * +vc4_ctm_duplicate_state(struct drm_private_obj *obj) +{ + struct vc4_ctm_state *state; + + state = kmemdup(obj->state, sizeof(*state), GFP_KERNEL); + if (!state) + return NULL; + + __drm_atomic_helper_private_obj_duplicate_state(obj, &state->base); + + return &state->base; +} + +static void vc4_ctm_destroy_state(struct drm_private_obj *obj, + struct drm_private_state *state) +{ + struct vc4_ctm_state *ctm_state = to_vc4_ctm_state(state); + + kfree(ctm_state); +} + +static const struct drm_private_state_funcs vc4_ctm_state_funcs = { + .atomic_duplicate_state = vc4_ctm_duplicate_state, + .atomic_destroy_state = vc4_ctm_destroy_state, +}; + +/* Converts a DRM S31.32 value to the HW S0.9 format. */ +static u16 vc4_ctm_s31_32_to_s0_9(u64 in) +{ + u16 r; + + /* Sign bit. */ + r = in & BIT_ULL(63) ? BIT(9) : 0; + + if ((in & GENMASK_ULL(62, 32)) > 0) { + /* We have zero integer bits so we can only saturate here. */ + r |= GENMASK(8, 0); + } else { + /* Otherwise take the 9 most important fractional bits. */ + r |= (in >> 23) & GENMASK(8, 0); + } + + return r; +} + +static void +vc4_ctm_commit(struct vc4_dev *vc4, struct drm_atomic_state *state) +{ + struct vc4_ctm_state *ctm_state = to_vc4_ctm_state(vc4->ctm_manager.state); + struct drm_color_ctm *ctm = ctm_state->ctm; + + if (ctm_state->fifo) { + HVS_WRITE(SCALER_OLEDCOEF2, + VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[0]), + SCALER_OLEDCOEF2_R_TO_R) | + VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[3]), + SCALER_OLEDCOEF2_R_TO_G) | + VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[6]), + SCALER_OLEDCOEF2_R_TO_B)); + HVS_WRITE(SCALER_OLEDCOEF1, + VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[1]), + SCALER_OLEDCOEF1_G_TO_R) | + VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[4]), + SCALER_OLEDCOEF1_G_TO_G) | + VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[7]), + SCALER_OLEDCOEF1_G_TO_B)); + HVS_WRITE(SCALER_OLEDCOEF0, + VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[2]), + SCALER_OLEDCOEF0_B_TO_R) | + VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[5]), + SCALER_OLEDCOEF0_B_TO_G) | + VC4_SET_FIELD(vc4_ctm_s31_32_to_s0_9(ctm->matrix[8]), + SCALER_OLEDCOEF0_B_TO_B)); + } + + HVS_WRITE(SCALER_OLEDOFFS, + VC4_SET_FIELD(ctm_state->fifo, SCALER_OLEDOFFS_DISPFIFO)); +} static void vc4_atomic_complete_commit(struct drm_atomic_state *state) @@ -36,6 +147,8 @@ vc4_atomic_complete_commit(struct drm_atomic_state *state) drm_atomic_helper_commit_modeset_disables(dev, state); + vc4_ctm_commit(vc4, state); + drm_atomic_helper_commit_planes(dev, state, 0); drm_atomic_helper_commit_modeset_enables(dev, state); @@ -90,6 +203,26 @@ static int vc4_atomic_commit(struct drm_device *dev, struct vc4_dev *vc4 = to_vc4_dev(dev); int ret; + if (state->async_update) { + ret = down_interruptible(&vc4->async_modeset); + if (ret) + return ret; + + ret = drm_atomic_helper_prepare_planes(dev, state); + if (ret) { + up(&vc4->async_modeset); + return ret; + } + + drm_atomic_helper_async_commit(dev, state); + + drm_atomic_helper_cleanup_planes(dev, state); + + up(&vc4->async_modeset); + + return 0; + } + ret = drm_atomic_helper_setup_commit(state, nonblock); if (ret) return ret; @@ -187,9 +320,89 @@ static struct drm_framebuffer *vc4_fb_create(struct drm_device *dev, return drm_gem_fb_create(dev, file_priv, mode_cmd); } +/* Our CTM has some peculiar limitations: we can only enable it for one CRTC + * at a time and the HW only supports S0.9 scalars. To account for the latter, + * we don't allow userland to set a CTM that we have no hope of approximating. + */ +static int +vc4_ctm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_ctm_state *ctm_state = NULL; + struct drm_crtc *crtc; + struct drm_crtc_state *old_crtc_state, *new_crtc_state; + struct drm_color_ctm *ctm; + int i; + + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + /* CTM is being disabled. */ + if (!new_crtc_state->ctm && old_crtc_state->ctm) { + ctm_state = vc4_get_ctm_state(state, &vc4->ctm_manager); + if (IS_ERR(ctm_state)) + return PTR_ERR(ctm_state); + ctm_state->fifo = 0; + } + } + + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + if (new_crtc_state->ctm == old_crtc_state->ctm) + continue; + + if (!ctm_state) { + ctm_state = vc4_get_ctm_state(state, &vc4->ctm_manager); + if (IS_ERR(ctm_state)) + return PTR_ERR(ctm_state); + } + + /* CTM is being enabled or the matrix changed. */ + if (new_crtc_state->ctm) { + /* fifo is 1-based since 0 disables CTM. */ + int fifo = to_vc4_crtc(crtc)->channel + 1; + + /* Check userland isn't trying to turn on CTM for more + * than one CRTC at a time. + */ + if (ctm_state->fifo && ctm_state->fifo != fifo) { + DRM_DEBUG_DRIVER("Too many CTM configured\n"); + return -EINVAL; + } + + /* Check we can approximate the specified CTM. + * We disallow scalars |c| > 1.0 since the HW has + * no integer bits. + */ + ctm = new_crtc_state->ctm->data; + for (i = 0; i < ARRAY_SIZE(ctm->matrix); i++) { + u64 val = ctm->matrix[i]; + + val &= ~BIT_ULL(63); + if (val > BIT_ULL(32)) + return -EINVAL; + } + + ctm_state->fifo = fifo; + ctm_state->ctm = ctm; + } + } + + return 0; +} + +static int +vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) +{ + int ret; + + ret = vc4_ctm_atomic_check(dev, state); + if (ret < 0) + return ret; + + return drm_atomic_helper_check(dev, state); +} + static const struct drm_mode_config_funcs vc4_mode_funcs = { .output_poll_changed = drm_fb_helper_output_poll_changed, - .atomic_check = drm_atomic_helper_check, + .atomic_check = vc4_atomic_check, .atomic_commit = vc4_atomic_commit, .fb_create = vc4_fb_create, }; @@ -197,6 +410,7 @@ static const struct drm_mode_config_funcs vc4_mode_funcs = { int vc4_kms_load(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_ctm_state *ctm_state; int ret; sema_init(&vc4->async_modeset, 1); @@ -217,6 +431,14 @@ int vc4_kms_load(struct drm_device *dev) dev->mode_config.async_page_flip = true; dev->mode_config.allow_fb_modifiers = true; + drm_modeset_lock_init(&vc4->ctm_state_lock); + + ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL); + if (!ctm_state) + return -ENOMEM; + drm_atomic_private_obj_init(&vc4->ctm_manager, &ctm_state->base, + &vc4_ctm_state_funcs); + drm_mode_config_reset(dev); if (dev->mode_config.num_connector) diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index ce39390..3483c05 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -201,6 +201,7 @@ static void vc4_plane_reset(struct drm_plane *plane) return; plane->state = &vc4_state->base; + plane->state->alpha = DRM_BLEND_ALPHA_OPAQUE; vc4_state->base.plane = plane; } @@ -467,6 +468,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane, u32 ctl0_offset = vc4_state->dlist_count; const struct hvs_format *format = vc4_get_hvs_format(fb->format->format); int num_planes = drm_format_num_planes(format->drm); + bool mix_plane_alpha; bool covers_screen; u32 scl0, scl1, pitch0; u32 lbm_size, tiling; @@ -552,7 +554,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane, /* Position Word 0: Image Positions and Alpha Value */ vc4_state->pos0_offset = vc4_state->dlist_count; vc4_dlist_write(vc4_state, - VC4_SET_FIELD(0xff, SCALER_POS0_FIXED_ALPHA) | + VC4_SET_FIELD(state->alpha >> 8, SCALER_POS0_FIXED_ALPHA) | VC4_SET_FIELD(vc4_state->crtc_x, SCALER_POS0_START_X) | VC4_SET_FIELD(vc4_state->crtc_y, SCALER_POS0_START_Y)); @@ -565,6 +567,13 @@ static int vc4_plane_mode_set(struct drm_plane *plane, SCALER_POS1_SCL_HEIGHT)); } + /* Don't waste cycles mixing with plane alpha if the set alpha + * is opaque or there is no per-pixel alpha information. + * In any case we use the alpha property value as the fixed alpha. + */ + mix_plane_alpha = state->alpha != DRM_BLEND_ALPHA_OPAQUE && + fb->format->has_alpha; + /* Position Word 2: Source Image Size, Alpha */ vc4_state->pos2_offset = vc4_state->dlist_count; vc4_dlist_write(vc4_state, @@ -572,6 +581,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane, SCALER_POS2_ALPHA_MODE_PIPELINE : SCALER_POS2_ALPHA_MODE_FIXED, SCALER_POS2_ALPHA_MODE) | + (mix_plane_alpha ? SCALER_POS2_ALPHA_MIX : 0) | (fb->format->has_alpha ? SCALER_POS2_ALPHA_PREMULT : 0) | VC4_SET_FIELD(vc4_state->src_w[0], SCALER_POS2_WIDTH) | VC4_SET_FIELD(vc4_state->src_h[0], SCALER_POS2_HEIGHT)); @@ -653,10 +663,11 @@ static int vc4_plane_mode_set(struct drm_plane *plane, vc4_state->crtc_w == state->crtc->mode.hdisplay && vc4_state->crtc_h == state->crtc->mode.vdisplay; /* Background fill might be necessary when the plane has per-pixel - * alpha content and blends from the background or does not cover - * the entire screen. + * alpha content or a non-opaque plane alpha and could blend from the + * background or does not cover the entire screen. */ - vc4_state->needs_bg_fill = fb->format->has_alpha || !covers_screen; + vc4_state->needs_bg_fill = fb->format->has_alpha || !covers_screen || + state->alpha != DRM_BLEND_ALPHA_OPAQUE; return 0; } @@ -741,6 +752,57 @@ void vc4_plane_async_set_fb(struct drm_plane *plane, struct drm_framebuffer *fb) vc4_state->dlist[vc4_state->ptr0_offset] = addr; } +static void vc4_plane_atomic_async_update(struct drm_plane *plane, + struct drm_plane_state *state) +{ + struct vc4_plane_state *vc4_state = to_vc4_plane_state(plane->state); + + if (plane->state->fb != state->fb) { + vc4_plane_async_set_fb(plane, state->fb); + drm_atomic_set_fb_for_plane(plane->state, state->fb); + } + + /* Set the cursor's position on the screen. This is the + * expected change from the drm_mode_cursor_universal() + * helper. + */ + plane->state->crtc_x = state->crtc_x; + plane->state->crtc_y = state->crtc_y; + + /* Allow changing the start position within the cursor BO, if + * that matters. + */ + plane->state->src_x = state->src_x; + plane->state->src_y = state->src_y; + + /* Update the display list based on the new crtc_x/y. */ + vc4_plane_atomic_check(plane, plane->state); + + /* Note that we can't just call vc4_plane_write_dlist() + * because that would smash the context data that the HVS is + * currently using. + */ + writel(vc4_state->dlist[vc4_state->pos0_offset], + &vc4_state->hw_dlist[vc4_state->pos0_offset]); + writel(vc4_state->dlist[vc4_state->pos2_offset], + &vc4_state->hw_dlist[vc4_state->pos2_offset]); + writel(vc4_state->dlist[vc4_state->ptr0_offset], + &vc4_state->hw_dlist[vc4_state->ptr0_offset]); +} + +static int vc4_plane_atomic_async_check(struct drm_plane *plane, + struct drm_plane_state *state) +{ + /* No configuring new scaling in the fast path. */ + if (plane->state->crtc_w != state->crtc_w || + plane->state->crtc_h != state->crtc_h || + plane->state->src_w != state->src_w || + plane->state->src_h != state->src_h) + return -EINVAL; + + return 0; +} + static int vc4_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) { @@ -780,6 +842,8 @@ static const struct drm_plane_helper_funcs vc4_plane_helper_funcs = { .atomic_update = vc4_plane_atomic_update, .prepare_fb = vc4_prepare_fb, .cleanup_fb = vc4_cleanup_fb, + .atomic_async_check = vc4_plane_atomic_async_check, + .atomic_async_update = vc4_plane_atomic_async_update, }; static void vc4_plane_destroy(struct drm_plane *plane) @@ -788,82 +852,6 @@ static void vc4_plane_destroy(struct drm_plane *plane) drm_plane_cleanup(plane); } -/* Implements immediate (non-vblank-synced) updates of the cursor - * position, or falls back to the atomic helper otherwise. - */ -static int -vc4_update_plane(struct drm_plane *plane, - struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int crtc_x, int crtc_y, - unsigned int crtc_w, unsigned int crtc_h, - uint32_t src_x, uint32_t src_y, - uint32_t src_w, uint32_t src_h, - struct drm_modeset_acquire_ctx *ctx) -{ - struct drm_plane_state *plane_state; - struct vc4_plane_state *vc4_state; - - if (plane != crtc->cursor) - goto out; - - plane_state = plane->state; - vc4_state = to_vc4_plane_state(plane_state); - - if (!plane_state) - goto out; - - /* No configuring new scaling in the fast path. */ - if (crtc_w != plane_state->crtc_w || - crtc_h != plane_state->crtc_h || - src_w != plane_state->src_w || - src_h != plane_state->src_h) { - goto out; - } - - if (fb != plane_state->fb) { - drm_atomic_set_fb_for_plane(plane->state, fb); - vc4_plane_async_set_fb(plane, fb); - } - - /* Set the cursor's position on the screen. This is the - * expected change from the drm_mode_cursor_universal() - * helper. - */ - plane_state->crtc_x = crtc_x; - plane_state->crtc_y = crtc_y; - - /* Allow changing the start position within the cursor BO, if - * that matters. - */ - plane_state->src_x = src_x; - plane_state->src_y = src_y; - - /* Update the display list based on the new crtc_x/y. */ - vc4_plane_atomic_check(plane, plane_state); - - /* Note that we can't just call vc4_plane_write_dlist() - * because that would smash the context data that the HVS is - * currently using. - */ - writel(vc4_state->dlist[vc4_state->pos0_offset], - &vc4_state->hw_dlist[vc4_state->pos0_offset]); - writel(vc4_state->dlist[vc4_state->pos2_offset], - &vc4_state->hw_dlist[vc4_state->pos2_offset]); - writel(vc4_state->dlist[vc4_state->ptr0_offset], - &vc4_state->hw_dlist[vc4_state->ptr0_offset]); - - return 0; - -out: - return drm_atomic_helper_update_plane(plane, crtc, fb, - crtc_x, crtc_y, - crtc_w, crtc_h, - src_x, src_y, - src_w, src_h, - ctx); -} - static bool vc4_format_mod_supported(struct drm_plane *plane, uint32_t format, uint64_t modifier) @@ -891,7 +879,7 @@ static bool vc4_format_mod_supported(struct drm_plane *plane, } static const struct drm_plane_funcs vc4_plane_funcs = { - .update_plane = vc4_update_plane, + .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .destroy = vc4_plane_destroy, .set_property = NULL, @@ -939,5 +927,7 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev, drm_plane_helper_add(plane, &vc4_plane_helper_funcs); + drm_plane_create_alpha_property(plane); + return plane; } diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h index a141496..d1fb6fe 100644 --- a/drivers/gpu/drm/vc4/vc4_regs.h +++ b/drivers/gpu/drm/vc4/vc4_regs.h @@ -330,6 +330,21 @@ #define SCALER_DISPCTRL0 0x00000040 # define SCALER_DISPCTRLX_ENABLE BIT(31) # define SCALER_DISPCTRLX_RESET BIT(30) +/* Generates a single frame when VSTART is seen and stops at the last + * pixel read from the FIFO. + */ +# define SCALER_DISPCTRLX_ONESHOT BIT(29) +/* Processes a single context in the dlist and then task switch, + * instead of an entire line. + */ +# define SCALER_DISPCTRLX_ONECTX BIT(28) +/* Set to have DISPSLAVE return 2 16bpp pixels and no status data. */ +# define SCALER_DISPCTRLX_FIFO32 BIT(27) +/* Turns on output to the DISPSLAVE register instead of the normal + * FIFO. + */ +# define SCALER_DISPCTRLX_FIFOREG BIT(26) + # define SCALER_DISPCTRLX_WIDTH_MASK VC4_MASK(23, 12) # define SCALER_DISPCTRLX_WIDTH_SHIFT 12 # define SCALER_DISPCTRLX_HEIGHT_MASK VC4_MASK(11, 0) @@ -402,6 +417,68 @@ */ # define SCALER_GAMADDR_SRAMENB BIT(30) +#define SCALER_OLEDOFFS 0x00000080 +/* Clamps R to [16,235] and G/B to [16,240]. */ +# define SCALER_OLEDOFFS_YUVCLAMP BIT(31) + +/* Chooses which display FIFO the matrix applies to. */ +# define SCALER_OLEDOFFS_DISPFIFO_MASK VC4_MASK(25, 24) +# define SCALER_OLEDOFFS_DISPFIFO_SHIFT 24 +# define SCALER_OLEDOFFS_DISPFIFO_DISABLED 0 +# define SCALER_OLEDOFFS_DISPFIFO_0 1 +# define SCALER_OLEDOFFS_DISPFIFO_1 2 +# define SCALER_OLEDOFFS_DISPFIFO_2 3 + +/* Offsets are 8-bit 2s-complement. */ +# define SCALER_OLEDOFFS_RED_MASK VC4_MASK(23, 16) +# define SCALER_OLEDOFFS_RED_SHIFT 16 +# define SCALER_OLEDOFFS_GREEN_MASK VC4_MASK(15, 8) +# define SCALER_OLEDOFFS_GREEN_SHIFT 8 +# define SCALER_OLEDOFFS_BLUE_MASK VC4_MASK(7, 0) +# define SCALER_OLEDOFFS_BLUE_SHIFT 0 + +/* The coefficients are S0.9 fractions. */ +#define SCALER_OLEDCOEF0 0x00000084 +# define SCALER_OLEDCOEF0_B_TO_R_MASK VC4_MASK(29, 20) +# define SCALER_OLEDCOEF0_B_TO_R_SHIFT 20 +# define SCALER_OLEDCOEF0_B_TO_G_MASK VC4_MASK(19, 10) +# define SCALER_OLEDCOEF0_B_TO_G_SHIFT 10 +# define SCALER_OLEDCOEF0_B_TO_B_MASK VC4_MASK(9, 0) +# define SCALER_OLEDCOEF0_B_TO_B_SHIFT 0 + +#define SCALER_OLEDCOEF1 0x00000088 +# define SCALER_OLEDCOEF1_G_TO_R_MASK VC4_MASK(29, 20) +# define SCALER_OLEDCOEF1_G_TO_R_SHIFT 20 +# define SCALER_OLEDCOEF1_G_TO_G_MASK VC4_MASK(19, 10) +# define SCALER_OLEDCOEF1_G_TO_G_SHIFT 10 +# define SCALER_OLEDCOEF1_G_TO_B_MASK VC4_MASK(9, 0) +# define SCALER_OLEDCOEF1_G_TO_B_SHIFT 0 + +#define SCALER_OLEDCOEF2 0x0000008c +# define SCALER_OLEDCOEF2_R_TO_R_MASK VC4_MASK(29, 20) +# define SCALER_OLEDCOEF2_R_TO_R_SHIFT 20 +# define SCALER_OLEDCOEF2_R_TO_G_MASK VC4_MASK(19, 10) +# define SCALER_OLEDCOEF2_R_TO_G_SHIFT 10 +# define SCALER_OLEDCOEF2_R_TO_B_MASK VC4_MASK(9, 0) +# define SCALER_OLEDCOEF2_R_TO_B_SHIFT 0 + +/* Slave addresses for DMAing from HVS composition output to other + * devices. The top bits are valid only in !FIFO32 mode. + */ +#define SCALER_DISPSLAVE0 0x000000c0 +#define SCALER_DISPSLAVE1 0x000000c9 +#define SCALER_DISPSLAVE2 0x000000d0 +# define SCALER_DISPSLAVE_ISSUE_VSTART BIT(31) +# define SCALER_DISPSLAVE_ISSUE_HSTART BIT(30) +/* Set when the current line has been read and an HSTART is required. */ +# define SCALER_DISPSLAVE_EOL BIT(26) +/* Set when the display FIFO is empty. */ +# define SCALER_DISPSLAVE_EMPTY BIT(25) +/* Set when there is RGB data ready to read. */ +# define SCALER_DISPSLAVE_VALID BIT(24) +# define SCALER_DISPSLAVE_RGB_MASK VC4_MASK(23, 0) +# define SCALER_DISPSLAVE_RGB_SHIFT 0 + #define SCALER_GAMDATA 0x000000e0 #define SCALER_DLIST_START 0x00002000 #define SCALER_DLIST_SIZE 0x00004000 @@ -767,6 +844,10 @@ enum hvs_pixel_format { HVS_PIXEL_FORMAT_YCBCR_YUV420_2PLANE = 9, HVS_PIXEL_FORMAT_YCBCR_YUV422_3PLANE = 10, HVS_PIXEL_FORMAT_YCBCR_YUV422_2PLANE = 11, + HVS_PIXEL_FORMAT_H264 = 12, + HVS_PIXEL_FORMAT_PALETTE = 13, + HVS_PIXEL_FORMAT_YUV444_RGB = 14, + HVS_PIXEL_FORMAT_AYUV444_RGB = 15, }; /* Note: the LSB is the rightmost character shown. Only valid for @@ -800,12 +881,27 @@ enum hvs_pixel_format { #define SCALER_CTL0_TILING_128B 2 #define SCALER_CTL0_TILING_256B_OR_T 3 +#define SCALER_CTL0_ALPHA_MASK BIT(19) #define SCALER_CTL0_HFLIP BIT(16) #define SCALER_CTL0_VFLIP BIT(15) +#define SCALER_CTL0_KEY_MODE_MASK VC4_MASK(18, 17) +#define SCALER_CTL0_KEY_MODE_SHIFT 17 +#define SCALER_CTL0_KEY_DISABLED 0 +#define SCALER_CTL0_KEY_LUMA_OR_COMMON_RGB 1 +#define SCALER_CTL0_KEY_MATCH 2 /* turn transparent */ +#define SCALER_CTL0_KEY_REPLACE 3 /* replace with value from key mask word 2 */ + #define SCALER_CTL0_ORDER_MASK VC4_MASK(14, 13) #define SCALER_CTL0_ORDER_SHIFT 13 +#define SCALER_CTL0_RGBA_EXPAND_MASK VC4_MASK(12, 11) +#define SCALER_CTL0_RGBA_EXPAND_SHIFT 11 +#define SCALER_CTL0_RGBA_EXPAND_ZERO 0 +#define SCALER_CTL0_RGBA_EXPAND_LSB 1 +#define SCALER_CTL0_RGBA_EXPAND_MSB 2 +#define SCALER_CTL0_RGBA_EXPAND_ROUND 3 + #define SCALER_CTL0_SCL1_MASK VC4_MASK(10, 8) #define SCALER_CTL0_SCL1_SHIFT 8 @@ -849,6 +945,7 @@ enum hvs_pixel_format { #define SCALER_POS2_ALPHA_MODE_FIXED_NONZERO 2 #define SCALER_POS2_ALPHA_MODE_FIXED_OVER_0x07 3 #define SCALER_POS2_ALPHA_PREMULT BIT(29) +#define SCALER_POS2_ALPHA_MIX BIT(28) #define SCALER_POS2_HEIGHT_MASK VC4_MASK(27, 16) #define SCALER_POS2_HEIGHT_SHIFT 16 diff --git a/drivers/gpu/drm/vc4/vc4_validate_shaders.c b/drivers/gpu/drm/vc4/vc4_validate_shaders.c index d3f15bf..7cf82b0 100644 --- a/drivers/gpu/drm/vc4/vc4_validate_shaders.c +++ b/drivers/gpu/drm/vc4/vc4_validate_shaders.c @@ -942,6 +942,7 @@ vc4_validate_shader(struct drm_gem_cma_object *shader_obj) fail: kfree(validation_state.branch_targets); if (validated_shader) { + kfree(validated_shader->uniform_addr_offsets); kfree(validated_shader->texture_samples); kfree(validated_shader); } diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 8cc8c34..a5edd86 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -208,7 +208,7 @@ static int virtio_gpu_conn_get_modes(struct drm_connector *connector) return count; } -static int virtio_gpu_conn_mode_valid(struct drm_connector *connector, +static enum drm_mode_status virtio_gpu_conn_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct virtio_gpu_output *output = diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index 48e4f1d..020070d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -293,7 +293,7 @@ retry: ret = virtqueue_add_sgs(vq, sgs, outcnt, incnt, vbuf, GFP_ATOMIC); if (ret == -ENOSPC) { spin_unlock(&vgdev->ctrlq.qlock); - wait_event(vgdev->ctrlq.ack_queue, vq->num_free); + wait_event(vgdev->ctrlq.ack_queue, vq->num_free >= outcnt + incnt); spin_lock(&vgdev->ctrlq.qlock); goto retry; } else { @@ -368,7 +368,7 @@ retry: ret = virtqueue_add_sgs(vq, sgs, outcnt, 0, vbuf, GFP_ATOMIC); if (ret == -ENOSPC) { spin_unlock(&vgdev->cursorq.qlock); - wait_event(vgdev->cursorq.ack_queue, vq->num_free); + wait_event(vgdev->cursorq.ack_queue, vq->num_free >= outcnt); spin_lock(&vgdev->cursorq.qlock); goto retry; } else { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index f11601b..6728c62 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -384,9 +384,9 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, hotspot_x = du->hotspot_x; hotspot_y = du->hotspot_y; - if (plane->fb) { - hotspot_x += plane->fb->hot_x; - hotspot_y += plane->fb->hot_y; + if (plane->state->fb) { + hotspot_x += plane->state->fb->hot_x; + hotspot_y += plane->state->fb->hot_y; } du->cursor_surface = vps->surf; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index 3824595..4a5907e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -281,39 +281,6 @@ drm_connector_helper_funcs vmw_ldu_connector_helper_funcs = { * Legacy Display Plane Functions */ -/** - * vmw_ldu_primary_plane_cleanup_fb - Noop - * - * @plane: display plane - * @old_state: Contains the FB to clean up - * - * Unpins the display surface - * - * Returns 0 on success - */ -static void -vmw_ldu_primary_plane_cleanup_fb(struct drm_plane *plane, - struct drm_plane_state *old_state) -{ -} - - -/** - * vmw_ldu_primary_plane_prepare_fb - Noop - * - * @plane: display plane - * @new_state: info on the new plane state, including the FB - * - * Returns 0 on success - */ -static int -vmw_ldu_primary_plane_prepare_fb(struct drm_plane *plane, - struct drm_plane_state *new_state) -{ - return 0; -} - - static void vmw_ldu_primary_plane_atomic_update(struct drm_plane *plane, struct drm_plane_state *old_state) @@ -373,8 +340,6 @@ static const struct drm_plane_helper_funcs vmw_ldu_primary_plane_helper_funcs = { .atomic_check = vmw_du_primary_plane_atomic_check, .atomic_update = vmw_ldu_primary_plane_atomic_update, - .prepare_fb = vmw_ldu_primary_plane_prepare_fb, - .cleanup_fb = vmw_ldu_primary_plane_cleanup_fb, }; static const struct drm_crtc_helper_funcs vmw_ldu_crtc_helper_funcs = { diff --git a/drivers/gpu/drm/xen/Kconfig b/drivers/gpu/drm/xen/Kconfig new file mode 100644 index 0000000..4cca160 --- /dev/null +++ b/drivers/gpu/drm/xen/Kconfig @@ -0,0 +1,17 @@ +config DRM_XEN + bool "DRM Support for Xen guest OS" + depends on XEN + help + Choose this option if you want to enable DRM support + for Xen. + +config DRM_XEN_FRONTEND + tristate "Para-virtualized frontend driver for Xen guest OS" + depends on DRM_XEN + depends on DRM + select DRM_KMS_HELPER + select VIDEOMODE_HELPERS + select XEN_XENBUS_FRONTEND + help + Choose this option if you want to enable a para-virtualized + frontend DRM/KMS driver for Xen guest OSes. diff --git a/drivers/gpu/drm/xen/Makefile b/drivers/gpu/drm/xen/Makefile new file mode 100644 index 0000000..712afff --- /dev/null +++ b/drivers/gpu/drm/xen/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 OR MIT + +drm_xen_front-objs := xen_drm_front.o \ + xen_drm_front_kms.o \ + xen_drm_front_conn.o \ + xen_drm_front_evtchnl.o \ + xen_drm_front_shbuf.o \ + xen_drm_front_cfg.o \ + xen_drm_front_gem.o + +obj-$(CONFIG_DRM_XEN_FRONTEND) += drm_xen_front.o diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c new file mode 100644 index 0000000..1b0ea9a --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -0,0 +1,840 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#include <drm/drmP.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_gem.h> + +#include <linux/of_device.h> + +#include <xen/platform_pci.h> +#include <xen/xen.h> +#include <xen/xenbus.h> + +#include <xen/interface/io/displif.h> + +#include "xen_drm_front.h" +#include "xen_drm_front_cfg.h" +#include "xen_drm_front_evtchnl.h" +#include "xen_drm_front_gem.h" +#include "xen_drm_front_kms.h" +#include "xen_drm_front_shbuf.h" + +struct xen_drm_front_dbuf { + struct list_head list; + u64 dbuf_cookie; + u64 fb_cookie; + struct xen_drm_front_shbuf *shbuf; +}; + +static int dbuf_add_to_list(struct xen_drm_front_info *front_info, + struct xen_drm_front_shbuf *shbuf, u64 dbuf_cookie) +{ + struct xen_drm_front_dbuf *dbuf; + + dbuf = kzalloc(sizeof(*dbuf), GFP_KERNEL); + if (!dbuf) + return -ENOMEM; + + dbuf->dbuf_cookie = dbuf_cookie; + dbuf->shbuf = shbuf; + list_add(&dbuf->list, &front_info->dbuf_list); + return 0; +} + +static struct xen_drm_front_dbuf *dbuf_get(struct list_head *dbuf_list, + u64 dbuf_cookie) +{ + struct xen_drm_front_dbuf *buf, *q; + + list_for_each_entry_safe(buf, q, dbuf_list, list) + if (buf->dbuf_cookie == dbuf_cookie) + return buf; + + return NULL; +} + +static void dbuf_flush_fb(struct list_head *dbuf_list, u64 fb_cookie) +{ + struct xen_drm_front_dbuf *buf, *q; + + list_for_each_entry_safe(buf, q, dbuf_list, list) + if (buf->fb_cookie == fb_cookie) + xen_drm_front_shbuf_flush(buf->shbuf); +} + +static void dbuf_free(struct list_head *dbuf_list, u64 dbuf_cookie) +{ + struct xen_drm_front_dbuf *buf, *q; + + list_for_each_entry_safe(buf, q, dbuf_list, list) + if (buf->dbuf_cookie == dbuf_cookie) { + list_del(&buf->list); + xen_drm_front_shbuf_unmap(buf->shbuf); + xen_drm_front_shbuf_free(buf->shbuf); + kfree(buf); + break; + } +} + +static void dbuf_free_all(struct list_head *dbuf_list) +{ + struct xen_drm_front_dbuf *buf, *q; + + list_for_each_entry_safe(buf, q, dbuf_list, list) { + list_del(&buf->list); + xen_drm_front_shbuf_unmap(buf->shbuf); + xen_drm_front_shbuf_free(buf->shbuf); + kfree(buf); + } +} + +static struct xendispl_req * +be_prepare_req(struct xen_drm_front_evtchnl *evtchnl, u8 operation) +{ + struct xendispl_req *req; + + req = RING_GET_REQUEST(&evtchnl->u.req.ring, + evtchnl->u.req.ring.req_prod_pvt); + req->operation = operation; + req->id = evtchnl->evt_next_id++; + evtchnl->evt_id = req->id; + return req; +} + +static int be_stream_do_io(struct xen_drm_front_evtchnl *evtchnl, + struct xendispl_req *req) +{ + reinit_completion(&evtchnl->u.req.completion); + if (unlikely(evtchnl->state != EVTCHNL_STATE_CONNECTED)) + return -EIO; + + xen_drm_front_evtchnl_flush(evtchnl); + return 0; +} + +static int be_stream_wait_io(struct xen_drm_front_evtchnl *evtchnl) +{ + if (wait_for_completion_timeout(&evtchnl->u.req.completion, + msecs_to_jiffies(XEN_DRM_FRONT_WAIT_BACK_MS)) <= 0) + return -ETIMEDOUT; + + return evtchnl->u.req.resp_status; +} + +int xen_drm_front_mode_set(struct xen_drm_front_drm_pipeline *pipeline, + u32 x, u32 y, u32 width, u32 height, + u32 bpp, u64 fb_cookie) +{ + struct xen_drm_front_evtchnl *evtchnl; + struct xen_drm_front_info *front_info; + struct xendispl_req *req; + unsigned long flags; + int ret; + + front_info = pipeline->drm_info->front_info; + evtchnl = &front_info->evt_pairs[pipeline->index].req; + if (unlikely(!evtchnl)) + return -EIO; + + mutex_lock(&evtchnl->u.req.req_io_lock); + + spin_lock_irqsave(&front_info->io_lock, flags); + req = be_prepare_req(evtchnl, XENDISPL_OP_SET_CONFIG); + req->op.set_config.x = x; + req->op.set_config.y = y; + req->op.set_config.width = width; + req->op.set_config.height = height; + req->op.set_config.bpp = bpp; + req->op.set_config.fb_cookie = fb_cookie; + + ret = be_stream_do_io(evtchnl, req); + spin_unlock_irqrestore(&front_info->io_lock, flags); + + if (ret == 0) + ret = be_stream_wait_io(evtchnl); + + mutex_unlock(&evtchnl->u.req.req_io_lock); + return ret; +} + +int xen_drm_front_dbuf_create(struct xen_drm_front_info *front_info, + u64 dbuf_cookie, u32 width, u32 height, + u32 bpp, u64 size, struct page **pages) +{ + struct xen_drm_front_evtchnl *evtchnl; + struct xen_drm_front_shbuf *shbuf; + struct xendispl_req *req; + struct xen_drm_front_shbuf_cfg buf_cfg; + unsigned long flags; + int ret; + + evtchnl = &front_info->evt_pairs[GENERIC_OP_EVT_CHNL].req; + if (unlikely(!evtchnl)) + return -EIO; + + memset(&buf_cfg, 0, sizeof(buf_cfg)); + buf_cfg.xb_dev = front_info->xb_dev; + buf_cfg.pages = pages; + buf_cfg.size = size; + buf_cfg.be_alloc = front_info->cfg.be_alloc; + + shbuf = xen_drm_front_shbuf_alloc(&buf_cfg); + if (!shbuf) + return -ENOMEM; + + ret = dbuf_add_to_list(front_info, shbuf, dbuf_cookie); + if (ret < 0) { + xen_drm_front_shbuf_free(shbuf); + return ret; + } + + mutex_lock(&evtchnl->u.req.req_io_lock); + + spin_lock_irqsave(&front_info->io_lock, flags); + req = be_prepare_req(evtchnl, XENDISPL_OP_DBUF_CREATE); + req->op.dbuf_create.gref_directory = + xen_drm_front_shbuf_get_dir_start(shbuf); + req->op.dbuf_create.buffer_sz = size; + req->op.dbuf_create.dbuf_cookie = dbuf_cookie; + req->op.dbuf_create.width = width; + req->op.dbuf_create.height = height; + req->op.dbuf_create.bpp = bpp; + if (buf_cfg.be_alloc) + req->op.dbuf_create.flags |= XENDISPL_DBUF_FLG_REQ_ALLOC; + + ret = be_stream_do_io(evtchnl, req); + spin_unlock_irqrestore(&front_info->io_lock, flags); + + if (ret < 0) + goto fail; + + ret = be_stream_wait_io(evtchnl); + if (ret < 0) + goto fail; + + ret = xen_drm_front_shbuf_map(shbuf); + if (ret < 0) + goto fail; + + mutex_unlock(&evtchnl->u.req.req_io_lock); + return 0; + +fail: + mutex_unlock(&evtchnl->u.req.req_io_lock); + dbuf_free(&front_info->dbuf_list, dbuf_cookie); + return ret; +} + +static int xen_drm_front_dbuf_destroy(struct xen_drm_front_info *front_info, + u64 dbuf_cookie) +{ + struct xen_drm_front_evtchnl *evtchnl; + struct xendispl_req *req; + unsigned long flags; + bool be_alloc; + int ret; + + evtchnl = &front_info->evt_pairs[GENERIC_OP_EVT_CHNL].req; + if (unlikely(!evtchnl)) + return -EIO; + + be_alloc = front_info->cfg.be_alloc; + + /* + * For the backend allocated buffer release references now, so backend + * can free the buffer. + */ + if (be_alloc) + dbuf_free(&front_info->dbuf_list, dbuf_cookie); + + mutex_lock(&evtchnl->u.req.req_io_lock); + + spin_lock_irqsave(&front_info->io_lock, flags); + req = be_prepare_req(evtchnl, XENDISPL_OP_DBUF_DESTROY); + req->op.dbuf_destroy.dbuf_cookie = dbuf_cookie; + + ret = be_stream_do_io(evtchnl, req); + spin_unlock_irqrestore(&front_info->io_lock, flags); + + if (ret == 0) + ret = be_stream_wait_io(evtchnl); + + /* + * Do this regardless of communication status with the backend: + * if we cannot remove remote resources remove what we can locally. + */ + if (!be_alloc) + dbuf_free(&front_info->dbuf_list, dbuf_cookie); + + mutex_unlock(&evtchnl->u.req.req_io_lock); + return ret; +} + +int xen_drm_front_fb_attach(struct xen_drm_front_info *front_info, + u64 dbuf_cookie, u64 fb_cookie, u32 width, + u32 height, u32 pixel_format) +{ + struct xen_drm_front_evtchnl *evtchnl; + struct xen_drm_front_dbuf *buf; + struct xendispl_req *req; + unsigned long flags; + int ret; + + evtchnl = &front_info->evt_pairs[GENERIC_OP_EVT_CHNL].req; + if (unlikely(!evtchnl)) + return -EIO; + + buf = dbuf_get(&front_info->dbuf_list, dbuf_cookie); + if (!buf) + return -EINVAL; + + buf->fb_cookie = fb_cookie; + + mutex_lock(&evtchnl->u.req.req_io_lock); + + spin_lock_irqsave(&front_info->io_lock, flags); + req = be_prepare_req(evtchnl, XENDISPL_OP_FB_ATTACH); + req->op.fb_attach.dbuf_cookie = dbuf_cookie; + req->op.fb_attach.fb_cookie = fb_cookie; + req->op.fb_attach.width = width; + req->op.fb_attach.height = height; + req->op.fb_attach.pixel_format = pixel_format; + + ret = be_stream_do_io(evtchnl, req); + spin_unlock_irqrestore(&front_info->io_lock, flags); + + if (ret == 0) + ret = be_stream_wait_io(evtchnl); + + mutex_unlock(&evtchnl->u.req.req_io_lock); + return ret; +} + +int xen_drm_front_fb_detach(struct xen_drm_front_info *front_info, + u64 fb_cookie) +{ + struct xen_drm_front_evtchnl *evtchnl; + struct xendispl_req *req; + unsigned long flags; + int ret; + + evtchnl = &front_info->evt_pairs[GENERIC_OP_EVT_CHNL].req; + if (unlikely(!evtchnl)) + return -EIO; + + mutex_lock(&evtchnl->u.req.req_io_lock); + + spin_lock_irqsave(&front_info->io_lock, flags); + req = be_prepare_req(evtchnl, XENDISPL_OP_FB_DETACH); + req->op.fb_detach.fb_cookie = fb_cookie; + + ret = be_stream_do_io(evtchnl, req); + spin_unlock_irqrestore(&front_info->io_lock, flags); + + if (ret == 0) + ret = be_stream_wait_io(evtchnl); + + mutex_unlock(&evtchnl->u.req.req_io_lock); + return ret; +} + +int xen_drm_front_page_flip(struct xen_drm_front_info *front_info, + int conn_idx, u64 fb_cookie) +{ + struct xen_drm_front_evtchnl *evtchnl; + struct xendispl_req *req; + unsigned long flags; + int ret; + + if (unlikely(conn_idx >= front_info->num_evt_pairs)) + return -EINVAL; + + dbuf_flush_fb(&front_info->dbuf_list, fb_cookie); + evtchnl = &front_info->evt_pairs[conn_idx].req; + + mutex_lock(&evtchnl->u.req.req_io_lock); + + spin_lock_irqsave(&front_info->io_lock, flags); + req = be_prepare_req(evtchnl, XENDISPL_OP_PG_FLIP); + req->op.pg_flip.fb_cookie = fb_cookie; + + ret = be_stream_do_io(evtchnl, req); + spin_unlock_irqrestore(&front_info->io_lock, flags); + + if (ret == 0) + ret = be_stream_wait_io(evtchnl); + + mutex_unlock(&evtchnl->u.req.req_io_lock); + return ret; +} + +void xen_drm_front_on_frame_done(struct xen_drm_front_info *front_info, + int conn_idx, u64 fb_cookie) +{ + struct xen_drm_front_drm_info *drm_info = front_info->drm_info; + + if (unlikely(conn_idx >= front_info->cfg.num_connectors)) + return; + + xen_drm_front_kms_on_frame_done(&drm_info->pipeline[conn_idx], + fb_cookie); +} + +static int xen_drm_drv_dumb_create(struct drm_file *filp, + struct drm_device *dev, + struct drm_mode_create_dumb *args) +{ + struct xen_drm_front_drm_info *drm_info = dev->dev_private; + struct drm_gem_object *obj; + int ret; + + /* + * Dumb creation is a two stage process: first we create a fully + * constructed GEM object which is communicated to the backend, and + * only after that we can create GEM's handle. This is done so, + * because of the possible races: once you create a handle it becomes + * immediately visible to user-space, so the latter can try accessing + * object without pages etc. + * For details also see drm_gem_handle_create + */ + args->pitch = DIV_ROUND_UP(args->width * args->bpp, 8); + args->size = args->pitch * args->height; + + obj = xen_drm_front_gem_create(dev, args->size); + if (IS_ERR_OR_NULL(obj)) { + ret = PTR_ERR(obj); + goto fail; + } + + ret = xen_drm_front_dbuf_create(drm_info->front_info, + xen_drm_front_dbuf_to_cookie(obj), + args->width, args->height, args->bpp, + args->size, + xen_drm_front_gem_get_pages(obj)); + if (ret) + goto fail_backend; + + /* This is the tail of GEM object creation */ + ret = drm_gem_handle_create(filp, obj, &args->handle); + if (ret) + goto fail_handle; + + /* Drop reference from allocate - handle holds it now */ + drm_gem_object_put_unlocked(obj); + return 0; + +fail_handle: + xen_drm_front_dbuf_destroy(drm_info->front_info, + xen_drm_front_dbuf_to_cookie(obj)); +fail_backend: + /* drop reference from allocate */ + drm_gem_object_put_unlocked(obj); +fail: + DRM_ERROR("Failed to create dumb buffer: %d\n", ret); + return ret; +} + +static void xen_drm_drv_free_object_unlocked(struct drm_gem_object *obj) +{ + struct xen_drm_front_drm_info *drm_info = obj->dev->dev_private; + int idx; + + if (drm_dev_enter(obj->dev, &idx)) { + xen_drm_front_dbuf_destroy(drm_info->front_info, + xen_drm_front_dbuf_to_cookie(obj)); + drm_dev_exit(idx); + } else { + dbuf_free(&drm_info->front_info->dbuf_list, + xen_drm_front_dbuf_to_cookie(obj)); + } + + xen_drm_front_gem_free_object_unlocked(obj); +} + +static void xen_drm_drv_release(struct drm_device *dev) +{ + struct xen_drm_front_drm_info *drm_info = dev->dev_private; + struct xen_drm_front_info *front_info = drm_info->front_info; + + xen_drm_front_kms_fini(drm_info); + + drm_atomic_helper_shutdown(dev); + drm_mode_config_cleanup(dev); + + drm_dev_fini(dev); + kfree(dev); + + if (front_info->cfg.be_alloc) + xenbus_switch_state(front_info->xb_dev, + XenbusStateInitialising); + + kfree(drm_info); +} + +static const struct file_operations xen_drm_dev_fops = { + .owner = THIS_MODULE, + .open = drm_open, + .release = drm_release, + .unlocked_ioctl = drm_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = drm_compat_ioctl, +#endif + .poll = drm_poll, + .read = drm_read, + .llseek = no_llseek, + .mmap = xen_drm_front_gem_mmap, +}; + +static const struct vm_operations_struct xen_drm_drv_vm_ops = { + .open = drm_gem_vm_open, + .close = drm_gem_vm_close, +}; + +static struct drm_driver xen_drm_driver = { + .driver_features = DRIVER_GEM | DRIVER_MODESET | + DRIVER_PRIME | DRIVER_ATOMIC, + .release = xen_drm_drv_release, + .gem_vm_ops = &xen_drm_drv_vm_ops, + .gem_free_object_unlocked = xen_drm_drv_free_object_unlocked, + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_import = drm_gem_prime_import, + .gem_prime_export = drm_gem_prime_export, + .gem_prime_import_sg_table = xen_drm_front_gem_import_sg_table, + .gem_prime_get_sg_table = xen_drm_front_gem_get_sg_table, + .gem_prime_vmap = xen_drm_front_gem_prime_vmap, + .gem_prime_vunmap = xen_drm_front_gem_prime_vunmap, + .gem_prime_mmap = xen_drm_front_gem_prime_mmap, + .dumb_create = xen_drm_drv_dumb_create, + .fops = &xen_drm_dev_fops, + .name = "xendrm-du", + .desc = "Xen PV DRM Display Unit", + .date = "20180221", + .major = 1, + .minor = 0, + +}; + +static int xen_drm_drv_init(struct xen_drm_front_info *front_info) +{ + struct device *dev = &front_info->xb_dev->dev; + struct xen_drm_front_drm_info *drm_info; + struct drm_device *drm_dev; + int ret; + + DRM_INFO("Creating %s\n", xen_drm_driver.desc); + + drm_info = kzalloc(sizeof(*drm_info), GFP_KERNEL); + if (!drm_info) { + ret = -ENOMEM; + goto fail; + } + + drm_info->front_info = front_info; + front_info->drm_info = drm_info; + + drm_dev = drm_dev_alloc(&xen_drm_driver, dev); + if (!drm_dev) { + ret = -ENOMEM; + goto fail; + } + + drm_info->drm_dev = drm_dev; + + drm_dev->dev_private = drm_info; + + ret = xen_drm_front_kms_init(drm_info); + if (ret) { + DRM_ERROR("Failed to initialize DRM/KMS, ret %d\n", ret); + goto fail_modeset; + } + + ret = drm_dev_register(drm_dev, 0); + if (ret) + goto fail_register; + + DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n", + xen_drm_driver.name, xen_drm_driver.major, + xen_drm_driver.minor, xen_drm_driver.patchlevel, + xen_drm_driver.date, drm_dev->primary->index); + + return 0; + +fail_register: + drm_dev_unregister(drm_dev); +fail_modeset: + drm_kms_helper_poll_fini(drm_dev); + drm_mode_config_cleanup(drm_dev); +fail: + kfree(drm_info); + return ret; +} + +static void xen_drm_drv_fini(struct xen_drm_front_info *front_info) +{ + struct xen_drm_front_drm_info *drm_info = front_info->drm_info; + struct drm_device *dev; + + if (!drm_info) + return; + + dev = drm_info->drm_dev; + if (!dev) + return; + + /* Nothing to do if device is already unplugged */ + if (drm_dev_is_unplugged(dev)) + return; + + drm_kms_helper_poll_fini(dev); + drm_dev_unplug(dev); + + front_info->drm_info = NULL; + + xen_drm_front_evtchnl_free_all(front_info); + dbuf_free_all(&front_info->dbuf_list); + + /* + * If we are not using backend allocated buffers, then tell the + * backend we are ready to (re)initialize. Otherwise, wait for + * drm_driver.release. + */ + if (!front_info->cfg.be_alloc) + xenbus_switch_state(front_info->xb_dev, + XenbusStateInitialising); +} + +static int displback_initwait(struct xen_drm_front_info *front_info) +{ + struct xen_drm_front_cfg *cfg = &front_info->cfg; + int ret; + + cfg->front_info = front_info; + ret = xen_drm_front_cfg_card(front_info, cfg); + if (ret < 0) + return ret; + + DRM_INFO("Have %d conector(s)\n", cfg->num_connectors); + /* Create event channels for all connectors and publish */ + ret = xen_drm_front_evtchnl_create_all(front_info); + if (ret < 0) + return ret; + + return xen_drm_front_evtchnl_publish_all(front_info); +} + +static int displback_connect(struct xen_drm_front_info *front_info) +{ + xen_drm_front_evtchnl_set_state(front_info, EVTCHNL_STATE_CONNECTED); + return xen_drm_drv_init(front_info); +} + +static void displback_disconnect(struct xen_drm_front_info *front_info) +{ + if (!front_info->drm_info) + return; + + /* Tell the backend to wait until we release the DRM driver. */ + xenbus_switch_state(front_info->xb_dev, XenbusStateReconfiguring); + + xen_drm_drv_fini(front_info); +} + +static void displback_changed(struct xenbus_device *xb_dev, + enum xenbus_state backend_state) +{ + struct xen_drm_front_info *front_info = dev_get_drvdata(&xb_dev->dev); + int ret; + + DRM_DEBUG("Backend state is %s, front is %s\n", + xenbus_strstate(backend_state), + xenbus_strstate(xb_dev->state)); + + switch (backend_state) { + case XenbusStateReconfiguring: + /* fall through */ + case XenbusStateReconfigured: + /* fall through */ + case XenbusStateInitialised: + break; + + case XenbusStateInitialising: + if (xb_dev->state == XenbusStateReconfiguring) + break; + + /* recovering after backend unexpected closure */ + displback_disconnect(front_info); + break; + + case XenbusStateInitWait: + if (xb_dev->state == XenbusStateReconfiguring) + break; + + /* recovering after backend unexpected closure */ + displback_disconnect(front_info); + if (xb_dev->state != XenbusStateInitialising) + break; + + ret = displback_initwait(front_info); + if (ret < 0) + xenbus_dev_fatal(xb_dev, ret, "initializing frontend"); + else + xenbus_switch_state(xb_dev, XenbusStateInitialised); + break; + + case XenbusStateConnected: + if (xb_dev->state != XenbusStateInitialised) + break; + + ret = displback_connect(front_info); + if (ret < 0) { + displback_disconnect(front_info); + xenbus_dev_fatal(xb_dev, ret, "connecting backend"); + } else { + xenbus_switch_state(xb_dev, XenbusStateConnected); + } + break; + + case XenbusStateClosing: + /* + * in this state backend starts freeing resources, + * so let it go into closed state, so we can also + * remove ours + */ + break; + + case XenbusStateUnknown: + /* fall through */ + case XenbusStateClosed: + if (xb_dev->state == XenbusStateClosed) + break; + + displback_disconnect(front_info); + break; + } +} + +static int xen_drv_probe(struct xenbus_device *xb_dev, + const struct xenbus_device_id *id) +{ + struct xen_drm_front_info *front_info; + struct device *dev = &xb_dev->dev; + int ret; + + /* + * The device is not spawn from a device tree, so arch_setup_dma_ops + * is not called, thus leaving the device with dummy DMA ops. + * This makes the device return error on PRIME buffer import, which + * is not correct: to fix this call of_dma_configure() with a NULL + * node to set default DMA ops. + */ + dev->bus->force_dma = true; + dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = of_dma_configure(dev, NULL); + if (ret < 0) { + DRM_ERROR("Cannot setup DMA ops, ret %d", ret); + return ret; + } + + front_info = devm_kzalloc(&xb_dev->dev, + sizeof(*front_info), GFP_KERNEL); + if (!front_info) + return -ENOMEM; + + front_info->xb_dev = xb_dev; + spin_lock_init(&front_info->io_lock); + INIT_LIST_HEAD(&front_info->dbuf_list); + dev_set_drvdata(&xb_dev->dev, front_info); + + return xenbus_switch_state(xb_dev, XenbusStateInitialising); +} + +static int xen_drv_remove(struct xenbus_device *dev) +{ + struct xen_drm_front_info *front_info = dev_get_drvdata(&dev->dev); + int to = 100; + + xenbus_switch_state(dev, XenbusStateClosing); + + /* + * On driver removal it is disconnected from XenBus, + * so no backend state change events come via .otherend_changed + * callback. This prevents us from exiting gracefully, e.g. + * signaling the backend to free event channels, waiting for its + * state to change to XenbusStateClosed and cleaning at our end. + * Normally when front driver removed backend will finally go into + * XenbusStateInitWait state. + * + * Workaround: read backend's state manually and wait with time-out. + */ + while ((xenbus_read_unsigned(front_info->xb_dev->otherend, "state", + XenbusStateUnknown) != XenbusStateInitWait) && + to--) + msleep(10); + + if (!to) { + unsigned int state; + + state = xenbus_read_unsigned(front_info->xb_dev->otherend, + "state", XenbusStateUnknown); + DRM_ERROR("Backend state is %s while removing driver\n", + xenbus_strstate(state)); + } + + xen_drm_drv_fini(front_info); + xenbus_frontend_closed(dev); + return 0; +} + +static const struct xenbus_device_id xen_driver_ids[] = { + { XENDISPL_DRIVER_NAME }, + { "" } +}; + +static struct xenbus_driver xen_driver = { + .ids = xen_driver_ids, + .probe = xen_drv_probe, + .remove = xen_drv_remove, + .otherend_changed = displback_changed, +}; + +static int __init xen_drv_init(void) +{ + /* At the moment we only support case with XEN_PAGE_SIZE == PAGE_SIZE */ + if (XEN_PAGE_SIZE != PAGE_SIZE) { + DRM_ERROR(XENDISPL_DRIVER_NAME ": different kernel and Xen page sizes are not supported: XEN_PAGE_SIZE (%lu) != PAGE_SIZE (%lu)\n", + XEN_PAGE_SIZE, PAGE_SIZE); + return -ENODEV; + } + + if (!xen_domain()) + return -ENODEV; + + if (!xen_has_pv_devices()) + return -ENODEV; + + DRM_INFO("Registering XEN PV " XENDISPL_DRIVER_NAME "\n"); + return xenbus_register_frontend(&xen_driver); +} + +static void __exit xen_drv_fini(void) +{ + DRM_INFO("Unregistering XEN PV " XENDISPL_DRIVER_NAME "\n"); + xenbus_unregister_driver(&xen_driver); +} + +module_init(xen_drv_init); +module_exit(xen_drv_fini); + +MODULE_DESCRIPTION("Xen para-virtualized display device frontend"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("xen:" XENDISPL_DRIVER_NAME); diff --git a/drivers/gpu/drm/xen/xen_drm_front.h b/drivers/gpu/drm/xen/xen_drm_front.h new file mode 100644 index 0000000..2c2479b --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#ifndef __XEN_DRM_FRONT_H_ +#define __XEN_DRM_FRONT_H_ + +#include <drm/drmP.h> +#include <drm/drm_simple_kms_helper.h> + +#include <linux/scatterlist.h> + +#include "xen_drm_front_cfg.h" + +/** + * DOC: Driver modes of operation in terms of display buffers used + * + * Depending on the requirements for the para-virtualized environment, namely + * requirements dictated by the accompanying DRM/(v)GPU drivers running in both + * host and guest environments, display buffers can be allocated by either + * frontend driver or backend. + */ + +/** + * DOC: Buffers allocated by the frontend driver + * + * In this mode of operation driver allocates buffers from system memory. + * + * Note! If used with accompanying DRM/(v)GPU drivers this mode of operation + * may require IOMMU support on the platform, so accompanying DRM/vGPU + * hardware can still reach display buffer memory while importing PRIME + * buffers from the frontend driver. + */ + +/** + * DOC: Buffers allocated by the backend + * + * This mode of operation is run-time configured via guest domain configuration + * through XenStore entries. + * + * For systems which do not provide IOMMU support, but having specific + * requirements for display buffers it is possible to allocate such buffers + * at backend side and share those with the frontend. + * For example, if host domain is 1:1 mapped and has DRM/GPU hardware expecting + * physically contiguous memory, this allows implementing zero-copying + * use-cases. + * + * Note, while using this scenario the following should be considered: + * + * #. If guest domain dies then pages/grants received from the backend + * cannot be claimed back + * + * #. Misbehaving guest may send too many requests to the + * backend exhausting its grant references and memory + * (consider this from security POV) + */ + +/** + * DOC: Driver limitations + * + * #. Only primary plane without additional properties is supported. + * + * #. Only one video mode per connector supported which is configured + * via XenStore. + * + * #. All CRTCs operate at fixed frequency of 60Hz. + */ + +/* timeout in ms to wait for backend to respond */ +#define XEN_DRM_FRONT_WAIT_BACK_MS 3000 + +#ifndef GRANT_INVALID_REF +/* + * Note on usage of grant reference 0 as invalid grant reference: + * grant reference 0 is valid, but never exposed to a PV driver, + * because of the fact it is already in use/reserved by the PV console. + */ +#define GRANT_INVALID_REF 0 +#endif + +struct xen_drm_front_info { + struct xenbus_device *xb_dev; + struct xen_drm_front_drm_info *drm_info; + + /* to protect data between backend IO code and interrupt handler */ + spinlock_t io_lock; + + int num_evt_pairs; + struct xen_drm_front_evtchnl_pair *evt_pairs; + struct xen_drm_front_cfg cfg; + + /* display buffers */ + struct list_head dbuf_list; +}; + +struct xen_drm_front_drm_pipeline { + struct xen_drm_front_drm_info *drm_info; + + int index; + + struct drm_simple_display_pipe pipe; + + struct drm_connector conn; + /* These are only for connector mode checking */ + int width, height; + + struct drm_pending_vblank_event *pending_event; + + struct delayed_work pflip_to_worker; + + bool conn_connected; +}; + +struct xen_drm_front_drm_info { + struct xen_drm_front_info *front_info; + struct drm_device *drm_dev; + + struct xen_drm_front_drm_pipeline pipeline[XEN_DRM_FRONT_MAX_CRTCS]; +}; + +static inline u64 xen_drm_front_fb_to_cookie(struct drm_framebuffer *fb) +{ + return (u64)fb; +} + +static inline u64 xen_drm_front_dbuf_to_cookie(struct drm_gem_object *gem_obj) +{ + return (u64)gem_obj; +} + +int xen_drm_front_mode_set(struct xen_drm_front_drm_pipeline *pipeline, + u32 x, u32 y, u32 width, u32 height, + u32 bpp, u64 fb_cookie); + +int xen_drm_front_dbuf_create(struct xen_drm_front_info *front_info, + u64 dbuf_cookie, u32 width, u32 height, + u32 bpp, u64 size, struct page **pages); + +int xen_drm_front_fb_attach(struct xen_drm_front_info *front_info, + u64 dbuf_cookie, u64 fb_cookie, u32 width, + u32 height, u32 pixel_format); + +int xen_drm_front_fb_detach(struct xen_drm_front_info *front_info, + u64 fb_cookie); + +int xen_drm_front_page_flip(struct xen_drm_front_info *front_info, + int conn_idx, u64 fb_cookie); + +void xen_drm_front_on_frame_done(struct xen_drm_front_info *front_info, + int conn_idx, u64 fb_cookie); + +#endif /* __XEN_DRM_FRONT_H_ */ diff --git a/drivers/gpu/drm/xen/xen_drm_front_cfg.c b/drivers/gpu/drm/xen/xen_drm_front_cfg.c new file mode 100644 index 0000000..5baf2b9 --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_cfg.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#include <drm/drmP.h> + +#include <linux/device.h> + +#include <xen/interface/io/displif.h> +#include <xen/xenbus.h> + +#include "xen_drm_front.h" +#include "xen_drm_front_cfg.h" + +static int cfg_connector(struct xen_drm_front_info *front_info, + struct xen_drm_front_cfg_connector *connector, + const char *path, int index) +{ + char *connector_path; + + connector_path = devm_kasprintf(&front_info->xb_dev->dev, + GFP_KERNEL, "%s/%d", path, index); + if (!connector_path) + return -ENOMEM; + + if (xenbus_scanf(XBT_NIL, connector_path, XENDISPL_FIELD_RESOLUTION, + "%d" XENDISPL_RESOLUTION_SEPARATOR "%d", + &connector->width, &connector->height) < 0) { + /* either no entry configured or wrong resolution set */ + connector->width = 0; + connector->height = 0; + return -EINVAL; + } + + connector->xenstore_path = connector_path; + + DRM_INFO("Connector %s: resolution %dx%d\n", + connector_path, connector->width, connector->height); + return 0; +} + +int xen_drm_front_cfg_card(struct xen_drm_front_info *front_info, + struct xen_drm_front_cfg *cfg) +{ + struct xenbus_device *xb_dev = front_info->xb_dev; + int ret, i; + + if (xenbus_read_unsigned(front_info->xb_dev->nodename, + XENDISPL_FIELD_BE_ALLOC, 0)) { + DRM_INFO("Backend can provide display buffers\n"); + cfg->be_alloc = true; + } + + cfg->num_connectors = 0; + for (i = 0; i < ARRAY_SIZE(cfg->connectors); i++) { + ret = cfg_connector(front_info, &cfg->connectors[i], + xb_dev->nodename, i); + if (ret < 0) + break; + cfg->num_connectors++; + } + + if (!cfg->num_connectors) { + DRM_ERROR("No connector(s) configured at %s\n", + xb_dev->nodename); + return -ENODEV; + } + + return 0; +} + diff --git a/drivers/gpu/drm/xen/xen_drm_front_cfg.h b/drivers/gpu/drm/xen/xen_drm_front_cfg.h new file mode 100644 index 0000000..aa8490b --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_cfg.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#ifndef __XEN_DRM_FRONT_CFG_H_ +#define __XEN_DRM_FRONT_CFG_H_ + +#include <linux/types.h> + +#define XEN_DRM_FRONT_MAX_CRTCS 4 + +struct xen_drm_front_cfg_connector { + int width; + int height; + char *xenstore_path; +}; + +struct xen_drm_front_cfg { + struct xen_drm_front_info *front_info; + /* number of connectors in this configuration */ + int num_connectors; + /* connector configurations */ + struct xen_drm_front_cfg_connector connectors[XEN_DRM_FRONT_MAX_CRTCS]; + /* set if dumb buffers are allocated externally on backend side */ + bool be_alloc; +}; + +int xen_drm_front_cfg_card(struct xen_drm_front_info *front_info, + struct xen_drm_front_cfg *cfg); + +#endif /* __XEN_DRM_FRONT_CFG_H_ */ diff --git a/drivers/gpu/drm/xen/xen_drm_front_conn.c b/drivers/gpu/drm/xen/xen_drm_front_conn.c new file mode 100644 index 0000000..c91ae53 --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_conn.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_crtc_helper.h> + +#include <video/videomode.h> + +#include "xen_drm_front.h" +#include "xen_drm_front_conn.h" +#include "xen_drm_front_kms.h" + +static struct xen_drm_front_drm_pipeline * +to_xen_drm_pipeline(struct drm_connector *connector) +{ + return container_of(connector, struct xen_drm_front_drm_pipeline, conn); +} + +static const u32 plane_formats[] = { + DRM_FORMAT_RGB565, + DRM_FORMAT_RGB888, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_XRGB4444, + DRM_FORMAT_ARGB4444, + DRM_FORMAT_XRGB1555, + DRM_FORMAT_ARGB1555, +}; + +const u32 *xen_drm_front_conn_get_formats(int *format_count) +{ + *format_count = ARRAY_SIZE(plane_formats); + return plane_formats; +} + +static int connector_detect(struct drm_connector *connector, + struct drm_modeset_acquire_ctx *ctx, + bool force) +{ + struct xen_drm_front_drm_pipeline *pipeline = + to_xen_drm_pipeline(connector); + + if (drm_dev_is_unplugged(connector->dev)) + pipeline->conn_connected = false; + + return pipeline->conn_connected ? connector_status_connected : + connector_status_disconnected; +} + +#define XEN_DRM_CRTC_VREFRESH_HZ 60 + +static int connector_get_modes(struct drm_connector *connector) +{ + struct xen_drm_front_drm_pipeline *pipeline = + to_xen_drm_pipeline(connector); + struct drm_display_mode *mode; + struct videomode videomode; + int width, height; + + mode = drm_mode_create(connector->dev); + if (!mode) + return 0; + + memset(&videomode, 0, sizeof(videomode)); + videomode.hactive = pipeline->width; + videomode.vactive = pipeline->height; + width = videomode.hactive + videomode.hfront_porch + + videomode.hback_porch + videomode.hsync_len; + height = videomode.vactive + videomode.vfront_porch + + videomode.vback_porch + videomode.vsync_len; + videomode.pixelclock = width * height * XEN_DRM_CRTC_VREFRESH_HZ; + mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER; + + drm_display_mode_from_videomode(&videomode, mode); + drm_mode_probed_add(connector, mode); + return 1; +} + +static const struct drm_connector_helper_funcs connector_helper_funcs = { + .get_modes = connector_get_modes, + .detect_ctx = connector_detect, +}; + +static const struct drm_connector_funcs connector_funcs = { + .dpms = drm_helper_connector_dpms, + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = drm_connector_cleanup, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +int xen_drm_front_conn_init(struct xen_drm_front_drm_info *drm_info, + struct drm_connector *connector) +{ + struct xen_drm_front_drm_pipeline *pipeline = + to_xen_drm_pipeline(connector); + + drm_connector_helper_add(connector, &connector_helper_funcs); + + pipeline->conn_connected = true; + + connector->polled = DRM_CONNECTOR_POLL_CONNECT | + DRM_CONNECTOR_POLL_DISCONNECT; + + return drm_connector_init(drm_info->drm_dev, connector, + &connector_funcs, DRM_MODE_CONNECTOR_VIRTUAL); +} diff --git a/drivers/gpu/drm/xen/xen_drm_front_conn.h b/drivers/gpu/drm/xen/xen_drm_front_conn.h new file mode 100644 index 0000000..39de7cf --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_conn.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#ifndef __XEN_DRM_FRONT_CONN_H_ +#define __XEN_DRM_FRONT_CONN_H_ + +#include <drm/drmP.h> +#include <drm/drm_crtc.h> +#include <drm/drm_encoder.h> + +#include <linux/wait.h> + +struct xen_drm_front_drm_info; + +int xen_drm_front_conn_init(struct xen_drm_front_drm_info *drm_info, + struct drm_connector *connector); + +const u32 *xen_drm_front_conn_get_formats(int *format_count); + +#endif /* __XEN_DRM_FRONT_CONN_H_ */ diff --git a/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c new file mode 100644 index 0000000..945226a --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.c @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#include <drm/drmP.h> + +#include <linux/errno.h> +#include <linux/irq.h> + +#include <xen/xenbus.h> +#include <xen/events.h> +#include <xen/grant_table.h> + +#include "xen_drm_front.h" +#include "xen_drm_front_evtchnl.h" + +static irqreturn_t evtchnl_interrupt_ctrl(int irq, void *dev_id) +{ + struct xen_drm_front_evtchnl *evtchnl = dev_id; + struct xen_drm_front_info *front_info = evtchnl->front_info; + struct xendispl_resp *resp; + RING_IDX i, rp; + unsigned long flags; + + if (unlikely(evtchnl->state != EVTCHNL_STATE_CONNECTED)) + return IRQ_HANDLED; + + spin_lock_irqsave(&front_info->io_lock, flags); + +again: + rp = evtchnl->u.req.ring.sring->rsp_prod; + /* ensure we see queued responses up to rp */ + virt_rmb(); + + for (i = evtchnl->u.req.ring.rsp_cons; i != rp; i++) { + resp = RING_GET_RESPONSE(&evtchnl->u.req.ring, i); + if (unlikely(resp->id != evtchnl->evt_id)) + continue; + + switch (resp->operation) { + case XENDISPL_OP_PG_FLIP: + case XENDISPL_OP_FB_ATTACH: + case XENDISPL_OP_FB_DETACH: + case XENDISPL_OP_DBUF_CREATE: + case XENDISPL_OP_DBUF_DESTROY: + case XENDISPL_OP_SET_CONFIG: + evtchnl->u.req.resp_status = resp->status; + complete(&evtchnl->u.req.completion); + break; + + default: + DRM_ERROR("Operation %d is not supported\n", + resp->operation); + break; + } + } + + evtchnl->u.req.ring.rsp_cons = i; + + if (i != evtchnl->u.req.ring.req_prod_pvt) { + int more_to_do; + + RING_FINAL_CHECK_FOR_RESPONSES(&evtchnl->u.req.ring, + more_to_do); + if (more_to_do) + goto again; + } else { + evtchnl->u.req.ring.sring->rsp_event = i + 1; + } + + spin_unlock_irqrestore(&front_info->io_lock, flags); + return IRQ_HANDLED; +} + +static irqreturn_t evtchnl_interrupt_evt(int irq, void *dev_id) +{ + struct xen_drm_front_evtchnl *evtchnl = dev_id; + struct xen_drm_front_info *front_info = evtchnl->front_info; + struct xendispl_event_page *page = evtchnl->u.evt.page; + u32 cons, prod; + unsigned long flags; + + if (unlikely(evtchnl->state != EVTCHNL_STATE_CONNECTED)) + return IRQ_HANDLED; + + spin_lock_irqsave(&front_info->io_lock, flags); + + prod = page->in_prod; + /* ensure we see ring contents up to prod */ + virt_rmb(); + if (prod == page->in_cons) + goto out; + + for (cons = page->in_cons; cons != prod; cons++) { + struct xendispl_evt *event; + + event = &XENDISPL_IN_RING_REF(page, cons); + if (unlikely(event->id != evtchnl->evt_id++)) + continue; + + switch (event->type) { + case XENDISPL_EVT_PG_FLIP: + xen_drm_front_on_frame_done(front_info, evtchnl->index, + event->op.pg_flip.fb_cookie); + break; + } + } + page->in_cons = cons; + /* ensure ring contents */ + virt_wmb(); + +out: + spin_unlock_irqrestore(&front_info->io_lock, flags); + return IRQ_HANDLED; +} + +static void evtchnl_free(struct xen_drm_front_info *front_info, + struct xen_drm_front_evtchnl *evtchnl) +{ + unsigned long page = 0; + + if (evtchnl->type == EVTCHNL_TYPE_REQ) + page = (unsigned long)evtchnl->u.req.ring.sring; + else if (evtchnl->type == EVTCHNL_TYPE_EVT) + page = (unsigned long)evtchnl->u.evt.page; + if (!page) + return; + + evtchnl->state = EVTCHNL_STATE_DISCONNECTED; + + if (evtchnl->type == EVTCHNL_TYPE_REQ) { + /* release all who still waits for response if any */ + evtchnl->u.req.resp_status = -EIO; + complete_all(&evtchnl->u.req.completion); + } + + if (evtchnl->irq) + unbind_from_irqhandler(evtchnl->irq, evtchnl); + + if (evtchnl->port) + xenbus_free_evtchn(front_info->xb_dev, evtchnl->port); + + /* end access and free the page */ + if (evtchnl->gref != GRANT_INVALID_REF) + gnttab_end_foreign_access(evtchnl->gref, 0, page); + + memset(evtchnl, 0, sizeof(*evtchnl)); +} + +static int evtchnl_alloc(struct xen_drm_front_info *front_info, int index, + struct xen_drm_front_evtchnl *evtchnl, + enum xen_drm_front_evtchnl_type type) +{ + struct xenbus_device *xb_dev = front_info->xb_dev; + unsigned long page; + grant_ref_t gref; + irq_handler_t handler; + int ret; + + memset(evtchnl, 0, sizeof(*evtchnl)); + evtchnl->type = type; + evtchnl->index = index; + evtchnl->front_info = front_info; + evtchnl->state = EVTCHNL_STATE_DISCONNECTED; + evtchnl->gref = GRANT_INVALID_REF; + + page = get_zeroed_page(GFP_NOIO | __GFP_HIGH); + if (!page) { + ret = -ENOMEM; + goto fail; + } + + if (type == EVTCHNL_TYPE_REQ) { + struct xen_displif_sring *sring; + + init_completion(&evtchnl->u.req.completion); + mutex_init(&evtchnl->u.req.req_io_lock); + sring = (struct xen_displif_sring *)page; + SHARED_RING_INIT(sring); + FRONT_RING_INIT(&evtchnl->u.req.ring, sring, XEN_PAGE_SIZE); + + ret = xenbus_grant_ring(xb_dev, sring, 1, &gref); + if (ret < 0) { + evtchnl->u.req.ring.sring = NULL; + free_page(page); + goto fail; + } + + handler = evtchnl_interrupt_ctrl; + } else { + ret = gnttab_grant_foreign_access(xb_dev->otherend_id, + virt_to_gfn((void *)page), 0); + if (ret < 0) { + free_page(page); + goto fail; + } + + evtchnl->u.evt.page = (struct xendispl_event_page *)page; + gref = ret; + handler = evtchnl_interrupt_evt; + } + evtchnl->gref = gref; + + ret = xenbus_alloc_evtchn(xb_dev, &evtchnl->port); + if (ret < 0) + goto fail; + + ret = bind_evtchn_to_irqhandler(evtchnl->port, + handler, 0, xb_dev->devicetype, + evtchnl); + if (ret < 0) + goto fail; + + evtchnl->irq = ret; + return 0; + +fail: + DRM_ERROR("Failed to allocate ring: %d\n", ret); + return ret; +} + +int xen_drm_front_evtchnl_create_all(struct xen_drm_front_info *front_info) +{ + struct xen_drm_front_cfg *cfg; + int ret, conn; + + cfg = &front_info->cfg; + + front_info->evt_pairs = + kcalloc(cfg->num_connectors, + sizeof(struct xen_drm_front_evtchnl_pair), + GFP_KERNEL); + if (!front_info->evt_pairs) { + ret = -ENOMEM; + goto fail; + } + + for (conn = 0; conn < cfg->num_connectors; conn++) { + ret = evtchnl_alloc(front_info, conn, + &front_info->evt_pairs[conn].req, + EVTCHNL_TYPE_REQ); + if (ret < 0) { + DRM_ERROR("Error allocating control channel\n"); + goto fail; + } + + ret = evtchnl_alloc(front_info, conn, + &front_info->evt_pairs[conn].evt, + EVTCHNL_TYPE_EVT); + if (ret < 0) { + DRM_ERROR("Error allocating in-event channel\n"); + goto fail; + } + } + front_info->num_evt_pairs = cfg->num_connectors; + return 0; + +fail: + xen_drm_front_evtchnl_free_all(front_info); + return ret; +} + +static int evtchnl_publish(struct xenbus_transaction xbt, + struct xen_drm_front_evtchnl *evtchnl, + const char *path, const char *node_ring, + const char *node_chnl) +{ + struct xenbus_device *xb_dev = evtchnl->front_info->xb_dev; + int ret; + + /* write control channel ring reference */ + ret = xenbus_printf(xbt, path, node_ring, "%u", evtchnl->gref); + if (ret < 0) { + xenbus_dev_error(xb_dev, ret, "writing ring-ref"); + return ret; + } + + /* write event channel ring reference */ + ret = xenbus_printf(xbt, path, node_chnl, "%u", evtchnl->port); + if (ret < 0) { + xenbus_dev_error(xb_dev, ret, "writing event channel"); + return ret; + } + + return 0; +} + +int xen_drm_front_evtchnl_publish_all(struct xen_drm_front_info *front_info) +{ + struct xenbus_transaction xbt; + struct xen_drm_front_cfg *plat_data; + int ret, conn; + + plat_data = &front_info->cfg; + +again: + ret = xenbus_transaction_start(&xbt); + if (ret < 0) { + xenbus_dev_fatal(front_info->xb_dev, ret, + "starting transaction"); + return ret; + } + + for (conn = 0; conn < plat_data->num_connectors; conn++) { + ret = evtchnl_publish(xbt, &front_info->evt_pairs[conn].req, + plat_data->connectors[conn].xenstore_path, + XENDISPL_FIELD_REQ_RING_REF, + XENDISPL_FIELD_REQ_CHANNEL); + if (ret < 0) + goto fail; + + ret = evtchnl_publish(xbt, &front_info->evt_pairs[conn].evt, + plat_data->connectors[conn].xenstore_path, + XENDISPL_FIELD_EVT_RING_REF, + XENDISPL_FIELD_EVT_CHANNEL); + if (ret < 0) + goto fail; + } + + ret = xenbus_transaction_end(xbt, 0); + if (ret < 0) { + if (ret == -EAGAIN) + goto again; + + xenbus_dev_fatal(front_info->xb_dev, ret, + "completing transaction"); + goto fail_to_end; + } + + return 0; + +fail: + xenbus_transaction_end(xbt, 1); + +fail_to_end: + xenbus_dev_fatal(front_info->xb_dev, ret, "writing Xen store"); + return ret; +} + +void xen_drm_front_evtchnl_flush(struct xen_drm_front_evtchnl *evtchnl) +{ + int notify; + + evtchnl->u.req.ring.req_prod_pvt++; + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&evtchnl->u.req.ring, notify); + if (notify) + notify_remote_via_irq(evtchnl->irq); +} + +void xen_drm_front_evtchnl_set_state(struct xen_drm_front_info *front_info, + enum xen_drm_front_evtchnl_state state) +{ + unsigned long flags; + int i; + + if (!front_info->evt_pairs) + return; + + spin_lock_irqsave(&front_info->io_lock, flags); + for (i = 0; i < front_info->num_evt_pairs; i++) { + front_info->evt_pairs[i].req.state = state; + front_info->evt_pairs[i].evt.state = state; + } + spin_unlock_irqrestore(&front_info->io_lock, flags); +} + +void xen_drm_front_evtchnl_free_all(struct xen_drm_front_info *front_info) +{ + int i; + + if (!front_info->evt_pairs) + return; + + for (i = 0; i < front_info->num_evt_pairs; i++) { + evtchnl_free(front_info, &front_info->evt_pairs[i].req); + evtchnl_free(front_info, &front_info->evt_pairs[i].evt); + } + + kfree(front_info->evt_pairs); + front_info->evt_pairs = NULL; +} diff --git a/drivers/gpu/drm/xen/xen_drm_front_evtchnl.h b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.h new file mode 100644 index 0000000..b0af699 --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_evtchnl.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#ifndef __XEN_DRM_FRONT_EVTCHNL_H_ +#define __XEN_DRM_FRONT_EVTCHNL_H_ + +#include <linux/completion.h> +#include <linux/types.h> + +#include <xen/interface/io/ring.h> +#include <xen/interface/io/displif.h> + +/* + * All operations which are not connector oriented use this ctrl event channel, + * e.g. fb_attach/destroy which belong to a DRM device, not to a CRTC. + */ +#define GENERIC_OP_EVT_CHNL 0 + +enum xen_drm_front_evtchnl_state { + EVTCHNL_STATE_DISCONNECTED, + EVTCHNL_STATE_CONNECTED, +}; + +enum xen_drm_front_evtchnl_type { + EVTCHNL_TYPE_REQ, + EVTCHNL_TYPE_EVT, +}; + +struct xen_drm_front_drm_info; + +struct xen_drm_front_evtchnl { + struct xen_drm_front_info *front_info; + int gref; + int port; + int irq; + int index; + enum xen_drm_front_evtchnl_state state; + enum xen_drm_front_evtchnl_type type; + /* either response id or incoming event id */ + u16 evt_id; + /* next request id or next expected event id */ + u16 evt_next_id; + union { + struct { + struct xen_displif_front_ring ring; + struct completion completion; + /* latest response status */ + int resp_status; + /* serializer for backend IO: request/response */ + struct mutex req_io_lock; + } req; + struct { + struct xendispl_event_page *page; + } evt; + } u; +}; + +struct xen_drm_front_evtchnl_pair { + struct xen_drm_front_evtchnl req; + struct xen_drm_front_evtchnl evt; +}; + +int xen_drm_front_evtchnl_create_all(struct xen_drm_front_info *front_info); + +int xen_drm_front_evtchnl_publish_all(struct xen_drm_front_info *front_info); + +void xen_drm_front_evtchnl_flush(struct xen_drm_front_evtchnl *evtchnl); + +void xen_drm_front_evtchnl_set_state(struct xen_drm_front_info *front_info, + enum xen_drm_front_evtchnl_state state); + +void xen_drm_front_evtchnl_free_all(struct xen_drm_front_info *front_info); + +#endif /* __XEN_DRM_FRONT_EVTCHNL_H_ */ diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c new file mode 100644 index 0000000..c85bfe7 --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#include "xen_drm_front_gem.h" + +#include <drm/drmP.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_gem.h> + +#include <linux/dma-buf.h> +#include <linux/scatterlist.h> +#include <linux/shmem_fs.h> + +#include <xen/balloon.h> + +#include "xen_drm_front.h" +#include "xen_drm_front_shbuf.h" + +struct xen_gem_object { + struct drm_gem_object base; + + size_t num_pages; + struct page **pages; + + /* set for buffers allocated by the backend */ + bool be_alloc; + + /* this is for imported PRIME buffer */ + struct sg_table *sgt_imported; +}; + +static inline struct xen_gem_object * +to_xen_gem_obj(struct drm_gem_object *gem_obj) +{ + return container_of(gem_obj, struct xen_gem_object, base); +} + +static int gem_alloc_pages_array(struct xen_gem_object *xen_obj, + size_t buf_size) +{ + xen_obj->num_pages = DIV_ROUND_UP(buf_size, PAGE_SIZE); + xen_obj->pages = kvmalloc_array(xen_obj->num_pages, + sizeof(struct page *), GFP_KERNEL); + return !xen_obj->pages ? -ENOMEM : 0; +} + +static void gem_free_pages_array(struct xen_gem_object *xen_obj) +{ + kvfree(xen_obj->pages); + xen_obj->pages = NULL; +} + +static struct xen_gem_object *gem_create_obj(struct drm_device *dev, + size_t size) +{ + struct xen_gem_object *xen_obj; + int ret; + + xen_obj = kzalloc(sizeof(*xen_obj), GFP_KERNEL); + if (!xen_obj) + return ERR_PTR(-ENOMEM); + + ret = drm_gem_object_init(dev, &xen_obj->base, size); + if (ret < 0) { + kfree(xen_obj); + return ERR_PTR(ret); + } + + return xen_obj; +} + +static struct xen_gem_object *gem_create(struct drm_device *dev, size_t size) +{ + struct xen_drm_front_drm_info *drm_info = dev->dev_private; + struct xen_gem_object *xen_obj; + int ret; + + size = round_up(size, PAGE_SIZE); + xen_obj = gem_create_obj(dev, size); + if (IS_ERR_OR_NULL(xen_obj)) + return xen_obj; + + if (drm_info->front_info->cfg.be_alloc) { + /* + * backend will allocate space for this buffer, so + * only allocate array of pointers to pages + */ + ret = gem_alloc_pages_array(xen_obj, size); + if (ret < 0) + goto fail; + + /* + * allocate ballooned pages which will be used to map + * grant references provided by the backend + */ + ret = alloc_xenballooned_pages(xen_obj->num_pages, + xen_obj->pages); + if (ret < 0) { + DRM_ERROR("Cannot allocate %zu ballooned pages: %d\n", + xen_obj->num_pages, ret); + gem_free_pages_array(xen_obj); + goto fail; + } + + xen_obj->be_alloc = true; + return xen_obj; + } + /* + * need to allocate backing pages now, so we can share those + * with the backend + */ + xen_obj->num_pages = DIV_ROUND_UP(size, PAGE_SIZE); + xen_obj->pages = drm_gem_get_pages(&xen_obj->base); + if (IS_ERR_OR_NULL(xen_obj->pages)) { + ret = PTR_ERR(xen_obj->pages); + xen_obj->pages = NULL; + goto fail; + } + + return xen_obj; + +fail: + DRM_ERROR("Failed to allocate buffer with size %zu\n", size); + return ERR_PTR(ret); +} + +struct drm_gem_object *xen_drm_front_gem_create(struct drm_device *dev, + size_t size) +{ + struct xen_gem_object *xen_obj; + + xen_obj = gem_create(dev, size); + if (IS_ERR_OR_NULL(xen_obj)) + return ERR_CAST(xen_obj); + + return &xen_obj->base; +} + +void xen_drm_front_gem_free_object_unlocked(struct drm_gem_object *gem_obj) +{ + struct xen_gem_object *xen_obj = to_xen_gem_obj(gem_obj); + + if (xen_obj->base.import_attach) { + drm_prime_gem_destroy(&xen_obj->base, xen_obj->sgt_imported); + gem_free_pages_array(xen_obj); + } else { + if (xen_obj->pages) { + if (xen_obj->be_alloc) { + free_xenballooned_pages(xen_obj->num_pages, + xen_obj->pages); + gem_free_pages_array(xen_obj); + } else { + drm_gem_put_pages(&xen_obj->base, + xen_obj->pages, true, false); + } + } + } + drm_gem_object_release(gem_obj); + kfree(xen_obj); +} + +struct page **xen_drm_front_gem_get_pages(struct drm_gem_object *gem_obj) +{ + struct xen_gem_object *xen_obj = to_xen_gem_obj(gem_obj); + + return xen_obj->pages; +} + +struct sg_table *xen_drm_front_gem_get_sg_table(struct drm_gem_object *gem_obj) +{ + struct xen_gem_object *xen_obj = to_xen_gem_obj(gem_obj); + + if (!xen_obj->pages) + return NULL; + + return drm_prime_pages_to_sg(xen_obj->pages, xen_obj->num_pages); +} + +struct drm_gem_object * +xen_drm_front_gem_import_sg_table(struct drm_device *dev, + struct dma_buf_attachment *attach, + struct sg_table *sgt) +{ + struct xen_drm_front_drm_info *drm_info = dev->dev_private; + struct xen_gem_object *xen_obj; + size_t size; + int ret; + + size = attach->dmabuf->size; + xen_obj = gem_create_obj(dev, size); + if (IS_ERR_OR_NULL(xen_obj)) + return ERR_CAST(xen_obj); + + ret = gem_alloc_pages_array(xen_obj, size); + if (ret < 0) + return ERR_PTR(ret); + + xen_obj->sgt_imported = sgt; + + ret = drm_prime_sg_to_page_addr_arrays(sgt, xen_obj->pages, + NULL, xen_obj->num_pages); + if (ret < 0) + return ERR_PTR(ret); + + ret = xen_drm_front_dbuf_create(drm_info->front_info, + xen_drm_front_dbuf_to_cookie(&xen_obj->base), + 0, 0, 0, size, xen_obj->pages); + if (ret < 0) + return ERR_PTR(ret); + + DRM_DEBUG("Imported buffer of size %zu with nents %u\n", + size, sgt->nents); + + return &xen_obj->base; +} + +static int gem_mmap_obj(struct xen_gem_object *xen_obj, + struct vm_area_struct *vma) +{ + unsigned long addr = vma->vm_start; + int i; + + /* + * clear the VM_PFNMAP flag that was set by drm_gem_mmap(), and set the + * vm_pgoff (used as a fake buffer offset by DRM) to 0 as we want to map + * the whole buffer. + */ + vma->vm_flags &= ~VM_PFNMAP; + vma->vm_flags |= VM_MIXEDMAP; + vma->vm_pgoff = 0; + vma->vm_page_prot = + pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); + + /* + * vm_operations_struct.fault handler will be called if CPU access + * to VM is here. For GPUs this isn't the case, because CPU + * doesn't touch the memory. Insert pages now, so both CPU and GPU are + * happy. + * FIXME: as we insert all the pages now then no .fault handler must + * be called, so don't provide one + */ + for (i = 0; i < xen_obj->num_pages; i++) { + int ret; + + ret = vm_insert_page(vma, addr, xen_obj->pages[i]); + if (ret < 0) { + DRM_ERROR("Failed to insert pages into vma: %d\n", ret); + return ret; + } + + addr += PAGE_SIZE; + } + return 0; +} + +int xen_drm_front_gem_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct xen_gem_object *xen_obj; + struct drm_gem_object *gem_obj; + int ret; + + ret = drm_gem_mmap(filp, vma); + if (ret < 0) + return ret; + + gem_obj = vma->vm_private_data; + xen_obj = to_xen_gem_obj(gem_obj); + return gem_mmap_obj(xen_obj, vma); +} + +void *xen_drm_front_gem_prime_vmap(struct drm_gem_object *gem_obj) +{ + struct xen_gem_object *xen_obj = to_xen_gem_obj(gem_obj); + + if (!xen_obj->pages) + return NULL; + + return vmap(xen_obj->pages, xen_obj->num_pages, + VM_MAP, pgprot_writecombine(PAGE_KERNEL)); +} + +void xen_drm_front_gem_prime_vunmap(struct drm_gem_object *gem_obj, + void *vaddr) +{ + vunmap(vaddr); +} + +int xen_drm_front_gem_prime_mmap(struct drm_gem_object *gem_obj, + struct vm_area_struct *vma) +{ + struct xen_gem_object *xen_obj; + int ret; + + ret = drm_gem_mmap_obj(gem_obj, gem_obj->size, vma); + if (ret < 0) + return ret; + + xen_obj = to_xen_gem_obj(gem_obj); + return gem_mmap_obj(xen_obj, vma); +} diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.h b/drivers/gpu/drm/xen/xen_drm_front_gem.h new file mode 100644 index 0000000..d5ab734 --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#ifndef __XEN_DRM_FRONT_GEM_H +#define __XEN_DRM_FRONT_GEM_H + +#include <drm/drmP.h> + +struct drm_gem_object *xen_drm_front_gem_create(struct drm_device *dev, + size_t size); + +struct drm_gem_object * +xen_drm_front_gem_import_sg_table(struct drm_device *dev, + struct dma_buf_attachment *attach, + struct sg_table *sgt); + +struct sg_table *xen_drm_front_gem_get_sg_table(struct drm_gem_object *gem_obj); + +struct page **xen_drm_front_gem_get_pages(struct drm_gem_object *obj); + +void xen_drm_front_gem_free_object_unlocked(struct drm_gem_object *gem_obj); + +int xen_drm_front_gem_mmap(struct file *filp, struct vm_area_struct *vma); + +void *xen_drm_front_gem_prime_vmap(struct drm_gem_object *gem_obj); + +void xen_drm_front_gem_prime_vunmap(struct drm_gem_object *gem_obj, + void *vaddr); + +int xen_drm_front_gem_prime_mmap(struct drm_gem_object *gem_obj, + struct vm_area_struct *vma); + +#endif /* __XEN_DRM_FRONT_GEM_H */ diff --git a/drivers/gpu/drm/xen/xen_drm_front_kms.c b/drivers/gpu/drm/xen/xen_drm_front_kms.c new file mode 100644 index 0000000..a3479eb --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_kms.c @@ -0,0 +1,366 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#include "xen_drm_front_kms.h" + +#include <drm/drmP.h> +#include <drm/drm_atomic.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_gem.h> +#include <drm/drm_gem_framebuffer_helper.h> + +#include "xen_drm_front.h" +#include "xen_drm_front_conn.h" + +/* + * Timeout in ms to wait for frame done event from the backend: + * must be a bit more than IO time-out + */ +#define FRAME_DONE_TO_MS (XEN_DRM_FRONT_WAIT_BACK_MS + 100) + +static struct xen_drm_front_drm_pipeline * +to_xen_drm_pipeline(struct drm_simple_display_pipe *pipe) +{ + return container_of(pipe, struct xen_drm_front_drm_pipeline, pipe); +} + +static void fb_destroy(struct drm_framebuffer *fb) +{ + struct xen_drm_front_drm_info *drm_info = fb->dev->dev_private; + int idx; + + if (drm_dev_enter(fb->dev, &idx)) { + xen_drm_front_fb_detach(drm_info->front_info, + xen_drm_front_fb_to_cookie(fb)); + drm_dev_exit(idx); + } + drm_gem_fb_destroy(fb); +} + +static struct drm_framebuffer_funcs fb_funcs = { + .destroy = fb_destroy, +}; + +static struct drm_framebuffer * +fb_create(struct drm_device *dev, struct drm_file *filp, + const struct drm_mode_fb_cmd2 *mode_cmd) +{ + struct xen_drm_front_drm_info *drm_info = dev->dev_private; + static struct drm_framebuffer *fb; + struct drm_gem_object *gem_obj; + int ret; + + fb = drm_gem_fb_create_with_funcs(dev, filp, mode_cmd, &fb_funcs); + if (IS_ERR_OR_NULL(fb)) + return fb; + + gem_obj = drm_gem_object_lookup(filp, mode_cmd->handles[0]); + if (!gem_obj) { + DRM_ERROR("Failed to lookup GEM object\n"); + ret = -ENOENT; + goto fail; + } + + drm_gem_object_put_unlocked(gem_obj); + + ret = xen_drm_front_fb_attach(drm_info->front_info, + xen_drm_front_dbuf_to_cookie(gem_obj), + xen_drm_front_fb_to_cookie(fb), + fb->width, fb->height, + fb->format->format); + if (ret < 0) { + DRM_ERROR("Back failed to attach FB %p: %d\n", fb, ret); + goto fail; + } + + return fb; + +fail: + drm_gem_fb_destroy(fb); + return ERR_PTR(ret); +} + +static const struct drm_mode_config_funcs mode_config_funcs = { + .fb_create = fb_create, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +static void send_pending_event(struct xen_drm_front_drm_pipeline *pipeline) +{ + struct drm_crtc *crtc = &pipeline->pipe.crtc; + struct drm_device *dev = crtc->dev; + unsigned long flags; + + spin_lock_irqsave(&dev->event_lock, flags); + if (pipeline->pending_event) + drm_crtc_send_vblank_event(crtc, pipeline->pending_event); + pipeline->pending_event = NULL; + spin_unlock_irqrestore(&dev->event_lock, flags); +} + +static void display_enable(struct drm_simple_display_pipe *pipe, + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) +{ + struct xen_drm_front_drm_pipeline *pipeline = + to_xen_drm_pipeline(pipe); + struct drm_crtc *crtc = &pipe->crtc; + struct drm_framebuffer *fb = plane_state->fb; + int ret, idx; + + if (!drm_dev_enter(pipe->crtc.dev, &idx)) + return; + + ret = xen_drm_front_mode_set(pipeline, crtc->x, crtc->y, + fb->width, fb->height, + fb->format->cpp[0] * 8, + xen_drm_front_fb_to_cookie(fb)); + + if (ret) { + DRM_ERROR("Failed to enable display: %d\n", ret); + pipeline->conn_connected = false; + } + + drm_dev_exit(idx); +} + +static void display_disable(struct drm_simple_display_pipe *pipe) +{ + struct xen_drm_front_drm_pipeline *pipeline = + to_xen_drm_pipeline(pipe); + int ret = 0, idx; + + if (drm_dev_enter(pipe->crtc.dev, &idx)) { + ret = xen_drm_front_mode_set(pipeline, 0, 0, 0, 0, 0, + xen_drm_front_fb_to_cookie(NULL)); + drm_dev_exit(idx); + } + if (ret) + DRM_ERROR("Failed to disable display: %d\n", ret); + + /* Make sure we can restart with enabled connector next time */ + pipeline->conn_connected = true; + + /* release stalled event if any */ + send_pending_event(pipeline); +} + +void xen_drm_front_kms_on_frame_done(struct xen_drm_front_drm_pipeline *pipeline, + u64 fb_cookie) +{ + /* + * This runs in interrupt context, e.g. under + * drm_info->front_info->io_lock, so we cannot call _sync version + * to cancel the work + */ + cancel_delayed_work(&pipeline->pflip_to_worker); + + send_pending_event(pipeline); +} + +static void pflip_to_worker(struct work_struct *work) +{ + struct delayed_work *delayed_work = to_delayed_work(work); + struct xen_drm_front_drm_pipeline *pipeline = + container_of(delayed_work, + struct xen_drm_front_drm_pipeline, + pflip_to_worker); + + DRM_ERROR("Frame done timed-out, releasing"); + send_pending_event(pipeline); +} + +static bool display_send_page_flip(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *old_plane_state) +{ + struct drm_plane_state *plane_state = + drm_atomic_get_new_plane_state(old_plane_state->state, + &pipe->plane); + + /* + * If old_plane_state->fb is NULL and plane_state->fb is not, + * then this is an atomic commit which will enable display. + * If old_plane_state->fb is not NULL and plane_state->fb is, + * then this is an atomic commit which will disable display. + * Ignore these and do not send page flip as this framebuffer will be + * sent to the backend as a part of display_set_config call. + */ + if (old_plane_state->fb && plane_state->fb) { + struct xen_drm_front_drm_pipeline *pipeline = + to_xen_drm_pipeline(pipe); + struct xen_drm_front_drm_info *drm_info = pipeline->drm_info; + int ret; + + schedule_delayed_work(&pipeline->pflip_to_worker, + msecs_to_jiffies(FRAME_DONE_TO_MS)); + + ret = xen_drm_front_page_flip(drm_info->front_info, + pipeline->index, + xen_drm_front_fb_to_cookie(plane_state->fb)); + if (ret) { + DRM_ERROR("Failed to send page flip request to backend: %d\n", ret); + + pipeline->conn_connected = false; + /* + * Report the flip not handled, so pending event is + * sent, unblocking user-space. + */ + return false; + } + /* + * Signal that page flip was handled, pending event will be sent + * on frame done event from the backend. + */ + return true; + } + + return false; +} + +static void display_update(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *old_plane_state) +{ + struct xen_drm_front_drm_pipeline *pipeline = + to_xen_drm_pipeline(pipe); + struct drm_crtc *crtc = &pipe->crtc; + struct drm_pending_vblank_event *event; + int idx; + + event = crtc->state->event; + if (event) { + struct drm_device *dev = crtc->dev; + unsigned long flags; + + WARN_ON(pipeline->pending_event); + + spin_lock_irqsave(&dev->event_lock, flags); + crtc->state->event = NULL; + + pipeline->pending_event = event; + spin_unlock_irqrestore(&dev->event_lock, flags); + } + + if (!drm_dev_enter(pipe->crtc.dev, &idx)) { + send_pending_event(pipeline); + return; + } + + /* + * Send page flip request to the backend *after* we have event cached + * above, so on page flip done event from the backend we can + * deliver it and there is no race condition between this code and + * event from the backend. + * If this is not a page flip, e.g. no flip done event from the backend + * is expected, then send now. + */ + if (!display_send_page_flip(pipe, old_plane_state)) + send_pending_event(pipeline); + + drm_dev_exit(idx); +} + +static enum drm_mode_status +display_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode) +{ + struct xen_drm_front_drm_pipeline *pipeline = + container_of(crtc, struct xen_drm_front_drm_pipeline, + pipe.crtc); + + if (mode->hdisplay != pipeline->width) + return MODE_ERROR; + + if (mode->vdisplay != pipeline->height) + return MODE_ERROR; + + return MODE_OK; +} + +static const struct drm_simple_display_pipe_funcs display_funcs = { + .mode_valid = display_mode_valid, + .enable = display_enable, + .disable = display_disable, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, + .update = display_update, +}; + +static int display_pipe_init(struct xen_drm_front_drm_info *drm_info, + int index, struct xen_drm_front_cfg_connector *cfg, + struct xen_drm_front_drm_pipeline *pipeline) +{ + struct drm_device *dev = drm_info->drm_dev; + const u32 *formats; + int format_count; + int ret; + + pipeline->drm_info = drm_info; + pipeline->index = index; + pipeline->height = cfg->height; + pipeline->width = cfg->width; + + INIT_DELAYED_WORK(&pipeline->pflip_to_worker, pflip_to_worker); + + ret = xen_drm_front_conn_init(drm_info, &pipeline->conn); + if (ret) + return ret; + + formats = xen_drm_front_conn_get_formats(&format_count); + + return drm_simple_display_pipe_init(dev, &pipeline->pipe, + &display_funcs, formats, + format_count, NULL, + &pipeline->conn); +} + +int xen_drm_front_kms_init(struct xen_drm_front_drm_info *drm_info) +{ + struct drm_device *dev = drm_info->drm_dev; + int i, ret; + + drm_mode_config_init(dev); + + dev->mode_config.min_width = 0; + dev->mode_config.min_height = 0; + dev->mode_config.max_width = 4095; + dev->mode_config.max_height = 2047; + dev->mode_config.funcs = &mode_config_funcs; + + for (i = 0; i < drm_info->front_info->cfg.num_connectors; i++) { + struct xen_drm_front_cfg_connector *cfg = + &drm_info->front_info->cfg.connectors[i]; + struct xen_drm_front_drm_pipeline *pipeline = + &drm_info->pipeline[i]; + + ret = display_pipe_init(drm_info, i, cfg, pipeline); + if (ret) { + drm_mode_config_cleanup(dev); + return ret; + } + } + + drm_mode_config_reset(dev); + drm_kms_helper_poll_init(dev); + return 0; +} + +void xen_drm_front_kms_fini(struct xen_drm_front_drm_info *drm_info) +{ + int i; + + for (i = 0; i < drm_info->front_info->cfg.num_connectors; i++) { + struct xen_drm_front_drm_pipeline *pipeline = + &drm_info->pipeline[i]; + + cancel_delayed_work_sync(&pipeline->pflip_to_worker); + + send_pending_event(pipeline); + } +} diff --git a/drivers/gpu/drm/xen/xen_drm_front_kms.h b/drivers/gpu/drm/xen/xen_drm_front_kms.h new file mode 100644 index 0000000..ab2fbad --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_kms.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#ifndef __XEN_DRM_FRONT_KMS_H_ +#define __XEN_DRM_FRONT_KMS_H_ + +#include <linux/types.h> + +struct xen_drm_front_drm_info; +struct xen_drm_front_drm_pipeline; + +int xen_drm_front_kms_init(struct xen_drm_front_drm_info *drm_info); + +void xen_drm_front_kms_fini(struct xen_drm_front_drm_info *drm_info); + +void xen_drm_front_kms_on_frame_done(struct xen_drm_front_drm_pipeline *pipeline, + u64 fb_cookie); + +#endif /* __XEN_DRM_FRONT_KMS_H_ */ diff --git a/drivers/gpu/drm/xen/xen_drm_front_shbuf.c b/drivers/gpu/drm/xen/xen_drm_front_shbuf.c new file mode 100644 index 0000000..d570525 --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_shbuf.c @@ -0,0 +1,414 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#include <drm/drmP.h> + +#if defined(CONFIG_X86) +#include <drm/drm_cache.h> +#endif +#include <linux/errno.h> +#include <linux/mm.h> + +#include <asm/xen/hypervisor.h> +#include <xen/balloon.h> +#include <xen/xen.h> +#include <xen/xenbus.h> +#include <xen/interface/io/ring.h> +#include <xen/interface/io/displif.h> + +#include "xen_drm_front.h" +#include "xen_drm_front_shbuf.h" + +struct xen_drm_front_shbuf_ops { + /* + * Calculate number of grefs required to handle this buffer, + * e.g. if grefs are required for page directory only or the buffer + * pages as well. + */ + void (*calc_num_grefs)(struct xen_drm_front_shbuf *buf); + /* Fill page directory according to para-virtual display protocol. */ + void (*fill_page_dir)(struct xen_drm_front_shbuf *buf); + /* Claim grant references for the pages of the buffer. */ + int (*grant_refs_for_buffer)(struct xen_drm_front_shbuf *buf, + grant_ref_t *priv_gref_head, int gref_idx); + /* Map grant references of the buffer. */ + int (*map)(struct xen_drm_front_shbuf *buf); + /* Unmap grant references of the buffer. */ + int (*unmap)(struct xen_drm_front_shbuf *buf); +}; + +grant_ref_t xen_drm_front_shbuf_get_dir_start(struct xen_drm_front_shbuf *buf) +{ + if (!buf->grefs) + return GRANT_INVALID_REF; + + return buf->grefs[0]; +} + +int xen_drm_front_shbuf_map(struct xen_drm_front_shbuf *buf) +{ + if (buf->ops->map) + return buf->ops->map(buf); + + /* no need to map own grant references */ + return 0; +} + +int xen_drm_front_shbuf_unmap(struct xen_drm_front_shbuf *buf) +{ + if (buf->ops->unmap) + return buf->ops->unmap(buf); + + /* no need to unmap own grant references */ + return 0; +} + +void xen_drm_front_shbuf_flush(struct xen_drm_front_shbuf *buf) +{ +#if defined(CONFIG_X86) + drm_clflush_pages(buf->pages, buf->num_pages); +#endif +} + +void xen_drm_front_shbuf_free(struct xen_drm_front_shbuf *buf) +{ + if (buf->grefs) { + int i; + + for (i = 0; i < buf->num_grefs; i++) + if (buf->grefs[i] != GRANT_INVALID_REF) + gnttab_end_foreign_access(buf->grefs[i], + 0, 0UL); + } + kfree(buf->grefs); + kfree(buf->directory); + kfree(buf); +} + +/* + * number of grefs a page can hold with respect to the + * struct xendispl_page_directory header + */ +#define XEN_DRM_NUM_GREFS_PER_PAGE ((PAGE_SIZE - \ + offsetof(struct xendispl_page_directory, gref)) / \ + sizeof(grant_ref_t)) + +static int get_num_pages_dir(struct xen_drm_front_shbuf *buf) +{ + /* number of pages the page directory consumes itself */ + return DIV_ROUND_UP(buf->num_pages, XEN_DRM_NUM_GREFS_PER_PAGE); +} + +static void backend_calc_num_grefs(struct xen_drm_front_shbuf *buf) +{ + /* only for pages the page directory consumes itself */ + buf->num_grefs = get_num_pages_dir(buf); +} + +static void guest_calc_num_grefs(struct xen_drm_front_shbuf *buf) +{ + /* + * number of pages the page directory consumes itself + * plus grefs for the buffer pages + */ + buf->num_grefs = get_num_pages_dir(buf) + buf->num_pages; +} + +#define xen_page_to_vaddr(page) \ + ((phys_addr_t)pfn_to_kaddr(page_to_xen_pfn(page))) + +static int backend_unmap(struct xen_drm_front_shbuf *buf) +{ + struct gnttab_unmap_grant_ref *unmap_ops; + int i, ret; + + if (!buf->pages || !buf->backend_map_handles || !buf->grefs) + return 0; + + unmap_ops = kcalloc(buf->num_pages, sizeof(*unmap_ops), + GFP_KERNEL); + if (!unmap_ops) { + DRM_ERROR("Failed to get memory while unmapping\n"); + return -ENOMEM; + } + + for (i = 0; i < buf->num_pages; i++) { + phys_addr_t addr; + + addr = xen_page_to_vaddr(buf->pages[i]); + gnttab_set_unmap_op(&unmap_ops[i], addr, GNTMAP_host_map, + buf->backend_map_handles[i]); + } + + ret = gnttab_unmap_refs(unmap_ops, NULL, buf->pages, + buf->num_pages); + + for (i = 0; i < buf->num_pages; i++) { + if (unlikely(unmap_ops[i].status != GNTST_okay)) + DRM_ERROR("Failed to unmap page %d: %d\n", + i, unmap_ops[i].status); + } + + if (ret) + DRM_ERROR("Failed to unmap grant references, ret %d", ret); + + kfree(unmap_ops); + kfree(buf->backend_map_handles); + buf->backend_map_handles = NULL; + return ret; +} + +static int backend_map(struct xen_drm_front_shbuf *buf) +{ + struct gnttab_map_grant_ref *map_ops = NULL; + unsigned char *ptr; + int ret, cur_gref, cur_dir_page, cur_page, grefs_left; + + map_ops = kcalloc(buf->num_pages, sizeof(*map_ops), GFP_KERNEL); + if (!map_ops) + return -ENOMEM; + + buf->backend_map_handles = kcalloc(buf->num_pages, + sizeof(*buf->backend_map_handles), + GFP_KERNEL); + if (!buf->backend_map_handles) { + kfree(map_ops); + return -ENOMEM; + } + + /* + * read page directory to get grefs from the backend: for external + * buffer we only allocate buf->grefs for the page directory, + * so buf->num_grefs has number of pages in the page directory itself + */ + ptr = buf->directory; + grefs_left = buf->num_pages; + cur_page = 0; + for (cur_dir_page = 0; cur_dir_page < buf->num_grefs; cur_dir_page++) { + struct xendispl_page_directory *page_dir = + (struct xendispl_page_directory *)ptr; + int to_copy = XEN_DRM_NUM_GREFS_PER_PAGE; + + if (to_copy > grefs_left) + to_copy = grefs_left; + + for (cur_gref = 0; cur_gref < to_copy; cur_gref++) { + phys_addr_t addr; + + addr = xen_page_to_vaddr(buf->pages[cur_page]); + gnttab_set_map_op(&map_ops[cur_page], addr, + GNTMAP_host_map, + page_dir->gref[cur_gref], + buf->xb_dev->otherend_id); + cur_page++; + } + + grefs_left -= to_copy; + ptr += PAGE_SIZE; + } + ret = gnttab_map_refs(map_ops, NULL, buf->pages, buf->num_pages); + + /* save handles even if error, so we can unmap */ + for (cur_page = 0; cur_page < buf->num_pages; cur_page++) { + buf->backend_map_handles[cur_page] = map_ops[cur_page].handle; + if (unlikely(map_ops[cur_page].status != GNTST_okay)) + DRM_ERROR("Failed to map page %d: %d\n", + cur_page, map_ops[cur_page].status); + } + + if (ret) { + DRM_ERROR("Failed to map grant references, ret %d", ret); + backend_unmap(buf); + } + + kfree(map_ops); + return ret; +} + +static void backend_fill_page_dir(struct xen_drm_front_shbuf *buf) +{ + struct xendispl_page_directory *page_dir; + unsigned char *ptr; + int i, num_pages_dir; + + ptr = buf->directory; + num_pages_dir = get_num_pages_dir(buf); + + /* fill only grefs for the page directory itself */ + for (i = 0; i < num_pages_dir - 1; i++) { + page_dir = (struct xendispl_page_directory *)ptr; + + page_dir->gref_dir_next_page = buf->grefs[i + 1]; + ptr += PAGE_SIZE; + } + /* last page must say there is no more pages */ + page_dir = (struct xendispl_page_directory *)ptr; + page_dir->gref_dir_next_page = GRANT_INVALID_REF; +} + +static void guest_fill_page_dir(struct xen_drm_front_shbuf *buf) +{ + unsigned char *ptr; + int cur_gref, grefs_left, to_copy, i, num_pages_dir; + + ptr = buf->directory; + num_pages_dir = get_num_pages_dir(buf); + + /* + * while copying, skip grefs at start, they are for pages + * granted for the page directory itself + */ + cur_gref = num_pages_dir; + grefs_left = buf->num_pages; + for (i = 0; i < num_pages_dir; i++) { + struct xendispl_page_directory *page_dir = + (struct xendispl_page_directory *)ptr; + + if (grefs_left <= XEN_DRM_NUM_GREFS_PER_PAGE) { + to_copy = grefs_left; + page_dir->gref_dir_next_page = GRANT_INVALID_REF; + } else { + to_copy = XEN_DRM_NUM_GREFS_PER_PAGE; + page_dir->gref_dir_next_page = buf->grefs[i + 1]; + } + memcpy(&page_dir->gref, &buf->grefs[cur_gref], + to_copy * sizeof(grant_ref_t)); + ptr += PAGE_SIZE; + grefs_left -= to_copy; + cur_gref += to_copy; + } +} + +static int guest_grant_refs_for_buffer(struct xen_drm_front_shbuf *buf, + grant_ref_t *priv_gref_head, + int gref_idx) +{ + int i, cur_ref, otherend_id; + + otherend_id = buf->xb_dev->otherend_id; + for (i = 0; i < buf->num_pages; i++) { + cur_ref = gnttab_claim_grant_reference(priv_gref_head); + if (cur_ref < 0) + return cur_ref; + + gnttab_grant_foreign_access_ref(cur_ref, otherend_id, + xen_page_to_gfn(buf->pages[i]), + 0); + buf->grefs[gref_idx++] = cur_ref; + } + return 0; +} + +static int grant_references(struct xen_drm_front_shbuf *buf) +{ + grant_ref_t priv_gref_head; + int ret, i, j, cur_ref; + int otherend_id, num_pages_dir; + + ret = gnttab_alloc_grant_references(buf->num_grefs, &priv_gref_head); + if (ret < 0) { + DRM_ERROR("Cannot allocate grant references\n"); + return ret; + } + + otherend_id = buf->xb_dev->otherend_id; + j = 0; + num_pages_dir = get_num_pages_dir(buf); + for (i = 0; i < num_pages_dir; i++) { + unsigned long frame; + + cur_ref = gnttab_claim_grant_reference(&priv_gref_head); + if (cur_ref < 0) + return cur_ref; + + frame = xen_page_to_gfn(virt_to_page(buf->directory + + PAGE_SIZE * i)); + gnttab_grant_foreign_access_ref(cur_ref, otherend_id, frame, 0); + buf->grefs[j++] = cur_ref; + } + + if (buf->ops->grant_refs_for_buffer) { + ret = buf->ops->grant_refs_for_buffer(buf, &priv_gref_head, j); + if (ret) + return ret; + } + + gnttab_free_grant_references(priv_gref_head); + return 0; +} + +static int alloc_storage(struct xen_drm_front_shbuf *buf) +{ + buf->grefs = kcalloc(buf->num_grefs, sizeof(*buf->grefs), GFP_KERNEL); + if (!buf->grefs) + return -ENOMEM; + + buf->directory = kcalloc(get_num_pages_dir(buf), PAGE_SIZE, GFP_KERNEL); + if (!buf->directory) + return -ENOMEM; + + return 0; +} + +/* + * For be allocated buffers we don't need grant_refs_for_buffer as those + * grant references are allocated at backend side + */ +static const struct xen_drm_front_shbuf_ops backend_ops = { + .calc_num_grefs = backend_calc_num_grefs, + .fill_page_dir = backend_fill_page_dir, + .map = backend_map, + .unmap = backend_unmap +}; + +/* For locally granted references we do not need to map/unmap the references */ +static const struct xen_drm_front_shbuf_ops local_ops = { + .calc_num_grefs = guest_calc_num_grefs, + .fill_page_dir = guest_fill_page_dir, + .grant_refs_for_buffer = guest_grant_refs_for_buffer, +}; + +struct xen_drm_front_shbuf * +xen_drm_front_shbuf_alloc(struct xen_drm_front_shbuf_cfg *cfg) +{ + struct xen_drm_front_shbuf *buf; + int ret; + + buf = kzalloc(sizeof(*buf), GFP_KERNEL); + if (!buf) + return NULL; + + if (cfg->be_alloc) + buf->ops = &backend_ops; + else + buf->ops = &local_ops; + + buf->xb_dev = cfg->xb_dev; + buf->num_pages = DIV_ROUND_UP(cfg->size, PAGE_SIZE); + buf->pages = cfg->pages; + + buf->ops->calc_num_grefs(buf); + + ret = alloc_storage(buf); + if (ret) + goto fail; + + ret = grant_references(buf); + if (ret) + goto fail; + + buf->ops->fill_page_dir(buf); + + return buf; + +fail: + xen_drm_front_shbuf_free(buf); + return ERR_PTR(ret); +} diff --git a/drivers/gpu/drm/xen/xen_drm_front_shbuf.h b/drivers/gpu/drm/xen/xen_drm_front_shbuf.h new file mode 100644 index 0000000..7545c69 --- /dev/null +++ b/drivers/gpu/drm/xen/xen_drm_front_shbuf.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +/* + * Xen para-virtual DRM device + * + * Copyright (C) 2016-2018 EPAM Systems Inc. + * + * Author: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> + */ + +#ifndef __XEN_DRM_FRONT_SHBUF_H_ +#define __XEN_DRM_FRONT_SHBUF_H_ + +#include <linux/kernel.h> +#include <linux/scatterlist.h> + +#include <xen/grant_table.h> + +struct xen_drm_front_shbuf { + /* + * number of references granted for the backend use: + * - for allocated/imported dma-buf's this holds number of grant + * references for the page directory and pages of the buffer + * - for the buffer provided by the backend this holds number of + * grant references for the page directory as grant references for + * the buffer will be provided by the backend + */ + int num_grefs; + grant_ref_t *grefs; + unsigned char *directory; + + int num_pages; + struct page **pages; + + struct xenbus_device *xb_dev; + + /* these are the ops used internally depending on be_alloc mode */ + const struct xen_drm_front_shbuf_ops *ops; + + /* Xen map handles for the buffer allocated by the backend */ + grant_handle_t *backend_map_handles; +}; + +struct xen_drm_front_shbuf_cfg { + struct xenbus_device *xb_dev; + size_t size; + struct page **pages; + bool be_alloc; +}; + +struct xen_drm_front_shbuf * +xen_drm_front_shbuf_alloc(struct xen_drm_front_shbuf_cfg *cfg); + +grant_ref_t xen_drm_front_shbuf_get_dir_start(struct xen_drm_front_shbuf *buf); + +int xen_drm_front_shbuf_map(struct xen_drm_front_shbuf *buf); + +int xen_drm_front_shbuf_unmap(struct xen_drm_front_shbuf *buf); + +void xen_drm_front_shbuf_flush(struct xen_drm_front_shbuf *buf); + +void xen_drm_front_shbuf_free(struct xen_drm_front_shbuf *buf); + +#endif /* __XEN_DRM_FRONT_SHBUF_H_ */ diff --git a/drivers/gpu/drm/zte/zx_plane.c b/drivers/gpu/drm/zte/zx_plane.c index 94545ad..d1931f5 100644 --- a/drivers/gpu/drm/zte/zx_plane.c +++ b/drivers/gpu/drm/zte/zx_plane.c @@ -268,7 +268,7 @@ static void zx_plane_atomic_disable(struct drm_plane *plane, struct zx_plane *zplane = to_zx_plane(plane); void __iomem *hbsc = zplane->hbsc; - zx_vou_layer_disable(plane); + zx_vou_layer_disable(plane, old_state); /* Disable HBSC block */ zx_writel_mask(hbsc + HBSC_CTRL0, HBSC_CTRL_EN, 0); diff --git a/drivers/gpu/drm/zte/zx_vou.c b/drivers/gpu/drm/zte/zx_vou.c index 7491813..442311d 100644 --- a/drivers/gpu/drm/zte/zx_vou.c +++ b/drivers/gpu/drm/zte/zx_vou.c @@ -627,9 +627,10 @@ void zx_vou_layer_enable(struct drm_plane *plane) zx_writel_mask(vou->osd + OSD_CTRL0, bits->enable, bits->enable); } -void zx_vou_layer_disable(struct drm_plane *plane) +void zx_vou_layer_disable(struct drm_plane *plane, + struct drm_plane_state *old_state) { - struct zx_crtc *zcrtc = to_zx_crtc(plane->crtc); + struct zx_crtc *zcrtc = to_zx_crtc(old_state->crtc); struct zx_vou_hw *vou = zcrtc->vou; struct zx_plane *zplane = to_zx_plane(plane); const struct vou_layer_bits *bits = zplane->bits; diff --git a/drivers/gpu/drm/zte/zx_vou.h b/drivers/gpu/drm/zte/zx_vou.h index 97d72bf..5b7f84f 100644 --- a/drivers/gpu/drm/zte/zx_vou.h +++ b/drivers/gpu/drm/zte/zx_vou.h @@ -62,6 +62,7 @@ void zx_vou_config_dividers(struct drm_crtc *crtc, struct vou_div_config *configs, int num); void zx_vou_layer_enable(struct drm_plane *plane); -void zx_vou_layer_disable(struct drm_plane *plane); +void zx_vou_layer_disable(struct drm_plane *plane, + struct drm_plane_state *old_state); #endif /* __ZX_VOU_H__ */ |
