diff options
Diffstat (limited to 'drivers/gpu/drm/msm')
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 6 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 48 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_hfi.c | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_gpu.c | 13 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_gpu.h | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c | 12 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c | 3 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c | 24 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/dsi/dsi_host.c | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/msm_drv.c | 11 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/msm_drv.h | 7 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/msm_gem.c | 33 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/msm_gem_shrinker.c | 44 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/msm_gem_submit.c | 6 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/msm_gem_vma.c | 12 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/msm_iommu.c | 5 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/msm_ringbuffer.c | 6 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/registers/adreno/a6xx.xml | 4 |
19 files changed, 141 insertions, 99 deletions
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index e44302251de5..79acae11154a 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1730,6 +1730,7 @@ static struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; unsigned int nr_rings; + u32 speedbin; int ret; a5xx_gpu = kzalloc_obj(*a5xx_gpu); @@ -1756,6 +1757,11 @@ static struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) return ERR_PTR(ret); } + /* Set the speedbin value that is passed to userspace */ + if (adreno_read_speedbin(&pdev->dev, &speedbin) || !speedbin) + speedbin = 0xffff; + adreno_gpu->speedbin = (uint16_t) (0xffff & speedbin); + msm_mmu_set_fault_handler(to_msm_vm(gpu->vm)->mmu, gpu, a5xx_fault_handler); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 0e8a48ca816d..3e26b60d7f67 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -2546,13 +2546,33 @@ static u32 fuse_to_supp_hw(const struct adreno_info *info, u32 fuse) return UINT_MAX; } -static int a6xx_set_supported_hw(struct device *dev, const struct adreno_info *info) +static int a6xx_read_speedbin(struct device *dev, struct a6xx_gpu *a6xx_gpu, + const struct adreno_info *info, u32 *speedbin) +{ + int ret; + + /* Use speedbin fuse if present. Otherwise, fallback to softfuse */ + ret = adreno_read_speedbin(dev, speedbin); + if (ret != -ENOENT) + return ret; + + if (info->quirks & ADRENO_QUIRK_SOFTFUSE) { + *speedbin = a6xx_llc_read(a6xx_gpu, REG_A8XX_CX_MISC_SW_FUSE_FREQ_LIMIT_STATUS); + *speedbin = A8XX_CX_MISC_SW_FUSE_FREQ_LIMIT_STATUS_FINALFREQLIMIT(*speedbin); + return 0; + } + + return -ENOENT; +} + +static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu, + const struct adreno_info *info) { u32 supp_hw; u32 speedbin; int ret; - ret = adreno_read_speedbin(dev, &speedbin); + ret = a6xx_read_speedbin(dev, a6xx_gpu, info, &speedbin); /* * -ENOENT means that the platform doesn't support speedbin which is * fine @@ -2586,11 +2606,12 @@ static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; struct adreno_platform_config *config = pdev->dev.platform_data; - struct device_node *node; + const struct adreno_info *info = config->info; struct a6xx_gpu *a6xx_gpu; struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; extern int enable_preemption; + u32 speedbin; bool is_a7xx; int ret, nr_rings = 1; @@ -2607,21 +2628,22 @@ static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = NULL; /* Check if there is a GMU phandle and set it up */ - node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0); + struct device_node *node __free(device_node) = + of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0); /* FIXME: How do we gracefully handle this? */ BUG_ON(!node); adreno_gpu->gmu_is_wrapper = of_device_is_compatible(node, "qcom,adreno-gmu-wrapper"); adreno_gpu->base.hw_apriv = - !!(config->info->quirks & ADRENO_QUIRK_HAS_HW_APRIV); + !!(info->quirks & ADRENO_QUIRK_HAS_HW_APRIV); /* gpu->info only gets assigned in adreno_gpu_init(). A8x is included intentionally */ - is_a7xx = config->info->family >= ADRENO_7XX_GEN1; + is_a7xx = info->family >= ADRENO_7XX_GEN1; a6xx_llc_slices_init(pdev, a6xx_gpu, is_a7xx); - ret = a6xx_set_supported_hw(&pdev->dev, config->info); + ret = a6xx_set_supported_hw(&pdev->dev, a6xx_gpu, info); if (ret) { a6xx_llc_slices_destroy(a6xx_gpu); kfree(a6xx_gpu); @@ -2629,15 +2651,20 @@ static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) } if ((enable_preemption == 1) || (enable_preemption == -1 && - (config->info->quirks & ADRENO_QUIRK_PREEMPTION))) + (info->quirks & ADRENO_QUIRK_PREEMPTION))) nr_rings = 4; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, nr_rings); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, info->funcs, nr_rings); if (ret) { a6xx_destroy(&(a6xx_gpu->base.base)); return ERR_PTR(ret); } + /* Set the speedbin value that is passed to userspace */ + if (a6xx_read_speedbin(&pdev->dev, a6xx_gpu, info, &speedbin) || !speedbin) + speedbin = 0xffff; + adreno_gpu->speedbin = (uint16_t) (0xffff & speedbin); + /* * For now only clamp to idle freq for devices where this is known not * to cause power supply issues: @@ -2649,7 +2676,6 @@ static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) ret = a6xx_gmu_wrapper_init(a6xx_gpu, node); else ret = a6xx_gmu_init(a6xx_gpu, node); - of_node_put(node); if (ret) { a6xx_destroy(&(a6xx_gpu->base.base)); return ERR_PTR(ret); @@ -2699,6 +2725,7 @@ const struct adreno_gpu_funcs a6xx_gpu_funcs = { .create_private_vm = a6xx_create_private_vm, .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, + .sysprof_setup = a6xx_gmu_sysprof_setup, }, .init = a6xx_gpu_init, .get_timestamp = a6xx_gmu_get_timestamp, @@ -2767,6 +2794,7 @@ const struct adreno_gpu_funcs a7xx_gpu_funcs = { .create_private_vm = a6xx_create_private_vm, .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, + .sysprof_setup = a6xx_gmu_sysprof_setup, }, .init = a6xx_gpu_init, .get_timestamp = a6xx_gmu_get_timestamp, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index 4f5dbf46132b..b40148b75420 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -289,6 +289,8 @@ static int a8xx_hfi_send_perf_table(struct a6xx_gmu *gmu) (gmu->nr_gpu_freqs * num_gx_votes * sizeof(gmu->gx_arc_votes[0])) + (gmu->nr_gmu_freqs * num_cx_votes * sizeof(gmu->cx_arc_votes[0])); tbl = kzalloc(size, GFP_KERNEL); + if (!tbl) + return -ENOMEM; tbl->type = HFI_TABLE_GPU_PERF; /* First fill GX votes */ diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 785e99fb5bd5..682a09a376fb 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -376,7 +376,7 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx, *value = adreno_gpu->info->gmem; return 0; case MSM_PARAM_GMEM_BASE: - if (adreno_gpu->info->family >= ADRENO_6XX_GEN4) + if (adreno_gpu->info->family >= ADRENO_6XX_GEN3) *value = 0; else *value = 0x100000; @@ -424,15 +424,21 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx, *value = vm->mm_range; return 0; case MSM_PARAM_HIGHEST_BANK_BIT: + if (!adreno_gpu->ubwc_config) + return UERR(ENOENT, drm, "no UBWC on this platform"); *value = adreno_gpu->ubwc_config->highest_bank_bit; return 0; case MSM_PARAM_RAYTRACING: *value = adreno_gpu->has_ray_tracing; return 0; case MSM_PARAM_UBWC_SWIZZLE: + if (!adreno_gpu->ubwc_config) + return UERR(ENOENT, drm, "no UBWC on this platform"); *value = adreno_gpu->ubwc_config->ubwc_swizzle; return 0; case MSM_PARAM_MACROTILE_MODE: + if (!adreno_gpu->ubwc_config) + return UERR(ENOENT, drm, "no UBWC on this platform"); *value = adreno_gpu->ubwc_config->macrotile_mode; return 0; case MSM_PARAM_UCHE_TRAP_BASE: @@ -1182,7 +1188,6 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct msm_gpu_config adreno_gpu_config = { 0 }; struct msm_gpu *gpu = &adreno_gpu->base; const char *gpu_name; - u32 speedbin; int ret; adreno_gpu->funcs = funcs; @@ -1211,10 +1216,6 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, devm_pm_opp_set_clkname(dev, "core"); } - if (adreno_read_speedbin(dev, &speedbin) || !speedbin) - speedbin = 0xffff; - adreno_gpu->speedbin = (uint16_t) (0xffff & speedbin); - gpu_name = devm_kasprintf(dev, GFP_KERNEL, "%"ADRENO_CHIPID_FMT, ADRENO_CHIPID_ARGS(config->chip_id)); if (!gpu_name) diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 29097e6b4253..044ed4d49aa7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -63,6 +63,7 @@ enum adreno_family { #define ADRENO_QUIRK_PREEMPTION BIT(5) #define ADRENO_QUIRK_4GB_VA BIT(6) #define ADRENO_QUIRK_IFPC BIT(7) +#define ADRENO_QUIRK_SOFTFUSE BIT(8) /* Helper for formating the chip_id in the way that userspace tools like * crashdec expect. diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h index 0b20401b04cf..e3c47b6702f1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h @@ -481,7 +481,7 @@ const struct dpu_mdss_cfg dpu_kaanapali_cfg = { .wb_count = ARRAY_SIZE(kaanapali_wb), .wb = kaanapali_wb, .cwb_count = ARRAY_SIZE(kaanapali_cwb), - .cwb = sm8650_cwb, + .cwb = kaanapali_cwb, .intf_count = ARRAY_SIZE(kaanapali_intf), .intf = kaanapali_intf, .vbif_count = ARRAY_SIZE(sm8650_vbif), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c index 6e8883dbfad4..590922c4f69b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c @@ -61,7 +61,7 @@ static int _dpu_format_populate_plane_sizes_ubwc( bool meta = MSM_FORMAT_IS_UBWC(fmt); if (MSM_FORMAT_IS_YUV(fmt)) { - unsigned int stride, sclines; + unsigned int stride, y_sclines, uv_sclines; unsigned int y_tile_width, y_tile_height; unsigned int y_meta_stride, y_meta_scanlines; unsigned int uv_meta_stride, uv_meta_scanlines; @@ -77,23 +77,25 @@ static int _dpu_format_populate_plane_sizes_ubwc( y_tile_width = 32; } - sclines = round_up(fb->height, 16); + y_sclines = round_up(fb->height, 16); + uv_sclines = round_up((fb->height+1)>>1, 16); y_tile_height = 4; } else { stride = round_up(fb->width, 128); y_tile_width = 32; - sclines = round_up(fb->height, 32); + y_sclines = round_up(fb->height, 32); + uv_sclines = round_up((fb->height+1)>>1, 32); y_tile_height = 8; } layout->plane_pitch[0] = stride; layout->plane_size[0] = round_up(layout->plane_pitch[0] * - sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); + y_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); layout->plane_pitch[1] = stride; layout->plane_size[1] = round_up(layout->plane_pitch[1] * - sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); + uv_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); if (!meta) return 0; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c index 7545c0293efb..6f2370c9dd98 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c @@ -5,6 +5,7 @@ #include <drm/drm_edid.h> #include <drm/drm_framebuffer.h> +#include <drm/drm_managed.h> #include "dpu_writeback.h" @@ -125,7 +126,7 @@ int dpu_writeback_init(struct drm_device *dev, struct drm_encoder *enc, struct dpu_wb_connector *dpu_wb_conn; int rc = 0; - dpu_wb_conn = devm_kzalloc(dev->dev, sizeof(*dpu_wb_conn), GFP_KERNEL); + dpu_wb_conn = drmm_kzalloc(dev, sizeof(*dpu_wb_conn), GFP_KERNEL); if (!dpu_wb_conn) return -ENOMEM; diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index 427d3ee2b833..6e0f8671bfb4 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -9,7 +9,7 @@ #include "msm_disp_snapshot.h" -static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *base_addr) +static void msm_disp_state_dump_regs(u32 **reg, u32 len, void __iomem *base_addr) { u32 len_padded; u32 num_rows; @@ -19,11 +19,11 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b void __iomem *end_addr; int i; - len_padded = aligned_len * REG_DUMP_ALIGN; - num_rows = aligned_len / REG_DUMP_ALIGN; + len_padded = round_up(len, REG_DUMP_ALIGN); + num_rows = DIV_ROUND_UP(len, REG_DUMP_ALIGN); addr = base_addr; - end_addr = base_addr + aligned_len; + end_addr = base_addr + len; *reg = kvzalloc(len_padded, GFP_KERNEL); if (!*reg) @@ -48,8 +48,8 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len, void __iomem *base_addr, struct drm_printer *p) { + void __iomem *addr, *end_addr; int i; - void __iomem *addr; u32 num_rows; if (!dump_addr) { @@ -58,6 +58,7 @@ static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len, } addr = base_addr; + end_addr = base_addr + len; num_rows = len / REG_DUMP_ALIGN; for (i = 0; i < num_rows; i++) { @@ -67,6 +68,17 @@ static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len, dump_addr[i * 4 + 2], dump_addr[i * 4 + 3]); addr += REG_DUMP_ALIGN; } + + if (addr != end_addr) { + drm_printf(p, "0x%lx : %08x", + (unsigned long)(addr - base_addr), + dump_addr[i * 4]); + if (addr + 0x4 < end_addr) + drm_printf(p, " %08x", dump_addr[i * 4 + 1]); + if (addr + 0x8 < end_addr) + drm_printf(p, " %08x", dump_addr[i * 4 + 2]); + drm_printf(p, "\n"); + } } void msm_disp_state_print(struct msm_disp_state *state, struct drm_printer *p) @@ -185,7 +197,7 @@ void msm_disp_snapshot_add_block(struct msm_disp_state *disp_state, u32 len, va_end(va); INIT_LIST_HEAD(&new_blk->node); - new_blk->size = ALIGN(len, REG_DUMP_ALIGN); + new_blk->size = len; new_blk->base_addr = base_addr; msm_disp_state_dump_regs(&new_blk->state, new_blk->size, base_addr); diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 1c0841a1c101..50474c994d47 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -2003,6 +2003,7 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) /* fixup base address by io offset */ msm_host->ctrl_base += cfg->io_offset; + msm_host->ctrl_size -= cfg->io_offset; ret = devm_regulator_bulk_get_const(&pdev->dev, cfg->num_regulators, cfg->regulator_data, diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 195f40e331e5..cc2bcd14b1c2 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -128,11 +128,10 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv, /* * Initialize the LRUs: */ - mutex_init(&priv->lru.lock); - drm_gem_lru_init(&priv->lru.unbacked, &priv->lru.lock); - drm_gem_lru_init(&priv->lru.pinned, &priv->lru.lock); - drm_gem_lru_init(&priv->lru.willneed, &priv->lru.lock); - drm_gem_lru_init(&priv->lru.dontneed, &priv->lru.lock); + drm_gem_lru_init(&priv->lru.unbacked); + drm_gem_lru_init(&priv->lru.pinned); + drm_gem_lru_init(&priv->lru.willneed); + drm_gem_lru_init(&priv->lru.dontneed); /* Initialize stall-on-fault */ spin_lock_init(&priv->fault_stall_lock); @@ -140,7 +139,7 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv, /* Teach lockdep about lock ordering wrt. shrinker: */ fs_reclaim_acquire(GFP_KERNEL); - might_lock(&priv->lru.lock); + might_lock(&ddev->gem_lru_mutex); fs_reclaim_release(GFP_KERNEL); if (priv->kms_init) { diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 6d847d593f1a..617b3c4b42c0 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -150,13 +150,6 @@ struct msm_drm_private { * DONTNEED state (ie. can be purged) */ struct drm_gem_lru dontneed; - - /** - * lock: - * - * Protects manipulation of all of the LRUs. - */ - struct mutex lock; } lru; struct notifier_block vmap_notifier; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 2cb3ab04f125..efd3d3c9a449 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -177,11 +177,11 @@ static void update_lru_locked(struct drm_gem_object *obj) static void update_lru(struct drm_gem_object *obj) { - struct msm_drm_private *priv = obj->dev->dev_private; + struct drm_device *dev = obj->dev; - mutex_lock(&priv->lru.lock); + mutex_lock(&dev->gem_lru_mutex); update_lru_locked(obj); - mutex_unlock(&priv->lru.lock); + mutex_unlock(&dev->gem_lru_mutex); } static struct page **get_pages(struct drm_gem_object *obj) @@ -292,11 +292,11 @@ void msm_gem_pin_obj_locked(struct drm_gem_object *obj) static void pin_obj_locked(struct drm_gem_object *obj) { - struct msm_drm_private *priv = obj->dev->dev_private; + struct drm_device *dev = obj->dev; - mutex_lock(&priv->lru.lock); + mutex_lock(&dev->gem_lru_mutex); msm_gem_pin_obj_locked(obj); - mutex_unlock(&priv->lru.lock); + mutex_unlock(&dev->gem_lru_mutex); } struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) @@ -487,16 +487,16 @@ int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct drm_gpuva *vma) void msm_gem_unpin_locked(struct drm_gem_object *obj) { - struct msm_drm_private *priv = obj->dev->dev_private; + struct drm_device *dev = obj->dev; struct msm_gem_object *msm_obj = to_msm_bo(obj); msm_gem_assert_locked(obj); - mutex_lock(&priv->lru.lock); + mutex_lock(&dev->gem_lru_mutex); msm_obj->pin_count--; GEM_WARN_ON(msm_obj->pin_count < 0); update_lru_locked(obj); - mutex_unlock(&priv->lru.lock); + mutex_unlock(&dev->gem_lru_mutex); } /* Special unpin path for use in fence-signaling path, avoiding the need @@ -507,10 +507,10 @@ void msm_gem_unpin_locked(struct drm_gem_object *obj) */ void msm_gem_unpin_active(struct drm_gem_object *obj) { - struct msm_drm_private *priv = obj->dev->dev_private; + struct drm_device *dev = obj->dev; struct msm_gem_object *msm_obj = to_msm_bo(obj); - GEM_WARN_ON(!mutex_is_locked(&priv->lru.lock)); + GEM_WARN_ON(!mutex_is_locked(&dev->gem_lru_mutex)); msm_obj->pin_count--; GEM_WARN_ON(msm_obj->pin_count < 0); @@ -797,12 +797,12 @@ void msm_gem_put_vaddr(struct drm_gem_object *obj) */ int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv) { - struct msm_drm_private *priv = obj->dev->dev_private; + struct drm_device *dev = obj->dev; struct msm_gem_object *msm_obj = to_msm_bo(obj); msm_gem_lock(obj); - mutex_lock(&priv->lru.lock); + mutex_lock(&dev->gem_lru_mutex); if (msm_obj->madv != __MSM_MADV_PURGED) msm_obj->madv = madv; @@ -814,7 +814,7 @@ int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv) */ update_lru_locked(obj); - mutex_unlock(&priv->lru.lock); + mutex_unlock(&dev->gem_lru_mutex); msm_gem_unlock(obj); @@ -824,7 +824,6 @@ int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv) void msm_gem_purge(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; - struct msm_drm_private *priv = obj->dev->dev_private; struct msm_gem_object *msm_obj = to_msm_bo(obj); msm_gem_assert_locked(obj); @@ -839,10 +838,10 @@ void msm_gem_purge(struct drm_gem_object *obj) put_pages(obj); - mutex_lock(&priv->lru.lock); + mutex_lock(&dev->gem_lru_mutex); /* A one-way transition: */ msm_obj->madv = __MSM_MADV_PURGED; - mutex_unlock(&priv->lru.lock); + mutex_unlock(&dev->gem_lru_mutex); drm_gem_free_mmap_offset(obj); diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 31fa51a44f86..9d2788f79ace 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -43,8 +43,7 @@ msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) } static bool -with_vm_locks(struct ww_acquire_ctx *ticket, - void (*fn)(struct drm_gem_object *obj), +with_vm_locks(void (*fn)(struct drm_gem_object *obj), struct drm_gem_object *obj) { /* @@ -52,7 +51,7 @@ with_vm_locks(struct ww_acquire_ctx *ticket, * success paths */ struct drm_gpuvm_bo *vm_bo, *last_locked = NULL; - int ret = 0; + bool locked = true; drm_gem_for_each_gpuvm_bo (vm_bo, obj) { struct dma_resv *resv = drm_gpuvm_resv(vm_bo->vm); @@ -60,23 +59,14 @@ with_vm_locks(struct ww_acquire_ctx *ticket, if (resv == obj->resv) continue; - ret = dma_resv_lock(resv, ticket); - - /* - * Since we already skip the case when the VM and obj - * share a resv (ie. _NO_SHARE objs), we don't expect - * to hit a double-locking scenario... which the lock - * unwinding cannot really cope with. - */ - WARN_ON(ret == -EALREADY); - /* - * Don't bother with slow-lock / backoff / retry sequence, - * if we can't get the lock just give up and move on to - * the next object. + * dma_resv_lock can't be used due to acquiring 'ticket' before the + * fs_reclaim lock, which is held in shrinker context */ - if (ret) + if (!dma_resv_trylock(resv)) { + locked = false; goto out_unlock; + } /* * Hold a ref to prevent the vm_bo from being freed @@ -108,11 +98,11 @@ out_unlock: } } - return ret == 0; + return locked; } static bool -purge(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket) +purge(struct drm_gem_object *obj, struct ww_acquire_ctx *unused) { if (!is_purgeable(to_msm_bo(obj))) return false; @@ -120,11 +110,11 @@ purge(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket) if (msm_gem_active(obj)) return false; - return with_vm_locks(ticket, msm_gem_purge, obj); + return with_vm_locks(msm_gem_purge, obj); } static bool -evict(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket) +evict(struct drm_gem_object *obj, struct ww_acquire_ctx *unused) { if (is_unevictable(to_msm_bo(obj))) return false; @@ -132,7 +122,7 @@ evict(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket) if (msm_gem_active(obj)) return false; - return with_vm_locks(ticket, msm_gem_evict, obj); + return with_vm_locks(msm_gem_evict, obj); } static bool @@ -164,7 +154,6 @@ static unsigned long msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { struct msm_drm_private *priv = shrinker->private_data; - struct ww_acquire_ctx ticket; struct { struct drm_gem_lru *lru; bool (*shrink)(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket); @@ -185,11 +174,14 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) for (unsigned i = 0; (nr > 0) && (i < ARRAY_SIZE(stages)); i++) { if (!stages[i].cond) continue; + /* + * 'ticket' not needed on trylock paths + */ stages[i].freed = - drm_gem_lru_scan(stages[i].lru, nr, + drm_gem_lru_scan(priv->dev, stages[i].lru, nr, &stages[i].remaining, stages[i].shrink, - &ticket); + NULL); nr -= stages[i].freed; freed += stages[i].freed; remaining += stages[i].remaining; @@ -255,7 +247,7 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr) unsigned long remaining = 0; for (idx = 0; lrus[idx] && unmapped < vmap_shrink_limit; idx++) { - unmapped += drm_gem_lru_scan(lrus[idx], + unmapped += drm_gem_lru_scan(priv->dev, lrus[idx], vmap_shrink_limit - unmapped, &remaining, vmap_shrink, diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 75d9f3574370..771d7bb12c2d 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -350,7 +350,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit) static int submit_pin_objects(struct msm_gem_submit *submit) { - struct msm_drm_private *priv = submit->dev->dev_private; + struct drm_device *dev = submit->dev; int i, ret = 0; for (i = 0; i < submit->nr_bos; i++) { @@ -379,11 +379,11 @@ static int submit_pin_objects(struct msm_gem_submit *submit) * get_pages() which could trigger reclaim.. and if we held the LRU lock * could trigger deadlock with the shrinker). */ - mutex_lock(&priv->lru.lock); + mutex_lock(&dev->gem_lru_mutex); for (i = 0; i < submit->nr_bos; i++) { msm_gem_pin_obj_locked(submit->bos[i].obj); } - mutex_unlock(&priv->lru.lock); + mutex_unlock(&dev->gem_lru_mutex); submit->bos_pinned = true; diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index 9e3632019bc9..3b418ee32658 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -696,7 +696,7 @@ static struct dma_fence * msm_vma_job_run(struct drm_sched_job *_job) { struct msm_vm_bind_job *job = to_msm_vm_bind_job(_job); - struct msm_drm_private *priv = job->vm->drm->dev_private; + struct drm_device *dev = job->vm->drm; struct msm_gem_vm *vm = to_msm_vm(job->vm); struct drm_gem_object *obj; int ret = vm->unusable ? -EINVAL : 0; @@ -739,13 +739,13 @@ msm_vma_job_run(struct drm_sched_job *_job) if (ret) msm_gem_vm_unusable(job->vm); - mutex_lock(&priv->lru.lock); + mutex_lock(&dev->gem_lru_mutex); job_foreach_bo (obj, job) { msm_gem_unpin_active(obj); } - mutex_unlock(&priv->lru.lock); + mutex_unlock(&dev->gem_lru_mutex); /* VM_BIND ops are synchronous, so no fence to wait on: */ return NULL; @@ -1299,7 +1299,7 @@ vm_bind_job_pin_objects(struct msm_vm_bind_job *job) return PTR_ERR(pages); } - struct msm_drm_private *priv = job->vm->drm->dev_private; + struct drm_device *dev = job->vm->drm; /* * A second loop while holding the LRU lock (a) avoids acquiring/dropping @@ -1308,10 +1308,10 @@ vm_bind_job_pin_objects(struct msm_vm_bind_job *job) * get_pages() which could trigger reclaim.. and if we held the LRU lock * could trigger deadlock with the shrinker). */ - mutex_lock(&priv->lru.lock); + mutex_lock(&dev->gem_lru_mutex); job_foreach_bo (obj, job) msm_gem_pin_obj_locked(obj); - mutex_unlock(&priv->lru.lock); + mutex_unlock(&dev->gem_lru_mutex); job->bos_pinned = true; diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 7d449e5202c5..058c71c82cf5 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -677,7 +677,7 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova, int prot) { struct msm_iommu *iommu = to_msm_iommu(mmu); - size_t ret; + ssize_t ret; WARN_ON(off != 0); @@ -686,7 +686,8 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova, iova |= GENMASK_ULL(63, 49); ret = iommu_map_sgtable(iommu->domain, iova, sgt, prot); - WARN_ON(!ret); + if (ret < 0) + return ret; return (ret == len) ? 0 : -EINVAL; } diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 30ddb5351e98..2d6b930b766e 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -16,13 +16,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) struct msm_gem_submit *submit = to_msm_submit(job); struct msm_fence_context *fctx = submit->ring->fctx; struct msm_gpu *gpu = submit->gpu; - struct msm_drm_private *priv = gpu->dev->dev_private; + struct drm_device *dev = gpu->dev; unsigned nr_cmds = submit->nr_cmds; int i; msm_fence_init(submit->hw_fence, fctx); - mutex_lock(&priv->lru.lock); + mutex_lock(&dev->gem_lru_mutex); for (i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = submit->bos[i].obj; @@ -32,7 +32,7 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) submit->bos_pinned = false; - mutex_unlock(&priv->lru.lock); + mutex_unlock(&dev->gem_lru_mutex); /* TODO move submit path over to using a per-ring lock.. */ mutex_lock(&gpu->lock); diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml index 3941e7510754..2309870f5031 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml @@ -5016,6 +5016,10 @@ by a particular renderpass/blit. <bitfield pos="1" name="LPAC" type="boolean"/> <bitfield pos="2" name="RAYTRACING" type="boolean"/> </reg32> + <reg32 offset="0x0405" name="CX_MISC_SW_FUSE_FREQ_LIMIT_STATUS" variants="A8XX-"> + <bitfield high="8" low="0" name="FINALFREQLIMIT"/> + <bitfield pos="24" name="SOFTSKUDISABLED" type="boolean"/> + </reg32> </domain> </database> |