diff options
Diffstat (limited to 'drivers')
74 files changed, 620 insertions, 293 deletions
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 42c672f1584e..cbe6aa77d50d 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -947,7 +947,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_user_end(alloc, index); } mmap_read_unlock(mm); - mmput(mm); + mmput_async(mm); trace_binder_unmap_kernel_start(alloc, index); diff --git a/drivers/base/property.c b/drivers/base/property.c index 1e6d75e65938..d58aa98fe964 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -721,7 +721,7 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev, return next; /* When no more children in primary, continue with secondary */ - if (!IS_ERR_OR_NULL(fwnode->secondary)) + if (fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) next = fwnode_get_next_child_node(fwnode->secondary, child); return next; diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 934c92dcb9ab..687d4af6945d 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -814,7 +814,8 @@ static struct inode *devmem_inode; #ifdef CONFIG_IO_STRICT_DEVMEM void revoke_devmem(struct resource *res) { - struct inode *inode = READ_ONCE(devmem_inode); + /* pairs with smp_store_release() in devmem_init_inode() */ + struct inode *inode = smp_load_acquire(&devmem_inode); /* * Check that the initialization has completed. Losing the race @@ -1028,8 +1029,11 @@ static int devmem_init_inode(void) return rc; } - /* publish /dev/mem initialized */ - WRITE_ONCE(devmem_inode, inode); + /* + * Publish /dev/mem initialized. + * Pairs with smp_load_acquire() in revoke_devmem(). + */ + smp_store_release(&devmem_inode, inode); return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index 2a41b21623ae..d20ba1b104ca 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1277,6 +1277,7 @@ void add_interrupt_randomness(int irq, int irq_flags) fast_mix(fast_pool); add_interrupt_bench(cycles); + this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]); if (unlikely(crng_init == 0)) { if ((fast_pool->count >= 64) && diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c index 039e0f91dba8..6945c3c96637 100644 --- a/drivers/firmware/qemu_fw_cfg.c +++ b/drivers/firmware/qemu_fw_cfg.c @@ -605,8 +605,10 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f) /* register entry under "/sys/firmware/qemu_fw_cfg/by_key/" */ err = kobject_init_and_add(&entry->kobj, &fw_cfg_sysfs_entry_ktype, fw_cfg_sel_ko, "%d", entry->select); - if (err) - goto err_register; + if (err) { + kobject_put(&entry->kobj); + return err; + } /* add raw binary content access */ err = sysfs_create_bin_file(&entry->kobj, &fw_cfg_sysfs_attr_raw); @@ -622,7 +624,6 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f) err_add_raw: kobject_del(&entry->kobj); -err_register: kfree(entry); return err; } diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c index b0c31789a909..3fa2c5992173 100644 --- a/drivers/fpga/dfl-afu-main.c +++ b/drivers/fpga/dfl-afu-main.c @@ -83,7 +83,8 @@ int __afu_port_disable(struct platform_device *pdev) * on this port and minimum soft reset pulse width has elapsed. * Driver polls port_soft_reset_ack to determine if reset done by HW. */ - if (readq_poll_timeout(base + PORT_HDR_CTRL, v, v & PORT_CTRL_SFTRST, + if (readq_poll_timeout(base + PORT_HDR_CTRL, v, + v & PORT_CTRL_SFTRST_ACK, RST_POLL_INVL, RST_POLL_TIMEOUT)) { dev_err(&pdev->dev, "timeout, fail to reset device\n"); return -ETIMEDOUT; diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c index 538755062ab7..a78c409bf2c4 100644 --- a/drivers/fpga/dfl-pci.c +++ b/drivers/fpga/dfl-pci.c @@ -227,7 +227,6 @@ static int cci_pci_sriov_configure(struct pci_dev *pcidev, int num_vfs) { struct cci_drvdata *drvdata = pci_get_drvdata(pcidev); struct dfl_fpga_cdev *cdev = drvdata->cdev; - int ret = 0; if (!num_vfs) { /* @@ -239,6 +238,8 @@ static int cci_pci_sriov_configure(struct pci_dev *pcidev, int num_vfs) dfl_fpga_cdev_config_ports_pf(cdev); } else { + int ret; + /* * before enable SRIOV, put released ports into VF access mode * first of all. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d7e17e34fee1..21292098bc02 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -692,9 +692,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file return n ? -EFAULT : 0; } case AMDGPU_INFO_DEV_INFO: { - struct drm_amdgpu_info_device dev_info = {}; + struct drm_amdgpu_info_device dev_info; uint64_t vm_size; + memset(&dev_info, 0, sizeof(dev_info)); dev_info.device_id = dev->pdev->device; dev_info.chip_rev = adev->rev_id; dev_info.external_rev = adev->external_rev_id; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index ebb8a28ff002..02e6f8c4dde0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -778,7 +778,8 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, tmp_str++; while (isspace(*++tmp_str)); - while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) { + while (tmp_str[0]) { + sub_str = strsep(&tmp_str, delimiter); ret = kstrtol(sub_str, 0, ¶meter[parameter_size]); if (ret) return -EINVAL; @@ -1038,7 +1039,8 @@ static ssize_t amdgpu_read_mask(const char *buf, size_t count, uint32_t *mask) memcpy(buf_cpy, buf, bytes); buf_cpy[bytes] = '\0'; tmp = buf_cpy; - while ((sub_str = strsep(&tmp, delimiter)) != NULL) { + while (tmp[0]) { + sub_str = strsep(&tmp, delimiter); if (strlen(sub_str)) { ret = kstrtol(sub_str, 0, &level); if (ret) @@ -1635,7 +1637,8 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev, i++; memcpy(buf_cpy, buf, count-i); tmp_str = buf_cpy; - while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) { + while (tmp_str[0]) { + sub_str = strsep(&tmp_str, delimiter); ret = kstrtol(sub_str, 0, ¶meter[parameter_size]); if (ret) return -EINVAL; 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 86ffa0c2880f..710edc70e37e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8717,20 +8717,38 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, * the same resource. If we have a new DC context as part of * the DM atomic state from validation we need to free it and * retain the existing one instead. + * + * Furthermore, since the DM atomic state only contains the DC + * context and can safely be annulled, we can free the state + * and clear the associated private object now to free + * some memory and avoid a possible use-after-free later. */ - struct dm_atomic_state *new_dm_state, *old_dm_state; - new_dm_state = dm_atomic_get_new_state(state); - old_dm_state = dm_atomic_get_old_state(state); + for (i = 0; i < state->num_private_objs; i++) { + struct drm_private_obj *obj = state->private_objs[i].ptr; - if (new_dm_state && old_dm_state) { - if (new_dm_state->context) - dc_release_state(new_dm_state->context); + if (obj->funcs == adev->dm.atomic_obj.funcs) { + int j = state->num_private_objs-1; - new_dm_state->context = old_dm_state->context; + dm_atomic_destroy_state(obj, + state->private_objs[i].state); + + /* If i is not at the end of the array then the + * last element needs to be moved to where i was + * before the array can safely be truncated. + */ + if (i != j) + state->private_objs[i] = + state->private_objs[j]; - if (old_dm_state->context) - dc_retain_state(old_dm_state->context); + state->private_objs[j].ptr = NULL; + state->private_objs[j].state = NULL; + state->private_objs[j].old_state = NULL; + state->private_objs[j].new_state = NULL; + + state->num_private_objs = j; + break; + } } } diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index 05d8373888e8..079f46f5cdb6 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -146,6 +146,7 @@ int bochs_kms_init(struct bochs_device *bochs) bochs->dev->mode_config.preferred_depth = 24; bochs->dev->mode_config.prefer_shadow = 0; bochs->dev->mode_config.prefer_shadow_fbdev = 1; + bochs->dev->mode_config.fbdev_use_iomem = true; bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true; bochs->dev->mode_config.funcs = &bochs_mode_funcs; diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 87b58c1acff4..648eb23d0784 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1224,6 +1224,7 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) adv7511->bridge.funcs = &adv7511_bridge_funcs; adv7511->bridge.of_node = dev->of_node; + adv7511->bridge.type = DRM_MODE_CONNECTOR_HDMIA; drm_bridge_add(&adv7511->bridge); diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c index b14d725bf609..c7bc194bbce3 100644 --- a/drivers/gpu/drm/bridge/nwl-dsi.c +++ b/drivers/gpu/drm/bridge/nwl-dsi.c @@ -917,11 +917,6 @@ static int nwl_dsi_bridge_attach(struct drm_bridge *bridge, struct drm_panel *panel; int ret; - if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR) { - DRM_ERROR("Fix bridge driver to make connector optional!"); - return -EINVAL; - } - ret = drm_of_find_panel_or_bridge(dsi->dev->of_node, 1, 0, &panel, &panel_bridge); if (ret) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 5609e164805f..89cfd68ef400 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -399,7 +399,11 @@ static void drm_fb_helper_dirty_blit_real(struct drm_fb_helper *fb_helper, unsigned int y; for (y = clip->y1; y < clip->y2; y++) { - memcpy(dst, src, len); + if (!fb_helper->dev->mode_config.fbdev_use_iomem) + memcpy(dst, src, len); + else + memcpy_toio((void __iomem *)dst, src, len); + src += fb->pitches[0]; dst += fb->pitches[0]; } diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 7bf628e13023..ee2058ad482c 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -871,9 +871,6 @@ err: * @file_priv: drm file-private structure * * Open an object using the global name, returning a handle and the size. - * - * This handle (of course) holds a reference to the object, so the object - * will not go away until the handle is deleted. */ int drm_gem_open_ioctl(struct drm_device *dev, void *data, @@ -898,14 +895,15 @@ drm_gem_open_ioctl(struct drm_device *dev, void *data, /* drm_gem_handle_create_tail unlocks dev->object_name_lock. */ ret = drm_gem_handle_create_tail(file_priv, obj, &handle); - drm_gem_object_put_unlocked(obj); if (ret) - return ret; + goto err; args->handle = handle; args->size = obj->size; - return 0; +err: + drm_gem_object_put_unlocked(obj); + return ret; } /** diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c index bb27c82757f1..bf7888ad9ad4 100644 --- a/drivers/gpu/drm/drm_mipi_dbi.c +++ b/drivers/gpu/drm/drm_mipi_dbi.c @@ -923,7 +923,7 @@ static int mipi_dbi_spi1_transfer(struct mipi_dbi *dbi, int dc, } } - tr.len = chunk; + tr.len = chunk * 2; len -= chunk; ret = spi_sync(spi, &m); diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index b50b44e76279..8fc3f67e3e76 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -322,10 +322,8 @@ static int drm_of_lvds_get_remote_pixels_type( * configurations by passing the endpoints explicitly to * drm_of_lvds_get_dual_link_pixel_order(). */ - if (!current_pt || pixels_type != current_pt) { - of_node_put(remote_port); + if (!current_pt || pixels_type != current_pt) return -EINVAL; - } } return pixels_type; diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c index 08802e5177f6..4d2290f88edb 100644 --- a/drivers/gpu/drm/mcde/mcde_display.c +++ b/drivers/gpu/drm/mcde/mcde_display.c @@ -1060,9 +1060,14 @@ static void mcde_display_update(struct drm_simple_display_pipe *pipe, */ if (fb) { mcde_set_extsrc(mcde, drm_fb_cma_get_gem_addr(fb, pstate, 0)); - if (!mcde->video_mode) - /* Send a single frame using software sync */ - mcde_display_send_one_frame(mcde); + if (!mcde->video_mode) { + /* + * Send a single frame using software sync if the flow + * is not active yet. + */ + if (mcde->flow_active == 0) + mcde_display_send_one_frame(mcde); + } dev_info_once(mcde->dev, "sent first display update\n"); } else { /* diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 519f99868e35..800b7757252e 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2073,7 +2073,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) */ if (core->assign_windows) { core->func->wndw.owner(core); - core->func->update(core, interlock, false); + nv50_disp_atomic_commit_core(state, interlock); core->assign_windows = false; interlock[NV50_DISP_INTERLOCK_CORE] = 0; } @@ -2506,7 +2506,7 @@ nv50_display_create(struct drm_device *dev) if (disp->disp->object.oclass >= TU102_DISP) nouveau_display(dev)->format_modifiers = wndwc57e_modifiers; else - if (disp->disp->object.oclass >= GF110_DISP) + if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_FERMI) nouveau_display(dev)->format_modifiers = disp90xx_modifiers; else nouveau_display(dev)->format_modifiers = disp50xx_modifiers; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 496c4621cc78..07373bbc2acf 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -191,6 +191,7 @@ nouveau_decode_mod(struct nouveau_drm *drm, uint32_t *tile_mode, uint8_t *kind) { + struct nouveau_display *disp = nouveau_display(drm->dev); BUG_ON(!tile_mode || !kind); if (modifier == DRM_FORMAT_MOD_LINEAR) { @@ -202,6 +203,12 @@ nouveau_decode_mod(struct nouveau_drm *drm, * Extract the block height and kind from the corresponding * modifier fields. See drm_fourcc.h for details. */ + + if ((modifier & (0xffull << 12)) == 0ull) { + /* Legacy modifier. Translate to this dev's 'kind.' */ + modifier |= disp->format_modifiers[0] & (0xffull << 12); + } + *tile_mode = (uint32_t)(modifier & 0xF); *kind = (uint8_t)((modifier >> 12) & 0xFF); @@ -227,6 +234,16 @@ nouveau_framebuffer_get_layout(struct drm_framebuffer *fb, } } +static const u64 legacy_modifiers[] = { + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(0), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(1), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(2), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(3), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(4), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(5), + DRM_FORMAT_MOD_INVALID +}; + static int nouveau_validate_decode_mod(struct nouveau_drm *drm, uint64_t modifier, @@ -247,8 +264,14 @@ nouveau_validate_decode_mod(struct nouveau_drm *drm, (disp->format_modifiers[mod] != modifier); mod++); - if (disp->format_modifiers[mod] == DRM_FORMAT_MOD_INVALID) - return -EINVAL; + if (disp->format_modifiers[mod] == DRM_FORMAT_MOD_INVALID) { + for (mod = 0; + (legacy_modifiers[mod] != DRM_FORMAT_MOD_INVALID) && + (legacy_modifiers[mod] != modifier); + mod++); + if (legacy_modifiers[mod] == DRM_FORMAT_MOD_INVALID) + return -EINVAL; + } nouveau_decode_mod(drm, modifier, tile_mode, kind); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 3d11b84d4cf9..d5c23d1c20d8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -315,7 +315,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper, struct drm_framebuffer *fb; struct nouveau_channel *chan; struct nouveau_bo *nvbo; - struct drm_mode_fb_cmd2 mode_cmd; + struct drm_mode_fb_cmd2 mode_cmd = {}; int ret; mode_cmd.width = sizes->surface_width; @@ -590,6 +590,7 @@ fini: drm_fb_helper_fini(&fbcon->helper); free: kfree(fbcon); + drm->fbcon = NULL; return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c index dcf08249374a..dffcac249211 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c @@ -117,15 +117,6 @@ nvkm_outp_acquire_hda(struct nvkm_outp *outp, enum nvkm_ior_type type, { struct nvkm_ior *ior; - /* First preference is to reuse the OR that is currently armed - * on HW, if any, in order to prevent unnecessary switching. - */ - list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->identity && !!ior->func->hda.hpd == hda && - !ior->asy.outp && ior->arm.outp == outp) - return nvkm_outp_acquire_ior(outp, user, ior); - } - /* Failing that, a completely unused OR is the next best thing. */ list_for_each_entry(ior, &outp->disp->ior, head) { if (!ior->identity && !!ior->func->hda.hpd == hda && @@ -173,6 +164,27 @@ nvkm_outp_acquire(struct nvkm_outp *outp, u8 user, bool hda) return nvkm_outp_acquire_ior(outp, user, ior); } + /* First preference is to reuse the OR that is currently armed + * on HW, if any, in order to prevent unnecessary switching. + */ + list_for_each_entry(ior, &outp->disp->ior, head) { + if (!ior->identity && !ior->asy.outp && ior->arm.outp == outp) { + /*XXX: For various complicated reasons, we can't outright switch + * the boot-time OR on the first modeset without some fairly + * invasive changes. + * + * The systems that were fixed by modifying the OR selection + * code to account for HDA support shouldn't regress here as + * the HDA-enabled ORs match the relevant output's pad macro + * index, and the firmware seems to select an OR this way. + * + * This warning is to make it obvious if that proves wrong. + */ + WARN_ON(hda && !ior->func->hda.hpd); + return nvkm_outp_acquire_ior(outp, user, ior); + } + } + /* If we don't need HDA, first try to acquire an OR that doesn't * support it to leave free the ones that do. */ diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 46fe1805c588..2649469070aa 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -615,9 +615,9 @@ static const struct panel_desc boe_tv101wum_nl6_desc = { static const struct drm_display_mode auo_kd101n80_45na_default_mode = { .clock = 157000, .hdisplay = 1200, - .hsync_start = 1200 + 80, - .hsync_end = 1200 + 80 + 24, - .htotal = 1200 + 80 + 24 + 36, + .hsync_start = 1200 + 60, + .hsync_end = 1200 + 60 + 24, + .htotal = 1200 + 60 + 24 + 56, .vdisplay = 1920, .vsync_start = 1920 + 16, .vsync_end = 1920 + 16 + 4, diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 5178f87d6574..4aeb960ccf15 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1250,7 +1250,21 @@ static const struct panel_desc boe_nv133fhm_n61 = { .height = 165, }, .delay = { - .hpd_absent_delay = 200, + /* + * When power is first given to the panel there's a short + * spike on the HPD line. It was explained that this spike + * was until the TCON data download was complete. On + * one system this was measured at 8 ms. We'll put 15 ms + * in the prepare delay just to be safe and take it away + * from the hpd_absent_delay (which would otherwise be 200 ms) + * to handle this. That means: + * - If HPD isn't hooked up you still have 200 ms delay. + * - If HPD is hooked up we won't try to look at it for the + * first 15 ms. + */ + .prepare = 15, + .hpd_absent_delay = 185, + .unprepare = 500, }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, diff --git a/drivers/i2c/i2c-core-slave.c b/drivers/i2c/i2c-core-slave.c index 5427f047faf0..1589179d5eb9 100644 --- a/drivers/i2c/i2c-core-slave.c +++ b/drivers/i2c/i2c-core-slave.c @@ -18,10 +18,8 @@ int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb) { int ret; - if (!client || !slave_cb) { - WARN(1, "insufficient data\n"); + if (WARN(IS_ERR_OR_NULL(client) || !slave_cb, "insufficient data\n")) return -EINVAL; - } if (!(client->flags & I2C_CLIENT_SLAVE)) dev_warn(&client->dev, "%s: client slave flag not set. You might see address collisions\n", @@ -60,6 +58,9 @@ int i2c_slave_unregister(struct i2c_client *client) { int ret; + if (IS_ERR_OR_NULL(client)) + return -EINVAL; + if (!client->adapter->algo->unreg_slave) { dev_err(&client->dev, "%s: not supported by adapter\n", __func__); return -EOPNOTSUPP; diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c index 655795bfa0ee..513825e424bf 100644 --- a/drivers/infiniband/core/cq.c +++ b/drivers/infiniband/core/cq.c @@ -72,6 +72,15 @@ static void rdma_dim_init(struct ib_cq *cq) INIT_WORK(&dim->work, ib_cq_rdma_dim_work); } +static void rdma_dim_destroy(struct ib_cq *cq) +{ + if (!cq->dim) + return; + + cancel_work_sync(&cq->dim->work); + kfree(cq->dim); +} + static int __poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { int rc; @@ -266,6 +275,7 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private, return cq; out_destroy_cq: + rdma_dim_destroy(cq); rdma_restrack_del(&cq->res); cq->device->ops.destroy_cq(cq, udata); out_free_wc: @@ -331,12 +341,10 @@ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata) WARN_ON_ONCE(1); } + rdma_dim_destroy(cq); trace_cq_free(cq); rdma_restrack_del(&cq->res); cq->device->ops.destroy_cq(cq, udata); - if (cq->dim) - cancel_work_sync(&cq->dim->work); - kfree(cq->dim); kfree(cq->wc); kfree(cq); } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 5b87eee8ccc8..d03dacaef788 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1084,6 +1084,8 @@ static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf, size_t in_size; int ret; + if (in_len < offsetofend(typeof(cmd), reserved)) + return -EINVAL; in_size = min_t(size_t, in_len, sizeof(cmd)); if (copy_from_user(&cmd, inbuf, in_size)) return -EFAULT; @@ -1141,6 +1143,8 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf, size_t in_size; int ret; + if (in_len < offsetofend(typeof(cmd), reserved)) + return -EINVAL; in_size = min_t(size_t, in_len, sizeof(cmd)); if (copy_from_user(&cmd, inbuf, in_size)) return -EFAULT; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 1ab676b66894..77dca1e05bba 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1797,9 +1797,7 @@ static bool init_prefetch_work(struct ib_pd *pd, work->frags[i].mr = get_prefetchable_mr(pd, advice, sg_list[i].lkey); if (!work->frags[i].mr) { - work->num_sge = i - 1; - if (i) - destroy_prefetch_work(work); + work->num_sge = i; return false; } @@ -1865,6 +1863,7 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, srcu_key = srcu_read_lock(&dev->odp_srcu); if (!init_prefetch_work(pd, advice, pf_flags, work, sg_list, num_sge)) { srcu_read_unlock(&dev->odp_srcu, srcu_key); + destroy_prefetch_work(work); return -EINVAL; } queue_work(system_unbound_wq, &work->work); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index e050eade97a1..1225b8d77510 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1766,15 +1766,14 @@ err: } static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev, + struct mlx5_ib_qp *qp, struct ib_qp_init_attr *init_attr, - struct mlx5_ib_create_qp *ucmd, void *qpc) { int scqe_sz; bool allow_scat_cqe = false; - if (ucmd) - allow_scat_cqe = ucmd->flags & MLX5_QP_FLAG_ALLOW_SCATTER_CQE; + allow_scat_cqe = qp->flags_en & MLX5_QP_FLAG_ALLOW_SCATTER_CQE; if (!allow_scat_cqe && init_attr->sq_sig_type != IB_SIGNAL_ALL_WR) return; @@ -1853,8 +1852,6 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, u32 *in; int err; - mutex_init(&qp->mutex); - if (attr->sq_sig_type == IB_SIGNAL_ALL_WR) qp->sq_signal_bits = MLX5_WQE_CTRL_CQ_UPDATE; @@ -1938,7 +1935,6 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 *in; int err; - mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); @@ -2012,7 +2008,7 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, } if ((qp->flags_en & MLX5_QP_FLAG_SCATTER_CQE) && (qp->type == MLX5_IB_QPT_DCI || qp->type == IB_QPT_RC)) - configure_requester_scat_cqe(dev, init_attr, ucmd, qpc); + configure_requester_scat_cqe(dev, qp, init_attr, qpc); if (qp->rq.wqe_cnt) { MLX5_SET(qpc, qpc, log_rq_stride, qp->rq.wqe_shift - 4); @@ -2129,7 +2125,6 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 *in; int err; - mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); @@ -2543,13 +2538,18 @@ static void process_vendor_flag(struct mlx5_ib_dev *dev, int *flags, int flag, return; } - if (flag == MLX5_QP_FLAG_SCATTER_CQE) { + switch (flag) { + case MLX5_QP_FLAG_SCATTER_CQE: + case MLX5_QP_FLAG_ALLOW_SCATTER_CQE: /* - * We don't return error if this flag was provided, - * and mlx5 doesn't have right capability. - */ - *flags &= ~MLX5_QP_FLAG_SCATTER_CQE; + * We don't return error if these flags were provided, + * and mlx5 doesn't have right capability. + */ + *flags &= ~(MLX5_QP_FLAG_SCATTER_CQE | + MLX5_QP_FLAG_ALLOW_SCATTER_CQE); return; + default: + break; } mlx5_ib_dbg(dev, "Vendor create QP flag 0x%X is not supported\n", flag); } @@ -2589,6 +2589,8 @@ static int process_vendor_flags(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SIGNATURE, true, qp); process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SCATTER_CQE, MLX5_CAP_GEN(mdev, sctr_data_cqe), qp); + process_vendor_flag(dev, &flags, MLX5_QP_FLAG_ALLOW_SCATTER_CQE, + MLX5_CAP_GEN(mdev, sctr_data_cqe), qp); if (qp->type == IB_QPT_RAW_PACKET) { cond = MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || @@ -2963,6 +2965,7 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attr, goto free_ucmd; } + mutex_init(&qp->mutex); qp->type = type; if (udata) { err = process_vendor_flags(dev, qp, params.ucmd, attr); diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 7db35dd6ad74..332a8ba94b81 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -901,8 +901,6 @@ static void rvt_init_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, qp->s_tail_ack_queue = 0; qp->s_acked_ack_queue = 0; qp->s_num_rd_atomic = 0; - if (qp->r_rq.kwq) - qp->r_rq.kwq->count = qp->r_rq.size; qp->r_sge.num_sge = 0; atomic_set(&qp->s_reserved_used, 0); } @@ -2367,31 +2365,6 @@ bad_lkey: } /** - * get_count - count numbers of request work queue entries - * in circular buffer - * @rq: data structure for request queue entry - * @tail: tail indices of the circular buffer - * @head: head indices of the circular buffer - * - * Return - total number of entries in the circular buffer - */ -static u32 get_count(struct rvt_rq *rq, u32 tail, u32 head) -{ - u32 count; - - count = head; - - if (count >= rq->size) - count = 0; - if (count < tail) - count += rq->size - tail; - else - count -= tail; - - return count; -} - -/** * get_rvt_head - get head indices of the circular buffer * @rq: data structure for request queue entry * @ip: the QP @@ -2465,7 +2438,7 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only) if (kwq->count < RVT_RWQ_COUNT_THRESHOLD) { head = get_rvt_head(rq, ip); - kwq->count = get_count(rq, tail, head); + kwq->count = rvt_get_rq_count(rq, head, tail); } if (unlikely(kwq->count == 0)) { ret = 0; @@ -2500,7 +2473,9 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only) * the number of remaining WQEs. */ if (kwq->count < srq->limit) { - kwq->count = get_count(rq, tail, get_rvt_head(rq, ip)); + kwq->count = + rvt_get_rq_count(rq, + get_rvt_head(rq, ip), tail); if (kwq->count < srq->limit) { struct ib_event ev; diff --git a/drivers/infiniband/sw/rdmavt/rc.c b/drivers/infiniband/sw/rdmavt/rc.c index 977906cc0d11..c58735f4c94a 100644 --- a/drivers/infiniband/sw/rdmavt/rc.c +++ b/drivers/infiniband/sw/rdmavt/rc.c @@ -127,9 +127,7 @@ __be32 rvt_compute_aeth(struct rvt_qp *qp) * not atomic, which is OK, since the fuzziness is * resolved as further ACKs go out. */ - credits = head - tail; - if ((int)credits < 0) - credits += qp->r_rq.size; + credits = rvt_get_rq_count(&qp->r_rq, head, tail); } /* * Binary search the credit table to find the code to diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index e5f998744501..9e1ab701785c 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -243,6 +243,7 @@ static int aggregate_requests(struct icc_node *node) { struct icc_provider *p = node->provider; struct icc_req *r; + u32 avg_bw, peak_bw; node->avg_bw = 0; node->peak_bw = 0; @@ -251,9 +252,14 @@ static int aggregate_requests(struct icc_node *node) p->pre_aggregate(node); hlist_for_each_entry(r, &node->req_list, req_node) { - if (!r->enabled) - continue; - p->aggregate(node, r->tag, r->avg_bw, r->peak_bw, + if (r->enabled) { + avg_bw = r->avg_bw; + peak_bw = r->peak_bw; + } else { + avg_bw = 0; + peak_bw = 0; + } + p->aggregate(node, r->tag, avg_bw, peak_bw, &node->avg_bw, &node->peak_bw); } diff --git a/drivers/interconnect/qcom/msm8916.c b/drivers/interconnect/qcom/msm8916.c index e94f3c5228b7..42c6c5581662 100644 --- a/drivers/interconnect/qcom/msm8916.c +++ b/drivers/interconnect/qcom/msm8916.c @@ -197,13 +197,13 @@ DEFINE_QNODE(pcnoc_int_0, MSM8916_PNOC_INT_0, 8, -1, -1, MSM8916_PNOC_SNOC_MAS, DEFINE_QNODE(pcnoc_int_1, MSM8916_PNOC_INT_1, 8, -1, -1, MSM8916_PNOC_SNOC_MAS); DEFINE_QNODE(pcnoc_m_0, MSM8916_PNOC_MAS_0, 8, -1, -1, MSM8916_PNOC_INT_0); DEFINE_QNODE(pcnoc_m_1, MSM8916_PNOC_MAS_1, 8, -1, -1, MSM8916_PNOC_SNOC_MAS); -DEFINE_QNODE(pcnoc_s_0, MSM8916_PNOC_SLV_0, 8, -1, -1, MSM8916_SLAVE_CLK_CTL, MSM8916_SLAVE_TLMM, MSM8916_SLAVE_TCSR, MSM8916_SLAVE_SECURITY, MSM8916_SLAVE_MSS); -DEFINE_QNODE(pcnoc_s_1, MSM8916_PNOC_SLV_1, 8, -1, -1, MSM8916_SLAVE_IMEM_CFG, MSM8916_SLAVE_CRYPTO_0_CFG, MSM8916_SLAVE_MSG_RAM, MSM8916_SLAVE_PDM, MSM8916_SLAVE_PRNG); -DEFINE_QNODE(pcnoc_s_2, MSM8916_PNOC_SLV_2, 8, -1, -1, MSM8916_SLAVE_SPDM, MSM8916_SLAVE_BOOT_ROM, MSM8916_SLAVE_BIMC_CFG, MSM8916_SLAVE_PNOC_CFG, MSM8916_SLAVE_PMIC_ARB); -DEFINE_QNODE(pcnoc_s_3, MSM8916_PNOC_SLV_3, 8, -1, -1, MSM8916_SLAVE_MPM, MSM8916_SLAVE_SNOC_CFG, MSM8916_SLAVE_RBCPR_CFG, MSM8916_SLAVE_QDSS_CFG, MSM8916_SLAVE_DEHR_CFG); -DEFINE_QNODE(pcnoc_s_4, MSM8916_PNOC_SLV_4, 8, -1, -1, MSM8916_SLAVE_VENUS_CFG, MSM8916_SLAVE_CAMERA_CFG, MSM8916_SLAVE_DISPLAY_CFG); -DEFINE_QNODE(pcnoc_s_8, MSM8916_PNOC_SLV_8, 8, -1, -1, MSM8916_SLAVE_USB_HS, MSM8916_SLAVE_SDCC_1, MSM8916_SLAVE_BLSP_1); -DEFINE_QNODE(pcnoc_s_9, MSM8916_PNOC_SLV_9, 8, -1, -1, MSM8916_SLAVE_SDCC_2, MSM8916_SLAVE_LPASS, MSM8916_SLAVE_GRAPHICS_3D_CFG); +DEFINE_QNODE(pcnoc_s_0, MSM8916_PNOC_SLV_0, 4, -1, -1, MSM8916_SLAVE_CLK_CTL, MSM8916_SLAVE_TLMM, MSM8916_SLAVE_TCSR, MSM8916_SLAVE_SECURITY, MSM8916_SLAVE_MSS); +DEFINE_QNODE(pcnoc_s_1, MSM8916_PNOC_SLV_1, 4, -1, -1, MSM8916_SLAVE_IMEM_CFG, MSM8916_SLAVE_CRYPTO_0_CFG, MSM8916_SLAVE_MSG_RAM, MSM8916_SLAVE_PDM, MSM8916_SLAVE_PRNG); +DEFINE_QNODE(pcnoc_s_2, MSM8916_PNOC_SLV_2, 4, -1, -1, MSM8916_SLAVE_SPDM, MSM8916_SLAVE_BOOT_ROM, MSM8916_SLAVE_BIMC_CFG, MSM8916_SLAVE_PNOC_CFG, MSM8916_SLAVE_PMIC_ARB); +DEFINE_QNODE(pcnoc_s_3, MSM8916_PNOC_SLV_3, 4, -1, -1, MSM8916_SLAVE_MPM, MSM8916_SLAVE_SNOC_CFG, MSM8916_SLAVE_RBCPR_CFG, MSM8916_SLAVE_QDSS_CFG, MSM8916_SLAVE_DEHR_CFG); +DEFINE_QNODE(pcnoc_s_4, MSM8916_PNOC_SLV_4, 4, -1, -1, MSM8916_SLAVE_VENUS_CFG, MSM8916_SLAVE_CAMERA_CFG, MSM8916_SLAVE_DISPLAY_CFG); +DEFINE_QNODE(pcnoc_s_8, MSM8916_PNOC_SLV_8, 4, -1, -1, MSM8916_SLAVE_USB_HS, MSM8916_SLAVE_SDCC_1, MSM8916_SLAVE_BLSP_1); +DEFINE_QNODE(pcnoc_s_9, MSM8916_PNOC_SLV_9, 4, -1, -1, MSM8916_SLAVE_SDCC_2, MSM8916_SLAVE_LPASS, MSM8916_SLAVE_GRAPHICS_3D_CFG); DEFINE_QNODE(pcnoc_snoc_mas, MSM8916_PNOC_SNOC_MAS, 8, 29, -1, MSM8916_PNOC_SNOC_SLV); DEFINE_QNODE(pcnoc_snoc_slv, MSM8916_PNOC_SNOC_SLV, 8, -1, 45, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC, MSM8916_SNOC_INT_1); DEFINE_QNODE(qdss_int, MSM8916_SNOC_QDSS_INT, 8, -1, -1, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC); diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index b0f62cbbdc87..f3a8f113865d 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -499,11 +499,19 @@ static int validate_queue_index(struct hl_device *hdev, struct asic_fixed_properties *asic = &hdev->asic_prop; struct hw_queue_properties *hw_queue_prop; + /* This must be checked here to prevent out-of-bounds access to + * hw_queues_props array + */ + if (chunk->queue_index >= HL_MAX_QUEUES) { + dev_err(hdev->dev, "Queue index %d is invalid\n", + chunk->queue_index); + return -EINVAL; + } + hw_queue_prop = &asic->hw_queues_props[chunk->queue_index]; - if ((chunk->queue_index >= HL_MAX_QUEUES) || - (hw_queue_prop->type == QUEUE_TYPE_NA)) { - dev_err(hdev->dev, "Queue index %d is invalid\n", + if (hw_queue_prop->type == QUEUE_TYPE_NA) { + dev_err(hdev->dev, "Queue index %d is not applicable\n", chunk->queue_index); return -EINVAL; } diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c index fc4372c18ce2..0bc036e01ee8 100644 --- a/drivers/misc/habanalabs/debugfs.c +++ b/drivers/misc/habanalabs/debugfs.c @@ -36,7 +36,7 @@ static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, pkt.i2c_reg = i2c_reg; rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, (long *) val); + 0, (long *) val); if (rc) dev_err(hdev->dev, "Failed to read from I2C, error %d\n", rc); @@ -63,7 +63,7 @@ static int hl_debugfs_i2c_write(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, pkt.value = cpu_to_le64(val); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, "Failed to write to I2C, error %d\n", rc); @@ -87,7 +87,7 @@ static void hl_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state) pkt.value = cpu_to_le64(state); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, "Failed to set LED %d, error %d\n", led, rc); @@ -981,7 +981,7 @@ static ssize_t hl_clk_gate_read(struct file *f, char __user *buf, if (*ppos) return 0; - sprintf(tmp_buf, "%d\n", hdev->clock_gating); + sprintf(tmp_buf, "0x%llx\n", hdev->clock_gating_mask); rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf, strlen(tmp_buf) + 1); @@ -993,7 +993,7 @@ static ssize_t hl_clk_gate_write(struct file *f, const char __user *buf, { struct hl_dbg_device_entry *entry = file_inode(f)->i_private; struct hl_device *hdev = entry->hdev; - u32 value; + u64 value; ssize_t rc; if (atomic_read(&hdev->in_reset)) { @@ -1002,19 +1002,12 @@ static ssize_t hl_clk_gate_write(struct file *f, const char __user *buf, return 0; } - rc = kstrtouint_from_user(buf, count, 10, &value); + rc = kstrtoull_from_user(buf, count, 16, &value); if (rc) return rc; - if (value) { - hdev->clock_gating = 1; - if (hdev->asic_funcs->enable_clock_gating) - hdev->asic_funcs->enable_clock_gating(hdev); - } else { - if (hdev->asic_funcs->disable_clock_gating) - hdev->asic_funcs->disable_clock_gating(hdev); - hdev->clock_gating = 0; - } + hdev->clock_gating_mask = value; + hdev->asic_funcs->set_clock_gating(hdev); return count; } diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 2b38a119704c..59608d1bac88 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -608,7 +608,7 @@ int hl_device_set_debug_mode(struct hl_device *hdev, bool enable) hdev->in_debug = 0; if (!hdev->hard_reset_pending) - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); goto out; } diff --git a/drivers/misc/habanalabs/firmware_if.c b/drivers/misc/habanalabs/firmware_if.c index baf790cf4b78..d27841cb5bcb 100644 --- a/drivers/misc/habanalabs/firmware_if.c +++ b/drivers/misc/habanalabs/firmware_if.c @@ -61,7 +61,7 @@ int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode) pkt.ctl = cpu_to_le32(opcode << ARMCP_PKT_CTL_OPCODE_SHIFT); return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, - sizeof(pkt), HL_DEVICE_TIMEOUT_USEC, NULL); + sizeof(pkt), 0, NULL); } int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg, @@ -144,7 +144,7 @@ int hl_fw_unmask_irq(struct hl_device *hdev, u16 event_type) pkt.value = cpu_to_le64(event_type); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, &result); + 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type); @@ -183,7 +183,7 @@ int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr, ARMCP_PKT_CTL_OPCODE_SHIFT); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt, - total_pkt_size, HL_DEVICE_TIMEOUT_USEC, &result); + total_pkt_size, 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask IRQ array\n"); @@ -204,7 +204,7 @@ int hl_fw_test_cpu_queue(struct hl_device *hdev) test_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &test_pkt, - sizeof(test_pkt), HL_DEVICE_TIMEOUT_USEC, &result); + sizeof(test_pkt), 0, &result); if (!rc) { if (result != ARMCP_PACKET_FENCE_VAL) @@ -248,7 +248,7 @@ int hl_fw_send_heartbeat(struct hl_device *hdev) hb_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt, - sizeof(hb_pkt), HL_DEVICE_TIMEOUT_USEC, &result); + sizeof(hb_pkt), 0, &result); if ((rc) || (result != ARMCP_PACKET_FENCE_VAL)) rc = -EIO; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 834470d10b46..637a9d608707 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -80,6 +80,7 @@ #define GAUDI_PLDM_QMAN0_TIMEOUT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GAUDI_PLDM_TPC_KERNEL_WAIT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GAUDI_BOOT_FIT_REQ_TIMEOUT_USEC 1000000 /* 1s */ +#define GAUDI_MSG_TO_CPU_TIMEOUT_USEC 4000000 /* 4s */ #define GAUDI_QMAN0_FENCE_VAL 0x72E91AB9 @@ -98,6 +99,11 @@ #define GAUDI_ARB_WDT_TIMEOUT 0x1000000 +#define GAUDI_CLK_GATE_DEBUGFS_MASK (\ + BIT(GAUDI_ENGINE_ID_MME_0) |\ + BIT(GAUDI_ENGINE_ID_MME_2) |\ + GENMASK_ULL(GAUDI_ENGINE_ID_TPC_7, GAUDI_ENGINE_ID_TPC_0)) + static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = { "gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3", "gaudi cq 1_0", "gaudi cq 1_1", "gaudi cq 1_2", "gaudi cq 1_3", @@ -106,14 +112,14 @@ static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = { }; static const u8 gaudi_dma_assignment[GAUDI_DMA_MAX] = { - [GAUDI_PCI_DMA_1] = 0, - [GAUDI_PCI_DMA_2] = 1, - [GAUDI_PCI_DMA_3] = 5, - [GAUDI_HBM_DMA_1] = 2, - [GAUDI_HBM_DMA_2] = 3, - [GAUDI_HBM_DMA_3] = 4, - [GAUDI_HBM_DMA_4] = 6, - [GAUDI_HBM_DMA_5] = 7 + [GAUDI_PCI_DMA_1] = GAUDI_ENGINE_ID_DMA_0, + [GAUDI_PCI_DMA_2] = GAUDI_ENGINE_ID_DMA_1, + [GAUDI_PCI_DMA_3] = GAUDI_ENGINE_ID_DMA_5, + [GAUDI_HBM_DMA_1] = GAUDI_ENGINE_ID_DMA_2, + [GAUDI_HBM_DMA_2] = GAUDI_ENGINE_ID_DMA_3, + [GAUDI_HBM_DMA_3] = GAUDI_ENGINE_ID_DMA_4, + [GAUDI_HBM_DMA_4] = GAUDI_ENGINE_ID_DMA_6, + [GAUDI_HBM_DMA_5] = GAUDI_ENGINE_ID_DMA_7 }; static const u8 gaudi_cq_assignment[NUMBER_OF_CMPLT_QUEUES] = { @@ -1819,7 +1825,7 @@ static void gaudi_init_golden_registers(struct hl_device *hdev) gaudi_init_rate_limiter(hdev); - gaudi_disable_clock_gating(hdev); + hdev->asic_funcs->disable_clock_gating(hdev); for (tpc_id = 0, tpc_offset = 0; tpc_id < TPC_NUMBER_OF_ENGINES; @@ -2531,46 +2537,55 @@ static void gaudi_tpc_stall(struct hl_device *hdev) WREG32(mmTPC7_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT); } -static void gaudi_enable_clock_gating(struct hl_device *hdev) +static void gaudi_set_clock_gating(struct hl_device *hdev) { struct gaudi_device *gaudi = hdev->asic_specific; u32 qman_offset; int i; - if (!hdev->clock_gating) - return; - - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) - return; - /* In case we are during debug session, don't enable the clock gate * as it may interfere */ if (hdev->in_debug) return; - for (i = 0, qman_offset = 0 ; i < PCI_DMA_NUMBER_OF_CHNLS ; i++) { + for (i = GAUDI_PCI_DMA_1, qman_offset = 0 ; i < GAUDI_HBM_DMA_1 ; i++) { + if (!(hdev->clock_gating_mask & + (BIT_ULL(gaudi_dma_assignment[i])))) + continue; + qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET; WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); WREG32(mmDMA0_QM_CGM_CFG + qman_offset, QMAN_UPPER_CP_CGM_PWR_GATE_EN); } - for (; i < HBM_DMA_NUMBER_OF_CHNLS ; i++) { + for (i = GAUDI_HBM_DMA_1 ; i < GAUDI_DMA_MAX ; i++) { + if (!(hdev->clock_gating_mask & + (BIT_ULL(gaudi_dma_assignment[i])))) + continue; + qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET; WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); WREG32(mmDMA0_QM_CGM_CFG + qman_offset, QMAN_COMMON_CP_CGM_PWR_GATE_EN); } - WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); - WREG32(mmMME0_QM_CGM_CFG, - QMAN_COMMON_CP_CGM_PWR_GATE_EN); - WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); - WREG32(mmMME2_QM_CGM_CFG, - QMAN_COMMON_CP_CGM_PWR_GATE_EN); + if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_0))) { + WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); + WREG32(mmMME0_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN); + } + + if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_2))) { + WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); + WREG32(mmMME2_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN); + } for (i = 0, qman_offset = 0 ; i < TPC_NUMBER_OF_ENGINES ; i++) { + if (!(hdev->clock_gating_mask & + (BIT_ULL(GAUDI_ENGINE_ID_TPC_0 + i)))) + continue; + WREG32(mmTPC0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); WREG32(mmTPC0_QM_CGM_CFG + qman_offset, @@ -2663,7 +2678,7 @@ static void gaudi_halt_engines(struct hl_device *hdev, bool hard_reset) gaudi_stop_hbm_dma_qmans(hdev); gaudi_stop_pci_dma_qmans(hdev); - gaudi_disable_clock_gating(hdev); + hdev->asic_funcs->disable_clock_gating(hdev); msleep(wait_timeout_ms); @@ -3003,7 +3018,7 @@ static int gaudi_hw_init(struct hl_device *hdev) gaudi_init_tpc_qmans(hdev); - gaudi_enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); gaudi_enable_timestamp(hdev); @@ -3112,7 +3127,9 @@ static void gaudi_hw_fini(struct hl_device *hdev, bool hard_reset) HW_CAP_HBM_DMA | HW_CAP_PLL | HW_CAP_MMU | HW_CAP_SRAM_SCRAMBLER | - HW_CAP_HBM_SCRAMBLER); + HW_CAP_HBM_SCRAMBLER | + HW_CAP_CLK_GATE); + memset(gaudi->events_stat, 0, sizeof(gaudi->events_stat)); } @@ -3463,6 +3480,9 @@ static int gaudi_send_cpu_message(struct hl_device *hdev, u32 *msg, return 0; } + if (!timeout) + timeout = GAUDI_MSG_TO_CPU_TIMEOUT_USEC; + return hl_fw_send_cpu_message(hdev, GAUDI_QUEUE_ID_CPU_PQ, msg, len, timeout, result); } @@ -3865,6 +3885,12 @@ static int gaudi_validate_cb(struct hl_device *hdev, rc = -EPERM; break; + case PACKET_WREG_BULK: + dev_err(hdev->dev, + "User not allowed to use WREG_BULK\n"); + rc = -EPERM; + break; + case PACKET_LOAD_AND_EXE: rc = gaudi_validate_load_and_exe_pkt(hdev, parser, (struct packet_load_and_exe *) user_pkt); @@ -3880,7 +3906,6 @@ static int gaudi_validate_cb(struct hl_device *hdev, break; case PACKET_WREG_32: - case PACKET_WREG_BULK: case PACKET_MSG_LONG: case PACKET_MSG_SHORT: case PACKET_REPEAT: @@ -4521,13 +4546,18 @@ static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) int rc = 0; if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't read register - clock gating is enabled!\n"); rc = -EFAULT; } else { *val = RREG32(addr - CFG_BASE); } + } else if ((addr >= SRAM_BASE_ADDR) && (addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) { *val = readl(hdev->pcie_bar[SRAM_BAR_ID] + @@ -4563,13 +4593,18 @@ static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) int rc = 0; if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't write register - clock gating is enabled!\n"); rc = -EFAULT; } else { WREG32(addr - CFG_BASE, val); } + } else if ((addr >= SRAM_BASE_ADDR) && (addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) { writel(val, hdev->pcie_bar[SRAM_BAR_ID] + @@ -4605,7 +4640,11 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) int rc = 0; if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't read register - clock gating is enabled!\n"); rc = -EFAULT; @@ -4615,6 +4654,7 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) *val = (((u64) val_h) << 32) | val_l; } + } else if ((addr >= SRAM_BASE_ADDR) && (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) { *val = readq(hdev->pcie_bar[SRAM_BAR_ID] + @@ -4651,7 +4691,11 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) int rc = 0; if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't write register - clock gating is enabled!\n"); rc = -EFAULT; @@ -4660,6 +4704,7 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) WREG32(addr + sizeof(u32) - CFG_BASE, upper_32_bits(val)); } + } else if ((addr >= SRAM_BASE_ADDR) && (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) { writeq(val, hdev->pcie_bar[SRAM_BAR_ID] + @@ -4881,7 +4926,7 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid) gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid); gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); } @@ -5262,7 +5307,7 @@ static void gaudi_print_ecc_info_generic(struct hl_device *hdev, } if (disable_clock_gating) { - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); } } @@ -5749,7 +5794,7 @@ static bool gaudi_tpc_read_interrupts(struct hl_device *hdev, u8 tpc_id, /* Clear interrupts */ WREG32(mmTPC0_CFG_TPC_INTR_CAUSE + tpc_offset, 0); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); @@ -6265,7 +6310,7 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u32 *mask, if (s) seq_puts(s, "\n"); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); @@ -6366,7 +6411,7 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel, dev_err(hdev->dev, "Timeout while waiting for TPC%d icache prefetch\n", tpc_id); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); return -EIO; } @@ -6395,7 +6440,7 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel, 1000, kernel_timeout); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); if (rc) { @@ -6736,7 +6781,7 @@ static const struct hl_asic_funcs gaudi_funcs = { .mmu_invalidate_cache = gaudi_mmu_invalidate_cache, .mmu_invalidate_cache_range = gaudi_mmu_invalidate_cache_range, .send_heartbeat = gaudi_send_heartbeat, - .enable_clock_gating = gaudi_enable_clock_gating, + .set_clock_gating = gaudi_set_clock_gating, .disable_clock_gating = gaudi_disable_clock_gating, .debug_coresight = gaudi_debug_coresight, .is_device_idle = gaudi_is_device_idle, diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 0d2952bb58df..88460b2138d8 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -88,6 +88,7 @@ #define GOYA_PLDM_MMU_TIMEOUT_USEC (MMU_CONFIG_TIMEOUT_USEC * 100) #define GOYA_PLDM_QMAN0_TIMEOUT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GOYA_BOOT_FIT_REQ_TIMEOUT_USEC 1000000 /* 1s */ +#define GOYA_MSG_TO_CPU_TIMEOUT_USEC 4000000 /* 4s */ #define GOYA_QMAN0_FENCE_VAL 0xD169B243 @@ -2830,6 +2831,9 @@ int goya_send_cpu_message(struct hl_device *hdev, u32 *msg, u16 len, return 0; } + if (!timeout) + timeout = GOYA_MSG_TO_CPU_TIMEOUT_USEC; + return hl_fw_send_cpu_message(hdev, GOYA_QUEUE_ID_CPU_PQ, msg, len, timeout, result); } @@ -4431,8 +4435,8 @@ static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr, pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY << ARMCP_PKT_CTL_OPCODE_SHIFT); - rc = goya_send_cpu_message(hdev, (u32 *) pkt, total_pkt_size, - HL_DEVICE_TIMEOUT_USEC, &result); + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt, + total_pkt_size, 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask IRQ array\n"); @@ -4464,8 +4468,8 @@ static int goya_unmask_irq(struct hl_device *hdev, u16 event_type) ARMCP_PKT_CTL_OPCODE_SHIFT); pkt.value = cpu_to_le64(event_type); - rc = goya_send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, &result); + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), + 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type); @@ -5028,14 +5032,14 @@ int goya_armcp_info_get(struct hl_device *hdev) return 0; } -static void goya_enable_clock_gating(struct hl_device *hdev) +static void goya_set_clock_gating(struct hl_device *hdev) { - + /* clock gating not supported in Goya */ } static void goya_disable_clock_gating(struct hl_device *hdev) { - + /* clock gating not supported in Goya */ } static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask, @@ -5259,7 +5263,7 @@ static const struct hl_asic_funcs goya_funcs = { .mmu_invalidate_cache = goya_mmu_invalidate_cache, .mmu_invalidate_cache_range = goya_mmu_invalidate_cache_range, .send_heartbeat = goya_send_heartbeat, - .enable_clock_gating = goya_enable_clock_gating, + .set_clock_gating = goya_set_clock_gating, .disable_clock_gating = goya_disable_clock_gating, .debug_coresight = goya_debug_coresight, .is_device_idle = goya_is_device_idle, diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 1ecdcf8b763a..194d83352696 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -578,8 +578,9 @@ enum hl_pll_frequency { * @mmu_invalidate_cache_range: flush specific MMU STLB cache lines with * ASID-VA-size mask. * @send_heartbeat: send is-alive packet to ArmCP and verify response. - * @enable_clock_gating: enable clock gating for reducing power consumption. - * @disable_clock_gating: disable clock for accessing registers on HBW. + * @set_clock_gating: enable/disable clock gating per engine according to + * clock gating mask in hdev + * @disable_clock_gating: disable clock gating completely * @debug_coresight: perform certain actions on Coresight for debugging. * @is_device_idle: return true if device is idle, false otherwise. * @soft_reset_late_init: perform certain actions needed after soft reset. @@ -587,7 +588,11 @@ enum hl_pll_frequency { * @hw_queues_unlock: release H/W queues lock. * @get_pci_id: retrieve PCI ID. * @get_eeprom_data: retrieve EEPROM data from F/W. - * @send_cpu_message: send buffer to ArmCP. + * @send_cpu_message: send message to F/W. If the message is timedout, the + * driver will eventually reset the device. The timeout can + * be determined by the calling function or it can be 0 and + * then the timeout is the default timeout for the specific + * ASIC * @get_hw_state: retrieve the H/W state * @pci_bars_map: Map PCI BARs. * @set_dram_bar_base: Set DRAM BAR to map specific device address. Returns @@ -680,7 +685,7 @@ struct hl_asic_funcs { int (*mmu_invalidate_cache_range)(struct hl_device *hdev, bool is_hard, u32 asid, u64 va, u64 size); int (*send_heartbeat)(struct hl_device *hdev); - void (*enable_clock_gating)(struct hl_device *hdev); + void (*set_clock_gating)(struct hl_device *hdev); void (*disable_clock_gating)(struct hl_device *hdev); int (*debug_coresight)(struct hl_device *hdev, void *data); bool (*is_device_idle)(struct hl_device *hdev, u32 *mask, @@ -1398,6 +1403,9 @@ struct hl_device_idle_busy_ts { * @max_power: the max power of the device, as configured by the sysadmin. This * value is saved so in case of hard-reset, the driver will restore * this value and update the F/W after the re-initialization + * @clock_gating_mask: is clock gating enabled. bitmask that represents the + * different engines. See debugfs-driver-habanalabs for + * details. * @in_reset: is device in reset flow. * @curr_pll_profile: current PLL profile. * @cs_active_cnt: number of active command submissions on this device (active @@ -1425,7 +1433,6 @@ struct hl_device_idle_busy_ts { * @init_done: is the initialization of the device done. * @mmu_enable: is MMU enabled. * @mmu_huge_page_opt: is MMU huge pages optimization enabled. - * @clock_gating: is clock gating enabled. * @device_cpu_disabled: is the device CPU disabled (due to timeouts) * @dma_mask: the dma mask that was set for this device * @in_debug: is device under debug. This, together with fpriv_list, enforces @@ -1493,6 +1500,7 @@ struct hl_device { atomic64_t dram_used_mem; u64 timeout_jiffies; u64 max_power; + u64 clock_gating_mask; atomic_t in_reset; enum hl_pll_frequency curr_pll_profile; int cs_active_cnt; @@ -1514,7 +1522,6 @@ struct hl_device { u8 dram_default_page_mapping; u8 pmmu_huge_range; u8 init_done; - u8 clock_gating; u8 device_cpu_disabled; u8 dma_mask; u8 in_debug; diff --git a/drivers/misc/habanalabs/habanalabs_drv.c b/drivers/misc/habanalabs/habanalabs_drv.c index 8652c7e5d7f1..22716da9f85f 100644 --- a/drivers/misc/habanalabs/habanalabs_drv.c +++ b/drivers/misc/habanalabs/habanalabs_drv.c @@ -232,7 +232,7 @@ static void set_driver_behavior_per_device(struct hl_device *hdev) hdev->fw_loading = 1; hdev->cpu_queues_enable = 1; hdev->heartbeat = 1; - hdev->clock_gating = 1; + hdev->clock_gating_mask = ULONG_MAX; hdev->reset_pcilink = 0; hdev->axi_drain = 0; diff --git a/drivers/misc/habanalabs/hwmon.c b/drivers/misc/habanalabs/hwmon.c index 8c6cd77e6af6..b997336fa75f 100644 --- a/drivers/misc/habanalabs/hwmon.c +++ b/drivers/misc/habanalabs/hwmon.c @@ -10,7 +10,6 @@ #include <linux/pci.h> #include <linux/hwmon.h> -#define SENSORS_PKT_TIMEOUT 1000000 /* 1s */ #define HWMON_NR_SENSOR_TYPES (hwmon_pwm + 1) int hl_build_hwmon_channel_info(struct hl_device *hdev, @@ -323,7 +322,7 @@ int hl_get_temperature(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -350,7 +349,7 @@ int hl_set_temperature(struct hl_device *hdev, pkt.value = __cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -374,7 +373,7 @@ int hl_get_voltage(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -400,7 +399,7 @@ int hl_get_current(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -426,7 +425,7 @@ int hl_get_fan_speed(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -452,7 +451,7 @@ int hl_get_pwm_info(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -479,7 +478,7 @@ void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr, pkt.value = cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -502,7 +501,7 @@ int hl_set_voltage(struct hl_device *hdev, pkt.value = __cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -527,7 +526,7 @@ int hl_set_current(struct hl_device *hdev, pkt.value = __cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, diff --git a/drivers/misc/habanalabs/sysfs.c b/drivers/misc/habanalabs/sysfs.c index 5d78d5e1c782..70b6b1863c2e 100644 --- a/drivers/misc/habanalabs/sysfs.c +++ b/drivers/misc/habanalabs/sysfs.c @@ -9,9 +9,6 @@ #include <linux/pci.h> -#define SET_CLK_PKT_TIMEOUT 1000000 /* 1s */ -#define SET_PWR_PKT_TIMEOUT 1000000 /* 1s */ - long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr) { struct armcp_packet pkt; @@ -29,7 +26,7 @@ long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr) pkt.pll_index = cpu_to_le32(pll_index); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_CLK_PKT_TIMEOUT, &result); + 0, &result); if (rc) { dev_err(hdev->dev, @@ -54,7 +51,7 @@ void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq) pkt.value = cpu_to_le64(freq); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_CLK_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -74,7 +71,7 @@ u64 hl_get_max_power(struct hl_device *hdev) ARMCP_PKT_CTL_OPCODE_SHIFT); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_PWR_PKT_TIMEOUT, &result); + 0, &result); if (rc) { dev_err(hdev->dev, "Failed to get max power, error %d\n", rc); @@ -96,7 +93,7 @@ void hl_set_max_power(struct hl_device *hdev, u64 value) pkt.value = cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_PWR_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, "Failed to set max power, error %d\n", rc); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index add040168e67..4ee2330c603e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1102,6 +1102,9 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, int pos; int len; + if (ctrl->quirks & NVME_QUIRK_NO_NS_DESC_LIST) + return 0; + c.identify.opcode = nvme_admin_identify; c.identify.nsid = cpu_to_le32(nsid); c.identify.cns = NVME_ID_CNS_NS_DESC_LIST; @@ -1115,18 +1118,6 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, if (status) { dev_warn(ctrl->device, "Identify Descriptors failed (%d)\n", status); - /* - * Don't treat non-retryable errors as fatal, as we potentially - * already have a NGUID or EUI-64. If we failed with DNR set, - * we want to silently ignore the error as we can still - * identify the device, but if the status has DNR set, we want - * to propagate the error back specifically for the disk - * revalidation flow to make sure we don't abandon the - * device just because of a temporal retry-able error (such - * as path of transport errors). - */ - if (status > 0 && (status & NVME_SC_DNR)) - status = 0; goto free_data; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 1de3f9b827aa..09ffc3246f60 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -129,6 +129,13 @@ enum nvme_quirks { * Don't change the value of the temperature threshold feature */ NVME_QUIRK_NO_TEMP_THRESH_CHANGE = (1 << 14), + + /* + * The controller doesn't handle the Identify Namespace + * Identification Descriptor list subcommand despite claiming + * NVMe 1.3 compliance. + */ + NVME_QUIRK_NO_NS_DESC_LIST = (1 << 15), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b1d18f0633c7..d4b1ff747123 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3099,6 +3099,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_IDENTIFY_CNS | NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ + .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */ @@ -3122,6 +3124,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x1c5c, 0x1504), /* SK Hynix PC400 */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001), .driver_data = NVME_QUIRK_SINGLE_VECTOR }, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 79ef2b8e2b3c..f3a91818167b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1382,6 +1382,9 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, if (nctrl->opts->tos >= 0) ip_sock_set_tos(queue->sock->sk, nctrl->opts->tos); + /* Set 10 seconds timeout for icresp recvmsg */ + queue->sock->sk->sk_rcvtimeo = 10 * HZ; + queue->sock->sk->sk_allocation = GFP_ATOMIC; nvme_tcp_set_queue_io_cpu(queue); queue->request = NULL; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 812bfc32ecb8..2ea61abd5830 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2330,6 +2330,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s); +static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev) +{ + pci_info(dev, "Disabling ASPM L0s/L1\n"); + pci_disable_link_state(dev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); +} + +/* + * ASM1083/1085 PCIe-PCI bridge devices cause AER timeout errors on the + * upstream PCIe root port when ASPM is enabled. At least L0s mode is affected; + * disable both L0s and L1 for now to be safe. + */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1); + /* * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain * Link bit cleared after starting the link retrain process to allow this diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index ff1ee159dca2..f8ff30cdafa6 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -7,6 +7,8 @@ config PINCTRL_MSM select PINCONF select GENERIC_PINCONF select GPIOLIB_IRQCHIP + select IRQ_DOMAIN_HIERARCHY + select IRQ_FASTEOI_HIERARCHY_HANDLERS config PINCTRL_APQ8064 tristate "Qualcomm APQ8064 pin controller driver" diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 83b7d64bc4c1..c322f30a2064 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -832,6 +832,52 @@ static void msm_gpio_irq_unmask(struct irq_data *d) msm_gpio_irq_clear_unmask(d, false); } +/** + * msm_gpio_update_dual_edge_parent() - Prime next edge for IRQs handled by parent. + * @d: The irq dta. + * + * This is much like msm_gpio_update_dual_edge_pos() but for IRQs that are + * normally handled by the parent irqchip. The logic here is slightly + * different due to what's easy to do with our parent, but in principle it's + * the same. + */ +static void msm_gpio_update_dual_edge_parent(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + const struct msm_pingroup *g = &pctrl->soc->groups[d->hwirq]; + int loop_limit = 100; + unsigned int val; + unsigned int type; + + /* Read the value and make a guess about what edge we need to catch */ + val = msm_readl_io(pctrl, g) & BIT(g->in_bit); + type = val ? IRQ_TYPE_EDGE_FALLING : IRQ_TYPE_EDGE_RISING; + + do { + /* Set the parent to catch the next edge */ + irq_chip_set_type_parent(d, type); + + /* + * Possibly the line changed between when we last read "val" + * (and decided what edge we needed) and when set the edge. + * If the value didn't change (or changed and then changed + * back) then we're done. + */ + val = msm_readl_io(pctrl, g) & BIT(g->in_bit); + if (type == IRQ_TYPE_EDGE_RISING) { + if (!val) + return; + type = IRQ_TYPE_EDGE_FALLING; + } else if (type == IRQ_TYPE_EDGE_FALLING) { + if (val) + return; + type = IRQ_TYPE_EDGE_RISING; + } + } while (loop_limit-- > 0); + dev_warn_once(pctrl->dev, "dual-edge irq failed to stabilize\n"); +} + static void msm_gpio_irq_ack(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -840,8 +886,11 @@ static void msm_gpio_irq_ack(struct irq_data *d) unsigned long flags; u32 val; - if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) { + if (test_bit(d->hwirq, pctrl->dual_edge_irqs)) + msm_gpio_update_dual_edge_parent(d); return; + } g = &pctrl->soc->groups[d->hwirq]; @@ -860,6 +909,17 @@ static void msm_gpio_irq_ack(struct irq_data *d) raw_spin_unlock_irqrestore(&pctrl->lock, flags); } +static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d, + unsigned int type) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + return type == IRQ_TYPE_EDGE_BOTH && + pctrl->soc->wakeirq_dual_edge_errata && d->parent_data && + test_bit(d->hwirq, pctrl->skip_wake_irqs); +} + static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -868,11 +928,21 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) unsigned long flags; u32 val; + if (msm_gpio_needs_dual_edge_parent_workaround(d, type)) { + set_bit(d->hwirq, pctrl->dual_edge_irqs); + irq_set_handler_locked(d, handle_fasteoi_ack_irq); + msm_gpio_update_dual_edge_parent(d); + return 0; + } + if (d->parent_data) irq_chip_set_type_parent(d, type); - if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) { + clear_bit(d->hwirq, pctrl->dual_edge_irqs); + irq_set_handler_locked(d, handle_fasteoi_irq); return 0; + } g = &pctrl->soc->groups[d->hwirq]; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h index 9452da18a78b..7486fe08eb9b 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.h +++ b/drivers/pinctrl/qcom/pinctrl-msm.h @@ -113,6 +113,9 @@ struct msm_gpio_wakeirq_map { * @pull_no_keeper: The SoC does not support keeper bias. * @wakeirq_map: The map of wakeup capable GPIOs and the pin at PDC/MPM * @nwakeirq_map: The number of entries in @wakeirq_map + * @wakeirq_dual_edge_errata: If true then GPIOs using the wakeirq_map need + * to be aware that their parent can't handle dual + * edge interrupts. */ struct msm_pinctrl_soc_data { const struct pinctrl_pin_desc *pins; @@ -128,6 +131,7 @@ struct msm_pinctrl_soc_data { const int *reserved_gpios; const struct msm_gpio_wakeirq_map *wakeirq_map; unsigned int nwakeirq_map; + bool wakeirq_dual_edge_errata; }; extern const struct dev_pm_ops msm_pinctrl_dev_pm_ops; diff --git a/drivers/pinctrl/qcom/pinctrl-sc7180.c b/drivers/pinctrl/qcom/pinctrl-sc7180.c index 1b6465a882f2..1d9acad3c1ce 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7180.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7180.c @@ -1147,6 +1147,7 @@ static const struct msm_pinctrl_soc_data sc7180_pinctrl = { .ntiles = ARRAY_SIZE(sc7180_tiles), .wakeirq_map = sc7180_pdc_map, .nwakeirq_map = ARRAY_SIZE(sc7180_pdc_map), + .wakeirq_dual_edge_errata = true, }; static int sc7180_pinctrl_probe(struct platform_device *pdev) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0ba7a65e7c8d..06056e9ec333 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -547,6 +547,15 @@ static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd) scsi_uninit_cmd(cmd); } +static void scsi_run_queue_async(struct scsi_device *sdev) +{ + if (scsi_target(sdev)->single_lun || + !list_empty(&sdev->host->starved_list)) + kblockd_schedule_work(&sdev->requeue_work); + else + blk_mq_run_hw_queues(sdev->request_queue, true); +} + /* Returns false when no more bytes to process, true if there are more */ static bool scsi_end_request(struct request *req, blk_status_t error, unsigned int bytes) @@ -591,11 +600,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error, __blk_mq_end_request(req, error); - if (scsi_target(sdev)->single_lun || - !list_empty(&sdev->host->starved_list)) - kblockd_schedule_work(&sdev->requeue_work); - else - blk_mq_run_hw_queues(q, true); + scsi_run_queue_async(sdev); percpu_ref_put(&q->q_usage_counter); return false; @@ -1702,6 +1707,7 @@ out_put_budget: */ if (req->rq_flags & RQF_DONTPREP) scsi_mq_uninit_cmd(cmd); + scsi_run_queue_async(sdev); break; } return ret; diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c index 560649be9d13..e035c9f757a1 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1032.c +++ b/drivers/staging/comedi/drivers/addi_apci_1032.c @@ -106,14 +106,22 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, unsigned int *data) { struct apci1032_private *devpriv = dev->private; - unsigned int shift, oldmask; + unsigned int shift, oldmask, himask, lomask; switch (data[0]) { case INSN_CONFIG_DIGITAL_TRIG: if (data[1] != 0) return -EINVAL; shift = data[3]; - oldmask = (1U << shift) - 1; + if (shift < 32) { + oldmask = (1U << shift) - 1; + himask = data[4] << shift; + lomask = data[5] << shift; + } else { + oldmask = 0xffffffffu; + himask = 0; + lomask = 0; + } switch (data[2]) { case COMEDI_DIGITAL_TRIG_DISABLE: devpriv->ctrl = 0; @@ -136,8 +144,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: if (devpriv->ctrl != (APCI1032_CTRL_INT_ENA | @@ -154,8 +162,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; default: return -EINVAL; diff --git a/drivers/staging/comedi/drivers/addi_apci_1500.c b/drivers/staging/comedi/drivers/addi_apci_1500.c index 689acd69a1b9..816dd25b9d0e 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1500.c +++ b/drivers/staging/comedi/drivers/addi_apci_1500.c @@ -452,13 +452,14 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev, struct apci1500_private *devpriv = dev->private; unsigned int trig = data[1]; unsigned int shift = data[3]; - unsigned int hi_mask = data[4] << shift; - unsigned int lo_mask = data[5] << shift; - unsigned int chan_mask = hi_mask | lo_mask; - unsigned int old_mask = (1 << shift) - 1; + unsigned int hi_mask; + unsigned int lo_mask; + unsigned int chan_mask; + unsigned int old_mask; unsigned int pm; unsigned int pt; unsigned int pp; + unsigned int invalid_chan; if (trig > 1) { dev_dbg(dev->class_dev, @@ -466,7 +467,20 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev, return -EINVAL; } - if (chan_mask > 0xffff) { + if (shift <= 16) { + hi_mask = data[4] << shift; + lo_mask = data[5] << shift; + old_mask = (1U << shift) - 1; + invalid_chan = (data[4] | data[5]) >> (16 - shift); + } else { + hi_mask = 0; + lo_mask = 0; + old_mask = 0xffff; + invalid_chan = data[4] | data[5]; + } + chan_mask = hi_mask | lo_mask; + + if (invalid_chan) { dev_dbg(dev->class_dev, "invalid digital trigger channel\n"); return -EINVAL; } diff --git a/drivers/staging/comedi/drivers/addi_apci_1564.c b/drivers/staging/comedi/drivers/addi_apci_1564.c index 10501fe6bb25..1268ba34be5f 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1564.c +++ b/drivers/staging/comedi/drivers/addi_apci_1564.c @@ -331,14 +331,22 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, unsigned int *data) { struct apci1564_private *devpriv = dev->private; - unsigned int shift, oldmask; + unsigned int shift, oldmask, himask, lomask; switch (data[0]) { case INSN_CONFIG_DIGITAL_TRIG: if (data[1] != 0) return -EINVAL; shift = data[3]; - oldmask = (1U << shift) - 1; + if (shift < 32) { + oldmask = (1U << shift) - 1; + himask = data[4] << shift; + lomask = data[5] << shift; + } else { + oldmask = 0xffffffffu; + himask = 0; + lomask = 0; + } switch (data[2]) { case COMEDI_DIGITAL_TRIG_DISABLE: devpriv->ctrl = 0; @@ -362,8 +370,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: if (devpriv->ctrl != (APCI1564_DI_IRQ_ENA | @@ -380,8 +388,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; default: return -EINVAL; diff --git a/drivers/staging/comedi/drivers/ni_6527.c b/drivers/staging/comedi/drivers/ni_6527.c index 4d1eccb5041d..4518c2680b7c 100644 --- a/drivers/staging/comedi/drivers/ni_6527.c +++ b/drivers/staging/comedi/drivers/ni_6527.c @@ -332,7 +332,7 @@ static int ni6527_intr_insn_config(struct comedi_device *dev, case COMEDI_DIGITAL_TRIG_ENABLE_EDGES: /* check shift amount */ shift = data[3]; - if (shift >= s->n_chan) { + if (shift >= 32) { mask = 0; rising = 0; falling = 0; diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c index 4689b2170e4f..456603fd26c0 100644 --- a/drivers/staging/wlan-ng/prism2usb.c +++ b/drivers/staging/wlan-ng/prism2usb.c @@ -61,11 +61,25 @@ static int prism2sta_probe_usb(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_device *dev; - + const struct usb_endpoint_descriptor *epd; + const struct usb_host_interface *iface_desc = interface->cur_altsetting; struct wlandevice *wlandev = NULL; struct hfa384x *hw = NULL; int result = 0; + if (iface_desc->desc.bNumEndpoints != 2) { + result = -ENODEV; + goto failed; + } + + result = -EINVAL; + epd = &iface_desc->endpoint[1].desc; + if (!usb_endpoint_is_bulk_in(epd)) + goto failed; + epd = &iface_desc->endpoint[2].desc; + if (!usb_endpoint_is_bulk_out(epd)) + goto failed; + dev = interface_to_usbdev(interface); wlandev = create_wlan(); if (!wlandev) { diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index fc118f649887..cae61d1ebec5 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -524,6 +524,7 @@ static void __init serial8250_isa_init_ports(void) */ up->mcr_mask = ~ALPHA_KLUDGE_MCR; up->mcr_force = ALPHA_KLUDGE_MCR; + serial8250_set_defaults(up); } /* chain base port ops to support Remote Supervisor Adapter */ @@ -547,7 +548,6 @@ static void __init serial8250_isa_init_ports(void) port->membase = old_serial_port[i].iomem_base; port->iotype = old_serial_port[i].io_type; port->regshift = old_serial_port[i].iomem_reg_shift; - serial8250_set_defaults(up); port->irqflags |= irqflag; if (serial8250_isa_config != NULL) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index ddb6aeb76dc5..04b9af7ed941 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -326,7 +326,17 @@ static void setup_gpio(struct pci_dev *pcidev, u8 __iomem *p) * devices will export them as GPIOs, so we pre-configure them safely * as inputs. */ - u8 dir = pcidev->vendor == PCI_VENDOR_ID_EXAR ? 0xff : 0x00; + + u8 dir = 0x00; + + if ((pcidev->vendor == PCI_VENDOR_ID_EXAR) && + (pcidev->subsystem_vendor != PCI_VENDOR_ID_SEALEVEL)) { + // Configure GPIO as inputs for Commtech adapters + dir = 0xff; + } else { + // Configure GPIO as outputs for SeaLevel adapters + dir = 0x00; + } writeb(0x00, p + UART_EXAR_MPIOINT_7_0); writeb(0x00, p + UART_EXAR_MPIOLVL_7_0); diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index f839380c2f4c..98b8a3e30733 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -306,8 +306,21 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios, } #endif + /* + * Store the requested baud rate before calling the generic 8250 + * set_termios method. Standard 8250 port expects bauds to be + * no higher than (uartclk / 16) so the baud will be clamped if it + * gets out of that bound. Mediatek 8250 port supports speed + * higher than that, therefore we'll get original baud rate back + * after calling the generic set_termios method and recalculate + * the speed later in this method. + */ + baud = tty_termios_baud_rate(termios); + serial8250_do_set_termios(port, termios, old); + tty_termios_encode_baud_rate(termios, baud, baud); + /* * Mediatek UARTs use an extra highspeed register (MTK_UART_HIGHS) * @@ -339,6 +352,11 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios, */ spin_lock_irqsave(&port->lock, flags); + /* + * Update the per-port timeout. + */ + uart_update_timeout(port, termios->c_cflag, baud); + /* set DLAB we have cval saved in up->lcr from the call to the core */ serial_port_out(port, UART_LCR, up->lcr | UART_LCR_DLAB); serial_dl_write(up, quot); diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index 8de8bac9c6c7..04d1b0807e66 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -635,7 +635,7 @@ static void tegra_uart_handle_tx_pio(struct tegra_uart_port *tup) } static void tegra_uart_handle_rx_pio(struct tegra_uart_port *tup, - struct tty_port *tty) + struct tty_port *port) { do { char flag = TTY_NORMAL; @@ -653,16 +653,18 @@ static void tegra_uart_handle_rx_pio(struct tegra_uart_port *tup, ch = (unsigned char) tegra_uart_read(tup, UART_RX); tup->uport.icount.rx++; - if (!uart_handle_sysrq_char(&tup->uport, ch) && tty) - tty_insert_flip_char(tty, ch, flag); + if (uart_handle_sysrq_char(&tup->uport, ch)) + continue; if (tup->uport.ignore_status_mask & UART_LSR_DR) continue; + + tty_insert_flip_char(port, ch, flag); } while (1); } static void tegra_uart_copy_rx_to_tty(struct tegra_uart_port *tup, - struct tty_port *tty, + struct tty_port *port, unsigned int count) { int copied; @@ -672,17 +674,13 @@ static void tegra_uart_copy_rx_to_tty(struct tegra_uart_port *tup, return; tup->uport.icount.rx += count; - if (!tty) { - dev_err(tup->uport.dev, "No tty port\n"); - return; - } if (tup->uport.ignore_status_mask & UART_LSR_DR) return; dma_sync_single_for_cpu(tup->uport.dev, tup->rx_dma_buf_phys, count, DMA_FROM_DEVICE); - copied = tty_insert_flip_string(tty, + copied = tty_insert_flip_string(port, ((unsigned char *)(tup->rx_dma_buf_virt)), count); if (copied != count) { WARN_ON(1); diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index 672cfa075e28..2833f1418d6d 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1580,8 +1580,10 @@ static int cdns_uart_probe(struct platform_device *pdev) * If register_console() don't assign value, then console_port pointer * is cleanup. */ - if (!console_port) + if (!console_port) { + cdns_uart_console.index = id; console_port = port; + } #endif rc = uart_add_one_port(&cdns_uart_uart_driver, port); @@ -1594,8 +1596,10 @@ static int cdns_uart_probe(struct platform_device *pdev) #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE /* This is not port which is used for console that's why clean it up */ if (console_port == port && - !(cdns_uart_uart_driver.cons->flags & CON_ENABLED)) + !(cdns_uart_uart_driver.cons->flags & CON_ENABLED)) { console_port = NULL; + cdns_uart_console.index = -1; + } #endif cdns_uart_data->cts_override = of_property_read_bool(pdev->dev.of_node, diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 48a8199f7845..42d8c67a481f 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1092,10 +1092,19 @@ static const struct tty_port_operations vc_port_ops = { .destruct = vc_port_destruct, }; +/* + * Change # of rows and columns (0 means unchanged/the size of fg_console) + * [this is to be used together with some user program + * like resize that changes the hardware videomode] + */ +#define VC_MAXCOL (32767) +#define VC_MAXROW (32767) + int vc_allocate(unsigned int currcons) /* return 0 on success */ { struct vt_notifier_param param; struct vc_data *vc; + int err; WARN_CONSOLE_UNLOCKED(); @@ -1125,6 +1134,11 @@ int vc_allocate(unsigned int currcons) /* return 0 on success */ if (!*vc->vc_uni_pagedir_loc) con_set_default_unimap(vc); + err = -EINVAL; + if (vc->vc_cols > VC_MAXCOL || vc->vc_rows > VC_MAXROW || + vc->vc_screenbuf_size > KMALLOC_MAX_SIZE || !vc->vc_screenbuf_size) + goto err_free; + err = -ENOMEM; vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL); if (!vc->vc_screenbuf) goto err_free; @@ -1143,7 +1157,7 @@ err_free: visual_deinit(vc); kfree(vc); vc_cons[currcons].d = NULL; - return -ENOMEM; + return err; } static inline int resize_screen(struct vc_data *vc, int width, int height, @@ -1158,14 +1172,6 @@ static inline int resize_screen(struct vc_data *vc, int width, int height, return err; } -/* - * Change # of rows and columns (0 means unchanged/the size of fg_console) - * [this is to be used together with some user program - * like resize that changes the hardware videomode] - */ -#define VC_RESIZE_MAXCOL (32767) -#define VC_RESIZE_MAXROW (32767) - /** * vc_do_resize - resizing method for the tty * @tty: tty being resized @@ -1201,7 +1207,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, user = vc->vc_resize_user; vc->vc_resize_user = 0; - if (cols > VC_RESIZE_MAXCOL || lines > VC_RESIZE_MAXROW) + if (cols > VC_MAXCOL || lines > VC_MAXROW) return -EINVAL; new_cols = (cols ? cols : vc->vc_cols); @@ -1212,7 +1218,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, if (new_cols == vc->vc_cols && new_rows == vc->vc_rows) return 0; - if (new_screen_size > KMALLOC_MAX_SIZE) + if (new_screen_size > KMALLOC_MAX_SIZE || !new_screen_size) return -EINVAL; newscreen = kzalloc(new_screen_size, GFP_USER); if (!newscreen) @@ -3393,6 +3399,7 @@ static int __init con_init(void) INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK); tty_port_init(&vc->port); visual_init(vc, currcons, 1); + /* Assuming vc->vc_{cols,rows,screenbuf_size} are sane here. */ vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT); vc_init(vc, vc->vc_rows, vc->vc_cols, currcons || !vc->vc_sw->con_save_screen); diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c index fea555570ad4..45c54d56ecbd 100644 --- a/drivers/usb/host/xhci-mtk-sch.c +++ b/drivers/usb/host/xhci-mtk-sch.c @@ -557,6 +557,10 @@ static bool need_bw_sch(struct usb_host_endpoint *ep, if (is_fs_or_ls(speed) && !has_tt) return false; + /* skip endpoint with zero maxpkt */ + if (usb_endpoint_maxp(&ep->desc) == 0) + return false; + return true; } diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ef513c2fb843..9234c82e70e4 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -265,6 +265,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == 0x1142) xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && + pdev->device == 0x2142) + xhci->quirks |= XHCI_NO_64BIT_SUPPORT; if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 2eaf5c0af80c..ee6bf01775bb 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -856,7 +856,7 @@ static int tegra_xusb_init_context(struct tegra_xusb *tegra) if (!tegra->context.ipfs) return -ENOMEM; - tegra->context.fpci = devm_kcalloc(tegra->dev, soc->ipfs.num_offsets, + tegra->context.fpci = devm_kcalloc(tegra->dev, soc->fpci.num_offsets, sizeof(u32), GFP_KERNEL); if (!tegra->context.fpci) return -ENOMEM; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 6fb4d7ecfa19..b22adf03f584 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1215,7 +1215,7 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) continue; } - switch (v_req.type) { + switch (vhost32_to_cpu(vq, v_req.type)) { case VIRTIO_SCSI_T_TMF: vc.req = &v_req.tmf; vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req); diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index ca935c09a261..35ebeeccde4d 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -216,7 +216,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = info->var.xoffset + rs; region.dy = 0; region.width = rw; @@ -224,7 +224,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset; region.dy = info->var.yoffset + bs; region.width = rs; diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index dfa9a8aa4509..78f3a5621478 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -201,7 +201,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = 0; region.dy = info->var.yoffset; region.height = rw; @@ -209,7 +209,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset + bs; region.dy = 0; region.height = info->var.yres_virtual; diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index ce08251bfd38..fd098ff17574 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -184,7 +184,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = 0; region.dy = info->var.yoffset + rs; region.height = rw; @@ -192,7 +192,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset; region.dy = info->var.yoffset; region.height = info->var.yres; diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 1936afc78fec..e165a3fad29a 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -231,7 +231,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dy = 0; region.dx = info->var.xoffset; region.width = rw; @@ -239,7 +239,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dy = info->var.yoffset; region.dx = info->var.xoffset; region.height = bh; diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 5809e5f5b157..5c92e4a50882 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -85,7 +85,7 @@ config VIRTIO_MEM depends on VIRTIO depends on MEMORY_HOTPLUG_SPARSE depends on MEMORY_HOTREMOVE - select CONTIG_ALLOC + depends on CONTIG_ALLOC help This driver provides access to virtio-mem paravirtualized memory devices, allowing to hotplug and hotunplug memory. diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 1f157d2f4952..8be02f333b7a 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -578,10 +578,14 @@ static int init_vqs(struct virtio_balloon *vb) static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb) { if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID, - &vb->config_read_bitmap)) + &vb->config_read_bitmap)) { virtio_cread(vb->vdev, struct virtio_balloon_config, free_page_hint_cmd_id, &vb->cmd_id_received_cache); + /* Legacy balloon config space is LE, unlike all other devices. */ + if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1)) + vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache); + } return vb->cmd_id_received_cache; } @@ -974,6 +978,11 @@ static int virtballoon_probe(struct virtio_device *vdev) /* * Let the hypervisor know that we are expecting a * specific value to be written back in balloon pages. + * + * If the PAGE_POISON value was larger than a byte we would + * need to byte swap poison_val here to guarantee it is + * little-endian. However for now it is a single byte so we + * can pass it as-is. */ if (!want_init_on_free()) memset(&poison_val, PAGE_POISON, sizeof(poison_val)); |