diff options
| author | Miquel Raynal <miquel.raynal@bootlin.com> | 2026-06-21 17:05:45 +0200 |
|---|---|---|
| committer | Miquel Raynal <miquel.raynal@bootlin.com> | 2026-06-21 17:05:45 +0200 |
| commit | 49420dfdedd676befaa999b165a76d8d7eec4fab (patch) | |
| tree | eafef38246f234752ad47e4ff7fb7d55fe6e95eb /drivers | |
| parent | c10f641fcb04a33da0b6bfc59cdadc250aafeb96 (diff) | |
| parent | 4f2692a5383e4bdd43ae940cda012360f7217a2d (diff) | |
Merge tag 'nand/for-7.2' into mtd/next
* Extend SPI NAND continuous read to Winbond devices, which requires
numerous changes in the spi-{mem,nand} layers such as the need for a
secondary read operation template.
* Continuous reads in general have also been enhanced/fixed for avoiding
potential issues at probe time and at block boundaries.
Plus, there is the usual load of misc fixes and improvements.
Diffstat (limited to 'drivers')
197 files changed, 2849 insertions, 1199 deletions
diff --git a/drivers/acpi/acpi_tad.c b/drivers/acpi/acpi_tad.c index b406d7a98996..cac07e997028 100644 --- a/drivers/acpi/acpi_tad.c +++ b/drivers/acpi/acpi_tad.c @@ -605,15 +605,12 @@ static umode_t acpi_tad_attr_is_visible(struct kobject *kobj, return 0; } -static const struct attribute_group acpi_tad_attr_group = { +static const struct attribute_group acpi_tad_group = { .attrs = acpi_tad_attrs, .is_visible = acpi_tad_attr_is_visible, }; -static const struct attribute_group *acpi_tad_attr_groups[] = { - &acpi_tad_attr_group, - NULL, -}; +__ATTRIBUTE_GROUPS(acpi_tad); #ifdef CONFIG_RTC_CLASS /* RTC class device interface */ @@ -683,9 +680,8 @@ static int acpi_tad_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *t) acpi_tad_rt_to_tm(&rt, &tm_now); - value = ktime_divns(ktime_sub(rtc_tm_to_ktime(t->time), - rtc_tm_to_ktime(tm_now)), NSEC_PER_SEC); - if (value <= 0 || value > U32_MAX) + value = rtc_tm_to_time64(&t->time) - rtc_tm_to_time64(&tm_now); + if (value <= 0 || value >= U32_MAX) return -EINVAL; } @@ -748,8 +744,7 @@ static int acpi_tad_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *t) if (retval != ACPI_TAD_WAKE_DISABLED) { t->enabled = 1; - t->time = rtc_ktime_to_tm(ktime_add_ns(rtc_tm_to_ktime(tm_now), - (u64)retval * NSEC_PER_SEC)); + rtc_time64_to_tm(rtc_tm_to_time64(&tm_now) + retval, &t->time); } else { t->enabled = 0; t->time = tm_now; @@ -795,9 +790,9 @@ static int acpi_tad_disable_timer(struct device *dev, u32 timer_id) return acpi_tad_wake_set(dev, "_STV", timer_id, ACPI_TAD_WAKE_DISABLED); } -static void acpi_tad_remove(struct platform_device *pdev) +static void acpi_tad_remove(void *data) { - struct device *dev = &pdev->dev; + struct device *dev = data; struct acpi_tad_driver_data *dd = dev_get_drvdata(dev); device_init_wakeup(dev, false); @@ -824,6 +819,7 @@ static int acpi_tad_probe(struct platform_device *pdev) struct acpi_tad_driver_data *dd; acpi_status status; unsigned long long caps; + int ret; /* * Initialization failure messages are mostly about firmware issues, so @@ -863,13 +859,21 @@ static int acpi_tad_probe(struct platform_device *pdev) } /* - * The platform bus type layer tells the ACPI PM domain powers up the - * device, so set the runtime PM status of it to "active". + * The platform bus type probe callback tells the ACPI PM domain to + * power up the device, so set the runtime PM status of it to "active". */ pm_runtime_set_active(dev); pm_runtime_enable(dev); pm_runtime_suspend(dev); + /* + * acpi_tad_remove() needs to run after unregistering the RTC class + * device to avoid racing with the latter's callbacks. + */ + ret = devm_add_action_or_reset(&pdev->dev, acpi_tad_remove, &pdev->dev); + if (ret) + return ret; + if (caps & ACPI_TAD_RT) acpi_tad_register_rtc(dev, caps); @@ -885,10 +889,9 @@ static struct platform_driver acpi_tad_driver = { .driver = { .name = "acpi-tad", .acpi_match_table = acpi_tad_ids, - .dev_groups = acpi_tad_attr_groups, + .dev_groups = acpi_tad_groups, }, .probe = acpi_tad_probe, - .remove = acpi_tad_remove, }; MODULE_DEVICE_TABLE(acpi, acpi_tad_ids); diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c index a9248af078f6..1f3fa2278584 100644 --- a/drivers/acpi/apei/einj-core.c +++ b/drivers/acpi/apei/einj-core.c @@ -401,8 +401,18 @@ static struct acpi_generic_address *einj_get_trigger_parameter_region( return NULL; } + +static bool is_memory_injection(u32 type, u32 flags) +{ + if (flags & SETWA_FLAGS_EINJV2) + return !!(type & ACPI_EINJV2_MEMORY); + if (type & ACPI5_VENDOR_BIT) + return !!(vendor_flags & SETWA_FLAGS_MEM); + return !!(type & MEM_ERROR_MASK) || !!(flags & SETWA_FLAGS_MEM); +} + /* Execute instructions in trigger error action table */ -static int __einj_error_trigger(u64 trigger_paddr, u32 type, +static int __einj_error_trigger(u64 trigger_paddr, u32 type, u32 flags, u64 param1, u64 param2) { struct acpi_einj_trigger trigger_tab; @@ -480,7 +490,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type, * This will cause resource conflict with regular memory. So * remove it from trigger table resources. */ - if ((param_extension || acpi5) && (type & MEM_ERROR_MASK) && param2) { + if ((param_extension || acpi5) && is_memory_injection(type, flags)) { struct apei_resources addr_resources; apei_resources_init(&addr_resources); @@ -660,7 +670,7 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, return rc; trigger_paddr = apei_exec_ctx_get_output(&ctx); if (notrigger == 0) { - rc = __einj_error_trigger(trigger_paddr, type, param1, param2); + rc = __einj_error_trigger(trigger_paddr, type, flags, param1, param2); if (rc) return rc; } @@ -718,35 +728,30 @@ int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3, SETWA_FLAGS_PCIE_SBDF | SETWA_FLAGS_EINJV2))) return -EINVAL; + /* + * Injections targeting a CXL 1.0/1.1 port have to be injected + * via the einj_cxl_rch_error_inject() path as that does the proper + * validation of the given RCRB base (MMIO) address. + */ + if (einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM)) + return -EINVAL; + /* check if type is a valid EINJv2 error type */ if (is_v2) { if (!(type & available_error_type_v2)) return -EINVAL; } - /* - * We need extra sanity checks for memory errors. - * Other types leap directly to injection. - */ /* ensure param1/param2 existed */ if (!(param_extension || acpi5)) goto inject; - /* ensure injection is memory related */ - if (type & ACPI5_VENDOR_BIT) { - if (vendor_flags != SETWA_FLAGS_MEM) - goto inject; - } else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM)) { - goto inject; - } - /* - * Injections targeting a CXL 1.0/1.1 port have to be injected - * via the einj_cxl_rch_error_inject() path as that does the proper - * validation of the given RCRB base (MMIO) address. + * We need extra sanity checks for memory errors. + * Other types leap directly to injection. */ - if (einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM)) - return -EINVAL; + if (!is_memory_injection(type, flags)) + goto inject; /* * Disallow crazy address masks that give BIOS leeway to pick diff --git a/drivers/acpi/arm64/cpuidle.c b/drivers/acpi/arm64/cpuidle.c index 801f9c450142..c68a5db8ebba 100644 --- a/drivers/acpi/arm64/cpuidle.c +++ b/drivers/acpi/arm64/cpuidle.c @@ -16,7 +16,7 @@ static int psci_acpi_cpu_init_idle(unsigned int cpu) { - int i, count; + int i; struct acpi_lpi_state *lpi; struct acpi_processor *pr = per_cpu(processors, cpu); @@ -30,14 +30,10 @@ static int psci_acpi_cpu_init_idle(unsigned int cpu) if (!psci_ops.cpu_suspend) return -EOPNOTSUPP; - count = pr->power.count - 1; - if (count <= 0) - return -ENODEV; - - for (i = 0; i < count; i++) { + for (i = 1; i < pr->power.count; i++) { u32 state; - lpi = &pr->power.lpi_states[i + 1]; + lpi = &pr->power.lpi_states[i]; /* * Only bits[31:0] represent a PSCI power_state while * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 2e91c5a97761..f370be8715ae 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -362,7 +362,7 @@ static int send_pcc_cmd(int pcc_ss_id, u16 cmd) end: if (cmd == CMD_WRITE) { if (unlikely(ret)) { - for_each_online_cpu(i) { + for_each_possible_cpu(i) { struct cpc_desc *desc = per_cpu(cpc_desc_ptr, i); if (!desc) @@ -524,13 +524,13 @@ int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data) else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY) cpu_data->shared_type = CPUFREQ_SHARED_TYPE_ANY; - for_each_online_cpu(i) { + for_each_possible_cpu(i) { if (i == cpu) continue; match_cpc_ptr = per_cpu(cpc_desc_ptr, i); if (!match_cpc_ptr) - goto err_fault; + continue; match_pdomain = &(match_cpc_ptr->domain_info); if (match_pdomain->domain != pdomain->domain) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 0a3c8232d15d..458efa4fe9d4 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -916,6 +916,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82K8"), }, }, + { + .callback = video_detect_force_native, + /* HP OMEN Gaming Laptop 16-n0xxx */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "OMEN by HP Gaming Laptop 16-n0xxx"), + }, + }, /* * x86 android tablets which directly control the backlight through diff --git a/drivers/ata/pata_parport/pata_parport.c b/drivers/ata/pata_parport/pata_parport.c index a5b959891cb7..40baeac594a9 100644 --- a/drivers/ata/pata_parport/pata_parport.c +++ b/drivers/ata/pata_parport/pata_parport.c @@ -459,19 +459,11 @@ static void pata_parport_dev_release(struct device *dev) kfree(pi); } -static void pata_parport_bus_release(struct device *dev) -{ - /* nothing to do here but required to avoid warning on device removal */ -} - static const struct bus_type pata_parport_bus_type = { .name = DRV_NAME, }; -static struct device pata_parport_bus = { - .init_name = DRV_NAME, - .release = pata_parport_bus_release, -}; +static struct device *pata_parport_bus; static const struct scsi_host_template pata_parport_sht = { PATA_PARPORT_SHT("pata_parport") @@ -518,7 +510,7 @@ static struct pi_adapter *pi_init_one(struct parport *parport, } /* set up pi->dev before pi_probe_unit() so it can use dev_printk() */ - pi->dev.parent = &pata_parport_bus; + pi->dev.parent = pata_parport_bus; pi->dev.bus = &pata_parport_bus_type; pi->dev.driver = &pr->driver; pi->dev.release = pata_parport_dev_release; @@ -780,8 +772,9 @@ static __init int pata_parport_init(void) return error; } - error = device_register(&pata_parport_bus); - if (error) { + pata_parport_bus = root_device_register(DRV_NAME); + if (IS_ERR(pata_parport_bus)) { + error = PTR_ERR(pata_parport_bus); pr_err("failed to register pata_parport bus, error: %d\n", error); goto out_unregister_bus; } @@ -811,7 +804,7 @@ out_remove_del: out_remove_new: bus_remove_file(&pata_parport_bus_type, &bus_attr_new_device); out_unregister_dev: - device_unregister(&pata_parport_bus); + root_device_unregister(pata_parport_bus); out_unregister_bus: bus_unregister(&pata_parport_bus_type); return error; @@ -822,7 +815,7 @@ static __exit void pata_parport_exit(void) parport_unregister_driver(&pata_parport_driver); bus_remove_file(&pata_parport_bus_type, &bus_attr_new_device); bus_remove_file(&pata_parport_bus_type, &bus_attr_delete_device); - device_unregister(&pata_parport_bus); + root_device_unregister(pata_parport_bus); bus_unregister(&pata_parport_bus_type); } diff --git a/drivers/base/regmap/regmap-sdw-mbq.c b/drivers/base/regmap/regmap-sdw-mbq.c index 4533fe793c5f..2585933d4946 100644 --- a/drivers/base/regmap/regmap-sdw-mbq.c +++ b/drivers/base/regmap/regmap-sdw-mbq.c @@ -172,7 +172,7 @@ static int regmap_sdw_mbq_read(void *context, unsigned int reg, unsigned int *va ret = regmap_sdw_mbq_read_impl(slave, reg, val, mbq_size); if (ret == -ENODATA) { if (!deferrable) - dev_warn(dev, "Defer on undeferable control: %x\n", reg); + dev_warn(dev, "Defer on undeferrable control: %x\n", reg); ret = regmap_sdw_mbq_poll_busy(slave, reg, ctx); if (ret) diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index fc049612d6dc..62934cf4b10d 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -631,6 +631,16 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) WARN_ON(!cdo->generic_packet); + /* + * Propagate the drive's write support to the block layer so BLKROGET + * reflects actual write capability. Drivers that use GET CONFIGURATION + * features (CDC_MRW_W, CDC_RAM) must have called + * cdrom_probe_write_features() before register_cdrom() so the mask is + * complete here. + */ + set_disk_ro(disk, !CDROM_CAN(CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | + CDC_CD_RW)); + cd_dbg(CD_REG_UNREG, "drive \"/dev/%s\" registered\n", cdi->name); mutex_lock(&cdrom_mutex); list_add(&cdi->list, &cdrom_list); @@ -742,6 +752,44 @@ static int cdrom_is_random_writable(struct cdrom_device_info *cdi, int *write) return 0; } +/* + * Probe write-related MMC features via GET CONFIGURATION and update + * cdi->mask accordingly. Drivers that populate cdi->mask from the MODE SENSE + * capabilities page (e.g. sr) should call this after those MODE SENSE bits + * have been set but before register_cdrom(), so that the full set of + * write-capability bits is known by the time register_cdrom() decides on the + * initial read-only state of the disk. + */ +void cdrom_probe_write_features(struct cdrom_device_info *cdi) +{ + int mrw, mrw_write, ram_write; + + mrw = 0; + if (!cdrom_is_mrw(cdi, &mrw_write)) + mrw = 1; + + if (CDROM_CAN(CDC_MO_DRIVE)) + ram_write = 1; + else + (void) cdrom_is_random_writable(cdi, &ram_write); + + if (mrw) + cdi->mask &= ~CDC_MRW; + else + cdi->mask |= CDC_MRW; + + if (mrw_write) + cdi->mask &= ~CDC_MRW_W; + else + cdi->mask |= CDC_MRW_W; + + if (ram_write) + cdi->mask &= ~CDC_RAM; + else + cdi->mask |= CDC_RAM; +} +EXPORT_SYMBOL(cdrom_probe_write_features); + static int cdrom_media_erasable(struct cdrom_device_info *cdi) { disc_information di; @@ -894,33 +942,8 @@ static int cdrom_is_dvd_rw(struct cdrom_device_info *cdi) */ static int cdrom_open_write(struct cdrom_device_info *cdi) { - int mrw, mrw_write, ram_write; int ret = 1; - mrw = 0; - if (!cdrom_is_mrw(cdi, &mrw_write)) - mrw = 1; - - if (CDROM_CAN(CDC_MO_DRIVE)) - ram_write = 1; - else - (void) cdrom_is_random_writable(cdi, &ram_write); - - if (mrw) - cdi->mask &= ~CDC_MRW; - else - cdi->mask |= CDC_MRW; - - if (mrw_write) - cdi->mask &= ~CDC_MRW_W; - else - cdi->mask |= CDC_MRW_W; - - if (ram_write) - cdi->mask &= ~CDC_RAM; - else - cdi->mask |= CDC_RAM; - if (CDROM_CAN(CDC_MRW_W)) ret = cdrom_mrw_open_write(cdi); else if (CDROM_CAN(CDC_DVD_RAM)) diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index af7ce62ec55c..0ff1658c2dc1 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -900,11 +900,21 @@ int dpll_pin_delete_ntf(struct dpll_pin *pin) return dpll_pin_event_send(DPLL_CMD_PIN_DELETE_NTF, pin); } +/** + * __dpll_pin_change_ntf - notify that the pin has been changed + * @pin: registered pin pointer + * + * Context: caller must hold dpll_lock. Suitable for use inside pin + * callbacks which are already invoked under dpll_lock. + * Return: 0 if succeeds, error code otherwise. + */ int __dpll_pin_change_ntf(struct dpll_pin *pin) { + lockdep_assert_held(&dpll_lock); dpll_pin_notify(pin, DPLL_PIN_CHANGED); return dpll_pin_event_send(DPLL_CMD_PIN_CHANGE_NTF, pin); } +EXPORT_SYMBOL_GPL(__dpll_pin_change_ntf); /** * dpll_pin_change_ntf - notify that the pin has been changed diff --git a/drivers/dpll/dpll_netlink.h b/drivers/dpll/dpll_netlink.h index dd28b56d27c5..a9cfd55f57fc 100644 --- a/drivers/dpll/dpll_netlink.h +++ b/drivers/dpll/dpll_netlink.h @@ -11,5 +11,3 @@ int dpll_device_delete_ntf(struct dpll_device *dpll); int dpll_pin_create_ntf(struct dpll_pin *pin); int dpll_pin_delete_ntf(struct dpll_pin *pin); - -int __dpll_pin_change_ntf(struct dpll_pin *pin); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 737ef1ef96a5..66ca043658ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2839,8 +2839,12 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev) * that checks whether the PSP is running. A solution for those issues * in the APU is to trigger a GPU reset, but this should be done during * the unload phase to avoid adding boot latency and screen flicker. + * GFX V11 has GC block as default off IP. Every time AMDGPU driver sends + * a request to PMFW to unload MP1, PMFW will put GC in reset and power down + * the voltage. Hence, skipping reset for APUs with GFX V11 or later. */ - if ((adev->flags & AMD_IS_APU) && !adev->gmc.is_app_apu) { + if ((adev->flags & AMD_IS_APU) && !adev->gmc.is_app_apu && + amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(11, 0, 0)) { r = amdgpu_asic_reset(adev); if (r) dev_err(adev->dev, "asic reset on %s failed\n", __func__); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index fcad7daaa41b..8d99bfaa498f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -3090,10 +3090,8 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 5, 1): case IP_VERSION(11, 5, 2): case IP_VERSION(11, 5, 3): - adev->family = AMDGPU_FAMILY_GC_11_5_0; - break; case IP_VERSION(11, 5, 4): - adev->family = AMDGPU_FAMILY_GC_11_5_4; + adev->family = AMDGPU_FAMILY_GC_11_5_0; break; case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index e47921e2a9af..46aae3fad4bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -3158,8 +3158,10 @@ static int __init amdgpu_init(void) amdgpu_register_atpx_handler(); amdgpu_acpi_detect(); - /* Ignore KFD init failures. Normal when CONFIG_HSA_AMD is not set. */ - amdgpu_amdkfd_init(); + /* Ignore KFD init failures when CONFIG_HSA_AMD is not set. */ + r = amdgpu_amdkfd_init(); + if (r && r != -ENOENT) + goto error_fence; if (amdgpu_pp_feature_mask & PP_OVERDRIVE_MASK) { add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 285e217fba04..3d9497d121ca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -314,7 +314,10 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc, mc->gart_start = max_mc_address - mc->gart_size + 1; break; case AMDGPU_GART_PLACEMENT_LOW: - mc->gart_start = 0; + if (size_bf >= mc->gart_size) + mc->gart_start = 0; + else + mc->gart_start = ALIGN(mc->fb_end, four_gb); break; case AMDGPU_GART_PLACEMENT_BEST_FIT: default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 06efce38f323..71272f40feef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -873,68 +873,59 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) ? -EFAULT : 0; } case AMDGPU_INFO_READ_MMR_REG: { - int ret = 0; - unsigned int n, alloc_size; - uint32_t *regs; unsigned int se_num = (info->read_mmr_reg.instance >> AMDGPU_INFO_MMR_SE_INDEX_SHIFT) & AMDGPU_INFO_MMR_SE_INDEX_MASK; unsigned int sh_num = (info->read_mmr_reg.instance >> AMDGPU_INFO_MMR_SH_INDEX_SHIFT) & AMDGPU_INFO_MMR_SH_INDEX_MASK; - - if (!down_read_trylock(&adev->reset_domain->sem)) - return -ENOENT; + unsigned int alloc_size; + uint32_t *regs; + int ret; /* set full masks if the userspace set all bits * in the bitfields */ - if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) { + if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) se_num = 0xffffffff; - } else if (se_num >= AMDGPU_GFX_MAX_SE) { - ret = -EINVAL; - goto out; - } + else if (se_num >= AMDGPU_GFX_MAX_SE) + return -EINVAL; - if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) { + if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) sh_num = 0xffffffff; - } else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) { - ret = -EINVAL; - goto out; - } + else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) + return -EINVAL; - if (info->read_mmr_reg.count > 128) { - ret = -EINVAL; - goto out; - } + if (info->read_mmr_reg.count > 128) + return -EINVAL; - regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL); - if (!regs) { - ret = -ENOMEM; - goto out; - } + regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), + GFP_KERNEL); + if (!regs) + return -ENOMEM; + down_read(&adev->reset_domain->sem); alloc_size = info->read_mmr_reg.count * sizeof(*regs); - amdgpu_gfx_off_ctrl(adev, false); + ret = 0; for (i = 0; i < info->read_mmr_reg.count; i++) { if (amdgpu_asic_read_register(adev, se_num, sh_num, info->read_mmr_reg.dword_offset + i, ®s[i])) { DRM_DEBUG_KMS("unallowed offset %#x\n", info->read_mmr_reg.dword_offset + i); - kfree(regs); - amdgpu_gfx_off_ctrl(adev, true); ret = -EFAULT; - goto out; + break; } } amdgpu_gfx_off_ctrl(adev, true); - n = copy_to_user(out, regs, min(size, alloc_size)); - kfree(regs); - ret = (n ? -EFAULT : 0); -out: up_read(&adev->reset_domain->sem); + + if (!ret) { + ret = copy_to_user(out, regs, min(size, alloc_size)) + ? -EFAULT : 0; + } + kfree(regs); return ret; } case AMDGPU_INFO_DEV_INFO: { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index cdf4909592d2..0c57fe259894 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -1950,7 +1950,7 @@ void amdgpu_ras_check_bad_page_status(struct amdgpu_device *adev) if (!control || amdgpu_bad_page_threshold == 0) return; - if (control->ras_num_bad_pages >= ras->bad_page_cnt_threshold) { + if (control->ras_num_bad_pages > ras->bad_page_cnt_threshold) { if (amdgpu_dpm_send_rma_reason(adev)) dev_warn(adev->dev, "Unable to send out-of-band RMA CPER"); else diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 0dc68fb9d88e..3d2e00efc741 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -75,6 +75,9 @@ static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev, unsigned int type, uint64_t size_in_page) { + if (!size_in_page) + return 0; + return ttm_range_man_init(&adev->mman.bdev, type, false, size_in_page); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index d5abf785ca17..de140a8ed135 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -205,6 +205,19 @@ void amdgpu_userq_start_hang_detect_work(struct amdgpu_usermode_queue *queue) msecs_to_jiffies(timeout_ms)); } +void amdgpu_userq_process_fence_irq(struct amdgpu_device *adev, u32 doorbell) +{ + struct xarray *xa = &adev->userq_doorbell_xa; + struct amdgpu_usermode_queue *queue; + unsigned long flags; + + xa_lock_irqsave(xa, flags); + queue = xa_load(xa, doorbell); + if (queue) + amdgpu_userq_fence_driver_process(queue->fence_drv); + xa_unlock_irqrestore(xa, flags); +} + static void amdgpu_userq_init_hang_detect_work(struct amdgpu_usermode_queue *queue) { INIT_DELAYED_WORK(&queue->hang_detect_work, amdgpu_userq_hang_detect_work); @@ -643,12 +656,6 @@ amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_que #endif amdgpu_userq_detect_and_reset_queues(uq_mgr); r = amdgpu_userq_unmap_helper(queue); - /*TODO: It requires a reset for userq hw unmap error*/ - if (r) { - drm_warn(adev_to_drm(uq_mgr->adev), "trying to destroy a HW mapping userq\n"); - queue->state = AMDGPU_USERQ_STATE_HUNG; - } - atomic_dec(&uq_mgr->userq_count[queue->queue_type]); amdgpu_userq_cleanup(queue); mutex_unlock(&uq_mgr->userq_mutex); @@ -1187,7 +1194,7 @@ retry_lock: bo = range->bo; ret = amdgpu_ttm_tt_get_user_pages(bo, range); if (ret) - goto unlock_all; + goto free_ranges; } invalidated = true; @@ -1214,6 +1221,7 @@ retry_lock: unlock_all: drm_exec_fini(&exec); +free_ranges: xa_for_each(&xa, tmp_key, range) { if (!range) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h index 675fe6395ac8..8b8f345b60b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h @@ -156,6 +156,7 @@ void amdgpu_userq_reset_work(struct work_struct *work); void amdgpu_userq_pre_reset(struct amdgpu_device *adev); int amdgpu_userq_post_reset(struct amdgpu_device *adev, bool vram_lost); void amdgpu_userq_start_hang_detect_work(struct amdgpu_usermode_queue *queue); +void amdgpu_userq_process_fence_irq(struct amdgpu_device *adev, u32 doorbell); int amdgpu_userq_input_va_validate(struct amdgpu_device *adev, struct amdgpu_usermode_queue *queue, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 115a7b269af3..9ba9de16a27a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3023,11 +3023,22 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, is_compute_context = vm->is_compute_context; - if (is_compute_context && !svm_range_restore_pages(adev, pasid, vmid, - node_id, addr >> PAGE_SHIFT, ts, write_fault)) { + if (is_compute_context) { + /* Unreserve root since svm_range_restore_pages might try to reserve it. */ + /* TODO: rework svm_range_restore_pages so that this isn't necessary. */ amdgpu_bo_unreserve(root); + + if (!svm_range_restore_pages(adev, pasid, vmid, + node_id, addr >> PAGE_SHIFT, ts, write_fault)) { + amdgpu_bo_unref(&root); + return true; + } amdgpu_bo_unref(&root); - return true; + + /* Re-acquire the VM lock, could be that the VM was freed in between. */ + vm = amdgpu_vm_lock_by_pasid(adev, &root, pasid); + if (!vm) + return false; } addr /= AMDGPU_GPU_PAGE_SIZE; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 8c82e90f871b..d40ab1e95480 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -6523,15 +6523,7 @@ static int gfx_v11_0_eop_irq(struct amdgpu_device *adev, DRM_DEBUG("IH: CP EOP\n"); if (adev->enable_mes && doorbell_offset) { - struct amdgpu_usermode_queue *queue; - struct xarray *xa = &adev->userq_doorbell_xa; - unsigned long flags; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } else { me_id = (entry->ring_id & 0x0c) >> 2; pipe_id = (entry->ring_id & 0x03) >> 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 65c33823a688..0e0b1e5b88fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -4854,15 +4854,7 @@ static int gfx_v12_0_eop_irq(struct amdgpu_device *adev, DRM_DEBUG("IH: CP EOP\n"); if (adev->enable_mes && doorbell_offset) { - struct xarray *xa = &adev->userq_doorbell_xa; - struct amdgpu_usermode_queue *queue; - unsigned long flags; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } else { me_id = (entry->ring_id & 0x0c) >> 2; pipe_id = (entry->ring_id & 0x03) >> 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c index 68fd3c04134d..68db1bc73bc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c @@ -3643,16 +3643,7 @@ static int gfx_v12_1_eop_irq(struct amdgpu_device *adev, DRM_DEBUG("IH: CP EOP\n"); if (adev->enable_mes && doorbell_offset) { - struct xarray *xa = &adev->userq_doorbell_xa; - struct amdgpu_usermode_queue *queue; - unsigned long flags; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } else { me_id = (entry->ring_id & 0x0c) >> 2; pipe_id = (entry->ring_id & 0x03) >> 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index 73223d97a87f..ac90d8e9d86a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -1571,6 +1571,71 @@ static void gfx_v6_0_setup_spi(struct amdgpu_device *adev) mutex_unlock(&adev->grbm_idx_mutex); } +/** + * gfx_v6_0_setup_tcc() - setup which TCCs are used + * + * @adev: amdgpu_device pointer + * + * Verify whether the current GPU has any TCCs disabled, + * which can happen when the GPU is harvested and some + * memory channels are disabled, reducing the memory bus width. + * For example, on the Radeon HD 7870 XT (Tahiti LE). + * + * If some TCCs are disabled, we need to make sure that + * the disabled TCCs are not used, and the remaining TCCs + * are used optimally. + * + * TCP_CHAN_STEER_LO/HI control which TCC is used by TCP channels. + * TCP_ADDR_CONFIG.NUM_TCC_BANKS controls how many channels are used. + * + * For optimal performance: + * - Rely on the CHAN_STEER from the golden registers table, + * only skip disabled TCCs but keep the mapping order. + * - Limit NUM_TCC_BANKS to number of active TCCs to avoid thrashing, + * which performs better than using the same TCC twice. + */ +static void gfx_v6_0_setup_tcc(struct amdgpu_device *adev) +{ + u32 i, tcc, tcp_addr_config, num_active_tcc = 0; + u64 chan_steer, patched_chan_steer = 0; + const u32 num_max_tcc = adev->gfx.config.max_texture_channel_caches; + const u32 dis_tcc_mask = + amdgpu_gfx_create_bitmask(num_max_tcc) & + (REG_GET_FIELD(RREG32(mmCGTS_TCC_DISABLE), + CGTS_TCC_DISABLE, TCC_DISABLE) | + REG_GET_FIELD(RREG32(mmCGTS_USER_TCC_DISABLE), + CGTS_USER_TCC_DISABLE, TCC_DISABLE)); + + /* When no TCC is disabled, the golden registers table already has optimal TCC setup */ + if (!dis_tcc_mask) + return; + + /* Each 4-bit nibble contains the index of a TCC used by all TCPs */ + chan_steer = RREG32(mmTCP_CHAN_STEER_LO) | ((u64)RREG32(mmTCP_CHAN_STEER_HI) << 32ull); + + /* Patch the TCP to TCC mapping to skip disabled TCCs */ + for (i = 0; i < num_max_tcc; ++i) { + tcc = (chan_steer >> (u64)(4 * i)) & 0xf; + + if (!((1 << tcc) & dis_tcc_mask)) { + /* Copy enabled TCC indices to the patched register value. */ + patched_chan_steer |= (u64)tcc << (u64)(4 * num_active_tcc); + ++num_active_tcc; + } + } + + WARN_ON(num_active_tcc != num_max_tcc - hweight32(dis_tcc_mask)); + + /* Patch number of TCCs used by TCPs */ + tcp_addr_config = REG_SET_FIELD(RREG32(mmTCP_ADDR_CONFIG), + TCP_ADDR_CONFIG, NUM_TCC_BANKS, + num_active_tcc - 1); + + WREG32(mmTCP_ADDR_CONFIG, tcp_addr_config); + WREG32(mmTCP_CHAN_STEER_HI, upper_32_bits(patched_chan_steer)); + WREG32(mmTCP_CHAN_STEER_LO, lower_32_bits(patched_chan_steer)); +} + static void gfx_v6_0_config_init(struct amdgpu_device *adev) { adev->gfx.config.double_offchip_lds_buf = 0; @@ -1729,6 +1794,7 @@ static void gfx_v6_0_constants_init(struct amdgpu_device *adev) gfx_v6_0_tiling_mode_table_init(adev); gfx_v6_0_setup_rb(adev); + gfx_v6_0_setup_tcc(adev); gfx_v6_0_setup_spi(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index 9fe8d10ab270..cffb1e6bab35 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -802,6 +802,7 @@ static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v2_0_dec_ring_get_rptr, .get_wptr = jpeg_v2_0_dec_ring_get_wptr, .set_wptr = jpeg_v2_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index 20983f126b49..13a6e24c624a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -693,6 +693,7 @@ static const struct amd_ip_funcs jpeg_v2_6_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v2_5_dec_ring_get_rptr, .get_wptr = jpeg_v2_5_dec_ring_get_wptr, .set_wptr = jpeg_v2_5_dec_ring_set_wptr, @@ -724,6 +725,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = { static const struct amdgpu_ring_funcs jpeg_v2_6_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v2_5_dec_ring_get_rptr, .get_wptr = jpeg_v2_5_dec_ring_get_wptr, .set_wptr = jpeg_v2_5_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index 98f5e0622bc5..d0445df39d2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -594,6 +594,7 @@ static const struct amd_ip_funcs jpeg_v3_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v3_0_dec_ring_get_rptr, .get_wptr = jpeg_v3_0_dec_ring_get_wptr, .set_wptr = jpeg_v3_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index 0bd83820dd20..6fd4238a8471 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -759,6 +759,7 @@ static const struct amd_ip_funcs jpeg_v4_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v4_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v4_0_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index 82abe181c730..0c746580de11 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -1219,6 +1219,7 @@ static const struct amd_ip_funcs jpeg_v4_0_3_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v4_0_3_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_3_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_3_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c index 54fd9c800c40..a43582b9c876 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c @@ -804,6 +804,7 @@ static const struct amd_ip_funcs jpeg_v4_0_5_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v4_0_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v4_0_5_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_5_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_5_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c index 46bf15dce2bd..72a4b2d0676f 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c @@ -680,6 +680,7 @@ static const struct amd_ip_funcs jpeg_v5_0_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_0_0_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_0_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c index edecbfe66c79..250316704dfa 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c @@ -884,6 +884,7 @@ static const struct amd_ip_funcs jpeg_v5_0_1_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_0_1_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_1_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_1_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_2.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_2.c index 285c459379c4..7a4ecea6b39a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_2.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_2.c @@ -703,6 +703,7 @@ static const struct amd_ip_funcs jpeg_v5_0_2_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_0_2_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_0_2_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_2_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_2_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c index 1821dced936f..e7546816baba 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_3_0.c @@ -661,6 +661,7 @@ static const struct amd_ip_funcs jpeg_v5_3_0_ip_funcs = { static const struct amdgpu_ring_funcs jpeg_v5_3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_JPEG, .align_mask = 0xf, + .no_user_fence = true, .get_rptr = jpeg_v5_3_0_dec_ring_get_rptr, .get_wptr = jpeg_v5_3_0_dec_ring_get_wptr, .set_wptr = jpeg_v5_3_0_dec_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 0f530bb8a9a3..8ca46e1e474e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1662,17 +1662,8 @@ static int sdma_v6_0_process_fence_irq(struct amdgpu_device *adev, u32 doorbell_offset = entry->src_data[0]; if (adev->enable_mes && doorbell_offset) { - struct amdgpu_usermode_queue *queue; - struct xarray *xa = &adev->userq_doorbell_xa; - unsigned long flags; - doorbell_offset >>= SDMA0_QUEUE0_DOORBELL_OFFSET__OFFSET__SHIFT; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index 9ed817b69a3b..37191e2918d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1594,17 +1594,8 @@ static int sdma_v7_0_process_fence_irq(struct amdgpu_device *adev, u32 doorbell_offset = entry->src_data[0]; if (adev->enable_mes && doorbell_offset) { - struct xarray *xa = &adev->userq_doorbell_xa; - struct amdgpu_usermode_queue *queue; - unsigned long flags; - doorbell_offset >>= SDMA0_QUEUE0_DOORBELL_OFFSET__OFFSET__SHIFT; - - xa_lock_irqsave(xa, flags); - queue = xa_load(xa, doorbell_offset); - if (queue) - amdgpu_userq_fence_driver_process(queue->fence_drv); - xa_unlock_irqrestore(xa, flags); + amdgpu_userq_process_fence_irq(adev, doorbell_offset); } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index fea576a7f397..efb3fde919ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -242,6 +242,10 @@ static void uvd_v3_1_mc_resume(struct amdgpu_device *adev) uint64_t addr; uint32_t size; + /* When the keyselect is already set, don't perturb it. */ + if (RREG32(mmUVD_FW_START)) + return; + /* program the VCPU memory controller bits 0-27 */ addr = (adev->uvd.inst->gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3; size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3; @@ -284,6 +288,12 @@ static int uvd_v3_1_fw_validate(struct amdgpu_device *adev) int i; uint32_t keysel = adev->uvd.keyselect; + if (RREG32(mmUVD_FW_START) & UVD_FW_STATUS__PASS_MASK) { + dev_dbg(adev->dev, "UVD keyselect already set: 0x%x (on CPU: 0x%x)\n", + RREG32(mmUVD_FW_START), adev->uvd.keyselect); + return 0; + } + WREG32(mmUVD_FW_START, keysel); for (i = 0; i < 10; ++i) { diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index e35fae9cdaf6..0442bfcfd384 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -2113,6 +2113,7 @@ static const struct amd_ip_funcs vcn_v2_0_ip_funcs = { static const struct amdgpu_ring_funcs vcn_v2_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v2_0_dec_ring_get_rptr, .get_wptr = vcn_v2_0_dec_ring_get_wptr, @@ -2145,6 +2146,7 @@ static const struct amdgpu_ring_funcs vcn_v2_0_enc_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v2_0_enc_ring_get_rptr, .get_wptr = vcn_v2_0_enc_ring_get_wptr, .set_wptr = vcn_v2_0_enc_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 006a15451197..8b8184fe6764 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -1778,6 +1778,7 @@ static void vcn_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring) static const struct amdgpu_ring_funcs vcn_v2_5_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v2_5_dec_ring_get_rptr, .get_wptr = vcn_v2_5_dec_ring_get_wptr, @@ -1879,6 +1880,7 @@ static const struct amdgpu_ring_funcs vcn_v2_5_enc_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v2_5_enc_ring_get_rptr, .get_wptr = vcn_v2_5_enc_ring_get_wptr, .set_wptr = vcn_v2_5_enc_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 6fb4fcdbba4f..81bba3ec2a93 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1856,6 +1856,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0x3f, .nop = VCN_DEC_SW_CMD_NO_OP, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v3_0_dec_ring_get_rptr, .get_wptr = vcn_v3_0_dec_ring_get_wptr, @@ -1972,6 +1973,7 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { uint32_t offset, size, *create; + uint64_t buf_end; if (msg[0] != RDECODE_MESSAGE_CREATE) continue; @@ -1979,7 +1981,8 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, offset = msg[1]; size = msg[2]; - if (size < 4 || offset + size > end - addr) { + if (size < 4 || check_add_overflow(offset, size, &buf_end) || + buf_end > end - addr) { DRM_ERROR("VCN message buffer exceeds BO bounds!\n"); r = -EINVAL; goto out; @@ -2036,6 +2039,7 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, static const struct amdgpu_ring_funcs vcn_v3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, + .no_user_fence = true, .secure_submission_supported = true, .get_rptr = vcn_v3_0_dec_ring_get_rptr, .get_wptr = vcn_v3_0_dec_ring_get_wptr, @@ -2138,6 +2142,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_enc_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v3_0_enc_ring_get_rptr, .get_wptr = vcn_v3_0_enc_ring_get_wptr, .set_wptr = vcn_v3_0_enc_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 5dec92691f73..ff7269bafae8 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1889,6 +1889,7 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { uint32_t offset, size, *create; + uint64_t buf_end; if (msg[0] != RDECODE_MESSAGE_CREATE) continue; @@ -1896,7 +1897,8 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, offset = msg[1]; size = msg[2]; - if (size < 4 || offset + size > end - addr) { + if (size < 4 || check_add_overflow(offset, size, &buf_end) || + buf_end > end - addr) { DRM_ERROR("VCN message buffer exceeds BO bounds!\n"); r = -EINVAL; goto out; @@ -1994,6 +1996,7 @@ static struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .extra_bytes = sizeof(struct amdgpu_vcn_rb_metadata), .get_rptr = vcn_v4_0_unified_ring_get_rptr, .get_wptr = vcn_v4_0_unified_ring_get_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c index ff3013b97abd..10e8fc2821f3 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -1775,6 +1775,7 @@ static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v4_0_3_unified_ring_get_rptr, .get_wptr = vcn_v4_0_3_unified_ring_get_wptr, .set_wptr = vcn_v4_0_3_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index 1f6a22983c0d..1571cc5a148c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -1483,6 +1483,7 @@ static struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v4_0_5_unified_ring_get_rptr, .get_wptr = vcn_v4_0_5_unified_ring_get_wptr, .set_wptr = vcn_v4_0_5_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index 6109124f852e..d5f49fa33bee 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -1207,6 +1207,7 @@ static const struct amdgpu_ring_funcs vcn_v5_0_0_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v5_0_0_unified_ring_get_rptr, .get_wptr = vcn_v5_0_0_unified_ring_get_wptr, .set_wptr = vcn_v5_0_0_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c index c28c6aff17aa..54fbf8d73ca6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c @@ -1419,6 +1419,7 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v5_0_1_unified_ring_get_rptr, .get_wptr = vcn_v5_0_1_unified_ring_get_wptr, .set_wptr = vcn_v5_0_1_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_2.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_2.c index c3d3cc023058..bbc172db91a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_2.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_2.c @@ -994,6 +994,7 @@ static const struct amdgpu_ring_funcs vcn_v5_0_2_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, .nop = VCN_ENC_CMD_NO_OP, + .no_user_fence = true, .get_rptr = vcn_v5_0_2_unified_ring_get_rptr, .get_wptr = vcn_v5_0_2_unified_ring_get_wptr, .set_wptr = vcn_v5_0_2_unified_ring_set_wptr, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 55ea5145a28a..f829d65a79b4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -25,6 +25,7 @@ #include <linux/err.h> #include <linux/fs.h> #include <linux/file.h> +#include <linux/overflow.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/uaccess.h> @@ -1695,6 +1696,16 @@ static int kfd_ioctl_smi_events(struct file *filep, return kfd_smi_event_open(pdd->dev, &args->anon_fd); } +static int kfd_ioctl_svm_validate(void *kdata, unsigned int usize) +{ + struct kfd_ioctl_svm_args *args = kdata; + size_t expected = struct_size(args, attrs, args->nattr); + + if (expected == SIZE_MAX || usize < expected) + return -EINVAL; + return 0; +} + #if IS_ENABLED(CONFIG_HSA_AMD_SVM) static int kfd_ioctl_set_xnack_mode(struct file *filep, @@ -3209,7 +3220,11 @@ static int kfd_ioctl_create_process(struct file *filep, struct kfd_process *p, v #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ - .cmd_drv = 0, .name = #ioctl} + .validate = NULL, .cmd_drv = 0, .name = #ioctl} + +#define AMDKFD_IOCTL_DEF_V(ioctl, _func, _validate, _flags) \ + [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ + .validate = _validate, .cmd_drv = 0, .name = #ioctl} /** Ioctl table */ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { @@ -3306,7 +3321,8 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_SMI_EVENTS, kfd_ioctl_smi_events, 0), - AMDKFD_IOCTL_DEF(AMDKFD_IOC_SVM, kfd_ioctl_svm, 0), + AMDKFD_IOCTL_DEF_V(AMDKFD_IOC_SVM, kfd_ioctl_svm, + kfd_ioctl_svm_validate, 0), AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_XNACK_MODE, kfd_ioctl_set_xnack_mode, 0), @@ -3431,6 +3447,12 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) memset(kdata, 0, usize); } + if (ioctl->validate) { + retcode = ioctl->validate(kdata, usize); + if (retcode) + goto err_i1; + } + retcode = func(filep, process, kdata); if (cmd & IOC_OUT) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 6e333bfa17d6..163d665a6074 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1047,10 +1047,13 @@ extern struct srcu_struct kfd_processes_srcu; typedef int amdkfd_ioctl_t(struct file *filep, struct kfd_process *p, void *data); +typedef int amdkfd_ioctl_validate_t(void *kdata, unsigned int usize); + struct amdkfd_ioctl_desc { unsigned int cmd; int flags; amdkfd_ioctl_t *func; + amdkfd_ioctl_validate_t *validate; unsigned int cmd_drv; const char *name; }; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index b120fdb0ef77..38085a0a0f58 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1366,6 +1366,12 @@ svm_range_unmap_from_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm, pr_debug("CPU[0x%llx 0x%llx] -> GPU[0x%llx 0x%llx]\n", start, last, gpu_start, gpu_end); + + if (!amdgpu_vm_ready(vm)) { + pr_debug("VM not ready, canceling unmap\n"); + return -EINVAL; + } + return amdgpu_vm_update_range(adev, vm, false, true, true, false, NULL, gpu_start, gpu_end, init_pte_value, 0, 0, NULL, NULL, fence); @@ -1443,6 +1449,11 @@ svm_range_map_to_gpu(struct kfd_process_device *pdd, struct svm_range *prange, pr_debug("svms 0x%p [0x%lx 0x%lx] readonly %d\n", prange->svms, last_start, last_start + npages - 1, readonly); + if (!amdgpu_vm_ready(vm)) { + pr_debug("VM not ready, canceling map\n"); + return -EINVAL; + } + for (i = offset; i < offset + npages; i++) { uint64_t gpu_start; uint64_t gpu_end; 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 e96a12ff2d31..5fc5d5608506 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1903,7 +1903,11 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) goto error; } - init_data.asic_id.chip_family = adev->family; + /* special handling for early revisions of GC 11.5.4 */ + if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 4)) + init_data.asic_id.chip_family = AMDGPU_FAMILY_GC_11_5_4; + else + init_data.asic_id.chip_family = adev->family; init_data.asic_id.pci_revision_id = adev->pdev->revision; init_data.asic_id.hw_internal_rev = adev->external_rev_id; @@ -9404,9 +9408,21 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, if (acrtc_state) { timing = &acrtc_state->stream->timing; - if (amdgpu_ip_version(adev, DCE_HWIP, 0) < - IP_VERSION(3, 5, 0) || - !(adev->flags & AMD_IS_APU)) { + if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= + IP_VERSION(3, 2, 0) && + !(adev->flags & AMD_IS_APU)) { + /* + * DGPUs NV3x and newer that support idle optimizations + * experience intermittent flip-done timeouts on cursor + * updates. Restore 5s offdelay behavior for now. + * + * Discussion on the issue: + * https://lore.kernel.org/amd-gfx/20260217191632.1243826-1-sysdadmin@m1k.cloud/ + */ + config.offdelay_ms = 5000; + config.disable_immediate = false; + } else if (amdgpu_ip_version(adev, DCE_HWIP, 0) < + IP_VERSION(3, 5, 0)) { /* * Older HW and DGPU have issues with instant off; * use a 2 frame offdelay. diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 3b8ae7798a93..a3cb05490dc9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -1032,6 +1032,45 @@ dm_helpers_read_acpi_edid(struct amdgpu_dm_connector *aconnector) return drm_edid_read_custom(connector, dm_helpers_probe_acpi_edid, connector); } +static const struct drm_edid * +dm_helpers_read_vbios_hardcoded_edid(struct dc_link *link, struct amdgpu_dm_connector *aconnector) +{ + struct dc_bios *bios = link->ctx->dc_bios; + struct embedded_panel_info info; + const struct drm_edid *edid; + enum bp_result r; + + if (!dc_is_embedded_signal(link->connector_signal) || + !bios->funcs->get_embedded_panel_info) + return NULL; + + memset(&info, 0, sizeof(info)); + r = bios->funcs->get_embedded_panel_info(bios, &info); + + if (r != BP_RESULT_OK) { + dm_error("Error when reading embedded panel info: %u\n", r); + return NULL; + } + + if (!info.fake_edid || !info.fake_edid_size) { + dm_error("Embedded panel info doesn't contain an EDID\n"); + return NULL; + } + + edid = drm_edid_alloc(info.fake_edid, info.fake_edid_size); + + if (!drm_edid_valid(edid)) { + dm_error("EDID from embedded panel info is invalid\n"); + drm_edid_free(edid); + return NULL; + } + + aconnector->base.display_info.width_mm = info.panel_width_mm; + aconnector->base.display_info.height_mm = info.panel_height_mm; + + return edid; +} + void populate_hdmi_info_from_connector(struct drm_hdmi_info *hdmi, struct dc_edid_caps *edid_caps) { edid_caps->scdc_present = hdmi->scdc.supported; @@ -1052,6 +1091,9 @@ enum dc_edid_status dm_helpers_read_local_edid( if (link->aux_mode) ddc = &aconnector->dm_dp_aux.aux.ddc; + else if (link->ddc_hw_inst == GPIO_DDC_LINE_UNKNOWN && + dc_is_embedded_signal(link->connector_signal)) + ddc = NULL; else ddc = &aconnector->i2c->base; @@ -1065,6 +1107,8 @@ enum dc_edid_status dm_helpers_read_local_edid( drm_edid = dm_helpers_read_acpi_edid(aconnector); if (drm_edid) drm_info(connector->dev, "Using ACPI provided EDID for %s\n", connector->name); + else if (!ddc) + drm_edid = dm_helpers_read_vbios_hardcoded_edid(link, aconnector); else drm_edid = drm_edid_read_ddc(connector, ddc); drm_edid_connector_update(connector, drm_edid); diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index dd362071a6c9..c307f42fe0b9 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -794,11 +794,13 @@ static enum bp_result bios_parser_external_encoder_control( static enum bp_result bios_parser_dac_load_detection( struct dc_bios *dcb, - enum engine_id engine_id) + enum engine_id engine_id, + struct graphics_object_id ext_enc_id) { struct bios_parser *bp = BP_FROM_DCB(dcb); struct dc_context *ctx = dcb->ctx; struct bp_load_detection_parameters bp_params = {0}; + struct bp_external_encoder_control ext_cntl = {0}; enum bp_result bp_result = BP_RESULT_UNSUPPORTED; uint32_t bios_0_scratch; uint32_t device_id_mask = 0; @@ -824,6 +826,13 @@ static enum bp_result bios_parser_dac_load_detection( bp_params.engine_id = engine_id; bp_result = bp->cmd_tbl.dac_load_detection(bp, &bp_params); + } else if (ext_enc_id.id) { + if (!bp->cmd_tbl.external_encoder_control) + return BP_RESULT_UNSUPPORTED; + + ext_cntl.action = EXTERNAL_ENCODER_CONTROL_DAC_LOAD_DETECT; + ext_cntl.encoder_id = ext_enc_id; + bp_result = bp->cmd_tbl.external_encoder_control(bp, &ext_cntl); } if (bp_result != BP_RESULT_OK) @@ -1304,6 +1313,60 @@ static enum bp_result bios_parser_get_embedded_panel_info( return BP_RESULT_FAILURE; } +static enum bp_result get_embedded_panel_extra_info( + struct bios_parser *bp, + struct embedded_panel_info *info, + const uint32_t table_offset) +{ + uint8_t *record = bios_get_image(&bp->base, table_offset, 1); + ATOM_PANEL_RESOLUTION_PATCH_RECORD *panel_res_record; + ATOM_FAKE_EDID_PATCH_RECORD *fake_edid_record; + + while (*record != ATOM_RECORD_END_TYPE) { + switch (*record) { + case LCD_MODE_PATCH_RECORD_MODE_TYPE: + record += sizeof(ATOM_PATCH_RECORD_MODE); + break; + case LCD_RTS_RECORD_TYPE: + record += sizeof(ATOM_LCD_RTS_RECORD); + break; + case LCD_CAP_RECORD_TYPE: + record += sizeof(ATOM_LCD_MODE_CONTROL_CAP); + break; + case LCD_FAKE_EDID_PATCH_RECORD_TYPE: + fake_edid_record = (ATOM_FAKE_EDID_PATCH_RECORD *)record; + if (fake_edid_record->ucFakeEDIDLength) { + if (fake_edid_record->ucFakeEDIDLength == 128) + info->fake_edid_size = + fake_edid_record->ucFakeEDIDLength; + else + info->fake_edid_size = + fake_edid_record->ucFakeEDIDLength * 128; + + info->fake_edid = fake_edid_record->ucFakeEDIDString; + + record += struct_size(fake_edid_record, + ucFakeEDIDString, + info->fake_edid_size); + } else { + /* empty fake edid record must be 3 bytes long */ + record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1; + } + break; + case LCD_PANEL_RESOLUTION_RECORD_TYPE: + panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record; + info->panel_width_mm = panel_res_record->usHSize; + info->panel_height_mm = panel_res_record->usVSize; + record += sizeof(ATOM_PANEL_RESOLUTION_PATCH_RECORD); + break; + default: + return BP_RESULT_BADBIOSTABLE; + } + } + + return BP_RESULT_OK; +} + static enum bp_result get_embedded_panel_info_v1_2( struct bios_parser *bp, struct embedded_panel_info *info) @@ -1420,6 +1483,10 @@ static enum bp_result get_embedded_panel_info_v1_2( if (ATOM_PANEL_MISC_API_ENABLED & lvds->ucLVDS_Misc) info->lcd_timing.misc_info.API_ENABLED = true; + if (lvds->usExtInfoTableOffset) + return get_embedded_panel_extra_info(bp, info, + le16_to_cpu(lvds->usExtInfoTableOffset) + DATA_TABLES(LCD_Info)); + return BP_RESULT_OK; } @@ -1545,6 +1612,10 @@ static enum bp_result get_embedded_panel_info_v1_3( (uint32_t) (ATOM_PANEL_MISC_V13_GREY_LEVEL & lvds->ucLCD_Misc) >> ATOM_PANEL_MISC_V13_GREY_LEVEL_SHIFT; + if (lvds->usExtInfoTableOffset) + return get_embedded_panel_extra_info(bp, info, + le16_to_cpu(lvds->usExtInfoTableOffset) + DATA_TABLES(LCD_Info)); + return BP_RESULT_OK; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 7f55ba09b191..37714d4371fb 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1682,7 +1682,7 @@ struct dc_scratch_space { struct dc_link_training_overrides preferred_training_settings; struct dp_audio_test_data audio_test_data; - uint8_t ddc_hw_inst; + enum gpio_ddc_line ddc_hw_inst; uint8_t hpd_src; diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h index 6f96c5cf39fe..526f71616f94 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h @@ -102,7 +102,8 @@ struct dc_vbios_funcs { struct bp_external_encoder_control *cntl); enum bp_result (*dac_load_detection)( struct dc_bios *bios, - enum engine_id engine_id); + enum engine_id engine_id, + struct graphics_object_id ext_enc_id); enum bp_result (*transmitter_control)( struct dc_bios *bios, struct bp_transmitter_control *cntl); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c index 5f40ae9e3120..e15fd1454d3b 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c @@ -1102,7 +1102,9 @@ void dce110_link_encoder_hw_init( ASSERT(result == BP_RESULT_OK); } - aux_initialize(enc110); + + if (enc110->aux_regs) + aux_initialize(enc110); /* reinitialize HPD. * hpd_initialize() will pass DIG_FE id to HW context. diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.c index 6f2a0d5d963b..62fe5c3b18dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.c @@ -40,8 +40,8 @@ #define FN(reg_name, field_name) \ mcif_wb30->mcif_wb_shift->field_name, mcif_wb30->mcif_wb_mask->field_name -#define MCIF_ADDR(addr) (((unsigned long long)addr & 0xffffffffff) + 0xFE) >> 8 -#define MCIF_ADDR_HIGH(addr) (unsigned long long)addr >> 40 +#define MCIF_ADDR(addr) ((uint32_t)((((unsigned long long)(addr) & 0xffffffffffULL) + 0xFEULL) >> 8)) +#define MCIF_ADDR_HIGH(addr) ((uint32_t)(((unsigned long long)(addr)) >> 40)) /* wbif programming guide: * 1. set up wbif parameter: diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c index a2c46350e44e..95f8b7c7d657 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c @@ -646,6 +646,9 @@ failure: enum gpio_ddc_line dal_ddc_get_line( const struct ddc *ddc) { + if (!ddc) + return GPIO_DDC_LINE_UNKNOWN; + return (enum gpio_ddc_line)dal_gpio_get_enum(ddc->pin_data); } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 5273ca09fe12..f0abbb7c2cb2 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -665,16 +665,45 @@ void dce110_update_info_frame(struct pipe_ctx *pipe_ctx) } static void -dce110_dac_encoder_control(struct pipe_ctx *pipe_ctx, bool enable) +dce110_external_encoder_control(enum bp_external_encoder_control_action action, + struct dc_link *link, + struct dc_crtc_timing *timing) { - struct dc_link *link = pipe_ctx->stream->link; + struct dc *dc = link->ctx->dc; struct dc_bios *bios = link->ctx->dc_bios; - struct bp_encoder_control encoder_control = {0}; + const struct dc_link_settings *link_settings = &link->cur_link_settings; + enum bp_result bp_result = BP_RESULT_OK; + struct bp_external_encoder_control ext_cntl = { + .action = action, + .connector_obj_id = link->link_enc->connector, + .encoder_id = link->ext_enc_id, + .lanes_number = link_settings->lane_count, + .link_rate = link_settings->link_rate, + + /* Use signal type of the real link encoder, ie. DP */ + .signal = link->connector_signal, + + /* We don't know the timing yet when executing the SETUP action, + * so use a reasonably high default value. It seems that ENABLE + * can change the actual pixel clock but doesn't work with higher + * pixel clocks than what SETUP was called with. + */ + .pixel_clock = timing ? timing->pix_clk_100hz / 10 : 300000, + .color_depth = timing ? timing->display_color_depth : COLOR_DEPTH_888, + }; + DC_LOGGER_INIT(dc->ctx); - encoder_control.action = enable ? ENCODER_CONTROL_ENABLE : ENCODER_CONTROL_DISABLE; - encoder_control.engine_id = link->link_enc->analog_engine; - encoder_control.pixel_clock = pipe_ctx->stream->timing.pix_clk_100hz / 10; - bios->funcs->encoder_control(bios, &encoder_control); + bp_result = bios->funcs->external_encoder_control(bios, &ext_cntl); + + if (bp_result != BP_RESULT_OK) + DC_LOG_ERROR("Failed to execute external encoder action: 0x%x\n", action); +} + +static void +dce110_prepare_ddc(struct dc_link *link) +{ + if (link->ext_enc_id.id) + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_DDC_SETUP, link, NULL); } static bool @@ -684,7 +713,8 @@ dce110_dac_load_detect(struct dc_link *link) struct link_encoder *link_enc = link->link_enc; enum bp_result bp_result; - bp_result = bios->funcs->dac_load_detection(bios, link_enc->analog_engine); + bp_result = bios->funcs->dac_load_detection( + bios, link_enc->analog_engine, link->ext_enc_id); return bp_result == BP_RESULT_OK; } @@ -700,7 +730,6 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx) uint32_t early_control = 0; struct timing_generator *tg = pipe_ctx->stream_res.tg; - link_hwss->setup_stream_attribute(pipe_ctx); link_hwss->setup_stream_encoder(pipe_ctx); dc->hwss.update_info_frame(pipe_ctx); @@ -719,8 +748,8 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx) tg->funcs->set_early_control(tg, early_control); - if (dc_is_rgb_signal(pipe_ctx->stream->signal)) - dce110_dac_encoder_control(pipe_ctx, true); + if (link->ext_enc_id.id) + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_ENABLE, link, timing); } static enum bp_result link_transmitter_control( @@ -1219,8 +1248,8 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) link_enc->transmitter - TRANSMITTER_UNIPHY_A); } - if (dc_is_rgb_signal(pipe_ctx->stream->signal)) - dce110_dac_encoder_control(pipe_ctx, false); + if (link->ext_enc_id.id) + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_DISABLE, link, NULL); } void dce110_unblank_stream(struct pipe_ctx *pipe_ctx, @@ -1603,22 +1632,6 @@ static enum dc_status dce110_enable_stream_timing( return DC_OK; } -static void -dce110_select_crtc_source(struct pipe_ctx *pipe_ctx) -{ - struct dc_link *link = pipe_ctx->stream->link; - struct dc_bios *bios = link->ctx->dc_bios; - struct bp_crtc_source_select crtc_source_select = {0}; - enum engine_id engine_id = link->link_enc->preferred_engine; - - if (dc_is_rgb_signal(pipe_ctx->stream->signal)) - engine_id = link->link_enc->analog_engine; - crtc_source_select.controller_id = CONTROLLER_ID_D0 + pipe_ctx->stream_res.tg->inst; - crtc_source_select.color_depth = pipe_ctx->stream->timing.display_color_depth; - crtc_source_select.engine_id = engine_id; - crtc_source_select.sink_signal = pipe_ctx->stream->signal; - bios->funcs->select_crtc_source(bios, &crtc_source_select); -} enum dc_status dce110_apply_single_controller_ctx_to_hw( struct pipe_ctx *pipe_ctx, @@ -1639,10 +1652,6 @@ enum dc_status dce110_apply_single_controller_ctx_to_hw( hws->funcs.disable_stream_gating(dc, pipe_ctx); } - if (pipe_ctx->stream->signal == SIGNAL_TYPE_RGB) { - dce110_select_crtc_source(pipe_ctx); - } - if (pipe_ctx->stream_res.audio != NULL) { struct audio_output audio_output = {0}; @@ -1722,8 +1731,7 @@ enum dc_status dce110_apply_single_controller_ctx_to_hw( pipe_ctx->stream_res.tg->funcs->set_static_screen_control( pipe_ctx->stream_res.tg, event_triggers, 2); - if (!dc_is_virtual_signal(pipe_ctx->stream->signal) && - !dc_is_rgb_signal(pipe_ctx->stream->signal)) + if (!dc_is_virtual_signal(pipe_ctx->stream->signal)) pipe_ctx->stream_res.stream_enc->funcs->dig_connect_to_otg( pipe_ctx->stream_res.stream_enc, pipe_ctx->stream_res.tg->inst); @@ -3376,6 +3384,15 @@ void dce110_enable_tmds_link_output(struct dc_link *link, link->phy_state.symclk_state = SYMCLK_ON_TX_ON; } +static void dce110_enable_analog_link_output( + struct dc_link *link, + uint32_t pix_clk_100hz) +{ + link->link_enc->funcs->enable_analog_output( + link->link_enc, + pix_clk_100hz); +} + void dce110_enable_dp_link_output( struct dc_link *link, const struct link_resource *link_res, @@ -3423,6 +3440,11 @@ void dce110_enable_dp_link_output( } } + if (link->ext_enc_id.id) { + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_INIT, link, NULL); + dce110_external_encoder_control(EXTERNAL_ENCODER_CONTROL_SETUP, link, NULL); + } + if (dc->link_srv->dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) { if (dc->clk_mgr->funcs->notify_link_rate_change) dc->clk_mgr->funcs->notify_link_rate_change(dc->clk_mgr, link); @@ -3513,8 +3535,10 @@ static const struct hw_sequencer_funcs dce110_funcs = { .enable_lvds_link_output = dce110_enable_lvds_link_output, .enable_tmds_link_output = dce110_enable_tmds_link_output, .enable_dp_link_output = dce110_enable_dp_link_output, + .enable_analog_link_output = dce110_enable_analog_link_output, .disable_link_output = dce110_disable_link_output, .dac_load_detect = dce110_dac_load_detect, + .prepare_ddc = dce110_prepare_ddc, }; static const struct hwseq_private_funcs dce110_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c index 7e7682d7dfc8..ae4c4ad05baa 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c @@ -568,7 +568,9 @@ static bool construct_phy(struct dc_link *link, goto ddc_create_fail; } - if (!link->ddc->ddc_pin) { + /* Embedded display connectors such as LVDS may not have DDC. */ + if (!link->ddc->ddc_pin && + !dc_is_embedded_signal(link->connector_signal)) { DC_ERROR("Failed to get I2C info for connector!\n"); goto ddc_create_fail; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c index 6a25dcfcdf17..d2d56a1c4b8b 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c @@ -753,7 +753,8 @@ static struct link_encoder *dce60_link_encoder_create( enc_init_data, &link_enc_feature, &link_enc_regs[link_regs_id], - &link_enc_aux_regs[enc_init_data->channel - 1], + enc_init_data->channel == CHANNEL_ID_UNKNOWN ? + NULL : &link_enc_aux_regs[enc_init_data->channel - 1], enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c index 33be49b3c1b1..6c00497e9a01 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c @@ -760,7 +760,8 @@ static struct link_encoder *dce80_link_encoder_create( enc_init_data, &link_enc_feature, &link_enc_regs[link_regs_id], - &link_enc_aux_regs[enc_init_data->channel - 1], + enc_init_data->channel == CHANNEL_ID_UNKNOWN ? + NULL : &link_enc_aux_regs[enc_init_data->channel - 1], enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ? NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]); return &enc110->base; diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index 38a77fa9b4af..a0f03fb67605 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -153,6 +153,10 @@ struct embedded_panel_info { uint32_t drr_enabled; uint32_t min_drr_refresh_rate; bool realtek_eDPToLVDS; + uint16_t panel_width_mm; + uint16_t panel_height_mm; + uint16_t fake_edid_size; + const uint8_t *fake_edid; }; struct dc_firmware_info { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index 7f386ff0c872..9d8b1227388f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -425,6 +425,7 @@ static int aldebaran_set_default_dpm_table(struct smu_context *smu) dpm_table->dpm_levels[0].enabled = true; dpm_table->dpm_levels[1].value = pptable->GfxclkFmax; dpm_table->dpm_levels[1].enabled = true; + dpm_table->flags |= SMU_DPM_TABLE_FINE_GRAINED; } else { dpm_table->count = 1; dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.gfxclk / 100; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index cd0a23f432ff..0df8c05a7fce 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -1129,6 +1129,7 @@ static int smu_v13_0_6_set_default_dpm_table(struct smu_context *smu) /* gfxclk dpm table setup */ dpm_table = &dpm_context->dpm_tables.gfx_table; dpm_table->clk_type = SMU_GFXCLK; + dpm_table->flags = SMU_DPM_TABLE_FINE_GRAINED; if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_GFXCLK_BIT)) { /* In the case of gfxclk, only fine-grained dpm is honored. * Get min/max values from FW. diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 3d49e58794d2..90c7127beabf 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -1370,7 +1370,7 @@ int smu_cmn_print_dpm_clk_levels(struct smu_context *smu, level_index = 1; } - if (!is_fine_grained) { + if (!is_fine_grained || count == 1) { for (i = 0; i < count; i++) { freq_match = !is_deep_sleep && smu_cmn_freqs_match( diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index c598b99673fc..e7db4e4ea700 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -831,7 +831,7 @@ static void fill_palette_332(struct drm_crtc *crtc, u16 r, u16 g, u16 b, } /** - * drm_crtc_fill_palette_332 - Programs a default palette for R332-like formats + * drm_crtc_fill_palette_332 - Programs a default palette for RGB332-like formats * @crtc: The displaying CRTC * @set_palette: Callback for programming the hardware gamma LUT * diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index 9166c353f131..88808e972cc1 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -172,8 +172,8 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev, } for (i = 0; i < info->num_planes; i++) { - unsigned int width = mode_cmd->width / (i ? info->hsub : 1); - unsigned int height = mode_cmd->height / (i ? info->vsub : 1); + unsigned int width = drm_format_info_plane_width(info, mode_cmd->width, i); + unsigned int height = drm_format_info_plane_height(info, mode_cmd->height, i); unsigned int min_size; objs[i] = drm_gem_object_lookup(file, mode_cmd->handles[i]); diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c index e154cb35f604..6193811ef7be 100644 --- a/drivers/gpu/drm/imagination/pvr_fw_trace.c +++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c @@ -558,6 +558,6 @@ pvr_fw_trace_debugfs_init(struct pvr_device *pvr_dev, struct dentry *dir) &pvr_fw_trace_fops); } - debugfs_create_file("trace_mask", 0600, dir, fw_trace, + debugfs_create_file("trace_mask", 0600, dir, pvr_dev, &pvr_fw_trace_mask_fops); } diff --git a/drivers/gpu/drm/sysfb/ofdrm.c b/drivers/gpu/drm/sysfb/ofdrm.c index d38ba70f4e0d..247cf13c80a0 100644 --- a/drivers/gpu/drm/sysfb/ofdrm.c +++ b/drivers/gpu/drm/sysfb/ofdrm.c @@ -350,6 +350,7 @@ static void ofdrm_pci_release(void *data) struct pci_dev *pcidev = data; pci_disable_device(pcidev); + pci_dev_put(pcidev); } static int ofdrm_device_init_pci(struct ofdrm_device *odev) @@ -375,6 +376,7 @@ static int ofdrm_device_init_pci(struct ofdrm_device *odev) if (ret) { drm_err(dev, "pci_enable_device(%s) failed: %d\n", dev_name(&pcidev->dev), ret); + pci_dev_put(pcidev); return ret; } ret = devm_add_action_or_reset(&pdev->dev, ofdrm_pci_release, pcidev); diff --git a/drivers/gpu/drm/tiny/appletbdrm.c b/drivers/gpu/drm/tiny/appletbdrm.c index 3bae91d7eefe..278bb23fe4c8 100644 --- a/drivers/gpu/drm/tiny/appletbdrm.c +++ b/drivers/gpu/drm/tiny/appletbdrm.c @@ -353,7 +353,7 @@ static int appletbdrm_primary_plane_helper_atomic_check(struct drm_plane *plane, frames_size + sizeof(struct appletbdrm_fb_request_footer), 16); - appletbdrm_state->request = kzalloc(request_size, GFP_KERNEL); + appletbdrm_state->request = kvzalloc(request_size, GFP_KERNEL); if (!appletbdrm_state->request) return -ENOMEM; @@ -543,7 +543,7 @@ static void appletbdrm_primary_plane_destroy_state(struct drm_plane *plane, { struct appletbdrm_plane_state *appletbdrm_state = to_appletbdrm_plane_state(state); - kfree(appletbdrm_state->request); + kvfree(appletbdrm_state->request); kfree(appletbdrm_state->response); __drm_gem_destroy_shadow_plane_state(&appletbdrm_state->base); diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c index 08a0e9480d70..17950fe3a0ec 100644 --- a/drivers/gpu/drm/udl/udl_main.c +++ b/drivers/gpu/drm/udl/udl_main.c @@ -285,13 +285,12 @@ static struct urb *udl_get_urb_locked(struct udl_device *udl, long timeout) return unode->urb; } -#define GET_URB_TIMEOUT HZ struct urb *udl_get_urb(struct udl_device *udl) { struct urb *urb; spin_lock_irq(&udl->urbs.lock); - urb = udl_get_urb_locked(udl, GET_URB_TIMEOUT); + urb = udl_get_urb_locked(udl, HZ * 2); spin_unlock_irq(&udl->urbs.lock); return urb; } diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c index 231e829bd709..1ca073a4ecb2 100644 --- a/drivers/gpu/drm/udl/udl_modeset.c +++ b/drivers/gpu/drm/udl/udl_modeset.c @@ -21,6 +21,7 @@ #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_gem_shmem_helper.h> #include <drm/drm_modeset_helper_vtables.h> +#include <drm/drm_print.h> #include <drm/drm_probe_helper.h> #include <drm/drm_vblank.h> @@ -342,8 +343,10 @@ static void udl_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atom return; urb = udl_get_urb(udl); - if (!urb) + if (!urb) { + drm_err_ratelimited(dev, "get urb failed when enabling crtc\n"); goto out; + } buf = (char *)urb->transfer_buffer; buf = udl_vidreg_lock(buf); diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 49de1c22a469..03242e8b3d87 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -88,6 +88,7 @@ xe-y += xe_bb.o \ xe_irq.o \ xe_late_bind_fw.o \ xe_lrc.o \ + xe_mem_pool.o \ xe_migrate.o \ xe_mmio.o \ xe_mmio_gem.o \ diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index 4ebaa0888a43..9c88ca3ce768 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -583,7 +583,7 @@ #define DISABLE_128B_EVICTION_COMMAND_UDW REG_BIT(36 - 32) #define LSCFE_SAME_ADDRESS_ATOMICS_COALESCING_DISABLE REG_BIT(35 - 32) -#define ROW_CHICKEN5 XE_REG_MCR(0xe7f0) +#define ROW_CHICKEN5 XE_REG_MCR(0xe7f0, XE_REG_OPTION_MASKED) #define CPSS_AWARE_DIS REG_BIT(3) #define SARB_CHICKEN1 XE_REG_MCR(0xe90c) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index a7c2dc7f224c..4075edf97421 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -2322,8 +2322,10 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, } /* XE_BO_FLAG_GGTTx requires XE_BO_FLAG_GGTT also be set */ - if ((flags & XE_BO_FLAG_GGTT_ALL) && !(flags & XE_BO_FLAG_GGTT)) + if ((flags & XE_BO_FLAG_GGTT_ALL) && !(flags & XE_BO_FLAG_GGTT)) { + xe_bo_free(bo); return ERR_PTR(-EINVAL); + } if (flags & (XE_BO_FLAG_VRAM_MASK | XE_BO_FLAG_STOLEN) && !(flags & XE_BO_FLAG_IGNORE_MIN_PAGE_SIZE) && @@ -2342,8 +2344,10 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, alignment = SZ_4K >> PAGE_SHIFT; } - if (type == ttm_bo_type_device && aligned_size != size) + if (type == ttm_bo_type_device && aligned_size != size) { + xe_bo_free(bo); return ERR_PTR(-EINVAL); + } if (!bo) { bo = xe_bo_alloc(); diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index ff8317bfc1ae..9d19940b8fc0 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -18,6 +18,7 @@ #include "xe_ggtt_types.h" struct xe_device; +struct xe_mem_pool_node; struct xe_vm; #define XE_BO_MAX_PLACEMENTS 3 @@ -88,7 +89,7 @@ struct xe_bo { bool ccs_cleared; /** @bb_ccs: BB instructions of CCS read/write. Valid only for VF */ - struct xe_bb *bb_ccs[XE_SRIOV_VF_CCS_CTX_COUNT]; + struct xe_mem_pool_node *bb_ccs[XE_SRIOV_VF_CCS_CTX_COUNT]; /** * @cpu_caching: CPU caching mode. Currently only used for userspace diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 7f9602b3363d..b9828da15897 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -258,6 +258,13 @@ out_unlock: return ERR_PTR(ret); } +/* + * Takes ownership of @storage: on success it is transferred to the returned + * drm_gem_object; on failure it is freed before returning the error. + * This matches the contract of xe_bo_init_locked() which frees @storage on + * its error paths, so callers need not (and must not) free @storage after + * this call. + */ static struct drm_gem_object * xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, struct dma_buf *dma_buf) @@ -271,8 +278,10 @@ xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, int ret = 0; dummy_obj = drm_gpuvm_resv_object_alloc(&xe->drm); - if (!dummy_obj) + if (!dummy_obj) { + xe_bo_free(storage); return ERR_PTR(-ENOMEM); + } dummy_obj->resv = resv; xe_validation_guard(&ctx, &xe->val, &exec, (struct xe_val_flags) {}, ret) { @@ -281,6 +290,7 @@ xe_dma_buf_init_obj(struct drm_device *dev, struct xe_bo *storage, if (ret) break; + /* xe_bo_init_locked() frees storage on error */ bo = xe_bo_init_locked(xe, storage, NULL, resv, NULL, dma_buf->size, 0, /* Will require 1way or 2way for vm_bind */ ttm_bo_type_sg, XE_BO_FLAG_SYSTEM, &exec); @@ -368,12 +378,15 @@ struct drm_gem_object *xe_gem_prime_import(struct drm_device *dev, goto out_err; } - /* Errors here will take care of freeing the bo. */ + /* + * xe_dma_buf_init_obj() takes ownership of bo on both success + * and failure, so we must not touch bo after this call. + */ obj = xe_dma_buf_init_obj(dev, bo, dma_buf); - if (IS_ERR(obj)) + if (IS_ERR(obj)) { + dma_buf_detach(dma_buf, attach); return obj; - - + } get_dma_buf(dma_buf); obj->import_attach = attach; return obj; diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c index c34408cfd292..dddcdd0bb7a3 100644 --- a/drivers/gpu/drm/xe/xe_eu_stall.c +++ b/drivers/gpu/drm/xe/xe_eu_stall.c @@ -869,14 +869,14 @@ static int xe_eu_stall_stream_close(struct inode *inode, struct file *file) struct xe_eu_stall_data_stream *stream = file->private_data; struct xe_gt *gt = stream->gt; - drm_dev_put(>->tile->xe->drm); - mutex_lock(>->eu_stall->stream_lock); xe_eu_stall_disable_locked(stream); xe_eu_stall_data_buf_destroy(stream); xe_eu_stall_stream_free(stream); mutex_unlock(>->eu_stall->stream_lock); + drm_dev_put(>->tile->xe->drm); + return 0; } diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index b287d0e0e60a..071b8c41df43 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -1405,7 +1405,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, if (q->vm && q->hwe->hw_engine_group) { err = xe_hw_engine_group_add_exec_queue(q->hwe->hw_engine_group, q); if (err) - goto put_exec_queue; + goto kill_exec_queue; } } @@ -1416,12 +1416,15 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, /* user id alloc must always be last in ioctl to prevent UAF */ err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL); if (err) - goto kill_exec_queue; + goto del_hw_engine_group; args->exec_queue_id = id; return 0; +del_hw_engine_group: + if (q->vm && q->hwe && q->hwe->hw_engine_group) + xe_hw_engine_group_del_exec_queue(q->hwe->hw_engine_group, q); kill_exec_queue: xe_exec_queue_kill(q); delete_queue_group: @@ -1760,7 +1763,7 @@ void xe_exec_queue_tlb_inval_last_fence_put(struct xe_exec_queue *q, void xe_exec_queue_tlb_inval_last_fence_put_unlocked(struct xe_exec_queue *q, unsigned int type) { - xe_assert(q->vm->xe, type == XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT || + xe_assert(gt_to_xe(q->gt), type == XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT || type == XE_EXEC_QUEUE_TLB_INVAL_PRIMARY_GT); dma_fence_put(q->tlb_inval[type].last_fence); diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c index e5c234f3d795..0d13e357fb43 100644 --- a/drivers/gpu/drm/xe/xe_gsc.c +++ b/drivers/gpu/drm/xe/xe_gsc.c @@ -166,7 +166,7 @@ static int query_compatibility_version(struct xe_gsc *gsc) &rd_offset); if (err) { xe_gt_err(gt, "HuC: invalid GSC reply for version query (err=%d)\n", err); - return err; + goto out_bo; } compat->major = version_query_rd(xe, &bo->vmap, rd_offset, proj_major); diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index a145234f662b..10556156eaad 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -261,22 +261,10 @@ static void guc_submit_sw_fini(struct drm_device *drm, void *arg) static void guc_submit_fini(void *arg) { struct xe_guc *guc = arg; - - /* Forcefully kill any remaining exec queues */ - xe_guc_ct_stop(&guc->ct); - guc_submit_reset_prepare(guc); - xe_guc_softreset(guc); - xe_guc_submit_stop(guc); - xe_uc_fw_sanitize(&guc->fw); - xe_guc_submit_pause_abort(guc); -} - -static void guc_submit_wedged_fini(void *arg) -{ - struct xe_guc *guc = arg; struct xe_exec_queue *q; unsigned long index; + /* Drop any wedged queue refs */ mutex_lock(&guc->submission_state.lock); xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) { if (exec_queue_wedged(q)) { @@ -286,6 +274,14 @@ static void guc_submit_wedged_fini(void *arg) } } mutex_unlock(&guc->submission_state.lock); + + /* Forcefully kill any remaining exec queues */ + xe_guc_ct_stop(&guc->ct); + guc_submit_reset_prepare(guc); + xe_guc_softreset(guc); + xe_guc_submit_stop(guc); + xe_uc_fw_sanitize(&guc->fw); + xe_guc_submit_pause_abort(guc); } static const struct xe_exec_queue_ops guc_exec_queue_ops; @@ -1320,10 +1316,8 @@ static void disable_scheduling_deregister(struct xe_guc *guc, void xe_guc_submit_wedge(struct xe_guc *guc) { struct xe_device *xe = guc_to_xe(guc); - struct xe_gt *gt = guc_to_gt(guc); struct xe_exec_queue *q; unsigned long index; - int err; xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode); @@ -1335,15 +1329,6 @@ void xe_guc_submit_wedge(struct xe_guc *guc) return; if (xe->wedged.mode == XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET) { - err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev, - guc_submit_wedged_fini, guc); - if (err) { - xe_gt_err(gt, "Failed to register clean-up on wedged.mode=%s; " - "Although device is wedged.\n", - xe_wedged_mode_to_string(XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET)); - return; - } - mutex_lock(&guc->submission_state.lock); xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) if (xe_exec_queue_get_unless_zero(q)) diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 9d12a0d2f0b5..c725cde4508d 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -1214,7 +1214,7 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc, if (xe_gt_WARN_ON(lrc->gt, max_len < 3)) return -ENOSPC; - *cmd++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1); + *cmd++ = MI_LOAD_REGISTER_IMM | MI_LRI_LRM_CS_MMIO | MI_LRI_NUM_REGS(1); *cmd++ = CS_DEBUG_MODE2(0).addr; *cmd++ = REG_MASKED_FIELD_ENABLE(INSTRUCTION_STATE_CACHE_INVALIDATE); diff --git a/drivers/gpu/drm/xe/xe_mem_pool.c b/drivers/gpu/drm/xe/xe_mem_pool.c new file mode 100644 index 000000000000..d5e24d6aa88d --- /dev/null +++ b/drivers/gpu/drm/xe/xe_mem_pool.c @@ -0,0 +1,403 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2026 Intel Corporation + */ + +#include <linux/kernel.h> + +#include <drm/drm_managed.h> + +#include "instructions/xe_mi_commands.h" +#include "xe_bo.h" +#include "xe_device_types.h" +#include "xe_map.h" +#include "xe_mem_pool.h" +#include "xe_mem_pool_types.h" +#include "xe_tile_printk.h" + +/** + * struct xe_mem_pool - DRM MM pool for sub-allocating memory from a BO on an + * XE tile. + * + * The XE memory pool is a DRM MM manager that provides sub-allocation of memory + * from a backing buffer object (BO) on a specific XE tile. It is designed to + * manage memory for GPU workloads, allowing for efficient allocation and + * deallocation of memory regions within the BO. + * + * The memory pool maintains a primary BO that is pinned in the GGTT and mapped + * into the CPU address space for direct access. Optionally, it can also maintain + * a shadow BO that can be used for atomic updates to the primary BO's contents. + * + * The API provided by the memory pool allows clients to allocate and free memory + * regions, retrieve GPU and CPU addresses, and synchronize data between the + * primary and shadow BOs as needed. + */ +struct xe_mem_pool { + /** @base: Range allocator over [0, @size) in bytes */ + struct drm_mm base; + /** @bo: Active pool BO (GGTT-pinned, CPU-mapped). */ + struct xe_bo *bo; + /** @shadow: Shadow BO for atomic command updates. */ + struct xe_bo *shadow; + /** @swap_guard: Timeline guard updating @bo and @shadow */ + struct mutex swap_guard; + /** @cpu_addr: CPU virtual address of the active BO. */ + void *cpu_addr; + /** @is_iomem: Indicates if the BO mapping is I/O memory. */ + bool is_iomem; +}; + +static struct xe_mem_pool *node_to_pool(struct xe_mem_pool_node *node) +{ + return container_of(node->sa_node.mm, struct xe_mem_pool, base); +} + +static struct xe_tile *pool_to_tile(struct xe_mem_pool *pool) +{ + return pool->bo->tile; +} + +static void fini_pool_action(struct drm_device *drm, void *arg) +{ + struct xe_mem_pool *pool = arg; + + if (pool->is_iomem) + kvfree(pool->cpu_addr); + + drm_mm_takedown(&pool->base); +} + +static int pool_shadow_init(struct xe_mem_pool *pool) +{ + struct xe_tile *tile = pool->bo->tile; + struct xe_device *xe = tile_to_xe(tile); + struct xe_bo *shadow; + int ret; + + xe_assert(xe, !pool->shadow); + + ret = drmm_mutex_init(&xe->drm, &pool->swap_guard); + if (ret) + return ret; + + if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { + fs_reclaim_acquire(GFP_KERNEL); + might_lock(&pool->swap_guard); + fs_reclaim_release(GFP_KERNEL); + } + shadow = xe_managed_bo_create_pin_map(xe, tile, + xe_bo_size(pool->bo), + XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_GGTT_INVALIDATE | + XE_BO_FLAG_PINNED_NORESTORE); + if (IS_ERR(shadow)) + return PTR_ERR(shadow); + + pool->shadow = shadow; + + return 0; +} + +/** + * xe_mem_pool_init() - Initialize memory pool. + * @tile: the &xe_tile where allocate. + * @size: number of bytes to allocate. + * @guard: the size of the guard region at the end of the BO that is not + * sub-allocated, in bytes. + * @flags: flags to use to create shadow pool. + * + * Initializes a memory pool for sub-allocating memory from a backing BO on the + * specified XE tile. The backing BO is pinned in the GGTT and mapped into + * the CPU address space for direct access. Optionally, a shadow BO can also be + * initialized for atomic updates to the primary BO's contents. + * + * Returns: a pointer to the &xe_mem_pool, or an error pointer on failure. + */ +struct xe_mem_pool *xe_mem_pool_init(struct xe_tile *tile, u32 size, + u32 guard, int flags) +{ + struct xe_device *xe = tile_to_xe(tile); + struct xe_mem_pool *pool; + struct xe_bo *bo; + u32 managed_size; + int ret; + + xe_tile_assert(tile, size > guard); + managed_size = size - guard; + + pool = drmm_kzalloc(&xe->drm, sizeof(*pool), GFP_KERNEL); + if (!pool) + return ERR_PTR(-ENOMEM); + + bo = xe_managed_bo_create_pin_map(xe, tile, size, + XE_BO_FLAG_VRAM_IF_DGFX(tile) | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_GGTT_INVALIDATE | + XE_BO_FLAG_PINNED_NORESTORE); + if (IS_ERR(bo)) { + xe_tile_err(tile, "Failed to prepare %uKiB BO for mem pool (%pe)\n", + size / SZ_1K, bo); + return ERR_CAST(bo); + } + pool->bo = bo; + pool->is_iomem = bo->vmap.is_iomem; + + if (pool->is_iomem) { + pool->cpu_addr = kvzalloc(size, GFP_KERNEL); + if (!pool->cpu_addr) + return ERR_PTR(-ENOMEM); + } else { + pool->cpu_addr = bo->vmap.vaddr; + } + + if (flags & XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY) { + ret = pool_shadow_init(pool); + + if (ret) + goto out_err; + } + + drm_mm_init(&pool->base, 0, managed_size); + ret = drmm_add_action_or_reset(&xe->drm, fini_pool_action, pool); + if (ret) + return ERR_PTR(ret); + + return pool; + +out_err: + if (flags & XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY) + xe_tile_err(tile, + "Failed to initialize shadow BO for mem pool (%d)\n", ret); + if (bo->vmap.is_iomem) + kvfree(pool->cpu_addr); + return ERR_PTR(ret); +} + +/** + * xe_mem_pool_sync() - Copy the entire contents of the main pool to shadow pool. + * @pool: the memory pool containing the primary and shadow BOs. + * + * Copies the entire contents of the primary pool to the shadow pool. This must + * be done after xe_mem_pool_init() with the XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY + * flag to ensure that the shadow pool has the same initial contents as the primary + * pool. After this initial synchronization, clients can choose to synchronize the + * shadow pool with the primary pool on a node basis using + * xe_mem_pool_sync_shadow_locked() as needed. + * + * Return: None. + */ +void xe_mem_pool_sync(struct xe_mem_pool *pool) +{ + struct xe_tile *tile = pool_to_tile(pool); + struct xe_device *xe = tile_to_xe(tile); + + xe_tile_assert(tile, pool->shadow); + + xe_map_memcpy_to(xe, &pool->shadow->vmap, 0, + pool->cpu_addr, xe_bo_size(pool->bo)); +} + +/** + * xe_mem_pool_swap_shadow_locked() - Swap the primary BO with the shadow BO. + * @pool: the memory pool containing the primary and shadow BOs. + * + * Swaps the primary buffer object with the shadow buffer object in the mem + * pool. This allows for atomic updates to the contents of the primary BO + * by first writing to the shadow BO and then swapping it with the primary BO. + * Swap_guard must be held to ensure synchronization with any concurrent swap + * operations. + * + * Return: None. + */ +void xe_mem_pool_swap_shadow_locked(struct xe_mem_pool *pool) +{ + struct xe_tile *tile = pool_to_tile(pool); + + xe_tile_assert(tile, pool->shadow); + lockdep_assert_held(&pool->swap_guard); + + swap(pool->bo, pool->shadow); + if (!pool->bo->vmap.is_iomem) + pool->cpu_addr = pool->bo->vmap.vaddr; +} + +/** + * xe_mem_pool_sync_shadow_locked() - Copy node from primary pool to shadow pool. + * @node: the node allocated in the memory pool. + * + * Copies the specified batch buffer from the primary pool to the shadow pool. + * Swap_guard must be held to ensure synchronization with any concurrent swap + * operations. + * + * Return: None. + */ +void xe_mem_pool_sync_shadow_locked(struct xe_mem_pool_node *node) +{ + struct xe_mem_pool *pool = node_to_pool(node); + struct xe_tile *tile = pool_to_tile(pool); + struct xe_device *xe = tile_to_xe(tile); + struct drm_mm_node *sa_node = &node->sa_node; + + xe_tile_assert(tile, pool->shadow); + lockdep_assert_held(&pool->swap_guard); + + xe_map_memcpy_to(xe, &pool->shadow->vmap, + sa_node->start, + pool->cpu_addr + sa_node->start, + sa_node->size); +} + +/** + * xe_mem_pool_gpu_addr() - Retrieve GPU address of memory pool. + * @pool: the memory pool + * + * Returns: GGTT address of the memory pool. + */ +u64 xe_mem_pool_gpu_addr(struct xe_mem_pool *pool) +{ + return xe_bo_ggtt_addr(pool->bo); +} + +/** + * xe_mem_pool_cpu_addr() - Retrieve CPU address of manager pool. + * @pool: the memory pool + * + * Returns: CPU virtual address of memory pool. + */ +void *xe_mem_pool_cpu_addr(struct xe_mem_pool *pool) +{ + return pool->cpu_addr; +} + +/** + * xe_mem_pool_bo_swap_guard() - Retrieve the mutex used to guard swap + * operations on a memory pool. + * @pool: the memory pool + * + * Returns: Swap guard mutex or NULL if shadow pool is not created. + */ +struct mutex *xe_mem_pool_bo_swap_guard(struct xe_mem_pool *pool) +{ + if (!pool->shadow) + return NULL; + + return &pool->swap_guard; +} + +/** + * xe_mem_pool_bo_flush_write() - Copy the data from the sub-allocation + * to the GPU memory. + * @node: the node allocated in the memory pool to flush. + */ +void xe_mem_pool_bo_flush_write(struct xe_mem_pool_node *node) +{ + struct xe_mem_pool *pool = node_to_pool(node); + struct xe_tile *tile = pool_to_tile(pool); + struct xe_device *xe = tile_to_xe(tile); + struct drm_mm_node *sa_node = &node->sa_node; + + if (!pool->bo->vmap.is_iomem) + return; + + xe_map_memcpy_to(xe, &pool->bo->vmap, sa_node->start, + pool->cpu_addr + sa_node->start, + sa_node->size); +} + +/** + * xe_mem_pool_bo_sync_read() - Copy the data from GPU memory to the + * sub-allocation. + * @node: the node allocated in the memory pool to read back. + */ +void xe_mem_pool_bo_sync_read(struct xe_mem_pool_node *node) +{ + struct xe_mem_pool *pool = node_to_pool(node); + struct xe_tile *tile = pool_to_tile(pool); + struct xe_device *xe = tile_to_xe(tile); + struct drm_mm_node *sa_node = &node->sa_node; + + if (!pool->bo->vmap.is_iomem) + return; + + xe_map_memcpy_from(xe, pool->cpu_addr + sa_node->start, + &pool->bo->vmap, sa_node->start, sa_node->size); +} + +/** + * xe_mem_pool_alloc_node() - Allocate a new node for use with xe_mem_pool. + * + * Returns: node structure or an ERR_PTR(-ENOMEM). + */ +struct xe_mem_pool_node *xe_mem_pool_alloc_node(void) +{ + struct xe_mem_pool_node *node = kzalloc_obj(*node); + + if (!node) + return ERR_PTR(-ENOMEM); + + return node; +} + +/** + * xe_mem_pool_insert_node() - Insert a node into the memory pool. + * @pool: the memory pool to insert into + * @node: the node to insert + * @size: the size of the node to be allocated in bytes. + * + * Inserts a node into the specified memory pool using drm_mm for + * allocation. + * + * Returns: 0 on success or a negative error code on failure. + */ +int xe_mem_pool_insert_node(struct xe_mem_pool *pool, + struct xe_mem_pool_node *node, u32 size) +{ + if (!pool) + return -EINVAL; + + return drm_mm_insert_node(&pool->base, &node->sa_node, size); +} + +/** + * xe_mem_pool_free_node() - Free a node allocated from the memory pool. + * @node: the node to free + * + * Returns: None. + */ +void xe_mem_pool_free_node(struct xe_mem_pool_node *node) +{ + if (!node) + return; + + drm_mm_remove_node(&node->sa_node); + kfree(node); +} + +/** + * xe_mem_pool_node_cpu_addr() - Retrieve CPU address of the node. + * @node: the node allocated in the memory pool + * + * Returns: CPU virtual address of the node. + */ +void *xe_mem_pool_node_cpu_addr(struct xe_mem_pool_node *node) +{ + struct xe_mem_pool *pool = node_to_pool(node); + + return xe_mem_pool_cpu_addr(pool) + node->sa_node.start; +} + +/** + * xe_mem_pool_dump() - Dump the state of the DRM MM manager for debugging. + * @pool: the memory pool info be dumped. + * @p: The DRM printer to use for output. + * + * Only the drm managed region is dumped, not the state of the BOs or any other + * pool information. + * + * Returns: None. + */ +void xe_mem_pool_dump(struct xe_mem_pool *pool, struct drm_printer *p) +{ + drm_mm_print(&pool->base, p); +} diff --git a/drivers/gpu/drm/xe/xe_mem_pool.h b/drivers/gpu/drm/xe/xe_mem_pool.h new file mode 100644 index 000000000000..89cd2555fe91 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_mem_pool.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2026 Intel Corporation + */ +#ifndef _XE_MEM_POOL_H_ +#define _XE_MEM_POOL_H_ + +#include <linux/sizes.h> +#include <linux/types.h> + +#include <drm/drm_mm.h> +#include "xe_mem_pool_types.h" + +struct drm_printer; +struct xe_mem_pool; +struct xe_tile; + +struct xe_mem_pool *xe_mem_pool_init(struct xe_tile *tile, u32 size, + u32 guard, int flags); +void xe_mem_pool_sync(struct xe_mem_pool *pool); +void xe_mem_pool_swap_shadow_locked(struct xe_mem_pool *pool); +void xe_mem_pool_sync_shadow_locked(struct xe_mem_pool_node *node); +u64 xe_mem_pool_gpu_addr(struct xe_mem_pool *pool); +void *xe_mem_pool_cpu_addr(struct xe_mem_pool *pool); +struct mutex *xe_mem_pool_bo_swap_guard(struct xe_mem_pool *pool); +void xe_mem_pool_bo_flush_write(struct xe_mem_pool_node *node); +void xe_mem_pool_bo_sync_read(struct xe_mem_pool_node *node); +struct xe_mem_pool_node *xe_mem_pool_alloc_node(void); +int xe_mem_pool_insert_node(struct xe_mem_pool *pool, + struct xe_mem_pool_node *node, u32 size); +void xe_mem_pool_free_node(struct xe_mem_pool_node *node); +void *xe_mem_pool_node_cpu_addr(struct xe_mem_pool_node *node); +void xe_mem_pool_dump(struct xe_mem_pool *pool, struct drm_printer *p); + +#endif diff --git a/drivers/gpu/drm/xe/xe_mem_pool_types.h b/drivers/gpu/drm/xe/xe_mem_pool_types.h new file mode 100644 index 000000000000..d5e926c93351 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_mem_pool_types.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2026 Intel Corporation + */ + +#ifndef _XE_MEM_POOL_TYPES_H_ +#define _XE_MEM_POOL_TYPES_H_ + +#include <drm/drm_mm.h> + +#define XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY BIT(0) + +/** + * struct xe_mem_pool_node - Sub-range allocations from mem pool. + */ +struct xe_mem_pool_node { + /** @sa_node: drm_mm_node for this allocation. */ + struct drm_mm_node sa_node; +}; + +#endif diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index fc918b4fba54..5fdc89ed5256 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -29,6 +29,7 @@ #include "xe_hw_engine.h" #include "xe_lrc.h" #include "xe_map.h" +#include "xe_mem_pool.h" #include "xe_mocs.h" #include "xe_printk.h" #include "xe_pt.h" @@ -1166,11 +1167,12 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, u32 batch_size, batch_size_allocated; struct xe_device *xe = gt_to_xe(gt); struct xe_res_cursor src_it, ccs_it; + struct xe_mem_pool *bb_pool; struct xe_sriov_vf_ccs_ctx *ctx; - struct xe_sa_manager *bb_pool; u64 size = xe_bo_size(src_bo); - struct xe_bb *bb = NULL; + struct xe_mem_pool_node *bb; u64 src_L0, src_L0_ofs; + struct xe_bb xe_bb_tmp; u32 src_L0_pt; int err; @@ -1208,18 +1210,18 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, size -= src_L0; } - bb = xe_bb_alloc(gt); + bb = xe_mem_pool_alloc_node(); if (IS_ERR(bb)) return PTR_ERR(bb); bb_pool = ctx->mem.ccs_bb_pool; - scoped_guard(mutex, xe_sa_bo_swap_guard(bb_pool)) { - xe_sa_bo_swap_shadow(bb_pool); + scoped_guard(mutex, xe_mem_pool_bo_swap_guard(bb_pool)) { + xe_mem_pool_swap_shadow_locked(bb_pool); - err = xe_bb_init(bb, bb_pool, batch_size); + err = xe_mem_pool_insert_node(bb_pool, bb, batch_size * sizeof(u32)); if (err) { xe_gt_err(gt, "BB allocation failed.\n"); - xe_bb_free(bb, NULL); + kfree(bb); return err; } @@ -1227,6 +1229,7 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, size = xe_bo_size(src_bo); batch_size = 0; + xe_bb_tmp = (struct xe_bb){ .cs = xe_mem_pool_node_cpu_addr(bb), .len = 0 }; /* * Emit PTE and copy commands here. * The CCS copy command can only support limited size. If the size to be @@ -1255,24 +1258,27 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE)); batch_size += EMIT_COPY_CCS_DW; - emit_pte(m, bb, src_L0_pt, false, true, &src_it, src_L0, src); + emit_pte(m, &xe_bb_tmp, src_L0_pt, false, true, &src_it, src_L0, src); - emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src); + emit_pte(m, &xe_bb_tmp, ccs_pt, false, false, &ccs_it, ccs_size, src); - bb->len = emit_flush_invalidate(bb->cs, bb->len, flush_flags); - flush_flags = xe_migrate_ccs_copy(m, bb, src_L0_ofs, src_is_pltt, + xe_bb_tmp.len = emit_flush_invalidate(xe_bb_tmp.cs, xe_bb_tmp.len, + flush_flags); + flush_flags = xe_migrate_ccs_copy(m, &xe_bb_tmp, src_L0_ofs, src_is_pltt, src_L0_ofs, dst_is_pltt, src_L0, ccs_ofs, true); - bb->len = emit_flush_invalidate(bb->cs, bb->len, flush_flags); + xe_bb_tmp.len = emit_flush_invalidate(xe_bb_tmp.cs, xe_bb_tmp.len, + flush_flags); size -= src_L0; } - xe_assert(xe, (batch_size_allocated == bb->len)); + xe_assert(xe, (batch_size_allocated == xe_bb_tmp.len)); + xe_assert(xe, bb->sa_node.size == xe_bb_tmp.len * sizeof(u32)); src_bo->bb_ccs[read_write] = bb; xe_sriov_vf_ccs_rw_update_bb_addr(ctx); - xe_sa_bo_sync_shadow(bb->bo); + xe_mem_pool_sync_shadow_locked(bb); } return 0; @@ -1297,10 +1303,10 @@ int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, void xe_migrate_ccs_rw_copy_clear(struct xe_bo *src_bo, enum xe_sriov_vf_ccs_rw_ctxs read_write) { - struct xe_bb *bb = src_bo->bb_ccs[read_write]; + struct xe_mem_pool_node *bb = src_bo->bb_ccs[read_write]; struct xe_device *xe = xe_bo_device(src_bo); + struct xe_mem_pool *bb_pool; struct xe_sriov_vf_ccs_ctx *ctx; - struct xe_sa_manager *bb_pool; u32 *cs; xe_assert(xe, IS_SRIOV_VF(xe)); @@ -1308,17 +1314,17 @@ void xe_migrate_ccs_rw_copy_clear(struct xe_bo *src_bo, ctx = &xe->sriov.vf.ccs.contexts[read_write]; bb_pool = ctx->mem.ccs_bb_pool; - guard(mutex) (xe_sa_bo_swap_guard(bb_pool)); - xe_sa_bo_swap_shadow(bb_pool); - - cs = xe_sa_bo_cpu_addr(bb->bo); - memset(cs, MI_NOOP, bb->len * sizeof(u32)); - xe_sriov_vf_ccs_rw_update_bb_addr(ctx); + scoped_guard(mutex, xe_mem_pool_bo_swap_guard(bb_pool)) { + xe_mem_pool_swap_shadow_locked(bb_pool); - xe_sa_bo_sync_shadow(bb->bo); + cs = xe_mem_pool_node_cpu_addr(bb); + memset(cs, MI_NOOP, bb->sa_node.size); + xe_sriov_vf_ccs_rw_update_bb_addr(ctx); - xe_bb_free(bb, NULL); - src_bo->bb_ccs[read_write] = NULL; + xe_mem_pool_sync_shadow_locked(bb); + xe_mem_pool_free_node(bb); + src_bo->bb_ccs[read_write] = NULL; + } } /** diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 01673d2b2464..9f98d0334164 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -118,6 +118,7 @@ static const struct xe_graphics_desc graphics_xe2 = { static const struct xe_graphics_desc graphics_xe3p_lpg = { XE2_GFX_FEATURES, + .has_indirect_ring_state = 1, .multi_queue_engine_class_mask = BIT(XE_ENGINE_CLASS_COPY) | BIT(XE_ENGINE_CLASS_COMPUTE), .num_geometry_xecore_fuse_regs = 3, .num_compute_xecore_fuse_regs = 3, diff --git a/drivers/gpu/drm/xe/xe_reg_whitelist.c b/drivers/gpu/drm/xe/xe_reg_whitelist.c index 80577e4b7437..8cc313182968 100644 --- a/drivers/gpu/drm/xe/xe_reg_whitelist.c +++ b/drivers/gpu/drm/xe/xe_reg_whitelist.c @@ -226,7 +226,7 @@ void xe_reg_whitelist_print_entry(struct drm_printer *p, unsigned int indent, } range_start = reg & REG_GENMASK(25, range_bit); - range_end = range_start | REG_GENMASK(range_bit, 0); + range_end = range_start | REG_GENMASK(range_bit - 1, 0); switch (val & RING_FORCE_TO_NONPRIV_ACCESS_MASK) { case RING_FORCE_TO_NONPRIV_ACCESS_RW: diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c index db023fb66a27..09b99fb2608b 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c @@ -14,9 +14,9 @@ #include "xe_guc.h" #include "xe_guc_submit.h" #include "xe_lrc.h" +#include "xe_mem_pool.h" #include "xe_migrate.h" #include "xe_pm.h" -#include "xe_sa.h" #include "xe_sriov_printk.h" #include "xe_sriov_vf.h" #include "xe_sriov_vf_ccs.h" @@ -141,43 +141,47 @@ static u64 get_ccs_bb_pool_size(struct xe_device *xe) static int alloc_bb_pool(struct xe_tile *tile, struct xe_sriov_vf_ccs_ctx *ctx) { + struct xe_mem_pool *pool; struct xe_device *xe = tile_to_xe(tile); - struct xe_sa_manager *sa_manager; + u32 *pool_cpu_addr, *last_dw_addr; u64 bb_pool_size; - int offset, err; + int err; bb_pool_size = get_ccs_bb_pool_size(xe); xe_sriov_info(xe, "Allocating %s CCS BB pool size = %lldMB\n", ctx->ctx_id ? "Restore" : "Save", bb_pool_size / SZ_1M); - sa_manager = __xe_sa_bo_manager_init(tile, bb_pool_size, SZ_4K, SZ_16, - XE_SA_BO_MANAGER_FLAG_SHADOW); - - if (IS_ERR(sa_manager)) { - xe_sriov_err(xe, "Suballocator init failed with error: %pe\n", - sa_manager); - err = PTR_ERR(sa_manager); + pool = xe_mem_pool_init(tile, bb_pool_size, sizeof(u32), + XE_MEM_POOL_BO_FLAG_INIT_SHADOW_COPY); + if (IS_ERR(pool)) { + xe_sriov_err(xe, "xe_mem_pool_init failed with error: %pe\n", + pool); + err = PTR_ERR(pool); return err; } - offset = 0; - xe_map_memset(xe, &sa_manager->bo->vmap, offset, MI_NOOP, - bb_pool_size); - xe_map_memset(xe, &sa_manager->shadow->vmap, offset, MI_NOOP, - bb_pool_size); + pool_cpu_addr = xe_mem_pool_cpu_addr(pool); + memset(pool_cpu_addr, 0, bb_pool_size); - offset = bb_pool_size - sizeof(u32); - xe_map_wr(xe, &sa_manager->bo->vmap, offset, u32, MI_BATCH_BUFFER_END); - xe_map_wr(xe, &sa_manager->shadow->vmap, offset, u32, MI_BATCH_BUFFER_END); + last_dw_addr = pool_cpu_addr + (bb_pool_size / sizeof(u32)) - 1; + *last_dw_addr = MI_BATCH_BUFFER_END; - ctx->mem.ccs_bb_pool = sa_manager; + /** + * Sync the main copy and shadow copy so that the shadow copy is + * replica of main copy. We sync only BBs after init part. So, we + * need to make sure the main pool and shadow copy are in sync after + * this point. This is needed as GuC may read the BB commands from + * shadow copy. + */ + xe_mem_pool_sync(pool); + ctx->mem.ccs_bb_pool = pool; return 0; } static void ccs_rw_update_ring(struct xe_sriov_vf_ccs_ctx *ctx) { - u64 addr = xe_sa_manager_gpu_addr(ctx->mem.ccs_bb_pool); + u64 addr = xe_mem_pool_gpu_addr(ctx->mem.ccs_bb_pool); struct xe_lrc *lrc = xe_exec_queue_lrc(ctx->mig_q); u32 dw[10], i = 0; @@ -388,7 +392,7 @@ err_ret: #define XE_SRIOV_VF_CCS_RW_BB_ADDR_OFFSET (2 * sizeof(u32)) void xe_sriov_vf_ccs_rw_update_bb_addr(struct xe_sriov_vf_ccs_ctx *ctx) { - u64 addr = xe_sa_manager_gpu_addr(ctx->mem.ccs_bb_pool); + u64 addr = xe_mem_pool_gpu_addr(ctx->mem.ccs_bb_pool); struct xe_lrc *lrc = xe_exec_queue_lrc(ctx->mig_q); struct xe_device *xe = gt_to_xe(ctx->mig_q->gt); @@ -412,8 +416,8 @@ int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo) struct xe_device *xe = xe_bo_device(bo); enum xe_sriov_vf_ccs_rw_ctxs ctx_id; struct xe_sriov_vf_ccs_ctx *ctx; + struct xe_mem_pool_node *bb; struct xe_tile *tile; - struct xe_bb *bb; int err = 0; xe_assert(xe, IS_VF_CCS_READY(xe)); @@ -445,7 +449,7 @@ int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo) { struct xe_device *xe = xe_bo_device(bo); enum xe_sriov_vf_ccs_rw_ctxs ctx_id; - struct xe_bb *bb; + struct xe_mem_pool_node *bb; xe_assert(xe, IS_VF_CCS_READY(xe)); @@ -471,8 +475,8 @@ int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo) */ void xe_sriov_vf_ccs_print(struct xe_device *xe, struct drm_printer *p) { - struct xe_sa_manager *bb_pool; enum xe_sriov_vf_ccs_rw_ctxs ctx_id; + struct xe_mem_pool *bb_pool; if (!IS_VF_CCS_READY(xe)) return; @@ -485,7 +489,7 @@ void xe_sriov_vf_ccs_print(struct xe_device *xe, struct drm_printer *p) drm_printf(p, "ccs %s bb suballoc info\n", ctx_id ? "write" : "read"); drm_printf(p, "-------------------------\n"); - drm_suballoc_dump_debug_info(&bb_pool->base, p, xe_sa_manager_gpu_addr(bb_pool)); + xe_mem_pool_dump(bb_pool, p); drm_puts(p, "\n"); } } diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h index 22c499943d2a..6fc8f97ef3f4 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h @@ -17,9 +17,6 @@ enum xe_sriov_vf_ccs_rw_ctxs { XE_SRIOV_VF_CCS_CTX_COUNT }; -struct xe_migrate; -struct xe_sa_manager; - /** * struct xe_sriov_vf_ccs_ctx - VF CCS migration context data. */ @@ -33,7 +30,7 @@ struct xe_sriov_vf_ccs_ctx { /** @mem: memory data */ struct { /** @mem.ccs_bb_pool: Pool from which batch buffers are allocated. */ - struct xe_sa_manager *ccs_bb_pool; + struct xe_mem_pool *ccs_bb_pool; } mem; }; diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tuning.c index f8de6a4bf189..0b78ec2bc6a4 100644 --- a/drivers/gpu/drm/xe/xe_tuning.c +++ b/drivers/gpu/drm/xe/xe_tuning.c @@ -97,7 +97,7 @@ static const struct xe_rtp_entry_sr gt_tunings[] = { { XE_RTP_NAME("Tuning: Set STLB Bank Hash Mode to 4KB"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3510, XE_RTP_END_VERSION_UNDEFINED), IS_INTEGRATED), - XE_RTP_ACTIONS(FIELD_SET(XEHP_GAMSTLB_CTRL, BANK_HASH_MODE, + XE_RTP_ACTIONS(FIELD_SET(GAMSTLB_CTRL, BANK_HASH_MODE, BANK_HASH_4KB_MODE)) }, }; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 56e2db50bb36..a717a2b8dea3 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -3658,6 +3658,8 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm, op == DRM_XE_VM_BIND_OP_MAP_USERPTR) || XE_IOCTL_DBG(xe, coh_mode == XE_COH_NONE && op == DRM_XE_VM_BIND_OP_MAP_USERPTR) || + XE_IOCTL_DBG(xe, !IS_DGFX(xe) && coh_mode == XE_COH_NONE && + is_cpu_addr_mirror) || XE_IOCTL_DBG(xe, xe_device_is_l2_flush_optimized(xe) && (op == DRM_XE_VM_BIND_OP_MAP_USERPTR || is_cpu_addr_mirror) && @@ -4156,7 +4158,8 @@ int xe_vm_get_property_ioctl(struct drm_device *drm, void *data, int ret = 0; if (XE_IOCTL_DBG(xe, (args->reserved[0] || args->reserved[1] || - args->reserved[2]))) + args->reserved[2] || args->extensions || + args->pad))) return -EINVAL; vm = xe_vm_lookup(xef, args->vm_id); diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c index 66f00d3f5c07..c78906dea82b 100644 --- a/drivers/gpu/drm/xe/xe_vm_madvise.c +++ b/drivers/gpu/drm/xe/xe_vm_madvise.c @@ -621,6 +621,45 @@ static int xe_madvise_purgeable_retained_to_user(const struct xe_madvise_details return 0; } +static bool check_pat_args_are_sane(struct xe_device *xe, + struct xe_vmas_in_madvise_range *madvise_range, + u16 pat_index) +{ + u16 coh_mode = xe_pat_index_get_coh_mode(xe, pat_index); + int i; + + /* + * Using coh_none with CPU cached buffers is not allowed on iGPU. + * On iGPU the GPU shares the LLC with the CPU, so with coh_none + * the GPU bypasses CPU caches and reads directly from DRAM, + * potentially seeing stale sensitive data from previously freed + * pages. On dGPU this restriction does not apply, because the + * platform does not provide a non-coherent system memory access + * path that would violate the DMA coherency contract. + */ + if (coh_mode != XE_COH_NONE || IS_DGFX(xe)) + return true; + + for (i = 0; i < madvise_range->num_vmas; i++) { + struct xe_vma *vma = madvise_range->vmas[i]; + struct xe_bo *bo = xe_vma_bo(vma); + + if (bo) { + /* BO with WB caching + COH_NONE is not allowed */ + if (XE_IOCTL_DBG(xe, bo->cpu_caching == DRM_XE_GEM_CPU_CACHING_WB)) + return false; + /* Imported dma-buf without caching info, assume cached */ + if (XE_IOCTL_DBG(xe, !bo->cpu_caching)) + return false; + } else if (XE_IOCTL_DBG(xe, xe_vma_is_cpu_addr_mirror(vma) || + xe_vma_is_userptr(vma))) + /* System memory (userptr/SVM) is always CPU cached */ + return false; + } + + return true; +} + static bool check_bo_args_are_sane(struct xe_vm *vm, struct xe_vma **vmas, int num_vmas, u32 atomic_val) { @@ -750,6 +789,14 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil } } + if (args->type == DRM_XE_MEM_RANGE_ATTR_PAT) { + if (!check_pat_args_are_sane(xe, &madvise_range, + args->pat_index.val)) { + err = -EINVAL; + goto free_vmas; + } + } + if (madvise_range.has_bo_vmas) { if (args->type == DRM_XE_MEM_RANGE_ATTR_ATOMIC) { if (!check_bo_args_are_sane(vm, madvise_range.vmas, diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index 546296f0220b..4b1cbced06be 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -743,14 +743,6 @@ static const struct xe_rtp_entry_sr lrc_was[] = { XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(WM_CHICKEN3, HIZ_PLANE_COMPRESSION_DIS)) }, - { XE_RTP_NAME("14019988906"), - XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), ENGINE_CLASS(RENDER)), - XE_RTP_ACTIONS(SET(XEHP_PSS_CHICKEN, FLSH_IGNORES_PSD)) - }, - { XE_RTP_NAME("14019877138"), - XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), ENGINE_CLASS(RENDER)), - XE_RTP_ACTIONS(SET(XEHP_PSS_CHICKEN, FD_END_COLLECT)) - }, { XE_RTP_NAME("14021490052"), XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(FF_MODE, diff --git a/drivers/mailbox/cix-mailbox.c b/drivers/mailbox/cix-mailbox.c index 443620e8ae37..43c76cdab24a 100644 --- a/drivers/mailbox/cix-mailbox.c +++ b/drivers/mailbox/cix-mailbox.c @@ -12,8 +12,6 @@ #include <linux/module.h> #include <linux/platform_device.h> -#include "mailbox.h" - /* * The maximum transmission size is 32 words or 128 bytes. */ @@ -405,7 +403,7 @@ static int cix_mbox_startup(struct mbox_chan *chan) int index = cp->index, ret; u32 val; - ret = request_irq(priv->irq, cix_mbox_isr, 0, + ret = request_irq(priv->irq, cix_mbox_isr, IRQF_NO_SUSPEND, dev_name(priv->dev), chan); if (ret) { dev_err(priv->dev, "Unable to acquire IRQ %d\n", priv->irq); @@ -415,7 +413,7 @@ static int cix_mbox_startup(struct mbox_chan *chan) switch (cp->type) { case CIX_MBOX_TYPE_DB: /* Overwrite txdone_method for DB channel */ - chan->txdone_method = TXDONE_BY_ACK; + chan->txdone_method = MBOX_TXDONE_BY_ACK; fallthrough; case CIX_MBOX_TYPE_REG: if (priv->dir == CIX_MBOX_TX) { diff --git a/drivers/mailbox/exynos-mailbox.c b/drivers/mailbox/exynos-mailbox.c index 5f2d3b81c1db..d2355b128ba4 100644 --- a/drivers/mailbox/exynos-mailbox.c +++ b/drivers/mailbox/exynos-mailbox.c @@ -99,7 +99,6 @@ static int exynos_mbox_probe(struct platform_device *pdev) struct mbox_controller *mbox; struct mbox_chan *chans; struct clk *pclk; - int i; exynos_mbox = devm_kzalloc(dev, sizeof(*exynos_mbox), GFP_KERNEL); if (!exynos_mbox) @@ -129,9 +128,6 @@ static int exynos_mbox_probe(struct platform_device *pdev) mbox->ops = &exynos_mbox_chan_ops; mbox->of_xlate = exynos_mbox_of_xlate; - for (i = 0; i < EXYNOS_MBOX_CHAN_COUNT; i++) - chans[i].mbox = mbox; - exynos_mbox->mbox = mbox; platform_set_drvdata(pdev, exynos_mbox); diff --git a/drivers/mailbox/hi3660-mailbox.c b/drivers/mailbox/hi3660-mailbox.c index 17c29e960fbf..9b727a2b54a5 100644 --- a/drivers/mailbox/hi3660-mailbox.c +++ b/drivers/mailbox/hi3660-mailbox.c @@ -15,8 +15,6 @@ #include <linux/platform_device.h> #include <linux/slab.h> -#include "mailbox.h" - #define MBOX_CHAN_MAX 32 #define MBOX_RX 0x0 diff --git a/drivers/mailbox/hi6220-mailbox.c b/drivers/mailbox/hi6220-mailbox.c index f77741ce42e7..69d15b6283e9 100644 --- a/drivers/mailbox/hi6220-mailbox.c +++ b/drivers/mailbox/hi6220-mailbox.c @@ -79,12 +79,12 @@ struct hi6220_mbox { /* region for mailbox */ void __iomem *base; - unsigned int chan_num; - struct hi6220_mbox_chan *mchan; - void *irq_map_chan[MBOX_CHAN_MAX]; struct mbox_chan *chan; struct mbox_controller controller; + + unsigned int chan_num; + struct hi6220_mbox_chan mchan[] __counted_by(chan_num); }; static void mbox_set_state(struct hi6220_mbox *mbox, @@ -267,16 +267,12 @@ static int hi6220_mbox_probe(struct platform_device *pdev) struct hi6220_mbox *mbox; int i, err; - mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL); + mbox = devm_kzalloc(dev, struct_size(mbox, mchan, MBOX_CHAN_MAX), GFP_KERNEL); if (!mbox) return -ENOMEM; - mbox->dev = dev; mbox->chan_num = MBOX_CHAN_MAX; - mbox->mchan = devm_kcalloc(dev, - mbox->chan_num, sizeof(*mbox->mchan), GFP_KERNEL); - if (!mbox->mchan) - return -ENOMEM; + mbox->dev = dev; mbox->chan = devm_kcalloc(dev, mbox->chan_num, sizeof(*mbox->chan), GFP_KERNEL); diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c index 003f9236c35e..246a9a9e3952 100644 --- a/drivers/mailbox/imx-mailbox.c +++ b/drivers/mailbox/imx-mailbox.c @@ -23,8 +23,6 @@ #include <linux/slab.h> #include <linux/workqueue.h> -#include "mailbox.h" - #define IMX_MU_CHANS 24 /* TX0/RX0/RXDB[0-3] */ #define IMX_MU_SCU_CHANS 6 @@ -734,7 +732,7 @@ static struct mbox_chan * imx_mu_xlate(struct mbox_controller *mbox, p_chan = &mbox->chans[chan]; if (type == IMX_MU_TYPE_TXDB_V2) - p_chan->txdone_method = TXDONE_BY_ACK; + p_chan->txdone_method = MBOX_TXDONE_BY_ACK; return p_chan; } diff --git a/drivers/mailbox/mailbox-sti.c b/drivers/mailbox/mailbox-sti.c index b4b5bdd503cf..b6c9ecbbc8ec 100644 --- a/drivers/mailbox/mailbox-sti.c +++ b/drivers/mailbox/mailbox-sti.c @@ -21,8 +21,6 @@ #include <linux/property.h> #include <linux/slab.h> -#include "mailbox.h" - #define STI_MBOX_INST_MAX 4 /* RAM saving: Max supported instances */ #define STI_MBOX_CHAN_MAX 20 /* RAM saving: Max supported channels */ diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 3a28ab5c42e5..7b6ef033e77a 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -28,8 +28,6 @@ #define MBOX_HEXDUMP_MAX_LEN (MBOX_HEXDUMP_LINE_LEN * \ (MBOX_MAX_MSG_LEN / MBOX_BYTES_PER_LINE)) -static bool mbox_data_ready; - struct mbox_test_device { struct device *dev; void __iomem *tx_mmio; @@ -42,6 +40,7 @@ struct mbox_test_device { spinlock_t lock; struct mutex mutex; wait_queue_head_t waitq; + bool data_ready; struct fasync_struct *async_queue; struct dentry *root_debugfs_dir; }; @@ -162,7 +161,7 @@ static bool mbox_test_message_data_ready(struct mbox_test_device *tdev) unsigned long flags; spin_lock_irqsave(&tdev->lock, flags); - data_ready = mbox_data_ready; + data_ready = tdev->data_ready; spin_unlock_irqrestore(&tdev->lock, flags); return data_ready; @@ -227,7 +226,7 @@ static ssize_t mbox_test_message_read(struct file *filp, char __user *userbuf, *(touser + l) = '\0'; memset(tdev->rx_buffer, 0, MBOX_MAX_MSG_LEN); - mbox_data_ready = false; + tdev->data_ready = false; spin_unlock_irqrestore(&tdev->lock, flags); @@ -297,7 +296,7 @@ static void mbox_test_receive_message(struct mbox_client *client, void *message) message, MBOX_MAX_MSG_LEN); memcpy(tdev->rx_buffer, message, MBOX_MAX_MSG_LEN); } - mbox_data_ready = true; + tdev->data_ready = true; spin_unlock_irqrestore(&tdev->lock, flags); wake_up_interruptible(&tdev->waitq); @@ -336,7 +335,7 @@ mbox_test_request_channel(struct platform_device *pdev, const char *name) client = devm_kzalloc(&pdev->dev, sizeof(*client), GFP_KERNEL); if (!client) - return ERR_PTR(-ENOMEM); + return NULL; client->dev = &pdev->dev; client->rx_callback = mbox_test_receive_message; @@ -355,67 +354,80 @@ mbox_test_request_channel(struct platform_device *pdev, const char *name) return channel; } +static void __iomem *mbox_test_ioremap(struct platform_device *pdev, unsigned int res_num) +{ + struct resource *res; + void __iomem *mmio; + + res = platform_get_resource(pdev, IORESOURCE_MEM, res_num); + if (!res) + return NULL; + + mmio = devm_ioremap_resource(&pdev->dev, res); + if (PTR_ERR(mmio) == -EBUSY) { + dev_info(&pdev->dev, "trying workaround with plain ioremap\n"); + return devm_ioremap(&pdev->dev, res->start, resource_size(res)); + } + + return IS_ERR(mmio) ? NULL : mmio; +} + static int mbox_test_probe(struct platform_device *pdev) { struct mbox_test_device *tdev; - struct resource *res; - resource_size_t size; int ret; tdev = devm_kzalloc(&pdev->dev, sizeof(*tdev), GFP_KERNEL); if (!tdev) return -ENOMEM; + tdev->dev = &pdev->dev; + spin_lock_init(&tdev->lock); + mutex_init(&tdev->mutex); + init_waitqueue_head(&tdev->waitq); + platform_set_drvdata(pdev, tdev); + /* It's okay for MMIO to be NULL */ - tdev->tx_mmio = devm_platform_get_and_ioremap_resource(pdev, 0, &res); - if (PTR_ERR(tdev->tx_mmio) == -EBUSY) { - /* if reserved area in SRAM, try just ioremap */ - size = resource_size(res); - tdev->tx_mmio = devm_ioremap(&pdev->dev, res->start, size); - } else if (IS_ERR(tdev->tx_mmio)) { - tdev->tx_mmio = NULL; - } + tdev->tx_mmio = mbox_test_ioremap(pdev, 0); /* If specified, second reg entry is Rx MMIO */ - tdev->rx_mmio = devm_platform_get_and_ioremap_resource(pdev, 1, &res); - if (PTR_ERR(tdev->rx_mmio) == -EBUSY) { - size = resource_size(res); - tdev->rx_mmio = devm_ioremap(&pdev->dev, res->start, size); - } else if (IS_ERR(tdev->rx_mmio)) { + tdev->rx_mmio = mbox_test_ioremap(pdev, 1); + if (!tdev->rx_mmio) tdev->rx_mmio = tdev->tx_mmio; - } tdev->tx_channel = mbox_test_request_channel(pdev, "tx"); tdev->rx_channel = mbox_test_request_channel(pdev, "rx"); - if (IS_ERR_OR_NULL(tdev->tx_channel) && IS_ERR_OR_NULL(tdev->rx_channel)) + if (!tdev->tx_channel && !tdev->rx_channel) return -EPROBE_DEFER; /* If Rx is not specified but has Rx MMIO, then Rx = Tx */ if (!tdev->rx_channel && (tdev->rx_mmio != tdev->tx_mmio)) tdev->rx_channel = tdev->tx_channel; - tdev->dev = &pdev->dev; - platform_set_drvdata(pdev, tdev); - - spin_lock_init(&tdev->lock); - mutex_init(&tdev->mutex); - if (tdev->rx_channel) { tdev->rx_buffer = devm_kzalloc(&pdev->dev, MBOX_MAX_MSG_LEN, GFP_KERNEL); - if (!tdev->rx_buffer) - return -ENOMEM; + if (!tdev->rx_buffer) { + ret = -ENOMEM; + goto err_free_chans; + } } ret = mbox_test_add_debugfs(pdev, tdev); if (ret) - return ret; + goto err_free_chans; - init_waitqueue_head(&tdev->waitq); dev_info(&pdev->dev, "Successfully registered\n"); return 0; + +err_free_chans: + if (tdev->tx_channel) + mbox_free_channel(tdev->tx_channel); + if (tdev->rx_channel && tdev->rx_channel != tdev->tx_channel) + mbox_free_channel(tdev->rx_channel); + return ret; } static void mbox_test_remove(struct platform_device *pdev) @@ -426,7 +438,7 @@ static void mbox_test_remove(struct platform_device *pdev) if (tdev->tx_channel) mbox_free_channel(tdev->tx_channel); - if (tdev->rx_channel) + if (tdev->rx_channel && tdev->rx_channel != tdev->tx_channel) mbox_free_channel(tdev->rx_channel); } diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 617ba505691d..bbc9fd75a95f 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -18,8 +18,6 @@ #include <linux/property.h> #include <linux/spinlock.h> -#include "mailbox.h" - static LIST_HEAD(mbox_cons); static DEFINE_MUTEX(con_mutex); @@ -52,7 +50,7 @@ static void msg_submit(struct mbox_chan *chan) int err = -EBUSY; scoped_guard(spinlock_irqsave, &chan->lock) { - if (!chan->msg_count || chan->active_req) + if (!chan->msg_count || chan->active_req != MBOX_NO_MSG) break; count = chan->msg_count; @@ -74,7 +72,7 @@ static void msg_submit(struct mbox_chan *chan) } } - if (!err && (chan->txdone_method & TXDONE_BY_POLL)) { + if (!err && (chan->txdone_method & MBOX_TXDONE_BY_POLL)) { /* kick start the timer immediately to avoid delays */ scoped_guard(spinlock_irqsave, &chan->mbox->poll_hrt_lock) hrtimer_start(&chan->mbox->poll_hrt, 0, HRTIMER_MODE_REL); @@ -87,13 +85,13 @@ static void tx_tick(struct mbox_chan *chan, int r) scoped_guard(spinlock_irqsave, &chan->lock) { mssg = chan->active_req; - chan->active_req = NULL; + chan->active_req = MBOX_NO_MSG; } /* Submit next message */ msg_submit(chan); - if (!mssg) + if (mssg == MBOX_NO_MSG) return; /* Notify the client */ @@ -114,7 +112,7 @@ static enum hrtimer_restart txdone_hrtimer(struct hrtimer *hrtimer) for (i = 0; i < mbox->num_chans; i++) { struct mbox_chan *chan = &mbox->chans[i]; - if (chan->active_req && chan->cl) { + if (chan->active_req != MBOX_NO_MSG && chan->cl) { txdone = chan->mbox->ops->last_tx_done(chan); if (txdone) tx_tick(chan, 0); @@ -164,7 +162,7 @@ EXPORT_SYMBOL_GPL(mbox_chan_received_data); */ void mbox_chan_txdone(struct mbox_chan *chan, int r) { - if (unlikely(!(chan->txdone_method & TXDONE_BY_IRQ))) { + if (unlikely(!(chan->txdone_method & MBOX_TXDONE_BY_IRQ))) { dev_err(chan->mbox->dev, "Controller can't run the TX ticker\n"); return; @@ -185,7 +183,7 @@ EXPORT_SYMBOL_GPL(mbox_chan_txdone); */ void mbox_client_txdone(struct mbox_chan *chan, int r) { - if (unlikely(!(chan->txdone_method & TXDONE_BY_ACK))) { + if (unlikely(!(chan->txdone_method & MBOX_TXDONE_BY_ACK))) { dev_err(chan->mbox->dev, "Client can't run the TX ticker\n"); return; } @@ -219,6 +217,29 @@ bool mbox_client_peek_data(struct mbox_chan *chan) EXPORT_SYMBOL_GPL(mbox_client_peek_data); /** + * mbox_chan_tx_slots_available - Query the number of available TX queue slots. + * @chan: Mailbox channel to query. + * + * Clients may call this to check how many messages can be queued via + * mbox_send_message() before the channel's TX queue is full. This helps + * clients avoid the -ENOBUFS error without needing to increase + * MBOX_TX_QUEUE_LEN. + * This can be called from atomic context. + * + * Return: Number of available slots in the channel's TX queue. + */ +unsigned int mbox_chan_tx_slots_available(struct mbox_chan *chan) +{ + unsigned int ret; + + guard(spinlock_irqsave)(&chan->lock); + ret = MBOX_TX_QUEUE_LEN - chan->msg_count; + + return ret; +} +EXPORT_SYMBOL_GPL(mbox_chan_tx_slots_available); + +/** * mbox_send_message - For client to submit a message to be * sent to the remote. * @chan: Mailbox channel assigned to this client. @@ -246,7 +267,7 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg) { int t; - if (!chan || !chan->cl) + if (!chan || !chan->cl || mssg == MBOX_NO_MSG) return -EINVAL; t = add_to_rbuf(chan, mssg); @@ -319,12 +340,12 @@ static int __mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl) scoped_guard(spinlock_irqsave, &chan->lock) { chan->msg_free = 0; chan->msg_count = 0; - chan->active_req = NULL; + chan->active_req = MBOX_NO_MSG; chan->cl = cl; init_completion(&chan->tx_complete); - if (chan->txdone_method == TXDONE_BY_POLL && cl->knows_txdone) - chan->txdone_method = TXDONE_BY_ACK; + if (chan->txdone_method == MBOX_TXDONE_BY_POLL && cl->knows_txdone) + chan->txdone_method = MBOX_TXDONE_BY_ACK; } if (chan->mbox->ops->startup) { @@ -341,7 +362,7 @@ static int __mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl) } /** - * mbox_bind_client - Request a mailbox channel. + * mbox_bind_client - Bind client to a mailbox channel. * @chan: The mailbox channel to bind the client to. * @cl: Identity of the client requesting the channel. * @@ -477,9 +498,9 @@ void mbox_free_channel(struct mbox_chan *chan) /* The queued TX requests are simply aborted, no callbacks are made */ scoped_guard(spinlock_irqsave, &chan->lock) { chan->cl = NULL; - chan->active_req = NULL; - if (chan->txdone_method == TXDONE_BY_ACK) - chan->txdone_method = TXDONE_BY_POLL; + chan->active_req = MBOX_NO_MSG; + if (chan->txdone_method == MBOX_TXDONE_BY_ACK) + chan->txdone_method = MBOX_TXDONE_BY_POLL; } module_put(chan->mbox->dev->driver->owner); @@ -505,18 +526,17 @@ int mbox_controller_register(struct mbox_controller *mbox) { int i, txdone; - /* Sanity check */ - if (!mbox || !mbox->dev || !mbox->ops || !mbox->num_chans) + if (!mbox || !mbox->dev || !mbox->ops || !mbox->chans || !mbox->num_chans) return -EINVAL; if (mbox->txdone_irq) - txdone = TXDONE_BY_IRQ; + txdone = MBOX_TXDONE_BY_IRQ; else if (mbox->txdone_poll) - txdone = TXDONE_BY_POLL; + txdone = MBOX_TXDONE_BY_POLL; else /* It has to be ACK then */ - txdone = TXDONE_BY_ACK; + txdone = MBOX_TXDONE_BY_ACK; - if (txdone == TXDONE_BY_POLL) { + if (txdone == MBOX_TXDONE_BY_POLL) { if (!mbox->ops->last_tx_done) { dev_err(mbox->dev, "last_tx_done method is absent\n"); @@ -532,6 +552,7 @@ int mbox_controller_register(struct mbox_controller *mbox) chan->cl = NULL; chan->mbox = mbox; + chan->active_req = MBOX_NO_MSG; chan->txdone_method = txdone; spin_lock_init(&chan->lock); } diff --git a/drivers/mailbox/mailbox.h b/drivers/mailbox/mailbox.h deleted file mode 100644 index e1ec4efab693..000000000000 --- a/drivers/mailbox/mailbox.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ - -#ifndef __MAILBOX_H -#define __MAILBOX_H - -#include <linux/bits.h> - -#define TXDONE_BY_IRQ BIT(0) /* controller has remote RTR irq */ -#define TXDONE_BY_POLL BIT(1) /* controller can read status of last TX */ -#define TXDONE_BY_ACK BIT(2) /* S/W ACK received by Client ticks the TX */ - -#endif /* __MAILBOX_H */ diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c index d7c6b38888a3..e523c84b4808 100644 --- a/drivers/mailbox/mtk-cmdq-mailbox.c +++ b/drivers/mailbox/mtk-cmdq-mailbox.c @@ -493,14 +493,14 @@ static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data) if (curr_pa == end_pa - CMDQ_INST_SIZE || curr_pa == end_pa) { /* set to this task directly */ - writel(task->pa_base >> cmdq->pdata->shift, - thread->base + CMDQ_THR_CURR_ADDR); + gce_addr = cmdq_convert_gce_addr(task->pa_base, cmdq->pdata); + writel(gce_addr, thread->base + CMDQ_THR_CURR_ADDR); } else { cmdq_task_insert_into_thread(task); smp_mb(); /* modify jump before enable thread */ } - writel((task->pa_base + pkt->cmd_buf_size) >> cmdq->pdata->shift, - thread->base + CMDQ_THR_END_ADDR); + gce_addr = cmdq_convert_gce_addr(task->pa_base + pkt->cmd_buf_size, cmdq->pdata); + writel(gce_addr, thread->base + CMDQ_THR_END_ADDR); cmdq_thread_resume(thread); } list_move_tail(&task->list_entry, &thread->task_busy_list); @@ -728,7 +728,7 @@ static int cmdq_probe(struct platform_device *pdev) cmdq->mbox.ops = &cmdq_mbox_chan_ops; cmdq->mbox.of_xlate = cmdq_xlate; - /* make use of TXDONE_BY_ACK */ + /* make use of MBOX_TXDONE_BY_ACK */ cmdq->mbox.txdone_irq = false; cmdq->mbox.txdone_poll = false; diff --git a/drivers/mailbox/mtk-vcp-mailbox.c b/drivers/mailbox/mtk-vcp-mailbox.c index cedad575528f..1b291b8ea15a 100644 --- a/drivers/mailbox/mtk-vcp-mailbox.c +++ b/drivers/mailbox/mtk-vcp-mailbox.c @@ -50,7 +50,7 @@ static struct mbox_chan *mtk_vcp_mbox_xlate(struct mbox_controller *mbox, const struct of_phandle_args *sp) { if (sp->args_count) - return NULL; + return ERR_PTR(-EINVAL); return &mbox->chans[0]; } diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c index d9f100c18895..535ca8020877 100644 --- a/drivers/mailbox/omap-mailbox.c +++ b/drivers/mailbox/omap-mailbox.c @@ -22,8 +22,6 @@ #include <linux/pm_runtime.h> #include <linux/mailbox_controller.h> -#include "mailbox.h" - #define MAILBOX_REVISION 0x000 #define MAILBOX_MESSAGE(m) (0x040 + 4 * (m)) #define MAILBOX_FIFOSTATUS(m) (0x080 + 4 * (m)) @@ -240,7 +238,7 @@ static int omap_mbox_startup(struct omap_mbox *mbox) } if (mbox->send_no_irq) - mbox->chan->txdone_method = TXDONE_BY_ACK; + mbox->chan->txdone_method = MBOX_TXDONE_BY_ACK; omap_mbox_enable_irq(mbox, IRQ_RX); diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c index 22e70af1ae5d..636879ae1db7 100644 --- a/drivers/mailbox/pcc.c +++ b/drivers/mailbox/pcc.c @@ -59,8 +59,6 @@ #include <linux/io-64-nonatomic-lo-hi.h> #include <acpi/pcc.h> -#include "mailbox.h" - #define MBOX_IRQ_NAME "pcc-mbox" /** diff --git a/drivers/mailbox/rockchip-mailbox.c b/drivers/mailbox/rockchip-mailbox.c index 4d966cb2ed03..a1a7dee64356 100644 --- a/drivers/mailbox/rockchip-mailbox.c +++ b/drivers/mailbox/rockchip-mailbox.c @@ -46,7 +46,7 @@ struct rockchip_mbox { /* The maximum size of buf for each channel */ u32 buf_size; - struct rockchip_mbox_chan *chans; + struct rockchip_mbox_chan chans[]; }; static int rockchip_mbox_send_data(struct mbox_chan *chan, void *data) @@ -173,15 +173,10 @@ static int rockchip_mbox_probe(struct platform_device *pdev) drv_data = (const struct rockchip_mbox_data *) device_get_match_data(&pdev->dev); - mb = devm_kzalloc(&pdev->dev, sizeof(*mb), GFP_KERNEL); + mb = devm_kzalloc(&pdev->dev, struct_size(mb, chans, drv_data->num_chans), GFP_KERNEL); if (!mb) return -ENOMEM; - mb->chans = devm_kcalloc(&pdev->dev, drv_data->num_chans, - sizeof(*mb->chans), GFP_KERNEL); - if (!mb->chans) - return -ENOMEM; - mb->mbox.chans = devm_kcalloc(&pdev->dev, drv_data->num_chans, sizeof(*mb->mbox.chans), GFP_KERNEL); if (!mb->mbox.chans) diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c index ed9a0bb2bcd8..500fa77c7d53 100644 --- a/drivers/mailbox/tegra-hsp.c +++ b/drivers/mailbox/tegra-hsp.c @@ -16,8 +16,6 @@ #include <dt-bindings/mailbox/tegra186-hsp.h> -#include "mailbox.h" - #define HSP_INT_IE(x) (0x100 + ((x) * 4)) #define HSP_INT_IV 0x300 #define HSP_INT_IR 0x304 @@ -497,7 +495,7 @@ static int tegra_hsp_mailbox_flush(struct mbox_chan *chan, mbox_chan_txdone(chan, 0); /* Wait until channel is empty */ - if (chan->active_req != NULL) + if (chan->active_req != MBOX_NO_MSG) continue; return 0; @@ -516,7 +514,7 @@ static int tegra_hsp_mailbox_startup(struct mbox_chan *chan) struct tegra_hsp *hsp = mb->channel.hsp; unsigned long flags; - chan->txdone_method = TXDONE_BY_IRQ; + chan->txdone_method = MBOX_TXDONE_BY_IRQ; /* * Shared mailboxes start out as consumers by default. FULL and EMPTY diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 83378c033c72..028b9ca8ce52 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -216,6 +216,7 @@ struct bitmap { }; static struct workqueue_struct *md_bitmap_wq; +static struct attribute_group md_bitmap_internal_group; static int __bitmap_resize(struct bitmap *bitmap, sector_t blocks, int chunksize, bool init); @@ -2580,6 +2581,30 @@ static int bitmap_resize(struct mddev *mddev, sector_t blocks, int chunksize) return __bitmap_resize(bitmap, blocks, chunksize, false); } +static bool bitmap_none_enabled(void *data, bool flush) +{ + return false; +} + +static int bitmap_none_create(struct mddev *mddev) +{ + return 0; +} + +static int bitmap_none_load(struct mddev *mddev) +{ + return 0; +} + +static void bitmap_none_destroy(struct mddev *mddev) +{ +} + +static int bitmap_none_get_stats(void *data, struct md_bitmap_stats *stats) +{ + return -ENOENT; +} + static ssize_t location_show(struct mddev *mddev, char *page) { @@ -2618,7 +2643,11 @@ location_store(struct mddev *mddev, const char *buf, size_t len) goto out; } - bitmap_destroy(mddev); + sysfs_unmerge_group(&mddev->kobj, &md_bitmap_internal_group); + md_bitmap_destroy_nosysfs(mddev); + mddev->bitmap_id = ID_BITMAP_NONE; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + goto none_err; mddev->bitmap_info.offset = 0; if (mddev->bitmap_info.file) { struct file *f = mddev->bitmap_info.file; @@ -2654,16 +2683,25 @@ location_store(struct mddev *mddev, const char *buf, size_t len) } mddev->bitmap_info.offset = offset; - rv = bitmap_create(mddev); + md_bitmap_destroy_nosysfs(mddev); + mddev->bitmap_id = ID_BITMAP; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + goto bitmap_err; + + rv = md_bitmap_create_nosysfs(mddev); if (rv) - goto out; + goto create_err; - rv = bitmap_load(mddev); + rv = mddev->bitmap_ops->load(mddev); if (rv) { mddev->bitmap_info.offset = 0; - bitmap_destroy(mddev); - goto out; + goto load_err; } + + rv = sysfs_merge_group(&mddev->kobj, + &md_bitmap_internal_group); + if (rv) + goto merge_err; } } if (!mddev->external) { @@ -2679,6 +2717,22 @@ out: if (rv) return rv; return len; + +merge_err: + mddev->bitmap_info.offset = 0; +load_err: + md_bitmap_destroy_nosysfs(mddev); +create_err: + mddev->bitmap_info.offset = 0; + mddev->bitmap_id = ID_BITMAP_NONE; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + rv = -ENOENT; + goto out; +bitmap_err: + rv = -ENOENT; +none_err: + mddev->bitmap_info.offset = 0; + goto out; } static struct md_sysfs_entry bitmap_location = @@ -2955,8 +3009,12 @@ static struct md_sysfs_entry max_backlog_used = __ATTR(max_backlog_used, S_IRUGO | S_IWUSR, behind_writes_used_show, behind_writes_used_reset); -static struct attribute *md_bitmap_attrs[] = { +static struct attribute *md_bitmap_common_attrs[] = { &bitmap_location.attr, + NULL +}; + +static struct attribute *md_bitmap_internal_attrs[] = { &bitmap_space.attr, &bitmap_timeout.attr, &bitmap_backlog.attr, @@ -2967,9 +3025,41 @@ static struct attribute *md_bitmap_attrs[] = { NULL }; -static struct attribute_group md_bitmap_group = { +static struct attribute_group md_bitmap_common_group = { .name = "bitmap", - .attrs = md_bitmap_attrs, + .attrs = md_bitmap_common_attrs, +}; + +static struct attribute_group md_bitmap_internal_group = { + .name = "bitmap", + .attrs = md_bitmap_internal_attrs, +}; + +static const struct attribute_group *bitmap_groups[] = { + &md_bitmap_common_group, + &md_bitmap_internal_group, + NULL, +}; + +static const struct attribute_group *bitmap_none_groups[] = { + &md_bitmap_common_group, + NULL, +}; + +static struct bitmap_operations bitmap_none_ops = { + .head = { + .type = MD_BITMAP, + .id = ID_BITMAP_NONE, + .name = "none", + }, + + .enabled = bitmap_none_enabled, + .create = bitmap_none_create, + .load = bitmap_none_load, + .destroy = bitmap_none_destroy, + .get_stats = bitmap_none_get_stats, + + .groups = bitmap_none_groups, }; static struct bitmap_operations bitmap_ops = { @@ -3013,21 +3103,38 @@ static struct bitmap_operations bitmap_ops = { .set_pages = bitmap_set_pages, .free = md_bitmap_free, - .group = &md_bitmap_group, + .groups = bitmap_groups, }; int md_bitmap_init(void) { + int err; + md_bitmap_wq = alloc_workqueue("md_bitmap", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (!md_bitmap_wq) return -ENOMEM; - return register_md_submodule(&bitmap_ops.head); + err = register_md_submodule(&bitmap_none_ops.head); + if (err) + goto err_wq; + + err = register_md_submodule(&bitmap_ops.head); + if (err) + goto err_none; + + return 0; + +err_none: + unregister_md_submodule(&bitmap_none_ops.head); +err_wq: + destroy_workqueue(md_bitmap_wq); + return err; } void md_bitmap_exit(void) { - destroy_workqueue(md_bitmap_wq); unregister_md_submodule(&bitmap_ops.head); + unregister_md_submodule(&bitmap_none_ops.head); + destroy_workqueue(md_bitmap_wq); } diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index b42a28fa83a0..214f623c7e79 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -125,7 +125,7 @@ struct bitmap_operations { void (*set_pages)(void *data, unsigned long pages); void (*free)(void *data); - struct attribute_group *group; + const struct attribute_group **groups; }; /* the bitmap API */ diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c index 9e7e6b1a6f15..1adc5b117821 100644 --- a/drivers/md/md-llbitmap.c +++ b/drivers/md/md-llbitmap.c @@ -1738,6 +1738,11 @@ static struct attribute_group md_llbitmap_group = { .attrs = md_llbitmap_attrs, }; +static const struct attribute_group *md_llbitmap_groups[] = { + &md_llbitmap_group, + NULL, +}; + static struct bitmap_operations llbitmap_ops = { .head = { .type = MD_BITMAP, @@ -1774,7 +1779,7 @@ static struct bitmap_operations llbitmap_ops = { .dirty_bits = llbitmap_dirty_bits, .write_all = llbitmap_write_all, - .group = &md_llbitmap_group, + .groups = md_llbitmap_groups, }; int md_llbitmap_init(void) diff --git a/drivers/md/md.c b/drivers/md/md.c index 5fb5ae8368ba..8b568eee8743 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -396,27 +396,19 @@ bool md_handle_request(struct mddev *mddev, struct bio *bio) { check_suspended: if (is_suspended(mddev, bio)) { - DEFINE_WAIT(__wait); /* Bail out if REQ_NOWAIT is set for the bio */ if (bio->bi_opf & REQ_NOWAIT) { bio_wouldblock_error(bio); return true; } - for (;;) { - prepare_to_wait(&mddev->sb_wait, &__wait, - TASK_UNINTERRUPTIBLE); - if (!is_suspended(mddev, bio)) - break; - schedule(); - } - finish_wait(&mddev->sb_wait, &__wait); + wait_event(mddev->sb_wait, !is_suspended(mddev, bio)); } if (!percpu_ref_tryget_live(&mddev->active_io)) goto check_suspended; if (!mddev->pers->make_request(mddev, bio)) { percpu_ref_put(&mddev->active_io); - if (!mddev->gendisk && mddev->pers->prepare_suspend) + if (mddev_is_dm(mddev) && mddev->pers->prepare_suspend) return false; goto check_suspended; } @@ -687,13 +679,38 @@ static void active_io_release(struct percpu_ref *ref) static void no_op(struct percpu_ref *r) {} -static bool mddev_set_bitmap_ops(struct mddev *mddev) +static void md_bitmap_sysfs_add(struct mddev *mddev) +{ + if (sysfs_update_groups(&mddev->kobj, mddev->bitmap_ops->groups)) + pr_warn("md: cannot register extra bitmap attributes for %s\n", + mdname(mddev)); + else + /* + * Inform user with KOBJ_CHANGE about new bitmap + * attributes. + */ + kobject_uevent(&mddev->kobj, KOBJ_CHANGE); +} + +static void md_bitmap_sysfs_del(struct mddev *mddev) +{ + int nr_groups = 0; + + for (nr_groups = 0; mddev->bitmap_ops->groups[nr_groups]; nr_groups++) + ; + + while (--nr_groups >= 1) + sysfs_unmerge_group(&mddev->kobj, + mddev->bitmap_ops->groups[nr_groups]); + sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->groups[0]); +} + +bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev) { - struct bitmap_operations *old = mddev->bitmap_ops; struct md_submodule_head *head; - if (mddev->bitmap_id == ID_BITMAP_NONE || - (old && old->head.id == mddev->bitmap_id)) + if (mddev->bitmap_ops && + mddev->bitmap_ops->head.id == mddev->bitmap_id) return true; xa_lock(&md_submodule); @@ -711,18 +728,6 @@ static bool mddev_set_bitmap_ops(struct mddev *mddev) mddev->bitmap_ops = (void *)head; xa_unlock(&md_submodule); - - if (!mddev_is_dm(mddev) && mddev->bitmap_ops->group) { - if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group)) - pr_warn("md: cannot register extra bitmap attributes for %s\n", - mdname(mddev)); - else - /* - * Inform user with KOBJ_CHANGE about new bitmap - * attributes. - */ - kobject_uevent(&mddev->kobj, KOBJ_CHANGE); - } return true; err: @@ -730,15 +735,6 @@ err: return false; } -static void mddev_clear_bitmap_ops(struct mddev *mddev) -{ - if (!mddev_is_dm(mddev) && mddev->bitmap_ops && - mddev->bitmap_ops->group) - sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->group); - - mddev->bitmap_ops = NULL; -} - int mddev_init(struct mddev *mddev) { int err = 0; @@ -4279,7 +4275,7 @@ bitmap_type_show(struct mddev *mddev, char *page) xa_lock(&md_submodule); xa_for_each(&md_submodule, i, head) { - if (head->type != MD_BITMAP) + if (head->type != MD_BITMAP || head->id == ID_BITMAP_NONE) continue; if (mddev->bitmap_id == head->id) @@ -6059,10 +6055,7 @@ static struct attribute *md_default_attrs[] = { &md_logical_block_size.attr, NULL, }; - -static const struct attribute_group md_default_group = { - .attrs = md_default_attrs, -}; +ATTRIBUTE_GROUPS(md_default); static struct attribute *md_redundancy_attrs[] = { &md_scan_mode.attr, @@ -6087,11 +6080,6 @@ static const struct attribute_group md_redundancy_group = { .attrs = md_redundancy_attrs, }; -static const struct attribute_group *md_attr_groups[] = { - &md_default_group, - NULL, -}; - static ssize_t md_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { @@ -6174,7 +6162,7 @@ static const struct sysfs_ops md_sysfs_ops = { static const struct kobj_type md_ktype = { .release = md_kobj_release, .sysfs_ops = &md_sysfs_ops, - .default_groups = md_attr_groups, + .default_groups = md_default_groups, }; int mdp_major = 0; @@ -6539,7 +6527,7 @@ out: return id; } -static int md_bitmap_create(struct mddev *mddev) +int md_bitmap_create_nosysfs(struct mddev *mddev) { enum md_submodule_id orig_id = mddev->bitmap_id; enum md_submodule_id sb_id; @@ -6548,8 +6536,10 @@ static int md_bitmap_create(struct mddev *mddev) if (mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; - if (!mddev_set_bitmap_ops(mddev)) + if (!mddev_set_bitmap_ops_nosysfs(mddev)) { + mddev->bitmap_id = orig_id; return -ENOENT; + } err = mddev->bitmap_ops->create(mddev); if (!err) @@ -6560,37 +6550,72 @@ static int md_bitmap_create(struct mddev *mddev) * doesn't match, and mdadm is not the latest version to set * bitmap_type, set bitmap_ops based on the disk version. */ - mddev_clear_bitmap_ops(mddev); + mddev->bitmap_ops = NULL; sb_id = md_bitmap_get_id_from_sb(mddev); - if (sb_id == ID_BITMAP_NONE || sb_id == orig_id) + if (sb_id == ID_BITMAP_NONE || sb_id == orig_id) { + mddev->bitmap_id = orig_id; return err; + } pr_info("md: %s: bitmap version mismatch, switching from %d to %d\n", mdname(mddev), orig_id, sb_id); mddev->bitmap_id = sb_id; - if (!mddev_set_bitmap_ops(mddev)) { + if (!mddev_set_bitmap_ops_nosysfs(mddev)) { mddev->bitmap_id = orig_id; return -ENOENT; } err = mddev->bitmap_ops->create(mddev); if (err) { - mddev_clear_bitmap_ops(mddev); + mddev->bitmap_ops = NULL; mddev->bitmap_id = orig_id; } return err; } -static void md_bitmap_destroy(struct mddev *mddev) +static int md_bitmap_create(struct mddev *mddev) +{ + int err; + + err = md_bitmap_create_nosysfs(mddev); + if (err) + return err; + + if (!mddev_is_dm(mddev) && mddev->bitmap_ops->groups) + md_bitmap_sysfs_add(mddev); + + return 0; +} + +void md_bitmap_destroy_nosysfs(struct mddev *mddev) { if (!md_bitmap_registered(mddev)) return; mddev->bitmap_ops->destroy(mddev); - mddev_clear_bitmap_ops(mddev); + mddev->bitmap_ops = NULL; +} + +static void md_bitmap_destroy(struct mddev *mddev) +{ + if (!mddev_is_dm(mddev) && mddev->bitmap_ops && + mddev->bitmap_ops->groups) + md_bitmap_sysfs_del(mddev); + + md_bitmap_destroy_nosysfs(mddev); +} + +static void md_bitmap_set_none(struct mddev *mddev) +{ + mddev->bitmap_id = ID_BITMAP_NONE; + if (!mddev_set_bitmap_ops_nosysfs(mddev)) + return; + + if (!mddev_is_dm(mddev) && mddev->bitmap_ops->groups) + md_bitmap_sysfs_add(mddev); } int md_run(struct mddev *mddev) @@ -6713,7 +6738,7 @@ int md_run(struct mddev *mddev) } /* dm-raid expect sync_thread to be frozen until resume */ - if (mddev->gendisk) + if (!mddev_is_dm(mddev)) mddev->recovery = 0; /* may be over-ridden by personality */ @@ -6802,6 +6827,10 @@ int md_run(struct mddev *mddev) if (mddev->sb_flags) md_update_sb(mddev, 0); + if (IS_ENABLED(CONFIG_MD_BITMAP) && !mddev->bitmap_info.file && + !mddev->bitmap_info.offset) + md_bitmap_set_none(mddev); + md_new_event(); return 0; @@ -7747,7 +7776,8 @@ static int set_bitmap_file(struct mddev *mddev, int fd) { int err = 0; - if (!md_bitmap_registered(mddev)) + if (!md_bitmap_registered(mddev) || + mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; if (mddev->pers) { @@ -7812,10 +7842,12 @@ static int set_bitmap_file(struct mddev *mddev, int fd) if (err) { md_bitmap_destroy(mddev); + md_bitmap_set_none(mddev); fd = -1; } } else if (fd < 0) { md_bitmap_destroy(mddev); + md_bitmap_set_none(mddev); } } @@ -8122,12 +8154,16 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) mddev->bitmap_info.default_offset; mddev->bitmap_info.space = mddev->bitmap_info.default_space; + mddev->bitmap_id = ID_BITMAP; rv = md_bitmap_create(mddev); if (!rv) rv = mddev->bitmap_ops->load(mddev); - if (rv) + if (rv) { md_bitmap_destroy(mddev); + mddev->bitmap_info.offset = 0; + md_bitmap_set_none(mddev); + } } else { struct md_bitmap_stats stats; @@ -8155,6 +8191,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) } md_bitmap_destroy(mddev); mddev->bitmap_info.offset = 0; + md_bitmap_set_none(mddev); } } md_update_sb(mddev, 1); @@ -9341,9 +9378,11 @@ static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone) static void md_end_clone_io(struct bio *bio) { - struct md_io_clone *md_io_clone = bio->bi_private; + struct md_io_clone *md_io_clone = container_of(bio, struct md_io_clone, + bio_clone); struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev; + struct completion *reshape_completion = bio->bi_private; if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, false)) md_bitmap_end(mddev, md_io_clone); @@ -9355,7 +9394,10 @@ static void md_end_clone_io(struct bio *bio) bio_end_io_acct(orig_bio, md_io_clone->start_time); bio_put(bio); - bio_endio(orig_bio); + if (unlikely(reshape_completion)) + complete(reshape_completion); + else + bio_endio(orig_bio); percpu_ref_put(&mddev->active_io); } @@ -9380,7 +9422,7 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio) } clone->bi_end_io = md_end_clone_io; - clone->bi_private = md_io_clone; + clone->bi_private = NULL; *bio = clone; } @@ -9391,26 +9433,6 @@ void md_account_bio(struct mddev *mddev, struct bio **bio) } EXPORT_SYMBOL_GPL(md_account_bio); -void md_free_cloned_bio(struct bio *bio) -{ - struct md_io_clone *md_io_clone = bio->bi_private; - struct bio *orig_bio = md_io_clone->orig_bio; - struct mddev *mddev = md_io_clone->mddev; - - if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, false)) - md_bitmap_end(mddev, md_io_clone); - - if (bio->bi_status && !orig_bio->bi_status) - orig_bio->bi_status = bio->bi_status; - - if (md_io_clone->start_time) - bio_end_io_acct(orig_bio, md_io_clone->start_time); - - bio_put(bio); - percpu_ref_put(&mddev->active_io); -} -EXPORT_SYMBOL_GPL(md_free_cloned_bio); - /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before diff --git a/drivers/md/md.h b/drivers/md/md.h index d6f5482e2479..52c378086046 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -920,7 +920,6 @@ extern void md_finish_reshape(struct mddev *mddev); void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio, sector_t start, sector_t size); void md_account_bio(struct mddev *mddev, struct bio **bio); -void md_free_cloned_bio(struct bio *bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); void md_write_metadata(struct mddev *mddev, struct md_rdev *rdev, @@ -935,6 +934,9 @@ extern void md_allow_write(struct mddev *mddev); extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); +bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev); +int md_bitmap_create_nosysfs(struct mddev *mddev); +void md_bitmap_destroy_nosysfs(struct mddev *mddev); extern int md_integrity_register(struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); @@ -1015,7 +1017,7 @@ static inline int mddev_suspend_and_lock(struct mddev *mddev) static inline void mddev_suspend_and_lock_nointr(struct mddev *mddev) { mddev_suspend(mddev, false); - mutex_lock(&mddev->reconfig_mutex); + mddev_lock_nointr(mddev); } static inline void mddev_unlock_and_resume(struct mddev *mddev) diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 942cd47eb52d..aeec5b9a1dd5 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -490,12 +490,20 @@ static int rebalance_children(struct shadow_spine *s, if (le32_to_cpu(n->header.nr_entries) == 1) { struct dm_block *child; + int is_shared; dm_block_t b = value64(n, 0); + r = dm_tm_block_is_shared(info->tm, b, &is_shared); + if (r) + return r; + r = dm_tm_read_lock(info->tm, b, &btree_node_validator, &child); if (r) return r; + if (is_shared) + inc_children(info->tm, dm_block_data(child), vt); + memcpy(n, dm_block_data(child), dm_bm_block_size(dm_tm_get_bm(info->tm))); diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index c33099925f23..56a56a4da4f8 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -293,8 +293,13 @@ static inline bool raid1_should_read_first(struct mddev *mddev, * bio with REQ_RAHEAD or REQ_NOWAIT can fail at anytime, before such IO is * submitted to the underlying disks, hence don't record badblocks or retry * in this case. + * + * BLK_STS_INVAL means the bio was not valid for the underlying device. This + * is a user error, not a device failure, so retrying or recording bad blocks + * would be wrong. */ static inline bool raid1_should_handle_error(struct bio *bio) { - return !(bio->bi_opf & (REQ_RAHEAD | REQ_NOWAIT)); + return !(bio->bi_opf & (REQ_RAHEAD | REQ_NOWAIT)) && + bio->bi_status != BLK_STS_INVAL; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ba91f7e61920..64d970e2ef50 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1510,21 +1510,14 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, mddev->cluster_ops->area_resyncing(mddev, WRITE, bio->bi_iter.bi_sector, bio_end_sector(bio))) { - DEFINE_WAIT(w); if (bio->bi_opf & REQ_NOWAIT) { bio_wouldblock_error(bio); return; } - for (;;) { - prepare_to_wait(&conf->wait_barrier, - &w, TASK_IDLE); - if (!mddev->cluster_ops->area_resyncing(mddev, WRITE, - bio->bi_iter.bi_sector, - bio_end_sector(bio))) - break; - schedule(); - } - finish_wait(&conf->wait_barrier, &w); + wait_event_idle(conf->wait_barrier, + !mddev->cluster_ops->area_resyncing(mddev, WRITE, + bio->bi_iter.bi_sector, + bio_end_sector(bio))); } /* diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 4901ebe45c87..39085e7dd6d2 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3791,6 +3791,8 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new) nc = layout & 255; fc = (layout >> 8) & 255; fo = layout & (1<<16); + if (!nc || !fc) + return -1; geo->raid_disks = disks; geo->near_copies = nc; geo->far_copies = fc; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 6e79829c5acb..0d76e82f4506 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6217,7 +6217,12 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) mempool_free(ctx, conf->ctx_pool); if (res == STRIPE_WAIT_RESHAPE) { - md_free_cloned_bio(bi); + DECLARE_COMPLETION_ONSTACK(done); + WRITE_ONCE(bi->bi_private, &done); + + bio_endio(bi); + + wait_for_completion(&done); return false; } diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig index d488213b631f..64b8b99a3a68 100644 --- a/drivers/mtd/nand/raw/Kconfig +++ b/drivers/mtd/nand/raw/Kconfig @@ -71,7 +71,7 @@ config MTD_NAND_AU1550 config MTD_NAND_NDFC tristate "IBM/MCC 4xx NAND controller" - depends on 4xx + depends on 44x || COMPILE_TEST select MTD_NAND_ECC_SW_HAMMING select MTD_NAND_ECC_SW_HAMMING_SMC help diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index d6d3e17ab407..a5b278ab9384 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -175,7 +175,7 @@ void nand_select_target(struct nand_chip *chip, unsigned int cs) * cs should always lie between 0 and nanddev_ntargets(), when that's * not the case it's a bug and the caller should be fixed. */ - if (WARN_ON(cs > nanddev_ntargets(&chip->base))) + if (WARN_ON(cs >= nanddev_ntargets(&chip->base))) return; chip->cur_cs = cs; @@ -1216,32 +1216,32 @@ static int nand_lp_exec_read_page_op(struct nand_chip *chip, unsigned int page, return nand_exec_op(chip, &op); } -static unsigned int rawnand_last_page_of_lun(unsigned int pages_per_lun, unsigned int lun) +static unsigned int rawnand_last_page_of_block(unsigned int ppb, unsigned int block) { - /* lun is expected to be very small */ - return (lun * pages_per_lun) + pages_per_lun - 1; + /* block is expected to be very small */ + return (block * ppb) + ppb - 1; } static void rawnand_cap_cont_reads(struct nand_chip *chip) { struct nand_memory_organization *memorg; - unsigned int ppl, first_lun, last_lun; + unsigned int ppb, first_block, last_block; memorg = nanddev_get_memorg(&chip->base); - ppl = memorg->pages_per_eraseblock * memorg->eraseblocks_per_lun; - first_lun = chip->cont_read.first_page / ppl; - last_lun = chip->cont_read.last_page / ppl; + ppb = memorg->pages_per_eraseblock; + first_block = chip->cont_read.first_page / ppb; + last_block = chip->cont_read.last_page / ppb; - /* Prevent sequential cache reads across LUN boundaries */ - if (first_lun != last_lun) - chip->cont_read.pause_page = rawnand_last_page_of_lun(ppl, first_lun); + /* Prevent sequential cache reads across block boundaries */ + if (first_block != last_block) + chip->cont_read.pause_page = rawnand_last_page_of_block(ppb, first_block); else chip->cont_read.pause_page = chip->cont_read.last_page; if (chip->cont_read.first_page == chip->cont_read.pause_page) { chip->cont_read.first_page++; chip->cont_read.pause_page = min(chip->cont_read.last_page, - rawnand_last_page_of_lun(ppl, first_lun + 1)); + rawnand_last_page_of_block(ppb, first_block + 1)); } if (chip->cont_read.first_page >= chip->cont_read.last_page) diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c index 7ad8bc04be1a..a937ca3eeff5 100644 --- a/drivers/mtd/nand/raw/ndfc.c +++ b/drivers/mtd/nand/raw/ndfc.c @@ -44,13 +44,13 @@ static void ndfc_select_chip(struct nand_chip *nchip, int chip) uint32_t ccr; struct ndfc_controller *ndfc = nand_get_controller_data(nchip); - ccr = in_be32(ndfc->ndfcbase + NDFC_CCR); + ccr = ioread32be(ndfc->ndfcbase + NDFC_CCR); if (chip >= 0) { ccr &= ~NDFC_CCR_BS_MASK; ccr |= NDFC_CCR_BS(chip + ndfc->chip_select); } else ccr |= NDFC_CCR_RESET_CE; - out_be32(ndfc->ndfcbase + NDFC_CCR, ccr); + iowrite32be(ccr, ndfc->ndfcbase + NDFC_CCR); } static void ndfc_hwcontrol(struct nand_chip *chip, int cmd, unsigned int ctrl) @@ -70,7 +70,7 @@ static int ndfc_ready(struct nand_chip *chip) { struct ndfc_controller *ndfc = nand_get_controller_data(chip); - return in_be32(ndfc->ndfcbase + NDFC_STAT) & NDFC_STAT_IS_READY; + return ioread32be(ndfc->ndfcbase + NDFC_STAT) & NDFC_STAT_IS_READY; } static void ndfc_enable_hwecc(struct nand_chip *chip, int mode) @@ -78,9 +78,9 @@ static void ndfc_enable_hwecc(struct nand_chip *chip, int mode) uint32_t ccr; struct ndfc_controller *ndfc = nand_get_controller_data(chip); - ccr = in_be32(ndfc->ndfcbase + NDFC_CCR); + ccr = ioread32be(ndfc->ndfcbase + NDFC_CCR); ccr |= NDFC_CCR_RESET_ECC; - out_be32(ndfc->ndfcbase + NDFC_CCR, ccr); + iowrite32be(ccr, ndfc->ndfcbase + NDFC_CCR); wmb(); } @@ -92,7 +92,7 @@ static int ndfc_calculate_ecc(struct nand_chip *chip, uint8_t *p = (uint8_t *)&ecc; wmb(); - ecc = in_be32(ndfc->ndfcbase + NDFC_ECC); + ecc = ioread32be(ndfc->ndfcbase + NDFC_ECC); /* The NDFC uses Smart Media (SMC) bytes order */ ecc_code[0] = p[1]; ecc_code[1] = p[2]; @@ -114,7 +114,7 @@ static void ndfc_read_buf(struct nand_chip *chip, uint8_t *buf, int len) uint32_t *p = (uint32_t *) buf; for(;len > 0; len -= 4) - *p++ = in_be32(ndfc->ndfcbase + NDFC_DATA); + *p++ = ioread32be(ndfc->ndfcbase + NDFC_DATA); } static void ndfc_write_buf(struct nand_chip *chip, const uint8_t *buf, int len) @@ -123,7 +123,7 @@ static void ndfc_write_buf(struct nand_chip *chip, const uint8_t *buf, int len) uint32_t *p = (uint32_t *) buf; for(;len > 0; len -= 4) - out_be32(ndfc->ndfcbase + NDFC_DATA, *p++); + iowrite32be(*p++, ndfc->ndfcbase + NDFC_DATA); } /* @@ -223,13 +223,13 @@ static int ndfc_probe(struct platform_device *ofdev) if (reg) ccr |= be32_to_cpup(reg); - out_be32(ndfc->ndfcbase + NDFC_CCR, ccr); + iowrite32be(ccr, ndfc->ndfcbase + NDFC_CCR); /* Set the bank settings if given */ reg = of_get_property(ofdev->dev.of_node, "bank-settings", NULL); if (reg) { int offset = NDFC_BCFG0 + (ndfc->chip_select << 2); - out_be32(ndfc->ndfcbase + offset, be32_to_cpup(reg)); + iowrite32be(be32_to_cpup(reg), ndfc->ndfcbase + offset); } err = ndfc_chip_init(ndfc, ofdev->dev.of_node); diff --git a/drivers/mtd/nand/raw/pl35x-nand-controller.c b/drivers/mtd/nand/raw/pl35x-nand-controller.c index f2c65eb7a8d9..06f8f1e14b9c 100644 --- a/drivers/mtd/nand/raw/pl35x-nand-controller.c +++ b/drivers/mtd/nand/raw/pl35x-nand-controller.c @@ -1155,7 +1155,7 @@ static int pl35x_nand_probe(struct platform_device *pdev) nfc->controller.ops = &pl35x_nandc_ops; INIT_LIST_HEAD(&nfc->chips); - nfc->conf_regs = devm_ioremap_resource(&smc_amba->dev, &smc_amba->res); + nfc->conf_regs = devm_ioremap_resource(nfc->dev, &smc_amba->res); if (IS_ERR(nfc->conf_regs)) return PTR_ERR(nfc->conf_regs); diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index b7e79b76654d..4b80ce084d9a 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -128,8 +128,8 @@ static struct qcom_nand_host *to_qcom_nand_host(struct nand_chip *chip) static struct qcom_nand_controller * get_qcom_nand_controller(struct nand_chip *chip) { - return (struct qcom_nand_controller *) - ((u8 *)chip->controller - sizeof(struct qcom_nand_controller)); + return container_of(chip->controller, struct qcom_nand_controller, + controller); } static u32 nandc_read(struct qcom_nand_controller *nandc, int offset) @@ -2034,8 +2034,8 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc) { u32 nand_ctrl; - nand_controller_init(nandc->controller); - nandc->controller->ops = &qcom_nandc_ops; + nand_controller_init(&nandc->controller); + nandc->controller.ops = &qcom_nandc_ops; /* kill onenand */ if (!nandc->props->nandc_part_of_qpic) @@ -2175,7 +2175,7 @@ static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc, chip->legacy.block_bad = qcom_nandc_block_bad; chip->legacy.block_markbad = qcom_nandc_block_markbad; - chip->controller = nandc->controller; + chip->controller = &nandc->controller; chip->options |= NAND_NO_SUBPAGE_WRITE | NAND_USES_DMA | NAND_SKIP_BBTSCAN; @@ -2256,21 +2256,17 @@ static int qcom_nandc_parse_dt(struct platform_device *pdev) static int qcom_nandc_probe(struct platform_device *pdev) { struct qcom_nand_controller *nandc; - struct nand_controller *controller; const void *dev_data; struct device *dev = &pdev->dev; struct resource *res; int ret; - nandc = devm_kzalloc(&pdev->dev, sizeof(*nandc) + sizeof(*controller), - GFP_KERNEL); + nandc = devm_kzalloc(&pdev->dev, sizeof(*nandc), GFP_KERNEL); if (!nandc) return -ENOMEM; - controller = (struct nand_controller *)&nandc[1]; platform_set_drvdata(pdev, nandc); nandc->dev = dev; - nandc->controller = controller; dev_data = of_device_get_match_data(dev); if (!dev_data) { diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 8aa3753aaaa1..f86786344d52 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -100,6 +100,17 @@ spinand_fill_page_read_op(struct spinand_device *spinand, u64 addr) return op; } +static struct spi_mem_op +spinand_fill_page_read_packed_op(struct spinand_device *spinand, u64 addr) +{ + struct spi_mem_op op = spinand->op_templates->page_read; + + op.cmd.opcode |= addr >> 16; + op.addr.val = addr & 0xFFFF; + + return op; +} + struct spi_mem_op spinand_fill_prog_exec_op(struct spinand_device *spinand, u64 addr) { @@ -453,7 +464,10 @@ static int spinand_load_page_op(struct spinand_device *spinand, { struct nand_device *nand = spinand_to_nand(spinand); unsigned int row = nanddev_pos_to_row(nand, &req->pos); - struct spi_mem_op op = SPINAND_OP(spinand, page_read, row); + bool packed = spinand->flags & SPINAND_ODTR_PACKED_PAGE_READ; + struct spi_mem_op op = packed ? + SPINAND_OP(spinand, page_read_packed, row) : + SPINAND_OP(spinand, page_read, row); return spi_mem_exec_op(spinand->spimem, &op); } @@ -487,10 +501,18 @@ static int spinand_read_from_cache_op(struct spinand_device *spinand, } } - if (req->mode == MTD_OPS_RAW) - rdesc = spinand->dirmaps[req->pos.plane].rdesc; + rdesc = spinand->dirmaps[req->pos.plane].rdesc; + + if (spinand->op_templates->cont_read_cache && req->continuous) + rdesc->info.op_tmpl = &rdesc->info.secondary_op_tmpl; + else + rdesc->info.op_tmpl = &rdesc->info.primary_op_tmpl; + + if (nand->ecc.engine->integration == NAND_ECC_ENGINE_INTEGRATION_PIPELINED && + req->mode != MTD_OPS_RAW) + rdesc->info.op_tmpl->data.ecc = true; else - rdesc = spinand->dirmaps[req->pos.plane].rdesc_ecc; + rdesc->info.op_tmpl->data.ecc = false; if (spinand->flags & SPINAND_HAS_READ_PLANE_SELECT_BIT) column |= req->pos.plane << fls(nanddev_page_size(nand)); @@ -579,10 +601,13 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, req->ooblen); } - if (req->mode == MTD_OPS_RAW) - wdesc = spinand->dirmaps[req->pos.plane].wdesc; + wdesc = spinand->dirmaps[req->pos.plane].wdesc; + + if (nand->ecc.engine->integration == NAND_ECC_ENGINE_INTEGRATION_PIPELINED && + req->mode != MTD_OPS_RAW) + wdesc->info.op_tmpl->data.ecc = true; else - wdesc = spinand->dirmaps[req->pos.plane].wdesc_ecc; + wdesc->info.op_tmpl->data.ecc = false; if (spinand->flags & SPINAND_HAS_PROG_PLANE_SELECT_BIT) column |= req->pos.plane << fls(nanddev_page_size(nand)); @@ -878,6 +903,12 @@ static int spinand_mtd_continuous_page_read(struct mtd_info *mtd, loff_t from, * Each data read must be a multiple of 4-bytes and full pages should be read; * otherwise, the data output might get out of sequence from one read command * to another. + * + * Continuous reads never cross LUN boundaries. Some devices don't + * support crossing planes boundaries. Some devices don't even support + * crossing blocks boundaries. The common case being to read through UBI, + * we will very rarely read two consequent blocks or more, so let's only enable + * continuous reads when reading within the same erase block. */ nanddev_io_for_each_block(nand, NAND_PAGE_READ, from, ops, &iter) { ret = spinand_select_target(spinand, iter.req.pos.target); @@ -934,13 +965,10 @@ static void spinand_cont_read_init(struct spinand_device *spinand) { struct nand_device *nand = spinand_to_nand(spinand); enum nand_ecc_engine_type engine_type = nand->ecc.ctx.conf.engine_type; + struct spi_controller *ctlr = spinand->spimem->spi->controller; /* OOBs cannot be retrieved so external/on-host ECC engine won't work */ - if (spinand->set_cont_read && - (engine_type == NAND_ECC_ENGINE_TYPE_ON_DIE || - engine_type == NAND_ECC_ENGINE_TYPE_NONE)) { - spinand->cont_read_possible = true; - + if (spinand->set_cont_read) { /* * Ensure continuous read is disabled on probe. * Some devices retain this state across soft reset, @@ -948,6 +976,11 @@ static void spinand_cont_read_init(struct spinand_device *spinand) * in false positive returns from spinand_isbad(). */ spinand_cont_read_enable(spinand, false); + + if ((engine_type == NAND_ECC_ENGINE_TYPE_ON_DIE || + engine_type == NAND_ECC_ENGINE_TYPE_NONE) && + !spi_mem_controller_is_capable(ctlr, no_cs_assertion)) + spinand->cont_read_possible = true; } } @@ -968,19 +1001,6 @@ static bool spinand_use_cont_read(struct mtd_info *mtd, loff_t from, nanddev_offs_to_pos(nand, from, &start_pos); nanddev_offs_to_pos(nand, from + ops->len - 1, &end_pos); - /* - * Continuous reads never cross LUN boundaries. Some devices don't - * support crossing planes boundaries. Some devices don't even support - * crossing blocks boundaries. The common case being to read through UBI, - * we will very rarely read two consequent blocks or more, so it is safer - * and easier (can be improved) to only enable continuous reads when - * reading within the same erase block. - */ - if (start_pos.target != end_pos.target || - start_pos.plane != end_pos.plane || - start_pos.eraseblock != end_pos.eraseblock) - return false; - return start_pos.page < end_pos.page; } @@ -1222,6 +1242,7 @@ static struct spi_mem_dirmap_desc *spinand_create_rdesc( * its spi controller, use regular reading */ spinand->cont_read_possible = false; + memset(&info->secondary_op_tmpl, 0, sizeof(info->secondary_op_tmpl)); info->length = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand); @@ -1238,12 +1259,31 @@ static int spinand_create_dirmap(struct spinand_device *spinand, struct nand_device *nand = spinand_to_nand(spinand); struct spi_mem_dirmap_info info = { 0 }; struct spi_mem_dirmap_desc *desc; + bool enable_ecc = false, secondary_op = false; + + if (nand->ecc.engine->integration == NAND_ECC_ENGINE_INTEGRATION_PIPELINED) + enable_ecc = true; + + if (spinand->cont_read_possible && spinand->op_templates->cont_read_cache) + secondary_op = true; + + /* + * Continuous read implies that only the main data is retrieved, backed + * by an on-die ECC engine. It is not possible to use a pipelind ECC + * engine with continuous read. + */ + if (enable_ecc && secondary_op) { + secondary_op = false; + spinand->cont_read_possible = false; + } /* The plane number is passed in MSB just above the column address */ info.offset = plane << fls(nand->memorg.pagesize); + /* Write descriptor */ info.length = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand); - info.op_tmpl = *spinand->op_templates->update_cache; + info.primary_op_tmpl = *spinand->op_templates->update_cache; + info.primary_op_tmpl.data.ecc = enable_ecc; desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev, spinand->spimem, &info); if (IS_ERR(desc)) @@ -1251,37 +1291,18 @@ static int spinand_create_dirmap(struct spinand_device *spinand, spinand->dirmaps[plane].wdesc = desc; - info.op_tmpl = *spinand->op_templates->read_cache; - desc = spinand_create_rdesc(spinand, &info); - if (IS_ERR(desc)) - return PTR_ERR(desc); - - spinand->dirmaps[plane].rdesc = desc; - - if (nand->ecc.engine->integration != NAND_ECC_ENGINE_INTEGRATION_PIPELINED) { - spinand->dirmaps[plane].wdesc_ecc = spinand->dirmaps[plane].wdesc; - spinand->dirmaps[plane].rdesc_ecc = spinand->dirmaps[plane].rdesc; - - return 0; + /* Read descriptor */ + info.primary_op_tmpl = *spinand->op_templates->read_cache; + info.primary_op_tmpl.data.ecc = enable_ecc; + if (secondary_op) { + info.secondary_op_tmpl = *spinand->op_templates->cont_read_cache; + info.secondary_op_tmpl.data.ecc = enable_ecc; } - - info.length = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand); - info.op_tmpl = *spinand->op_templates->update_cache; - info.op_tmpl.data.ecc = true; - desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev, - spinand->spimem, &info); - if (IS_ERR(desc)) - return PTR_ERR(desc); - - spinand->dirmaps[plane].wdesc_ecc = desc; - - info.op_tmpl = *spinand->op_templates->read_cache; - info.op_tmpl.data.ecc = true; desc = spinand_create_rdesc(spinand, &info); if (IS_ERR(desc)) return PTR_ERR(desc); - spinand->dirmaps[plane].rdesc_ecc = desc; + spinand->dirmaps[plane].rdesc = desc; return 0; } @@ -1307,6 +1328,22 @@ static int spinand_create_dirmaps(struct spinand_device *spinand) return 0; } +static int spinand_randomizer_init(struct spinand_device *spinand) +{ + struct device_node *np = spinand->spimem->spi->dev.of_node; + u32 rand_val; + int ret; + + if (!spinand->set_randomizer) + return 0; + + ret = of_property_read_u32(np, "nand-randomizer", &rand_val); + if (ret) + return 0; + + return spinand->set_randomizer(spinand, rand_val); +} + static const struct nand_ops spinand_ops = { .erase = spinand_erase, .markbad = spinand_markbad, @@ -1407,7 +1444,7 @@ static void spinand_manufacturer_cleanup(struct spinand_device *spinand) return spinand->manufacturer->ops->cleanup(spinand); } -static bool spinand_op_is_odtr(const struct spi_mem_op *op) +bool spinand_op_is_odtr(const struct spi_mem_op *op) { return op->cmd.dtr && op->cmd.buswidth == 8; } @@ -1489,9 +1526,13 @@ static int spinand_init_odtr_instruction_set(struct spinand_device *spinand) if (!spi_mem_supports_op(spinand->spimem, &tmpl->blk_erase)) return -EOPNOTSUPP; - tmpl->page_read = (struct spi_mem_op)SPINAND_PAGE_READ_8D_8D_0_OP(0); - if (!spi_mem_supports_op(spinand->spimem, &tmpl->page_read)) + if (spinand->flags & SPINAND_ODTR_PACKED_PAGE_READ) + tmpl->page_read = (struct spi_mem_op)SPINAND_PAGE_READ_PACKED_8D_8D_0_OP(0); + else + tmpl->page_read = (struct spi_mem_op)SPINAND_PAGE_READ_8D_8D_0_OP(0); + if (!spi_mem_supports_op(spinand->spimem, &tmpl->page_read)) { return -EOPNOTSUPP; + } tmpl->prog_exec = (struct spi_mem_op)SPINAND_PROG_EXEC_8D_8D_0_OP(0); if (!spi_mem_supports_op(spinand->spimem, &tmpl->prog_exec)) @@ -1594,6 +1635,7 @@ int spinand_match_and_init(struct spinand_device *spinand, spinand->user_otp = &table[i].user_otp; spinand->read_retries = table[i].read_retries; spinand->set_read_retry = table[i].set_read_retry; + spinand->set_randomizer = table[i].set_randomizer; /* I/O variants selection with single-spi SDR commands */ @@ -1622,6 +1664,33 @@ int spinand_match_and_init(struct spinand_device *spinand, if (ret) return ret; + if (info->op_variants.cont_read_cache) { + op = spinand_select_op_variant(spinand, SSDR, + info->op_variants.cont_read_cache); + if (op) { + const struct spi_mem_op *read_op; + + read_op = spinand->ssdr_op_templates.read_cache; + + /* + * Sometimes the fastest continuous read variant may not + * be supported. In this case, prefer to use the fastest + * read from cache variant and disable continuous reads. + */ + if (read_op->cmd.buswidth > op->cmd.buswidth || + (read_op->cmd.dtr && !op->cmd.dtr) || + read_op->addr.buswidth > op->addr.buswidth || + (read_op->addr.dtr && !op->addr.dtr) || + read_op->data.buswidth > op->data.buswidth || + (read_op->data.dtr && !op->data.dtr)) + spinand->cont_read_possible = false; + else + spinand->ssdr_op_templates.cont_read_cache = op; + } else { + spinand->cont_read_possible = false; + } + } + /* I/O variants selection with octo-spi DDR commands (optional) */ ret = spinand_init_odtr_instruction_set(spinand); @@ -1644,6 +1713,15 @@ int spinand_match_and_init(struct spinand_device *spinand, info->op_variants.update_cache); spinand->odtr_op_templates.update_cache = op; + if (info->op_variants.cont_read_cache) { + op = spinand_select_op_variant(spinand, ODTR, + info->op_variants.cont_read_cache); + if (op) + spinand->odtr_op_templates.cont_read_cache = op; + else + spinand->cont_read_possible = false; + } + return 0; } @@ -1881,6 +1959,9 @@ static int spinand_init(struct spinand_device *spinand) * ECC initialization must have happened previously. */ spinand_cont_read_init(spinand); + ret = spinand_randomizer_init(spinand); + if (ret) + goto err_cleanup_nanddev; mtd->_read_oob = spinand_mtd_read; mtd->_write_oob = spinand_mtd_write; diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c index 67cafa1bb8ef..7dfcc34e9b72 100644 --- a/drivers/mtd/nand/spi/macronix.c +++ b/drivers/mtd/nand/spi/macronix.c @@ -14,6 +14,8 @@ #define MACRONIX_ECCSR_BF_LAST_PAGE(eccsr) FIELD_GET(GENMASK(3, 0), eccsr) #define MACRONIX_ECCSR_BF_ACCUMULATED_PAGES(eccsr) FIELD_GET(GENMASK(7, 4), eccsr) #define MACRONIX_CFG_CONT_READ BIT(2) +#define MACRONIX_CFG_RANDOMIZER_EN BIT(1) +#define MACRONIX_FEATURE_ADDR_RANDOMIZER 0x10 #define MACRONIX_FEATURE_ADDR_READ_RETRY 0x70 #define MACRONIX_NUM_READ_RETRY_MODES 5 @@ -170,6 +172,12 @@ static int macronix_set_read_retry(struct spinand_device *spinand, return spi_mem_exec_op(spinand->spimem, &op); } +static int macronix_set_randomizer(struct spinand_device *spinand, bool enable) +{ + return spinand_write_reg_op(spinand, MACRONIX_FEATURE_ADDR_RANDOMIZER, + enable ? MACRONIX_CFG_RANDOMIZER_EN : 0); +} + static const struct spinand_info macronix_spinand_table[] = { SPINAND_INFO("MX35LF1GE4AB", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x12), @@ -231,7 +239,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX35LF2G24AD", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x24, 0x03), NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 2, 1, 1), @@ -243,7 +252,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_HAS_PROG_PLANE_SELECT_BIT, SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX35LF2G24AD-Z4I8", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x64, 0x03), NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), @@ -254,7 +264,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX35LF4G24AD", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x35, 0x03), NAND_MEMORG(1, 4096, 256, 64, 2048, 40, 2, 1, 1), @@ -266,7 +277,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_HAS_PROG_PLANE_SELECT_BIT, SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX35LF4G24AD-Z4I8", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x75, 0x03), NAND_MEMORG(1, 4096, 256, 64, 2048, 40, 1, 1, 1), @@ -277,7 +289,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX31LF1GE4BC", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x1e), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), @@ -327,7 +340,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, macronix_ecc_get_status), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX35UF4G24AD-Z4I8", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xf5, 0x03), NAND_MEMORG(1, 4096, 256, 64, 2048, 40, 1, 1, 1), @@ -340,7 +354,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, macronix_ecc_get_status), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX35UF4GE4AD", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xb7, 0x03), NAND_MEMORG(1, 4096, 256, 64, 2048, 40, 1, 1, 1), @@ -381,7 +396,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, macronix_ecc_get_status), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX35UF2G24AD-Z4I8", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xe4, 0x03), NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), @@ -394,7 +410,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, macronix_ecc_get_status), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX35UF2GE4AD", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xa6, 0x03), NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), @@ -444,7 +461,8 @@ static const struct spinand_info macronix_spinand_table[] = { SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, macronix_ecc_get_status), SPINAND_READ_RETRY(MACRONIX_NUM_READ_RETRY_MODES, - macronix_set_read_retry)), + macronix_set_read_retry), + SPINAND_RANDOMIZER(macronix_set_randomizer)), SPINAND_INFO("MX35UF1GE4AD", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x96, 0x03), NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1), diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index ad22774096e6..9b78c1e6cbc9 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -15,9 +15,11 @@ #define SPINAND_MFR_WINBOND 0xEF +#define WINBOND_CFG_HFREQ BIT(0) #define WINBOND_CFG_BUF_READ BIT(3) #define W25N04KV_STATUS_ECC_5_8_BITFLIPS (3 << 4) +#define W25W35NXXJW_STATUS_ECC_MULT_UNCOR (3 << 4) #define W25N0XJW_SR4 0xD0 #define W25N0XJW_SR4_HS BIT(2) @@ -30,6 +32,105 @@ #define W35N01JW_VCR_DUMMY_CLOCK_REG 0x01 /* + * Winbond chips ignore the address bytes during continuous reads, and + * because the dummy cycles are enough they indicate dropping the + * address cycles from the continuous read from cache variants. This is + * very poorly supported by SPI controller drivers which are "wired" to + * always at least provide the column. Keep using address cycles, but + * reduce the number of dummy cycles accordingly. + */ +#define WINBOND_CONT_READ_FROM_CACHE_FAST_1S_1S_1S_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1), \ + SPI_MEM_OP_ADDR(1, 0, 1), \ + SPI_MEM_OP_DUMMY(ndummy - 1, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_1D_1D_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0d, 1), \ + SPI_MEM_DTR_OP_ADDR(2, 0, 1), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 1), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 1), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_1S_2S_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1), \ + SPI_MEM_OP_ADDR(1, 0, 1), \ + SPI_MEM_OP_DUMMY(ndummy - 1, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 2), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_2S_2S_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1), \ + SPI_MEM_OP_ADDR(1, 0, 2), \ + SPI_MEM_OP_DUMMY(ndummy - 1, 2), \ + SPI_MEM_OP_DATA_IN(len, buf, 2), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_2D_2D_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xbd, 1), \ + SPI_MEM_DTR_OP_ADDR(1, 0, 2), \ + SPI_MEM_DTR_OP_DUMMY(ndummy - 1, 2), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 2), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_1S_4S_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1), \ + SPI_MEM_OP_ADDR(1, 0, 1), \ + SPI_MEM_OP_DUMMY(ndummy - 1, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 4), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_1D_4D_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x6d, 1), \ + SPI_MEM_DTR_OP_ADDR(1, 0, 1), \ + SPI_MEM_DTR_OP_DUMMY(ndummy - 1, 1), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 4), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_4S_4S_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1), \ + SPI_MEM_OP_ADDR(1, 0, 4), \ + SPI_MEM_OP_DUMMY(ndummy - 1, 4), \ + SPI_MEM_OP_DATA_IN(len, buf, 4), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_4D_4D_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xed, 1), \ + SPI_MEM_DTR_OP_ADDR(1, 0, 4), \ + SPI_MEM_DTR_OP_DUMMY(ndummy - 1, 4), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 4), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_1S_8S_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x8b, 1), \ + SPI_MEM_OP_ADDR(1, 0, 1), \ + SPI_MEM_OP_DUMMY(ndummy - 1, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 8), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_1D_8D_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x9d, 1), \ + SPI_MEM_DTR_OP_ADDR(1, 0, 1), \ + SPI_MEM_DTR_OP_DUMMY(ndummy - 1, 1), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 8), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_1S_8S_8S_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xcb, 1), \ + SPI_MEM_OP_ADDR(1, 0, 8), \ + SPI_MEM_OP_DUMMY(ndummy - 1, 8), \ + SPI_MEM_OP_DATA_IN(len, buf, 8), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +#define WINBOND_CONT_READ_FROM_CACHE_8D_8D_8D_OP(ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_DTR_OP_RPT_CMD(0x9d, 8), \ + SPI_MEM_DTR_OP_ADDR(2, 0, 8), \ + SPI_MEM_DTR_OP_DUMMY(ndummy - 2, 8), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 8), \ + SPI_MEM_OP_MAX_FREQ(freq)) + +/* * "X2" in the core is equivalent to "dual output" in the datasheets, * "X4" in the core is equivalent to "quad output" in the datasheets. * Quad and octal capable chips feature an absolute maximum frequency of 166MHz. @@ -49,6 +150,19 @@ static SPINAND_OP_VARIANTS(read_cache_octal_variants, SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0), SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0)); +static SPINAND_OP_VARIANTS(cont_read_cache_octal_variants, + WINBOND_CONT_READ_FROM_CACHE_8D_8D_8D_OP(24, NULL, 0, 120 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_8D_8D_8D_OP(16, NULL, 0, 86 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_1D_8D_OP(3, NULL, 0, 120 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_1D_8D_OP(2, NULL, 0, 105 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_8S_8S_OP(20, NULL, 0, 0), + WINBOND_CONT_READ_FROM_CACHE_1S_8S_8S_OP(16, NULL, 0, 162 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_8S_8S_OP(12, NULL, 0, 124 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_8S_8S_OP(8, NULL, 0, 86 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_1S_8S_OP(2, NULL, 0, 0), + WINBOND_CONT_READ_FROM_CACHE_1S_1S_8S_OP(1, NULL, 0, 133 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_FAST_1S_1S_1S_OP(1, NULL, 0, 0)); + static SPINAND_OP_VARIANTS(write_cache_octal_variants, SPINAND_PROG_LOAD_8D_8D_8D_OP(true, 0, NULL, 0), SPINAND_PROG_LOAD_1S_8S_8S_OP(true, 0, NULL, 0), @@ -75,6 +189,20 @@ static SPINAND_OP_VARIANTS(read_cache_dual_quad_dtr_variants, SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0), SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 54 * HZ_PER_MHZ)); +static SPINAND_OP_VARIANTS(cont_read_cache_dual_quad_dtr_variants, + WINBOND_CONT_READ_FROM_CACHE_1S_4D_4D_OP(11, NULL, 0, 80 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_1D_4D_OP(5, NULL, 0, 80 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_4S_4S_OP(7, NULL, 0, 0), + WINBOND_CONT_READ_FROM_CACHE_1S_4S_4S_OP(6, NULL, 0, 104 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_1S_4S_OP(4, NULL, 0, 0), + WINBOND_CONT_READ_FROM_CACHE_1S_2D_2D_OP(6, NULL, 0, 80 * HZ_PER_MHZ), + /* The 1S_1D_2D variant would require 4.5 dummy bytes, this is not possible */ + WINBOND_CONT_READ_FROM_CACHE_1S_2S_2S_OP(5, NULL, 0, 0), + WINBOND_CONT_READ_FROM_CACHE_1S_2S_2S_OP(4, NULL, 0, 104 * HZ_PER_MHZ), + WINBOND_CONT_READ_FROM_CACHE_1S_1S_2S_OP(4, NULL, 0, 0), + /* The 1S_1D_1D variant would require 4.5 dummy bytes, this is not possible */ + WINBOND_CONT_READ_FROM_CACHE_FAST_1S_1S_1S_OP(4, NULL, 0, 0)); + static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 0), SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0), @@ -99,7 +227,7 @@ static SPINAND_OP_VARIANTS(update_cache_variants, #define SPINAND_WINBOND_WRITE_VCR_8D_8D_8D(reg, buf) \ SPI_MEM_OP(SPI_MEM_DTR_OP_RPT_CMD(0x81, 8), \ - SPI_MEM_DTR_OP_ADDR(4, reg, 8), \ + SPI_MEM_DTR_OP_ADDR(4, reg << 8, 8), \ SPI_MEM_OP_NO_DUMMY, \ SPI_MEM_DTR_OP_DATA_OUT(2, buf, 8)) @@ -326,45 +454,84 @@ static int w25n02kv_ecc_get_status(struct spinand_device *spinand, return -EINVAL; } +static int w25w35nxxjw_ecc_get_status(struct spinand_device *spinand, u8 status) +{ + switch (status & STATUS_ECC_MASK) { + case STATUS_ECC_NO_BITFLIPS: + return 0; + + case STATUS_ECC_HAS_BITFLIPS: + return 1; + + case STATUS_ECC_UNCOR_ERROR: + case W25W35NXXJW_STATUS_ECC_MULT_UNCOR: + return -EBADMSG; + + default: + break; + } + + return -EINVAL; +} + +static int w25n0xjw_set_sr4_hs(struct spinand_device *spinand, bool enable) +{ + int ret; + u8 sr4; + + ret = spinand_read_reg_op(spinand, W25N0XJW_SR4, &sr4); + if (ret) + return ret; + + if (enable) + sr4 |= W25N0XJW_SR4_HS; + else + sr4 &= ~W25N0XJW_SR4_HS; + + return spinand_write_reg_op(spinand, W25N0XJW_SR4, sr4); +} + +/* + * SDR dual and quad I/O operations over 104MHz require the HS bit to + * enable a few more dummy cycles. + */ +static bool w25n0xjw_op_needs_hs(const struct spi_mem_op *op) +{ + if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr) + return false; + else if (op->cmd.buswidth != 1 || op->addr.buswidth == 1) + return false; + else if (op->max_freq && op->max_freq <= 104 * HZ_PER_MHZ) + return false; + + return true; +} + static int w25n0xjw_hs_cfg(struct spinand_device *spinand, enum spinand_bus_interface iface) { const struct spi_mem_op *op; - bool hs; - u8 sr4; - int ret; if (iface != SSDR) return -EOPNOTSUPP; /* - * SDR dual and quad I/O operations over 104MHz require the HS bit to - * enable a few more dummy cycles. + * At this stage, we do not yet know the continuous read template, nor + * if there is going to be one. Let's assume the continuous read + * template will be selected with the same heuristics as the buffered + * read variant, as there cannot be a HS configuration mismatch between + * them. */ op = spinand->op_templates->read_cache; - if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr) - hs = false; - else if (op->cmd.buswidth != 1 || op->addr.buswidth == 1) - hs = false; - else if (op->max_freq && op->max_freq <= 104 * HZ_PER_MHZ) - hs = false; - else - hs = true; - - ret = spinand_read_reg_op(spinand, W25N0XJW_SR4, &sr4); - if (ret) - return ret; - if (hs) - sr4 |= W25N0XJW_SR4_HS; - else - sr4 &= ~W25N0XJW_SR4_HS; + return w25n0xjw_set_sr4_hs(spinand, w25n0xjw_op_needs_hs(op)); +} - ret = spinand_write_reg_op(spinand, W25N0XJW_SR4, sr4); - if (ret) - return ret; +static int w25n0xjw_set_cont_read(struct spinand_device *spinand, bool enable) +{ + u8 mask = enable ? 0 : WINBOND_CFG_BUF_READ; - return 0; + return spinand_upd_cfg(spinand, WINBOND_CFG_BUF_READ, mask); } static int w35n0xjw_write_vcr(struct spinand_device *spinand, u8 reg, u8 val) @@ -451,6 +618,18 @@ static int w35n0xjw_vcr_cfg(struct spinand_device *spinand, return 0; } +static int w35n0xjw_set_cont_read(struct spinand_device *spinand, bool enable) +{ + const struct spi_mem_op *cont_op = spinand->op_templates->cont_read_cache; + u8 mask = enable ? 0 : WINBOND_CFG_BUF_READ; + + if (cont_op && enable && spinand_op_is_odtr(cont_op) && + cont_op->max_freq >= 90 * HZ_PER_MHZ) + mask |= WINBOND_CFG_HFREQ; + + return spinand_upd_cfg(spinand, WINBOND_CFG_BUF_READ | WINBOND_CFG_HFREQ, mask); +} + static const struct spinand_info winbond_spinand_table[] = { /* 512M-bit densities */ SPINAND_INFO("W25N512GW", /* 1.8V */ @@ -485,12 +664,14 @@ static const struct spinand_info winbond_spinand_table[] = { SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xbc, 0x21), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), NAND_ECCREQ(1, 512), - SPINAND_INFO_OP_VARIANTS(&read_cache_dual_quad_dtr_variants, - &write_cache_variants, - &update_cache_variants), + SPINAND_INFO_OP_VARIANTS_WITH_CONT(&read_cache_dual_quad_dtr_variants, + &write_cache_variants, + &update_cache_variants, + &cont_read_cache_dual_quad_dtr_variants), SPINAND_HAS_QE_BIT, - SPINAND_ECCINFO(&w25n01jw_ooblayout, NULL), - SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg)), + SPINAND_ECCINFO(&w25n01jw_ooblayout, w25w35nxxjw_ecc_get_status), + SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg), + SPINAND_CONT_READ(w25n0xjw_set_cont_read)), SPINAND_INFO("W25N01KV", /* 3.3V */ SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xae, 0x21), NAND_MEMORG(1, 2048, 96, 64, 1024, 20, 1, 1, 1), @@ -504,35 +685,15 @@ static const struct spinand_info winbond_spinand_table[] = { SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdc, 0x21), NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 1, 1), NAND_ECCREQ(1, 512), - SPINAND_INFO_OP_VARIANTS(&read_cache_octal_variants, - &write_cache_octal_variants, - &update_cache_octal_variants), + SPINAND_INFO_OP_VARIANTS_WITH_CONT(&read_cache_octal_variants, + &write_cache_octal_variants, + &update_cache_octal_variants, + &cont_read_cache_octal_variants), 0, SPINAND_INFO_VENDOR_OPS(&winbond_w35_ops), - SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL), - SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg)), - SPINAND_INFO("W35N02JW", /* 1.8V */ - SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x22), - NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 2, 1), - NAND_ECCREQ(1, 512), - SPINAND_INFO_OP_VARIANTS(&read_cache_octal_variants, - &write_cache_octal_variants, - &update_cache_octal_variants), - 0, - SPINAND_INFO_VENDOR_OPS(&winbond_w35_ops), - SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL), - SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg)), - SPINAND_INFO("W35N04JW", /* 1.8V */ - SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x23), - NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 4, 1), - NAND_ECCREQ(1, 512), - SPINAND_INFO_OP_VARIANTS(&read_cache_octal_variants, - &write_cache_octal_variants, - &update_cache_octal_variants), - 0, - SPINAND_INFO_VENDOR_OPS(&winbond_w35_ops), - SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL), - SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg)), + SPINAND_ECCINFO(&w35n01jw_ooblayout, w25w35nxxjw_ecc_get_status), + SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg), + SPINAND_CONT_READ(w35n0xjw_set_cont_read)), /* 2G-bit densities */ SPINAND_INFO("W25M02GV", /* 2x1G-bit 3.3V */ SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xab, 0x21), @@ -549,12 +710,14 @@ static const struct spinand_info winbond_spinand_table[] = { SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xbf, 0x22), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 2, 1), NAND_ECCREQ(1, 512), - SPINAND_INFO_OP_VARIANTS(&read_cache_dual_quad_dtr_variants, - &write_cache_variants, - &update_cache_variants), + SPINAND_INFO_OP_VARIANTS_WITH_CONT(&read_cache_dual_quad_dtr_variants, + &write_cache_variants, + &update_cache_variants, + &cont_read_cache_dual_quad_dtr_variants), SPINAND_HAS_QE_BIT, - SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL), - SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg)), + SPINAND_ECCINFO(&w25m02gv_ooblayout, w25w35nxxjw_ecc_get_status), + SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg), + SPINAND_CONT_READ(w25n0xjw_set_cont_read)), SPINAND_INFO("W25N02KV", /* 3.3V */ SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xaa, 0x22), NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), @@ -573,6 +736,19 @@ static const struct spinand_info winbond_spinand_table[] = { &update_cache_variants), 0, SPINAND_ECCINFO(&w25n02kv_ooblayout, w25n02kv_ecc_get_status)), + SPINAND_INFO("W35N02JW", /* 1.8V */ + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x22), + NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 2, 1), + NAND_ECCREQ(1, 512), + SPINAND_INFO_OP_VARIANTS_WITH_CONT(&read_cache_octal_variants, + &write_cache_octal_variants, + &update_cache_octal_variants, + &cont_read_cache_octal_variants), + SPINAND_ODTR_PACKED_PAGE_READ, + SPINAND_INFO_VENDOR_OPS(&winbond_w35_ops), + SPINAND_ECCINFO(&w35n01jw_ooblayout, w25w35nxxjw_ecc_get_status), + SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg), + SPINAND_CONT_READ(w35n0xjw_set_cont_read)), /* 4G-bit densities */ SPINAND_INFO("W25N04KV", /* 3.3V */ SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xaa, 0x23), @@ -592,6 +768,19 @@ static const struct spinand_info winbond_spinand_table[] = { &update_cache_variants), 0, SPINAND_ECCINFO(&w25n02kv_ooblayout, w25n02kv_ecc_get_status)), + SPINAND_INFO("W35N04JW", /* 1.8V */ + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x23), + NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 4, 1), + NAND_ECCREQ(1, 512), + SPINAND_INFO_OP_VARIANTS_WITH_CONT(&read_cache_octal_variants, + &write_cache_octal_variants, + &update_cache_octal_variants, + &cont_read_cache_octal_variants), + SPINAND_ODTR_PACKED_PAGE_READ, + SPINAND_INFO_VENDOR_OPS(&winbond_w35_ops), + SPINAND_ECCINFO(&w35n01jw_ooblayout, w25w35nxxjw_ecc_get_status), + SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg), + SPINAND_CONT_READ(w35n0xjw_set_cont_read)), }; static int winbond_spinand_init(struct spinand_device *spinand) diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index b25d1a870a22..ccf4396cdcd0 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -3711,14 +3711,15 @@ EXPORT_SYMBOL_GPL(spi_nor_scan); static int spi_nor_create_read_dirmap(struct spi_nor *nor) { struct spi_mem_dirmap_info info = { - .op_tmpl = SPI_MEM_OP(SPI_MEM_OP_CMD(nor->read_opcode, 0), - SPI_MEM_OP_ADDR(nor->addr_nbytes, 0, 0), - SPI_MEM_OP_DUMMY(nor->read_dummy, 0), - SPI_MEM_OP_DATA_IN(0, NULL, 0)), + .op_tmpl = &info.primary_op_tmpl, + .primary_op_tmpl = SPI_MEM_OP(SPI_MEM_OP_CMD(nor->read_opcode, 0), + SPI_MEM_OP_ADDR(nor->addr_nbytes, 0, 0), + SPI_MEM_OP_DUMMY(nor->read_dummy, 0), + SPI_MEM_OP_DATA_IN(0, NULL, 0)), .offset = 0, .length = nor->params->size, }; - struct spi_mem_op *op = &info.op_tmpl; + struct spi_mem_op *op = info.op_tmpl; spi_nor_spimem_setup_op(nor, op, nor->read_proto); @@ -3742,14 +3743,15 @@ static int spi_nor_create_read_dirmap(struct spi_nor *nor) static int spi_nor_create_write_dirmap(struct spi_nor *nor) { struct spi_mem_dirmap_info info = { - .op_tmpl = SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 0), - SPI_MEM_OP_ADDR(nor->addr_nbytes, 0, 0), - SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(0, NULL, 0)), + .op_tmpl = &info.primary_op_tmpl, + .primary_op_tmpl = SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 0), + SPI_MEM_OP_ADDR(nor->addr_nbytes, 0, 0), + SPI_MEM_OP_NO_DUMMY, + SPI_MEM_OP_DATA_OUT(0, NULL, 0)), .offset = 0, .length = nor->params->size, }; - struct spi_mem_op *op = &info.op_tmpl; + struct spi_mem_op *op = info.op_tmpl; if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second) op->addr.nbytes = 0; diff --git a/drivers/mtd/spi-nor/debugfs.c b/drivers/mtd/spi-nor/debugfs.c index e80c03dd5461..288e2866daed 100644 --- a/drivers/mtd/spi-nor/debugfs.c +++ b/drivers/mtd/spi-nor/debugfs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/array_size.h> #include <linux/debugfs.h> #include <linux/math64.h> #include <linux/mtd/spi-nor.h> @@ -98,7 +99,8 @@ static int spi_nor_params_show(struct seq_file *s, void *data) seq_printf(s, "address nbytes\t%u\n", nor->addr_nbytes); seq_puts(s, "flags\t\t"); - spi_nor_print_flags(s, nor->flags, snor_f_names, sizeof(snor_f_names)); + spi_nor_print_flags(s, nor->flags, snor_f_names, + ARRAY_SIZE(snor_f_names)); seq_puts(s, "\n"); seq_puts(s, "\nopcodes\n"); diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 0df3208783ad..da5866ba0699 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -529,6 +529,9 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, struct in6_addr saddr; struct socket *sock = rcu_dereference(bareudp->sock); + if (!sock) + return -ESHUTDOWN; + dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sock, 0, &saddr, &info->key, sport, bareudp->port, info->key.tos, diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index af7f74cfdc08..f0aa7d2f2171 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1029,6 +1029,7 @@ static void ad_cond_set_peer_notif(struct port *port) static void ad_mux_machine(struct port *port, bool *update_slave_arr) { struct bonding *bond = __get_bond_by_port(port); + struct aggregator *aggregator; mux_states_t last_state; /* keep current State Machine state to compare later if it was @@ -1036,6 +1037,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) */ last_state = port->sm_mux_state; + aggregator = rcu_dereference(port->aggregator); if (port->sm_vars & AD_PORT_BEGIN) { port->sm_mux_state = AD_MUX_DETACHED; } else { @@ -1055,7 +1057,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * cycle to update ready variable, we check * READY_N and update READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); port->sm_mux_state = AD_MUX_DETACHED; break; } @@ -1070,7 +1072,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * update ready variable, we check READY_N and update * READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); /* if the wait_while_timer expired, and the port is * in READY state, move to ATTACHED state @@ -1086,7 +1088,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) if ((port->sm_vars & AD_PORT_SELECTED) && (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) && !__check_agg_selection_timer(port)) { - if (port->aggregator->is_active) { + if (aggregator->is_active) { int state = AD_MUX_COLLECTING_DISTRIBUTING; if (!bond->params.coupled_control) @@ -1102,9 +1104,9 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * cycle to update ready variable, we check * READY_N and update READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); port->sm_mux_state = AD_MUX_DETACHED; - } else if (port->aggregator->is_active) { + } else if (aggregator->is_active) { port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; } @@ -1115,7 +1117,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * sure that a collecting distributing * port in an active aggregator is enabled */ - if (port->aggregator->is_active && + if (aggregator->is_active && !__port_is_collecting_distributing(port)) { __enable_port(port); *update_slave_arr = true; @@ -1134,7 +1136,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) */ struct slave *slave = port->slave; - if (port->aggregator->is_active && + if (aggregator->is_active && bond_is_slave_rx_disabled(slave)) { ad_enable_collecting(port); *update_slave_arr = true; @@ -1154,8 +1156,8 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * sure that a collecting distributing * port in an active aggregator is enabled */ - if (port->aggregator && - port->aggregator->is_active && + if (aggregator && + aggregator->is_active && !__port_is_collecting_distributing(port)) { __enable_port(port); *update_slave_arr = true; @@ -1187,7 +1189,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) port->sm_mux_timer_counter = __ad_timer_to_ticks(AD_WAIT_WHILE_TIMER, 0); break; case AD_MUX_ATTACHED: - if (port->aggregator->is_active) + if (aggregator->is_active) port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; else @@ -1561,9 +1563,9 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) bond = __get_bond_by_port(port); /* if the port is connected to other aggregator, detach it */ - if (port->aggregator) { + temp_aggregator = rcu_dereference(port->aggregator); + if (temp_aggregator) { /* detach the port from its former aggregator */ - temp_aggregator = port->aggregator; for (curr_port = temp_aggregator->lag_ports; curr_port; last_port = curr_port, curr_port = curr_port->next_port_in_aggregator) { @@ -1586,7 +1588,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) /* clear the port's relations to this * aggregator */ - port->aggregator = NULL; + RCU_INIT_POINTER(port->aggregator, NULL); port->next_port_in_aggregator = NULL; port->actor_port_aggregator_identifier = 0; @@ -1609,7 +1611,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) port->slave->bond->dev->name, port->slave->dev->name, port->actor_port_number, - port->aggregator->aggregator_identifier); + temp_aggregator->aggregator_identifier); } } /* search on all aggregators for a suitable aggregator for this port */ @@ -1633,15 +1635,15 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) ) ) { /* attach to the founded aggregator */ - port->aggregator = aggregator; + rcu_assign_pointer(port->aggregator, aggregator); port->actor_port_aggregator_identifier = - port->aggregator->aggregator_identifier; + aggregator->aggregator_identifier; port->next_port_in_aggregator = aggregator->lag_ports; - port->aggregator->num_of_ports++; + aggregator->num_of_ports++; aggregator->lag_ports = port; slave_dbg(bond->dev, slave->dev, "Port %d joined LAG %d (existing LAG)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; @@ -1656,39 +1658,40 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) if (!found) { if (free_aggregator) { /* assign port a new aggregator */ - port->aggregator = free_aggregator; port->actor_port_aggregator_identifier = - port->aggregator->aggregator_identifier; + free_aggregator->aggregator_identifier; /* update the new aggregator's parameters * if port was responsed from the end-user */ if (port->actor_oper_port_key & AD_DUPLEX_KEY_MASKS) /* if port is full duplex */ - port->aggregator->is_individual = false; + free_aggregator->is_individual = false; else - port->aggregator->is_individual = true; + free_aggregator->is_individual = true; - port->aggregator->actor_admin_aggregator_key = + free_aggregator->actor_admin_aggregator_key = port->actor_admin_port_key; - port->aggregator->actor_oper_aggregator_key = + free_aggregator->actor_oper_aggregator_key = port->actor_oper_port_key; - port->aggregator->partner_system = + free_aggregator->partner_system = port->partner_oper.system; - port->aggregator->partner_system_priority = + free_aggregator->partner_system_priority = port->partner_oper.system_priority; - port->aggregator->partner_oper_aggregator_key = port->partner_oper.key; - port->aggregator->receive_state = 1; - port->aggregator->transmit_state = 1; - port->aggregator->lag_ports = port; - port->aggregator->num_of_ports++; + free_aggregator->partner_oper_aggregator_key = port->partner_oper.key; + free_aggregator->receive_state = 1; + free_aggregator->transmit_state = 1; + free_aggregator->lag_ports = port; + free_aggregator->num_of_ports++; + + rcu_assign_pointer(port->aggregator, free_aggregator); /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; slave_dbg(bond->dev, port->slave->dev, "Port %d joined LAG %d (new LAG)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + free_aggregator->aggregator_identifier); } else { slave_err(bond->dev, port->slave->dev, "Port %d did not find a suitable aggregator\n", @@ -1700,13 +1703,12 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) * in all aggregator's ports, else set ready=FALSE in all * aggregator's ports */ - __set_agg_ports_ready(port->aggregator, - __agg_ports_are_ready(port->aggregator)); + aggregator = rcu_dereference(port->aggregator); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); - aggregator = __get_first_agg(port); - ad_agg_selection_logic(aggregator, update_slave_arr); + ad_agg_selection_logic(__get_first_agg(port), update_slave_arr); - if (!port->aggregator->is_active) + if (!aggregator->is_active) port->actor_oper_port_state &= ~LACP_STATE_SYNCHRONIZATION; } @@ -2075,13 +2077,15 @@ static void ad_initialize_port(struct port *port, const struct bond_params *bond */ static void ad_enable_collecting(struct port *port) { - if (port->aggregator->is_active) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator->is_active) { struct slave *slave = port->slave; slave_dbg(slave->bond->dev, slave->dev, "Enabling collecting on port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __enable_collecting_port(port); } } @@ -2093,11 +2097,13 @@ static void ad_enable_collecting(struct port *port) */ static void ad_disable_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator && __agg_has_partner(port->aggregator)) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator && __agg_has_partner(aggregator)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Disabling distributing on port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __disable_distributing_port(port); /* Slave array needs an update */ *update_slave_arr = true; @@ -2114,11 +2120,13 @@ static void ad_disable_distributing(struct port *port, bool *update_slave_arr) static void ad_enable_collecting_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator->is_active) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator->is_active) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Enabling port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __enable_port(port); /* Slave array needs update */ *update_slave_arr = true; @@ -2135,11 +2143,13 @@ static void ad_enable_collecting_distributing(struct port *port, static void ad_disable_collecting_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator && __agg_has_partner(port->aggregator)) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator && __agg_has_partner(aggregator)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Disabling port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __disable_port(port); /* Slave array needs an update */ *update_slave_arr = true; @@ -2379,7 +2389,7 @@ void bond_3ad_unbind_slave(struct slave *slave) */ for (temp_port = aggregator->lag_ports; temp_port; temp_port = temp_port->next_port_in_aggregator) { - temp_port->aggregator = new_aggregator; + rcu_assign_pointer(temp_port->aggregator, new_aggregator); temp_port->actor_port_aggregator_identifier = new_aggregator->aggregator_identifier; } @@ -2848,15 +2858,16 @@ out: int __bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) { - struct aggregator *aggregator = NULL; + struct aggregator *aggregator = NULL, *tmp; struct list_head *iter; struct slave *slave; struct port *port; bond_for_each_slave_rcu(bond, slave, iter) { port = &(SLAVE_AD_INFO(slave)->port); - if (port->aggregator && port->aggregator->is_active) { - aggregator = port->aggregator; + tmp = rcu_dereference(port->aggregator); + if (tmp && tmp->is_active) { + aggregator = tmp; break; } } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c7baa5c4bf40..af82a3df2c5d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1433,7 +1433,7 @@ static void bond_poll_controller(struct net_device *bond_dev) if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg = - SLAVE_AD_INFO(slave)->port.aggregator; + rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (agg && agg->aggregator_identifier != ad_info.aggregator_id) @@ -5179,15 +5179,16 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) spin_unlock_bh(&bond->mode_lock); agg_id = ad_info.aggregator_id; } + rcu_read_lock(); bond_for_each_slave(bond, slave, iter) { if (skipslave == slave) continue; all_slaves->arr[all_slaves->count++] = slave; if (BOND_MODE(bond) == BOND_MODE_8023AD) { - struct aggregator *agg; + const struct aggregator *agg; - agg = SLAVE_AD_INFO(slave)->port.aggregator; + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (!agg || agg->aggregator_identifier != agg_id) continue; } @@ -5199,6 +5200,7 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) usable_slaves->arr[usable_slaves->count++] = slave; } + rcu_read_unlock(); bond_set_slave_arr(bond, usable_slaves, all_slaves); return ret; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index ea1a80e658ae..c7d3e0602c83 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -66,27 +66,29 @@ static int bond_fill_slave_info(struct sk_buff *skb, const struct port *ad_port; ad_port = &SLAVE_AD_INFO(slave)->port; - agg = SLAVE_AD_INFO(slave)->port.aggregator; + rcu_read_lock(); + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (agg) { if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, agg->aggregator_identifier)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, ad_port->actor_oper_port_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, ad_port->partner_oper.port_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_ACTOR_STATE, ad_port->sm_churn_actor_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_PARTNER_STATE, ad_port->sm_churn_partner_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; } + rcu_read_unlock(); if (nla_put_u16(skb, IFLA_BOND_SLAVE_ACTOR_PORT_PRIO, SLAVE_AD_INFO(slave)->port_priority)) @@ -95,6 +97,8 @@ static int bond_fill_slave_info(struct sk_buff *skb, return 0; +nla_put_failure_rcu: + rcu_read_unlock(); nla_put_failure: return -EMSGSIZE; } diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index e34f80305191..3714aab1a3d9 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -188,6 +188,7 @@ static void bond_info_show_master(struct seq_file *seq) } } +/* Note: runs under rcu_read_lock() */ static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave) { @@ -214,7 +215,7 @@ static void bond_info_show_slave(struct seq_file *seq, if (BOND_MODE(bond) == BOND_MODE_8023AD) { const struct port *port = &SLAVE_AD_INFO(slave)->port; - const struct aggregator *agg = port->aggregator; + const struct aggregator *agg = rcu_dereference(port->aggregator); if (agg) { seq_printf(seq, "Aggregator ID: %d\n", diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c index 36d0e8440b5b..fc6fe7181789 100644 --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -62,10 +62,15 @@ static ssize_t ad_aggregator_id_show(struct slave *slave, char *buf) const struct aggregator *agg; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { - agg = SLAVE_AD_INFO(slave)->port.aggregator; - if (agg) - return sysfs_emit(buf, "%d\n", - agg->aggregator_identifier); + rcu_read_lock(); + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); + if (agg) { + ssize_t res = sysfs_emit(buf, "%d\n", + agg->aggregator_identifier); + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); } return sysfs_emit(buf, "N/A\n"); @@ -78,7 +83,7 @@ static ssize_t ad_actor_oper_port_state_show(struct slave *slave, char *buf) if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; - if (ad_port->aggregator) + if (rcu_access_pointer(ad_port->aggregator)) return sysfs_emit(buf, "%u\n", ad_port->actor_oper_port_state); } @@ -93,7 +98,7 @@ static ssize_t ad_partner_oper_port_state_show(struct slave *slave, char *buf) if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; - if (ad_port->aggregator) + if (rcu_access_pointer(ad_port->aggregator)) return sysfs_emit(buf, "%u\n", ad_port->partner_oper.port_state); } diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 2bb0a3ff9810..f8b3d53bccad 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -847,13 +847,24 @@ static void airoha_qdma_wake_netdev_txqs(struct airoha_queue *q) { struct airoha_qdma *qdma = q->qdma; struct airoha_eth *eth = qdma->eth; - int i; + int i, qid = q - &qdma->q_tx[0]; for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; + int j; + + if (!port) + continue; + + if (port->qdma != qdma) + continue; - if (port && port->qdma == qdma) - netif_tx_wake_all_queues(port->dev); + for (j = 0; j < port->dev->num_tx_queues; j++) { + if (airoha_qdma_get_txq(qdma, j) != qid) + continue; + + netif_wake_subqueue(port->dev, j); + } } q->txq_stopped = false; } @@ -929,10 +940,9 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) q->queued--; if (skb) { - u16 queue = skb_get_queue_mapping(skb); struct netdev_queue *txq; - txq = netdev_get_tx_queue(skb->dev, queue); + txq = skb_get_tx_queue(skb->dev, skb); netdev_tx_completed_queue(txq, 1, skb->len); dev_kfree_skb_any(skb); } @@ -1737,14 +1747,11 @@ static int airoha_dev_stop(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); struct airoha_qdma *qdma = port->qdma; - int i, err; + int i; netif_tx_disable(dev); - err = airoha_set_vip_for_gdm_port(port, false); - if (err) - return err; - - for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) + airoha_set_vip_for_gdm_port(port, false); + for (i = 0; i < dev->num_tx_queues; i++) netdev_tx_reset_subqueue(dev, i); airoha_set_gdm_port_fwd_cfg(qdma->eth, REG_GDM_FWD_CFG(port->id), @@ -1997,12 +2004,12 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct netdev_queue *txq; struct airoha_queue *q; LIST_HEAD(tx_list); + int i = 0, qid; void *data; - int i, qid; u16 index; u8 fport; - qid = skb_get_queue_mapping(skb) % ARRAY_SIZE(qdma->q_tx); + qid = airoha_qdma_get_txq(qdma, skb_get_queue_mapping(skb)); tag = airoha_get_dsa_tag(skb, dev); msg0 = FIELD_PREP(QDMA_ETH_TXMSG_CHAN_MASK, @@ -2039,7 +2046,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, spin_lock_bh(&q->lock); - txq = netdev_get_tx_queue(dev, qid); + txq = skb_get_tx_queue(dev, skb); nr_frags = 1 + skb_shinfo(skb)->nr_frags; if (q->queued + nr_frags >= q->ndesc) { @@ -2057,7 +2064,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, list); index = e - q->entry; - for (i = 0; i < nr_frags; i++) { + while (true) { struct airoha_qdma_desc *desc = &q->desc[index]; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t addr; @@ -2069,7 +2076,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, goto error_unmap; list_move_tail(&e->list, &tx_list); - e->skb = i ? NULL : skb; + e->skb = i == nr_frags - 1 ? skb : NULL; e->dma_addr = addr; e->dma_len = len; @@ -2088,6 +2095,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, WRITE_ONCE(desc->msg1, cpu_to_le32(msg1)); WRITE_ONCE(desc->msg2, cpu_to_le32(0xffff)); + if (++i == nr_frags) + break; + data = skb_frag_address(frag); len = skb_frag_size(frag); } @@ -2095,17 +2105,16 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, skb_tx_timestamp(skb); netdev_tx_sent_queue(txq, skb->len); + if (q->ndesc - q->queued < q->free_thr) { + netif_tx_stop_queue(txq); + q->txq_stopped = true; + } if (netif_xmit_stopped(txq) || !netdev_xmit_more()) airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, FIELD_PREP(TX_RING_CPU_IDX_MASK, index)); - if (q->ndesc - q->queued < q->free_thr) { - netif_tx_stop_queue(txq); - q->txq_stopped = true; - } - spin_unlock_bh(&q->lock); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index e389d2fe3b86..4fad3acc3ccf 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -631,6 +631,11 @@ u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val); #define airoha_qdma_clear(qdma, offset, val) \ airoha_rmw((qdma)->regs, (offset), (val), 0) +static inline u16 airoha_qdma_get_txq(struct airoha_qdma *qdma, u16 qid) +{ + return qid % ARRAY_SIZE(qdma->q_tx); +} + static inline bool airoha_is_lan_gdm_port(struct airoha_gdm_port *port) { /* GDM1 port on EN7581 SoC is connected to the lan dsa switch. diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 58cc3147afe2..73e051d26b9d 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1756,6 +1756,27 @@ static int ibmveth_set_mac_addr(struct net_device *dev, void *p) return 0; } +static netdev_features_t ibmveth_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + /* Some physical adapters do not support segmentation offload with + * MSS < 224. Disable GSO for such packets to avoid adapter freeze. + * Note: Single-segment packets (gso_segs == 1) don't need this check + * as they bypass the LSO path and are transmitted without segmentation. + */ + if (skb_is_gso(skb)) { + if (skb_shinfo(skb)->gso_size < IBMVETH_MIN_LSO_MSS) { + netdev_warn_once(dev, + "MSS %u too small for LSO, disabling GSO\n", + skb_shinfo(skb)->gso_size); + features &= ~NETIF_F_GSO_MASK; + } + } + + return vlan_features_check(skb, features); +} + static const struct net_device_ops ibmveth_netdev_ops = { .ndo_open = ibmveth_open, .ndo_stop = ibmveth_close, @@ -1767,6 +1788,7 @@ static const struct net_device_ops ibmveth_netdev_ops = { .ndo_set_features = ibmveth_set_features, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ibmveth_set_mac_addr, + .ndo_features_check = ibmveth_features_check, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ibmveth_poll_controller, #endif diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 068f99df133e..d87713668ed3 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -37,6 +37,7 @@ #define IBMVETH_ILLAN_IPV4_TCP_CSUM 0x0000000000000002UL #define IBMVETH_ILLAN_ACTIVE_TRUNK 0x0000000000000001UL +#define IBMVETH_MIN_LSO_MSS 224 /* Minimum MSS for LSO */ /* hcall macros */ #define h_register_logical_lan(ua, buflst, rxq, fltlst, mac) \ plpar_hcall_norets(H_REGISTER_LOGICAL_LAN, ua, buflst, rxq, fltlst, mac) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index e9fb0a0919e3..050f8241ef5e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -158,11 +158,10 @@ struct iavf_vlan { enum iavf_vlan_state_t { IAVF_VLAN_INVALID, IAVF_VLAN_ADD, /* filter needs to be added */ - IAVF_VLAN_IS_NEW, /* filter is new, wait for PF answer */ - IAVF_VLAN_ACTIVE, /* filter is accepted by PF */ - IAVF_VLAN_DISABLE, /* filter needs to be deleted by PF, then marked INACTIVE */ - IAVF_VLAN_INACTIVE, /* filter is inactive, we are in IFF_DOWN */ - IAVF_VLAN_REMOVE, /* filter needs to be removed from list */ + IAVF_VLAN_ADDING, /* ADD sent to PF, waiting for response */ + IAVF_VLAN_ACTIVE, /* PF confirmed, filter is in HW */ + IAVF_VLAN_REMOVE, /* filter queued for DEL from PF */ + IAVF_VLAN_REMOVING, /* DEL sent to PF, waiting for response */ }; struct iavf_vlan_filter { diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 3c1465cf0515..d2914c511e1e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -757,10 +757,10 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, adapter->num_vlan_filters++; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); } else if (f->state == IAVF_VLAN_REMOVE) { - /* Re-add the filter since we cannot tell whether the - * pending delete has already been processed by the PF. - * A duplicate add is harmless. - */ + /* DEL not yet sent to PF, cancel it */ + f->state = IAVF_VLAN_ACTIVE; + } else if (f->state == IAVF_VLAN_REMOVING) { + /* DEL already sent to PF, re-add after completion */ f->state = IAVF_VLAN_ADD; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); @@ -791,37 +791,19 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) list_del(&f->list); kfree(f); adapter->num_vlan_filters--; - } else { + } else if (f->state != IAVF_VLAN_REMOVING) { f->state = IAVF_VLAN_REMOVE; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); } + /* If REMOVING, DEL is already sent to PF; completion + * handler will free the filter when PF confirms. + */ } spin_unlock_bh(&adapter->mac_vlan_list_lock); } -/** - * iavf_restore_filters - * @adapter: board private structure - * - * Restore existing non MAC filters when VF netdev comes back up - **/ -static void iavf_restore_filters(struct iavf_adapter *adapter) -{ - struct iavf_vlan_filter *f; - - /* re-add all VLAN filters */ - spin_lock_bh(&adapter->mac_vlan_list_lock); - - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_INACTIVE) - f->state = IAVF_VLAN_ADD; - } - - spin_unlock_bh(&adapter->mac_vlan_list_lock); - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; -} /** * iavf_get_num_vlans_added - get number of VLANs added @@ -1246,13 +1228,12 @@ static void iavf_up_complete(struct iavf_adapter *adapter) } /** - * iavf_clear_mac_vlan_filters - Remove mac and vlan filters not sent to PF - * yet and mark other to be removed. + * iavf_clear_mac_filters - Remove MAC filters not sent to PF yet and mark + * others to be removed. * @adapter: board private structure **/ -static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) +static void iavf_clear_mac_filters(struct iavf_adapter *adapter) { - struct iavf_vlan_filter *vlf, *vlftmp; struct iavf_mac_filter *f, *ftmp; spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -1271,11 +1252,6 @@ static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) } } - /* disable all VLAN filters */ - list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, - list) - vlf->state = IAVF_VLAN_DISABLE; - spin_unlock_bh(&adapter->mac_vlan_list_lock); } @@ -1371,7 +1347,7 @@ void iavf_down(struct iavf_adapter *adapter) iavf_napi_disable_all(adapter); iavf_irq_disable(adapter); - iavf_clear_mac_vlan_filters(adapter); + iavf_clear_mac_filters(adapter); iavf_clear_cloud_filters(adapter); iavf_clear_fdir_filters(adapter); iavf_clear_adv_rss_conf(adapter); @@ -1388,8 +1364,6 @@ void iavf_down(struct iavf_adapter *adapter) */ if (!list_empty(&adapter->mac_filter_list)) adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; - if (!list_empty(&adapter->vlan_filter_list)) - adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; if (!list_empty(&adapter->cloud_filter_list)) adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; if (!list_empty(&adapter->fdir_list_head)) @@ -4494,8 +4468,6 @@ static int iavf_open(struct net_device *netdev) iavf_add_filter(adapter, adapter->hw.mac.addr); spin_unlock_bh(&adapter->mac_vlan_list_lock); - /* Restore filters that were removed with IFF_DOWN */ - iavf_restore_filters(adapter); iavf_restore_fdir_filters(adapter); iavf_configure(adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index a52c100dcbc5..4f2defd2331b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -746,7 +746,7 @@ static void iavf_vlan_add_reject(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_IS_NEW) { + if (f->state == IAVF_VLAN_ADDING) { list_del(&f->list); kfree(f); adapter->num_vlan_filters--; @@ -812,7 +812,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) if (f->state == IAVF_VLAN_ADD) { vvfl->vlan_id[i] = f->vlan.vid; i++; - f->state = IAVF_VLAN_IS_NEW; + f->state = IAVF_VLAN_ADDING; if (i == count) break; } @@ -874,7 +874,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vlan->tpid = f->vlan.tpid; i++; - f->state = IAVF_VLAN_IS_NEW; + f->state = IAVF_VLAN_ADDING; } } @@ -911,22 +911,12 @@ void iavf_del_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - /* since VLAN capabilities are not allowed, we dont want to send - * a VLAN delete request because it will most likely fail and - * create unnecessary errors/noise, so just free the VLAN - * filters marked for removal to enable bailing out before - * sending a virtchnl message - */ if (f->state == IAVF_VLAN_REMOVE && !VLAN_FILTERING_ALLOWED(adapter)) { list_del(&f->list); kfree(f); adapter->num_vlan_filters--; - } else if (f->state == IAVF_VLAN_DISABLE && - !VLAN_FILTERING_ALLOWED(adapter)) { - f->state = IAVF_VLAN_INACTIVE; - } else if (f->state == IAVF_VLAN_REMOVE || - f->state == IAVF_VLAN_DISABLE) { + } else if (f->state == IAVF_VLAN_REMOVE) { count++; } } @@ -958,18 +948,10 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; - list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_DISABLE) { - vvfl->vlan_id[i] = f->vlan.vid; - f->state = IAVF_VLAN_INACTIVE; - i++; - if (i == count) - break; - } else if (f->state == IAVF_VLAN_REMOVE) { + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->state == IAVF_VLAN_REMOVE) { vvfl->vlan_id[i] = f->vlan.vid; - list_del(&f->list); - kfree(f); - adapter->num_vlan_filters--; + f->state = IAVF_VLAN_REMOVING; i++; if (i == count) break; @@ -1006,9 +988,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; - list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_DISABLE || - f->state == IAVF_VLAN_REMOVE) { + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->state == IAVF_VLAN_REMOVE) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -1022,13 +1003,7 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vlan->tci = f->vlan.vid; vlan->tpid = f->vlan.tpid; - if (f->state == IAVF_VLAN_DISABLE) { - f->state = IAVF_VLAN_INACTIVE; - } else { - list_del(&f->list); - kfree(f); - adapter->num_vlan_filters--; - } + f->state = IAVF_VLAN_REMOVING; i++; if (i == count) break; @@ -2391,10 +2366,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); wake_up(&adapter->vc_waitqueue); break; - case VIRTCHNL_OP_DEL_VLAN: - dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n", - iavf_stat_str(&adapter->hw, v_retval)); - break; case VIRTCHNL_OP_DEL_ETH_ADDR: dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n", iavf_stat_str(&adapter->hw, v_retval)); @@ -2905,17 +2876,42 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->adv_rss_lock); } break; + case VIRTCHNL_OP_ADD_VLAN: case VIRTCHNL_OP_ADD_VLAN_V2: { struct iavf_vlan_filter *f; + if (v_retval) + break; + spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->state == IAVF_VLAN_IS_NEW) + if (f->state == IAVF_VLAN_ADDING) f->state = IAVF_VLAN_ACTIVE; } spin_unlock_bh(&adapter->mac_vlan_list_lock); } break; + case VIRTCHNL_OP_DEL_VLAN: + case VIRTCHNL_OP_DEL_VLAN_V2: { + struct iavf_vlan_filter *f, *ftmp; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, + list) { + if (f->state == IAVF_VLAN_REMOVING) { + if (v_retval) { + /* PF rejected DEL, keep filter */ + f->state = IAVF_VLAN_ACTIVE; + } else { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } + } + } + spin_unlock_bh(&adapter->mac_vlan_list_lock); + } + break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: /* PF enabled vlan strip on this VF. * Update netdev->features if needed to be in sync with ethtool. diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 6144cee8034d..641d6e289d5c 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -1245,6 +1245,8 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) return err; } + ice_init_dev_hw(pf); + /* load MSI-X values */ ice_set_min_max_msix(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index ce11fea122d0..b617a6bff891 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1126,8 +1126,6 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_fltr_mgmt_struct; - ice_init_dev_hw(hw->back); - mutex_init(&hw->tnl_lock); ice_init_chk_recipe_reuse_support(hw); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 62f75701d652..27b460926bac 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -1155,6 +1155,32 @@ ice_dpll_input_state_get(const struct dpll_pin *pin, void *pin_priv, } /** + * ice_dpll_sw_pin_notify_peer - notify the paired SW pin after a state change + * @d: pointer to dplls struct + * @changed: the SW pin that was explicitly changed (already notified by dpll core) + * + * SMA and U.FL pins share physical signal paths in pairs (SMA1/U.FL1 and + * SMA2/U.FL2). When one pin's routing changes via the PCA9575 GPIO + * expander, the paired pin's state may also change. Send a change + * notification for the peer pin so userspace consumers monitoring the + * peer via dpll netlink learn about the update. + * + * Context: Called from dpll_pin_ops callbacks after pf->dplls.lock is + * released. Uses __dpll_pin_change_ntf() because dpll_lock is + * still held by the dpll netlink layer. + */ +static void ice_dpll_sw_pin_notify_peer(struct ice_dplls *d, + struct ice_dpll_pin *changed) +{ + struct ice_dpll_pin *peer; + + peer = (changed >= d->sma && changed < d->sma + ICE_DPLL_PIN_SW_NUM) ? + &d->ufl[changed->idx] : &d->sma[changed->idx]; + if (peer->pin) + __dpll_pin_change_ntf(peer->pin); +} + +/** * ice_dpll_sma_direction_set - set direction of SMA pin * @p: pointer to a pin * @direction: requested direction of the pin @@ -1171,6 +1197,8 @@ static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p, enum dpll_pin_direction direction, struct netlink_ext_ack *extack) { + struct ice_dplls *d = &p->pf->dplls; + struct ice_dpll_pin *peer; u8 data; int ret; @@ -1189,8 +1217,9 @@ static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p, case ICE_DPLL_PIN_SW_2_IDX: if (direction == DPLL_PIN_DIRECTION_INPUT) { data &= ~ICE_SMA2_DIR_EN; + data |= ICE_SMA2_UFL2_RX_DIS; } else { - data &= ~ICE_SMA2_TX_EN; + data &= ~(ICE_SMA2_TX_EN | ICE_SMA2_UFL2_RX_DIS); data |= ICE_SMA2_DIR_EN; } break; @@ -1202,6 +1231,34 @@ static int ice_dpll_sma_direction_set(struct ice_dpll_pin *p, ret = ice_dpll_pin_state_update(p->pf, p, ICE_DPLL_PIN_TYPE_SOFTWARE, extack); + if (ret) + return ret; + + /* When a direction change activates the paired U.FL pin, enable + * its backing CGU pin so the pin reports as connected. Without + * this the U.FL routing is correct but the CGU pin stays disabled + * and userspace sees the pin as disconnected. Do not disable the + * backing pin when U.FL becomes inactive because the SMA pin may + * still be using it. + */ + peer = &d->ufl[p->idx]; + if (peer->active) { + struct ice_dpll_pin *target; + enum ice_dpll_pin_type type; + + if (peer->output) { + target = peer->output; + type = ICE_DPLL_PIN_TYPE_OUTPUT; + } else { + target = peer->input; + type = ICE_DPLL_PIN_TYPE_INPUT; + } + ret = ice_dpll_pin_enable(&p->pf->hw, target, + d->eec.dpll_idx, type, extack); + if (!ret) + ret = ice_dpll_pin_state_update(p->pf, target, + type, extack); + } return ret; } @@ -1253,6 +1310,14 @@ ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv, data &= ~ICE_SMA1_MASK; enable = true; } else if (state == DPLL_PIN_STATE_DISCONNECTED) { + /* Skip if U.FL1 is not active, setting TX_EN + * while DIR_EN is set would also deactivate + * the paired SMA1 output. + */ + if (data & (ICE_SMA1_DIR_EN | ICE_SMA1_TX_EN)) { + ret = 0; + goto unlock; + } data |= ICE_SMA1_TX_EN; enable = false; } else { @@ -1267,6 +1332,15 @@ ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv, data &= ~ICE_SMA2_UFL2_RX_DIS; enable = true; } else if (state == DPLL_PIN_STATE_DISCONNECTED) { + /* Skip if U.FL2 is not active, setting + * UFL2_RX_DIS could also disable the paired + * SMA2 input. + */ + if (!(data & ICE_SMA2_DIR_EN) || + (data & ICE_SMA2_UFL2_RX_DIS)) { + ret = 0; + goto unlock; + } data |= ICE_SMA2_UFL2_RX_DIS; enable = false; } else { @@ -1296,6 +1370,8 @@ ice_dpll_ufl_pin_state_set(const struct dpll_pin *pin, void *pin_priv, unlock: mutex_unlock(&pf->dplls.lock); + if (!ret) + ice_dpll_sw_pin_notify_peer(&pf->dplls, p); return ret; } @@ -1414,6 +1490,8 @@ ice_dpll_sma_pin_state_set(const struct dpll_pin *pin, void *pin_priv, unlock: mutex_unlock(&pf->dplls.lock); + if (!ret) + ice_dpll_sw_pin_notify_peer(&pf->dplls, sma); return ret; } @@ -1609,6 +1687,8 @@ ice_dpll_pin_sma_direction_set(const struct dpll_pin *pin, void *pin_priv, mutex_lock(&pf->dplls.lock); ret = ice_dpll_sma_direction_set(p, direction, extack); mutex_unlock(&pf->dplls.lock); + if (!ret) + ice_dpll_sw_pin_notify_peer(&pf->dplls, p); return ret; } @@ -1915,7 +1995,10 @@ ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv, d->active_input == p->input->pin)) *phase_offset = d->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; else if (d->phase_offset_monitor_period) - *phase_offset = p->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; + *phase_offset = (p->input && + p->direction == DPLL_PIN_DIRECTION_INPUT ? + p->input->phase_offset : + p->phase_offset) * ICE_DPLL_PHASE_OFFSET_FACTOR; else *phase_offset = 0; mutex_unlock(&pf->dplls.lock); @@ -2610,6 +2693,27 @@ static u64 ice_generate_clock_id(struct ice_pf *pf) } /** + * ice_dpll_pin_ntf - notify pin change including any SW pin wrappers + * @dplls: pointer to dplls struct + * @pin: the dpll_pin that changed + * + * Send a change notification for @pin and for any registered SMA/U.FL pin + * whose backing CGU input matches @pin. + */ +static void ice_dpll_pin_ntf(struct ice_dplls *dplls, struct dpll_pin *pin) +{ + dpll_pin_change_ntf(pin); + for (int i = 0; i < ICE_DPLL_PIN_SW_NUM; i++) { + if (dplls->sma[i].pin && dplls->sma[i].input && + dplls->sma[i].input->pin == pin) + dpll_pin_change_ntf(dplls->sma[i].pin); + if (dplls->ufl[i].pin && dplls->ufl[i].input && + dplls->ufl[i].input->pin == pin) + dpll_pin_change_ntf(dplls->ufl[i].pin); + } +} + +/** * ice_dpll_notify_changes - notify dpll subsystem about changes * @d: pointer do dpll * @@ -2617,6 +2721,7 @@ static u64 ice_generate_clock_id(struct ice_pf *pf) */ static void ice_dpll_notify_changes(struct ice_dpll *d) { + struct ice_dplls *dplls = &d->pf->dplls; bool pin_notified = false; if (d->prev_dpll_state != d->dpll_state) { @@ -2625,17 +2730,17 @@ static void ice_dpll_notify_changes(struct ice_dpll *d) } if (d->prev_input != d->active_input) { if (d->prev_input) - dpll_pin_change_ntf(d->prev_input); + ice_dpll_pin_ntf(dplls, d->prev_input); d->prev_input = d->active_input; if (d->active_input) { - dpll_pin_change_ntf(d->active_input); + ice_dpll_pin_ntf(dplls, d->active_input); pin_notified = true; } } if (d->prev_phase_offset != d->phase_offset) { d->prev_phase_offset = d->phase_offset; if (!pin_notified && d->active_input) - dpll_pin_change_ntf(d->active_input); + ice_dpll_pin_ntf(dplls, d->active_input); } } @@ -2664,6 +2769,7 @@ static bool ice_dpll_is_pps_phase_monitor(struct ice_pf *pf) /** * ice_dpll_pins_notify_mask - notify dpll subsystem about bulk pin changes + * @dplls: pointer to dplls struct * @pins: array of ice_dpll_pin pointers registered within dpll subsystem * @pin_num: number of pins * @phase_offset_ntf_mask: bitmask of pin indexes to notify @@ -2673,15 +2779,14 @@ static bool ice_dpll_is_pps_phase_monitor(struct ice_pf *pf) * * Context: Must be called while pf->dplls.lock is released. */ -static void ice_dpll_pins_notify_mask(struct ice_dpll_pin *pins, +static void ice_dpll_pins_notify_mask(struct ice_dplls *dplls, + struct ice_dpll_pin *pins, u8 pin_num, u32 phase_offset_ntf_mask) { - int i = 0; - - for (i = 0; i < pin_num; i++) - if (phase_offset_ntf_mask & (1 << i)) - dpll_pin_change_ntf(pins[i].pin); + for (int i = 0; i < pin_num; i++) + if (phase_offset_ntf_mask & BIT(i)) + ice_dpll_pin_ntf(dplls, pins[i].pin); } /** @@ -2857,7 +2962,7 @@ static void ice_dpll_periodic_work(struct kthread_work *work) ice_dpll_notify_changes(de); ice_dpll_notify_changes(dp); if (phase_offset_ntf) - ice_dpll_pins_notify_mask(d->inputs, d->num_inputs, + ice_dpll_pins_notify_mask(d, d->inputs, d->num_inputs, phase_offset_ntf); resched: @@ -4014,6 +4119,7 @@ static int ice_dpll_init_info_sw_pins(struct ice_pf *pf) struct ice_dpll_pin *pin; u32 phase_adj_max, caps; int i, ret; + u8 data; if (pf->hw.device_id == ICE_DEV_ID_E810C_QSFP) input_idx_offset = ICE_E810_RCLK_PINS_NUM; @@ -4073,6 +4179,22 @@ static int ice_dpll_init_info_sw_pins(struct ice_pf *pf) } ice_dpll_phase_range_set(&pin->prop.phase_range, phase_adj_max); } + + /* Initialize the SMA control register to a known-good default state. + * Without this write the PCA9575 GPIO expander retains its power-on + * default (all outputs high) which makes all SW pins appear inactive. + * Set SMA1 and SMA2 as active inputs, disable U.FL1 output and + * U.FL2 input. + */ + ret = ice_read_sma_ctrl(&pf->hw, &data); + if (ret) + return ret; + data &= ~ICE_ALL_SMA_MASK; + data |= ICE_SMA1_TX_EN | ICE_SMA2_TX_EN | ICE_SMA2_UFL2_RX_DIS; + ret = ice_write_sma_ctrl(&pf->hw, data); + if (ret) + return ret; + ret = ice_dpll_pin_state_update(pf, pin, ICE_DPLL_PIN_TYPE_SOFTWARE, NULL); if (ret) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 5f92377d4dfc..1d1947a7fe11 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5245,6 +5245,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) return err; } + ice_init_dev_hw(pf); + adapter = ice_adapter_get(pdev); if (IS_ERR(adapter)) { err = PTR_ERR(adapter); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 772f6b07340d..b1f46707dcc0 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -804,7 +804,12 @@ void ice_reset_all_vfs(struct ice_pf *pf) ice_vf_ctrl_invalidate_vsi(vf); ice_vf_pre_vsi_rebuild(vf); - ice_vf_rebuild_vsi(vf); + if (ice_vf_rebuild_vsi(vf)) { + dev_err(dev, "VF %u VSI rebuild failed, leaving VF disabled\n", + vf->vf_id); + mutex_unlock(&vf->cfg_lock); + continue; + } ice_vf_post_vsi_rebuild(vf); ice_eswitch_attach_vf(pf, vf); diff --git a/drivers/net/ethernet/sfc/efx_devlink.c b/drivers/net/ethernet/sfc/efx_devlink.c index d842c60dfc10..e5c6f81af48b 100644 --- a/drivers/net/ethernet/sfc/efx_devlink.c +++ b/drivers/net/ethernet/sfc/efx_devlink.c @@ -531,7 +531,7 @@ static int efx_devlink_info_running_versions(struct efx_nic *efx, if (rc || outlength < MC_CMD_GET_VERSION_OUT_LEN) { netif_err(efx, drv, efx->net_dev, "mcdi MC_CMD_GET_VERSION failed\n"); - return rc; + return rc ?: -EIO; } /* Handle previous output */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ca68248dbc78..3591755ea30b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5549,9 +5549,12 @@ read_again: break; /* Prefetch the next RX descriptor */ - rx_q->cur_rx = STMMAC_NEXT_ENTRY(rx_q->cur_rx, - priv->dma_conf.dma_rx_size); - next_entry = rx_q->cur_rx; + next_entry = STMMAC_NEXT_ENTRY(rx_q->cur_rx, + priv->dma_conf.dma_rx_size); + if (unlikely(next_entry == rx_q->dirty_rx)) + break; + + rx_q->cur_rx = next_entry; np = stmmac_get_rx_desc(priv, rx_q, next_entry); @@ -5686,7 +5689,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) dma_dir = page_pool_get_dma_dir(rx_q->page_pool); bufsz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE; - limit = min(priv->dma_conf.dma_rx_size - 1, (unsigned int)limit); if (netif_msg_rx_status(priv)) { void *rx_head = stmmac_get_rx_desc(priv, rx_q, 0); @@ -5733,9 +5735,12 @@ read_again: if (unlikely(status & dma_own)) break; - rx_q->cur_rx = STMMAC_NEXT_ENTRY(rx_q->cur_rx, - priv->dma_conf.dma_rx_size); - next_entry = rx_q->cur_rx; + next_entry = STMMAC_NEXT_ENTRY(rx_q->cur_rx, + priv->dma_conf.dma_rx_size); + if (unlikely(next_entry == rx_q->dirty_rx)) + break; + + rx_q->cur_rx = next_entry; np = stmmac_get_rx_desc(priv, rx_q, next_entry); diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index 15fe4d1163c1..ee2913758e54 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -496,8 +496,6 @@ static void mctp_i2c_xmit(struct mctp_i2c_dev *midev, struct sk_buff *skb) u8 *pecp; int rc; - fs = mctp_i2c_get_tx_flow_state(midev, skb); - hdr = (void *)skb_mac_header(skb); /* Sanity check that packet contents matches skb length, * and can't exceed MCTP_I2C_BUFSZ @@ -509,6 +507,8 @@ static void mctp_i2c_xmit(struct mctp_i2c_dev *midev, struct sk_buff *skb) return; } + fs = mctp_i2c_get_tx_flow_state(midev, skb); + if (skb_tailroom(skb) >= 1) { /* Linear case with space, we can just append the PEC */ skb_put(skb, 1); diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 205384dab89a..57dd6821a8aa 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -752,7 +752,7 @@ static ssize_t enabled_store(struct config_item *item, unregister_netcons_consoles(); } - ret = strnlen(buf, count); + ret = count; /* Deferred cleanup */ netconsole_process_cleanups(); out_unlock: @@ -781,7 +781,7 @@ static ssize_t release_store(struct config_item *item, const char *buf, nt->release = release; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -807,7 +807,7 @@ static ssize_t extended_store(struct config_item *item, const char *buf, goto out_unlock; nt->extended = extended; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -817,6 +817,13 @@ static ssize_t dev_name_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); + size_t len = count; + + /* Account for a trailing newline appended by tools like echo */ + if (len && buf[len - 1] == '\n') + len--; + if (len >= IFNAMSIZ) + return -ENAMETOOLONG; dynamic_netconsole_mutex_lock(); if (nt->state == STATE_ENABLED) { @@ -830,7 +837,7 @@ static ssize_t dev_name_store(struct config_item *item, const char *buf, trim_newline(nt->np.dev_name, IFNAMSIZ); dynamic_netconsole_mutex_unlock(); - return strnlen(buf, count); + return count; } static ssize_t local_port_store(struct config_item *item, const char *buf, @@ -849,7 +856,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf, ret = kstrtou16(buf, 10, &nt->np.local_port); if (ret < 0) goto out_unlock; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -871,7 +878,7 @@ static ssize_t remote_port_store(struct config_item *item, ret = kstrtou16(buf, 10, &nt->np.remote_port); if (ret < 0) goto out_unlock; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -896,7 +903,7 @@ static ssize_t local_ip_store(struct config_item *item, const char *buf, goto out_unlock; nt->np.ipv6 = !!ipv6; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -921,7 +928,7 @@ static ssize_t remote_ip_store(struct config_item *item, const char *buf, goto out_unlock; nt->np.ipv6 = !!ipv6; - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -957,7 +964,7 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf, goto out_unlock; memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN); - ret = strnlen(buf, count); + ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); return ret; @@ -1072,26 +1079,30 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf, size_t count) { struct userdatum *udm = to_userdatum(item); + char old_value[MAX_EXTRADATA_VALUE_LEN]; struct netconsole_target *nt; struct userdata *ud; ssize_t ret; - if (count > MAX_EXTRADATA_VALUE_LEN) + if (count >= MAX_EXTRADATA_VALUE_LEN) return -EMSGSIZE; mutex_lock(&netconsole_subsys.su_mutex); dynamic_netconsole_mutex_lock(); - - ret = strscpy(udm->value, buf, sizeof(udm->value)); - if (ret < 0) - goto out_unlock; + /* Snapshot for rollback if update_userdata() fails below */ + strscpy(old_value, udm->value, sizeof(old_value)); + /* count is bounded above, so strscpy() cannot truncate here */ + strscpy(udm->value, buf, sizeof(udm->value)); trim_newline(udm->value, sizeof(udm->value)); ud = to_userdata(item->ci_parent); nt = userdata_to_target(ud); ret = update_userdata(nt); - if (ret < 0) + if (ret < 0) { + /* Restore the previous value so it matches the live payload */ + strscpy(udm->value, old_value, sizeof(udm->value)); goto out_unlock; + } ret = count; out_unlock: dynamic_netconsole_mutex_unlock(); @@ -1133,7 +1144,7 @@ static ssize_t sysdata_msgid_enabled_store(struct config_item *item, disable_sysdata_feature(nt, SYSDATA_MSGID); unlock_ok: - ret = strnlen(buf, count); + ret = count; dynamic_netconsole_mutex_unlock(); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1162,7 +1173,7 @@ static ssize_t sysdata_release_enabled_store(struct config_item *item, disable_sysdata_feature(nt, SYSDATA_RELEASE); unlock_ok: - ret = strnlen(buf, count); + ret = count; dynamic_netconsole_mutex_unlock(); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1191,7 +1202,7 @@ static ssize_t sysdata_taskname_enabled_store(struct config_item *item, disable_sysdata_feature(nt, SYSDATA_TASKNAME); unlock_ok: - ret = strnlen(buf, count); + ret = count; dynamic_netconsole_mutex_unlock(); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1225,7 +1236,7 @@ static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item, disable_sysdata_feature(nt, SYSDATA_CPU_NR); unlock_ok: - ret = strnlen(buf, count); + ret = count; dynamic_netconsole_mutex_unlock(); mutex_unlock(&netconsole_subsys.su_mutex); return ret; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 1e06e781c835..f00fc2f9ebde 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -829,7 +829,7 @@ static struct sk_buff *nsim_dev_trap_skb_build(void) skb->protocol = htons(ETH_P_IP); skb_set_network_header(skb, skb->len); - iph = skb_put(skb, sizeof(struct iphdr)); + iph = skb_put_zero(skb, sizeof(struct iphdr)); iph->protocol = IPPROTO_UDP; iph->saddr = in_aton("192.0.2.1"); iph->daddr = in_aton("198.51.100.1"); diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index 1f381d7b13ff..96a7d255f50f 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -31,6 +31,7 @@ #define DP83869_RGMIICTL 0x0032 #define DP83869_STRAP_STS1 0x006e #define DP83869_RGMIIDCTL 0x0086 +#define DP83869_ANA_PLL_PROG_PI 0x00c6 #define DP83869_RXFCFG 0x0134 #define DP83869_RXFPMD1 0x0136 #define DP83869_RXFPMD2 0x0137 @@ -826,12 +827,22 @@ static int dp83869_config_init(struct phy_device *phydev) dp83869_config_port_mirroring(phydev); /* Clock output selection if muxing property is set */ - if (dp83869->clk_output_sel != DP83869_CLK_O_SEL_REF_CLK) + if (dp83869->clk_output_sel != DP83869_CLK_O_SEL_REF_CLK) { + /* + * Table 7-121 in datasheet says we have to set register 0xc6 + * to value 0x10 before CLK_O_SEL can be modified. + */ + ret = phy_write_mmd(phydev, DP83869_DEVADDR, + DP83869_ANA_PLL_PROG_PI, 0x10); + if (ret) + return ret; + ret = phy_modify_mmd(phydev, DP83869_DEVADDR, DP83869_IO_MUX_CFG, DP83869_IO_MUX_CFG_CLK_O_SEL_MASK, dp83869->clk_output_sel << DP83869_IO_MUX_CFG_CLK_O_SEL_SHIFT); + } if (phy_interface_is_rgmii(phydev)) { ret = phy_write_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIIDCTL, diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 4cda0643afb6..c880c95c41a5 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -683,6 +683,7 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, struct net_device *netdev) { rtl8150_t *dev = netdev_priv(netdev); + unsigned int skb_len; int count, res; /* pad the frame and ensure terminating USB packet, datasheet 9.2.3 */ @@ -694,6 +695,8 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } + skb_len = skb->len; + netif_stop_queue(netdev); dev->tx_skb = skb; usb_fill_bulk_urb(dev->tx_urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), @@ -707,9 +710,16 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, netdev->stats.tx_errors++; netif_start_queue(netdev); } + /* + * The URB was not submitted, so write_bulk_callback() will + * never run to free dev->tx_skb. Drop the skb here and + * clear tx_skb to avoid leaving a stale pointer. + */ + dev->tx_skb = NULL; + dev_kfree_skb_any(skb); } else { netdev->stats.tx_packets++; - netdev->stats.tx_bytes += skb->len; + netdev->stats.tx_bytes += skb_len; netif_trans_update(netdev); } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 2cf2dbd1c12f..46209917ae4d 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1034,6 +1034,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, err: port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; + synchronize_net(); return ret; } @@ -1053,10 +1054,16 @@ static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, } /* inverse of do_vrf_add_slave */ -static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) +static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev, + bool needs_sync) { netdev_upper_dev_unlink(port_dev, dev); port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; + /* Make sure that concurrent RCU readers that identified the device + * as a VRF port see a VRF master or no master at all. + */ + if (needs_sync) + synchronize_net(); cycle_netdev(port_dev, NULL); @@ -1065,7 +1072,7 @@ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { - return do_vrf_del_slave(dev, port_dev); + return do_vrf_del_slave(dev, port_dev, true); } static void vrf_dev_uninit(struct net_device *dev) @@ -1619,7 +1626,7 @@ static void vrf_dellink(struct net_device *dev, struct list_head *head) struct list_head *iter; netdev_for_each_lower_dev(dev, port_dev, iter) - vrf_del_slave(dev, port_dev); + do_vrf_del_slave(dev, port_dev, false); vrf_map_unregister_dev(dev); @@ -1751,7 +1758,7 @@ static int vrf_device_event(struct notifier_block *unused, goto out; vrf_dev = netdev_master_upper_dev_get(dev); - vrf_del_slave(vrf_dev, dev); + do_vrf_del_slave(vrf_dev, dev, false); } out: return NOTIFY_DONE; diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index d17c701c7888..08c27bb438b5 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -317,6 +317,7 @@ #define TRF7970A_RSSI_OSC_STATUS_RSSI_MASK (BIT(2) | BIT(1) | BIT(0)) #define TRF7970A_RSSI_OSC_STATUS_RSSI_X_MASK (BIT(5) | BIT(4) | BIT(3)) #define TRF7970A_RSSI_OSC_STATUS_RSSI_OSC_OK BIT(6) +#define TRF7970A_RSSI_OSC_STATUS_RSSI_NOISE_LEVEL 1 #define TRF7970A_SPECIAL_FCN_REG1_COL_7_6 BIT(0) #define TRF7970A_SPECIAL_FCN_REG1_14_ANTICOLL BIT(1) @@ -1300,7 +1301,7 @@ static int trf7970a_is_rf_field(struct trf7970a *trf, bool *is_rf_field) if (ret) return ret; - if (rssi & TRF7970A_RSSI_OSC_STATUS_RSSI_MASK) + if ((rssi & TRF7970A_RSSI_OSC_STATUS_RSSI_MASK) > TRF7970A_RSSI_OSC_STATUS_RSSI_NOISE_LEVEL) *is_rf_field = true; else *is_rf_field = false; diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c index 2d325fb93083..77f1d22512f8 100644 --- a/drivers/nvme/common/auth.c +++ b/drivers/nvme/common/auth.c @@ -351,18 +351,29 @@ struct nvme_dhchap_key *nvme_auth_transform_key( } EXPORT_SYMBOL_GPL(nvme_auth_transform_key); +/** + * nvme_auth_augmented_challenge() - Compute the augmented DH-HMAC-CHAP challenge + * @hmac_id: Hash algorithm identifier + * @skey: Session key + * @skey_len: Length of @skey + * @challenge: Challenge value + * @aug: Output buffer for the augmented challenge + * @hlen: Hash output length (length of @challenge and @aug) + * + * NVMe base specification 8.3.5.5.4: The augmented challenge is computed + * applying the HMAC function using the hash function H() selected by the + * HashID parameter ... with the hash of the ephemeral DH key ... as HMAC key + * to the challenge C (i.e., Ca = HMAC(H(g^xy mod p), C)). + * + * As the session key skey is already H(g^xy mod p) per section 8.3.5.5.9, use + * it directly as the HMAC key without additional hashing. + * + * Return: 0 on success, negative errno on failure. + */ int nvme_auth_augmented_challenge(u8 hmac_id, const u8 *skey, size_t skey_len, const u8 *challenge, u8 *aug, size_t hlen) { - u8 hashed_key[NVME_AUTH_MAX_DIGEST_SIZE]; - int ret; - - ret = nvme_auth_hash(hmac_id, skey, skey_len, hashed_key); - if (ret) - return ret; - ret = nvme_auth_hmac(hmac_id, hashed_key, hlen, challenge, hlen, aug); - memzero_explicit(hashed_key, sizeof(hashed_key)); - return ret; + return nvme_auth_hmac(hmac_id, skey, skey_len, challenge, hlen, aug); } EXPORT_SYMBOL_GPL(nvme_auth_augmented_challenge); @@ -403,33 +414,76 @@ int nvme_auth_gen_pubkey(struct crypto_kpp *dh_tfm, } EXPORT_SYMBOL_GPL(nvme_auth_gen_pubkey); -int nvme_auth_gen_shared_secret(struct crypto_kpp *dh_tfm, - const u8 *ctrl_key, size_t ctrl_key_len, - u8 *sess_key, size_t sess_key_len) +/** + * nvme_auth_gen_session_key() - Generate an ephemeral session key + * @dh_tfm: Diffie-Hellman transform with local private key already set + * @public_key: Peer's public key + * @public_key_len: Length of @public_key + * @sess_key: Output buffer for the session key + * @sess_key_len: Size of @sess_key buffer + * @hash_id: Hash algorithm identifier + * + * NVMe base specification 8.3.5.5.9: The session key Ks shall be computed from + * the ephemeral DH key (i.e., g^xy mod p) ... by applying the hash function + * H() selected by the HashID parameter ... (i.e., Ks = H(g^xy mod p)). + * + * Return: 0 on success, negative errno on failure. + */ +int nvme_auth_gen_session_key(struct crypto_kpp *dh_tfm, + const u8 *public_key, size_t public_key_len, + u8 *sess_key, size_t sess_key_len, u8 hash_id) { struct kpp_request *req; struct crypto_wait wait; struct scatterlist src, dst; + u8 *dh_secret; + size_t dh_secret_len, hash_len; int ret; - req = kpp_request_alloc(dh_tfm, GFP_KERNEL); - if (!req) + hash_len = nvme_auth_hmac_hash_len(hash_id); + if (!hash_len) { + pr_warn("%s: invalid hash algorithm %d\n", __func__, hash_id); + return -EINVAL; + } + + if (sess_key_len != hash_len) { + pr_warn("%s: sess_key buffer missized (%zu != %zu)\n", + __func__, sess_key_len, hash_len); + return -EINVAL; + } + + dh_secret_len = crypto_kpp_maxsize(dh_tfm); + dh_secret = kzalloc(dh_secret_len, GFP_KERNEL); + if (!dh_secret) return -ENOMEM; + req = kpp_request_alloc(dh_tfm, GFP_KERNEL); + if (!req) { + ret = -ENOMEM; + goto out_free_secret; + } + crypto_init_wait(&wait); - sg_init_one(&src, ctrl_key, ctrl_key_len); - kpp_request_set_input(req, &src, ctrl_key_len); - sg_init_one(&dst, sess_key, sess_key_len); - kpp_request_set_output(req, &dst, sess_key_len); + sg_init_one(&src, public_key, public_key_len); + kpp_request_set_input(req, &src, public_key_len); + sg_init_one(&dst, dh_secret, dh_secret_len); + kpp_request_set_output(req, &dst, dh_secret_len); kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &wait); ret = crypto_wait_req(crypto_kpp_compute_shared_secret(req), &wait); - kpp_request_free(req); + + if (ret) + goto out_free_secret; + + ret = nvme_auth_hash(hash_id, dh_secret, dh_secret_len, sess_key); + +out_free_secret: + kfree_sensitive(dh_secret); return ret; } -EXPORT_SYMBOL_GPL(nvme_auth_gen_shared_secret); +EXPORT_SYMBOL_GPL(nvme_auth_gen_session_key); int nvme_auth_parse_key(const char *secret, struct nvme_dhchap_key **ret_key) { diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index ed61b97fde59..423c9c628e7b 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1267,11 +1267,7 @@ static int apple_nvme_get_address(struct nvme_ctrl *ctrl, char *buf, int size) static void apple_nvme_free_ctrl(struct nvme_ctrl *ctrl) { - struct apple_nvme *anv = ctrl_to_apple_nvme(ctrl); - - if (anv->ctrl.admin_q) - blk_put_queue(anv->ctrl.admin_q); - put_device(anv->dev); + put_device(ctrl->dev); } static const struct nvme_ctrl_ops nvme_ctrl_ops = { diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index bbedbe181c8a..16de4499a8e7 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -535,11 +535,12 @@ static int nvme_auth_dhchap_setup_ctrl_response(struct nvme_ctrl *ctrl, put_unaligned_le16(chap->transaction, buf); nvme_auth_hmac_update(&hmac, buf, 2); - memset(buf, 0, 4); + *buf = chap->sc_c; nvme_auth_hmac_update(&hmac, buf, 1); nvme_auth_hmac_update(&hmac, "Controller", 10); nvme_auth_hmac_update(&hmac, ctrl->opts->subsysnqn, strlen(ctrl->opts->subsysnqn)); + memset(buf, 0, 4); nvme_auth_hmac_update(&hmac, buf, 1); nvme_auth_hmac_update(&hmac, ctrl->opts->host->nqn, strlen(ctrl->opts->host->nqn)); @@ -587,7 +588,7 @@ static int nvme_auth_dhchap_exponential(struct nvme_ctrl *ctrl, } gen_sesskey: - chap->sess_key_len = chap->host_key_len; + chap->sess_key_len = chap->hash_len; chap->sess_key = kmalloc(chap->sess_key_len, GFP_KERNEL); if (!chap->sess_key) { chap->sess_key_len = 0; @@ -595,16 +596,17 @@ gen_sesskey: return -ENOMEM; } - ret = nvme_auth_gen_shared_secret(chap->dh_tfm, - chap->ctrl_key, chap->ctrl_key_len, - chap->sess_key, chap->sess_key_len); + ret = nvme_auth_gen_session_key(chap->dh_tfm, + chap->ctrl_key, chap->ctrl_key_len, + chap->sess_key, chap->sess_key_len, + chap->hash_id); if (ret) { dev_dbg(ctrl->device, - "failed to generate shared secret, error %d\n", ret); + "failed to generate session key, error %d\n", ret); chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; return ret; } - dev_dbg(ctrl->device, "shared secret %*ph\n", + dev_dbg(ctrl->device, "session key %*ph\n", (int)chap->sess_key_len, chap->sess_key); return 0; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 1e33af94c24b..dc388e24caad 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -454,11 +454,10 @@ void nvme_end_req(struct request *req) blk_mq_end_request(req, status); } -void nvme_complete_rq(struct request *req) +static void __nvme_complete_rq(struct request *req) { struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; - trace_nvme_complete_rq(req); nvme_cleanup_cmd(req); /* @@ -493,6 +492,12 @@ void nvme_complete_rq(struct request *req) return; } } + +void nvme_complete_rq(struct request *req) +{ + trace_nvme_complete_rq(req); + __nvme_complete_rq(req); +} EXPORT_SYMBOL_GPL(nvme_complete_rq); void nvme_complete_batch_req(struct request *req) @@ -513,7 +518,7 @@ blk_status_t nvme_host_path_error(struct request *req) { nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR; blk_mq_set_request_complete(req); - nvme_complete_rq(req); + __nvme_complete_rq(req); return BLK_STS_OK; } EXPORT_SYMBOL_GPL(nvme_host_path_error); @@ -3044,7 +3049,7 @@ static const struct nvme_core_quirk_entry core_quirks[] = { * * The device is left in a state where it is also not possible * to use "nvme set-feature" to disable APST, but booting with - * nvme_core.default_ps_max_latency=0 works. + * nvme_core.default_ps_max_latency_us=0 works. */ .vid = 0x1e0f, .mn = "KCD6XVUL6T40", @@ -4083,7 +4088,8 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) mutex_unlock(&ctrl->subsys->lock); #ifdef CONFIG_NVME_MULTIPATH - cancel_delayed_work(&head->remove_work); + if (cancel_delayed_work(&head->remove_work)) + module_put(THIS_MODULE); #endif return 0; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index e1bb4707183c..e4f4528fe2a2 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3968,3 +3968,4 @@ module_exit(nvme_fc_exit_module); MODULE_DESCRIPTION("NVMe host FC transport driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("nvme-fc"); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index ba00f0b72b85..263161cb8ac0 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -231,16 +231,12 @@ bool nvme_mpath_clear_current_path(struct nvme_ns *ns) bool changed = false; int node; - if (!head) - goto out; - for_each_node(node) { if (ns == rcu_access_pointer(head->current_path[node])) { rcu_assign_pointer(head->current_path[node], NULL); changed = true; } } -out: return changed; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index db5fc9bf6627..9fd04cd7c5cb 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2241,6 +2241,7 @@ release_cq: static const struct blk_mq_ops nvme_mq_admin_ops = { .queue_rq = nvme_queue_rq, .complete = nvme_pci_complete_rq, + .commit_rqs = nvme_commit_rqs, .init_hctx = nvme_admin_init_hctx, .init_request = nvme_pci_init_request, .timeout = nvme_timeout, @@ -4104,6 +4105,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x1c5f, 0x0540), /* Memblaze Pblaze4 adapter */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, + { PCI_DEVICE(0x1c5f, 0x0555), /* Memblaze Pblaze5 adapter */ + .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, + { PCI_DEVICE(0x144d, 0xa808), /* Samsung PM981/983 */ + .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x144d, 0xa821), /* Samsung PM1725 */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x144d, 0xa822), /* Samsung PM1725a */ diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 57111139e84f..f77c960f7632 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2189,6 +2189,13 @@ out_fail: nvme_rdma_reconnect_or_remove(ctrl, ret); } +static bool nvme_rdma_supports_pci_p2pdma(struct nvme_ctrl *ctrl) +{ + struct nvme_rdma_ctrl *r_ctrl = to_rdma_ctrl(ctrl); + + return ib_dma_pci_p2p_dma_supported(r_ctrl->device->dev); +} + static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .name = "rdma", .module = THIS_MODULE, @@ -2203,6 +2210,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .get_address = nvmf_get_address, .stop_ctrl = nvme_rdma_stop_ctrl, .get_virt_boundary = nvme_get_virt_boundary, + .supports_pci_p2pdma = nvme_rdma_supports_pci_p2pdma, }; /* @@ -2432,3 +2440,4 @@ module_exit(nvme_rdma_cleanup_module); MODULE_DESCRIPTION("NVMe host RDMA transport driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("nvme-rdma"); diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index 7bf2e972126b..e59758616f27 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -883,10 +883,26 @@ static ssize_t tls_keyring_show(struct device *dev, } static DEVICE_ATTR_RO(tls_keyring); +static ssize_t tls_mode_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + const char *mode; + + if (ctrl->opts->tls) + mode = "tls"; + else + mode = "concat"; + + return sysfs_emit(buf, "%s\n", mode); +} +static DEVICE_ATTR_RO(tls_mode); + static struct attribute *nvme_tls_attrs[] = { &dev_attr_tls_key.attr, &dev_attr_tls_configured_key.attr, &dev_attr_tls_keyring.attr, + &dev_attr_tls_mode.attr, NULL, }; @@ -908,6 +924,9 @@ static umode_t nvme_tls_attrs_are_visible(struct kobject *kobj, if (a == &dev_attr_tls_keyring.attr && !ctrl->opts->keyring) return 0; + if (a == &dev_attr_tls_mode.attr && + !ctrl->opts->tls && !ctrl->opts->concat) + return 0; return a->mode; } diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 243dab830dc8..15d36d6a728e 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1438,18 +1438,32 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; - unsigned int noreclaim_flag; + unsigned int noio_flag; if (!test_and_clear_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) return; page_frag_cache_drain(&queue->pf_cache); - noreclaim_flag = memalloc_noreclaim_save(); - /* ->sock will be released by fput() */ - fput(queue->sock->file); + /** + * Prevent memory reclaim from triggering block I/O during socket + * teardown. The socket release path fput -> tcp_close -> + * tcp_disconnect -> tcp_send_active_reset may allocate memory, and + * allowing reclaim to issue I/O could deadlock if we're being called + * from block device teardown (e.g., del_gendisk -> elevator cleanup) + * which holds locks that the I/O completion path needs. + */ + noio_flag = memalloc_noio_save(); + + /** + * Release the socket synchronously. During reset in + * nvme_reset_ctrl_work(), queue teardown is immediately followed by + * re-allocation. fput() defers socket cleanup to delayed_fput_work + * in workqueue context, which can race with new queue setup. + */ + __fput_sync(queue->sock->file); queue->sock = NULL; - memalloc_noreclaim_restore(noreclaim_flag); + memalloc_noio_restore(noio_flag); kfree(queue->pdu); mutex_destroy(&queue->send_mutex); @@ -1901,8 +1915,8 @@ err_init_connect: err_rcv_pdu: kfree(queue->pdu); err_sock: - /* ->sock will be released by fput() */ - fput(queue->sock->file); + /* Use sync variant - see nvme_tcp_free_queue() for explanation */ + __fput_sync(queue->sock->file); queue->sock = NULL; err_destroy_mutex: mutex_destroy(&queue->send_mutex); @@ -3071,3 +3085,4 @@ module_exit(nvme_tcp_cleanup_module); MODULE_DESCRIPTION("NVMe host TCP transport driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("nvme-tcp"); diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index e4fd1caadfb0..01b799e92ae6 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -687,12 +687,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->cmic = NVME_CTRL_CMIC_MULTI_PORT | NVME_CTRL_CMIC_MULTI_CTRL | NVME_CTRL_CMIC_ANA; - /* Limit MDTS according to transport capability */ - if (ctrl->ops->get_mdts) - id->mdts = ctrl->ops->get_mdts(ctrl); - else - id->mdts = 0; - + /* Limit MDTS according to port config or transport capability */ + id->mdts = nvmet_ctrl_mdts(req); id->cntlid = cpu_to_le16(ctrl->cntlid); id->ver = cpu_to_le32(ctrl->subsys->ver); diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index b34610e2f19d..9a2eccdc8b13 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -229,9 +229,6 @@ out_unlock: void nvmet_auth_sq_free(struct nvmet_sq *sq) { cancel_delayed_work(&sq->auth_expired_work); -#ifdef CONFIG_NVME_TARGET_TCP_TLS - sq->tls_key = NULL; -#endif kfree(sq->dhchap_c1); sq->dhchap_c1 = NULL; kfree(sq->dhchap_c2); @@ -402,11 +399,12 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, put_unaligned_le16(req->sq->dhchap_tid, buf); nvme_auth_hmac_update(&hmac, buf, 2); - memset(buf, 0, 4); + *buf = req->sq->sc_c; nvme_auth_hmac_update(&hmac, buf, 1); nvme_auth_hmac_update(&hmac, "Controller", 10); nvme_auth_hmac_update(&hmac, ctrl->subsys->subsysnqn, strlen(ctrl->subsys->subsysnqn)); + memset(buf, 0, 4); nvme_auth_hmac_update(&hmac, buf, 1); nvme_auth_hmac_update(&hmac, ctrl->hostnqn, strlen(ctrl->hostnqn)); nvme_auth_hmac_final(&hmac, response); @@ -449,18 +447,19 @@ int nvmet_auth_ctrl_sesskey(struct nvmet_req *req, struct nvmet_ctrl *ctrl = req->sq->ctrl; int ret; - req->sq->dhchap_skey_len = ctrl->dh_keysize; + req->sq->dhchap_skey_len = nvme_auth_hmac_hash_len(ctrl->shash_id); req->sq->dhchap_skey = kzalloc(req->sq->dhchap_skey_len, GFP_KERNEL); if (!req->sq->dhchap_skey) return -ENOMEM; - ret = nvme_auth_gen_shared_secret(ctrl->dh_tfm, - pkey, pkey_size, - req->sq->dhchap_skey, - req->sq->dhchap_skey_len); + ret = nvme_auth_gen_session_key(ctrl->dh_tfm, + pkey, pkey_size, + req->sq->dhchap_skey, + req->sq->dhchap_skey_len, + ctrl->shash_id); if (ret) - pr_debug("failed to compute shared secret, err %d\n", ret); + pr_debug("failed to compute session key, err %d\n", ret); else - pr_debug("%s: shared secret %*ph\n", __func__, + pr_debug("%s: session key %*ph\n", __func__, (int)req->sq->dhchap_skey_len, req->sq->dhchap_skey); diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 463348c7f097..b88f897f06e2 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -301,6 +301,31 @@ static ssize_t nvmet_param_max_queue_size_store(struct config_item *item, CONFIGFS_ATTR(nvmet_, param_max_queue_size); +static ssize_t nvmet_param_mdts_show(struct config_item *item, char *page) +{ + struct nvmet_port *port = to_nvmet_port(item); + + return snprintf(page, PAGE_SIZE, "%d\n", port->mdts); +} + +static ssize_t nvmet_param_mdts_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_port *port = to_nvmet_port(item); + int ret; + + if (nvmet_is_port_enabled(port, __func__)) + return -EACCES; + ret = kstrtoint(page, 0, &port->mdts); + if (ret) { + pr_err("Invalid value '%s' for mdts\n", page); + return -EINVAL; + } + return count; +} + +CONFIGFS_ATTR(nvmet_, param_mdts); + #ifdef CONFIG_BLK_DEV_INTEGRITY static ssize_t nvmet_param_pi_enable_show(struct config_item *item, char *page) @@ -1995,6 +2020,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = { &nvmet_attr_addr_tsas, &nvmet_attr_param_inline_data_size, &nvmet_attr_param_max_queue_size, + &nvmet_attr_param_mdts, #ifdef CONFIG_BLK_DEV_INTEGRITY &nvmet_attr_param_pi_enable, #endif @@ -2053,6 +2079,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group, INIT_LIST_HEAD(&port->referrals); port->inline_data_size = -1; /* < 0 == let the transport choose */ port->max_queue_size = -1; /* < 0 == let the transport choose */ + port->mdts = -1; /* < 0 == let the transport choose */ port->disc_addr.trtype = NVMF_TRTYPE_MAX; port->disc_addr.portid = cpu_to_le16(portid); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 45f686175fea..62dd59b9aa4f 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -370,6 +370,14 @@ int nvmet_enable_port(struct nvmet_port *port) NVMET_MIN_QUEUE_SIZE, NVMET_MAX_QUEUE_SIZE); + /* + * If the transport didn't set the mdts properly, then clamp it to the + * target limits. Also set default values in case the transport didn't + * set it at all. + */ + if (port->mdts < 0 || port->mdts > NVMET_MAX_MDTS) + port->mdts = 0; + port->enabled = true; port->tr_ops = ops; return 0; @@ -1743,7 +1751,7 @@ static void nvmet_ctrl_free(struct kref *ref) nvmet_stop_keep_alive_timer(ctrl); - flush_work(&ctrl->async_event_work); + cancel_work_sync(&ctrl->async_event_work); cancel_work_sync(&ctrl->fatal_err_work); nvmet_destroy_auth(ctrl); diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index b9ab80c7a694..f1e613e7c63e 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -395,10 +395,9 @@ done: goto complete; } /* Final states, clear up variables */ - if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) { - nvmet_auth_sq_free(req->sq); + nvmet_auth_sq_free(req->sq); + if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) nvmet_ctrl_fatal_error(ctrl); - } complete: nvmet_req_complete(req, status); @@ -574,7 +573,9 @@ void nvmet_execute_auth_receive(struct nvmet_req *req) status = nvmet_copy_to_sgl(req, 0, d, al); kfree(d); done: - if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) { + if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2) + nvmet_auth_sq_free(req->sq); + else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) { nvmet_auth_sq_free(req->sq); nvmet_ctrl_fatal_error(ctrl); } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 50070cfb782a..3305a88684ec 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -214,6 +214,7 @@ struct nvmet_port { bool enabled; int inline_data_size; int max_queue_size; + int mdts; const struct nvmet_fabrics_ops *tr_ops; bool pi_enable; }; @@ -673,6 +674,7 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type, #define NVMET_MAX_QUEUE_SIZE 1024 #define NVMET_NR_QUEUES 128 #define NVMET_MAX_CMD(ctrl) (NVME_CAP_MQES(ctrl->cap) + 1) +#define NVMET_MAX_MDTS 255 /* * Nice round number that makes a list of nsids fit into a page. @@ -761,6 +763,17 @@ static inline bool nvmet_is_pci_ctrl(struct nvmet_ctrl *ctrl) return ctrl->port->disc_addr.trtype == NVMF_TRTYPE_PCI; } +/* Limit MDTS according to port config or transport capability */ +static inline u8 nvmet_ctrl_mdts(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u8 mdts = req->port->mdts; + + if (!ctrl->ops->get_mdts) + return mdts; + return min_not_zero(ctrl->ops->get_mdts(ctrl), mdts); +} + #ifdef CONFIG_NVME_TARGET_PASSTHRU void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys); int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys); diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 4b8b02341ddc..164a564ba3b4 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -349,9 +349,7 @@ static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd) cmd->req.sg = NULL; } -static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue); - -static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) +static int nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) { struct bio_vec *iov = cmd->iov; struct scatterlist *sg; @@ -364,22 +362,19 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) offset = cmd->rbytes_done; cmd->sg_idx = offset / PAGE_SIZE; sg_offset = offset % PAGE_SIZE; - if (!cmd->req.sg_cnt || cmd->sg_idx >= cmd->req.sg_cnt) { - nvmet_tcp_fatal_error(cmd->queue); - return; - } + if (!cmd->req.sg_cnt || cmd->sg_idx >= cmd->req.sg_cnt) + return -EPROTO; + sg = &cmd->req.sg[cmd->sg_idx]; sg_remaining = cmd->req.sg_cnt - cmd->sg_idx; while (length) { - if (!sg_remaining) { - nvmet_tcp_fatal_error(cmd->queue); - return; - } - if (!sg->length || sg->length <= sg_offset) { - nvmet_tcp_fatal_error(cmd->queue); - return; - } + if (!sg_remaining) + return -EPROTO; + + if (!sg->length || sg->length <= sg_offset) + return -EPROTO; + u32 iov_len = min_t(u32, length, sg->length - sg_offset); bvec_set_page(iov, sg_page(sg), iov_len, @@ -394,24 +389,29 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) iov_iter_bvec(&cmd->recv_msg.msg_iter, ITER_DEST, cmd->iov, nr_pages, cmd->pdu_len); -} - -static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) -{ - queue->rcv_state = NVMET_TCP_RECV_ERR; - if (queue->nvme_sq.ctrl) - nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl); - else - kernel_sock_shutdown(queue->sock, SHUT_RDWR); + return 0; } static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status) { + /* + * Keep rcv_state at RECV_ERR even for the internal -ESHUTDOWN path. + * nvmet_tcp_handle_icreq() can return -ESHUTDOWN after the ICReq has + * already been consumed and queue teardown has started. + * + * If nvmet_tcp_data_ready() or nvmet_tcp_write_space() queues + * nvmet_tcp_io_work() again before nvmet_tcp_release_queue_work() + * cancels it, the queue must not keep that old receive state. + * Otherwise the next nvmet_tcp_io_work() run can reach + * nvmet_tcp_done_recv_pdu() and try to handle the same ICReq again. + * + * That is why queue->rcv_state needs to be updated before we return. + */ queue->rcv_state = NVMET_TCP_RECV_ERR; - if (status == -EPIPE || status == -ECONNRESET) + if (status == -EPIPE || status == -ECONNRESET || !queue->nvme_sq.ctrl) kernel_sock_shutdown(queue->sock, SHUT_RDWR); else - nvmet_tcp_fatal_error(queue); + nvmet_ctrl_fatal_error(queue->nvme_sq.ctrl); } static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) @@ -887,7 +887,6 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) if (le32_to_cpu(icreq->hdr.plen) != sizeof(struct nvme_tcp_icreq_pdu)) { pr_err("bad nvme-tcp pdu length (%d)\n", le32_to_cpu(icreq->hdr.plen)); - nvmet_tcp_fatal_error(queue); return -EPROTO; } @@ -922,16 +921,29 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) iov.iov_len = sizeof(*icresp); ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); if (ret < 0) { + spin_lock_bh(&queue->state_lock); + if (queue->state == NVMET_TCP_Q_DISCONNECTING) { + spin_unlock_bh(&queue->state_lock); + return -ESHUTDOWN; + } queue->state = NVMET_TCP_Q_FAILED; + spin_unlock_bh(&queue->state_lock); return ret; /* queue removal will cleanup */ } + spin_lock_bh(&queue->state_lock); + if (queue->state == NVMET_TCP_Q_DISCONNECTING) { + spin_unlock_bh(&queue->state_lock); + /* Tell nvmet_tcp_socket_error() teardown is in progress. */ + return -ESHUTDOWN; + } queue->state = NVMET_TCP_Q_LIVE; + spin_unlock_bh(&queue->state_lock); nvmet_prepare_receive_pdu(queue); return 0; } -static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, +static int nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, struct nvmet_tcp_cmd *cmd, struct nvmet_req *req) { size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); @@ -947,19 +959,22 @@ static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, if (!nvme_is_write(cmd->req.cmd) || !data_len || data_len > cmd->req.port->inline_data_size) { nvmet_prepare_receive_pdu(queue); - return; + return 0; } ret = nvmet_tcp_map_data(cmd); if (unlikely(ret)) { pr_err("queue %d: failed to map data\n", queue->idx); - nvmet_tcp_fatal_error(queue); - return; + return -EPROTO; } queue->rcv_state = NVMET_TCP_RECV_DATA; - nvmet_tcp_build_pdu_iovec(cmd); cmd->flags |= NVMET_TCP_F_INIT_FAILED; + ret = nvmet_tcp_build_pdu_iovec(cmd); + if (unlikely(ret)) + pr_err("queue %d: failed to build PDU iovec\n", queue->idx); + + return ret; } static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) @@ -1011,7 +1026,10 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) goto err_proto; } cmd->pdu_recv = 0; - nvmet_tcp_build_pdu_iovec(cmd); + if (unlikely(nvmet_tcp_build_pdu_iovec(cmd))) { + pr_err("queue %d: failed to build PDU iovec\n", queue->idx); + goto err_proto; + } queue->cmd = cmd; queue->rcv_state = NVMET_TCP_RECV_DATA; @@ -1019,7 +1037,6 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) err_proto: /* FIXME: use proper transport errors */ - nvmet_tcp_fatal_error(queue); return -EPROTO; } @@ -1034,7 +1051,6 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) if (hdr->type != nvme_tcp_icreq) { pr_err("unexpected pdu type (%d) before icreq\n", hdr->type); - nvmet_tcp_fatal_error(queue); return -EPROTO; } return nvmet_tcp_handle_icreq(queue); @@ -1043,7 +1059,6 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) if (unlikely(hdr->type == nvme_tcp_icreq)) { pr_err("queue %d: received icreq pdu in state %d\n", queue->idx, queue->state); - nvmet_tcp_fatal_error(queue); return -EPROTO; } @@ -1060,7 +1075,6 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) pr_err("queue %d: out of commands (%d) send_list_len: %d, opcode: %d", queue->idx, queue->nr_cmds, queue->send_list_len, nvme_cmd->common.opcode); - nvmet_tcp_fatal_error(queue); return -ENOMEM; } @@ -1074,17 +1088,16 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) le32_to_cpu(req->cmd->common.dptr.sgl.length), le16_to_cpu(req->cqe->status)); - nvmet_tcp_handle_req_failure(queue, queue->cmd, req); - return 0; + return nvmet_tcp_handle_req_failure(queue, queue->cmd, req); } ret = nvmet_tcp_map_data(queue->cmd); if (unlikely(ret)) { pr_err("queue %d: failed to map data\n", queue->idx); if (nvmet_tcp_has_inline_data(queue->cmd)) - nvmet_tcp_fatal_error(queue); - else - nvmet_req_complete(req, ret); + return -EPROTO; + + nvmet_req_complete(req, ret); ret = -EAGAIN; goto out; } @@ -1092,8 +1105,11 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) if (nvmet_tcp_need_data_in(queue->cmd)) { if (nvmet_tcp_has_inline_data(queue->cmd)) { queue->rcv_state = NVMET_TCP_RECV_DATA; - nvmet_tcp_build_pdu_iovec(queue->cmd); - return 0; + ret = nvmet_tcp_build_pdu_iovec(queue->cmd); + if (unlikely(ret)) + pr_err("queue %d: failed to build PDU iovec\n", + queue->idx); + return ret; } /* send back R2T */ nvmet_tcp_queue_response(&queue->cmd->req); @@ -1204,7 +1220,6 @@ recv: if (unlikely(!nvmet_tcp_pdu_valid(hdr->type))) { pr_err("unexpected pdu type %d\n", hdr->type); - nvmet_tcp_fatal_error(queue); return -EIO; } @@ -1218,16 +1233,12 @@ recv: } if (queue->hdr_digest && - nvmet_tcp_verify_hdgst(queue, &queue->pdu, hdr->hlen)) { - nvmet_tcp_fatal_error(queue); /* fatal */ + nvmet_tcp_verify_hdgst(queue, &queue->pdu, hdr->hlen)) return -EPROTO; - } if (queue->data_digest && - nvmet_tcp_check_ddgst(queue, &queue->pdu)) { - nvmet_tcp_fatal_error(queue); /* fatal */ + nvmet_tcp_check_ddgst(queue, &queue->pdu)) return -EPROTO; - } return nvmet_tcp_done_recv_pdu(queue); } @@ -1310,9 +1321,9 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue) queue->idx, cmd->req.cmd->common.command_id, queue->pdu.cmd.hdr.type, le32_to_cpu(cmd->recv_ddgst), le32_to_cpu(cmd->exp_ddgst)); - nvmet_req_uninit(&cmd->req); + if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED)) + nvmet_req_uninit(&cmd->req); nvmet_tcp_free_cmd_buffers(cmd); - nvmet_tcp_fatal_error(queue); ret = -EPROTO; goto out; } diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index aeaf73b54c3a..f00921931eb6 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -69,7 +69,6 @@ bool nvmet_bdev_zns_enable(struct nvmet_ns *ns) void nvmet_execute_identify_ctrl_zns(struct nvmet_req *req) { u8 zasl = req->sq->ctrl->subsys->zasl; - struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl_zns *id; u16 status; @@ -79,10 +78,7 @@ void nvmet_execute_identify_ctrl_zns(struct nvmet_req *req) goto out; } - if (ctrl->ops->get_mdts) - id->zasl = min_t(u8, ctrl->ops->get_mdts(ctrl), zasl); - else - id->zasl = zasl; + id->zasl = min_not_zero(nvmet_ctrl_mdts(req), zasl); status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index e8002526cfb0..d71dac9436e3 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -1231,6 +1231,7 @@ config REGULATOR_RASPBERRYPI_TOUCHSCREEN_ATTINY tristate "Raspberry Pi 7-inch touchscreen panel ATTINY regulator" depends on ARM || ARM64 || COMPILE_TEST depends on BACKLIGHT_CLASS_DEVICE + depends on GPIOLIB depends on I2C select REGMAP_I2C help diff --git a/drivers/s390/char/Kconfig b/drivers/s390/char/Kconfig index 4d8f09910a46..7416f941e5b6 100644 --- a/drivers/s390/char/Kconfig +++ b/drivers/s390/char/Kconfig @@ -85,14 +85,6 @@ config HMC_DRV transfer cache size from its default value 0.5MB to N bytes. If N is zero, then no caching is performed. -config SCLP_OFB - def_bool n - prompt "Support for Open-for-Business SCLP Event" - depends on S390 - help - This option enables the Open-for-Business interface to the s390 - Service Element. - config S390_UV_UAPI def_tristate m prompt "Ultravisor userspace API" diff --git a/drivers/s390/char/sclp_config.c b/drivers/s390/char/sclp_config.c index 9cfbe3fc3dca..8c77e8c44fc2 100644 --- a/drivers/s390/char/sclp_config.c +++ b/drivers/s390/char/sclp_config.c @@ -80,14 +80,11 @@ static void sclp_conf_receiver_fn(struct evbuf_header *evbuf) static struct sclp_register sclp_conf_register = { -#ifdef CONFIG_SCLP_OFB .send_mask = EVTYP_CONFMGMDATA_MASK, -#endif .receive_mask = EVTYP_CONFMGMDATA_MASK, .receiver_fn = sclp_conf_receiver_fn, }; -#ifdef CONFIG_SCLP_OFB static int sclp_ofb_send_req(char *ev_data, size_t len) { static DEFINE_MUTEX(send_mutex); @@ -143,11 +140,9 @@ static const struct bin_attribute ofb_bin_attr = { }, .write = sysfs_ofb_data_write, }; -#endif static int __init sclp_ofb_setup(void) { -#ifdef CONFIG_SCLP_OFB struct kset *ofb_kset; int rc; @@ -159,7 +154,6 @@ static int __init sclp_ofb_setup(void) kset_unregister(ofb_kset); return rc; } -#endif return 0; } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 7adb2573f50d..c36c54ecd354 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -395,7 +395,7 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt) switch (req_op(rq)) { case REQ_OP_WRITE: - if (!cd->writeable) + if (get_disk_ro(cd->disk)) goto out; SCpnt->cmnd[0] = WRITE_10; cd->cdi.media_written = 1; @@ -681,6 +681,7 @@ static int sr_probe(struct scsi_device *sdev) error = -ENOMEM; if (get_capabilities(cd)) goto fail_minor; + cdrom_probe_write_features(&cd->cdi); sr_vendor_init(cd); set_capacity(disk, cd->capacity); @@ -899,14 +900,6 @@ static int get_capabilities(struct scsi_cd *cd) /*else I don't think it can close its tray cd->cdi.mask |= CDC_CLOSE_TRAY; */ - /* - * if DVD-RAM, MRW-W or CD-RW, we are randomly writable - */ - if ((cd->cdi.mask & (CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | CDC_CD_RW)) != - (CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | CDC_CD_RW)) { - cd->writeable = 1; - } - kfree(buffer); return 0; } diff --git a/drivers/scsi/sr.h b/drivers/scsi/sr.h index dc899277b3a4..2d92f9cb6fec 100644 --- a/drivers/scsi/sr.h +++ b/drivers/scsi/sr.h @@ -35,7 +35,6 @@ typedef struct scsi_cd { struct scsi_device *device; unsigned int vendor; /* vendor code, see sr_vendor.c */ unsigned long ms_offset; /* for reading multisession-CD's */ - unsigned writeable : 1; unsigned use:1; /* is this device still supportable */ unsigned xa_flag:1; /* CD has XA sectors ? */ unsigned readcd_known:1; /* drive supports READ_CD (0xbe) */ diff --git a/drivers/spi/spi-airoha-snfi.c b/drivers/spi/spi-airoha-snfi.c index 7b6c09f91fef..95bfde7c8e7f 100644 --- a/drivers/spi/spi-airoha-snfi.c +++ b/drivers/spi/spi-airoha-snfi.c @@ -546,7 +546,7 @@ static int airoha_snand_dirmap_create(struct spi_mem_dirmap_desc *desc) if (desc->info.length > SPI_NAND_CACHE_SIZE) return -E2BIG; - if (!airoha_snand_supports_op(desc->mem, &desc->info.op_tmpl)) + if (!airoha_snand_supports_op(desc->mem, desc->info.op_tmpl)) return -EOPNOTSUPP; return 0; @@ -572,7 +572,7 @@ static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc, * DUALIO and QUADIO opcodes are not supported by the spi controller, * replace them with supported opcodes. */ - opcode = desc->info.op_tmpl.cmd.opcode; + opcode = desc->info.op_tmpl->cmd.opcode; switch (opcode) { case SPI_NAND_OP_READ_FROM_CACHE_SINGLE: case SPI_NAND_OP_READ_FROM_CACHE_SINGLE_FAST: @@ -761,7 +761,7 @@ static ssize_t airoha_snand_dirmap_write(struct spi_mem_dirmap_desc *desc, /* minimum oob size is 64 */ bytes = round_up(offs + len, 64); - opcode = desc->info.op_tmpl.cmd.opcode; + opcode = desc->info.op_tmpl->cmd.opcode; switch (opcode) { case SPI_NAND_OP_PROGRAM_LOAD_SINGLE: case SPI_NAND_OP_PROGRAM_LOAD_RAMDOM_SINGLE: diff --git a/drivers/spi/spi-amlogic-spisg.c b/drivers/spi/spi-amlogic-spisg.c index 19c5eba412ef..f9de2d2c9213 100644 --- a/drivers/spi/spi-amlogic-spisg.c +++ b/drivers/spi/spi-amlogic-spisg.c @@ -794,6 +794,7 @@ static int aml_spisg_probe(struct platform_device *pdev) dma_set_max_seg_size(&pdev->dev, SPISG_BLOCK_MAX); + init_completion(&spisg->completion); ret = devm_request_irq(&pdev->dev, irq, aml_spisg_irq, 0, NULL, spisg); if (ret) { dev_err(&pdev->dev, "irq request failed\n"); @@ -806,8 +807,6 @@ static int aml_spisg_probe(struct platform_device *pdev) goto out_clk; } - init_completion(&spisg->completion); - pm_runtime_put(&spisg->pdev->dev); return 0; diff --git a/drivers/spi/spi-aspeed-smc.c b/drivers/spi/spi-aspeed-smc.c index c21323e07d3c..c20a33734f5c 100644 --- a/drivers/spi/spi-aspeed-smc.c +++ b/drivers/spi/spi-aspeed-smc.c @@ -697,7 +697,7 @@ static int aspeed_spi_dirmap_create(struct spi_mem_dirmap_desc *desc) { struct aspeed_spi *aspi = spi_controller_get_devdata(desc->mem->spi->controller); struct aspeed_spi_chip *chip = &aspi->chips[spi_get_chipselect(desc->mem->spi, 0)]; - struct spi_mem_op *op = &desc->info.op_tmpl; + struct spi_mem_op *op = desc->info.op_tmpl; u32 ctl_val; int ret = 0; @@ -769,7 +769,7 @@ static ssize_t aspeed_spi_dirmap_read(struct spi_mem_dirmap_desc *desc, if (chip->ahb_window_size < offset + len || chip->force_user_mode) { int ret; - ret = aspeed_spi_read_user(chip, &desc->info.op_tmpl, offset, len, buf); + ret = aspeed_spi_read_user(chip, desc->info.op_tmpl, offset, len, buf); if (ret < 0) return ret; } else { diff --git a/drivers/spi/spi-axiado.c b/drivers/spi/spi-axiado.c index 9057a0a8df4a..649f149617ce 100644 --- a/drivers/spi/spi-axiado.c +++ b/drivers/spi/spi-axiado.c @@ -201,7 +201,7 @@ static void ax_spi_fill_tx_fifo(struct ax_spi *xspi) * then spi control did't work thoroughly, add one byte delay */ if (ax_spi_read(xspi, AX_SPI_IVR) & AX_SPI_IVR_TFOV) - usleep_range(10, 10); + udelay(10); if (xspi->tx_buf) ax_spi_write_b(xspi, AX_SPI_TXFIFO, *xspi->tx_buf++); else diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 65aff2e70265..057381e56a7f 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1860,14 +1860,10 @@ static int cqspi_probe(struct platform_device *pdev) if (irq < 0) return -ENXIO; - ret = pm_runtime_set_active(dev); - if (ret) - return ret; - ret = clk_bulk_prepare_enable(CLK_QSPI_NUM, cqspi->clks); if (ret) { dev_err(dev, "Cannot enable QSPI clocks.\n"); - goto disable_rpm; + return ret; } /* Obtain QSPI reset control */ @@ -1962,10 +1958,11 @@ static int cqspi_probe(struct platform_device *pdev) cqspi->sclk = 0; if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) { - pm_runtime_enable(dev); pm_runtime_set_autosuspend_delay(dev, CQSPI_AUTOSUSPEND_TIMEOUT); pm_runtime_use_autosuspend(dev); pm_runtime_get_noresume(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); } host->num_chipselect = cqspi->num_chipselect; @@ -1977,7 +1974,7 @@ static int cqspi_probe(struct platform_device *pdev) ret = cqspi_request_mmap_dma(cqspi); if (ret == -EPROBE_DEFER) { dev_err_probe(&pdev->dev, ret, "Failed to request mmap DMA\n"); - goto disable_controller; + goto disable_rpm; } } @@ -1995,14 +1992,16 @@ static int cqspi_probe(struct platform_device *pdev) release_dma_chan: if (cqspi->rx_chan) dma_release_channel(cqspi->rx_chan); -disable_controller: - cqspi_controller_enable(cqspi, 0); -disable_clks: - if (pm_runtime_get_sync(&pdev->dev) >= 0) - clk_bulk_disable_unprepare(CLK_QSPI_NUM, cqspi->clks); disable_rpm: - if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) + if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) { pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + pm_runtime_put_noidle(dev); + pm_runtime_dont_use_autosuspend(dev); + } + cqspi_controller_enable(cqspi, 0); +disable_clks: + clk_bulk_disable_unprepare(CLK_QSPI_NUM, cqspi->clks); return ret; } @@ -2026,18 +2025,19 @@ static void cqspi_remove(struct platform_device *pdev) if (cqspi->rx_chan) dma_release_channel(cqspi->rx_chan); - cqspi_controller_enable(cqspi, 0); - - if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) ret = pm_runtime_get_sync(&pdev->dev); - if (ret >= 0) + if (ret >= 0) { + cqspi_controller_enable(cqspi, 0); clk_bulk_disable_unprepare(CLK_QSPI_NUM, cqspi->clks); + } if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) { - pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); } } diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 08d7dabe818d..891e2ba36958 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -741,7 +741,6 @@ static int cdns_spi_probe(struct platform_device *pdev) /* Set to default valid value */ ctlr->max_speed_hz = xspi->clk_rate / 4; xspi->speed_hz = ctlr->max_speed_hz; - pm_runtime_put_autosuspend(&pdev->dev); } else { ctlr->mode_bits |= SPI_NO_CS; ctlr->target_abort = cdns_target_abort; @@ -752,12 +751,17 @@ static int cdns_spi_probe(struct platform_device *pdev) goto clk_dis_all; } + if (!spi_controller_is_target(ctlr)) + pm_runtime_put_autosuspend(&pdev->dev); + return ret; clk_dis_all: if (!spi_controller_is_target(ctlr)) { pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); } remove_ctlr: spi_controller_put(ctlr); @@ -776,16 +780,23 @@ static void cdns_spi_remove(struct platform_device *pdev) { struct spi_controller *ctlr = platform_get_drvdata(pdev); struct cdns_spi *xspi = spi_controller_get_devdata(ctlr); + int ret = 0; + + if (!spi_controller_is_target(ctlr)) + ret = pm_runtime_get_sync(&pdev->dev); spi_controller_get(ctlr); spi_unregister_controller(ctlr); - cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE); + if (ret >= 0) + cdns_spi_write(xspi, CDNS_SPI_ER, CDNS_SPI_ER_DISABLE); if (!spi_controller_is_target(ctlr)) { pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); } spi_controller_put(ctlr); diff --git a/drivers/spi/spi-intel.c b/drivers/spi/spi-intel.c index 1775ad39e633..7494b921a743 100644 --- a/drivers/spi/spi-intel.c +++ b/drivers/spi/spi-intel.c @@ -814,7 +814,7 @@ static int intel_spi_dirmap_create(struct spi_mem_dirmap_desc *desc) struct intel_spi *ispi = spi_controller_get_devdata(desc->mem->spi->controller); const struct intel_spi_mem_op *iop; - iop = intel_spi_match_mem_op(ispi, &desc->info.op_tmpl); + iop = intel_spi_match_mem_op(ispi, desc->info.op_tmpl); if (!iop) return -EOPNOTSUPP; @@ -827,7 +827,7 @@ static ssize_t intel_spi_dirmap_read(struct spi_mem_dirmap_desc *desc, u64 offs, { struct intel_spi *ispi = spi_controller_get_devdata(desc->mem->spi->controller); const struct intel_spi_mem_op *iop = desc->priv; - struct spi_mem_op op = desc->info.op_tmpl; + struct spi_mem_op op = *desc->info.op_tmpl; int ret; /* Fill in the gaps */ @@ -844,7 +844,7 @@ static ssize_t intel_spi_dirmap_write(struct spi_mem_dirmap_desc *desc, u64 offs { struct intel_spi *ispi = spi_controller_get_devdata(desc->mem->spi->controller); const struct intel_spi_mem_op *iop = desc->priv; - struct spi_mem_op op = desc->info.op_tmpl; + struct spi_mem_op op = *desc->info.op_tmpl; int ret; op.addr.val = offs; diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index a09371a075d2..f64eda9bbd9f 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -647,7 +647,7 @@ EXPORT_SYMBOL_GPL(spi_mem_calc_op_duration); static ssize_t spi_mem_no_dirmap_read(struct spi_mem_dirmap_desc *desc, u64 offs, size_t len, void *buf) { - struct spi_mem_op op = desc->info.op_tmpl; + struct spi_mem_op op = *desc->info.op_tmpl; int ret; op.addr.val = desc->info.offset + offs; @@ -667,7 +667,7 @@ static ssize_t spi_mem_no_dirmap_read(struct spi_mem_dirmap_desc *desc, static ssize_t spi_mem_no_dirmap_write(struct spi_mem_dirmap_desc *desc, u64 offs, size_t len, const void *buf) { - struct spi_mem_op op = desc->info.op_tmpl; + struct spi_mem_op op = *desc->info.op_tmpl; int ret; op.addr.val = desc->info.offset + offs; @@ -706,19 +706,37 @@ spi_mem_dirmap_create(struct spi_mem *mem, int ret = -ENOTSUPP; /* Make sure the number of address cycles is between 1 and 8 bytes. */ - if (!info->op_tmpl.addr.nbytes || info->op_tmpl.addr.nbytes > 8) + if (!info->primary_op_tmpl.addr.nbytes || info->primary_op_tmpl.addr.nbytes > 8) return ERR_PTR(-EINVAL); /* data.dir should either be SPI_MEM_DATA_IN or SPI_MEM_DATA_OUT. */ - if (info->op_tmpl.data.dir == SPI_MEM_NO_DATA) + if (info->primary_op_tmpl.data.dir == SPI_MEM_NO_DATA) return ERR_PTR(-EINVAL); + /* Apply similar constraints to the secondary template */ + if (info->secondary_op_tmpl.cmd.opcode) { + if (!info->secondary_op_tmpl.addr.nbytes || + info->secondary_op_tmpl.addr.nbytes > 8) + return ERR_PTR(-EINVAL); + + if (info->secondary_op_tmpl.data.dir == SPI_MEM_NO_DATA) + return ERR_PTR(-EINVAL); + + if (!spi_mem_supports_op(mem, &info->secondary_op_tmpl)) + return ERR_PTR(-EOPNOTSUPP); + + if (ctlr->mem_ops && ctlr->mem_ops->dirmap_create && + !spi_mem_controller_is_capable(ctlr, secondary_op_tmpl)) + return ERR_PTR(-EOPNOTSUPP); + } + desc = kzalloc_obj(*desc); if (!desc) return ERR_PTR(-ENOMEM); desc->mem = mem; desc->info = *info; + desc->info.op_tmpl = &desc->info.primary_op_tmpl; if (ctlr->mem_ops && ctlr->mem_ops->dirmap_create) { ret = spi_mem_access_start(mem); if (ret) { @@ -733,7 +751,7 @@ spi_mem_dirmap_create(struct spi_mem *mem, if (ret) { desc->nodirmap = true; - if (!spi_mem_supports_op(desc->mem, &desc->info.op_tmpl)) + if (!spi_mem_supports_op(desc->mem, &desc->info.primary_op_tmpl)) ret = -EOPNOTSUPP; else ret = 0; @@ -857,7 +875,7 @@ ssize_t spi_mem_dirmap_read(struct spi_mem_dirmap_desc *desc, struct spi_controller *ctlr = desc->mem->spi->controller; ssize_t ret; - if (desc->info.op_tmpl.data.dir != SPI_MEM_DATA_IN) + if (desc->info.op_tmpl->data.dir != SPI_MEM_DATA_IN) return -EINVAL; if (!len) @@ -903,7 +921,7 @@ ssize_t spi_mem_dirmap_write(struct spi_mem_dirmap_desc *desc, struct spi_controller *ctlr = desc->mem->spi->controller; ssize_t ret; - if (desc->info.op_tmpl.data.dir != SPI_MEM_DATA_OUT) + if (desc->info.op_tmpl->data.dir != SPI_MEM_DATA_OUT) return -EINVAL; if (!len) diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c index b0e7fc828a50..83b688e65284 100644 --- a/drivers/spi/spi-mxic.c +++ b/drivers/spi/spi-mxic.c @@ -403,20 +403,20 @@ static ssize_t mxic_spi_mem_dirmap_read(struct spi_mem_dirmap_desc *desc, if (WARN_ON(offs + desc->info.offset + len > U32_MAX)) return -EINVAL; - writel(mxic_spi_prep_hc_cfg(desc->mem->spi, 0, desc->info.op_tmpl.data.swap16), + writel(mxic_spi_prep_hc_cfg(desc->mem->spi, 0, desc->info.op_tmpl->data.swap16), mxic->regs + HC_CFG); - writel(mxic_spi_mem_prep_op_cfg(&desc->info.op_tmpl, len), + writel(mxic_spi_mem_prep_op_cfg(desc->info.op_tmpl, len), mxic->regs + LRD_CFG); writel(desc->info.offset + offs, mxic->regs + LRD_ADDR); len = min_t(size_t, len, mxic->linear.size); writel(len, mxic->regs + LRD_RANGE); - writel(LMODE_CMD0(desc->info.op_tmpl.cmd.opcode) | + writel(LMODE_CMD0(desc->info.op_tmpl->cmd.opcode) | LMODE_SLV_ACT(spi_get_chipselect(desc->mem->spi, 0)) | LMODE_EN, mxic->regs + LRD_CTRL); - if (mxic->ecc.use_pipelined_conf && desc->info.op_tmpl.data.ecc) { + if (mxic->ecc.use_pipelined_conf && desc->info.op_tmpl->data.ecc) { ret = mxic_ecc_process_data_pipelined(mxic->ecc.pipelined_engine, NAND_PAGE_READ, mxic->linear.dma + offs); @@ -448,20 +448,20 @@ static ssize_t mxic_spi_mem_dirmap_write(struct spi_mem_dirmap_desc *desc, if (WARN_ON(offs + desc->info.offset + len > U32_MAX)) return -EINVAL; - writel(mxic_spi_prep_hc_cfg(desc->mem->spi, 0, desc->info.op_tmpl.data.swap16), + writel(mxic_spi_prep_hc_cfg(desc->mem->spi, 0, desc->info.op_tmpl->data.swap16), mxic->regs + HC_CFG); - writel(mxic_spi_mem_prep_op_cfg(&desc->info.op_tmpl, len), + writel(mxic_spi_mem_prep_op_cfg(desc->info.op_tmpl, len), mxic->regs + LWR_CFG); writel(desc->info.offset + offs, mxic->regs + LWR_ADDR); len = min_t(size_t, len, mxic->linear.size); writel(len, mxic->regs + LWR_RANGE); - writel(LMODE_CMD0(desc->info.op_tmpl.cmd.opcode) | + writel(LMODE_CMD0(desc->info.op_tmpl->cmd.opcode) | LMODE_SLV_ACT(spi_get_chipselect(desc->mem->spi, 0)) | LMODE_EN, mxic->regs + LWR_CTRL); - if (mxic->ecc.use_pipelined_conf && desc->info.op_tmpl.data.ecc) { + if (mxic->ecc.use_pipelined_conf && desc->info.op_tmpl->data.ecc) { ret = mxic_ecc_process_data_pipelined(mxic->ecc.pipelined_engine, NAND_PAGE_WRITE, mxic->linear.dma + offs); @@ -509,7 +509,7 @@ static int mxic_spi_mem_dirmap_create(struct spi_mem_dirmap_desc *desc) if (desc->info.offset + desc->info.length > U32_MAX) return -EINVAL; - if (!mxic_spi_mem_supports_op(desc->mem, &desc->info.op_tmpl)) + if (!mxic_spi_mem_supports_op(desc->mem, desc->info.op_tmpl)) return -EOPNOTSUPP; return 0; diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c index 6617751009c3..4b825044038b 100644 --- a/drivers/spi/spi-npcm-fiu.c +++ b/drivers/spi/spi-npcm-fiu.c @@ -299,11 +299,11 @@ static ssize_t npcm_fiu_direct_read(struct spi_mem_dirmap_desc *desc, for (i = 0 ; i < len ; i++) *(buf_rx + i) = ioread8(src + i); } else { - if (desc->info.op_tmpl.addr.buswidth != fiu->drd_op.addr.buswidth || - desc->info.op_tmpl.dummy.nbytes != fiu->drd_op.dummy.nbytes || - desc->info.op_tmpl.cmd.opcode != fiu->drd_op.cmd.opcode || - desc->info.op_tmpl.addr.nbytes != fiu->drd_op.addr.nbytes) - npcm_fiu_set_drd(fiu, &desc->info.op_tmpl); + if (desc->info.op_tmpl->addr.buswidth != fiu->drd_op.addr.buswidth || + desc->info.op_tmpl->dummy.nbytes != fiu->drd_op.dummy.nbytes || + desc->info.op_tmpl->cmd.opcode != fiu->drd_op.cmd.opcode || + desc->info.op_tmpl->addr.nbytes != fiu->drd_op.addr.nbytes) + npcm_fiu_set_drd(fiu, desc->info.op_tmpl); memcpy_fromio(buf_rx, src, len); } @@ -609,7 +609,7 @@ static int npcm_fiu_dirmap_create(struct spi_mem_dirmap_desc *desc) } if (!fiu->spix_mode && - desc->info.op_tmpl.data.dir == SPI_MEM_DATA_OUT) { + desc->info.op_tmpl->data.dir == SPI_MEM_DATA_OUT) { desc->nodirmap = true; return 0; } @@ -644,9 +644,9 @@ static int npcm_fiu_dirmap_create(struct spi_mem_dirmap_desc *desc) NPCM_FIU_CFG_FIU_FIX); } - if (desc->info.op_tmpl.data.dir == SPI_MEM_DATA_IN) { + if (desc->info.op_tmpl->data.dir == SPI_MEM_DATA_IN) { if (!fiu->spix_mode) - npcm_fiu_set_drd(fiu, &desc->info.op_tmpl); + npcm_fiu_set_drd(fiu, desc->info.op_tmpl); else npcm_fiux_set_direct_rd(fiu); diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 14cd1b9d9793..231fbcf0e7aa 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -98,7 +98,6 @@ #define CR0_FRF_MICROWIRE 0x2 #define CR0_XFM_OFFSET 18 -#define CR0_XFM_MASK (0x03 << SPI_XFM_OFFSET) #define CR0_XFM_TR 0x0 #define CR0_XFM_TO 0x1 #define CR0_XFM_RO 0x2 @@ -109,8 +108,6 @@ #define CR0_SOI_OFFSET 23 -#define CR0_MTM_OFFSET 0x21 - /* Bit fields in SER, 2bit */ #define SER_MASK 0x3 @@ -357,7 +354,8 @@ static irqreturn_t rockchip_spi_isr(int irq, void *dev_id) struct rockchip_spi *rs = spi_controller_get_devdata(ctlr); /* When int_cs_inactive comes, spi target abort */ - if (rs->cs_inactive && readl_relaxed(rs->regs + ROCKCHIP_SPI_IMR) & INT_CS_INACTIVE) { + if (rs->cs_inactive && + (readl_relaxed(rs->regs + ROCKCHIP_SPI_ISR) & INT_CS_INACTIVE)) { ctlr->target_abort(ctlr); writel_relaxed(0, rs->regs + ROCKCHIP_SPI_IMR); writel_relaxed(0xffffffff, rs->regs + ROCKCHIP_SPI_ICR); diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c index 6edc0c4db854..1ef7bd91b3b3 100644 --- a/drivers/spi/spi-rpc-if.c +++ b/drivers/spi/spi-rpc-if.c @@ -83,7 +83,7 @@ static ssize_t xspi_spi_mem_dirmap_write(struct spi_mem_dirmap_desc *desc, if (offs + desc->info.offset + len > U32_MAX) return -EINVAL; - rpcif_spi_mem_prepare(desc->mem->spi, &desc->info.op_tmpl, &offs, &len); + rpcif_spi_mem_prepare(desc->mem->spi, desc->info.op_tmpl, &offs, &len); return xspi_dirmap_write(rpc->dev, offs, len, buf); } @@ -97,7 +97,7 @@ static ssize_t rpcif_spi_mem_dirmap_read(struct spi_mem_dirmap_desc *desc, if (offs + desc->info.offset + len > U32_MAX) return -EINVAL; - rpcif_spi_mem_prepare(desc->mem->spi, &desc->info.op_tmpl, &offs, &len); + rpcif_spi_mem_prepare(desc->mem->spi, desc->info.op_tmpl, &offs, &len); return rpcif_dirmap_read(rpc->dev, offs, len, buf); } @@ -110,13 +110,13 @@ static int rpcif_spi_mem_dirmap_create(struct spi_mem_dirmap_desc *desc) if (desc->info.offset + desc->info.length > U32_MAX) return -EINVAL; - if (!rpcif_spi_mem_supports_op(desc->mem, &desc->info.op_tmpl)) + if (!rpcif_spi_mem_supports_op(desc->mem, desc->info.op_tmpl)) return -EOPNOTSUPP; if (!rpc->dirmap) return -EOPNOTSUPP; - if (!rpc->xspi && desc->info.op_tmpl.data.dir != SPI_MEM_DATA_IN) + if (!rpc->xspi && desc->info.op_tmpl->data.dir != SPI_MEM_DATA_IN) return -EOPNOTSUPP; return 0; diff --git a/drivers/spi/spi-rzv2h-rspi.c b/drivers/spi/spi-rzv2h-rspi.c index f45af5884638..1655efda7d20 100644 --- a/drivers/spi/spi-rzv2h-rspi.c +++ b/drivers/spi/spi-rzv2h-rspi.c @@ -579,7 +579,7 @@ static u32 rzv2h_rspi_setup_clock(struct rzv2h_rspi_priv *rspi, u32 hz) rspi->info->find_pclk_rate(rspi->pclk, hz, &best_clock); if (!best_clock.clk_rate) - return -EINVAL; + return 0; ret = clk_set_rate(best_clock.clk, best_clock.clk_rate); if (ret) diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c index 4461c6e24b9e..5f5b3cd5d725 100644 --- a/drivers/spi/spi-stm32-ospi.c +++ b/drivers/spi/spi-stm32-ospi.c @@ -602,11 +602,11 @@ static int stm32_ospi_dirmap_create(struct spi_mem_dirmap_desc *desc) { struct stm32_ospi *ospi = spi_controller_get_devdata(desc->mem->spi->controller); - if (desc->info.op_tmpl.data.dir == SPI_MEM_DATA_OUT) + if (desc->info.op_tmpl->data.dir == SPI_MEM_DATA_OUT) return -EOPNOTSUPP; /* Should never happen, as mm_base == null is an error probe exit condition */ - if (!ospi->mm_base && desc->info.op_tmpl.data.dir == SPI_MEM_DATA_IN) + if (!ospi->mm_base && desc->info.op_tmpl->data.dir == SPI_MEM_DATA_IN) return -EOPNOTSUPP; if (!ospi->mm_size) @@ -633,7 +633,7 @@ static ssize_t stm32_ospi_dirmap_read(struct spi_mem_dirmap_desc *desc, * spi_mem_op template with offs, len and *buf in order to get * all needed transfer information into struct spi_mem_op */ - memcpy(&op, &desc->info.op_tmpl, sizeof(struct spi_mem_op)); + memcpy(&op, desc->info.op_tmpl, sizeof(struct spi_mem_op)); dev_dbg(ospi->dev, "%s len = 0x%zx offs = 0x%llx buf = 0x%p\n", __func__, len, offs, buf); op.data.nbytes = len; diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index df1bbacec90a..e2a6a6eaf9b2 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -506,11 +506,11 @@ static int stm32_qspi_dirmap_create(struct spi_mem_dirmap_desc *desc) { struct stm32_qspi *qspi = spi_controller_get_devdata(desc->mem->spi->controller); - if (desc->info.op_tmpl.data.dir == SPI_MEM_DATA_OUT) + if (desc->info.op_tmpl->data.dir == SPI_MEM_DATA_OUT) return -EOPNOTSUPP; /* should never happen, as mm_base == null is an error probe exit condition */ - if (!qspi->mm_base && desc->info.op_tmpl.data.dir == SPI_MEM_DATA_IN) + if (!qspi->mm_base && desc->info.op_tmpl->data.dir == SPI_MEM_DATA_IN) return -EOPNOTSUPP; if (!qspi->mm_size) @@ -536,7 +536,7 @@ static ssize_t stm32_qspi_dirmap_read(struct spi_mem_dirmap_desc *desc, * spi_mem_op template with offs, len and *buf in order to get * all needed transfer information into struct spi_mem_op */ - memcpy(&op, &desc->info.op_tmpl, sizeof(struct spi_mem_op)); + memcpy(&op, desc->info.op_tmpl, sizeof(struct spi_mem_op)); dev_dbg(qspi->dev, "%s len = 0x%zx offs = 0x%llx buf = 0x%p\n", __func__, len, offs, buf); op.data.nbytes = len; diff --git a/drivers/spi/spi-wpcm-fiu.c b/drivers/spi/spi-wpcm-fiu.c index 0e26ff178505..cd78e927953d 100644 --- a/drivers/spi/spi-wpcm-fiu.c +++ b/drivers/spi/spi-wpcm-fiu.c @@ -377,7 +377,7 @@ static int wpcm_fiu_dirmap_create(struct spi_mem_dirmap_desc *desc) struct wpcm_fiu_spi *fiu = spi_controller_get_devdata(desc->mem->spi->controller); int cs = spi_get_chipselect(desc->mem->spi, 0); - if (desc->info.op_tmpl.data.dir != SPI_MEM_DATA_IN) + if (desc->info.op_tmpl->data.dir != SPI_MEM_DATA_IN) return -EOPNOTSUPP; /* diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 15ba592236e8..725a49a0eee7 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -1620,6 +1620,12 @@ static void privcmd_close(struct vm_area_struct *vma) kvfree(pages); } +static int privcmd_may_split(struct vm_area_struct *area, unsigned long addr) +{ + /* Forbid splitting, avoids double free via privcmd_close(). */ + return -EINVAL; +} + static vm_fault_t privcmd_fault(struct vm_fault *vmf) { printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n", @@ -1631,6 +1637,7 @@ static vm_fault_t privcmd_fault(struct vm_fault *vmf) static const struct vm_operations_struct privcmd_vm_ops = { .close = privcmd_close, + .may_split = privcmd_may_split, .fault = privcmd_fault }; diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c index b1bb01ba82f8..91923242a5ae 100644 --- a/drivers/xen/sys-hypervisor.c +++ b/drivers/xen/sys-hypervisor.c @@ -366,6 +366,8 @@ static ssize_t buildid_show(struct hyp_sysfs_attr *attr, char *buffer) ret = sprintf(buffer, "<denied>"); return ret; } + if (ret > PAGE_SIZE) + return -ENOSPC; buildid = kmalloc(sizeof(*buildid) + ret, GFP_KERNEL); if (!buildid) @@ -373,8 +375,10 @@ static ssize_t buildid_show(struct hyp_sysfs_attr *attr, char *buffer) buildid->len = ret; ret = HYPERVISOR_xen_version(XENVER_build_id, buildid); - if (ret > 0) - ret = sprintf(buffer, "%s", buildid->buf); + if (ret > 0) { + /* Build id is binary, not a string. */ + memcpy(buffer, buildid->buf, ret); + } kfree(buildid); return ret; |