diff options
Diffstat (limited to 'drivers')
138 files changed, 1398 insertions, 792 deletions
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 08bb9f2f2d23..5e4a8860a9c0 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1314,9 +1314,19 @@ static void acpi_dev_pm_detach(struct device *dev, bool power_off) */ int acpi_dev_pm_attach(struct device *dev, bool power_on) { + /* + * Skip devices whose ACPI companions match the device IDs below, + * because they require special power management handling incompatible + * with the generic ACPI PM domain. + */ + static const struct acpi_device_id special_pm_ids[] = { + {"PNP0C0B", }, /* Generic ACPI fan */ + {"INT3404", }, /* Fan */ + {} + }; struct acpi_device *adev = ACPI_COMPANION(dev); - if (!adev) + if (!adev || !acpi_match_device_ids(adev, special_pm_ids)) return 0; /* diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 0005be5ea2b4..33d19c8eb027 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -381,7 +381,8 @@ u64 cpuidle_poll_time(struct cpuidle_driver *drv, if (dev->states_usage[i].disable) continue; - limit_ns = (u64)drv->states[i].target_residency_ns; + limit_ns = drv->states[i].target_residency_ns; + break; } dev->poll_limit_ns = limit_ns; diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index c76423aaef4d..ce6a5f80fb83 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -403,6 +403,13 @@ void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx, mutex_lock(&cpuidle_lock); + spin_lock(&cpuidle_driver_lock); + + if (!drv->cpumask) { + drv->states[idx].flags |= CPUIDLE_FLAG_UNUSABLE; + goto unlock; + } + for_each_cpu(cpu, drv->cpumask) { struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); @@ -415,5 +422,8 @@ void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx, dev->states_usage[idx].disable &= ~CPUIDLE_STATE_DISABLED_BY_DRIVER; } +unlock: + spin_unlock(&cpuidle_driver_lock); + mutex_unlock(&cpuidle_lock); } diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 425149e8bab0..57f6944d65a6 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -24,11 +24,14 @@ #include <linux/printk.h> #include <linux/hrtimer.h> #include <linux/of.h> +#include <linux/pm_qos.h> #include "governor.h" #define CREATE_TRACE_POINTS #include <trace/events/devfreq.h> +#define HZ_PER_KHZ 1000 + static struct class *devfreq_class; /* @@ -99,6 +102,54 @@ static unsigned long find_available_max_freq(struct devfreq *devfreq) } /** + * get_freq_range() - Get the current freq range + * @devfreq: the devfreq instance + * @min_freq: the min frequency + * @max_freq: the max frequency + * + * This takes into consideration all constraints. + */ +static void get_freq_range(struct devfreq *devfreq, + unsigned long *min_freq, + unsigned long *max_freq) +{ + unsigned long *freq_table = devfreq->profile->freq_table; + s32 qos_min_freq, qos_max_freq; + + lockdep_assert_held(&devfreq->lock); + + /* + * Initialize minimum/maximum frequency from freq table. + * The devfreq drivers can initialize this in either ascending or + * descending order and devfreq core supports both. + */ + if (freq_table[0] < freq_table[devfreq->profile->max_state - 1]) { + *min_freq = freq_table[0]; + *max_freq = freq_table[devfreq->profile->max_state - 1]; + } else { + *min_freq = freq_table[devfreq->profile->max_state - 1]; + *max_freq = freq_table[0]; + } + + /* Apply constraints from PM QoS */ + qos_min_freq = dev_pm_qos_read_value(devfreq->dev.parent, + DEV_PM_QOS_MIN_FREQUENCY); + qos_max_freq = dev_pm_qos_read_value(devfreq->dev.parent, + DEV_PM_QOS_MAX_FREQUENCY); + *min_freq = max(*min_freq, (unsigned long)HZ_PER_KHZ * qos_min_freq); + if (qos_max_freq != PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE) + *max_freq = min(*max_freq, + (unsigned long)HZ_PER_KHZ * qos_max_freq); + + /* Apply constraints from OPP interface */ + *min_freq = max(*min_freq, devfreq->scaling_min_freq); + *max_freq = min(*max_freq, devfreq->scaling_max_freq); + + if (*min_freq > *max_freq) + *min_freq = *max_freq; +} + +/** * devfreq_get_freq_level() - Lookup freq_table for the frequency * @devfreq: the devfreq instance * @freq: the target frequency @@ -351,16 +402,7 @@ int update_devfreq(struct devfreq *devfreq) err = devfreq->governor->get_target_freq(devfreq, &freq); if (err) return err; - - /* - * Adjust the frequency with user freq, QoS and available freq. - * - * List from the highest priority - * max_freq - * min_freq - */ - max_freq = min(devfreq->scaling_max_freq, devfreq->max_freq); - min_freq = max(devfreq->scaling_min_freq, devfreq->min_freq); + get_freq_range(devfreq, &min_freq, &max_freq); if (freq < min_freq) { freq = min_freq; @@ -568,26 +610,69 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type, void *devp) { struct devfreq *devfreq = container_of(nb, struct devfreq, nb); - int ret; + int err = -EINVAL; mutex_lock(&devfreq->lock); devfreq->scaling_min_freq = find_available_min_freq(devfreq); - if (!devfreq->scaling_min_freq) { - mutex_unlock(&devfreq->lock); - return -EINVAL; - } + if (!devfreq->scaling_min_freq) + goto out; devfreq->scaling_max_freq = find_available_max_freq(devfreq); if (!devfreq->scaling_max_freq) { - mutex_unlock(&devfreq->lock); - return -EINVAL; + devfreq->scaling_max_freq = ULONG_MAX; + goto out; } - ret = update_devfreq(devfreq); + err = update_devfreq(devfreq); + +out: mutex_unlock(&devfreq->lock); + if (err) + dev_err(devfreq->dev.parent, + "failed to update frequency from OPP notifier (%d)\n", + err); - return ret; + return NOTIFY_OK; +} + +/** + * qos_notifier_call() - Common handler for QoS constraints. + * @devfreq: the devfreq instance. + */ +static int qos_notifier_call(struct devfreq *devfreq) +{ + int err; + + mutex_lock(&devfreq->lock); + err = update_devfreq(devfreq); + mutex_unlock(&devfreq->lock); + if (err) + dev_err(devfreq->dev.parent, + "failed to update frequency from PM QoS (%d)\n", + err); + + return NOTIFY_OK; +} + +/** + * qos_min_notifier_call() - Callback for QoS min_freq changes. + * @nb: Should be devfreq->nb_min + */ +static int qos_min_notifier_call(struct notifier_block *nb, + unsigned long val, void *ptr) +{ + return qos_notifier_call(container_of(nb, struct devfreq, nb_min)); +} + +/** + * qos_max_notifier_call() - Callback for QoS max_freq changes. + * @nb: Should be devfreq->nb_max + */ +static int qos_max_notifier_call(struct notifier_block *nb, + unsigned long val, void *ptr) +{ + return qos_notifier_call(container_of(nb, struct devfreq, nb_max)); } /** @@ -599,16 +684,36 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type, static void devfreq_dev_release(struct device *dev) { struct devfreq *devfreq = to_devfreq(dev); + int err; mutex_lock(&devfreq_list_lock); - if (IS_ERR(find_device_devfreq(devfreq->dev.parent))) { - mutex_unlock(&devfreq_list_lock); - dev_warn(&devfreq->dev, "releasing devfreq which doesn't exist\n"); - return; - } list_del(&devfreq->node); mutex_unlock(&devfreq_list_lock); + err = dev_pm_qos_remove_notifier(devfreq->dev.parent, &devfreq->nb_max, + DEV_PM_QOS_MAX_FREQUENCY); + if (err && err != -ENOENT) + dev_warn(dev->parent, + "Failed to remove max_freq notifier: %d\n", err); + err = dev_pm_qos_remove_notifier(devfreq->dev.parent, &devfreq->nb_min, + DEV_PM_QOS_MIN_FREQUENCY); + if (err && err != -ENOENT) + dev_warn(dev->parent, + "Failed to remove min_freq notifier: %d\n", err); + + if (dev_pm_qos_request_active(&devfreq->user_max_freq_req)) { + err = dev_pm_qos_remove_request(&devfreq->user_max_freq_req); + if (err) + dev_warn(dev->parent, + "Failed to remove max_freq request: %d\n", err); + } + if (dev_pm_qos_request_active(&devfreq->user_min_freq_req)) { + err = dev_pm_qos_remove_request(&devfreq->user_min_freq_req); + if (err) + dev_warn(dev->parent, + "Failed to remove min_freq request: %d\n", err); + } + if (devfreq->profile->exit) devfreq->profile->exit(devfreq->dev.parent); @@ -660,6 +765,7 @@ struct devfreq *devfreq_add_device(struct device *dev, devfreq->dev.parent = dev; devfreq->dev.class = devfreq_class; devfreq->dev.release = devfreq_dev_release; + INIT_LIST_HEAD(&devfreq->node); devfreq->profile = profile; strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN); devfreq->previous_freq = profile->initial_freq; @@ -681,7 +787,6 @@ struct devfreq *devfreq_add_device(struct device *dev, err = -EINVAL; goto err_dev; } - devfreq->min_freq = devfreq->scaling_min_freq; devfreq->scaling_max_freq = find_available_max_freq(devfreq); if (!devfreq->scaling_max_freq) { @@ -689,7 +794,6 @@ struct devfreq *devfreq_add_device(struct device *dev, err = -EINVAL; goto err_dev; } - devfreq->max_freq = devfreq->scaling_max_freq; devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev); atomic_set(&devfreq->suspend_count, 0); @@ -730,6 +834,28 @@ struct devfreq *devfreq_add_device(struct device *dev, mutex_unlock(&devfreq->lock); + err = dev_pm_qos_add_request(dev, &devfreq->user_min_freq_req, + DEV_PM_QOS_MIN_FREQUENCY, 0); + if (err < 0) + goto err_devfreq; + err = dev_pm_qos_add_request(dev, &devfreq->user_max_freq_req, + DEV_PM_QOS_MAX_FREQUENCY, + PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); + if (err < 0) + goto err_devfreq; + + devfreq->nb_min.notifier_call = qos_min_notifier_call; + err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_min, + DEV_PM_QOS_MIN_FREQUENCY); + if (err) + goto err_devfreq; + + devfreq->nb_max.notifier_call = qos_max_notifier_call; + err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_max, + DEV_PM_QOS_MAX_FREQUENCY); + if (err) + goto err_devfreq; + mutex_lock(&devfreq_list_lock); governor = try_then_request_governor(devfreq->governor_name); @@ -1303,41 +1429,37 @@ static ssize_t min_freq_store(struct device *dev, struct device_attribute *attr, unsigned long value; int ret; + /* + * Protect against theoretical sysfs writes between + * device_add and dev_pm_qos_add_request + */ + if (!dev_pm_qos_request_active(&df->user_min_freq_req)) + return -EAGAIN; + ret = sscanf(buf, "%lu", &value); if (ret != 1) return -EINVAL; - mutex_lock(&df->lock); - - if (value) { - if (value > df->max_freq) { - ret = -EINVAL; - goto unlock; - } - } else { - unsigned long *freq_table = df->profile->freq_table; - - /* Get minimum frequency according to sorting order */ - if (freq_table[0] < freq_table[df->profile->max_state - 1]) - value = freq_table[0]; - else - value = freq_table[df->profile->max_state - 1]; - } + /* Round down to kHz for PM QoS */ + ret = dev_pm_qos_update_request(&df->user_min_freq_req, + value / HZ_PER_KHZ); + if (ret < 0) + return ret; - df->min_freq = value; - update_devfreq(df); - ret = count; -unlock: - mutex_unlock(&df->lock); - return ret; + return count; } static ssize_t min_freq_show(struct device *dev, struct device_attribute *attr, char *buf) { struct devfreq *df = to_devfreq(dev); + unsigned long min_freq, max_freq; - return sprintf(buf, "%lu\n", max(df->scaling_min_freq, df->min_freq)); + mutex_lock(&df->lock); + get_freq_range(df, &min_freq, &max_freq); + mutex_unlock(&df->lock); + + return sprintf(buf, "%lu\n", min_freq); } static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr, @@ -1347,33 +1469,37 @@ static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr, unsigned long value; int ret; + /* + * Protect against theoretical sysfs writes between + * device_add and dev_pm_qos_add_request + */ + if (!dev_pm_qos_request_active(&df->user_max_freq_req)) + return -EINVAL; + ret = sscanf(buf, "%lu", &value); if (ret != 1) return -EINVAL; - mutex_lock(&df->lock); - - if (value) { - if (value < df->min_freq) { - ret = -EINVAL; - goto unlock; - } - } else { - unsigned long *freq_table = df->profile->freq_table; + /* + * PM QoS frequencies are in kHz so we need to convert. Convert by + * rounding upwards so that the acceptable interval never shrinks. + * + * For example if the user writes "666666666" to sysfs this value will + * be converted to 666667 kHz and back to 666667000 Hz before an OPP + * lookup, this ensures that an OPP of 666666666Hz is still accepted. + * + * A value of zero means "no limit". + */ + if (value) + value = DIV_ROUND_UP(value, HZ_PER_KHZ); + else + value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; - /* Get maximum frequency according to sorting order */ - if (freq_table[0] < freq_table[df->profile->max_state - 1]) - value = freq_table[df->profile->max_state - 1]; - else - value = freq_table[0]; - } + ret = dev_pm_qos_update_request(&df->user_max_freq_req, value); + if (ret < 0) + return ret; - df->max_freq = value; - update_devfreq(df); - ret = count; -unlock: - mutex_unlock(&df->lock); - return ret; + return count; } static DEVICE_ATTR_RW(min_freq); @@ -1381,8 +1507,13 @@ static ssize_t max_freq_show(struct device *dev, struct device_attribute *attr, char *buf) { struct devfreq *df = to_devfreq(dev); + unsigned long min_freq, max_freq; + + mutex_lock(&df->lock); + get_freq_range(df, &min_freq, &max_freq); + mutex_unlock(&df->lock); - return sprintf(buf, "%lu\n", min(df->scaling_max_freq, df->max_freq)); + return sprintf(buf, "%lu\n", max_freq); } static DEVICE_ATTR_RW(max_freq); diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 76fb072c22dc..5a5a1da01a00 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -221,7 +221,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, a_fences = get_fences(a, &a_num_fences); b_fences = get_fences(b, &b_num_fences); if (a_num_fences > INT_MAX - b_num_fences) - return NULL; + goto err; num_fences = a_num_fences + b_num_fences; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index d101f072c8f8..407816da9fcb 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -681,7 +681,7 @@ device_initcall(efi_load_efivars); { name }, \ { prop }, \ offsetof(struct efi_fdt_params, field), \ - FIELD_SIZEOF(struct efi_fdt_params, field) \ + sizeof_field(struct efi_fdt_params, field) \ } struct params { diff --git a/drivers/gpu/drm/amd/acp/Kconfig b/drivers/gpu/drm/amd/acp/Kconfig index d968c2471412..0d12ebf66174 100644 --- a/drivers/gpu/drm/amd/acp/Kconfig +++ b/drivers/gpu/drm/amd/acp/Kconfig @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: MIT menu "ACP (Audio CoProcessor) Configuration" config DRM_AMD_ACP diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig index 2e98c016cb47..9375e7f12420 100644 --- a/drivers/gpu/drm/amd/amdgpu/Kconfig +++ b/drivers/gpu/drm/amd/amdgpu/Kconfig @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: MIT config DRM_AMDGPU_SI bool "Enable amdgpu support for SI parts" depends on DRM_AMDGPU diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 2cdaf3b2a721..6614d8a6f4c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -604,11 +604,8 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr) continue; } - for (i = 0; i < num_entities; i++) { - mutex_lock(&ctx->adev->lock_reset); + for (i = 0; i < num_entities; i++) drm_sched_entity_fini(&ctx->entities[0][i].entity); - mutex_unlock(&ctx->adev->lock_reset); - } } } diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c index 16fbd2bc8ad1..4043ebcea5de 100644 --- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c +++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c @@ -268,23 +268,29 @@ static void df_v3_6_update_medium_grain_clock_gating(struct amdgpu_device *adev, { u32 tmp; - /* Put DF on broadcast mode */ - adev->df_funcs->enable_broadcast_mode(adev, true); - - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) { - tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater); - tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; - tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY; - WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp); - } else { - tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater); - tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; - tmp |= DF_V3_6_MGCG_DISABLE; - WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp); - } + if (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG) { + /* Put DF on broadcast mode */ + adev->df_funcs->enable_broadcast_mode(adev, true); + + if (enable) { + tmp = RREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater); + tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; + tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY; + WREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater, tmp); + } else { + tmp = RREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater); + tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; + tmp |= DF_V3_6_MGCG_DISABLE; + WREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater, tmp); + } - /* Exit broadcast mode */ - adev->df_funcs->enable_broadcast_mode(adev, false); + /* Exit broadcast mode */ + adev->df_funcs->enable_broadcast_mode(adev, false); + } } static void df_v3_6_get_clockgating_state(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f2c1b026397b..ba9e53a1abc3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -117,10 +117,13 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CGTT_SCLK_CTRL, 0x10000000, 0x10000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL2, 0xffffffff, 0x1402002f), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL3, 0xffff9fff, 0x00001188), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_TIMEOUT_COUNTER, 0xffffffff, 0x00000800), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE, 0x3fffffff, 0x08000009), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0x00400000, 0x04440000), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0x00000800, 0x00000820), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL, 0x001f0000, 0x00070104), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000100, 0x00000130), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff), @@ -162,10 +165,13 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CGTT_SCLK_CTRL, 0xffff0fff, 0x10000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL2, 0xffffffff, 0x1402002f), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL3, 0xffffbfff, 0x00000188), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_TIMEOUT_COUNTER, 0xffffffff, 0x00000800), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE, 0x3fffffff, 0x08000009), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0x00400000, 0x04440000), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0x00000800, 0x00000820), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL, 0x001f0000, 0x00070105), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000133, 0x00000130), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff), diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 983db77999e7..52a647d7022d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -6146,7 +6146,23 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr, bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT; bool int_sel = flags & AMDGPU_FENCE_FLAG_INT; - /* EVENT_WRITE_EOP - flush caches, send int */ + /* Workaround for cache flush problems. First send a dummy EOP + * event down the pipe with seq one below. + */ + amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); + amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN | + EOP_TC_ACTION_EN | + EOP_TC_WB_ACTION_EN | + EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) | + EVENT_INDEX(5))); + amdgpu_ring_write(ring, addr & 0xfffffffc); + amdgpu_ring_write(ring, (upper_32_bits(addr) & 0xffff) | + DATA_SEL(1) | INT_SEL(0)); + amdgpu_ring_write(ring, lower_32_bits(seq - 1)); + amdgpu_ring_write(ring, upper_32_bits(seq - 1)); + + /* Then send the real EOP event down the pipe: + * EVENT_WRITE_EOP - flush caches, send int */ amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN | EOP_TC_ACTION_EN | @@ -6888,7 +6904,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = { 5 + /* COND_EXEC */ 7 + /* PIPELINE_SYNC */ VI_FLUSH_GPU_TLB_NUM_WREG * 5 + 9 + /* VM_FLUSH */ - 8 + /* FENCE for VM_FLUSH */ + 12 + /* FENCE for VM_FLUSH */ 20 + /* GDS switch */ 4 + /* double SWITCH_BUFFER, the first COND_EXEC jump to the place just @@ -6900,7 +6916,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = { 31 + /* DE_META */ 3 + /* CNTX_CTRL */ 5 + /* HDP_INVL */ - 8 + 8 + /* FENCE x2 */ + 12 + 12 + /* FENCE x2 */ 2, /* SWITCH_BUFFER */ .emit_ib_size = 4, /* gfx_v8_0_ring_emit_ib_gfx */ .emit_ib = gfx_v8_0_ring_emit_ib_gfx, diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 232469507446..f5725336a5f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -219,6 +219,21 @@ static uint32_t gmc_v10_0_get_invalidate_req(unsigned int vmid, return req; } +/** + * gmc_v10_0_use_invalidate_semaphore - judge whether to use semaphore + * + * @adev: amdgpu_device pointer + * @vmhub: vmhub type + * + */ +static bool gmc_v10_0_use_invalidate_semaphore(struct amdgpu_device *adev, + uint32_t vmhub) +{ + return ((vmhub == AMDGPU_MMHUB_0 || + vmhub == AMDGPU_MMHUB_1) && + (!amdgpu_sriov_vf(adev))); +} + /* * GART * VMID 0 is the physical GPU addresses as used by the kernel. @@ -229,6 +244,7 @@ static uint32_t gmc_v10_0_get_invalidate_req(unsigned int vmid, static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid, unsigned int vmhub, uint32_t flush_type) { + bool use_semaphore = gmc_v10_0_use_invalidate_semaphore(adev, vmhub); struct amdgpu_vmhub *hub = &adev->vmhub[vmhub]; u32 tmp = gmc_v10_0_get_invalidate_req(vmid, flush_type); /* Use register 17 for GART */ @@ -244,8 +260,7 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid, */ /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ - if (vmhub == AMDGPU_MMHUB_0 || - vmhub == AMDGPU_MMHUB_1) { + if (use_semaphore) { for (i = 0; i < adev->usec_timeout; i++) { /* a read return value of 1 means semaphore acuqire */ tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng); @@ -278,8 +293,7 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid, } /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ - if (vmhub == AMDGPU_MMHUB_0 || - vmhub == AMDGPU_MMHUB_1) + if (use_semaphore) /* * add semaphore release after invalidation, * write with 0 means semaphore release @@ -369,6 +383,7 @@ error_alloc: static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, unsigned vmid, uint64_t pd_addr) { + bool use_semaphore = gmc_v10_0_use_invalidate_semaphore(ring->adev, ring->funcs->vmhub); struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub]; uint32_t req = gmc_v10_0_get_invalidate_req(vmid, 0); unsigned eng = ring->vm_inv_eng; @@ -381,8 +396,7 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, */ /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ - if (ring->funcs->vmhub == AMDGPU_MMHUB_0 || - ring->funcs->vmhub == AMDGPU_MMHUB_1) + if (use_semaphore) /* a read return value of 1 means semaphore acuqire */ amdgpu_ring_emit_reg_wait(ring, hub->vm_inv_eng0_sem + eng, 0x1, 0x1); @@ -398,8 +412,7 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, req, 1 << vmid); /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ - if (ring->funcs->vmhub == AMDGPU_MMHUB_0 || - ring->funcs->vmhub == AMDGPU_MMHUB_1) + if (use_semaphore) /* * add semaphore release after invalidation, * write with 0 means semaphore release diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 3c355fb5d2b4..a5b68b5e452f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -416,6 +416,24 @@ static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vmid, return req; } +/** + * gmc_v9_0_use_invalidate_semaphore - judge whether to use semaphore + * + * @adev: amdgpu_device pointer + * @vmhub: vmhub type + * + */ +static bool gmc_v9_0_use_invalidate_semaphore(struct amdgpu_device *adev, + uint32_t vmhub) +{ + return ((vmhub == AMDGPU_MMHUB_0 || + vmhub == AMDGPU_MMHUB_1) && + (!amdgpu_sriov_vf(adev)) && + (!(adev->asic_type == CHIP_RAVEN && + adev->rev_id < 0x8 && + adev->pdev->device == 0x15d8))); +} + /* * GART * VMID 0 is the physical GPU addresses as used by the kernel. @@ -435,6 +453,7 @@ static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vmid, static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, uint32_t vmhub, uint32_t flush_type) { + bool use_semaphore = gmc_v9_0_use_invalidate_semaphore(adev, vmhub); const unsigned eng = 17; u32 j, tmp; struct amdgpu_vmhub *hub; @@ -468,8 +487,7 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, */ /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ - if (vmhub == AMDGPU_MMHUB_0 || - vmhub == AMDGPU_MMHUB_1) { + if (use_semaphore) { for (j = 0; j < adev->usec_timeout; j++) { /* a read return value of 1 means semaphore acuqire */ tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng); @@ -499,8 +517,7 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, } /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ - if (vmhub == AMDGPU_MMHUB_0 || - vmhub == AMDGPU_MMHUB_1) + if (use_semaphore) /* * add semaphore release after invalidation, * write with 0 means semaphore release @@ -518,6 +535,7 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, unsigned vmid, uint64_t pd_addr) { + bool use_semaphore = gmc_v9_0_use_invalidate_semaphore(ring->adev, ring->funcs->vmhub); struct amdgpu_device *adev = ring->adev; struct amdgpu_vmhub *hub = &adev->vmhub[ring->funcs->vmhub]; uint32_t req = gmc_v9_0_get_invalidate_req(vmid, 0); @@ -531,8 +549,7 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, */ /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ - if (ring->funcs->vmhub == AMDGPU_MMHUB_0 || - ring->funcs->vmhub == AMDGPU_MMHUB_1) + if (use_semaphore) /* a read return value of 1 means semaphore acuqire */ amdgpu_ring_emit_reg_wait(ring, hub->vm_inv_eng0_sem + eng, 0x1, 0x1); @@ -548,8 +565,7 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, req, 1 << vmid); /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ - if (ring->funcs->vmhub == AMDGPU_MMHUB_0 || - ring->funcs->vmhub == AMDGPU_MMHUB_1) + if (use_semaphore) /* * add semaphore release after invalidation, * write with 0 means semaphore release diff --git a/drivers/gpu/drm/amd/amdkfd/Kconfig b/drivers/gpu/drm/amd/amdkfd/Kconfig index ba0e68057a89..b3672d10ea54 100644 --- a/drivers/gpu/drm/amd/amdkfd/Kconfig +++ b/drivers/gpu/drm/amd/amdkfd/Kconfig @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: MIT # # Heterogenous system architecture configuration # diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 313183b80032..ae161fe86ebb 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: MIT menu "Display Engine Configuration" depends on DRM && DRM_AMDGPU diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 7873abea4112..5c3fcaa47410 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1625,6 +1625,7 @@ static enum bp_result construct_integrated_info( /* Don't need to check major revision as they are all 1 */ switch (revision.minor) { case 11: + case 12: result = get_integrated_info_v11(bp, info); break; default: diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 790a2d211bd6..35c55e54eac0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -471,12 +471,28 @@ static void rn_notify_wm_ranges(struct clk_mgr *clk_mgr_base) } +static bool rn_are_clock_states_equal(struct dc_clocks *a, + struct dc_clocks *b) +{ + if (a->dispclk_khz != b->dispclk_khz) + return false; + else if (a->dppclk_khz != b->dppclk_khz) + return false; + else if (a->dcfclk_khz != b->dcfclk_khz) + return false; + else if (a->dcfclk_deep_sleep_khz != b->dcfclk_deep_sleep_khz) + return false; + + return true; +} + + static struct clk_mgr_funcs dcn21_funcs = { .get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz, .update_clocks = rn_update_clocks, .init_clocks = rn_init_clocks, .enable_pme_wa = rn_enable_pme_wa, - /* .dump_clk_registers = rn_dump_clk_registers, */ + .are_clock_states_equal = rn_are_clock_states_equal, .notify_wm_ranges = rn_notify_wm_ranges }; @@ -518,36 +534,83 @@ struct clk_bw_params rn_bw_params = { .num_entries = 4, }, - .wm_table = { - .entries = { - { - .wm_inst = WM_A, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 23.84, - .valid = true, - }, - { - .wm_inst = WM_B, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 23.84, - .valid = true, - }, - { - .wm_inst = WM_C, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 23.84, - .valid = true, - }, - { - .wm_inst = WM_D, - .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 23.84, - .valid = true, - }, +}; + +struct wm_table ddr4_wm_table = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 6.09, + .sr_enter_plus_exit_time_us = 7.14, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, }, } }; +struct wm_table lpddr4_wm_table = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 23.84, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 17.0, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 23.84, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 17.0, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 23.84, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 17.0, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 23.84, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 17.0, + .valid = true, + }, + } +}; + + static unsigned int find_dcfclk_for_voltage(struct dpm_clocks *clock_table, unsigned int voltage) { int i; @@ -561,7 +624,7 @@ static unsigned int find_dcfclk_for_voltage(struct dpm_clocks *clock_table, unsi return 0; } -static void rn_clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params, struct dpm_clocks *clock_table, struct hw_asic_id *asic_id) +static void rn_clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params, struct dpm_clocks *clock_table, struct integrated_info *bios_info) { int i, j = 0; @@ -593,8 +656,8 @@ static void rn_clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params bw_params->clk_table.entries[i].dcfclk_mhz = find_dcfclk_for_voltage(clock_table, clock_table->FClocks[j].Vol); } - bw_params->vram_type = asic_id->vram_type; - bw_params->num_channels = asic_id->vram_width / DDR4_DRAM_WIDTH; + bw_params->vram_type = bios_info->memory_type; + bw_params->num_channels = bios_info->ma_channel_number; for (i = 0; i < WM_SET_COUNT; i++) { bw_params->wm_table.entries[i].wm_inst = i; @@ -669,15 +732,24 @@ void rn_clk_mgr_construct( ASSERT(clk_mgr->base.dprefclk_khz == 600000); clk_mgr->base.dprefclk_khz = 600000; } + + if (ctx->dc_bios->integrated_info->memory_type == LpDdr4MemType) { + rn_bw_params.wm_table = lpddr4_wm_table; + } else { + rn_bw_params.wm_table = ddr4_wm_table; + } } dce_clock_read_ss_info(clk_mgr); + clk_mgr->base.bw_params = &rn_bw_params; if (pp_smu && pp_smu->rn_funcs.get_dpm_clock_table) { pp_smu->rn_funcs.get_dpm_clock_table(&pp_smu->rn_funcs.pp_smu, &clock_table); - rn_clk_mgr_helper_populate_bw_params(clk_mgr->base.bw_params, &clock_table, &ctx->asic_id); + if (ctx->dc_bios && ctx->dc_bios->integrated_info) { + rn_clk_mgr_helper_populate_bw_params (clk_mgr->base.bw_params, &clock_table, ctx->dc_bios->integrated_info); + } } if (!IS_FPGA_MAXIMUS_DC(ctx->dce_environment) && clk_mgr->smu_ver >= 0x00371500) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 12ba6fdf89b7..62d8289abb4e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -372,7 +372,7 @@ bool dc_link_is_dp_sink_present(struct dc_link *link) if (GPIO_RESULT_OK != dal_ddc_open( ddc, GPIO_MODE_INPUT, GPIO_DDC_CONFIG_TYPE_MODE_I2C)) { - dal_gpio_destroy_ddc(&ddc); + dal_ddc_close(ddc); return present; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index 7f904d55c1bc..81789191d4ec 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -586,7 +586,7 @@ bool dal_ddc_service_query_ddc_data( bool dal_ddc_submit_aux_command(struct ddc_service *ddc, struct aux_payload *payload) { - uint8_t retrieved = 0; + uint32_t retrieved = 0; bool ret = 0; if (!ddc) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 0f59b68aa4c2..504055fc70e8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -3522,7 +3522,14 @@ void dp_set_fec_enable(struct dc_link *link, bool enable) if (link_enc->funcs->fec_set_enable && link->dpcd_caps.fec_cap.bits.FEC_CAPABLE) { if (link->fec_state == dc_link_fec_ready && enable) { - msleep(1); + /* Accord to DP spec, FEC enable sequence can first + * be transmitted anytime after 1000 LL codes have + * been transmitted on the link after link training + * completion. Using 1 lane RBR should have the maximum + * time for transmitting 1000 LL codes which is 6.173 us. + * So use 7 microseconds delay instead. + */ + udelay(7); link_enc->funcs->fec_set_enable(link_enc, true); link->fec_state = dc_link_fec_enabled; } else if (link->fec_state == dc_link_fec_enabled && !enable) { diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index e472608faf33..793c0cec407f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -583,6 +583,8 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, uint8_t reply; bool payload_reply = true; enum aux_channel_operation_result operation_result; + bool retry_on_defer = false; + int aux_ack_retries = 0, aux_defer_retries = 0, aux_i2c_defer_retries = 0, @@ -613,8 +615,10 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, break; case AUX_TRANSACTION_REPLY_AUX_DEFER: - case AUX_TRANSACTION_REPLY_I2C_OVER_AUX_NACK: case AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER: + retry_on_defer = true; + /* fall through */ + case AUX_TRANSACTION_REPLY_I2C_OVER_AUX_NACK: if (++aux_defer_retries >= AUX_MAX_DEFER_RETRIES) { goto fail; } else { @@ -647,15 +651,24 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, break; case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT: - if (++aux_timeout_retries >= AUX_MAX_TIMEOUT_RETRIES) - goto fail; - else { - /* - * DP 1.4, 2.8.2: AUX Transaction Response/Reply Timeouts - * According to the DP spec there should be 3 retries total - * with a 400us wait inbetween each. Hardware already waits - * for 550us therefore no wait is required here. - */ + // Check whether a DEFER had occurred before the timeout. + // If so, treat timeout as a DEFER. + if (retry_on_defer) { + if (++aux_defer_retries >= AUX_MAX_DEFER_RETRIES) + goto fail; + else if (payload->defer_delay > 0) + msleep(payload->defer_delay); + } else { + if (++aux_timeout_retries >= AUX_MAX_TIMEOUT_RETRIES) + goto fail; + else { + /* + * DP 1.4, 2.8.2: AUX Transaction Response/Reply Timeouts + * According to the DP spec there should be 3 retries total + * with a 400us wait inbetween each. Hardware already waits + * for 550us therefore no wait is required here. + */ + } } break; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile index 63f3bddba7da..10b47986526b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: MIT # # Makefile for DCN. diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 09793336d84f..23ff2f1c75b5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -923,7 +923,9 @@ static const struct resource_caps res_cap_nv14 = { .num_dwb = 1, .num_ddc = 5, .num_vmid = 16, +#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT .num_dsc = 5, +#endif }; static const struct dc_debug_options debug_defaults_drv = { @@ -1536,13 +1538,20 @@ enum dc_status dcn20_build_mapped_resource(const struct dc *dc, struct dc_state static void acquire_dsc(struct resource_context *res_ctx, const struct resource_pool *pool, - struct display_stream_compressor **dsc) + struct display_stream_compressor **dsc, + int pipe_idx) { int i; ASSERT(*dsc == NULL); *dsc = NULL; + if (pool->res_cap->num_dsc == pool->res_cap->num_opp) { + *dsc = pool->dscs[pipe_idx]; + res_ctx->is_dsc_acquired[pipe_idx] = true; + return; + } + /* Find first free DSC */ for (i = 0; i < pool->res_cap->num_dsc; i++) if (!res_ctx->is_dsc_acquired[i]) { @@ -1585,7 +1594,7 @@ static enum dc_status add_dsc_to_stream_resource(struct dc *dc, if (pipe_ctx->stream != dc_stream) continue; - acquire_dsc(&dc_ctx->res_ctx, pool, &pipe_ctx->stream_res.dsc); + acquire_dsc(&dc_ctx->res_ctx, pool, &pipe_ctx->stream_res.dsc, i); /* The number of DSCs can be less than the number of pipes */ if (!pipe_ctx->stream_res.dsc) { @@ -1785,7 +1794,7 @@ bool dcn20_split_stream_for_odm( next_odm_pipe->stream_res.opp = pool->opps[next_odm_pipe->pipe_idx]; #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT if (next_odm_pipe->stream->timing.flags.DSC == 1) { - acquire_dsc(res_ctx, pool, &next_odm_pipe->stream_res.dsc); + acquire_dsc(res_ctx, pool, &next_odm_pipe->stream_res.dsc, next_odm_pipe->pipe_idx); ASSERT(next_odm_pipe->stream_res.dsc); if (next_odm_pipe->stream_res.dsc == NULL) return false; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c index 4b3401616434..fcb3877b4fcb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c @@ -492,15 +492,23 @@ void enc2_stream_encoder_dp_unblank( DP_VID_N_MUL, n_multiply); } - /* set DIG_START to 0x1 to reset FIFO */ + /* make sure stream is disabled before resetting steer fifo */ + REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, false); + REG_WAIT(DP_VID_STREAM_CNTL, DP_VID_STREAM_STATUS, 0, 10, 5000); + /* set DIG_START to 0x1 to reset FIFO */ REG_UPDATE(DIG_FE_CNTL, DIG_START, 1); + udelay(1); /* write 0 to take the FIFO out of reset */ REG_UPDATE(DIG_FE_CNTL, DIG_START, 0); - /* switch DP encoder to CRTC data */ + /* switch DP encoder to CRTC data, but reset it the fifo first. It may happen + * that it overflows during mode transition, and sometimes doesn't recover. + */ + REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 1); + udelay(10); REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 0); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile index 14113ccf498d..5b8c17564bc1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: MIT # # Makefile for DCN21. diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 459bd9a5caed..b29b2c99a564 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -23,6 +23,8 @@ * */ +#include <linux/slab.h> + #include "dm_services.h" #include "dc.h" @@ -257,7 +259,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .vmm_page_size_bytes = 4096, .dram_clock_change_latency_us = 23.84, .return_bus_width_bytes = 64, - .dispclk_dppclk_vco_speed_mhz = 3550, + .dispclk_dppclk_vco_speed_mhz = 3600, .xfc_bus_transport_time_us = 4, .xfc_xbuf_latency_tolerance_us = 4, .use_urgent_burst_bw = 1, @@ -1000,6 +1002,8 @@ static void calculate_wm_set_for_vlevel( pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz; dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us; + dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us; + dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us; wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000; wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000; @@ -1017,14 +1021,21 @@ static void calculate_wm_set_for_vlevel( static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb) { + int i; + kernel_fpu_begin(); if (dc->bb_overrides.sr_exit_time_ns) { - bb->sr_exit_time_us = dc->bb_overrides.sr_exit_time_ns / 1000.0; + for (i = 0; i < WM_SET_COUNT; i++) { + dc->clk_mgr->bw_params->wm_table.entries[i].sr_exit_time_us = + dc->bb_overrides.sr_exit_time_ns / 1000.0; + } } if (dc->bb_overrides.sr_enter_plus_exit_time_ns) { - bb->sr_enter_plus_exit_time_us = - dc->bb_overrides.sr_enter_plus_exit_time_ns / 1000.0; + for (i = 0; i < WM_SET_COUNT; i++) { + dc->clk_mgr->bw_params->wm_table.entries[i].sr_enter_plus_exit_time_us = + dc->bb_overrides.sr_enter_plus_exit_time_ns / 1000.0; + } } if (dc->bb_overrides.urgent_latency_ns) { @@ -1032,9 +1043,12 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s } if (dc->bb_overrides.dram_clock_change_latency_ns) { - bb->dram_clock_change_latency_us = + for (i = 0; i < WM_SET_COUNT; i++) { + dc->clk_mgr->bw_params->wm_table.entries[i].pstate_latency_us = dc->bb_overrides.dram_clock_change_latency_ns / 1000.0; + } } + kernel_fpu_end(); } diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile index 970737217e53..641ffb7cfaed 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: MIT # # Makefile for the 'dsc' sub-component of DAL. diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index 4e18e77dcf42..026e6a2a2c44 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -69,6 +69,8 @@ struct wm_range_table_entry { unsigned int wm_inst; unsigned int wm_type; double pstate_latency_us; + double sr_exit_time_us; + double sr_enter_plus_exit_time_us; bool valid; }; diff --git a/drivers/gpu/drm/amd/display/include/i2caux_interface.h b/drivers/gpu/drm/amd/display/include/i2caux_interface.h index bb012cb1a9f5..c7fbb9c3ad6b 100644 --- a/drivers/gpu/drm/amd/display/include/i2caux_interface.h +++ b/drivers/gpu/drm/amd/display/include/i2caux_interface.h @@ -42,7 +42,7 @@ struct aux_payload { bool write; bool mot; uint32_t address; - uint8_t length; + uint32_t length; uint8_t *data; /* * used to return the reply type of the transaction diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 16e69bbc69aa..5437b50e9f90 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -37,8 +37,8 @@ #define STATIC_SCREEN_RAMP_DELTA_REFRESH_RATE_PER_FRAME ((1000 / 60) * 65) /* Number of elements in the render times cache array */ #define RENDER_TIMES_MAX_COUNT 10 -/* Threshold to exit/exit BTR (to avoid frequent enter-exits at the lower limit) */ -#define BTR_MAX_MARGIN 2500 +/* Threshold to exit BTR (to avoid frequent enter-exits at the lower limit) */ +#define BTR_EXIT_MARGIN 2000 /* Threshold to change BTR multiplier (to avoid frequent changes) */ #define BTR_DRIFT_MARGIN 2000 /*Threshold to exit fixed refresh rate*/ @@ -254,22 +254,24 @@ static void apply_below_the_range(struct core_freesync *core_freesync, unsigned int delta_from_mid_point_in_us_1 = 0xFFFFFFFF; unsigned int delta_from_mid_point_in_us_2 = 0xFFFFFFFF; unsigned int frames_to_insert = 0; + unsigned int min_frame_duration_in_ns = 0; + unsigned int max_render_time_in_us = in_out_vrr->max_duration_in_us; unsigned int delta_from_mid_point_delta_in_us; - unsigned int max_render_time_in_us = - in_out_vrr->max_duration_in_us - in_out_vrr->btr.margin_in_us; + + min_frame_duration_in_ns = ((unsigned int) (div64_u64( + (1000000000ULL * 1000000), + in_out_vrr->max_refresh_in_uhz))); /* Program BTR */ - if ((last_render_time_in_us + in_out_vrr->btr.margin_in_us / 2) < max_render_time_in_us) { + if (last_render_time_in_us + BTR_EXIT_MARGIN < max_render_time_in_us) { /* Exit Below the Range */ if (in_out_vrr->btr.btr_active) { in_out_vrr->btr.frame_counter = 0; in_out_vrr->btr.btr_active = false; } - } else if (last_render_time_in_us > (max_render_time_in_us + in_out_vrr->btr.margin_in_us / 2)) { + } else if (last_render_time_in_us > max_render_time_in_us) { /* Enter Below the Range */ - if (!in_out_vrr->btr.btr_active) { - in_out_vrr->btr.btr_active = true; - } + in_out_vrr->btr.btr_active = true; } /* BTR set to "not active" so disengage */ @@ -325,9 +327,7 @@ static void apply_below_the_range(struct core_freesync *core_freesync, /* Choose number of frames to insert based on how close it * can get to the mid point of the variable range. */ - if ((frame_time_in_us / mid_point_frames_ceil) > in_out_vrr->min_duration_in_us && - (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2 || - mid_point_frames_floor < 2)) { + if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) { frames_to_insert = mid_point_frames_ceil; delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 - delta_from_mid_point_in_us_1; @@ -343,7 +343,7 @@ static void apply_below_the_range(struct core_freesync *core_freesync, if (in_out_vrr->btr.frames_to_insert != 0 && delta_from_mid_point_delta_in_us < BTR_DRIFT_MARGIN) { if (((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) < - max_render_time_in_us) && + in_out_vrr->max_duration_in_us) && ((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) > in_out_vrr->min_duration_in_us)) frames_to_insert = in_out_vrr->btr.frames_to_insert; @@ -796,11 +796,6 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, refresh_range = in_out_vrr->max_refresh_in_uhz - in_out_vrr->min_refresh_in_uhz; - in_out_vrr->btr.margin_in_us = in_out_vrr->max_duration_in_us - - 2 * in_out_vrr->min_duration_in_us; - if (in_out_vrr->btr.margin_in_us > BTR_MAX_MARGIN) - in_out_vrr->btr.margin_in_us = BTR_MAX_MARGIN; - in_out_vrr->supported = true; } @@ -816,7 +811,6 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, in_out_vrr->btr.inserted_duration_in_us = 0; in_out_vrr->btr.frames_to_insert = 0; in_out_vrr->btr.frame_counter = 0; - in_out_vrr->btr.mid_point_in_us = (in_out_vrr->min_duration_in_us + in_out_vrr->max_duration_in_us) / 2; diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h index dbe7835aabcf..dc187844d10b 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h @@ -92,7 +92,6 @@ struct mod_vrr_params_btr { uint32_t inserted_duration_in_us; uint32_t frames_to_insert; uint32_t frame_counter; - uint32_t margin_in_us; }; struct mod_vrr_params_fixed_refresh { diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index ce3566ca3e24..cc71a1078a7a 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -1313,12 +1313,17 @@ static int arcturus_get_power_profile_mode(struct smu_context *smu, "VR", "COMPUTE", "CUSTOM"}; + static const char *title[] = { + "PROFILE_INDEX(NAME)"}; uint32_t i, size = 0; int16_t workload_type = 0; if (!smu->pm_enabled || !buf) return -EINVAL; + size += sprintf(buf + size, "%16s\n", + title[0]); + for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) { /* * Conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index c7c2b349858d..2a27fb5d7dc6 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3986,6 +3986,7 @@ static void intel_enable_ddi(struct intel_encoder *encoder, if (conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) intel_hdcp_enable(to_intel_connector(conn_state->connector), + crtc_state->cpu_transcoder, (u8)conn_state->hdcp_content_type); } @@ -4089,7 +4090,9 @@ static void intel_ddi_update_pipe(struct intel_encoder *encoder, if (conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED || content_protection_type_changed) - intel_hdcp_enable(connector, (u8)conn_state->hdcp_content_type); + intel_hdcp_enable(connector, + crtc_state->cpu_transcoder, + (u8)conn_state->hdcp_content_type); } static void diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 050655a1a3d8..b05b2191b919 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -2414,9 +2414,6 @@ intel_dp_compute_config(struct intel_encoder *encoder, intel_psr_compute_config(intel_dp, pipe_config); - intel_hdcp_transcoder_config(intel_connector, - pipe_config->cpu_transcoder); - return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 3111ecaeabd0..20616639b8ab 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -1284,7 +1284,7 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv) return 0; /* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */ - if (IS_GEMINILAKE(dev_priv)) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return 0; if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9) diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index f1f41ca8402b..a448815d8fc2 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -1821,23 +1821,6 @@ enum mei_fw_tc intel_get_mei_fw_tc(enum transcoder cpu_transcoder) } } -void intel_hdcp_transcoder_config(struct intel_connector *connector, - enum transcoder cpu_transcoder) -{ - struct drm_i915_private *dev_priv = to_i915(connector->base.dev); - struct intel_hdcp *hdcp = &connector->hdcp; - - if (!hdcp->shim) - return; - - if (INTEL_GEN(dev_priv) >= 12) { - mutex_lock(&hdcp->mutex); - hdcp->cpu_transcoder = cpu_transcoder; - hdcp->port_data.fw_tc = intel_get_mei_fw_tc(cpu_transcoder); - mutex_unlock(&hdcp->mutex); - } -} - static inline int initialize_hdcp_port_data(struct intel_connector *connector, const struct intel_hdcp_shim *shim) { @@ -1959,8 +1942,10 @@ int intel_hdcp_init(struct intel_connector *connector, return 0; } -int intel_hdcp_enable(struct intel_connector *connector, u8 content_type) +int intel_hdcp_enable(struct intel_connector *connector, + enum transcoder cpu_transcoder, u8 content_type) { + struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_hdcp *hdcp = &connector->hdcp; unsigned long check_link_interval = DRM_HDCP_CHECK_PERIOD_MS; int ret = -EINVAL; @@ -1972,6 +1957,11 @@ int intel_hdcp_enable(struct intel_connector *connector, u8 content_type) WARN_ON(hdcp->value == DRM_MODE_CONTENT_PROTECTION_ENABLED); hdcp->content_type = content_type; + if (INTEL_GEN(dev_priv) >= 12) { + hdcp->cpu_transcoder = cpu_transcoder; + hdcp->port_data.fw_tc = intel_get_mei_fw_tc(cpu_transcoder); + } + /* * Considering that HDCP2.2 is more secure than HDCP1.4, If the setup * is capable of HDCP2.2, it is preferred to use HDCP2.2. diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.h b/drivers/gpu/drm/i915/display/intel_hdcp.h index 41c1053d9e38..f3c3272e712a 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.h +++ b/drivers/gpu/drm/i915/display/intel_hdcp.h @@ -21,11 +21,10 @@ enum transcoder; void intel_hdcp_atomic_check(struct drm_connector *connector, struct drm_connector_state *old_state, struct drm_connector_state *new_state); -void intel_hdcp_transcoder_config(struct intel_connector *connector, - enum transcoder cpu_transcoder); int intel_hdcp_init(struct intel_connector *connector, const struct intel_hdcp_shim *hdcp_shim); -int intel_hdcp_enable(struct intel_connector *connector, u8 content_type); +int intel_hdcp_enable(struct intel_connector *connector, + enum transcoder cpu_transcoder, u8 content_type); int intel_hdcp_disable(struct intel_connector *connector); bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port); bool intel_hdcp_capable(struct intel_connector *connector); diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index f6f5312205c4..f56fffc474fa 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -2489,9 +2489,6 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, return -EINVAL; } - intel_hdcp_transcoder_config(intel_hdmi->attached_connector, - pipe_config->cpu_transcoder); - return 0; } diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 9fdefbdc3546..75dd0e0367b7 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -845,12 +845,6 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine) } } -static void unwind_wa_tail(struct i915_request *rq) -{ - rq->tail = intel_ring_wrap(rq->ring, rq->wa_tail - WA_TAIL_BYTES); - assert_ring_tail_valid(rq->ring, rq->tail); -} - static struct i915_request * __unwind_incomplete_requests(struct intel_engine_cs *engine) { @@ -863,12 +857,10 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine) list_for_each_entry_safe_reverse(rq, rn, &engine->active.requests, sched.link) { - if (i915_request_completed(rq)) continue; /* XXX */ __i915_request_unsubmit(rq); - unwind_wa_tail(rq); /* * Push the request back into the queue for later resubmission. @@ -1161,13 +1153,29 @@ execlists_schedule_out(struct i915_request *rq) i915_request_put(rq); } -static u64 execlists_update_context(const struct i915_request *rq) +static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->hw_context; - u64 desc; + u64 desc = ce->lrc_desc; + u32 tail; - ce->lrc_reg_state[CTX_RING_TAIL] = - intel_ring_set_tail(rq->ring, rq->tail); + /* + * WaIdleLiteRestore:bdw,skl + * + * We should never submit the context with the same RING_TAIL twice + * just in case we submit an empty ring, which confuses the HW. + * + * We append a couple of NOOPs (gen8_emit_wa_tail) after the end of + * the normal request to be able to always advance the RING_TAIL on + * subsequent resubmissions (for lite restore). Should that fail us, + * and we try and submit the same tail again, force the context + * reload. + */ + tail = intel_ring_set_tail(rq->ring, rq->tail); + if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail)) + desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc_reg_state[CTX_RING_TAIL] = tail; + rq->tail = rq->wa_tail; /* * Make sure the context image is complete before we submit it to HW. @@ -1186,13 +1194,11 @@ static u64 execlists_update_context(const struct i915_request *rq) */ mb(); - desc = ce->lrc_desc; - ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; - /* Wa_1607138340:tgl */ if (IS_TGL_REVID(rq->i915, TGL_REVID_A0, TGL_REVID_A0)) desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; return desc; } @@ -1703,16 +1709,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) return; } - - /* - * WaIdleLiteRestore:bdw,skl - * Apply the wa NOOPs to prevent - * ring:HEAD == rq:TAIL as we resubmit the - * request. See gen8_emit_fini_breadcrumb() for - * where we prepare the padding after the - * end of the request. - */ - last->tail = last->wa_tail; } } @@ -4120,17 +4116,18 @@ static void virtual_context_destroy(struct kref *kref) for (n = 0; n < ve->num_siblings; n++) { struct intel_engine_cs *sibling = ve->siblings[n]; struct rb_node *node = &ve->nodes[sibling->id].rb; + unsigned long flags; if (RB_EMPTY_NODE(node)) continue; - spin_lock_irq(&sibling->active.lock); + spin_lock_irqsave(&sibling->active.lock, flags); /* Detachment is lazily performed in the execlists tasklet */ if (!RB_EMPTY_NODE(node)) rb_erase_cached(node, &sibling->execlists.virtual); - spin_unlock_irq(&sibling->active.lock); + spin_unlock_irqrestore(&sibling->active.lock, flags); } GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet)); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index b9eb6b3149b7..d034fa413164 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -45,6 +45,7 @@ #include "gem/i915_gem_context.h" #include "gem/i915_gem_ioctls.h" #include "gem/i915_gem_pm.h" +#include "gt/intel_context.h" #include "gt/intel_engine_user.h" #include "gt/intel_gt.h" #include "gt/intel_gt_pm.h" @@ -1053,6 +1054,18 @@ out: return err; } +static int __intel_context_flush_retire(struct intel_context *ce) +{ + struct intel_timeline *tl; + + tl = intel_context_timeline_lock(ce); + if (IS_ERR(tl)) + return PTR_ERR(tl); + + intel_context_timeline_unlock(tl); + return 0; +} + static int __intel_engines_record_defaults(struct intel_gt *gt) { struct i915_request *requests[I915_NUM_ENGINES] = {}; @@ -1121,13 +1134,20 @@ err_rq: if (!rq) continue; - /* We want to be able to unbind the state from the GGTT */ - GEM_BUG_ON(intel_context_is_pinned(rq->hw_context)); - + GEM_BUG_ON(!test_bit(CONTEXT_ALLOC_BIT, + &rq->hw_context->flags)); state = rq->hw_context->state; if (!state) continue; + /* Serialise with retirement on another CPU */ + err = __intel_context_flush_retire(rq->hw_context); + if (err) + goto out; + + /* We want to be able to unbind the state from the GGTT */ + GEM_BUG_ON(intel_context_is_pinned(rq->hw_context)); + /* * As we will hold a reference to the logical state, it will * not be torn down with the context, and importantly the diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 65d7c2e599de..2ae14bc14931 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -2078,20 +2078,12 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce, u32 *reg_state = ce->lrc_reg_state; int i; - if (IS_GEN(stream->perf->i915, 12)) { - u32 format = stream->oa_buffer.format; + reg_state[ctx_oactxctrl + 1] = + (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) | + (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) | + GEN8_OA_COUNTER_RESUME; - reg_state[ctx_oactxctrl + 1] = - (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) | - (stream->oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0); - } else { - reg_state[ctx_oactxctrl + 1] = - (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) | - (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) | - GEN8_OA_COUNTER_RESUME; - } - - for (i = 0; !!ctx_flexeu0 && i < ARRAY_SIZE(flex_regs); i++) + for (i = 0; i < ARRAY_SIZE(flex_regs); i++) reg_state[ctx_flexeu0 + i * 2 + 1] = oa_config_flex_reg(stream->oa_config, flex_regs[i]); @@ -2224,34 +2216,51 @@ static int gen8_configure_context(struct i915_gem_context *ctx, return err; } -static int gen12_emit_oar_config(struct intel_context *ce, bool enable) +static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool enable) { - struct i915_request *rq; - u32 *cs; - int err = 0; - - rq = i915_request_create(ce); - if (IS_ERR(rq)) - return PTR_ERR(rq); - - cs = intel_ring_begin(rq, 4); - if (IS_ERR(cs)) { - err = PTR_ERR(cs); - goto out; - } - - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(RING_CONTEXT_CONTROL(ce->engine->mmio_base)); - *cs++ = _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE, - enable ? GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : 0); - *cs++ = MI_NOOP; + int err; + struct intel_context *ce = stream->pinned_ctx; + u32 format = stream->oa_buffer.format; + struct flex regs_context[] = { + { + GEN8_OACTXCONTROL, + stream->perf->ctx_oactxctrl_offset + 1, + enable ? GEN8_OA_COUNTER_RESUME : 0, + }, + }; + /* Offsets in regs_lri are not used since this configuration is only + * applied using LRI. Initialize the correct offsets for posterity. + */ +#define GEN12_OAR_OACONTROL_OFFSET 0x5B0 + struct flex regs_lri[] = { + { + GEN12_OAR_OACONTROL, + GEN12_OAR_OACONTROL_OFFSET + 1, + (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) | + (enable ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0) + }, + { + RING_CONTEXT_CONTROL(ce->engine->mmio_base), + CTX_CONTEXT_CONTROL, + _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE, + enable ? + GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : + 0) + }, + }; - intel_ring_advance(rq, cs); + /* Modify the context image of pinned context with regs_context*/ + err = intel_context_lock_pinned(ce); + if (err) + return err; -out: - i915_request_add(rq); + err = gen8_modify_context(ce, regs_context, ARRAY_SIZE(regs_context)); + intel_context_unlock_pinned(ce); + if (err) + return err; - return err; + /* Apply regs_lri using LRI with pinned context */ + return gen8_modify_self(ce, regs_lri, ARRAY_SIZE(regs_lri)); } /* @@ -2277,53 +2286,16 @@ out: * per-context OA state. * * Note: it's only the RCS/Render context that has any OA state. + * Note: the first flex register passed must always be R_PWR_CLK_STATE */ -static int lrc_configure_all_contexts(struct i915_perf_stream *stream, - const struct i915_oa_config *oa_config) +static int oa_configure_all_contexts(struct i915_perf_stream *stream, + struct flex *regs, + size_t num_regs) { struct drm_i915_private *i915 = stream->perf->i915; - /* The MMIO offsets for Flex EU registers aren't contiguous */ - const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; -#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1) - struct flex regs[] = { - { - GEN8_R_PWR_CLK_STATE, - CTX_R_PWR_CLK_STATE, - }, - { - IS_GEN(i915, 12) ? - GEN12_OAR_OACONTROL : GEN8_OACTXCONTROL, - stream->perf->ctx_oactxctrl_offset + 1, - }, - { EU_PERF_CNTL0, ctx_flexeuN(0) }, - { EU_PERF_CNTL1, ctx_flexeuN(1) }, - { EU_PERF_CNTL2, ctx_flexeuN(2) }, - { EU_PERF_CNTL3, ctx_flexeuN(3) }, - { EU_PERF_CNTL4, ctx_flexeuN(4) }, - { EU_PERF_CNTL5, ctx_flexeuN(5) }, - { EU_PERF_CNTL6, ctx_flexeuN(6) }, - }; -#undef ctx_flexeuN struct intel_engine_cs *engine; struct i915_gem_context *ctx, *cn; - size_t array_size = IS_GEN(i915, 12) ? 2 : ARRAY_SIZE(regs); - int i, err; - - if (IS_GEN(i915, 12)) { - u32 format = stream->oa_buffer.format; - - regs[1].value = - (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) | - (oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0); - } else { - regs[1].value = - (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) | - (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) | - GEN8_OA_COUNTER_RESUME; - } - - for (i = 2; !!ctx_flexeu0 && i < array_size; i++) - regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg); + int err; lockdep_assert_held(&stream->perf->lock); @@ -2353,7 +2325,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, spin_unlock(&i915->gem.contexts.lock); - err = gen8_configure_context(ctx, regs, array_size); + err = gen8_configure_context(ctx, regs, num_regs); if (err) { i915_gem_context_put(ctx); return err; @@ -2378,7 +2350,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, regs[0].value = intel_sseu_make_rpcs(i915, &ce->sseu); - err = gen8_modify_self(ce, regs, array_size); + err = gen8_modify_self(ce, regs, num_regs); if (err) return err; } @@ -2386,6 +2358,56 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, return 0; } +static int gen12_configure_all_contexts(struct i915_perf_stream *stream, + const struct i915_oa_config *oa_config) +{ + struct flex regs[] = { + { + GEN8_R_PWR_CLK_STATE, + CTX_R_PWR_CLK_STATE, + }, + }; + + return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs)); +} + +static int lrc_configure_all_contexts(struct i915_perf_stream *stream, + const struct i915_oa_config *oa_config) +{ + /* The MMIO offsets for Flex EU registers aren't contiguous */ + const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; +#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1) + struct flex regs[] = { + { + GEN8_R_PWR_CLK_STATE, + CTX_R_PWR_CLK_STATE, + }, + { + GEN8_OACTXCONTROL, + stream->perf->ctx_oactxctrl_offset + 1, + }, + { EU_PERF_CNTL0, ctx_flexeuN(0) }, + { EU_PERF_CNTL1, ctx_flexeuN(1) }, + { EU_PERF_CNTL2, ctx_flexeuN(2) }, + { EU_PERF_CNTL3, ctx_flexeuN(3) }, + { EU_PERF_CNTL4, ctx_flexeuN(4) }, + { EU_PERF_CNTL5, ctx_flexeuN(5) }, + { EU_PERF_CNTL6, ctx_flexeuN(6) }, + }; +#undef ctx_flexeuN + int i; + + regs[1].value = + (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) | + (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) | + GEN8_OA_COUNTER_RESUME; + + for (i = 2; i < ARRAY_SIZE(regs); i++) + regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg); + + return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs)); +} + static int gen8_enable_metric_set(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; @@ -2464,7 +2486,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream) * to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret = lrc_configure_all_contexts(stream, oa_config); + ret = gen12_configure_all_contexts(stream, oa_config); if (ret) return ret; @@ -2474,8 +2496,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream) * requested this. */ if (stream->ctx) { - ret = gen12_emit_oar_config(stream->pinned_ctx, - oa_config != NULL); + ret = gen12_configure_oar_context(stream, true); if (ret) return ret; } @@ -2509,11 +2530,11 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream) struct intel_uncore *uncore = stream->uncore; /* Reset all contexts' slices/subslices configurations. */ - lrc_configure_all_contexts(stream, NULL); + gen12_configure_all_contexts(stream, NULL); /* disable the context save/restore or OAR counters */ if (stream->ctx) - gen12_emit_oar_config(stream->pinned_ctx, false); + gen12_configure_oar_context(stream, false); /* Make sure we disable noa to save power. */ intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0); @@ -2713,7 +2734,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, return -EINVAL; } - if (!(props->sample_flags & SAMPLE_OA_REPORT)) { + if (!(props->sample_flags & SAMPLE_OA_REPORT) && + (INTEL_GEN(perf->i915) < 12 || !stream->ctx)) { DRM_DEBUG("Only OA report sampling supported\n"); return -EINVAL; } @@ -2745,7 +2767,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, format_size = perf->oa_formats[props->oa_format].size; - stream->sample_flags |= SAMPLE_OA_REPORT; + stream->sample_flags = props->sample_flags; stream->sample_size += format_size; stream->oa_buffer.format_size = format_size; @@ -2854,7 +2876,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce, return; stream = engine->i915->perf.exclusive_stream; - if (stream) + /* + * For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller + * is already doing that, so nothing to be done for gen12 here. + */ + if (stream && INTEL_GEN(stream->perf->i915) < 12) gen8_update_reg_state_unlocked(ce, stream); } diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c index d6214d3c8b33..ef4c630afe3f 100644 --- a/drivers/gpu/drm/mcde/mcde_dsi.c +++ b/drivers/gpu/drm/mcde/mcde_dsi.c @@ -935,11 +935,13 @@ static int mcde_dsi_bind(struct device *dev, struct device *master, for_each_available_child_of_node(dev->of_node, child) { panel = of_drm_find_panel(child); if (IS_ERR(panel)) { - dev_err(dev, "failed to find panel try bridge (%lu)\n", + dev_err(dev, "failed to find panel try bridge (%ld)\n", PTR_ERR(panel)); + panel = NULL; + bridge = of_drm_find_bridge(child); if (IS_ERR(bridge)) { - dev_err(dev, "failed to find bridge (%lu)\n", + dev_err(dev, "failed to find bridge (%ld)\n", PTR_ERR(bridge)); return PTR_ERR(bridge); } diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c index 9ab27aecfcf3..1bd6b6d15ffb 100644 --- a/drivers/gpu/drm/meson/meson_venc_cvbs.c +++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c @@ -64,6 +64,25 @@ struct meson_cvbs_mode meson_cvbs_modes[MESON_CVBS_MODES_COUNT] = { }, }; +static const struct meson_cvbs_mode * +meson_cvbs_get_mode(const struct drm_display_mode *req_mode) +{ + int i; + + for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) { + struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i]; + + if (drm_mode_match(req_mode, &meson_mode->mode, + DRM_MODE_MATCH_TIMINGS | + DRM_MODE_MATCH_CLOCK | + DRM_MODE_MATCH_FLAGS | + DRM_MODE_MATCH_3D_FLAGS)) + return meson_mode; + } + + return NULL; +} + /* Connector */ static void meson_cvbs_connector_destroy(struct drm_connector *connector) @@ -136,14 +155,8 @@ static int meson_venc_cvbs_encoder_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, struct drm_connector_state *conn_state) { - int i; - - for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) { - struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i]; - - if (drm_mode_equal(&crtc_state->mode, &meson_mode->mode)) - return 0; - } + if (meson_cvbs_get_mode(&crtc_state->mode)) + return 0; return -EINVAL; } @@ -191,24 +204,17 @@ static void meson_venc_cvbs_encoder_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) { + const struct meson_cvbs_mode *meson_mode = meson_cvbs_get_mode(mode); struct meson_venc_cvbs *meson_venc_cvbs = encoder_to_meson_venc_cvbs(encoder); struct meson_drm *priv = meson_venc_cvbs->priv; - int i; - for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) { - struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i]; + if (meson_mode) { + meson_venci_cvbs_mode_set(priv, meson_mode->enci); - if (drm_mode_equal(mode, &meson_mode->mode)) { - meson_venci_cvbs_mode_set(priv, - meson_mode->enci); - - /* Setup 27MHz vclk2 for ENCI and VDAC */ - meson_vclk_setup(priv, MESON_VCLK_TARGET_CVBS, - MESON_VCLK_CVBS, MESON_VCLK_CVBS, - MESON_VCLK_CVBS, true); - break; - } + /* Setup 27MHz vclk2 for ENCI and VDAC */ + meson_vclk_setup(priv, MESON_VCLK_TARGET_CVBS, MESON_VCLK_CVBS, + MESON_VCLK_CVBS, MESON_VCLK_CVBS, true); } } diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c index d43951caeea0..b113876c2428 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.c +++ b/drivers/gpu/drm/mgag200/mgag200_drv.c @@ -30,9 +30,8 @@ module_param_named(modeset, mgag200_modeset, int, 0400); static struct drm_driver driver; static const struct pci_device_id pciidlist[] = { - { PCI_VENDOR_ID_MATROX, 0x522, PCI_VENDOR_ID_SUN, 0x4852, 0, 0, + { PCI_VENDOR_ID_MATROX, 0x522, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_SE_A | MGAG200_FLAG_HW_BUG_NO_STARTADD}, - { PCI_VENDOR_ID_MATROX, 0x522, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_SE_A }, { PCI_VENDOR_ID_MATROX, 0x524, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_SE_B }, { PCI_VENDOR_ID_MATROX, 0x530, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_EV }, { PCI_VENDOR_ID_MATROX, 0x532, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_WB }, diff --git a/drivers/gpu/drm/nouveau/dispnv50/atom.h b/drivers/gpu/drm/nouveau/dispnv50/atom.h index 43df86c38f58..24f7700768da 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/atom.h +++ b/drivers/gpu/drm/nouveau/dispnv50/atom.h @@ -114,6 +114,7 @@ struct nv50_head_atom { u8 nhsync:1; u8 nvsync:1; u8 depth:4; + u8 bpc; } or; /* Currently only used for MST */ diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 549486f1d937..63425e246018 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -326,9 +326,9 @@ nv50_outp_atomic_check_view(struct drm_encoder *encoder, * same size as the native one (e.g. different * refresh rate) */ - if (adjusted_mode->hdisplay == native_mode->hdisplay && - adjusted_mode->vdisplay == native_mode->vdisplay && - adjusted_mode->type & DRM_MODE_TYPE_DRIVER) + if (mode->hdisplay == native_mode->hdisplay && + mode->vdisplay == native_mode->vdisplay && + mode->type & DRM_MODE_TYPE_DRIVER) break; mode = native_mode; asyc->scaler.full = true; @@ -353,10 +353,20 @@ nv50_outp_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, struct drm_connector_state *conn_state) { - struct nouveau_connector *nv_connector = - nouveau_connector(conn_state->connector); - return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state, - nv_connector->native_mode); + struct drm_connector *connector = conn_state->connector; + struct nouveau_connector *nv_connector = nouveau_connector(connector); + struct nv50_head_atom *asyh = nv50_head_atom(crtc_state); + int ret; + + ret = nv50_outp_atomic_check_view(encoder, crtc_state, conn_state, + nv_connector->native_mode); + if (ret) + return ret; + + if (crtc_state->mode_changed || crtc_state->connectors_changed) + asyh->or.bpc = connector->display_info.bpc; + + return 0; } /****************************************************************************** @@ -770,32 +780,54 @@ nv50_msto_atomic_check(struct drm_encoder *encoder, struct nv50_mstm *mstm = mstc->mstm; struct nv50_head_atom *asyh = nv50_head_atom(crtc_state); int slots; + int ret; + + ret = nv50_outp_atomic_check_view(encoder, crtc_state, conn_state, + mstc->native); + if (ret) + return ret; + + if (!crtc_state->mode_changed && !crtc_state->connectors_changed) + return 0; + + /* + * When restoring duplicated states, we need to make sure that the bw + * remains the same and avoid recalculating it, as the connector's bpc + * may have changed after the state was duplicated + */ + if (!state->duplicated) { + const int clock = crtc_state->adjusted_mode.clock; - if (crtc_state->mode_changed || crtc_state->connectors_changed) { /* - * When restoring duplicated states, we need to make sure that - * the bw remains the same and avoid recalculating it, as the - * connector's bpc may have changed after the state was - * duplicated + * XXX: Since we don't use HDR in userspace quite yet, limit + * the bpc to 8 to save bandwidth on the topology. In the + * future, we'll want to properly fix this by dynamically + * selecting the highest possible bpc that would fit in the + * topology */ - if (!state->duplicated) { - const int bpp = connector->display_info.bpc * 3; - const int clock = crtc_state->adjusted_mode.clock; + asyh->or.bpc = min(connector->display_info.bpc, 8U); + asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, asyh->or.bpc * 3); + } - asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, bpp); - } + slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, mstc->port, + asyh->dp.pbn); + if (slots < 0) + return slots; - slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, - mstc->port, - asyh->dp.pbn); - if (slots < 0) - return slots; + asyh->dp.tu = slots; - asyh->dp.tu = slots; - } + return 0; +} - return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state, - mstc->native); +static u8 +nv50_dp_bpc_to_depth(unsigned int bpc) +{ + switch (bpc) { + case 6: return 0x2; + case 8: return 0x5; + case 10: /* fall-through */ + default: return 0x6; + } } static void @@ -808,7 +840,7 @@ nv50_msto_enable(struct drm_encoder *encoder) struct nv50_mstm *mstm = NULL; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; - u8 proto, depth; + u8 proto; bool r; drm_connector_list_iter_begin(encoder->dev, &conn_iter); @@ -837,14 +869,8 @@ nv50_msto_enable(struct drm_encoder *encoder) else proto = 0x9; - switch (mstc->connector.display_info.bpc) { - case 6: depth = 0x2; break; - case 8: depth = 0x5; break; - case 10: - default: depth = 0x6; break; - } - - mstm->outp->update(mstm->outp, head->base.index, armh, proto, depth); + mstm->outp->update(mstm->outp, head->base.index, armh, proto, + nv50_dp_bpc_to_depth(armh->or.bpc)); msto->head = head; msto->mstc = mstc; @@ -1498,20 +1524,14 @@ nv50_sor_enable(struct drm_encoder *encoder) lvds.lvds.script |= 0x0200; } - if (nv_connector->base.display_info.bpc == 8) + if (asyh->or.bpc == 8) lvds.lvds.script |= 0x0200; } nvif_mthd(&disp->disp->object, 0, &lvds, sizeof(lvds)); break; case DCB_OUTPUT_DP: - if (nv_connector->base.display_info.bpc == 6) - depth = 0x2; - else - if (nv_connector->base.display_info.bpc == 8) - depth = 0x5; - else - depth = 0x6; + depth = nv50_dp_bpc_to_depth(asyh->or.bpc); if (nv_encoder->link & 1) proto = 0x8; @@ -1662,7 +1682,7 @@ nv50_pior_enable(struct drm_encoder *encoder) nv50_outp_acquire(nv_encoder); nv_connector = nouveau_encoder_connector_get(nv_encoder); - switch (nv_connector->base.display_info.bpc) { + switch (asyh->or.bpc) { case 10: asyh->or.depth = 0x6; break; case 8: asyh->or.depth = 0x5; break; case 6: asyh->or.depth = 0x2; break; diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c index 71c23bf1fe25..c9692df2b76c 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/head.c +++ b/drivers/gpu/drm/nouveau/dispnv50/head.c @@ -81,18 +81,17 @@ nv50_head_atomic_check_dither(struct nv50_head_atom *armh, struct nv50_head_atom *asyh, struct nouveau_conn_atom *asyc) { - struct drm_connector *connector = asyc->state.connector; u32 mode = 0x00; if (asyc->dither.mode == DITHERING_MODE_AUTO) { - if (asyh->base.depth > connector->display_info.bpc * 3) + if (asyh->base.depth > asyh->or.bpc * 3) mode = DITHERING_MODE_DYNAMIC2X2; } else { mode = asyc->dither.mode; } if (asyc->dither.depth == DITHERING_DEPTH_AUTO) { - if (connector->display_info.bpc >= 8) + if (asyh->or.bpc >= 8) mode |= DITHERING_DEPTH_8BPC; } else { mode |= asyc->dither.depth; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 5b413588b823..9a9a7f5003d3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -245,14 +245,22 @@ nouveau_conn_atomic_duplicate_state(struct drm_connector *connector) void nouveau_conn_reset(struct drm_connector *connector) { + struct nouveau_connector *nv_connector = nouveau_connector(connector); struct nouveau_conn_atom *asyc; - if (WARN_ON(!(asyc = kzalloc(sizeof(*asyc), GFP_KERNEL)))) - return; + if (drm_drv_uses_atomic_modeset(connector->dev)) { + if (WARN_ON(!(asyc = kzalloc(sizeof(*asyc), GFP_KERNEL)))) + return; + + if (connector->state) + nouveau_conn_atomic_destroy_state(connector, + connector->state); + + __drm_atomic_helper_connector_reset(connector, &asyc->state); + } else { + asyc = &nv_connector->properties_state; + } - if (connector->state) - nouveau_conn_atomic_destroy_state(connector, connector->state); - __drm_atomic_helper_connector_reset(connector, &asyc->state); asyc->dither.mode = DITHERING_MODE_AUTO; asyc->dither.depth = DITHERING_DEPTH_AUTO; asyc->scaler.mode = DRM_MODE_SCALE_NONE; @@ -276,8 +284,14 @@ void nouveau_conn_attach_properties(struct drm_connector *connector) { struct drm_device *dev = connector->dev; - struct nouveau_conn_atom *armc = nouveau_conn_atom(connector->state); struct nouveau_display *disp = nouveau_display(dev); + struct nouveau_connector *nv_connector = nouveau_connector(connector); + struct nouveau_conn_atom *armc; + + if (drm_drv_uses_atomic_modeset(connector->dev)) + armc = nouveau_conn_atom(connector->state); + else + armc = &nv_connector->properties_state; /* Init DVI-I specific properties. */ if (connector->connector_type == DRM_MODE_CONNECTOR_DVII) @@ -748,9 +762,9 @@ static int nouveau_connector_set_property(struct drm_connector *connector, struct drm_property *property, uint64_t value) { - struct nouveau_conn_atom *asyc = nouveau_conn_atom(connector->state); struct nouveau_connector *nv_connector = nouveau_connector(connector); struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder; + struct nouveau_conn_atom *asyc = &nv_connector->properties_state; struct drm_encoder *encoder = to_drm_encoder(nv_encoder); int ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h index f43a8d63aef8..de84fb4708c7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.h +++ b/drivers/gpu/drm/nouveau/nouveau_connector.h @@ -29,6 +29,7 @@ #include <nvif/notify.h> +#include <drm/drm_crtc.h> #include <drm/drm_edid.h> #include <drm/drm_encoder.h> #include <drm/drm_dp_helper.h> @@ -44,6 +45,60 @@ struct dcb_output; struct nouveau_backlight; #endif +#define nouveau_conn_atom(p) \ + container_of((p), struct nouveau_conn_atom, state) + +struct nouveau_conn_atom { + struct drm_connector_state state; + + struct { + /* The enum values specifically defined here match nv50/gf119 + * hw values, and the code relies on this. + */ + enum { + DITHERING_MODE_OFF = 0x00, + DITHERING_MODE_ON = 0x01, + DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON, + DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON, + DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON, + DITHERING_MODE_AUTO + } mode; + enum { + DITHERING_DEPTH_6BPC = 0x00, + DITHERING_DEPTH_8BPC = 0x02, + DITHERING_DEPTH_AUTO + } depth; + } dither; + + struct { + int mode; /* DRM_MODE_SCALE_* */ + struct { + enum { + UNDERSCAN_OFF, + UNDERSCAN_ON, + UNDERSCAN_AUTO, + } mode; + u32 hborder; + u32 vborder; + } underscan; + bool full; + } scaler; + + struct { + int color_vibrance; + int vibrant_hue; + } procamp; + + union { + struct { + bool dither:1; + bool scaler:1; + bool procamp:1; + }; + u8 mask; + } set; +}; + struct nouveau_connector { struct drm_connector base; enum dcb_connector_type type; @@ -63,6 +118,12 @@ struct nouveau_connector { #ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT struct nouveau_backlight *backlight; #endif + /* + * Our connector property code expects a nouveau_conn_atom struct + * even on pre-nv50 where we do not support atomic. This embedded + * version gets used in the non atomic modeset case. + */ + struct nouveau_conn_atom properties_state; }; static inline struct nouveau_connector *nouveau_connector( @@ -121,61 +182,6 @@ extern int nouveau_ignorelid; extern int nouveau_duallink; extern int nouveau_hdmimhz; -#include <drm/drm_crtc.h> -#define nouveau_conn_atom(p) \ - container_of((p), struct nouveau_conn_atom, state) - -struct nouveau_conn_atom { - struct drm_connector_state state; - - struct { - /* The enum values specifically defined here match nv50/gf119 - * hw values, and the code relies on this. - */ - enum { - DITHERING_MODE_OFF = 0x00, - DITHERING_MODE_ON = 0x01, - DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON, - DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON, - DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON, - DITHERING_MODE_AUTO - } mode; - enum { - DITHERING_DEPTH_6BPC = 0x00, - DITHERING_DEPTH_8BPC = 0x02, - DITHERING_DEPTH_AUTO - } depth; - } dither; - - struct { - int mode; /* DRM_MODE_SCALE_* */ - struct { - enum { - UNDERSCAN_OFF, - UNDERSCAN_ON, - UNDERSCAN_AUTO, - } mode; - u32 hborder; - u32 vborder; - } underscan; - bool full; - } scaler; - - struct { - int color_vibrance; - int vibrant_hue; - } procamp; - - union { - struct { - bool dither:1; - bool scaler:1; - bool procamp:1; - }; - u8 mask; - } set; -}; - void nouveau_conn_attach_properties(struct drm_connector *); void nouveau_conn_reset(struct drm_connector *); struct drm_connector_state * diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c index 4c4e8a30a1ac..536ba93b0f46 100644 --- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c +++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c @@ -18,15 +18,18 @@ static void panfrost_devfreq_update_utilization(struct panfrost_device *pfdev); static int panfrost_devfreq_target(struct device *dev, unsigned long *freq, u32 flags) { - struct panfrost_device *pfdev = dev_get_drvdata(dev); + struct dev_pm_opp *opp; int err; + opp = devfreq_recommended_opp(dev, freq, flags); + if (IS_ERR(opp)) + return PTR_ERR(opp); + dev_pm_opp_put(opp); + err = dev_pm_opp_set_rate(dev, *freq); if (err) return err; - *freq = clk_get_rate(pfdev->clock); - return 0; } @@ -60,20 +63,10 @@ static int panfrost_devfreq_get_dev_status(struct device *dev, return 0; } -static int panfrost_devfreq_get_cur_freq(struct device *dev, unsigned long *freq) -{ - struct panfrost_device *pfdev = platform_get_drvdata(to_platform_device(dev)); - - *freq = clk_get_rate(pfdev->clock); - - return 0; -} - static struct devfreq_dev_profile panfrost_devfreq_profile = { .polling_ms = 50, /* ~3 frames */ .target = panfrost_devfreq_target, .get_dev_status = panfrost_devfreq_get_dev_status, - .get_cur_freq = panfrost_devfreq_get_cur_freq, }; int panfrost_devfreq_init(struct panfrost_device *pfdev) diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 9458dc6c750c..f61364f7c471 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -303,14 +303,17 @@ static int panfrost_ioctl_mmap_bo(struct drm_device *dev, void *data, } /* Don't allow mmapping of heap objects as pages are not pinned. */ - if (to_panfrost_bo(gem_obj)->is_heap) - return -EINVAL; + if (to_panfrost_bo(gem_obj)->is_heap) { + ret = -EINVAL; + goto out; + } ret = drm_gem_create_mmap_offset(gem_obj); if (ret == 0) args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node); - drm_gem_object_put_unlocked(gem_obj); +out: + drm_gem_object_put_unlocked(gem_obj); return ret; } @@ -347,20 +350,19 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data, return -ENOENT; } + mutex_lock(&pfdev->shrinker_lock); args->retained = drm_gem_shmem_madvise(gem_obj, args->madv); if (args->retained) { struct panfrost_gem_object *bo = to_panfrost_bo(gem_obj); - mutex_lock(&pfdev->shrinker_lock); - if (args->madv == PANFROST_MADV_DONTNEED) - list_add_tail(&bo->base.madv_list, &pfdev->shrinker_list); + list_add_tail(&bo->base.madv_list, + &pfdev->shrinker_list); else if (args->madv == PANFROST_MADV_WILLNEED) list_del_init(&bo->base.madv_list); - - mutex_unlock(&pfdev->shrinker_lock); } + mutex_unlock(&pfdev->shrinker_lock); drm_gem_object_put_unlocked(gem_obj); return 0; @@ -443,7 +445,7 @@ panfrost_postclose(struct drm_device *dev, struct drm_file *file) { struct panfrost_file_priv *panfrost_priv = file->driver_priv; - panfrost_perfcnt_close(panfrost_priv); + panfrost_perfcnt_close(file); panfrost_job_close(panfrost_priv); panfrost_mmu_pgtable_free(panfrost_priv); diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index deca0c30bbd4..fd766b1395fb 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -19,6 +19,16 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj) struct panfrost_gem_object *bo = to_panfrost_bo(obj); struct panfrost_device *pfdev = obj->dev->dev_private; + /* + * Make sure the BO is no longer inserted in the shrinker list before + * taking care of the destruction itself. If we don't do that we have a + * race condition between this function and what's done in + * panfrost_gem_shrinker_scan(). + */ + mutex_lock(&pfdev->shrinker_lock); + list_del_init(&bo->base.madv_list); + mutex_unlock(&pfdev->shrinker_lock); + if (bo->sgts) { int i; int n_sgt = bo->base.base.size / SZ_2M; @@ -33,15 +43,10 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj) kfree(bo->sgts); } - mutex_lock(&pfdev->shrinker_lock); - if (!list_empty(&bo->base.madv_list)) - list_del(&bo->base.madv_list); - mutex_unlock(&pfdev->shrinker_lock); - drm_gem_shmem_free_object(obj); } -static int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) +int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) { int ret; size_t size = obj->size; @@ -80,7 +85,7 @@ static int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_p return ret; } -static void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv) +void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv) { struct panfrost_gem_object *bo = to_panfrost_bo(obj); struct panfrost_file_priv *priv = file_priv->driver_priv; diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h index 50920819cc16..4b17e7308764 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.h +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h @@ -45,6 +45,10 @@ panfrost_gem_create_with_handle(struct drm_file *file_priv, u32 flags, uint32_t *handle); +int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv); +void panfrost_gem_close(struct drm_gem_object *obj, + struct drm_file *file_priv); + void panfrost_gem_shrinker_init(struct drm_device *dev); void panfrost_gem_shrinker_cleanup(struct drm_device *dev); diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c index 2dba192bf198..2c04e858c50a 100644 --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c @@ -67,9 +67,10 @@ static int panfrost_perfcnt_dump_locked(struct panfrost_device *pfdev) } static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, - struct panfrost_file_priv *user, + struct drm_file *file_priv, unsigned int counterset) { + struct panfrost_file_priv *user = file_priv->driver_priv; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; struct drm_gem_shmem_object *bo; u32 cfg; @@ -91,14 +92,14 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, perfcnt->bo = to_panfrost_bo(&bo->base); /* Map the perfcnt buf in the address space attached to file_priv. */ - ret = panfrost_mmu_map(perfcnt->bo); + ret = panfrost_gem_open(&perfcnt->bo->base.base, file_priv); if (ret) goto err_put_bo; perfcnt->buf = drm_gem_shmem_vmap(&bo->base); if (IS_ERR(perfcnt->buf)) { ret = PTR_ERR(perfcnt->buf); - goto err_put_bo; + goto err_close_bo; } /* @@ -157,14 +158,17 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, err_vunmap: drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf); +err_close_bo: + panfrost_gem_close(&perfcnt->bo->base.base, file_priv); err_put_bo: drm_gem_object_put_unlocked(&bo->base); return ret; } static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, - struct panfrost_file_priv *user) + struct drm_file *file_priv) { + struct panfrost_file_priv *user = file_priv->driver_priv; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; if (user != perfcnt->user) @@ -180,6 +184,7 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, perfcnt->user = NULL; drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf); perfcnt->buf = NULL; + panfrost_gem_close(&perfcnt->bo->base.base, file_priv); drm_gem_object_put_unlocked(&perfcnt->bo->base.base); perfcnt->bo = NULL; pm_runtime_mark_last_busy(pfdev->dev); @@ -191,7 +196,6 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, int panfrost_ioctl_perfcnt_enable(struct drm_device *dev, void *data, struct drm_file *file_priv) { - struct panfrost_file_priv *pfile = file_priv->driver_priv; struct panfrost_device *pfdev = dev->dev_private; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; struct drm_panfrost_perfcnt_enable *req = data; @@ -207,10 +211,10 @@ int panfrost_ioctl_perfcnt_enable(struct drm_device *dev, void *data, mutex_lock(&perfcnt->lock); if (req->enable) - ret = panfrost_perfcnt_enable_locked(pfdev, pfile, + ret = panfrost_perfcnt_enable_locked(pfdev, file_priv, req->counterset); else - ret = panfrost_perfcnt_disable_locked(pfdev, pfile); + ret = panfrost_perfcnt_disable_locked(pfdev, file_priv); mutex_unlock(&perfcnt->lock); return ret; @@ -248,15 +252,16 @@ out: return ret; } -void panfrost_perfcnt_close(struct panfrost_file_priv *pfile) +void panfrost_perfcnt_close(struct drm_file *file_priv) { + struct panfrost_file_priv *pfile = file_priv->driver_priv; struct panfrost_device *pfdev = pfile->pfdev; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; pm_runtime_get_sync(pfdev->dev); mutex_lock(&perfcnt->lock); if (perfcnt->user == pfile) - panfrost_perfcnt_disable_locked(pfdev, pfile); + panfrost_perfcnt_disable_locked(pfdev, file_priv); mutex_unlock(&perfcnt->lock); pm_runtime_mark_last_busy(pfdev->dev); pm_runtime_put_autosuspend(pfdev->dev); diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.h b/drivers/gpu/drm/panfrost/panfrost_perfcnt.h index 13b8fdaa1b43..8bbcf5f5fb33 100644 --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.h +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.h @@ -9,7 +9,7 @@ void panfrost_perfcnt_sample_done(struct panfrost_device *pfdev); void panfrost_perfcnt_clean_cache_done(struct panfrost_device *pfdev); int panfrost_perfcnt_init(struct panfrost_device *pfdev); void panfrost_perfcnt_fini(struct panfrost_device *pfdev); -void panfrost_perfcnt_close(struct panfrost_file_priv *pfile); +void panfrost_perfcnt_close(struct drm_file *file_priv); int panfrost_ioctl_perfcnt_enable(struct drm_device *dev, void *data, struct drm_file *file_priv); int panfrost_ioctl_perfcnt_dump(struct drm_device *dev, void *data, diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 9333c865d4a9..9f8dcd3f8385 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -896,29 +896,6 @@ struct i2c_client *i2c_new_dummy_device(struct i2c_adapter *adapter, u16 address } EXPORT_SYMBOL_GPL(i2c_new_dummy_device); -/** - * i2c_new_dummy - return a new i2c device bound to a dummy driver - * @adapter: the adapter managing the device - * @address: seven bit address to be used - * Context: can sleep - * - * This deprecated function has the same functionality as @i2c_new_dummy_device, - * it just returns NULL instead of an ERR_PTR in case of an error for - * compatibility with current I2C API. It will be removed once all users are - * converted. - * - * This returns the new i2c client, which should be saved for later use with - * i2c_unregister_device(); or NULL to indicate an error. - */ -struct i2c_client *i2c_new_dummy(struct i2c_adapter *adapter, u16 address) -{ - struct i2c_client *ret; - - ret = i2c_new_dummy_device(adapter, address); - return IS_ERR(ret) ? NULL : ret; -} -EXPORT_SYMBOL_GPL(i2c_new_dummy); - struct i2c_dummy_devres { struct i2c_client *client; }; diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index c9d294caa27a..50c22575aed6 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -145,7 +145,7 @@ static inline bool is_rdma_read_cap(struct efa_dev *dev) } #define field_avail(x, fld, sz) (offsetof(typeof(x), fld) + \ - FIELD_SIZEOF(typeof(x), fld) <= (sz)) + sizeof_field(typeof(x), fld) <= (sz)) #define is_reserved_cleared(reserved) \ !memchr_inv(reserved, 0, sizeof(reserved)) diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 5774dfc22e18..a51525647ac8 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -848,7 +848,7 @@ static const struct rhashtable_params sdma_rht_params = { .nelem_hint = NR_CPUS_HINT, .head_offset = offsetof(struct sdma_rht_node, node), .key_offset = offsetof(struct sdma_rht_node, cpu_id), - .key_len = FIELD_SIZEOF(struct sdma_rht_node, cpu_id), + .key_len = sizeof_field(struct sdma_rht_node, cpu_id), .max_size = NR_CPUS, .min_size = 8, .automatic_shrinking = true, diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h index b0e9bf7cd150..d36e3e14896d 100644 --- a/drivers/infiniband/hw/hfi1/verbs.h +++ b/drivers/infiniband/hw/hfi1/verbs.h @@ -107,9 +107,9 @@ enum { HFI1_HAS_GRH = (1 << 0), }; -#define LRH_16B_BYTES (FIELD_SIZEOF(struct hfi1_16b_header, lrh)) +#define LRH_16B_BYTES (sizeof_field(struct hfi1_16b_header, lrh)) #define LRH_16B_DWORDS (LRH_16B_BYTES / sizeof(u32)) -#define LRH_9B_BYTES (FIELD_SIZEOF(struct ib_header, lrh)) +#define LRH_9B_BYTES (sizeof_field(struct ib_header, lrh)) #define LRH_9B_DWORDS (LRH_9B_BYTES / sizeof(u32)) /* 24Bits for qpn, upper 8Bits reserved */ diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c index 62390e9e0023..8ad7da989a0e 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c @@ -63,7 +63,7 @@ struct vnic_stats { }; }; -#define VNIC_STAT(m) { FIELD_SIZEOF(struct opa_vnic_stats, m), \ +#define VNIC_STAT(m) { sizeof_field(struct opa_vnic_stats, m), \ offsetof(struct opa_vnic_stats, m) } static struct vnic_stats vnic_gstrings_stats[] = { diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c index 08c552e5e41b..c05b12110456 100644 --- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -67,23 +67,34 @@ struct superblock_disk { * To save constantly doing look ups on disk we keep an in core copy of the * on-disk bitmap, the region_map. * - * To further reduce metadata I/O overhead we use a second bitmap, the dmap - * (dirty bitmap), which tracks the dirty words, i.e. longs, of the region_map. + * In order to track which regions are hydrated during a metadata transaction, + * we use a second set of bitmaps, the dmap (dirty bitmap), which includes two + * bitmaps, namely dirty_regions and dirty_words. The dirty_regions bitmap + * tracks the regions that got hydrated during the current metadata + * transaction. The dirty_words bitmap tracks the dirty words, i.e. longs, of + * the dirty_regions bitmap. + * + * This allows us to precisely track the regions that were hydrated during the + * current metadata transaction and update the metadata accordingly, when we + * commit the current transaction. This is important because dm-clone should + * only commit the metadata of regions that were properly flushed to the + * destination device beforehand. Otherwise, in case of a crash, we could end + * up with a corrupted dm-clone device. * * When a region finishes hydrating dm-clone calls * dm_clone_set_region_hydrated(), or for discard requests * dm_clone_cond_set_range(), which sets the corresponding bits in region_map * and dmap. * - * During a metadata commit we scan the dmap for dirty region_map words (longs) - * and update accordingly the on-disk metadata. Thus, we don't have to flush to - * disk the whole region_map. We can just flush the dirty region_map words. + * During a metadata commit we scan dmap->dirty_words and dmap->dirty_regions + * and update the on-disk metadata accordingly. Thus, we don't have to flush to + * disk the whole region_map. We can just flush the dirty region_map bits. * - * We use a dirty bitmap, which is smaller than the original region_map, to - * reduce the amount of memory accesses during a metadata commit. As dm-bitset - * accesses the on-disk bitmap in 64-bit word granularity, there is no - * significant benefit in tracking the dirty region_map bits with a smaller - * granularity. + * We use the helper dmap->dirty_words bitmap, which is smaller than the + * original region_map, to reduce the amount of memory accesses during a + * metadata commit. Moreover, as dm-bitset also accesses the on-disk bitmap in + * 64-bit word granularity, the dirty_words bitmap helps us avoid useless disk + * accesses. * * We could update directly the on-disk bitmap, when dm-clone calls either * dm_clone_set_region_hydrated() or dm_clone_cond_set_range(), buts this @@ -92,12 +103,13 @@ struct superblock_disk { * e.g., in a hooked overwrite bio's completion routine, and further reduce the * I/O completion latency. * - * We maintain two dirty bitmaps. During a metadata commit we atomically swap - * the currently used dmap with the unused one. This allows the metadata update - * functions to run concurrently with an ongoing commit. + * We maintain two dirty bitmap sets. During a metadata commit we atomically + * swap the currently used dmap with the unused one. This allows the metadata + * update functions to run concurrently with an ongoing commit. */ struct dirty_map { unsigned long *dirty_words; + unsigned long *dirty_regions; unsigned int changed; }; @@ -115,6 +127,9 @@ struct dm_clone_metadata { struct dirty_map dmap[2]; struct dirty_map *current_dmap; + /* Protected by lock */ + struct dirty_map *committing_dmap; + /* * In core copy of the on-disk bitmap to save constantly doing look ups * on disk. @@ -461,34 +476,53 @@ static size_t bitmap_size(unsigned long nr_bits) return BITS_TO_LONGS(nr_bits) * sizeof(long); } -static int dirty_map_init(struct dm_clone_metadata *cmd) +static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words, + unsigned long nr_regions) { - cmd->dmap[0].changed = 0; - cmd->dmap[0].dirty_words = kvzalloc(bitmap_size(cmd->nr_words), GFP_KERNEL); + dmap->changed = 0; - if (!cmd->dmap[0].dirty_words) { - DMERR("Failed to allocate dirty bitmap"); + dmap->dirty_words = kvzalloc(bitmap_size(nr_words), GFP_KERNEL); + if (!dmap->dirty_words) + return -ENOMEM; + + dmap->dirty_regions = kvzalloc(bitmap_size(nr_regions), GFP_KERNEL); + if (!dmap->dirty_regions) { + kvfree(dmap->dirty_words); return -ENOMEM; } - cmd->dmap[1].changed = 0; - cmd->dmap[1].dirty_words = kvzalloc(bitmap_size(cmd->nr_words), GFP_KERNEL); + return 0; +} + +static void __dirty_map_exit(struct dirty_map *dmap) +{ + kvfree(dmap->dirty_words); + kvfree(dmap->dirty_regions); +} + +static int dirty_map_init(struct dm_clone_metadata *cmd) +{ + if (__dirty_map_init(&cmd->dmap[0], cmd->nr_words, cmd->nr_regions)) { + DMERR("Failed to allocate dirty bitmap"); + return -ENOMEM; + } - if (!cmd->dmap[1].dirty_words) { + if (__dirty_map_init(&cmd->dmap[1], cmd->nr_words, cmd->nr_regions)) { DMERR("Failed to allocate dirty bitmap"); - kvfree(cmd->dmap[0].dirty_words); + __dirty_map_exit(&cmd->dmap[0]); return -ENOMEM; } cmd->current_dmap = &cmd->dmap[0]; + cmd->committing_dmap = NULL; return 0; } static void dirty_map_exit(struct dm_clone_metadata *cmd) { - kvfree(cmd->dmap[0].dirty_words); - kvfree(cmd->dmap[1].dirty_words); + __dirty_map_exit(&cmd->dmap[0]); + __dirty_map_exit(&cmd->dmap[1]); } static int __load_bitset_in_core(struct dm_clone_metadata *cmd) @@ -633,21 +667,23 @@ unsigned long dm_clone_find_next_unhydrated_region(struct dm_clone_metadata *cmd return find_next_zero_bit(cmd->region_map, cmd->nr_regions, start); } -static int __update_metadata_word(struct dm_clone_metadata *cmd, unsigned long word) +static int __update_metadata_word(struct dm_clone_metadata *cmd, + unsigned long *dirty_regions, + unsigned long word) { int r; unsigned long index = word * BITS_PER_LONG; unsigned long max_index = min(cmd->nr_regions, (word + 1) * BITS_PER_LONG); while (index < max_index) { - if (test_bit(index, cmd->region_map)) { + if (test_bit(index, dirty_regions)) { r = dm_bitset_set_bit(&cmd->bitset_info, cmd->bitset_root, index, &cmd->bitset_root); - if (r) { DMERR("dm_bitset_set_bit failed"); return r; } + __clear_bit(index, dirty_regions); } index++; } @@ -721,7 +757,7 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) if (word == cmd->nr_words) break; - r = __update_metadata_word(cmd, word); + r = __update_metadata_word(cmd, dmap->dirty_regions, word); if (r) return r; @@ -743,15 +779,17 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) return 0; } -int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) +int dm_clone_metadata_pre_commit(struct dm_clone_metadata *cmd) { - int r = -EPERM; + int r = 0; struct dirty_map *dmap, *next_dmap; down_write(&cmd->lock); - if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) + if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { + r = -EPERM; goto out; + } /* Get current dirty bitmap */ dmap = cmd->current_dmap; @@ -763,7 +801,7 @@ int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) * The last commit failed, so we don't have a clean dirty-bitmap to * use. */ - if (WARN_ON(next_dmap->changed)) { + if (WARN_ON(next_dmap->changed || cmd->committing_dmap)) { r = -EINVAL; goto out; } @@ -773,11 +811,33 @@ int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) cmd->current_dmap = next_dmap; spin_unlock_irq(&cmd->bitmap_lock); - /* - * No one is accessing the old dirty bitmap anymore, so we can flush - * it. - */ - r = __flush_dmap(cmd, dmap); + /* Set old dirty bitmap as currently committing */ + cmd->committing_dmap = dmap; +out: + up_write(&cmd->lock); + + return r; +} + +int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) +{ + int r = -EPERM; + + down_write(&cmd->lock); + + if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) + goto out; + + if (WARN_ON(!cmd->committing_dmap)) { + r = -EINVAL; + goto out; + } + + r = __flush_dmap(cmd, cmd->committing_dmap); + if (!r) { + /* Clear committing dmap */ + cmd->committing_dmap = NULL; + } out: up_write(&cmd->lock); @@ -802,6 +862,7 @@ int dm_clone_set_region_hydrated(struct dm_clone_metadata *cmd, unsigned long re dmap = cmd->current_dmap; __set_bit(word, dmap->dirty_words); + __set_bit(region_nr, dmap->dirty_regions); __set_bit(region_nr, cmd->region_map); dmap->changed = 1; @@ -830,6 +891,7 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start, if (!test_bit(region_nr, cmd->region_map)) { word = region_nr / BITS_PER_LONG; __set_bit(word, dmap->dirty_words); + __set_bit(region_nr, dmap->dirty_regions); __set_bit(region_nr, cmd->region_map); dmap->changed = 1; } diff --git a/drivers/md/dm-clone-metadata.h b/drivers/md/dm-clone-metadata.h index 3fe50a781c11..14af1ebd853f 100644 --- a/drivers/md/dm-clone-metadata.h +++ b/drivers/md/dm-clone-metadata.h @@ -75,7 +75,23 @@ void dm_clone_metadata_close(struct dm_clone_metadata *cmd); /* * Commit dm-clone metadata to disk. + * + * We use a two phase commit: + * + * 1. dm_clone_metadata_pre_commit(): Prepare the current transaction for + * committing. After this is called, all subsequent metadata updates, done + * through either dm_clone_set_region_hydrated() or + * dm_clone_cond_set_range(), will be part of the **next** transaction. + * + * 2. dm_clone_metadata_commit(): Actually commit the current transaction to + * disk and start a new transaction. + * + * This allows dm-clone to flush the destination device after step (1) to + * ensure that all freshly hydrated regions, for which we are updating the + * metadata, are properly written to non-volatile storage and won't be lost in + * case of a crash. */ +int dm_clone_metadata_pre_commit(struct dm_clone_metadata *cmd); int dm_clone_metadata_commit(struct dm_clone_metadata *cmd); /* @@ -112,6 +128,7 @@ int dm_clone_metadata_abort(struct dm_clone_metadata *cmd); * Switches metadata to a read only mode. Once read-only mode has been entered * the following functions will return -EPERM: * + * dm_clone_metadata_pre_commit() * dm_clone_metadata_commit() * dm_clone_set_region_hydrated() * dm_clone_cond_set_range() diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index b3d89072d21c..d1e1b5b56b1b 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -86,6 +86,12 @@ struct clone { struct dm_clone_metadata *cmd; + /* + * bio used to flush the destination device, before committing the + * metadata. + */ + struct bio flush_bio; + /* Region hydration hash table */ struct hash_table_bucket *ht; @@ -1108,10 +1114,13 @@ static bool need_commit_due_to_time(struct clone *clone) /* * A non-zero return indicates read-only or fail mode. */ -static int commit_metadata(struct clone *clone) +static int commit_metadata(struct clone *clone, bool *dest_dev_flushed) { int r = 0; + if (dest_dev_flushed) + *dest_dev_flushed = false; + mutex_lock(&clone->commit_lock); if (!dm_clone_changed_this_transaction(clone->cmd)) @@ -1122,8 +1131,26 @@ static int commit_metadata(struct clone *clone) goto out; } - r = dm_clone_metadata_commit(clone->cmd); + r = dm_clone_metadata_pre_commit(clone->cmd); + if (unlikely(r)) { + __metadata_operation_failed(clone, "dm_clone_metadata_pre_commit", r); + goto out; + } + bio_reset(&clone->flush_bio); + bio_set_dev(&clone->flush_bio, clone->dest_dev->bdev); + clone->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; + + r = submit_bio_wait(&clone->flush_bio); + if (unlikely(r)) { + __metadata_operation_failed(clone, "flush destination device", r); + goto out; + } + + if (dest_dev_flushed) + *dest_dev_flushed = true; + + r = dm_clone_metadata_commit(clone->cmd); if (unlikely(r)) { __metadata_operation_failed(clone, "dm_clone_metadata_commit", r); goto out; @@ -1194,6 +1221,7 @@ static void process_deferred_bios(struct clone *clone) static void process_deferred_flush_bios(struct clone *clone) { struct bio *bio; + bool dest_dev_flushed; struct bio_list bios = BIO_EMPTY_LIST; struct bio_list bio_completions = BIO_EMPTY_LIST; @@ -1213,7 +1241,7 @@ static void process_deferred_flush_bios(struct clone *clone) !(dm_clone_changed_this_transaction(clone->cmd) && need_commit_due_to_time(clone))) return; - if (commit_metadata(clone)) { + if (commit_metadata(clone, &dest_dev_flushed)) { bio_list_merge(&bios, &bio_completions); while ((bio = bio_list_pop(&bios))) @@ -1227,8 +1255,17 @@ static void process_deferred_flush_bios(struct clone *clone) while ((bio = bio_list_pop(&bio_completions))) bio_endio(bio); - while ((bio = bio_list_pop(&bios))) - generic_make_request(bio); + while ((bio = bio_list_pop(&bios))) { + if ((bio->bi_opf & REQ_PREFLUSH) && dest_dev_flushed) { + /* We just flushed the destination device as part of + * the metadata commit, so there is no reason to send + * another flush. + */ + bio_endio(bio); + } else { + generic_make_request(bio); + } + } } static void do_worker(struct work_struct *work) @@ -1400,7 +1437,7 @@ static void clone_status(struct dm_target *ti, status_type_t type, /* Commit to ensure statistics aren't out-of-date */ if (!(status_flags & DM_STATUS_NOFLUSH_FLAG) && !dm_suspended(ti)) - (void) commit_metadata(clone); + (void) commit_metadata(clone, NULL); r = dm_clone_get_free_metadata_block_count(clone->cmd, &nr_free_metadata_blocks); @@ -1834,6 +1871,7 @@ static int clone_ctr(struct dm_target *ti, unsigned int argc, char **argv) bio_list_init(&clone->deferred_flush_completions); clone->hydration_offset = 0; atomic_set(&clone->hydrations_in_flight, 0); + bio_init(&clone->flush_bio, NULL, 0); clone->wq = alloc_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM, 0); if (!clone->wq) { @@ -1907,6 +1945,7 @@ static void clone_dtr(struct dm_target *ti) struct clone *clone = ti->private; mutex_destroy(&clone->commit_lock); + bio_uninit(&clone->flush_bio); for (i = 0; i < clone->nr_ctr_args; i++) kfree(clone->ctr_args[i]); @@ -1961,7 +2000,7 @@ static void clone_postsuspend(struct dm_target *ti) wait_event(clone->hydration_stopped, !atomic_read(&clone->hydrations_in_flight)); flush_workqueue(clone->wq); - (void) commit_metadata(clone); + (void) commit_metadata(clone, NULL); } static void clone_resume(struct dm_target *ti) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index dbcc1e41cd57..e0c32793c248 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -599,45 +599,10 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio) return pgpath; } -static struct pgpath *__map_bio_fast(struct multipath *m, struct bio *bio) -{ - struct pgpath *pgpath; - unsigned long flags; - - /* Do we need to select a new pgpath? */ - /* - * FIXME: currently only switching path if no path (due to failure, etc) - * - which negates the point of using a path selector - */ - pgpath = READ_ONCE(m->current_pgpath); - if (!pgpath) - pgpath = choose_pgpath(m, bio->bi_iter.bi_size); - - if (!pgpath) { - if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { - /* Queue for the daemon to resubmit */ - spin_lock_irqsave(&m->lock, flags); - bio_list_add(&m->queued_bios, bio); - spin_unlock_irqrestore(&m->lock, flags); - queue_work(kmultipathd, &m->process_queued_bios); - - return ERR_PTR(-EAGAIN); - } - return NULL; - } - - return pgpath; -} - static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_mpath_io *mpio) { - struct pgpath *pgpath; - - if (!m->hw_handler_name) - pgpath = __map_bio_fast(m, bio); - else - pgpath = __map_bio(m, bio); + struct pgpath *pgpath = __map_bio(m, bio); if (IS_ERR(pgpath)) return DM_MAPIO_SUBMITTED; diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 4c68a7b93d5e..b88d6d701f5b 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -189,6 +189,15 @@ struct dm_pool_metadata { sector_t data_block_size; /* + * Pre-commit callback. + * + * This allows the thin provisioning target to run a callback before + * the metadata are committed. + */ + dm_pool_pre_commit_fn pre_commit_fn; + void *pre_commit_context; + + /* * We reserve a section of the metadata for commit overhead. * All reported space does *not* include this. */ @@ -826,6 +835,14 @@ static int __commit_transaction(struct dm_pool_metadata *pmd) if (unlikely(!pmd->in_service)) return 0; + if (pmd->pre_commit_fn) { + r = pmd->pre_commit_fn(pmd->pre_commit_context); + if (r < 0) { + DMERR("pre-commit callback failed"); + return r; + } + } + r = __write_changed_details(pmd); if (r < 0) return r; @@ -892,6 +909,8 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, pmd->in_service = false; pmd->bdev = bdev; pmd->data_block_size = data_block_size; + pmd->pre_commit_fn = NULL; + pmd->pre_commit_context = NULL; r = __create_persistent_data_objects(pmd, format_device); if (r) { @@ -2044,6 +2063,16 @@ int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd, return r; } +void dm_pool_register_pre_commit_callback(struct dm_pool_metadata *pmd, + dm_pool_pre_commit_fn fn, + void *context) +{ + pmd_write_lock_in_core(pmd); + pmd->pre_commit_fn = fn; + pmd->pre_commit_context = context; + pmd_write_unlock(pmd); +} + int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd) { int r = -EINVAL; diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h index f6be0d733c20..7ef56bd2a7e3 100644 --- a/drivers/md/dm-thin-metadata.h +++ b/drivers/md/dm-thin-metadata.h @@ -230,6 +230,13 @@ bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd); */ void dm_pool_issue_prefetches(struct dm_pool_metadata *pmd); +/* Pre-commit callback */ +typedef int (*dm_pool_pre_commit_fn)(void *context); + +void dm_pool_register_pre_commit_callback(struct dm_pool_metadata *pmd, + dm_pool_pre_commit_fn fn, + void *context); + /*----------------------------------------------------------------*/ #endif diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 5a2c494cb552..57626c27a54b 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -328,6 +328,7 @@ struct pool_c { dm_block_t low_water_blocks; struct pool_features requested_pf; /* Features requested during table load */ struct pool_features adjusted_pf; /* Features used after adjusting for constituent devices */ + struct bio flush_bio; }; /* @@ -2383,8 +2384,16 @@ static void process_deferred_bios(struct pool *pool) while ((bio = bio_list_pop(&bio_completions))) bio_endio(bio); - while ((bio = bio_list_pop(&bios))) - generic_make_request(bio); + while ((bio = bio_list_pop(&bios))) { + /* + * The data device was flushed as part of metadata commit, + * so complete redundant flushes immediately. + */ + if (bio->bi_opf & REQ_PREFLUSH) + bio_endio(bio); + else + generic_make_request(bio); + } } static void do_worker(struct work_struct *ws) @@ -3115,6 +3124,7 @@ static void pool_dtr(struct dm_target *ti) __pool_dec(pt->pool); dm_put_device(ti, pt->metadata_dev); dm_put_device(ti, pt->data_dev); + bio_uninit(&pt->flush_bio); kfree(pt); mutex_unlock(&dm_thin_pool_table.mutex); @@ -3180,6 +3190,29 @@ static void metadata_low_callback(void *context) dm_table_event(pool->ti->table); } +/* + * We need to flush the data device **before** committing the metadata. + * + * This ensures that the data blocks of any newly inserted mappings are + * properly written to non-volatile storage and won't be lost in case of a + * crash. + * + * Failure to do so can result in data corruption in the case of internal or + * external snapshots and in the case of newly provisioned blocks, when block + * zeroing is enabled. + */ +static int metadata_pre_commit_callback(void *context) +{ + struct pool_c *pt = context; + struct bio *flush_bio = &pt->flush_bio; + + bio_reset(flush_bio); + bio_set_dev(flush_bio, pt->data_dev->bdev); + flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; + + return submit_bio_wait(flush_bio); +} + static sector_t get_dev_size(struct block_device *bdev) { return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; @@ -3348,6 +3381,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) pt->data_dev = data_dev; pt->low_water_blocks = low_water_blocks; pt->adjusted_pf = pt->requested_pf = pf; + bio_init(&pt->flush_bio, NULL, 0); ti->num_flush_bios = 1; /* @@ -3374,6 +3408,10 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) if (r) goto out_flags_changed; + dm_pool_register_pre_commit_callback(pt->pool->pmd, + metadata_pre_commit_callback, + pt); + pt->callbacks.congested_fn = pool_is_congested; dm_table_add_target_callbacks(ti->table, &pt->callbacks); diff --git a/drivers/md/md.c b/drivers/md/md.c index 805b33e27496..4e7c9f398bc6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1159,6 +1159,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor /* not spare disk, or LEVEL_MULTIPATH */ if (sb->level == LEVEL_MULTIPATH || (rdev->desc_nr >= 0 && + rdev->desc_nr < MD_SB_DISKS && sb->disks[rdev->desc_nr].state & ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))) spare_disk = false; diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 21ea537bd55e..eff04fa23dfa 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -203,7 +203,13 @@ static void __rebalance2(struct dm_btree_info *info, struct btree_node *parent, struct btree_node *right = r->n; uint32_t nr_left = le32_to_cpu(left->header.nr_entries); uint32_t nr_right = le32_to_cpu(right->header.nr_entries); - unsigned threshold = 2 * merge_threshold(left) + 1; + /* + * Ensure the number of entries in each child will be greater + * than or equal to (max_entries / 3 + 1), so no matter which + * child is used for removal, the number will still be not + * less than (max_entries / 3). + */ + unsigned int threshold = 2 * (merge_threshold(left) + 1); if (nr_left + nr_right < threshold) { /* diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a409ab6f30bc..201fd8aec59a 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2782,7 +2782,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, write_targets++; } } - if (bio->bi_end_io) { + if (rdev && bio->bi_end_io) { atomic_inc(&rdev->nr_pending); bio->bi_iter.bi_sector = sector_nr + rdev->data_offset; bio_set_dev(bio, rdev->bdev); diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index cab5b1352892..d50238d0a85d 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1360,7 +1360,7 @@ int ppl_init_log(struct r5conf *conf) return -EINVAL; } - max_disks = FIELD_SIZEOF(struct ppl_log, disk_flush_bitmap) * + max_disks = sizeof_field(struct ppl_log, disk_flush_bitmap) * BITS_PER_BYTE; if (conf->raid_disks > max_disks) { pr_warn("md/raid:%s PPL doesn't support over %d disks in the array\n", diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index f0fc538bfe59..d4d3b67ffbba 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5726,7 +5726,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) do_flush = false; } - if (!sh->batch_head) + if (!sh->batch_head || sh == sh->batch_head) set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); if ((!sh->batch_head || sh == sh->batch_head) && diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c index 97d660606d98..4dbdf3180d10 100644 --- a/drivers/media/platform/omap3isp/isppreview.c +++ b/drivers/media/platform/omap3isp/isppreview.c @@ -753,7 +753,7 @@ static const struct preview_update update_attrs[] = { preview_config_luma_enhancement, preview_enable_luma_enhancement, offsetof(struct prev_params, luma), - FIELD_SIZEOF(struct prev_params, luma), + sizeof_field(struct prev_params, luma), offsetof(struct omap3isp_prev_update_config, luma), }, /* OMAP3ISP_PREV_INVALAW */ { NULL, @@ -762,55 +762,55 @@ static const struct preview_update update_attrs[] = { preview_config_hmed, preview_enable_hmed, offsetof(struct prev_params, hmed), - FIELD_SIZEOF(struct prev_params, hmed), + sizeof_field(struct prev_params, hmed), offsetof(struct omap3isp_prev_update_config, hmed), }, /* OMAP3ISP_PREV_CFA */ { preview_config_cfa, NULL, offsetof(struct prev_params, cfa), - FIELD_SIZEOF(struct prev_params, cfa), + sizeof_field(struct prev_params, cfa), offsetof(struct omap3isp_prev_update_config, cfa), }, /* OMAP3ISP_PREV_CHROMA_SUPP */ { preview_config_chroma_suppression, preview_enable_chroma_suppression, offsetof(struct prev_params, csup), - FIELD_SIZEOF(struct prev_params, csup), + sizeof_field(struct prev_params, csup), offsetof(struct omap3isp_prev_update_config, csup), }, /* OMAP3ISP_PREV_WB */ { preview_config_whitebalance, NULL, offsetof(struct prev_params, wbal), - FIELD_SIZEOF(struct prev_params, wbal), + sizeof_field(struct prev_params, wbal), offsetof(struct omap3isp_prev_update_config, wbal), }, /* OMAP3ISP_PREV_BLKADJ */ { preview_config_blkadj, NULL, offsetof(struct prev_params, blkadj), - FIELD_SIZEOF(struct prev_params, blkadj), + sizeof_field(struct prev_params, blkadj), offsetof(struct omap3isp_prev_update_config, blkadj), }, /* OMAP3ISP_PREV_RGB2RGB */ { preview_config_rgb_blending, NULL, offsetof(struct prev_params, rgb2rgb), - FIELD_SIZEOF(struct prev_params, rgb2rgb), + sizeof_field(struct prev_params, rgb2rgb), offsetof(struct omap3isp_prev_update_config, rgb2rgb), }, /* OMAP3ISP_PREV_COLOR_CONV */ { preview_config_csc, NULL, offsetof(struct prev_params, csc), - FIELD_SIZEOF(struct prev_params, csc), + sizeof_field(struct prev_params, csc), offsetof(struct omap3isp_prev_update_config, csc), }, /* OMAP3ISP_PREV_YC_LIMIT */ { preview_config_yc_range, NULL, offsetof(struct prev_params, yclimit), - FIELD_SIZEOF(struct prev_params, yclimit), + sizeof_field(struct prev_params, yclimit), offsetof(struct omap3isp_prev_update_config, yclimit), }, /* OMAP3ISP_PREV_DEFECT_COR */ { preview_config_dcor, preview_enable_dcor, offsetof(struct prev_params, dcor), - FIELD_SIZEOF(struct prev_params, dcor), + sizeof_field(struct prev_params, dcor), offsetof(struct omap3isp_prev_update_config, dcor), }, /* Previously OMAP3ISP_PREV_GAMMABYPASS, not used anymore */ { NULL, @@ -828,13 +828,13 @@ static const struct preview_update update_attrs[] = { preview_config_noisefilter, preview_enable_noisefilter, offsetof(struct prev_params, nf), - FIELD_SIZEOF(struct prev_params, nf), + sizeof_field(struct prev_params, nf), offsetof(struct omap3isp_prev_update_config, nf), }, /* OMAP3ISP_PREV_GAMMA */ { preview_config_gammacorrn, preview_enable_gammacorrn, offsetof(struct prev_params, gamma), - FIELD_SIZEOF(struct prev_params, gamma), + sizeof_field(struct prev_params, gamma), offsetof(struct omap3isp_prev_update_config, gamma), }, /* OMAP3ISP_PREV_CONTRAST */ { preview_config_contrast, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 4e700583659b..003b7422aeef 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2652,7 +2652,7 @@ struct v4l2_ioctl_info { /* Zero struct from after the field to the end */ #define INFO_FL_CLEAR(v4l2_struct, field) \ ((offsetof(struct v4l2_struct, field) + \ - FIELD_SIZEOF(struct v4l2_struct, field)) << 16) + sizeof_field(struct v4l2_struct, field)) << 16) #define INFO_FL_CLEAR_MASK (_IOC_SIZEMASK << 16) #define DEFINE_V4L_STUB_FUNC(_vidioc) \ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index a880f10e3e70..8083173f1a8f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -129,13 +129,13 @@ struct xgbe_stats { #define XGMAC_MMC_STAT(_string, _var) \ { _string, \ - FIELD_SIZEOF(struct xgbe_mmc_stats, _var), \ + sizeof_field(struct xgbe_mmc_stats, _var), \ offsetof(struct xgbe_prv_data, mmc_stats._var), \ } #define XGMAC_EXT_STAT(_string, _var) \ { _string, \ - FIELD_SIZEOF(struct xgbe_ext_stats, _var), \ + sizeof_field(struct xgbe_ext_stats, _var), \ offsetof(struct xgbe_prv_data, ext_stats._var), \ } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c index 0cc2338d8d2a..dfc77507b159 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c @@ -205,11 +205,11 @@ static int __cvmx_bootmem_check_version(struct octeon_device *oct, major_version = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, major_version), - FIELD_SIZEOF(struct cvmx_bootmem_desc, major_version)); + sizeof_field(struct cvmx_bootmem_desc, major_version)); minor_version = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, minor_version), - FIELD_SIZEOF(struct cvmx_bootmem_desc, minor_version)); + sizeof_field(struct cvmx_bootmem_desc, minor_version)); dev_dbg(&oct->pci_dev->dev, "%s: major_version=%d\n", __func__, major_version); @@ -237,13 +237,13 @@ static const struct cvmx_bootmem_named_block_desc oct, named_addr, offsetof(struct cvmx_bootmem_named_block_desc, base_addr), - FIELD_SIZEOF( + sizeof_field( struct cvmx_bootmem_named_block_desc, base_addr)); desc->size = __cvmx_bootmem_desc_get(oct, named_addr, offsetof(struct cvmx_bootmem_named_block_desc, size), - FIELD_SIZEOF( + sizeof_field( struct cvmx_bootmem_named_block_desc, size)); @@ -268,20 +268,20 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct, oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, named_block_array_addr), - FIELD_SIZEOF(struct cvmx_bootmem_desc, + sizeof_field(struct cvmx_bootmem_desc, named_block_array_addr)); u32 num_blocks = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, nb_num_blocks), - FIELD_SIZEOF(struct cvmx_bootmem_desc, + sizeof_field(struct cvmx_bootmem_desc, nb_num_blocks)); u32 name_length = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, named_block_name_len), - FIELD_SIZEOF(struct cvmx_bootmem_desc, + sizeof_field(struct cvmx_bootmem_desc, named_block_name_len)); u64 named_addr = named_block_array_addr; @@ -292,7 +292,7 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct, offsetof( struct cvmx_bootmem_named_block_desc, size), - FIELD_SIZEOF( + sizeof_field( struct cvmx_bootmem_named_block_desc, size)); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 5bb5abf99588..022a54a1805b 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -23,7 +23,7 @@ struct be_ethtool_stat { }; enum {DRVSTAT_TX, DRVSTAT_RX, DRVSTAT}; -#define FIELDINFO(_struct, field) FIELD_SIZEOF(_struct, field), \ +#define FIELDINFO(_struct, field) sizeof_field(_struct, field), \ offsetof(_struct, field) #define DRVSTAT_TX_INFO(field) #field, DRVSTAT_TX,\ FIELDINFO(struct be_tx_stats, field) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index d862e9ba27e1..13dbd249f35f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -10240,7 +10240,7 @@ static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len) return ret; } - data_len_per_desc = FIELD_SIZEOF(struct hclge_desc, data); + data_len_per_desc = sizeof_field(struct hclge_desc, data); *len = 0; for (i = 0; i < dfx_reg_type_num; i++) { bd_num = bd_num_list[i]; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index fbc39a2480d0..180224eab1ca 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -614,7 +614,7 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) } memcpy(kinfo->prio_tc, hdev->tm_info.prio_tc, - FIELD_SIZEOF(struct hnae3_knic_private_info, prio_tc)); + sizeof_field(struct hnae3_knic_private_info, prio_tc)); } static void hclge_tm_vport_info_update(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 60ec48fe4144..966aea949c0b 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -450,7 +450,7 @@ static u32 hinic_get_rxfh_indir_size(struct net_device *netdev) #define HINIC_FUNC_STAT(_stat_item) { \ .name = #_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_vport_stats, _stat_item), \ + .size = sizeof_field(struct hinic_vport_stats, _stat_item), \ .offset = offsetof(struct hinic_vport_stats, _stat_item) \ } @@ -477,7 +477,7 @@ static struct hinic_stats hinic_function_stats[] = { #define HINIC_PORT_STAT(_stat_item) { \ .name = #_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_phy_port_stats, _stat_item), \ + .size = sizeof_field(struct hinic_phy_port_stats, _stat_item), \ .offset = offsetof(struct hinic_phy_port_stats, _stat_item) \ } @@ -571,7 +571,7 @@ static struct hinic_stats hinic_port_stats[] = { #define HINIC_TXQ_STAT(_stat_item) { \ .name = "txq%d_"#_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_txq_stats, _stat_item), \ + .size = sizeof_field(struct hinic_txq_stats, _stat_item), \ .offset = offsetof(struct hinic_txq_stats, _stat_item) \ } @@ -586,7 +586,7 @@ static struct hinic_stats hinic_tx_queue_stats[] = { #define HINIC_RXQ_STAT(_stat_item) { \ .name = "rxq%d_"#_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_rxq_stats, _stat_item), \ + .size = sizeof_field(struct hinic_rxq_stats, _stat_item), \ .offset = offsetof(struct hinic_rxq_stats, _stat_item) \ } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index c681d2d28107..68edf55ac906 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -18,7 +18,7 @@ struct fm10k_stats { #define FM10K_STAT_FIELDS(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index d24d8731bef0..317f3f1458db 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -43,7 +43,7 @@ struct i40e_stats { */ #define I40E_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index be24d42280d8..a3da422ab05b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -659,7 +659,7 @@ i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw) #define I40E_HMC_STORE(_struct, _ele) \ offsetof(struct _struct, _ele), \ - FIELD_SIZEOF(struct _struct, _ele) + sizeof_field(struct _struct, _ele) struct i40e_context_ele { u16 offset; diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index dad3eec8ccd8..84c3d8d97ef6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -42,7 +42,7 @@ struct iavf_stats { */ #define IAVF_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index aec3c6c379df..9ebd93e79aeb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -15,7 +15,7 @@ struct ice_stats { #define ICE_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } @@ -36,10 +36,10 @@ static int ice_q_stats_len(struct net_device *netdev) #define ICE_VSI_STATS_LEN ARRAY_SIZE(ice_gstrings_vsi_stats) #define ICE_PFC_STATS_LEN ( \ - (FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_rx) + \ - FIELD_SIZEOF(struct ice_pf, stats.priority_xon_rx) + \ - FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_tx) + \ - FIELD_SIZEOF(struct ice_pf, stats.priority_xon_tx)) \ + (sizeof_field(struct ice_pf, stats.priority_xoff_rx) + \ + sizeof_field(struct ice_pf, stats.priority_xon_rx) + \ + sizeof_field(struct ice_pf, stats.priority_xoff_tx) + \ + sizeof_field(struct ice_pf, stats.priority_xon_tx)) \ / sizeof(u64)) #define ICE_ALL_STATS_LEN(n) (ICE_PF_STATS_LEN + ICE_PFC_STATS_LEN + \ ICE_VSI_STATS_LEN + ice_q_stats_len(n)) diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index ad34f22d44ef..0997d352709b 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -302,7 +302,7 @@ struct ice_ctx_ele { #define ICE_CTX_STORE(_struct, _ele, _width, _lsb) { \ .offset = offsetof(struct _struct, _ele), \ - .size_of = FIELD_SIZEOF(struct _struct, _ele), \ + .size_of = sizeof_field(struct _struct, _ele), \ .width = _width, \ .lsb = _lsb, \ } diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 3182b059bf55..4690d6c87f39 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -26,7 +26,7 @@ struct igb_stats { #define IGB_STAT(_name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(struct igb_adapter, _stat), \ + .sizeof_stat = sizeof_field(struct igb_adapter, _stat), \ .stat_offset = offsetof(struct igb_adapter, _stat) \ } static const struct igb_stats igb_gstrings_stats[] = { @@ -76,7 +76,7 @@ static const struct igb_stats igb_gstrings_stats[] = { #define IGB_NETDEV_STAT(_net_stat) { \ .stat_string = __stringify(_net_stat), \ - .sizeof_stat = FIELD_SIZEOF(struct rtnl_link_stats64, _net_stat), \ + .sizeof_stat = sizeof_field(struct rtnl_link_stats64, _net_stat), \ .stat_offset = offsetof(struct rtnl_link_stats64, _net_stat) \ } static const struct igb_stats igb_gstrings_net_stats[] = { diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index ac98f1d96892..455c1cdceb6e 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -16,7 +16,7 @@ struct igc_stats { #define IGC_STAT(_name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(struct igc_adapter, _stat), \ + .sizeof_stat = sizeof_field(struct igc_adapter, _stat), \ .stat_offset = offsetof(struct igc_adapter, _stat) \ } @@ -67,7 +67,7 @@ static const struct igc_stats igc_gstrings_stats[] = { #define IGC_NETDEV_STAT(_net_stat) { \ .stat_string = __stringify(_net_stat), \ - .sizeof_stat = FIELD_SIZEOF(struct rtnl_link_stats64, _net_stat), \ + .sizeof_stat = sizeof_field(struct rtnl_link_stats64, _net_stat), \ .stat_offset = offsetof(struct rtnl_link_stats64, _net_stat) \ } diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c index c8c93ac436d4..c65eb1afc8fb 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c @@ -19,10 +19,10 @@ struct ixgb_stats { }; #define IXGB_STAT(m) IXGB_STATS, \ - FIELD_SIZEOF(struct ixgb_adapter, m), \ + sizeof_field(struct ixgb_adapter, m), \ offsetof(struct ixgb_adapter, m) #define IXGB_NETDEV_STAT(m) NETDEV_STATS, \ - FIELD_SIZEOF(struct net_device, m), \ + sizeof_field(struct net_device, m), \ offsetof(struct net_device, m) static struct ixgb_stats ixgb_gstrings_stats[] = { diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 54459b69c948..f7f309c96fa8 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -31,14 +31,14 @@ struct ixgbe_stats { #define IXGBEVF_STAT(_name, _stat) { \ .stat_string = _name, \ .type = IXGBEVF_STATS, \ - .sizeof_stat = FIELD_SIZEOF(struct ixgbevf_adapter, _stat), \ + .sizeof_stat = sizeof_field(struct ixgbevf_adapter, _stat), \ .stat_offset = offsetof(struct ixgbevf_adapter, _stat) \ } #define IXGBEVF_NETDEV_STAT(_net_stat) { \ .stat_string = #_net_stat, \ .type = NETDEV_STATS, \ - .sizeof_stat = FIELD_SIZEOF(struct net_device_stats, _net_stat), \ + .sizeof_stat = sizeof_field(struct net_device_stats, _net_stat), \ .stat_offset = offsetof(struct net_device_stats, _net_stat) \ } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index d5b644131cff..65a093216dac 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1432,11 +1432,11 @@ struct mv643xx_eth_stats { }; #define SSTAT(m) \ - { #m, FIELD_SIZEOF(struct net_device_stats, m), \ + { #m, sizeof_field(struct net_device_stats, m), \ offsetof(struct net_device, stats.m), -1 } #define MIBSTAT(m) \ - { #m, FIELD_SIZEOF(struct mib_counters, m), \ + { #m, sizeof_field(struct mib_counters, m), \ -1, offsetof(struct mv643xx_eth_private, mib_counters.m) } static const struct mv643xx_eth_stats mv643xx_eth_stats[] = { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index a1202e53710c..8bf1f08fdee2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -611,7 +611,7 @@ static u32 ptys_get_active_port(struct mlx4_ptys_reg *ptys_reg) } #define MLX4_LINK_MODES_SZ \ - (FIELD_SIZEOF(struct mlx4_ptys_reg, eth_proto_cap) * 8) + (sizeof_field(struct mlx4_ptys_reg, eth_proto_cap) * 8) enum ethtool_report { SUPPORTED = 0, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index c76da309506b..e4ec0e03c289 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -87,10 +87,10 @@ static const struct rhashtable_params rhash_sa = { * value is not constant during the lifetime * of the key object. */ - .key_len = FIELD_SIZEOF(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) - - FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), + .key_len = sizeof_field(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) - + sizeof_field(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), .key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) + - FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), + sizeof_field(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), .head_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hash), .automatic_shrinking = true, .min_size = 1, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d60577484567..9a48c4310887 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -209,7 +209,7 @@ enum fs_i_lock_class { }; static const struct rhashtable_params rhash_fte = { - .key_len = FIELD_SIZEOF(struct fs_fte, val), + .key_len = sizeof_field(struct fs_fte, val), .key_offset = offsetof(struct fs_fte, val), .head_offset = offsetof(struct fs_fte, hash), .automatic_shrinking = true, @@ -217,7 +217,7 @@ static const struct rhashtable_params rhash_fte = { }; static const struct rhashtable_params rhash_fg = { - .key_len = FIELD_SIZEOF(struct mlx5_flow_group, mask), + .key_len = sizeof_field(struct mlx5_flow_group, mask), .key_offset = offsetof(struct mlx5_flow_group, mask), .head_offset = offsetof(struct mlx5_flow_group, hash), .automatic_shrinking = true, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index c80bb83c8ac9..0a721f6e8676 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -2652,17 +2652,17 @@ static int mem_ldx_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, switch (meta->insn.off) { case offsetof(struct __sk_buff, len): - if (size != FIELD_SIZEOF(struct __sk_buff, len)) + if (size != sizeof_field(struct __sk_buff, len)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, plen_reg(nfp_prog)); break; case offsetof(struct __sk_buff, data): - if (size != FIELD_SIZEOF(struct __sk_buff, data)) + if (size != sizeof_field(struct __sk_buff, data)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); break; case offsetof(struct __sk_buff, data_end): - if (size != FIELD_SIZEOF(struct __sk_buff, data_end)) + if (size != sizeof_field(struct __sk_buff, data_end)) return -EOPNOTSUPP; emit_alu(nfp_prog, dst, plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); @@ -2683,12 +2683,12 @@ static int mem_ldx_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, switch (meta->insn.off) { case offsetof(struct xdp_md, data): - if (size != FIELD_SIZEOF(struct xdp_md, data)) + if (size != sizeof_field(struct xdp_md, data)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); break; case offsetof(struct xdp_md, data_end): - if (size != FIELD_SIZEOF(struct xdp_md, data_end)) + if (size != sizeof_field(struct xdp_md, data_end)) return -EOPNOTSUPP; emit_alu(nfp_prog, dst, plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 8f732771d3fa..11c83a99b014 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -15,7 +15,7 @@ const struct rhashtable_params nfp_bpf_maps_neutral_params = { .nelem_hint = 4, - .key_len = FIELD_SIZEOF(struct bpf_map, id), + .key_len = sizeof_field(struct bpf_map, id), .key_offset = offsetof(struct nfp_bpf_neutral_map, map_id), .head_offset = offsetof(struct nfp_bpf_neutral_map, l), .automatic_shrinking = true, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 95a0d3910e31..ac02369174a9 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -374,7 +374,7 @@ nfp_bpf_map_alloc(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap) } use_map_size = DIV_ROUND_UP(offmap->map.value_size, 4) * - FIELD_SIZEOF(struct nfp_bpf_map, use_map[0]); + sizeof_field(struct nfp_bpf_map, use_map[0]); nfp_map = kzalloc(sizeof(*nfp_map) + use_map_size, GFP_USER); if (!nfp_map) diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 31d94592a7c0..e0c985fcaec1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -24,7 +24,7 @@ struct nfp_app; #define NFP_FL_STAT_ID_MU_NUM GENMASK(31, 22) #define NFP_FL_STAT_ID_STAT GENMASK(21, 0) -#define NFP_FL_STATS_ELEM_RS FIELD_SIZEOF(struct nfp_fl_stats_id, \ +#define NFP_FL_STATS_ELEM_RS sizeof_field(struct nfp_fl_stats_id, \ init_unalloc) #define NFP_FLOWER_MASK_ENTRY_RS 256 #define NFP_FLOWER_MASK_ELEMENT_RS 1 diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c index 1a3008e33182..b36aa5bf3c5f 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c @@ -20,7 +20,7 @@ struct pch_gbe_stats { #define PCH_GBE_STAT(m) \ { \ .string = #m, \ - .size = FIELD_SIZEOF(struct pch_gbe_hw_stats, m), \ + .size = sizeof_field(struct pch_gbe_hw_stats, m), \ .offset = offsetof(struct pch_gbe_hw_stats, m), \ } diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index c303a92d5b06..e8a1b27db84d 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -464,7 +464,7 @@ struct qede_fastpath { struct qede_tx_queue *txq; struct qede_tx_queue *xdp_tx; -#define VEC_NAME_SIZE (FIELD_SIZEOF(struct net_device, name) + 8) +#define VEC_NAME_SIZE (sizeof_field(struct net_device, name) + 8) char name[VEC_NAME_SIZE]; }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index a4cd6f2cfb86..75d83c3cbf27 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -20,7 +20,7 @@ struct qlcnic_stats { int stat_offset; }; -#define QLC_SIZEOF(m) FIELD_SIZEOF(struct qlcnic_adapter, m) +#define QLC_SIZEOF(m) sizeof_field(struct qlcnic_adapter, m) #define QLC_OFF(m) offsetof(struct qlcnic_adapter, m) static const u32 qlcnic_fw_dump_level[] = { 0x3, 0x7, 0xf, 0x1f, 0x3f, 0x7f, 0xff diff --git a/drivers/net/ethernet/realtek/r8169_firmware.c b/drivers/net/ethernet/realtek/r8169_firmware.c index 355cc810e322..cbc6b846ded5 100644 --- a/drivers/net/ethernet/realtek/r8169_firmware.c +++ b/drivers/net/ethernet/realtek/r8169_firmware.c @@ -37,7 +37,7 @@ struct fw_info { u8 chksum; } __packed; -#define FW_OPCODE_SIZE FIELD_SIZEOF(struct rtl_fw_phy_action, code[0]) +#define FW_OPCODE_SIZE sizeof_field(struct rtl_fw_phy_action, code[0]) static bool rtl_fw_format_ok(struct rtl_fw *rtl_fw) { diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c index 0775b9464b4e..466483c4ac67 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c @@ -30,7 +30,7 @@ struct sxgbe_stats { #define SXGBE_STAT(m) \ { \ #m, \ - FIELD_SIZEOF(struct sxgbe_extra_stats, m), \ + sizeof_field(struct sxgbe_extra_stats, m), \ offsetof(struct sxgbe_priv_data, xstats.m) \ } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 1a768837ca72..b29603ec744c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -34,7 +34,7 @@ struct stmmac_stats { }; #define STMMAC_STAT(m) \ - { #m, FIELD_SIZEOF(struct stmmac_extra_stats, m), \ + { #m, sizeof_field(struct stmmac_extra_stats, m), \ offsetof(struct stmmac_priv, xstats.m)} static const struct stmmac_stats stmmac_gstrings_stats[] = { @@ -163,7 +163,7 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = { /* HW MAC Management counters (if supported) */ #define STMMAC_MMC_STAT(m) \ - { #m, FIELD_SIZEOF(struct stmmac_counters, m), \ + { #m, sizeof_field(struct stmmac_counters, m), \ offsetof(struct stmmac_priv, mmc.m)} static const struct stmmac_stats stmmac_mmc[] = { diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c index 31248a6cc642..fa54efe3be63 100644 --- a/drivers/net/ethernet/ti/cpsw_ethtool.c +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c @@ -73,13 +73,13 @@ enum { }; #define CPSW_STAT(m) CPSW_STATS, \ - FIELD_SIZEOF(struct cpsw_hw_stats, m), \ + sizeof_field(struct cpsw_hw_stats, m), \ offsetof(struct cpsw_hw_stats, m) #define CPDMA_RX_STAT(m) CPDMA_RX_STATS, \ - FIELD_SIZEOF(struct cpdma_chan_stats, m), \ + sizeof_field(struct cpdma_chan_stats, m), \ offsetof(struct cpdma_chan_stats, m) #define CPDMA_TX_STAT(m) CPDMA_TX_STATS, \ - FIELD_SIZEOF(struct cpdma_chan_stats, m), \ + sizeof_field(struct cpdma_chan_stats, m), \ offsetof(struct cpdma_chan_stats, m) static const struct cpsw_stats cpsw_gstrings_stats[] = { diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 86a3f42a3dcc..d6a192c1f337 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -783,28 +783,28 @@ struct netcp_ethtool_stat { #define GBE_STATSA_INFO(field) \ { \ "GBE_A:"#field, GBE_STATSA_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } #define GBE_STATSB_INFO(field) \ { \ "GBE_B:"#field, GBE_STATSB_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } #define GBE_STATSC_INFO(field) \ { \ "GBE_C:"#field, GBE_STATSC_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } #define GBE_STATSD_INFO(field) \ { \ "GBE_D:"#field, GBE_STATSD_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } @@ -957,7 +957,7 @@ static const struct netcp_ethtool_stat gbe13_et_stats[] = { #define GBENU_STATS_HOST(field) \ { \ "GBE_HOST:"#field, GBENU_STATS0_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } @@ -967,56 +967,56 @@ static const struct netcp_ethtool_stat gbe13_et_stats[] = { #define GBENU_STATS_P1(field) \ { \ "GBE_P1:"#field, GBENU_STATS1_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P2(field) \ { \ "GBE_P2:"#field, GBENU_STATS2_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P3(field) \ { \ "GBE_P3:"#field, GBENU_STATS3_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P4(field) \ { \ "GBE_P4:"#field, GBENU_STATS4_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P5(field) \ { \ "GBE_P5:"#field, GBENU_STATS5_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P6(field) \ { \ "GBE_P6:"#field, GBENU_STATS6_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P7(field) \ { \ "GBE_P7:"#field, GBENU_STATS7_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P8(field) \ { \ "GBE_P8:"#field, GBENU_STATS8_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } @@ -1607,21 +1607,21 @@ static const struct netcp_ethtool_stat gbenu_et_stats[] = { #define XGBE_STATS0_INFO(field) \ { \ "GBE_0:"#field, XGBE_STATS0_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + sizeof_field(struct xgbe_hw_stats, field), \ offsetof(struct xgbe_hw_stats, field) \ } #define XGBE_STATS1_INFO(field) \ { \ "GBE_1:"#field, XGBE_STATS1_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + sizeof_field(struct xgbe_hw_stats, field), \ offsetof(struct xgbe_hw_stats, field) \ } #define XGBE_STATS2_INFO(field) \ { \ "GBE_2:"#field, XGBE_STATS2_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + sizeof_field(struct xgbe_hw_stats, field), \ offsetof(struct xgbe_hw_stats, field) \ } diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c index 09f3604cfbf8..746736c83873 100644 --- a/drivers/net/fjes/fjes_ethtool.c +++ b/drivers/net/fjes/fjes_ethtool.c @@ -21,7 +21,7 @@ struct fjes_stats { #define FJES_STAT(name, stat) { \ .stat_string = name, \ - .sizeof_stat = FIELD_SIZEOF(struct fjes_adapter, stat), \ + .sizeof_stat = sizeof_field(struct fjes_adapter, stat), \ .stat_offset = offsetof(struct fjes_adapter, stat) \ } diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 5c6b7fc04ea6..75757e9954ba 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1156,7 +1156,7 @@ static void geneve_setup(struct net_device *dev) static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_ID] = { .type = NLA_U32 }, - [IFLA_GENEVE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GENEVE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index eff8fef4f775..02e66473f2ed 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -571,7 +571,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) /* Use the skb control buffer for building up the packet */ BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); packet = (struct hv_netvsc_packet *)skb->cb; packet->q_idx = skb_get_queue_mapping(skb); diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index 34c1eaba536c..389d19dd7909 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -865,7 +865,7 @@ static struct sk_buff *sierra_net_tx_fixup(struct usbnet *dev, u16 len; bool need_tail; - BUILD_BUG_ON(FIELD_SIZEOF(struct usbnet, data) + BUILD_BUG_ON(sizeof_field(struct usbnet, data) < sizeof(struct cdc_state)); dev_dbg(&dev->udev->dev, "%s", __func__); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 30e511c2c8d0..9ce6d30576dd 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -2184,7 +2184,7 @@ static int __init usbnet_init(void) { /* Compiler should optimize this out. */ BUILD_BUG_ON( - FIELD_SIZEOF(struct sk_buff, cb) < sizeof(struct skb_data)); + sizeof_field(struct sk_buff, cb) < sizeof(struct skb_data)); eth_random_addr(node_id); return 0; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 4c34375c2e22..3ec6b506033d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3069,10 +3069,10 @@ static void vxlan_raw_setup(struct net_device *dev) static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_ID] = { .type = NLA_U32 }, - [IFLA_VXLAN_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, - [IFLA_VXLAN_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, + [IFLA_VXLAN_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, diff --git a/drivers/net/wireless/marvell/libertas/debugfs.c b/drivers/net/wireless/marvell/libertas/debugfs.c index fe14814af300..c604613ab506 100644 --- a/drivers/net/wireless/marvell/libertas/debugfs.c +++ b/drivers/net/wireless/marvell/libertas/debugfs.c @@ -774,7 +774,7 @@ void lbs_debugfs_remove_one(struct lbs_private *priv) #ifdef PROC_DEBUG -#define item_size(n) (FIELD_SIZEOF(struct lbs_private, n)) +#define item_size(n) (sizeof_field(struct lbs_private, n)) #define item_addr(n) (offsetof(struct lbs_private, n)) diff --git a/drivers/net/wireless/marvell/mwifiex/util.h b/drivers/net/wireless/marvell/mwifiex/util.h index c386992abcdb..7cafcecd7b85 100644 --- a/drivers/net/wireless/marvell/mwifiex/util.h +++ b/drivers/net/wireless/marvell/mwifiex/util.h @@ -36,11 +36,11 @@ struct mwifiex_cb { }; /* size/addr for mwifiex_debug_info */ -#define item_size(n) (FIELD_SIZEOF(struct mwifiex_debug_info, n)) +#define item_size(n) (sizeof_field(struct mwifiex_debug_info, n)) #define item_addr(n) (offsetof(struct mwifiex_debug_info, n)) /* size/addr for struct mwifiex_adapter */ -#define adapter_item_size(n) (FIELD_SIZEOF(struct mwifiex_adapter, n)) +#define adapter_item_size(n) (sizeof_field(struct mwifiex_adapter, n)) #define adapter_item_addr(n) (offsetof(struct mwifiex_adapter, n)) struct mwifiex_debug_data { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index dfe37a525f3a..667f18f465be 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1735,6 +1735,8 @@ static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid, if (ret) dev_warn(ctrl->device, "Identify Descriptors failed (%d)\n", ret); + if (ret > 0) + ret = 0; } return ret; } @@ -2852,6 +2854,10 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) * admin connect */ if (ctrl->cntlid != le16_to_cpu(id->cntlid)) { + dev_err(ctrl->device, + "Mismatching cntlid: Connect %u vs Identify " + "%u, rejecting\n", + ctrl->cntlid, le16_to_cpu(id->cntlid)); ret = -EINVAL; goto out_free; } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 679a721ae229..5a70ac395d53 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -95,7 +95,7 @@ struct nvme_fc_fcp_op { struct nvme_fcp_op_w_sgl { struct nvme_fc_fcp_op op; - struct scatterlist sgl[SG_CHUNK_SIZE]; + struct scatterlist sgl[NVME_INLINE_SG_CNT]; uint8_t priv[0]; }; @@ -342,7 +342,8 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, !template->ls_req || !template->fcp_io || !template->ls_abort || !template->fcp_abort || !template->max_hw_queues || !template->max_sgl_segments || - !template->max_dif_sgl_segments || !template->dma_boundary) { + !template->max_dif_sgl_segments || !template->dma_boundary || + !template->module) { ret = -EINVAL; goto out_reghost_failed; } @@ -2015,6 +2016,7 @@ nvme_fc_ctrl_free(struct kref *ref) { struct nvme_fc_ctrl *ctrl = container_of(ref, struct nvme_fc_ctrl, ref); + struct nvme_fc_lport *lport = ctrl->lport; unsigned long flags; if (ctrl->ctrl.tagset) { @@ -2041,6 +2043,7 @@ nvme_fc_ctrl_free(struct kref *ref) if (ctrl->ctrl.opts) nvmf_free_options(ctrl->ctrl.opts); kfree(ctrl); + module_put(lport->ops->module); } static void @@ -2141,7 +2144,7 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq, freq->sg_table.sgl = freq->first_sgl; ret = sg_alloc_table_chained(&freq->sg_table, blk_rq_nr_phys_segments(rq), freq->sg_table.sgl, - SG_CHUNK_SIZE); + NVME_INLINE_SG_CNT); if (ret) return -ENOMEM; @@ -2150,7 +2153,7 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq, freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents, rq_dma_dir(rq)); if (unlikely(freq->sg_cnt <= 0)) { - sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE); + sg_free_table_chained(&freq->sg_table, NVME_INLINE_SG_CNT); freq->sg_cnt = 0; return -EFAULT; } @@ -2173,7 +2176,7 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq, fc_dma_unmap_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents, rq_dma_dir(rq)); - sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE); + sg_free_table_chained(&freq->sg_table, NVME_INLINE_SG_CNT); freq->sg_cnt = 0; } @@ -2910,10 +2913,22 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) static void __nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl) { - nvme_stop_keep_alive(&ctrl->ctrl); + /* + * if state is connecting - the error occurred as part of a + * reconnect attempt. The create_association error paths will + * clean up any outstanding io. + * + * if it's a different state - ensure all pending io is + * terminated. Given this can delay while waiting for the + * aborted io to return, we recheck adapter state below + * before changing state. + */ + if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) { + nvme_stop_keep_alive(&ctrl->ctrl); - /* will block will waiting for io to terminate */ - nvme_fc_delete_association(ctrl); + /* will block will waiting for io to terminate */ + nvme_fc_delete_association(ctrl); + } if (ctrl->ctrl.state != NVME_CTRL_CONNECTING && !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) @@ -3059,10 +3074,15 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, goto out_fail; } + if (!try_module_get(lport->ops->module)) { + ret = -EUNATCH; + goto out_free_ctrl; + } + idx = ida_simple_get(&nvme_fc_ctrl_cnt, 0, 0, GFP_KERNEL); if (idx < 0) { ret = -ENOSPC; - goto out_free_ctrl; + goto out_mod_put; } ctrl->ctrl.opts = opts; @@ -3215,6 +3235,8 @@ out_free_queues: out_free_ida: put_device(ctrl->dev); ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum); +out_mod_put: + module_put(lport->ops->module); out_free_ctrl: kfree(ctrl); out_fail: diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 3b9cbe0668fa..1024fec7914c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -28,6 +28,12 @@ extern unsigned int admin_timeout; #define NVME_DEFAULT_KATO 5 #define NVME_KATO_GRACE 10 +#ifdef CONFIG_ARCH_NO_SG_CHAIN +#define NVME_INLINE_SG_CNT 0 +#else +#define NVME_INLINE_SG_CNT 2 +#endif + extern struct workqueue_struct *nvme_wq; extern struct workqueue_struct *nvme_reset_wq; extern struct workqueue_struct *nvme_delete_wq; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index dcaad5831cee..365a2ddbeaa7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -68,14 +68,14 @@ static int io_queue_depth = 1024; module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644); MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2"); -static int write_queues; -module_param(write_queues, int, 0644); +static unsigned int write_queues; +module_param(write_queues, uint, 0644); MODULE_PARM_DESC(write_queues, "Number of queues to use for writes. If not set, reads and writes " "will share a queue set."); -static int poll_queues; -module_param(poll_queues, int, 0644); +static unsigned int poll_queues; +module_param(poll_queues, uint, 0644); MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO."); struct nvme_dev; @@ -176,7 +176,6 @@ struct nvme_queue { u16 sq_tail; u16 last_sq_tail; u16 cq_head; - u16 last_cq_head; u16 qid; u8 cq_phase; u8 sqes; @@ -1026,10 +1025,7 @@ static irqreturn_t nvme_irq(int irq, void *data) * the irq handler, even if that was on another CPU. */ rmb(); - if (nvmeq->cq_head != nvmeq->last_cq_head) - ret = IRQ_HANDLED; nvme_process_cq(nvmeq, &start, &end, -1); - nvmeq->last_cq_head = nvmeq->cq_head; wmb(); if (start != end) { @@ -1549,7 +1545,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) result = adapter_alloc_sq(dev, qid, nvmeq); if (result < 0) return result; - else if (result) + if (result) goto release_cq; nvmeq->cq_vector = vector; @@ -2058,7 +2054,6 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) .priv = dev, }; unsigned int irq_queues, this_p_queues; - unsigned int nr_cpus = num_possible_cpus(); /* * Poll queues don't need interrupts, but we need at least one IO @@ -2069,10 +2064,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) this_p_queues = nr_io_queues - 1; irq_queues = 1; } else { - if (nr_cpus < nr_io_queues - this_p_queues) - irq_queues = nr_cpus + 1; - else - irq_queues = nr_io_queues - this_p_queues + 1; + irq_queues = nr_io_queues - this_p_queues + 1; } dev->io_queues[HCTX_TYPE_POLL] = this_p_queues; @@ -3142,6 +3134,9 @@ static int __init nvme_init(void) BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64); BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64); BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2); + + write_queues = min(write_queues, num_possible_cpus()); + poll_queues = min(poll_queues, num_possible_cpus()); return pci_register_driver(&nvme_driver); } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index dce59459ed41..2a47c6c5007e 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -731,7 +731,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, set->reserved_tags = 2; /* connect + keep-alive */ set->numa_node = nctrl->numa_node; set->cmd_size = sizeof(struct nvme_rdma_request) + - SG_CHUNK_SIZE * sizeof(struct scatterlist); + NVME_INLINE_SG_CNT * sizeof(struct scatterlist); set->driver_data = ctrl; set->nr_hw_queues = 1; set->timeout = ADMIN_TIMEOUT; @@ -745,7 +745,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, set->numa_node = nctrl->numa_node; set->flags = BLK_MQ_F_SHOULD_MERGE; set->cmd_size = sizeof(struct nvme_rdma_request) + - SG_CHUNK_SIZE * sizeof(struct scatterlist); + NVME_INLINE_SG_CNT * sizeof(struct scatterlist); set->driver_data = ctrl; set->nr_hw_queues = nctrl->queue_count - 1; set->timeout = NVME_IO_TIMEOUT; @@ -1160,7 +1160,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, } ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq)); - sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE); + sg_free_table_chained(&req->sg_table, NVME_INLINE_SG_CNT); } static int nvme_rdma_set_sg_null(struct nvme_command *c) @@ -1276,7 +1276,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue, req->sg_table.sgl = req->first_sgl; ret = sg_alloc_table_chained(&req->sg_table, blk_rq_nr_phys_segments(rq), req->sg_table.sgl, - SG_CHUNK_SIZE); + NVME_INLINE_SG_CNT); if (ret) return -ENOMEM; @@ -1314,7 +1314,7 @@ out: out_unmap_sg: ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq)); out_free_table: - sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE); + sg_free_table_chained(&req->sg_table, NVME_INLINE_SG_CNT); return ret; } diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index b50b53db3746..1c50af6219f3 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -850,6 +850,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) #define FCLOOP_DMABOUND_4G 0xFFFFFFFF static struct nvme_fc_port_template fctemplate = { + .module = THIS_MODULE, .localport_delete = fcloop_localport_delete, .remoteport_delete = fcloop_remoteport_delete, .create_queue = fcloop_create_queue, diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index a758bb3d5dd4..4df4ebde208a 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -76,7 +76,7 @@ static void nvme_loop_complete_rq(struct request *req) { struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req); - sg_free_table_chained(&iod->sg_table, SG_CHUNK_SIZE); + sg_free_table_chained(&iod->sg_table, NVME_INLINE_SG_CNT); nvme_complete_rq(req); } @@ -156,7 +156,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, iod->sg_table.sgl = iod->first_sgl; if (sg_alloc_table_chained(&iod->sg_table, blk_rq_nr_phys_segments(req), - iod->sg_table.sgl, SG_CHUNK_SIZE)) { + iod->sg_table.sgl, NVME_INLINE_SG_CNT)) { nvme_cleanup_cmd(req); return BLK_STS_RESOURCE; } @@ -342,7 +342,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */ ctrl->admin_tag_set.numa_node = NUMA_NO_NODE; ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) + - SG_CHUNK_SIZE * sizeof(struct scatterlist); + NVME_INLINE_SG_CNT * sizeof(struct scatterlist); ctrl->admin_tag_set.driver_data = ctrl; ctrl->admin_tag_set.nr_hw_queues = 1; ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT; @@ -516,7 +516,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) ctrl->tag_set.numa_node = NUMA_NO_NODE; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) + - SG_CHUNK_SIZE * sizeof(struct scatterlist); + NVME_INLINE_SG_CNT * sizeof(struct scatterlist); ctrl->tag_set.driver_data = ctrl; ctrl->tag_set.nr_hw_queues = ctrl->ctrl.queue_count - 1; ctrl->tag_set.timeout = NVME_IO_TIMEOUT; diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c index d9b63bfa5dd7..94af6f5828a3 100644 --- a/drivers/pci/controller/pcie-rockchip-host.c +++ b/drivers/pci/controller/pcie-rockchip-host.c @@ -834,10 +834,12 @@ static int rockchip_pcie_cfg_atu(struct rockchip_pcie *rockchip) if (!entry) return -ENODEV; + /* store the register number offset to program RC io outbound ATU */ + offset = size >> 20; + size = resource_size(entry->res); pci_addr = entry->res->start - entry->offset; - offset = size >> 20; for (reg_no = 0; reg_no < (size >> 20); reg_no++) { err = rockchip_pcie_prog_ob_atu(rockchip, reg_no + 1 + offset, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index b9a2349e4b90..33a62a6692c0 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4779,7 +4779,7 @@ static int qeth_qdio_establish(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "qdioest"); - qib_param_field = kzalloc(FIELD_SIZEOF(struct qib, parm), GFP_KERNEL); + qib_param_field = kzalloc(sizeof_field(struct qib, parm), GFP_KERNEL); if (!qib_param_field) { rc = -ENOMEM; goto out_free_nothing; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 88f4dc140751..c1ecce95094d 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -421,7 +421,7 @@ struct qeth_ipacmd_setassparms { } data; } __attribute__ ((packed)); -#define SETASS_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setassparms,\ +#define SETASS_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_setassparms,\ data.field) /* SETRTG IPA Command: ****************************************************/ @@ -535,7 +535,7 @@ struct qeth_ipacmd_setadpparms { } data; } __attribute__ ((packed)); -#define SETADP_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setadpparms,\ +#define SETADP_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_setadpparms,\ data.field) /* CREATE_ADDR IPA Command: ***********************************************/ @@ -648,7 +648,7 @@ struct qeth_ipacmd_vnicc { } data; }; -#define VNICC_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_vnicc,\ +#define VNICC_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_vnicc,\ data.field) /* SETBRIDGEPORT IPA Command: *********************************************/ @@ -729,7 +729,7 @@ struct qeth_ipacmd_setbridgeport { } data; } __packed; -#define SBP_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setbridgeport,\ +#define SBP_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_setbridgeport,\ data.field) /* ADDRESS_CHANGE_NOTIFICATION adapter-initiated "command" *******************/ @@ -790,7 +790,7 @@ struct qeth_ipa_cmd { } data; } __attribute__ ((packed)); -#define IPA_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipa_cmd, data.field) +#define IPA_DATA_SIZEOF(field) sizeof_field(struct qeth_ipa_cmd, data.field) /* * special command for ARP processing. diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index e36608ce937a..33dbc051bff9 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -535,7 +535,7 @@ static void get_container_name_callback(void *context, struct fib * fibptr) if ((le32_to_cpu(get_name_reply->status) == CT_OK) && (get_name_reply->data[0] != '\0')) { char *sp = get_name_reply->data; - int data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + int data_size = sizeof_field(struct aac_get_name_resp, data); sp[data_size - 1] = '\0'; while (*sp == ' ') @@ -574,7 +574,7 @@ static int aac_get_container_name(struct scsi_cmnd * scsicmd) dev = (struct aac_dev *)scsicmd->device->host->hostdata; - data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + data_size = sizeof_field(struct aac_get_name_resp, data); cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd); diff --git a/drivers/scsi/be2iscsi/be_cmds.h b/drivers/scsi/be2iscsi/be_cmds.h index 063dccc18f70..5f9f0b18ddf3 100644 --- a/drivers/scsi/be2iscsi/be_cmds.h +++ b/drivers/scsi/be2iscsi/be_cmds.h @@ -1300,7 +1300,7 @@ struct be_cmd_get_port_name { /* Returns the number of items in the field array. */ #define BE_NUMBER_OF_FIELD(_type_, _field_) \ - (FIELD_SIZEOF(_type_, _field_)/sizeof((((_type_ *)0)->_field_[0])))\ + (sizeof_field(_type_, _field_)/sizeof((((_type_ *)0)->_field_[0])))\ /** * Different types of iSCSI completions to host driver for both initiator diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 0d044c165960..c4e4b0136f86 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -2746,7 +2746,7 @@ static int __init libcxgbi_init_module(void) { pr_info("%s", version); - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) < + BUILD_BUG_ON(sizeof_field(struct sk_buff, cb) < sizeof(struct cxgbi_skb_cb)); return 0; } diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index db4a04a207ec..f6c8963c915d 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -1985,6 +1985,8 @@ out_unlock: /* Declare and initialization an instance of the FC NVME template. */ static struct nvme_fc_port_template lpfc_nvme_template = { + .module = THIS_MODULE, + /* initiator-based functions */ .localport_delete = lpfc_nvme_localport_delete, .remoteport_delete = lpfc_nvme_remoteport_delete, diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 941aa53363f5..bfcd02fdf2b8 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -610,6 +610,7 @@ static void qla_nvme_remoteport_delete(struct nvme_fc_remote_port *rport) } static struct nvme_fc_port_template qla_nvme_fc_transport = { + .module = THIS_MODULE, .localport_delete = qla_nvme_localport_delete, .remoteport_delete = qla_nvme_remoteport_delete, .create_queue = qla_nvme_alloc_queue, diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 7b7ef3acb504..412ac56ecd60 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -8689,11 +8689,11 @@ static void __attribute__((unused)) verify_structures(void) BUILD_BUG_ON(offsetof(struct pqi_general_admin_request, data.delete_operational_queue.queue_id) != 12); BUILD_BUG_ON(sizeof(struct pqi_general_admin_request) != 64); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_field(struct pqi_general_admin_request, data.create_operational_iq) != 64 - 11); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_field(struct pqi_general_admin_request, data.create_operational_oq) != 64 - 11); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_field(struct pqi_general_admin_request, data.delete_operational_queue) != 64 - 11); BUILD_BUG_ON(offsetof(struct pqi_general_admin_response, diff --git a/drivers/staging/qlge/qlge_ethtool.c b/drivers/staging/qlge/qlge_ethtool.c index a6886cc5654c..56d116d79e56 100644 --- a/drivers/staging/qlge/qlge_ethtool.c +++ b/drivers/staging/qlge/qlge_ethtool.c @@ -41,7 +41,7 @@ struct ql_stats { int stat_offset; }; -#define QL_SIZEOF(m) FIELD_SIZEOF(struct ql_adapter, m) +#define QL_SIZEOF(m) sizeof_field(struct ql_adapter, m) #define QL_OFF(m) offsetof(struct ql_adapter, m) static const struct ql_stats ql_gstrings_stats[] = { diff --git a/drivers/staging/wfx/data_tx.c b/drivers/staging/wfx/data_tx.c index b722e9773232..df2640a79f02 100644 --- a/drivers/staging/wfx/data_tx.c +++ b/drivers/staging/wfx/data_tx.c @@ -679,7 +679,7 @@ void wfx_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct ieee80211_sta *sta = control ? control->sta : NULL; struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - size_t driver_data_room = FIELD_SIZEOF(struct ieee80211_tx_info, + size_t driver_data_room = sizeof_field(struct ieee80211_tx_info, rate_driver_data); compiletime_assert(sizeof(struct wfx_tx_priv) <= driver_data_room, diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c index e877b917c15f..30ea37e1a3f5 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_main.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -708,7 +708,7 @@ static int __init cxgbit_init(void) pr_info("%s dcb enabled.\n", DRV_NAME); register_dcbevent_notifier(&cxgbit_dcbevent_nb); #endif - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) < + BUILD_BUG_ON(sizeof_field(struct sk_buff, cb) < sizeof(union cxgbit_skb_cb)); return 0; } diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index 59b79fc48266..79b27865c6f4 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -108,7 +108,7 @@ config THERMAL_DEFAULT_GOV_USER_SPACE config THERMAL_DEFAULT_GOV_POWER_ALLOCATOR bool "power_allocator" - select THERMAL_GOV_POWER_ALLOCATOR + depends on THERMAL_GOV_POWER_ALLOCATOR help Select this if you want to control temperature based on system and device power allocation. This governor can only diff --git a/drivers/usb/atm/usbatm.c b/drivers/usb/atm/usbatm.c index dbea28495e1d..4e12a32ca392 100644 --- a/drivers/usb/atm/usbatm.c +++ b/drivers/usb/atm/usbatm.c @@ -1275,7 +1275,7 @@ EXPORT_SYMBOL_GPL(usbatm_usb_disconnect); static int __init usbatm_usb_init(void) { - if (sizeof(struct usbatm_control) > FIELD_SIZEOF(struct sk_buff, cb)) { + if (sizeof(struct usbatm_control) > sizeof_field(struct sk_buff, cb)) { printk(KERN_ERR "%s unusable with this kernel!\n", usbatm_driver_name); return -EIO; } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ce1d0235969c..0bbccac94d6c 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3509,7 +3509,7 @@ static void ffs_free_inst(struct usb_function_instance *f) static int ffs_set_inst_name(struct usb_function_instance *fi, const char *name) { - if (strlen(name) >= FIELD_SIZEOF(struct ffs_dev, name)) + if (strlen(name) >= sizeof_field(struct ffs_dev, name)) return -ENAMETOOLONG; return ffs_name_dev(to_f_fs_opts(fi)->dev, name); } diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index e05679c478e2..93f995f6cf36 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -32,10 +32,11 @@ #define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \ __GFP_NOMEMALLOC) /* The order of free page blocks to report to host */ -#define VIRTIO_BALLOON_FREE_PAGE_ORDER (MAX_ORDER - 1) +#define VIRTIO_BALLOON_HINT_BLOCK_ORDER (MAX_ORDER - 1) /* The size of a free page block in bytes */ -#define VIRTIO_BALLOON_FREE_PAGE_SIZE \ - (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT)) +#define VIRTIO_BALLOON_HINT_BLOCK_BYTES \ + (1 << (VIRTIO_BALLOON_HINT_BLOCK_ORDER + PAGE_SHIFT)) +#define VIRTIO_BALLOON_HINT_BLOCK_PAGES (1 << VIRTIO_BALLOON_HINT_BLOCK_ORDER) #ifdef CONFIG_BALLOON_COMPACTION static struct vfsmount *balloon_mnt; @@ -380,7 +381,7 @@ static unsigned long return_free_pages_to_mm(struct virtio_balloon *vb, if (!page) break; free_pages((unsigned long)page_address(page), - VIRTIO_BALLOON_FREE_PAGE_ORDER); + VIRTIO_BALLOON_HINT_BLOCK_ORDER); } vb->num_free_page_blocks -= num_returned; spin_unlock_irq(&vb->free_page_list_lock); @@ -582,7 +583,7 @@ static int get_free_page_and_send(struct virtio_balloon *vb) ; page = alloc_pages(VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG, - VIRTIO_BALLOON_FREE_PAGE_ORDER); + VIRTIO_BALLOON_HINT_BLOCK_ORDER); /* * When the allocation returns NULL, it indicates that we have got all * the possible free pages, so return -EINTR to stop. @@ -591,13 +592,13 @@ static int get_free_page_and_send(struct virtio_balloon *vb) return -EINTR; p = page_address(page); - sg_init_one(&sg, p, VIRTIO_BALLOON_FREE_PAGE_SIZE); + sg_init_one(&sg, p, VIRTIO_BALLOON_HINT_BLOCK_BYTES); /* There is always 1 entry reserved for the cmd id to use. */ if (vq->num_free > 1) { err = virtqueue_add_inbuf(vq, &sg, 1, p, GFP_KERNEL); if (unlikely(err)) { free_pages((unsigned long)p, - VIRTIO_BALLOON_FREE_PAGE_ORDER); + VIRTIO_BALLOON_HINT_BLOCK_ORDER); return err; } virtqueue_kick(vq); @@ -610,7 +611,7 @@ static int get_free_page_and_send(struct virtio_balloon *vb) * The vq has no available entry to add this page block, so * just free it. */ - free_pages((unsigned long)p, VIRTIO_BALLOON_FREE_PAGE_ORDER); + free_pages((unsigned long)p, VIRTIO_BALLOON_HINT_BLOCK_ORDER); } return 0; @@ -721,6 +722,17 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, get_page(newpage); /* balloon reference */ + /* + * When we migrate a page to a different zone and adjusted the + * managed page count when inflating, we have to fixup the count of + * both involved zones. + */ + if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM) && + page_zone(page) != page_zone(newpage)) { + adjust_managed_page_count(page, 1); + adjust_managed_page_count(newpage, -1); + } + /* balloon's page migration 1st step -- inflate "newpage" */ spin_lock_irqsave(&vb_dev_info->pages_lock, flags); balloon_page_insert(vb_dev_info, newpage); @@ -765,11 +777,11 @@ static unsigned long shrink_free_pages(struct virtio_balloon *vb, unsigned long blocks_to_free, blocks_freed; pages_to_free = round_up(pages_to_free, - 1 << VIRTIO_BALLOON_FREE_PAGE_ORDER); - blocks_to_free = pages_to_free >> VIRTIO_BALLOON_FREE_PAGE_ORDER; + VIRTIO_BALLOON_HINT_BLOCK_PAGES); + blocks_to_free = pages_to_free / VIRTIO_BALLOON_HINT_BLOCK_PAGES; blocks_freed = return_free_pages_to_mm(vb, blocks_to_free); - return blocks_freed << VIRTIO_BALLOON_FREE_PAGE_ORDER; + return blocks_freed * VIRTIO_BALLOON_HINT_BLOCK_PAGES; } static unsigned long leak_balloon_pages(struct virtio_balloon *vb, @@ -826,7 +838,7 @@ static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker, unsigned long count; count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE; - count += vb->num_free_page_blocks << VIRTIO_BALLOON_FREE_PAGE_ORDER; + count += vb->num_free_page_blocks * VIRTIO_BALLOON_HINT_BLOCK_PAGES; return count; } |