From a2697972b9369c41afea8a928c30ac5b7f28d292 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 29 Oct 2021 16:40:27 -0500 Subject: [PATCH 001/358] ASoC: cs35l41: Change monitor widgets to siggens Currently the internal monitor sources are input widgets, which means if the card is set to fully routed these will not enable unless connected to something in the machine driver. However, all these are internal monitor signals so it makes no sense to connect them to something in the machine driver. As such switch them to siggen widgets which will have the same behaviour except not require external linkage on a fully routed card. Signed-off-by: Charles Keepax Signed-off-by: David Rhodes Link: https://lore.kernel.org/r/20211029214028.401284-1-drhodes@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/cs35l41.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index 94ed21d7676fb0..9d0530dde99672 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -612,6 +612,12 @@ static const struct snd_soc_dapm_widget cs35l41_dapm_widgets[] = { SND_SOC_DAPM_AIF_OUT("ASPTX3", NULL, 0, CS35L41_SP_ENABLES, 2, 0), SND_SOC_DAPM_AIF_OUT("ASPTX4", NULL, 0, CS35L41_SP_ENABLES, 3, 0), + SND_SOC_DAPM_SIGGEN("VSENSE"), + SND_SOC_DAPM_SIGGEN("ISENSE"), + SND_SOC_DAPM_SIGGEN("VP"), + SND_SOC_DAPM_SIGGEN("VBST"), + SND_SOC_DAPM_SIGGEN("TEMP"), + SND_SOC_DAPM_ADC("VMON ADC", NULL, CS35L41_PWR_CTRL2, 12, 0), SND_SOC_DAPM_ADC("IMON ADC", NULL, CS35L41_PWR_CTRL2, 13, 0), SND_SOC_DAPM_ADC("VPMON ADC", NULL, CS35L41_PWR_CTRL2, 8, 0), @@ -623,12 +629,6 @@ static const struct snd_soc_dapm_widget cs35l41_dapm_widgets[] = { cs35l41_main_amp_event, SND_SOC_DAPM_POST_PMD | SND_SOC_DAPM_POST_PMU), - SND_SOC_DAPM_INPUT("VP"), - SND_SOC_DAPM_INPUT("VBST"), - SND_SOC_DAPM_INPUT("ISENSE"), - SND_SOC_DAPM_INPUT("VSENSE"), - SND_SOC_DAPM_INPUT("TEMP"), - SND_SOC_DAPM_MUX("ASP TX1 Source", SND_SOC_NOPM, 0, 0, &asp_tx1_mux), SND_SOC_DAPM_MUX("ASP TX2 Source", SND_SOC_NOPM, 0, 0, &asp_tx2_mux), SND_SOC_DAPM_MUX("ASP TX3 Source", SND_SOC_NOPM, 0, 0, &asp_tx3_mux), @@ -674,8 +674,8 @@ static const struct snd_soc_dapm_route cs35l41_audio_map[] = { {"VMON ADC", NULL, "VSENSE"}, {"IMON ADC", NULL, "ISENSE"}, {"VPMON ADC", NULL, "VP"}, - {"TEMPMON ADC", NULL, "TEMP"}, {"VBSTMON ADC", NULL, "VBST"}, + {"TEMPMON ADC", NULL, "TEMP"}, {"ASPRX1", NULL, "AMP Playback"}, {"ASPRX2", NULL, "AMP Playback"}, From d9835eaa3e9fb4770745294fef3f8416446178c0 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 3 Nov 2021 10:27:10 +0200 Subject: [PATCH 002/358] ASoC: SOF:control: Fix variable type in snd_sof_refresh_control() The second parameter for snd_sof_ipc_set_get_comp_data() is ipc_cmd, not ipc_ctrl_type and the type is u32. Fixes: 756bbe4205bc6 ("ASoC: SOF: Handle control change notification from firmware") Signed-off-by: Peter Ujfalusi Acked-by: Ranjani Sridharan Link: https://lore.kernel.org/r/20211103082710.17165-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/control.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/soc/sof/control.c b/sound/soc/sof/control.c index 58bb89af4de1f7..bb1dfe4f6d4010 100644 --- a/sound/soc/sof/control.c +++ b/sound/soc/sof/control.c @@ -69,7 +69,7 @@ static void snd_sof_refresh_control(struct snd_sof_control *scontrol) { struct sof_ipc_ctrl_data *cdata = scontrol->control_data; struct snd_soc_component *scomp = scontrol->scomp; - enum sof_ipc_ctrl_type ctrl_type; + u32 ipc_cmd; int ret; if (!scontrol->comp_data_dirty) @@ -79,9 +79,9 @@ static void snd_sof_refresh_control(struct snd_sof_control *scontrol) return; if (scontrol->cmd == SOF_CTRL_CMD_BINARY) - ctrl_type = SOF_IPC_COMP_GET_DATA; + ipc_cmd = SOF_IPC_COMP_GET_DATA; else - ctrl_type = SOF_IPC_COMP_GET_VALUE; + ipc_cmd = SOF_IPC_COMP_GET_VALUE; /* set the ABI header values */ cdata->data->magic = SOF_ABI_MAGIC; @@ -89,7 +89,7 @@ static void snd_sof_refresh_control(struct snd_sof_control *scontrol) /* refresh the component data from DSP */ scontrol->comp_data_dirty = false; - ret = snd_sof_ipc_set_get_comp_data(scontrol, ctrl_type, + ret = snd_sof_ipc_set_get_comp_data(scontrol, ipc_cmd, SOF_CTRL_TYPE_VALUE_CHAN_GET, scontrol->cmd, false); if (ret < 0) { From fd572393baf0350835e8d822db588f679dc7bcb8 Mon Sep 17 00:00:00 2001 From: Kai Vehmanen Date: Fri, 5 Nov 2021 13:16:55 +0200 Subject: [PATCH 003/358] ASoC: SOF: Intel: hda: fix hotplug when only codec is suspended MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If codec is in runtime suspend, but controller is not, hotplug events are missed as the codec has no way to alert the controller. Problem does not occur if both controller and codec are active, or when both are suspended. An easy way to reproduce is to play an audio stream on one codec (e.g. to HDMI/DP display codec), wait for other HDA codec to go to runtime suspend, and then plug in a headset to the suspended codec. The jack event is not reported correctly in this case. Another way to reproduce is to force controller to stay active with "snd_sof_pci.sof_pci_debug=0x1" Fix the issue by reconfiguring the WAKEEN register when powering up/down individual links, and handling control events in the interrupt handler. Fixes: 87fc20e4a0cb ("ASoC: SOF: Intel: hda: use hdac_ext fine-grained link management") Reported-by: Hui Wang Signed-off-by: Kai Vehmanen Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20211105111655.668777-1-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/intel/hda-bus.c | 17 +++++++++++++++++ sound/soc/sof/intel/hda-dsp.c | 3 +-- sound/soc/sof/intel/hda.c | 16 ++++++++++++++++ 3 files changed, 34 insertions(+), 2 deletions(-) diff --git a/sound/soc/sof/intel/hda-bus.c b/sound/soc/sof/intel/hda-bus.c index 30025d3c16b6e9..0862ff8b662733 100644 --- a/sound/soc/sof/intel/hda-bus.c +++ b/sound/soc/sof/intel/hda-bus.c @@ -10,6 +10,8 @@ #include #include #include +#include +#include #include "../sof-priv.h" #include "hda.h" @@ -21,6 +23,18 @@ #endif #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) +static void update_codec_wake_enable(struct hdac_bus *bus, unsigned int addr, bool link_power) +{ + unsigned int mask = snd_hdac_chip_readw(bus, WAKEEN); + + if (link_power) + mask &= ~BIT(addr); + else + mask |= BIT(addr); + + snd_hdac_chip_updatew(bus, WAKEEN, STATESTS_INT_MASK, mask); +} + static void sof_hda_bus_link_power(struct hdac_device *codec, bool enable) { struct hdac_bus *bus = codec->bus; @@ -41,6 +55,9 @@ static void sof_hda_bus_link_power(struct hdac_device *codec, bool enable) */ if (codec->addr == HDA_IDISP_ADDR && !enable) snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, false); + + /* WAKEEN needs to be set for disabled links */ + update_codec_wake_enable(bus, codec->addr, enable); } static const struct hdac_bus_ops bus_core_ops = { diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c index 058baca2cd0e90..287dc0eb6686f5 100644 --- a/sound/soc/sof/intel/hda-dsp.c +++ b/sound/soc/sof/intel/hda-dsp.c @@ -622,8 +622,7 @@ static int hda_suspend(struct snd_sof_dev *sdev, bool runtime_suspend) hda_dsp_ipc_int_disable(sdev); #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) - if (runtime_suspend) - hda_codec_jack_wake_enable(sdev, true); + hda_codec_jack_wake_enable(sdev, runtime_suspend); /* power down all hda link */ snd_hdac_ext_bus_link_power_down_all(bus); diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 883d78dd01b5a4..568d351b7a4e97 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -810,6 +810,20 @@ static int hda_init_caps(struct snd_sof_dev *sdev) return 0; } +static void hda_check_for_state_change(struct snd_sof_dev *sdev) +{ +#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) + struct hdac_bus *bus = sof_to_bus(sdev); + unsigned int codec_mask; + + codec_mask = snd_hdac_chip_readw(bus, STATESTS); + if (codec_mask) { + hda_codec_jack_check(sdev); + snd_hdac_chip_writew(bus, STATESTS, codec_mask); + } +#endif +} + static irqreturn_t hda_dsp_interrupt_handler(int irq, void *context) { struct snd_sof_dev *sdev = context; @@ -851,6 +865,8 @@ static irqreturn_t hda_dsp_interrupt_thread(int irq, void *context) if (hda_sdw_check_wakeen_irq(sdev)) hda_sdw_process_wakeen(sdev); + hda_check_for_state_change(sdev); + /* enable GIE interrupt */ snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, SOF_HDA_INTCTL, From 827b0913a9d9d07a0c3e559dbb20ca4d6d285a54 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 5 Nov 2021 10:09:25 +0100 Subject: [PATCH 004/358] ASoC: DAPM: Cover regression by kctl change notification fix The recent fix for DAPM to correct the kctl change notification by the commit 5af82c81b2c4 ("ASoC: DAPM: Fix missing kctl change notifications") caused other regressions since it changed the behavior of snd_soc_dapm_set_pin() that is called from several API functions. Formerly it returned always 0 for success, but now it returns 0 or 1. This patch addresses it, restoring the old behavior of snd_soc_dapm_set_pin() while keeping the fix in snd_soc_dapm_put_pin_switch(). Fixes: 5af82c81b2c4 ("ASoC: DAPM: Fix missing kctl change notifications") Reported-by: Yu-Hsuan Hsu Cc: Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20211105090925.20575-1-tiwai@suse.de Signed-off-by: Mark Brown --- sound/soc/soc-dapm.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 2892b0aba151c0..b06c5682445c03 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -2559,8 +2559,13 @@ static struct snd_soc_dapm_widget *dapm_find_widget( return NULL; } -static int snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm, - const char *pin, int status) +/* + * set the DAPM pin status: + * returns 1 when the value has been updated, 0 when unchanged, or a negative + * error code; called from kcontrol put callback + */ +static int __snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm, + const char *pin, int status) { struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true); int ret = 0; @@ -2586,6 +2591,18 @@ static int snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm, return ret; } +/* + * similar as __snd_soc_dapm_set_pin(), but returns 0 when successful; + * called from several API functions below + */ +static int snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm, + const char *pin, int status) +{ + int ret = __snd_soc_dapm_set_pin(dapm, pin, status); + + return ret < 0 ? ret : 0; +} + /** * snd_soc_dapm_sync_unlocked - scan and power dapm paths * @dapm: DAPM context @@ -3589,10 +3606,10 @@ int snd_soc_dapm_put_pin_switch(struct snd_kcontrol *kcontrol, const char *pin = (const char *)kcontrol->private_value; int ret; - if (ucontrol->value.integer.value[0]) - ret = snd_soc_dapm_enable_pin(&card->dapm, pin); - else - ret = snd_soc_dapm_disable_pin(&card->dapm, pin); + mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + ret = __snd_soc_dapm_set_pin(&card->dapm, pin, + !!ucontrol->value.integer.value[0]); + mutex_unlock(&card->dapm_mutex); snd_soc_dapm_sync(&card->dapm); return ret; From 0a8facac0d1e38dc8b86ade6d3f0d8b33dae7c58 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Fri, 5 Nov 2021 16:20:13 +0100 Subject: [PATCH 005/358] ASoC: mediatek: mt8173-rt5650: Rename Speaker control to Ext Spk Some RT5645 and RT5650 powered platforms are using "Ext Spk" instead of "Speaker", and this is also reflected in alsa-lib configurations for the generic RT5645 usecase manager configs. Rename the "Speaker" control to "Ext Spk" in order to be able to make the userspace reuse/inherit the same configurations also for this machine, along with the others. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20211105152013.75252-1-angelogioacchino.delregno@collabora.com Signed-off-by: Mark Brown --- sound/soc/mediatek/mt8173/mt8173-rt5650.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650.c b/sound/soc/mediatek/mt8173/mt8173-rt5650.c index c28ebf891cb05f..2cbf679f5c74b3 100644 --- a/sound/soc/mediatek/mt8173/mt8173-rt5650.c +++ b/sound/soc/mediatek/mt8173/mt8173-rt5650.c @@ -30,15 +30,15 @@ static struct mt8173_rt5650_platform_data mt8173_rt5650_priv = { }; static const struct snd_soc_dapm_widget mt8173_rt5650_widgets[] = { - SND_SOC_DAPM_SPK("Speaker", NULL), + SND_SOC_DAPM_SPK("Ext Spk", NULL), SND_SOC_DAPM_MIC("Int Mic", NULL), SND_SOC_DAPM_HP("Headphone", NULL), SND_SOC_DAPM_MIC("Headset Mic", NULL), }; static const struct snd_soc_dapm_route mt8173_rt5650_routes[] = { - {"Speaker", NULL, "SPOL"}, - {"Speaker", NULL, "SPOR"}, + {"Ext Spk", NULL, "SPOL"}, + {"Ext Spk", NULL, "SPOR"}, {"DMIC L1", NULL, "Int Mic"}, {"DMIC R1", NULL, "Int Mic"}, {"Headphone", NULL, "HPOL"}, @@ -48,7 +48,7 @@ static const struct snd_soc_dapm_route mt8173_rt5650_routes[] = { }; static const struct snd_kcontrol_new mt8173_rt5650_controls[] = { - SOC_DAPM_PIN_SWITCH("Speaker"), + SOC_DAPM_PIN_SWITCH("Ext Spk"), SOC_DAPM_PIN_SWITCH("Int Mic"), SOC_DAPM_PIN_SWITCH("Headphone"), SOC_DAPM_PIN_SWITCH("Headset Mic"), From 8f4fa45982b3f2daf5b3626ca0f12bde735f31ff Mon Sep 17 00:00:00 2001 From: Gongjun Song Date: Fri, 5 Nov 2021 10:26:38 +0800 Subject: [PATCH 006/358] ASoC: Intel: sof_sdw: Add support for SKU 0AF3 product This product supports SoundWire capture from local microphones and two SoundWire amplifiers(no headset codec). Signed-off-by: Gongjun Song Reviewed-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211105022646.26305-2-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_sdw.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index f10496206ceed0..584f9f2db2076f 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -248,6 +248,16 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { SOF_BT_OFFLOAD_SSP(2) | SOF_SSP_BT_OFFLOAD_PRESENT), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0AF3"), + }, + /* No Jack */ + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + SOF_SDW_FOUR_SPK), + }, {} }; From a1797d61cb35848432867a5bc294ce43058b5ead Mon Sep 17 00:00:00 2001 From: Gongjun Song Date: Fri, 5 Nov 2021 10:26:39 +0800 Subject: [PATCH 007/358] ASoC: Intel: soc-acpi: add SKU 0AF3 SoundWire configuration New product audio hardware configuration is rt714 on link0, two rt1316s on link1 and link2 Signed-off-by: Gongjun Song Reviewed-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211105022646.26305-3-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- .../intel/common/soc-acpi-intel-adl-match.c | 26 +++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/sound/soc/intel/common/soc-acpi-intel-adl-match.c b/sound/soc/intel/common/soc-acpi-intel-adl-match.c index 06f503452aa50d..d8ae94d39d5760 100644 --- a/sound/soc/intel/common/soc-acpi-intel-adl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-adl-match.c @@ -209,6 +209,25 @@ static const struct snd_soc_acpi_link_adr adl_sdca_3_in_1[] = { {} }; +static const struct snd_soc_acpi_link_adr adl_sdw_rt1316_link12_rt714_link0[] = { + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(rt1316_1_group1_adr), + .adr_d = rt1316_1_group1_adr, + }, + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(rt1316_2_group1_adr), + .adr_d = rt1316_2_group1_adr, + }, + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(rt714_0_adr), + .adr_d = rt714_0_adr, + }, + {} +}; + static const struct snd_soc_acpi_link_adr adl_sdw_rt1316_link2_rt714_link0[] = { { .mask = BIT(2), @@ -339,6 +358,13 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_sdw_machines[] = { .drv_name = "sof_sdw", .sof_tplg_filename = "sof-adl-rt711-l0-rt1316-l13-rt714-l2.tplg", }, + { + .link_mask = 0x7, /* rt714 on link0 & two rt1316s on link1 and link2 */ + .links = adl_sdw_rt1316_link12_rt714_link0, + .drv_name = "sof_sdw", + .sof_fw_filename = "sof-adl.ri", + .sof_tplg_filename = "sof-adl-rt1316-l12-rt714-l0.tplg", + }, { .link_mask = 0x5, /* 2 active links required */ .links = adl_sdw_rt1316_link2_rt714_link0, From cf304329e4afb97ffabce232eadaba94f025641d Mon Sep 17 00:00:00 2001 From: Gongjun Song Date: Fri, 5 Nov 2021 10:26:40 +0800 Subject: [PATCH 008/358] ASoC: Intel: sof_sdw: Add support for SKU 0B00 and 0B01 products Both products support a SoundWire headset codec, SoundWire capture from local microphones and two SoundWire amplifiers. Signed-off-by: Gongjun Song Reviewed-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211105022646.26305-4-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_sdw.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 584f9f2db2076f..55c3e5935585ca 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -258,6 +258,26 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .driver_data = (void *)(SOF_SDW_TGL_HDMI | SOF_SDW_FOUR_SPK), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B00") + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + RT711_JD2 | + SOF_SDW_FOUR_SPK), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B01") + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + RT711_JD2 | + SOF_SDW_FOUR_SPK), + }, {} }; From 6fef4c2f458680399b7c512cb810c1e1784d7444 Mon Sep 17 00:00:00 2001 From: Gongjun Song Date: Fri, 5 Nov 2021 10:26:41 +0800 Subject: [PATCH 009/358] ASoC: Intel: sof_sdw: Add support for SKU 0B11 product This product supports a SoundWire headset codec, SoundWire capture from local microphones and two SoundWire amplifiers. Signed-off-by: Gongjun Song Reviewed-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211105022646.26305-5-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_sdw.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 55c3e5935585ca..d0bea028b9b765 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -278,6 +278,16 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { RT711_JD2 | SOF_SDW_FOUR_SPK), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B11") + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + RT711_JD2 | + SOF_SDW_FOUR_SPK), + }, {} }; From 6448d0596e48dbc16a910f04ffc248c3f3c0a65c Mon Sep 17 00:00:00 2001 From: Gongjun Song Date: Fri, 5 Nov 2021 10:26:42 +0800 Subject: [PATCH 010/358] ASoC: Intel: sof_sdw: Add support for SKU 0B13 product This product supports SoundWire capture from local microphones and one SoundWire amplifier(no headset codec). Signed-off-by: Gongjun Song Reviewed-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211105022646.26305-6-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_sdw.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index d0bea028b9b765..25cdd61f09a807 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -288,6 +288,15 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { RT711_JD2 | SOF_SDW_FOUR_SPK), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B13"), + }, + /* No Jack */ + .driver_data = (void *)SOF_SDW_TGL_HDMI, + }, {} }; From 11e18f582c14fdf08f52d99d439d2b82d98ac37d Mon Sep 17 00:00:00 2001 From: Gongjun Song Date: Fri, 5 Nov 2021 10:26:43 +0800 Subject: [PATCH 011/358] ASoC: Intel: soc-acpi: add SKU 0B13 SoundWire configuration Product audio hardware configuration is rt1316 on link2, rt714 on link 3. Signed-off-by: Gongjun Song Reviewed-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211105022646.26305-7-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- .../intel/common/soc-acpi-intel-adl-match.c | 21 +++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/sound/soc/intel/common/soc-acpi-intel-adl-match.c b/sound/soc/intel/common/soc-acpi-intel-adl-match.c index d8ae94d39d5760..3440c0fa31fa4f 100644 --- a/sound/soc/intel/common/soc-acpi-intel-adl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-adl-match.c @@ -228,6 +228,20 @@ static const struct snd_soc_acpi_link_adr adl_sdw_rt1316_link12_rt714_link0[] = {} }; +static const struct snd_soc_acpi_link_adr adl_sdw_rt1316_link2_rt714_link3[] = { + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(rt1316_2_single_adr), + .adr_d = rt1316_2_single_adr, + }, + { + .mask = BIT(3), + .num_adr = ARRAY_SIZE(rt714_3_adr), + .adr_d = rt714_3_adr, + }, + {} +}; + static const struct snd_soc_acpi_link_adr adl_sdw_rt1316_link2_rt714_link0[] = { { .mask = BIT(2), @@ -358,6 +372,13 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_sdw_machines[] = { .drv_name = "sof_sdw", .sof_tplg_filename = "sof-adl-rt711-l0-rt1316-l13-rt714-l2.tplg", }, + { + .link_mask = 0xC, /* rt1316 on link2 & rt714 on link3 */ + .links = adl_sdw_rt1316_link2_rt714_link3, + .drv_name = "sof_sdw", + .sof_fw_filename = "sof-adl.ri", + .sof_tplg_filename = "sof-adl-rt1316-l2-mono-rt714-l3.tplg", + }, { .link_mask = 0x7, /* rt714 on link0 & two rt1316s on link1 and link2 */ .links = adl_sdw_rt1316_link12_rt714_link0, From 0c2ed4f03f0bfe2be34efbabbebe9875c3aa9ca9 Mon Sep 17 00:00:00 2001 From: Gongjun Song Date: Fri, 5 Nov 2021 10:26:44 +0800 Subject: [PATCH 012/358] ASoC: Intel: sof_sdw: Add support for SKU 0B29 product This product supports a SoundWire headset codec, SoundWire capture from local microphones and two SoundWire amplifiers. Signed-off-by: Gongjun Song Reviewed-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211105022646.26305-8-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_sdw.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 25cdd61f09a807..bfbdda323b877d 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -297,6 +297,16 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { /* No Jack */ .driver_data = (void *)SOF_SDW_TGL_HDMI, }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B29"), + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + RT711_JD2 | + SOF_SDW_FOUR_SPK), + }, {} }; From 359ace2b9a411c3bd4b89fdc56f8b60e0f6696d2 Mon Sep 17 00:00:00 2001 From: Gongjun Song Date: Fri, 5 Nov 2021 10:26:45 +0800 Subject: [PATCH 013/358] ASoC: Intel: soc-acpi: add SKU 0B29 SoundWire configuration Product audio hardware configuration is rt711 on link2, two rt1316s on link0 and link1, rt714 on link 3. Signed-off-by: Gongjun Song Reviewed-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211105022646.26305-9-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- .../intel/common/soc-acpi-intel-adl-match.c | 58 +++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/sound/soc/intel/common/soc-acpi-intel-adl-match.c b/sound/soc/intel/common/soc-acpi-intel-adl-match.c index 3440c0fa31fa4f..b61a778a9d26b4 100644 --- a/sound/soc/intel/common/soc-acpi-intel-adl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-adl-match.c @@ -74,6 +74,15 @@ static const struct snd_soc_acpi_adr_device rt711_sdca_0_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt711_sdca_2_adr[] = { + { + .adr = 0x000230025D071101ull, + .num_endpoints = 1, + .endpoints = &single_endpoint, + .name_prefix = "rt711" + } +}; + static const struct snd_soc_acpi_adr_device rt1316_1_group1_adr[] = { { .adr = 0x000131025D131601ull, /* unique ID is set for some reason */ @@ -101,6 +110,24 @@ static const struct snd_soc_acpi_adr_device rt1316_3_group1_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt1316_0_group2_adr[] = { + { + .adr = 0x000031025D131601ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "rt1316-1" + } +}; + +static const struct snd_soc_acpi_adr_device rt1316_1_group2_adr[] = { + { + .adr = 0x000130025D131601ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "rt1316-2" + } +}; + static const struct snd_soc_acpi_adr_device rt1316_2_single_adr[] = { { .adr = 0x000230025D131601ull, @@ -209,6 +236,30 @@ static const struct snd_soc_acpi_link_adr adl_sdca_3_in_1[] = { {} }; +static const struct snd_soc_acpi_link_adr adl_sdw_rt711_link2_rt1316_link01_rt714_link3[] = { + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(rt711_sdca_2_adr), + .adr_d = rt711_sdca_2_adr, + }, + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(rt1316_0_group2_adr), + .adr_d = rt1316_0_group2_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(rt1316_1_group2_adr), + .adr_d = rt1316_1_group2_adr, + }, + { + .mask = BIT(3), + .num_adr = ARRAY_SIZE(rt714_3_adr), + .adr_d = rt714_3_adr, + }, + {} +}; + static const struct snd_soc_acpi_link_adr adl_sdw_rt1316_link12_rt714_link0[] = { { .mask = BIT(1), @@ -372,6 +423,13 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_sdw_machines[] = { .drv_name = "sof_sdw", .sof_tplg_filename = "sof-adl-rt711-l0-rt1316-l13-rt714-l2.tplg", }, + { + .link_mask = 0xF, /* 4 active links required */ + .links = adl_sdw_rt711_link2_rt1316_link01_rt714_link3, + .drv_name = "sof_sdw", + .sof_fw_filename = "sof-adl.ri", + .sof_tplg_filename = "sof-adl-rt711-l2-rt1316-l01-rt714-l3.tplg", + }, { .link_mask = 0xC, /* rt1316 on link2 & rt714 on link3 */ .links = adl_sdw_rt1316_link2_rt714_link3, From f55af7055cd465f6b767a0c1126977d4529c63c8 Mon Sep 17 00:00:00 2001 From: Gongjun Song Date: Fri, 5 Nov 2021 10:26:46 +0800 Subject: [PATCH 014/358] ASoC: Intel: sof_sdw: Add support for SKU 0B12 product This product supports a SoundWire headset codec, SoundWire capture from local microphones and two SoundWire amplifiers. Signed-off-by: Libin Yang Signed-off-by: Gongjun Song Reviewed-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211105022646.26305-10-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_sdw.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index bfbdda323b877d..77219c3f8766cc 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -288,6 +288,16 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { RT711_JD2 | SOF_SDW_FOUR_SPK), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B12") + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + RT711_JD2 | + SOF_SDW_FOUR_SPK), + }, { .callback = sof_sdw_quirk_cb, .matches = { From 33b8aad21ac175eba9577a73eb62b0aa141c241c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 18 Oct 2021 14:38:13 +0200 Subject: [PATCH 015/358] selftests: netfilter: add a vrf+conntrack testcase Rework the reproducer for the vrf+conntrack regression reported by Eugene into a selftest and also add a test for ip masquerading that Lahav fixed recently. With net or net-next tree, the first test fails and the latter two pass. With 09e856d54bda5f28 ("vrf: Reset skb conntrack connection on VRF rcv") reverted first test passes but the last two fail. A proper fix needs more work, for time being a revert seems to be the best choice, snat/masquerade did not work before the fix. Link: https://lore.kernel.org/netdev/378ca299-4474-7e9a-3d36-2350c8c98995@gmail.com/T/#m95358a31810df7392f541f99d187227bc75c9963 Reported-by: Eugene Crosser Cc: Lahav Schlesinger Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 3 +- .../selftests/netfilter/conntrack_vrf.sh | 219 ++++++++++++++++++ 2 files changed, 221 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/conntrack_vrf.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 8748199ac10984..ffca314897c4c6 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -5,7 +5,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ - ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh + ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ + conntrack_vrf.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh new file mode 100755 index 00000000000000..91f3ef0f1192cb --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh @@ -0,0 +1,219 @@ +#!/bin/sh + +# This script demonstrates interaction of conntrack and vrf. +# The vrf driver calls the netfilter hooks again, with oif/iif +# pointing at the VRF device. +# +# For ingress, this means first iteration has iifname of lower/real +# device. In this script, thats veth0. +# Second iteration is iifname set to vrf device, tvrf in this script. +# +# For egress, this is reversed: first iteration has the vrf device, +# second iteration is done with the lower/real/veth0 device. +# +# test_ct_zone_in demonstrates unexpected change of nftables +# behavior # caused by commit 09e856d54bda5f28 "vrf: Reset skb conntrack +# connection on VRF rcv" +# +# It was possible to assign conntrack zone to a packet (or mark it for +# `notracking`) in the prerouting chain before conntrack, based on real iif. +# +# After the change, the zone assignment is lost and the zone is assigned based +# on the VRF master interface (in case such a rule exists). +# assignment is lost. Instead, assignment based on the `iif` matching +# Thus it is impossible to distinguish packets based on the original +# interface. +# +# test_masquerade_vrf and test_masquerade_veth0 demonstrate the problem +# that was supposed to be fixed by the commit mentioned above to make sure +# that any fix to test case 1 won't break masquerade again. + +ksft_skip=4 + +IP0=172.30.30.1 +IP1=172.30.30.2 +PFXL=30 +ret=0 + +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" +ns1="ns1-$sfx" + +cleanup() +{ + ip netns pids $ns0 | xargs kill 2>/dev/null + ip netns pids $ns1 | xargs kill 2>/dev/null + + ip netns del $ns0 $ns1 +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add "$ns0" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns0" + exit $ksft_skip +fi +ip netns add "$ns1" + +trap cleanup EXIT + +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.default.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 + +ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not add veth device" + exit $ksft_skip +fi + +ip -net $ns0 li add tvrf type vrf table 9876 +if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + exit $ksft_skip +fi + +ip -net $ns0 li set lo up + +ip -net $ns0 li set veth0 master tvrf +ip -net $ns0 li set tvrf up +ip -net $ns0 li set veth0 up +ip -net $ns1 li set veth0 up + +ip -net $ns0 addr add $IP0/$PFXL dev veth0 +ip -net $ns1 addr add $IP1/$PFXL dev veth0 + +ip netns exec $ns1 iperf3 -s > /dev/null 2>&1& +if [ $? -ne 0 ];then + echo "SKIP: Could not start iperf3" + exit $ksft_skip +fi + +# test vrf ingress handling. +# The incoming connection should be placed in conntrack zone 1, +# as decided by the first iteration of the ruleset. +test_ct_zone_in() +{ +ip netns exec $ns0 nft -f - < /dev/null + + # should be in zone 1, not zone 2 + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 1 2>/dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "PASS: entry found in conntrack zone 1" + else + echo "FAIL: entry not found in conntrack zone 1" + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 2 2> /dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "FAIL: entry found in zone 2 instead" + else + echo "FAIL: entry not in zone 1 or 2, dumping table" + ip netns exec $ns0 conntrack -L + ip netns exec $ns0 nft list ruleset + fi + fi +} + +# add masq rule that gets evaluated w. outif set to vrf device. +# This tests the first iteration of the packet through conntrack, +# oifname is the vrf device. +test_masquerade_vrf() +{ + ip netns exec $ns0 conntrack -F 2>/dev/null + +ip netns exec $ns0 nft -f - </dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on vrf device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device" + else + echo "FAIL: vrf masq rule has unexpected counter value" + ret=1 + fi +} + +# add masq rule that gets evaluated w. outif set to veth device. +# This tests the 2nd iteration of the packet through conntrack, +# oifname is the lower device (veth0 in this case). +test_masquerade_veth() +{ + ip netns exec $ns0 conntrack -F 2>/dev/null +ip netns exec $ns0 nft -f - < /dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on veth device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on veth device" + else + echo "FAIL: vrf masq rule has unexpected counter value" + ret=1 + fi +} + +test_ct_zone_in +test_masquerade_vrf +test_masquerade_veth + +exit $ret From 228c3fa054ad118f78fc60f1a3f05ba29b043608 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 20 Oct 2021 18:25:37 +0200 Subject: [PATCH 016/358] selftests: netfilter: extend nfqueue tests to cover vrf device VRF device calls the output/postrouting hooks so packet should be seeon with oifname tvrf and once with eth0. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- .../testing/selftests/netfilter/nft_queue.sh | 54 +++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh index 3d202b90b33d2f..7d27f1f3bc0108 100755 --- a/tools/testing/selftests/netfilter/nft_queue.sh +++ b/tools/testing/selftests/netfilter/nft_queue.sh @@ -16,6 +16,10 @@ timeout=4 cleanup() { + ip netns pids ${ns1} | xargs kill 2>/dev/null + ip netns pids ${ns2} | xargs kill 2>/dev/null + ip netns pids ${nsrouter} | xargs kill 2>/dev/null + ip netns del ${ns1} ip netns del ${ns2} ip netns del ${nsrouter} @@ -332,6 +336,55 @@ EOF echo "PASS: tcp via loopback and re-queueing" } +test_icmp_vrf() { + ip -net $ns1 link add tvrf type vrf table 9876 + if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + return + fi + + ip -net $ns1 li set eth0 master tvrf + ip -net $ns1 li set tvrf up + + ip -net $ns1 route add 10.0.2.0/24 via 10.0.1.1 dev eth0 table 9876 +ip netns exec ${ns1} nft -f /dev/stdin < /dev/null + + for n in output post; do + for d in tvrf eth0; do + ip netns exec ${ns1} nft list chain inet filter $n | grep -q "oifname \"$d\" icmp type echo-request counter packets 1" + if [ $? -ne 0 ] ; then + echo "FAIL: chain $n: icmp packet counter mismatch for device $d" 1>&2 + ip netns exec ${ns1} nft list ruleset + ret=1 + return + fi + done + done + + wait $nfqpid + [ $? -eq 0 ] && echo "PASS: icmp+nfqueue via vrf" + wait 2>/dev/null +} + ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null @@ -372,5 +425,6 @@ test_queue 20 test_tcp_forward test_tcp_localhost test_tcp_localhost_requeue +test_icmp_vrf exit $ret From 00d8b83725e9b9bf5eac1f23712aa94ce30dad46 Mon Sep 17 00:00:00 2001 From: Wan Jiabing Date: Tue, 2 Nov 2021 05:13:55 -0400 Subject: [PATCH 017/358] netfilter: nft_payload: Remove duplicated include in nft_payload.c Fix following checkincludes.pl warning: ./net/netfilter/nft_payload.c: linux/ip.h is included more than once. Signed-off-by: Wan Jiabing Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_payload.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index cbfe4e4a4ad7af..bd689938a2e0c7 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -22,7 +22,6 @@ #include #include #include -#include #include static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off, From e1f8bc06e49794ebecc0f276429a7ab9f105ac06 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 3 Nov 2021 19:53:42 +0100 Subject: [PATCH 018/358] selftests: nft_nat: Improve port shadow test stability Setup phase in test_port_shadow() relied upon a race-condition: Listening nc on port 1405 was started in background before attempting to create the fake conntrack entry using the same source port. If listening nc won, fake conntrack entry could not be created causing wrong behaviour. Reorder nc calls to fix this and introduce a short delay before testing the setup to wait for listening nc process startup. Fixes: 465f15a6d1a8f ("selftests: nft_nat: add udp hole punch test case") Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_nat.sh | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index da1c1e4b6c86bf..905c033db74dc9 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -759,14 +759,16 @@ test_port_shadow() local result="" local logmsg="" + # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. + echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & nc_r=$! echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & nc_c=$! - # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. - echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + sleep 0.3 # ns1 tries to connect to ns0:1405. With default settings this should connect # to client, it matches the conntrack entry created above. From 85c0c8b342e89761554eed3f572ee55c0e5c6536 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 3 Nov 2021 19:53:43 +0100 Subject: [PATCH 019/358] selftests: nft_nat: Simplify port shadow notrack test The second rule in prerouting chain was probably a leftover: The router listens on veth0, so not tracking connections via that interface is sufficient. Likewise, the rule in output chain can be limited to that interface as well. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_nat.sh | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 905c033db74dc9..c62e4e26252c15 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -818,11 +818,10 @@ table $family raw { chain prerouting { type filter hook prerouting priority -300; policy accept; meta iif veth0 udp dport 1405 notrack - udp dport 1405 notrack } chain output { type filter hook output priority -300; policy accept; - udp sport 1405 notrack + meta oif veth0 udp sport 1405 notrack } } EOF From ad81d4daf6a3f4769a346e635d5e1e967ca455d9 Mon Sep 17 00:00:00 2001 From: Florent Fourcot Date: Wed, 3 Nov 2021 23:21:54 +0100 Subject: [PATCH 020/358] netfilter: ctnetlink: fix filtering with CTA_TUPLE_REPLY filter->orig_flags was used for a reply context. Fixes: cb8aa9a3affb ("netfilter: ctnetlink: add kernel side filtering for dump") Signed-off-by: Florent Fourcot Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index f1e5443fe7c74c..2663764d0b6eeb 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1011,7 +1011,7 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) CTA_TUPLE_REPLY, filter->family, &filter->zone, - filter->orig_flags); + filter->reply_flags); if (err < 0) { err = -EINVAL; goto err_filter; From 77522ff02f333434612bd72df9b376f8d3836e4d Mon Sep 17 00:00:00 2001 From: Florent Fourcot Date: Wed, 3 Nov 2021 23:21:55 +0100 Subject: [PATCH 021/358] netfilter: ctnetlink: do not erase error code with EINVAL And be consistent in error management for both orig/reply filtering Fixes: cb8aa9a3affb ("netfilter: ctnetlink: add kernel side filtering for dump") Signed-off-by: Florent Fourcot Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 2663764d0b6eeb..c7708bde057cb4 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1012,10 +1012,8 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) filter->family, &filter->zone, filter->reply_flags); - if (err < 0) { - err = -EINVAL; + if (err < 0) goto err_filter; - } } return filter; From c95c07836fa4c1767ed11d8eca0769c652760e32 Mon Sep 17 00:00:00 2001 From: yangxingwu Date: Thu, 4 Nov 2021 03:10:29 +0100 Subject: [PATCH 022/358] netfilter: ipvs: Fix reuse connection if RS weight is 0 We are changing expire_nodest_conn to work even for reused connections when conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs: Fix reuse connection if real server is dead"). For controlled and persistent connections, the new connection will get the needed real server depending on the rules in ip_vs_check_template(). Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when port reuse is detected") Co-developed-by: Chuanqi Liu Signed-off-by: Chuanqi Liu Signed-off-by: yangxingwu Acked-by: Simon Horman Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/ipvs-sysctl.rst | 3 +-- net/netfilter/ipvs/ip_vs_core.c | 8 ++++---- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst index 95ef56d62077f7..387fda80f05fbb 100644 --- a/Documentation/networking/ipvs-sysctl.rst +++ b/Documentation/networking/ipvs-sysctl.rst @@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER 0: disable any special handling on port reuse. The new connection will be delivered to the same real server that was - servicing the previous connection. This will effectively - disable expire_nodest_conn. + servicing the previous connection. bit 1: enable rescheduling of new connections when it is safe. That is, whenever expire_nodest_conn and for TCP sockets, when diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index e93c937a8bf026..51ad557a525b56 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1919,7 +1919,6 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; - int conn_reuse_mode; struct sock *sk; int af = state->pf; @@ -1997,15 +1996,16 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, af, skb, &iph); - conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); - if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { + if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { + int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); - } else if (is_new_conn_expected(cp, conn_reuse_mode)) { + } else if (conn_reuse_mode && + is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; From c08d3286caf1ec774b80ebb26e3ec31a0b434973 Mon Sep 17 00:00:00 2001 From: Jing Yao Date: Thu, 4 Nov 2021 11:49:11 +0000 Subject: [PATCH 023/358] netfilter: xt_IDLETIMER: replace snprintf in show functions with sysfs_emit coccicheck complains about the use of snprintf() in sysfs show functions: WARNING use scnprintf or sprintf Use sysfs_emit instead of scnprintf, snprintf or sprintf makes more sense. Reported-by: Zeal Robot Signed-off-by: Jing Yao Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_IDLETIMER.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 2f7cf5ecebf4f3..0f8bb0bf558f97 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -85,9 +85,9 @@ static ssize_t idletimer_tg_show(struct device *dev, mutex_unlock(&list_mutex); if (time_after(expires, jiffies) || ktimespec.tv_sec > 0) - return snprintf(buf, PAGE_SIZE, "%ld\n", time_diff); + return sysfs_emit(buf, "%ld\n", time_diff); - return snprintf(buf, PAGE_SIZE, "0\n"); + return sysfs_emit(buf, "0\n"); } static void idletimer_tg_work(struct work_struct *work) From 39f6eed4cb209643f3f8633291854ed7375d7264 Mon Sep 17 00:00:00 2001 From: Will Mortensen Date: Sat, 6 Nov 2021 18:28:21 -0700 Subject: [PATCH 024/358] netfilter: flowtable: fix IPv6 tunnel addr match Previously the IPv6 addresses in the key were clobbered and the mask was left unset. I haven't tested this; I noticed it while skimming the code to understand an unrelated issue. Fixes: cfab6dbd0ecf ("netfilter: flowtable: add tunnel match offload support") Cc: wenxu Signed-off-by: Will Mortensen Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_flow_table_offload.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index d6bf1b2cd541b7..b561e0a44a45f3 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -65,11 +65,11 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, sizeof(struct in6_addr)); if (memcmp(&key->enc_ipv6.src, &in6addr_any, sizeof(struct in6_addr))) - memset(&key->enc_ipv6.src, 0xff, + memset(&mask->enc_ipv6.src, 0xff, sizeof(struct in6_addr)); if (memcmp(&key->enc_ipv6.dst, &in6addr_any, sizeof(struct in6_addr))) - memset(&key->enc_ipv6.dst, 0xff, + memset(&mask->enc_ipv6.dst, 0xff, sizeof(struct in6_addr)); enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS); key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; From fa443bc3c1e4b28d9315dea882e8358ba6e26f8b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Fri, 29 Oct 2021 17:28:56 +0200 Subject: [PATCH 025/358] HID: intel-ish-hid: add support for MODULE_DEVICE_TABLE() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows to selectively autoload drivers for ISH devices. Currently all ISH drivers are loaded for all systems having any ISH device. Signed-off-by: Thomas Weißschuh Acked-by: Srinivas Pandruvada Acked-by: Hans de Goede Signed-off-by: Jiri Kosina --- include/linux/mod_devicetable.h | 13 +++++++++++++ scripts/mod/devicetable-offsets.c | 3 +++ scripts/mod/file2alias.c | 24 ++++++++++++++++++++++++ 3 files changed, 40 insertions(+) diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index ae2e75d15b2199..befbf53c4b7cfe 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -895,4 +895,17 @@ struct dfl_device_id { kernel_ulong_t driver_data; }; +/* ISHTP (Integrated Sensor Hub Transport Protocol) */ + +#define ISHTP_MODULE_PREFIX "ishtp:" + +/** + * struct ishtp_device_id - ISHTP device identifier + * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba + * @context: pointer to driver specific data + */ +struct ishtp_device_id { + guid_t guid; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index cc3625617a0ef5..c0d3bcb9913809 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -259,5 +259,8 @@ int main(void) DEVID_FIELD(dfl_device_id, type); DEVID_FIELD(dfl_device_id, feature_id); + DEVID(ishtp_device_id); + DEVID_FIELD(ishtp_device_id, guid); + return 0; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 49aba862073e01..5258247d78ac29 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -115,6 +115,17 @@ static inline void add_uuid(char *str, uuid_le uuid) uuid.b[12], uuid.b[13], uuid.b[14], uuid.b[15]); } +static inline void add_guid(char *str, guid_t guid) +{ + int len = strlen(str); + + sprintf(str + len, "%02X%02X%02X%02X-%02X%02X-%02X%02X-%02X%02X-%02X%02X%02X%02X%02X%02X", + guid.b[3], guid.b[2], guid.b[1], guid.b[0], + guid.b[5], guid.b[4], guid.b[7], guid.b[6], + guid.b[8], guid.b[9], guid.b[10], guid.b[11], + guid.b[12], guid.b[13], guid.b[14], guid.b[15]); +} + /** * Check that sizeof(device_id type) are consistent with size of section * in .o file. If in-consistent then userspace and kernel does not agree @@ -1380,6 +1391,18 @@ static int do_mhi_entry(const char *filename, void *symval, char *alias) return 1; } +/* Looks like: ishtp:{guid} */ +static int do_ishtp_entry(const char *filename, void *symval, char *alias) +{ + DEF_FIELD(symval, ishtp_device_id, guid); + + strcpy(alias, ISHTP_MODULE_PREFIX "{"); + add_guid(alias, guid); + strcat(alias, "}"); + + return 1; +} + static int do_auxiliary_entry(const char *filename, void *symval, char *alias) { DEF_FIELD_ADDR(symval, auxiliary_device_id, name); @@ -1499,6 +1522,7 @@ static const struct devtable devtable[] = { {"auxiliary", SIZE_auxiliary_device_id, do_auxiliary_entry}, {"ssam", SIZE_ssam_device_id, do_ssam_entry}, {"dfl", SIZE_dfl_device_id, do_dfl_entry}, + {"ishtp", SIZE_ishtp_device_id, do_ishtp_entry}, }; /* Create MODULE_ALIAS() statements. From cb1a2c6847f7bd2ba45ee1b2c86543c783aec270 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Fri, 29 Oct 2021 17:28:57 +0200 Subject: [PATCH 026/358] HID: intel-ish-hid: use constants for modaliases MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Thomas Weißschuh Signed-off-by: Jiri Kosina --- drivers/hid/intel-ish-hid/ishtp/bus.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index 334eac611774d7..e159cd1c5f37df 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -350,7 +350,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a, { int len; - len = snprintf(buf, PAGE_SIZE, "ishtp:%s\n", dev_name(dev)); + len = snprintf(buf, PAGE_SIZE, ISHTP_MODULE_PREFIX "%s\n", dev_name(dev)); return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len; } static DEVICE_ATTR_RO(modalias); @@ -363,7 +363,7 @@ ATTRIBUTE_GROUPS(ishtp_cl_dev); static int ishtp_cl_uevent(struct device *dev, struct kobj_uevent_env *env) { - if (add_uevent_var(env, "MODALIAS=ishtp:%s", dev_name(dev))) + if (add_uevent_var(env, "MODALIAS=" ISHTP_MODULE_PREFIX "%s", dev_name(dev))) return -ENOMEM; return 0; } From 44e2a58cb8803e3e40eaf5708c4d15b4118913c4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Fri, 29 Oct 2021 17:28:58 +0200 Subject: [PATCH 027/358] HID: intel-ish-hid: fw-loader: only load for matching devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously it was loaded for all ISHTP devices. Signed-off-by: Thomas Weißschuh Acked-by: Srinivas Pandruvada Acked-by: Hans de Goede Signed-off-by: Jiri Kosina --- drivers/hid/intel-ish-hid/ishtp-fw-loader.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c index 1b486f2627477c..945a9d0b68cd44 100644 --- a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c +++ b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c @@ -1063,6 +1063,12 @@ static struct ishtp_cl_driver loader_ishtp_cl_driver = { .reset = loader_ishtp_cl_reset, }; +static const struct ishtp_device_id loader_ishtp_id_table[] = { + { loader_ishtp_guid }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, loader_ishtp_id_table); + static int __init ish_loader_init(void) { return ishtp_cl_driver_register(&loader_ishtp_cl_driver, THIS_MODULE); @@ -1083,4 +1089,3 @@ MODULE_DESCRIPTION("ISH ISH-TP Host firmware Loader Client Driver"); MODULE_AUTHOR("Rushikesh S Kadam "); MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("ishtp:*"); From 0d0cccc0fd83f4657cfc2e50706bfa16f125057e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Fri, 29 Oct 2021 17:28:59 +0200 Subject: [PATCH 028/358] HID: intel-ish-hid: hid-client: only load for matching devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously it was loaded for all ISHTP devices. Signed-off-by: Thomas Weißschuh Acked-by: Srinivas Pandruvada Acked-by: Hans de Goede Signed-off-by: Jiri Kosina --- drivers/hid/intel-ish-hid/ishtp-hid-client.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index 91bf4d01e91a7c..fb47d38d1e8700 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -952,6 +952,12 @@ static struct ishtp_cl_driver hid_ishtp_cl_driver = { .driver.pm = &hid_ishtp_pm_ops, }; +static const struct ishtp_device_id hid_ishtp_id_table[] = { + { hid_ishtp_guid }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, hid_ishtp_id_table); + static int __init ish_hid_init(void) { int rv; @@ -981,4 +987,3 @@ MODULE_AUTHOR("Daniel Drubin "); MODULE_AUTHOR("Srinivas Pandruvada "); MODULE_LICENSE("GPL"); -MODULE_ALIAS("ishtp:*"); From facfe0a4fdce3f545a4a883358eda3078b0425c7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Fri, 29 Oct 2021 17:29:00 +0200 Subject: [PATCH 029/358] platform/chrome: chros_ec_ishtp: only load for matching devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously it was loaded for all ISHTP devices. Signed-off-by: Thomas Weißschuh Acked-by: Srinivas Pandruvada Acked-by: Hans de Goede Signed-off-by: Jiri Kosina --- drivers/platform/chrome/cros_ec_ishtp.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index 9d1e7e03628e20..8c17358e84c1da 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -774,6 +774,12 @@ static struct ishtp_cl_driver cros_ec_ishtp_driver = { }, }; +static const struct ishtp_device_id cros_ec_ishtp_id_table[] = { + { cros_ish_guid }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, cros_ec_ishtp_id_table); + static int __init cros_ec_ishtp_mod_init(void) { return ishtp_cl_driver_register(&cros_ec_ishtp_driver, THIS_MODULE); @@ -791,4 +797,3 @@ MODULE_DESCRIPTION("ChromeOS EC ISHTP Client Driver"); MODULE_AUTHOR("Rushikesh S Kadam "); MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("ishtp:*"); From f155dfeaa4ee21bce3f8f76b2addaec396b41b39 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Fri, 29 Oct 2021 17:29:01 +0200 Subject: [PATCH 030/358] platform/x86: isthp_eclite: only load for matching devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previously it was loaded for all ISHTP devices. Signed-off-by: Thomas Weißschuh Acked-by: Srinivas Pandruvada Acked-by: Hans de Goede Signed-off-by: Jiri Kosina --- drivers/platform/x86/intel/ishtp_eclite.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/intel/ishtp_eclite.c b/drivers/platform/x86/intel/ishtp_eclite.c index 12fc98a4865776..b9fb8f28fd63cb 100644 --- a/drivers/platform/x86/intel/ishtp_eclite.c +++ b/drivers/platform/x86/intel/ishtp_eclite.c @@ -681,6 +681,12 @@ static struct ishtp_cl_driver ecl_ishtp_cl_driver = { .driver.pm = &ecl_ishtp_pm_ops, }; +static const struct ishtp_device_id ecl_ishtp_id_table[] = { + { ecl_ishtp_guid }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, ecl_ishtp_id_table); + static int __init ecl_ishtp_init(void) { return ishtp_cl_driver_register(&ecl_ishtp_cl_driver, THIS_MODULE); @@ -698,4 +704,3 @@ MODULE_DESCRIPTION("ISH ISHTP eclite client opregion driver"); MODULE_AUTHOR("K Naduvalath, Sumesh "); MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("ishtp:*"); From 304dd3680b56a2a5c8eaff41bcf1a3e49adf7dfc Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 10 Nov 2021 11:12:08 +0300 Subject: [PATCH 031/358] HID: nintendo: unlock on error in joycon_leds_create() These two error paths need to drop the lock before returning. Fixes: c5e626769563 ("HID: nintendo: add player led support") Signed-off-by: Dan Carpenter Signed-off-by: Jiri Kosina --- drivers/hid/hid-nintendo.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index a1e0f6849875e4..7e1d1127493ed6 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -1850,8 +1850,10 @@ static int joycon_leds_create(struct joycon_ctlr *ctlr) d_name, "green", joycon_player_led_names[i]); - if (!name) + if (!name) { + mutex_unlock(&joycon_input_num_mutex); return -ENOMEM; + } led = &ctlr->leds[i]; led->name = name; @@ -1864,6 +1866,7 @@ static int joycon_leds_create(struct joycon_ctlr *ctlr) ret = devm_led_classdev_register(&hdev->dev, led); if (ret) { hid_err(hdev, "Failed registering %s LED\n", led->name); + mutex_unlock(&joycon_input_num_mutex); return ret; } } From 7fb0413baa7f8a04caef0c504df9af7e0623d296 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Mon, 8 Nov 2021 16:31:01 -0800 Subject: [PATCH 032/358] HID: wacom: Use "Confidence" flag to prevent reporting invalid contacts The HID descriptor of many of Wacom's touch input devices include a "Confidence" usage that signals if a particular touch collection contains useful data. The driver does not look at this flag, however, which causes even invalid contacts to be reported to userspace. A lucky combination of kernel event filtering and device behavior (specifically: contact ID 0 == invalid, contact ID >0 == valid; and order all data so that all valid contacts are reported before any invalid contacts) spare most devices from any visibly-bad behavior. The DTH-2452 is one example of an unlucky device that misbehaves. It uses ID 0 for both the first valid contact and all invalid contacts. Because we report both the valid and invalid contacts, the kernel reports that contact 0 first goes down (valid) and then goes up (invalid) in every report. This causes ~100 clicks per second simply by touching the screen. This patch inroduces new `confidence` flag in our `hid_data` structure. The value is initially set to `true` at the start of a report and can be set to `false` if an invalid touch usage is seen. Link: https://github.com/linuxwacom/input-wacom/issues/270 Fixes: f8b6a74719b5 ("HID: wacom: generic: Support multiple tools per report") Signed-off-by: Jason Gerecke Tested-by: Joshua Dickens Cc: Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 8 +++++++- drivers/hid/wacom_wac.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 33a6908995b1be..2a4cc39962e765 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2603,6 +2603,9 @@ static void wacom_wac_finger_event(struct hid_device *hdev, return; switch (equivalent_usage) { + case HID_DG_CONFIDENCE: + wacom_wac->hid_data.confidence = value; + break; case HID_GD_X: wacom_wac->hid_data.x = value; break; @@ -2635,7 +2638,8 @@ static void wacom_wac_finger_event(struct hid_device *hdev, } if (usage->usage_index + 1 == field->report_count) { - if (equivalent_usage == wacom_wac->hid_data.last_slot_field) + if (equivalent_usage == wacom_wac->hid_data.last_slot_field && + wacom_wac->hid_data.confidence) wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input); } } @@ -2653,6 +2657,8 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev, wacom_wac->is_invalid_bt_frame = false; + hid_data->confidence = true; + for (i = 0; i < report->maxfield; i++) { struct hid_field *field = report->field[i]; int j; diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index 8b2d4e5b2303c3..466b62cc16dc19 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -301,6 +301,7 @@ struct hid_data { bool barrelswitch; bool barrelswitch2; bool serialhi; + bool confidence; int x; int y; int pressure; From 678d92b6126b9f55419b6a51ef0a88bce2ef2f20 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 26 Oct 2021 06:49:54 +0100 Subject: [PATCH 033/358] media: v4l2-core: fix VIDIOC_DQEVENT handling on non-x86 My previous bugfix addressed an API inconsistency found by syzbot, and it correctly fixed the issue on x86-64 machines, which now behave correctly for both native and compat tasks. Unfortunately, John found that the patch broke compat mode on all other architectures, as they can no longer rely on the VIDIOC_DQEVENT_TIME32 code from the native handler as a fallback in the compat code. The best way I can see for addressing this is to generalize the VIDIOC_DQEVENT32_TIME32 code from x86 and use that for all architectures, leaving only the VIDIOC_DQEVENT32 variant as x86 specific. The original code was trying to be clever and use the same conversion helper for native 32-bit code and compat mode, but that turned out to be too obscure so even I missed that bit I had introduced myself when I made the fix. Fixes: c344f07aa1b4 ("media: v4l2-core: ignore native time32 ioctls on 64-bit") Reported-by: John Stultz Signed-off-by: Arnd Bergmann Tested-by: John Stultz Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-compat-ioctl32.c | 41 ++++++++----------- 1 file changed, 17 insertions(+), 24 deletions(-) diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index 8176769a89fa44..0f3d6b5667b07e 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -751,10 +751,6 @@ static int put_v4l2_ext_controls32(struct v4l2_ext_controls *p64, /* * x86 is the only compat architecture with different struct alignment * between 32-bit and 64-bit tasks. - * - * On all other architectures, v4l2_event32 and v4l2_event32_time32 are - * the same as v4l2_event and v4l2_event_time32, so we can use the native - * handlers, converting v4l2_event to v4l2_event_time32 if necessary. */ struct v4l2_event32 { __u32 type; @@ -772,21 +768,6 @@ struct v4l2_event32 { __u32 reserved[8]; }; -#ifdef CONFIG_COMPAT_32BIT_TIME -struct v4l2_event32_time32 { - __u32 type; - union { - compat_s64 value64; - __u8 data[64]; - } u; - __u32 pending; - __u32 sequence; - struct old_timespec32 timestamp; - __u32 id; - __u32 reserved[8]; -}; -#endif - static int put_v4l2_event32(struct v4l2_event *p64, struct v4l2_event32 __user *p32) { @@ -802,7 +783,22 @@ static int put_v4l2_event32(struct v4l2_event *p64, return 0; } +#endif + #ifdef CONFIG_COMPAT_32BIT_TIME +struct v4l2_event32_time32 { + __u32 type; + union { + compat_s64 value64; + __u8 data[64]; + } u; + __u32 pending; + __u32 sequence; + struct old_timespec32 timestamp; + __u32 id; + __u32 reserved[8]; +}; + static int put_v4l2_event32_time32(struct v4l2_event *p64, struct v4l2_event32_time32 __user *p32) { @@ -818,7 +814,6 @@ static int put_v4l2_event32_time32(struct v4l2_event *p64, return 0; } #endif -#endif struct v4l2_edid32 { __u32 pad; @@ -880,9 +875,7 @@ static int put_v4l2_edid32(struct v4l2_edid *p64, #define VIDIOC_QUERYBUF32_TIME32 _IOWR('V', 9, struct v4l2_buffer32_time32) #define VIDIOC_QBUF32_TIME32 _IOWR('V', 15, struct v4l2_buffer32_time32) #define VIDIOC_DQBUF32_TIME32 _IOWR('V', 17, struct v4l2_buffer32_time32) -#ifdef CONFIG_X86_64 #define VIDIOC_DQEVENT32_TIME32 _IOR ('V', 89, struct v4l2_event32_time32) -#endif #define VIDIOC_PREPARE_BUF32_TIME32 _IOWR('V', 93, struct v4l2_buffer32_time32) #endif @@ -936,10 +929,10 @@ unsigned int v4l2_compat_translate_cmd(unsigned int cmd) #ifdef CONFIG_X86_64 case VIDIOC_DQEVENT32: return VIDIOC_DQEVENT; +#endif #ifdef CONFIG_COMPAT_32BIT_TIME case VIDIOC_DQEVENT32_TIME32: return VIDIOC_DQEVENT; -#endif #endif } return cmd; @@ -1032,10 +1025,10 @@ int v4l2_compat_put_user(void __user *arg, void *parg, unsigned int cmd) #ifdef CONFIG_X86_64 case VIDIOC_DQEVENT32: return put_v4l2_event32(parg, arg); +#endif #ifdef CONFIG_COMPAT_32BIT_TIME case VIDIOC_DQEVENT32_TIME32: return put_v4l2_event32_time32(parg, arg); -#endif #endif } return 0; From d55c3ee6b4c7b76326eb257403762f8bd7cc48c2 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 1 Nov 2021 14:53:55 +0000 Subject: [PATCH 034/358] media: videobuf2-dma-sg: Fix buf->vb NULL pointer dereference Commit a4b83deb3e76 ("media: videobuf2: rework vb2_mem_ops API") added a new vb member to struct vb2_dma_sg_buf, but it only added code setting this to the vb2_dma_sg_alloc() function and not to the vb2_dma_sg_get_userptr() and vb2_dma_sg_attach_dmabuf() which also create vb2_dma_sg_buf objects. This is causing a crash due to a NULL pointer deref when using libcamera on devices with an Intel IPU3 (qcam app). Fix these crashes by assigning buf->vb in the other 2 functions too, note libcamera tests the vb2_dma_sg_get_userptr() path, the change to the vb2_dma_sg_attach_dmabuf() path is untested. Fixes: a4b83deb3e76 ("media: videobuf2: rework vb2_mem_ops API") Cc: Sergey Senozhatsky Signed-off-by: Hans de Goede Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-dma-sg.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index 33ee63a9913984..0452ed9fac950f 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -241,6 +241,7 @@ static void *vb2_dma_sg_get_userptr(struct vb2_buffer *vb, struct device *dev, buf->offset = vaddr & ~PAGE_MASK; buf->size = size; buf->dma_sgt = &buf->sg_table; + buf->vb = vb; vec = vb2_create_framevec(vaddr, size); if (IS_ERR(vec)) goto userptr_fail_pfnvec; @@ -642,6 +643,7 @@ static void *vb2_dma_sg_attach_dmabuf(struct vb2_buffer *vb, struct device *dev, buf->dma_dir = vb->vb2_queue->dma_dir; buf->size = size; buf->db_attach = dba; + buf->vb = vb; return buf; } From 13cbaa4c2b7bf9f8285e1164d005dbf08244ecd5 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 2 Nov 2021 12:24:26 +0000 Subject: [PATCH 035/358] media: cec: copy sequence field for the reply When the reply for a non-blocking transmit arrives, the sequence field for that reply was never filled in, so userspace would have no way of associating the reply to the original transmit. Copy the sequence field to ensure that this is now possible. Signed-off-by: Hans Verkuil Fixes: 0dbacebede1e ([media] cec: move the CEC framework out of staging and to media) Cc: Signed-off-by: Mauro Carvalho Chehab --- drivers/media/cec/core/cec-adap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 79fa36de8a04a9..cd9cb354dc2c7f 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1199,6 +1199,7 @@ void cec_received_msg_ts(struct cec_adapter *adap, if (abort) dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT; msg->flags = dst->flags; + msg->sequence = dst->sequence; /* Remove it from the wait_queue */ list_del_init(&data->list); From 64355db3caf6468dc711995239efe0cbcd7d0091 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Wed, 10 Nov 2021 13:16:55 +0100 Subject: [PATCH 036/358] mod_devicetable: fix kdocs for ishtp_device_id MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The kdocs were copied from another device_id struct and not adapted. Fixes: fa443bc3c1e4 ("HID: intel-ish-hid: add support for MODULE_DEVICE_TABLE()") Signed-off-by: Thomas Weißschuh Reported-by: Stephen Rothwell Signed-off-by: Jiri Kosina --- include/linux/mod_devicetable.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index befbf53c4b7cfe..c70abe7aaef24d 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -901,8 +901,7 @@ struct dfl_device_id { /** * struct ishtp_device_id - ISHTP device identifier - * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba - * @context: pointer to driver specific data + * @guid: GUID of the device. */ struct ishtp_device_id { guid_t guid; From bf9167a8b40c9cf463521da05342db81808c1b6e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Nov 2021 09:56:33 +0100 Subject: [PATCH 037/358] HID: intel-ish-hid: fix module device-id handling A late addititon to the intel-ish-hid framework caused a build failure with clang, and introduced an ABI to the module loader that stops working if any driver ever needs to bind to more than one UUID: drivers/hid/intel-ish-hid/ishtp-fw-loader.c:1067:4: error: initializer element is not a compile-time constant Change the ishtp_device_id to have correct documentation and a driver_data field like all the other ones, and change the drivers to use the ID table as the primary identification in a way that works with all compilers and avoids duplciating the identifiers. Fixes: f155dfeaa4ee ("platform/x86: isthp_eclite: only load for matching devices") Fixes: facfe0a4fdce ("platform/chrome: chros_ec_ishtp: only load for matching devices") Fixes: 0d0cccc0fd83 ("HID: intel-ish-hid: hid-client: only load for matching devices") Fixes: 44e2a58cb880 ("HID: intel-ish-hid: fw-loader: only load for matching devices") Fixes: cb1a2c6847f7 ("HID: intel-ish-hid: use constants for modaliases") Fixes: fa443bc3c1e4 ("HID: intel-ish-hid: add support for MODULE_DEVICE_TABLE()") Signed-off-by: Arnd Bergmann Reviewed-by: Hans de Goede [jkosina@suse.cz: fix ecl_ishtp_cl_driver.id initialization] [jkosina@suse.cz: fix conflict with already fixed kerneldoc] Signed-off-by: Jiri Kosina --- drivers/hid/intel-ish-hid/ishtp-fw-loader.c | 19 ++++++++----------- drivers/hid/intel-ish-hid/ishtp-hid-client.c | 19 ++++++++----------- drivers/hid/intel-ish-hid/ishtp/bus.c | 2 +- drivers/platform/chrome/cros_ec_ishtp.c | 19 ++++++++----------- drivers/platform/x86/intel/ishtp_eclite.c | 19 ++++++++----------- include/linux/intel-ish-client-if.h | 4 ++-- include/linux/mod_devicetable.h | 2 ++ 7 files changed, 37 insertions(+), 47 deletions(-) diff --git a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c index 945a9d0b68cd44..0e1183e961471d 100644 --- a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c +++ b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c @@ -76,9 +76,12 @@ enum ish_loader_commands { #define LOADER_XFER_MODE_ISHTP BIT(1) /* ISH Transport Loader client unique GUID */ -static const guid_t loader_ishtp_guid = - GUID_INIT(0xc804d06a, 0x55bd, 0x4ea7, - 0xad, 0xed, 0x1e, 0x31, 0x22, 0x8c, 0x76, 0xdc); +static const struct ishtp_device_id loader_ishtp_id_table[] = { + { .guid = GUID_INIT(0xc804d06a, 0x55bd, 0x4ea7, + 0xad, 0xed, 0x1e, 0x31, 0x22, 0x8c, 0x76, 0xdc) }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, loader_ishtp_id_table); #define FILENAME_SIZE 256 @@ -880,7 +883,7 @@ static int loader_init(struct ishtp_cl *loader_ishtp_cl, int reset) fw_client = ishtp_fw_cl_get_client(ishtp_get_ishtp_device(loader_ishtp_cl), - &loader_ishtp_guid); + &loader_ishtp_id_table[0].guid); if (!fw_client) { dev_err(cl_data_to_dev(client_data), "ISH client uuid not found\n"); @@ -1057,18 +1060,12 @@ static int loader_ishtp_cl_reset(struct ishtp_cl_device *cl_device) static struct ishtp_cl_driver loader_ishtp_cl_driver = { .name = "ish-loader", - .guid = &loader_ishtp_guid, + .id = loader_ishtp_id_table, .probe = loader_ishtp_cl_probe, .remove = loader_ishtp_cl_remove, .reset = loader_ishtp_cl_reset, }; -static const struct ishtp_device_id loader_ishtp_id_table[] = { - { loader_ishtp_guid }, - { } -}; -MODULE_DEVICE_TABLE(ishtp, loader_ishtp_id_table); - static int __init ish_loader_init(void) { return ishtp_cl_driver_register(&loader_ishtp_cl_driver, THIS_MODULE); diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index fb47d38d1e8700..4338c9b68a43d3 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -12,9 +12,12 @@ #include "ishtp-hid.h" /* ISH Transport protocol (ISHTP in short) GUID */ -static const guid_t hid_ishtp_guid = - GUID_INIT(0x33AECD58, 0xB679, 0x4E54, - 0x9B, 0xD9, 0xA0, 0x4D, 0x34, 0xF0, 0xC2, 0x26); +static const struct ishtp_device_id hid_ishtp_id_table[] = { + { .guid = GUID_INIT(0x33AECD58, 0xB679, 0x4E54, + 0x9B, 0xD9, 0xA0, 0x4D, 0x34, 0xF0, 0xC2, 0x26), }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, hid_ishtp_id_table); /* Rx ring buffer pool size */ #define HID_CL_RX_RING_SIZE 32 @@ -662,7 +665,7 @@ static int hid_ishtp_cl_init(struct ishtp_cl *hid_ishtp_cl, int reset) ishtp_set_tx_ring_size(hid_ishtp_cl, HID_CL_TX_RING_SIZE); ishtp_set_rx_ring_size(hid_ishtp_cl, HID_CL_RX_RING_SIZE); - fw_client = ishtp_fw_cl_get_client(dev, &hid_ishtp_guid); + fw_client = ishtp_fw_cl_get_client(dev, &hid_ishtp_id_table[0].guid); if (!fw_client) { dev_err(cl_data_to_dev(client_data), "ish client uuid not found\n"); @@ -945,19 +948,13 @@ static const struct dev_pm_ops hid_ishtp_pm_ops = { static struct ishtp_cl_driver hid_ishtp_cl_driver = { .name = "ish-hid", - .guid = &hid_ishtp_guid, + .id = hid_ishtp_id_table, .probe = hid_ishtp_cl_probe, .remove = hid_ishtp_cl_remove, .reset = hid_ishtp_cl_reset, .driver.pm = &hid_ishtp_pm_ops, }; -static const struct ishtp_device_id hid_ishtp_id_table[] = { - { hid_ishtp_guid }, - { } -}; -MODULE_DEVICE_TABLE(ishtp, hid_ishtp_id_table); - static int __init ish_hid_init(void) { int rv; diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index e159cd1c5f37df..f68aba8794fe50 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -241,7 +241,7 @@ static int ishtp_cl_bus_match(struct device *dev, struct device_driver *drv) struct ishtp_cl_device *device = to_ishtp_cl_device(dev); struct ishtp_cl_driver *driver = to_ishtp_cl_driver(drv); - return guid_equal(driver->guid, + return guid_equal(&driver->id[0].guid, &device->fw_client->props.protocol_name); } diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index 8c17358e84c1da..4020b8354bae90 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -41,9 +41,12 @@ enum cros_ec_ish_channel { #define ISHTP_SEND_TIMEOUT (3 * HZ) /* ISH Transport CrOS EC ISH client unique GUID */ -static const guid_t cros_ish_guid = - GUID_INIT(0x7b7154d0, 0x56f4, 0x4bdc, - 0xb0, 0xd8, 0x9e, 0x7c, 0xda, 0xe0, 0xd6, 0xa0); +static const struct ishtp_device_id cros_ec_ishtp_id_table[] = { + { .guid = GUID_INIT(0x7b7154d0, 0x56f4, 0x4bdc, + 0xb0, 0xd8, 0x9e, 0x7c, 0xda, 0xe0, 0xd6, 0xa0), }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, cros_ec_ishtp_id_table); struct header { u8 channel; @@ -389,7 +392,7 @@ static int cros_ish_init(struct ishtp_cl *cros_ish_cl) ishtp_set_tx_ring_size(cros_ish_cl, CROS_ISH_CL_TX_RING_SIZE); ishtp_set_rx_ring_size(cros_ish_cl, CROS_ISH_CL_RX_RING_SIZE); - fw_client = ishtp_fw_cl_get_client(dev, &cros_ish_guid); + fw_client = ishtp_fw_cl_get_client(dev, &cros_ec_ishtp_id_table[0].guid); if (!fw_client) { dev_err(cl_data_to_dev(client_data), "ish client uuid not found\n"); @@ -765,7 +768,7 @@ static SIMPLE_DEV_PM_OPS(cros_ec_ishtp_pm_ops, cros_ec_ishtp_suspend, static struct ishtp_cl_driver cros_ec_ishtp_driver = { .name = "cros_ec_ishtp", - .guid = &cros_ish_guid, + .id = cros_ec_ishtp_id_table, .probe = cros_ec_ishtp_probe, .remove = cros_ec_ishtp_remove, .reset = cros_ec_ishtp_reset, @@ -774,12 +777,6 @@ static struct ishtp_cl_driver cros_ec_ishtp_driver = { }, }; -static const struct ishtp_device_id cros_ec_ishtp_id_table[] = { - { cros_ish_guid }, - { } -}; -MODULE_DEVICE_TABLE(ishtp, cros_ec_ishtp_id_table); - static int __init cros_ec_ishtp_mod_init(void) { return ishtp_cl_driver_register(&cros_ec_ishtp_driver, THIS_MODULE); diff --git a/drivers/platform/x86/intel/ishtp_eclite.c b/drivers/platform/x86/intel/ishtp_eclite.c index b9fb8f28fd63cb..93ac8b2dbf3878 100644 --- a/drivers/platform/x86/intel/ishtp_eclite.c +++ b/drivers/platform/x86/intel/ishtp_eclite.c @@ -93,9 +93,12 @@ struct ishtp_opregion_dev { }; /* eclite ishtp client UUID: 6a19cc4b-d760-4de3-b14d-f25ebd0fbcd9 */ -static const guid_t ecl_ishtp_guid = - GUID_INIT(0x6a19cc4b, 0xd760, 0x4de3, - 0xb1, 0x4d, 0xf2, 0x5e, 0xbd, 0xf, 0xbc, 0xd9); +static const struct ishtp_device_id ecl_ishtp_id_table[] = { + { .guid = GUID_INIT(0x6a19cc4b, 0xd760, 0x4de3, + 0xb1, 0x4d, 0xf2, 0x5e, 0xbd, 0xf, 0xbc, 0xd9), }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, ecl_ishtp_id_table); /* ACPI DSM UUID: 91d936a7-1f01-49c6-a6b4-72f00ad8d8a5 */ static const guid_t ecl_acpi_guid = @@ -462,7 +465,7 @@ static int ecl_ishtp_cl_init(struct ishtp_cl *ecl_ishtp_cl) ishtp_set_tx_ring_size(ecl_ishtp_cl, ECL_CL_TX_RING_SIZE); ishtp_set_rx_ring_size(ecl_ishtp_cl, ECL_CL_RX_RING_SIZE); - fw_client = ishtp_fw_cl_get_client(dev, &ecl_ishtp_guid); + fw_client = ishtp_fw_cl_get_client(dev, &ecl_ishtp_id_table[0].guid); if (!fw_client) { dev_err(cl_data_to_dev(opr_dev), "fw client not found\n"); return -ENOENT; @@ -674,19 +677,13 @@ static const struct dev_pm_ops ecl_ishtp_pm_ops = { static struct ishtp_cl_driver ecl_ishtp_cl_driver = { .name = "ishtp-eclite", - .guid = &ecl_ishtp_guid, + .id = ecl_ishtp_id_table, .probe = ecl_ishtp_cl_probe, .remove = ecl_ishtp_cl_remove, .reset = ecl_ishtp_cl_reset, .driver.pm = &ecl_ishtp_pm_ops, }; -static const struct ishtp_device_id ecl_ishtp_id_table[] = { - { ecl_ishtp_guid }, - { } -}; -MODULE_DEVICE_TABLE(ishtp, ecl_ishtp_id_table); - static int __init ecl_ishtp_init(void) { return ishtp_cl_driver_register(&ecl_ishtp_cl_driver, THIS_MODULE); diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index aee8ff4739b146..f45f13304addd6 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -9,7 +9,7 @@ #define _INTEL_ISH_CLIENT_IF_H_ #include -#include +#include struct ishtp_cl_device; struct ishtp_device; @@ -40,7 +40,7 @@ enum cl_state { struct ishtp_cl_driver { struct device_driver driver; const char *name; - const guid_t *guid; + const struct ishtp_device_id *id; int (*probe)(struct ishtp_cl_device *dev); void (*remove)(struct ishtp_cl_device *dev); int (*reset)(struct ishtp_cl_device *dev); diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index c70abe7aaef24d..4bb71979a8fd18 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -902,9 +902,11 @@ struct dfl_device_id { /** * struct ishtp_device_id - ISHTP device identifier * @guid: GUID of the device. + * @driver_data: pointer to driver specific data */ struct ishtp_device_id { guid_t guid; + kernel_ulong_t driver_data; }; #endif /* LINUX_MOD_DEVICETABLE_H */ From e3d9234f3002bb23eb021f6d317e037b5487d4d0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Vin=C3=ADcius=20Angiolucci=20Reis?= Date: Thu, 11 Nov 2021 19:47:35 -0300 Subject: [PATCH 038/358] Revert "HID: hid-asus.c: Maps key 0x35 (display off) to KEY_SCREENLOCK" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 2ea5999d07d2a0ab6ad92ccf65524707f2c5e456. As Dmitry Torokhov pointed out, the previous code (KEY_DISPLAY_OFF) is actually correct. The real issue is that current desktop environments don't deal it properly. Mapping it to another event does not solve the issue. So I'm reverting that change, keeping key 0x35 mapped to KEY_DISPLAY_OFF Signed-off-by: Vinícius Angiolucci Reis Signed-off-by: Jiri Kosina --- drivers/hid/hid-asus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 5d57214d8dee4a..f3ecddc519ee8c 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -854,7 +854,7 @@ static int asus_input_mapping(struct hid_device *hdev, switch (usage->hid & HID_USAGE) { case 0x10: asus_map_key_clear(KEY_BRIGHTNESSDOWN); break; case 0x20: asus_map_key_clear(KEY_BRIGHTNESSUP); break; - case 0x35: asus_map_key_clear(KEY_SCREENLOCK); break; + case 0x35: asus_map_key_clear(KEY_DISPLAY_OFF); break; case 0x6c: asus_map_key_clear(KEY_SLEEP); break; case 0x7c: asus_map_key_clear(KEY_MICMUTE); break; case 0x82: asus_map_key_clear(KEY_CAMERA); break; From 9bb4e4bae5a19ca68527392e85ad5ee88fc4b786 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Wed, 10 Nov 2021 11:45:19 +0800 Subject: [PATCH 039/358] ASoC: rt9120: Update internal ocp level to the correct value Update internal ocp level to correct value. Even the wrong ocp setting can also make the sound output, but the power cannot match the IC capability. Signed-off-by: ChiYuan Huang Link: https://lore.kernel.org/r/1636515921-31694-2-git-send-email-u0084500@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt9120.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/soc/codecs/rt9120.c b/sound/soc/codecs/rt9120.c index f9574980a40724..032c520aca0c4b 100644 --- a/sound/soc/codecs/rt9120.c +++ b/sound/soc/codecs/rt9120.c @@ -149,8 +149,7 @@ static int rt9120_codec_probe(struct snd_soc_component *comp) snd_soc_component_init_regmap(comp, data->regmap); /* Internal setting */ - snd_soc_component_write(comp, RT9120_REG_INTERNAL1, 0x03); - snd_soc_component_write(comp, RT9120_REG_INTERNAL0, 0x69); + snd_soc_component_write(comp, RT9120_REG_INTERNAL0, 0x04); return 0; } From 8f1f1846d78a318c7cdb8268b47a964a3dbc0075 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Wed, 10 Nov 2021 11:45:20 +0800 Subject: [PATCH 040/358] ASoC: rt9120: Fix clock auto sync issue when fs is the multiple of 48 If fs is divided by 48, to make audio clock sync rate correct, internal sync function have be disabled. Signed-off-by: ChiYuan Huang Link: https://lore.kernel.org/r/1636515921-31694-3-git-send-email-u0084500@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt9120.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/sound/soc/codecs/rt9120.c b/sound/soc/codecs/rt9120.c index 032c520aca0c4b..981aead83814a0 100644 --- a/sound/soc/codecs/rt9120.c +++ b/sound/soc/codecs/rt9120.c @@ -26,6 +26,7 @@ #define RT9120_REG_INTERNAL0 0x65 #define RT9120_REG_INTERNAL1 0x69 #define RT9120_REG_UVPOPT 0x6C +#define RT9120_REG_DIGCFG 0xF8 #define RT9120_VID_MASK GENMASK(15, 8) #define RT9120_SWRST_MASK BIT(7) @@ -46,6 +47,7 @@ #define RT9120_CFG_WORDLEN_24 24 #define RT9120_CFG_WORDLEN_32 32 #define RT9120_DVDD_UVSEL_MASK GENMASK(5, 4) +#define RT9120_AUTOSYNC_MASK BIT(6) #define RT9120_VENDOR_ID 0x4200 #define RT9120_RESET_WAITMS 20 @@ -200,8 +202,8 @@ static int rt9120_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct snd_soc_component *comp = dai->component; - unsigned int param_width, param_slot_width; - int width; + unsigned int param_width, param_slot_width, auto_sync; + int width, fs; switch (width = params_width(param)) { case 16: @@ -239,6 +241,16 @@ static int rt9120_hw_params(struct snd_pcm_substream *substream, snd_soc_component_update_bits(comp, RT9120_REG_I2SWL, RT9120_AUDWL_MASK, param_slot_width); + + fs = width * params_channels(param); + /* If fs is divided by 48, disable auto sync */ + if (fs % 48 == 0) + auto_sync = 0; + else + auto_sync = RT9120_AUTOSYNC_MASK; + + snd_soc_component_update_bits(comp, RT9120_REG_DIGCFG, + RT9120_AUTOSYNC_MASK, auto_sync); return 0; } @@ -280,7 +292,8 @@ static const struct regmap_range rt9120_rd_yes_ranges[] = { regmap_reg_range(0x3A, 0x40), regmap_reg_range(0x65, 0x65), regmap_reg_range(0x69, 0x69), - regmap_reg_range(0x6C, 0x6C) + regmap_reg_range(0x6C, 0x6C), + regmap_reg_range(0xF8, 0xF8) }; static const struct regmap_access_table rt9120_rd_table = { @@ -298,7 +311,8 @@ static const struct regmap_range rt9120_wr_yes_ranges[] = { regmap_reg_range(0x40, 0x40), regmap_reg_range(0x65, 0x65), regmap_reg_range(0x69, 0x69), - regmap_reg_range(0x6C, 0x6C) + regmap_reg_range(0x6C, 0x6C), + regmap_reg_range(0xF8, 0xF8) }; static const struct regmap_access_table rt9120_wr_table = { @@ -369,7 +383,7 @@ static int rt9120_reg_write(void *context, unsigned int reg, unsigned int val) static const struct regmap_config rt9120_regmap_config = { .reg_bits = 8, .val_bits = 32, - .max_register = RT9120_REG_UVPOPT, + .max_register = RT9120_REG_DIGCFG, .reg_read = rt9120_reg_read, .reg_write = rt9120_reg_write, From dbe638f71eaed5c7b5fbbf03fb044e429c4a2d48 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Wed, 10 Nov 2021 11:45:21 +0800 Subject: [PATCH 041/358] ASoC: rt9120: Add the compatibility with rt9120s Use device id reg to be compatible with rt9120 and rt9120s. Signed-off-by: ChiYuan Huang Link: https://lore.kernel.org/r/1636515921-31694-4-git-send-email-u0084500@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt9120.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/sound/soc/codecs/rt9120.c b/sound/soc/codecs/rt9120.c index 981aead83814a0..7aa1772a915f32 100644 --- a/sound/soc/codecs/rt9120.c +++ b/sound/soc/codecs/rt9120.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include #include @@ -23,6 +24,7 @@ #define RT9120_REG_ERRRPT 0x10 #define RT9120_REG_MSVOL 0x20 #define RT9120_REG_SWRESET 0x40 +#define RT9120_REG_INTERCFG 0x63 #define RT9120_REG_INTERNAL0 0x65 #define RT9120_REG_INTERNAL1 0x69 #define RT9120_REG_UVPOPT 0x6C @@ -49,7 +51,8 @@ #define RT9120_DVDD_UVSEL_MASK GENMASK(5, 4) #define RT9120_AUTOSYNC_MASK BIT(6) -#define RT9120_VENDOR_ID 0x4200 +#define RT9120_VENDOR_ID 0x42 +#define RT9120S_VENDOR_ID 0x43 #define RT9120_RESET_WAITMS 20 #define RT9120_CHIPON_WAITMS 20 #define RT9120_AMPON_WAITMS 50 @@ -63,9 +66,16 @@ SNDRV_PCM_FMTBIT_S24_LE |\ SNDRV_PCM_FMTBIT_S32_LE) +enum { + CHIP_IDX_RT9120 = 0, + CHIP_IDX_RT9120S, + CHIP_IDX_MAX +}; + struct rt9120_data { struct device *dev; struct regmap *regmap; + int chip_idx; }; /* 11bit [min,max,step] = [-103.9375dB, 24dB, 0.0625dB] */ @@ -151,7 +161,12 @@ static int rt9120_codec_probe(struct snd_soc_component *comp) snd_soc_component_init_regmap(comp, data->regmap); /* Internal setting */ - snd_soc_component_write(comp, RT9120_REG_INTERNAL0, 0x04); + if (data->chip_idx == CHIP_IDX_RT9120S) { + snd_soc_component_write(comp, RT9120_REG_INTERCFG, 0xde); + snd_soc_component_write(comp, RT9120_REG_INTERNAL0, 0x66); + } else + snd_soc_component_write(comp, RT9120_REG_INTERNAL0, 0x04); + return 0; } @@ -290,6 +305,7 @@ static const struct regmap_range rt9120_rd_yes_ranges[] = { regmap_reg_range(0x20, 0x27), regmap_reg_range(0x30, 0x38), regmap_reg_range(0x3A, 0x40), + regmap_reg_range(0x63, 0x63), regmap_reg_range(0x65, 0x65), regmap_reg_range(0x69, 0x69), regmap_reg_range(0x6C, 0x6C), @@ -309,6 +325,7 @@ static const struct regmap_range rt9120_wr_yes_ranges[] = { regmap_reg_range(0x30, 0x38), regmap_reg_range(0x3A, 0x3D), regmap_reg_range(0x40, 0x40), + regmap_reg_range(0x63, 0x63), regmap_reg_range(0x65, 0x65), regmap_reg_range(0x69, 0x69), regmap_reg_range(0x6C, 0x6C), @@ -401,8 +418,16 @@ static int rt9120_check_vendor_info(struct rt9120_data *data) if (ret) return ret; - if ((devid & RT9120_VID_MASK) != RT9120_VENDOR_ID) { - dev_err(data->dev, "DEVID not correct [0x%04x]\n", devid); + devid = FIELD_GET(RT9120_VID_MASK, devid); + switch (devid) { + case RT9120_VENDOR_ID: + data->chip_idx = CHIP_IDX_RT9120; + break; + case RT9120S_VENDOR_ID: + data->chip_idx = CHIP_IDX_RT9120S; + break; + default: + dev_err(data->dev, "DEVID not correct [0x%0x]\n", devid); return -ENODEV; } From a382285b6feda8db56955e5897453405c198048d Mon Sep 17 00:00:00 2001 From: Jack Yu Date: Thu, 11 Nov 2021 17:17:05 +0800 Subject: [PATCH 042/358] ASoC: rt1011: revert 'I2S Reference' to SOC_ENUM_EXT Revert 'I2S Reference' to SOC_ENUM_EXT because the settings are specific for some platforms, the default setting for 'I2S Reference' does nothing, only some SoC platform need to configure it. Previous 'I2S Reference' in SOC_ENUM format only toggles one bit of RT1011_TDM1_SET_1 register, which isn't enough for specific platform. Signed-off-by: Jack Yu Link: https://lore.kernel.org/r/20211111091705.20879-1-jack.yu@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt1011.c | 55 ++++++++++++++++++++++++++++++++++----- sound/soc/codecs/rt1011.h | 7 +++++ 2 files changed, 56 insertions(+), 6 deletions(-) diff --git a/sound/soc/codecs/rt1011.c b/sound/soc/codecs/rt1011.c index 297af7ff824ce5..b62301a6281f91 100644 --- a/sound/soc/codecs/rt1011.c +++ b/sound/soc/codecs/rt1011.c @@ -1311,13 +1311,54 @@ static int rt1011_r0_load_info(struct snd_kcontrol *kcontrol, .put = rt1011_r0_load_mode_put \ } -static const char * const rt1011_i2s_ref_texts[] = { - "Left Channel", "Right Channel" +static const char * const rt1011_i2s_ref[] = { + "None", "Left Channel", "Right Channel" }; -static SOC_ENUM_SINGLE_DECL(rt1011_i2s_ref_enum, - RT1011_TDM1_SET_1, 7, - rt1011_i2s_ref_texts); +static SOC_ENUM_SINGLE_DECL(rt1011_i2s_ref_enum, 0, 0, + rt1011_i2s_ref); + +static int rt1011_i2s_ref_put(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *component = + snd_soc_kcontrol_component(kcontrol); + struct rt1011_priv *rt1011 = + snd_soc_component_get_drvdata(component); + + rt1011->i2s_ref = ucontrol->value.enumerated.item[0]; + switch (rt1011->i2s_ref) { + case RT1011_I2S_REF_LEFT_CH: + regmap_write(rt1011->regmap, RT1011_TDM_TOTAL_SET, 0x0240); + regmap_write(rt1011->regmap, RT1011_TDM1_SET_2, 0x8); + regmap_write(rt1011->regmap, RT1011_TDM1_SET_1, 0x1022); + regmap_write(rt1011->regmap, RT1011_ADCDAT_OUT_SOURCE, 0x4); + break; + case RT1011_I2S_REF_RIGHT_CH: + regmap_write(rt1011->regmap, RT1011_TDM_TOTAL_SET, 0x0240); + regmap_write(rt1011->regmap, RT1011_TDM1_SET_2, 0x8); + regmap_write(rt1011->regmap, RT1011_TDM1_SET_1, 0x10a2); + regmap_write(rt1011->regmap, RT1011_ADCDAT_OUT_SOURCE, 0x4); + break; + default: + dev_info(component->dev, "I2S Reference: Do nothing\n"); + } + + return 0; +} + +static int rt1011_i2s_ref_get(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *component = + snd_soc_kcontrol_component(kcontrol); + struct rt1011_priv *rt1011 = + snd_soc_component_get_drvdata(component); + + ucontrol->value.enumerated.item[0] = rt1011->i2s_ref; + + return 0; +} static const struct snd_kcontrol_new rt1011_snd_controls[] = { /* I2S Data In Selection */ @@ -1358,7 +1399,8 @@ static const struct snd_kcontrol_new rt1011_snd_controls[] = { SOC_SINGLE("R0 Temperature", RT1011_STP_INITIAL_RESISTANCE_TEMP, 2, 255, 0), /* I2S Reference */ - SOC_ENUM("I2S Reference", rt1011_i2s_ref_enum), + SOC_ENUM_EXT("I2S Reference", rt1011_i2s_ref_enum, + rt1011_i2s_ref_get, rt1011_i2s_ref_put), }; static int rt1011_is_sys_clk_from_pll(struct snd_soc_dapm_widget *source, @@ -2017,6 +2059,7 @@ static int rt1011_probe(struct snd_soc_component *component) schedule_work(&rt1011->cali_work); + rt1011->i2s_ref = 0; rt1011->bq_drc_params = devm_kcalloc(component->dev, RT1011_ADVMODE_NUM, sizeof(struct rt1011_bq_drc_params *), GFP_KERNEL); diff --git a/sound/soc/codecs/rt1011.h b/sound/soc/codecs/rt1011.h index 68fadc15fa8c1c..4d6e7492d99cd4 100644 --- a/sound/soc/codecs/rt1011.h +++ b/sound/soc/codecs/rt1011.h @@ -654,6 +654,12 @@ enum { RT1011_AIFS }; +enum { + RT1011_I2S_REF_NONE, + RT1011_I2S_REF_LEFT_CH, + RT1011_I2S_REF_RIGHT_CH, +}; + /* BiQual & DRC related settings */ #define RT1011_BQ_DRC_NUM 128 struct rt1011_bq_drc_params { @@ -692,6 +698,7 @@ struct rt1011_priv { unsigned int r0_reg, cali_done; unsigned int r0_calib, temperature_calib; int recv_spk_mode; + int i2s_ref; }; #endif /* end of _RT1011_H_ */ From a3774a2a6544a7a4a85186e768afc07044aa507f Mon Sep 17 00:00:00 2001 From: Derek Fang Date: Tue, 9 Nov 2021 17:54:49 +0800 Subject: [PATCH 043/358] ASoC: rt5682: Avoid the unexpected IRQ event during going to suspend When the system suspends, the codec driver will set SAR to power saving mode if a headset is plugged in. There is a chance to generate an unexpected IRQ, and leads to issues after resuming such as noise from OMTP type headsets. Signed-off-by: Derek Fang Link: https://lore.kernel.org/r/20211109095450.12950-1-derek.fang@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt5682.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 78b4cb5fb6c8f2..a486ac268c3370 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -48,6 +48,7 @@ static const struct reg_sequence patch_list[] = { {RT5682_SAR_IL_CMD_6, 0x0110}, {RT5682_CHARGE_PUMP_1, 0x0210}, {RT5682_HP_LOGIC_CTRL_2, 0x0007}, + {RT5682_SAR_IL_CMD_2, 0xac00}, }; void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev) @@ -2943,9 +2944,6 @@ static int rt5682_suspend(struct snd_soc_component *component) cancel_delayed_work_sync(&rt5682->jack_detect_work); cancel_delayed_work_sync(&rt5682->jd_check_work); if (rt5682->hs_jack && rt5682->jack_type == SND_JACK_HEADSET) { - snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, - RT5682_MB1_PATH_MASK | RT5682_MB2_PATH_MASK, - RT5682_CTRL_MB1_REG | RT5682_CTRL_MB2_REG); val = snd_soc_component_read(component, RT5682_CBJ_CTRL_2) & RT5682_JACK_TYPE_MASK; @@ -2967,10 +2965,15 @@ static int rt5682_suspend(struct snd_soc_component *component) /* enter SAR ADC power saving mode */ snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1, RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK | - RT5682_SAR_BUTDET_RST_MASK | RT5682_SAR_SEL_MB1_MB2_MASK, 0); + RT5682_SAR_SEL_MB1_MB2_MASK, 0); + usleep_range(5000, 6000); + snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, + RT5682_MB1_PATH_MASK | RT5682_MB2_PATH_MASK, + RT5682_CTRL_MB1_REG | RT5682_CTRL_MB2_REG); + usleep_range(10000, 12000); snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1, - RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK | RT5682_SAR_BUTDET_RST_MASK, - RT5682_SAR_BUTT_DET_EN | RT5682_SAR_BUTDET_POW_SAV | RT5682_SAR_BUTDET_RST_NORMAL); + RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK, + RT5682_SAR_BUTT_DET_EN | RT5682_SAR_BUTDET_POW_SAV); } regcache_cache_only(rt5682->regmap, true); From 2cd9b0ef82d936623d789bb3fbb6fcf52c500367 Mon Sep 17 00:00:00 2001 From: Derek Fang Date: Tue, 9 Nov 2021 17:54:50 +0800 Subject: [PATCH 044/358] ASoC: rt5682: Re-detect the combo jack after resuming Sometimes, end-users change the jack type under suspending, so it needs to re-detect the combo jack type after resuming to avoid any unexpected behaviors. Signed-off-by: Derek Fang Link: https://lore.kernel.org/r/20211109095450.12950-2-derek.fang@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt5682-i2c.c | 1 + sound/soc/codecs/rt5682.c | 23 ++++++++++++++++++++--- sound/soc/codecs/rt5682.h | 1 + 3 files changed, 22 insertions(+), 3 deletions(-) diff --git a/sound/soc/codecs/rt5682-i2c.c b/sound/soc/codecs/rt5682-i2c.c index 983347b65127b9..20e0f90ea49863 100644 --- a/sound/soc/codecs/rt5682-i2c.c +++ b/sound/soc/codecs/rt5682-i2c.c @@ -198,6 +198,7 @@ static int rt5682_i2c_probe(struct i2c_client *i2c, } mutex_init(&rt5682->calibrate_mutex); + mutex_init(&rt5682->jdet_mutex); rt5682_calibrate(rt5682); rt5682_apply_patch_list(rt5682, &i2c->dev); diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index a486ac268c3370..04cb747c2b1257 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -49,6 +49,7 @@ static const struct reg_sequence patch_list[] = { {RT5682_CHARGE_PUMP_1, 0x0210}, {RT5682_HP_LOGIC_CTRL_2, 0x0007}, {RT5682_SAR_IL_CMD_2, 0xac00}, + {RT5682_CBJ_CTRL_7, 0x0104}, }; void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev) @@ -941,6 +942,10 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) snd_soc_component_update_bits(component, RT5682_HP_CHARGE_PUMP_1, RT5682_OSW_L_MASK | RT5682_OSW_R_MASK, 0); + rt5682_enable_push_button_irq(component, false); + snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, + RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW); + usleep_range(55000, 60000); snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH); @@ -1093,6 +1098,7 @@ void rt5682_jack_detect_handler(struct work_struct *work) while (!rt5682->component->card->instantiated) usleep_range(10000, 15000); + mutex_lock(&rt5682->jdet_mutex); mutex_lock(&rt5682->calibrate_mutex); val = snd_soc_component_read(rt5682->component, RT5682_AJD1_CTRL) @@ -1166,6 +1172,7 @@ void rt5682_jack_detect_handler(struct work_struct *work) } mutex_unlock(&rt5682->calibrate_mutex); + mutex_unlock(&rt5682->jdet_mutex); } EXPORT_SYMBOL_GPL(rt5682_jack_detect_handler); @@ -1515,6 +1522,7 @@ static int rt5682_hp_event(struct snd_soc_dapm_widget *w, { struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); switch (event) { case SND_SOC_DAPM_PRE_PMU: @@ -1526,12 +1534,17 @@ static int rt5682_hp_event(struct snd_soc_dapm_widget *w, RT5682_DEPOP_1, 0x60, 0x60); snd_soc_component_update_bits(component, RT5682_DAC_ADC_DIG_VOL1, 0x00c0, 0x0080); + + mutex_lock(&rt5682->jdet_mutex); + snd_soc_component_update_bits(component, RT5682_HP_CTRL_2, RT5682_HP_C2_DAC_L_EN | RT5682_HP_C2_DAC_R_EN, RT5682_HP_C2_DAC_L_EN | RT5682_HP_C2_DAC_R_EN); usleep_range(5000, 10000); snd_soc_component_update_bits(component, RT5682_CHARGE_PUMP_1, RT5682_CP_SW_SIZE_MASK, RT5682_CP_SW_SIZE_L); + + mutex_unlock(&rt5682->jdet_mutex); break; case SND_SOC_DAPM_POST_PMD: @@ -2943,7 +2956,7 @@ static int rt5682_suspend(struct snd_soc_component *component) cancel_delayed_work_sync(&rt5682->jack_detect_work); cancel_delayed_work_sync(&rt5682->jd_check_work); - if (rt5682->hs_jack && rt5682->jack_type == SND_JACK_HEADSET) { + if (rt5682->hs_jack && (rt5682->jack_type & SND_JACK_HEADSET) == SND_JACK_HEADSET) { val = snd_soc_component_read(component, RT5682_CBJ_CTRL_2) & RT5682_JACK_TYPE_MASK; @@ -2974,6 +2987,8 @@ static int rt5682_suspend(struct snd_soc_component *component) snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1, RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK, RT5682_SAR_BUTT_DET_EN | RT5682_SAR_BUTDET_POW_SAV); + snd_soc_component_update_bits(component, RT5682_HP_CHARGE_PUMP_1, + RT5682_OSW_L_MASK | RT5682_OSW_R_MASK, 0); } regcache_cache_only(rt5682->regmap, true); @@ -2991,10 +3006,11 @@ static int rt5682_resume(struct snd_soc_component *component) regcache_cache_only(rt5682->regmap, false); regcache_sync(rt5682->regmap); - if (rt5682->hs_jack && rt5682->jack_type == SND_JACK_HEADSET) { + if (rt5682->hs_jack && (rt5682->jack_type & SND_JACK_HEADSET) == SND_JACK_HEADSET) { snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1, RT5682_SAR_BUTDET_MODE_MASK | RT5682_SAR_SEL_MB1_MB2_MASK, RT5682_SAR_BUTDET_POW_NORM | RT5682_SAR_SEL_MB1_MB2_AUTO); + usleep_range(5000, 6000); snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, RT5682_MB1_PATH_MASK | RT5682_MB2_PATH_MASK, RT5682_CTRL_MB1_FSM | RT5682_CTRL_MB2_FSM); @@ -3002,8 +3018,9 @@ static int rt5682_resume(struct snd_soc_component *component) RT5682_PWR_CBJ, RT5682_PWR_CBJ); } + rt5682->jack_type = 0; mod_delayed_work(system_power_efficient_wq, - &rt5682->jack_detect_work, msecs_to_jiffies(250)); + &rt5682->jack_detect_work, msecs_to_jiffies(0)); return 0; } diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h index d93829c35585cd..c917c76200ea2b 100644 --- a/sound/soc/codecs/rt5682.h +++ b/sound/soc/codecs/rt5682.h @@ -1463,6 +1463,7 @@ struct rt5682_priv { int jack_type; int irq_work_delay_time; + struct mutex jdet_mutex; }; extern const char *rt5682_supply_names[RT5682_NUM_SUPPLIES]; From 8c32984bc7da29828260ac514d5d4967f7e8f62d Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 11 Nov 2021 17:11:08 +0100 Subject: [PATCH 045/358] ASoC: mediatek: mt8173: Fix debugfs registration for components When registering the mt8173-afe-pcm driver, we are also adding two components: one is for the PCM DAIs and one is for the HDMI DAIs, but when debugfs is enabled, we're getting the following issue: [ 17.279176] debugfs: Directory '11220000.audio-controller' with parent 'mtk-rt5650' already present! [ 17.288345] debugfs: Directory '11220000.audio-controller' with parent 'mtk-rt5650' already present! To overcome to that without any potentially big rewrite of this driver, similarly to what was done in mt8195-afe-pcm, add a debugfs_prefix to the components before actually adding them. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20211111161108.502344-1-angelogioacchino.delregno@collabora.com Signed-off-by: Mark Brown --- sound/soc/mediatek/mt8173/mt8173-afe-pcm.c | 51 ++++++++++++++++++---- 1 file changed, 43 insertions(+), 8 deletions(-) diff --git a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c index 6350390414d4a2..31494930433f7f 100644 --- a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c +++ b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c @@ -1054,6 +1054,7 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) int irq_id; struct mtk_base_afe *afe; struct mt8173_afe_private *afe_priv; + struct snd_soc_component *comp_pcm, *comp_hdmi; ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(33)); if (ret) @@ -1142,23 +1143,55 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) if (ret) goto err_pm_disable; - ret = devm_snd_soc_register_component(&pdev->dev, - &mt8173_afe_pcm_dai_component, - mt8173_afe_pcm_dais, - ARRAY_SIZE(mt8173_afe_pcm_dais)); + comp_pcm = devm_kzalloc(&pdev->dev, sizeof(*comp_pcm), GFP_KERNEL); + if (!comp_pcm) { + ret = -ENOMEM; + goto err_pm_disable; + } + + ret = snd_soc_component_initialize(comp_pcm, + &mt8173_afe_pcm_dai_component, + &pdev->dev); if (ret) goto err_pm_disable; - ret = devm_snd_soc_register_component(&pdev->dev, - &mt8173_afe_hdmi_dai_component, - mt8173_afe_hdmi_dais, - ARRAY_SIZE(mt8173_afe_hdmi_dais)); +#ifdef CONFIG_DEBUG_FS + comp_pcm->debugfs_prefix = "pcm"; +#endif + + ret = snd_soc_add_component(comp_pcm, + mt8173_afe_pcm_dais, + ARRAY_SIZE(mt8173_afe_pcm_dais)); + if (ret) + goto err_pm_disable; + + comp_hdmi = devm_kzalloc(&pdev->dev, sizeof(*comp_hdmi), GFP_KERNEL); + if (!comp_hdmi) { + ret = -ENOMEM; + goto err_pm_disable; + } + + ret = snd_soc_component_initialize(comp_hdmi, + &mt8173_afe_hdmi_dai_component, + &pdev->dev); if (ret) goto err_pm_disable; +#ifdef CONFIG_DEBUG_FS + comp_hdmi->debugfs_prefix = "hdmi"; +#endif + + ret = snd_soc_add_component(comp_hdmi, + mt8173_afe_hdmi_dais, + ARRAY_SIZE(mt8173_afe_hdmi_dais)); + if (ret) + goto err_cleanup_components; + dev_info(&pdev->dev, "MT8173 AFE driver initialized.\n"); return 0; +err_cleanup_components: + snd_soc_unregister_component(&pdev->dev); err_pm_disable: pm_runtime_disable(&pdev->dev); return ret; @@ -1166,6 +1199,8 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) static int mt8173_afe_pcm_dev_remove(struct platform_device *pdev) { + snd_soc_unregister_component(&pdev->dev); + pm_runtime_disable(&pdev->dev); if (!pm_runtime_status_suspended(&pdev->dev)) mt8173_afe_runtime_suspend(&pdev->dev); From 1218f06cb3c6e2c51699998bc17c0d9a41ab37a6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 8 Nov 2021 12:11:14 +0100 Subject: [PATCH 046/358] ASoC: SOF: build compression interface into snd_sof.ko With CONFIG_SND_SOC_SOF_COMPRESS=m, the compression code is not built into a the main SOF driver when that is built-in: x86_64-linux-ld: sound/soc/sof/ipc.o: in function `ipc_stream_message': ipc.c:(.text+0x5a2): undefined reference to `snd_sof_compr_fragment_elapsed' x86_64-linux-ld: sound/soc/sof/topology.o: in function `sof_dai_load': topology.c:(.text+0x32d1): undefined reference to `snd_sof_compr_init_elapsed_work' x86_64-linux-ld: topology.c:(.text+0x32e1): undefined reference to `snd_sof_compr_init_elapsed_work' Make this a 'bool' symbol so it just decides whether the code gets built at all. Fixes: 858f7a5c45ca ("ASoC: SOF: Introduce fragment elapsed notification API") Signed-off-by: Arnd Bergmann Tested-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20211108111132.3800548-1-arnd@kernel.org Signed-off-by: Mark Brown --- sound/soc/sof/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/sof/Kconfig b/sound/soc/sof/Kconfig index 6bb4db87af0330..041c54639c4d9a 100644 --- a/sound/soc/sof/Kconfig +++ b/sound/soc/sof/Kconfig @@ -47,7 +47,7 @@ config SND_SOC_SOF_OF Say Y if you need this option. If unsure select "N". config SND_SOC_SOF_COMPRESS - tristate + bool select SND_SOC_COMPRESS config SND_SOC_SOF_DEBUG_PROBES From 2ce1b21cb3326e12af3c72c47e1d294b19d73947 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 8 Nov 2021 13:22:55 +0900 Subject: [PATCH 047/358] ASoC: rsnd: fixup DMAEngine API commit d5bb69dc54ec1 ("ASoC: sh: rcar: dma: : use proper DMAENGINE API for termination") updated DMAEngine API _all() to _sync(), but it should be _async(). _all() and _async() are almost same, the difference is only return error code. _sync() will call dmaengine_synchronize() and will be kernel panic. This patch is needed for v5.15 or later. [ 27.293264] BUG: scheduling while atomic: irq/130-ec70000/131/0x00000003 [ 27.300084] 2 locks held by irq/130-ec70000/131: [ 27.304743] #0: ffff0004c274d908 (&group->lock){....}-{2:2}, at: _snd_pcm_stream_lock_irqsave+0x48/0x54 [ 27.314344] #1: ffff0004c1788c60 (&priv->lock#2){....}-{2:2}, at: rsnd_soc_dai_trigger+0x70/0x7bc [ 27.323409] irq event stamp: 206 [ 27.326664] hardirqs last enabled at (205): [] _raw_spin_unlock_irq+0x50/0xa0 [ 27.335529] hardirqs last disabled at (206): [] _raw_spin_lock_irqsave+0xc4/0xd0 [ 27.344564] softirqs last enabled at (0): [] copy_process+0x644/0x1b10 [ 27.352819] softirqs last disabled at (0): [<0000000000000000>] 0x0 [ 27.359142] CPU: 0 PID: 131 Comm: irq/130-ec70000 Not tainted 5.14.0-rc1+ #918 [ 27.366429] Hardware name: Renesas H3ULCB Kingfisher board based on r8a77950 (DT) [ 27.373975] Call trace: [ 27.376442] dump_backtrace+0x0/0x1b4 [ 27.380141] show_stack+0x24/0x30 [ 27.383488] dump_stack_lvl+0x8c/0xb8 [ 27.387184] dump_stack+0x18/0x34 [ 27.390528] __schedule_bug+0x8c/0x9c [ 27.394224] __schedule+0x790/0x8dc [ 27.397746] schedule+0x7c/0x110 [ 27.401003] synchronize_irq+0x94/0xd0 [ 27.404786] rcar_dmac_device_synchronize+0x20/0x2c [ 27.409710] rsnd_dmaen_stop+0x50/0x64 [ 27.413495] rsnd_soc_dai_trigger+0x554/0x7bc [ 27.417890] snd_soc_pcm_dai_trigger+0xe8/0x264 Cc: Fixes: commit d5bb69dc54ec1 ("ASoC: sh: rcar: dma: : use proper DMAENGINE API for termination") Link: https://lore.kernel.org/r/TY2PR01MB3692889E1A7476C4322CC296D8AE9@TY2PR01MB3692.jpnprd01.prod.outlook.com Reported-by: Yoshihiro Shimoda Acked-by: Wolfram Sang Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/87mtmfz36o.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown --- sound/soc/sh/rcar/dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c index 16c6e0265749bc..03e0d4eca78156 100644 --- a/sound/soc/sh/rcar/dma.c +++ b/sound/soc/sh/rcar/dma.c @@ -102,7 +102,7 @@ static int rsnd_dmaen_stop(struct rsnd_mod *mod, struct rsnd_dmaen *dmaen = rsnd_dma_to_dmaen(dma); if (dmaen->chan) - dmaengine_terminate_sync(dmaen->chan); + dmaengine_terminate_async(dmaen->chan); return 0; } From 174a7fb3859ae75b0f0e35ef852459d8882b55b5 Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Fri, 12 Nov 2021 12:07:04 +0100 Subject: [PATCH 048/358] ALSA: hda/realtek: Add quirk for ASRock NUC Box 1100 This applies a SND_PCI_QUIRK(...) to the ASRock NUC Box 1100 series. This fixes the issue of the headphone jack not being detected unless warm rebooted from a certain other OS. When booting a certain other OS some coeff settings are changed that enable the audio jack. These settings are preserved on a warm reboot and can be easily dumped. The relevant indexes and values where gathered by naively diff-ing and reading a working and a non-working coeff dump. Signed-off-by: Werner Sembach Cc: Link: https://lore.kernel.org/r/20211112110704.1022501-1-wse@tuxedocomputers.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2f1727faec698c..701c80ed83dc8c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6521,6 +6521,27 @@ static void alc256_fixup_tongfang_reset_persistent_settings(struct hda_codec *co alc_write_coef_idx(codec, 0x45, 0x5089); } +static const struct coef_fw alc233_fixup_no_audio_jack_coefs[] = { + WRITE_COEF(0x1a, 0x9003), WRITE_COEF(0x1b, 0x0e2b), WRITE_COEF(0x37, 0xfe06), + WRITE_COEF(0x38, 0x4981), WRITE_COEF(0x45, 0xd489), WRITE_COEF(0x46, 0x0074), + WRITE_COEF(0x49, 0x0149), + {} +}; + +static void alc233_fixup_no_audio_jack(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + /* + * The audio jack input and output is not detected on the ASRock NUC Box + * 1100 series when cold booting without this fix. Warm rebooting from a + * certain other OS makes the audio functional, as COEF settings are + * preserved in this case. This fix sets these altered COEF values as + * the default. + */ + alc_process_coef_fw(codec, alc233_fixup_no_audio_jack_coefs); +} + enum { ALC269_FIXUP_GPIO2, ALC269_FIXUP_SONY_VAIO, @@ -6740,6 +6761,7 @@ enum { ALC287_FIXUP_13S_GEN2_SPEAKERS, ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS, ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE, + ALC233_FIXUP_NO_AUDIO_JACK, }; static const struct hda_fixup alc269_fixups[] = { @@ -8460,6 +8482,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, }, + [ALC233_FIXUP_NO_AUDIO_JACK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc233_fixup_no_audio_jack, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8894,6 +8920,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x511e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), + SND_PCI_QUIRK(0x1849, 0x1233, "ASRock NUC Box 1100", ALC233_FIXUP_NO_AUDIO_JACK), SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS), SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20), SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI), From bd5e2c22a9cfe7c3735d71920dc4a286348c61d2 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 12 Nov 2021 11:31:37 +0100 Subject: [PATCH 049/358] ALSA: cmipci: Drop stale variable assignment Since the recent code refactoring using devres, the variable cm in snd_cmipci_probe() is no longer referred. Fixes: 87e082ad84a7 ("ALSA: cmipci: Allocate resources with device-managed APIs") Reported-by: kernel test robot Link: https://lore.kernel.org/r/cc6383a2-cafb-ffe7-0b4f-27a310a1005c@intel.com Link: https://lore.kernel.org/r/20211112103137.9504-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/cmipci.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c index ea20236f35dbc2..9a678b5cf2855f 100644 --- a/sound/pci/cmipci.c +++ b/sound/pci/cmipci.c @@ -3218,7 +3218,6 @@ static int snd_cmipci_probe(struct pci_dev *pci, { static int dev; struct snd_card *card; - struct cmipci *cm; int err; if (dev >= SNDRV_CARDS) @@ -3229,10 +3228,9 @@ static int snd_cmipci_probe(struct pci_dev *pci, } err = snd_devm_card_new(&pci->dev, index[dev], id[dev], THIS_MODULE, - sizeof(*cm), &card); + sizeof(struct cmipci), &card); if (err < 0) return err; - cm = card->private_data; switch (pci->device) { case PCI_DEVICE_ID_CMEDIA_CM8738: From d5f0b804368951b6b4a77d2f14b5bb6a04b0e011 Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Sun, 7 Nov 2021 11:35:43 -0600 Subject: [PATCH 050/358] staging: r8188eu: Fix breakage introduced when 5G code was removed In commit 221abd4d478a ("staging: r8188eu: Remove no more necessary definitions and code"), two entries were removed from RTW_ChannelPlanMap[], but not replaced with zeros. The position within this table is important, thus the patch broke systems operating in regulatory domains osted later than entry 0x13 in the table. Unfortunately, the FCC entry comes before that point and most testers did not see this problem. Fixes: 221abd4d478a ("staging: r8188eu: Remove no more necessary definitions and code") Cc: Stable # v5.5+ Reported-and-tested-by: Zameer Manji Reported-by: kernel test robot Reviewed-by: Phillip Potter Signed-off-by: Larry Finger Link: https://lore.kernel.org/r/20211107173543.7486-1-Larry.Finger@lwfinger.net Signed-off-by: Greg Kroah-Hartman --- drivers/staging/r8188eu/core/rtw_mlme_ext.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/staging/r8188eu/core/rtw_mlme_ext.c b/drivers/staging/r8188eu/core/rtw_mlme_ext.c index 55c3d4a6faeb8f..5b60e6df5f8779 100644 --- a/drivers/staging/r8188eu/core/rtw_mlme_ext.c +++ b/drivers/staging/r8188eu/core/rtw_mlme_ext.c @@ -107,6 +107,7 @@ static struct rt_channel_plan_map RTW_ChannelPlanMap[RT_CHANNEL_DOMAIN_MAX] = { {0x01}, /* 0x10, RT_CHANNEL_DOMAIN_JAPAN */ {0x02}, /* 0x11, RT_CHANNEL_DOMAIN_FCC_NO_DFS */ {0x01}, /* 0x12, RT_CHANNEL_DOMAIN_JAPAN_NO_DFS */ + {0x00}, /* 0x13 */ {0x02}, /* 0x14, RT_CHANNEL_DOMAIN_TAIWAN_NO_DFS */ {0x00}, /* 0x15, RT_CHANNEL_DOMAIN_ETSI_NO_DFS */ {0x00}, /* 0x16, RT_CHANNEL_DOMAIN_KOREA_NO_DFS */ @@ -118,6 +119,7 @@ static struct rt_channel_plan_map RTW_ChannelPlanMap[RT_CHANNEL_DOMAIN_MAX] = { {0x00}, /* 0x1C, */ {0x00}, /* 0x1D, */ {0x00}, /* 0x1E, */ + {0x00}, /* 0x1F, */ /* 0x20 ~ 0x7F , New Define ===== */ {0x00}, /* 0x20, RT_CHANNEL_DOMAIN_WORLD_NULL */ {0x01}, /* 0x21, RT_CHANNEL_DOMAIN_ETSI1_NULL */ From 7865dd24934ad580d1bcde8f63c39f324211a23b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Noralf=20Tr=C3=B8nnes?= Date: Fri, 5 Nov 2021 21:43:58 +0100 Subject: [PATCH 051/358] staging/fbtft: Fix backlight MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit b4a1ed0cd18b ("fbdev: make FB_BACKLIGHT a tristate") forgot to update fbtft breaking its backlight support when FB_BACKLIGHT is a module. Since FB_TFT selects FB_BACKLIGHT there's no need for this conditional so just remove it and we're good. Fixes: b4a1ed0cd18b ("fbdev: make FB_BACKLIGHT a tristate") Cc: Acked-by: Sam Ravnborg Signed-off-by: Noralf Trønnes Link: https://lore.kernel.org/r/20211105204358.2991-1-noralf@tronnes.org Signed-off-by: Greg Kroah-Hartman --- drivers/staging/fbtft/fb_ssd1351.c | 4 ---- drivers/staging/fbtft/fbtft-core.c | 9 +-------- 2 files changed, 1 insertion(+), 12 deletions(-) diff --git a/drivers/staging/fbtft/fb_ssd1351.c b/drivers/staging/fbtft/fb_ssd1351.c index cf263a58a1489f..6fd549a424d53f 100644 --- a/drivers/staging/fbtft/fb_ssd1351.c +++ b/drivers/staging/fbtft/fb_ssd1351.c @@ -187,7 +187,6 @@ static struct fbtft_display display = { }, }; -#ifdef CONFIG_FB_BACKLIGHT static int update_onboard_backlight(struct backlight_device *bd) { struct fbtft_par *par = bl_get_data(bd); @@ -231,9 +230,6 @@ static void register_onboard_backlight(struct fbtft_par *par) if (!par->fbtftops.unregister_backlight) par->fbtftops.unregister_backlight = fbtft_unregister_backlight; } -#else -static void register_onboard_backlight(struct fbtft_par *par) { }; -#endif FBTFT_REGISTER_DRIVER(DRVNAME, "solomon,ssd1351", &display); diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c index ecb5f75f6dd568..f2684d2d68516c 100644 --- a/drivers/staging/fbtft/fbtft-core.c +++ b/drivers/staging/fbtft/fbtft-core.c @@ -128,7 +128,6 @@ static int fbtft_request_gpios(struct fbtft_par *par) return 0; } -#ifdef CONFIG_FB_BACKLIGHT static int fbtft_backlight_update_status(struct backlight_device *bd) { struct fbtft_par *par = bl_get_data(bd); @@ -161,6 +160,7 @@ void fbtft_unregister_backlight(struct fbtft_par *par) par->info->bl_dev = NULL; } } +EXPORT_SYMBOL(fbtft_unregister_backlight); static const struct backlight_ops fbtft_bl_ops = { .get_brightness = fbtft_backlight_get_brightness, @@ -198,12 +198,7 @@ void fbtft_register_backlight(struct fbtft_par *par) if (!par->fbtftops.unregister_backlight) par->fbtftops.unregister_backlight = fbtft_unregister_backlight; } -#else -void fbtft_register_backlight(struct fbtft_par *par) { }; -void fbtft_unregister_backlight(struct fbtft_par *par) { }; -#endif EXPORT_SYMBOL(fbtft_register_backlight); -EXPORT_SYMBOL(fbtft_unregister_backlight); static void fbtft_set_addr_win(struct fbtft_par *par, int xs, int ys, int xe, int ye) @@ -853,13 +848,11 @@ int fbtft_register_framebuffer(struct fb_info *fb_info) fb_info->fix.smem_len >> 10, text1, HZ / fb_info->fbdefio->delay, text2); -#ifdef CONFIG_FB_BACKLIGHT /* Turn on backlight if available */ if (fb_info->bl_dev) { fb_info->bl_dev->props.power = FB_BLANK_UNBLANK; fb_info->bl_dev->ops->update_status(fb_info->bl_dev); } -#endif return 0; From c15a059f85de49c542e6ec2464967dd2b2aa18f6 Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Mon, 1 Nov 2021 20:18:47 +0100 Subject: [PATCH 052/358] staging: r8188eu: Use kzalloc() with GFP_ATOMIC in atomic context Use the GFP_ATOMIC flag of kzalloc() with two memory allocation in report_del_sta_event(). This function is called while holding spinlocks, therefore it is not allowed to sleep. With the GFP_ATOMIC type flag, the allocation is high priority and must not sleep. This issue is detected by Smatch which emits the following warning: "drivers/staging/r8188eu/core/rtw_mlme_ext.c:6848 report_del_sta_event() warn: sleeping in atomic context". After the change, the post-commit hook output the following message: "CHECK: Prefer kzalloc(sizeof(*pcmd_obj)...) over kzalloc(sizeof(struct cmd_obj)...)". According to the above "CHECK", use the preferred style in the first kzalloc(). Fixes: 79f712ea994d ("staging: r8188eu: Remove wrappers for kalloc() and kzalloc()") Fixes: 15865124feed ("staging: r8188eu: introduce new core dir for RTL8188eu driver") Signed-off-by: Fabio M. De Francesco Link: https://lore.kernel.org/r/20211101191847.6749-1-fmdefrancesco@gmail.com Signed-off-by: Greg Kroah-Hartman Cc: stable --- drivers/staging/r8188eu/core/rtw_mlme_ext.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/r8188eu/core/rtw_mlme_ext.c b/drivers/staging/r8188eu/core/rtw_mlme_ext.c index 5b60e6df5f8779..b4820ad2cee735 100644 --- a/drivers/staging/r8188eu/core/rtw_mlme_ext.c +++ b/drivers/staging/r8188eu/core/rtw_mlme_ext.c @@ -6847,12 +6847,12 @@ void report_del_sta_event(struct adapter *padapter, unsigned char *MacAddr, unsi struct mlme_ext_priv *pmlmeext = &padapter->mlmeextpriv; struct cmd_priv *pcmdpriv = &padapter->cmdpriv; - pcmd_obj = kzalloc(sizeof(struct cmd_obj), GFP_KERNEL); + pcmd_obj = kzalloc(sizeof(*pcmd_obj), GFP_ATOMIC); if (!pcmd_obj) return; cmdsz = (sizeof(struct stadel_event) + sizeof(struct C2HEvent_Header)); - pevtcmd = kzalloc(cmdsz, GFP_KERNEL); + pevtcmd = kzalloc(cmdsz, GFP_ATOMIC); if (!pevtcmd) { kfree(pcmd_obj); return; From 4a293eaf92a510ff688dc7b3f0815221f99c9d1b Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Mon, 8 Nov 2021 11:55:37 +0100 Subject: [PATCH 053/358] staging: r8188eu: use GFP_ATOMIC under spinlock In function rtw_report_sec_ie() kzalloc() is called under a spinlock, so the allocation have to be atomic. Call tree: -> rtw_select_and_join_from_scanned_queue() <- takes a spinlock -> rtw_joinbss_cmd() -> rtw_restruct_sec_ie() -> rtw_report_sec_ie() Fixes: 2b42bd58b321 ("staging: r8188eu: introduce new os_dep dir for RTL8188eu driver") Cc: stable Signed-off-by: Michael Straube Link: https://lore.kernel.org/r/20211108105537.31655-1-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/r8188eu/os_dep/mlme_linux.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/r8188eu/os_dep/mlme_linux.c b/drivers/staging/r8188eu/os_dep/mlme_linux.c index a9b6ffdbf31ab9..f7ce724ebf87ed 100644 --- a/drivers/staging/r8188eu/os_dep/mlme_linux.c +++ b/drivers/staging/r8188eu/os_dep/mlme_linux.c @@ -112,7 +112,7 @@ void rtw_report_sec_ie(struct adapter *adapter, u8 authmode, u8 *sec_ie) buff = NULL; if (authmode == _WPA_IE_ID_) { - buff = kzalloc(IW_CUSTOM_MAX, GFP_KERNEL); + buff = kzalloc(IW_CUSTOM_MAX, GFP_ATOMIC); if (!buff) return; p = buff; From be4ea8f383551b9dae11b8dfff1f38b3b5436e9a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 9 Nov 2021 14:49:36 +0300 Subject: [PATCH 054/358] staging: r8188eu: fix a memory leak in rtw_wx_read32() Free "ptmp" before returning -EINVAL. Fixes: 2b42bd58b321 ("staging: r8188eu: introduce new os_dep dir for RTL8188eu driver") Cc: stable Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20211109114935.GC16587@kili Signed-off-by: Greg Kroah-Hartman --- drivers/staging/r8188eu/os_dep/ioctl_linux.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/staging/r8188eu/os_dep/ioctl_linux.c b/drivers/staging/r8188eu/os_dep/ioctl_linux.c index 52d42e57644332..9404355726d0ae 100644 --- a/drivers/staging/r8188eu/os_dep/ioctl_linux.c +++ b/drivers/staging/r8188eu/os_dep/ioctl_linux.c @@ -1980,6 +1980,7 @@ static int rtw_wx_read32(struct net_device *dev, u32 data32; u32 bytes; u8 *ptmp; + int ret; padapter = (struct adapter *)rtw_netdev_priv(dev); p = &wrqu->data; @@ -2007,12 +2008,17 @@ static int rtw_wx_read32(struct net_device *dev, break; default: DBG_88E(KERN_INFO "%s: usage> read [bytes],[address(hex)]\n", __func__); - return -EINVAL; + ret = -EINVAL; + goto err_free_ptmp; } DBG_88E(KERN_INFO "%s: addr = 0x%08X data =%s\n", __func__, addr, extra); kfree(ptmp); return 0; + +err_free_ptmp: + kfree(ptmp); + return ret; } static int rtw_wx_write32(struct net_device *dev, From 47ac6f567c28581f7729bd1f168639f8f066a2eb Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 9 Nov 2021 10:14:01 -0600 Subject: [PATCH 055/358] staging: Remove Netlogic XLP network driver The Netlogic XLP platform was removed in commit 95b8a5e0111a ("MIPS: Remove NETLOGIC support"), so this driver is now dead. Cc: Greg Kroah-Hartman Cc: Ganesan Ramalingam Cc: Jayachandran Chandrashekaran Nair Cc: linux-staging@lists.linux.dev Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20211109161401.2204280-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/staging/Kconfig | 2 - drivers/staging/Makefile | 1 - drivers/staging/netlogic/Kconfig | 9 - drivers/staging/netlogic/Makefile | 2 - drivers/staging/netlogic/TODO | 11 - drivers/staging/netlogic/platform_net.c | 219 ----- drivers/staging/netlogic/platform_net.h | 21 - drivers/staging/netlogic/xlr_net.c | 1080 ----------------------- drivers/staging/netlogic/xlr_net.h | 1079 ---------------------- 9 files changed, 2424 deletions(-) delete mode 100644 drivers/staging/netlogic/Kconfig delete mode 100644 drivers/staging/netlogic/Makefile delete mode 100644 drivers/staging/netlogic/TODO delete mode 100644 drivers/staging/netlogic/platform_net.c delete mode 100644 drivers/staging/netlogic/platform_net.h delete mode 100644 drivers/staging/netlogic/xlr_net.c delete mode 100644 drivers/staging/netlogic/xlr_net.h diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index 59af251e75769c..7fec8694613126 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -66,8 +66,6 @@ source "drivers/staging/gdm724x/Kconfig" source "drivers/staging/fwserial/Kconfig" -source "drivers/staging/netlogic/Kconfig" - source "drivers/staging/gs_fpgaboot/Kconfig" source "drivers/staging/unisys/Kconfig" diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile index 76f413470bc8fe..e66e19c454257a 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -10,7 +10,6 @@ obj-$(CONFIG_RTL8723BS) += rtl8723bs/ obj-$(CONFIG_R8712U) += rtl8712/ obj-$(CONFIG_R8188EU) += r8188eu/ obj-$(CONFIG_RTS5208) += rts5208/ -obj-$(CONFIG_NETLOGIC_XLR_NET) += netlogic/ obj-$(CONFIG_OCTEON_ETHERNET) += octeon/ obj-$(CONFIG_OCTEON_USB) += octeon-usb/ obj-$(CONFIG_VT6655) += vt6655/ diff --git a/drivers/staging/netlogic/Kconfig b/drivers/staging/netlogic/Kconfig deleted file mode 100644 index e1712606ee3ce0..00000000000000 --- a/drivers/staging/netlogic/Kconfig +++ /dev/null @@ -1,9 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -config NETLOGIC_XLR_NET - tristate "Netlogic XLR/XLS network device" - depends on CPU_XLR - depends on NETDEVICES - select PHYLIB - help - This driver support Netlogic XLR/XLS on chip gigabit - Ethernet. diff --git a/drivers/staging/netlogic/Makefile b/drivers/staging/netlogic/Makefile deleted file mode 100644 index 7e2902af26a38b..00000000000000 --- a/drivers/staging/netlogic/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_NETLOGIC_XLR_NET) += xlr_net.o platform_net.o diff --git a/drivers/staging/netlogic/TODO b/drivers/staging/netlogic/TODO deleted file mode 100644 index 20e22ecb9903b0..00000000000000 --- a/drivers/staging/netlogic/TODO +++ /dev/null @@ -1,11 +0,0 @@ -* Implementing 64bit stat counter in software -* All memory allocation should be changed to DMA allocations -* Changing comments into linux standard format - -Please send patches -To: -Ganesan Ramalingam -Greg Kroah-Hartman -Cc: -Jayachandran Chandrashekaran Nair - diff --git a/drivers/staging/netlogic/platform_net.c b/drivers/staging/netlogic/platform_net.c deleted file mode 100644 index 8be9d0b0c22c47..00000000000000 --- a/drivers/staging/netlogic/platform_net.c +++ /dev/null @@ -1,219 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) -/* - * Copyright (c) 2003-2012 Broadcom Corporation - * All Rights Reserved - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include - -#include "platform_net.h" - -/* Linux Net */ -#define MAX_NUM_GMAC 8 -#define MAX_NUM_XLS_GMAC 8 -#define MAX_NUM_XLR_GMAC 4 - -static u32 xlr_gmac_offsets[] = { - NETLOGIC_IO_GMAC_0_OFFSET, NETLOGIC_IO_GMAC_1_OFFSET, - NETLOGIC_IO_GMAC_2_OFFSET, NETLOGIC_IO_GMAC_3_OFFSET, - NETLOGIC_IO_GMAC_4_OFFSET, NETLOGIC_IO_GMAC_5_OFFSET, - NETLOGIC_IO_GMAC_6_OFFSET, NETLOGIC_IO_GMAC_7_OFFSET -}; - -static u32 xlr_gmac_irqs[] = { PIC_GMAC_0_IRQ, PIC_GMAC_1_IRQ, - PIC_GMAC_2_IRQ, PIC_GMAC_3_IRQ, - PIC_GMAC_4_IRQ, PIC_GMAC_5_IRQ, - PIC_GMAC_6_IRQ, PIC_GMAC_7_IRQ -}; - -static struct resource xlr_net0_res[8]; -static struct resource xlr_net1_res[8]; -static u32 __iomem *gmac4_addr; -static u32 __iomem *gpio_addr; - -static void xlr_resource_init(struct resource *res, int offset, int irq) -{ - res->name = "gmac"; - - res->start = CPHYSADDR(nlm_mmio_base(offset)); - res->end = res->start + 0xfff; - res->flags = IORESOURCE_MEM; - - res++; - res->name = "gmac"; - res->start = irq; - res->end = irq; - res->flags = IORESOURCE_IRQ; -} - -static struct platform_device *gmac_controller2_init(void *gmac0_addr) -{ - int mac; - static struct xlr_net_data ndata1 = { - .phy_interface = PHY_INTERFACE_MODE_SGMII, - .rfr_station = FMN_STNID_GMAC1_FR_0, - .bucket_size = xlr_board_fmn_config.bucket_size, - .gmac_fmn_info = &xlr_board_fmn_config.gmac[1], - }; - - static struct platform_device xlr_net_dev1 = { - .name = "xlr-net", - .id = 1, - .dev.platform_data = &ndata1, - }; - - gmac4_addr = - ioremap(CPHYSADDR(nlm_mmio_base(NETLOGIC_IO_GMAC_4_OFFSET)), - 0xfff); - ndata1.serdes_addr = gmac4_addr; - ndata1.pcs_addr = gmac4_addr; - ndata1.mii_addr = gmac0_addr; - ndata1.gpio_addr = gpio_addr; - ndata1.cpu_mask = nlm_current_node()->coremask; - - xlr_net_dev1.resource = xlr_net1_res; - - for (mac = 0; mac < 4; mac++) { - ndata1.tx_stnid[mac] = FMN_STNID_GMAC1_TX0 + mac; - ndata1.phy_addr[mac] = mac + 4 + 0x10; - - xlr_resource_init(&xlr_net1_res[mac * 2], - xlr_gmac_offsets[mac + 4], - xlr_gmac_irqs[mac + 4]); - } - xlr_net_dev1.num_resources = 8; - - return &xlr_net_dev1; -} - -static void xls_gmac_init(void) -{ - int mac; - struct platform_device *xlr_net_dev1; - void __iomem *gmac0_addr = - ioremap(CPHYSADDR(nlm_mmio_base(NETLOGIC_IO_GMAC_0_OFFSET)), - 0xfff); - - static struct xlr_net_data ndata0 = { - .rfr_station = FMN_STNID_GMACRFR_0, - .bucket_size = xlr_board_fmn_config.bucket_size, - .gmac_fmn_info = &xlr_board_fmn_config.gmac[0], - }; - - static struct platform_device xlr_net_dev0 = { - .name = "xlr-net", - .id = 0, - }; - xlr_net_dev0.dev.platform_data = &ndata0; - ndata0.serdes_addr = gmac0_addr; - ndata0.pcs_addr = gmac0_addr; - ndata0.mii_addr = gmac0_addr; - - /* Passing GPIO base for serdes init. Only needed on sgmii ports */ - gpio_addr = - ioremap(CPHYSADDR(nlm_mmio_base(NETLOGIC_IO_GPIO_OFFSET)), - 0xfff); - ndata0.gpio_addr = gpio_addr; - ndata0.cpu_mask = nlm_current_node()->coremask; - - xlr_net_dev0.resource = xlr_net0_res; - - switch (nlm_prom_info.board_major_version) { - case 12: - /* first block RGMII or XAUI, use RGMII */ - ndata0.phy_interface = PHY_INTERFACE_MODE_RGMII; - ndata0.tx_stnid[0] = FMN_STNID_GMAC0_TX0; - ndata0.phy_addr[0] = 0; - - xlr_net_dev0.num_resources = 2; - - xlr_resource_init(&xlr_net0_res[0], xlr_gmac_offsets[0], - xlr_gmac_irqs[0]); - platform_device_register(&xlr_net_dev0); - - /* second block is XAUI, not supported yet */ - break; - default: - /* default XLS config, all ports SGMII */ - ndata0.phy_interface = PHY_INTERFACE_MODE_SGMII; - for (mac = 0; mac < 4; mac++) { - ndata0.tx_stnid[mac] = FMN_STNID_GMAC0_TX0 + mac; - ndata0.phy_addr[mac] = mac + 0x10; - - xlr_resource_init(&xlr_net0_res[mac * 2], - xlr_gmac_offsets[mac], - xlr_gmac_irqs[mac]); - } - xlr_net_dev0.num_resources = 8; - platform_device_register(&xlr_net_dev0); - - xlr_net_dev1 = gmac_controller2_init(gmac0_addr); - platform_device_register(xlr_net_dev1); - } -} - -static void xlr_gmac_init(void) -{ - int mac; - - /* assume all GMACs for now */ - static struct xlr_net_data ndata0 = { - .phy_interface = PHY_INTERFACE_MODE_RGMII, - .serdes_addr = NULL, - .pcs_addr = NULL, - .rfr_station = FMN_STNID_GMACRFR_0, - .bucket_size = xlr_board_fmn_config.bucket_size, - .gmac_fmn_info = &xlr_board_fmn_config.gmac[0], - .gpio_addr = NULL, - }; - - static struct platform_device xlr_net_dev0 = { - .name = "xlr-net", - .id = 0, - .dev.platform_data = &ndata0, - }; - ndata0.mii_addr = - ioremap(CPHYSADDR(nlm_mmio_base(NETLOGIC_IO_GMAC_0_OFFSET)), - 0xfff); - - ndata0.cpu_mask = nlm_current_node()->coremask; - - for (mac = 0; mac < MAX_NUM_XLR_GMAC; mac++) { - ndata0.tx_stnid[mac] = FMN_STNID_GMAC0_TX0 + mac; - ndata0.phy_addr[mac] = mac; - xlr_resource_init(&xlr_net0_res[mac * 2], xlr_gmac_offsets[mac], - xlr_gmac_irqs[mac]); - } - xlr_net_dev0.num_resources = 8; - xlr_net_dev0.resource = xlr_net0_res; - - platform_device_register(&xlr_net_dev0); -} - -static int __init xlr_net_init(void) -{ - if (nlm_chip_is_xls()) - xls_gmac_init(); - else - xlr_gmac_init(); - - return 0; -} - -arch_initcall(xlr_net_init); diff --git a/drivers/staging/netlogic/platform_net.h b/drivers/staging/netlogic/platform_net.h deleted file mode 100644 index c8d4c13424c6ba..00000000000000 --- a/drivers/staging/netlogic/platform_net.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */ -/* - * Copyright (c) 2003-2012 Broadcom Corporation - * All Rights Reserved - */ - -#define PORTS_PER_CONTROLLER 4 - -struct xlr_net_data { - int cpu_mask; - u32 __iomem *mii_addr; - u32 __iomem *serdes_addr; - u32 __iomem *pcs_addr; - u32 __iomem *gpio_addr; - int phy_interface; - int rfr_station; - int tx_stnid[PORTS_PER_CONTROLLER]; - int *bucket_size; - int phy_addr[PORTS_PER_CONTROLLER]; - struct xlr_fmn_info *gmac_fmn_info; -}; diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c deleted file mode 100644 index 69ea61faf8fa0c..00000000000000 --- a/drivers/staging/netlogic/xlr_net.c +++ /dev/null @@ -1,1080 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) -/* - * Copyright (c) 2003-2012 Broadcom Corporation - * All Rights Reserved - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -/* - * fmn.h - For FMN credit configuration and registering fmn_handler. - * FMN is communication mechanism that allows processing agents within - * XLR/XLS to communicate each other. - */ -#include - -#include "platform_net.h" -#include "xlr_net.h" - -/* - * The readl/writel implementation byteswaps on XLR/XLS, so - * we need to use __raw_ IO to read the NAE registers - * because they are in the big-endian MMIO area on the SoC. - */ -static inline void xlr_nae_wreg(u32 __iomem *base, unsigned int reg, u32 val) -{ - __raw_writel(val, base + reg); -} - -static inline u32 xlr_nae_rdreg(u32 __iomem *base, unsigned int reg) -{ - return __raw_readl(base + reg); -} - -static inline void xlr_reg_update(u32 *base_addr, u32 off, u32 val, u32 mask) -{ - u32 tmp; - - tmp = xlr_nae_rdreg(base_addr, off); - xlr_nae_wreg(base_addr, off, (tmp & ~mask) | (val & mask)); -} - -#define MAC_SKB_BACK_PTR_SIZE SMP_CACHE_BYTES - -static int send_to_rfr_fifo(struct xlr_net_priv *priv, void *addr) -{ - struct nlm_fmn_msg msg; - int ret = 0, num_try = 0, stnid; - unsigned long paddr, mflags; - - paddr = virt_to_bus(addr); - msg.msg0 = (u64)paddr & 0xffffffffe0ULL; - msg.msg1 = 0; - msg.msg2 = 0; - msg.msg3 = 0; - stnid = priv->nd->rfr_station; - do { - mflags = nlm_cop2_enable_irqsave(); - ret = nlm_fmn_send(1, 0, stnid, &msg); - nlm_cop2_disable_irqrestore(mflags); - if (ret == 0) - return 0; - } while (++num_try < 10000); - - netdev_err(priv->ndev, "Send to RFR failed in RX path\n"); - return ret; -} - -static inline unsigned char *xlr_alloc_skb(void) -{ - struct sk_buff *skb; - int buf_len = sizeof(struct sk_buff *); - unsigned char *skb_data; - - /* skb->data is cache aligned */ - skb = alloc_skb(XLR_RX_BUF_SIZE, GFP_ATOMIC); - if (!skb) - return NULL; - skb_data = skb->data; - skb_reserve(skb, MAC_SKB_BACK_PTR_SIZE); - memcpy(skb_data, &skb, buf_len); - - return skb->data; -} - -static void xlr_net_fmn_handler(int bkt, int src_stnid, int size, int code, - struct nlm_fmn_msg *msg, void *arg) -{ - struct sk_buff *skb; - void *skb_data = NULL; - struct net_device *ndev; - struct xlr_net_priv *priv; - u32 port, length; - unsigned char *addr; - struct xlr_adapter *adapter = arg; - - length = (msg->msg0 >> 40) & 0x3fff; - if (length == 0) { - addr = bus_to_virt(msg->msg0 & 0xffffffffffULL); - addr = addr - MAC_SKB_BACK_PTR_SIZE; - skb = (struct sk_buff *)(*(unsigned long *)addr); - dev_kfree_skb_any((struct sk_buff *)addr); - } else { - addr = (unsigned char *) - bus_to_virt(msg->msg0 & 0xffffffffe0ULL); - length = length - BYTE_OFFSET - MAC_CRC_LEN; - port = ((int)msg->msg0) & 0x0f; - addr = addr - MAC_SKB_BACK_PTR_SIZE; - skb = (struct sk_buff *)(*(unsigned long *)addr); - skb->dev = adapter->netdev[port]; - if (!skb->dev) - return; - ndev = skb->dev; - priv = netdev_priv(ndev); - - /* 16 byte IP header align */ - skb_reserve(skb, BYTE_OFFSET); - skb_put(skb, length); - skb->protocol = eth_type_trans(skb, skb->dev); - netif_rx(skb); - /* Fill rx ring */ - skb_data = xlr_alloc_skb(); - if (skb_data) - send_to_rfr_fifo(priv, skb_data); - } -} - -static struct phy_device *xlr_get_phydev(struct xlr_net_priv *priv) -{ - return mdiobus_get_phy(priv->mii_bus, priv->phy_addr); -} - -/* - * Ethtool operation - */ -static int xlr_get_link_ksettings(struct net_device *ndev, - struct ethtool_link_ksettings *ecmd) -{ - struct xlr_net_priv *priv = netdev_priv(ndev); - struct phy_device *phydev = xlr_get_phydev(priv); - - if (!phydev) - return -ENODEV; - - phy_ethtool_ksettings_get(phydev, ecmd); - - return 0; -} - -static int xlr_set_link_ksettings(struct net_device *ndev, - const struct ethtool_link_ksettings *ecmd) -{ - struct xlr_net_priv *priv = netdev_priv(ndev); - struct phy_device *phydev = xlr_get_phydev(priv); - - if (!phydev) - return -ENODEV; - return phy_ethtool_ksettings_set(phydev, ecmd); -} - -static const struct ethtool_ops xlr_ethtool_ops = { - .get_link_ksettings = xlr_get_link_ksettings, - .set_link_ksettings = xlr_set_link_ksettings, -}; - -/* - * Net operations - */ -static int xlr_net_fill_rx_ring(struct net_device *ndev) -{ - void *skb_data; - struct xlr_net_priv *priv = netdev_priv(ndev); - int i; - - for (i = 0; i < MAX_FRIN_SPILL / 4; i++) { - skb_data = xlr_alloc_skb(); - if (!skb_data) - return -ENOMEM; - send_to_rfr_fifo(priv, skb_data); - } - netdev_info(ndev, "Rx ring setup done\n"); - return 0; -} - -static int xlr_net_open(struct net_device *ndev) -{ - u32 err; - struct xlr_net_priv *priv = netdev_priv(ndev); - struct phy_device *phydev = xlr_get_phydev(priv); - - /* schedule a link state check */ - phy_start(phydev); - - err = phy_start_aneg(phydev); - if (err) { - pr_err("Autoneg failed\n"); - return err; - } - /* Setup the speed from PHY to internal reg*/ - xlr_set_gmac_speed(priv); - - netif_tx_start_all_queues(ndev); - - return 0; -} - -static int xlr_net_stop(struct net_device *ndev) -{ - struct xlr_net_priv *priv = netdev_priv(ndev); - struct phy_device *phydev = xlr_get_phydev(priv); - - phy_stop(phydev); - netif_tx_stop_all_queues(ndev); - return 0; -} - -static void xlr_make_tx_desc(struct nlm_fmn_msg *msg, unsigned long addr, - struct sk_buff *skb) -{ - unsigned long physkb = virt_to_phys(skb); - int cpu_core = nlm_core_id(); - int fr_stn_id = cpu_core * 8 + XLR_FB_STN; /* FB to 6th bucket */ - - msg->msg0 = (((u64)1 << 63) | /* End of packet descriptor */ - ((u64)127 << 54) | /* No Free back */ - (u64)skb->len << 40 | /* Length of data */ - ((u64)addr)); - msg->msg1 = (((u64)1 << 63) | - ((u64)fr_stn_id << 54) | /* Free back id */ - (u64)0 << 40 | /* Set len to 0 */ - ((u64)physkb & 0xffffffff)); /* 32bit address */ - msg->msg2 = 0; - msg->msg3 = 0; -} - -static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb, - struct net_device *ndev) -{ - struct nlm_fmn_msg msg; - struct xlr_net_priv *priv = netdev_priv(ndev); - int ret; - u32 flags; - - xlr_make_tx_desc(&msg, virt_to_phys(skb->data), skb); - flags = nlm_cop2_enable_irqsave(); - ret = nlm_fmn_send(2, 0, priv->tx_stnid, &msg); - nlm_cop2_disable_irqrestore(flags); - if (ret) - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; -} - -static void xlr_hw_set_mac_addr(struct net_device *ndev) -{ - struct xlr_net_priv *priv = netdev_priv(ndev); - - /* set mac station address */ - xlr_nae_wreg(priv->base_addr, R_MAC_ADDR0, - ((ndev->dev_addr[5] << 24) | (ndev->dev_addr[4] << 16) | - (ndev->dev_addr[3] << 8) | (ndev->dev_addr[2]))); - xlr_nae_wreg(priv->base_addr, R_MAC_ADDR0 + 1, - ((ndev->dev_addr[1] << 24) | (ndev->dev_addr[0] << 16))); - - xlr_nae_wreg(priv->base_addr, R_MAC_ADDR_MASK2, 0xffffffff); - xlr_nae_wreg(priv->base_addr, R_MAC_ADDR_MASK2 + 1, 0xffffffff); - xlr_nae_wreg(priv->base_addr, R_MAC_ADDR_MASK3, 0xffffffff); - xlr_nae_wreg(priv->base_addr, R_MAC_ADDR_MASK3 + 1, 0xffffffff); - - xlr_nae_wreg(priv->base_addr, R_MAC_FILTER_CONFIG, - (1 << O_MAC_FILTER_CONFIG__BROADCAST_EN) | - (1 << O_MAC_FILTER_CONFIG__ALL_MCAST_EN) | - (1 << O_MAC_FILTER_CONFIG__MAC_ADDR0_VALID)); - - if (priv->nd->phy_interface == PHY_INTERFACE_MODE_RGMII || - priv->nd->phy_interface == PHY_INTERFACE_MODE_SGMII) - xlr_reg_update(priv->base_addr, R_IPG_IFG, MAC_B2B_IPG, 0x7f); -} - -static int xlr_net_set_mac_addr(struct net_device *ndev, void *data) -{ - int err; - - err = eth_mac_addr(ndev, data); - if (err) - return err; - xlr_hw_set_mac_addr(ndev); - return 0; -} - -static void xlr_set_rx_mode(struct net_device *ndev) -{ - struct xlr_net_priv *priv = netdev_priv(ndev); - u32 regval; - - regval = xlr_nae_rdreg(priv->base_addr, R_MAC_FILTER_CONFIG); - - if (ndev->flags & IFF_PROMISC) { - regval |= (1 << O_MAC_FILTER_CONFIG__BROADCAST_EN) | - (1 << O_MAC_FILTER_CONFIG__PAUSE_FRAME_EN) | - (1 << O_MAC_FILTER_CONFIG__ALL_MCAST_EN) | - (1 << O_MAC_FILTER_CONFIG__ALL_UCAST_EN); - } else { - regval &= ~((1 << O_MAC_FILTER_CONFIG__PAUSE_FRAME_EN) | - (1 << O_MAC_FILTER_CONFIG__ALL_UCAST_EN)); - } - - xlr_nae_wreg(priv->base_addr, R_MAC_FILTER_CONFIG, regval); -} - -static void xlr_stats(struct net_device *ndev, struct rtnl_link_stats64 *stats) -{ - struct xlr_net_priv *priv = netdev_priv(ndev); - - stats->rx_packets = xlr_nae_rdreg(priv->base_addr, RX_PACKET_COUNTER); - stats->tx_packets = xlr_nae_rdreg(priv->base_addr, TX_PACKET_COUNTER); - stats->rx_bytes = xlr_nae_rdreg(priv->base_addr, RX_BYTE_COUNTER); - stats->tx_bytes = xlr_nae_rdreg(priv->base_addr, TX_BYTE_COUNTER); - stats->tx_errors = xlr_nae_rdreg(priv->base_addr, TX_FCS_ERROR_COUNTER); - stats->rx_dropped = xlr_nae_rdreg(priv->base_addr, - RX_DROP_PACKET_COUNTER); - stats->tx_dropped = xlr_nae_rdreg(priv->base_addr, - TX_DROP_FRAME_COUNTER); - - stats->multicast = xlr_nae_rdreg(priv->base_addr, - RX_MULTICAST_PACKET_COUNTER); - stats->collisions = xlr_nae_rdreg(priv->base_addr, - TX_TOTAL_COLLISION_COUNTER); - - stats->rx_length_errors = xlr_nae_rdreg(priv->base_addr, - RX_FRAME_LENGTH_ERROR_COUNTER); - stats->rx_over_errors = xlr_nae_rdreg(priv->base_addr, - RX_DROP_PACKET_COUNTER); - stats->rx_crc_errors = xlr_nae_rdreg(priv->base_addr, - RX_FCS_ERROR_COUNTER); - stats->rx_frame_errors = xlr_nae_rdreg(priv->base_addr, - RX_ALIGNMENT_ERROR_COUNTER); - - stats->rx_fifo_errors = xlr_nae_rdreg(priv->base_addr, - RX_DROP_PACKET_COUNTER); - stats->rx_missed_errors = xlr_nae_rdreg(priv->base_addr, - RX_CARRIER_SENSE_ERROR_COUNTER); - - stats->rx_errors = (stats->rx_over_errors + stats->rx_crc_errors + - stats->rx_frame_errors + stats->rx_fifo_errors + - stats->rx_missed_errors); - - stats->tx_aborted_errors = xlr_nae_rdreg(priv->base_addr, - TX_EXCESSIVE_COLLISION_PACKET_COUNTER); - stats->tx_carrier_errors = xlr_nae_rdreg(priv->base_addr, - TX_DROP_FRAME_COUNTER); - stats->tx_fifo_errors = xlr_nae_rdreg(priv->base_addr, - TX_DROP_FRAME_COUNTER); -} - -static const struct net_device_ops xlr_netdev_ops = { - .ndo_open = xlr_net_open, - .ndo_stop = xlr_net_stop, - .ndo_start_xmit = xlr_net_start_xmit, - .ndo_select_queue = dev_pick_tx_cpu_id, - .ndo_set_mac_address = xlr_net_set_mac_addr, - .ndo_set_rx_mode = xlr_set_rx_mode, - .ndo_get_stats64 = xlr_stats, -}; - -/* - * Gmac init - */ -static void *xlr_config_spill(struct xlr_net_priv *priv, int reg_start_0, - int reg_start_1, int reg_size, int size) -{ - void *spill; - u32 *base; - unsigned long phys_addr; - u32 spill_size; - - base = priv->base_addr; - spill_size = size; - spill = kmalloc(spill_size + SMP_CACHE_BYTES, GFP_KERNEL); - if (!spill) - return ZERO_SIZE_PTR; - - spill = PTR_ALIGN(spill, SMP_CACHE_BYTES); - phys_addr = virt_to_phys(spill); - dev_dbg(&priv->ndev->dev, "Allocated spill %d bytes at %lx\n", - size, phys_addr); - xlr_nae_wreg(base, reg_start_0, (phys_addr >> 5) & 0xffffffff); - xlr_nae_wreg(base, reg_start_1, ((u64)phys_addr >> 37) & 0x07); - xlr_nae_wreg(base, reg_size, spill_size); - - return spill; -} - -/* - * Configure the 6 FIFO's that are used by the network accelarator to - * communicate with the rest of the XLx device. 4 of the FIFO's are for - * packets from NA --> cpu (called Class FIFO's) and 2 are for feeding - * the NA with free descriptors. - */ -static void xlr_config_fifo_spill_area(struct xlr_net_priv *priv) -{ - priv->frin_spill = xlr_config_spill(priv, - R_REG_FRIN_SPILL_MEM_START_0, - R_REG_FRIN_SPILL_MEM_START_1, - R_REG_FRIN_SPILL_MEM_SIZE, - MAX_FRIN_SPILL * sizeof(u64)); - priv->frout_spill = xlr_config_spill(priv, - R_FROUT_SPILL_MEM_START_0, - R_FROUT_SPILL_MEM_START_1, - R_FROUT_SPILL_MEM_SIZE, - MAX_FROUT_SPILL * sizeof(u64)); - priv->class_0_spill = xlr_config_spill(priv, - R_CLASS0_SPILL_MEM_START_0, - R_CLASS0_SPILL_MEM_START_1, - R_CLASS0_SPILL_MEM_SIZE, - MAX_CLASS_0_SPILL * sizeof(u64)); - priv->class_1_spill = xlr_config_spill(priv, - R_CLASS1_SPILL_MEM_START_0, - R_CLASS1_SPILL_MEM_START_1, - R_CLASS1_SPILL_MEM_SIZE, - MAX_CLASS_1_SPILL * sizeof(u64)); - priv->class_2_spill = xlr_config_spill(priv, - R_CLASS2_SPILL_MEM_START_0, - R_CLASS2_SPILL_MEM_START_1, - R_CLASS2_SPILL_MEM_SIZE, - MAX_CLASS_2_SPILL * sizeof(u64)); - priv->class_3_spill = xlr_config_spill(priv, - R_CLASS3_SPILL_MEM_START_0, - R_CLASS3_SPILL_MEM_START_1, - R_CLASS3_SPILL_MEM_SIZE, - MAX_CLASS_3_SPILL * sizeof(u64)); -} - -/* - * Configure PDE to Round-Robin distribution of packets to the - * available cpu - */ -static void xlr_config_pde(struct xlr_net_priv *priv) -{ - int i = 0; - u64 bkt_map = 0; - - /* Each core has 8 buckets(station) */ - for (i = 0; i < hweight32(priv->nd->cpu_mask); i++) - bkt_map |= (0xff << (i * 8)); - - xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_0, (bkt_map & 0xffffffff)); - xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_0 + 1, - ((bkt_map >> 32) & 0xffffffff)); - - xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_1, (bkt_map & 0xffffffff)); - xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_1 + 1, - ((bkt_map >> 32) & 0xffffffff)); - - xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_2, (bkt_map & 0xffffffff)); - xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_2 + 1, - ((bkt_map >> 32) & 0xffffffff)); - - xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_3, (bkt_map & 0xffffffff)); - xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_3 + 1, - ((bkt_map >> 32) & 0xffffffff)); -} - -/* - * Setup the Message ring credits, bucket size and other - * common configuration - */ -static int xlr_config_common(struct xlr_net_priv *priv) -{ - struct xlr_fmn_info *gmac = priv->nd->gmac_fmn_info; - int start_stn_id = gmac->start_stn_id; - int end_stn_id = gmac->end_stn_id; - int *bucket_size = priv->nd->bucket_size; - int i, j, err; - - /* Setting non-core MsgBktSize(0x321 - 0x325) */ - for (i = start_stn_id; i <= end_stn_id; i++) { - xlr_nae_wreg(priv->base_addr, - R_GMAC_RFR0_BUCKET_SIZE + i - start_stn_id, - bucket_size[i]); - } - - /* - * Setting non-core Credit counter register - * Distributing Gmac's credit to CPU's - */ - for (i = 0; i < 8; i++) { - for (j = 0; j < 8; j++) - xlr_nae_wreg(priv->base_addr, - (R_CC_CPU0_0 + (i * 8)) + j, - gmac->credit_config[(i * 8) + j]); - } - - xlr_nae_wreg(priv->base_addr, R_MSG_TX_THRESHOLD, 3); - xlr_nae_wreg(priv->base_addr, R_DMACR0, 0xffffffff); - xlr_nae_wreg(priv->base_addr, R_DMACR1, 0xffffffff); - xlr_nae_wreg(priv->base_addr, R_DMACR2, 0xffffffff); - xlr_nae_wreg(priv->base_addr, R_DMACR3, 0xffffffff); - xlr_nae_wreg(priv->base_addr, R_FREEQCARVE, 0); - - err = xlr_net_fill_rx_ring(priv->ndev); - if (err) - return err; - nlm_register_fmn_handler(start_stn_id, end_stn_id, xlr_net_fmn_handler, - priv->adapter); - return 0; -} - -static void xlr_config_translate_table(struct xlr_net_priv *priv) -{ - u32 cpu_mask; - u32 val; - int bkts[32]; /* one bucket is assumed for each cpu */ - int b1, b2, c1, c2, i, j, k; - int use_bkt; - - use_bkt = 0; - cpu_mask = priv->nd->cpu_mask; - - pr_info("Using %s-based distribution\n", - (use_bkt) ? "bucket" : "class"); - j = 0; - for (i = 0; i < 32; i++) { - if ((1 << i) & cpu_mask) { - /* for each cpu, mark the 4+threadid bucket */ - bkts[j] = ((i / 4) * 8) + (i % 4); - j++; - } - } - - /*configure the 128 * 9 Translation table to send to available buckets*/ - k = 0; - c1 = 3; - c2 = 0; - for (i = 0; i < 64; i++) { - /* - * On use_bkt set the b0, b1 are used, else - * the 4 classes are used, here implemented - * a logic to distribute the packets to the - * buckets equally or based on the class - */ - c1 = (c1 + 1) & 3; - c2 = (c1 + 1) & 3; - b1 = bkts[k]; - k = (k + 1) % j; - b2 = bkts[k]; - k = (k + 1) % j; - - val = ((c1 << 23) | (b1 << 17) | (use_bkt << 16) | - (c2 << 7) | (b2 << 1) | (use_bkt << 0)); - dev_dbg(&priv->ndev->dev, "Table[%d] b1=%d b2=%d c1=%d c2=%d\n", - i, b1, b2, c1, c2); - xlr_nae_wreg(priv->base_addr, R_TRANSLATETABLE + i, val); - c1 = c2; - } -} - -static void xlr_config_parser(struct xlr_net_priv *priv) -{ - u32 val; - - /* Mark it as ETHERNET type */ - xlr_nae_wreg(priv->base_addr, R_L2TYPE_0, 0x01); - - /* Use 7bit CRChash for flow classification with 127 as CRC polynomial*/ - xlr_nae_wreg(priv->base_addr, R_PARSERCONFIGREG, - ((0x7f << 8) | (1 << 1))); - - /* configure the parser : L2 Type is configured in the bootloader */ - /* extract IP: src, dest protocol */ - xlr_nae_wreg(priv->base_addr, R_L3CTABLE, - (9 << 20) | (1 << 19) | (1 << 18) | (0x01 << 16) | - (0x0800 << 0)); - xlr_nae_wreg(priv->base_addr, R_L3CTABLE + 1, - (9 << 25) | (1 << 21) | (12 << 14) | (4 << 10) | - (16 << 4) | 4); - - /* Configure to extract SRC port and Dest port for TCP and UDP pkts */ - xlr_nae_wreg(priv->base_addr, R_L4CTABLE, 6); - xlr_nae_wreg(priv->base_addr, R_L4CTABLE + 2, 17); - val = ((0 << 21) | (2 << 17) | (2 << 11) | (2 << 7)); - xlr_nae_wreg(priv->base_addr, R_L4CTABLE + 1, val); - xlr_nae_wreg(priv->base_addr, R_L4CTABLE + 3, val); - - xlr_config_translate_table(priv); -} - -static int xlr_phy_write(u32 *base_addr, int phy_addr, int regnum, u16 val) -{ - unsigned long timeout, stoptime, checktime; - int timedout; - - /* 100ms timeout*/ - timeout = msecs_to_jiffies(100); - stoptime = jiffies + timeout; - timedout = 0; - - xlr_nae_wreg(base_addr, R_MII_MGMT_ADDRESS, (phy_addr << 8) | regnum); - - /* Write the data which starts the write cycle */ - xlr_nae_wreg(base_addr, R_MII_MGMT_WRITE_DATA, (u32)val); - - /* poll for the read cycle to complete */ - while (!timedout) { - checktime = jiffies; - if (xlr_nae_rdreg(base_addr, R_MII_MGMT_INDICATORS) == 0) - break; - timedout = time_after(checktime, stoptime); - } - if (timedout) { - pr_info("Phy device write err: device busy"); - return -EBUSY; - } - - return 0; -} - -static int xlr_phy_read(u32 *base_addr, int phy_addr, int regnum) -{ - unsigned long timeout, stoptime, checktime; - int timedout; - - /* 100ms timeout*/ - timeout = msecs_to_jiffies(100); - stoptime = jiffies + timeout; - timedout = 0; - - /* setup the phy reg to be used */ - xlr_nae_wreg(base_addr, R_MII_MGMT_ADDRESS, - (phy_addr << 8) | (regnum << 0)); - - /* Issue the read command */ - xlr_nae_wreg(base_addr, R_MII_MGMT_COMMAND, - (1 << O_MII_MGMT_COMMAND__rstat)); - - /* poll for the read cycle to complete */ - while (!timedout) { - checktime = jiffies; - if (xlr_nae_rdreg(base_addr, R_MII_MGMT_INDICATORS) == 0) - break; - timedout = time_after(checktime, stoptime); - } - if (timedout) { - pr_info("Phy device read err: device busy"); - return -EBUSY; - } - - /* clear the read cycle */ - xlr_nae_wreg(base_addr, R_MII_MGMT_COMMAND, 0); - - /* Read the data */ - return xlr_nae_rdreg(base_addr, R_MII_MGMT_STATUS); -} - -static int xlr_mii_write(struct mii_bus *bus, int phy_addr, int regnum, u16 val) -{ - struct xlr_net_priv *priv = bus->priv; - int ret; - - ret = xlr_phy_write(priv->mii_addr, phy_addr, regnum, val); - dev_dbg(&priv->ndev->dev, "mii_write phy %d : %d <- %x [%x]\n", - phy_addr, regnum, val, ret); - return ret; -} - -static int xlr_mii_read(struct mii_bus *bus, int phy_addr, int regnum) -{ - struct xlr_net_priv *priv = bus->priv; - int ret; - - ret = xlr_phy_read(priv->mii_addr, phy_addr, regnum); - dev_dbg(&priv->ndev->dev, "mii_read phy %d : %d [%x]\n", - phy_addr, regnum, ret); - return ret; -} - -/* - * XLR ports are RGMII. XLS ports are SGMII mostly except the port0, - * which can be configured either SGMII or RGMII, considered SGMII - * by default, if board setup to RGMII the port_type need to set - * accordingly.Serdes and PCS layer need to configured for SGMII - */ -static void xlr_sgmii_init(struct xlr_net_priv *priv) -{ - int phy; - - xlr_phy_write(priv->serdes_addr, 26, 0, 0x6DB0); - xlr_phy_write(priv->serdes_addr, 26, 1, 0xFFFF); - xlr_phy_write(priv->serdes_addr, 26, 2, 0xB6D0); - xlr_phy_write(priv->serdes_addr, 26, 3, 0x00FF); - xlr_phy_write(priv->serdes_addr, 26, 4, 0x0000); - xlr_phy_write(priv->serdes_addr, 26, 5, 0x0000); - xlr_phy_write(priv->serdes_addr, 26, 6, 0x0005); - xlr_phy_write(priv->serdes_addr, 26, 7, 0x0001); - xlr_phy_write(priv->serdes_addr, 26, 8, 0x0000); - xlr_phy_write(priv->serdes_addr, 26, 9, 0x0000); - xlr_phy_write(priv->serdes_addr, 26, 10, 0x0000); - - /* program GPIO values for serdes init parameters */ - xlr_nae_wreg(priv->gpio_addr, 0x20, 0x7e6802); - xlr_nae_wreg(priv->gpio_addr, 0x10, 0x7104); - - xlr_nae_wreg(priv->gpio_addr, 0x22, 0x7e6802); - xlr_nae_wreg(priv->gpio_addr, 0x21, 0x7104); - - /* enable autoneg - more magic */ - phy = priv->phy_addr % 4 + 27; - xlr_phy_write(priv->pcs_addr, phy, 0, 0x1000); - xlr_phy_write(priv->pcs_addr, phy, 0, 0x0200); -} - -void xlr_set_gmac_speed(struct xlr_net_priv *priv) -{ - struct phy_device *phydev = xlr_get_phydev(priv); - int speed; - - if (phydev->interface == PHY_INTERFACE_MODE_SGMII) - xlr_sgmii_init(priv); - - if (phydev->speed != priv->phy_speed) { - speed = phydev->speed; - if (speed == SPEED_1000) { - /* Set interface to Byte mode */ - xlr_nae_wreg(priv->base_addr, R_MAC_CONFIG_2, 0x7217); - priv->phy_speed = speed; - } else if (speed == SPEED_100 || speed == SPEED_10) { - /* Set interface to Nibble mode */ - xlr_nae_wreg(priv->base_addr, R_MAC_CONFIG_2, 0x7117); - priv->phy_speed = speed; - } - /* Set SGMII speed in Interface control reg */ - if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { - if (speed == SPEED_10) - xlr_nae_wreg(priv->base_addr, - R_INTERFACE_CONTROL, - SGMII_SPEED_10); - if (speed == SPEED_100) - xlr_nae_wreg(priv->base_addr, - R_INTERFACE_CONTROL, - SGMII_SPEED_100); - if (speed == SPEED_1000) - xlr_nae_wreg(priv->base_addr, - R_INTERFACE_CONTROL, - SGMII_SPEED_1000); - } - if (speed == SPEED_10) - xlr_nae_wreg(priv->base_addr, R_CORECONTROL, 0x2); - if (speed == SPEED_100) - xlr_nae_wreg(priv->base_addr, R_CORECONTROL, 0x1); - if (speed == SPEED_1000) - xlr_nae_wreg(priv->base_addr, R_CORECONTROL, 0x0); - } - pr_info("gmac%d : %dMbps\n", priv->port_id, priv->phy_speed); -} - -static void xlr_gmac_link_adjust(struct net_device *ndev) -{ - struct xlr_net_priv *priv = netdev_priv(ndev); - struct phy_device *phydev = xlr_get_phydev(priv); - u32 intreg; - - intreg = xlr_nae_rdreg(priv->base_addr, R_INTREG); - if (phydev->link) { - if (phydev->speed != priv->phy_speed) { - xlr_set_gmac_speed(priv); - pr_info("gmac%d : Link up\n", priv->port_id); - } - } else { - xlr_set_gmac_speed(priv); - pr_info("gmac%d : Link down\n", priv->port_id); - } -} - -static int xlr_mii_probe(struct xlr_net_priv *priv) -{ - struct phy_device *phydev = xlr_get_phydev(priv); - - if (!phydev) { - pr_err("no PHY found on phy_addr %d\n", priv->phy_addr); - return -ENODEV; - } - - /* Attach MAC to PHY */ - phydev = phy_connect(priv->ndev, phydev_name(phydev), - xlr_gmac_link_adjust, priv->nd->phy_interface); - - if (IS_ERR(phydev)) { - pr_err("could not attach PHY\n"); - return PTR_ERR(phydev); - } - phydev->supported &= (ADVERTISED_10baseT_Full - | ADVERTISED_10baseT_Half - | ADVERTISED_100baseT_Full - | ADVERTISED_100baseT_Half - | ADVERTISED_1000baseT_Full - | ADVERTISED_Autoneg - | ADVERTISED_MII); - - phydev->advertising = phydev->supported; - phy_attached_info(phydev); - return 0; -} - -static int xlr_setup_mdio(struct xlr_net_priv *priv, - struct platform_device *pdev) -{ - int err; - - priv->mii_bus = mdiobus_alloc(); - if (!priv->mii_bus) { - pr_err("mdiobus alloc failed\n"); - return -ENOMEM; - } - - priv->mii_bus->priv = priv; - priv->mii_bus->name = "xlr-mdio"; - snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%d", - priv->mii_bus->name, priv->port_id); - priv->mii_bus->read = xlr_mii_read; - priv->mii_bus->write = xlr_mii_write; - priv->mii_bus->parent = &pdev->dev; - - /* Scan only the enabled address */ - priv->mii_bus->phy_mask = ~(1 << priv->phy_addr); - - /* setting clock divisor to 54 */ - xlr_nae_wreg(priv->base_addr, R_MII_MGMT_CONFIG, 0x7); - - err = mdiobus_register(priv->mii_bus); - if (err) { - mdiobus_free(priv->mii_bus); - pr_err("mdio bus registration failed\n"); - return err; - } - - pr_info("Registered mdio bus id : %s\n", priv->mii_bus->id); - err = xlr_mii_probe(priv); - if (err) { - mdiobus_free(priv->mii_bus); - return err; - } - return 0; -} - -static void xlr_port_enable(struct xlr_net_priv *priv) -{ - u32 prid = (read_c0_prid() & 0xf000); - - /* Setup MAC_CONFIG reg if (xls & rgmii) */ - if ((prid == 0x8000 || prid == 0x4000 || prid == 0xc000) && - priv->nd->phy_interface == PHY_INTERFACE_MODE_RGMII) - xlr_reg_update(priv->base_addr, R_RX_CONTROL, - (1 << O_RX_CONTROL__RGMII), - (1 << O_RX_CONTROL__RGMII)); - - /* Rx Tx enable */ - xlr_reg_update(priv->base_addr, R_MAC_CONFIG_1, - ((1 << O_MAC_CONFIG_1__rxen) | - (1 << O_MAC_CONFIG_1__txen) | - (1 << O_MAC_CONFIG_1__rxfc) | - (1 << O_MAC_CONFIG_1__txfc)), - ((1 << O_MAC_CONFIG_1__rxen) | - (1 << O_MAC_CONFIG_1__txen) | - (1 << O_MAC_CONFIG_1__rxfc) | - (1 << O_MAC_CONFIG_1__txfc))); - - /* Setup tx control reg */ - xlr_reg_update(priv->base_addr, R_TX_CONTROL, - ((1 << O_TX_CONTROL__TXENABLE) | - (512 << O_TX_CONTROL__TXTHRESHOLD)), 0x3fff); - - /* Setup rx control reg */ - xlr_reg_update(priv->base_addr, R_RX_CONTROL, - 1 << O_RX_CONTROL__RXENABLE, - 1 << O_RX_CONTROL__RXENABLE); -} - -static void xlr_port_disable(struct xlr_net_priv *priv) -{ - /* Setup MAC_CONFIG reg */ - /* Rx Tx disable*/ - xlr_reg_update(priv->base_addr, R_MAC_CONFIG_1, - ((1 << O_MAC_CONFIG_1__rxen) | - (1 << O_MAC_CONFIG_1__txen) | - (1 << O_MAC_CONFIG_1__rxfc) | - (1 << O_MAC_CONFIG_1__txfc)), 0x0); - - /* Setup tx control reg */ - xlr_reg_update(priv->base_addr, R_TX_CONTROL, - ((1 << O_TX_CONTROL__TXENABLE) | - (512 << O_TX_CONTROL__TXTHRESHOLD)), 0); - - /* Setup rx control reg */ - xlr_reg_update(priv->base_addr, R_RX_CONTROL, - 1 << O_RX_CONTROL__RXENABLE, 0); -} - -/* - * Initialization of gmac - */ -static int xlr_gmac_init(struct xlr_net_priv *priv, - struct platform_device *pdev) -{ - int ret; - - pr_info("Initializing the gmac%d\n", priv->port_id); - - xlr_port_disable(priv); - - xlr_nae_wreg(priv->base_addr, R_DESC_PACK_CTRL, - (1 << O_DESC_PACK_CTRL__MAXENTRY) | - (BYTE_OFFSET << O_DESC_PACK_CTRL__BYTEOFFSET) | - (1600 << O_DESC_PACK_CTRL__REGULARSIZE)); - - ret = xlr_setup_mdio(priv, pdev); - if (ret) - return ret; - xlr_port_enable(priv); - - /* Enable Full-duplex/1000Mbps/CRC */ - xlr_nae_wreg(priv->base_addr, R_MAC_CONFIG_2, 0x7217); - /* speed 2.5Mhz */ - xlr_nae_wreg(priv->base_addr, R_CORECONTROL, 0x02); - /* Setup Interrupt mask reg */ - xlr_nae_wreg(priv->base_addr, R_INTMASK, (1 << O_INTMASK__TXILLEGAL) | - (1 << O_INTMASK__MDINT) | (1 << O_INTMASK__TXFETCHERROR) | - (1 << O_INTMASK__P2PSPILLECC) | (1 << O_INTMASK__TAGFULL) | - (1 << O_INTMASK__UNDERRUN) | (1 << O_INTMASK__ABORT)); - - /* Clear all stats */ - xlr_reg_update(priv->base_addr, R_STATCTRL, 0, 1 << O_STATCTRL__CLRCNT); - xlr_reg_update(priv->base_addr, R_STATCTRL, 1 << 2, 1 << 2); - return 0; -} - -static int xlr_net_probe(struct platform_device *pdev) -{ - struct xlr_net_priv *priv = NULL; - struct net_device *ndev; - struct resource *res; - struct xlr_adapter *adapter; - int err, port; - - pr_info("XLR/XLS Ethernet Driver controller %d\n", pdev->id); - /* - * Allocate our adapter data structure and attach it to the device. - */ - adapter = devm_kzalloc(&pdev->dev, sizeof(*adapter), GFP_KERNEL); - if (!adapter) - return -ENOMEM; - - /* - * XLR and XLS have 1 and 2 NAE controller respectively - * Each controller has 4 gmac ports, mapping each controller - * under one parent device, 4 gmac ports under one device. - */ - for (port = 0; port < pdev->num_resources / 2; port++) { - ndev = alloc_etherdev_mq(sizeof(struct xlr_net_priv), 32); - if (!ndev) { - dev_err(&pdev->dev, - "Allocation of Ethernet device failed\n"); - return -ENOMEM; - } - - priv = netdev_priv(ndev); - priv->pdev = pdev; - priv->ndev = ndev; - priv->port_id = (pdev->id * 4) + port; - priv->nd = (struct xlr_net_data *)pdev->dev.platform_data; - priv->base_addr = devm_platform_ioremap_resource(pdev, port); - if (IS_ERR(priv->base_addr)) { - err = PTR_ERR(priv->base_addr); - goto err_gmac; - } - priv->adapter = adapter; - adapter->netdev[port] = ndev; - - res = platform_get_resource(pdev, IORESOURCE_IRQ, port); - if (!res) { - dev_err(&pdev->dev, "No irq resource for MAC %d\n", - priv->port_id); - err = -ENODEV; - goto err_gmac; - } - - ndev->irq = res->start; - - priv->phy_addr = priv->nd->phy_addr[port]; - priv->tx_stnid = priv->nd->tx_stnid[port]; - priv->mii_addr = priv->nd->mii_addr; - priv->serdes_addr = priv->nd->serdes_addr; - priv->pcs_addr = priv->nd->pcs_addr; - priv->gpio_addr = priv->nd->gpio_addr; - - ndev->netdev_ops = &xlr_netdev_ops; - ndev->watchdog_timeo = HZ; - - /* Setup Mac address and Rx mode */ - eth_hw_addr_random(ndev); - xlr_hw_set_mac_addr(ndev); - xlr_set_rx_mode(ndev); - - priv->num_rx_desc += MAX_NUM_DESC_SPILL; - ndev->ethtool_ops = &xlr_ethtool_ops; - SET_NETDEV_DEV(ndev, &pdev->dev); - - xlr_config_fifo_spill_area(priv); - /* Configure PDE to Round-Robin pkt distribution */ - xlr_config_pde(priv); - xlr_config_parser(priv); - - /* Call init with respect to port */ - if (strcmp(res->name, "gmac") == 0) { - err = xlr_gmac_init(priv, pdev); - if (err) { - dev_err(&pdev->dev, "gmac%d init failed\n", - priv->port_id); - goto err_gmac; - } - } - - if (priv->port_id == 0 || priv->port_id == 4) { - err = xlr_config_common(priv); - if (err) - goto err_netdev; - } - - err = register_netdev(ndev); - if (err) { - dev_err(&pdev->dev, - "Registering netdev failed for gmac%d\n", - priv->port_id); - goto err_netdev; - } - platform_set_drvdata(pdev, priv); - } - - return 0; - -err_netdev: - mdiobus_free(priv->mii_bus); -err_gmac: - free_netdev(ndev); - return err; -} - -static int xlr_net_remove(struct platform_device *pdev) -{ - struct xlr_net_priv *priv = platform_get_drvdata(pdev); - - unregister_netdev(priv->ndev); - mdiobus_unregister(priv->mii_bus); - mdiobus_free(priv->mii_bus); - free_netdev(priv->ndev); - return 0; -} - -static struct platform_driver xlr_net_driver = { - .probe = xlr_net_probe, - .remove = xlr_net_remove, - .driver = { - .name = "xlr-net", - }, -}; - -module_platform_driver(xlr_net_driver); - -MODULE_AUTHOR("Ganesan Ramalingam "); -MODULE_DESCRIPTION("Ethernet driver for Netlogic XLR/XLS"); -MODULE_LICENSE("Dual BSD/GPL"); -MODULE_ALIAS("platform:xlr-net"); diff --git a/drivers/staging/netlogic/xlr_net.h b/drivers/staging/netlogic/xlr_net.h deleted file mode 100644 index 8365b744f9b37a..00000000000000 --- a/drivers/staging/netlogic/xlr_net.h +++ /dev/null @@ -1,1079 +0,0 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */ -/* - * Copyright (c) 2003-2012 Broadcom Corporation - * All Rights Reserved - */ - -/* #define MAC_SPLIT_MODE */ - -#define MAC_SPACING 0x400 -#define XGMAC_SPACING 0x400 - -/* PE-MCXMAC register and bit field definitions */ -#define R_MAC_CONFIG_1 0x00 -#define O_MAC_CONFIG_1__srst 31 -#define O_MAC_CONFIG_1__simr 30 -#define O_MAC_CONFIG_1__hrrmc 18 -#define W_MAC_CONFIG_1__hrtmc 2 -#define O_MAC_CONFIG_1__hrrfn 16 -#define W_MAC_CONFIG_1__hrtfn 2 -#define O_MAC_CONFIG_1__intlb 8 -#define O_MAC_CONFIG_1__rxfc 5 -#define O_MAC_CONFIG_1__txfc 4 -#define O_MAC_CONFIG_1__srxen 3 -#define O_MAC_CONFIG_1__rxen 2 -#define O_MAC_CONFIG_1__stxen 1 -#define O_MAC_CONFIG_1__txen 0 -#define R_MAC_CONFIG_2 0x01 -#define O_MAC_CONFIG_2__prlen 12 -#define W_MAC_CONFIG_2__prlen 4 -#define O_MAC_CONFIG_2__speed 8 -#define W_MAC_CONFIG_2__speed 2 -#define O_MAC_CONFIG_2__hugen 5 -#define O_MAC_CONFIG_2__flchk 4 -#define O_MAC_CONFIG_2__crce 1 -#define O_MAC_CONFIG_2__fulld 0 -#define R_IPG_IFG 0x02 -#define O_IPG_IFG__ipgr1 24 -#define W_IPG_IFG__ipgr1 7 -#define O_IPG_IFG__ipgr2 16 -#define W_IPG_IFG__ipgr2 7 -#define O_IPG_IFG__mifg 8 -#define W_IPG_IFG__mifg 8 -#define O_IPG_IFG__ipgt 0 -#define W_IPG_IFG__ipgt 7 -#define R_HALF_DUPLEX 0x03 -#define O_HALF_DUPLEX__abebt 24 -#define W_HALF_DUPLEX__abebt 4 -#define O_HALF_DUPLEX__abebe 19 -#define O_HALF_DUPLEX__bpnb 18 -#define O_HALF_DUPLEX__nobo 17 -#define O_HALF_DUPLEX__edxsdfr 16 -#define O_HALF_DUPLEX__retry 12 -#define W_HALF_DUPLEX__retry 4 -#define O_HALF_DUPLEX__lcol 0 -#define W_HALF_DUPLEX__lcol 10 -#define R_MAXIMUM_FRAME_LENGTH 0x04 -#define O_MAXIMUM_FRAME_LENGTH__maxf 0 -#define W_MAXIMUM_FRAME_LENGTH__maxf 16 -#define R_TEST 0x07 -#define O_TEST__mbof 3 -#define O_TEST__rthdf 2 -#define O_TEST__tpause 1 -#define O_TEST__sstct 0 -#define R_MII_MGMT_CONFIG 0x08 -#define O_MII_MGMT_CONFIG__scinc 5 -#define O_MII_MGMT_CONFIG__spre 4 -#define O_MII_MGMT_CONFIG__clks 3 -#define W_MII_MGMT_CONFIG__clks 3 -#define R_MII_MGMT_COMMAND 0x09 -#define O_MII_MGMT_COMMAND__scan 1 -#define O_MII_MGMT_COMMAND__rstat 0 -#define R_MII_MGMT_ADDRESS 0x0A -#define O_MII_MGMT_ADDRESS__fiad 8 -#define W_MII_MGMT_ADDRESS__fiad 5 -#define O_MII_MGMT_ADDRESS__fgad 5 -#define W_MII_MGMT_ADDRESS__fgad 0 -#define R_MII_MGMT_WRITE_DATA 0x0B -#define O_MII_MGMT_WRITE_DATA__ctld 0 -#define W_MII_MGMT_WRITE_DATA__ctld 16 -#define R_MII_MGMT_STATUS 0x0C -#define R_MII_MGMT_INDICATORS 0x0D -#define O_MII_MGMT_INDICATORS__nvalid 2 -#define O_MII_MGMT_INDICATORS__scan 1 -#define O_MII_MGMT_INDICATORS__busy 0 -#define R_INTERFACE_CONTROL 0x0E -#define O_INTERFACE_CONTROL__hrstint 31 -#define O_INTERFACE_CONTROL__tbimode 27 -#define O_INTERFACE_CONTROL__ghdmode 26 -#define O_INTERFACE_CONTROL__lhdmode 25 -#define O_INTERFACE_CONTROL__phymod 24 -#define O_INTERFACE_CONTROL__hrrmi 23 -#define O_INTERFACE_CONTROL__rspd 16 -#define O_INTERFACE_CONTROL__hr100 15 -#define O_INTERFACE_CONTROL__frcq 10 -#define O_INTERFACE_CONTROL__nocfr 9 -#define O_INTERFACE_CONTROL__dlfct 8 -#define O_INTERFACE_CONTROL__enjab 0 -#define R_INTERFACE_STATUS 0x0F -#define O_INTERFACE_STATUS__xsdfr 9 -#define O_INTERFACE_STATUS__ssrr 8 -#define W_INTERFACE_STATUS__ssrr 5 -#define O_INTERFACE_STATUS__miilf 3 -#define O_INTERFACE_STATUS__locar 2 -#define O_INTERFACE_STATUS__sqerr 1 -#define O_INTERFACE_STATUS__jabber 0 -#define R_STATION_ADDRESS_LS 0x10 -#define R_STATION_ADDRESS_MS 0x11 - -/* A-XGMAC register and bit field definitions */ -#define R_XGMAC_CONFIG_0 0x00 -#define O_XGMAC_CONFIG_0__hstmacrst 31 -#define O_XGMAC_CONFIG_0__hstrstrctl 23 -#define O_XGMAC_CONFIG_0__hstrstrfn 22 -#define O_XGMAC_CONFIG_0__hstrsttctl 18 -#define O_XGMAC_CONFIG_0__hstrsttfn 17 -#define O_XGMAC_CONFIG_0__hstrstmiim 16 -#define O_XGMAC_CONFIG_0__hstloopback 8 -#define R_XGMAC_CONFIG_1 0x01 -#define O_XGMAC_CONFIG_1__hsttctlen 31 -#define O_XGMAC_CONFIG_1__hsttfen 30 -#define O_XGMAC_CONFIG_1__hstrctlen 29 -#define O_XGMAC_CONFIG_1__hstrfen 28 -#define O_XGMAC_CONFIG_1__tfen 26 -#define O_XGMAC_CONFIG_1__rfen 24 -#define O_XGMAC_CONFIG_1__hstrctlshrtp 12 -#define O_XGMAC_CONFIG_1__hstdlyfcstx 10 -#define W_XGMAC_CONFIG_1__hstdlyfcstx 2 -#define O_XGMAC_CONFIG_1__hstdlyfcsrx 8 -#define W_XGMAC_CONFIG_1__hstdlyfcsrx 2 -#define O_XGMAC_CONFIG_1__hstppen 7 -#define O_XGMAC_CONFIG_1__hstbytswp 6 -#define O_XGMAC_CONFIG_1__hstdrplt64 5 -#define O_XGMAC_CONFIG_1__hstprmscrx 4 -#define O_XGMAC_CONFIG_1__hstlenchk 3 -#define O_XGMAC_CONFIG_1__hstgenfcs 2 -#define O_XGMAC_CONFIG_1__hstpadmode 0 -#define W_XGMAC_CONFIG_1__hstpadmode 2 -#define R_XGMAC_CONFIG_2 0x02 -#define O_XGMAC_CONFIG_2__hsttctlfrcp 31 -#define O_XGMAC_CONFIG_2__hstmlnkflth 27 -#define O_XGMAC_CONFIG_2__hstalnkflth 26 -#define O_XGMAC_CONFIG_2__rflnkflt 24 -#define W_XGMAC_CONFIG_2__rflnkflt 2 -#define O_XGMAC_CONFIG_2__hstipgextmod 16 -#define W_XGMAC_CONFIG_2__hstipgextmod 5 -#define O_XGMAC_CONFIG_2__hstrctlfrcp 15 -#define O_XGMAC_CONFIG_2__hstipgexten 5 -#define O_XGMAC_CONFIG_2__hstmipgext 0 -#define W_XGMAC_CONFIG_2__hstmipgext 5 -#define R_XGMAC_CONFIG_3 0x03 -#define O_XGMAC_CONFIG_3__hstfltrfrm 31 -#define W_XGMAC_CONFIG_3__hstfltrfrm 16 -#define O_XGMAC_CONFIG_3__hstfltrfrmdc 15 -#define W_XGMAC_CONFIG_3__hstfltrfrmdc 16 -#define R_XGMAC_STATION_ADDRESS_LS 0x04 -#define O_XGMAC_STATION_ADDRESS_LS__hstmacadr0 0 -#define W_XGMAC_STATION_ADDRESS_LS__hstmacadr0 32 -#define R_XGMAC_STATION_ADDRESS_MS 0x05 -#define R_XGMAC_MAX_FRAME_LEN 0x08 -#define O_XGMAC_MAX_FRAME_LEN__hstmxfrmwctx 16 -#define W_XGMAC_MAX_FRAME_LEN__hstmxfrmwctx 14 -#define O_XGMAC_MAX_FRAME_LEN__hstmxfrmbcrx 0 -#define W_XGMAC_MAX_FRAME_LEN__hstmxfrmbcrx 16 -#define R_XGMAC_REV_LEVEL 0x0B -#define O_XGMAC_REV_LEVEL__revlvl 0 -#define W_XGMAC_REV_LEVEL__revlvl 15 -#define R_XGMAC_MIIM_COMMAND 0x10 -#define O_XGMAC_MIIM_COMMAND__hstldcmd 3 -#define O_XGMAC_MIIM_COMMAND__hstmiimcmd 0 -#define W_XGMAC_MIIM_COMMAND__hstmiimcmd 3 -#define R_XGMAC_MIIM_FILED 0x11 -#define O_XGMAC_MIIM_FILED__hststfield 30 -#define W_XGMAC_MIIM_FILED__hststfield 2 -#define O_XGMAC_MIIM_FILED__hstopfield 28 -#define W_XGMAC_MIIM_FILED__hstopfield 2 -#define O_XGMAC_MIIM_FILED__hstphyadx 23 -#define W_XGMAC_MIIM_FILED__hstphyadx 5 -#define O_XGMAC_MIIM_FILED__hstregadx 18 -#define W_XGMAC_MIIM_FILED__hstregadx 5 -#define O_XGMAC_MIIM_FILED__hsttafield 16 -#define W_XGMAC_MIIM_FILED__hsttafield 2 -#define O_XGMAC_MIIM_FILED__miimrddat 0 -#define W_XGMAC_MIIM_FILED__miimrddat 16 -#define R_XGMAC_MIIM_CONFIG 0x12 -#define O_XGMAC_MIIM_CONFIG__hstnopram 7 -#define O_XGMAC_MIIM_CONFIG__hstclkdiv 0 -#define W_XGMAC_MIIM_CONFIG__hstclkdiv 7 -#define R_XGMAC_MIIM_LINK_FAIL_VECTOR 0x13 -#define O_XGMAC_MIIM_LINK_FAIL_VECTOR__miimlfvec 0 -#define W_XGMAC_MIIM_LINK_FAIL_VECTOR__miimlfvec 32 -#define R_XGMAC_MIIM_INDICATOR 0x14 -#define O_XGMAC_MIIM_INDICATOR__miimphylf 4 -#define O_XGMAC_MIIM_INDICATOR__miimmoncplt 3 -#define O_XGMAC_MIIM_INDICATOR__miimmonvld 2 -#define O_XGMAC_MIIM_INDICATOR__miimmon 1 -#define O_XGMAC_MIIM_INDICATOR__miimbusy 0 - -/* GMAC stats registers */ -#define R_RBYT 0x27 -#define R_RPKT 0x28 -#define R_RFCS 0x29 -#define R_RMCA 0x2A -#define R_RBCA 0x2B -#define R_RXCF 0x2C -#define R_RXPF 0x2D -#define R_RXUO 0x2E -#define R_RALN 0x2F -#define R_RFLR 0x30 -#define R_RCDE 0x31 -#define R_RCSE 0x32 -#define R_RUND 0x33 -#define R_ROVR 0x34 -#define R_TBYT 0x38 -#define R_TPKT 0x39 -#define R_TMCA 0x3A -#define R_TBCA 0x3B -#define R_TXPF 0x3C -#define R_TDFR 0x3D -#define R_TEDF 0x3E -#define R_TSCL 0x3F -#define R_TMCL 0x40 -#define R_TLCL 0x41 -#define R_TXCL 0x42 -#define R_TNCL 0x43 -#define R_TJBR 0x46 -#define R_TFCS 0x47 -#define R_TXCF 0x48 -#define R_TOVR 0x49 -#define R_TUND 0x4A -#define R_TFRG 0x4B - -/* Glue logic register and bit field definitions */ -#define R_MAC_ADDR0 0x50 -#define R_MAC_ADDR1 0x52 -#define R_MAC_ADDR2 0x54 -#define R_MAC_ADDR3 0x56 -#define R_MAC_ADDR_MASK2 0x58 -#define R_MAC_ADDR_MASK3 0x5A -#define R_MAC_FILTER_CONFIG 0x5C -#define O_MAC_FILTER_CONFIG__BROADCAST_EN 10 -#define O_MAC_FILTER_CONFIG__PAUSE_FRAME_EN 9 -#define O_MAC_FILTER_CONFIG__ALL_MCAST_EN 8 -#define O_MAC_FILTER_CONFIG__ALL_UCAST_EN 7 -#define O_MAC_FILTER_CONFIG__HASH_MCAST_EN 6 -#define O_MAC_FILTER_CONFIG__HASH_UCAST_EN 5 -#define O_MAC_FILTER_CONFIG__ADDR_MATCH_DISC 4 -#define O_MAC_FILTER_CONFIG__MAC_ADDR3_VALID 3 -#define O_MAC_FILTER_CONFIG__MAC_ADDR2_VALID 2 -#define O_MAC_FILTER_CONFIG__MAC_ADDR1_VALID 1 -#define O_MAC_FILTER_CONFIG__MAC_ADDR0_VALID 0 -#define R_HASH_TABLE_VECTOR 0x30 -#define R_TX_CONTROL 0x0A0 -#define O_TX_CONTROL__TX15HALT 31 -#define O_TX_CONTROL__TX14HALT 30 -#define O_TX_CONTROL__TX13HALT 29 -#define O_TX_CONTROL__TX12HALT 28 -#define O_TX_CONTROL__TX11HALT 27 -#define O_TX_CONTROL__TX10HALT 26 -#define O_TX_CONTROL__TX9HALT 25 -#define O_TX_CONTROL__TX8HALT 24 -#define O_TX_CONTROL__TX7HALT 23 -#define O_TX_CONTROL__TX6HALT 22 -#define O_TX_CONTROL__TX5HALT 21 -#define O_TX_CONTROL__TX4HALT 20 -#define O_TX_CONTROL__TX3HALT 19 -#define O_TX_CONTROL__TX2HALT 18 -#define O_TX_CONTROL__TX1HALT 17 -#define O_TX_CONTROL__TX0HALT 16 -#define O_TX_CONTROL__TXIDLE 15 -#define O_TX_CONTROL__TXENABLE 14 -#define O_TX_CONTROL__TXTHRESHOLD 0 -#define W_TX_CONTROL__TXTHRESHOLD 14 -#define R_RX_CONTROL 0x0A1 -#define O_RX_CONTROL__RGMII 10 -#define O_RX_CONTROL__SOFTRESET 2 -#define O_RX_CONTROL__RXHALT 1 -#define O_RX_CONTROL__RXENABLE 0 -#define R_DESC_PACK_CTRL 0x0A2 -#define O_DESC_PACK_CTRL__BYTEOFFSET 17 -#define W_DESC_PACK_CTRL__BYTEOFFSET 3 -#define O_DESC_PACK_CTRL__PREPADENABLE 16 -#define O_DESC_PACK_CTRL__MAXENTRY 14 -#define W_DESC_PACK_CTRL__MAXENTRY 2 -#define O_DESC_PACK_CTRL__REGULARSIZE 0 -#define W_DESC_PACK_CTRL__REGULARSIZE 14 -#define R_STATCTRL 0x0A3 -#define O_STATCTRL__OVERFLOWEN 4 -#define O_STATCTRL__GIG 3 -#define O_STATCTRL__STEN 2 -#define O_STATCTRL__CLRCNT 1 -#define O_STATCTRL__AUTOZ 0 -#define R_L2ALLOCCTRL 0x0A4 -#define O_L2ALLOCCTRL__TXL2ALLOCATE 9 -#define W_L2ALLOCCTRL__TXL2ALLOCATE 9 -#define O_L2ALLOCCTRL__RXL2ALLOCATE 0 -#define W_L2ALLOCCTRL__RXL2ALLOCATE 9 -#define R_INTMASK 0x0A5 -#define O_INTMASK__SPI4TXERROR 28 -#define O_INTMASK__SPI4RXERROR 27 -#define O_INTMASK__RGMIIHALFDUPCOLLISION 27 -#define O_INTMASK__ABORT 26 -#define O_INTMASK__UNDERRUN 25 -#define O_INTMASK__DISCARDPACKET 24 -#define O_INTMASK__ASYNCFIFOFULL 23 -#define O_INTMASK__TAGFULL 22 -#define O_INTMASK__CLASS3FULL 21 -#define O_INTMASK__C3EARLYFULL 20 -#define O_INTMASK__CLASS2FULL 19 -#define O_INTMASK__C2EARLYFULL 18 -#define O_INTMASK__CLASS1FULL 17 -#define O_INTMASK__C1EARLYFULL 16 -#define O_INTMASK__CLASS0FULL 15 -#define O_INTMASK__C0EARLYFULL 14 -#define O_INTMASK__RXDATAFULL 13 -#define O_INTMASK__RXEARLYFULL 12 -#define O_INTMASK__RFREEEMPTY 9 -#define O_INTMASK__RFEARLYEMPTY 8 -#define O_INTMASK__P2PSPILLECC 7 -#define O_INTMASK__FREEDESCFULL 5 -#define O_INTMASK__FREEEARLYFULL 4 -#define O_INTMASK__TXFETCHERROR 3 -#define O_INTMASK__STATCARRY 2 -#define O_INTMASK__MDINT 1 -#define O_INTMASK__TXILLEGAL 0 -#define R_INTREG 0x0A6 -#define O_INTREG__SPI4TXERROR 28 -#define O_INTREG__SPI4RXERROR 27 -#define O_INTREG__RGMIIHALFDUPCOLLISION 27 -#define O_INTREG__ABORT 26 -#define O_INTREG__UNDERRUN 25 -#define O_INTREG__DISCARDPACKET 24 -#define O_INTREG__ASYNCFIFOFULL 23 -#define O_INTREG__TAGFULL 22 -#define O_INTREG__CLASS3FULL 21 -#define O_INTREG__C3EARLYFULL 20 -#define O_INTREG__CLASS2FULL 19 -#define O_INTREG__C2EARLYFULL 18 -#define O_INTREG__CLASS1FULL 17 -#define O_INTREG__C1EARLYFULL 16 -#define O_INTREG__CLASS0FULL 15 -#define O_INTREG__C0EARLYFULL 14 -#define O_INTREG__RXDATAFULL 13 -#define O_INTREG__RXEARLYFULL 12 -#define O_INTREG__RFREEEMPTY 9 -#define O_INTREG__RFEARLYEMPTY 8 -#define O_INTREG__P2PSPILLECC 7 -#define O_INTREG__FREEDESCFULL 5 -#define O_INTREG__FREEEARLYFULL 4 -#define O_INTREG__TXFETCHERROR 3 -#define O_INTREG__STATCARRY 2 -#define O_INTREG__MDINT 1 -#define O_INTREG__TXILLEGAL 0 -#define R_TXRETRY 0x0A7 -#define O_TXRETRY__COLLISIONRETRY 6 -#define O_TXRETRY__BUSERRORRETRY 5 -#define O_TXRETRY__UNDERRUNRETRY 4 -#define O_TXRETRY__RETRIES 0 -#define W_TXRETRY__RETRIES 4 -#define R_CORECONTROL 0x0A8 -#define O_CORECONTROL__ERRORTHREAD 4 -#define W_CORECONTROL__ERRORTHREAD 7 -#define O_CORECONTROL__SHUTDOWN 2 -#define O_CORECONTROL__SPEED 0 -#define W_CORECONTROL__SPEED 2 -#define R_BYTEOFFSET0 0x0A9 -#define R_BYTEOFFSET1 0x0AA -#define R_L2TYPE_0 0x0F0 -#define O_L2TYPE__EXTRAHDRPROTOSIZE 26 -#define W_L2TYPE__EXTRAHDRPROTOSIZE 5 -#define O_L2TYPE__EXTRAHDRPROTOOFFSET 20 -#define W_L2TYPE__EXTRAHDRPROTOOFFSET 6 -#define O_L2TYPE__EXTRAHEADERSIZE 14 -#define W_L2TYPE__EXTRAHEADERSIZE 6 -#define O_L2TYPE__PROTOOFFSET 8 -#define W_L2TYPE__PROTOOFFSET 6 -#define O_L2TYPE__L2HDROFFSET 2 -#define W_L2TYPE__L2HDROFFSET 6 -#define O_L2TYPE__L2PROTO 0 -#define W_L2TYPE__L2PROTO 2 -#define R_L2TYPE_1 0xF0 -#define R_L2TYPE_2 0xF0 -#define R_L2TYPE_3 0xF0 -#define R_PARSERCONFIGREG 0x100 -#define O_PARSERCONFIGREG__CRCHASHPOLY 8 -#define W_PARSERCONFIGREG__CRCHASHPOLY 7 -#define O_PARSERCONFIGREG__PREPADOFFSET 4 -#define W_PARSERCONFIGREG__PREPADOFFSET 4 -#define O_PARSERCONFIGREG__USECAM 2 -#define O_PARSERCONFIGREG__USEHASH 1 -#define O_PARSERCONFIGREG__USEPROTO 0 -#define R_L3CTABLE 0x140 -#define O_L3CTABLE__OFFSET0 25 -#define W_L3CTABLE__OFFSET0 7 -#define O_L3CTABLE__LEN0 21 -#define W_L3CTABLE__LEN0 4 -#define O_L3CTABLE__OFFSET1 14 -#define W_L3CTABLE__OFFSET1 7 -#define O_L3CTABLE__LEN1 10 -#define W_L3CTABLE__LEN1 4 -#define O_L3CTABLE__OFFSET2 4 -#define W_L3CTABLE__OFFSET2 6 -#define O_L3CTABLE__LEN2 0 -#define W_L3CTABLE__LEN2 4 -#define O_L3CTABLE__L3HDROFFSET 26 -#define W_L3CTABLE__L3HDROFFSET 6 -#define O_L3CTABLE__L4PROTOOFFSET 20 -#define W_L3CTABLE__L4PROTOOFFSET 6 -#define O_L3CTABLE__IPCHKSUMCOMPUTE 19 -#define O_L3CTABLE__L4CLASSIFY 18 -#define O_L3CTABLE__L2PROTO 16 -#define W_L3CTABLE__L2PROTO 2 -#define O_L3CTABLE__L3PROTOKEY 0 -#define W_L3CTABLE__L3PROTOKEY 16 -#define R_L4CTABLE 0x160 -#define O_L4CTABLE__OFFSET0 21 -#define W_L4CTABLE__OFFSET0 6 -#define O_L4CTABLE__LEN0 17 -#define W_L4CTABLE__LEN0 4 -#define O_L4CTABLE__OFFSET1 11 -#define W_L4CTABLE__OFFSET1 6 -#define O_L4CTABLE__LEN1 7 -#define W_L4CTABLE__LEN1 4 -#define O_L4CTABLE__TCPCHKSUMENABLE 0 -#define R_CAM4X128TABLE 0x172 -#define O_CAM4X128TABLE__CLASSID 7 -#define W_CAM4X128TABLE__CLASSID 2 -#define O_CAM4X128TABLE__BUCKETID 1 -#define W_CAM4X128TABLE__BUCKETID 6 -#define O_CAM4X128TABLE__USEBUCKET 0 -#define R_CAM4X128KEY 0x180 -#define R_TRANSLATETABLE 0x1A0 -#define R_DMACR0 0x200 -#define O_DMACR0__DATA0WRMAXCR 27 -#define W_DMACR0__DATA0WRMAXCR 3 -#define O_DMACR0__DATA0RDMAXCR 24 -#define W_DMACR0__DATA0RDMAXCR 3 -#define O_DMACR0__DATA1WRMAXCR 21 -#define W_DMACR0__DATA1WRMAXCR 3 -#define O_DMACR0__DATA1RDMAXCR 18 -#define W_DMACR0__DATA1RDMAXCR 3 -#define O_DMACR0__DATA2WRMAXCR 15 -#define W_DMACR0__DATA2WRMAXCR 3 -#define O_DMACR0__DATA2RDMAXCR 12 -#define W_DMACR0__DATA2RDMAXCR 3 -#define O_DMACR0__DATA3WRMAXCR 9 -#define W_DMACR0__DATA3WRMAXCR 3 -#define O_DMACR0__DATA3RDMAXCR 6 -#define W_DMACR0__DATA3RDMAXCR 3 -#define O_DMACR0__DATA4WRMAXCR 3 -#define W_DMACR0__DATA4WRMAXCR 3 -#define O_DMACR0__DATA4RDMAXCR 0 -#define W_DMACR0__DATA4RDMAXCR 3 -#define R_DMACR1 0x201 -#define O_DMACR1__DATA5WRMAXCR 27 -#define W_DMACR1__DATA5WRMAXCR 3 -#define O_DMACR1__DATA5RDMAXCR 24 -#define W_DMACR1__DATA5RDMAXCR 3 -#define O_DMACR1__DATA6WRMAXCR 21 -#define W_DMACR1__DATA6WRMAXCR 3 -#define O_DMACR1__DATA6RDMAXCR 18 -#define W_DMACR1__DATA6RDMAXCR 3 -#define O_DMACR1__DATA7WRMAXCR 15 -#define W_DMACR1__DATA7WRMAXCR 3 -#define O_DMACR1__DATA7RDMAXCR 12 -#define W_DMACR1__DATA7RDMAXCR 3 -#define O_DMACR1__DATA8WRMAXCR 9 -#define W_DMACR1__DATA8WRMAXCR 3 -#define O_DMACR1__DATA8RDMAXCR 6 -#define W_DMACR1__DATA8RDMAXCR 3 -#define O_DMACR1__DATA9WRMAXCR 3 -#define W_DMACR1__DATA9WRMAXCR 3 -#define O_DMACR1__DATA9RDMAXCR 0 -#define W_DMACR1__DATA9RDMAXCR 3 -#define R_DMACR2 0x202 -#define O_DMACR2__DATA10WRMAXCR 27 -#define W_DMACR2__DATA10WRMAXCR 3 -#define O_DMACR2__DATA10RDMAXCR 24 -#define W_DMACR2__DATA10RDMAXCR 3 -#define O_DMACR2__DATA11WRMAXCR 21 -#define W_DMACR2__DATA11WRMAXCR 3 -#define O_DMACR2__DATA11RDMAXCR 18 -#define W_DMACR2__DATA11RDMAXCR 3 -#define O_DMACR2__DATA12WRMAXCR 15 -#define W_DMACR2__DATA12WRMAXCR 3 -#define O_DMACR2__DATA12RDMAXCR 12 -#define W_DMACR2__DATA12RDMAXCR 3 -#define O_DMACR2__DATA13WRMAXCR 9 -#define W_DMACR2__DATA13WRMAXCR 3 -#define O_DMACR2__DATA13RDMAXCR 6 -#define W_DMACR2__DATA13RDMAXCR 3 -#define O_DMACR2__DATA14WRMAXCR 3 -#define W_DMACR2__DATA14WRMAXCR 3 -#define O_DMACR2__DATA14RDMAXCR 0 -#define W_DMACR2__DATA14RDMAXCR 3 -#define R_DMACR3 0x203 -#define O_DMACR3__DATA15WRMAXCR 27 -#define W_DMACR3__DATA15WRMAXCR 3 -#define O_DMACR3__DATA15RDMAXCR 24 -#define W_DMACR3__DATA15RDMAXCR 3 -#define O_DMACR3__SPCLASSWRMAXCR 21 -#define W_DMACR3__SPCLASSWRMAXCR 3 -#define O_DMACR3__SPCLASSRDMAXCR 18 -#define W_DMACR3__SPCLASSRDMAXCR 3 -#define O_DMACR3__JUMFRINWRMAXCR 15 -#define W_DMACR3__JUMFRINWRMAXCR 3 -#define O_DMACR3__JUMFRINRDMAXCR 12 -#define W_DMACR3__JUMFRINRDMAXCR 3 -#define O_DMACR3__REGFRINWRMAXCR 9 -#define W_DMACR3__REGFRINWRMAXCR 3 -#define O_DMACR3__REGFRINRDMAXCR 6 -#define W_DMACR3__REGFRINRDMAXCR 3 -#define O_DMACR3__FROUTWRMAXCR 3 -#define W_DMACR3__FROUTWRMAXCR 3 -#define O_DMACR3__FROUTRDMAXCR 0 -#define W_DMACR3__FROUTRDMAXCR 3 -#define R_REG_FRIN_SPILL_MEM_START_0 0x204 -#define O_REG_FRIN_SPILL_MEM_START_0__REGFRINSPILLMEMSTART0 0 -#define W_REG_FRIN_SPILL_MEM_START_0__REGFRINSPILLMEMSTART0 32 -#define R_REG_FRIN_SPILL_MEM_START_1 0x205 -#define O_REG_FRIN_SPILL_MEM_START_1__REGFRINSPILLMEMSTART1 0 -#define W_REG_FRIN_SPILL_MEM_START_1__REGFRINSPILLMEMSTART1 3 -#define R_REG_FRIN_SPILL_MEM_SIZE 0x206 -#define O_REG_FRIN_SPILL_MEM_SIZE__REGFRINSPILLMEMSIZE 0 -#define W_REG_FRIN_SPILL_MEM_SIZE__REGFRINSPILLMEMSIZE 32 -#define R_FROUT_SPILL_MEM_START_0 0x207 -#define O_FROUT_SPILL_MEM_START_0__FROUTSPILLMEMSTART0 0 -#define W_FROUT_SPILL_MEM_START_0__FROUTSPILLMEMSTART0 32 -#define R_FROUT_SPILL_MEM_START_1 0x208 -#define O_FROUT_SPILL_MEM_START_1__FROUTSPILLMEMSTART1 0 -#define W_FROUT_SPILL_MEM_START_1__FROUTSPILLMEMSTART1 3 -#define R_FROUT_SPILL_MEM_SIZE 0x209 -#define O_FROUT_SPILL_MEM_SIZE__FROUTSPILLMEMSIZE 0 -#define W_FROUT_SPILL_MEM_SIZE__FROUTSPILLMEMSIZE 32 -#define R_CLASS0_SPILL_MEM_START_0 0x20A -#define O_CLASS0_SPILL_MEM_START_0__CLASS0SPILLMEMSTART0 0 -#define W_CLASS0_SPILL_MEM_START_0__CLASS0SPILLMEMSTART0 32 -#define R_CLASS0_SPILL_MEM_START_1 0x20B -#define O_CLASS0_SPILL_MEM_START_1__CLASS0SPILLMEMSTART1 0 -#define W_CLASS0_SPILL_MEM_START_1__CLASS0SPILLMEMSTART1 3 -#define R_CLASS0_SPILL_MEM_SIZE 0x20C -#define O_CLASS0_SPILL_MEM_SIZE__CLASS0SPILLMEMSIZE 0 -#define W_CLASS0_SPILL_MEM_SIZE__CLASS0SPILLMEMSIZE 32 -#define R_JUMFRIN_SPILL_MEM_START_0 0x20D -#define O_JUMFRIN_SPILL_MEM_START_0__JUMFRINSPILLMEMSTART0 0 -#define W_JUMFRIN_SPILL_MEM_START_0__JUMFRINSPILLMEMSTART0 32 -#define R_JUMFRIN_SPILL_MEM_START_1 0x20E -#define O_JUMFRIN_SPILL_MEM_START_1__JUMFRINSPILLMEMSTART1 0 -#define W_JUMFRIN_SPILL_MEM_START_1__JUMFRINSPILLMEMSTART1 3 -#define R_JUMFRIN_SPILL_MEM_SIZE 0x20F -#define O_JUMFRIN_SPILL_MEM_SIZE__JUMFRINSPILLMEMSIZE 0 -#define W_JUMFRIN_SPILL_MEM_SIZE__JUMFRINSPILLMEMSIZE 32 -#define R_CLASS1_SPILL_MEM_START_0 0x210 -#define O_CLASS1_SPILL_MEM_START_0__CLASS1SPILLMEMSTART0 0 -#define W_CLASS1_SPILL_MEM_START_0__CLASS1SPILLMEMSTART0 32 -#define R_CLASS1_SPILL_MEM_START_1 0x211 -#define O_CLASS1_SPILL_MEM_START_1__CLASS1SPILLMEMSTART1 0 -#define W_CLASS1_SPILL_MEM_START_1__CLASS1SPILLMEMSTART1 3 -#define R_CLASS1_SPILL_MEM_SIZE 0x212 -#define O_CLASS1_SPILL_MEM_SIZE__CLASS1SPILLMEMSIZE 0 -#define W_CLASS1_SPILL_MEM_SIZE__CLASS1SPILLMEMSIZE 32 -#define R_CLASS2_SPILL_MEM_START_0 0x213 -#define O_CLASS2_SPILL_MEM_START_0__CLASS2SPILLMEMSTART0 0 -#define W_CLASS2_SPILL_MEM_START_0__CLASS2SPILLMEMSTART0 32 -#define R_CLASS2_SPILL_MEM_START_1 0x214 -#define O_CLASS2_SPILL_MEM_START_1__CLASS2SPILLMEMSTART1 0 -#define W_CLASS2_SPILL_MEM_START_1__CLASS2SPILLMEMSTART1 3 -#define R_CLASS2_SPILL_MEM_SIZE 0x215 -#define O_CLASS2_SPILL_MEM_SIZE__CLASS2SPILLMEMSIZE 0 -#define W_CLASS2_SPILL_MEM_SIZE__CLASS2SPILLMEMSIZE 32 -#define R_CLASS3_SPILL_MEM_START_0 0x216 -#define O_CLASS3_SPILL_MEM_START_0__CLASS3SPILLMEMSTART0 0 -#define W_CLASS3_SPILL_MEM_START_0__CLASS3SPILLMEMSTART0 32 -#define R_CLASS3_SPILL_MEM_START_1 0x217 -#define O_CLASS3_SPILL_MEM_START_1__CLASS3SPILLMEMSTART1 0 -#define W_CLASS3_SPILL_MEM_START_1__CLASS3SPILLMEMSTART1 3 -#define R_CLASS3_SPILL_MEM_SIZE 0x218 -#define O_CLASS3_SPILL_MEM_SIZE__CLASS3SPILLMEMSIZE 0 -#define W_CLASS3_SPILL_MEM_SIZE__CLASS3SPILLMEMSIZE 32 -#define R_REG_FRIN1_SPILL_MEM_START_0 0x219 -#define R_REG_FRIN1_SPILL_MEM_START_1 0x21a -#define R_REG_FRIN1_SPILL_MEM_SIZE 0x21b -#define R_SPIHNGY0 0x219 -#define O_SPIHNGY0__EG_HNGY_THRESH_0 24 -#define W_SPIHNGY0__EG_HNGY_THRESH_0 7 -#define O_SPIHNGY0__EG_HNGY_THRESH_1 16 -#define W_SPIHNGY0__EG_HNGY_THRESH_1 7 -#define O_SPIHNGY0__EG_HNGY_THRESH_2 8 -#define W_SPIHNGY0__EG_HNGY_THRESH_2 7 -#define O_SPIHNGY0__EG_HNGY_THRESH_3 0 -#define W_SPIHNGY0__EG_HNGY_THRESH_3 7 -#define R_SPIHNGY1 0x21A -#define O_SPIHNGY1__EG_HNGY_THRESH_4 24 -#define W_SPIHNGY1__EG_HNGY_THRESH_4 7 -#define O_SPIHNGY1__EG_HNGY_THRESH_5 16 -#define W_SPIHNGY1__EG_HNGY_THRESH_5 7 -#define O_SPIHNGY1__EG_HNGY_THRESH_6 8 -#define W_SPIHNGY1__EG_HNGY_THRESH_6 7 -#define O_SPIHNGY1__EG_HNGY_THRESH_7 0 -#define W_SPIHNGY1__EG_HNGY_THRESH_7 7 -#define R_SPIHNGY2 0x21B -#define O_SPIHNGY2__EG_HNGY_THRESH_8 24 -#define W_SPIHNGY2__EG_HNGY_THRESH_8 7 -#define O_SPIHNGY2__EG_HNGY_THRESH_9 16 -#define W_SPIHNGY2__EG_HNGY_THRESH_9 7 -#define O_SPIHNGY2__EG_HNGY_THRESH_10 8 -#define W_SPIHNGY2__EG_HNGY_THRESH_10 7 -#define O_SPIHNGY2__EG_HNGY_THRESH_11 0 -#define W_SPIHNGY2__EG_HNGY_THRESH_11 7 -#define R_SPIHNGY3 0x21C -#define O_SPIHNGY3__EG_HNGY_THRESH_12 24 -#define W_SPIHNGY3__EG_HNGY_THRESH_12 7 -#define O_SPIHNGY3__EG_HNGY_THRESH_13 16 -#define W_SPIHNGY3__EG_HNGY_THRESH_13 7 -#define O_SPIHNGY3__EG_HNGY_THRESH_14 8 -#define W_SPIHNGY3__EG_HNGY_THRESH_14 7 -#define O_SPIHNGY3__EG_HNGY_THRESH_15 0 -#define W_SPIHNGY3__EG_HNGY_THRESH_15 7 -#define R_SPISTRV0 0x21D -#define O_SPISTRV0__EG_STRV_THRESH_0 24 -#define W_SPISTRV0__EG_STRV_THRESH_0 7 -#define O_SPISTRV0__EG_STRV_THRESH_1 16 -#define W_SPISTRV0__EG_STRV_THRESH_1 7 -#define O_SPISTRV0__EG_STRV_THRESH_2 8 -#define W_SPISTRV0__EG_STRV_THRESH_2 7 -#define O_SPISTRV0__EG_STRV_THRESH_3 0 -#define W_SPISTRV0__EG_STRV_THRESH_3 7 -#define R_SPISTRV1 0x21E -#define O_SPISTRV1__EG_STRV_THRESH_4 24 -#define W_SPISTRV1__EG_STRV_THRESH_4 7 -#define O_SPISTRV1__EG_STRV_THRESH_5 16 -#define W_SPISTRV1__EG_STRV_THRESH_5 7 -#define O_SPISTRV1__EG_STRV_THRESH_6 8 -#define W_SPISTRV1__EG_STRV_THRESH_6 7 -#define O_SPISTRV1__EG_STRV_THRESH_7 0 -#define W_SPISTRV1__EG_STRV_THRESH_7 7 -#define R_SPISTRV2 0x21F -#define O_SPISTRV2__EG_STRV_THRESH_8 24 -#define W_SPISTRV2__EG_STRV_THRESH_8 7 -#define O_SPISTRV2__EG_STRV_THRESH_9 16 -#define W_SPISTRV2__EG_STRV_THRESH_9 7 -#define O_SPISTRV2__EG_STRV_THRESH_10 8 -#define W_SPISTRV2__EG_STRV_THRESH_10 7 -#define O_SPISTRV2__EG_STRV_THRESH_11 0 -#define W_SPISTRV2__EG_STRV_THRESH_11 7 -#define R_SPISTRV3 0x220 -#define O_SPISTRV3__EG_STRV_THRESH_12 24 -#define W_SPISTRV3__EG_STRV_THRESH_12 7 -#define O_SPISTRV3__EG_STRV_THRESH_13 16 -#define W_SPISTRV3__EG_STRV_THRESH_13 7 -#define O_SPISTRV3__EG_STRV_THRESH_14 8 -#define W_SPISTRV3__EG_STRV_THRESH_14 7 -#define O_SPISTRV3__EG_STRV_THRESH_15 0 -#define W_SPISTRV3__EG_STRV_THRESH_15 7 -#define R_TXDATAFIFO0 0x221 -#define O_TXDATAFIFO0__TX0DATAFIFOSTART 24 -#define W_TXDATAFIFO0__TX0DATAFIFOSTART 7 -#define O_TXDATAFIFO0__TX0DATAFIFOSIZE 16 -#define W_TXDATAFIFO0__TX0DATAFIFOSIZE 7 -#define O_TXDATAFIFO0__TX1DATAFIFOSTART 8 -#define W_TXDATAFIFO0__TX1DATAFIFOSTART 7 -#define O_TXDATAFIFO0__TX1DATAFIFOSIZE 0 -#define W_TXDATAFIFO0__TX1DATAFIFOSIZE 7 -#define R_TXDATAFIFO1 0x222 -#define O_TXDATAFIFO1__TX2DATAFIFOSTART 24 -#define W_TXDATAFIFO1__TX2DATAFIFOSTART 7 -#define O_TXDATAFIFO1__TX2DATAFIFOSIZE 16 -#define W_TXDATAFIFO1__TX2DATAFIFOSIZE 7 -#define O_TXDATAFIFO1__TX3DATAFIFOSTART 8 -#define W_TXDATAFIFO1__TX3DATAFIFOSTART 7 -#define O_TXDATAFIFO1__TX3DATAFIFOSIZE 0 -#define W_TXDATAFIFO1__TX3DATAFIFOSIZE 7 -#define R_TXDATAFIFO2 0x223 -#define O_TXDATAFIFO2__TX4DATAFIFOSTART 24 -#define W_TXDATAFIFO2__TX4DATAFIFOSTART 7 -#define O_TXDATAFIFO2__TX4DATAFIFOSIZE 16 -#define W_TXDATAFIFO2__TX4DATAFIFOSIZE 7 -#define O_TXDATAFIFO2__TX5DATAFIFOSTART 8 -#define W_TXDATAFIFO2__TX5DATAFIFOSTART 7 -#define O_TXDATAFIFO2__TX5DATAFIFOSIZE 0 -#define W_TXDATAFIFO2__TX5DATAFIFOSIZE 7 -#define R_TXDATAFIFO3 0x224 -#define O_TXDATAFIFO3__TX6DATAFIFOSTART 24 -#define W_TXDATAFIFO3__TX6DATAFIFOSTART 7 -#define O_TXDATAFIFO3__TX6DATAFIFOSIZE 16 -#define W_TXDATAFIFO3__TX6DATAFIFOSIZE 7 -#define O_TXDATAFIFO3__TX7DATAFIFOSTART 8 -#define W_TXDATAFIFO3__TX7DATAFIFOSTART 7 -#define O_TXDATAFIFO3__TX7DATAFIFOSIZE 0 -#define W_TXDATAFIFO3__TX7DATAFIFOSIZE 7 -#define R_TXDATAFIFO4 0x225 -#define O_TXDATAFIFO4__TX8DATAFIFOSTART 24 -#define W_TXDATAFIFO4__TX8DATAFIFOSTART 7 -#define O_TXDATAFIFO4__TX8DATAFIFOSIZE 16 -#define W_TXDATAFIFO4__TX8DATAFIFOSIZE 7 -#define O_TXDATAFIFO4__TX9DATAFIFOSTART 8 -#define W_TXDATAFIFO4__TX9DATAFIFOSTART 7 -#define O_TXDATAFIFO4__TX9DATAFIFOSIZE 0 -#define W_TXDATAFIFO4__TX9DATAFIFOSIZE 7 -#define R_TXDATAFIFO5 0x226 -#define O_TXDATAFIFO5__TX10DATAFIFOSTART 24 -#define W_TXDATAFIFO5__TX10DATAFIFOSTART 7 -#define O_TXDATAFIFO5__TX10DATAFIFOSIZE 16 -#define W_TXDATAFIFO5__TX10DATAFIFOSIZE 7 -#define O_TXDATAFIFO5__TX11DATAFIFOSTART 8 -#define W_TXDATAFIFO5__TX11DATAFIFOSTART 7 -#define O_TXDATAFIFO5__TX11DATAFIFOSIZE 0 -#define W_TXDATAFIFO5__TX11DATAFIFOSIZE 7 -#define R_TXDATAFIFO6 0x227 -#define O_TXDATAFIFO6__TX12DATAFIFOSTART 24 -#define W_TXDATAFIFO6__TX12DATAFIFOSTART 7 -#define O_TXDATAFIFO6__TX12DATAFIFOSIZE 16 -#define W_TXDATAFIFO6__TX12DATAFIFOSIZE 7 -#define O_TXDATAFIFO6__TX13DATAFIFOSTART 8 -#define W_TXDATAFIFO6__TX13DATAFIFOSTART 7 -#define O_TXDATAFIFO6__TX13DATAFIFOSIZE 0 -#define W_TXDATAFIFO6__TX13DATAFIFOSIZE 7 -#define R_TXDATAFIFO7 0x228 -#define O_TXDATAFIFO7__TX14DATAFIFOSTART 24 -#define W_TXDATAFIFO7__TX14DATAFIFOSTART 7 -#define O_TXDATAFIFO7__TX14DATAFIFOSIZE 16 -#define W_TXDATAFIFO7__TX14DATAFIFOSIZE 7 -#define O_TXDATAFIFO7__TX15DATAFIFOSTART 8 -#define W_TXDATAFIFO7__TX15DATAFIFOSTART 7 -#define O_TXDATAFIFO7__TX15DATAFIFOSIZE 0 -#define W_TXDATAFIFO7__TX15DATAFIFOSIZE 7 -#define R_RXDATAFIFO0 0x229 -#define O_RXDATAFIFO0__RX0DATAFIFOSTART 24 -#define W_RXDATAFIFO0__RX0DATAFIFOSTART 7 -#define O_RXDATAFIFO0__RX0DATAFIFOSIZE 16 -#define W_RXDATAFIFO0__RX0DATAFIFOSIZE 7 -#define O_RXDATAFIFO0__RX1DATAFIFOSTART 8 -#define W_RXDATAFIFO0__RX1DATAFIFOSTART 7 -#define O_RXDATAFIFO0__RX1DATAFIFOSIZE 0 -#define W_RXDATAFIFO0__RX1DATAFIFOSIZE 7 -#define R_RXDATAFIFO1 0x22A -#define O_RXDATAFIFO1__RX2DATAFIFOSTART 24 -#define W_RXDATAFIFO1__RX2DATAFIFOSTART 7 -#define O_RXDATAFIFO1__RX2DATAFIFOSIZE 16 -#define W_RXDATAFIFO1__RX2DATAFIFOSIZE 7 -#define O_RXDATAFIFO1__RX3DATAFIFOSTART 8 -#define W_RXDATAFIFO1__RX3DATAFIFOSTART 7 -#define O_RXDATAFIFO1__RX3DATAFIFOSIZE 0 -#define W_RXDATAFIFO1__RX3DATAFIFOSIZE 7 -#define R_RXDATAFIFO2 0x22B -#define O_RXDATAFIFO2__RX4DATAFIFOSTART 24 -#define W_RXDATAFIFO2__RX4DATAFIFOSTART 7 -#define O_RXDATAFIFO2__RX4DATAFIFOSIZE 16 -#define W_RXDATAFIFO2__RX4DATAFIFOSIZE 7 -#define O_RXDATAFIFO2__RX5DATAFIFOSTART 8 -#define W_RXDATAFIFO2__RX5DATAFIFOSTART 7 -#define O_RXDATAFIFO2__RX5DATAFIFOSIZE 0 -#define W_RXDATAFIFO2__RX5DATAFIFOSIZE 7 -#define R_RXDATAFIFO3 0x22C -#define O_RXDATAFIFO3__RX6DATAFIFOSTART 24 -#define W_RXDATAFIFO3__RX6DATAFIFOSTART 7 -#define O_RXDATAFIFO3__RX6DATAFIFOSIZE 16 -#define W_RXDATAFIFO3__RX6DATAFIFOSIZE 7 -#define O_RXDATAFIFO3__RX7DATAFIFOSTART 8 -#define W_RXDATAFIFO3__RX7DATAFIFOSTART 7 -#define O_RXDATAFIFO3__RX7DATAFIFOSIZE 0 -#define W_RXDATAFIFO3__RX7DATAFIFOSIZE 7 -#define R_RXDATAFIFO4 0x22D -#define O_RXDATAFIFO4__RX8DATAFIFOSTART 24 -#define W_RXDATAFIFO4__RX8DATAFIFOSTART 7 -#define O_RXDATAFIFO4__RX8DATAFIFOSIZE 16 -#define W_RXDATAFIFO4__RX8DATAFIFOSIZE 7 -#define O_RXDATAFIFO4__RX9DATAFIFOSTART 8 -#define W_RXDATAFIFO4__RX9DATAFIFOSTART 7 -#define O_RXDATAFIFO4__RX9DATAFIFOSIZE 0 -#define W_RXDATAFIFO4__RX9DATAFIFOSIZE 7 -#define R_RXDATAFIFO5 0x22E -#define O_RXDATAFIFO5__RX10DATAFIFOSTART 24 -#define W_RXDATAFIFO5__RX10DATAFIFOSTART 7 -#define O_RXDATAFIFO5__RX10DATAFIFOSIZE 16 -#define W_RXDATAFIFO5__RX10DATAFIFOSIZE 7 -#define O_RXDATAFIFO5__RX11DATAFIFOSTART 8 -#define W_RXDATAFIFO5__RX11DATAFIFOSTART 7 -#define O_RXDATAFIFO5__RX11DATAFIFOSIZE 0 -#define W_RXDATAFIFO5__RX11DATAFIFOSIZE 7 -#define R_RXDATAFIFO6 0x22F -#define O_RXDATAFIFO6__RX12DATAFIFOSTART 24 -#define W_RXDATAFIFO6__RX12DATAFIFOSTART 7 -#define O_RXDATAFIFO6__RX12DATAFIFOSIZE 16 -#define W_RXDATAFIFO6__RX12DATAFIFOSIZE 7 -#define O_RXDATAFIFO6__RX13DATAFIFOSTART 8 -#define W_RXDATAFIFO6__RX13DATAFIFOSTART 7 -#define O_RXDATAFIFO6__RX13DATAFIFOSIZE 0 -#define W_RXDATAFIFO6__RX13DATAFIFOSIZE 7 -#define R_RXDATAFIFO7 0x230 -#define O_RXDATAFIFO7__RX14DATAFIFOSTART 24 -#define W_RXDATAFIFO7__RX14DATAFIFOSTART 7 -#define O_RXDATAFIFO7__RX14DATAFIFOSIZE 16 -#define W_RXDATAFIFO7__RX14DATAFIFOSIZE 7 -#define O_RXDATAFIFO7__RX15DATAFIFOSTART 8 -#define W_RXDATAFIFO7__RX15DATAFIFOSTART 7 -#define O_RXDATAFIFO7__RX15DATAFIFOSIZE 0 -#define W_RXDATAFIFO7__RX15DATAFIFOSIZE 7 -#define R_XGMACPADCALIBRATION 0x231 -#define R_FREEQCARVE 0x233 -#define R_SPI4STATICDELAY0 0x240 -#define O_SPI4STATICDELAY0__DATALINE7 28 -#define W_SPI4STATICDELAY0__DATALINE7 4 -#define O_SPI4STATICDELAY0__DATALINE6 24 -#define W_SPI4STATICDELAY0__DATALINE6 4 -#define O_SPI4STATICDELAY0__DATALINE5 20 -#define W_SPI4STATICDELAY0__DATALINE5 4 -#define O_SPI4STATICDELAY0__DATALINE4 16 -#define W_SPI4STATICDELAY0__DATALINE4 4 -#define O_SPI4STATICDELAY0__DATALINE3 12 -#define W_SPI4STATICDELAY0__DATALINE3 4 -#define O_SPI4STATICDELAY0__DATALINE2 8 -#define W_SPI4STATICDELAY0__DATALINE2 4 -#define O_SPI4STATICDELAY0__DATALINE1 4 -#define W_SPI4STATICDELAY0__DATALINE1 4 -#define O_SPI4STATICDELAY0__DATALINE0 0 -#define W_SPI4STATICDELAY0__DATALINE0 4 -#define R_SPI4STATICDELAY1 0x241 -#define O_SPI4STATICDELAY1__DATALINE15 28 -#define W_SPI4STATICDELAY1__DATALINE15 4 -#define O_SPI4STATICDELAY1__DATALINE14 24 -#define W_SPI4STATICDELAY1__DATALINE14 4 -#define O_SPI4STATICDELAY1__DATALINE13 20 -#define W_SPI4STATICDELAY1__DATALINE13 4 -#define O_SPI4STATICDELAY1__DATALINE12 16 -#define W_SPI4STATICDELAY1__DATALINE12 4 -#define O_SPI4STATICDELAY1__DATALINE11 12 -#define W_SPI4STATICDELAY1__DATALINE11 4 -#define O_SPI4STATICDELAY1__DATALINE10 8 -#define W_SPI4STATICDELAY1__DATALINE10 4 -#define O_SPI4STATICDELAY1__DATALINE9 4 -#define W_SPI4STATICDELAY1__DATALINE9 4 -#define O_SPI4STATICDELAY1__DATALINE8 0 -#define W_SPI4STATICDELAY1__DATALINE8 4 -#define R_SPI4STATICDELAY2 0x242 -#define O_SPI4STATICDELAY0__TXSTAT1 8 -#define W_SPI4STATICDELAY0__TXSTAT1 4 -#define O_SPI4STATICDELAY0__TXSTAT0 4 -#define W_SPI4STATICDELAY0__TXSTAT0 4 -#define O_SPI4STATICDELAY0__RXCONTROL 0 -#define W_SPI4STATICDELAY0__RXCONTROL 4 -#define R_SPI4CONTROL 0x243 -#define O_SPI4CONTROL__STATICDELAY 2 -#define O_SPI4CONTROL__LVDS_LVTTL 1 -#define O_SPI4CONTROL__SPI4ENABLE 0 -#define R_CLASSWATERMARKS 0x244 -#define O_CLASSWATERMARKS__CLASS0WATERMARK 24 -#define W_CLASSWATERMARKS__CLASS0WATERMARK 5 -#define O_CLASSWATERMARKS__CLASS1WATERMARK 16 -#define W_CLASSWATERMARKS__CLASS1WATERMARK 5 -#define O_CLASSWATERMARKS__CLASS3WATERMARK 0 -#define W_CLASSWATERMARKS__CLASS3WATERMARK 5 -#define R_RXWATERMARKS1 0x245 -#define O_RXWATERMARKS__RX0DATAWATERMARK 24 -#define W_RXWATERMARKS__RX0DATAWATERMARK 7 -#define O_RXWATERMARKS__RX1DATAWATERMARK 16 -#define W_RXWATERMARKS__RX1DATAWATERMARK 7 -#define O_RXWATERMARKS__RX3DATAWATERMARK 0 -#define W_RXWATERMARKS__RX3DATAWATERMARK 7 -#define R_RXWATERMARKS2 0x246 -#define O_RXWATERMARKS__RX4DATAWATERMARK 24 -#define W_RXWATERMARKS__RX4DATAWATERMARK 7 -#define O_RXWATERMARKS__RX5DATAWATERMARK 16 -#define W_RXWATERMARKS__RX5DATAWATERMARK 7 -#define O_RXWATERMARKS__RX6DATAWATERMARK 8 -#define W_RXWATERMARKS__RX6DATAWATERMARK 7 -#define O_RXWATERMARKS__RX7DATAWATERMARK 0 -#define W_RXWATERMARKS__RX7DATAWATERMARK 7 -#define R_RXWATERMARKS3 0x247 -#define O_RXWATERMARKS__RX8DATAWATERMARK 24 -#define W_RXWATERMARKS__RX8DATAWATERMARK 7 -#define O_RXWATERMARKS__RX9DATAWATERMARK 16 -#define W_RXWATERMARKS__RX9DATAWATERMARK 7 -#define O_RXWATERMARKS__RX10DATAWATERMARK 8 -#define W_RXWATERMARKS__RX10DATAWATERMARK 7 -#define O_RXWATERMARKS__RX11DATAWATERMARK 0 -#define W_RXWATERMARKS__RX11DATAWATERMARK 7 -#define R_RXWATERMARKS4 0x248 -#define O_RXWATERMARKS__RX12DATAWATERMARK 24 -#define W_RXWATERMARKS__RX12DATAWATERMARK 7 -#define O_RXWATERMARKS__RX13DATAWATERMARK 16 -#define W_RXWATERMARKS__RX13DATAWATERMARK 7 -#define O_RXWATERMARKS__RX14DATAWATERMARK 8 -#define W_RXWATERMARKS__RX14DATAWATERMARK 7 -#define O_RXWATERMARKS__RX15DATAWATERMARK 0 -#define W_RXWATERMARKS__RX15DATAWATERMARK 7 -#define R_FREEWATERMARKS 0x249 -#define O_FREEWATERMARKS__FREEOUTWATERMARK 16 -#define W_FREEWATERMARKS__FREEOUTWATERMARK 16 -#define O_FREEWATERMARKS__JUMFRWATERMARK 8 -#define W_FREEWATERMARKS__JUMFRWATERMARK 7 -#define O_FREEWATERMARKS__REGFRWATERMARK 0 -#define W_FREEWATERMARKS__REGFRWATERMARK 7 -#define R_EGRESSFIFOCARVINGSLOTS 0x24a - -#define CTRL_RES0 0 -#define CTRL_RES1 1 -#define CTRL_REG_FREE 2 -#define CTRL_JUMBO_FREE 3 -#define CTRL_CONT 4 -#define CTRL_EOP 5 -#define CTRL_START 6 -#define CTRL_SNGL 7 - -#define CTRL_B0_NOT_EOP 0 -#define CTRL_B0_EOP 1 - -#define R_ROUND_ROBIN_TABLE 0 -#define R_PDE_CLASS_0 0x300 -#define R_PDE_CLASS_1 0x302 -#define R_PDE_CLASS_2 0x304 -#define R_PDE_CLASS_3 0x306 - -#define R_MSG_TX_THRESHOLD 0x308 - -#define R_GMAC_JFR0_BUCKET_SIZE 0x320 -#define R_GMAC_RFR0_BUCKET_SIZE 0x321 -#define R_GMAC_TX0_BUCKET_SIZE 0x322 -#define R_GMAC_TX1_BUCKET_SIZE 0x323 -#define R_GMAC_TX2_BUCKET_SIZE 0x324 -#define R_GMAC_TX3_BUCKET_SIZE 0x325 -#define R_GMAC_JFR1_BUCKET_SIZE 0x326 -#define R_GMAC_RFR1_BUCKET_SIZE 0x327 - -#define R_XGS_TX0_BUCKET_SIZE 0x320 -#define R_XGS_TX1_BUCKET_SIZE 0x321 -#define R_XGS_TX2_BUCKET_SIZE 0x322 -#define R_XGS_TX3_BUCKET_SIZE 0x323 -#define R_XGS_TX4_BUCKET_SIZE 0x324 -#define R_XGS_TX5_BUCKET_SIZE 0x325 -#define R_XGS_TX6_BUCKET_SIZE 0x326 -#define R_XGS_TX7_BUCKET_SIZE 0x327 -#define R_XGS_TX8_BUCKET_SIZE 0x328 -#define R_XGS_TX9_BUCKET_SIZE 0x329 -#define R_XGS_TX10_BUCKET_SIZE 0x32A -#define R_XGS_TX11_BUCKET_SIZE 0x32B -#define R_XGS_TX12_BUCKET_SIZE 0x32C -#define R_XGS_TX13_BUCKET_SIZE 0x32D -#define R_XGS_TX14_BUCKET_SIZE 0x32E -#define R_XGS_TX15_BUCKET_SIZE 0x32F -#define R_XGS_JFR_BUCKET_SIZE 0x330 -#define R_XGS_RFR_BUCKET_SIZE 0x331 - -#define R_CC_CPU0_0 0x380 -#define R_CC_CPU1_0 0x388 -#define R_CC_CPU2_0 0x390 -#define R_CC_CPU3_0 0x398 -#define R_CC_CPU4_0 0x3a0 -#define R_CC_CPU5_0 0x3a8 -#define R_CC_CPU6_0 0x3b0 -#define R_CC_CPU7_0 0x3b8 - -#define XLR_GMAC_BLK_SZ (XLR_IO_GMAC_1_OFFSET - \ - XLR_IO_GMAC_0_OFFSET) - -/* Constants used for configuring the devices */ - -#define XLR_FB_STN 6 /* Bucket used for Tx freeback */ - -#define MAC_B2B_IPG 88 - -#define XLR_NET_PREPAD_LEN 32 - -/* frame sizes need to be cacheline aligned */ -#define MAX_FRAME_SIZE (1536 + XLR_NET_PREPAD_LEN) -#define MAX_FRAME_SIZE_JUMBO 9216 - -#define MAC_SKB_BACK_PTR_SIZE SMP_CACHE_BYTES -#define MAC_PREPAD 0 -#define BYTE_OFFSET 2 -#define XLR_RX_BUF_SIZE (MAX_FRAME_SIZE + BYTE_OFFSET + \ - MAC_PREPAD + MAC_SKB_BACK_PTR_SIZE + SMP_CACHE_BYTES) -#define MAC_CRC_LEN 4 -#define MAX_NUM_MSGRNG_STN_CC 128 -#define MAX_MSG_SND_ATTEMPTS 100 /* 13 stns x 4 entry msg/stn + - * headroom - */ - -#define MAC_FRIN_TO_BE_SENT_THRESHOLD 16 - -#define MAX_NUM_DESC_SPILL 1024 -#define MAX_FRIN_SPILL (MAX_NUM_DESC_SPILL << 2) -#define MAX_FROUT_SPILL (MAX_NUM_DESC_SPILL << 2) -#define MAX_CLASS_0_SPILL (MAX_NUM_DESC_SPILL << 2) -#define MAX_CLASS_1_SPILL (MAX_NUM_DESC_SPILL << 2) -#define MAX_CLASS_2_SPILL (MAX_NUM_DESC_SPILL << 2) -#define MAX_CLASS_3_SPILL (MAX_NUM_DESC_SPILL << 2) - -enum { - SGMII_SPEED_10 = 0x00000000, - SGMII_SPEED_100 = 0x02000000, - SGMII_SPEED_1000 = 0x04000000, -}; - -enum tsv_rsv_reg { - TX_RX_64_BYTE_FRAME = 0x20, - TX_RX_64_127_BYTE_FRAME, - TX_RX_128_255_BYTE_FRAME, - TX_RX_256_511_BYTE_FRAME, - TX_RX_512_1023_BYTE_FRAME, - TX_RX_1024_1518_BYTE_FRAME, - TX_RX_1519_1522_VLAN_BYTE_FRAME, - - RX_BYTE_COUNTER = 0x27, - RX_PACKET_COUNTER, - RX_FCS_ERROR_COUNTER, - RX_MULTICAST_PACKET_COUNTER, - RX_BROADCAST_PACKET_COUNTER, - RX_CONTROL_FRAME_PACKET_COUNTER, - RX_PAUSE_FRAME_PACKET_COUNTER, - RX_UNKNOWN_OP_CODE_COUNTER, - RX_ALIGNMENT_ERROR_COUNTER, - RX_FRAME_LENGTH_ERROR_COUNTER, - RX_CODE_ERROR_COUNTER, - RX_CARRIER_SENSE_ERROR_COUNTER, - RX_UNDERSIZE_PACKET_COUNTER, - RX_OVERSIZE_PACKET_COUNTER, - RX_FRAGMENTS_COUNTER, - RX_JABBER_COUNTER, - RX_DROP_PACKET_COUNTER, - - TX_BYTE_COUNTER = 0x38, - TX_PACKET_COUNTER, - TX_MULTICAST_PACKET_COUNTER, - TX_BROADCAST_PACKET_COUNTER, - TX_PAUSE_CONTROL_FRAME_COUNTER, - TX_DEFERRAL_PACKET_COUNTER, - TX_EXCESSIVE_DEFERRAL_PACKET_COUNTER, - TX_SINGLE_COLLISION_PACKET_COUNTER, - TX_MULTI_COLLISION_PACKET_COUNTER, - TX_LATE_COLLISION_PACKET_COUNTER, - TX_EXCESSIVE_COLLISION_PACKET_COUNTER, - TX_TOTAL_COLLISION_COUNTER, - TX_PAUSE_FRAME_HONERED_COUNTER, - TX_DROP_FRAME_COUNTER, - TX_JABBER_FRAME_COUNTER, - TX_FCS_ERROR_COUNTER, - TX_CONTROL_FRAME_COUNTER, - TX_OVERSIZE_FRAME_COUNTER, - TX_UNDERSIZE_FRAME_COUNTER, - TX_FRAGMENT_FRAME_COUNTER, - - CARRY_REG_1 = 0x4c, - CARRY_REG_2 = 0x4d, -}; - -struct xlr_adapter { - struct net_device *netdev[4]; -}; - -struct xlr_net_priv { - u32 __iomem *base_addr; - struct net_device *ndev; - struct xlr_adapter *adapter; - struct mii_bus *mii_bus; - int num_rx_desc; - int phy_addr; /* PHY addr on MDIO bus */ - int pcs_id; /* PCS id on MDIO bus */ - int port_id; /* Port(gmac/xgmac) number, i.e 0-7 */ - int tx_stnid; - u32 __iomem *mii_addr; - u32 __iomem *serdes_addr; - u32 __iomem *pcs_addr; - u32 __iomem *gpio_addr; - int phy_speed; - int port_type; - struct timer_list queue_timer; - int wakeup_q; - struct platform_device *pdev; - struct xlr_net_data *nd; - - u64 *frin_spill; - u64 *frout_spill; - u64 *class_0_spill; - u64 *class_1_spill; - u64 *class_2_spill; - u64 *class_3_spill; -}; - -void xlr_set_gmac_speed(struct xlr_net_priv *priv); From 95161165727650a707bc34ecfac286a418b6bb00 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Fri, 12 Nov 2021 18:07:05 +0000 Subject: [PATCH 056/358] firmware: arm_scmi: Fix null de-reference on error path During channel setup a failure in the call of scmi_vio_feed_vq_rx() leads to an attempt to access a dev pointer by dereferencing vioch->cinfo at a time when vioch->cinfo has still to be initialized. Fix it by providing the device reference directly to scmi_vio_feed_vq_rx. Link: https://lore.kernel.org/r/20211112180705.41601-1-cristian.marussi@arm.com Fixes: 46abe13b5e3db ("firmware: arm_scmi: Add virtio transport") Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/virtio.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c index 11e8efb7137512..87039c5c03fdb9 100644 --- a/drivers/firmware/arm_scmi/virtio.c +++ b/drivers/firmware/arm_scmi/virtio.c @@ -82,7 +82,8 @@ static bool scmi_vio_have_vq_rx(struct virtio_device *vdev) } static int scmi_vio_feed_vq_rx(struct scmi_vio_channel *vioch, - struct scmi_vio_msg *msg) + struct scmi_vio_msg *msg, + struct device *dev) { struct scatterlist sg_in; int rc; @@ -94,8 +95,7 @@ static int scmi_vio_feed_vq_rx(struct scmi_vio_channel *vioch, rc = virtqueue_add_inbuf(vioch->vqueue, &sg_in, 1, msg, GFP_ATOMIC); if (rc) - dev_err_once(vioch->cinfo->dev, - "failed to add to virtqueue (%d)\n", rc); + dev_err_once(dev, "failed to add to virtqueue (%d)\n", rc); else virtqueue_kick(vioch->vqueue); @@ -108,7 +108,7 @@ static void scmi_finalize_message(struct scmi_vio_channel *vioch, struct scmi_vio_msg *msg) { if (vioch->is_rx) { - scmi_vio_feed_vq_rx(vioch, msg); + scmi_vio_feed_vq_rx(vioch, msg, vioch->cinfo->dev); } else { /* Here IRQs are assumed to be already disabled by the caller */ spin_lock(&vioch->lock); @@ -269,7 +269,7 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, list_add_tail(&msg->list, &vioch->free_list); spin_unlock_irqrestore(&vioch->lock, flags); } else { - scmi_vio_feed_vq_rx(vioch, msg); + scmi_vio_feed_vq_rx(vioch, msg, cinfo->dev); } } From a2acf0c0e2da29950d0361a3b5ea05e8d0351dfe Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 11 Nov 2021 18:23:30 +0100 Subject: [PATCH 057/358] selftests: nft_nat: switch port shadow test cases to socat There are now at least three distinct flavours of netcat/nc tool: 'original' version, one version ported from openbsd and nmap-ncat. The script only works with original because it sets SOREUSEPORT option. Other nc versions return 'port already in use' error and port shadow test fails: PASS: inet IPv6 redirection for ns2-hMHcaRvx nc: bind failed: Address already in use ERROR: portshadow test default: got reply from "ROUTER", not CLIENT as intended Switch to socat instead. Reported-by: kernel test robot Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_nat.sh | 26 ++++++++++++++------ 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index c62e4e26252c15..d88867d2fed755 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -760,20 +760,20 @@ test_port_shadow() local logmsg="" # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. - echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + echo "fake-entry" | ip netns exec "$ns2" timeout 1 socat -u STDIN UDP:"$daddrc":41404,sourceport=1405 - echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_r=$! + echo ROUTER | ip netns exec "$ns0" timeout 5 socat -u STDIN UDP4-LISTEN:1405 & + sc_r=$! - echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_c=$! + echo CLIENT | ip netns exec "$ns2" timeout 5 socat -u STDIN UDP4-LISTEN:1405,reuseport & + sc_c=$! sleep 0.3 # ns1 tries to connect to ns0:1405. With default settings this should connect # to client, it matches the conntrack entry created above. - result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405) + result=$(echo "data" | ip netns exec "$ns1" timeout 1 socat - UDP:"$daddrs":1405,sourceport=41404) if [ "$result" = "$expect" ] ;then echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}" @@ -782,7 +782,7 @@ test_port_shadow() ret=1 fi - kill $nc_r $nc_c 2>/dev/null + kill $sc_r $sc_c 2>/dev/null # flush udp entries for next test round, if any ip netns exec "$ns0" conntrack -F >/dev/null 2>&1 @@ -852,6 +852,18 @@ test_port_shadowing() { local family="ip" + conntrack -h >/dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without conntrack tool" + return + fi + + socat -h > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without socat tool" + return + fi + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null From adab993c25191b839b415781bdc7173a77315240 Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Wed, 3 Nov 2021 09:54:15 -0700 Subject: [PATCH 058/358] mmc: sdhci-esdhc-imx: disable CMDQ support On IMX SoC's which support CMDQ the following can occur during high a high cpu load: mmc2: cqhci: ============ CQHCI REGISTER DUMP =========== mmc2: cqhci: Caps: 0x0000310a | Version: 0x00000510 mmc2: cqhci: Config: 0x00001001 | Control: 0x00000000 mmc2: cqhci: Int stat: 0x00000000 | Int enab: 0x00000006 mmc2: cqhci: Int sig: 0x00000006 | Int Coal: 0x00000000 mmc2: cqhci: TDL base: 0x8003f000 | TDL up32: 0x00000000 mmc2: cqhci: Doorbell: 0xbf01dfff | TCN: 0x00000000 mmc2: cqhci: Dev queue: 0x00000000 | Dev Pend: 0x08000000 mmc2: cqhci: Task clr: 0x00000000 | SSC1: 0x00011000 mmc2: cqhci: SSC2: 0x00000001 | DCMD rsp: 0x00000800 mmc2: cqhci: RED mask: 0xfdf9a080 | TERRI: 0x00000000 mmc2: cqhci: Resp idx: 0x0000000d | Resp arg: 0x00000000 mmc2: sdhci: ============ SDHCI REGISTER DUMP =========== mmc2: sdhci: Sys addr: 0x7c722000 | Version: 0x00000002 mmc2: sdhci: Blk size: 0x00000200 | Blk cnt: 0x00000020 mmc2: sdhci: Argument: 0x00018000 | Trn mode: 0x00000023 mmc2: sdhci: Present: 0x01f88008 | Host ctl: 0x00000030 mmc2: sdhci: Power: 0x00000002 | Blk gap: 0x00000080 mmc2: sdhci: Wake-up: 0x00000008 | Clock: 0x0000000f mmc2: sdhci: Timeout: 0x0000008f | Int stat: 0x00000000 mmc2: sdhci: Int enab: 0x107f4000 | Sig enab: 0x107f4000 mmc2: sdhci: ACmd stat: 0x00000000 | Slot int: 0x00000502 mmc2: sdhci: Caps: 0x07eb0000 | Caps_1: 0x8000b407 mmc2: sdhci: Cmd: 0x00000d1a | Max curr: 0x00ffffff mmc2: sdhci: Resp[0]: 0x00000000 | Resp[1]: 0xffc003ff mmc2: sdhci: Resp[2]: 0x328f5903 | Resp[3]: 0x00d07f01 mmc2: sdhci: Host ctl2: 0x00000088 mmc2: sdhci: ADMA Err: 0x00000000 | ADMA Ptr: 0xfe179020 mmc2: sdhci-esdhc-imx: ========= ESDHC IMX DEBUG STATUS DUMP ==== mmc2: sdhci-esdhc-imx: cmd debug status: 0x2120 mmc2: sdhci-esdhc-imx: data debug status: 0x2200 mmc2: sdhci-esdhc-imx: trans debug status: 0x2300 mmc2: sdhci-esdhc-imx: dma debug status: 0x2400 mmc2: sdhci-esdhc-imx: adma debug status: 0x2510 mmc2: sdhci-esdhc-imx: fifo debug status: 0x2680 mmc2: sdhci-esdhc-imx: async fifo debug status: 0x2750 mmc2: sdhci: ============================================ For now, disable CMDQ support on the imx8qm/imx8qxp/imx8mm until the issue is found and resolved. Fixes: bb6e358169bf6 ("mmc: sdhci-esdhc-imx: add CMDQ support") Fixes: cde5e8e9ff146 ("mmc: sdhci-esdhc-imx: Add an new esdhc_soc_data for i.MX8MM") Cc: stable@vger.kernel.org Signed-off-by: Tim Harvey Reviewed-by: Haibo Chen Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20211103165415.2016-1-tharvey@gateworks.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-esdhc-imx.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index afaf33707d46a9..764ee1b761d9bd 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -310,7 +310,6 @@ static struct esdhc_soc_data usdhc_imx8qxp_data = { .flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING | ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200 | ESDHC_FLAG_HS400 | ESDHC_FLAG_HS400_ES - | ESDHC_FLAG_CQHCI | ESDHC_FLAG_STATE_LOST_IN_LPMODE | ESDHC_FLAG_CLK_RATE_LOST_IN_PM_RUNTIME, }; @@ -319,7 +318,6 @@ static struct esdhc_soc_data usdhc_imx8mm_data = { .flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING | ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200 | ESDHC_FLAG_HS400 | ESDHC_FLAG_HS400_ES - | ESDHC_FLAG_CQHCI | ESDHC_FLAG_STATE_LOST_IN_LPMODE, }; From a6e849d0007b374fc7fbb18d55941c77aa7c3923 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Mon, 15 Nov 2021 12:01:54 +0000 Subject: [PATCH 059/358] ASoC: wm_adsp: wm_adsp_control_add() error: uninitialized symbol 'ret' This patch fixes the static analysis warning as it is correctly indicating a possible code path, it cannot know that for the affected firmware versions subname would always be NULL. Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Simon Trimmer Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20211115120154.56782-1-simont@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/wm_adsp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index d4f0d72cbcc806..6cb01a8e08fb6a 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -617,8 +617,9 @@ static int wm_adsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl) switch (cs_dsp->fw_ver) { case 0: case 1: - snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s %x", - cs_dsp->name, region_name, cs_ctl->alg_region.alg); + ret = scnprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, + "%s %s %x", cs_dsp->name, region_name, + cs_ctl->alg_region.alg); break; case 2: ret = scnprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, From 754c4050a00e802e122690112fc2c3a6abafa7e2 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 27 Oct 2021 12:37:29 -0700 Subject: [PATCH 060/358] ARM: dts: BCM5301X: Fix I2C controller interrupt The I2C interrupt controller line is off by 32 because the datasheet describes interrupt inputs into the GIC which are for Shared Peripheral Interrupts and are starting at offset 32. The ARM GIC binding expects the SPI interrupts to be numbered from 0 relative to the SPI base. Fixes: bb097e3e0045 ("ARM: dts: BCM5301X: Add I2C support to the DT") Tested-by: Christian Lamparter Signed-off-by: Florian Fainelli --- arch/arm/boot/dts/bcm5301x.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index d4f355015e3cab..437a2b0f68de31 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -408,7 +408,7 @@ i2c0: i2c@18009000 { compatible = "brcm,iproc-i2c"; reg = <0x18009000 0x50>; - interrupts = ; + interrupts = ; #address-cells = <1>; #size-cells = <0>; clock-frequency = <100000>; From 40f7342f0587639e5ad625adaa15efdd3cffb18f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 28 Oct 2021 09:46:53 -0700 Subject: [PATCH 061/358] ARM: dts: BCM5301X: Add interrupt properties to GPIO node The GPIO controller is also an interrupt controller provider and is currently missing the appropriate 'interrupt-controller' and '#interrupt-cells' properties to denote that. Fixes: fb026d3de33b ("ARM: BCM5301X: Add Broadcom's bus-axi to the DTS file") Signed-off-by: Florian Fainelli --- arch/arm/boot/dts/bcm5301x.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index 437a2b0f68de31..f69d2af3c1fa48 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -242,6 +242,8 @@ gpio-controller; #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; }; pcie0: pcie@12000 { From 98481f3d72fb88cb5b973153434061015f094925 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 29 Oct 2021 14:09:26 -0700 Subject: [PATCH 062/358] ARM: dts: bcm2711: Fix PCIe interrupts The PCIe host bridge has two interrupt lines, one that goes towards it PCIE_INTR2 second level interrupt controller and one for its MSI second level interrupt controller. The first interrupt line is not currently managed by the driver, which is why it was not a functional problem. The interrupt-map property was also only listing the PCI_INTA interrupts when there are also the INTB, C and D. Reported-by: Jim Quinlan Fixes: d5c8dc0d4c88 ("ARM: dts: bcm2711: Enable PCIe controller") Signed-off-by: Florian Fainelli --- arch/arm/boot/dts/bcm2711.dtsi | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi index 3b60297af7f60b..9e01dbca4a011f 100644 --- a/arch/arm/boot/dts/bcm2711.dtsi +++ b/arch/arm/boot/dts/bcm2711.dtsi @@ -506,11 +506,17 @@ #address-cells = <3>; #interrupt-cells = <1>; #size-cells = <2>; - interrupts = , + interrupts = , ; interrupt-names = "pcie", "msi"; interrupt-map-mask = <0x0 0x0 0x0 0x7>; interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143 + IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &gicv2 GIC_SPI 144 + IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &gicv2 GIC_SPI 145 + IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &gicv2 GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>; msi-controller; msi-parent = <&pcie0>; From c6d3cd32fd0064af7611d00877a67e6993bf220b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 29 Oct 2021 17:22:45 +0100 Subject: [PATCH 063/358] arm64: ftrace: use HAVE_FUNCTION_GRAPH_RET_ADDR_PTR When CONFIG_FUNCTION_GRAPH_TRACER is selected and the function graph tracer is in use, unwind_frame() may erroneously associate a traced function with an incorrect return address. This can happen when starting an unwind from a pt_regs, or when unwinding across an exception boundary. This can be seen when recording with perf while the function graph tracer is in use. For example: | # echo function_graph > /sys/kernel/debug/tracing/current_tracer | # perf record -g -e raw_syscalls:sys_enter:k /bin/true | # perf report ... reports the callchain erroneously as: | el0t_64_sync | el0t_64_sync_handler | el0_svc_common.constprop.0 | perf_callchain | get_perf_callchain | syscall_trace_enter | syscall_trace_enter ... whereas when the function graph tracer is not in use, it reports: | el0t_64_sync | el0t_64_sync_handler | el0_svc | do_el0_svc | el0_svc_common.constprop.0 | syscall_trace_enter | syscall_trace_enter The underlying problem is that ftrace_graph_get_ret_stack() takes an index offset from the most recent entry added to the fgraph return stack. We start an unwind at offset 0, and increment the offset each time we encounter a rewritten return address (i.e. when we see `return_to_handler`). This is broken in two cases: 1) Between creating a pt_regs and starting the unwind, function calls may place entries on the stack, leaving an arbitrary offset which we can only determine by performing a full unwind from the caller of the unwind code (and relying on none of the unwind code being instrumented). This can result in erroneous entries being reported in a backtrace recorded by perf or kfence when the function graph tracer is in use. Currently show_regs() is unaffected as dump_backtrace() performs an initial unwind. 2) When unwinding across an exception boundary (whether continuing an unwind or starting a new unwind from regs), we currently always skip the LR of the interrupted context. Where this was live and contained a rewritten address, we won't consume the corresponding fgraph ret stack entry, leaving subsequent entries off-by-one. This can result in erroneous entries being reported in a backtrace performed by any in-kernel unwinder when that backtrace crosses an exception boundary, with entries after the boundary being reported incorrectly. This includes perf, kfence, show_regs(), panic(), etc. To fix this, we need to be able to uniquely identify each rewritten return address such that we can map this back to the original return address. We can use HAVE_FUNCTION_GRAPH_RET_ADDR_PTR to associate each rewritten return address with a unique location on the stack. As the return address is passed in the LR (and so is not guaranteed a unique location in memory), we use the FP upon entry to the function (i.e. the address of the caller's frame record) as the return address pointer. Any nested call will have a different FP value as the caller must create its own frame record and update FP to point to this. Since ftrace_graph_ret_addr() requires the return address with the PAC stripped, the stripping of the PAC is moved before the fixup of the rewritten address. As we would unconditionally strip the PAC, moving this earlier is not harmful, and we can avoid a redundant strip in the return address fixup code. I've tested this with the perf case above, the ftrace selftests, and a number of ad-hoc unwinder tests. The tests all pass, and I have seen no unexpected behaviour as a result of this change. I've tested with pointer authentication under QEMU TCG where magic-sysrq+l correctly recovers the original return addresses. Note that this doesn't fix the issue of skipping a live LR at an exception boundary, which is a more general problem and requires more substantial rework. Were we to consume the LR in all cases this would result in warnings where the interrupted context's LR contains `return_to_handler`, but the FP has been altered, e.g. | func: | <--- ftrace entry ---> // logs FP & LR, rewrites LR | STP FP, LR, [SP, #-16]! | MOV FP, SP | <--- INTERRUPT ---> ... as ftrace_graph_get_ret_stack() fill not find a matching entry, triggering the WARN_ON_ONCE() in unwind_frame(). Link: https://lore.kernel.org/r/20211025164925.GB2001@C02TD0UTHF1T.local Link: https://lore.kernel.org/r/20211027132529.30027-1-mark.rutland@arm.com Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: Madhavan T. Venkataraman Cc: Mark Brown Cc: Steven Rostedt Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20211029162245.39761-1-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/ftrace.h | 11 +++++++++++ arch/arm64/include/asm/stacktrace.h | 6 ------ arch/arm64/kernel/ftrace.c | 6 +++--- arch/arm64/kernel/stacktrace.c | 18 ++++++++---------- 4 files changed, 22 insertions(+), 19 deletions(-) diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 347b0cc68f0719..1494cfa8639bec 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -12,6 +12,17 @@ #define HAVE_FUNCTION_GRAPH_FP_TEST +/* + * HAVE_FUNCTION_GRAPH_RET_ADDR_PTR means that the architecture can provide a + * "return address pointer" which can be used to uniquely identify a return + * address which has been overwritten. + * + * On arm64 we use the address of the caller's frame record, which remains the + * same for the lifetime of the instrumented function, unlike the return + * address in the LR. + */ +#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS #define ARCH_SUPPORTS_FTRACE_OPS 1 #else diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index a4e046ef4568e2..6564a01cc085a9 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -47,9 +47,6 @@ struct stack_info { * @prev_type: The type of stack this frame record was on, or a synthetic * value of STACK_TYPE_UNKNOWN. This is used to detect a * transition from one stack to another. - * - * @graph: When FUNCTION_GRAPH_TRACER is selected, holds the index of a - * replacement lr value in the ftrace graph stack. */ struct stackframe { unsigned long fp; @@ -57,9 +54,6 @@ struct stackframe { DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES); unsigned long prev_fp; enum stack_type prev_type; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - int graph; -#endif #ifdef CONFIG_KRETPROBES struct llist_node *kr_cur; #endif diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index fc62dfe73f933a..4506c4a90ac10f 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -244,8 +244,6 @@ void arch_ftrace_update_code(int command) * on the way back to parent. For this purpose, this function is called * in _mcount() or ftrace_caller() to replace return address (*parent) on * the call stack to return_to_handler. - * - * Note that @frame_pointer is used only for sanity check later. */ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer) @@ -263,8 +261,10 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, */ old = *parent; - if (!function_graph_enter(old, self_addr, frame_pointer, NULL)) + if (!function_graph_enter(old, self_addr, frame_pointer, + (void *)frame_pointer)) { *parent = return_hooker; + } } #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index c30624fff6acd6..94f83cd44e5076 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -38,9 +38,6 @@ void start_backtrace(struct stackframe *frame, unsigned long fp, { frame->fp = fp; frame->pc = pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame->graph = 0; -#endif #ifdef CONFIG_KRETPROBES frame->kr_cur = NULL; #endif @@ -116,20 +113,23 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->prev_fp = fp; frame->prev_type = info.type; + frame->pc = ptrauth_strip_insn_pac(frame->pc); + #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && - (ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) { - struct ftrace_ret_stack *ret_stack; + (frame->pc == (unsigned long)return_to_handler)) { + unsigned long orig_pc; /* * This is a case where function graph tracer has * modified a return address (LR) in a stack frame * to hook a function return. * So replace it to an original value. */ - ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++); - if (WARN_ON_ONCE(!ret_stack)) + orig_pc = ftrace_graph_ret_addr(tsk, NULL, frame->pc, + (void *)frame->fp); + if (WARN_ON_ONCE(frame->pc == orig_pc)) return -EINVAL; - frame->pc = ret_stack->ret; + frame->pc = orig_pc; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_KRETPROBES @@ -137,8 +137,6 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->pc = kretprobe_find_ret_addr(tsk, (void *)frame->fp, &frame->kr_cur); #endif - frame->pc = ptrauth_strip_insn_pac(frame->pc); - return 0; } NOKPROBE_SYMBOL(unwind_frame); From d3eb70ead6474ec16f976fcacf10a7a890a95bd3 Mon Sep 17 00:00:00 2001 From: Pingfan Liu Date: Fri, 12 Nov 2021 13:22:14 +0800 Subject: [PATCH 064/358] arm64: mm: Fix VM_BUG_ON(mm != &init_mm) for trans_pgd trans_pgd_create_copy() can hit "VM_BUG_ON(mm != &init_mm)" in the function pmd_populate_kernel(). This is the combined consequence of commit 5de59884ac0e ("arm64: trans_pgd: pass NULL instead of init_mm to *_populate functions"), which replaced &init_mm with NULL and commit 59511cfd08f3 ("arm64: mm: use XN table mapping attributes for user/kernel mappings"), which introduced the VM_BUG_ON. Since the former sounds reasonable, it is better to work on the later. From the perspective of trans_pgd, two groups of functions are considered in the later one: pmd_populate_kernel() mm == NULL should be fixed, else it hits VM_BUG_ON() p?d_populate() mm == NULL means PXN, that is OK, since trans_pgd only copies a linear map, no execution will happen on the map. So it is good enough to just relax VM_BUG_ON() to disregard mm == NULL Fixes: 59511cfd08f3 ("arm64: mm: use XN table mapping attributes for user/kernel mappings") Signed-off-by: Pingfan Liu Cc: # 5.13.x Cc: Ard Biesheuvel Cc: James Morse Cc: Matthias Brugger Reviewed-by: Catalin Marinas Reviewed-by: Pasha Tatashin Link: https://lore.kernel.org/r/20211112052214.9086-1-kernelfans@gmail.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index 8433a2058eb15f..237224484d0f6f 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -76,7 +76,7 @@ static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep) { - VM_BUG_ON(mm != &init_mm); + VM_BUG_ON(mm && mm != &init_mm); __pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN); } From c23ca66a4dadb6f050dc57358bc8d57a747c35bf Mon Sep 17 00:00:00 2001 From: Lv Ruyi Date: Thu, 4 Nov 2021 11:30:47 +0000 Subject: [PATCH 065/358] optee: fix kfree NULL pointer This patch fixes the following Coccinelle error: drivers/tee/optee/ffa_abi.c: 877: ERROR optee is NULL but dereferenced. If memory allocation fails, optee is null pointer. the code will goto err and release optee. Fixes: 4615e5a34b95 ("optee: add FF-A support") Reported-by: Zeal Robot Signed-off-by: Lv Ruyi Reviewed-by: Sumit Garg [jw: removed the redundant braces] Signed-off-by: Jens Wiklander --- drivers/tee/optee/ffa_abi.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c index 45424824e0f9fc..d8c8683863aa06 100644 --- a/drivers/tee/optee/ffa_abi.c +++ b/drivers/tee/optee/ffa_abi.c @@ -810,10 +810,9 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev) return -EINVAL; optee = kzalloc(sizeof(*optee), GFP_KERNEL); - if (!optee) { - rc = -ENOMEM; - goto err; - } + if (!optee) + return -ENOMEM; + optee->pool = optee_ffa_config_dyn_shm(); if (IS_ERR(optee->pool)) { rc = PTR_ERR(optee->pool); From 2f20640491edda3c03eb6b899d0b92630d3d4c63 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Nov 2021 11:47:17 +0000 Subject: [PATCH 066/358] ASoC: qdsp6: qdsp6: q6prm: handle clk disable correctly Q6PRM clks need to be disabled using PRM_CMD_RELEASE_HW_RSC dsp command rather then using PRM_CMD_RSP_REQUEST_HW_RSC cmd with rate set to zero. DSP will throw errors if we try to disable the clock using existing code. Fix this by properly handling the clk release. Fixes: 9a0e5d6fb16f ("ASoC: qdsp6: audioreach: add q6prm support") Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20211116114721.12517-2-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/qcom/qdsp6/audioreach.h | 4 +++ sound/soc/qcom/qdsp6/q6prm.c | 53 +++++++++++++++++++++++++++++-- 2 files changed, 55 insertions(+), 2 deletions(-) diff --git a/sound/soc/qcom/qdsp6/audioreach.h b/sound/soc/qcom/qdsp6/audioreach.h index 4f693a2660b561..3ee8bfcd012115 100644 --- a/sound/soc/qcom/qdsp6/audioreach.h +++ b/sound/soc/qcom/qdsp6/audioreach.h @@ -550,6 +550,10 @@ struct audio_hw_clk_cfg { uint32_t clock_root; } __packed; +struct audio_hw_clk_rel_cfg { + uint32_t clock_id; +} __packed; + #define PARAM_ID_HW_EP_POWER_MODE_CFG 0x8001176 #define AR_HW_EP_POWER_MODE_0 0 /* default */ #define AR_HW_EP_POWER_MODE_1 1 /* XO Shutdown allowed */ diff --git a/sound/soc/qcom/qdsp6/q6prm.c b/sound/soc/qcom/qdsp6/q6prm.c index 82c40f2d4e1df8..cda33ded29bed3 100644 --- a/sound/soc/qcom/qdsp6/q6prm.c +++ b/sound/soc/qcom/qdsp6/q6prm.c @@ -42,6 +42,12 @@ struct prm_cmd_request_rsc { struct audio_hw_clk_cfg clock_id; } __packed; +struct prm_cmd_release_rsc { + struct apm_module_param_data param_data; + uint32_t num_clk_id; + struct audio_hw_clk_rel_cfg clock_id; +} __packed; + static int q6prm_send_cmd_sync(struct q6prm *prm, struct gpr_pkt *pkt, uint32_t rsp_opcode) { return audioreach_send_cmd_sync(prm->dev, prm->gdev, &prm->result, &prm->lock, @@ -102,8 +108,8 @@ int q6prm_unvote_lpass_core_hw(struct device *dev, uint32_t hw_block_id, uint32_ } EXPORT_SYMBOL_GPL(q6prm_unvote_lpass_core_hw); -int q6prm_set_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_root, - unsigned int freq) +static int q6prm_request_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_root, + unsigned int freq) { struct q6prm *prm = dev_get_drvdata(dev->parent); struct apm_module_param_data *param_data; @@ -138,6 +144,49 @@ int q6prm_set_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_ return rc; } + +static int q6prm_release_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_root, + unsigned int freq) +{ + struct q6prm *prm = dev_get_drvdata(dev->parent); + struct apm_module_param_data *param_data; + struct prm_cmd_release_rsc *rel; + gpr_device_t *gdev = prm->gdev; + struct gpr_pkt *pkt; + int rc; + + pkt = audioreach_alloc_cmd_pkt(sizeof(*rel), PRM_CMD_RELEASE_HW_RSC, 0, gdev->svc.id, + GPR_PRM_MODULE_IID); + if (IS_ERR(pkt)) + return PTR_ERR(pkt); + + rel = (void *)pkt + GPR_HDR_SIZE + APM_CMD_HDR_SIZE; + + param_data = &rel->param_data; + + param_data->module_instance_id = GPR_PRM_MODULE_IID; + param_data->error_code = 0; + param_data->param_id = PARAM_ID_RSC_AUDIO_HW_CLK; + param_data->param_size = sizeof(*rel) - APM_MODULE_PARAM_DATA_SIZE; + + rel->num_clk_id = 1; + rel->clock_id.clock_id = clk_id; + + rc = q6prm_send_cmd_sync(prm, pkt, PRM_CMD_RSP_RELEASE_HW_RSC); + + kfree(pkt); + + return rc; +} + +int q6prm_set_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_root, + unsigned int freq) +{ + if (freq) + return q6prm_request_lpass_clock(dev, clk_id, clk_attr, clk_attr, freq); + + return q6prm_release_lpass_clock(dev, clk_id, clk_attr, clk_attr, freq); +} EXPORT_SYMBOL_GPL(q6prm_set_lpass_clock); static int prm_callback(struct gpr_resp_pkt *data, void *priv, int op) From 861afeac7990587588d057b2c0b3222331c3da29 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Nov 2021 11:47:18 +0000 Subject: [PATCH 067/358] ASoC: qdsp6: q6routing: Conditionally reset FrontEnd Mixer Stream IDs are reused across multiple BackEnd mixers, do not reset the stream mixers if they are not already set for that particular FrontEnd. Ex: amixer cset iface=MIXER,name='SLIMBUS_0_RX Audio Mixer MultiMedia1' 1 would set the MultiMedia1 steam for SLIMBUS_0_RX, however doing below command will reset previously setup MultiMedia1 stream, because both of them are using MultiMedia1 PCM stream. amixer cset iface=MIXER,name='SLIMBUS_2_RX Audio Mixer MultiMedia1' 0 reset the FrontEnd Mixers conditionally to fix this issue. This is more noticeable in desktop setup, where in alsactl tries to restore the alsa state and overwriting the previous mixer settings. Fixes: e3a33673e845 ("ASoC: qdsp6: q6routing: Add q6routing driver") Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20211116114721.12517-3-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/qcom/qdsp6/q6routing.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c index 3390ebef9549d2..243b8179e59df5 100644 --- a/sound/soc/qcom/qdsp6/q6routing.c +++ b/sound/soc/qcom/qdsp6/q6routing.c @@ -495,7 +495,11 @@ static int msm_routing_put_audio_mixer(struct snd_kcontrol *kcontrol, session->port_id = be_id; snd_soc_dapm_mixer_update_power(dapm, kcontrol, 1, update); } else { - session->port_id = -1; + if (session->port_id == be_id) { + session->port_id = -1; + return 0; + } + snd_soc_dapm_mixer_update_power(dapm, kcontrol, 0, update); } From 721a94b4352dc8e47bff90b549a0118c39776756 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Nov 2021 11:47:19 +0000 Subject: [PATCH 068/358] ASoC: qdsp6: q6asm: fix q6asm_dai_prepare error handling Error handling in q6asm_dai_prepare() seems to be completely broken, Fix this by handling it properly. Fixes: 2a9e92d371db ("ASoC: qdsp6: q6asm: Add q6asm dai driver") Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20211116114721.12517-4-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/qcom/qdsp6/q6asm-dai.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c index 46f365528d5018..b74b67720ef437 100644 --- a/sound/soc/qcom/qdsp6/q6asm-dai.c +++ b/sound/soc/qcom/qdsp6/q6asm-dai.c @@ -269,9 +269,7 @@ static int q6asm_dai_prepare(struct snd_soc_component *component, if (ret < 0) { dev_err(dev, "%s: q6asm_open_write failed\n", __func__); - q6asm_audio_client_free(prtd->audio_client); - prtd->audio_client = NULL; - return -ENOMEM; + goto open_err; } prtd->session_id = q6asm_get_session_id(prtd->audio_client); @@ -279,7 +277,7 @@ static int q6asm_dai_prepare(struct snd_soc_component *component, prtd->session_id, substream->stream); if (ret) { dev_err(dev, "%s: stream reg failed ret:%d\n", __func__, ret); - return ret; + goto routing_err; } if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { @@ -301,10 +299,19 @@ static int q6asm_dai_prepare(struct snd_soc_component *component, } if (ret < 0) dev_info(dev, "%s: CMD Format block failed\n", __func__); + else + prtd->state = Q6ASM_STREAM_RUNNING; - prtd->state = Q6ASM_STREAM_RUNNING; + return ret; - return 0; +routing_err: + q6asm_cmd(prtd->audio_client, prtd->stream_id, CMD_CLOSE); +open_err: + q6asm_unmap_memory_regions(substream->stream, prtd->audio_client); + q6asm_audio_client_free(prtd->audio_client); + prtd->audio_client = NULL; + + return ret; } static int q6asm_dai_trigger(struct snd_soc_component *component, From 0a270471d68533f59c5cfd631a3fce31a3b17144 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Nov 2021 11:47:20 +0000 Subject: [PATCH 069/358] ASoC: qdsp6: q6adm: improve error reporting reset value for port is -1 so printing an hex would not give us very useful debug information, so use %d instead. Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20211116114721.12517-5-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/qcom/qdsp6/q6adm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/qcom/qdsp6/q6adm.c b/sound/soc/qcom/qdsp6/q6adm.c index 3d831b635524fb..72c5719f1d253e 100644 --- a/sound/soc/qcom/qdsp6/q6adm.c +++ b/sound/soc/qcom/qdsp6/q6adm.c @@ -390,7 +390,7 @@ struct q6copp *q6adm_open(struct device *dev, int port_id, int path, int rate, int ret = 0; if (port_id < 0) { - dev_err(dev, "Invalid port_id 0x%x\n", port_id); + dev_err(dev, "Invalid port_id %d\n", port_id); return ERR_PTR(-EINVAL); } @@ -508,7 +508,7 @@ int q6adm_matrix_map(struct device *dev, int path, int port_idx = payload_map.port_id[i]; if (port_idx < 0) { - dev_err(dev, "Invalid port_id 0x%x\n", + dev_err(dev, "Invalid port_id %d\n", payload_map.port_id[i]); kfree(pkt); return -EINVAL; From 6712c2e18c06b0976559fd4bd47774b243038e9c Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Nov 2021 11:47:21 +0000 Subject: [PATCH 070/358] ASoC: qdsp6: q6routing: validate port id before setting up route Validate port id before it starts sending commands to dsp this would make error handling simpler. Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20211116114721.12517-6-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/qcom/qdsp6/q6routing.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c index 243b8179e59df5..cd74681e811e1f 100644 --- a/sound/soc/qcom/qdsp6/q6routing.c +++ b/sound/soc/qcom/qdsp6/q6routing.c @@ -372,6 +372,12 @@ int q6routing_stream_open(int fedai_id, int perf_mode, } session = &routing_data->sessions[stream_id - 1]; + if (session->port_id < 0) { + dev_err(routing_data->dev, "Routing not setup for MultiMedia%d Session\n", + session->fedai_id); + return -EINVAL; + } + pdata = &routing_data->port_data[session->port_id]; mutex_lock(&routing_data->lock); From 7e567b5ae06315ef2d70666b149962e2bb4b97af Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 Nov 2021 08:18:12 +0100 Subject: [PATCH 071/358] ASoC: topology: Add missing rwsem around snd_ctl_remove() calls snd_ctl_remove() has to be called with card->controls_rwsem held (when called after the card instantiation). This patch add the missing rwsem calls around it. Fixes: 8a9782346dcc ("ASoC: topology: Add topology core") Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20211116071812.18109-1-tiwai@suse.de Signed-off-by: Mark Brown --- sound/soc/soc-topology.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 557e22c5254c76..f5b9e66ac3b82b 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -2700,6 +2700,7 @@ EXPORT_SYMBOL_GPL(snd_soc_tplg_component_load); /* remove dynamic controls from the component driver */ int snd_soc_tplg_component_remove(struct snd_soc_component *comp) { + struct snd_card *card = comp->card->snd_card; struct snd_soc_dobj *dobj, *next_dobj; int pass = SOC_TPLG_PASS_END; @@ -2707,6 +2708,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp) while (pass >= SOC_TPLG_PASS_START) { /* remove mixer controls */ + down_write(&card->controls_rwsem); list_for_each_entry_safe(dobj, next_dobj, &comp->dobj_list, list) { @@ -2745,6 +2747,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp) break; } } + up_write(&card->controls_rwsem); pass--; } From ea157c2ba821dab789a544cd9fbe44dc07036ff8 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Nov 2021 11:46:21 +0000 Subject: [PATCH 072/358] ASoC: codecs: wcd938x: fix volatile register range Interrupt Clear registers WCD938X_INTR_CLEAR_0 - WCD938X_INTR_CLEAR_2 are not marked as volatile. This has resulted in a missing interrupt bug while performing runtime pm. regcache_sync() during runtime pm resume path will write to Interrupt clear registers with previous values which basically clears the pending interrupt and actual interrupt handler never sees this interrupt. This issue is more visible with headset plug-in plug-out case compared to headset button. Fix this by adding the Interrupt clear registers to volatile range Fixes: 8d78602aa87a ("ASoC: codecs: wcd938x: add basic driver") Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20211116114623.11891-2-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/codecs/wcd938x.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c index 52de7d14b13985..67151c7770c650 100644 --- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -1174,6 +1174,9 @@ static bool wcd938x_readonly_register(struct device *dev, unsigned int reg) case WCD938X_DIGITAL_INTR_STATUS_0: case WCD938X_DIGITAL_INTR_STATUS_1: case WCD938X_DIGITAL_INTR_STATUS_2: + case WCD938X_DIGITAL_INTR_CLEAR_0: + case WCD938X_DIGITAL_INTR_CLEAR_1: + case WCD938X_DIGITAL_INTR_CLEAR_2: case WCD938X_DIGITAL_SWR_HM_TEST_0: case WCD938X_DIGITAL_SWR_HM_TEST_1: case WCD938X_DIGITAL_EFUSE_T_DATA_0: From 006ea27c4e7037369085755c7b5389effa508c04 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Nov 2021 11:46:22 +0000 Subject: [PATCH 073/358] ASoC: codecs: wcd934x: return error code correctly from hw_params Error returned from wcd934x_slim_set_hw_params() are not passed to upper layer, this could be misleading to the user which can start sending stream leading to unnecessary errors. Fix this by properly returning the errors. Fixes: a61f3b4f476e ("ASoC: wcd934x: add support to wcd9340/wcd9341 codec") Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20211116114623.11891-3-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/codecs/wcd934x.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c index c496b359f2f40b..4f568abd59e24a 100644 --- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -1896,9 +1896,8 @@ static int wcd934x_hw_params(struct snd_pcm_substream *substream, } wcd->dai[dai->id].sconfig.rate = params_rate(params); - wcd934x_slim_set_hw_params(wcd, &wcd->dai[dai->id], substream->stream); - return 0; + return wcd934x_slim_set_hw_params(wcd, &wcd->dai[dai->id], substream->stream); } static int wcd934x_hw_free(struct snd_pcm_substream *substream, From cb04d8cd0bb0b82acc34cc73cb33ae77cbfb020d Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Nov 2021 11:46:23 +0000 Subject: [PATCH 074/358] ASoC: codecs: lpass-rx-macro: fix HPHR setting CLSH mask For some reason we ended up using snd_soc_component_write_field for HPHL and snd_soc_component_update_bits for HPHR, so fix this. Fixes: af3d54b99764 ("ASoC: codecs: lpass-rx-macro: add support for lpass rx macro") Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20211116114623.11891-4-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- sound/soc/codecs/lpass-rx-macro.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index 2bed5cf229be72..aec5127260fd4e 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -2188,7 +2188,7 @@ static int rx_macro_config_classh(struct snd_soc_component *component, snd_soc_component_update_bits(component, CDC_RX_CLSH_DECAY_CTRL, CDC_RX_CLSH_DECAY_RATE_MASK, 0x0); - snd_soc_component_update_bits(component, + snd_soc_component_write_field(component, CDC_RX_RX1_RX_PATH_CFG0, CDC_RX_RXn_CLSH_EN_MASK, 0x1); break; From 451dc48c806a7ce9fbec5e7a24ccf4b2c936e834 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 11 Nov 2021 22:09:16 -0500 Subject: [PATCH 075/358] net: ieee802154: handle iftypes as u32 This patch fixes an issue that an u32 netlink value is handled as a signed enum value which doesn't fit into the range of u32 netlink type. If it's handled as -1 value some BIT() evaluation ends in a shift-out-of-bounds issue. To solve the issue we set the to u32 max which is s32 "-1" value to keep backwards compatibility and let the followed enum values start counting at 0. This brings the compiler to never handle the enum as signed and a check if the value is above NL802154_IFTYPE_MAX should filter -1 out. Fixes: f3ea5e44231a ("ieee802154: add new interface command") Signed-off-by: Alexander Aring Link: https://lore.kernel.org/r/20211112030916.685793-1-aahringo@redhat.com Signed-off-by: Stefan Schmidt --- include/net/nl802154.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/include/net/nl802154.h b/include/net/nl802154.h index ddcee128f5d9ac..145acb8f250957 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -19,6 +19,8 @@ * */ +#include + #define NL802154_GENL_NAME "nl802154" enum nl802154_commands { @@ -150,10 +152,9 @@ enum nl802154_attrs { }; enum nl802154_iftype { - /* for backwards compatibility TODO */ - NL802154_IFTYPE_UNSPEC = -1, + NL802154_IFTYPE_UNSPEC = (~(__u32)0), - NL802154_IFTYPE_NODE, + NL802154_IFTYPE_NODE = 0, NL802154_IFTYPE_MONITOR, NL802154_IFTYPE_COORD, From 897919ad8b42eb8222553838ab82414a924694aa Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 16 Nov 2021 15:33:23 +0100 Subject: [PATCH 076/358] xen/privcmd: make option visible in Kconfig MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This configuration option provides a misc device as an API to userspace. Make this API usable without having to select the module as a transitive dependency. This also fixes an issue where localyesconfig would select CONFIG_XEN_PRIVCMD=m because it was not visible and defaulted to building as module. [boris: clarified help message per Jan's suggestion] Based-on-patch-by: Thomas Weißschuh Signed-off-by: Juergen Gross Link: https://lore.kernel.org/r/20211116143323.18866-1-jgross@suse.com Reviewed-by: Jan Beulich Reviewed-by: Thomas Weißschuh Signed-off-by: Boris Ostrovsky --- drivers/xen/Kconfig | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index a1b11c62da9e36..33e941e40082d9 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -259,9 +259,15 @@ config XEN_SCSI_BACKEND if guests need generic access to SCSI devices. config XEN_PRIVCMD - tristate + tristate "Xen hypercall passthrough driver" depends on XEN default m + help + The hypercall passthrough driver allows privileged user programs to + perform Xen hypercalls. This driver is normally required for systems + running as Dom0 to perform privileged operations, but in some + disaggregated Xen setups this driver might be needed for other + domains, too. config XEN_ACPI_PROCESSOR tristate "Xen ACPI processor" From 08f6c2b09ebd4b326dbe96d13f94fee8f9814c78 Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Mon, 15 Nov 2021 14:27:19 -0800 Subject: [PATCH 077/358] xen: don't continue xenstore initialization in case of errors In case of errors in xenbus_init (e.g. missing xen_store_gfn parameter), we goto out_error but we forget to reset xen_store_domain_type to XS_UNKNOWN. As a consequence xenbus_probe_initcall and other initcalls will still try to initialize xenstore resulting into a crash at boot. [ 2.479830] Call trace: [ 2.482314] xb_init_comms+0x18/0x150 [ 2.486354] xs_init+0x34/0x138 [ 2.489786] xenbus_probe+0x4c/0x70 [ 2.498432] xenbus_probe_initcall+0x2c/0x7c [ 2.503944] do_one_initcall+0x54/0x1b8 [ 2.507358] kernel_init_freeable+0x1ac/0x210 [ 2.511617] kernel_init+0x28/0x130 [ 2.516112] ret_from_fork+0x10/0x20 Cc: Cc: jbeulich@suse.com Signed-off-by: Stefano Stabellini Link: https://lore.kernel.org/r/20211115222719.2558207-1-sstabellini@kernel.org Reviewed-by: Jan Beulich Signed-off-by: Boris Ostrovsky --- drivers/xen/xenbus/xenbus_probe.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index bd003ca8acbe92..5967aa9372550e 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -909,7 +909,7 @@ static struct notifier_block xenbus_resume_nb = { static int __init xenbus_init(void) { - int err = 0; + int err; uint64_t v = 0; xen_store_domain_type = XS_UNKNOWN; @@ -983,8 +983,10 @@ static int __init xenbus_init(void) */ proc_create_mount_point("xen"); #endif + return 0; out_error: + xen_store_domain_type = XS_UNKNOWN; return err; } From f6f9b278f2059478e9a57ac221995105641c7498 Mon Sep 17 00:00:00 2001 From: Kamal Mostafa Date: Tue, 16 Nov 2021 09:55:30 -0800 Subject: [PATCH 078/358] io_uring: fix missed comment from *task_file rename Fix comment referring to function "io_uring_del_task_file()", now called "io_uring_del_tctx_node()". Fixes: eef51daa72f7 ("io_uring: rename function *task_file") Signed-off-by: Kamal Mostafa Link: https://lore.kernel.org/r/20211116175530.31608-1-kamal@canonical.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index b07196b4511c42..e98e7ce3dc393a 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9764,7 +9764,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) } if (wq) { /* - * Must be after io_uring_del_task_file() (removes nodes under + * Must be after io_uring_del_tctx_node() (removes nodes under * uring_lock) to avoid race with io_uring_try_cancel_iowq(). */ io_wq_put_and_exit(wq); From 3d7c194b7c9ad414264935ad4f943a6ce285ebb1 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 15 Nov 2021 10:23:45 +0200 Subject: [PATCH 079/358] mmc: sdhci: Fix ADMA for PAGE_SIZE >= 64KiB The block layer forces a minimum segment size of PAGE_SIZE, so a segment can be too big for the ADMA table, if PAGE_SIZE >= 64KiB. Fix by writing multiple descriptors, noting that the ADMA table is sized for 4KiB chunks anyway, so it will be big enough. Reported-and-tested-by: Bough Chen Signed-off-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211115082345.802238-1-adrian.hunter@intel.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci.c | 21 ++++++++++++++++++--- drivers/mmc/host/sdhci.h | 4 +++- 2 files changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 269c865694024c..07c6da1f2f0fe7 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -771,7 +771,19 @@ static void sdhci_adma_table_pre(struct sdhci_host *host, len -= offset; } - BUG_ON(len > 65536); + /* + * The block layer forces a minimum segment size of PAGE_SIZE, + * so 'len' can be too big here if PAGE_SIZE >= 64KiB. Write + * multiple descriptors, noting that the ADMA table is sized + * for 4KiB chunks anyway, so it will be big enough. + */ + while (len > host->max_adma) { + int n = 32 * 1024; /* 32KiB*/ + + __sdhci_adma_write_desc(host, &desc, addr, n, ADMA2_TRAN_VALID); + addr += n; + len -= n; + } /* tran, valid */ if (len) @@ -3968,6 +3980,7 @@ struct sdhci_host *sdhci_alloc_host(struct device *dev, * descriptor for each segment, plus 1 for a nop end descriptor. */ host->adma_table_cnt = SDHCI_MAX_SEGS * 2 + 1; + host->max_adma = 65536; host->max_timeout_count = 0xE; @@ -4633,10 +4646,12 @@ int sdhci_setup_host(struct sdhci_host *host) * be larger than 64 KiB though. */ if (host->flags & SDHCI_USE_ADMA) { - if (host->quirks & SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC) + if (host->quirks & SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC) { + host->max_adma = 65532; /* 32-bit alignment */ mmc->max_seg_size = 65535; - else + } else { mmc->max_seg_size = 65536; + } } else { mmc->max_seg_size = mmc->max_req_size; } diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index bb883553d3b461..d7929d72573006 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -340,7 +340,8 @@ struct sdhci_adma2_64_desc { /* * Maximum segments assuming a 512KiB maximum requisition size and a minimum - * 4KiB page size. + * 4KiB page size. Note this also allows enough for multiple descriptors in + * case of PAGE_SIZE >= 64KiB. */ #define SDHCI_MAX_SEGS 128 @@ -543,6 +544,7 @@ struct sdhci_host { unsigned int blocks; /* remaining PIO blocks */ int sg_count; /* Mapped sg entries */ + int max_adma; /* Max. length in ADMA descriptor */ void *adma_table; /* ADMA descriptor table */ void *align_buffer; /* Bounce buffer */ From d1cbd9e0f7e51ae8e3638a36ba884fdbb2fc967e Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 17 Nov 2021 09:18:56 +0100 Subject: [PATCH 080/358] firmware: arm_scmi: Fix base agent discover response According to scmi specification, the response of the discover agent request is made of: - int32 status - uint32 agent_id - uint8 name[16] but the current implementation doesn't take into account the agent_id field and only allocates a rx buffer of SCMI_MAX_STR_SIZE length Allocate the correct length for rx buffer and copy the name from the correct offset in the response. While no error were returned until v5.15, v5.16-rc1 fails with virtio_scmi transport channel: | arm-scmi firmware:scmi0: SCMI Notifications - Core Enabled. | arm-scmi firmware:scmi0: SCMI Protocol v2.0 'Linaro:PMWG' Firmware version 0x2090000 | scmi-virtio virtio0: tx:used len 28 is larger than in buflen 24 Link: https://lore.kernel.org/r/20211117081856.9932-1-vincent.guittot@linaro.org Fixes: b6f20ff8bd94 ("firmware: arm_scmi: add common infrastructure and support for base protocol") Tested-by: Cristian Marussi Reviewed-by: Cristian Marussi Signed-off-by: Vincent Guittot Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/base.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/arm_scmi/base.c b/drivers/firmware/arm_scmi/base.c index de416f9e792132..f5219334fd3a56 100644 --- a/drivers/firmware/arm_scmi/base.c +++ b/drivers/firmware/arm_scmi/base.c @@ -34,6 +34,12 @@ struct scmi_msg_resp_base_attributes { __le16 reserved; }; +struct scmi_msg_resp_base_discover_agent { + __le32 agent_id; + u8 name[SCMI_MAX_STR_SIZE]; +}; + + struct scmi_msg_base_error_notify { __le32 event_control; #define BASE_TP_NOTIFY_ALL BIT(0) @@ -225,18 +231,21 @@ static int scmi_base_discover_agent_get(const struct scmi_protocol_handle *ph, int id, char *name) { int ret; + struct scmi_msg_resp_base_discover_agent *agent_info; struct scmi_xfer *t; ret = ph->xops->xfer_get_init(ph, BASE_DISCOVER_AGENT, - sizeof(__le32), SCMI_MAX_STR_SIZE, &t); + sizeof(__le32), sizeof(*agent_info), &t); if (ret) return ret; put_unaligned_le32(id, t->tx.buf); ret = ph->xops->do_xfer(ph, t); - if (!ret) - strlcpy(name, t->rx.buf, SCMI_MAX_STR_SIZE); + if (!ret) { + agent_info = t->rx.buf; + strlcpy(name, agent_info->name, SCMI_MAX_STR_SIZE); + } ph->xops->xfer_put(ph, t); From 1446fc6c678e8d8b31606a4b877abe205f344b38 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Tue, 16 Nov 2021 14:42:27 +0800 Subject: [PATCH 081/358] firmware: arm_scmi: pm: Propagate return value to caller of_genpd_add_provider_onecell may return error, so let's propagate its return value to caller Link: https://lore.kernel.org/r/20211116064227.20571-1-peng.fan@oss.nxp.com Fixes: 898216c97ed2 ("firmware: arm_scmi: add device power domain support using genpd") Signed-off-by: Peng Fan Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/scmi_pm_domain.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/firmware/arm_scmi/scmi_pm_domain.c b/drivers/firmware/arm_scmi/scmi_pm_domain.c index 4371fdcd5a73f3..581d34c9576954 100644 --- a/drivers/firmware/arm_scmi/scmi_pm_domain.c +++ b/drivers/firmware/arm_scmi/scmi_pm_domain.c @@ -138,9 +138,7 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev) scmi_pd_data->domains = domains; scmi_pd_data->num_domains = num_domains; - of_genpd_add_provider_onecell(np, scmi_pd_data); - - return 0; + return of_genpd_add_provider_onecell(np, scmi_pd_data); } static const struct scmi_device_id scmi_id_table[] = { From bd074e5039ee16d71833a67337e2f6bf5d106b3a Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 15 Nov 2021 15:40:43 +0000 Subject: [PATCH 082/358] firmware: arm_scmi: Fix type error in sensor protocol Fix incorrect type error reported by sparse as: drivers/firmware/arm_scmi/sensors.c:640:28: warning: incorrect type in argument 1 (different base types) drivers/firmware/arm_scmi/sensors.c:640:28: expected unsigned int [usertype] val drivers/firmware/arm_scmi/sensors.c:640:28: got restricted __le32 [usertype] Link: https://lore.kernel.org/r/20211115154043.49284-2-cristian.marussi@arm.com Fixes: 7b83c5f410889 ("firmware: arm_scmi: Add SCMI v3.0 sensor configuration support") Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/sensors.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c index 308471586381f4..cdbb287bd8bcd4 100644 --- a/drivers/firmware/arm_scmi/sensors.c +++ b/drivers/firmware/arm_scmi/sensors.c @@ -637,7 +637,7 @@ static int scmi_sensor_config_get(const struct scmi_protocol_handle *ph, if (ret) return ret; - put_unaligned_le32(cpu_to_le32(sensor_id), t->tx.buf); + put_unaligned_le32(sensor_id, t->tx.buf); ret = ph->xops->do_xfer(ph, t); if (!ret) { struct sensors_info *si = ph->get_priv(ph); From 026d9835b62bba34b7e657a0bfb76717822f9319 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 15 Nov 2021 15:40:42 +0000 Subject: [PATCH 083/358] firmware: arm_scmi: Fix type error assignment in voltage protocol Fix incorrect type assignment error reported by sparse as: drivers/firmware/arm_scmi/voltage.c:159:42: warning: incorrect type in assignment (different base types) drivers/firmware/arm_scmi/voltage.c:159:42: expected restricted __le32 [usertype] level_index drivers/firmware/arm_scmi/voltage.c:159:42: got unsigned int [usertype] desc_index Link: https://lore.kernel.org/r/20211115154043.49284-1-cristian.marussi@arm.com Fixes: 2add5cacff353 ("firmware: arm_scmi: Add voltage domain management protocol support") Reported-by: kernel test robot Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/voltage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_scmi/voltage.c b/drivers/firmware/arm_scmi/voltage.c index a5048956a0be94..ac08e819088bba 100644 --- a/drivers/firmware/arm_scmi/voltage.c +++ b/drivers/firmware/arm_scmi/voltage.c @@ -156,7 +156,7 @@ static int scmi_voltage_descriptors_get(const struct scmi_protocol_handle *ph, int cnt; cmd->domain_id = cpu_to_le32(v->id); - cmd->level_index = desc_index; + cmd->level_index = cpu_to_le32(desc_index); ret = ph->xops->do_xfer(ph, tl); if (ret) break; From 424fe7edbed18d47f7b97f7e1322a6f8969b77ae Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Wed, 17 Nov 2021 11:44:04 +0100 Subject: [PATCH 084/358] ASoC: stm32: i2s: fix 32 bits channel length without mclk Fix divider calculation in the case of 32 bits channel configuration, when no master clock is used. Fixes: e4e6ec7b127c ("ASoC: stm32: Add I2S driver") Signed-off-by: Olivier Moysan Link: https://lore.kernel.org/r/20211117104404.3832-1-olivier.moysan@foss.st.com Signed-off-by: Mark Brown --- sound/soc/stm/stm32_i2s.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/stm/stm32_i2s.c b/sound/soc/stm/stm32_i2s.c index 6254bacad6eb76..717f45a83445c1 100644 --- a/sound/soc/stm/stm32_i2s.c +++ b/sound/soc/stm/stm32_i2s.c @@ -700,7 +700,7 @@ static int stm32_i2s_configure_clock(struct snd_soc_dai *cpu_dai, if (ret < 0) return ret; - nb_bits = frame_len * ((cgfr & I2S_CGFR_CHLEN) + 1); + nb_bits = frame_len * (FIELD_GET(I2S_CGFR_CHLEN, cgfr) + 1); ret = stm32_i2s_calc_clk_div(i2s, i2s_clock_rate, (nb_bits * rate)); if (ret) From ffcf7ae90f4489047d7b076539ba207024dea5f6 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 Nov 2021 08:20:27 +0100 Subject: [PATCH 085/358] staging: greybus: Add missing rwsem around snd_ctl_remove() calls snd_ctl_remove() has to be called with card->controls_rwsem held (when called after the card instantiation). This patch adds the missing rwsem calls around it. Fixes: 510e340efe0c ("staging: greybus: audio: Add helper APIs for dynamic audio modules") Cc: stable Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20211116072027.18466-1-tiwai@suse.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/audio_helper.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/staging/greybus/audio_helper.c b/drivers/staging/greybus/audio_helper.c index 1ed4772d277150..843760675876af 100644 --- a/drivers/staging/greybus/audio_helper.c +++ b/drivers/staging/greybus/audio_helper.c @@ -192,7 +192,11 @@ int gbaudio_remove_component_controls(struct snd_soc_component *component, unsigned int num_controls) { struct snd_card *card = component->card->snd_card; + int err; - return gbaudio_remove_controls(card, component->dev, controls, - num_controls, component->name_prefix); + down_write(&card->controls_rwsem); + err = gbaudio_remove_controls(card, component->dev, controls, + num_controls, component->name_prefix); + up_write(&card->controls_rwsem); + return err; } From b535917c51acc97fb0761b1edec85f1f3d02bda4 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 17 Nov 2021 10:20:16 +0300 Subject: [PATCH 086/358] staging: rtl8192e: Fix use after free in _rtl92e_pci_disconnect() The free_rtllib() function frees the "dev" pointer so there is use after free on the next line. Re-arrange things to avoid that. Fixes: 66898177e7e5 ("staging: rtl8192e: Fix unload/reload problem") Cc: stable Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20211117072016.GA5237@kili Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index d2e9df60e9baff..b9ce71848023a3 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -2549,13 +2549,14 @@ static void _rtl92e_pci_disconnect(struct pci_dev *pdev) free_irq(dev->irq, dev); priv->irq = 0; } - free_rtllib(dev); if (dev->mem_start != 0) { iounmap((void __iomem *)dev->mem_start); release_mem_region(pci_resource_start(pdev, 1), pci_resource_len(pdev, 1)); } + + free_rtllib(dev); } pci_disable_device(pdev); From 250fdabec6ffcaf895c5e0dedca62706ef10d8f6 Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Mon, 25 Oct 2021 16:15:32 -0700 Subject: [PATCH 087/358] usb: dwc3: core: Revise GHWPARAMS9 offset During our predesign phase for DWC_usb32, the GHWPARAMS9 register offset was 0xc680. We revised our final design, and the GHWPARAMS9 offset is now moved to 0xc6e8 on release. Fixes: 16710380d3aa ("usb: dwc3: Capture new capability register GHWPARAMS9") Cc: Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/1541737108266a97208ff827805be1f32852590c.1635202893.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 620c8d3914d7cc..5c491d0a19d7b9 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -143,7 +143,7 @@ #define DWC3_GHWPARAMS8 0xc600 #define DWC3_GUCTL3 0xc60c #define DWC3_GFLADJ 0xc630 -#define DWC3_GHWPARAMS9 0xc680 +#define DWC3_GHWPARAMS9 0xc6e0 /* Device Registers */ #define DWC3_DCFG 0xc700 From d74dc3e9f58c28689cef1faccf918e06587367d3 Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Mon, 25 Oct 2021 16:21:10 -0700 Subject: [PATCH 088/358] usb: dwc3: gadget: Ignore NoStream after End Transfer The End Transfer command from a stream endpoint will generate a NoStream event, and we should ignore it. Currently we set the flag DWC3_EP_IGNORE_NEXT_NOSTREAM to track this prior to sending the command, and it will be cleared on the next stream event. However, a stream event may be generated before the End Transfer command completion and prematurely clear the flag. Fix this by setting the flag on End Transfer completion instead. Fixes: 140ca4cfea8a ("usb: dwc3: gadget: Handle stream transfers") Cc: Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/cee1253af4c3600edb878d11c9c08b040817ae23.1635203975.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 23de2a5a40d6ef..3d6f4adaa15a5a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3352,6 +3352,14 @@ static void dwc3_gadget_endpoint_command_complete(struct dwc3_ep *dep, if (cmd != DWC3_DEPCMD_ENDTRANSFER) return; + /* + * The END_TRANSFER command will cause the controller to generate a + * NoStream Event, and it's not due to the host DP NoStream rejection. + * Ignore the next NoStream event. + */ + if (dep->stream_capable) + dep->flags |= DWC3_EP_IGNORE_NEXT_NOSTREAM; + dep->flags &= ~DWC3_EP_END_TRANSFER_PENDING; dep->flags &= ~DWC3_EP_TRANSFER_STARTED; dwc3_gadget_ep_cleanup_cancelled_requests(dep); @@ -3574,14 +3582,6 @@ static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, WARN_ON_ONCE(ret); dep->resource_index = 0; - /* - * The END_TRANSFER command will cause the controller to generate a - * NoStream Event, and it's not due to the host DP NoStream rejection. - * Ignore the next NoStream event. - */ - if (dep->stream_capable) - dep->flags |= DWC3_EP_IGNORE_NEXT_NOSTREAM; - if (!interrupt) dep->flags &= ~DWC3_EP_TRANSFER_STARTED; else From 63c4c320ccf77074ffe9019ac596603133c1b517 Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Mon, 25 Oct 2021 16:35:06 -0700 Subject: [PATCH 089/358] usb: dwc3: gadget: Check for L1/L2/U3 for Start Transfer The programming guide noted that the driver needs to verify if the link state is in U0 before executing the Start Transfer command. If it's not in U0, the driver needs to perform remote wakeup. This is not accurate. If the link state is in U1/U2, then the controller will not respond to link recovery request from DCTL.ULSTCHNGREQ. The Start Transfer command will trigger a link recovery if it is in U1/U2. A clarification will be added to the programming guide for all controller versions. The current implementation shouldn't cause any functional issue. It may occasionally report an invalid time out warning from failed link recovery request. The driver will still go ahead with the Start Transfer command if the remote wakeup fails. The new change only initiates remote wakeup where it is needed, which is when the link state is in L1/L2/U3. Fixes: c36d8e947a56 ("usb: dwc3: gadget: put link to U0 before Start Transfer") Cc: Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/05b4a5fbfbd0863fc9b1d7af934a366219e3d0b4.1635204761.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 3d6f4adaa15a5a..daa8f8548a2e18 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -310,13 +310,24 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, if (DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_STARTTRANSFER) { int link_state; + /* + * Initiate remote wakeup if the link state is in U3 when + * operating in SS/SSP or L1/L2 when operating in HS/FS. If the + * link state is in U1/U2, no remote wakeup is needed. The Start + * Transfer command will initiate the link recovery. + */ link_state = dwc3_gadget_get_link_state(dwc); - if (link_state == DWC3_LINK_STATE_U1 || - link_state == DWC3_LINK_STATE_U2 || - link_state == DWC3_LINK_STATE_U3) { + switch (link_state) { + case DWC3_LINK_STATE_U2: + if (dwc->gadget->speed >= USB_SPEED_SUPER) + break; + + fallthrough; + case DWC3_LINK_STATE_U3: ret = __dwc3_gadget_wakeup(dwc); dev_WARN_ONCE(dwc->dev, ret, "wakeup failed --> %d\n", ret); + break; } } From 7ad4a0b1d46b2612f4429a72afd8f137d7efa9a9 Mon Sep 17 00:00:00 2001 From: Minas Harutyunyan Date: Thu, 4 Nov 2021 11:36:01 +0400 Subject: [PATCH 090/358] usb: dwc2: gadget: Fix ISOC flow for elapsed frames Added updating of request frame number for elapsed frames, otherwise frame number will remain as previous use of request. This will allow function driver to correctly track frames in case of Missed ISOC occurs. Added setting request actual length to 0 for elapsed frames. In Slave mode when pushing data to RxFIFO by dwords, request actual length incrementing accordingly. But before whole packet will be pushed into RxFIFO and send to host can occurs Missed ISOC and data will not send to host. So, in this case request actual length should be reset to 0. Fixes: 91bb163e1e4f ("usb: dwc2: gadget: Fix ISOC flow for BDMA and Slave") Cc: stable Reviewed-by: John Keeping Signed-off-by: Minas Harutyunyan Link: https://lore.kernel.org/r/c356baade6e9716d312d43df08d53ae557cb8037.1636011277.git.Minas.Harutyunyan@synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/gadget.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 4ab4a1d5062b2a..ab8d7dad9f5670 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -1198,6 +1198,8 @@ static void dwc2_hsotg_start_req(struct dwc2_hsotg *hsotg, } ctrl |= DXEPCTL_CNAK; } else { + hs_req->req.frame_number = hs_ep->target_frame; + hs_req->req.actual = 0; dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, -ENODATA); return; } @@ -2857,9 +2859,12 @@ static void dwc2_gadget_handle_ep_disabled(struct dwc2_hsotg_ep *hs_ep) do { hs_req = get_ep_head(hs_ep); - if (hs_req) + if (hs_req) { + hs_req->req.frame_number = hs_ep->target_frame; + hs_req->req.actual = 0; dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, -ENODATA); + } dwc2_gadget_incr_frame_num(hs_ep); /* Update current frame number value. */ hsotg->frame_number = dwc2_hsotg_read_frameno(hsotg); @@ -2912,8 +2917,11 @@ static void dwc2_gadget_handle_out_token_ep_disabled(struct dwc2_hsotg_ep *ep) while (dwc2_gadget_target_frame_elapsed(ep)) { hs_req = get_ep_head(ep); - if (hs_req) + if (hs_req) { + hs_req->req.frame_number = ep->target_frame; + hs_req->req.actual = 0; dwc2_hsotg_complete_request(hsotg, ep, hs_req, -ENODATA); + } dwc2_gadget_incr_frame_num(ep); /* Update current frame number value. */ @@ -3002,8 +3010,11 @@ static void dwc2_gadget_handle_nak(struct dwc2_hsotg_ep *hs_ep) while (dwc2_gadget_target_frame_elapsed(hs_ep)) { hs_req = get_ep_head(hs_ep); - if (hs_req) + if (hs_req) { + hs_req->req.frame_number = hs_ep->target_frame; + hs_req->req.actual = 0; dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, -ENODATA); + } dwc2_gadget_incr_frame_num(hs_ep); /* Update current frame number value. */ From 51f2246158f686c881859f4b620f831f06e296e1 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 8 Nov 2021 01:44:55 +0300 Subject: [PATCH 091/358] usb: xhci: tegra: Check padctrl interrupt presence in device tree Older device-trees don't specify padctrl interrupt and xhci-tegra driver now fails to probe with -EINVAL using those device-trees. Check interrupt presence and keep runtime PM disabled if it's missing to fix the trouble. Fixes: 971ee247060d ("usb: xhci: tegra: Enable ELPG for runtime/system PM") Cc: # 5.14+ Reported-by: Nicolas Chauvet Tested-by: Nicolas Chauvet # T124 TK1 Tested-by: Thomas Graichen # T124 Nyan Big Tested-by: Thierry Reding # Tegra CI Acked-by: Thierry Reding Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20211107224455.10359-1-digetx@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-tegra.c | 41 +++++++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 12 deletions(-) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 1bf494b649bd24..c8af2cd2216d60 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1400,6 +1400,7 @@ static void tegra_xusb_deinit_usb_phy(struct tegra_xusb *tegra) static int tegra_xusb_probe(struct platform_device *pdev) { + struct of_phandle_args args; struct tegra_xusb *tegra; struct device_node *np; struct resource *regs; @@ -1454,10 +1455,17 @@ static int tegra_xusb_probe(struct platform_device *pdev) goto put_padctl; } - tegra->padctl_irq = of_irq_get(np, 0); - if (tegra->padctl_irq <= 0) { - err = (tegra->padctl_irq == 0) ? -ENODEV : tegra->padctl_irq; - goto put_padctl; + /* Older device-trees don't have padctrl interrupt */ + err = of_irq_parse_one(np, 0, &args); + if (!err) { + tegra->padctl_irq = of_irq_get(np, 0); + if (tegra->padctl_irq <= 0) { + err = (tegra->padctl_irq == 0) ? -ENODEV : tegra->padctl_irq; + goto put_padctl; + } + } else { + dev_dbg(&pdev->dev, + "%pOF is missing an interrupt, disabling PM support\n", np); } tegra->host_clk = devm_clk_get(&pdev->dev, "xusb_host"); @@ -1696,11 +1704,15 @@ static int tegra_xusb_probe(struct platform_device *pdev) goto remove_usb3; } - err = devm_request_threaded_irq(&pdev->dev, tegra->padctl_irq, NULL, tegra_xusb_padctl_irq, - IRQF_ONESHOT, dev_name(&pdev->dev), tegra); - if (err < 0) { - dev_err(&pdev->dev, "failed to request padctl IRQ: %d\n", err); - goto remove_usb3; + if (tegra->padctl_irq) { + err = devm_request_threaded_irq(&pdev->dev, tegra->padctl_irq, + NULL, tegra_xusb_padctl_irq, + IRQF_ONESHOT, dev_name(&pdev->dev), + tegra); + if (err < 0) { + dev_err(&pdev->dev, "failed to request padctl IRQ: %d\n", err); + goto remove_usb3; + } } err = tegra_xusb_enable_firmware_messages(tegra); @@ -1718,13 +1730,16 @@ static int tegra_xusb_probe(struct platform_device *pdev) /* Enable wake for both USB 2.0 and USB 3.0 roothubs */ device_init_wakeup(&tegra->hcd->self.root_hub->dev, true); device_init_wakeup(&xhci->shared_hcd->self.root_hub->dev, true); - device_init_wakeup(tegra->dev, true); pm_runtime_use_autosuspend(tegra->dev); pm_runtime_set_autosuspend_delay(tegra->dev, 2000); pm_runtime_mark_last_busy(tegra->dev); pm_runtime_set_active(tegra->dev); - pm_runtime_enable(tegra->dev); + + if (tegra->padctl_irq) { + device_init_wakeup(tegra->dev, true); + pm_runtime_enable(tegra->dev); + } return 0; @@ -1772,7 +1787,9 @@ static int tegra_xusb_remove(struct platform_device *pdev) dma_free_coherent(&pdev->dev, tegra->fw.size, tegra->fw.virt, tegra->fw.phys); - pm_runtime_disable(&pdev->dev); + if (tegra->padctl_irq) + pm_runtime_disable(&pdev->dev); + pm_runtime_put(&pdev->dev); tegra_xusb_powergate_partitions(tegra); From 3b8599a6f4817bdd7c5e7145f2972b7f22f00a9d Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 7 Nov 2021 17:25:48 +0100 Subject: [PATCH 092/358] usb: gadget: udc-xilinx: Fix an error handling path in 'xudc_probe()' A successful 'clk_prepare_enable()' call should be balanced by a corresponding 'clk_disable_unprepare()' call in the error handling path of the probe, as already done in the remove function. Fixes: 24749229211c ("usb: gadget: udc-xilinx: Add clock support") Reviewed-by: Shubhrajyoti Datta Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/ec61a89b83ce34b53a3bdaacfd1413a9869cc608.1636302246.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/udc-xilinx.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/udc-xilinx.c b/drivers/usb/gadget/udc/udc-xilinx.c index f5ca670776a370..857159dd5ae05f 100644 --- a/drivers/usb/gadget/udc/udc-xilinx.c +++ b/drivers/usb/gadget/udc/udc-xilinx.c @@ -2136,7 +2136,7 @@ static int xudc_probe(struct platform_device *pdev) ret = usb_add_gadget_udc(&pdev->dev, &udc->gadget); if (ret) - goto fail; + goto err_disable_unprepare_clk; udc->dev = &udc->gadget.dev; @@ -2155,6 +2155,9 @@ static int xudc_probe(struct platform_device *pdev) udc->dma_enabled ? "with DMA" : "without DMA"); return 0; + +err_disable_unprepare_clk: + clk_disable_unprepare(udc->clk); fail: dev_err(&pdev->dev, "probe failed, %d\n", ret); return ret; From 26288448120b28af1dfd85a6fa6b6d55a16c7f2f Mon Sep 17 00:00:00 2001 From: Albert Wang Date: Tue, 9 Nov 2021 17:26:42 +0800 Subject: [PATCH 093/358] usb: dwc3: gadget: Fix null pointer exception In the endpoint interrupt functions dwc3_gadget_endpoint_transfer_in_progress() and dwc3_gadget_endpoint_trbs_complete() will dereference the endpoint descriptor. But it could be cleared in __dwc3_gadget_ep_disable() when accessory disconnected. So we need to check whether it is null or not before dereferencing it. Fixes: f09ddcfcb8c5 ("usb: dwc3: gadget: Prevent EP queuing while stopping transfers") Cc: stable Reviewed-by: Jack Pham Signed-off-by: Albert Wang Link: https://lore.kernel.org/r/20211109092642.3507692-1-albertccwang@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index daa8f8548a2e18..7e3db00e975952 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3263,6 +3263,9 @@ static bool dwc3_gadget_endpoint_trbs_complete(struct dwc3_ep *dep, struct dwc3 *dwc = dep->dwc; bool no_started_trb = true; + if (!dep->endpoint.desc) + return no_started_trb; + dwc3_gadget_ep_cleanup_completed_requests(dep, event, status); if (dep->flags & DWC3_EP_END_TRANSFER_PENDING) @@ -3310,6 +3313,9 @@ static void dwc3_gadget_endpoint_transfer_in_progress(struct dwc3_ep *dep, { int status = 0; + if (!dep->endpoint.desc) + return; + if (usb_endpoint_xfer_isoc(dep->endpoint.desc)) dwc3_gadget_endpoint_frame_from_event(dep, event); From 310780e825f3ffd211b479b8f828885a6faedd63 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 5 Nov 2021 07:58:03 -0700 Subject: [PATCH 094/358] usb: dwc2: hcd_queue: Fix use of floating point literal A new commit in LLVM causes an error on the use of 'long double' when '-mno-x87' is used, which the kernel does through an alias, '-mno-80387' (see the LLVM commit below for more details around why it does this). drivers/usb/dwc2/hcd_queue.c:1744:25: error: expression requires 'long double' type support, but target 'x86_64-unknown-linux-gnu' does not support it delay = ktime_set(0, DWC2_RETRY_WAIT_DELAY); ^ drivers/usb/dwc2/hcd_queue.c:62:34: note: expanded from macro 'DWC2_RETRY_WAIT_DELAY' #define DWC2_RETRY_WAIT_DELAY (1 * 1E6L) ^ 1 error generated. This happens due to the use of a 'long double' literal. The 'E6' part of '1E6L' causes the literal to be a 'double' then the 'L' suffix promotes it to 'long double'. There is no visible reason for a floating point value in this driver, as the value is only used as a parameter to a function that expects an integer type. Use NSEC_PER_MSEC, which is the same integer value as '1E6L', to avoid changing functionality but fix the error. Link: https://github.com/ClangBuiltLinux/linux/issues/1497 Link: https://github.com/llvm/llvm-project/commit/a8083d42b1c346e21623a1d36d1f0cadd7801d83 Fixes: 6ed30a7d8ec2 ("usb: dwc2: host: use hrtimer for NAK retries") Cc: stable Reviewed-by: Nick Desaulniers Reviewed-by: John Keeping Acked-by: Minas Harutyunyan Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20211105145802.2520658-1-nathan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/hcd_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/dwc2/hcd_queue.c b/drivers/usb/dwc2/hcd_queue.c index 89a788326c5620..24beff610cf2c6 100644 --- a/drivers/usb/dwc2/hcd_queue.c +++ b/drivers/usb/dwc2/hcd_queue.c @@ -59,7 +59,7 @@ #define DWC2_UNRESERVE_DELAY (msecs_to_jiffies(5)) /* If we get a NAK, wait this long before retrying */ -#define DWC2_RETRY_WAIT_DELAY (1 * 1E6L) +#define DWC2_RETRY_WAIT_DELAY (1 * NSEC_PER_MSEC) /** * dwc2_periodic_channel_available() - Checks that a channel is available for a From 47ce45906ca9870cf5267261f155fb7c70307cf0 Mon Sep 17 00:00:00 2001 From: Fabio Aiuto Date: Sat, 13 Nov 2021 15:29:59 +0100 Subject: [PATCH 095/358] usb: dwc3: leave default DMA for PCI devices in case of a PCI dwc3 controller, leave the default DMA mask. Calling of a 64 bit DMA mask breaks the driver on cherrytrail based tablets like Cyberbook T116. Fixes: 45d39448b4d0 ("usb: dwc3: support 64 bit DMA in platform driver") Cc: stable Reported-by: Hans De Goede Tested-by: Fabio Aiuto Tested-by: Hans de Goede Signed-off-by: Fabio Aiuto Link: https://lore.kernel.org/r/20211113142959.27191-1-fabioaiuto83@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 643239d7d37007..f4c09951b517eb 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1594,9 +1594,11 @@ static int dwc3_probe(struct platform_device *pdev) dwc3_get_properties(dwc); - ret = dma_set_mask_and_coherent(dwc->sysdev, DMA_BIT_MASK(64)); - if (ret) - return ret; + if (!dwc->sysdev_is_parent) { + ret = dma_set_mask_and_coherent(dwc->sysdev, DMA_BIT_MASK(64)); + if (ret) + return ret; + } dwc->reset = devm_reset_control_array_get_optional_shared(dev); if (IS_ERR(dwc->reset)) From 362468830dd5bea8bf6ad5203b2ea61f8a4e8288 Mon Sep 17 00:00:00 2001 From: Ondrej Jirman Date: Mon, 8 Nov 2021 11:28:32 +0100 Subject: [PATCH 096/358] usb: typec: fusb302: Fix masking of comparator and bc_lvl interrupts The code that enables either BC_LVL or COMP_CHNG interrupt in tcpm_set_cc wrongly assumes that the interrupt is unmasked by writing 1 to the apropriate bit in the mask register. In fact, interrupts are enabled when the mask is 0, so the tcpm_set_cc enables interrupt for COMP_CHNG when it expects BC_LVL interrupt to be enabled. This causes inability of the driver to recognize cable unplug events in host mode (unplug is recognized only via a COMP_CHNG interrupt). In device mode this bug was masked by simultaneous triggering of the VBUS change interrupt, because of loss of VBUS when the port peer is providing power. Fixes: 48242e30532b ("usb: typec: fusb302: Revert "Resolve fixed power role contract setup"") Cc: stable Cc: Hans de Goede Reviewed-by: Hans de Goede Acked-by: Heikki Krogerus Signed-off-by: Ondrej Jirman Link: https://lore.kernel.org/r/20211108102833.2793803-1-megous@megous.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/fusb302.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c index 7a2a17866a823b..72f9001b07921c 100644 --- a/drivers/usb/typec/tcpm/fusb302.c +++ b/drivers/usb/typec/tcpm/fusb302.c @@ -669,25 +669,27 @@ static int tcpm_set_cc(struct tcpc_dev *dev, enum typec_cc_status cc) ret = fusb302_i2c_mask_write(chip, FUSB_REG_MASK, FUSB_REG_MASK_BC_LVL | FUSB_REG_MASK_COMP_CHNG, - FUSB_REG_MASK_COMP_CHNG); + FUSB_REG_MASK_BC_LVL); if (ret < 0) { fusb302_log(chip, "cannot set SRC interrupt, ret=%d", ret); goto done; } chip->intr_comp_chng = true; + chip->intr_bc_lvl = false; break; case TYPEC_CC_RD: ret = fusb302_i2c_mask_write(chip, FUSB_REG_MASK, FUSB_REG_MASK_BC_LVL | FUSB_REG_MASK_COMP_CHNG, - FUSB_REG_MASK_BC_LVL); + FUSB_REG_MASK_COMP_CHNG); if (ret < 0) { fusb302_log(chip, "cannot set SRC interrupt, ret=%d", ret); goto done; } chip->intr_bc_lvl = true; + chip->intr_comp_chng = false; break; default: break; From 6ae6dc22d2d1ce6aa77a6da8a761e61aca216f8b Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Tue, 16 Nov 2021 00:16:30 +0200 Subject: [PATCH 097/358] usb: hub: Fix usb enumeration issue due to address0 race xHC hardware can only have one slot in default state with address 0 waiting for a unique address at a time, otherwise "undefined behavior may occur" according to xhci spec 5.4.3.4 The address0_mutex exists to prevent this across both xhci roothubs. If hub_port_init() fails, it may unlock the mutex and exit with a xhci slot in default state. If the other xhci roothub calls hub_port_init() at this point we end up with two slots in default state. Make sure the address0_mutex protects the slot default state across hub_port_init() retries, until slot is addressed or disabled. Note, one known minor case is not fixed by this patch. If device needs to be reset during resume, but fails all hub_port_init() retries in usb_reset_and_verify_device(), then it's possible the slot is still left in default state when address0_mutex is unlocked. Cc: Fixes: 638139eb95d2 ("usb: hub: allow to process more usb hub events in parallel") Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20211115221630.871204-1-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 86658a81d28445..00c3506324e47d 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4700,8 +4700,6 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, if (oldspeed == USB_SPEED_LOW) delay = HUB_LONG_RESET_TIME; - mutex_lock(hcd->address0_mutex); - /* Reset the device; full speed may morph to high speed */ /* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */ retval = hub_port_reset(hub, port1, udev, delay, false); @@ -5016,7 +5014,6 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, hub_port_disable(hub, port1, 0); update_devnum(udev, devnum); /* for disconnect processing */ } - mutex_unlock(hcd->address0_mutex); return retval; } @@ -5246,6 +5243,9 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, unit_load = 100; status = 0; + + mutex_lock(hcd->address0_mutex); + for (i = 0; i < PORT_INIT_TRIES; i++) { /* reallocate for each attempt, since references @@ -5282,6 +5282,8 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, if (status < 0) goto loop; + mutex_unlock(hcd->address0_mutex); + if (udev->quirks & USB_QUIRK_DELAY_INIT) msleep(2000); @@ -5370,6 +5372,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, loop_disable: hub_port_disable(hub, port1, 1); + mutex_lock(hcd->address0_mutex); loop: usb_ep0_reinit(udev); release_devnum(udev); @@ -5396,6 +5399,8 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, } done: + mutex_unlock(hcd->address0_mutex); + hub_port_disable(hub, port1, 1); if (hcd->driver->relinquish_port && !hub->hdev->parent) { if (status != -ENOTCONN && status != -ENODEV) @@ -5915,6 +5920,8 @@ static int usb_reset_and_verify_device(struct usb_device *udev) bos = udev->bos; udev->bos = NULL; + mutex_lock(hcd->address0_mutex); + for (i = 0; i < PORT_INIT_TRIES; ++i) { /* ep0 maxpacket size may change; let the HCD know about it. @@ -5924,6 +5931,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) if (ret >= 0 || ret == -ENOTCONN || ret == -ENODEV) break; } + mutex_unlock(hcd->address0_mutex); if (ret < 0) goto re_enumerate; From d4d2e5329ae9dfd6742c84d79f7d143d10410f1b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 17 Nov 2021 10:49:23 +0300 Subject: [PATCH 098/358] usb: chipidea: ci_hdrc_imx: fix potential error pointer dereference in probe If the first call to devm_usb_get_phy_by_phandle(dev, "fsl,usbphy", 0) fails with something other than -ENODEV then it leads to an error pointer dereference. For those errors we should just jump directly to the error handling. Fixes: 8253a34bfae3 ("usb: chipidea: ci_hdrc_imx: Also search for 'phys' phandle") Cc: stable Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20211117074923.GF5237@kili Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/ci_hdrc_imx.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index f1d100671ee6a1..097142ffb18420 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -420,15 +420,15 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) data->phy = devm_usb_get_phy_by_phandle(dev, "fsl,usbphy", 0); if (IS_ERR(data->phy)) { ret = PTR_ERR(data->phy); - if (ret == -ENODEV) { - data->phy = devm_usb_get_phy_by_phandle(dev, "phys", 0); - if (IS_ERR(data->phy)) { - ret = PTR_ERR(data->phy); - if (ret == -ENODEV) - data->phy = NULL; - else - goto err_clk; - } + if (ret != -ENODEV) + goto err_clk; + data->phy = devm_usb_get_phy_by_phandle(dev, "phys", 0); + if (IS_ERR(data->phy)) { + ret = PTR_ERR(data->phy); + if (ret == -ENODEV) + data->phy = NULL; + else + goto err_clk; } } From c21a80ca0684ec2910344d72556c816cb8940c01 Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Fri, 12 Nov 2021 10:07:20 -0800 Subject: [PATCH 099/358] binder: fix test regression due to sender_euid change This is a partial revert of commit 29bc22ac5e5b ("binder: use euid from cred instead of using task"). Setting sender_euid using proc->cred caused some Android system test regressions that need further investigation. It is a partial reversion because subsequent patches rely on proc->cred. Fixes: 29bc22ac5e5b ("binder: use euid from cred instead of using task") Cc: stable@vger.kernel.org # 4.4+ Acked-by: Christian Brauner Signed-off-by: Todd Kjos Change-Id: I9b1769a3510fed250bb21859ef8beebabe034c66 Link: https://lore.kernel.org/r/20211112180720.2858135-1-tkjos@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 49fb74196d02fb..cffbe57a8e0863 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2710,7 +2710,7 @@ static void binder_transaction(struct binder_proc *proc, t->from = thread; else t->from = NULL; - t->sender_euid = proc->cred->euid; + t->sender_euid = task_euid(proc->tsk); t->to_proc = target_proc; t->to_thread = target_thread; t->code = tr->code; From 522a0032af005502507f5f81ae64fdcc82b5d068 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 6 Nov 2021 17:13:35 -0400 Subject: [PATCH 100/358] Add linux/cacheflush.h Many architectures do not include asm-generic/cacheflush.h, so turn the includes on their head and add linux/cacheflush.h which includes asm/cacheflush.h. Move the flush_dcache_folio() declaration from asm-generic/cacheflush.h to linux/cacheflush.h and change linux/highmem.h to include linux/cacheflush.h instead of asm/cacheflush.h so that all necessary places will see flush_dcache_folio(). More functions should have their default implementations moved in the future, but those are for follow-on patches. This fixes csky, sparc and sparc64 which were missed in the commit which added flush_dcache_folio(). Fixes: 08b0b0059bf1 ("mm: Add flush_dcache_folio()") Suggested-by: Christoph Hellwig Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Geert Uytterhoeven --- arch/arc/include/asm/cacheflush.h | 1 - arch/arm/include/asm/cacheflush.h | 1 - arch/m68k/include/asm/cacheflush_mm.h | 1 - arch/mips/include/asm/cacheflush.h | 2 -- arch/nds32/include/asm/cacheflush.h | 1 - arch/nios2/include/asm/cacheflush.h | 1 - arch/parisc/include/asm/cacheflush.h | 1 - arch/sh/include/asm/cacheflush.h | 1 - arch/xtensa/include/asm/cacheflush.h | 3 --- include/asm-generic/cacheflush.h | 6 ------ include/linux/cacheflush.h | 18 ++++++++++++++++++ include/linux/highmem.h | 3 +-- 12 files changed, 19 insertions(+), 20 deletions(-) create mode 100644 include/linux/cacheflush.h diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index e8c2c7469e107f..e201b4b1655afe 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -36,7 +36,6 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); void dma_cache_wback_inv(phys_addr_t start, unsigned long sz); void dma_cache_inv(phys_addr_t start, unsigned long sz); diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index e68fb879e4f9d5..5e56288e343bb6 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -290,7 +290,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); -void flush_dcache_folio(struct folio *folio); #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h index 8ab46625ddd32d..1ac55e7b47f01c 100644 --- a/arch/m68k/include/asm/cacheflush_mm.h +++ b/arch/m68k/include/asm/cacheflush_mm.h @@ -250,7 +250,6 @@ static inline void __flush_page_to_ram(void *vaddr) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) __flush_page_to_ram(page_address(page)) -void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_icache_page(vma, page) __flush_page_to_ram(page_address(page)) diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index f207388541d509..b3dc9c589442a8 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -61,8 +61,6 @@ static inline void flush_dcache_page(struct page *page) SetPageDcacheDirty(page); } -void flush_dcache_folio(struct folio *folio); - #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index 3fc0bb7d6487cc..c2a222ebfa2af1 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -27,7 +27,6 @@ void flush_cache_vunmap(unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, void *src, int len); void copy_from_user_page(struct vm_area_struct *vma, struct page *page, diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h index 1999561b22aa50..d0b71dd7128724 100644 --- a/arch/nios2/include/asm/cacheflush.h +++ b/arch/nios2/include/asm/cacheflush.h @@ -29,7 +29,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); extern void flush_icache_page(struct vm_area_struct *vma, struct page *page); diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index da0cd4b3a28f29..859b8a34adcfbc 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -50,7 +50,6 @@ void invalidate_kernel_vmap_range(void *vaddr, int size); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index c7a97f32432fb2..481a664287e2e4 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -43,7 +43,6 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); #define flush_icache_user_range flush_icache_range extern void flush_icache_page(struct vm_area_struct *vma, diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index a8a041609c5d0e..7b4359312c2576 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -121,7 +121,6 @@ void flush_cache_page(struct vm_area_struct*, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *); -void flush_dcache_folio(struct folio *); void local_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -138,9 +137,7 @@ void local_flush_cache_page(struct vm_area_struct *vma, #define flush_cache_vunmap(start,end) do { } while (0) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO #define flush_dcache_page(page) do { } while (0) -static inline void flush_dcache_folio(struct folio *folio) { } #define flush_icache_range local_flush_icache_range #define flush_cache_page(vma, addr, pfn) do { } while (0) diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index fedc0dfa4877c7..4f07afacbc2395 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -50,13 +50,7 @@ static inline void flush_dcache_page(struct page *page) { } -static inline void flush_dcache_folio(struct folio *folio) { } #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO -#endif - -#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO -void flush_dcache_folio(struct folio *folio); #endif #ifndef flush_dcache_mmap_lock diff --git a/include/linux/cacheflush.h b/include/linux/cacheflush.h new file mode 100644 index 00000000000000..fef8b607f97e28 --- /dev/null +++ b/include/linux/cacheflush.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CACHEFLUSH_H +#define _LINUX_CACHEFLUSH_H + +#include + +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO +void flush_dcache_folio(struct folio *folio); +#endif +#else +static inline void flush_dcache_folio(struct folio *folio) +{ +} +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO 0 +#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */ + +#endif /* _LINUX_CACHEFLUSH_H */ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 25aff0f2ed0b00..c944b3b70ee7bb 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -5,12 +5,11 @@ #include #include #include +#include #include #include #include -#include - #include "highmem-internal.h" /** From 9c3252152e8a6401c2b9e32490a5a16ec4472778 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 16 Nov 2021 21:17:14 -0500 Subject: [PATCH 101/358] mm: Rename folio_test_multi to folio_test_large This is a better name. Also add kernel-doc. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/page-flags.h | 8 +++++++- mm/memcontrol.c | 2 +- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 52ec4b5e561566..05510118fbb86a 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -692,7 +692,13 @@ static inline bool folio_test_single(struct folio *folio) return !folio_test_head(folio); } -static inline bool folio_test_multi(struct folio *folio) +/** + * folio_test_large() - Does this folio contain more than one page? + * @folio: The folio to test. + * + * Return: True if the folio is larger than one page. + */ +static inline bool folio_test_large(struct folio *folio) { return folio_test_head(folio); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 781605e920153c..6863a834ed4257 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5558,7 +5558,7 @@ static int mem_cgroup_move_account(struct page *page, VM_BUG_ON(from == to); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - VM_BUG_ON(compound && !folio_test_multi(folio)); + VM_BUG_ON(compound && !folio_test_large(folio)); /* * Prevent mem_cgroup_migrate() from looking at From a1efe484dd8c04c4c2d4eb1ee6b04d01cfc07ccc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 16 Nov 2021 21:18:52 -0500 Subject: [PATCH 102/358] mm: Remove folio_test_single There's no need for this predicate; callers can just use !folio_test_large(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/page-flags.h | 6 ------ mm/util.c | 2 +- 2 files changed, 1 insertion(+), 7 deletions(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 05510118fbb86a..b5f14d5811135f 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -686,12 +686,6 @@ static inline bool test_set_page_writeback(struct page *page) __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) -/* Whether there are one or multiple pages in a folio */ -static inline bool folio_test_single(struct folio *folio) -{ - return !folio_test_head(folio); -} - /** * folio_test_large() - Does this folio contain more than one page? * @folio: The folio to test. diff --git a/mm/util.c b/mm/util.c index e58151a612555c..741ba32a43ac4b 100644 --- a/mm/util.c +++ b/mm/util.c @@ -670,7 +670,7 @@ bool folio_mapped(struct folio *folio) { long i, nr; - if (folio_test_single(folio)) + if (!folio_test_large(folio)) return atomic_read(&folio->_mapcount) >= 0; if (atomic_read(folio_mapcount_ptr(folio)) >= 0) return true; From ff36da69bc90d80b0c73f47f4b2e270b3ff6da99 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 29 Aug 2021 06:07:03 -0400 Subject: [PATCH 103/358] fs: Remove FS_THP_SUPPORT Instead of setting a bit in the fs_flags to set a bit in the address_space, set the bit in the address_space directly. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- fs/inode.c | 2 -- include/linux/fs.h | 1 - include/linux/pagemap.h | 16 ++++++++++++++++ mm/shmem.c | 3 ++- 4 files changed, 18 insertions(+), 4 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 3eba0940ffcf16..6b80a51129d56f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -180,8 +180,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode) mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; - if (sb->s_type->fs_flags & FS_THP_SUPPORT) - __set_bit(AS_THP_SUPPORT, &mapping->flags); mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS diff --git a/include/linux/fs.h b/include/linux/fs.h index 1cb616fc11053b..bbf812ce89a8c0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2518,7 +2518,6 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ -#define FS_THP_SUPPORT 8192 /* Remove once all fs converted */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1a0c646eb6ff7c..9e33878bf23b27 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -176,6 +176,22 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +/** + * mapping_set_large_folios() - Indicate the file supports large folios. + * @mapping: The file. + * + * The filesystem should call this function in its inode constructor to + * indicate that the VFS can use large folios to cache the contents of + * the file. + * + * Context: This should not be called while the inode is active as it + * is non-atomic. + */ +static inline void mapping_set_large_folios(struct address_space *mapping) +{ + __set_bit(AS_THP_SUPPORT, &mapping->flags); +} + static inline bool mapping_thp_support(struct address_space *mapping) { return test_bit(AS_THP_SUPPORT, &mapping->flags); diff --git a/mm/shmem.c b/mm/shmem.c index dc038ce78700cc..18f93c2d68f16e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2303,6 +2303,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); + mapping_set_large_folios(inode->i_mapping); switch (mode & S_IFMT) { default: @@ -3870,7 +3871,7 @@ static struct file_system_type shmem_fs_type = { .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, - .fs_flags = FS_USERNS_MOUNT | FS_THP_SUPPORT, + .fs_flags = FS_USERNS_MOUNT, }; int __init shmem_init(void) From ed2145c474c9015bc634e35f6d1a9b7767f3fbfc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 29 Aug 2021 06:28:19 -0400 Subject: [PATCH 104/358] fs: Rename AS_THP_SUPPORT and mapping_thp_support These are now indicators of large folio support, not THP support. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/pagemap.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 9e33878bf23b27..60524645230514 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -84,7 +84,7 @@ enum mapping_flags { AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, - AS_THP_SUPPORT = 6, /* THPs supported */ + AS_LARGE_FOLIO_SUPPORT = 6, }; /** @@ -189,12 +189,12 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) */ static inline void mapping_set_large_folios(struct address_space *mapping) { - __set_bit(AS_THP_SUPPORT, &mapping->flags); + __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } -static inline bool mapping_thp_support(struct address_space *mapping) +static inline bool mapping_large_folio_support(struct address_space *mapping) { - return test_bit(AS_THP_SUPPORT, &mapping->flags); + return test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } static inline int filemap_nr_thps(struct address_space *mapping) @@ -209,7 +209,7 @@ static inline int filemap_nr_thps(struct address_space *mapping) static inline void filemap_nr_thps_inc(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS - if (!mapping_thp_support(mapping)) + if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else WARN_ON_ONCE(1); @@ -219,7 +219,7 @@ static inline void filemap_nr_thps_inc(struct address_space *mapping) static inline void filemap_nr_thps_dec(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS - if (!mapping_thp_support(mapping)) + if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else WARN_ON_ONCE(1); From d3c45824ad65aebf765fcf51366d317a29538820 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 16 Nov 2021 09:55:01 -0500 Subject: [PATCH 105/358] NFSv42: Don't fail clone() unless the OP_CLONE operation failed The failure to retrieve post-op attributes has no bearing on whether or not the clone operation itself was successful. We must therefore ignore the return value of decode_getfattr() when looking at the success or failure of nfs4_xdr_dec_clone(). Fixes: 36022770de6c ("nfs42: add CLONE xdr functions") Signed-off-by: Trond Myklebust --- fs/nfs/nfs42xdr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index c8bad735e4c19d..271e5f92ed0195 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -1434,8 +1434,7 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, status = decode_clone(xdr); if (status) goto out; - status = decode_getfattr(xdr, res->dst_fattr, res->server); - + decode_getfattr(xdr, res->dst_fattr, res->server); out: res->rpc_status = status; return status; From 93c2e5e0a9ecfc183ab1204e1ecaa7ee7eb2a61a Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 16 Nov 2021 08:49:24 -0500 Subject: [PATCH 106/358] NFS: Add a tracepoint to show the results of nfs_set_cache_invalid() This provides some insight into the client's invalidation behavior to show both when the client uses the helper, and the results of calling the helper which can vary depending on how the helper is called. Signed-off-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 1 + fs/nfs/nfstrace.h | 1 + 2 files changed, 2 insertions(+) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index dd53704c3f4040..fda530d5e76405 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -219,6 +219,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) NFS_INO_DATA_INVAL_DEFER); else if (nfsi->cache_validity & NFS_INO_INVALID_DATA) nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; + trace_nfs_set_cache_invalid(inode, 0); } EXPORT_SYMBOL_GPL(nfs_set_cache_invalid); diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 21dac847f1e404..b3aee261801e5d 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -162,6 +162,7 @@ DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_inode_exit); DEFINE_NFS_INODE_EVENT(nfs_fsync_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit); DEFINE_NFS_INODE_EVENT(nfs_access_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid); TRACE_EVENT(nfs_access_exit, TP_PROTO( From 3f015d89a47cd8855cd92f71fff770095bd885a1 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 16 Nov 2021 10:48:13 -0500 Subject: [PATCH 107/358] NFSv42: Fix pagecache invalidation after COPY/CLONE The mechanism in use to allow the client to see the results of COPY/CLONE is to drop those pages from the pagecache. This forces the client to read those pages once more from the server. However, truncate_pagecache_range() zeros out partial pages instead of dropping them. Let us instead use invalidate_inode_pages2_range() with full-page offsets to ensure the client properly sees the results of COPY/CLONE operations. Cc: # v4.7+ Fixes: 2e72448b07dc ("NFS: Add COPY nfs operation") Signed-off-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- fs/nfs/nfs42proc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 08355b66e7cb81..8b21ff1be71754 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -289,7 +289,9 @@ static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len) loff_t newsize = pos + len; loff_t end = newsize - 1; - truncate_pagecache_range(inode, pos, end); + WARN_ON_ONCE(invalidate_inode_pages2_range(inode->i_mapping, + pos >> PAGE_SHIFT, end >> PAGE_SHIFT)); + spin_lock(&inode->i_lock); if (newsize > i_size_read(inode)) i_size_write(inode, newsize); From ea027cb2e1b59c76582af867b71d5c037fa6bb8e Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 15 Nov 2021 16:30:40 -0500 Subject: [PATCH 108/358] NFSv4.1: handle NFS4ERR_NOSPC by CREATE_SESSION When the client receives ERR_NOSPC on reply to CREATE_SESSION it leads to a client hanging in nfs_wait_client_init_complete(). Instead, complete and fail the client initiation with an EIO error which allows for the mount command to fail instead of hanging. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- fs/nfs/nfs4state.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index ecc4594299d6fe..f63dfa01001c97 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1998,6 +1998,10 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) dprintk("%s: exit with error %d for server %s\n", __func__, -EPROTONOSUPPORT, clp->cl_hostname); return -EPROTONOSUPPORT; + case -ENOSPC: + if (clp->cl_cons_state == NFS_CS_SESSION_INITING) + nfs_mark_client_ready(clp, -EIO); + return -EIO; case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery * in nfs4_exchange_id */ default: From 268bb03856ed6c8511c31d08de0148782f50822f Mon Sep 17 00:00:00 2001 From: Thiago Rafael Becker Date: Wed, 17 Nov 2021 10:26:30 -0300 Subject: [PATCH 109/358] sunrpc: fix header include guard in trace header rpcgss.h include protection was protecting against the define for rpcrdma.h. Signed-off-by: Thiago Rafael Becker Signed-off-by: Trond Myklebust --- include/trace/events/rpcgss.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index 3ba63319af3cd7..c9048f3e471bb9 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -8,7 +8,7 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM rpcgss -#if !defined(_TRACE_RPCRDMA_H) || defined(TRACE_HEADER_MULTI_READ) +#if !defined(_TRACE_RPCGSS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RPCGSS_H #include From 05ec7161084565365ecf267e9909a897a95f243a Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 18 Nov 2021 08:16:36 +0100 Subject: [PATCH 110/358] ALSA: hda/realtek: Fix LED on HP ProBook 435 G7 HP ProBook 435 G7 (SSID 103c:8735) needs the similar quirk as another HP ProBook for enabling the mute and the mic-mute LEDs. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=215021 Cc: Link: https://lore.kernel.org/r/20211118071636.14738-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 701c80ed83dc8c..9ce7457533c966 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8665,6 +8665,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8728, "HP EliteBook 840 G7", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8730, "HP ProBook 445 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8735, "HP ProBook 435 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), From c035713998700e8843c7d087f55bce3c54c0e3ec Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 5 Nov 2021 10:19:05 -0400 Subject: [PATCH 111/358] mm: Add functions to zero portions of a folio These functions are wrappers around zero_user_segments(), which means that zero_user_segments() can now be called for compound pages even when CONFIG_TRANSPARENT_HUGEPAGE is disabled. Use 'xend' as the name of the parameter to indicate that this is an excluded end, not the more usual included end. Excluding the end makes more sense to the callers, but can cause confusion to readers who are more used to seeing included ends. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- include/linux/highmem.h | 44 ++++++++++++++++++++++++++++++++++++++--- mm/highmem.c | 2 -- 2 files changed, 41 insertions(+), 5 deletions(-) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index c944b3b70ee7bb..39bb9b47fa9cd4 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -230,10 +230,10 @@ static inline void tag_clear_highpage(struct page *page) * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ -#if defined(CONFIG_HIGHMEM) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +#ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); -#else /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */ +#else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) @@ -253,7 +253,7 @@ static inline void zero_user_segments(struct page *page, for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } -#endif /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */ +#endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) @@ -363,4 +363,42 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len) kunmap_local(addr); } +/** + * folio_zero_segments() - Zero two byte ranges in a folio. + * @folio: The folio to write to. + * @start1: The first byte to zero. + * @xend1: One more than the last byte in the first range. + * @start2: The first byte to zero in the second range. + * @xend2: One more than the last byte in the second range. + */ +static inline void folio_zero_segments(struct folio *folio, + size_t start1, size_t xend1, size_t start2, size_t xend2) +{ + zero_user_segments(&folio->page, start1, xend1, start2, xend2); +} + +/** + * folio_zero_segment() - Zero a byte range in a folio. + * @folio: The folio to write to. + * @start: The first byte to zero. + * @xend: One more than the last byte to zero. + */ +static inline void folio_zero_segment(struct folio *folio, + size_t start, size_t xend) +{ + zero_user_segments(&folio->page, start, xend, 0, 0); +} + +/** + * folio_zero_range() - Zero a byte range in a folio. + * @folio: The folio to write to. + * @start: The first byte to zero. + * @length: The number of bytes to zero. + */ +static inline void folio_zero_range(struct folio *folio, + size_t start, size_t length) +{ + zero_user_segments(&folio->page, start, start + length, 0, 0); +} + #endif /* _LINUX_HIGHMEM_H */ diff --git a/mm/highmem.c b/mm/highmem.c index 88f65f15584533..819d41140e5b45 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -359,7 +359,6 @@ void kunmap_high(struct page *page) } EXPORT_SYMBOL(kunmap_high); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { @@ -416,7 +415,6 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, BUG_ON((start1 | start2 | end1 | end2) != 0); } EXPORT_SYMBOL(zero_user_segments); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_HIGHMEM */ #ifdef CONFIG_KMAP_LOCAL From 76c47183224c86e4011048b80f0e2d0d166f01c2 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 18 Nov 2021 22:57:29 +0100 Subject: [PATCH 112/358] ALSA: ctxfi: Fix out-of-range access The master and next_conj of rcs_ops are used for iterating the resource list entries, and currently those are supposed to return the current value. The problem is that next_conf may go over the last entry before the loop abort condition is evaluated, and it may return the "current" value that is beyond the array size. It was caught recently as a GPF, for example. Those return values are, however, never actually evaluated, hence basically we don't have to consider the current value as the return at all. By dropping those return values, the potential out-of-range access above is also fixed automatically. This patch changes the return type of master and next_conj callbacks to void and drop the superfluous code accordingly. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=214985 Cc: Link: https://lore.kernel.org/r/20211118215729.26257-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/ctxfi/ctamixer.c | 14 ++++++-------- sound/pci/ctxfi/ctdaio.c | 16 ++++++++-------- sound/pci/ctxfi/ctresource.c | 7 +++---- sound/pci/ctxfi/ctresource.h | 4 ++-- sound/pci/ctxfi/ctsrc.c | 7 +++---- 5 files changed, 22 insertions(+), 26 deletions(-) diff --git a/sound/pci/ctxfi/ctamixer.c b/sound/pci/ctxfi/ctamixer.c index da6e6350ceafad..d074727c3e21d3 100644 --- a/sound/pci/ctxfi/ctamixer.c +++ b/sound/pci/ctxfi/ctamixer.c @@ -23,16 +23,15 @@ #define BLANK_SLOT 4094 -static int amixer_master(struct rsc *rsc) +static void amixer_master(struct rsc *rsc) { rsc->conj = 0; - return rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0]; + rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0]; } -static int amixer_next_conj(struct rsc *rsc) +static void amixer_next_conj(struct rsc *rsc) { rsc->conj++; - return container_of(rsc, struct amixer, rsc)->idx[rsc->conj]; } static int amixer_index(const struct rsc *rsc) @@ -331,16 +330,15 @@ int amixer_mgr_destroy(struct amixer_mgr *amixer_mgr) /* SUM resource management */ -static int sum_master(struct rsc *rsc) +static void sum_master(struct rsc *rsc) { rsc->conj = 0; - return rsc->idx = container_of(rsc, struct sum, rsc)->idx[0]; + rsc->idx = container_of(rsc, struct sum, rsc)->idx[0]; } -static int sum_next_conj(struct rsc *rsc) +static void sum_next_conj(struct rsc *rsc) { rsc->conj++; - return container_of(rsc, struct sum, rsc)->idx[rsc->conj]; } static int sum_index(const struct rsc *rsc) diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c index f589da04534244..7fc720046ce293 100644 --- a/sound/pci/ctxfi/ctdaio.c +++ b/sound/pci/ctxfi/ctdaio.c @@ -51,12 +51,12 @@ static const struct daio_rsc_idx idx_20k2[NUM_DAIOTYP] = { [SPDIFIO] = {.left = 0x05, .right = 0x85}, }; -static int daio_master(struct rsc *rsc) +static void daio_master(struct rsc *rsc) { /* Actually, this is not the resource index of DAIO. * For DAO, it is the input mapper index. And, for DAI, * it is the output time-slot index. */ - return rsc->conj = rsc->idx; + rsc->conj = rsc->idx; } static int daio_index(const struct rsc *rsc) @@ -64,19 +64,19 @@ static int daio_index(const struct rsc *rsc) return rsc->conj; } -static int daio_out_next_conj(struct rsc *rsc) +static void daio_out_next_conj(struct rsc *rsc) { - return rsc->conj += 2; + rsc->conj += 2; } -static int daio_in_next_conj_20k1(struct rsc *rsc) +static void daio_in_next_conj_20k1(struct rsc *rsc) { - return rsc->conj += 0x200; + rsc->conj += 0x200; } -static int daio_in_next_conj_20k2(struct rsc *rsc) +static void daio_in_next_conj_20k2(struct rsc *rsc) { - return rsc->conj += 0x100; + rsc->conj += 0x100; } static const struct rsc_ops daio_out_rsc_ops = { diff --git a/sound/pci/ctxfi/ctresource.c b/sound/pci/ctxfi/ctresource.c index 81ad2693451827..be1d3e61309ce2 100644 --- a/sound/pci/ctxfi/ctresource.c +++ b/sound/pci/ctxfi/ctresource.c @@ -109,18 +109,17 @@ static int audio_ring_slot(const struct rsc *rsc) return (rsc->conj << 4) + offset_in_audio_slot_block[rsc->type]; } -static int rsc_next_conj(struct rsc *rsc) +static void rsc_next_conj(struct rsc *rsc) { unsigned int i; for (i = 0; (i < 8) && (!(rsc->msr & (0x1 << i))); ) i++; rsc->conj += (AUDIO_SLOT_BLOCK_NUM >> i); - return rsc->conj; } -static int rsc_master(struct rsc *rsc) +static void rsc_master(struct rsc *rsc) { - return rsc->conj = rsc->idx; + rsc->conj = rsc->idx; } static const struct rsc_ops rsc_generic_ops = { diff --git a/sound/pci/ctxfi/ctresource.h b/sound/pci/ctxfi/ctresource.h index fdbfd808816d37..58553bda44f436 100644 --- a/sound/pci/ctxfi/ctresource.h +++ b/sound/pci/ctxfi/ctresource.h @@ -39,8 +39,8 @@ struct rsc { }; struct rsc_ops { - int (*master)(struct rsc *rsc); /* Move to master resource */ - int (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */ + void (*master)(struct rsc *rsc); /* Move to master resource */ + void (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */ int (*index)(const struct rsc *rsc); /* Return the index of resource */ /* Return the output slot number */ int (*output_slot)(const struct rsc *rsc); diff --git a/sound/pci/ctxfi/ctsrc.c b/sound/pci/ctxfi/ctsrc.c index bd4697b4423346..4a94b4708a77e5 100644 --- a/sound/pci/ctxfi/ctsrc.c +++ b/sound/pci/ctxfi/ctsrc.c @@ -590,16 +590,15 @@ int src_mgr_destroy(struct src_mgr *src_mgr) /* SRCIMP resource manager operations */ -static int srcimp_master(struct rsc *rsc) +static void srcimp_master(struct rsc *rsc) { rsc->conj = 0; - return rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0]; + rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0]; } -static int srcimp_next_conj(struct rsc *rsc) +static void srcimp_next_conj(struct rsc *rsc) { rsc->conj++; - return container_of(rsc, struct srcimp, rsc)->idx[rsc->conj]; } static int srcimp_index(const struct rsc *rsc) From 187bea472600dcc8d2eb714335053264dd437172 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 18 Nov 2021 15:25:08 +0100 Subject: [PATCH 113/358] ARM: socfpga: Fix crash with CONFIG_FORTIRY_SOURCE When CONFIG_FORTIFY_SOURCE is set, memcpy() checks the potential buffer overflow and panics. The code in sofcpga bootstrapping contains the memcpy() calls are mistakenly translated as the shorter size, hence it triggers a panic as if it were overflowing. This patch changes the secondary_trampoline and *_end definitions to arrays for avoiding the false-positive crash above. Fixes: 9c4566a117a6 ("ARM: socfpga: Enable SMP for socfpga") Suggested-by: Kees Cook Buglink: https://bugzilla.suse.com/show_bug.cgi?id=1192473 Link: https://lore.kernel.org/r/20211117193244.31162-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Dinh Nguyen --- arch/arm/mach-socfpga/core.h | 2 +- arch/arm/mach-socfpga/platsmp.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h index fc2608b18a0d04..18f01190dcfd42 100644 --- a/arch/arm/mach-socfpga/core.h +++ b/arch/arm/mach-socfpga/core.h @@ -33,7 +33,7 @@ extern void __iomem *sdr_ctl_base_addr; u32 socfpga_sdram_self_refresh(u32 sdr_base); extern unsigned int socfpga_sdram_self_refresh_sz; -extern char secondary_trampoline, secondary_trampoline_end; +extern char secondary_trampoline[], secondary_trampoline_end[]; extern unsigned long socfpga_cpu1start_addr; diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c index fbb80b883e5dd2..201191cf68f324 100644 --- a/arch/arm/mach-socfpga/platsmp.c +++ b/arch/arm/mach-socfpga/platsmp.c @@ -20,14 +20,14 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) { - int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; + int trampoline_size = secondary_trampoline_end - secondary_trampoline; if (socfpga_cpu1start_addr) { /* This will put CPU #1 into reset. */ writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST); - memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); + memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); writel(__pa_symbol(secondary_startup), sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff)); @@ -45,12 +45,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle) { - int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; + int trampoline_size = secondary_trampoline_end - secondary_trampoline; if (socfpga_cpu1start_addr) { writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr + SOCFPGA_A10_RSTMGR_MODMPURST); - memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); + memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); writel(__pa_symbol(secondary_startup), sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff)); From 46741e4f593ff1bd0e4a140ab7e566701946484b Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Thu, 18 Nov 2021 13:04:13 +1000 Subject: [PATCH 114/358] drm/nouveau: recognise GA106 I've got HW now, appears to work as expected so far. Signed-off-by: Ben Skeggs Cc: # 5.14+ Reviewed-by: Karol Herbst Signed-off-by: Karol Herbst Link: https://patchwork.freedesktop.org/patch/msgid/20211118030413.2610-1-skeggsb@gmail.com --- .../gpu/drm/nouveau/nvkm/engine/device/base.c | 22 +++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index b51d690f375ff4..88d262ba648cf9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2626,6 +2626,27 @@ nv174_chipset = { .fifo = { 0x00000001, ga102_fifo_new }, }; +static const struct nvkm_device_chip +nv176_chipset = { + .name = "GA106", + .bar = { 0x00000001, tu102_bar_new }, + .bios = { 0x00000001, nvkm_bios_new }, + .devinit = { 0x00000001, ga100_devinit_new }, + .fb = { 0x00000001, ga102_fb_new }, + .gpio = { 0x00000001, ga102_gpio_new }, + .i2c = { 0x00000001, gm200_i2c_new }, + .imem = { 0x00000001, nv50_instmem_new }, + .mc = { 0x00000001, ga100_mc_new }, + .mmu = { 0x00000001, tu102_mmu_new }, + .pci = { 0x00000001, gp100_pci_new }, + .privring = { 0x00000001, gm200_privring_new }, + .timer = { 0x00000001, gk20a_timer_new }, + .top = { 0x00000001, ga100_top_new }, + .disp = { 0x00000001, ga102_disp_new }, + .dma = { 0x00000001, gv100_dma_new }, + .fifo = { 0x00000001, ga102_fifo_new }, +}; + static const struct nvkm_device_chip nv177_chipset = { .name = "GA107", @@ -3072,6 +3093,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x168: device->chip = &nv168_chipset; break; case 0x172: device->chip = &nv172_chipset; break; case 0x174: device->chip = &nv174_chipset; break; + case 0x176: device->chip = &nv176_chipset; break; case 0x177: device->chip = &nv177_chipset; break; default: if (nvkm_boolopt(device->cfgopt, "NvEnableUnsupportedChipsets", false)) { From b371fd131fcec59f6165c80778bdc2cd1abd616b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 18 Nov 2021 14:13:14 +0300 Subject: [PATCH 115/358] drm/nouveau/acr: fix a couple NULL vs IS_ERR() checks The nvkm_acr_lsfw_add() function never returns NULL. It returns error pointers on error. Fixes: 22dcda45a3d1 ("drm/nouveau/acr: implement new subdev to replace "secure boot"") Signed-off-by: Dan Carpenter Reviewed-by: Ben Skeggs Signed-off-by: Karol Herbst Link: https://patchwork.freedesktop.org/patch/msgid/20211118111314.GB1147@kili --- drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c | 6 ++++-- drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c index cdb1ead26d84f0..82b4c8e1457c28 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c @@ -207,11 +207,13 @@ int gm200_acr_wpr_parse(struct nvkm_acr *acr) { const struct wpr_header *hdr = (void *)acr->wpr_fw->data; + struct nvkm_acr_lsfw *lsfw; while (hdr->falcon_id != WPR_HEADER_V0_FALCON_ID_INVALID) { wpr_header_dump(&acr->subdev, hdr); - if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id)) - return -ENOMEM; + lsfw = nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id); + if (IS_ERR(lsfw)) + return PTR_ERR(lsfw); } return 0; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c index fb9132a39bb1a5..fd97a935a380e8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c @@ -161,11 +161,13 @@ int gp102_acr_wpr_parse(struct nvkm_acr *acr) { const struct wpr_header_v1 *hdr = (void *)acr->wpr_fw->data; + struct nvkm_acr_lsfw *lsfw; while (hdr->falcon_id != WPR_HEADER_V1_FALCON_ID_INVALID) { wpr_header_v1_dump(&acr->subdev, hdr); - if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id)) - return -ENOMEM; + lsfw = nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id); + if (IS_ERR(lsfw)) + return PTR_ERR(lsfw); } return 0; From 73185a13773af10264f9d8ee70386c01c849ff2c Mon Sep 17 00:00:00 2001 From: Bean Huo Date: Thu, 11 Nov 2021 23:24:52 +0100 Subject: [PATCH 116/358] scsi: ufs: ufshpb: Fix warning in ufshpb_set_hpb_read_to_upiu() Fix the following sparse warnings in ufshpb_set_hpb_read_to_upiu(): sparse warnings: (new ones prefixed by >>) drivers/scsi/ufs/ufshpb.c:335:27: sparse: sparse: cast from restricted __be64 drivers/scsi/ufs/ufshpb.c:335:25: sparse: expected restricted __be64 [usertype] ppn_tmp drivers/scsi/ufs/ufshpb.c:335:25: sparse: got unsigned long long [usertype] Link: https://lore.kernel.org/r/20211111222452.384089-1-huobean@gmail.com Reported-by: kernel test robot Reviewed-by: Bart Van Assche Signed-off-by: Bean Huo Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshpb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 2e31e14138262c..ded5ba9b1466a9 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -331,7 +331,7 @@ ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, cdb[0] = UFSHPB_READ; if (hba->dev_quirks & UFS_DEVICE_QUIRK_SWAP_L2P_ENTRY_FOR_HPB_READ) - ppn_tmp = swab64(ppn); + ppn_tmp = (__force __be64)swab64((__force u64)ppn); /* ppn value is stored as big-endian in the host memory */ memcpy(&cdb[6], &ppn_tmp, sizeof(__be64)); From e11e285b9cd132db21568b5d29c291f590841944 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 9 Nov 2021 14:52:19 +0300 Subject: [PATCH 117/358] scsi: qla2xxx: edif: Fix off by one bug in qla_edif_app_getfcinfo() The > comparison needs to be >= to prevent accessing one element beyond the end of the app_reply->ports[] array. Link: https://lore.kernel.org/r/20211109115219.GE16587@kili Fixes: 7878f22a2e03 ("scsi: qla2xxx: edif: Add getfcinfo and statistic bsgs") Reviewed-by: Ewan D. Milne Reviewed-by: Himanshu Madhani Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_edif.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c index 2e37b189cb7559..53d2b85620271a 100644 --- a/drivers/scsi/qla2xxx/qla_edif.c +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -865,7 +865,7 @@ qla_edif_app_getfcinfo(scsi_qla_host_t *vha, struct bsg_job *bsg_job) "APP request entry - portid=%06x.\n", tdid.b24); /* Ran out of space */ - if (pcnt > app_req.num_ports) + if (pcnt >= app_req.num_ports) break; if (tdid.b24 != 0 && tdid.b24 != fcport->d_id.b24) From 36e07d7ede88a1f1ef8f0f209af5b7612324ac2c Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Tue, 9 Nov 2021 13:57:27 -0500 Subject: [PATCH 118/358] scsi: scsi_debug: Fix type in min_t to avoid stack OOB Change min_t() to use type "u32" instead of type "int" to avoid stack out of bounds. With min_t() type "int" the values get sign extended and the larger value gets used causing stack out of bounds. BUG: KASAN: stack-out-of-bounds in memcpy include/linux/fortify-string.h:191 [inline] BUG: KASAN: stack-out-of-bounds in sg_copy_buffer+0x1de/0x240 lib/scatterlist.c:976 Read of size 127 at addr ffff888072607128 by task syz-executor.7/18707 CPU: 1 PID: 18707 Comm: syz-executor.7 Not tainted 5.15.0-syzk #1 Hardware name: Red Hat KVM, BIOS 1.13.0-2 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:106 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:256 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold.14+0x7d/0x117 mm/kasan/report.c:459 check_region_inline mm/kasan/generic.c:183 [inline] kasan_check_range+0x1a3/0x210 mm/kasan/generic.c:189 memcpy+0x23/0x60 mm/kasan/shadow.c:65 memcpy include/linux/fortify-string.h:191 [inline] sg_copy_buffer+0x1de/0x240 lib/scatterlist.c:976 sg_copy_from_buffer+0x33/0x40 lib/scatterlist.c:1000 fill_from_dev_buffer.part.34+0x82/0x130 drivers/scsi/scsi_debug.c:1162 fill_from_dev_buffer drivers/scsi/scsi_debug.c:1888 [inline] resp_readcap16+0x365/0x3b0 drivers/scsi/scsi_debug.c:1887 schedule_resp+0x4d8/0x1a70 drivers/scsi/scsi_debug.c:5478 scsi_debug_queuecommand+0x8c9/0x1ec0 drivers/scsi/scsi_debug.c:7533 scsi_dispatch_cmd drivers/scsi/scsi_lib.c:1520 [inline] scsi_queue_rq+0x16b0/0x2d40 drivers/scsi/scsi_lib.c:1699 blk_mq_dispatch_rq_list+0xb9b/0x2700 block/blk-mq.c:1639 __blk_mq_sched_dispatch_requests+0x28f/0x590 block/blk-mq-sched.c:325 blk_mq_sched_dispatch_requests+0x105/0x190 block/blk-mq-sched.c:358 __blk_mq_run_hw_queue+0xe5/0x150 block/blk-mq.c:1761 __blk_mq_delay_run_hw_queue+0x4f8/0x5c0 block/blk-mq.c:1838 blk_mq_run_hw_queue+0x18d/0x350 block/blk-mq.c:1891 blk_mq_sched_insert_request+0x3db/0x4e0 block/blk-mq-sched.c:474 blk_execute_rq_nowait+0x16b/0x1c0 block/blk-exec.c:62 sg_common_write.isra.18+0xeb3/0x2000 drivers/scsi/sg.c:836 sg_new_write.isra.19+0x570/0x8c0 drivers/scsi/sg.c:774 sg_ioctl_common+0x14d6/0x2710 drivers/scsi/sg.c:939 sg_ioctl+0xa2/0x180 drivers/scsi/sg.c:1165 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Link: https://lore.kernel.org/r/1636484247-21254-1-git-send-email-george.kennedy@oracle.com Reported-by: syzkaller Acked-by: Douglas Gilbert Signed-off-by: George Kennedy Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_debug.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 1d0278da904139..ab01ef7d37f4da 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -1189,7 +1189,7 @@ static int p_fill_from_dev_buffer(struct scsi_cmnd *scp, const void *arr, __func__, off_dst, scsi_bufflen(scp), act_len, scsi_get_resid(scp)); n = scsi_bufflen(scp) - (off_dst + act_len); - scsi_set_resid(scp, min_t(int, scsi_get_resid(scp), n)); + scsi_set_resid(scp, min_t(u32, scsi_get_resid(scp), n)); return 0; } @@ -1562,7 +1562,8 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) unsigned char pq_pdt; unsigned char *arr; unsigned char *cmd = scp->cmnd; - int alloc_len, n, ret; + u32 alloc_len, n; + int ret; bool have_wlun, is_disk, is_zbc, is_disk_zbc; alloc_len = get_unaligned_be16(cmd + 3); @@ -1585,7 +1586,8 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) kfree(arr); return check_condition_result; } else if (0x1 & cmd[1]) { /* EVPD bit set */ - int lu_id_num, port_group_id, target_dev_id, len; + int lu_id_num, port_group_id, target_dev_id; + u32 len; char lu_id_str[6]; int host_no = devip->sdbg_host->shost->host_no; @@ -1676,9 +1678,9 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) kfree(arr); return check_condition_result; } - len = min(get_unaligned_be16(arr + 2) + 4, alloc_len); + len = min_t(u32, get_unaligned_be16(arr + 2) + 4, alloc_len); ret = fill_from_dev_buffer(scp, arr, - min(len, SDEBUG_MAX_INQ_ARR_SZ)); + min_t(u32, len, SDEBUG_MAX_INQ_ARR_SZ)); kfree(arr); return ret; } @@ -1714,7 +1716,7 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) } put_unaligned_be16(0x2100, arr + n); /* SPL-4 no version claimed */ ret = fill_from_dev_buffer(scp, arr, - min_t(int, alloc_len, SDEBUG_LONG_INQ_SZ)); + min_t(u32, alloc_len, SDEBUG_LONG_INQ_SZ)); kfree(arr); return ret; } @@ -1729,8 +1731,8 @@ static int resp_requests(struct scsi_cmnd *scp, unsigned char *cmd = scp->cmnd; unsigned char arr[SCSI_SENSE_BUFFERSIZE]; /* assume >= 18 bytes */ bool dsense = !!(cmd[1] & 1); - int alloc_len = cmd[4]; - int len = 18; + u32 alloc_len = cmd[4]; + u32 len = 18; int stopped_state = atomic_read(&devip->stopped); memset(arr, 0, sizeof(arr)); @@ -1774,7 +1776,7 @@ static int resp_requests(struct scsi_cmnd *scp, arr[7] = 0xa; } } - return fill_from_dev_buffer(scp, arr, min_t(int, len, alloc_len)); + return fill_from_dev_buffer(scp, arr, min_t(u32, len, alloc_len)); } static int resp_start_stop(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) @@ -2312,7 +2314,8 @@ static int resp_mode_sense(struct scsi_cmnd *scp, { int pcontrol, pcode, subpcode, bd_len; unsigned char dev_spec; - int alloc_len, offset, len, target_dev_id; + u32 alloc_len, offset, len; + int target_dev_id; int target = scp->device->id; unsigned char *ap; unsigned char arr[SDEBUG_MAX_MSENSE_SZ]; @@ -2468,7 +2471,7 @@ static int resp_mode_sense(struct scsi_cmnd *scp, arr[0] = offset - 1; else put_unaligned_be16((offset - 2), arr + 0); - return fill_from_dev_buffer(scp, arr, min_t(int, alloc_len, offset)); + return fill_from_dev_buffer(scp, arr, min_t(u32, alloc_len, offset)); } #define SDEBUG_MAX_MSELECT_SZ 512 @@ -2583,7 +2586,8 @@ static int resp_ie_l_pg(unsigned char *arr) static int resp_log_sense(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) { - int ppc, sp, pcode, subpcode, alloc_len, len, n; + int ppc, sp, pcode, subpcode; + u32 alloc_len, len, n; unsigned char arr[SDEBUG_MAX_LSENSE_SZ]; unsigned char *cmd = scp->cmnd; @@ -2653,9 +2657,9 @@ static int resp_log_sense(struct scsi_cmnd *scp, mk_sense_invalid_fld(scp, SDEB_IN_CDB, 3, -1); return check_condition_result; } - len = min_t(int, get_unaligned_be16(arr + 2) + 4, alloc_len); + len = min_t(u32, get_unaligned_be16(arr + 2) + 4, alloc_len); return fill_from_dev_buffer(scp, arr, - min_t(int, len, SDEBUG_MAX_INQ_ARR_SZ)); + min_t(u32, len, SDEBUG_MAX_INQ_ARR_SZ)); } static inline bool sdebug_dev_is_zoned(struct sdebug_dev_info *devip) @@ -4430,7 +4434,7 @@ static int resp_report_zones(struct scsi_cmnd *scp, put_unaligned_be64(sdebug_capacity - 1, arr + 8); rep_len = (unsigned long)desc - (unsigned long)arr; - ret = fill_from_dev_buffer(scp, arr, min_t(int, alloc_len, rep_len)); + ret = fill_from_dev_buffer(scp, arr, min_t(u32, alloc_len, rep_len)); fini: read_unlock(macc_lckp); From cc03facb1c4248997592fc683518c00cc257db1a Mon Sep 17 00:00:00 2001 From: Ye Guojin Date: Wed, 10 Nov 2021 10:51:33 +0000 Subject: [PATCH 119/358] scsi: ufs: ufs-mediatek: Add put_device() after of_find_device_by_node() This was found by coccicheck: ./drivers/scsi/ufs/ufs-mediatek.c, 211, 1-7, ERROR missing put_device; call of_find_device_by_node on line 1185, but without a corresponding object release within this function. Link: https://lore.kernel.org/r/20211110105133.150171-1-ye.guojin@zte.com.cn Reported-by: Zeal Robot Reviewed-by: Peter Wang Signed-off-by: Ye Guojin Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufs-mediatek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index fc5b214347b364..5393b5c9dd9c87 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -1189,6 +1189,7 @@ static int ufs_mtk_probe(struct platform_device *pdev) } link = device_link_add(dev, &reset_pdev->dev, DL_FLAG_AUTOPROBE_CONSUMER); + put_device(&reset_pdev->dev); if (!link) { dev_notice(dev, "add reset device_link fail\n"); goto skip_reset; From 0ee4ba13e09c9d9c1cb6abb59da8295d9952328b Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Wed, 17 Nov 2021 16:19:09 +0530 Subject: [PATCH 120/358] scsi: mpt3sas: Fix kernel panic during drive powercycle test While looping over shost's sdev list it is possible that one of the drives is getting removed and its sas_target object is freed but its sdev object remains intact. Consequently, a kernel panic can occur while the driver is trying to access the sas_address field of sas_target object without also checking the sas_target object for NULL. Link: https://lore.kernel.org/r/20211117104909.2069-1-sreekanth.reddy@broadcom.com Fixes: f92363d12359 ("[SCSI] mpt3sas: add new driver supporting 12GB SAS") Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index cee7170beae856..bb0036b418258d 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -3869,7 +3869,7 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc, shost_for_each_device(sdev, ioc->shost) { sas_device_priv_data = sdev->hostdata; - if (!sas_device_priv_data) + if (!sas_device_priv_data || !sas_device_priv_data->sas_target) continue; if (sas_device_priv_data->sas_target->sas_address != sas_address) From 91202a01a2fb2b78da3d03811b6d3d973ae426aa Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Wed, 17 Nov 2021 16:20:58 +0530 Subject: [PATCH 121/358] scsi: mpt3sas: Fix system going into read-only mode While determining the SAS address of a drive, the driver checks whether the handle number is less than the HBA phy count or not. If the handle number is less than the HBA phy count then driver assumes that this handle belongs to HBA and hence it assigns the HBA SAS address. During IOC firmware downgrade operation, if the number of HBA phys is reduced and the OS drive's device handle drops below the phy count while determining the drive's SAS address, the driver ends up using the HBA's SAS address. This leads to a mismatch of drive's SAS address and hence the driver unregisters the OS drive and the system goes into read-only mode. Update the IOC's num_phys to the HBA phy count provided by actual loaded firmware. Link: https://lore.kernel.org/r/20211117105058.3505-1-sreekanth.reddy@broadcom.com Fixes: a5e99fda0172 ("scsi: mpt3sas: Update hba_port objects after host reset") Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.h | 4 ++ drivers/scsi/mpt3sas/mpt3sas_scsih.c | 57 +++++++++++++++++++++++++++- 2 files changed, 60 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index db6a759de1e993..a0af986633d2a0 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -142,6 +142,8 @@ #define MPT_MAX_CALLBACKS 32 +#define MPT_MAX_HBA_NUM_PHYS 32 + #define INTERNAL_CMDS_COUNT 10 /* reserved cmds */ /* reserved for issuing internally framed scsi io cmds */ #define INTERNAL_SCSIIO_CMDS_COUNT 3 @@ -798,6 +800,7 @@ struct _sas_phy { * @enclosure_handle: handle for this a member of an enclosure * @device_info: bitwise defining capabilities of this sas_host/expander * @responding: used in _scsih_expander_device_mark_responding + * @nr_phys_allocated: Allocated memory for this many count phys * @phy: a list of phys that make up this sas_host/expander * @sas_port_list: list of ports attached to this sas_host/expander * @port: hba port entry containing node's port number info @@ -813,6 +816,7 @@ struct _sas_node { u16 enclosure_handle; u64 enclosure_logical_id; u8 responding; + u8 nr_phys_allocated; struct hba_port *port; struct _sas_phy *phy; struct list_head sas_port_list; diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index bb0036b418258d..00792767c620d7 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -6406,11 +6406,26 @@ _scsih_sas_port_refresh(struct MPT3SAS_ADAPTER *ioc) int i, j, count = 0, lcount = 0; int ret; u64 sas_addr; + u8 num_phys; drsprintk(ioc, ioc_info(ioc, "updating ports for sas_host(0x%016llx)\n", (unsigned long long)ioc->sas_hba.sas_address)); + mpt3sas_config_get_number_hba_phys(ioc, &num_phys); + if (!num_phys) { + ioc_err(ioc, "failure at %s:%d/%s()!\n", + __FILE__, __LINE__, __func__); + return; + } + + if (num_phys > ioc->sas_hba.nr_phys_allocated) { + ioc_err(ioc, "failure at %s:%d/%s()!\n", + __FILE__, __LINE__, __func__); + return; + } + ioc->sas_hba.num_phys = num_phys; + port_table = kcalloc(ioc->sas_hba.num_phys, sizeof(struct hba_port), GFP_KERNEL); if (!port_table) @@ -6611,6 +6626,30 @@ _scsih_sas_host_refresh(struct MPT3SAS_ADAPTER *ioc) ioc->sas_hba.phy[i].hba_vphy = 1; } + /* + * Add new HBA phys to STL if these new phys got added as part + * of HBA Firmware upgrade/downgrade operation. + */ + if (!ioc->sas_hba.phy[i].phy) { + if ((mpt3sas_config_get_phy_pg0(ioc, &mpi_reply, + &phy_pg0, i))) { + ioc_err(ioc, "failure at %s:%d/%s()!\n", + __FILE__, __LINE__, __func__); + continue; + } + ioc_status = le16_to_cpu(mpi_reply.IOCStatus) & + MPI2_IOCSTATUS_MASK; + if (ioc_status != MPI2_IOCSTATUS_SUCCESS) { + ioc_err(ioc, "failure at %s:%d/%s()!\n", + __FILE__, __LINE__, __func__); + continue; + } + ioc->sas_hba.phy[i].phy_id = i; + mpt3sas_transport_add_host_phy(ioc, + &ioc->sas_hba.phy[i], phy_pg0, + ioc->sas_hba.parent_dev); + continue; + } ioc->sas_hba.phy[i].handle = ioc->sas_hba.handle; attached_handle = le16_to_cpu(sas_iounit_pg0->PhyData[i]. AttachedDevHandle); @@ -6622,6 +6661,19 @@ _scsih_sas_host_refresh(struct MPT3SAS_ADAPTER *ioc) attached_handle, i, link_rate, ioc->sas_hba.phy[i].port); } + /* + * Clear the phy details if this phy got disabled as part of + * HBA Firmware upgrade/downgrade operation. + */ + for (i = ioc->sas_hba.num_phys; + i < ioc->sas_hba.nr_phys_allocated; i++) { + if (ioc->sas_hba.phy[i].phy && + ioc->sas_hba.phy[i].phy->negotiated_linkrate >= + SAS_LINK_RATE_1_5_GBPS) + mpt3sas_transport_update_links(ioc, + ioc->sas_hba.sas_address, 0, i, + MPI2_SAS_NEG_LINK_RATE_PHY_DISABLED, NULL); + } out: kfree(sas_iounit_pg0); } @@ -6654,7 +6706,10 @@ _scsih_sas_host_add(struct MPT3SAS_ADAPTER *ioc) __FILE__, __LINE__, __func__); return; } - ioc->sas_hba.phy = kcalloc(num_phys, + + ioc->sas_hba.nr_phys_allocated = max_t(u8, + MPT_MAX_HBA_NUM_PHYS, num_phys); + ioc->sas_hba.phy = kcalloc(ioc->sas_hba.nr_phys_allocated, sizeof(struct _sas_phy), GFP_KERNEL); if (!ioc->sas_hba.phy) { ioc_err(ioc, "failure at %s:%d/%s()!\n", From 5ecae9f8c705fae85fe4d2ed9f1b9cddf91e88e9 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Wed, 17 Nov 2021 18:02:15 +0530 Subject: [PATCH 122/358] scsi: mpt3sas: Fix incorrect system timestamp For updating the IOC firmware's timestamp with system timestamp, the driver issues the Mpi26IoUnitControlRequest message. While framing the Mpi26IoUnitControlRequest, the driver should copy the lower 32 bits of the current timestamp into IOCParameterValue field and the higher 32 bits into Reserved7 field. Link: https://lore.kernel.org/r/20211117123215.25487-1-sreekanth.reddy@broadcom.com Fixes: f98790c00375 ("scsi: mpt3sas: Sync time periodically between driver and firmware") Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 27eb652b564f54..81dab9b82f79f9 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -639,8 +639,8 @@ static void _base_sync_drv_fw_timestamp(struct MPT3SAS_ADAPTER *ioc) mpi_request->IOCParameter = MPI26_SET_IOC_PARAMETER_SYNC_TIMESTAMP; current_time = ktime_get_real(); TimeStamp = ktime_to_ms(current_time); - mpi_request->Reserved7 = cpu_to_le32(TimeStamp & 0xFFFFFFFF); - mpi_request->IOCParameterValue = cpu_to_le32(TimeStamp >> 32); + mpi_request->Reserved7 = cpu_to_le32(TimeStamp >> 32); + mpi_request->IOCParameterValue = cpu_to_le32(TimeStamp & 0xFFFFFFFF); init_completion(&ioc->scsih_cmds.done); ioc->put_smid_default(ioc, smid); dinitprintk(ioc, ioc_info(ioc, From e2a49a95b571d9d208f28a03d63353374e724f13 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Wed, 17 Nov 2021 15:39:28 -0600 Subject: [PATCH 123/358] scsi: target: core: Use RCU helpers for INQUIRY t10_alua_tg_pt_gp Fix the sparse warnings about t10_alua_tg_pt_gp accesses in target_core_spc.c caused by commit 7324f47d4293 ("scsi: target: Replace lun_tg_pt_gp_lock with rcu in I/O path") That commit replaced the lun_tg_pt_gp_lock use in the I/O path, but it didn't update the INQUIRY code. Link: https://lore.kernel.org/r/20211117213928.8634-1-michael.christie@oracle.com Reported-by: kernel test robot Reviewed-by: Maurizio Lombardi Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/target/target_core_spc.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 22703a0dbd072e..4c76498d3fb06e 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -40,11 +40,11 @@ static void spc_fill_alua_data(struct se_lun *lun, unsigned char *buf) * * See spc4r17 section 6.4.2 Table 135 */ - spin_lock(&lun->lun_tg_pt_gp_lock); - tg_pt_gp = lun->lun_tg_pt_gp; + rcu_read_lock(); + tg_pt_gp = rcu_dereference(lun->lun_tg_pt_gp); if (tg_pt_gp) buf[5] |= tg_pt_gp->tg_pt_gp_alua_access_type; - spin_unlock(&lun->lun_tg_pt_gp_lock); + rcu_read_unlock(); } static u16 @@ -325,14 +325,14 @@ spc_emulate_evpd_83(struct se_cmd *cmd, unsigned char *buf) * Get the PROTOCOL IDENTIFIER as defined by spc4r17 * section 7.5.1 Table 362 */ - spin_lock(&lun->lun_tg_pt_gp_lock); - tg_pt_gp = lun->lun_tg_pt_gp; + rcu_read_lock(); + tg_pt_gp = rcu_dereference(lun->lun_tg_pt_gp); if (!tg_pt_gp) { - spin_unlock(&lun->lun_tg_pt_gp_lock); + rcu_read_unlock(); goto check_lu_gp; } tg_pt_gp_id = tg_pt_gp->tg_pt_gp_id; - spin_unlock(&lun->lun_tg_pt_gp_lock); + rcu_read_unlock(); buf[off] = tpg->proto_id << 4; buf[off++] |= 0x1; /* CODE SET == Binary */ From 9c6603e1faf880bada541e9cce6514d2f3248da0 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 18 Nov 2021 11:49:00 +0300 Subject: [PATCH 124/358] scsi: target: configfs: Delete unnecessary checks for NULL The "item" pointer is always going to be valid pointer and does not need to be checked. But if "item" were NULL then item_to_lun() would not return a NULL, but instead, the container_of() pointer math would return a value in the error pointer range. This confuses static checkers since it looks like a NULL vs IS_ERR() bug. Delete the bogus checks. Link: https://lore.kernel.org/r/20211118084900.GA24550@kili Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- drivers/target/target_core_fabric_configfs.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 0b65de9f2df18c..95a88f6224cd96 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -520,7 +520,7 @@ static ssize_t target_fabric_port_alua_tg_pt_gp_show(struct config_item *item, { struct se_lun *lun = item_to_lun(item); - if (!lun || !lun->lun_se_dev) + if (!lun->lun_se_dev) return -ENODEV; return core_alua_show_tg_pt_gp_info(lun, page); @@ -531,7 +531,7 @@ static ssize_t target_fabric_port_alua_tg_pt_gp_store(struct config_item *item, { struct se_lun *lun = item_to_lun(item); - if (!lun || !lun->lun_se_dev) + if (!lun->lun_se_dev) return -ENODEV; return core_alua_store_tg_pt_gp_info(lun, page, count); @@ -542,7 +542,7 @@ static ssize_t target_fabric_port_alua_tg_pt_offline_show( { struct se_lun *lun = item_to_lun(item); - if (!lun || !lun->lun_se_dev) + if (!lun->lun_se_dev) return -ENODEV; return core_alua_show_offline_bit(lun, page); @@ -553,7 +553,7 @@ static ssize_t target_fabric_port_alua_tg_pt_offline_store( { struct se_lun *lun = item_to_lun(item); - if (!lun || !lun->lun_se_dev) + if (!lun->lun_se_dev) return -ENODEV; return core_alua_store_offline_bit(lun, page, count); @@ -564,7 +564,7 @@ static ssize_t target_fabric_port_alua_tg_pt_status_show( { struct se_lun *lun = item_to_lun(item); - if (!lun || !lun->lun_se_dev) + if (!lun->lun_se_dev) return -ENODEV; return core_alua_show_secondary_status(lun, page); @@ -575,7 +575,7 @@ static ssize_t target_fabric_port_alua_tg_pt_status_store( { struct se_lun *lun = item_to_lun(item); - if (!lun || !lun->lun_se_dev) + if (!lun->lun_se_dev) return -ENODEV; return core_alua_store_secondary_status(lun, page, count); @@ -586,7 +586,7 @@ static ssize_t target_fabric_port_alua_tg_pt_write_md_show( { struct se_lun *lun = item_to_lun(item); - if (!lun || !lun->lun_se_dev) + if (!lun->lun_se_dev) return -ENODEV; return core_alua_show_secondary_write_metadata(lun, page); @@ -597,7 +597,7 @@ static ssize_t target_fabric_port_alua_tg_pt_write_md_store( { struct se_lun *lun = item_to_lun(item); - if (!lun || !lun->lun_se_dev) + if (!lun->lun_se_dev) return -ENODEV; return core_alua_store_secondary_write_metadata(lun, page, count); From e7cc3e09600822eb4f87734ff850724ea4dc540b Mon Sep 17 00:00:00 2001 From: Martin Kepplinger Date: Tue, 19 Oct 2021 16:55:08 +0100 Subject: [PATCH 125/358] media: hi846: include property.h instead of of_graph.h Include the more portable property.h instead of the OF specific of_graph.h Signed-off-by: Martin Kepplinger Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/i2c/hi846.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/hi846.c b/drivers/media/i2c/hi846.c index 822ce3021fde4d..614d5593290361 100644 --- a/drivers/media/i2c/hi846.c +++ b/drivers/media/i2c/hi846.c @@ -7,9 +7,9 @@ #include #include #include -#include #include #include +#include #include #include #include From 62456590b84965ad8d633dbd8f8c75fcf1e765d6 Mon Sep 17 00:00:00 2001 From: Martin Kepplinger Date: Tue, 19 Oct 2021 16:55:09 +0100 Subject: [PATCH 126/358] media: hi846: remove the of_match_ptr macro Similar to other drivers, this should fix a Clang compilar warning when building without CONFIG_OF in which case of_match_ptr() is NULL and the const struct we would use otherwise is unused. Signed-off-by: Martin Kepplinger Reported-by: kernel test robot Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/i2c/hi846.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/hi846.c b/drivers/media/i2c/hi846.c index 614d5593290361..48909faeced466 100644 --- a/drivers/media/i2c/hi846.c +++ b/drivers/media/i2c/hi846.c @@ -2176,7 +2176,7 @@ static struct i2c_driver hi846_i2c_driver = { .driver = { .name = "hi846", .pm = &hi846_pm_ops, - .of_match_table = of_match_ptr(hi846_of_match), + .of_match_table = hi846_of_match, }, .probe_new = hi846_probe, .remove = hi846_remove, From eee5d6f1356a016105a974fb176b491288439efa Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 19 Nov 2021 11:24:59 +0100 Subject: [PATCH 127/358] ALSA: usb-audio: Switch back to non-latency mode at a later point The recent regression report revealed that the judgment of the low-latency playback mode based on the runtime->stop_threshold cannot work reliably at the prepare stage, as sw_params call may happen at any time, and PCM dmix actually sets it up after the prepare call. This ended up with the stall of the stream as PCM ack won't be issued at all. For addressing this, check the free-wheeling mode again at the PCM trigger right before starting the stream again, and allow switching to the non-LL mode at a late stage. Fixes: d5f871f89e21 ("ALSA: usb-audio: Improved lowlatency playback support") Reported-and-tested-by: Kirill A. Shutemov Link: https://lore.kernel.org/r/20211117161855.m45mxcqszkfcetai@box.shutemov.name Link: https://lore.kernel.org/r/20211119102459.7055-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/pcm.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 95ec8eec1bb046..57b046e73bfedc 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -581,6 +581,12 @@ static int snd_usb_hw_free(struct snd_pcm_substream *substream) return 0; } +/* free-wheeling mode? (e.g. dmix) */ +static int in_free_wheeling_mode(struct snd_pcm_runtime *runtime) +{ + return runtime->stop_threshold > runtime->buffer_size; +} + /* check whether early start is needed for playback stream */ static int lowlatency_playback_available(struct snd_pcm_runtime *runtime, struct snd_usb_substream *subs) @@ -592,8 +598,7 @@ static int lowlatency_playback_available(struct snd_pcm_runtime *runtime, /* disabled via module option? */ if (!chip->lowlatency) return false; - /* free-wheeling mode? (e.g. dmix) */ - if (runtime->stop_threshold > runtime->buffer_size) + if (in_free_wheeling_mode(runtime)) return false; /* implicit feedback mode has own operation mode */ if (snd_usb_endpoint_implicit_feedback_sink(subs->data_endpoint)) @@ -1552,6 +1557,8 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea subs); if (subs->lowlatency_playback && cmd == SNDRV_PCM_TRIGGER_START) { + if (in_free_wheeling_mode(substream->runtime)) + subs->lowlatency_playback = false; err = start_endpoints(subs); if (err < 0) { snd_usb_endpoint_set_callback(subs->data_endpoint, From 83de8f83816e8e15227dac985163e3d433a2bf9d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 19 Nov 2021 11:26:29 +0100 Subject: [PATCH 128/358] ALSA: usb-audio: Don't start stream for capture at prepare The recent change made mistakenly the stream for capture started at prepare stage. Add the stream direction check to avoid it. Fixes: 9c9a3b9da891 ("ALSA: usb-audio: Rename early_playback_start flag with lowlatency_playback") Link: https://lore.kernel.org/r/20211119102629.7476-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/pcm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 57b046e73bfedc..cec6e91afea240 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -640,7 +640,8 @@ static int snd_usb_pcm_prepare(struct snd_pcm_substream *substream) runtime->delay = 0; subs->lowlatency_playback = lowlatency_playback_available(runtime, subs); - if (!subs->lowlatency_playback) + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && + !subs->lowlatency_playback) ret = start_endpoints(subs); unlock: From 96c5f82ef0a145d3e56e5b26f2bf6dcd2ffeae1c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 18 Nov 2021 14:14:16 +0300 Subject: [PATCH 129/358] drm/vc4: fix error code in vc4_create_object() The ->gem_create_object() functions are supposed to return NULL if there is an error. None of the callers expect error pointers so returing one will lead to an Oops. See drm_gem_vram_create(), for example. Fixes: c826a6e10644 ("drm/vc4: Add a BO cache.") Signed-off-by: Dan Carpenter Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20211118111416.GC1147@kili --- drivers/gpu/drm/vc4/vc4_bo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index fddaeb0b09c117..f642bd6e71ff49 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -391,7 +391,7 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size) bo = kzalloc(sizeof(*bo), GFP_KERNEL); if (!bo) - return ERR_PTR(-ENOMEM); + return NULL; bo->madv = VC4_MADV_WILLNEED; refcount_set(&bo->usecnt, 0); From b4a6aaeaf4aa79f23775f6688a7e8db3ee1c1303 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Wed, 17 Nov 2021 09:01:45 +0800 Subject: [PATCH 130/358] drm/aspeed: Fix vga_pw sysfs output Before the drm driver had support for this file there was a driver that exposed the contents of the vga password register to userspace. It would present the entire register instead of interpreting it. The drm implementation chose to mask of the lower bit, without explaining why. This breaks the existing userspace, which is looking for 0xa8 in the lower byte. Change our implementation to expose the entire register. Fixes: 696029eb36c0 ("drm/aspeed: Add sysfs for output settings") Reported-by: Oskar Senft Signed-off-by: Joel Stanley Reviewed-by: Jeremy Kerr Tested-by: Oskar Senft Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20211117010145.297253-1-joel@jms.id.au --- drivers/gpu/drm/aspeed/aspeed_gfx_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c index b53fee6f1c170a..65f172807a0d57 100644 --- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c @@ -291,7 +291,7 @@ vga_pw_show(struct device *dev, struct device_attribute *attr, char *buf) if (rc) return rc; - return sprintf(buf, "%u\n", reg & 1); + return sprintf(buf, "%u\n", reg); } static DEVICE_ATTR_RO(vga_pw); From 253e9b4d11e577bb8cbc77ef68a9ff46438065ca Mon Sep 17 00:00:00 2001 From: Volodymyr Mytnyk Date: Thu, 18 Nov 2021 21:48:03 +0200 Subject: [PATCH 131/358] net: marvell: prestera: fix brige port operation Return NOTIFY_DONE (dont't care) for switchdev notifications that prestera driver don't know how to handle them. With introduction of SWITCHDEV_BRPORT_[UN]OFFLOADED switchdev events, the driver rejects adding swport to bridge operation which is handled by prestera_bridge_port_join() func. The root cause of this is that prestera driver returns error (EOPNOTSUPP) in prestera_switchdev_blk_event() handler for unknown swdev events. This causes switchdev_bridge_port_offload() to fail when adding port to bridge in prestera_bridge_port_join(). Fixes: 957e2235e526 ("net: make switchdev_bridge_port_{,unoffload} loosely coupled with the bridge") Signed-off-by: Volodymyr Mytnyk Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/prestera/prestera_switchdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 3ce6ccd0f53942..79f2fca0d412d0 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -1124,7 +1124,7 @@ static int prestera_switchdev_blk_event(struct notifier_block *unused, prestera_port_obj_attr_set); break; default: - err = -EOPNOTSUPP; + return NOTIFY_DONE; } return notifier_from_errno(err); From e8d032507cb7912baf1d3e0af54516f823befefd Mon Sep 17 00:00:00 2001 From: Volodymyr Mytnyk Date: Thu, 18 Nov 2021 21:51:40 +0200 Subject: [PATCH 132/358] net: marvell: prestera: fix double free issue on err path fix error path handling in prestera_bridge_port_join() that cases prestera driver to crash (see below). Trace: Internal error: Oops: 96000044 [#1] SMP Modules linked in: prestera_pci prestera uio_pdrv_genirq CPU: 1 PID: 881 Comm: ip Not tainted 5.15.0 #1 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : prestera_bridge_destroy+0x2c/0xb0 [prestera] lr : prestera_bridge_port_join+0x2cc/0x350 [prestera] sp : ffff800011a1b0f0 ... x2 : ffff000109ca6c80 x1 : dead000000000100 x0 : dead000000000122 Call trace: prestera_bridge_destroy+0x2c/0xb0 [prestera] prestera_bridge_port_join+0x2cc/0x350 [prestera] prestera_netdev_port_event.constprop.0+0x3c4/0x450 [prestera] prestera_netdev_event_handler+0xf4/0x110 [prestera] raw_notifier_call_chain+0x54/0x80 call_netdevice_notifiers_info+0x54/0xa0 __netdev_upper_dev_link+0x19c/0x380 Fixes: e1189d9a5fbe ("net: marvell: prestera: Add Switchdev driver implementation") Signed-off-by: Volodymyr Mytnyk Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/prestera/prestera_switchdev.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 79f2fca0d412d0..b4599fe4ca8da6 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -497,8 +497,8 @@ int prestera_bridge_port_join(struct net_device *br_dev, br_port = prestera_bridge_port_add(bridge, port->dev); if (IS_ERR(br_port)) { - err = PTR_ERR(br_port); - goto err_brport_create; + prestera_bridge_put(bridge); + return PTR_ERR(br_port); } err = switchdev_bridge_port_offload(br_port->dev, port->dev, NULL, @@ -519,8 +519,6 @@ int prestera_bridge_port_join(struct net_device *br_dev, switchdev_bridge_port_unoffload(br_port->dev, NULL, NULL, NULL); err_switchdev_offload: prestera_bridge_port_put(br_port); -err_brport_create: - prestera_bridge_put(bridge); return err; } From 6a405f6c372d14707b87d3097b361b69899a26c8 Mon Sep 17 00:00:00 2001 From: Zekun Shen Date: Thu, 18 Nov 2021 16:08:02 -0500 Subject: [PATCH 133/358] atlantic: fix double-free in aq_ring_tx_clean We found this bug while fuzzing the device driver. Using and freeing the dangling pointer buff->skb would cause use-after-free and double-free. This bug is triggerable with compromised/malfunctioning devices. We found the bug with QEMU emulation and tested the patch by emulation. We did NOT test on a real device. Attached is the bug report. BUG: KASAN: double-free or invalid-free in consume_skb+0x6c/0x1c0 Call Trace: dump_stack+0x76/0xa0 print_address_description.constprop.0+0x16/0x200 ? consume_skb+0x6c/0x1c0 kasan_report_invalid_free+0x61/0xa0 ? consume_skb+0x6c/0x1c0 __kasan_slab_free+0x15e/0x170 ? consume_skb+0x6c/0x1c0 kfree+0x8c/0x230 consume_skb+0x6c/0x1c0 aq_ring_tx_clean+0x5c2/0xa80 [atlantic] aq_vec_poll+0x309/0x5d0 [atlantic] ? _sub_I_65535_1+0x20/0x20 [atlantic] ? __next_timer_interrupt+0xba/0xf0 net_rx_action+0x363/0xbd0 ? call_timer_fn+0x240/0x240 ? __switch_to_asm+0x34/0x70 ? napi_busy_loop+0x520/0x520 ? net_tx_action+0x379/0x720 __do_softirq+0x18c/0x634 ? takeover_tasklets+0x5f0/0x5f0 run_ksoftirqd+0x15/0x20 smpboot_thread_fn+0x2f1/0x6b0 ? smpboot_unregister_percpu_thread+0x160/0x160 ? __kthread_parkme+0x80/0x100 ? smpboot_unregister_percpu_thread+0x160/0x160 kthread+0x2b5/0x3b0 ? kthread_create_on_node+0xd0/0xd0 ret_from_fork+0x22/0x40 Reported-by: Brendan Dolan-Gavitt Signed-off-by: Zekun Shen Reviewed-by: Igor Russkikh Signed-off-by: David S. Miller --- drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 24122ccda614cc..81b3756417ec2c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -298,13 +298,14 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) } } - if (unlikely(buff->is_eop)) { + if (unlikely(buff->is_eop && buff->skb)) { u64_stats_update_begin(&self->stats.tx.syncp); ++self->stats.tx.packets; self->stats.tx.bytes += buff->skb->len; u64_stats_update_end(&self->stats.tx.syncp); dev_kfree_skb_any(buff->skb); + buff->skb = NULL; } buff->pa = 0U; buff->eop_index = 0xffffU; From 0f296e782f21dc1c55475a3c107ac68ab09cc1cf Mon Sep 17 00:00:00 2001 From: Zekun Shen Date: Thu, 18 Nov 2021 16:42:47 -0500 Subject: [PATCH 134/358] stmmac_pci: Fix underflow size in stmmac_rx This bug report came up when we were testing the device driver by fuzzing. It shows that buf1_len can get underflowed and be 0xfffffffc (4294967292). This bug is triggerable with a compromised/malfunctioning device. We found the bug through QEMU emulation tested the patch with emulation. We did NOT test it on real hardware. Attached is the bug report by fuzzing. BUG: KASAN: use-after-free in stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] Read of size 4294967292 at addr ffff888016358000 by task ksoftirqd/0/9 CPU: 0 PID: 9 Comm: ksoftirqd/0 Tainted: G W 5.6.0 #1 Call Trace: dump_stack+0x76/0xa0 print_address_description.constprop.0+0x16/0x200 ? stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] ? stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] __kasan_report.cold+0x37/0x7c ? stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] kasan_report+0xe/0x20 check_memory_region+0x15a/0x1d0 memcpy+0x20/0x50 stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] ? stmmac_suspend+0x850/0x850 [stmmac] ? __next_timer_interrupt+0xba/0xf0 net_rx_action+0x363/0xbd0 ? call_timer_fn+0x240/0x240 ? __switch_to_asm+0x40/0x70 ? napi_busy_loop+0x520/0x520 ? __schedule+0x839/0x15a0 __do_softirq+0x18c/0x634 ? takeover_tasklets+0x5f0/0x5f0 run_ksoftirqd+0x15/0x20 smpboot_thread_fn+0x2f1/0x6b0 ? smpboot_unregister_percpu_thread+0x160/0x160 ? __kthread_parkme+0x80/0x100 ? smpboot_unregister_percpu_thread+0x160/0x160 kthread+0x2b5/0x3b0 ? kthread_create_on_node+0xd0/0xd0 ret_from_fork+0x22/0x40 Reported-by: Brendan Dolan-Gavitt Signed-off-by: Zekun Shen Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 2eb28457633674..19bc86f2092fc3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5161,12 +5161,13 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) if (likely(!(status & rx_not_ls)) && (likely(priv->synopsys_id >= DWMAC_CORE_4_00) || unlikely(status != llc_snap))) { - if (buf2_len) + if (buf2_len) { buf2_len -= ETH_FCS_LEN; - else + len -= ETH_FCS_LEN; + } else if (buf1_len) { buf1_len -= ETH_FCS_LEN; - - len -= ETH_FCS_LEN; + len -= ETH_FCS_LEN; + } } if (!skb) { From a94f61e63f337d95001e1a976ab701100fa1d666 Mon Sep 17 00:00:00 2001 From: Michael Zaidman Date: Sat, 23 Oct 2021 22:39:57 +0300 Subject: [PATCH 135/358] HID: ft260: fix i2c probing for hwmon devices The below scenario causes the kernel NULL pointer dereference failure: 1. sudo insmod hid-ft260.ko 2. sudo modprobe lm75 3. unplug USB hid-ft260 4. plug USB hid-ft260 [ +0.000006] Call Trace: [ +0.000004] __i2c_smbus_xfer.part.0+0xd1/0x310 [ +0.000007] ? ft260_smbus_write+0x140/0x140 [hid_ft260] [ +0.000005] __i2c_smbus_xfer+0x2b/0x80 [ +0.000004] i2c_smbus_xfer+0x61/0xf0 [ +0.000005] i2c_default_probe+0xf9/0x130 [ +0.000004] i2c_detect_address+0x84/0x160 [ +0.000004] ? kmem_cache_alloc_trace+0xf6/0x200 [ +0.000009] ? i2c_detect.isra.0+0x69/0x130 [ +0.000005] i2c_detect.isra.0+0xbf/0x130 [ +0.000004] ? __process_new_driver+0x30/0x30 [ +0.000004] __process_new_adapter+0x18/0x20 [ +0.000004] bus_for_each_drv+0x84/0xd0 [ +0.000003] i2c_register_adapter+0x1e4/0x400 [ +0.000005] i2c_add_adapter+0x5c/0x80 [ +0.000004] ft260_probe.cold+0x222/0x2e2 [hid_ft260] [ +0.000006] hid_device_probe+0x10e/0x170 [hid] [ +0.000009] really_probe+0xff/0x460 [ +0.000004] driver_probe_device+0xe9/0x160 [ +0.000003] __device_attach_driver+0x71/0xd0 [ +0.000004] ? driver_allows_async_probing+0x50/0x50 [ +0.000004] bus_for_each_drv+0x84/0xd0 [ +0.000002] __device_attach+0xde/0x1e0 [ +0.000004] device_initial_probe+0x13/0x20 [ +0.000004] bus_probe_device+0x8f/0xa0 [ +0.000003] device_add+0x333/0x5f0 It happened when i2c core probed for the devices associated with the lm75 driver by invoking 2c_detect()-->..-->ft260_smbus_write() from within the ft260_probe before setting the adapter data with i2c_set_adapdata(). Moving the i2c_set_adapdata() before i2c_add_adapter() fixed the failure. Signed-off-by: Michael Zaidman Signed-off-by: Germain Hebert Signed-off-by: Jiri Kosina --- drivers/hid/hid-ft260.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c index 4ef1c3b8094ea0..8ee77f4afe9ff6 100644 --- a/drivers/hid/hid-ft260.c +++ b/drivers/hid/hid-ft260.c @@ -966,24 +966,23 @@ static int ft260_probe(struct hid_device *hdev, const struct hid_device_id *id) mutex_init(&dev->lock); init_completion(&dev->wait); + ret = ft260_xfer_status(dev); + if (ret) + ft260_i2c_reset(hdev); + + i2c_set_adapdata(&dev->adap, dev); ret = i2c_add_adapter(&dev->adap); if (ret) { hid_err(hdev, "failed to add i2c adapter\n"); goto err_hid_close; } - i2c_set_adapdata(&dev->adap, dev); - ret = sysfs_create_group(&hdev->dev.kobj, &ft260_attr_group); if (ret < 0) { hid_err(hdev, "failed to create sysfs attrs\n"); goto err_i2c_free; } - ret = ft260_xfer_status(dev); - if (ret) - ft260_i2c_reset(hdev); - return 0; err_i2c_free: From 7fc48fd6b2c0acacd8130d83d2a037670d6192d2 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 28 Oct 2021 18:33:30 +0200 Subject: [PATCH 136/358] HID: input: Fix parsing of HID_CP_CONSUMER_CONTROL fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix parsing of HID_CP_CONSUMER_CONTROL fields which are not in the HID_CP_PROGRAMMABLEBUTTONS collection. Fixes: bcfa8d14570d ("HID: input: Add support for Programmable Buttons") BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=2018096 Cc: Thomas Weißschuh Suggested-by: Benjamin Tissoires Signed-off-by: Hans de Goede Reviewed-By: Thomas Weißschuh Signed-off-by: Jiri Kosina --- drivers/hid/hid-input.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 2c72ce4147b174..92e87992b586e9 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -650,10 +650,9 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel code += KEY_MACRO1; else code += BTN_TRIGGER_HAPPY - 0x1e; - } else { - goto ignore; + break; } - break; + fallthrough; default: switch (field->physical) { case HID_GD_MOUSE: From 3e6a950d98366f5e716904e9a7e8ffc7ed638bd6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Thu, 28 Oct 2021 22:55:42 +0200 Subject: [PATCH 137/358] HID: input: set usage type to key on keycode remap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When a scancode is manually remapped that previously was not handled as key, then the old usage type was incorrectly reused. This caused issues on a "04b3:301b IBM Corp. SK-8815 Keyboard" which has marked some of its keys with an invalid HID usage. These invalid usage keys are being ignored since support for USB programmable buttons was added. The scancodes are however remapped explicitly by the systemd hwdb to the keycodes that are printed on the physical buttons. During this mapping step the existing usage is retrieved which will be found with a default type of 0 (EV_SYN) instead of EV_KEY. The events with the correct code but EV_SYN type are not forwarded to userspace. This also leads to a kernel oops when trying to print the report descriptor via debugfs. hid_resolv_event() tries to resolve a EV_SYN event with an EV_KEY code which leads to an out-of-bounds access in the EV_SYN names array. Fixes: bcfa8d1457 ("HID: input: Add support for Programmable Buttons") Fixes: f5854fad39 ("Input: hid-input - allow mapping unknown usages") Reported-by: Brent Roman Tested-by: Brent Roman Signed-off-by: Thomas Weißschuh Reviewed-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- drivers/hid/hid-input.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 92e87992b586e9..4c4cebd8e1fcaf 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -160,6 +160,7 @@ static int hidinput_setkeycode(struct input_dev *dev, if (usage) { *old_keycode = usage->type == EV_KEY ? usage->code : KEY_RESERVED; + usage->type = EV_KEY; usage->code = ke->keycode; clear_bit(*old_keycode, dev->keybit); From b74edf9bfbc11a7d0d0d756f06b17beb213ad5ca Mon Sep 17 00:00:00 2001 From: Trevor Davenport Date: Wed, 3 Nov 2021 00:40:24 -0600 Subject: [PATCH 138/358] HID: Ignore battery for Elan touchscreen on HP Envy X360 15-eu0xxx Battery status is reported for the HP Envy X360 Convertible 15-eu0xxx even if it does not have a battery. Prevent it from always reporting the battery as low. Signed-off-by: Trevor Davenport Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-input.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 95037a3e2e6ef9..96a455921c67ae 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -397,6 +397,7 @@ #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W 0x0401 #define USB_DEVICE_ID_HP_X2 0x074d #define USB_DEVICE_ID_HP_X2_10_COVER 0x0755 +#define I2C_DEVICE_ID_HP_ENVY_X360_15 0x2d05 #define I2C_DEVICE_ID_HP_SPECTRE_X360_15 0x2817 #define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706 #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 4c4cebd8e1fcaf..217f2d1b91c56e 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -325,6 +325,8 @@ static const struct hid_device_id hid_battery_quirks[] = { HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15), + HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN), From fa48020c9fae2872f7bf8f38e09f73eb61fdb4ce Mon Sep 17 00:00:00 2001 From: Vihas Mak Date: Sun, 14 Nov 2021 01:34:48 +0530 Subject: [PATCH 139/358] HID: thrustmaster: fix sparse warnings Changed 0 to NULL to fix following sparse warnings: drivers/hid/hid-thrustmaster.c:208:43: warning: Using plain integer as NULL pointer drivers/hid/hid-thrustmaster.c:241:17: warning: Using plain integer as NULL pointer drivers/hid/hid-thrustmaster.c:275:37: warning: Using plain integer as NULL pointer Signed-off-by: Vihas Mak Signed-off-by: Jiri Kosina --- drivers/hid/hid-thrustmaster.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c index d44550aa880573..3a5333424aa327 100644 --- a/drivers/hid/hid-thrustmaster.c +++ b/drivers/hid/hid-thrustmaster.c @@ -205,7 +205,7 @@ static void thrustmaster_model_handler(struct urb *urb) struct tm_wheel *tm_wheel = hid_get_drvdata(hdev); uint16_t model = 0; int i, ret; - const struct tm_wheel_info *twi = 0; + const struct tm_wheel_info *twi = NULL; if (urb->status) { hid_err(hdev, "URB to get model id failed with error %d\n", urb->status); @@ -238,7 +238,7 @@ static void thrustmaster_model_handler(struct urb *urb) tm_wheel->usb_dev, usb_sndctrlpipe(tm_wheel->usb_dev, 0), (char *)tm_wheel->change_request, - 0, 0, // We do not expect any response from the wheel + NULL, 0, // We do not expect any response from the wheel thrustmaster_change_handler, hdev ); @@ -272,7 +272,7 @@ static void thrustmaster_remove(struct hid_device *hdev) static int thrustmaster_probe(struct hid_device *hdev, const struct hid_device_id *id) { int ret = 0; - struct tm_wheel *tm_wheel = 0; + struct tm_wheel *tm_wheel = NULL; ret = hid_parse(hdev); if (ret) { From a1091118e0d6d84c2fdb94e6c397ac790bfb9dd6 Mon Sep 17 00:00:00 2001 From: Claudia Pellegrino Date: Sun, 14 Nov 2021 03:53:27 +0100 Subject: [PATCH 140/358] HID: magicmouse: prevent division by 0 on scroll MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In hid_magicmouse, if the user has set scroll_speed to a value between 55 and 63 and scrolls seven times in quick succession, the step_hr variable in the magicmouse_emit_touch function becomes 0. That causes a division by zero further down in the function when it does `step_x_hr /= step_hr`. To reproduce, create `/etc/modprobe.d/hid_magicmouse.conf` with the following content: ``` options hid_magicmouse scroll_acceleration=1 scroll_speed=55 ``` Then reboot, connect a Magic Mouse and scroll seven times quickly. The system will freeze for a minute, and after that `dmesg` will confirm that a division by zero occurred. Enforce a minimum of 1 for the variable so the high resolution step count can never reach 0 even at maximum scroll acceleration. Fixes: d4b9f10a0eb6 ("HID: magicmouse: enable high-resolution scroll") Signed-off-by: Claudia Pellegrino Tested-by: José Expósito Signed-off-by: Jiri Kosina --- drivers/hid/hid-magicmouse.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 686788ebf3e1e7..d7687ce706144a 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -256,8 +256,11 @@ static void magicmouse_emit_touch(struct magicmouse_sc *msc, int raw_id, u8 *tda unsigned long now = jiffies; int step_x = msc->touches[id].scroll_x - x; int step_y = msc->touches[id].scroll_y - y; - int step_hr = ((64 - (int)scroll_speed) * msc->scroll_accel) / - SCROLL_HR_STEPS; + int step_hr = + max_t(int, + ((64 - (int)scroll_speed) * msc->scroll_accel) / + SCROLL_HR_STEPS, + 1); int step_x_hr = msc->touches[id].scroll_x_hr - x; int step_y_hr = msc->touches[id].scroll_y_hr - y; From f61e06391d65c4ecb11ff2a0bdc1e7d70c2aa407 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 19 Nov 2021 15:58:30 +0100 Subject: [PATCH 141/358] HID: nintendo: eliminate dead datastructures in !CONFIG_NINTENDO_FF case The rumbling-related identifiers are never used in !CONFIG_NINTENDO_FF case, so let's hide them in order to avoid unused warnings. Reported-by: kernel test robot Signed-off-by: Jiri Kosina --- drivers/hid/hid-nintendo.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index 7e1d1127493ed6..b6a9a0f3966ee0 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -189,6 +189,7 @@ struct joycon_rumble_amp_data { u16 amp; }; +#if IS_ENABLED(CONFIG_NINTENDO_FF) /* * These tables are from * https://github.com/dekuNukem/Nintendo_Switch_Reverse_Engineering/blob/master/rumble_data_table.md @@ -289,6 +290,10 @@ static const struct joycon_rumble_amp_data joycon_rumble_amplitudes[] = { { 0xc2, 0x8070, 940 }, { 0xc4, 0x0071, 960 }, { 0xc6, 0x8071, 981 }, { 0xc8, 0x0072, joycon_max_rumble_amp } }; +static const u16 JC_RUMBLE_DFLT_LOW_FREQ = 160; +static const u16 JC_RUMBLE_DFLT_HIGH_FREQ = 320; +#endif /* IS_ENABLED(CONFIG_NINTENDO_FF) */ +static const u16 JC_RUMBLE_PERIOD_MS = 50; /* States for controller state machine */ enum joycon_ctlr_state { @@ -397,9 +402,6 @@ struct joycon_input_report { #define JC_RUMBLE_DATA_SIZE 8 #define JC_RUMBLE_QUEUE_SIZE 8 -static const u16 JC_RUMBLE_DFLT_LOW_FREQ = 160; -static const u16 JC_RUMBLE_DFLT_HIGH_FREQ = 320; -static const u16 JC_RUMBLE_PERIOD_MS = 50; static const unsigned short JC_RUMBLE_ZERO_AMP_PKT_CNT = 5; static const char * const joycon_player_led_names[] = { From 32bea35746097985c48cec836d5f557a3b66b60a Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Tue, 16 Nov 2021 14:15:02 +0100 Subject: [PATCH 142/358] HID: multitouch: Fix Iiyama ProLite T1931SAW (0eef:0001 again!) Iiyama ProLite T1931SAW does not work with Linux - input devices are created but cursor does not move. It has the infamous 0eef:0001 ID which has been reused for various devices before. It seems to require export_all_inputs = true. Hopefully there are no HID devices using this ID that will break. It should not break non-HID devices (handled by usbtouchscreen). Signed-off-by: Ondrej Zary Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-multitouch.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index e1afddb7b33d8e..082376a6cb3d73 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1888,6 +1888,11 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_CVTOUCH, USB_DEVICE_ID_CVTOUCH_SCREEN) }, + /* eGalax devices (SAW) */ + { .driver_data = MT_CLS_EXPORT_ALL_INPUTS, + MT_USB_DEVICE(USB_VENDOR_ID_DWAV, + USB_DEVICE_ID_EGALAX_TOUCHCONTROLLER) }, + /* eGalax devices (resistive) */ { .driver_data = MT_CLS_EGALAX, MT_USB_DEVICE(USB_VENDOR_ID_DWAV, From e792779e6b639c182df91b46ac1e5803460b0b15 Mon Sep 17 00:00:00 2001 From: Nitesh B Venkatesh Date: Fri, 4 Jun 2021 09:53:31 -0700 Subject: [PATCH 143/358] iavf: Prevent changing static ITR values if adaptive moderation is on Resolve being able to change static values on VF when adaptive interrupt moderation is enabled. This problem is fixed by checking the interrupt settings is not a combination of change of static value while adaptive interrupt moderation is turned on. Without this fix, the user would be able to change static values on VF with adaptive moderation enabled. Fixes: 65e87c0398f5 ("i40evf: support queue-specific settings for interrupt moderation") Signed-off-by: Nitesh B Venkatesh Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen --- .../net/ethernet/intel/iavf/iavf_ethtool.c | 30 ++++++++++++++++--- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 144a776793597f..71b23922089fbb 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -723,12 +723,31 @@ static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue, * * Change the ITR settings for a specific queue. **/ -static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, - struct ethtool_coalesce *ec, int queue) +static int iavf_set_itr_per_queue(struct iavf_adapter *adapter, + struct ethtool_coalesce *ec, int queue) { struct iavf_ring *rx_ring = &adapter->rx_rings[queue]; struct iavf_ring *tx_ring = &adapter->tx_rings[queue]; struct iavf_q_vector *q_vector; + u16 itr_setting; + + itr_setting = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + if (ec->rx_coalesce_usecs != itr_setting && + ec->use_adaptive_rx_coalesce) { + netif_info(adapter, drv, adapter->netdev, + "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n"); + return -EINVAL; + } + + itr_setting = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + if (ec->tx_coalesce_usecs != itr_setting && + ec->use_adaptive_tx_coalesce) { + netif_info(adapter, drv, adapter->netdev, + "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n"); + return -EINVAL; + } rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); @@ -751,6 +770,7 @@ static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, * the Tx and Rx ITR values based on the values we have entered * into the q_vector, no need to write the values now. */ + return 0; } /** @@ -792,9 +812,11 @@ static int __iavf_set_coalesce(struct net_device *netdev, */ if (queue < 0) { for (i = 0; i < adapter->num_active_queues; i++) - iavf_set_itr_per_queue(adapter, ec, i); + if (iavf_set_itr_per_queue(adapter, ec, i)) + return -EINVAL; } else if (queue < adapter->num_active_queues) { - iavf_set_itr_per_queue(adapter, ec, queue); + if (iavf_set_itr_per_queue(adapter, ec, queue)) + return -EINVAL; } else { netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", adapter->num_active_queues - 1); From 0cc318d2e8408bc0ffb4662a0c3e5e57005ac6ff Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Tue, 7 Sep 2021 09:25:40 +0000 Subject: [PATCH 144/358] iavf: Fix deadlock occurrence during resetting VF interface System hangs if close the interface is called from the kernel during the interface is in resetting state. During resetting operation the link is closing but kernel didn't know it and it tried to close this interface again what sometimes led to deadlock. Inform kernel about current state of interface and turn off the flag IFF_UP when interface is closing until reset is finished. Previously it was most likely to hang the system when kernel (network manager) tried to close the interface in the same time when interface was in resetting state because of deadlock. Fixes: 3c8e0b989aa1 ("i40vf: don't stop me now") Signed-off-by: Jaroslaw Gawin Signed-off-by: Jedrzej Jagielski Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 336e6bf95e48fc..84680777ac12b6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2254,6 +2254,7 @@ static void iavf_reset_task(struct work_struct *work) (adapter->state == __IAVF_RESETTING)); if (running) { + netdev->flags &= ~IFF_UP; netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; @@ -2365,7 +2366,7 @@ static void iavf_reset_task(struct work_struct *work) * to __IAVF_RUNNING */ iavf_up_complete(adapter); - + netdev->flags |= IFF_UP; iavf_irq_enable(adapter, true); } else { iavf_change_state(adapter, __IAVF_DOWN); @@ -2378,8 +2379,10 @@ static void iavf_reset_task(struct work_struct *work) reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - if (running) + if (running) { iavf_change_state(adapter, __IAVF_RUNNING); + netdev->flags |= IFF_UP; + } dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); iavf_close(netdev); } From 3b5bdd18eb76e7570d9bacbcab6828a9b26ae121 Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Wed, 15 Sep 2021 09:01:00 +0000 Subject: [PATCH 145/358] iavf: Fix refreshing iavf adapter stats on ethtool request Currently iavf adapter statistics are refreshed only in a watchdog task, triggered approximately every two seconds, which causes some ethtool requests to return outdated values. Add explicit statistics refresh when requested by ethtool -S. Fixes: b476b0030e61 ("iavf: Move commands processing to the separate function") Signed-off-by: Jan Sokolowski Signed-off-by: Jedrzej Jagielski Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf.h | 2 ++ drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 3 +++ drivers/net/ethernet/intel/iavf/iavf_main.c | 18 ++++++++++++++++++ .../net/ethernet/intel/iavf/iavf_virtchnl.c | 2 ++ 4 files changed, 25 insertions(+) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 75635bd57cf6d9..bb9cc227d1e1c0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -305,6 +305,7 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_DEL_FDIR_FILTER BIT(26) #define IAVF_FLAG_AQ_ADD_ADV_RSS_CFG BIT(27) #define IAVF_FLAG_AQ_DEL_ADV_RSS_CFG BIT(28) +#define IAVF_FLAG_AQ_REQUEST_STATS BIT(29) /* OS defined structs */ struct net_device *netdev; @@ -444,6 +445,7 @@ int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_schedule_request_stats(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); void iavf_update_stats(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 71b23922089fbb..0cecaff38d0427 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -354,6 +354,9 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, struct iavf_adapter *adapter = netdev_priv(netdev); unsigned int i; + /* Explicitly request stats refresh */ + iavf_schedule_request_stats(adapter); + iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); rcu_read_lock(); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 84680777ac12b6..8e96ae746c3df7 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -174,6 +174,19 @@ void iavf_schedule_reset(struct iavf_adapter *adapter) } } +/** + * iavf_schedule_request_stats - Set the flags and schedule statistics request + * @adapter: board private structure + * + * Sets IAVF_FLAG_AQ_REQUEST_STATS flag so iavf_watchdog_task() will explicitly + * request and refresh ethtool stats + **/ +void iavf_schedule_request_stats(struct iavf_adapter *adapter) +{ + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS; + mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); +} + /** * iavf_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure @@ -1709,6 +1722,11 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_del_adv_rss_cfg(adapter); return 0; } + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) { + iavf_request_stats(adapter); + return 0; + } + return -EAGAIN; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 8c3f0f77cb5742..8421cbe6a19731 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -784,6 +784,8 @@ void iavf_request_stats(struct iavf_adapter *adapter) /* no error message, this isn't crucial */ return; } + + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_STATS; adapter->current_op = VIRTCHNL_OP_GET_STATS; vqs.vsi_id = adapter->vsi_res->vsi_id; /* queue maps are ignored for this message - only the vsi is used */ From 5951a2b9812d8227d33f20d1899fae60e4f72c04 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 5 Nov 2021 09:20:25 -0700 Subject: [PATCH 146/358] iavf: Fix VLAN feature flags after VFR When a VF goes through a reset, it's possible for the VF's feature set to change. For example it may lose the VIRTCHNL_VF_OFFLOAD_VLAN capability after VF reset. Unfortunately, the driver doesn't correctly deal with this situation and errors are seen from downing/upping the interface and/or moving the interface in/out of a network namespace. When setting the interface down/up we see the following errors after the VIRTCHNL_VF_OFFLOAD_VLAN capability was taken away from the VF: ice 0000:51:00.1: VF 1 failed opcode 12, retval: -64 iavf 0000:51:09.1: Failed to add VLAN filter, error IAVF_NOT_SUPPORTED ice 0000:51:00.1: VF 1 failed opcode 13, retval: -64 iavf 0000:51:09.1: Failed to delete VLAN filter, error IAVF_NOT_SUPPORTED These add/delete errors are happening because the VLAN filters are tracked internally to the driver and regardless of the VLAN_ALLOWED() setting the driver tries to delete/re-add them over virtchnl. Fix the delete failure by making sure to delete any VLAN filter tracking in the driver when a removal request is made, while preventing the virtchnl request. This makes it so the driver's VLAN list is up to date and the errors are Fix the add failure by making sure the check for VLAN_ALLOWED() during reset is done after the VF receives its capability list from the PF via VIRTCHNL_OP_GET_VF_RESOURCES. If VLAN functionality is not allowed, then prevent requesting re-adding the filters over virtchnl. When moving the interface into a network namespace we see the following errors after the VIRTCHNL_VF_OFFLOAD_VLAN capability was taken away from the VF: iavf 0000:51:09.1 enp81s0f1v1: NIC Link is Up Speed is 25 Gbps Full Duplex iavf 0000:51:09.1 temp_27: renamed from enp81s0f1v1 iavf 0000:51:09.1 mgmt: renamed from temp_27 iavf 0000:51:09.1 dev27: set_features() failed (-22); wanted 0x020190001fd54833, left 0x020190001fd54bb3 These errors are happening because we aren't correctly updating the netdev capabilities and dealing with ndo_fix_features() and ndo_set_features() correctly. Fix this by only reporting errors in the driver's ndo_set_features() callback when VIRTCHNL_VF_OFFLOAD_VLAN is not allowed and any attempt to enable the VLAN features is made. Also, make sure to disable VLAN insertion, filtering, and stripping since the VIRTCHNL_VF_OFFLOAD_VLAN flag applies to all of them and not just VLAN stripping. Also, after we process the capabilities in the VF reset path, make sure to call netdev_update_features() in case the capabilities have changed in order to update the netdev's feature set to match the VF's actual capabilities. Lastly, make sure to always report success on VLAN filter delete when VIRTCHNL_VF_OFFLOAD_VLAN is not supported. The changed flow in iavf_del_vlans() allows the stack to delete previosly existing VLAN filters even if VLAN filtering is not allowed. This makes it so the VLAN filter list is up to date. Fixes: 8774370d268f ("i40e/i40evf: support for VF VLAN tag stripping control") Signed-off-by: Brett Creeley Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf.h | 1 + drivers/net/ethernet/intel/iavf/iavf_main.c | 33 ++++++-------- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 45 +++++++++++++++++-- 3 files changed, 56 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index bb9cc227d1e1c0..3789269ce741d4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -503,4 +503,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); +int iavf_lock_timeout(struct mutex *lock, unsigned int msecs); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 8e96ae746c3df7..14934a7a13efdc 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -147,7 +147,7 @@ enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, * * Returns 0 on success, negative on failure **/ -static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) +int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) { unsigned int wait, delay = 10; @@ -717,13 +717,11 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) **/ static void iavf_restore_filters(struct iavf_adapter *adapter) { - /* re-add all VLAN filters */ - if (VLAN_ALLOWED(adapter)) { - u16 vid; + u16 vid; - for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID) - iavf_add_vlan(adapter, vid); - } + /* re-add all VLAN filters */ + for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID) + iavf_add_vlan(adapter, vid); } /** @@ -758,9 +756,6 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (!VLAN_ALLOWED(adapter)) - return -EIO; - iavf_del_vlan(adapter, vid); clear_bit(vid, adapter->vsi.active_vlans); @@ -2191,7 +2186,6 @@ static void iavf_reset_task(struct work_struct *work) struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; struct iavf_mac_filter *f, *ftmp; - struct iavf_vlan_filter *vlf; struct iavf_cloud_filter *cf; u32 reg_val; int i = 0, err; @@ -2332,11 +2326,6 @@ static void iavf_reset_task(struct work_struct *work) list_for_each_entry(f, &adapter->mac_filter_list, list) { f->add = true; } - /* re-add all VLAN filters */ - list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { - vlf->add = true; - } - spin_unlock_bh(&adapter->mac_vlan_list_lock); /* check if TCs are running and re-add all cloud filters */ @@ -2350,7 +2339,6 @@ static void iavf_reset_task(struct work_struct *work) spin_unlock_bh(&adapter->cloud_filter_list_lock); adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); @@ -3462,11 +3450,16 @@ static int iavf_set_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - /* Don't allow changing VLAN_RX flag when adapter is not capable - * of VLAN offload + /* Don't allow enabling VLAN features when adapter is not capable + * of VLAN offload/filtering */ if (!VLAN_ALLOWED(adapter)) { - if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) + netdev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER); + if (features & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER)) return -EINVAL; } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { if (features & NETIF_F_HW_VLAN_CTAG_RX) diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 8421cbe6a19731..d60bf7c2120063 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -607,7 +607,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) if (f->add) count++; } - if (!count) { + if (!count || !VLAN_ALLOWED(adapter)) { adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -673,9 +673,19 @@ void iavf_del_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->remove) + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { + /* since VLAN capabilities are not allowed, we dont want to send + * a VLAN delete request because it will most likely fail and + * create unnecessary errors/noise, so just free the VLAN + * filters marked for removal to enable bailing out before + * sending a virtchnl message + */ + if (f->remove && !VLAN_ALLOWED(adapter)) { + list_del(&f->list); + kfree(f); + } else if (f->remove) { count++; + } } if (!count) { adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; @@ -1724,8 +1734,37 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } spin_lock_bh(&adapter->mac_vlan_list_lock); iavf_add_filter(adapter, adapter->hw.mac.addr); + + if (VLAN_ALLOWED(adapter)) { + if (!list_empty(&adapter->vlan_filter_list)) { + struct iavf_vlan_filter *vlf; + + /* re-add all VLAN filters over virtchnl */ + list_for_each_entry(vlf, + &adapter->vlan_filter_list, + list) + vlf->add = true; + + adapter->aq_required |= + IAVF_FLAG_AQ_ADD_VLAN_FILTER; + } + } + spin_unlock_bh(&adapter->mac_vlan_list_lock); iavf_process_config(adapter); + + /* unlock crit_lock before acquiring rtnl_lock as other + * processes holding rtnl_lock could be waiting for the same + * crit_lock + */ + mutex_unlock(&adapter->crit_lock); + rtnl_lock(); + netdev_update_features(adapter->netdev); + rtnl_unlock(); + if (iavf_lock_timeout(&adapter->crit_lock, 10000)) + dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", + __FUNCTION__); + } break; case VIRTCHNL_OP_ENABLE_QUEUES: From dc27f3c5d10c58069672215787a96b4fae01818b Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Fri, 19 Nov 2021 14:45:20 +0100 Subject: [PATCH 147/358] selinux: fix NULL-pointer dereference when hashtab allocation fails When the hash table slot array allocation fails in hashtab_init(), h->size is left initialized with a non-zero value, but the h->htable pointer is NULL. This may then cause a NULL pointer dereference, since the policydb code relies on the assumption that even after a failed hashtab_init(), hashtab_map() and hashtab_destroy() can be safely called on it. Yet, these detect an empty hashtab only by looking at the size. Fix this by making sure that hashtab_init() always leaves behind a valid empty hashtab when the allocation fails. Cc: stable@vger.kernel.org Fixes: 03414a49ad5f ("selinux: do not allocate hashtabs dynamically") Signed-off-by: Ondrej Mosnacek Signed-off-by: Paul Moore --- security/selinux/ss/hashtab.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/security/selinux/ss/hashtab.c b/security/selinux/ss/hashtab.c index 727c3b484bd34f..0ae4e4e57a401e 100644 --- a/security/selinux/ss/hashtab.c +++ b/security/selinux/ss/hashtab.c @@ -31,13 +31,20 @@ static u32 hashtab_compute_size(u32 nel) int hashtab_init(struct hashtab *h, u32 nel_hint) { - h->size = hashtab_compute_size(nel_hint); + u32 size = hashtab_compute_size(nel_hint); + + /* should already be zeroed, but better be safe */ h->nel = 0; - if (!h->size) - return 0; + h->size = 0; + h->htable = NULL; - h->htable = kcalloc(h->size, sizeof(*h->htable), GFP_KERNEL); - return h->htable ? 0 : -ENOMEM; + if (size) { + h->htable = kcalloc(size, sizeof(*h->htable), GFP_KERNEL); + if (!h->htable) + return -ENOMEM; + h->size = size; + } + return 0; } int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, From 2a0991929aba0a3dd6fe51d1daba06a93a96a021 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 19 Nov 2021 16:39:13 +0100 Subject: [PATCH 148/358] xen/pvh: add missing prototype to header The prototype of mem_map_via_hcall() is missing in its header, so add it. Reported-by: kernel test robot Fixes: a43fb7da53007e67ad ("xen/pvh: Move Xen code for getting mem map via hcall out of common file") Signed-off-by: Juergen Gross Link: https://lore.kernel.org/r/20211119153913.21678-1-jgross@suse.com Reviewed-by: Boris Ostrovsky Signed-off-by: Boris Ostrovsky --- arch/x86/include/asm/xen/hypervisor.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 4957f59deb40bd..5adab895127e19 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -64,6 +64,7 @@ void xen_arch_unregister_cpu(int num); #ifdef CONFIG_PVH void __init xen_pvh_init(struct boot_params *boot_params); +void __init mem_map_via_hcall(struct boot_params *boot_params_p); #endif #endif /* _ASM_X86_XEN_HYPERVISOR_H */ From fa9730b4f28b7bd183d28a0bf636ab7108de35d7 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 27 Oct 2021 10:32:54 +0800 Subject: [PATCH 149/358] ALSA: intel-dsp-config: add quirk for JSL devices based on ES8336 codec These devices are based on an I2C/I2S device, we need to force the use of the SOF driver otherwise the legacy HDaudio driver will be loaded - only HDMI will be supported. We previously added support for other Intel platforms but missed JasperLake. BugLink: https://github.com/thesofproject/linux/issues/3210 Fixes: 9d36ceab9415 ('ALSA: intel-dsp-config: add quirk for APL/GLK/TGL devices based on ES8336 codec') Signed-off-by: Pierre-Louis Bossart Reviewed-by: Kai Vehmanen Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211027023254.24955-1-yung-chuan.liao@linux.intel.com Signed-off-by: Takashi Iwai --- sound/hda/intel-dsp-config.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index b9ac9e9e45a484..10a0bffc3cf6c2 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -299,6 +299,15 @@ static const struct config_entry config_table[] = { }, #endif +/* JasperLake */ +#if IS_ENABLED(CONFIG_SND_SOC_SOF_JASPERLAKE) + { + .flags = FLAG_SOF, + .device = 0x4dc8, + .codec_hid = "ESSX8336", + }, +#endif + /* Tigerlake */ #if IS_ENABLED(CONFIG_SND_SOC_SOF_TIGERLAKE) { From ee50e67ba0e17b1a1a8d76691d02eadf9e0f392c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Nov 2021 15:27:54 +0100 Subject: [PATCH 150/358] mptcp: fix delack timer To compute the rtx timeout schedule_3rdack_retransmission() does multiple things in the wrong way: srtt_us is measured in usec/8 and the timeout itself is an absolute value. Fixes: ec3edaa7ca6ce02f ("mptcp: Add handling of outgoing MP_JOIN requests") Acked-by: Paolo Abeni Reviewed-by: Mat Martineau @linux.intel.com> Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/mptcp/options.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 7c3420afb1a013..2e9b73eeeeb58e 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -434,9 +434,10 @@ static void schedule_3rdack_retransmission(struct sock *sk) /* reschedule with a timeout above RTT, as we must look only for drop */ if (tp->srtt_us) - timeout = tp->srtt_us << 1; + timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); else timeout = TCP_TIMEOUT_INIT; + timeout += jiffies; WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; From bcd97734318d1d87bb237dbc0a60c81237b0ac50 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 19 Nov 2021 15:27:55 +0100 Subject: [PATCH 151/358] mptcp: use delegate action to schedule 3rd ack retrans Scheduling a delack in mptcp_established_options_mp() is not a good idea: such function is called by tcp_send_ack() and the pending delayed ack will be cleared shortly after by the tcp_event_ack_sent() call in __tcp_transmit_skb(). Instead use the mptcp delegated action infrastructure to schedule the delayed ack after the current bh processing completes. Additionally moves the schedule_3rdack_retransmission() helper into protocol.c to avoid making it visible in a different compilation unit. Fixes: ec3edaa7ca6ce02f ("mptcp: Add handling of outgoing MP_JOIN requests") Reviewed-by: Mat Martineau @linux.intel.com> Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/mptcp/options.c | 33 ++++++++-------------------- net/mptcp/protocol.c | 51 ++++++++++++++++++++++++++++++++++++-------- net/mptcp/protocol.h | 17 ++++++++------- 3 files changed, 60 insertions(+), 41 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 2e9b73eeeeb58e..fe98e4f475baa4 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -422,29 +422,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, return false; } -/* MP_JOIN client subflow must wait for 4th ack before sending any data: - * TCP can't schedule delack timer before the subflow is fully established. - * MPTCP uses the delack timer to do 3rd ack retransmissions - */ -static void schedule_3rdack_retransmission(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - unsigned long timeout; - - /* reschedule with a timeout above RTT, as we must look only for drop */ - if (tp->srtt_us) - timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); - else - timeout = TCP_TIMEOUT_INIT; - timeout += jiffies; - - WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); - icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; - icsk->icsk_ack.timeout = timeout; - sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); -} - static void clear_3rdack_retransmission(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -527,7 +504,15 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPJ_ACK; pr_debug("subflow=%p", subflow); - schedule_3rdack_retransmission(sk); + /* we can use the full delegate action helper only from BH context + * If we are in process context - sk is flushing the backlog at + * socket lock release time - just set the appropriate flag, will + * be handled by the release callback + */ + if (sock_owned_by_user(sk)) + set_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status); + else + mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_ACK); return true; } return false; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b7e32e316738b8..c82a76d2d0bfeb 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1596,7 +1596,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) if (!xmit_ssk) goto out; if (xmit_ssk != ssk) { - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), + MPTCP_DELEGATE_SEND); goto out; } @@ -2943,7 +2944,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk) if (xmit_ssk == ssk) __mptcp_subflow_push_pending(sk, ssk); else if (xmit_ssk) - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), MPTCP_DELEGATE_SEND); } else { set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); } @@ -2993,18 +2994,50 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_update_rmem(sk); } +/* MP_JOIN client subflow must wait for 4th ack before sending any data: + * TCP can't schedule delack timer before the subflow is fully established. + * MPTCP uses the delack timer to do 3rd ack retransmissions + */ +static void schedule_3rdack_retransmission(struct sock *ssk) +{ + struct inet_connection_sock *icsk = inet_csk(ssk); + struct tcp_sock *tp = tcp_sk(ssk); + unsigned long timeout; + + if (mptcp_subflow_ctx(ssk)->fully_established) + return; + + /* reschedule with a timeout above RTT, as we must look only for drop */ + if (tp->srtt_us) + timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); + else + timeout = TCP_TIMEOUT_INIT; + timeout += jiffies; + + WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); + icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; + icsk->icsk_ack.timeout = timeout; + sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); +} + void mptcp_subflow_process_delegated(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; - mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) - __mptcp_subflow_push_pending(sk, ssk); - else - set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); - mptcp_data_unlock(sk); - mptcp_subflow_delegated_done(subflow); + if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_subflow_push_pending(sk, ssk); + else + set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); + mptcp_data_unlock(sk); + mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND); + } + if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) { + schedule_3rdack_retransmission(ssk); + mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK); + } } static int mptcp_hash(struct sock *sk) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 67a61ac48b20a9..d87cc040352e3c 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -387,6 +387,7 @@ struct mptcp_delegated_action { DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); #define MPTCP_DELEGATE_SEND 0 +#define MPTCP_DELEGATE_ACK 1 /* MPTCP subflow context */ struct mptcp_subflow_context { @@ -492,23 +493,23 @@ static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk, void mptcp_subflow_process_delegated(struct sock *ssk); -static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action) { struct mptcp_delegated_action *delegated; bool schedule; + /* the caller held the subflow bh socket lock */ + lockdep_assert_in_softirq(); + /* The implied barrier pairs with mptcp_subflow_delegated_done(), and * ensures the below list check sees list updates done prior to status * bit changes */ - if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + if (!test_and_set_bit(action, &subflow->delegated_status)) { /* still on delegated list from previous scheduling */ if (!list_empty(&subflow->delegated_node)) return; - /* the caller held the subflow bh socket lock */ - lockdep_assert_in_softirq(); - delegated = this_cpu_ptr(&mptcp_delegated_actions); schedule = list_empty(&delegated->head); list_add_tail(&subflow->delegated_node, &delegated->head); @@ -533,16 +534,16 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated) static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow) { - return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); + return !!READ_ONCE(subflow->delegated_status); } -static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action) { /* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before * touching the status bit */ smp_wmb(); - clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); + clear_bit(action, &subflow->delegated_status); } int mptcp_is_enabled(const struct net *net); From f9390b249c90a15a4d9e69fbfb7a53c860b1fcaf Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Fri, 19 Nov 2021 13:05:21 +0100 Subject: [PATCH 152/358] af_unix: fix regression in read after shutdown On kernels before v5.15, calling read() on a unix socket after shutdown(SHUT_RD) or shutdown(SHUT_RDWR) would return the data previously written or EOF. But now, while read() after shutdown(SHUT_RD) still behaves the same way, read() after shutdown(SHUT_RDWR) always fails with -EINVAL. This behaviour change was apparently inadvertently introduced as part of a bug fix for a different regression caused by the commit adding sockmap support to af_unix, commit 94531cfcbe79c359 ("af_unix: Add unix_stream_proto for sockmap"). Those commits, for unclear reasons, started setting the socket state to TCP_CLOSE on shutdown(SHUT_RDWR), while this state change had previously only been done in unix_release_sock(). Restore the original behaviour. The sockmap tests in tests/selftests/bpf continue to pass after this patch. Fixes: d0c6416bd7091647f60 ("unix: Fix an issue in unix_shutdown causing the other end read/write failures") Link: https://lore.kernel.org/lkml/20211111140000.GA10779@axis.com/ Signed-off-by: Vincent Whitchurch Tested-by: Casey Schaufler Signed-off-by: David S. Miller --- net/unix/af_unix.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 78e08e82c08c42..b0bfc78e421cee 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2882,9 +2882,6 @@ static int unix_shutdown(struct socket *sock, int mode) unix_state_lock(sk); sk->sk_shutdown |= mode; - if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && - mode == SHUTDOWN_MASK) - sk->sk_state = TCP_CLOSE; other = unix_peer(sk); if (other) sock_hold(other); From d8af404ffce71448f29bbc19a05e3d095baf98eb Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 17 Nov 2021 17:59:01 -0800 Subject: [PATCH 153/358] iomap: Fix inline extent handling in iomap_readpage Before commit 740499c78408 ("iomap: fix the iomap_readpage_actor return value for inline data"), when hitting an IOMAP_INLINE extent, iomap_readpage_actor would report having read the entire page. Since then, it only reports having read the inline data (iomap->length). This will force iomap_readpage into another iteration, and the filesystem will report an unaligned hole after the IOMAP_INLINE extent. But iomap_readpage_actor (now iomap_readpage_iter) isn't prepared to deal with unaligned extents, it will get things wrong on filesystems with a block size smaller than the page size, and we'll eventually run into the following warning in iomap_iter_advance: WARN_ON_ONCE(iter->processed > iomap_length(iter)); Fix that by changing iomap_readpage_iter to return 0 when hitting an inline extent; this will cause iomap_iter to stop immediately. To fix readahead as well, change iomap_readahead_iter to pass on iomap_readpage_iter return values less than or equal to zero. Fixes: 740499c78408 ("iomap: fix the iomap_readpage_actor return value for inline data") Cc: stable@vger.kernel.org # v5.15+ Signed-off-by: Andreas Gruenbacher Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 1753c26c8e76e3..fe10d8a30f6bdf 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -256,8 +256,13 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter, unsigned poff, plen; sector_t sector; - if (iomap->type == IOMAP_INLINE) - return min(iomap_read_inline_data(iter, page), length); + if (iomap->type == IOMAP_INLINE) { + loff_t ret = iomap_read_inline_data(iter, page); + + if (ret < 0) + return ret; + return 0; + } /* zero post-eof blocks as the page may be mapped */ iop = iomap_page_create(iter->inode, page); @@ -370,6 +375,8 @@ static loff_t iomap_readahead_iter(const struct iomap_iter *iter, ctx->cur_page_in_bio = false; } ret = iomap_readpage_iter(iter, ctx, done); + if (ret <= 0) + return ret; } return done; From 8d192bec534bd5b778135769a12e5f04580771f7 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 19 Nov 2021 22:31:03 +0100 Subject: [PATCH 154/358] parisc: Increase FRAME_WARN to 2048 bytes on parisc PA-RISC uses a much bigger frame size for functions than other architectures. So increase it to 2048 for 32- and 64-bit kernels. This fixes e.g. a warning in lib/xxhash.c. Reported-by: kernel test robot Signed-off-by: Helge Deller --- lib/Kconfig.debug | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 9ef7ce18b4f561..5c12bde10996cf 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -346,8 +346,9 @@ config FRAME_WARN int "Warn for stack frames larger than" range 0 8192 default 2048 if GCC_PLUGIN_LATENT_ENTROPY - default 1536 if (!64BIT && (PARISC || XTENSA)) - default 1024 if (!64BIT && !PARISC) + default 2048 if PARISC + default 1536 if (!64BIT && XTENSA) + default 1024 if !64BIT default 2048 if 64BIT help Tell gcc to warn at build time for stack frames larger than this. From 169d1a4a2adb2c246396c56aa2f9eec3868546f1 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 19 Nov 2021 22:16:37 +0100 Subject: [PATCH 155/358] parisc: Provide an extru_safe() macro to extract unsigned bits The extru instruction leaves the most significant 32 bits of the target register in an undefined state on PA 2.0 systems. Provide a macro to safely use extru on 32- and 64-bit machines. Suggested-by: John David Anglin Signed-off-by: Helge Deller --- arch/parisc/include/asm/assembly.h | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 39e7985086f925..6d13ae236fcb07 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -147,6 +147,17 @@ extrd,u \r, 63-(\sa), 64-(\sa), \t .endm + /* Extract unsigned for 32- and 64-bit + * The extru instruction leaves the most significant 32 bits of the + * target register in an undefined state on PA 2.0 systems. */ + .macro extru_safe r, p, len, t +#ifdef CONFIG_64BIT + extrd,u \r, 32+(\p), \len, \t +#else + extru \r, \p, \len, \t +#endif + .endm + /* load 32-bit 'value' into 'reg' compensating for the ldil * sign-extension when running in wide mode. * WARNING!! neither 'value' nor 'reg' can be expressions From df2ffeda6370a77011902e7c9d7a1eb1cbffed4f Mon Sep 17 00:00:00 2001 From: John David Anglin Date: Fri, 19 Nov 2021 22:18:47 +0100 Subject: [PATCH 156/358] parisc: Fix extraction of hash lock bits in syscall.S The extru instruction leaves the most significant 32 bits of the target register in an undefined state on PA 2.0 systems. If any of these bits are nonzero, this will break the calculation of the lock pointer. Fix by using extrd,u instruction via extru_safe macro on 64-bit kernels. Signed-off-by: John David Anglin Signed-off-by: Helge Deller --- arch/parisc/kernel/syscall.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 4fb3b6a993bf6e..d2497b339d1392 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -566,7 +566,7 @@ lws_compare_and_swap: ldo R%lws_lock_start(%r20), %r28 /* Extract eight bits from r26 and hash lock (Bits 3-11) */ - extru %r26, 28, 8, %r20 + extru_safe %r26, 28, 8, %r20 /* Find lock to use, the hash is either one of 0 to 15, multiplied by 16 (keep it 16-byte aligned) @@ -751,7 +751,7 @@ cas2_lock_start: ldo R%lws_lock_start(%r20), %r28 /* Extract eight bits from r26 and hash lock (Bits 3-11) */ - extru %r26, 28, 8, %r20 + extru_safe %r26, 28, 8, %r20 /* Find lock to use, the hash is either one of 0 to 15, multiplied by 16 (keep it 16-byte aligned) From 3fbdc121bd051d9f1b3b2e232ad734c44b47d32c Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 19 Nov 2021 22:20:14 +0100 Subject: [PATCH 157/358] parisc: Convert PTE lookup to use extru_safe() macro Convert the PTE lookup functions to use the safer extru_safe macro. Signed-off-by: Helge Deller --- arch/parisc/kernel/entry.S | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 88c188a965d86f..6e9cdb26986282 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -366,17 +366,9 @@ */ .macro L2_ptep pmd,pte,index,va,fault #if CONFIG_PGTABLE_LEVELS == 3 - extru \va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index + extru_safe \va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index #else -# if defined(CONFIG_64BIT) - extrd,u \va,63-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index - #else - # if PAGE_SIZE > 4096 - extru \va,31-ASM_PGDIR_SHIFT,32-ASM_PGDIR_SHIFT,\index - # else - extru \va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index - # endif -# endif + extru_safe \va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index #endif dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */ #if CONFIG_PGTABLE_LEVELS < 3 @@ -386,7 +378,7 @@ bb,>=,n \pmd,_PxD_PRESENT_BIT,\fault dep %r0,31,PxD_FLAG_SHIFT,\pmd /* clear flags */ SHLREG \pmd,PxD_VALUE_SHIFT,\pmd - extru \va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index + extru_safe \va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */ shladd \index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */ .endm From 98400ad75e95860e9a10ec78b0b90ab66184a2ce Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 21 Nov 2021 11:10:55 +0100 Subject: [PATCH 158/358] Revert "parisc: Fix backtrace to always include init funtion names" This reverts commit 279917e27edc293eb645a25428c6ab3f3bca3f86. With the CONFIG_HARDENED_USERCOPY option enabled, this patch triggers kernel bugs at runtime: usercopy: Kernel memory overwrite attempt detected to kernel text (offset 2084839, size 6)! kernel BUG at mm/usercopy.c:99! Backtrace: IAOQ[0]: usercopy_abort+0xc4/0xe8 [<00000000406ed1c8>] __check_object_size+0x174/0x238 [<00000000407086d4>] copy_strings.isra.0+0x3e8/0x708 [<0000000040709a20>] do_execveat_common.isra.0+0x1bc/0x328 [<000000004070b760>] compat_sys_execve+0x7c/0xb8 [<0000000040303eb8>] syscall_exit+0x0/0x14 The problem is, that we have an init section of at least 2MB size which starts at _stext and is freed after bootup. If then later some kernel data is (temporarily) stored in this free memory, check_kernel_text_object() will trigger a bug since the data appears to be inside the kernel text (>=_stext) area: if (overlaps(ptr, len, _stext, _etext)) usercopy_abort("kernel text"); Signed-off-by: Helge Deller Cc: stable@kernel.org # 5.4+ --- arch/parisc/kernel/vmlinux.lds.S | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 3d208afd15bc6d..2769eb991f58d1 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -57,8 +57,6 @@ SECTIONS { . = KERNEL_BINARY_TEXT_START; - _stext = .; /* start of kernel text, includes init code & data */ - __init_begin = .; HEAD_TEXT_SECTION MLONGCALL_DISCARD(INIT_TEXT_SECTION(8)) @@ -82,6 +80,7 @@ SECTIONS /* freed after init ends here */ _text = .; /* Text and read-only data */ + _stext = .; MLONGCALL_KEEP(INIT_TEXT_SECTION(8)) .text ALIGN(PAGE_SIZE) : { TEXT_TEXT From e353f3e88720300c3d72f49a4bea54f42db1fa5e Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Fri, 19 Nov 2021 15:03:19 +0100 Subject: [PATCH 159/358] USB: serial: option: add Telit LE910S1 0x9200 composition Add the following Telit LE910S1 composition: 0x9200: tty Signed-off-by: Daniele Palmas Link: https://lore.kernel.org/r/20211119140319.10448-1-dnlplm@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index a484ff5e4ebf83..0902e79c8493f4 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1267,6 +1267,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x9010), /* Telit SBL FN980 flashing device */ .driver_info = NCTRL(0) | ZLP }, + { USB_DEVICE(TELIT_VENDOR_ID, 0x9200), /* Telit LE910S1 flashing device */ + .driver_info = NCTRL(0) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff), .driver_info = RSVD(1) }, From e95d8eaee21cd0d117d34125d4cdc97489c1ab82 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Fri, 19 Nov 2021 15:39:01 -0800 Subject: [PATCH 160/358] firmware: smccc: Fix check for ARCH_SOC_ID not implemented The ARCH_FEATURES function ID is a 32-bit SMC call, which returns a 32-bit result per the SMCCC spec. Current code is doing a 64-bit comparison against -1 (SMCCC_RET_NOT_SUPPORTED) to detect that the feature is unimplemented. That check doesn't work in a Hyper-V VM, where the upper 32-bits are zero as allowed by the spec. Cast the result as an 'int' so the comparison works. The change also makes the code consistent with other similar checks in this file. Fixes: 821b67fa4639 ("firmware: smccc: Add ARCH_SOC_ID support") Signed-off-by: Michael Kelley Reviewed-by: Sudeep Holla Signed-off-by: Arnd Bergmann --- drivers/firmware/smccc/soc_id.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/smccc/soc_id.c b/drivers/firmware/smccc/soc_id.c index 581aa5e9b0778b..dd7c3d5e8b0bba 100644 --- a/drivers/firmware/smccc/soc_id.c +++ b/drivers/firmware/smccc/soc_id.c @@ -50,7 +50,7 @@ static int __init smccc_soc_init(void) arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_SOC_ID, &res); - if (res.a0 == SMCCC_RET_NOT_SUPPORTED) { + if ((int)res.a0 == SMCCC_RET_NOT_SUPPORTED) { pr_info("ARCH_SOC_ID not implemented, skipping ....\n"); return 0; } From 3b00a07c2443745d62babfe08dbb2ad8e649526e Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Fri, 19 Nov 2021 03:03:49 +0100 Subject: [PATCH 161/358] net: dsa: qca8k: fix internal delay applied to the wrong PAD config With SGMII phy the internal delay is always applied to the PAD0 config. This is caused by the falling edge configuration that hardcode the reg to PAD0 (as the falling edge bits are present only in PAD0 reg) Move the delay configuration before the reg overwrite to correctly apply the delay. Fixes: cef08115846e ("net: dsa: qca8k: set internal delay also for sgmii") Signed-off-by: Ansuel Smith Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/qca8k.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index a429c9750add1b..d7bcecbc1c5300 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1433,6 +1433,12 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, qca8k_write(priv, QCA8K_REG_SGMII_CTRL, val); + /* From original code is reported port instability as SGMII also + * require delay set. Apply advised values here or take them from DT. + */ + if (state->interface == PHY_INTERFACE_MODE_SGMII) + qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); + /* For qca8327/qca8328/qca8334/qca8338 sgmii is unique and * falling edge is set writing in the PORT0 PAD reg */ @@ -1455,12 +1461,6 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE, val); - /* From original code is reported port instability as SGMII also - * require delay set. Apply advised values here or take them from DT. - */ - if (state->interface == PHY_INTERFACE_MODE_SGMII) - qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); - break; default: dev_err(ds->dev, "xMII mode %s not supported for port %d\n", From 65258b9d8cde45689bdc86ca39b50f01f983733b Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 19 Nov 2021 03:03:50 +0100 Subject: [PATCH 162/358] net: dsa: qca8k: fix MTU calculation qca8k has a global MTU, so its tracking the MTU per port to make sure that the largest MTU gets applied. Since it uses the frame size instead of MTU the driver MTU change function will then add the size of Ethernet header and checksum on top of MTU. The driver currently populates the per port MTU size as Ethernet frame length + checksum which equals 1518. The issue is that then MTU change function will go through all of the ports, find the largest MTU and apply the Ethernet header + checksum on top of it again, so for a desired MTU of 1500 you will end up with 1536. This is obviously incorrect, so to correct it populate the per port struct MTU with just the MTU and not include the Ethernet header + checksum size as those will be added by the MTU change function. Fixes: f58d2598cf70 ("net: dsa: qca8k: implement the port MTU callbacks") Signed-off-by: Robert Marko Signed-off-by: Ansuel Smith Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/qca8k.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index d7bcecbc1c5300..147ca39531a3bb 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1256,8 +1256,12 @@ qca8k_setup(struct dsa_switch *ds) /* Set initial MTU for every port. * We have only have a general MTU setting. So track * every port and set the max across all port. + * Set per port MTU to 1500 as the MTU change function + * will add the overhead and if its set to 1518 then it + * will apply the overhead again and we will end up with + * MTU of 1536 instead of 1518 */ - priv->port_mtu[i] = ETH_FRAME_LEN + ETH_FCS_LEN; + priv->port_mtu[i] = ETH_DATA_LEN; } /* Special GLOBAL_FC_THRESH value are needed for ar8327 switch */ From bdf1565fe03d29777d24e239163d0d53e4af9ce0 Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Fri, 19 Nov 2021 14:24:56 +0800 Subject: [PATCH 163/358] selftests/tc-testing: match any qdisc type We should not always presume all kernels use pfifo_fast as the default qdisc. For example, a fq_codel qdisk could have below output: qdisc fq_codel 0: parent 1:4 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64 Reported-by: kernel test robot Suggested-by: Peilin Ye Signed-off-by: Li Zhijian Signed-off-by: David S. Miller --- .../selftests/tc-testing/tc-tests/qdiscs/mq.json | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json index 88a20c781e4982..c6046096d9db8a 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json @@ -15,7 +15,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -37,7 +37,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-9,a-f][0-9,a-f]{0,2} bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-9,a-f][0-9,a-f]{0,2}", "matchCount": "256", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -60,7 +60,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -82,7 +82,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -106,7 +106,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -128,7 +128,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" From ac2944abe4d7732f29a79f063c9cae7df2a3e3cc Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Fri, 19 Nov 2021 14:24:57 +0800 Subject: [PATCH 164/358] selftests/tc-testings: Be compatible with newer tc output old tc(iproute2-5.9.0) output: action order 1: bpf action.o:[action-ok] id 60 tag bcf7977d3b93787c jited default-action pipe newer tc(iproute2-5.14.0) output: action order 1: bpf action.o:[action-ok] id 64 name tag bcf7977d3b93787c jited default-action pipe It can fix below errors: # ok 260 f84a - Add cBPF action with invalid bytecode # not ok 261 e939 - Add eBPF action with valid object-file # Could not match regex pattern. Verify command output: # total acts 0 # # action order 1: bpf action.o:[action-ok] id 42 name tag bcf7977d3b93787c jited default-action pipe # index 667 ref 1 bind 0 Signed-off-by: Li Zhijian Signed-off-by: David S. Miller --- tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 503982b8f295b9..91832400ddbdbb 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -68,7 +68,7 @@ "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667", "expExitCode": "0", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", + "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", "matchCount": "1", "teardown": [ "$TC action flush action bpf" From 19d36c5f294879949c9d6f57cb61d39cc4c48553 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Nov 2021 17:37:58 -0800 Subject: [PATCH 165/358] ipv6: fix typos in __ip6_finish_output() We deal with IPv6 packets, so we need to use IP6CB(skb)->flags and IP6SKB_REROUTED, instead of IPCB(skb)->flags and IPSKB_REROUTED Found by code inspection, please double check that fixing this bug does not surface other bugs. Fixes: 09ee9dba9611 ("ipv6: Reinject IPv6 packets if IPsec policy matches after SNAT") Signed-off-by: Eric Dumazet Cc: Tobias Brunner Cc: Steffen Klassert Cc: David Ahern Reviewed-by: David Ahern Tested-by: Tobias Brunner Acked-by: Tobias Brunner Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2f044a49afa8cf..ff4e83e2a50683 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -174,7 +174,7 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { - IPCB(skb)->flags |= IPSKB_REROUTED; + IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif From 3bd6b2a838ba6a3b86d41b077f570b1b61174def Mon Sep 17 00:00:00 2001 From: Diana Wang Date: Fri, 19 Nov 2021 14:38:03 +0100 Subject: [PATCH 166/358] nfp: checking parameter process for rx-usecs/tx-usecs is invalid Use nn->tlv_caps.me_freq_mhz instead of nn->me_freq_mhz to check whether rx-usecs/tx-usecs is valid. This is because nn->tlv_caps.me_freq_mhz represents the clock_freq (MHz) of the flow processing cores (FPC) on the NIC. While nn->me_freq_mhz is not be set. Fixes: ce991ab6662a ("nfp: read ME frequency from vNIC ctrl memory") Signed-off-by: Diana Wang Signed-off-by: Simon Horman Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 3 --- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 2 +- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index df203738511bfd..0b1865e9f0b596 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -565,7 +565,6 @@ struct nfp_net_dp { * @exn_name: Name for Exception interrupt * @shared_handler: Handler for shared interrupts * @shared_name: Name for shared interrupt - * @me_freq_mhz: ME clock_freq (MHz) * @reconfig_lock: Protects @reconfig_posted, @reconfig_timer_active, * @reconfig_sync_present and HW reconfiguration request * regs/machinery from async requests (sync must take @@ -650,8 +649,6 @@ struct nfp_net { irq_handler_t shared_handler; char shared_name[IFNAMSIZ + 8]; - u32 me_freq_mhz; - bool link_up; spinlock_t link_status_lock; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 1de076f557405e..cf788293399349 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1344,7 +1344,7 @@ static int nfp_net_set_coalesce(struct net_device *netdev, * ME timestamp ticks. There are 16 ME clock cycles for each timestamp * count. */ - factor = nn->me_freq_mhz / 16; + factor = nn->tlv_caps.me_freq_mhz / 16; /* Each pair of (usecs, max_frames) fields specifies that interrupts * should be coalesced until From 18fe42bdd635d290d230ff279e5e86072f1e7e9f Mon Sep 17 00:00:00 2001 From: Sugaya Taichi Date: Mon, 15 Nov 2021 18:30:56 +0900 Subject: [PATCH 167/358] MAINTAINERS: Add entry to MAINTAINERS for Milbeaut Add entry to MAINTAINERS for Milbeaut that supported minimal drivers. Signed-off-by: Sugaya Taichi Link: https://lore.kernel.org/r/1636968656-14033-5-git-send-email-sugaya.taichi@socionext.com' Signed-off-by: Arnd Bergmann --- MAINTAINERS | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 5250298d281708..a241e6e3b7d200 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2263,6 +2263,15 @@ L: linux-iio@vger.kernel.org S: Maintained F: drivers/counter/microchip-tcb-capture.c +ARM/MILBEAUT ARCHITECTURE +M: Taichi Sugaya +M: Takao Orito +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: arch/arm/boot/dts/milbeaut* +F: arch/arm/mach-milbeaut/ +N: milbeaut + ARM/MIOA701 MACHINE SUPPORT M: Robert Jarzmik L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) From a6da2bbb0005e6b4909472962c9d0af29e75dd06 Mon Sep 17 00:00:00 2001 From: Holger Assmann Date: Sun, 21 Nov 2021 19:57:04 +0200 Subject: [PATCH 168/358] net: stmmac: retain PTP clock time during SIOCSHWTSTAMP ioctls Currently, when user space emits SIOCSHWTSTAMP ioctl calls such as enabling/disabling timestamping or changing filter settings, the driver reads the current CLOCK_REALTIME value and programming this into the NIC's hardware clock. This might be necessary during system initialization, but at runtime, when the PTP clock has already been synchronized to a grandmaster, a reset of the timestamp settings might result in a clock jump. Furthermore, if the clock is also controlled by phc2sys in automatic mode (where the UTC offset is queried from ptp4l), that UTC-to-TAI offset (currently 37 seconds in 2021) would be temporarily reset to 0, and it would take a long time for phc2sys to readjust so that CLOCK_REALTIME and the PHC are apart by 37 seconds again. To address the issue, we introduce a new function called stmmac_init_tstamp_counter(), which gets called during ndo_open(). It contains the code snippet moved from stmmac_hwtstamp_set() that manages the time synchronization. Besides, the sub second increment configuration is also moved here since the related values are hardware dependent and runtime invariant. Furthermore, the hardware clock must be kept running even when no time stamping mode is selected in order to retain the synchronized time base. That way, timestamping can be enabled again at any time only with the need to compensate the clock's natural drifting. As a side effect, this patch fixes the issue that ptp_clock_info::enable can be called before SIOCSHWTSTAMP and the driver (which looks at priv->systime_flags) was not prepared to handle that ordering. Fixes: 92ba6888510c ("stmmac: add the support for PTP hw clock driver") Reported-by: Michael Olbrich Signed-off-by: Ahmad Fatoum Signed-off-by: Holger Assmann Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 1 + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 125 +++++++++++------- .../ethernet/stmicro/stmmac/stmmac_platform.c | 2 +- 3 files changed, 81 insertions(+), 47 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 43eead726886a0..5f129733aabd2e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -314,6 +314,7 @@ int stmmac_mdio_reset(struct mii_bus *mii); int stmmac_xpcs_setup(struct mii_bus *mii); void stmmac_set_ethtool_ops(struct net_device *netdev); +int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags); void stmmac_ptp_register(struct stmmac_priv *priv); void stmmac_ptp_unregister(struct stmmac_priv *priv); int stmmac_open(struct net_device *dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 19bc86f2092fc3..f12097c8a48506 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -50,6 +50,13 @@ #include "dwxgmac2.h" #include "hwif.h" +/* As long as the interface is active, we keep the timestamping counter enabled + * with fine resolution and binary rollover. This avoid non-monotonic behavior + * (clock jumps) when changing timestamping settings at runtime. + */ +#define STMMAC_HWTS_ACTIVE (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | \ + PTP_TCR_TSCTRLSSR) + #define STMMAC_ALIGN(x) ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) @@ -613,8 +620,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) { struct stmmac_priv *priv = netdev_priv(dev); struct hwtstamp_config config; - struct timespec64 now; - u64 temp = 0; u32 ptp_v2 = 0; u32 tstamp_all = 0; u32 ptp_over_ipv4_udp = 0; @@ -623,11 +628,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) u32 snap_type_sel = 0; u32 ts_master_en = 0; u32 ts_event_en = 0; - u32 sec_inc = 0; - u32 value = 0; - bool xmac; - - xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; if (!(priv->dma_cap.time_stamp || priv->adv_ts)) { netdev_alert(priv->dev, "No support for HW time stamping\n"); @@ -789,42 +789,17 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) priv->hwts_rx_en = ((config.rx_filter == HWTSTAMP_FILTER_NONE) ? 0 : 1); priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON; - if (!priv->hwts_tx_en && !priv->hwts_rx_en) - stmmac_config_hw_tstamping(priv, priv->ptpaddr, 0); - else { - value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR | - tstamp_all | ptp_v2 | ptp_over_ethernet | - ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en | - ts_master_en | snap_type_sel); - stmmac_config_hw_tstamping(priv, priv->ptpaddr, value); - - /* program Sub Second Increment reg */ - stmmac_config_sub_second_increment(priv, - priv->ptpaddr, priv->plat->clk_ptp_rate, - xmac, &sec_inc); - temp = div_u64(1000000000ULL, sec_inc); - - /* Store sub second increment and flags for later use */ - priv->sub_second_inc = sec_inc; - priv->systime_flags = value; - - /* calculate default added value: - * formula is : - * addend = (2^32)/freq_div_ratio; - * where, freq_div_ratio = 1e9ns/sec_inc - */ - temp = (u64)(temp << 32); - priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); - stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); - - /* initialize system time */ - ktime_get_real_ts64(&now); + priv->systime_flags = STMMAC_HWTS_ACTIVE; - /* lower 32 bits of tv_sec are safe until y2106 */ - stmmac_init_systime(priv, priv->ptpaddr, - (u32)now.tv_sec, now.tv_nsec); + if (priv->hwts_tx_en || priv->hwts_rx_en) { + priv->systime_flags |= tstamp_all | ptp_v2 | + ptp_over_ethernet | ptp_over_ipv6_udp | + ptp_over_ipv4_udp | ts_event_en | + ts_master_en | snap_type_sel; } + stmmac_config_hw_tstamping(priv, priv->ptpaddr, priv->systime_flags); + memcpy(&priv->tstamp_config, &config, sizeof(config)); return copy_to_user(ifr->ifr_data, &config, @@ -852,6 +827,66 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) sizeof(*config)) ? -EFAULT : 0; } +/** + * stmmac_init_tstamp_counter - init hardware timestamping counter + * @priv: driver private structure + * @systime_flags: timestamping flags + * Description: + * Initialize hardware counter for packet timestamping. + * This is valid as long as the interface is open and not suspended. + * Will be rerun after resuming from suspend, case in which the timestamping + * flags updated by stmmac_hwtstamp_set() also need to be restored. + */ +int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags) +{ + bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + struct timespec64 now; + u32 sec_inc = 0; + u64 temp = 0; + int ret; + + if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) + return -EOPNOTSUPP; + + ret = clk_prepare_enable(priv->plat->clk_ptp_ref); + if (ret < 0) { + netdev_warn(priv->dev, + "failed to enable PTP reference clock: %pe\n", + ERR_PTR(ret)); + return ret; + } + + stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags); + priv->systime_flags = systime_flags; + + /* program Sub Second Increment reg */ + stmmac_config_sub_second_increment(priv, priv->ptpaddr, + priv->plat->clk_ptp_rate, + xmac, &sec_inc); + temp = div_u64(1000000000ULL, sec_inc); + + /* Store sub second increment for later use */ + priv->sub_second_inc = sec_inc; + + /* calculate default added value: + * formula is : + * addend = (2^32)/freq_div_ratio; + * where, freq_div_ratio = 1e9ns/sec_inc + */ + temp = (u64)(temp << 32); + priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); + stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); + + /* initialize system time */ + ktime_get_real_ts64(&now); + + /* lower 32 bits of tv_sec are safe until y2106 */ + stmmac_init_systime(priv, priv->ptpaddr, (u32)now.tv_sec, now.tv_nsec); + + return 0; +} +EXPORT_SYMBOL_GPL(stmmac_init_tstamp_counter); + /** * stmmac_init_ptp - init PTP * @priv: driver private structure @@ -862,9 +897,11 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) static int stmmac_init_ptp(struct stmmac_priv *priv) { bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + int ret; - if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) - return -EOPNOTSUPP; + ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE); + if (ret) + return ret; priv->adv_ts = 0; /* Check if adv_ts can be enabled for dwmac 4.x / xgmac core */ @@ -3272,10 +3309,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) stmmac_mmc_setup(priv); if (init_ptp) { - ret = clk_prepare_enable(priv->plat->clk_ptp_ref); - if (ret < 0) - netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret); - ret = stmmac_init_ptp(priv); if (ret == -EOPNOTSUPP) netdev_warn(priv->dev, "PTP not supported by HW\n"); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 232ac98943cd08..5d29f336315b79 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -816,7 +816,7 @@ static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev) if (ret) return ret; - clk_prepare_enable(priv->plat->clk_ptp_ref); + stmmac_init_tstamp_counter(priv, priv->systime_flags); } return 0; From f93fd0ca5e7de743ce687951266950fb37877e34 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Sun, 21 Nov 2021 21:06:42 +0100 Subject: [PATCH 169/358] net: ax88796c: do not receive data in pointer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Function axspi_read_status calls: ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)&status, 3); status is a pointer to a struct spi_status, which is 3-byte wide: struct spi_status { u16 isr; u8 status; }; But &status is the pointer to this pointer, and spi_write_then_read does not dereference this parameter: int spi_write_then_read(struct spi_device *spi, const void *txbuf, unsigned n_tx, void *rxbuf, unsigned n_rx) Therefore axspi_read_status currently receive a SPI response in the pointer status, which overwrites 24 bits of the pointer. Thankfully, on Little-Endian systems, the pointer is only used in le16_to_cpus(&status->isr); ... which is a no-operation. So there, the overwritten pointer is not dereferenced. Nevertheless on Big-Endian systems, this can lead to dereferencing pointers after their 24 most significant bits were overwritten. And in all systems this leads to possible use of uninitialized value in functions calling spi_write_then_read which expect status to be initialized when the function returns. Moreover function axspi_read_status (and macro AX_READ_STATUS) do not seem to be used anywhere. So currently this seems to be dead code. Fix the issue anyway so that future code works properly when using function axspi_read_status. Fixes: a97c69ba4f30 ("net: ax88796c: ASIX AX88796C SPI Ethernet Adapter Driver") Signed-off-by: Nicolas Iooss Acked-by: Łukasz Stelmach Signed-off-by: David S. Miller --- drivers/net/ethernet/asix/ax88796c_spi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/asix/ax88796c_spi.c b/drivers/net/ethernet/asix/ax88796c_spi.c index 94df4f96d2be21..0710e716d6825f 100644 --- a/drivers/net/ethernet/asix/ax88796c_spi.c +++ b/drivers/net/ethernet/asix/ax88796c_spi.c @@ -34,7 +34,7 @@ int axspi_read_status(struct axspi_data *ax_spi, struct spi_status *status) /* OP */ ax_spi->cmd_buf[0] = AX_SPICMD_READ_STATUS; - ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)&status, 3); + ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)status, 3); if (ret) dev_err(&ax_spi->spi->dev, "%s() failed: ret = %d\n", __func__, ret); else From f7a36b03a7320d1a3ba52f9305571eddad325a05 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 22 Nov 2021 04:32:01 -0500 Subject: [PATCH 170/358] vsock/virtio: suppress used length validation It turns out that vhost vsock violates the virtio spec by supplying the out buffer length in the used length (should just be the in length). As a result, attempts to validate the used length fail with: vmw_vsock_virtio_transport virtio1: tx: used len 44 is larger than in buflen 0 Since vsock driver does not use the length fox tx and validates the length before use for rx, it is safe to suppress the validation in virtio core for this driver. Reported-by: Halil Pasic Fixes: 939779f5152d ("virtio_ring: validate used buffer length") Cc: "Jason Wang" Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 4f7c99dfd16cfe..3f82b2f1e6ddcd 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -731,6 +731,7 @@ static unsigned int features[] = { static struct virtio_driver virtio_vsock_driver = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), + .suppress_used_validation = true, .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, From 7a61432dc81375be06b02f0061247d3efbdfce3a Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Mon, 22 Nov 2021 20:32:53 +0800 Subject: [PATCH 171/358] net/smc: Avoid warning of possible recursive locking Possible recursive locking is detected by lockdep when SMC falls back to TCP. The corresponding warnings are as follows: ============================================ WARNING: possible recursive locking detected 5.16.0-rc1+ #18 Tainted: G E -------------------------------------------- wrk/1391 is trying to acquire lock: ffff975246c8e7d8 (&ei->socket.wq.wait){..-.}-{3:3}, at: smc_switch_to_fallback+0x109/0x250 [smc] but task is already holding lock: ffff975246c8f918 (&ei->socket.wq.wait){..-.}-{3:3}, at: smc_switch_to_fallback+0xfe/0x250 [smc] other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&ei->socket.wq.wait); lock(&ei->socket.wq.wait); *** DEADLOCK *** May be due to missing lock nesting notation 2 locks held by wrk/1391: #0: ffff975246040130 (sk_lock-AF_SMC){+.+.}-{0:0}, at: smc_connect+0x43/0x150 [smc] #1: ffff975246c8f918 (&ei->socket.wq.wait){..-.}-{3:3}, at: smc_switch_to_fallback+0xfe/0x250 [smc] stack backtrace: Call Trace: dump_stack_lvl+0x56/0x7b __lock_acquire+0x951/0x11f0 lock_acquire+0x27a/0x320 ? smc_switch_to_fallback+0x109/0x250 [smc] ? smc_switch_to_fallback+0xfe/0x250 [smc] _raw_spin_lock_irq+0x3b/0x80 ? smc_switch_to_fallback+0x109/0x250 [smc] smc_switch_to_fallback+0x109/0x250 [smc] smc_connect_fallback+0xe/0x30 [smc] __smc_connect+0xcf/0x1090 [smc] ? mark_held_locks+0x61/0x80 ? __local_bh_enable_ip+0x77/0xe0 ? lockdep_hardirqs_on+0xbf/0x130 ? smc_connect+0x12a/0x150 [smc] smc_connect+0x12a/0x150 [smc] __sys_connect+0x8a/0xc0 ? syscall_enter_from_user_mode+0x20/0x70 __x64_sys_connect+0x16/0x20 do_syscall_64+0x34/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae The nested locking in smc_switch_to_fallback() is considered to possibly cause a deadlock because smc_wait->lock and clc_wait->lock are the same type of lock. But actually it is safe so far since there is no other place trying to obtain smc_wait->lock when clc_wait->lock is held. So the patch replaces spin_lock() with spin_lock_nested() to avoid false report by lockdep. Link: https://lkml.org/lkml/2021/11/19/962 Fixes: 2153bd1e3d3d ("Transfer remaining wait queue entries during fallback") Reported-by: syzbot+e979d3597f48262cb4ee@syzkaller.appspotmail.com Signed-off-by: Wen Gu Acked-by: Tony Lu Signed-off-by: David S. Miller --- net/smc/af_smc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b61c802e3bf324..2692cba5a7b682 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -585,7 +585,7 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) * to clcsocket->wq during the fallback. */ spin_lock_irqsave(&smc_wait->lock, flags); - spin_lock(&clc_wait->lock); + spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING); list_splice_init(&smc_wait->head, &clc_wait->head); spin_unlock(&clc_wait->lock); spin_unlock_irqrestore(&smc_wait->lock, flags); From a68229ca634066975fff6d4780155bd2eb14a82a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Nov 2021 16:02:49 +0100 Subject: [PATCH 172/358] nixge: fix mac address error handling again The change to eth_hw_addr_set() caused gcc to correctly spot a bug that was introduced in an earlier incorrect fix: In file included from include/linux/etherdevice.h:21, from drivers/net/ethernet/ni/nixge.c:7: In function '__dev_addr_set', inlined from 'eth_hw_addr_set' at include/linux/etherdevice.h:319:2, inlined from 'nixge_probe' at drivers/net/ethernet/ni/nixge.c:1286:3: include/linux/netdevice.h:4648:9: error: 'memcpy' reading 6 bytes from a region of size 0 [-Werror=stringop-overread] 4648 | memcpy(dev->dev_addr, addr, len); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ As nixge_get_nvmem_address() can return either NULL or an error pointer, the NULL check is wrong, and we can end up reading from ERR_PTR(-EOPNOTSUPP), which gcc knows to contain zero readable bytes. Make the function always return an error pointer again but fix the check to match that. Fixes: f3956ebb3bf0 ("ethernet: use eth_hw_addr_set() instead of ether_addr_copy()") Fixes: abcd3d6fc640 ("net: nixge: Fix error path for obtaining mac address") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/ni/nixge.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index cfeb7620ae20b6..07a00dd9cfe0a6 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1209,7 +1209,7 @@ static void *nixge_get_nvmem_address(struct device *dev) cell = nvmem_cell_get(dev, "address"); if (IS_ERR(cell)) - return NULL; + return cell; mac = nvmem_cell_read(cell, &cell_size); nvmem_cell_put(cell); @@ -1282,7 +1282,7 @@ static int nixge_probe(struct platform_device *pdev) ndev->max_mtu = NIXGE_JUMBO_MTU; mac_addr = nixge_get_nvmem_address(&pdev->dev); - if (mac_addr && is_valid_ether_addr(mac_addr)) { + if (!IS_ERR(mac_addr) && is_valid_ether_addr(mac_addr)) { eth_hw_addr_set(ndev, mac_addr); kfree(mac_addr); } else { From 4177d5b017a71433d4760889b88f7a29e11fad10 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 22 Nov 2021 16:01:51 +0100 Subject: [PATCH 173/358] net, neigh: Fix crash in v6 module initialization error path When IPv6 module gets initialized, but it's hitting an error in inet6_init() where it then needs to undo all the prior initialization work, it also might do a call to ndisc_cleanup() which then calls neigh_table_clear(). In there is a missing timer cancellation of the table's managed_work item. The kernel test robot explicitly triggered this error path and caused a UAF crash similar to the below: [...] [ 28.833183][ C0] BUG: unable to handle page fault for address: f7a43288 [ 28.833973][ C0] #PF: supervisor write access in kernel mode [ 28.834660][ C0] #PF: error_code(0x0002) - not-present page [ 28.835319][ C0] *pde = 06b2c067 *pte = 00000000 [ 28.835853][ C0] Oops: 0002 [#1] PREEMPT [ 28.836367][ C0] CPU: 0 PID: 303 Comm: sed Not tainted 5.16.0-rc1-00233-g83ff5faa0d3b #7 [ 28.837293][ C0] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1 04/01/2014 [ 28.838338][ C0] EIP: __run_timers.constprop.0+0x82/0x440 [...] [ 28.845607][ C0] Call Trace: [ 28.845942][ C0] [ 28.846333][ C0] ? check_preemption_disabled.isra.0+0x2a/0x80 [ 28.846975][ C0] ? __this_cpu_preempt_check+0x8/0xa [ 28.847570][ C0] run_timer_softirq+0xd/0x40 [ 28.848050][ C0] __do_softirq+0xf5/0x576 [ 28.848547][ C0] ? __softirqentry_text_start+0x10/0x10 [ 28.849127][ C0] do_softirq_own_stack+0x2b/0x40 [ 28.849749][ C0] [ 28.850087][ C0] irq_exit_rcu+0x7d/0xc0 [ 28.850587][ C0] common_interrupt+0x2a/0x40 [ 28.851068][ C0] asm_common_interrupt+0x119/0x120 [...] Note that IPv6 module cannot be unloaded as per 8ce440610357 ("ipv6: do not allow ipv6 module to be removed") hence this can only be seen during module initialization error. Tested with kernel test robot's reproducer. Fixes: 7482e3841d52 ("net, neigh: Add NTF_MANAGED flag for managed neighbor entries") Reported-by: kernel test robot Signed-off-by: Daniel Borkmann Cc: Li Zhijian Signed-off-by: David S. Miller --- net/core/neighbour.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 47931c8be04b80..72ba027c34cfea 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1779,6 +1779,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) { neigh_tables[index] = NULL; /* It is not clean... Fix it to unload IPv6 module safely */ + cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); From 8837cbbf854246f5f4d565f21e6baa945d37aded Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 22 Nov 2021 17:15:12 +0200 Subject: [PATCH 174/358] net: ipv6: add fib6_nh_release_dsts stub We need a way to release a fib6_nh's per-cpu dsts when replacing nexthops otherwise we can end up with stale per-cpu dsts which hold net device references, so add a new IPv6 stub called fib6_nh_release_dsts. It must be used after an RCU grace period, so no new dsts can be created through a group's nexthop entry. Similar to fib6_nh_release it shouldn't be used if fib6_nh_init has failed so it doesn't need a dummy stub when IPv6 is not enabled. Fixes: 7bf4796dd099 ("nexthops: add support for replace") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 + include/net/ipv6_stubs.h | 1 + net/ipv6/af_inet6.c | 1 + net/ipv6/route.c | 19 +++++++++++++++++++ 4 files changed, 22 insertions(+) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index c412dde4d67dca..83b8070d1cc93a 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -485,6 +485,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); +void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index afbce90c44808a..45e0339be6fa4a 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -47,6 +47,7 @@ struct ipv6_stub { struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void (*fib6_nh_release)(struct fib6_nh *fib6_nh); + void (*fib6_nh_release_dsts)(struct fib6_nh *fib6_nh); void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt); int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify); void (*fib6_rt_update)(struct net *net, struct fib6_info *rt, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0c4da163535ad9..dab4a047590b73 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1026,6 +1026,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .ip6_mtu_from_fib6 = ip6_mtu_from_fib6, .fib6_nh_init = fib6_nh_init, .fib6_nh_release = fib6_nh_release, + .fib6_nh_release_dsts = fib6_nh_release_dsts, .fib6_update_sernum = fib6_update_sernum_stub, .fib6_rt_update = fib6_rt_update, .ip6_del_rt = ip6_del_rt, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3ae25b8ffbd6fb..42d60c76d30a03 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3680,6 +3680,25 @@ void fib6_nh_release(struct fib6_nh *fib6_nh) fib_nh_common_release(&fib6_nh->nh_common); } +void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) +{ + int cpu; + + if (!fib6_nh->rt6i_pcpu) + return; + + for_each_possible_cpu(cpu) { + struct rt6_info *pcpu_rt, **ppcpu_rt; + + ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); + pcpu_rt = xchg(ppcpu_rt, NULL); + if (pcpu_rt) { + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); + } + } +} + static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) From 1005f19b9357b81aa64e1decd08d6e332caaa284 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 22 Nov 2021 17:15:13 +0200 Subject: [PATCH 175/358] net: nexthop: release IPv6 per-cpu dsts when replacing a nexthop group When replacing a nexthop group, we must release the IPv6 per-cpu dsts of the removed nexthop entries after an RCU grace period because they contain references to the nexthop's net device and to the fib6 info. With specific series of events[1] we can reach net device refcount imbalance which is unrecoverable. IPv4 is not affected because dsts don't take a refcount on the route. [1] $ ip nexthop list id 200 via 2002:db8::2 dev bridge.10 scope link onlink id 201 via 2002:db8::3 dev bridge scope link onlink id 203 group 201/200 $ ip -6 route 2001:db8::10 nhid 203 metric 1024 pref medium nexthop via 2002:db8::3 dev bridge weight 1 onlink nexthop via 2002:db8::2 dev bridge.10 weight 1 onlink Create rt6_info through one of the multipath legs, e.g.: $ taskset -a -c 1 ./pkt_inj 24 bridge.10 2001:db8::10 (pkt_inj is just a custom packet generator, nothing special) Then remove that leg from the group by replace (let's assume it is id 200 in this case): $ ip nexthop replace id 203 group 201 Now remove the IPv6 route: $ ip -6 route del 2001:db8::10/128 The route won't be really deleted due to the stale rt6_info holding 1 refcnt in nexthop id 200. At this point we have the following reference count dependency: (deleted) IPv6 route holds 1 reference over nhid 203 nh 203 holds 1 ref over id 201 nh 200 holds 1 ref over the net device and the route due to the stale rt6_info Now to create circular dependency between nh 200 and the IPv6 route, and also to get a reference over nh 200, restore nhid 200 in the group: $ ip nexthop replace id 203 group 201/200 And now we have a permanent circular dependncy because nhid 203 holds a reference over nh 200 and 201, but the route holds a ref over nh 203 and is deleted. To trigger the bug just delete the group (nhid 203): $ ip nexthop del id 203 It won't really be deleted due to the IPv6 route dependency, and now we have 2 unlinked and deleted objects that reference each other: the group and the IPv6 route. Since the group drops the reference it holds over its entries at free time (i.e. its own refcount needs to drop to 0) that will never happen and we get a permanent ref on them, since one of the entries holds a reference over the IPv6 route it will also never be released. At this point the dependencies are: (deleted, only unlinked) IPv6 route holds reference over group nh 203 (deleted, only unlinked) group nh 203 holds reference over nh 201 and 200 nh 200 holds 1 ref over the net device and the route due to the stale rt6_info This is the last point where it can be fixed by running traffic through nh 200, and specifically through the same CPU so the rt6_info (dst) will get released due to the IPv6 genid, that in turn will free the IPv6 route, which in turn will free the ref count over the group nh 203. If nh 200 is deleted at this point, it will never be released due to the ref from the unlinked group 203, it will only be unlinked: $ ip nexthop del id 200 $ ip nexthop $ Now we can never release that stale rt6_info, we have IPv6 route with ref over group nh 203, group nh 203 with ref over nh 200 and 201, nh 200 with rt6_info (dst) with ref over the net device and the IPv6 route. All of these objects are only unlinked, and cannot be released, thus they can't release their ref counts. Message from syslogd@dev at Nov 19 14:04:10 ... kernel:[73501.828730] unregister_netdevice: waiting for bridge.10 to become free. Usage count = 3 Message from syslogd@dev at Nov 19 14:04:20 ... kernel:[73512.068811] unregister_netdevice: waiting for bridge.10 to become free. Usage count = 3 Fixes: 7bf4796dd099 ("nexthops: add support for replace") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 9e8100728d464d..a69a9e76f99fec 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1899,15 +1899,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, /* if any FIB entries reference this nexthop, any dst entries * need to be regenerated */ -static void nh_rt_cache_flush(struct net *net, struct nexthop *nh) +static void nh_rt_cache_flush(struct net *net, struct nexthop *nh, + struct nexthop *replaced_nh) { struct fib6_info *f6i; + struct nh_group *nhg; + int i; if (!list_empty(&nh->fi_list)) rt_cache_flush(net); list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_update_sernum(net, f6i); + + /* if an IPv6 group was replaced, we have to release all old + * dsts to make sure all refcounts are released + */ + if (!replaced_nh->is_group) + return; + + /* new dsts must use only the new nexthop group */ + synchronize_net(); + + nhg = rtnl_dereference(replaced_nh->nh_grp); + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info); + + if (nhi->family == AF_INET6) + ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh); + } } static int replace_nexthop_grp(struct net *net, struct nexthop *old, @@ -2247,7 +2268,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old, err = replace_nexthop_single(net, old, new, extack); if (!err) { - nh_rt_cache_flush(net, old); + nh_rt_cache_flush(net, old, new); __remove_nexthop(net, new, NULL); nexthop_put(new); From 02ebe49ab06111a887202959e4d58a3cf252b5ee Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 22 Nov 2021 17:15:14 +0200 Subject: [PATCH 176/358] selftests: net: fib_nexthops: add test for group refcount imbalance bug The new selftest runs a sequence which causes circular refcount dependency between deleted objects which cannot be released and results in a netdevice refcount imbalance. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- tools/testing/selftests/net/fib_nexthops.sh | 63 +++++++++++++++++++++ 1 file changed, 63 insertions(+) diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index b5a69ad191b078..d444ee6aa3cb0f 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -629,6 +629,66 @@ ipv6_fcnal() log_test $? 0 "Nexthops removed on admin down" } +ipv6_grp_refs() +{ + if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test; need mausezahn tool" + return + fi + + run_cmd "$IP link set dev veth1 up" + run_cmd "$IP link add veth1.10 link veth1 up type vlan id 10" + run_cmd "$IP link add veth1.20 link veth1 up type vlan id 20" + run_cmd "$IP -6 addr add 2001:db8:91::1/64 dev veth1.10" + run_cmd "$IP -6 addr add 2001:db8:92::1/64 dev veth1.20" + run_cmd "$IP -6 neigh add 2001:db8:91::2 lladdr 00:11:22:33:44:55 dev veth1.10" + run_cmd "$IP -6 neigh add 2001:db8:92::2 lladdr 00:11:22:33:44:55 dev veth1.20" + run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1.10" + run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth1.20" + run_cmd "$IP nexthop add id 102 group 100" + run_cmd "$IP route add 2001:db8:101::1/128 nhid 102" + + # create per-cpu dsts through nh 100 + run_cmd "ip netns exec me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1" + + # remove nh 100 from the group to delete the route potentially leaving + # a stale per-cpu dst which holds a reference to the nexthop's net + # device and to the IPv6 route + run_cmd "$IP nexthop replace id 102 group 101" + run_cmd "$IP route del 2001:db8:101::1/128" + + # add both nexthops to the group so a reference is taken on them + run_cmd "$IP nexthop replace id 102 group 100/101" + + # if the bug described in commit "net: nexthop: release IPv6 per-cpu + # dsts when replacing a nexthop group" exists at this point we have + # an unlinked IPv6 route (but not freed due to stale dst) with a + # reference over the group so we delete the group which will again + # only unlink it due to the route reference + run_cmd "$IP nexthop del id 102" + + # delete the nexthop with stale dst, since we have an unlinked + # group with a ref to it and an unlinked IPv6 route with ref to the + # group, the nh will only be unlinked and not freed so the stale dst + # remains forever and we get a net device refcount imbalance + run_cmd "$IP nexthop del id 100" + + # if a reference was lost this command will hang because the net device + # cannot be removed + timeout -s KILL 5 ip netns exec me ip link del veth1.10 >/dev/null 2>&1 + + # we can't cleanup if the command is hung trying to delete the netdev + if [ $? -eq 137 ]; then + return 1 + fi + + # cleanup + run_cmd "$IP link del veth1.20" + run_cmd "$IP nexthop flush" + + return 0 +} + ipv6_grp_fcnal() { local rc @@ -734,6 +794,9 @@ ipv6_grp_fcnal() run_cmd "$IP nexthop add id 108 group 31/24" log_test $? 2 "Nexthop group can not have a blackhole and another nexthop" + + ipv6_grp_refs + log_test $? 0 "Nexthop group replace refcounts" } ipv6_res_grp_fcnal() From 792b2086584f25d84081a526beee80d103c2a913 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Tue, 26 Oct 2021 18:47:18 +0200 Subject: [PATCH 177/358] ice: fix vsi->txq_map sizing The approach of having XDP queue per CPU regardless of user's setting exposed a hidden bug that could occur in case when Rx queue count differ from Tx queue count. Currently vsi->txq_map's size is equal to the doubled vsi->alloc_txq, which is not correct due to the fact that XDP rings were previously based on the Rx queue count. Below splat can be seen when ethtool -L is used and XDP rings are configured: [ 682.875339] BUG: kernel NULL pointer dereference, address: 000000000000000f [ 682.883403] #PF: supervisor read access in kernel mode [ 682.889345] #PF: error_code(0x0000) - not-present page [ 682.895289] PGD 0 P4D 0 [ 682.898218] Oops: 0000 [#1] PREEMPT SMP PTI [ 682.903055] CPU: 42 PID: 2878 Comm: ethtool Tainted: G OE 5.15.0-rc5+ #1 [ 682.912214] Hardware name: Intel Corp. GRANTLEY/GRANTLEY, BIOS GRRFCRB1.86B.0276.D07.1605190235 05/19/2016 [ 682.923380] RIP: 0010:devres_remove+0x44/0x130 [ 682.928527] Code: 49 89 f4 55 48 89 fd 4c 89 ff 53 48 83 ec 10 e8 92 b9 49 00 48 8b 9d a8 02 00 00 48 8d 8d a0 02 00 00 49 89 c2 48 39 cb 74 0f <4c> 3b 63 10 74 25 48 8b 5b 08 48 39 cb 75 f1 4c 89 ff 4c 89 d6 e8 [ 682.950237] RSP: 0018:ffffc90006a679f0 EFLAGS: 00010002 [ 682.956285] RAX: 0000000000000286 RBX: ffffffffffffffff RCX: ffff88908343a370 [ 682.964538] RDX: 0000000000000001 RSI: ffffffff81690d60 RDI: 0000000000000000 [ 682.972789] RBP: ffff88908343a0d0 R08: 0000000000000000 R09: 0000000000000000 [ 682.981040] R10: 0000000000000286 R11: 3fffffffffffffff R12: ffffffff81690d60 [ 682.989282] R13: ffffffff81690a00 R14: ffff8890819807a8 R15: ffff88908343a36c [ 682.997535] FS: 00007f08c7bfa740(0000) GS:ffff88a03fd00000(0000) knlGS:0000000000000000 [ 683.006910] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 683.013557] CR2: 000000000000000f CR3: 0000001080a66003 CR4: 00000000003706e0 [ 683.021819] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 683.030075] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 683.038336] Call Trace: [ 683.041167] devm_kfree+0x33/0x50 [ 683.045004] ice_vsi_free_arrays+0x5e/0xc0 [ice] [ 683.050380] ice_vsi_rebuild+0x4c8/0x750 [ice] [ 683.055543] ice_vsi_recfg_qs+0x9a/0x110 [ice] [ 683.060697] ice_set_channels+0x14f/0x290 [ice] [ 683.065962] ethnl_set_channels+0x333/0x3f0 [ 683.070807] genl_family_rcv_msg_doit+0xea/0x150 [ 683.076152] genl_rcv_msg+0xde/0x1d0 [ 683.080289] ? channels_prepare_data+0x60/0x60 [ 683.085432] ? genl_get_cmd+0xd0/0xd0 [ 683.089667] netlink_rcv_skb+0x50/0xf0 [ 683.094006] genl_rcv+0x24/0x40 [ 683.097638] netlink_unicast+0x239/0x340 [ 683.102177] netlink_sendmsg+0x22e/0x470 [ 683.106717] sock_sendmsg+0x5e/0x60 [ 683.110756] __sys_sendto+0xee/0x150 [ 683.114894] ? handle_mm_fault+0xd0/0x2a0 [ 683.119535] ? do_user_addr_fault+0x1f3/0x690 [ 683.134173] __x64_sys_sendto+0x25/0x30 [ 683.148231] do_syscall_64+0x3b/0xc0 [ 683.161992] entry_SYSCALL_64_after_hwframe+0x44/0xae Fix this by taking into account the value that num_possible_cpus() yields in addition to vsi->alloc_txq instead of doubling the latter. Fixes: efc2214b6047 ("ice: Add support for XDP") Fixes: 22bf877e528f ("ice: introduce XDP_TX fallback path") Reviewed-by: Alexander Lobakin Signed-off-by: Maciej Fijalkowski Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 40562600a8cf2b..09a3297cd63cd3 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -89,8 +89,13 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->rx_rings) goto err_rings; - /* XDP will have vsi->alloc_txq Tx queues as well, so double the size */ - vsi->txq_map = devm_kcalloc(dev, (2 * vsi->alloc_txq), + /* txq_map needs to have enough space to track both Tx (stack) rings + * and XDP rings; at this point vsi->num_xdp_txq might not be set, + * so use num_possible_cpus() as we want to always provide XDP ring + * per CPU, regardless of queue count settings from user that might + * have come from ethtool's set_channels() callback; + */ + vsi->txq_map = devm_kcalloc(dev, (vsi->alloc_txq + num_possible_cpus()), sizeof(*vsi->txq_map), GFP_KERNEL); if (!vsi->txq_map) From f65ee535df775a13a1046c0a0b2d72db342f8a5b Mon Sep 17 00:00:00 2001 From: Marta Plantykow Date: Tue, 26 Oct 2021 18:47:19 +0200 Subject: [PATCH 178/358] ice: avoid bpf_prog refcount underflow Ice driver has the routines for managing XDP resources that are shared between ndo_bpf op and VSI rebuild flow. The latter takes place for example when user changes queue count on an interface via ethtool's set_channels(). There is an issue around the bpf_prog refcounting when VSI is being rebuilt - since ice_prepare_xdp_rings() is called with vsi->xdp_prog as an argument that is used later on by ice_vsi_assign_bpf_prog(), same bpf_prog pointers are swapped with each other. Then it is also interpreted as an 'old_prog' which in turn causes us to call bpf_prog_put on it that will decrement its refcount. Below splat can be interpreted in a way that due to zero refcount of a bpf_prog it is wiped out from the system while kernel still tries to refer to it: [ 481.069429] BUG: unable to handle page fault for address: ffffc9000640f038 [ 481.077390] #PF: supervisor read access in kernel mode [ 481.083335] #PF: error_code(0x0000) - not-present page [ 481.089276] PGD 100000067 P4D 100000067 PUD 1001cb067 PMD 106d2b067 PTE 0 [ 481.097141] Oops: 0000 [#1] PREEMPT SMP PTI [ 481.101980] CPU: 12 PID: 3339 Comm: sudo Tainted: G OE 5.15.0-rc5+ #1 [ 481.110840] Hardware name: Intel Corp. GRANTLEY/GRANTLEY, BIOS GRRFCRB1.86B.0276.D07.1605190235 05/19/2016 [ 481.122021] RIP: 0010:dev_xdp_prog_id+0x25/0x40 [ 481.127265] Code: 80 00 00 00 00 0f 1f 44 00 00 89 f6 48 c1 e6 04 48 01 fe 48 8b 86 98 08 00 00 48 85 c0 74 13 48 8b 50 18 31 c0 48 85 d2 74 07 <48> 8b 42 38 8b 40 20 c3 48 8b 96 90 08 00 00 eb e8 66 2e 0f 1f 84 [ 481.148991] RSP: 0018:ffffc90007b63868 EFLAGS: 00010286 [ 481.155034] RAX: 0000000000000000 RBX: ffff889080824000 RCX: 0000000000000000 [ 481.163278] RDX: ffffc9000640f000 RSI: ffff889080824010 RDI: ffff889080824000 [ 481.171527] RBP: ffff888107af7d00 R08: 0000000000000000 R09: ffff88810db5f6e0 [ 481.179776] R10: 0000000000000000 R11: ffff8890885b9988 R12: ffff88810db5f4bc [ 481.188026] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 481.196276] FS: 00007f5466d5bec0(0000) GS:ffff88903fb00000(0000) knlGS:0000000000000000 [ 481.205633] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 481.212279] CR2: ffffc9000640f038 CR3: 000000014429c006 CR4: 00000000003706e0 [ 481.220530] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 481.228771] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 481.237029] Call Trace: [ 481.239856] rtnl_fill_ifinfo+0x768/0x12e0 [ 481.244602] rtnl_dump_ifinfo+0x525/0x650 [ 481.249246] ? __alloc_skb+0xa5/0x280 [ 481.253484] netlink_dump+0x168/0x3c0 [ 481.257725] netlink_recvmsg+0x21e/0x3e0 [ 481.262263] ____sys_recvmsg+0x87/0x170 [ 481.266707] ? __might_fault+0x20/0x30 [ 481.271046] ? _copy_from_user+0x66/0xa0 [ 481.275591] ? iovec_from_user+0xf6/0x1c0 [ 481.280226] ___sys_recvmsg+0x82/0x100 [ 481.284566] ? sock_sendmsg+0x5e/0x60 [ 481.288791] ? __sys_sendto+0xee/0x150 [ 481.293129] __sys_recvmsg+0x56/0xa0 [ 481.297267] do_syscall_64+0x3b/0xc0 [ 481.301395] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 481.307238] RIP: 0033:0x7f5466f39617 [ 481.311373] Code: 0c 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb bd 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2f 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 [ 481.342944] RSP: 002b:00007ffedc7f4308 EFLAGS: 00000246 ORIG_RAX: 000000000000002f [ 481.361783] RAX: ffffffffffffffda RBX: 00007ffedc7f5460 RCX: 00007f5466f39617 [ 481.380278] RDX: 0000000000000000 RSI: 00007ffedc7f5360 RDI: 0000000000000003 [ 481.398500] RBP: 00007ffedc7f53f0 R08: 0000000000000000 R09: 000055d556f04d50 [ 481.416463] R10: 0000000000000077 R11: 0000000000000246 R12: 00007ffedc7f5360 [ 481.434131] R13: 00007ffedc7f5350 R14: 00007ffedc7f5344 R15: 0000000000000e98 [ 481.451520] Modules linked in: ice(OE) af_packet binfmt_misc nls_iso8859_1 ipmi_ssif intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp mxm_wmi mei_me coretemp mei ipmi_si ipmi_msghandler wmi acpi_pad acpi_power_meter ip_tables x_tables autofs4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel ahci crypto_simd cryptd libahci lpc_ich [last unloaded: ice] [ 481.528558] CR2: ffffc9000640f038 [ 481.542041] ---[ end trace d1f24c9ecf5b61c1 ]--- Fix this by only calling ice_vsi_assign_bpf_prog() inside ice_prepare_xdp_rings() when current vsi->xdp_prog pointer is NULL. This way set_channels() flow will not attempt to swap the vsi->xdp_prog pointers with itself. Also, sprinkle around some comments that provide a reasoning about correlation between driver and kernel in terms of bpf_prog refcount. Fixes: efc2214b6047 ("ice: Add support for XDP") Reviewed-by: Alexander Lobakin Signed-off-by: Marta Plantykow Co-developed-by: Maciej Fijalkowski Signed-off-by: Maciej Fijalkowski Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f099797f35e375..4d1fc48c9744b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2609,7 +2609,18 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) ice_stat_str(status)); goto clear_xdp_rings; } - ice_vsi_assign_bpf_prog(vsi, prog); + + /* assign the prog only when it's not already present on VSI; + * this flow is a subject of both ethtool -L and ndo_bpf flows; + * VSI rebuild that happens under ethtool -L can expose us to + * the bpf_prog refcount issues as we would be swapping same + * bpf_prog pointers from vsi->xdp_prog and calling bpf_prog_put + * on it as it would be treated as an 'old_prog'; for ndo_bpf + * this is not harmful as dev_xdp_install bumps the refcount + * before calling the op exposed by the driver; + */ + if (!ice_is_xdp_ena_vsi(vsi)) + ice_vsi_assign_bpf_prog(vsi, prog); return 0; clear_xdp_rings: @@ -2785,6 +2796,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); } else { + /* safe to call even when prog == vsi->xdp_prog as + * dev_xdp_install in net/core/dev.c incremented prog's + * refcount so corresponding bpf_prog_put won't cause + * underflow + */ ice_vsi_assign_bpf_prog(vsi, prog); } From a4a118f2eead1d6c49e00765de89878288d4b890 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sun, 21 Nov 2021 12:40:07 -0800 Subject: [PATCH 179/358] hugetlbfs: flush TLBs correctly after huge_pmd_unshare When __unmap_hugepage_range() calls to huge_pmd_unshare() succeed, a TLB flush is missing. This TLB flush must be performed before releasing the i_mmap_rwsem, in order to prevent an unshared PMDs page from being released and reused before the TLB flush took place. Arguably, a comprehensive solution would use mmu_gather interface to batch the TLB flushes and the PMDs page release, however it is not an easy solution: (1) try_to_unmap_one() and try_to_migrate_one() also call huge_pmd_unshare() and they cannot use the mmu_gather interface; and (2) deferring the release of the page reference for the PMDs page until after i_mmap_rwsem is dropeed can confuse huge_pmd_unshare() into thinking PMDs are shared when they are not. Fix __unmap_hugepage_range() by adding the missing TLB flush, and forcing a flush when unshare is successful. Fixes: 24669e58477e ("hugetlb: use mmu_gather instead of a temporary linked list for accumulating pages)" # 3.6 Signed-off-by: Nadav Amit Reviewed-by: Mike Kravetz Cc: Aneesh Kumar K.V Cc: KAMEZAWA Hiroyuki Cc: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f025d234522fbf..2ccebe1ca9f41b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4939,6 +4939,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; + bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -4967,10 +4968,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, &address, ptep)) { spin_unlock(ptl); - /* - * We just unmapped a page of PMDs by clearing a PUD. - * The caller's TLB flush range should cover this area. - */ + tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); + force_flush = true; continue; } @@ -5027,6 +5026,22 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct } mmu_notifier_invalidate_range_end(&range); tlb_end_vma(tlb, vma); + + /* + * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We + * could defer the flush until now, since by holding i_mmap_rwsem we + * guaranteed that the last refernece would not be dropped. But we must + * do the flushing before we return, as otherwise i_mmap_rwsem will be + * dropped and the last reference to the shared PMDs page might be + * dropped as well. + * + * In theory we could defer the freeing of the PMD pages as well, but + * huge_pmd_unshare() relies on the exact page_count for the PMD page to + * detect sharing, so we cannot defer the release of the page either. + * Instead, do flush now. + */ + if (force_flush) + tlb_flush_mmu_tlbonly(tlb); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, From 13e4ad2ce8df6e058ef482a31fdd81c725b0f7ea Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sun, 21 Nov 2021 12:40:08 -0800 Subject: [PATCH 180/358] hugetlbfs: flush before unlock on move_hugetlb_page_tables() We must flush the TLB before releasing i_mmap_rwsem to avoid the potential reuse of an unshared PMDs page. This is not true in the case of move_hugetlb_page_tables(). The last reference on the page table can therefore be dropped before the TLB flush took place. Prevent it by reordering the operations and flushing the TLB before releasing i_mmap_rwsem. Fixes: 550a7d60bd5e ("mm, hugepages: add mremap() support for hugepage backed vma") Signed-off-by: Nadav Amit Reviewed-by: Mike Kravetz Cc: Mina Almasry Cc: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2ccebe1ca9f41b..abcd1785c629c4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4919,9 +4919,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, move_huge_pte(vma, old_addr, new_addr, src_pte); } - i_mmap_unlock_write(mapping); flush_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); + i_mmap_unlock_write(mapping); return len + old_addr - old_end; } From 064a91771f7aae4ea2d13033b64e921951d216ce Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 23 Nov 2021 09:40:35 +1100 Subject: [PATCH 181/358] SUNRPC: use different lock keys for INET6 and LOCAL xprtsock.c reclassifies sock locks based on the protocol. However there are 3 protocols and only 2 classification keys. The same key is used for both INET6 and LOCAL. This causes lockdep complaints. The complaints started since Commit ea9afca88bbe ("SUNRPC: Replace use of socket sk_callback_lock with sock_lock") which resulted in the sock locks beings used more. So add another key, and renumber them slightly. Fixes: ea9afca88bbe ("SUNRPC: Replace use of socket sk_callback_lock with sock_lock") Fixes: 176e21ee2ec8 ("SUNRPC: Support for RPC over AF_LOCAL transports") Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ae48c9c84ee17a..d8ee06a9650a16 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1720,15 +1720,15 @@ static void xs_local_set_port(struct rpc_xprt *xprt, unsigned short port) } #ifdef CONFIG_DEBUG_LOCK_ALLOC -static struct lock_class_key xs_key[2]; -static struct lock_class_key xs_slock_key[2]; +static struct lock_class_key xs_key[3]; +static struct lock_class_key xs_slock_key[3]; static inline void xs_reclassify_socketu(struct socket *sock) { struct sock *sk = sock->sk; sock_lock_init_class_and_name(sk, "slock-AF_LOCAL-RPC", - &xs_slock_key[1], "sk_lock-AF_LOCAL-RPC", &xs_key[1]); + &xs_slock_key[0], "sk_lock-AF_LOCAL-RPC", &xs_key[0]); } static inline void xs_reclassify_socket4(struct socket *sock) @@ -1736,7 +1736,7 @@ static inline void xs_reclassify_socket4(struct socket *sock) struct sock *sk = sock->sk; sock_lock_init_class_and_name(sk, "slock-AF_INET-RPC", - &xs_slock_key[0], "sk_lock-AF_INET-RPC", &xs_key[0]); + &xs_slock_key[1], "sk_lock-AF_INET-RPC", &xs_key[1]); } static inline void xs_reclassify_socket6(struct socket *sock) @@ -1744,7 +1744,7 @@ static inline void xs_reclassify_socket6(struct socket *sock) struct sock *sk = sock->sk; sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC", - &xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]); + &xs_slock_key[2], "sk_lock-AF_INET6-RPC", &xs_key[2]); } static inline void xs_reclassify_socket(int family, struct socket *sock) From efcf5932230b9472cfdbe01c858726f29ac5ec7d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 11 Nov 2021 10:03:43 +0800 Subject: [PATCH 182/358] block: avoid to touch unloaded module instance when opening bdev disk->fops->owner is grabbed in blkdev_get_no_open() after the disk kobject refcount is increased. This way can't make sure that disk->fops->owner is still alive since del_gendisk() still can move on if the kobject refcount of disk is grabbed by open() and disk->fops->open() isn't called yet. Fixes the issue by moving try_module_get() into blkdev_get_by_dev() with ->open_mutex() held, then we can drain the in-progress open() in del_gendisk(). Meantime new open() won't succeed because disk becomes not alive. This way is reasonable because blkdev_get_no_open() needn't to touch disk->fops or defined callbacks. Cc: Christoph Hellwig Cc: czhong@redhat.com Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211111020343.316126-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/bdev.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/block/bdev.c b/block/bdev.c index b4dab2fb6a7469..b1d087e5e205f6 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -753,8 +753,7 @@ struct block_device *blkdev_get_no_open(dev_t dev) if (!bdev) return NULL; - if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN) || - !try_module_get(bdev->bd_disk->fops->owner)) { + if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN)) { put_device(&bdev->bd_device); return NULL; } @@ -764,7 +763,6 @@ struct block_device *blkdev_get_no_open(dev_t dev) void blkdev_put_no_open(struct block_device *bdev) { - module_put(bdev->bd_disk->fops->owner); put_device(&bdev->bd_device); } @@ -820,12 +818,14 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) ret = -ENXIO; if (!disk_live(disk)) goto abort_claiming; + if (!try_module_get(disk->fops->owner)) + goto abort_claiming; if (bdev_is_partition(bdev)) ret = blkdev_get_part(bdev, mode); else ret = blkdev_get_whole(bdev, mode); if (ret) - goto abort_claiming; + goto put_module; if (mode & FMODE_EXCL) { bd_finish_claiming(bdev, holder); @@ -847,7 +847,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) if (unblock_events) disk_unblock_events(disk); return bdev; - +put_module: + module_put(disk->fops->owner); abort_claiming: if (mode & FMODE_EXCL) bd_abort_claiming(bdev, holder); @@ -956,6 +957,7 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) blkdev_put_whole(bdev, mode); mutex_unlock(&disk->open_mutex); + module_put(disk->fops->owner); blkdev_put_no_open(bdev); } EXPORT_SYMBOL(blkdev_put); From 674ee8e1b4a41d2fdffc885c55350c3fbb38c22a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 23 Nov 2021 01:45:35 +0000 Subject: [PATCH 183/358] io_uring: correct link-list traversal locking As io_remove_next_linked() is now under ->timeout_lock (see io_link_timeout_fn), we should update locking around io_for_each_link() and io_match_task() to use the new lock. Cc: stable@kernel.org # 5.15+ Fixes: 89850fce16a1a ("io_uring: run timeouts from task_work") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/b54541cedf7de59cb5ae36109e58529ca16e66aa.1637631883.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index e98e7ce3dc393a..a4c508a1e0cff7 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1502,10 +1502,10 @@ static void io_prep_async_link(struct io_kiocb *req) if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; - spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); io_for_each_link(cur, req) io_prep_async_work(cur); - spin_unlock(&ctx->completion_lock); + spin_unlock_irq(&ctx->timeout_lock); } else { io_for_each_link(cur, req) io_prep_async_work(cur); @@ -5699,6 +5699,7 @@ static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx, int posted = 0, i; spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { struct hlist_head *list; @@ -5708,6 +5709,7 @@ static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx, posted += io_poll_remove_one(req); } } + spin_unlock_irq(&ctx->timeout_lock); spin_unlock(&ctx->completion_lock); if (posted) @@ -9568,9 +9570,9 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data) struct io_ring_ctx *ctx = req->ctx; /* protect against races with linked timeouts */ - spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); ret = io_match_task(req, cancel->task, cancel->all); - spin_unlock(&ctx->completion_lock); + spin_unlock_irq(&ctx->timeout_lock); } else { ret = io_match_task(req, cancel->task, cancel->all); } @@ -9585,12 +9587,14 @@ static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, LIST_HEAD(list); spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); list_for_each_entry_reverse(de, &ctx->defer_list, list) { if (io_match_task(de->req, task, cancel_all)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } } + spin_unlock_irq(&ctx->timeout_lock); spin_unlock(&ctx->completion_lock); if (list_empty(&list)) return false; From e0a2c28da11e2c2b963fc01d50acbf03045ac732 Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Thu, 18 Nov 2021 14:03:28 -0500 Subject: [PATCH 184/358] scsi: scsi_debug: Sanity check block descriptor length in resp_mode_select() In resp_mode_select() sanity check the block descriptor len to avoid UAF. BUG: KASAN: use-after-free in resp_mode_select+0xa4c/0xb40 drivers/scsi/scsi_debug.c:2509 Read of size 1 at addr ffff888026670f50 by task scsicmd/15032 CPU: 1 PID: 15032 Comm: scsicmd Not tainted 5.15.0-01d0625 #15 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Call Trace: dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:107 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:257 kasan_report.cold.14+0x7d/0x117 mm/kasan/report.c:443 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report_generic.c:306 resp_mode_select+0xa4c/0xb40 drivers/scsi/scsi_debug.c:2509 schedule_resp+0x4af/0x1a10 drivers/scsi/scsi_debug.c:5483 scsi_debug_queuecommand+0x8c9/0x1e70 drivers/scsi/scsi_debug.c:7537 scsi_queue_rq+0x16b4/0x2d10 drivers/scsi/scsi_lib.c:1521 blk_mq_dispatch_rq_list+0xb9b/0x2700 block/blk-mq.c:1640 __blk_mq_sched_dispatch_requests+0x28f/0x590 block/blk-mq-sched.c:325 blk_mq_sched_dispatch_requests+0x105/0x190 block/blk-mq-sched.c:358 __blk_mq_run_hw_queue+0xe5/0x150 block/blk-mq.c:1762 __blk_mq_delay_run_hw_queue+0x4f8/0x5c0 block/blk-mq.c:1839 blk_mq_run_hw_queue+0x18d/0x350 block/blk-mq.c:1891 blk_mq_sched_insert_request+0x3db/0x4e0 block/blk-mq-sched.c:474 blk_execute_rq_nowait+0x16b/0x1c0 block/blk-exec.c:63 sg_common_write.isra.18+0xeb3/0x2000 drivers/scsi/sg.c:837 sg_new_write.isra.19+0x570/0x8c0 drivers/scsi/sg.c:775 sg_ioctl_common+0x14d6/0x2710 drivers/scsi/sg.c:941 sg_ioctl+0xa2/0x180 drivers/scsi/sg.c:1166 __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:52 do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:50 entry_SYSCALL_64_after_hwframe+0x44/0xae arch/x86/entry/entry_64.S:113 Link: https://lore.kernel.org/r/1637262208-28850-1-git-send-email-george.kennedy@oracle.com Reported-by: syzkaller Acked-by: Douglas Gilbert Signed-off-by: George Kennedy Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_debug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index ab01ef7d37f4da..e5cbeb701629f2 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -2502,11 +2502,11 @@ static int resp_mode_select(struct scsi_cmnd *scp, __func__, param_len, res); md_len = mselect6 ? (arr[0] + 1) : (get_unaligned_be16(arr + 0) + 2); bd_len = mselect6 ? arr[3] : get_unaligned_be16(arr + 6); - if (md_len > 2) { + off = bd_len + (mselect6 ? 4 : 8); + if (md_len > 2 || off >= res) { mk_sense_invalid_fld(scp, SDEB_IN_DATA, 0, -1); return check_condition_result; } - off = bd_len + (mselect6 ? 4 : 8); mpage = arr[off] & 0x3f; ps = !!(arr[off] & 0x80); if (ps) { From eb97545d6264b341b06ba7603f52ff6c0b2af6ea Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sat, 20 Nov 2021 10:49:17 -0600 Subject: [PATCH 185/358] scsi: core: sysfs: Fix setting device state to SDEV_RUNNING This fixes an issue added in commit 4edd8cd4e86d ("scsi: core: sysfs: Fix hang when device state is set via sysfs") where if userspace is requesting to set the device state to SDEV_RUNNING when the state is already SDEV_RUNNING, we return -EINVAL instead of count. The commmit above set ret to count for this case, when it should have set it to 0. Link: https://lore.kernel.org/r/20211120164917.4924-1-michael.christie@oracle.com Fixes: 4edd8cd4e86d ("scsi: core: sysfs: Fix hang when device state is set via sysfs") Reviewed-by: Lee Duncan Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 7afcec250f9b5a..d4edce930a4a06 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -812,7 +812,7 @@ store_state_field(struct device *dev, struct device_attribute *attr, mutex_lock(&sdev->state_mutex); if (sdev->sdev_state == SDEV_RUNNING && state == SDEV_RUNNING) { - ret = count; + ret = 0; } else { ret = scsi_device_set_state(sdev, state); if (ret == 0 && state == SDEV_RUNNING) From 2d62253eb1b60f4ce8b39125eee282739b519297 Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Mon, 22 Nov 2021 15:12:23 +0900 Subject: [PATCH 186/358] scsi: scsi_debug: Zero clear zones at reset write pointer When a reset is requested the position of the write pointer is updated but the data in the corresponding zone is not cleared. Instead scsi_debug returns any data written before the write pointer was reset. This is an error and prevents using scsi_debug for stale page cache testing of the BLKRESETZONE ioctl. Zero written data in the zone when resetting the write pointer. Link: https://lore.kernel.org/r/20211122061223.298890-1-shinichiro.kawasaki@wdc.com Fixes: f0d1cf9378bd ("scsi: scsi_debug: Add ZBC zone commands") Reviewed-by: Damien Le Moal Acked-by: Douglas Gilbert Signed-off-by: Shin'ichiro Kawasaki Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_debug.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index e5cbeb701629f2..3c0da3770edf91 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -4657,6 +4657,7 @@ static void zbc_rwp_zone(struct sdebug_dev_info *devip, struct sdeb_zone_state *zsp) { enum sdebug_z_cond zc; + struct sdeb_store_info *sip = devip2sip(devip, false); if (zbc_zone_is_conv(zsp)) return; @@ -4668,6 +4669,10 @@ static void zbc_rwp_zone(struct sdebug_dev_info *devip, if (zsp->z_cond == ZC4_CLOSED) devip->nr_closed--; + if (zsp->z_wp > zsp->z_start) + memset(sip->storep + zsp->z_start * sdebug_sector_size, 0, + (zsp->z_wp - zsp->z_start) * sdebug_sector_size); + zsp->z_non_seq_resource = false; zsp->z_wp = zsp->z_start; zsp->z_cond = ZC1_EMPTY; From 57bbeacdbee72a54eb97d56b876cf9c94059fc34 Mon Sep 17 00:00:00 2001 From: Huang Jianan Date: Thu, 18 Nov 2021 21:58:44 +0800 Subject: [PATCH 187/358] erofs: fix deadlock when shrink erofs slab We observed the following deadlock in the stress test under low memory scenario: Thread A Thread B - erofs_shrink_scan - erofs_try_to_release_workgroup - erofs_workgroup_try_to_freeze -- A - z_erofs_do_read_page - z_erofs_collection_begin - z_erofs_register_collection - erofs_insert_workgroup - xa_lock(&sbi->managed_pslots) -- B - erofs_workgroup_get - erofs_wait_on_workgroup_freezed -- A - xa_erase - xa_lock(&sbi->managed_pslots) -- B To fix this, it needs to hold xa_lock before freezing the workgroup since xarray will be touched then. So let's hold the lock before accessing each workgroup, just like what we did with the radix tree before. [ Gao Xiang: Jianhua Hao also reports this issue at https://lore.kernel.org/r/b10b85df30694bac8aadfe43537c897a@xiaomi.com ] Link: https://lore.kernel.org/r/20211118135844.3559-1-huangjianan@oppo.com Fixes: 64094a04414f ("erofs: convert workstn to XArray") Reviewed-by: Chao Yu Reviewed-by: Gao Xiang Signed-off-by: Huang Jianan Reported-by: Jianhua Hao Signed-off-by: Gao Xiang --- fs/erofs/utils.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c index 84da2c28001298..ec9a1d780dc143 100644 --- a/fs/erofs/utils.c +++ b/fs/erofs/utils.c @@ -150,7 +150,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi, * however in order to avoid some race conditions, add a * DBG_BUGON to observe this in advance. */ - DBG_BUGON(xa_erase(&sbi->managed_pslots, grp->index) != grp); + DBG_BUGON(__xa_erase(&sbi->managed_pslots, grp->index) != grp); /* last refcount should be connected with its managed pslot. */ erofs_workgroup_unfreeze(grp, 0); @@ -165,15 +165,19 @@ static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi, unsigned int freed = 0; unsigned long index; + xa_lock(&sbi->managed_pslots); xa_for_each(&sbi->managed_pslots, index, grp) { /* try to shrink each valid workgroup */ if (!erofs_try_to_release_workgroup(sbi, grp)) continue; + xa_unlock(&sbi->managed_pslots); ++freed; if (!--nr_shrink) - break; + return freed; + xa_lock(&sbi->managed_pslots); } + xa_unlock(&sbi->managed_pslots); return freed; } From d257cc8cb8d5355ffc43a96bab94db7b5a324803 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 15 Nov 2021 20:29:12 -0500 Subject: [PATCH 188/358] locking/rwsem: Make handoff bit handling more consistent There are some inconsistency in the way that the handoff bit is being handled in readers and writers that lead to a race condition. Firstly, when a queue head writer set the handoff bit, it will clear it when the writer is being killed or interrupted on its way out without acquiring the lock. That is not the case for a queue head reader. The handoff bit will simply be inherited by the next waiter. Secondly, in the out_nolock path of rwsem_down_read_slowpath(), both the waiter and handoff bits are cleared if the wait queue becomes empty. For rwsem_down_write_slowpath(), however, the handoff bit is not checked and cleared if the wait queue is empty. This can potentially make the handoff bit set with empty wait queue. Worse, the situation in rwsem_down_write_slowpath() relies on wstate, a variable set outside of the critical section containing the ->count manipulation, this leads to race condition where RWSEM_FLAG_HANDOFF can be double subtracted, corrupting ->count. To make the handoff bit handling more consistent and robust, extract out handoff bit clearing code into the new rwsem_del_waiter() helper function. Also, completely eradicate wstate; always evaluate everything inside the same critical section. The common function will only use atomic_long_andnot() to clear bits when the wait queue is empty to avoid possible race condition. If the first waiter with handoff bit set is killed or interrupted to exit the slowpath without acquiring the lock, the next waiter will inherit the handoff bit. While at it, simplify the trylock for loop in rwsem_down_write_slowpath() to make it easier to read. Fixes: 4f23dbc1e657 ("locking/rwsem: Implement lock handoff to prevent lock starvation") Reported-by: Zhenhua Ma Suggested-by: Peter Zijlstra Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20211116012912.723980-1-longman@redhat.com --- kernel/locking/rwsem.c | 171 ++++++++++++++++++++--------------------- 1 file changed, 85 insertions(+), 86 deletions(-) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index c51387a4326574..e039cf1605af53 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -105,9 +105,9 @@ * atomic_long_cmpxchg() will be used to obtain writer lock. * * There are three places where the lock handoff bit may be set or cleared. - * 1) rwsem_mark_wake() for readers. - * 2) rwsem_try_write_lock() for writers. - * 3) Error path of rwsem_down_write_slowpath(). + * 1) rwsem_mark_wake() for readers -- set, clear + * 2) rwsem_try_write_lock() for writers -- set, clear + * 3) rwsem_del_waiter() -- clear * * For all the above cases, wait_lock will be held. A writer must also * be the first one in the wait_list to be eligible for setting the handoff @@ -334,6 +334,9 @@ struct rwsem_waiter { struct task_struct *task; enum rwsem_waiter_type type; unsigned long timeout; + + /* Writer only, not initialized in reader */ + bool handoff_set; }; #define rwsem_first_waiter(sem) \ list_first_entry(&sem->wait_list, struct rwsem_waiter, list) @@ -344,12 +347,6 @@ enum rwsem_wake_type { RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */ }; -enum writer_wait_state { - WRITER_NOT_FIRST, /* Writer is not first in wait list */ - WRITER_FIRST, /* Writer is first in wait list */ - WRITER_HANDOFF /* Writer is first & handoff needed */ -}; - /* * The typical HZ value is either 250 or 1000. So set the minimum waiting * time to at least 4ms or 1 jiffy (if it is higher than 4ms) in the wait @@ -365,6 +362,31 @@ enum writer_wait_state { */ #define MAX_READERS_WAKEUP 0x100 +static inline void +rwsem_add_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter) +{ + lockdep_assert_held(&sem->wait_lock); + list_add_tail(&waiter->list, &sem->wait_list); + /* caller will set RWSEM_FLAG_WAITERS */ +} + +/* + * Remove a waiter from the wait_list and clear flags. + * + * Both rwsem_mark_wake() and rwsem_try_write_lock() contain a full 'copy' of + * this function. Modify with care. + */ +static inline void +rwsem_del_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter) +{ + lockdep_assert_held(&sem->wait_lock); + list_del(&waiter->list); + if (likely(!list_empty(&sem->wait_list))) + return; + + atomic_long_andnot(RWSEM_FLAG_HANDOFF | RWSEM_FLAG_WAITERS, &sem->count); +} + /* * handle the lock release when processes blocked on it that can now run * - if we come here from up_xxxx(), then the RWSEM_FLAG_WAITERS bit must @@ -376,6 +398,8 @@ enum writer_wait_state { * preferably when the wait_lock is released * - woken process blocks are discarded from the list after having task zeroed * - writers are only marked woken if downgrading is false + * + * Implies rwsem_del_waiter() for all woken readers. */ static void rwsem_mark_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type, @@ -490,18 +514,25 @@ static void rwsem_mark_wake(struct rw_semaphore *sem, adjustment = woken * RWSEM_READER_BIAS - adjustment; lockevent_cond_inc(rwsem_wake_reader, woken); + + oldcount = atomic_long_read(&sem->count); if (list_empty(&sem->wait_list)) { - /* hit end of list above */ + /* + * Combined with list_move_tail() above, this implies + * rwsem_del_waiter(). + */ adjustment -= RWSEM_FLAG_WAITERS; + if (oldcount & RWSEM_FLAG_HANDOFF) + adjustment -= RWSEM_FLAG_HANDOFF; + } else if (woken) { + /* + * When we've woken a reader, we no longer need to force + * writers to give up the lock and we can clear HANDOFF. + */ + if (oldcount & RWSEM_FLAG_HANDOFF) + adjustment -= RWSEM_FLAG_HANDOFF; } - /* - * When we've woken a reader, we no longer need to force writers - * to give up the lock and we can clear HANDOFF. - */ - if (woken && (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF)) - adjustment -= RWSEM_FLAG_HANDOFF; - if (adjustment) atomic_long_add(adjustment, &sem->count); @@ -532,12 +563,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem, * race conditions between checking the rwsem wait list and setting the * sem->count accordingly. * - * If wstate is WRITER_HANDOFF, it will make sure that either the handoff - * bit is set or the lock is acquired with handoff bit cleared. + * Implies rwsem_del_waiter() on success. */ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, - enum writer_wait_state wstate) + struct rwsem_waiter *waiter) { + bool first = rwsem_first_waiter(sem) == waiter; long count, new; lockdep_assert_held(&sem->wait_lock); @@ -546,13 +577,19 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, do { bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF); - if (has_handoff && wstate == WRITER_NOT_FIRST) - return false; + if (has_handoff) { + if (!first) + return false; + + /* First waiter inherits a previously set handoff bit */ + waiter->handoff_set = true; + } new = count; if (count & RWSEM_LOCK_MASK) { - if (has_handoff || (wstate != WRITER_HANDOFF)) + if (has_handoff || (!rt_task(waiter->task) && + !time_after(jiffies, waiter->timeout))) return false; new |= RWSEM_FLAG_HANDOFF; @@ -569,9 +606,17 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, * We have either acquired the lock with handoff bit cleared or * set the handoff bit. */ - if (new & RWSEM_FLAG_HANDOFF) + if (new & RWSEM_FLAG_HANDOFF) { + waiter->handoff_set = true; + lockevent_inc(rwsem_wlock_handoff); return false; + } + /* + * Have rwsem_try_write_lock() fully imply rwsem_del_waiter() on + * success. + */ + list_del(&waiter->list); rwsem_set_owner(sem); return true; } @@ -956,7 +1001,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat } adjustment += RWSEM_FLAG_WAITERS; } - list_add_tail(&waiter.list, &sem->wait_list); + rwsem_add_waiter(sem, &waiter); /* we're now waiting on the lock, but no longer actively locking */ count = atomic_long_add_return(adjustment, &sem->count); @@ -1002,11 +1047,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat return sem; out_nolock: - list_del(&waiter.list); - if (list_empty(&sem->wait_list)) { - atomic_long_andnot(RWSEM_FLAG_WAITERS|RWSEM_FLAG_HANDOFF, - &sem->count); - } + rwsem_del_waiter(sem, &waiter); raw_spin_unlock_irq(&sem->wait_lock); __set_current_state(TASK_RUNNING); lockevent_inc(rwsem_rlock_fail); @@ -1020,9 +1061,7 @@ static struct rw_semaphore * rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) { long count; - enum writer_wait_state wstate; struct rwsem_waiter waiter; - struct rw_semaphore *ret = sem; DEFINE_WAKE_Q(wake_q); /* do optimistic spinning and steal lock if possible */ @@ -1038,16 +1077,13 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) waiter.task = current; waiter.type = RWSEM_WAITING_FOR_WRITE; waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT; + waiter.handoff_set = false; raw_spin_lock_irq(&sem->wait_lock); - - /* account for this before adding a new element to the list */ - wstate = list_empty(&sem->wait_list) ? WRITER_FIRST : WRITER_NOT_FIRST; - - list_add_tail(&waiter.list, &sem->wait_list); + rwsem_add_waiter(sem, &waiter); /* we're now waiting on the lock */ - if (wstate == WRITER_NOT_FIRST) { + if (rwsem_first_waiter(sem) != &waiter) { count = atomic_long_read(&sem->count); /* @@ -1083,13 +1119,16 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) /* wait until we successfully acquire the lock */ set_current_state(state); for (;;) { - if (rwsem_try_write_lock(sem, wstate)) { + if (rwsem_try_write_lock(sem, &waiter)) { /* rwsem_try_write_lock() implies ACQUIRE on success */ break; } raw_spin_unlock_irq(&sem->wait_lock); + if (signal_pending_state(state, current)) + goto out_nolock; + /* * After setting the handoff bit and failing to acquire * the lock, attempt to spin on owner to accelerate lock @@ -1098,7 +1137,7 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) * In this case, we attempt to acquire the lock again * without sleeping. */ - if (wstate == WRITER_HANDOFF) { + if (waiter.handoff_set) { enum owner_state owner_state; preempt_disable(); @@ -1109,66 +1148,26 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) goto trylock_again; } - /* Block until there are no active lockers. */ - for (;;) { - if (signal_pending_state(state, current)) - goto out_nolock; - - schedule(); - lockevent_inc(rwsem_sleep_writer); - set_current_state(state); - /* - * If HANDOFF bit is set, unconditionally do - * a trylock. - */ - if (wstate == WRITER_HANDOFF) - break; - - if ((wstate == WRITER_NOT_FIRST) && - (rwsem_first_waiter(sem) == &waiter)) - wstate = WRITER_FIRST; - - count = atomic_long_read(&sem->count); - if (!(count & RWSEM_LOCK_MASK)) - break; - - /* - * The setting of the handoff bit is deferred - * until rwsem_try_write_lock() is called. - */ - if ((wstate == WRITER_FIRST) && (rt_task(current) || - time_after(jiffies, waiter.timeout))) { - wstate = WRITER_HANDOFF; - lockevent_inc(rwsem_wlock_handoff); - break; - } - } + schedule(); + lockevent_inc(rwsem_sleep_writer); + set_current_state(state); trylock_again: raw_spin_lock_irq(&sem->wait_lock); } __set_current_state(TASK_RUNNING); - list_del(&waiter.list); raw_spin_unlock_irq(&sem->wait_lock); lockevent_inc(rwsem_wlock); - - return ret; + return sem; out_nolock: __set_current_state(TASK_RUNNING); raw_spin_lock_irq(&sem->wait_lock); - list_del(&waiter.list); - - if (unlikely(wstate == WRITER_HANDOFF)) - atomic_long_add(-RWSEM_FLAG_HANDOFF, &sem->count); - - if (list_empty(&sem->wait_list)) - atomic_long_andnot(RWSEM_FLAG_WAITERS, &sem->count); - else + rwsem_del_waiter(sem, &waiter); + if (!list_empty(&sem->wait_list)) rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); raw_spin_unlock_irq(&sem->wait_lock); wake_up_q(&wake_q); lockevent_inc(rwsem_wlock_fail); - return ERR_PTR(-EINTR); } From 14c24048841151548a3f4d9e218510c844c1b737 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 18 Nov 2021 17:44:55 +0800 Subject: [PATCH 189/358] locking/rwsem: Optimize down_read_trylock() under highly contended case MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We found that a process with 10 thousnads threads has been encountered a regression problem from Linux-v4.14 to Linux-v5.4. It is a kind of workload which will concurrently allocate lots of memory in different threads sometimes. In this case, we will see the down_read_trylock() with a high hotspot. Therefore, we suppose that rwsem has a regression at least since Linux-v5.4. In order to easily debug this problem, we write a simply benchmark to create the similar situation lile the following. ```c++ #include #include #include #include #include #include #include #include #include volatile int mutex; void trigger(int cpu, char* ptr, std::size_t sz) { cpu_set_t set; CPU_ZERO(&set); CPU_SET(cpu, &set); assert(pthread_setaffinity_np(pthread_self(), sizeof(set), &set) == 0); while (mutex); for (std::size_t i = 0; i < sz; i += 4096) { *ptr = '\0'; ptr += 4096; } } int main(int argc, char* argv[]) { std::size_t sz = 100; if (argc > 1) sz = atoi(argv[1]); auto nproc = std::thread::hardware_concurrency(); std::vector thr; sz <<= 30; auto* ptr = mmap(nullptr, sz, PROT_READ | PROT_WRITE, MAP_ANON | MAP_PRIVATE, -1, 0); assert(ptr != MAP_FAILED); char* cptr = static_cast(ptr); auto run = sz / nproc; run = (run >> 12) << 12; mutex = 1; for (auto i = 0U; i < nproc; ++i) { thr.emplace_back(std::thread([i, cptr, run]() { trigger(i, cptr, run); })); cptr += run; } rusage usage_start; getrusage(RUSAGE_SELF, &usage_start); auto start = std::chrono::system_clock::now(); mutex = 0; for (auto& t : thr) t.join(); rusage usage_end; getrusage(RUSAGE_SELF, &usage_end); auto end = std::chrono::system_clock::now(); timeval utime; timeval stime; timersub(&usage_end.ru_utime, &usage_start.ru_utime, &utime); timersub(&usage_end.ru_stime, &usage_start.ru_stime, &stime); printf("usr: %ld.%06ld\n", utime.tv_sec, utime.tv_usec); printf("sys: %ld.%06ld\n", stime.tv_sec, stime.tv_usec); printf("real: %lu\n", std::chrono::duration_cast(end - start).count()); return 0; } ``` The functionality of above program is simply which creates `nproc` threads and each of them are trying to touch memory (trigger page fault) on different CPU. Then we will see the similar profile by `perf top`. 25.55% [kernel] [k] down_read_trylock 14.78% [kernel] [k] handle_mm_fault 13.45% [kernel] [k] up_read 8.61% [kernel] [k] clear_page_erms 3.89% [kernel] [k] __do_page_fault The highest hot instruction, which accounts for about 92%, in down_read_trylock() is cmpxchg like the following. 91.89 │ lock cmpxchg %rdx,(%rdi) Sice the problem is found by migrating from Linux-v4.14 to Linux-v5.4, so we easily found that the commit ddb20d1d3aed ("locking/rwsem: Optimize down_read_trylock()") caused the regression. The reason is that the commit assumes the rwsem is not contended at all. But it is not always true for mmap lock which could be contended with thousands threads. So most threads almost need to run at least 2 times of "cmpxchg" to acquire the lock. The overhead of atomic operation is higher than non-atomic instructions, which caused the regression. By using the above benchmark, the real executing time on a x86-64 system before and after the patch were: Before Patch After Patch # of Threads real real reduced by ------------ ------ ------ ---------- 1 65,373 65,206 ~0.0% 4 15,467 15,378 ~0.5% 40 6,214 5,528 ~11.0% For the uncontended case, the new down_read_trylock() is the same as before. For the contended cases, the new down_read_trylock() is faster than before. The more contended, the more fast. Signed-off-by: Muchun Song Signed-off-by: Peter Zijlstra (Intel) Acked-by: Waiman Long Link: https://lore.kernel.org/r/20211118094455.9068-1-songmuchun@bytedance.com --- kernel/locking/rwsem.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index e039cf1605af53..04a74d040a6d3a 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1248,17 +1248,14 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); - /* - * Optimize for the case when the rwsem is not locked at all. - */ - tmp = RWSEM_UNLOCKED_VALUE; - do { + tmp = atomic_long_read(&sem->count); + while (!(tmp & RWSEM_READ_FAILED_MASK)) { if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, - tmp + RWSEM_READER_BIAS)) { + tmp + RWSEM_READER_BIAS)) { rwsem_set_reader_owned(sem); return 1; } - } while (!(tmp & RWSEM_READ_FAILED_MASK)); + } return 0; } From 73743c3b092277febbf69b250ce8ebbca0525aa2 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 9 Nov 2021 13:22:32 +0100 Subject: [PATCH 190/358] perf: Ignore sigtrap for tracepoints destined for other tasks syzbot reported that the warning in perf_sigtrap() fires, saying that the event's task does not match current: | WARNING: CPU: 0 PID: 9090 at kernel/events/core.c:6446 perf_pending_event+0x40d/0x4b0 kernel/events/core.c:6513 | Modules linked in: | CPU: 0 PID: 9090 Comm: syz-executor.1 Not tainted 5.15.0-syzkaller #0 | Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 | RIP: 0010:perf_sigtrap kernel/events/core.c:6446 [inline] | RIP: 0010:perf_pending_event_disable kernel/events/core.c:6470 [inline] | RIP: 0010:perf_pending_event+0x40d/0x4b0 kernel/events/core.c:6513 | ... | Call Trace: | | irq_work_single+0x106/0x220 kernel/irq_work.c:211 | irq_work_run_list+0x6a/0x90 kernel/irq_work.c:242 | irq_work_run+0x4f/0xd0 kernel/irq_work.c:251 | __sysvec_irq_work+0x95/0x3d0 arch/x86/kernel/irq_work.c:22 | sysvec_irq_work+0x8e/0xc0 arch/x86/kernel/irq_work.c:17 | | | asm_sysvec_irq_work+0x12/0x20 arch/x86/include/asm/idtentry.h:664 | RIP: 0010:__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:152 [inline] | RIP: 0010:_raw_spin_unlock_irqrestore+0x38/0x70 kernel/locking/spinlock.c:194 | ... | coredump_task_exit kernel/exit.c:371 [inline] | do_exit+0x1865/0x25c0 kernel/exit.c:771 | do_group_exit+0xe7/0x290 kernel/exit.c:929 | get_signal+0x3b0/0x1ce0 kernel/signal.c:2820 | arch_do_signal_or_restart+0x2a9/0x1c40 arch/x86/kernel/signal.c:868 | handle_signal_work kernel/entry/common.c:148 [inline] | exit_to_user_mode_loop kernel/entry/common.c:172 [inline] | exit_to_user_mode_prepare+0x17d/0x290 kernel/entry/common.c:207 | __syscall_exit_to_user_mode_work kernel/entry/common.c:289 [inline] | syscall_exit_to_user_mode+0x19/0x60 kernel/entry/common.c:300 | do_syscall_64+0x42/0xb0 arch/x86/entry/common.c:86 | entry_SYSCALL_64_after_hwframe+0x44/0xae On x86 this shouldn't happen, which has arch_irq_work_raise(). The test program sets up a perf event with sigtrap set to fire on the 'sched_wakeup' tracepoint, which fired in ttwu_do_wakeup(). This happened because the 'sched_wakeup' tracepoint also takes a task argument passed on to perf_tp_event(), which is used to deliver the event to that other task. Since we cannot deliver synchronous signals to other tasks, skip an event if perf_tp_event() is targeted at another task and perf_event_attr::sigtrap is set, which will avoid ever entering perf_sigtrap() for such events. Fixes: 97ba62b27867 ("perf: Add support for SIGTRAP on perf events") Reported-by: syzbot+663359e32ce6f1a305ad@syzkaller.appspotmail.com Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/YYpoCOBmC/kJWfmI@elver.google.com --- kernel/events/core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index 523106a506eed0..30d94f68c5bdbc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9759,6 +9759,9 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, continue; if (event->attr.config != entry->type) continue; + /* Cannot deliver synchronous signal to other task. */ + if (event->attr.sigtrap) + continue; if (perf_tp_event_match(event, &data, regs)) perf_swevent_event(event, count, &data, regs); } From aa6fed90fea20bf52215952b276169efab8ae5ad Mon Sep 17 00:00:00 2001 From: Abel Vesa Date: Wed, 10 Nov 2021 19:46:44 +0200 Subject: [PATCH 191/358] dt-bindings: i2c: imx-lpi2c: Fix i.MX 8QM compatible matching The i.MX 8QM DTS files use two compatibles, so update the binding to fix dtbs_check warnings like: arch/arm64/boot/dts/freescale/imx8qm-mek.dt.yaml: i2c@5a800000: compatible: ['fsl,imx8qm-lpi2c', 'fsl,imx7ulp-lpi2c'] is too long Signed-off-by: Abel Vesa Acked-by: Rob Herring Signed-off-by: Wolfram Sang --- Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml index 29b9447f3b84af..fe0c89edf7c10f 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml @@ -17,9 +17,10 @@ properties: oneOf: - enum: - fsl,imx7ulp-lpi2c - - fsl,imx8qm-lpi2c - items: - - const: fsl,imx8qxp-lpi2c + - enum: + - fsl,imx8qxp-lpi2c + - fsl,imx8qm-lpi2c - const: fsl,imx7ulp-lpi2c reg: From 9b5bf5878138293fb5b14a48a7a17b6ede6bea25 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 9 Nov 2021 16:02:57 +0100 Subject: [PATCH 192/358] i2c: i801: Restore INTREN on unload If driver interrupts are enabled, SMBHSTCNT_INTREN will be 1 after the first transaction, and will stay to that value forever. This means that interrupts will be generated for both host-initiated transactions and also SMBus Alert events even after the driver is unloaded. To be on the safe side, we should restore the initial state of this bit at suspend and reboot time, as we do for several other configuration bits already and for the same reason: the BIOS should be handed the device in the same configuration state in which we received it. Otherwise interrupts may be generated which nobody will process. Signed-off-by: Jean Delvare Tested-by: Jarkko Nikula Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-i801.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 05187457f88a2e..ed271274250b19 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -259,6 +259,7 @@ struct i801_priv { struct i2c_adapter adapter; unsigned long smba; unsigned char original_hstcfg; + unsigned char original_hstcnt; unsigned char original_slvcmd; struct pci_dev *pci_dev; unsigned int features; @@ -1805,7 +1806,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) outb_p(inb_p(SMBAUXCTL(priv)) & ~(SMBAUXCTL_CRC | SMBAUXCTL_E32B), SMBAUXCTL(priv)); - /* Remember original Host Notify setting */ + /* Remember original Interrupt and Host Notify settings */ + priv->original_hstcnt = inb_p(SMBHSTCNT(priv)) & ~SMBHSTCNT_KILL; if (priv->features & FEATURE_HOST_NOTIFY) priv->original_slvcmd = inb_p(SMBSLVCMD(priv)); @@ -1869,6 +1871,7 @@ static void i801_remove(struct pci_dev *dev) { struct i801_priv *priv = pci_get_drvdata(dev); + outb_p(priv->original_hstcnt, SMBHSTCNT(priv)); i801_disable_host_notify(priv); i801_del_mux(priv); i2c_del_adapter(&priv->adapter); @@ -1892,6 +1895,7 @@ static void i801_shutdown(struct pci_dev *dev) struct i801_priv *priv = pci_get_drvdata(dev); /* Restore config registers to avoid hard hang on some systems */ + outb_p(priv->original_hstcnt, SMBHSTCNT(priv)); i801_disable_host_notify(priv); pci_write_config_byte(dev, SMBHSTCFG, priv->original_hstcfg); } @@ -1901,6 +1905,7 @@ static int i801_suspend(struct device *dev) { struct i801_priv *priv = dev_get_drvdata(dev); + outb_p(priv->original_hstcnt, SMBHSTCNT(priv)); pci_write_config_byte(priv->pci_dev, SMBHSTCFG, priv->original_hstcfg); return 0; } From 03a976c9afb5e3c4f8260c6c08a27d723b279c92 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Wed, 17 Nov 2021 11:45:09 +0200 Subject: [PATCH 193/358] i2c: i801: Fix interrupt storm from SMB_ALERT signal Currently interrupt storm will occur from i2c-i801 after first transaction if SMB_ALERT signal is enabled and ever asserted. It is enough if the signal is asserted once even before the driver is loaded and does not recover because that interrupt is not acknowledged. This fix aims to fix it by two ways: - Add acknowledging for the SMB_ALERT interrupt status - Disable the SMB_ALERT interrupt on platforms where possible since the driver currently does not make use for it Acknowledging resets the SMB_ALERT interrupt status on all platforms and also should help to avoid interrupt storm on older platforms where the SMB_ALERT interrupt disabling is not available. For simplicity this fix reuses the host notify feature for disabling and restoring original register value. Link: https://bugzilla.kernel.org/show_bug.cgi?id=177311 Reported-by: ck+kernelbugzilla@bl4ckb0x.de Reported-by: stephane.poignant@protonmail.com Signed-off-by: Jarkko Nikula Reviewed-by: Jean Delvare Tested-by: Jean Delvare Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-i801.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index ed271274250b19..41446f9cc52da9 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -191,6 +191,7 @@ #define SMBSLVSTS_HST_NTFY_STS BIT(0) /* Host Notify Command register bits */ +#define SMBSLVCMD_SMBALERT_DISABLE BIT(2) #define SMBSLVCMD_HST_NTFY_INTREN BIT(0) #define STATUS_ERROR_FLAGS (SMBHSTSTS_FAILED | SMBHSTSTS_BUS_ERR | \ @@ -642,12 +643,20 @@ static irqreturn_t i801_isr(int irq, void *dev_id) i801_isr_byte_done(priv); /* - * Clear irq sources and report transaction result. + * Clear remaining IRQ sources: Completion of last command, errors + * and the SMB_ALERT signal. SMB_ALERT status is set after signal + * assertion independently of the interrupt generation being blocked + * or not so clear it always when the status is set. + */ + status &= SMBHSTSTS_INTR | STATUS_ERROR_FLAGS | SMBHSTSTS_SMBALERT_STS; + if (status) + outb_p(status, SMBHSTSTS(priv)); + status &= ~SMBHSTSTS_SMBALERT_STS; /* SMB_ALERT not reported */ + /* + * Report transaction result. * ->status must be cleared before the next transaction is started. */ - status &= SMBHSTSTS_INTR | STATUS_ERROR_FLAGS; if (status) { - outb_p(status, SMBHSTSTS(priv)); priv->status = status; complete(&priv->done); } @@ -975,9 +984,13 @@ static void i801_enable_host_notify(struct i2c_adapter *adapter) if (!(priv->features & FEATURE_HOST_NOTIFY)) return; - if (!(SMBSLVCMD_HST_NTFY_INTREN & priv->original_slvcmd)) - outb_p(SMBSLVCMD_HST_NTFY_INTREN | priv->original_slvcmd, - SMBSLVCMD(priv)); + /* + * Enable host notify interrupt and block the generation of interrupt + * from the SMB_ALERT signal because the driver does not support + * SMBus Alert. + */ + outb_p(SMBSLVCMD_HST_NTFY_INTREN | SMBSLVCMD_SMBALERT_DISABLE | + priv->original_slvcmd, SMBSLVCMD(priv)); /* clear Host Notify bit to allow a new notification */ outb_p(SMBSLVSTS_HST_NTFY_STS, SMBSLVSTS(priv)); From aa5721a9e0c9fb8a4bdfe0c8751377cd537d6174 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 23 Nov 2021 10:10:17 +0100 Subject: [PATCH 194/358] USB: serial: pl2303: fix GC type detection At least some PL2303GC have a bcdDevice of 0x105 instead of 0x100 as the datasheet claims. Add it to the list of known release numbers for the HXN (G) type. Note the chip type could only be determined indirectly based on its package being of QFP type, which appears to only be available for PL2303GC. Fixes: 894758d0571d ("USB: serial: pl2303: tighten type HXN (G) detection") Cc: stable@vger.kernel.org # 5.13 Reported-by: Anton Lundin Link: https://lore.kernel.org/r/20211123071613.GZ108031@montezuma.acc.umu.se Link: https://lore.kernel.org/r/20211123091017.30708-1-johan@kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/pl2303.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index f45ca7ddf78eac..a70fd86f735ca8 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -432,6 +432,7 @@ static int pl2303_detect_type(struct usb_serial *serial) case 0x200: switch (bcdDevice) { case 0x100: + case 0x105: case 0x305: case 0x405: /* From 84e1d0bf1d7121759622dabf8fbef4c99ad597c5 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Thu, 11 Nov 2021 17:04:11 +0100 Subject: [PATCH 195/358] i2c: virtio: disable timeout handling If a timeout is hit, it can result is incorrect data on the I2C bus and/or memory corruptions in the guest since the device can still be operating on the buffers it was given while the guest has freed them. Here is, for example, the start of a slub_debug splat which was triggered on the next transfer after one transfer was forced to timeout by setting a breakpoint in the backend (rust-vmm/vhost-device): BUG kmalloc-1k (Not tainted): Poison overwritten First byte 0x1 instead of 0x6b Allocated in virtio_i2c_xfer+0x65/0x35c age=350 cpu=0 pid=29 __kmalloc+0xc2/0x1c9 virtio_i2c_xfer+0x65/0x35c __i2c_transfer+0x429/0x57d i2c_transfer+0x115/0x134 i2cdev_ioctl_rdwr+0x16a/0x1de i2cdev_ioctl+0x247/0x2ed vfs_ioctl+0x21/0x30 sys_ioctl+0xb18/0xb41 Freed in virtio_i2c_xfer+0x32e/0x35c age=244 cpu=0 pid=29 kfree+0x1bd/0x1cc virtio_i2c_xfer+0x32e/0x35c __i2c_transfer+0x429/0x57d i2c_transfer+0x115/0x134 i2cdev_ioctl_rdwr+0x16a/0x1de i2cdev_ioctl+0x247/0x2ed vfs_ioctl+0x21/0x30 sys_ioctl+0xb18/0xb41 There is no simple fix for this (the driver would have to always create bounce buffers and hold on to them until the device eventually returns the buffers), so just disable the timeout support for now. Fixes: 3cfc88380413d20f ("i2c: virtio: add a virtio i2c frontend driver") Acked-by: Jie Deng Signed-off-by: Vincent Whitchurch Acked-by: Michael S. Tsirkin Reviewed-by: Viresh Kumar Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-virtio.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c index 1ed4daa918a06d..95378780da6d6d 100644 --- a/drivers/i2c/busses/i2c-virtio.c +++ b/drivers/i2c/busses/i2c-virtio.c @@ -104,11 +104,10 @@ static int virtio_i2c_prepare_reqs(struct virtqueue *vq, static int virtio_i2c_complete_reqs(struct virtqueue *vq, struct virtio_i2c_req *reqs, - struct i2c_msg *msgs, int num, - bool timedout) + struct i2c_msg *msgs, int num) { struct virtio_i2c_req *req; - bool failed = timedout; + bool failed = false; unsigned int len; int i, j = 0; @@ -130,7 +129,7 @@ static int virtio_i2c_complete_reqs(struct virtqueue *vq, j++; } - return timedout ? -ETIMEDOUT : j; + return j; } static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, @@ -139,7 +138,6 @@ static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, struct virtio_i2c *vi = i2c_get_adapdata(adap); struct virtqueue *vq = vi->vq; struct virtio_i2c_req *reqs; - unsigned long time_left; int count; reqs = kcalloc(num, sizeof(*reqs), GFP_KERNEL); @@ -162,11 +160,9 @@ static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, reinit_completion(&vi->completion); virtqueue_kick(vq); - time_left = wait_for_completion_timeout(&vi->completion, adap->timeout); - if (!time_left) - dev_err(&adap->dev, "virtio i2c backend timeout.\n"); + wait_for_completion(&vi->completion); - count = virtio_i2c_complete_reqs(vq, reqs, msgs, count, !time_left); + count = virtio_i2c_complete_reqs(vq, reqs, msgs, count); err_free: kfree(reqs); From 5f719948b5d43eb39356e94e8d0b462568915381 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Mon, 15 Nov 2021 11:38:13 +0000 Subject: [PATCH 196/358] mmc: spi: Add device-tree SPI IDs Commit 5fa6863ba692 ("spi: Check we have a spi_device_id for each DT compatible") added a test to check that every SPI driver has a spi_device_id for each DT compatiable string defined by the driver and warns if the spi_device_id is missing. The spi_device_id is missing for the MMC SPI driver and the following warning is now seen. WARNING KERN SPI driver mmc_spi has no spi_device_id for mmc-spi-slot Fix this by adding the necessary spi_device_id. Signed-off-by: Jon Hunter Link: https://lore.kernel.org/r/20211115113813.238044-1-jonathanh@nvidia.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/mmc_spi.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index f4c8e1a61f5373..b431cdd27353b7 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1514,6 +1514,12 @@ static int mmc_spi_remove(struct spi_device *spi) return 0; } +static const struct spi_device_id mmc_spi_dev_ids[] = { + { "mmc-spi-slot"}, + { }, +}; +MODULE_DEVICE_TABLE(spi, mmc_spi_dev_ids); + static const struct of_device_id mmc_spi_of_match_table[] = { { .compatible = "mmc-spi-slot", }, {}, @@ -1525,6 +1531,7 @@ static struct spi_driver mmc_spi_driver = { .name = "mmc_spi", .of_match_table = mmc_spi_of_match_table, }, + .id_table = mmc_spi_dev_ids, .probe = mmc_spi_probe, .remove = mmc_spi_remove, }; From 16517829f2e02f096fb5ea9083d160381127faf3 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Tue, 23 Nov 2021 19:07:48 +0800 Subject: [PATCH 197/358] hamradio: fix macro redefine warning MIPS/IA64 define END as assembly function ending, which conflict with END definition in mkiss.c, just undef it at first Reported-by: lkp@intel.com Signed-off-by: Huang Pei Signed-off-by: David S. Miller --- drivers/net/hamradio/mkiss.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index e2b332b54f06d2..7da2bb8a443c02 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -31,6 +31,8 @@ #define AX_MTU 236 +/* some arch define END as assembly function ending, just undef it */ +#undef END /* SLIP/KISS protocol characters. */ #define END 0300 /* indicates end of frame */ #define ESC 0333 /* indicates byte stuffing */ From e5b40668e930979bd1e82c7ed7c9029db635f0e4 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Tue, 23 Nov 2021 19:07:49 +0800 Subject: [PATCH 198/358] slip: fix macro redefine warning MIPS/IA64 define END as assembly function ending, which conflict with END definition in slip.h, just undef it at first Reported-by: lkp@intel.com Signed-off-by: Huang Pei Signed-off-by: David S. Miller --- drivers/net/slip/slip.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/slip/slip.h b/drivers/net/slip/slip.h index c420e59485221d..3d7f88b330c1e0 100644 --- a/drivers/net/slip/slip.h +++ b/drivers/net/slip/slip.h @@ -40,6 +40,8 @@ insmod -oslip_maxdev=nnn */ #define SL_MTU 296 /* 296; I am used to 600- FvK */ +/* some arch define END as assembly function ending, just undef it */ +#undef END /* SLIP protocol characters. */ #define END 0300 /* indicates end of frame */ #define ESC 0333 /* indicates byte stuffing */ From 1c743127cc54b112b155f434756bd4b5fa565a99 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 23 Nov 2021 12:27:19 +0200 Subject: [PATCH 199/358] net: nexthop: fix null pointer dereference when IPv6 is not enabled When we try to add an IPv6 nexthop and IPv6 is not enabled (!CONFIG_IPV6) we'll hit a NULL pointer dereference[1] in the error path of nh_create_ipv6() due to calling ipv6_stub->fib6_nh_release. The bug has been present since the beginning of IPv6 nexthop gateway support. Commit 1aefd3de7bc6 ("ipv6: Add fib6_nh_init and release to stubs") tells us that only fib6_nh_init has a dummy stub because fib6_nh_release should not be called if fib6_nh_init returns an error, but the commit below added a call to ipv6_stub->fib6_nh_release in its error path. To fix it return the dummy stub's -EAFNOSUPPORT error directly without calling ipv6_stub->fib6_nh_release in nh_create_ipv6()'s error path. [1] Output is a bit truncated, but it clearly shows the error. BUG: kernel NULL pointer dereference, address: 000000000000000000 #PF: supervisor instruction fetch in kernel modede #PF: error_code(0x0010) - not-present pagege PGD 0 P4D 0 Oops: 0010 [#1] PREEMPT SMP NOPTI CPU: 4 PID: 638 Comm: ip Kdump: loaded Not tainted 5.16.0-rc1+ #446 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-4.fc34 04/01/2014 RIP: 0010:0x0 Code: Unable to access opcode bytes at RIP 0xffffffffffffffd6. RSP: 0018:ffff888109f5b8f0 EFLAGS: 00010286^Ac RAX: 0000000000000000 RBX: ffff888109f5ba28 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8881008a2860 RBP: ffff888109f5b9d8 R08: 0000000000000000 R09: 0000000000000000 R10: ffff888109f5b978 R11: ffff888109f5b948 R12: 00000000ffffff9f R13: ffff8881008a2a80 R14: ffff8881008a2860 R15: ffff8881008a2840 FS: 00007f98de70f100(0000) GS:ffff88822bf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 0000000100efc000 CR4: 00000000000006e0 Call Trace: nh_create_ipv6+0xed/0x10c rtm_new_nexthop+0x6d7/0x13f3 ? check_preemption_disabled+0x3d/0xf2 ? lock_is_held_type+0xbe/0xfd rtnetlink_rcv_msg+0x23f/0x26a ? check_preemption_disabled+0x3d/0xf2 ? rtnl_calcit.isra.0+0x147/0x147 netlink_rcv_skb+0x61/0xb2 netlink_unicast+0x100/0x187 netlink_sendmsg+0x37f/0x3a0 ? netlink_unicast+0x187/0x187 sock_sendmsg_nosec+0x67/0x9b ____sys_sendmsg+0x19d/0x1f9 ? copy_msghdr_from_user+0x4c/0x5e ? rcu_read_lock_any_held+0x2a/0x78 ___sys_sendmsg+0x6c/0x8c ? asm_sysvec_apic_timer_interrupt+0x12/0x20 ? lockdep_hardirqs_on+0xd9/0x102 ? sockfd_lookup_light+0x69/0x99 __sys_sendmsg+0x50/0x6e do_syscall_64+0xcb/0xf2 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f98dea28914 Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b5 0f 1f 80 00 00 00 00 48 8d 05 e9 5d 0c 00 8b 00 85 c0 75 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 41 54 41 89 d4 55 48 89 f5 53 RSP: 002b:00007fff859f5e68 EFLAGS: 00000246 ORIG_RAX: 000000000000002e2e RAX: ffffffffffffffda RBX: 00000000619cb810 RCX: 00007f98dea28914 RDX: 0000000000000000 RSI: 00007fff859f5ed0 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000008 R10: fffffffffffffce6 R11: 0000000000000246 R12: 0000000000000001 R13: 000055c0097ae520 R14: 000055c0097957fd R15: 00007fff859f63a0 Modules linked in: bridge stp llc bonding virtio_net Cc: stable@vger.kernel.org Fixes: 53010f991a9f ("nexthop: Add support for IPv6 gateways") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index a69a9e76f99fec..5dbd4b5505ebaa 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2565,11 +2565,15 @@ static int nh_create_ipv6(struct net *net, struct nexthop *nh, /* sets nh_dev if successful */ err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL, extack); - if (err) + if (err) { + /* IPv6 is not enabled, don't call fib6_nh_release */ + if (err == -EAFNOSUPPORT) + goto out; ipv6_stub->fib6_nh_release(fib6_nh); - else + } else { nh->nh_flags = fib6_nh->fib_nh_flags; - + } +out: return err; } From 45c3ff7a9ac195135536057021c1d3ac664f3f62 Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Tue, 23 Nov 2021 16:25:16 +0800 Subject: [PATCH 200/358] net/smc: Clean up local struct sock variables There remains some variables to replace with local struct sock. So clean them up all. Fixes: 3163c5071f25 ("net/smc: use local struct sock variables consistently") Signed-off-by: Tony Lu Reviewed-by: Wen Gu Signed-off-by: David S. Miller --- net/smc/smc_close.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 0f9ffba07d2685..9b235fbb089a47 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -354,9 +354,9 @@ static void smc_close_passive_work(struct work_struct *work) if (rxflags->peer_conn_abort) { /* peer has not received all data */ smc_close_passive_abort_received(smc); - release_sock(&smc->sk); + release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); - lock_sock(&smc->sk); + lock_sock(sk); goto wakeup; } From 606a63c9783a32a45bd2ef0eee393711d75b3284 Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Tue, 23 Nov 2021 16:25:18 +0800 Subject: [PATCH 201/358] net/smc: Ensure the active closing peer first closes clcsock The side that actively closed socket, it's clcsock doesn't enter TIME_WAIT state, but the passive side does it. It should show the same behavior as TCP sockets. Consider this, when client actively closes the socket, the clcsock in server enters TIME_WAIT state, which means the address is occupied and won't be reused before TIME_WAIT dismissing. If we restarted server, the service would be unavailable for a long time. To solve this issue, shutdown the clcsock in [A], perform the TCP active close progress first, before the passive closed side closing it. So that the actively closed side enters TIME_WAIT, not the passive one. Client | Server close() // client actively close | smc_release() | smc_close_active() // PEERCLOSEWAIT1 | smc_close_final() // abort or closed = 1| smc_cdc_get_slot_and_msg_send() | [A] | |smc_cdc_msg_recv_action() // ACTIVE | queue_work(smc_close_wq, &conn->close_work) | smc_close_passive_work() // PROCESSABORT or APPCLOSEWAIT1 | smc_close_passive_abort_received() // only in abort | |close() // server recv zero, close | smc_release() // PROCESSABORT or APPCLOSEWAIT1 | smc_close_active() | smc_close_abort() or smc_close_final() // CLOSED | smc_cdc_get_slot_and_msg_send() // abort or closed = 1 smc_cdc_msg_recv_action() | smc_clcsock_release() queue_work(smc_close_wq, &conn->close_work) | sock_release(tcp) // actively close clc, enter TIME_WAIT smc_close_passive_work() // PEERCLOSEWAIT1 | smc_conn_free() smc_close_passive_abort_received() // CLOSED| smc_conn_free() | smc_clcsock_release() | sock_release(tcp) // passive close clc | Link: https://www.spinics.net/lists/netdev/msg780407.html Fixes: b38d732477e4 ("smc: socket closing and linkgroup cleanup") Signed-off-by: Tony Lu Reviewed-by: Wen Gu Signed-off-by: David S. Miller --- net/smc/smc_close.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 9b235fbb089a47..3715d2f5ad555c 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -228,6 +228,12 @@ int smc_close_active(struct smc_sock *smc) /* send close request */ rc = smc_close_final(conn); sk->sk_state = SMC_PEERCLOSEWAIT1; + + /* actively shutdown clcsock before peer close it, + * prevent peer from entering TIME_WAIT state. + */ + if (smc->clcsock && smc->clcsock->sk) + rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } else { /* peer event has changed the state */ goto again; From ce4995bc6c8eec9685707e36c3f38aea3c8694fa Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 23 Nov 2021 09:52:55 +0200 Subject: [PATCH 202/358] mlxsw: spectrum: Allow driver to load with old firmware versions The driver fails to load with old firmware versions that cannot report the maximum number of RIF MAC profiles [1]. Fix this by defaulting to a maximum of a single profile in such situations, as multiple profiles are not supported by old firmware versions. [1] mlxsw_spectrum 0000:03:00.0: cannot register bus device mlxsw_spectrum: probe of 0000:03:00.0 failed with error -5 Fixes: 1c375ffb2efab ("mlxsw: spectrum_router: Expose RIF MAC profiles to devlink resource") Signed-off-by: Danielle Ratson Reported-by: Vadim Pasternak Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 5925db386b1ba5..738ee3b0d3c344 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3290,10 +3290,10 @@ mlxsw_sp_resources_rif_mac_profile_register(struct mlxsw_core *mlxsw_core) u8 max_rif_mac_profiles; if (!MLXSW_CORE_RES_VALID(mlxsw_core, MAX_RIF_MAC_PROFILES)) - return -EIO; - - max_rif_mac_profiles = MLXSW_CORE_RES_GET(mlxsw_core, - MAX_RIF_MAC_PROFILES); + max_rif_mac_profiles = 1; + else + max_rif_mac_profiles = MLXSW_CORE_RES_GET(mlxsw_core, + MAX_RIF_MAC_PROFILES); devlink_resource_size_params_init(&size_params, max_rif_mac_profiles, max_rif_mac_profiles, 1, DEVLINK_RESOURCE_UNIT_ENTRY); From 63b08b1f6834bbb0b4f7783bf63b80c8c8e9a047 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Tue, 23 Nov 2021 09:52:56 +0200 Subject: [PATCH 203/358] mlxsw: spectrum: Protect driver from buggy firmware When processing port up/down events generated by the device's firmware, the driver protects itself from events reported for non-existent local ports, but not the CPU port (local port 0), which exists, but lacks a netdev. This can result in a NULL pointer dereference when calling netif_carrier_{on,off}(). Fix this by bailing early when processing an event reported for the CPU port. Problem was only observed when running on top of a buggy emulator. Fixes: 28b1987ef506 ("mlxsw: spectrum: Register CPU port with devlink") Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 738ee3b0d3c344..03e5bad4e405fe 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2153,7 +2153,7 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, max_ports = mlxsw_core_max_ports(mlxsw_sp->core); local_port = mlxsw_reg_pude_local_port_get(pude_pl); - if (WARN_ON_ONCE(local_port >= max_ports)) + if (WARN_ON_ONCE(!local_port || local_port >= max_ports)) return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) From bed68f4f4db429a0bf544887e64dc710e5a690ea Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 15 Nov 2021 12:08:18 +0100 Subject: [PATCH 204/358] docs: i2c: smbus-protocol: mention the repeated start condition Sr is a repeated start, it is used in both I2C and SMBus protocols. Provide its description and replace start ("S") conditions with repeated start ("Sr") conditions when relevant. This allows the documentation to match the SMBus specification available at [1]. [1] http://www.smbus.org/specs/SMBus_3_1_20180319.pdf Signed-off-by: Miquel Raynal Signed-off-by: Wolfram Sang --- Documentation/i2c/smbus-protocol.rst | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/Documentation/i2c/smbus-protocol.rst b/Documentation/i2c/smbus-protocol.rst index 9e07e6bbe6a392..00d8e17d0acabc 100644 --- a/Documentation/i2c/smbus-protocol.rst +++ b/Documentation/i2c/smbus-protocol.rst @@ -36,6 +36,8 @@ Key to symbols =============== ============================================================= S Start condition +Sr Repeated start condition, used to switch from write to + read mode. P Stop condition Rd/Wr (1 bit) Read/Write bit. Rd equals 1, Wr equals 0. A, NA (1 bit) Acknowledge (ACK) and Not Acknowledge (NACK) bit @@ -100,7 +102,7 @@ Implemented by i2c_smbus_read_byte_data() This reads a single byte from a device, from a designated register. The register is specified through the Comm byte:: - S Addr Wr [A] Comm [A] S Addr Rd [A] [Data] NA P + S Addr Wr [A] Comm [A] Sr Addr Rd [A] [Data] NA P Functionality flag: I2C_FUNC_SMBUS_READ_BYTE_DATA @@ -114,7 +116,7 @@ This operation is very like Read Byte; again, data is read from a device, from a designated register that is specified through the Comm byte. But this time, the data is a complete word (16 bits):: - S Addr Wr [A] Comm [A] S Addr Rd [A] [DataLow] A [DataHigh] NA P + S Addr Wr [A] Comm [A] Sr Addr Rd [A] [DataLow] A [DataHigh] NA P Functionality flag: I2C_FUNC_SMBUS_READ_WORD_DATA @@ -164,7 +166,7 @@ This command selects a device register (through the Comm byte), sends 16 bits of data to it, and reads 16 bits of data in return:: S Addr Wr [A] Comm [A] DataLow [A] DataHigh [A] - S Addr Rd [A] [DataLow] A [DataHigh] NA P + Sr Addr Rd [A] [DataLow] A [DataHigh] NA P Functionality flag: I2C_FUNC_SMBUS_PROC_CALL @@ -181,7 +183,7 @@ of data is specified by the device in the Count byte. :: S Addr Wr [A] Comm [A] - S Addr Rd [A] [Count] A [Data] A [Data] A ... A [Data] NA P + Sr Addr Rd [A] [Count] A [Data] A [Data] A ... A [Data] NA P Functionality flag: I2C_FUNC_SMBUS_READ_BLOCK_DATA @@ -212,7 +214,7 @@ This command selects a device register (through the Comm byte), sends 1 to 31 bytes of data to it, and reads 1 to 31 bytes of data in return:: S Addr Wr [A] Comm [A] Count [A] Data [A] ... - S Addr Rd [A] [Count] A [Data] ... A P + Sr Addr Rd [A] [Count] A [Data] ... A P Functionality flag: I2C_FUNC_SMBUS_BLOCK_PROC_CALL @@ -300,7 +302,7 @@ This command reads a block of bytes from a device, from a designated register that is specified through the Comm byte:: S Addr Wr [A] Comm [A] - S Addr Rd [A] [Data] A [Data] A ... A [Data] NA P + Sr Addr Rd [A] [Data] A [Data] A ... A [Data] NA P Functionality flag: I2C_FUNC_SMBUS_READ_I2C_BLOCK From 33a153100bb3459479bd95d3259c2915b53fefa8 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 22 Nov 2021 18:15:54 -0600 Subject: [PATCH 205/358] net: ipa: directly disable ipa-setup-ready interrupt We currently maintain a "disabled" Boolean flag to determine whether the "ipa-setup-ready" SMP2P IRQ handler does anything. That flag must be accessed under protection of a mutex. Instead, disable the SMP2P interrupt when requested, which prevents the interrupt handler from ever being called. More importantly, it synchronizes a thread disabling the interrupt with the completion of the interrupt handler in case they run concurrently. Use the IPA setup_complete flag rather than the disabled flag in the handler to determine whether to ignore any interrupts arriving after the first. Rename the "disabled" flag to be "setup_disabled", to be specific about its purpose. Fixes: 530f9216a953 ("soc: qcom: ipa: AP/modem communications") Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- drivers/net/ipa/ipa_smp2p.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index df7639c39d7160..24bc112a072c60 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -53,7 +53,7 @@ * @setup_ready_irq: IPA interrupt triggered by modem to signal GSI ready * @power_on: Whether IPA power is on * @notified: Whether modem has been notified of power state - * @disabled: Whether setup ready interrupt handling is disabled + * @setup_disabled: Whether setup ready interrupt handler is disabled * @mutex: Mutex protecting ready-interrupt/shutdown interlock * @panic_notifier: Panic notifier structure */ @@ -67,7 +67,7 @@ struct ipa_smp2p { u32 setup_ready_irq; bool power_on; bool notified; - bool disabled; + bool setup_disabled; struct mutex mutex; struct notifier_block panic_notifier; }; @@ -155,11 +155,9 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id) struct device *dev; int ret; - mutex_lock(&smp2p->mutex); - - if (smp2p->disabled) - goto out_mutex_unlock; - smp2p->disabled = true; /* If any others arrive, ignore them */ + /* Ignore any (spurious) interrupts received after the first */ + if (smp2p->ipa->setup_complete) + return IRQ_HANDLED; /* Power needs to be active for setup */ dev = &smp2p->ipa->pdev->dev; @@ -176,8 +174,6 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id) out_power_put: pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); -out_mutex_unlock: - mutex_unlock(&smp2p->mutex); return IRQ_HANDLED; } @@ -322,7 +318,10 @@ void ipa_smp2p_disable(struct ipa *ipa) mutex_lock(&smp2p->mutex); - smp2p->disabled = true; + if (!smp2p->setup_disabled) { + disable_irq(smp2p->setup_ready_irq); + smp2p->setup_disabled = true; + } mutex_unlock(&smp2p->mutex); } From 8afc7e471ad3c92a9c96adc62d1b67de77378bb6 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 22 Nov 2021 18:15:55 -0600 Subject: [PATCH 206/358] net: ipa: separate disabling setup from modem stop The IPA setup_complete flag is set at the end of ipa_setup(), when the setup phase of initialization has completed successfully. This occurs as part of driver probe processing, or (if "modem-init" is specified in the DTS file) it is triggered by the "ipa-setup-ready" SMP2P interrupt generated by the modem. In the latter case, it's possible for driver shutdown (or remove) to begin while setup processing is underway, and this can't be allowed. The problem is that the setup_complete flag is not adequate to signal that setup is underway. If setup_complete is set, it will never be un-set, so that case is not a problem. But if setup_complete is false, there's a chance setup is underway. Because setup is triggered by an interrupt on a "modem-init" system, there is a simple way to ensure the value of setup_complete is safe to read. The threaded handler--if it is executing--will complete as part of a request to disable the "ipa-modem-ready" interrupt. This means that ipa_setup() (which is called from the handler) will run to completion if it was underway, or will never be called otherwise. The request to disable the "ipa-setup-ready" interrupt is currently made within ipa_modem_stop(). Instead, disable the interrupt outside that function in the two places it's called. In the case of ipa_remove(), this ensures the setup_complete flag is safe to read before we read it. Rename ipa_smp2p_disable() to be ipa_smp2p_irq_disable_setup(), to be more specific about its effect. Fixes: 530f9216a953 ("soc: qcom: ipa: AP/modem communications") Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- drivers/net/ipa/ipa_main.c | 6 ++++++ drivers/net/ipa/ipa_modem.c | 6 +++--- drivers/net/ipa/ipa_smp2p.c | 2 +- drivers/net/ipa/ipa_smp2p.h | 7 +++---- 4 files changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index cdfa98a76e1f4a..a448ec198bee18 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -28,6 +28,7 @@ #include "ipa_reg.h" #include "ipa_mem.h" #include "ipa_table.h" +#include "ipa_smp2p.h" #include "ipa_modem.h" #include "ipa_uc.h" #include "ipa_interrupt.h" @@ -801,6 +802,11 @@ static int ipa_remove(struct platform_device *pdev) struct device *dev = &pdev->dev; int ret; + /* Prevent the modem from triggering a call to ipa_setup(). This + * also ensures a modem-initiated setup that's underway completes. + */ + ipa_smp2p_irq_disable_setup(ipa); + ret = pm_runtime_get_sync(dev); if (WARN_ON(ret < 0)) goto out_power_put; diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c index ad116bcc0580e8..d0ab4d70c303b0 100644 --- a/drivers/net/ipa/ipa_modem.c +++ b/drivers/net/ipa/ipa_modem.c @@ -339,9 +339,6 @@ int ipa_modem_stop(struct ipa *ipa) if (state != IPA_MODEM_STATE_RUNNING) return -EBUSY; - /* Prevent the modem from triggering a call to ipa_setup() */ - ipa_smp2p_disable(ipa); - /* Clean up the netdev and endpoints if it was started */ if (netdev) { struct ipa_priv *priv = netdev_priv(netdev); @@ -369,6 +366,9 @@ static void ipa_modem_crashed(struct ipa *ipa) struct device *dev = &ipa->pdev->dev; int ret; + /* Prevent the modem from triggering a call to ipa_setup() */ + ipa_smp2p_irq_disable_setup(ipa); + ret = pm_runtime_get_sync(dev); if (ret < 0) { dev_err(dev, "error %d getting power to handle crash\n", ret); diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index 24bc112a072c60..2112336120391c 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -309,7 +309,7 @@ void ipa_smp2p_exit(struct ipa *ipa) kfree(smp2p); } -void ipa_smp2p_disable(struct ipa *ipa) +void ipa_smp2p_irq_disable_setup(struct ipa *ipa) { struct ipa_smp2p *smp2p = ipa->smp2p; diff --git a/drivers/net/ipa/ipa_smp2p.h b/drivers/net/ipa/ipa_smp2p.h index 99a9567896388b..59cee31a738365 100644 --- a/drivers/net/ipa/ipa_smp2p.h +++ b/drivers/net/ipa/ipa_smp2p.h @@ -27,13 +27,12 @@ int ipa_smp2p_init(struct ipa *ipa, bool modem_init); void ipa_smp2p_exit(struct ipa *ipa); /** - * ipa_smp2p_disable() - Prevent "ipa-setup-ready" interrupt handling + * ipa_smp2p_irq_disable_setup() - Disable the "setup ready" interrupt * @ipa: IPA pointer * - * Prevent handling of the "setup ready" interrupt from the modem. - * This is used before initiating shutdown of the driver. + * Disable the "ipa-setup-ready" interrupt from the modem. */ -void ipa_smp2p_disable(struct ipa *ipa); +void ipa_smp2p_irq_disable_setup(struct ipa *ipa); /** * ipa_smp2p_notify_reset() - Reset modem notification state From c75a9ad43691de040bead75f1924928111571f9c Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 22 Nov 2021 22:35:33 +0100 Subject: [PATCH 207/358] r8169: fix incorrect mac address assignment The original changes brakes MAC address assignment on older chip versions (see bug report [0]), and it brakes random MAC assignment. is_valid_ether_addr() requires that its argument is word-aligned. Add the missing alignment to array mac_addr. [0] https://bugzilla.kernel.org/show_bug.cgi?id=215087 Fixes: 1c5d09d58748 ("ethernet: r8169: use eth_hw_addr_set()") Reported-by: Richard Herbert Tested-by: Richard Herbert Signed-off-by: Heiner Kallweit Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index bbe21db204172d..86c44bc5f73f8b 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5217,8 +5217,8 @@ static int rtl_get_ether_clk(struct rtl8169_private *tp) static void rtl_init_mac_address(struct rtl8169_private *tp) { + u8 mac_addr[ETH_ALEN] __aligned(2) = {}; struct net_device *dev = tp->dev; - u8 mac_addr[ETH_ALEN]; int rc; rc = eth_platform_get_mac_address(tp_to_dev(tp), mac_addr); @@ -5233,7 +5233,8 @@ static void rtl_init_mac_address(struct rtl8169_private *tp) if (is_valid_ether_addr(mac_addr)) goto done; - eth_hw_addr_random(dev); + eth_random_addr(mac_addr); + dev->addr_assign_type = NET_ADDR_RANDOM; dev_warn(tp_to_dev(tp), "can't read MAC address, setting random one\n"); done: eth_hw_addr_set(dev, mac_addr); From b82d71c0f84a2e5ccaaa7571dfd5c69e0e2cfb4a Mon Sep 17 00:00:00 2001 From: Zheyu Ma Date: Tue, 23 Nov 2021 02:21:50 +0000 Subject: [PATCH 208/358] net: chelsio: cxgb4vf: Fix an error code in cxgb4vf_pci_probe() During the process of driver probing, probe function should return < 0 for failure, otherwise kernel will treat value == 0 as success. Therefore, we should set err to -EINVAL when adapter->registered_device_map is NULL. Otherwise kernel will assume that driver has been successfully probed and will cause unexpected errors. Signed-off-by: Zheyu Ma Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 64479c464b4ec5..ae9cca768d748a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -3196,6 +3196,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, } if (adapter->registered_device_map == 0) { dev_err(&pdev->dev, "could not register any net devices\n"); + err = -EINVAL; goto err_disable_interrupts; } From a049a30fc27c1cb2e12889bbdbd463dbf750103a Mon Sep 17 00:00:00 2001 From: Martyn Welch Date: Mon, 22 Nov 2021 18:44:45 +0000 Subject: [PATCH 209/358] net: usb: Correct PHY handling of smsc95xx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The smsc95xx driver is dropping phy speed settings and causing a stack trace at device unbind: [  536.379147] smsc95xx 2-1:1.0 eth1: unregister 'smsc95xx' usb-ci_hdrc.2-1, smsc95xx USB 2.0 Ethernet [  536.425029] ------------[ cut here ]------------ [  536.429650] WARNING: CPU: 0 PID: 439 at fs/kernfs/dir.c:1535 kernfs_remove_by_name_ns+0xb8/0xc0 [  536.438416] kernfs: can not remove 'attached_dev', no directory [  536.444363] Modules linked in: xts dm_crypt dm_mod atmel_mxt_ts smsc95xx usbnet [  536.451748] CPU: 0 PID: 439 Comm: sh Tainted: G        W         5.15.0 #1 [  536.458636] Hardware name: Freescale i.MX53 (Device Tree Support) [  536.464735] Backtrace:  [  536.467190] [<80b1c904>] (dump_backtrace) from [<80b1cb48>] (show_stack+0x20/0x24) [  536.474787]  r7:000005ff r6:8035b294 r5:600f0013 r4:80d8af78 [  536.480449] [<80b1cb28>] (show_stack) from [<80b1f764>] (dump_stack_lvl+0x48/0x54) [  536.488035] [<80b1f71c>] (dump_stack_lvl) from [<80b1f788>] (dump_stack+0x18/0x1c) [  536.495620]  r5:00000009 r4:80d9b820 [  536.499198] [<80b1f770>] (dump_stack) from [<80124fac>] (__warn+0xfc/0x114) [  536.506187] [<80124eb0>] (__warn) from [<80b1d21c>] (warn_slowpath_fmt+0xa8/0xdc) [  536.513688]  r7:000005ff r6:80d9b820 r5:80d9b8e0 r4:83744000 [  536.519349] [<80b1d178>] (warn_slowpath_fmt) from [<8035b294>] (kernfs_remove_by_name_ns+0xb8/0xc0) [  536.528416]  r9:00000001 r8:00000000 r7:824926dc r6:00000000 r5:80df6c2c r4:00000000 [  536.536162] [<8035b1dc>] (kernfs_remove_by_name_ns) from [<80b1f56c>] (sysfs_remove_link+0x4c/0x50) [  536.545225]  r6:7f00f02c r5:80df6c2c r4:83306400 [  536.549845] [<80b1f520>] (sysfs_remove_link) from [<806f9c8c>] (phy_detach+0xfc/0x11c) [  536.557780]  r5:82492000 r4:83306400 [  536.561359] [<806f9b90>] (phy_detach) from [<806f9cf8>] (phy_disconnect+0x4c/0x58) [  536.568943]  r7:824926dc r6:7f00f02c r5:82492580 r4:83306400 [  536.574604] [<806f9cac>] (phy_disconnect) from [<7f00a310>] (smsc95xx_disconnect_phy+0x30/0x38 [smsc95xx]) [  536.584290]  r5:82492580 r4:82492580 [  536.587868] [<7f00a2e0>] (smsc95xx_disconnect_phy [smsc95xx]) from [<7f001570>] (usbnet_stop+0x70/0x1a0 [usbnet]) [  536.598161]  r5:82492580 r4:82492000 [  536.601740] [<7f001500>] (usbnet_stop [usbnet]) from [<808baa70>] (__dev_close_many+0xb4/0x12c) [  536.610466]  r8:83744000 r7:00000000 r6:83744000 r5:83745b74 r4:82492000 [  536.617170] [<808ba9bc>] (__dev_close_many) from [<808bab78>] (dev_close_many+0x90/0x120) [  536.625365]  r7:00000001 r6:83745b74 r5:83745b8c r4:82492000 [  536.631026] [<808baae8>] (dev_close_many) from [<808bf408>] (unregister_netdevice_many+0x15c/0x704) [  536.640094]  r9:00000001 r8:81130b98 r7:83745b74 r6:83745bc4 r5:83745b8c r4:82492000 [  536.647840] [<808bf2ac>] (unregister_netdevice_many) from [<808bfa50>] (unregister_netdevice_queue+0xa0/0xe8) [  536.657775]  r10:8112bcc0 r9:83306c00 r8:83306c80 r7:8291e420 r6:83744000 r5:00000000 [  536.665608]  r4:82492000 [  536.668143] [<808bf9b0>] (unregister_netdevice_queue) from [<808bfac0>] (unregister_netdev+0x28/0x30) [  536.677381]  r6:7f01003c r5:82492000 r4:82492000 [  536.682000] [<808bfa98>] (unregister_netdev) from [<7f000b40>] (usbnet_disconnect+0x64/0xdc [usbnet]) [  536.691241]  r5:82492000 r4:82492580 [  536.694819] [<7f000adc>] (usbnet_disconnect [usbnet]) from [<8076b958>] (usb_unbind_interface+0x80/0x248) [  536.704406]  r5:7f01003c r4:83306c80 [  536.707984] [<8076b8d8>] (usb_unbind_interface) from [<8061765c>] (device_release_driver_internal+0x1c4/0x1cc) [  536.718005]  r10:8112bcc0 r9:80dff1dc r8:83306c80 r7:83744000 r6:7f01003c r5:00000000 [  536.725838]  r4:8291e420 [  536.728373] [<80617498>] (device_release_driver_internal) from [<80617684>] (device_release_driver+0x20/0x24) [  536.738302]  r7:83744000 r6:810d4f4c r5:8291e420 r4:8176ae30 [  536.743963] [<80617664>] (device_release_driver) from [<806156cc>] (bus_remove_device+0xf0/0x148) [  536.752858] [<806155dc>] (bus_remove_device) from [<80610018>] (device_del+0x198/0x41c) [  536.760880]  r7:83744000 r6:8116e2e4 r5:8291e464 r4:8291e420 [  536.766542] [<8060fe80>] (device_del) from [<80768fe8>] (usb_disable_device+0xcc/0x1e0) [  536.774576]  r10:8112bcc0 r9:80dff1dc r8:00000001 r7:8112bc48 r6:8291e400 r5:00000001 [  536.782410]  r4:83306c00 [  536.784945] [<80768f1c>] (usb_disable_device) from [<80769c30>] (usb_set_configuration+0x514/0x8dc) [  536.794011]  r10:00000000 r9:00000000 r8:832c3600 r7:00000004 r6:810d5688 r5:00000000 [  536.801844]  r4:83306c00 [  536.804379] [<8076971c>] (usb_set_configuration) from [<80775fac>] (usb_generic_driver_disconnect+0x34/0x38) [  536.814236]  r10:832c3610 r9:83745ef8 r8:832c3600 r7:00000004 r6:810d5688 r5:83306c00 [  536.822069]  r4:83306c00 [  536.824605] [<80775f78>] (usb_generic_driver_disconnect) from [<8076b850>] (usb_unbind_device+0x30/0x70) [  536.834100]  r5:83306c00 r4:810d5688 [  536.837678] [<8076b820>] (usb_unbind_device) from [<8061765c>] (device_release_driver_internal+0x1c4/0x1cc) [  536.847432]  r5:822fb480 r4:83306c80 [  536.851009] [<80617498>] (device_release_driver_internal) from [<806176a8>] (device_driver_detach+0x20/0x24) [  536.860853]  r7:00000004 r6:810d4f4c r5:810d5688 r4:83306c80 [  536.866515] [<80617688>] (device_driver_detach) from [<80614d98>] (unbind_store+0x70/0xe4) [  536.874793] [<80614d28>] (unbind_store) from [<80614118>] (drv_attr_store+0x30/0x3c) [  536.882554]  r7:00000000 r6:00000000 r5:83739200 r4:80614d28 [  536.888217] [<806140e8>] (drv_attr_store) from [<8035cb68>] (sysfs_kf_write+0x48/0x54) [  536.896154]  r5:83739200 r4:806140e8 [  536.899732] [<8035cb20>] (sysfs_kf_write) from [<8035be84>] (kernfs_fop_write_iter+0x11c/0x1d4) [  536.908446]  r5:83739200 r4:00000004 [  536.912024] [<8035bd68>] (kernfs_fop_write_iter) from [<802b87fc>] (vfs_write+0x258/0x3e4) [  536.920317]  r10:00000000 r9:83745f58 r8:83744000 r7:00000000 r6:00000004 r5:00000000 [  536.928151]  r4:82adacc0 [  536.930687] [<802b85a4>] (vfs_write) from [<802b8b0c>] (ksys_write+0x74/0xf4) [  536.937842]  r10:00000004 r9:007767a0 r8:83744000 r7:00000000 r6:00000000 r5:82adacc0 [  536.945676]  r4:82adacc0 [  536.948213] [<802b8a98>] (ksys_write) from [<802b8ba4>] (sys_write+0x18/0x1c) [  536.955367]  r10:00000004 r9:83744000 r8:80100244 r7:00000004 r6:76f47b58 r5:76fc0350 [  536.963200]  r4:00000004 [  536.965735] [<802b8b8c>] (sys_write) from [<80100060>] (ret_fast_syscall+0x0/0x48) [  536.973320] Exception stack(0x83745fa8 to 0x83745ff0) [  536.978383] 5fa0:                   00000004 76fc0350 00000001 007767a0 00000004 00000000 [  536.986569] 5fc0: 00000004 76fc0350 76f47b58 00000004 76f47c7c 76f48114 00000000 7e87991c [  536.994753] 5fe0: 00000498 7e879908 76e6dce8 76eca2e8 [  536.999922] ---[ end trace 9b835d809816b435 ]--- The driver should not be connecting and disconnecting the PHY when the device is opened and closed, it should be stopping and starting the PHY. The phy should be connected as part of binding and disconnected during unbinding. As this results in the PHY not being reset during open, link speed, etc. settings set prior to the link coming up are now not being lost. It is necessary for phy_stop() to only be called when the phydev still exists (resolving the above stack trace). When unbinding, ".unbind" will be called prior to ".stop", with phy_disconnect() already having called phy_stop() before the phydev becomes inaccessible. Signed-off-by: Martyn Welch Cc: Steve Glendinning Cc: UNGLinuxDriver@microchip.com Cc: "David S. Miller" Cc: Jakub Kicinski Cc: stable@kernel.org # v5.15 Signed-off-by: David S. Miller --- drivers/net/usb/smsc95xx.c | 55 ++++++++++++++++++-------------------- 1 file changed, 26 insertions(+), 29 deletions(-) diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 20fe4cd8f7840c..abe0149ed917a5 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1050,6 +1050,14 @@ static const struct net_device_ops smsc95xx_netdev_ops = { .ndo_set_features = smsc95xx_set_features, }; +static void smsc95xx_handle_link_change(struct net_device *net) +{ + struct usbnet *dev = netdev_priv(net); + + phy_print_status(net->phydev); + usbnet_defer_kevent(dev, EVENT_LINK_CHANGE); +} + static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) { struct smsc95xx_priv *pdata; @@ -1154,6 +1162,17 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->min_mtu = ETH_MIN_MTU; dev->net->max_mtu = ETH_DATA_LEN; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; + + ret = phy_connect_direct(dev->net, pdata->phydev, + &smsc95xx_handle_link_change, + PHY_INTERFACE_MODE_MII); + if (ret) { + netdev_err(dev->net, "can't attach PHY to %s\n", pdata->mdiobus->id); + goto unregister_mdio; + } + + phy_attached_info(dev->net->phydev); + return 0; unregister_mdio: @@ -1171,47 +1190,25 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) { struct smsc95xx_priv *pdata = dev->driver_priv; + phy_disconnect(dev->net->phydev); mdiobus_unregister(pdata->mdiobus); mdiobus_free(pdata->mdiobus); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); } -static void smsc95xx_handle_link_change(struct net_device *net) -{ - struct usbnet *dev = netdev_priv(net); - - phy_print_status(net->phydev); - usbnet_defer_kevent(dev, EVENT_LINK_CHANGE); -} - static int smsc95xx_start_phy(struct usbnet *dev) { - struct smsc95xx_priv *pdata = dev->driver_priv; - struct net_device *net = dev->net; - int ret; + phy_start(dev->net->phydev); - ret = smsc95xx_reset(dev); - if (ret < 0) - return ret; - - ret = phy_connect_direct(net, pdata->phydev, - &smsc95xx_handle_link_change, - PHY_INTERFACE_MODE_MII); - if (ret) { - netdev_err(net, "can't attach PHY to %s\n", pdata->mdiobus->id); - return ret; - } - - phy_attached_info(net->phydev); - phy_start(net->phydev); return 0; } -static int smsc95xx_disconnect_phy(struct usbnet *dev) +static int smsc95xx_stop(struct usbnet *dev) { - phy_stop(dev->net->phydev); - phy_disconnect(dev->net->phydev); + if (dev->net->phydev) + phy_stop(dev->net->phydev); + return 0; } @@ -1966,7 +1963,7 @@ static const struct driver_info smsc95xx_info = { .unbind = smsc95xx_unbind, .link_reset = smsc95xx_link_reset, .reset = smsc95xx_start_phy, - .stop = smsc95xx_disconnect_phy, + .stop = smsc95xx_stop, .rx_fixup = smsc95xx_rx_fixup, .tx_fixup = smsc95xx_tx_fixup, .status = smsc95xx_status, From e4e9bfb7c93d7e78aa4ad7e1c411a8df15386062 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 22 Nov 2021 19:16:40 -0600 Subject: [PATCH 210/358] net: ipa: kill ipa_cmd_pipeline_clear() Calling ipa_cmd_pipeline_clear() after stopping the channel underlying the AP<-modem RX endpoint can lead to a deadlock. This occurs in the ->runtime_suspend device power operation for the IPA driver. While this callback is in progress, any other requests for power will block until the callback returns. Stopping the AP<-modem RX channel does not prevent the modem from sending another packet to this endpoint. If a packet arrives for an RX channel when the channel is stopped, an SUSPEND IPA interrupt condition will be pending. Handling an IPA interrupt requires power, so ipa_isr_thread() calls pm_runtime_get_sync() first thing. The problem occurs because a "pipeline clear" command will not complete while such a SUSPEND interrupt condition exists. So the SUSPEND IPA interrupt handler won't proceed until it gets power; that won't happen until the ->runtime_suspend callback (and its "pipeline clear" command) completes; and that can't happen while the SUSPEND interrupt condition exists. It turns out that in this case there is no need to use the "pipeline clear" command. There are scenarios in which clearing the pipeline is required while suspending, but those are not (yet) supported upstream. So a simple fix, avoiding the potential deadlock, is to stop calling ipa_cmd_pipeline_clear() in ipa_endpoint_suspend(). This removes the only user of ipa_cmd_pipeline_clear(), so get rid of that function. It can be restored again whenever it's needed. This is basically a manual revert along with an explanation for commit 6cb63ea6a39ea ("net: ipa: introduce ipa_cmd_tag_process()"). Fixes: 6cb63ea6a39ea ("net: ipa: introduce ipa_cmd_tag_process()") Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- drivers/net/ipa/ipa_cmd.c | 16 ---------------- drivers/net/ipa/ipa_cmd.h | 6 ------ drivers/net/ipa/ipa_endpoint.c | 2 -- 3 files changed, 24 deletions(-) diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index cff51731195aa4..d57472ea077f2d 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -661,22 +661,6 @@ void ipa_cmd_pipeline_clear_wait(struct ipa *ipa) wait_for_completion(&ipa->completion); } -void ipa_cmd_pipeline_clear(struct ipa *ipa) -{ - u32 count = ipa_cmd_pipeline_clear_count(); - struct gsi_trans *trans; - - trans = ipa_cmd_trans_alloc(ipa, count); - if (trans) { - ipa_cmd_pipeline_clear_add(trans); - gsi_trans_commit_wait(trans); - ipa_cmd_pipeline_clear_wait(ipa); - } else { - dev_err(&ipa->pdev->dev, - "error allocating %u entry tag transaction\n", count); - } -} - static struct ipa_cmd_info * ipa_cmd_info_alloc(struct ipa_endpoint *endpoint, u32 tre_count) { diff --git a/drivers/net/ipa/ipa_cmd.h b/drivers/net/ipa/ipa_cmd.h index 69cd085d427dbf..05ed7e42e18420 100644 --- a/drivers/net/ipa/ipa_cmd.h +++ b/drivers/net/ipa/ipa_cmd.h @@ -163,12 +163,6 @@ u32 ipa_cmd_pipeline_clear_count(void); */ void ipa_cmd_pipeline_clear_wait(struct ipa *ipa); -/** - * ipa_cmd_pipeline_clear() - Clear the hardware pipeline - * @ipa: - IPA pointer - */ -void ipa_cmd_pipeline_clear(struct ipa *ipa); - /** * ipa_cmd_trans_alloc() - Allocate a transaction for the command TX endpoint * @ipa: IPA pointer diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index ef790fd0ab56a7..03a17099342087 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1636,8 +1636,6 @@ void ipa_endpoint_suspend(struct ipa *ipa) if (ipa->modem_netdev) ipa_modem_suspend(ipa->modem_netdev); - ipa_cmd_pipeline_clear(ipa); - ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]); ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]); } From 7b1b62bc1e6a7b2fd5ee7a4296268eb291d23aeb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Mon, 22 Nov 2021 21:08:34 +0100 Subject: [PATCH 211/358] net: marvell: mvpp2: increase MTU limit when XDP enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently mvpp2_xdp_setup won't allow attaching XDP program if mtu > ETH_DATA_LEN (1500). The mvpp2_change_mtu on the other hand checks whether MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE. These two checks are semantically different. Moreover this limit can be increased to MVPP2_MAX_RX_BUF_SIZE, since in mvpp2_rx we have xdp.data = data + MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM; xdp.frame_sz = PAGE_SIZE; Change the checks to check whether mtu > MVPP2_MAX_RX_BUF_SIZE Fixes: 07dd0a7aae7f ("mvpp2: add basic XDP support") Signed-off-by: Marek Behún Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 2b18d89d9756d8..ce486e16489c59 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5017,11 +5017,13 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu) mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8); } + if (port->xdp_prog && mtu > MVPP2_MAX_RX_BUF_SIZE) { + netdev_err(dev, "Illegal MTU value %d (> %d) for XDP mode\n", + mtu, (int)MVPP2_MAX_RX_BUF_SIZE); + return -EINVAL; + } + if (MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE) { - if (port->xdp_prog) { - netdev_err(dev, "Jumbo frames are not supported with XDP\n"); - return -EINVAL; - } if (priv->percpu_pools) { netdev_warn(dev, "mtu %d too high, switching to shared buffers", mtu); mvpp2_bm_switch_buffers(priv, false); @@ -5307,8 +5309,8 @@ static int mvpp2_xdp_setup(struct mvpp2_port *port, struct netdev_bpf *bpf) bool running = netif_running(port->dev); bool reset = !prog != !port->xdp_prog; - if (port->dev->mtu > ETH_DATA_LEN) { - NL_SET_ERR_MSG_MOD(bpf->extack, "XDP is not supported with jumbo frames enabled"); + if (port->dev->mtu > MVPP2_MAX_RX_BUF_SIZE) { + NL_SET_ERR_MSG_MOD(bpf->extack, "MTU too large for XDP"); return -EOPNOTSUPP; } From cd23f02f166892603eb9f2d488152b975872b682 Mon Sep 17 00:00:00 2001 From: Adamos Ttofari Date: Fri, 12 Nov 2021 09:16:57 +0000 Subject: [PATCH 212/358] cpufreq: intel_pstate: Add Ice Lake server to out-of-band IDs Commit fbdc21e9b038 ("cpufreq: intel_pstate: Add Icelake servers support in no-HWP mode") enabled the use of Intel P-State driver for Ice Lake servers. But it doesn't cover the case when OS can't control P-States. Therefore, for Ice Lake server, if MSR_MISC_PWR_MGMT bits 8 or 18 are enabled, then the Intel P-State driver should exit as OS can't control P-States. Fixes: fbdc21e9b038 ("cpufreq: intel_pstate: Add Icelake servers support in no-HWP mode") Signed-off-by: Adamos Ttofari Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 815df3daae9df3..1088ff350159b8 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2353,6 +2353,7 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { X86_MATCH(BROADWELL_D, core_funcs), X86_MATCH(BROADWELL_X, core_funcs), X86_MATCH(SKYLAKE_X, core_funcs), + X86_MATCH(ICELAKE_X, core_funcs), {} }; From ed38eb49d101e829ae0f8c0a0d3bf5cb6bcbc6b2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 17 Nov 2021 14:57:31 +0100 Subject: [PATCH 213/358] cpufreq: intel_pstate: Fix active mode offline/online EPP handling After commit 4adcf2e5829f ("cpufreq: intel_pstate: Add ->offline and ->online callbacks") the EPP value set by the "performance" scaling algorithm in the active mode is not restored after an offline/online cycle which replaces it with the saved EPP value coming from user space. Address this issue by forcing intel_pstate_hwp_set() to set a new EPP value when it runs first time after online. Fixes: 4adcf2e5829f ("cpufreq: intel_pstate: Add ->offline and ->online callbacks") Link: https://lore.kernel.org/linux-pm/adc7132c8655bd4d1c8b6129578e931a14fe1db2.camel@linux.intel.com/ Reported-by: Srinivas Pandruvada Cc: 5.9+ # 5.9+ Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 1088ff350159b8..1bc00645b65651 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1006,6 +1006,12 @@ static void intel_pstate_hwp_offline(struct cpudata *cpu) */ value &= ~GENMASK_ULL(31, 24); value |= HWP_ENERGY_PERF_PREFERENCE(cpu->epp_cached); + /* + * However, make sure that EPP will be set to "performance" when + * the CPU is brought back online again and the "performance" + * scaling algorithm is still in effect. + */ + cpu->epp_policy = CPUFREQ_POLICY_UNKNOWN; } /* From 6cca13de26eea6d32a98d96d916a048d16a12822 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Tue, 23 Nov 2021 12:16:56 +0200 Subject: [PATCH 214/358] usb: hub: Fix locking issues with address0_mutex Fix the circular lock dependency and unbalanced unlock of addess0_mutex introduced when fixing an address0_mutex enumeration retry race in commit ae6dc22d2d1 ("usb: hub: Fix usb enumeration issue due to address0 race") Make sure locking order between port_dev->status_lock and address0_mutex is correct, and that address0_mutex is not unlocked in hub_port_connect "done:" codepath which may be reached without locking address0_mutex Fixes: 6ae6dc22d2d1 ("usb: hub: Fix usb enumeration issue due to address0 race") Cc: Reported-by: Marek Szyprowski Tested-by: Hans de Goede Tested-by: Marek Szyprowski Acked-by: Hans de Goede Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20211123101656.1113518-1-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 00c3506324e47d..00070a8a650792 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5188,6 +5188,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, struct usb_port *port_dev = hub->ports[port1 - 1]; struct usb_device *udev = port_dev->child; static int unreliable_port = -1; + bool retry_locked; /* Disconnect any existing devices under this port */ if (udev) { @@ -5244,10 +5245,10 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, status = 0; - mutex_lock(hcd->address0_mutex); - for (i = 0; i < PORT_INIT_TRIES; i++) { - + usb_lock_port(port_dev); + mutex_lock(hcd->address0_mutex); + retry_locked = true; /* reallocate for each attempt, since references * to the previous one can escape in various ways */ @@ -5255,6 +5256,8 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, if (!udev) { dev_err(&port_dev->dev, "couldn't allocate usb_device\n"); + mutex_unlock(hcd->address0_mutex); + usb_unlock_port(port_dev); goto done; } @@ -5276,13 +5279,13 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, } /* reset (non-USB 3.0 devices) and get descriptor */ - usb_lock_port(port_dev); status = hub_port_init(hub, udev, port1, i); - usb_unlock_port(port_dev); if (status < 0) goto loop; mutex_unlock(hcd->address0_mutex); + usb_unlock_port(port_dev); + retry_locked = false; if (udev->quirks & USB_QUIRK_DELAY_INIT) msleep(2000); @@ -5372,11 +5375,14 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, loop_disable: hub_port_disable(hub, port1, 1); - mutex_lock(hcd->address0_mutex); loop: usb_ep0_reinit(udev); release_devnum(udev); hub_free_dev(udev); + if (retry_locked) { + mutex_unlock(hcd->address0_mutex); + usb_unlock_port(port_dev); + } usb_put_dev(udev); if ((status == -ENOTCONN) || (status == -ENOTSUPP)) break; @@ -5399,8 +5405,6 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, } done: - mutex_unlock(hcd->address0_mutex); - hub_port_disable(hub, port1, 1); if (hcd->driver->relinquish_port && !hub->hdev->parent) { if (status != -ENOTCONN && status != -ENODEV) From 7b9c90e3e6a13d89048717f846ba664dfbd4c6c7 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Sat, 20 Nov 2021 12:07:16 +0900 Subject: [PATCH 215/358] usb: typec: tipd: Fix typo in cd321x_switch_power_state SPSS should've been SSPS. Fixes: c9c14be664cf ("usb: typec: tipd: Switch CD321X power state to S0") Reviewed-by: Heikki Krogerus Reviewed-by: Sven Peter Signed-off-by: Hector Martin Link: https://lore.kernel.org/r/20211120030717.84287-2-marcan@marcan.st Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tipd/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index fb8ef12bbe9c85..4da5a0b2aed271 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -653,7 +653,7 @@ static int cd321x_switch_power_state(struct tps6598x *tps, u8 target_state) if (state == target_state) return 0; - ret = tps6598x_exec_cmd(tps, "SPSS", sizeof(u8), &target_state, 0, NULL); + ret = tps6598x_exec_cmd(tps, "SSPS", sizeof(u8), &target_state, 0, NULL); if (ret) return ret; From 113972d2e111304553d4d3226f49d18ea4b7f2f7 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Sat, 20 Nov 2021 12:07:17 +0900 Subject: [PATCH 216/358] usb: typec: tipd: Fix initialization sequence for cd321x The power state switch needs to happen first, as that kickstarts the firmware into normal mode. Fixes: c9c14be664cf ("usb: typec: tipd: Switch CD321X power state to S0") Reviewed-by: Heikki Krogerus Reviewed-by: Sven Peter Signed-off-by: Hector Martin Link: https://lore.kernel.org/r/20211120030717.84287-3-marcan@marcan.st Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tipd/core.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 4da5a0b2aed271..6d27a5b5e3cac6 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -707,6 +707,7 @@ static int tps6598x_probe(struct i2c_client *client) u32 conf; u32 vid; int ret; + u64 mask1; tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL); if (!tps) @@ -730,11 +731,6 @@ static int tps6598x_probe(struct i2c_client *client) if (i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) tps->i2c_protocol = true; - /* Make sure the controller has application firmware running */ - ret = tps6598x_check_mode(tps); - if (ret) - return ret; - if (np && of_device_is_compatible(np, "apple,cd321x")) { /* Switch CD321X chips to the correct system power state */ ret = cd321x_switch_power_state(tps, TPS_SYSTEM_POWER_STATE_S0); @@ -742,24 +738,27 @@ static int tps6598x_probe(struct i2c_client *client) return ret; /* CD321X chips have all interrupts masked initially */ - ret = tps6598x_write64(tps, TPS_REG_INT_MASK1, - APPLE_CD_REG_INT_POWER_STATUS_UPDATE | - APPLE_CD_REG_INT_DATA_STATUS_UPDATE | - APPLE_CD_REG_INT_PLUG_EVENT); - if (ret) - return ret; + mask1 = APPLE_CD_REG_INT_POWER_STATUS_UPDATE | + APPLE_CD_REG_INT_DATA_STATUS_UPDATE | + APPLE_CD_REG_INT_PLUG_EVENT; irq_handler = cd321x_interrupt; } else { /* Enable power status, data status and plug event interrupts */ - ret = tps6598x_write64(tps, TPS_REG_INT_MASK1, - TPS_REG_INT_POWER_STATUS_UPDATE | - TPS_REG_INT_DATA_STATUS_UPDATE | - TPS_REG_INT_PLUG_EVENT); - if (ret) - return ret; + mask1 = TPS_REG_INT_POWER_STATUS_UPDATE | + TPS_REG_INT_DATA_STATUS_UPDATE | + TPS_REG_INT_PLUG_EVENT; } + /* Make sure the controller has application firmware running */ + ret = tps6598x_check_mode(tps); + if (ret) + return ret; + + ret = tps6598x_write64(tps, TPS_REG_INT_MASK1, mask1); + if (ret) + return ret; + ret = tps6598x_read32(tps, TPS_REG_STATUS, &status); if (ret < 0) return ret; From 03c83982a0278207709143ba78c5a470179febee Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Thu, 18 Nov 2021 21:18:01 -0800 Subject: [PATCH 217/358] cpufreq: intel_pstate: ITMT support for overclocked system On systems with overclocking enabled, CPPC Highest Performance can be hard coded to 0xff. In this case even if we have cores with different highest performance, ITMT can't be enabled as the current implementation depends on CPPC Highest Performance. On such systems we can use MSR_HWP_CAPABILITIES maximum performance field when CPPC.Highest Performance is 0xff. Due to legacy reasons, we can't solely depend on MSR_HWP_CAPABILITIES as in some older systems CPPC Highest Performance is the only way to identify different performing cores. Reported-by: Michael Larabel Signed-off-by: Srinivas Pandruvada Tested-by: Michael Larabel Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 1bc00645b65651..dec2a5649ac1af 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -338,6 +338,8 @@ static void intel_pstste_sched_itmt_work_fn(struct work_struct *work) static DECLARE_WORK(sched_itmt_work, intel_pstste_sched_itmt_work_fn); +#define CPPC_MAX_PERF U8_MAX + static void intel_pstate_set_itmt_prio(int cpu) { struct cppc_perf_caps cppc_perf; @@ -348,6 +350,14 @@ static void intel_pstate_set_itmt_prio(int cpu) if (ret) return; + /* + * On some systems with overclocking enabled, CPPC.highest_perf is hardcoded to 0xff. + * In this case we can't use CPPC.highest_perf to enable ITMT. + * In this case we can look at MSR_HWP_CAPABILITIES bits [8:0] to decide. + */ + if (cppc_perf.highest_perf == CPPC_MAX_PERF) + cppc_perf.highest_perf = HWP_HIGHEST_PERF(READ_ONCE(all_cpu_data[cpu]->hwp_cap_cached)); + /* * The priorities can be set regardless of whether or not * sched_set_itmt_support(true) has been called and it is valid to From b9ad6b5b687e798746024e5fc4574d8fa8bdfade Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Sun, 21 Nov 2021 16:45:44 +0000 Subject: [PATCH 218/358] cifs: nosharesock should be set on new server Recent fix to maintain a nosharesock state on the server struct caused a regression. It updated this field in the old tcp session, and not the new one. This caused the multichannel scenario to misbehave. Fixes: c9f1c19cf7c5 (cifs: nosharesock should not share socket with future sessions) Signed-off-by: Shyam Prasad N Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/connect.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 67e4c5548e9d0d..6b705026da1a37 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1271,10 +1271,8 @@ static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context * { struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr; - if (ctx->nosharesock) { - server->nosharesock = true; + if (ctx->nosharesock) return 0; - } /* this server does not share socket */ if (server->nosharesock) @@ -1438,6 +1436,9 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, goto out_err; } + if (ctx->nosharesock) + tcp_ses->nosharesock = true; + tcp_ses->ops = ctx->ops; tcp_ses->vals = ctx->vals; cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); From 5112d80c162f456b3956dd4f5c58e9f0c6498516 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Fri, 19 Nov 2021 13:04:11 +0000 Subject: [PATCH 219/358] cifs: populate server_hostname for extra channels Recently, a new field got added to the smb3_fs_context struct named server_hostname. While creating extra channels, pick up this field from primary channel. Signed-off-by: Shyam Prasad N Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/sess.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 8ad2993785afb1..af63548eaf26da 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -222,6 +222,7 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, /* Auth */ ctx.domainauto = ses->domainAuto; ctx.domainname = ses->domainName; + ctx.server_hostname = ses->server->hostname; ctx.username = ses->user_name; ctx.password = ses->password; ctx.sectype = ses->sectype; From 350f4a562e1ffc2e4869e3083dc9b0ec4bca6c3a Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 22 Nov 2021 18:31:03 -0600 Subject: [PATCH 220/358] smb2: clarify rc initialization in smb2_reconnect It is clearer to initialize rc at the beginning of the function. Reported-by: kernel test robot Reported-by: Dan Carpenter Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2f5f2c4c6183c9..8b3670388cdaf6 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -142,7 +142,7 @@ static int smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, struct TCP_Server_Info *server) { - int rc; + int rc = 0; struct nls_table *nls_codepage; struct cifs_ses *ses; int retries; From 0b03fe6d3ae21a7769d867ccdce33737eb348454 Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 22 Nov 2021 18:37:37 -0600 Subject: [PATCH 221/358] cifs: update internal version number To 2.34 Signed-off-by: Steve French --- fs/cifs/cifsfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index b50da1901ebd2d..9e5d9e192ef042 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -152,5 +152,5 @@ extern struct dentry *cifs_smb3_do_mount(struct file_system_type *fs_type, extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.33" +#define CIFS_VERSION "2.34" #endif /* _CIFSFS_H */ From a208fc56721775987c1b86e20d86d7e0d017c0b2 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Tue, 16 Nov 2021 16:49:18 +0100 Subject: [PATCH 222/358] nvmet-tcp: fix a race condition between release_queue and io_work If the initiator executes a reset controller operation while performing I/O, the target kernel will crash because of a race condition between release_queue and io_work; nvmet_tcp_uninit_data_in_cmds() may be executed while io_work is running, calling flush_work() was not sufficient to prevent this because io_work could requeue itself. Fix this bug by using cancel_work_sync() to prevent io_work from requeuing itself and set rcv_state to NVMET_TCP_RECV_ERR to make sure we don't receive any more data from the socket. Signed-off-by: Maurizio Lombardi Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: John Meneghini Signed-off-by: Christoph Hellwig --- drivers/nvme/target/tcp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 84c387e4bf4314..18f36256095f62 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1437,7 +1437,9 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w) mutex_unlock(&nvmet_tcp_queue_mutex); nvmet_tcp_restore_socket_callbacks(queue); - flush_work(&queue->io_work); + cancel_work_sync(&queue->io_work); + /* stop accepting incoming data */ + queue->rcv_state = NVMET_TCP_RECV_ERR; nvmet_tcp_uninit_data_in_cmds(queue); nvmet_sq_destroy(&queue->nvme_sq); From 69b85e1f1d1d1e49601ec3e85d2031188657cca2 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Tue, 16 Nov 2021 16:49:19 +0100 Subject: [PATCH 223/358] nvmet-tcp: add an helper to free the cmd buffers Makes the code easier to read and to debug. Sets the freed pointers to NULL, it will be useful when destroying the queues to understand if the commands' buffers have been released already or not. Signed-off-by: Maurizio Lombardi Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: John Meneghini Signed-off-by: Christoph Hellwig --- drivers/nvme/target/tcp.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 18f36256095f62..786b1440a9af48 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -166,6 +166,8 @@ static struct workqueue_struct *nvmet_tcp_wq; static const struct nvmet_fabrics_ops nvmet_tcp_ops; static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c); static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd); +static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd); +static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd); static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue, struct nvmet_tcp_cmd *cmd) @@ -297,6 +299,16 @@ static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu) return 0; } +static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd) +{ + WARN_ON(unlikely(cmd->nr_mapped > 0)); + + kfree(cmd->iov); + sgl_free(cmd->req.sg); + cmd->iov = NULL; + cmd->req.sg = NULL; +} + static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd) { struct scatterlist *sg; @@ -306,6 +318,8 @@ static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd) for (i = 0; i < cmd->nr_mapped; i++) kunmap(sg_page(&sg[i])); + + cmd->nr_mapped = 0; } static void nvmet_tcp_map_pdu_iovec(struct nvmet_tcp_cmd *cmd) @@ -387,7 +401,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) return 0; err: - sgl_free(cmd->req.sg); + nvmet_tcp_free_cmd_buffers(cmd); return NVME_SC_INTERNAL; } @@ -632,10 +646,8 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch) } } - if (queue->nvme_sq.sqhd_disabled) { - kfree(cmd->iov); - sgl_free(cmd->req.sg); - } + if (queue->nvme_sq.sqhd_disabled) + nvmet_tcp_free_cmd_buffers(cmd); return 1; @@ -664,8 +676,7 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd, if (left) return -EAGAIN; - kfree(cmd->iov); - sgl_free(cmd->req.sg); + nvmet_tcp_free_cmd_buffers(cmd); cmd->queue->snd_cmd = NULL; nvmet_tcp_put_cmd(cmd); return 1; @@ -1406,8 +1417,7 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd) { nvmet_req_uninit(&cmd->req); nvmet_tcp_unmap_pdu_iovec(cmd); - kfree(cmd->iov); - sgl_free(cmd->req.sg); + nvmet_tcp_free_cmd_buffers(cmd); } static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue) From af21250bb503a02e705b461886321e394b300524 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Tue, 16 Nov 2021 16:49:20 +0100 Subject: [PATCH 224/358] nvmet-tcp: fix memory leak when performing a controller reset If a reset controller is executed while the initiator is performing some I/O the driver may leak the memory allocated for the commands' iovec. Make sure that nvmet_tcp_uninit_data_in_cmds() releases all the memory. Signed-off-by: Maurizio Lombardi Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: John Meneghini Signed-off-by: Christoph Hellwig --- drivers/nvme/target/tcp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 786b1440a9af48..605aa2a8ca536b 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1427,7 +1427,10 @@ static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue) for (i = 0; i < queue->nr_cmds; i++, cmd++) { if (nvmet_tcp_need_data_in(cmd)) - nvmet_tcp_finish_cmd(cmd); + nvmet_req_uninit(&cmd->req); + + nvmet_tcp_unmap_pdu_iovec(cmd); + nvmet_tcp_free_cmd_buffers(cmd); } if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect)) { From 102110efdff6beedece6ab9b51664c32ac01e2db Mon Sep 17 00:00:00 2001 From: Varun Prakash Date: Mon, 22 Nov 2021 15:38:41 +0530 Subject: [PATCH 225/358] nvmet-tcp: fix incomplete data digest send Current nvmet_try_send_ddgst() code does not check whether all data digest bytes are transmitted, fix this by returning -EAGAIN if all data digest bytes are not transmitted. Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") Signed-off-by: Varun Prakash Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/tcp.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 605aa2a8ca536b..cb6a473c3eafa5 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -711,10 +711,11 @@ static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch) static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch) { struct nvmet_tcp_queue *queue = cmd->queue; + int left = NVME_TCP_DIGEST_LENGTH - cmd->offset; struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; struct kvec iov = { .iov_base = (u8 *)&cmd->exp_ddgst + cmd->offset, - .iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset + .iov_len = left }; int ret; @@ -728,6 +729,10 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch) return ret; cmd->offset += ret; + left -= ret; + + if (left) + return -EAGAIN; if (queue->nvme_sq.sqhd_disabled) { cmd->queue->snd_cmd = NULL; From 1d3ef9c3a39e04be31155c27ebf80342350c3abf Mon Sep 17 00:00:00 2001 From: Varun Prakash Date: Tue, 23 Nov 2021 16:28:56 +0530 Subject: [PATCH 226/358] nvme-tcp: validate R2T PDU in nvme_tcp_handle_r2t() If maxh2cdata < r2t_length then driver will form multiple H2CData PDUs, validate R2T PDU in nvme_tcp_handle_r2t() to reuse nvme_tcp_setup_h2c_data_pdu(). Also set req->state to NVME_TCP_SEND_H2C_PDU in nvme_tcp_setup_h2c_data_pdu(). Signed-off-by: Varun Prakash Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 55 ++++++++++++++++++----------------------- 1 file changed, 24 insertions(+), 31 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 33bc83d8d99285..5f8ad4d4ac8cf1 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -572,7 +572,7 @@ static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue, return ret; } -static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, +static void nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, struct nvme_tcp_r2t_pdu *pdu) { struct nvme_tcp_data_pdu *data = req->pdu; @@ -581,32 +581,11 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, u8 hdgst = nvme_tcp_hdgst_len(queue); u8 ddgst = nvme_tcp_ddgst_len(queue); + req->state = NVME_TCP_SEND_H2C_PDU; + req->offset = 0; req->pdu_len = le32_to_cpu(pdu->r2t_length); req->pdu_sent = 0; - if (unlikely(!req->pdu_len)) { - dev_err(queue->ctrl->ctrl.device, - "req %d r2t len is %u, probably a bug...\n", - rq->tag, req->pdu_len); - return -EPROTO; - } - - if (unlikely(req->data_sent + req->pdu_len > req->data_len)) { - dev_err(queue->ctrl->ctrl.device, - "req %d r2t len %u exceeded data len %u (%zu sent)\n", - rq->tag, req->pdu_len, req->data_len, - req->data_sent); - return -EPROTO; - } - - if (unlikely(le32_to_cpu(pdu->r2t_offset) < req->data_sent)) { - dev_err(queue->ctrl->ctrl.device, - "req %d unexpected r2t offset %u (expected %zu)\n", - rq->tag, le32_to_cpu(pdu->r2t_offset), - req->data_sent); - return -EPROTO; - } - memset(data, 0, sizeof(*data)); data->hdr.type = nvme_tcp_h2c_data; data->hdr.flags = NVME_TCP_F_DATA_LAST; @@ -622,7 +601,6 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, data->command_id = nvme_cid(rq); data->data_offset = pdu->r2t_offset; data->data_length = cpu_to_le32(req->pdu_len); - return 0; } static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, @@ -630,7 +608,7 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, { struct nvme_tcp_request *req; struct request *rq; - int ret; + u32 r2t_length = le32_to_cpu(pdu->r2t_length); rq = nvme_find_rq(nvme_tcp_tagset(queue), pdu->command_id); if (!rq) { @@ -641,13 +619,28 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, } req = blk_mq_rq_to_pdu(rq); - ret = nvme_tcp_setup_h2c_data_pdu(req, pdu); - if (unlikely(ret)) - return ret; + if (unlikely(!r2t_length)) { + dev_err(queue->ctrl->ctrl.device, + "req %d r2t len is %u, probably a bug...\n", + rq->tag, r2t_length); + return -EPROTO; + } - req->state = NVME_TCP_SEND_H2C_PDU; - req->offset = 0; + if (unlikely(req->data_sent + r2t_length > req->data_len)) { + dev_err(queue->ctrl->ctrl.device, + "req %d r2t len %u exceeded data len %u (%zu sent)\n", + rq->tag, r2t_length, req->data_len, req->data_sent); + return -EPROTO; + } + + if (unlikely(le32_to_cpu(pdu->r2t_offset) < req->data_sent)) { + dev_err(queue->ctrl->ctrl.device, + "req %d unexpected r2t offset %u (expected %zu)\n", + rq->tag, le32_to_cpu(pdu->r2t_offset), req->data_sent); + return -EPROTO; + } + nvme_tcp_setup_h2c_data_pdu(req, pdu); nvme_tcp_queue_request(req, false, true); return 0; From a5053c92b3db71c3f7f9f13934ca620632828d06 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Wed, 3 Nov 2021 09:18:17 +0100 Subject: [PATCH 227/358] nvme-tcp: fix memory leak when freeing a queue Release the page frag cache when tearing down the io queues Signed-off-by: Maurizio Lombardi Reviewed-by: Sagi Grimberg Reviewed-by: John Meneghini Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 5f8ad4d4ac8cf1..4ceb28675fdf63 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1225,6 +1225,7 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) { + struct page *page; struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; @@ -1234,6 +1235,11 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) if (queue->hdr_digest || queue->data_digest) nvme_tcp_free_crypto(queue); + if (queue->pf_cache.va) { + page = virt_to_head_page(queue->pf_cache.va); + __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias); + queue->pf_cache.va = NULL; + } sock_release(queue->sock); kfree(queue->pdu); mutex_destroy(&queue->send_mutex); From 5a6254d55e2a9f7919ead8580d7aa0c7a382b26a Mon Sep 17 00:00:00 2001 From: Enzo Matsumiya Date: Fri, 5 Nov 2021 23:08:57 -0300 Subject: [PATCH 228/358] nvme-pci: add NO APST quirk for Kioxia device This particular Kioxia device times out and aborts I/O during any load, but it's more easily observable with discards (fstrim). The device gets to a state that is also not possible to use "nvme set-feature" to disable APST. Booting with nvme_core.default_ps_max_latency=0 solves the issue. We had a dozen or so of these devices behaving this same way in customer environments. Signed-off-by: Enzo Matsumiya Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 4b5de8f5435a5f..50a98f56da88ce 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2469,6 +2469,20 @@ static const struct nvme_core_quirk_entry core_quirks[] = { .vid = 0x14a4, .fr = "22301111", .quirks = NVME_QUIRK_SIMPLE_SUSPEND, + }, + { + /* + * This Kioxia CD6-V Series / HPE PE8030 device times out and + * aborts I/O during any load, but more easily reproducible + * with discards (fstrim). + * + * The device is left in a state where it is also not possible + * to use "nvme set-feature" to disable APST, but booting with + * nvme_core.default_ps_max_latency=0 works. + */ + .vid = 0x1e0f, + .mn = "KCD6XVUL6T40", + .quirks = NVME_QUIRK_NO_APST, } }; From 8e8aaf512a91ae44d40647a88b51326c7b0a70a8 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Fri, 12 Nov 2021 15:16:12 +0100 Subject: [PATCH 229/358] nvme-fabrics: ignore invalid fast_io_fail_tmo values Valid fast_io_fail_tmo values are integers >= 0 or -1 (disabled). Prevent userspace from setting arbitrary negative values. Signed-off-by: Maurizio Lombardi Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fabrics.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index c5a2b71c526863..282d54117e0ac7 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -698,6 +698,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, if (token >= 0) pr_warn("I/O fail on reconnect controller after %d sec\n", token); + else + token = -1; + opts->fast_io_fail_tmo = token; break; case NVMF_OPT_HOSTNQN: From 00b33cf3da726757aef636365bb52e9536434e9a Mon Sep 17 00:00:00 2001 From: Klaus Jensen Date: Wed, 10 Nov 2021 10:19:06 +0100 Subject: [PATCH 230/358] nvme: fix write zeroes pi Write Zeroes sets PRACT when block integrity is enabled (as it should), but neglects to also set the reftag which is expected by reads. This causes protection errors on reads. Fix this by setting the reftag for type 1 and 2 (for type 3, reads will not check the reftag). Signed-off-by: Klaus Jensen Reviewed-by: Martin K. Petersen Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 50a98f56da88ce..4c63564adeaa6a 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -895,10 +895,19 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->write_zeroes.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); - if (nvme_ns_has_pi(ns)) + + if (nvme_ns_has_pi(ns)) { cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT); - else - cmnd->write_zeroes.control = 0; + + switch (ns->pi_type) { + case NVME_NS_DPS_PI_TYPE1: + case NVME_NS_DPS_PI_TYPE2: + cmnd->write_zeroes.reftag = + cpu_to_le32(t10_pi_ref_tag(req)); + break; + } + } + return BLK_STS_OK; } From 9054fc6d57e80c27c0b0632966416144f2092c2b Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 17 Nov 2021 20:07:34 +0200 Subject: [PATCH 231/358] ACPI: Get acpi_device's parent from the parent field Printk modifier %pfw is used to print the full path of the device name. This is obtained device by device until a device no longer has a parent. On ACPI getting the parent fwnode is done by calling acpi_get_parent() which tries to down() a semaphore. But local IRQs are now disabled in vprintk_store() before the mutex is acquired. This is obviously a problem. Luckily struct device, embedded in struct acpi_device, has a parent field already. Use that field to get the parent instead of relying on acpi_get_parent(). Fixes: 3bd32d6a2ee6 ("lib/vsprintf: Add %pfw conversion specifier for printing fwnode names") Cc: 5.5+ # 5.5+ Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/property.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index e312ebaed8db49..781e312f453427 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1090,15 +1090,10 @@ struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode) /* All data nodes have parent pointer so just return that */ return to_acpi_data_node(fwnode)->parent; } else if (is_acpi_device_node(fwnode)) { - acpi_handle handle, parent_handle; + struct device *dev = to_acpi_device_node(fwnode)->dev.parent; - handle = to_acpi_device_node(fwnode)->handle; - if (ACPI_SUCCESS(acpi_get_parent(handle, &parent_handle))) { - struct acpi_device *adev; - - if (!acpi_bus_get_device(parent_handle, &adev)) - return acpi_fwnode_handle(adev); - } + if (dev) + return acpi_fwnode_handle(to_acpi_device(dev)); } return NULL; From 985e9ece1e55a94da842f6c1f9ff84d587b26267 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 17 Nov 2021 20:07:35 +0200 Subject: [PATCH 232/358] ACPI: Make acpi_node_get_parent() local acpi_node_get_parent() isn't used outside drivers/acpi/property.c. Make it local. Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/property.c | 3 ++- include/linux/acpi.h | 7 ------- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 781e312f453427..2366f54d8e9cf8 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1084,7 +1084,8 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, * Returns parent node of an ACPI device or data firmware node or %NULL if * not available. */ -struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode) +static struct fwnode_handle * +acpi_node_get_parent(const struct fwnode_handle *fwnode) { if (is_acpi_data_node(fwnode)) { /* All data nodes have parent pointer so just return that */ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 668d007f091751..b28f8790192a22 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1182,7 +1182,6 @@ int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); -struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode); struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, @@ -1287,12 +1286,6 @@ acpi_get_next_subnode(const struct fwnode_handle *fwnode, return NULL; } -static inline struct fwnode_handle * -acpi_node_get_parent(const struct fwnode_handle *fwnode) -{ - return NULL; -} - static inline struct fwnode_handle * acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) From e048834c209a02e3776bcc47d43c6d863e3a67ca Mon Sep 17 00:00:00 2001 From: Mohammed Gamal Date: Fri, 19 Nov 2021 12:29:00 +0100 Subject: [PATCH 233/358] drm/hyperv: Fix device removal on Gen1 VMs The Hyper-V DRM driver tries to free MMIO region on removing the device regardless of VM type, while Gen1 VMs don't use MMIO and hence causing the kernel to crash on a NULL pointer dereference. Fix this by making deallocating MMIO only on Gen2 machines and implement removal for Gen1 Fixes: 76c56a5affeb ("drm/hyperv: Add DRM driver for hyperv synthetic video device") Signed-off-by: Mohammed Gamal Reviewed-by: Deepak Rawat Signed-off-by: Deepak Rawat Link: https://patchwork.freedesktop.org/patch/msgid/20211119112900.300537-1-mgamal@redhat.com --- drivers/gpu/drm/hyperv/hyperv_drm_drv.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index cd818a6291835d..00e53de4812bb5 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -225,12 +225,29 @@ static int hyperv_vmbus_remove(struct hv_device *hdev) { struct drm_device *dev = hv_get_drvdata(hdev); struct hyperv_drm_device *hv = to_hv(dev); + struct pci_dev *pdev; drm_dev_unplug(dev); drm_atomic_helper_shutdown(dev); vmbus_close(hdev->channel); hv_set_drvdata(hdev, NULL); - vmbus_free_mmio(hv->mem->start, hv->fb_size); + + /* + * Free allocated MMIO memory only on Gen2 VMs. + * On Gen1 VMs, release the PCI device + */ + if (efi_enabled(EFI_BOOT)) { + vmbus_free_mmio(hv->mem->start, hv->fb_size); + } else { + pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT, + PCI_DEVICE_ID_HYPERV_VIDEO, NULL); + if (!pdev) { + drm_err(dev, "Unable to find PCI Hyper-V video\n"); + return -ENODEV; + } + pci_release_region(pdev, 0); + pci_dev_put(pdev); + } return 0; } From 37a72b08a3e1eb28053214dd8211eb09c2fd3187 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 22 Oct 2021 08:47:56 +0200 Subject: [PATCH 234/358] xen: add "not_essential" flag to struct xenbus_driver When booting the xenbus driver will wait for PV devices to have connected to their backends before continuing. The timeout is different between essential and non-essential devices. Non-essential devices are identified by their nodenames directly in the xenbus driver, which requires to update this list in case a new device type being non-essential is added (this was missed for several types in the past). In order to avoid this problem, add a "not_essential" flag to struct xenbus_driver which can be set to "true" by the respective frontend. Set this flag for the frontends currently regarded to be not essential (vkbs and vfb) and use it for testing in the xenbus driver. Signed-off-by: Juergen Gross Link: https://lore.kernel.org/r/20211022064800.14978-2-jgross@suse.com Reviewed-by: Boris Ostrovsky Signed-off-by: Boris Ostrovsky --- drivers/input/misc/xen-kbdfront.c | 1 + drivers/video/fbdev/xen-fbfront.c | 1 + drivers/xen/xenbus/xenbus_probe_frontend.c | 14 +++----------- include/xen/xenbus.h | 1 + 4 files changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c index 4ff5cd2a6d8de6..3d17a0b3fe5118 100644 --- a/drivers/input/misc/xen-kbdfront.c +++ b/drivers/input/misc/xen-kbdfront.c @@ -542,6 +542,7 @@ static struct xenbus_driver xenkbd_driver = { .remove = xenkbd_remove, .resume = xenkbd_resume, .otherend_changed = xenkbd_backend_changed, + .not_essential = true, }; static int __init xenkbd_init(void) diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c index 5ec51445bee882..6826f986da4368 100644 --- a/drivers/video/fbdev/xen-fbfront.c +++ b/drivers/video/fbdev/xen-fbfront.c @@ -695,6 +695,7 @@ static struct xenbus_driver xenfb_driver = { .remove = xenfb_remove, .resume = xenfb_resume, .otherend_changed = xenfb_backend_changed, + .not_essential = true, }; static int __init xenfb_init(void) diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index 480944606a3c99..07b010a68fcf9c 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -211,19 +211,11 @@ static int is_device_connecting(struct device *dev, void *data, bool ignore_none if (drv && (dev->driver != drv)) return 0; - if (ignore_nonessential) { - /* With older QEMU, for PVonHVM guests the guest config files - * could contain: vfb = [ 'vnc=1, vnclisten=0.0.0.0'] - * which is nonsensical as there is no PV FB (there can be - * a PVKB) running as HVM guest. */ + xendrv = to_xenbus_driver(dev->driver); - if ((strncmp(xendev->nodename, "device/vkbd", 11) == 0)) - return 0; + if (ignore_nonessential && xendrv->not_essential) + return 0; - if ((strncmp(xendev->nodename, "device/vfb", 10) == 0)) - return 0; - } - xendrv = to_xenbus_driver(dev->driver); return (xendev->state < XenbusStateConnected || (xendev->state == XenbusStateConnected && xendrv->is_ready && !xendrv->is_ready(xendev))); diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b94074c827721b..b13eb86395e059 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -112,6 +112,7 @@ struct xenbus_driver { const char *name; /* defaults to ids[0].devicetype */ const struct xenbus_device_id *ids; bool allow_rebind; /* avoid setting xenstore closed during remove */ + bool not_essential; /* is not mandatory for boot progress */ int (*probe)(struct xenbus_device *dev, const struct xenbus_device_id *id); void (*otherend_changed)(struct xenbus_device *dev, From 1c669938c31b6e2a0d5149c3c6257ca9df6cb100 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 22 Oct 2021 08:47:57 +0200 Subject: [PATCH 235/358] xen: flag xen_drm_front to be not essential for system boot Similar to the virtual frame buffer (vfb) the pv display driver is not essential for booting the system. Set the respective flag. Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Andrushchenko Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20211022064800.14978-3-jgross@suse.com Signed-off-by: Boris Ostrovsky --- drivers/gpu/drm/xen/xen_drm_front.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index 9f14d99c763c2b..bc7605324db395 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -773,6 +773,7 @@ static struct xenbus_driver xen_driver = { .probe = xen_drv_probe, .remove = xen_drv_remove, .otherend_changed = displback_changed, + .not_essential = true, }; static int __init xen_drv_init(void) From 0239143490a9fa1344955dde93527b09f5576dac Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 22 Oct 2021 08:47:58 +0200 Subject: [PATCH 236/358] xen: flag hvc_xen to be not essential for system boot The Xen pv console driver is not essential for boot. Set the respective flag. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20211022064800.14978-4-jgross@suse.com Signed-off-by: Boris Ostrovsky --- drivers/tty/hvc/hvc_xen.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index f0bf01ea069ae0..71e0dd2c0ce5b7 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -522,6 +522,7 @@ static struct xenbus_driver xencons_driver = { .remove = xencons_remove, .resume = xencons_resume, .otherend_changed = xencons_backend_changed, + .not_essential = true, }; #endif /* CONFIG_HVC_XEN_FRONTEND */ From 03e143b2acebe23c893f22ebed9abc0fe2a7f27e Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 22 Oct 2021 08:47:59 +0200 Subject: [PATCH 237/358] xen: flag pvcalls-front to be not essential for system boot The Xen pvcalls device is not essential for booting. Set the respective flag. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20211022064800.14978-5-jgross@suse.com Signed-off-by: Boris Ostrovsky --- drivers/xen/pvcalls-front.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 7984645b59563b..3c9ae156b597fa 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -1275,6 +1275,7 @@ static struct xenbus_driver pvcalls_front_driver = { .probe = pvcalls_front_probe, .remove = pvcalls_front_remove, .otherend_changed = pvcalls_front_changed, + .not_essential = true, }; static int __init pvcalls_frontend_init(void) From de6da33e6cb79abd4a5721b65b9a7dbed24378f8 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 22 Oct 2021 08:48:00 +0200 Subject: [PATCH 238/358] xen: flag xen_snd_front to be not essential for system boot The Xen pv sound driver is not essential for booting. Set the respective flag. [boris: replace semicolon with comma] Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Andrushchenko Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20211022064800.14978-6-jgross@suse.com Signed-off-by: Boris Ostrovsky --- sound/xen/xen_snd_front.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/xen/xen_snd_front.c b/sound/xen/xen_snd_front.c index 2cb0a19be2b858..4041748c12e515 100644 --- a/sound/xen/xen_snd_front.c +++ b/sound/xen/xen_snd_front.c @@ -358,6 +358,7 @@ static struct xenbus_driver xen_driver = { .probe = xen_drv_probe, .remove = xen_drv_remove, .otherend_changed = sndback_changed, + .not_essential = true, }; static int __init xen_drv_init(void) From 1880ed71ce863318c1ce93bf324876fb5f92854f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 23 Nov 2021 15:28:01 +0100 Subject: [PATCH 239/358] tracing/uprobe: Fix uprobe_perf_open probes iteration Add missing 'tu' variable initialization in the probes loop, otherwise the head 'tu' is used instead of added probes. Link: https://lkml.kernel.org/r/20211123142801.182530-1-jolsa@kernel.org Cc: stable@vger.kernel.org Fixes: 99c9a923e97a ("tracing/uprobe: Fix double perf_event linking on multiprobe uprobe") Acked-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_uprobe.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 0a5c0db3137ee9..f5f0039d31e5aa 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1313,6 +1313,7 @@ static int uprobe_perf_open(struct trace_event_call *call, return 0; list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + tu = container_of(pos, struct trace_uprobe, tp); err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); From 710d5835b7ae17c517f5aeaff853c300959c87ec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Nov 2021 10:48:10 -0800 Subject: [PATCH 240/358] tools: sync uapi/linux/if_link.h header This file has not been updated for a while. Sync it before BIG TCP patch series. Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20211122184810.769159-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- tools/include/uapi/linux/if_link.h | 293 +++++++++++++++++++++++++---- 1 file changed, 259 insertions(+), 34 deletions(-) diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index b3610fdd1feec3..eebd3894fe89a0 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -7,24 +7,23 @@ /* This struct should be in sync with struct rtnl_link_stats64 */ struct rtnl_link_stats { - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ + __u32 rx_packets; + __u32 tx_packets; + __u32 rx_bytes; + __u32 tx_bytes; + __u32 rx_errors; + __u32 tx_errors; + __u32 rx_dropped; + __u32 tx_dropped; + __u32 multicast; __u32 collisions; - /* detailed rx_errors: */ __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ + __u32 rx_over_errors; + __u32 rx_crc_errors; + __u32 rx_frame_errors; + __u32 rx_fifo_errors; + __u32 rx_missed_errors; /* detailed tx_errors */ __u32 tx_aborted_errors; @@ -37,29 +36,201 @@ struct rtnl_link_stats { __u32 rx_compressed; __u32 tx_compressed; - __u32 rx_nohandler; /* dropped, no handler found */ + __u32 rx_nohandler; }; -/* The main device statistics structure */ +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter may include packets discarded + * due to L2 address filtering but should not include packets dropped + * by the device due to buffer exhaustion which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + */ struct rtnl_link_stats64 { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ - __u64 multicast; /* multicast packets received */ + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; __u64 collisions; /* detailed rx_errors: */ __u64 rx_length_errors; - __u64 rx_over_errors; /* receiver ring buff overflow */ - __u64 rx_crc_errors; /* recved pkt with crc error */ - __u64 rx_frame_errors; /* recv'd frame alignment error */ - __u64 rx_fifo_errors; /* recv'r fifo overrun */ - __u64 rx_missed_errors; /* receiver missed packet */ + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; /* detailed tx_errors */ __u64 tx_aborted_errors; @@ -71,8 +242,7 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; - - __u64 rx_nohandler; /* dropped, no handler found */ + __u64 rx_nohandler; }; /* The struct should be in sync with struct ifmap */ @@ -170,12 +340,29 @@ enum { IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ IFLA_PERM_ADDRESS, + IFLA_PROTO_DOWN_REASON, + + /* device (sysfs) name as parent, used instead + * of IFLA_LINK where there's no parent netdev + */ + IFLA_PARENT_DEV_NAME, + IFLA_PARENT_DEV_BUS_NAME, + __IFLA_MAX }; #define IFLA_MAX (__IFLA_MAX - 1) +enum { + IFLA_PROTO_DOWN_REASON_UNSPEC, + IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */ + IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */ + + __IFLA_PROTO_DOWN_REASON_CNT, + IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1 +}; + /* backwards compatibility for userspace */ #ifndef __KERNEL__ #define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) @@ -293,6 +480,7 @@ enum { IFLA_BR_MCAST_MLD_VERSION, IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, + IFLA_BR_MCAST_QUERIER_STATE, __IFLA_BR_MAX, }; @@ -346,6 +534,8 @@ enum { IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -433,6 +623,7 @@ enum macvlan_macaddr_mode { }; #define MACVLAN_FLAG_NOPROMISC 1 +#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */ /* VRF section */ enum { @@ -597,6 +788,18 @@ enum ifla_geneve_df { GENEVE_DF_MAX = __GENEVE_DF_END - 1, }; +/* Bareudp section */ +enum { + IFLA_BAREUDP_UNSPEC, + IFLA_BAREUDP_PORT, + IFLA_BAREUDP_ETHERTYPE, + IFLA_BAREUDP_SRCPORT_MIN, + IFLA_BAREUDP_MULTIPROTO_MODE, + __IFLA_BAREUDP_MAX +}; + +#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1) + /* PPP section */ enum { IFLA_PPP_UNSPEC, @@ -899,7 +1102,14 @@ enum { #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) -/* HSR section */ +/* HSR/PRP section, both uses same interface */ + +/* Different redundancy protocols for hsr device */ +enum { + HSR_PROTOCOL_HSR, + HSR_PROTOCOL_PRP, + HSR_PROTOCOL_MAX, +}; enum { IFLA_HSR_UNSPEC, @@ -909,6 +1119,9 @@ enum { IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ IFLA_HSR_SEQ_NR, IFLA_HSR_VERSION, /* HSR version */ + IFLA_HSR_PROTOCOL, /* Indicate different protocol than + * HSR. For example PRP. + */ __IFLA_HSR_MAX, }; @@ -1033,6 +1246,8 @@ enum { #define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5) enum { IFLA_RMNET_UNSPEC, @@ -1048,4 +1263,14 @@ struct ifla_rmnet_flags { __u32 mask; }; +/* MCTP section */ + +enum { + IFLA_MCTP_UNSPEC, + IFLA_MCTP_NET, + __IFLA_MCTP_MAX, +}; + +#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ From 0afefdced47d039bd418f5d67f594a60aea20871 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 22 Nov 2021 09:42:52 -0500 Subject: [PATCH 241/358] tc-testing: Add link for reviews with TC MAINTAINERS Signed-off-by: Jamal Hadi Salim Acked-by: Cong Wang Link: https://lore.kernel.org/r/20211122144252.25156-1-jhs@emojatatu.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 10c8ae3a8c7399..2f1e78333883a7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18483,6 +18483,7 @@ F: include/uapi/linux/pkt_sched.h F: include/uapi/linux/tc_act/ F: include/uapi/linux/tc_ematch/ F: net/sched/ +F: tools/testing/selftests/tc-testing TC90522 MEDIA DRIVER M: Akihiro Tsukada From 619ca0d0108a5866cca7793bd7e19c5d7a30e750 Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Mon, 22 Nov 2021 09:18:06 -0800 Subject: [PATCH 242/358] selftests: add arp_ndisc_evict_nocarrier to Makefile This was previously added in selftests but never added to the Makefile Signed-off-by: James Prestwood Link: https://lore.kernel.org/r/20211122171806.3529401-1-prestwoj@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 7615f29831ebd6..9897fa9ab95373 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -34,6 +34,7 @@ TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh TEST_PROGS += vrf_strict_mode_test.sh +TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest From 94902d849e85093aafcdbea2be8e2beff47233e6 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 22 Nov 2021 12:58:20 +0000 Subject: [PATCH 243/358] arm64: uaccess: avoid blocking within critical sections As Vincent reports in: https://lore.kernel.org/r/20211118163417.21617-1-vincent.whitchurch@axis.com The put_user() in schedule_tail() can get stuck in a livelock, similar to a problem recently fixed on riscv in commit: 285a76bb2cf51b0c ("riscv: evaluate put_user() arg before enabling user access") In __raw_put_user() we have a critical section between uaccess_ttbr0_enable() and uaccess_ttbr0_disable() where we cannot safely call into the scheduler without having taken an exception, as schedule() and other scheduling functions will not save/restore the TTBR0 state. If either of the `x` or `ptr` arguments to __raw_put_user() contain a blocking call, we may call into the scheduler within the critical section. This can result in two problems: 1) The access within the critical section will occur without the required TTBR0 tables installed. This will fault, and where the required tables permit access, the access will be retried without the required tables, resulting in a livelock. 2) When TTBR0 SW PAN is in use, check_and_switch_context() does not modify TTBR0, leaving a stale value installed. The mappings of the blocked task will erroneously be accessible to regular accesses in the context of the new task. Additionally, if the tables are subsequently freed, local TLB maintenance required to reuse the ASID may be lost, potentially resulting in TLB corruption (e.g. in the presence of CnP). The same issue exists for __raw_get_user() in the critical section between uaccess_ttbr0_enable() and uaccess_ttbr0_disable(). A similar issue exists for __get_kernel_nofault() and __put_kernel_nofault() for the critical section between __uaccess_enable_tco_async() and __uaccess_disable_tco_async(), as the TCO state is not context-switched by direct calls into the scheduler. Here the TCO state may be lost from the context of the current task, resulting in unexpected asynchronous tag check faults. It may also be leaked to another task, suppressing expected tag check faults. To fix all of these cases, we must ensure that we do not directly call into the scheduler in their respective critical sections. This patch reworks __raw_put_user(), __raw_get_user(), __get_kernel_nofault(), and __put_kernel_nofault(), ensuring that parameters are evaluated outside of the critical sections. To make this requirement clear, comments are added describing the problem, and line spaces added to separate the critical sections from other portions of the macros. For __raw_get_user() and __raw_put_user() the `err` parameter is conditionally assigned to, and we must currently evaluate this in the critical section. This behaviour is relied upon by the signal code, which uses chains of put_user_error() and get_user_error(), checking the return value at the end. In all cases, the `err` parameter is a plain int rather than a more complex expression with a blocking call, so this is safe. In future we should try to clean up the `err` usage to remove the potential for this to be a problem. Aside from the changes to time of evaluation, there should be no functional change as a result of this patch. Reported-by: Vincent Whitchurch Link: https://lore.kernel.org/r/20211118163417.21617-1-vincent.whitchurch@axis.com Fixes: f253d827f33c ("arm64: uaccess: refactor __{get,put}_user") Signed-off-by: Mark Rutland Cc: Will Deacon Cc: Catalin Marinas Link: https://lore.kernel.org/r/20211122125820.55286-1-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/uaccess.h | 48 +++++++++++++++++++++++++++----- 1 file changed, 41 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 6e2e0b7031aba0..3a5ff5e2058630 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -281,12 +281,22 @@ do { \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) +/* + * We must not call into the scheduler between uaccess_ttbr0_enable() and + * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions, + * we must evaluate these outside of the critical section. + */ #define __raw_get_user(x, ptr, err) \ do { \ + __typeof__(*(ptr)) __user *__rgu_ptr = (ptr); \ + __typeof__(x) __rgu_val; \ __chk_user_ptr(ptr); \ + \ uaccess_ttbr0_enable(); \ - __raw_get_mem("ldtr", x, ptr, err); \ + __raw_get_mem("ldtr", __rgu_val, __rgu_ptr, err); \ uaccess_ttbr0_disable(); \ + \ + (x) = __rgu_val; \ } while (0) #define __get_user_error(x, ptr, err) \ @@ -310,14 +320,22 @@ do { \ #define get_user __get_user +/* + * We must not call into the scheduler between __uaccess_enable_tco_async() and + * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking + * functions, we must evaluate these outside of the critical section. + */ #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ + __typeof__(dst) __gkn_dst = (dst); \ + __typeof__(src) __gkn_src = (src); \ int __gkn_err = 0; \ \ __uaccess_enable_tco_async(); \ - __raw_get_mem("ldr", *((type *)(dst)), \ - (__force type *)(src), __gkn_err); \ + __raw_get_mem("ldr", *((type *)(__gkn_dst)), \ + (__force type *)(__gkn_src), __gkn_err); \ __uaccess_disable_tco_async(); \ + \ if (unlikely(__gkn_err)) \ goto err_label; \ } while (0) @@ -351,11 +369,19 @@ do { \ } \ } while (0) +/* + * We must not call into the scheduler between uaccess_ttbr0_enable() and + * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions, + * we must evaluate these outside of the critical section. + */ #define __raw_put_user(x, ptr, err) \ do { \ - __chk_user_ptr(ptr); \ + __typeof__(*(ptr)) __user *__rpu_ptr = (ptr); \ + __typeof__(*(ptr)) __rpu_val = (x); \ + __chk_user_ptr(__rpu_ptr); \ + \ uaccess_ttbr0_enable(); \ - __raw_put_mem("sttr", x, ptr, err); \ + __raw_put_mem("sttr", __rpu_val, __rpu_ptr, err); \ uaccess_ttbr0_disable(); \ } while (0) @@ -380,14 +406,22 @@ do { \ #define put_user __put_user +/* + * We must not call into the scheduler between __uaccess_enable_tco_async() and + * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking + * functions, we must evaluate these outside of the critical section. + */ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ + __typeof__(dst) __pkn_dst = (dst); \ + __typeof__(src) __pkn_src = (src); \ int __pkn_err = 0; \ \ __uaccess_enable_tco_async(); \ - __raw_put_mem("str", *((type *)(src)), \ - (__force type *)(dst), __pkn_err); \ + __raw_put_mem("str", *((type *)(__pkn_src)), \ + (__force type *)(__pkn_dst), __pkn_err); \ __uaccess_disable_tco_async(); \ + \ if (unlikely(__pkn_err)) \ goto err_label; \ } while(0) From cf0b0e3712f7af90006f8317ff27278094c2c128 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 19 Nov 2021 13:16:27 +1000 Subject: [PATCH 244/358] KVM: PPC: Book3S HV: Prevent POWER7/8 TLB flush flushing SLB The POWER9 ERAT flush instruction is a SLBIA with IH=7, which is a reserved value on POWER7/8. On POWER8 this invalidates the SLB entries above index 0, similarly to SLBIA IH=0. If the SLB entries are invalidated, and then the guest is bypassed, the host SLB does not get re-loaded, so the bolted entries above 0 will be lost. This can result in kernel stack access causing a SLB fault. Kernel stack access causing a SLB fault was responsible for the infamous mega bug (search "Fix SLB reload bug"). Although since commit 48e7b7695745 ("powerpc/64s/hash: Convert SLB miss handlers to C") that starts using the kernel stack in the SLB miss handler, it might only result in an infinite loop of SLB faults. In any case it's a bug. Fix this by only executing the instruction on >= POWER9 where IH=7 is defined not to invalidate the SLB. POWER7/8 don't require this ERAT flush. Fixes: 500871125920 ("KVM: PPC: Book3S HV: Invalidate ERAT when flushing guest TLB entries") Cc: stable@vger.kernel.org # v5.2+ Signed-off-by: Nicholas Piggin Reviewed-by: Fabiano Rosas Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211119031627.577853-1-npiggin@gmail.com --- arch/powerpc/kvm/book3s_hv_builtin.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index fcf4760a3a0ea2..70b7a8f9715384 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -695,6 +695,7 @@ static void flush_guest_tlb(struct kvm *kvm) "r" (0) : "memory"); } asm volatile("ptesync": : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); } else { for (set = 0; set < kvm->arch.tlb_sets; ++set) { @@ -705,7 +706,9 @@ static void flush_guest_tlb(struct kvm *kvm) rb += PPC_BIT(51); /* increment set number */ } asm volatile("ptesync": : :"memory"); - asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. + if (cpu_has_feature(CPU_FTR_ARCH_300)) + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); } } From 5bb60ea611db1e04814426ed4bd1c95d1487678e Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 18 Nov 2021 10:39:53 +0100 Subject: [PATCH 245/358] powerpc/32: Fix hardlockup on vmap stack overflow Since the commit c118c7303ad5 ("powerpc/32: Fix vmap stack - Do not activate MMU before reading task struct") a vmap stack overflow results in a hard lockup. This is because emergency_ctx is still addressed with its virtual address allthough data MMU is not active anymore at that time. Fix it by using a physical address instead. Fixes: c118c7303ad5 ("powerpc/32: Fix vmap stack - Do not activate MMU before reading task struct") Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/ce30364fb7ccda489272af4a1612b6aa147e1d23.1637227521.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_32.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 6b1ec9e3541b90..349c4a820231bd 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -202,11 +202,11 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt) mfspr r1, SPRN_SPRG_THREAD lwz r1, TASK_CPU - THREAD(r1) slwi r1, r1, 3 - addis r1, r1, emergency_ctx@ha + addis r1, r1, emergency_ctx-PAGE_OFFSET@ha #else - lis r1, emergency_ctx@ha + lis r1, emergency_ctx-PAGE_OFFSET@ha #endif - lwz r1, emergency_ctx@l(r1) + lwz r1, emergency_ctx-PAGE_OFFSET@l(r1) addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE EXCEPTION_PROLOG_2 0 vmap_stack_overflow prepare_transfer_to_handler From c0f2077baa4113f38f008b8e912b9fb3ff8d43df Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 23 Nov 2021 08:04:34 +0100 Subject: [PATCH 246/358] x86/boot: Mark prepare_command_line() __init Fix: WARNING: modpost: vmlinux.o(.text.unlikely+0x64d0): Section mismatch in reference \ from the function prepare_command_line() to the variable .init.data:command_line The function prepare_command_line() references the variable __initdata command_line. This is often because prepare_command_line lacks a __initdata annotation or the annotation of command_line is wrong. Apparently some toolchains do different inlining decisions. Reported-by: Stephen Rothwell Signed-off-by: Borislav Petkov Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/YZySgpmBcNNM2qca@zn.tnic --- arch/x86/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c410be738ae78e..6a190c7f4d71b0 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -742,7 +742,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } -static char *prepare_command_line(void) +static char * __init prepare_command_line(void) { #ifdef CONFIG_CMDLINE_BOOL #ifdef CONFIG_CMDLINE_OVERRIDE From dce1ca0525bfdc8a69a9343bc714fbc19a2f04b3 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 23 Nov 2021 11:40:47 +0000 Subject: [PATCH 247/358] sched/scs: Reset task stack state in bringup_cpu() To hot unplug a CPU, the idle task on that CPU calls a few layers of C code before finally leaving the kernel. When KASAN is in use, poisoned shadow is left around for each of the active stack frames, and when shadow call stacks are in use. When shadow call stacks (SCS) are in use the task's saved SCS SP is left pointing at an arbitrary point within the task's shadow call stack. When a CPU is offlined than onlined back into the kernel, this stale state can adversely affect execution. Stale KASAN shadow can alias new stackframes and result in bogus KASAN warnings. A stale SCS SP is effectively a memory leak, and prevents a portion of the shadow call stack being used. Across a number of hotplug cycles the idle task's entire shadow call stack can become unusable. We previously fixed the KASAN issue in commit: e1b77c92981a5222 ("sched/kasan: remove stale KASAN poison after hotplug") ... by removing any stale KASAN stack poison immediately prior to onlining a CPU. Subsequently in commit: f1a0a376ca0c4ef1 ("sched/core: Initialize the idle task with preemption disabled") ... the refactoring left the KASAN and SCS cleanup in one-time idle thread initialization code rather than something invoked prior to each CPU being onlined, breaking both as above. We fixed SCS (but not KASAN) in commit: 63acd42c0d4942f7 ("sched/scs: Reset the shadow stack when idle_task_exit") ... but as this runs in the context of the idle task being offlined it's potentially fragile. To fix these consistently and more robustly, reset the SCS SP and KASAN shadow of a CPU's idle task immediately before we online that CPU in bringup_cpu(). This ensures the idle task always has a consistent state when it is running, and removes the need to so so when exiting an idle task. Whenever any thread is created, dup_task_struct() will give the task a stack which is free of KASAN shadow, and initialize the task's SCS SP, so there's no need to specially initialize either for idle thread within init_idle(), as this was only necessary to handle hotplug cycles. I've tested this on arm64 with: * gcc 11.1.0, defconfig +KASAN_INLINE, KASAN_STACK * clang 12.0.0, defconfig +KASAN_INLINE, KASAN_STACK, SHADOW_CALL_STACK ... offlining and onlining CPUS with: | while true; do | for C in /sys/devices/system/cpu/cpu*/online; do | echo 0 > $C; | echo 1 > $C; | done | done Fixes: f1a0a376ca0c4ef1 ("sched/core: Initialize the idle task with preemption disabled") Reported-by: Qian Cai Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Qian Cai Link: https://lore.kernel.org/lkml/20211115113310.35693-1-mark.rutland@arm.com/ --- kernel/cpu.c | 7 +++++++ kernel/sched/core.c | 4 ---- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index 192e43a874076d..407a2568f35ebb 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -587,6 +588,12 @@ static int bringup_cpu(unsigned int cpu) struct task_struct *idle = idle_thread_get(cpu); int ret; + /* + * Reset stale stack state from the last time this CPU was online. + */ + scs_task_reset(idle); + kasan_unpoison_task_stack(idle); + /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3c9b0fda64ac08..76f9deeaa94209 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8619,9 +8619,6 @@ void __init init_idle(struct task_struct *idle, int cpu) idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY; kthread_set_per_cpu(idle, cpu); - scs_task_reset(idle); - kasan_unpoison_task_stack(idle); - #ifdef CONFIG_SMP /* * It's possible that init_idle() gets called multiple times on a task, @@ -8777,7 +8774,6 @@ void idle_task_exit(void) finish_arch_post_lock_switch(); } - scs_task_reset(current); /* finish_cpu(), as ran on the BP, will clean up the active_mm state */ } From ac132852147ad303a938dda318970dd1bbdfda4e Mon Sep 17 00:00:00 2001 From: Kumar Thangavel Date: Mon, 22 Nov 2021 22:08:18 +0530 Subject: [PATCH 248/358] net/ncsi : Add payload to be 32-bit aligned to fix dropped packets Update NC-SI command handler (both standard and OEM) to take into account of payload paddings in allocating skb (in case of payload size is not 32-bit aligned). The checksum field follows payload field, without taking payload padding into account can cause checksum being truncated, leading to dropped packets. Fixes: fb4ee67529ff ("net/ncsi: Add NCSI OEM command support") Signed-off-by: Kumar Thangavel Acked-by: Samuel Mendoza-Jonas Reviewed-by: Paul Menzel Signed-off-by: David S. Miller --- net/ncsi/ncsi-cmd.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index ba9ae482141b0f..dda8b76b77988a 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -18,6 +18,8 @@ #include "internal.h" #include "ncsi-pkt.h" +static const int padding_bytes = 26; + u32 ncsi_calculate_checksum(unsigned char *data, int len) { u32 checksum = 0; @@ -213,12 +215,17 @@ static int ncsi_cmd_handler_oem(struct sk_buff *skb, { struct ncsi_cmd_oem_pkt *cmd; unsigned int len; + int payload; + /* NC-SI spec DSP_0222_1.2.0, section 8.2.2.2 + * requires payload to be padded with 0 to + * 32-bit boundary before the checksum field. + * Ensure the padding bytes are accounted for in + * skb allocation + */ + payload = ALIGN(nca->payload, 4); len = sizeof(struct ncsi_cmd_pkt_hdr) + 4; - if (nca->payload < 26) - len += 26; - else - len += nca->payload; + len += max(payload, padding_bytes); cmd = skb_put_zero(skb, len); memcpy(&cmd->mfr_id, nca->data, nca->payload); @@ -272,6 +279,7 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) struct net_device *dev = nd->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; + int payload; int len = hlen + tlen; struct sk_buff *skb; struct ncsi_request *nr; @@ -281,14 +289,14 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) return NULL; /* NCSI command packet has 16-bytes header, payload, 4 bytes checksum. + * Payload needs padding so that the checksum field following payload is + * aligned to 32-bit boundary. * The packet needs padding if its payload is less than 26 bytes to * meet 64 bytes minimal ethernet frame length. */ len += sizeof(struct ncsi_cmd_pkt_hdr) + 4; - if (nca->payload < 26) - len += 26; - else - len += nca->payload; + payload = ALIGN(nca->payload, 4); + len += max(payload, padding_bytes); /* Allocate skb */ skb = alloc_skb(len, GFP_ATOMIC); From 935dff305da2be7957a5ce8f07f45d6c4c1c6984 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 18 Nov 2021 14:37:38 +0100 Subject: [PATCH 249/358] ACPI: CPPC: Add NULL pointer check to cppc_get_perf() Check cpc_desc against NULL in cppc_get_perf(), so it doesn't crash down the road if cpc_desc is NULL. Fixes: 0654cf05d17b ("ACPI: CPPC: Introduce cppc_get_nominal_perf()") Reported-by: Kai-Heng Feng Signed-off-by: Rafael J. Wysocki Cc: 5.15+ # 5.15+ Tested-by: Kai-Heng Feng --- drivers/acpi/cppc_acpi.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index a85c351589bee5..b62c87b8ce4a99 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -998,7 +998,14 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) static int cppc_get_perf(int cpunum, enum cppc_regs reg_idx, u64 *perf) { struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum); - struct cpc_register_resource *reg = &cpc_desc->cpc_regs[reg_idx]; + struct cpc_register_resource *reg; + + if (!cpc_desc) { + pr_debug("No CPC descriptor for CPU:%d\n", cpunum); + return -ENODEV; + } + + reg = &cpc_desc->cpc_regs[reg_idx]; if (CPC_IN_PCC(reg)) { int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum); From cefcf24b4d351daf70ecd945324e200d3736821e Mon Sep 17 00:00:00 2001 From: Thomas Zeitlhofer Date: Tue, 23 Nov 2021 20:18:43 +0100 Subject: [PATCH 250/358] PM: hibernate: use correct mode for swsusp_close() Commit 39fbef4b0f77 ("PM: hibernate: Get block device exclusively in swsusp_check()") changed the opening mode of the block device to (FMODE_READ | FMODE_EXCL). In the corresponding calls to swsusp_close(), the mode is still just FMODE_READ which triggers the warning in blkdev_flush_mapping() on resume from hibernate. So, use the mode (FMODE_READ | FMODE_EXCL) also when closing the device. Fixes: 39fbef4b0f77 ("PM: hibernate: Get block device exclusively in swsusp_check()") Signed-off-by: Thomas Zeitlhofer Signed-off-by: Rafael J. Wysocki --- kernel/power/hibernate.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 9ed9b744876c12..e6af502c2fd774 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -693,7 +693,7 @@ static int load_image_and_restore(void) goto Unlock; error = swsusp_read(&flags); - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); if (!error) error = hibernation_restore(flags & SF_PLATFORM_MODE); @@ -983,7 +983,7 @@ static int software_resume(void) /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); goto Unlock; } @@ -1018,7 +1018,7 @@ static int software_resume(void) pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); goto Finish; } From 88a5045f176b78c33a269a30a7b146e99c550bd9 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Fri, 29 Oct 2021 12:24:22 -0700 Subject: [PATCH 251/358] PM: hibernate: Fix snapshot partial write lengths snapshot_write() is inappropriately limiting the amount of data that can be written in cases where a partial page has already been written. For example, one would expect to be able to write 1 byte, then 4095 bytes to the snapshot device, and have both of those complete fully (since now we're aligned to a page again). But what ends up happening is we write 1 byte, then 4094/4095 bytes complete successfully. The reason is that simple_write_to_buffer()'s second argument is the total size of the buffer, not the size of the buffer minus the offset. Since simple_write_to_buffer() accounts for the offset in its implementation, snapshot_write() can just pass the full page size directly down. Signed-off-by: Evan Green Signed-off-by: Rafael J. Wysocki --- kernel/power/user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/power/user.c b/kernel/power/user.c index 740723bb388524..ad241b4ff64c58 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -177,7 +177,7 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, if (res <= 0) goto unlock; } else { - res = PAGE_SIZE - pg_offp; + res = PAGE_SIZE; } if (!data_of(data->handle)) { From b8d8436840caa2e9b6d156e69336d2135f49f10f Mon Sep 17 00:00:00 2001 From: Tejas Upadhyay Date: Wed, 17 Nov 2021 11:33:21 +0530 Subject: [PATCH 252/358] drm/i915/gt: Hold RPM wakelock during PXP suspend selftest --r live shows failure in suspend tests when RPM wakelock is not acquired during suspend. This changes addresses below error : <4> [154.177535] RPM wakelock ref not held during HW access <4> [154.177575] WARNING: CPU: 4 PID: 5772 at drivers/gpu/drm/i915/intel_runtime_pm.h:113 fwtable_write32+0x240/0x320 [i915] <4> [154.177974] Modules linked in: i915(+) vgem drm_shmem_helper fuse snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio mei_hdcp mei_pxp x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_intel_dspcfg snd_hda_codec snd_hwdep igc snd_hda_core ttm mei_me ptp snd_pcm prime_numbers mei i2c_i801 pps_core i2c_smbus intel_lpss_pci btusb btrtl btbcm btintel bluetooth ecdh_generic ecc [last unloaded: i915] <4> [154.178143] CPU: 4 PID: 5772 Comm: i915_selftest Tainted: G U 5.15.0-rc6-CI-Patchwork_21432+ #1 <4> [154.178154] Hardware name: ASUS System Product Name/TUF GAMING Z590-PLUS WIFI, BIOS 0811 04/06/2021 <4> [154.178160] RIP: 0010:fwtable_write32+0x240/0x320 [i915] <4> [154.178604] Code: 15 7b e1 0f 0b e9 34 fe ff ff 80 3d a9 89 31 00 00 0f 85 31 fe ff ff 48 c7 c7 88 9e 4f a0 c6 05 95 89 31 00 01 e8 c0 15 7b e1 <0f> 0b e9 17 fe ff ff 8b 05 0f 83 58 e2 85 c0 0f 85 8d 00 00 00 48 <4> [154.178614] RSP: 0018:ffffc900016279f0 EFLAGS: 00010286 <4> [154.178626] RAX: 0000000000000000 RBX: ffff888204fe0ee0 RCX: 0000000000000001 <4> [154.178634] RDX: 0000000080000001 RSI: ffffffff823142b5 RDI: 00000000ffffffff <4> [154.178641] RBP: 00000000000320f0 R08: 0000000000000000 R09: c0000000ffffcd5a <4> [154.178647] R10: 00000000000f8c90 R11: ffffc90001627808 R12: 0000000000000000 <4> [154.178654] R13: 0000000040000000 R14: ffffffffa04d12e0 R15: 0000000000000000 <4> [154.178660] FS: 00007f7390aa4c00(0000) GS:ffff88844f000000(0000) knlGS:0000000000000000 <4> [154.178669] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4> [154.178675] CR2: 000055bc40595028 CR3: 0000000204474005 CR4: 0000000000770ee0 <4> [154.178682] PKRU: 55555554 <4> [154.178687] Call Trace: <4> [154.178706] intel_pxp_fini_hw+0x23/0x30 [i915] <4> [154.179284] intel_pxp_suspend+0x1f/0x30 [i915] <4> [154.179807] live_gt_resume+0x5b/0x90 [i915] Changes since V2 : - Remove boolean in intel_pxp_runtime_preapre for non-pxp configs. Solves build error Changes since V2 : - Open-code intel_pxp_runtime_suspend - Daniele - Remove boolean in intel_pxp_runtime_preapre - Daniele Changes since V1 : - split the HW access parts in gt_suspend_late - Daniele - Remove default PXP configs Signed-off-by: Tejas Upadhyay Reviewed-by: Daniele Ceraolo Spurio Fixes: 0cfab4cb3c4e ("drm/i915/pxp: Enable PXP power management") Signed-off-by: Daniele Ceraolo Spurio Link: https://patchwork.freedesktop.org/patch/msgid/20211117060321.3729343-1-tejaskumarx.surendrakumar.upadhyay@intel.com (cherry picked from commit d22d446f7a1ccd0db8c138749dde601388b2327d) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gt/intel_gt_pm.c | 7 +++-- drivers/gpu/drm/i915/pxp/intel_pxp_pm.c | 37 +++++++++++++++++-------- drivers/gpu/drm/i915/pxp/intel_pxp_pm.h | 19 +++++++++++-- 3 files changed, 46 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 524eaf67879066..795689eb3fc7bd 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -301,7 +301,7 @@ void intel_gt_suspend_prepare(struct intel_gt *gt) user_forcewake(gt, true); wait_for_suspend(gt); - intel_pxp_suspend(>->pxp, false); + intel_pxp_suspend_prepare(>->pxp); } static suspend_state_t pm_suspend_target(void) @@ -326,6 +326,7 @@ void intel_gt_suspend_late(struct intel_gt *gt) GEM_BUG_ON(gt->awake); intel_uc_suspend(>->uc); + intel_pxp_suspend(>->pxp); /* * On disabling the device, we want to turn off HW access to memory @@ -353,7 +354,7 @@ void intel_gt_suspend_late(struct intel_gt *gt) void intel_gt_runtime_suspend(struct intel_gt *gt) { - intel_pxp_suspend(>->pxp, true); + intel_pxp_runtime_suspend(>->pxp); intel_uc_runtime_suspend(>->uc); GT_TRACE(gt, "\n"); @@ -371,7 +372,7 @@ int intel_gt_runtime_resume(struct intel_gt *gt) if (ret) return ret; - intel_pxp_resume(>->pxp); + intel_pxp_runtime_resume(>->pxp); return 0; } diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c index 23fd86de5a240f..6a7d4e2ee138dd 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c @@ -7,26 +7,29 @@ #include "intel_pxp_irq.h" #include "intel_pxp_pm.h" #include "intel_pxp_session.h" +#include "i915_drv.h" -void intel_pxp_suspend(struct intel_pxp *pxp, bool runtime) +void intel_pxp_suspend_prepare(struct intel_pxp *pxp) { if (!intel_pxp_is_enabled(pxp)) return; pxp->arb_is_valid = false; - /* - * Contexts using protected objects keep a runtime PM reference, so we - * can only runtime suspend when all of them have been either closed - * or banned. Therefore, there is no need to invalidate in that - * scenario. - */ - if (!runtime) - intel_pxp_invalidate(pxp); + intel_pxp_invalidate(pxp); +} - intel_pxp_fini_hw(pxp); +void intel_pxp_suspend(struct intel_pxp *pxp) +{ + intel_wakeref_t wakeref; - pxp->hw_state_invalidated = false; + if (!intel_pxp_is_enabled(pxp)) + return; + + with_intel_runtime_pm(&pxp_to_gt(pxp)->i915->runtime_pm, wakeref) { + intel_pxp_fini_hw(pxp); + pxp->hw_state_invalidated = false; + } } void intel_pxp_resume(struct intel_pxp *pxp) @@ -44,3 +47,15 @@ void intel_pxp_resume(struct intel_pxp *pxp) intel_pxp_init_hw(pxp); } + +void intel_pxp_runtime_suspend(struct intel_pxp *pxp) +{ + if (!intel_pxp_is_enabled(pxp)) + return; + + pxp->arb_is_valid = false; + + intel_pxp_fini_hw(pxp); + + pxp->hw_state_invalidated = false; +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h index c89e97a0c3d00a..16990a3f2f8518 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h @@ -9,16 +9,29 @@ #include "intel_pxp_types.h" #ifdef CONFIG_DRM_I915_PXP -void intel_pxp_suspend(struct intel_pxp *pxp, bool runtime); +void intel_pxp_suspend_prepare(struct intel_pxp *pxp); +void intel_pxp_suspend(struct intel_pxp *pxp); void intel_pxp_resume(struct intel_pxp *pxp); +void intel_pxp_runtime_suspend(struct intel_pxp *pxp); #else -static inline void intel_pxp_suspend(struct intel_pxp *pxp, bool runtime) +static inline void intel_pxp_suspend_prepare(struct intel_pxp *pxp) +{ +} + +static inline void intel_pxp_suspend(struct intel_pxp *pxp) { } static inline void intel_pxp_resume(struct intel_pxp *pxp) { } -#endif +static inline void intel_pxp_runtime_suspend(struct intel_pxp *pxp) +{ +} +#endif +static inline void intel_pxp_runtime_resume(struct intel_pxp *pxp) +{ + intel_pxp_resume(pxp); +} #endif /* __INTEL_PXP_PM_H__ */ From 36e8f60f0867d3b70d398d653c17108459a04efe Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Tue, 23 Nov 2021 13:07:48 -0800 Subject: [PATCH 253/358] xen: detect uninitialized xenbus in xenbus_init If the xenstore page hasn't been allocated properly, reading the value of the related hvm_param (HVM_PARAM_STORE_PFN) won't actually return error. Instead, it will succeed and return zero. Instead of attempting to xen_remap a bad guest physical address, detect this condition and return early. Note that although a guest physical address of zero for HVM_PARAM_STORE_PFN is theoretically possible, it is not a good choice and zero has never been validly used in that capacity. Also recognize all bits set as an invalid value. For 32-bit Linux, any pfn above ULONG_MAX would get truncated. Pfns above ULONG_MAX should never be passed by the Xen tools to HVM guests anyway, so check for this condition and return early. Cc: stable@vger.kernel.org Signed-off-by: Stefano Stabellini Reviewed-by: Juergen Gross Reviewed-by: Jan Beulich Link: https://lore.kernel.org/r/20211123210748.1910236-1-sstabellini@kernel.org Signed-off-by: Boris Ostrovsky --- drivers/xen/xenbus/xenbus_probe.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 5967aa9372550e..fe360c33ce717f 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -949,6 +949,29 @@ static int __init xenbus_init(void) err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); if (err) goto out_error; + /* + * Uninitialized hvm_params are zero and return no error. + * Although it is theoretically possible to have + * HVM_PARAM_STORE_PFN set to zero on purpose, in reality it is + * not zero when valid. If zero, it means that Xenstore hasn't + * been properly initialized. Instead of attempting to map a + * wrong guest physical address return error. + * + * Also recognize all bits set as an invalid value. + */ + if (!v || !~v) { + err = -ENOENT; + goto out_error; + } + /* Avoid truncation on 32-bit. */ +#if BITS_PER_LONG == 32 + if (v > ULONG_MAX) { + pr_err("%s: cannot handle HVM_PARAM_STORE_PFN=%llx > ULONG_MAX\n", + __func__, v); + err = -EINVAL; + goto out_error; + } +#endif xen_store_gfn = (unsigned long)v; xen_store_interface = xen_remap(xen_store_gfn << XEN_PAGE_SHIFT, From 88459e3e42760abb2299bbf6cb1026491170e02a Mon Sep 17 00:00:00 2001 From: Mingjie Zhang Date: Tue, 23 Nov 2021 21:37:57 +0800 Subject: [PATCH 254/358] USB: serial: option: add Fibocom FM101-GL variants Update the USB serial option driver support for the Fibocom FM101-GL Cat.6 LTE modules as there are actually several different variants. - VID:PID 2cb7:01a2, FM101-GL are laptop M.2 cards (with MBIM interfaces for /Linux/Chrome OS) - VID:PID 2cb7:01a4, FM101-GL for laptop debug M.2 cards(with adb interface for /Linux/Chrome OS) 0x01a2: mbim, tty, tty, diag, gnss 0x01a4: mbim, diag, tty, adb, gnss, gnss Here are the outputs of lsusb -v and usb-devices: T: Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 86 Spd=5000 MxCh= 0 D: Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs= 1 P: Vendor=2cb7 ProdID=01a2 Rev= 5.04 S: Manufacturer=Fibocom Wireless Inc. S: Product=Fibocom FM101-GL Module S: SerialNumber=673326ce C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=896mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=(none) I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=(none) I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=(none) I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=40 Driver=(none) Bus 002 Device 084: ID 2cb7:01a2 Fibocom Wireless Inc. Fibocom FM101-GL Module Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 3.20 bDeviceClass 0 bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 9 idVendor 0x2cb7 idProduct 0x01a2 bcdDevice 5.04 iManufacturer 1 Fibocom Wireless Inc. iProduct 2 Fibocom FM101-GL Module iSerial 3 673326ce bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 0x015d bNumInterfaces 6 bConfigurationValue 1 iConfiguration 4 MBIM_DUN_DUN_DIAG_NMEA bmAttributes 0xa0 (Bus Powered) Remote Wakeup MaxPower 896mA Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 0 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 14 bFunctionProtocol 0 iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 14 bInterfaceProtocol 0 iInterface 5 Fibocom FM101-GL LTE Modem CDC Header: bcdCDC 1.10 CDC Union: bMasterInterface 0 bSlaveInterface 1 CDC MBIM: bcdMBIMVersion 1.00 wMaxControlMessage 4096 bNumberFilters 32 bMaxFilterSize 128 wMaxSegmentSize 2048 bmNetworkCapabilities 0x20 8-byte ntb input size CDC MBIM Extended: bcdMBIMExtendedVersion 1.00 bMaxOutstandingCommandMessages 64 wMTU 1500 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 9 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 0 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 1 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 6 MBIM Data Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x8e EP 14 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 6 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x0f EP 15 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 2 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 2 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 3 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x84 EP 4 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 4 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 48 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x86 EP 6 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 5 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 0 bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x88 EP 8 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 T: Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 85 Spd=5000 MxCh= 0 D: Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs= 1 P: Vendor=2cb7 ProdID=01a4 Rev= 5.04 S: Manufacturer=Fibocom Wireless Inc. S: Product=Fibocom FM101-GL Module S: SerialNumber=673326ce C:* #Ifs= 7 Cfg#= 1 Atr=a0 MxPwr=896mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=(none) I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=(none) I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=40 Driver=(none) I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=40 Driver=(none) Bus 002 Device 085: ID 2cb7:01a4 Fibocom Wireless Inc. Fibocom FM101-GL Module Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 3.20 bDeviceClass 0 bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 9 idVendor 0x2cb7 idProduct 0x01a4 bcdDevice 5.04 iManufacturer 1 Fibocom Wireless Inc. iProduct 2 Fibocom FM101-GL Module iSerial 3 673326ce bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 0x0180 bNumInterfaces 7 bConfigurationValue 1 iConfiguration 4 MBIM_DIAG_DUN_ADB_GNSS_GNSS bmAttributes 0xa0 (Bus Powered) Remote Wakeup MaxPower 896mA Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 0 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 14 bFunctionProtocol 0 iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 14 bInterfaceProtocol 0 iInterface 5 Fibocom FM101-GL LTE Modem CDC Header: bcdCDC 1.10 CDC Union: bMasterInterface 0 bSlaveInterface 1 CDC MBIM: bcdMBIMVersion 1.00 wMaxControlMessage 4096 bNumberFilters 32 bMaxFilterSize 128 wMaxSegmentSize 2048 bmNetworkCapabilities 0x20 8-byte ntb input size CDC MBIM Extended: bcdMBIMExtendedVersion 1.00 bMaxOutstandingCommandMessages 64 wMTU 1500 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 9 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 0 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 1 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 6 MBIM Data Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x8e EP 14 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 6 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x0f EP 15 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 2 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 2 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 48 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 3 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x84 EP 4 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 4 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 66 bInterfaceProtocol 1 iInterface 8 ADB Interface Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 5 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 0 bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x86 EP 6 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 6 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 0 bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x89 EP 9 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x88 EP 8 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x05 EP 5 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Signed-off-by: Mingjie Zhang Link: https://lore.kernel.org/r/20211123133757.37475-1-superzmj@fibocom.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 0902e79c8493f4..546fce4617a854 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2096,6 +2096,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */ + .driver_info = RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ From a1de97fe296c52eafc6590a3506f4bbd44ecb19a Mon Sep 17 00:00:00 2001 From: Yang Xu Date: Wed, 24 Nov 2021 10:06:02 -0800 Subject: [PATCH 255/358] xfs: Fix the free logic of state in xfs_attr_node_hasname When testing xfstests xfs/126 on lastest upstream kernel, it will hang on some machine. Adding a getxattr operation after xattr corrupted, I can reproduce it 100%. The deadlock as below: [983.923403] task:setfattr state:D stack: 0 pid:17639 ppid: 14687 flags:0x00000080 [ 983.923405] Call Trace: [ 983.923410] __schedule+0x2c4/0x700 [ 983.923412] schedule+0x37/0xa0 [ 983.923414] schedule_timeout+0x274/0x300 [ 983.923416] __down+0x9b/0xf0 [ 983.923451] ? xfs_buf_find.isra.29+0x3c8/0x5f0 [xfs] [ 983.923453] down+0x3b/0x50 [ 983.923471] xfs_buf_lock+0x33/0xf0 [xfs] [ 983.923490] xfs_buf_find.isra.29+0x3c8/0x5f0 [xfs] [ 983.923508] xfs_buf_get_map+0x4c/0x320 [xfs] [ 983.923525] xfs_buf_read_map+0x53/0x310 [xfs] [ 983.923541] ? xfs_da_read_buf+0xcf/0x120 [xfs] [ 983.923560] xfs_trans_read_buf_map+0x1cf/0x360 [xfs] [ 983.923575] ? xfs_da_read_buf+0xcf/0x120 [xfs] [ 983.923590] xfs_da_read_buf+0xcf/0x120 [xfs] [ 983.923606] xfs_da3_node_read+0x1f/0x40 [xfs] [ 983.923621] xfs_da3_node_lookup_int+0x69/0x4a0 [xfs] [ 983.923624] ? kmem_cache_alloc+0x12e/0x270 [ 983.923637] xfs_attr_node_hasname+0x6e/0xa0 [xfs] [ 983.923651] xfs_has_attr+0x6e/0xd0 [xfs] [ 983.923664] xfs_attr_set+0x273/0x320 [xfs] [ 983.923683] xfs_xattr_set+0x87/0xd0 [xfs] [ 983.923686] __vfs_removexattr+0x4d/0x60 [ 983.923688] __vfs_removexattr_locked+0xac/0x130 [ 983.923689] vfs_removexattr+0x4e/0xf0 [ 983.923690] removexattr+0x4d/0x80 [ 983.923693] ? __check_object_size+0xa8/0x16b [ 983.923695] ? strncpy_from_user+0x47/0x1a0 [ 983.923696] ? getname_flags+0x6a/0x1e0 [ 983.923697] ? _cond_resched+0x15/0x30 [ 983.923699] ? __sb_start_write+0x1e/0x70 [ 983.923700] ? mnt_want_write+0x28/0x50 [ 983.923701] path_removexattr+0x9b/0xb0 [ 983.923702] __x64_sys_removexattr+0x17/0x20 [ 983.923704] do_syscall_64+0x5b/0x1a0 [ 983.923705] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 983.923707] RIP: 0033:0x7f080f10ee1b When getxattr calls xfs_attr_node_get function, xfs_da3_node_lookup_int fails with EFSCORRUPTED in xfs_attr_node_hasname because we have use blocktrash to random it in xfs/126. So it free state in internal and xfs_attr_node_get doesn't do xfs_buf_trans release job. Then subsequent removexattr will hang because of it. This bug was introduced by kernel commit 07120f1abdff ("xfs: Add xfs_has_attr and subroutines"). It adds xfs_attr_node_hasname helper and said caller will be responsible for freeing the state in this case. But xfs_attr_node_hasname will free state itself instead of caller if xfs_da3_node_lookup_int fails. Fix this bug by moving the step of free state into caller. Also, use "goto error/out" instead of returning error directly in xfs_attr_node_addname_find_attr and xfs_attr_node_removename_setup function because we should free state ourselves. Fixes: 07120f1abdff ("xfs: Add xfs_has_attr and subroutines") Signed-off-by: Yang Xu Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_attr.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index fbc9d816882ce6..23523b802539e1 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -1077,21 +1077,18 @@ xfs_attr_node_hasname( state = xfs_da_state_alloc(args); if (statep != NULL) - *statep = NULL; + *statep = state; /* * Search to see if name exists, and get back a pointer to it. */ error = xfs_da3_node_lookup_int(state, &retval); - if (error) { - xfs_da_state_free(state); - return error; - } + if (error) + retval = error; - if (statep != NULL) - *statep = state; - else + if (!statep) xfs_da_state_free(state); + return retval; } @@ -1112,7 +1109,7 @@ xfs_attr_node_addname_find_attr( */ retval = xfs_attr_node_hasname(args, &dac->da_state); if (retval != -ENOATTR && retval != -EEXIST) - return retval; + goto error; if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE)) goto error; @@ -1337,7 +1334,7 @@ int xfs_attr_node_removename_setup( error = xfs_attr_node_hasname(args, state); if (error != -EEXIST) - return error; + goto out; error = 0; ASSERT((*state)->path.blk[(*state)->path.active - 1].bp != NULL); From 1090427bf18f9835b3ccbd36edf43f2509444e27 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Nov 2021 10:06:02 -0800 Subject: [PATCH 256/358] xfs: remove xfs_inew_wait With the remove of xfs_dqrele_all_inodes, xfs_inew_wait and all the infrastructure used to wake the XFS_INEW bit waitqueue is unused. Reported-by: kernel test robot Fixes: 777eb1fa857e ("xfs: remove xfs_dqrele_all_inodes") Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_icache.c | 21 --------------------- fs/xfs/xfs_inode.h | 4 +--- 2 files changed, 1 insertion(+), 24 deletions(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index e1472004170e8f..da4af2142a2b49 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -289,22 +289,6 @@ xfs_perag_clear_inode_tag( trace_xfs_perag_clear_inode_tag(mp, pag->pag_agno, tag, _RET_IP_); } -static inline void -xfs_inew_wait( - struct xfs_inode *ip) -{ - wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT); - DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT); - - do { - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - if (!xfs_iflags_test(ip, XFS_INEW)) - break; - schedule(); - } while (true); - finish_wait(wq, &wait.wq_entry); -} - /* * When we recycle a reclaimable inode, we need to re-initialise the VFS inode * part of the structure. This is made more complex by the fact we store @@ -368,18 +352,13 @@ xfs_iget_recycle( ASSERT(!rwsem_is_locked(&inode->i_rwsem)); error = xfs_reinit_inode(mp, inode); if (error) { - bool wake; - /* * Re-initializing the inode failed, and we are in deep * trouble. Try to re-add it to the reclaim list. */ rcu_read_lock(); spin_lock(&ip->i_flags_lock); - wake = !!__xfs_iflags_test(ip, XFS_INEW); ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM); - if (wake) - wake_up_bit(&ip->i_flags, __XFS_INEW_BIT); ASSERT(ip->i_flags & XFS_IRECLAIMABLE); spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index e635a3d64cba21..c447bf04205a8e 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -231,8 +231,7 @@ static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip) #define XFS_IRECLAIM (1 << 0) /* started reclaiming this inode */ #define XFS_ISTALE (1 << 1) /* inode has been staled */ #define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */ -#define __XFS_INEW_BIT 3 /* inode has just been allocated */ -#define XFS_INEW (1 << __XFS_INEW_BIT) +#define XFS_INEW (1 << 3) /* inode has just been allocated */ #define XFS_IPRESERVE_DM_FIELDS (1 << 4) /* has legacy DMAPI fields set */ #define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */ #define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */ @@ -492,7 +491,6 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip) xfs_iflags_clear(ip, XFS_INEW); barrier(); unlock_new_inode(VFS_I(ip)); - wake_up_bit(&ip->i_flags, __XFS_INEW_BIT); } static inline void xfs_setup_existing_inode(struct xfs_inode *ip) From 5ad448ce2976f829d95dcae5e6e91f6686b0e4de Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 24 Nov 2021 10:15:47 -0800 Subject: [PATCH 257/358] iomap: iomap_read_inline_data cleanup Change iomap_read_inline_data to return 0 or an error code; this simplifies the callers. Add a description. Signed-off-by: Andreas Gruenbacher Reviewed-by: Christoph Hellwig [djwong: document the return value of iomap_read_inline_data explicitly] Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index fe10d8a30f6bdf..71a36ae120ee8a 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -205,7 +205,16 @@ struct iomap_readpage_ctx { struct readahead_control *rac; }; -static loff_t iomap_read_inline_data(const struct iomap_iter *iter, +/** + * iomap_read_inline_data - copy inline data into the page cache + * @iter: iteration structure + * @page: page to copy to + * + * Copy the inline data in @iter into @page and zero out the rest of the page. + * Only a single IOMAP_INLINE extent is allowed at the end of each file. + * Returns zero for success to complete the read, or the usual negative errno. + */ +static int iomap_read_inline_data(const struct iomap_iter *iter, struct page *page) { const struct iomap *iomap = iomap_iter_srcmap(iter); @@ -214,7 +223,7 @@ static loff_t iomap_read_inline_data(const struct iomap_iter *iter, void *addr; if (PageUptodate(page)) - return PAGE_SIZE - poff; + return 0; if (WARN_ON_ONCE(size > PAGE_SIZE - poff)) return -EIO; @@ -231,7 +240,7 @@ static loff_t iomap_read_inline_data(const struct iomap_iter *iter, memset(addr + size, 0, PAGE_SIZE - poff - size); kunmap_local(addr); iomap_set_range_uptodate(page, poff, PAGE_SIZE - poff); - return PAGE_SIZE - poff; + return 0; } static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter, @@ -256,13 +265,8 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter, unsigned poff, plen; sector_t sector; - if (iomap->type == IOMAP_INLINE) { - loff_t ret = iomap_read_inline_data(iter, page); - - if (ret < 0) - return ret; - return 0; - } + if (iomap->type == IOMAP_INLINE) + return iomap_read_inline_data(iter, page); /* zero post-eof blocks as the page may be mapped */ iop = iomap_page_create(iter->inode, page); @@ -587,15 +591,10 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, static int iomap_write_begin_inline(const struct iomap_iter *iter, struct page *page) { - int ret; - /* needs more work for the tailpacking case; disable for now */ if (WARN_ON_ONCE(iomap_iter_srcmap(iter)->offset != 0)) return -EIO; - ret = iomap_read_inline_data(iter, page); - if (ret < 0) - return ret; - return 0; + return iomap_read_inline_data(iter, page); } static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos, From d3a21f7e353dc8d6939383578f3bd45b4ae3a946 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Thu, 4 Nov 2021 16:15:43 -0400 Subject: [PATCH 258/358] drm/amdgpu: Fix MMIO HDP flush on SRIOV Disable HDP register remapping on SRIOV and set rmmio_remap.reg_offset to the fixed address of the VF register for hdp_v*_flush_hdp. Signed-off-by: Felix Kuehling Tested-by: Bokun Zhang Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c | 4 ++++ drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c | 4 ++++ drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c | 4 +++- drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c | 4 ++++ drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 4 +++- drivers/gpu/drm/amd/amdgpu/nv.c | 8 +++++--- drivers/gpu/drm/amd/amdgpu/soc15.c | 8 +++++--- 7 files changed, 28 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index 4ecd2b5808cee0..ee7cab37dfd58a 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -359,6 +359,10 @@ static void nbio_v2_3_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_CONFIG_CNTL, data); + + if (amdgpu_sriov_vf(adev)) + adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, + mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; } #define NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT 0x00000000 // off by default, no gains over L1 diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c index 0d2d629e2d6a22..4bbacf1be25a41 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c @@ -276,6 +276,10 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_CI_CNTL, data); + + if (amdgpu_sriov_vf(adev)) + adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, + mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; } static void nbio_v6_1_program_ltr(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c index 3c00666a13e16b..37a4039fdfc53d 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c @@ -273,7 +273,9 @@ const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg = { static void nbio_v7_0_init_registers(struct amdgpu_device *adev) { - + if (amdgpu_sriov_vf(adev)) + adev->rmmio_remap.reg_offset = + SOC15_REG_OFFSET(NBIO, 0, mmHDP_MEM_COHERENCY_FLUSH_CNTL) << 2; } const struct amdgpu_nbio_funcs nbio_v7_0_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c index 8f2a315e7c73ce..3444332ea1104e 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c @@ -371,6 +371,10 @@ static void nbio_v7_2_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_PCIE_PORT(SOC15_REG_OFFSET(NBIO, 0, regPCIE_CONFIG_CNTL), data); } + + if (amdgpu_sriov_vf(adev)) + adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, + regBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; } const struct amdgpu_nbio_funcs nbio_v7_2_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index b8bd03d16dbaf1..e96516d3fd45eb 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -362,7 +362,9 @@ const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg_ald = { static void nbio_v7_4_init_registers(struct amdgpu_device *adev) { - + if (amdgpu_sriov_vf(adev)) + adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, + mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; } static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 59eafa31c626ac..a6659d9ecdd220 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -731,8 +731,10 @@ static int nv_common_early_init(void *handle) #define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE) struct amdgpu_device *adev = (struct amdgpu_device *)handle; - adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET; - adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET; + if (!amdgpu_sriov_vf(adev)) { + adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET; + adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET; + } adev->smc_rreg = NULL; adev->smc_wreg = NULL; adev->pcie_rreg = &nv_pcie_rreg; @@ -1032,7 +1034,7 @@ static int nv_common_hw_init(void *handle) * for the purpose of expose those registers * to process space */ - if (adev->nbio.funcs->remap_hdp_registers) + if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev)) adev->nbio.funcs->remap_hdp_registers(adev); /* enable the doorbell aperture */ nv_enable_doorbell_aperture(adev, true); diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 0c316a2d42ed24..de9b55383e9f80 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -971,8 +971,10 @@ static int soc15_common_early_init(void *handle) #define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE) struct amdgpu_device *adev = (struct amdgpu_device *)handle; - adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET; - adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET; + if (!amdgpu_sriov_vf(adev)) { + adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET; + adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET; + } adev->smc_rreg = NULL; adev->smc_wreg = NULL; adev->pcie_rreg = &soc15_pcie_rreg; @@ -1285,7 +1287,7 @@ static int soc15_common_hw_init(void *handle) * for the purpose of expose those registers * to process space */ - if (adev->nbio.funcs->remap_hdp_registers) + if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev)) adev->nbio.funcs->remap_hdp_registers(adev); /* enable the doorbell aperture */ From 4eb6bb649fe041472ddd00f94870c0b86ef49d34 Mon Sep 17 00:00:00 2001 From: xinhui pan Date: Fri, 19 Nov 2021 18:08:31 +0800 Subject: [PATCH 259/358] drm/amdgpu: Fix double free of dmabuf MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit amdgpu_amdkfd_gpuvm_free_memory_of_gpu drop dmabuf reference increased in amdgpu_gem_prime_export. amdgpu_bo_destroy drop dmabuf reference increased in amdgpu_gem_prime_import. So remove this extra dma_buf_put to avoid double free. Signed-off-by: xinhui pan Tested-by: Felix Kuehling Reviewed-by: Felix Kuehling Acked-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 71acd577803ec3..71a6a9ef54ac79 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -646,12 +646,6 @@ kfd_mem_attach_dmabuf(struct amdgpu_device *adev, struct kgd_mem *mem, if (IS_ERR(gobj)) return PTR_ERR(gobj); - /* Import takes an extra reference on the dmabuf. Drop it now to - * avoid leaking it. We only need the one reference in - * kgd_mem->dmabuf. - */ - dma_buf_put(mem->dmabuf); - *bo = gem_to_amdgpu_bo(gobj); (*bo)->flags |= AMDGPU_GEM_CREATE_PREEMPTIBLE; (*bo)->parent = amdgpu_bo_ref(mem->bo); From 6eff272dbee7ad444c491c9a96d49e78e91e2161 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Mon, 8 Nov 2021 16:49:48 -0500 Subject: [PATCH 260/358] drm/amd/display: Fix DPIA outbox timeout after GPU reset [Why] The HW interrupt gets disabled after GPU reset so we don't receive notifications for HPD or AUX from DMUB - leading to timeout and black screen with (or without) DPIA links connected. [How] Re-enable the interrupt after GPU reset like we do for the other DC interrupts. Fixes: 81927e2808be ("drm/amd/display: Support for DMUB AUX") Reviewed-by: Jude Shih Acked-by: Qingqing Zhuo Signed-off-by: Nicholas Kazlauskas Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c27cb47bc9881a..1dee25326e2be1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2561,6 +2561,8 @@ static int dm_resume(void *handle) if (amdgpu_in_reset(adev)) { dc_state = dm->cached_dc_state; + amdgpu_dm_outbox_init(adev); + r = dm_dmub_hw_init(adev); if (r) DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r); From 21431f70f6014f81b0d118ff4fcee12b00b9dd70 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Tue, 9 Nov 2021 11:24:10 -0500 Subject: [PATCH 261/358] drm/amd/display: Set plane update flags for all planes in reset [Why] We're only setting the flags on stream[0]'s planes so this logic fails if we have more than one stream in the state. This can cause a page flip timeout with multiple displays in the configuration. [How] Index into the stream_status array using the stream index - it's a 1:1 mapping. Fixes: cdaae8371aa9 ("drm/amd/display: Handle GPU reset for DC block") Reviewed-by: Harry Wentland Acked-by: Qingqing Zhuo Signed-off-by: Nicholas Kazlauskas Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 1dee25326e2be1..b3210928b9cbdc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2574,8 +2574,8 @@ static int dm_resume(void *handle) for (i = 0; i < dc_state->stream_count; i++) { dc_state->streams[i]->mode_changed = true; - for (j = 0; j < dc_state->stream_status->plane_count; j++) { - dc_state->stream_status->plane_states[j]->update_flags.raw + for (j = 0; j < dc_state->stream_status[i].plane_count; j++) { + dc_state->stream_status[i].plane_states[j]->update_flags.raw = 0xffffffff; } } From 2276ee6d1bf9e6a3b7dfbeef05cf71c784ff8c64 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Tue, 9 Nov 2021 16:03:21 -0500 Subject: [PATCH 262/358] drm/amd/display: Reset link encoder assignments for GPU reset [Why] A warning appears in the log on GPU reset for link_enc_cfg_link_encs_assign for the following condition: ASSERT(state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].valid == false); This is not expected behavior and may result in link encoders being incorrectly assigned. [How] The dc->current_state is backed up into dm->cached_dc_state before we commit 0 streams. DC will clear link encoder assignments on the real state but the changes won't propagate over to the copy we made before the 0 streams commit. DC expects that link encoder assignments are *not* valid when committing a state, so as a workaround it needs to be cleared before passing it back into DC. Reviewed-by: Harry Wentland Acked-by: Qingqing Zhuo Signed-off-by: Nicholas Kazlauskas Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b3210928b9cbdc..e439f9d7c3f1d0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2561,6 +2561,20 @@ static int dm_resume(void *handle) if (amdgpu_in_reset(adev)) { dc_state = dm->cached_dc_state; + /* + * The dc->current_state is backed up into dm->cached_dc_state + * before we commit 0 streams. + * + * DC will clear link encoder assignments on the real state + * but the changes won't propagate over to the copy we made + * before the 0 streams commit. + * + * DC expects that link encoder assignments are *not* valid + * when committing a state, so as a workaround it needs to be + * cleared here. + */ + link_enc_cfg_init(dm->dc, dc_state); + amdgpu_dm_outbox_init(adev); r = dm_dmub_hw_init(adev); From 2da8f0beece08a5c3c2e20c0e38e1a4bbc153f9e Mon Sep 17 00:00:00 2001 From: Yi-Ling Chen Date: Wed, 10 Nov 2021 14:26:53 +0800 Subject: [PATCH 263/358] drm/amd/display: Fixed DSC would not PG after removing DSC stream [WHY] Due to pass the wrong parameter down to the enable_stream_gating(), it would cause the DSC of the removing stream would not be PG. [HOW] To pass the correct parameter down th the enable_stream_gating(). Reviewed-by: Anthony Koo Acked-by: Qingqing Zhuo Signed-off-by: Yi-Ling Chen Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 0b788d794fb334..04d7bddc915bde 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1637,7 +1637,7 @@ void dcn10_reset_hw_ctx_wrap( dcn10_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state); if (hws->funcs.enable_stream_gating) - hws->funcs.enable_stream_gating(dc, pipe_ctx); + hws->funcs.enable_stream_gating(dc, pipe_ctx_old); if (old_clk) old_clk->funcs->cs_power_down(old_clk); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 4f88376a118f81..e6af99ae3d9f54 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2270,7 +2270,7 @@ void dcn20_reset_hw_ctx_wrap( dcn20_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state); if (hws->funcs.enable_stream_gating) - hws->funcs.enable_stream_gating(dc, pipe_ctx); + hws->funcs.enable_stream_gating(dc, pipe_ctx_old); if (old_clk) old_clk->funcs->cs_power_down(old_clk); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 5dd1ce9ddb539a..4d4ac4ceb1e87d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -602,7 +602,7 @@ void dcn31_reset_hw_ctx_wrap( dcn31_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state); if (hws->funcs.enable_stream_gating) - hws->funcs.enable_stream_gating(dc, pipe_ctx); + hws->funcs.enable_stream_gating(dc, pipe_ctx_old); if (old_clk) old_clk->funcs->cs_power_down(old_clk); } From 271fd38ce56d6f143ddbd7bb999ad337d151b561 Mon Sep 17 00:00:00 2001 From: shaoyunl Date: Thu, 18 Nov 2021 11:43:16 -0500 Subject: [PATCH 264/358] drm/amdgpu: move kfd post_reset out of reset_sriov function Fixes: 9f4f2c1a3524 ("drm/amd/amdgpu: fix the kfd pre_reset sequence in sriov") For sriov XGMI configuration, the host driver will handle the hive reset, so in guest side, the reset_sriov only be called once on one device. This will make kfd post_reset unblanced with kfd pre_reset since kfd pre_reset already been moved out of reset_sriov function. Move kfd post_reset out of reset_sriov function to make them balance . Signed-off-by: shaoyunl Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 188accb7124937..d94fa748e6bbe6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4316,7 +4316,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, amdgpu_irq_gpu_reset_resume_helper(adev); r = amdgpu_ib_ring_tests(adev); - amdgpu_amdkfd_post_reset(adev); error: if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) { @@ -5089,7 +5088,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, tmp_vram_lost_counter = atomic_read(&((adev)->vram_lost_counter)); /* Actual ASIC resets if needed.*/ - /* TODO Implement XGMI hive reset logic for SRIOV */ + /* Host driver will handle XGMI hive reset for SRIOV */ if (amdgpu_sriov_vf(adev)) { r = amdgpu_device_reset_sriov(adev, job ? false : true); if (r) @@ -5149,8 +5148,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, skip_sched_resume: list_for_each_entry(tmp_adev, device_list_handle, reset_list) { - /* unlock kfd: SRIOV would do it separately */ - if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev)) + /* unlock kfd */ + if (!need_emergency_restart) amdgpu_amdkfd_post_reset(tmp_adev); /* kfd_post_reset will do nothing if kfd device is not initialized, From 244ee398855df2adc7d3ac5702b58424a5f684cc Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 18 Nov 2021 14:33:23 -0500 Subject: [PATCH 265/358] drm/amdgpu/gfx10: add wraparound gpu counter check for APUs as well Apply the same check we do for dGPUs for APUs as well. Acked-by: Luben Tuikov Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index e7dfeb466a0e4d..dbe7442fb25cc4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -7707,8 +7707,19 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): - clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh) | - ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL); + preempt_disable(); + clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh); + clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh); + hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh); + /* The SMUIO TSC clock frequency is 100MHz, which sets 32-bit carry over + * roughly every 42 seconds. + */ + if (hi_check != clock_hi) { + clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh); + clock_hi = hi_check; + } + preempt_enable(); + clock = clock_lo | (clock_hi << 32ULL); break; default: preempt_disable(); From 53af98c091bc42fd9ec64cfabc40da4e5f3aae93 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 18 Nov 2021 14:50:37 -0500 Subject: [PATCH 266/358] drm/amdgpu/gfx9: switch to golden tsc registers for renoir+ Renoir and newer gfx9 APUs have new TSC register that is not part of the gfxoff tile, so it can be read without needing to disable gfx off. Acked-by: Luben Tuikov Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 46 ++++++++++++++++++++------- 1 file changed, 35 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index b4b80f27b89409..34478bcc4d095c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -140,6 +140,11 @@ MODULE_FIRMWARE("amdgpu/aldebaran_rlc.bin"); #define mmTCP_CHAN_STEER_5_ARCT 0x0b0c #define mmTCP_CHAN_STEER_5_ARCT_BASE_IDX 0 +#define mmGOLDEN_TSC_COUNT_UPPER_Renoir 0x0025 +#define mmGOLDEN_TSC_COUNT_UPPER_Renoir_BASE_IDX 1 +#define mmGOLDEN_TSC_COUNT_LOWER_Renoir 0x0026 +#define mmGOLDEN_TSC_COUNT_LOWER_Renoir_BASE_IDX 1 + enum ta_ras_gfx_subblock { /*CPC*/ TA_RAS_BLOCK__GFX_CPC_INDEX_START = 0, @@ -4238,19 +4243,38 @@ static uint64_t gfx_v9_0_kiq_read_clock(struct amdgpu_device *adev) static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev) { - uint64_t clock; + uint64_t clock, clock_lo, clock_hi, hi_check; - amdgpu_gfx_off_ctrl(adev, false); - mutex_lock(&adev->gfx.gpu_clock_mutex); - if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 0, 1) && amdgpu_sriov_runtime(adev)) { - clock = gfx_v9_0_kiq_read_clock(adev); - } else { - WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1); - clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) | - ((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL); + switch (adev->ip_versions[GC_HWIP][0]) { + case IP_VERSION(9, 3, 0): + preempt_disable(); + clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Renoir); + clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Renoir); + hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Renoir); + /* The SMUIO TSC clock frequency is 100MHz, which sets 32-bit carry over + * roughly every 42 seconds. + */ + if (hi_check != clock_hi) { + clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Renoir); + clock_hi = hi_check; + } + preempt_enable(); + clock = clock_lo | (clock_hi << 32ULL); + break; + default: + amdgpu_gfx_off_ctrl(adev, false); + mutex_lock(&adev->gfx.gpu_clock_mutex); + if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 0, 1) && amdgpu_sriov_runtime(adev)) { + clock = gfx_v9_0_kiq_read_clock(adev); + } else { + WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1); + clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) | + ((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL); + } + mutex_unlock(&adev->gfx.gpu_clock_mutex); + amdgpu_gfx_off_ctrl(adev, true); + break; } - mutex_unlock(&adev->gfx.gpu_clock_mutex); - amdgpu_gfx_off_ctrl(adev, true); return clock; } From 4d62555f624582e60be416fbc4772cd3fcd12b1a Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Fri, 12 Nov 2021 19:05:08 -0500 Subject: [PATCH 267/358] drm/amdgpu: IH process reset count when restart MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Otherwise when IH process restart, count is zero, the loop will not exit to wake_up_all after processing AMDGPU_IH_MAX_NUM_IVS interrupts. Cc: stable@vger.kernel.org Signed-off-by: Philip Yang Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c index f3d62e196901a8..0c7963dfacad1e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c @@ -223,7 +223,7 @@ int amdgpu_ih_wait_on_checkpoint_process(struct amdgpu_device *adev, */ int amdgpu_ih_process(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih) { - unsigned int count = AMDGPU_IH_MAX_NUM_IVS; + unsigned int count; u32 wptr; if (!ih->enabled || adev->shutdown) @@ -232,6 +232,7 @@ int amdgpu_ih_process(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih) wptr = amdgpu_ih_get_wptr(adev, ih); restart_ih: + count = AMDGPU_IH_MAX_NUM_IVS; DRM_DEBUG("%s: rptr %d, wptr %d\n", __func__, ih->rptr, wptr); /* Order reading of wptr vs. reading of IH ring data */ From cda0817b41bdd509c37036c482a60230a5063772 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Tue, 16 Nov 2021 11:45:32 -0500 Subject: [PATCH 268/358] drm/amdkfd: process exit and retry fault race kfd_process_wq_release drain retry fault to ensure no retry fault comes after removing kfd process from the hash table, otherwise svm page fault handler will fail to recover the fault and dump GPU vm fault log. Refactor deferred list work to get_task_mm and take mmap write lock to handle all ranges, and avoid mm is gone while inserting mmu notifier. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 63 ++++++++++++++++------------ 1 file changed, 36 insertions(+), 27 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 16137c4247bbec..b553c34cc99b7b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1990,43 +1990,42 @@ static void svm_range_deferred_list_work(struct work_struct *work) struct svm_range_list *svms; struct svm_range *prange; struct mm_struct *mm; + struct kfd_process *p; svms = container_of(work, struct svm_range_list, deferred_list_work); pr_debug("enter svms 0x%p\n", svms); + p = container_of(svms, struct kfd_process, svms); + /* Avoid mm is gone when inserting mmu notifier */ + mm = get_task_mm(p->lead_thread); + if (!mm) { + pr_debug("svms 0x%p process mm gone\n", svms); + return; + } +retry: + mmap_write_lock(mm); + + /* Checking for the need to drain retry faults must be inside + * mmap write lock to serialize with munmap notifiers. + */ + if (unlikely(READ_ONCE(svms->drain_pagefaults))) { + WRITE_ONCE(svms->drain_pagefaults, false); + mmap_write_unlock(mm); + svm_range_drain_retry_fault(svms); + goto retry; + } + spin_lock(&svms->deferred_list_lock); while (!list_empty(&svms->deferred_range_list)) { prange = list_first_entry(&svms->deferred_range_list, struct svm_range, deferred_list); + list_del_init(&prange->deferred_list); spin_unlock(&svms->deferred_list_lock); + pr_debug("prange 0x%p [0x%lx 0x%lx] op %d\n", prange, prange->start, prange->last, prange->work_item.op); - mm = prange->work_item.mm; -retry: - mmap_write_lock(mm); mutex_lock(&svms->lock); - - /* Checking for the need to drain retry faults must be in - * mmap write lock to serialize with munmap notifiers. - * - * Remove from deferred_list must be inside mmap write lock, - * otherwise, svm_range_list_lock_and_flush_work may hold mmap - * write lock, and continue because deferred_list is empty, then - * deferred_list handle is blocked by mmap write lock. - */ - spin_lock(&svms->deferred_list_lock); - if (unlikely(svms->drain_pagefaults)) { - svms->drain_pagefaults = false; - spin_unlock(&svms->deferred_list_lock); - mutex_unlock(&svms->lock); - mmap_write_unlock(mm); - svm_range_drain_retry_fault(svms); - goto retry; - } - list_del_init(&prange->deferred_list); - spin_unlock(&svms->deferred_list_lock); - mutex_lock(&prange->migrate_mutex); while (!list_empty(&prange->child_list)) { struct svm_range *pchild; @@ -2042,12 +2041,13 @@ static void svm_range_deferred_list_work(struct work_struct *work) svm_range_handle_list_op(svms, prange); mutex_unlock(&svms->lock); - mmap_write_unlock(mm); spin_lock(&svms->deferred_list_lock); } spin_unlock(&svms->deferred_list_lock); + mmap_write_unlock(mm); + mmput(mm); pr_debug("exit svms 0x%p\n", svms); } @@ -2600,7 +2600,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, p = kfd_lookup_process_by_pasid(pasid); if (!p) { pr_debug("kfd process not founded pasid 0x%x\n", pasid); - return -ESRCH; + return 0; } if (!p->xnack_enabled) { pr_debug("XNACK not enabled for pasid 0x%x\n", pasid); @@ -2611,10 +2611,12 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, pr_debug("restoring svms 0x%p fault address 0x%llx\n", svms, addr); + /* p->lead_thread is available as kfd_process_wq_release flush the work + * before releasing task ref. + */ mm = get_task_mm(p->lead_thread); if (!mm) { pr_debug("svms 0x%p failed to get mm\n", svms); - r = -ESRCH; goto out; } @@ -2741,6 +2743,13 @@ void svm_range_list_fini(struct kfd_process *p) /* Ensure list work is finished before process is destroyed */ flush_work(&p->svms.deferred_list_work); + /* + * Ensure no retry fault comes in afterwards, as page fault handler will + * not find kfd process and take mm lock to recover fault. + */ + svm_range_drain_retry_fault(&p->svms); + + list_for_each_entry_safe(prange, next, &p->svms.list, list) { svm_range_unlink(prange); svm_range_remove_notifier(prange); From 0cc53cb450669cf1def4ff89e8cbcd8ec3c62380 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Fri, 19 Nov 2021 16:16:39 -0500 Subject: [PATCH 269/358] drm/amdkfd: handle VMA remove race VMA may be removed before unmap notifier callback, and deferred list work remove range, return success for this special case as we are handling stale retry fault. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index b553c34cc99b7b..c69748e693fd1d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -2559,20 +2559,13 @@ svm_range_count_fault(struct amdgpu_device *adev, struct kfd_process *p, } static bool -svm_fault_allowed(struct mm_struct *mm, uint64_t addr, bool write_fault) +svm_fault_allowed(struct vm_area_struct *vma, bool write_fault) { unsigned long requested = VM_READ; - struct vm_area_struct *vma; if (write_fault) requested |= VM_WRITE; - vma = find_vma(mm, addr << PAGE_SHIFT); - if (!vma || (addr << PAGE_SHIFT) < vma->vm_start) { - pr_debug("address 0x%llx VMA is removed\n", addr); - return true; - } - pr_debug("requested 0x%lx, vma permission flags 0x%lx\n", requested, vma->vm_flags); return (vma->vm_flags & requested) == requested; @@ -2590,6 +2583,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, int32_t best_loc; int32_t gpuidx = MAX_GPU_INSTANCE; bool write_locked = false; + struct vm_area_struct *vma; int r = 0; if (!KFD_IS_SVM_API_SUPPORTED(adev->kfd.dev)) { @@ -2665,7 +2659,17 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, goto out_unlock_range; } - if (!svm_fault_allowed(mm, addr, write_fault)) { + /* __do_munmap removed VMA, return success as we are handling stale + * retry fault. + */ + vma = find_vma(mm, addr << PAGE_SHIFT); + if (!vma || (addr << PAGE_SHIFT) < vma->vm_start) { + pr_debug("address 0x%llx VMA is removed\n", addr); + r = 0; + goto out_unlock_range; + } + + if (!svm_fault_allowed(vma, write_fault)) { pr_debug("fault addr 0x%llx no %s permission\n", addr, write_fault ? "write" : "read"); r = -EPERM; From 6946be2443cfd4755eb8e465c20e7cf33fb259b3 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Fri, 19 Nov 2021 17:02:50 -0500 Subject: [PATCH 270/358] drm/amdkfd: simplify drain retry fault unmap range always increase atomic svms->drain_pagefaults to simplify both parent range and child range unmap, page fault handle ignores the retry fault if svms->drain_pagefaults is set to speed up interrupt handling. svm_range_drain_retry_fault restart draining if another range unmap from cpu. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 30 ++++++++++++++++++++------- 2 files changed, 23 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 94e92c0812db73..8fd48d0ed240ce 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -766,7 +766,7 @@ struct svm_range_list { struct list_head deferred_range_list; spinlock_t deferred_list_lock; atomic_t evicted_ranges; - bool drain_pagefaults; + atomic_t drain_pagefaults; struct delayed_work restore_work; DECLARE_BITMAP(bitmap_supported, MAX_GPU_INSTANCE); struct task_struct *faulting_task; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index c69748e693fd1d..58b89b53ebe617 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1968,10 +1968,16 @@ static void svm_range_drain_retry_fault(struct svm_range_list *svms) struct kfd_process_device *pdd; struct amdgpu_device *adev; struct kfd_process *p; + int drain; uint32_t i; p = container_of(svms, struct kfd_process, svms); +restart: + drain = atomic_read(&svms->drain_pagefaults); + if (!drain) + return; + for_each_set_bit(i, svms->bitmap_supported, p->n_pdds) { pdd = p->pdds[i]; if (!pdd) @@ -1983,6 +1989,8 @@ static void svm_range_drain_retry_fault(struct svm_range_list *svms) amdgpu_ih_wait_on_checkpoint_process(adev, &adev->irq.ih1); pr_debug("drain retry fault gpu %d svms 0x%p done\n", i, svms); } + if (atomic_cmpxchg(&svms->drain_pagefaults, drain, 0) != drain) + goto restart; } static void svm_range_deferred_list_work(struct work_struct *work) @@ -2008,8 +2016,7 @@ static void svm_range_deferred_list_work(struct work_struct *work) /* Checking for the need to drain retry faults must be inside * mmap write lock to serialize with munmap notifiers. */ - if (unlikely(READ_ONCE(svms->drain_pagefaults))) { - WRITE_ONCE(svms->drain_pagefaults, false); + if (unlikely(atomic_read(&svms->drain_pagefaults))) { mmap_write_unlock(mm); svm_range_drain_retry_fault(svms); goto retry; @@ -2056,12 +2063,6 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange, struct mm_struct *mm, enum svm_work_list_ops op) { spin_lock(&svms->deferred_list_lock); - /* Make sure pending page faults are drained in the deferred worker - * before the range is freed to avoid straggler interrupts on - * unmapped memory causing "phantom faults". - */ - if (op == SVM_OP_UNMAP_RANGE) - svms->drain_pagefaults = true; /* if prange is on the deferred list */ if (!list_empty(&prange->deferred_list)) { pr_debug("update exist prange 0x%p work op %d\n", prange, op); @@ -2140,6 +2141,12 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange, pr_debug("svms 0x%p prange 0x%p [0x%lx 0x%lx] [0x%lx 0x%lx]\n", svms, prange, prange->start, prange->last, start, last); + /* Make sure pending page faults are drained in the deferred worker + * before the range is freed to avoid straggler interrupts on + * unmapped memory causing "phantom faults". + */ + atomic_inc(&svms->drain_pagefaults); + unmap_parent = start <= prange->start && last >= prange->last; list_for_each_entry(pchild, &prange->child_list, child_list) { @@ -2605,6 +2612,11 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, pr_debug("restoring svms 0x%p fault address 0x%llx\n", svms, addr); + if (atomic_read(&svms->drain_pagefaults)) { + pr_debug("draining retry fault, drop fault 0x%llx\n", addr); + goto out; + } + /* p->lead_thread is available as kfd_process_wq_release flush the work * before releasing task ref. */ @@ -2751,6 +2763,7 @@ void svm_range_list_fini(struct kfd_process *p) * Ensure no retry fault comes in afterwards, as page fault handler will * not find kfd process and take mm lock to recover fault. */ + atomic_inc(&p->svms.drain_pagefaults); svm_range_drain_retry_fault(&p->svms); @@ -2774,6 +2787,7 @@ int svm_range_list_init(struct kfd_process *p) mutex_init(&svms->lock); INIT_LIST_HEAD(&svms->list); atomic_set(&svms->evicted_ranges, 0); + atomic_set(&svms->drain_pagefaults, 0); INIT_DELAYED_WORK(&svms->restore_work, svm_range_restore_work); INIT_WORK(&svms->deferred_list_work, svm_range_deferred_list_work); INIT_LIST_HEAD(&svms->deferred_range_list); From 8888e2fe9c77983a9644cd9bf0d23ca9023b16d4 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Tue, 23 Nov 2021 09:59:46 -0500 Subject: [PATCH 271/358] drm/amdgpu: enable Navi 48-bit IH timestamp counter By default this timestamp is 32 bit counter. It gets overflowed in around 10 minutes. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/navi10_ih.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c index 1d8414c3fadb6d..dafad603094789 100644 --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c @@ -160,6 +160,7 @@ static int navi10_ih_toggle_ring_interrupts(struct amdgpu_device *adev, tmp = RREG32(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_ENABLE, (enable ? 1 : 0)); + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_GPU_TS_ENABLE, 1); /* enable_intr field is only valid in ring0 */ if (ih == &adev->irq.ih) tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, ENABLE_INTR, (enable ? 1 : 0)); From c4ef8a73bfc84fad3de46b38f313c0b159103b28 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Tue, 23 Nov 2021 10:20:17 -0500 Subject: [PATCH 272/358] drm/amdgpu: enable Navi retry fault wptr overflow If xnack is on, VM retry fault interrupt send to IH ring1, and ring1 will be full quickly. IH cannot receive other interrupts, this causes deadlock if migrating buffer using sdma and waiting for sdma done while handling retry fault. Remove VMC from IH storm client, enable ring1 write pointer overflow, then IH will drop retry fault interrupts and be able to receive other interrupts while driver is handling retry fault. IH ring1 write pointer doesn't writeback to memory by IH, and ring1 write pointer recorded by self-irq is not updated, so always read the latest ring1 write pointer from register. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/navi10_ih.c | 33 ++++++++++---------------- 1 file changed, 12 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c index dafad603094789..38241cf0e1f163 100644 --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c @@ -276,10 +276,8 @@ static int navi10_ih_enable_ring(struct amdgpu_device *adev, tmp = navi10_ih_rb_cntl(ih, tmp); if (ih == &adev->irq.ih) tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RPTR_REARM, !!adev->irq.msi_enabled); - if (ih == &adev->irq.ih1) { - tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_ENABLE, 0); + if (ih == &adev->irq.ih1) tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_FULL_DRAIN_ENABLE, 1); - } if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) { if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) { @@ -320,7 +318,6 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev) { struct amdgpu_ih_ring *ih[] = {&adev->irq.ih, &adev->irq.ih1, &adev->irq.ih2}; u32 ih_chicken; - u32 tmp; int ret; int i; @@ -364,15 +361,6 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev) adev->nbio.funcs->ih_doorbell_range(adev, ih[0]->use_doorbell, ih[0]->doorbell_index); - tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL); - tmp = REG_SET_FIELD(tmp, IH_STORM_CLIENT_LIST_CNTL, - CLIENT18_IS_STORM_CLIENT, 1); - WREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL, tmp); - - tmp = RREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL); - tmp = REG_SET_FIELD(tmp, IH_INT_FLOOD_CNTL, FLOOD_CNTL_ENABLE, 1); - WREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL, tmp); - pci_set_master(adev->pdev); /* enable interrupts */ @@ -421,12 +409,19 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev, u32 wptr, tmp; struct amdgpu_ih_regs *ih_regs; - wptr = le32_to_cpu(*ih->wptr_cpu); - ih_regs = &ih->ih_regs; + if (ih == &adev->irq.ih) { + /* Only ring0 supports writeback. On other rings fall back + * to register-based code with overflow checking below. + */ + wptr = le32_to_cpu(*ih->wptr_cpu); - if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) - goto out; + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) + goto out; + } + ih_regs = &ih->ih_regs; + + /* Double check that the overflow wasn't already cleared. */ wptr = RREG32_NO_KIQ(ih_regs->ih_rb_wptr); if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) goto out; @@ -514,15 +509,11 @@ static int navi10_ih_self_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - uint32_t wptr = cpu_to_le32(entry->src_data[0]); - switch (entry->ring_id) { case 1: - *adev->irq.ih1.wptr_cpu = wptr; schedule_work(&adev->irq.ih1_work); break; case 2: - *adev->irq.ih2.wptr_cpu = wptr; schedule_work(&adev->irq.ih2_work); break; default: break; From fd08953b2de911f32c06aedbc8ad111c2fd0168b Mon Sep 17 00:00:00 2001 From: Yang Wang Date: Wed, 24 Nov 2021 12:26:02 +0800 Subject: [PATCH 273/358] drm/amdgpu: fix byteorder error in amdgpu discovery fix some byteorder issues about amdgpu discovery. This will result in running errors on the big end system. (e.g:MIPS) Signed-off-by: Yang Wang Reviewed-by: Guchun Chen Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 4e3669407518f9..503995c7ff6c1e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -248,8 +248,8 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) offset = offsetof(struct binary_header, binary_checksum) + sizeof(bhdr->binary_checksum); - size = bhdr->binary_size - offset; - checksum = bhdr->binary_checksum; + size = le16_to_cpu(bhdr->binary_size) - offset; + checksum = le16_to_cpu(bhdr->binary_checksum); if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset, size, checksum)) { @@ -270,7 +270,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) } if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset, - ihdr->size, checksum)) { + le16_to_cpu(ihdr->size), checksum)) { DRM_ERROR("invalid ip discovery data table checksum\n"); r = -EINVAL; goto out; @@ -282,7 +282,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) ghdr = (struct gpu_info_header *)(adev->mman.discovery_bin + offset); if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset, - ghdr->size, checksum)) { + le32_to_cpu(ghdr->size), checksum)) { DRM_ERROR("invalid gc data table checksum\n"); r = -EINVAL; goto out; @@ -489,10 +489,10 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) le16_to_cpu(bhdr->table_list[HARVEST_INFO].offset)); for (i = 0; i < 32; i++) { - if (le32_to_cpu(harvest_info->list[i].hw_id) == 0) + if (le16_to_cpu(harvest_info->list[i].hw_id) == 0) break; - switch (le32_to_cpu(harvest_info->list[i].hw_id)) { + switch (le16_to_cpu(harvest_info->list[i].hw_id)) { case VCN_HWID: vcn_harvest_count++; if (harvest_info->list[i].number_instance == 0) From 57961c4c1818a8a2cc5cd964a430581f77f7eb6a Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Wed, 24 Nov 2021 19:26:38 +0800 Subject: [PATCH 274/358] drm/amdgpu: Skip ASPM programming on aldebaran There is no need for additional programming, keep the default settings. Signed-off-by: Lijo Lazar Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index e96516d3fd45eb..dc5e93756fea4f 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -694,6 +694,9 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) { uint32_t def, data; + if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(7, 4, 4)) + return; + def = data = RREG32_PCIE(smnPCIE_LC_CNTL); data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK; data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK; From d5c7255dc7ff6e1239d794b9c53029d83ced04ca Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 23 Nov 2021 11:36:01 -0500 Subject: [PATCH 275/358] drm/amdgpu/pm: fix powerplay OD interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The overclocking interface currently appends data to a string. Revert back to using sprintf(). Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1774 Fixes: 6db0c87a0a8ee1 ("amdgpu/pm: Replace hwmgr smu usage of sprintf with sysfs_emit") Acked-by: Evan Quan Acked-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- .../drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c | 20 +++---- .../drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 24 ++++---- .../drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c | 6 +- .../drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 28 +++++---- .../drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c | 10 ++-- .../drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c | 58 +++++++++---------- 6 files changed, 67 insertions(+), 79 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 258c573acc9798..1f406f21b452fa 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1024,8 +1024,6 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, uint32_t min_freq, max_freq = 0; uint32_t ret = 0; - phm_get_sysfs_buf(&buf, &size); - switch (type) { case PP_SCLK: smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now); @@ -1038,13 +1036,13 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, else i = 1; - size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", + size += sprintf(buf + size, "0: %uMhz %s\n", data->gfx_min_freq_limit/100, i == 0 ? "*" : ""); - size += sysfs_emit_at(buf, size, "1: %uMhz %s\n", + size += sprintf(buf + size, "1: %uMhz %s\n", i == 1 ? now : SMU10_UMD_PSTATE_GFXCLK, i == 1 ? "*" : ""); - size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", + size += sprintf(buf + size, "2: %uMhz %s\n", data->gfx_max_freq_limit/100, i == 2 ? "*" : ""); break; @@ -1052,7 +1050,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency, &now); for (i = 0; i < mclk_table->count; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, mclk_table->entries[i].clk / 100, ((mclk_table->entries[i].clk / 100) @@ -1067,10 +1065,10 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, if (ret) return ret; - size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); - size += sysfs_emit_at(buf, size, "0: %10uMhz\n", + size += sprintf(buf + size, "%s:\n", "OD_SCLK"); + size += sprintf(buf + size, "0: %10uMhz\n", (data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : min_freq); - size += sysfs_emit_at(buf, size, "1: %10uMhz\n", + size += sprintf(buf + size, "1: %10uMhz\n", (data->gfx_actual_soft_max_freq > 0) ? data->gfx_actual_soft_max_freq : max_freq); } break; @@ -1083,8 +1081,8 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, if (ret) return ret; - size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); - size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n", + size += sprintf(buf + size, "%s:\n", "OD_RANGE"); + size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n", min_freq, max_freq); } break; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index aceebf58422530..611969bf452077 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -4914,8 +4914,6 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr, int size = 0; uint32_t i, now, clock, pcie_speed; - phm_get_sysfs_buf(&buf, &size); - switch (type) { case PP_SCLK: smum_send_msg_to_smc(hwmgr, PPSMC_MSG_API_GetSclkFrequency, &clock); @@ -4928,7 +4926,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr, now = i; for (i = 0; i < sclk_table->count; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, sclk_table->dpm_levels[i].value / 100, (i == now) ? "*" : ""); break; @@ -4943,7 +4941,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr, now = i; for (i = 0; i < mclk_table->count; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, mclk_table->dpm_levels[i].value / 100, (i == now) ? "*" : ""); break; @@ -4957,7 +4955,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr, now = i; for (i = 0; i < pcie_table->count; i++) - size += sysfs_emit_at(buf, size, "%d: %s %s\n", i, + size += sprintf(buf + size, "%d: %s %s\n", i, (pcie_table->dpm_levels[i].value == 0) ? "2.5GT/s, x8" : (pcie_table->dpm_levels[i].value == 1) ? "5.0GT/s, x16" : (pcie_table->dpm_levels[i].value == 2) ? "8.0GT/s, x16" : "", @@ -4965,32 +4963,32 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr, break; case OD_SCLK: if (hwmgr->od_enabled) { - size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); + size += sprintf(buf + size, "%s:\n", "OD_SCLK"); for (i = 0; i < odn_sclk_table->num_of_pl; i++) - size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n", + size += sprintf(buf + size, "%d: %10uMHz %10umV\n", i, odn_sclk_table->entries[i].clock/100, odn_sclk_table->entries[i].vddc); } break; case OD_MCLK: if (hwmgr->od_enabled) { - size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK"); + size += sprintf(buf + size, "%s:\n", "OD_MCLK"); for (i = 0; i < odn_mclk_table->num_of_pl; i++) - size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n", + size += sprintf(buf + size, "%d: %10uMHz %10umV\n", i, odn_mclk_table->entries[i].clock/100, odn_mclk_table->entries[i].vddc); } break; case OD_RANGE: if (hwmgr->od_enabled) { - size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); - size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n", + size += sprintf(buf + size, "%s:\n", "OD_RANGE"); + size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n", data->golden_dpm_table.sclk_table.dpm_levels[0].value/100, hwmgr->platform_descriptor.overdriveLimit.engineClock/100); - size += sysfs_emit_at(buf, size, "MCLK: %7uMHz %10uMHz\n", + size += sprintf(buf + size, "MCLK: %7uMHz %10uMHz\n", data->golden_dpm_table.mclk_table.dpm_levels[0].value/100, hwmgr->platform_descriptor.overdriveLimit.memoryClock/100); - size += sysfs_emit_at(buf, size, "VDDC: %7umV %11umV\n", + size += sprintf(buf + size, "VDDC: %7umV %11umV\n", data->odn_dpm_table.min_vddc, data->odn_dpm_table.max_vddc); } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index 8e28a8eecefc64..03bf8f0692228d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -1550,8 +1550,6 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr, uint32_t i, now; int size = 0; - phm_get_sysfs_buf(&buf, &size); - switch (type) { case PP_SCLK: now = PHM_GET_FIELD(cgs_read_ind_register(hwmgr->device, @@ -1561,7 +1559,7 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr, CURR_SCLK_INDEX); for (i = 0; i < sclk_table->count; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, sclk_table->entries[i].clk / 100, (i == now) ? "*" : ""); break; @@ -1573,7 +1571,7 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr, CURR_MCLK_INDEX); for (i = SMU8_NUM_NBPMEMORYCLOCK; i > 0; i--) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", SMU8_NUM_NBPMEMORYCLOCK-i, data->sys_info.nbp_memory_clock[i-1] / 100, (SMU8_NUM_NBPMEMORYCLOCK-i == now) ? "*" : ""); break; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index c981fc2882f017..e6336654c5655e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -4639,8 +4639,6 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, int i, now, size = 0, count = 0; - phm_get_sysfs_buf(&buf, &size); - switch (type) { case PP_SCLK: if (data->registry_data.sclk_dpm_key_disabled) @@ -4654,7 +4652,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, else count = sclk_table->count; for (i = 0; i < count; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, sclk_table->dpm_levels[i].value / 100, (i == now) ? "*" : ""); break; @@ -4665,7 +4663,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex, &now); for (i = 0; i < mclk_table->count; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, mclk_table->dpm_levels[i].value / 100, (i == now) ? "*" : ""); break; @@ -4676,7 +4674,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentSocclkIndex, &now); for (i = 0; i < soc_table->count; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, soc_table->dpm_levels[i].value / 100, (i == now) ? "*" : ""); break; @@ -4688,7 +4686,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, PPSMC_MSG_GetClockFreqMHz, CLK_DCEFCLK, &now); for (i = 0; i < dcef_table->count; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, dcef_table->dpm_levels[i].value / 100, (dcef_table->dpm_levels[i].value / 100 == now) ? "*" : ""); @@ -4702,7 +4700,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, gen_speed = pptable->PcieGenSpeed[i]; lane_width = pptable->PcieLaneCount[i]; - size += sysfs_emit_at(buf, size, "%d: %s %s %s\n", i, + size += sprintf(buf + size, "%d: %s %s %s\n", i, (gen_speed == 0) ? "2.5GT/s," : (gen_speed == 1) ? "5.0GT/s," : (gen_speed == 2) ? "8.0GT/s," : @@ -4721,34 +4719,34 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, case OD_SCLK: if (hwmgr->od_enabled) { - size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); + size += sprintf(buf + size, "%s:\n", "OD_SCLK"); podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk; for (i = 0; i < podn_vdd_dep->count; i++) - size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n", + size += sprintf(buf + size, "%d: %10uMhz %10umV\n", i, podn_vdd_dep->entries[i].clk / 100, podn_vdd_dep->entries[i].vddc); } break; case OD_MCLK: if (hwmgr->od_enabled) { - size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK"); + size += sprintf(buf + size, "%s:\n", "OD_MCLK"); podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk; for (i = 0; i < podn_vdd_dep->count; i++) - size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n", + size += sprintf(buf + size, "%d: %10uMhz %10umV\n", i, podn_vdd_dep->entries[i].clk/100, podn_vdd_dep->entries[i].vddc); } break; case OD_RANGE: if (hwmgr->od_enabled) { - size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); - size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n", + size += sprintf(buf + size, "%s:\n", "OD_RANGE"); + size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n", data->golden_dpm_table.gfx_table.dpm_levels[0].value/100, hwmgr->platform_descriptor.overdriveLimit.engineClock/100); - size += sysfs_emit_at(buf, size, "MCLK: %7uMHz %10uMHz\n", + size += sprintf(buf + size, "MCLK: %7uMHz %10uMHz\n", data->golden_dpm_table.mem_table.dpm_levels[0].value/100, hwmgr->platform_descriptor.overdriveLimit.memoryClock/100); - size += sysfs_emit_at(buf, size, "VDDC: %7umV %11umV\n", + size += sprintf(buf + size, "VDDC: %7umV %11umV\n", data->odn_dpm_table.min_vddc, data->odn_dpm_table.max_vddc); } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index f7e783e1c888f3..a2f4d6773d458c 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -2246,8 +2246,6 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr, int i, now, size = 0; struct pp_clock_levels_with_latency clocks; - phm_get_sysfs_buf(&buf, &size); - switch (type) { case PP_SCLK: PP_ASSERT_WITH_CODE( @@ -2260,7 +2258,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr, "Attempt to get gfx clk levels Failed!", return -1); for (i = 0; i < clocks.num_levels; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : ""); break; @@ -2276,7 +2274,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr, "Attempt to get memory clk levels Failed!", return -1); for (i = 0; i < clocks.num_levels; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : ""); break; @@ -2294,7 +2292,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr, "Attempt to get soc clk levels Failed!", return -1); for (i = 0; i < clocks.num_levels; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : ""); break; @@ -2312,7 +2310,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr, "Attempt to get dcef clk levels Failed!", return -1); for (i = 0; i < clocks.num_levels; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : ""); break; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 03e63be4ee2756..85d55ab4e369fc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -3366,8 +3366,6 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, int ret = 0; uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width; - phm_get_sysfs_buf(&buf, &size); - switch (type) { case PP_SCLK: ret = vega20_get_current_clk_freq(hwmgr, PPCLK_GFXCLK, &now); @@ -3376,13 +3374,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, return ret); if (vega20_get_sclks(hwmgr, &clocks)) { - size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n", + size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n", now / 100); break; } for (i = 0; i < clocks.num_levels; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz == now * 10) ? "*" : ""); break; @@ -3394,13 +3392,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, return ret); if (vega20_get_memclocks(hwmgr, &clocks)) { - size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n", + size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n", now / 100); break; } for (i = 0; i < clocks.num_levels; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz == now * 10) ? "*" : ""); break; @@ -3412,13 +3410,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, return ret); if (vega20_get_socclocks(hwmgr, &clocks)) { - size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n", + size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n", now / 100); break; } for (i = 0; i < clocks.num_levels; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz == now * 10) ? "*" : ""); break; @@ -3430,7 +3428,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, return ret); for (i = 0; i < fclk_dpm_table->count; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, fclk_dpm_table->dpm_levels[i].value, fclk_dpm_table->dpm_levels[i].value == (now / 100) ? "*" : ""); break; @@ -3442,13 +3440,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, return ret); if (vega20_get_dcefclocks(hwmgr, &clocks)) { - size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n", + size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n", now / 100); break; } for (i = 0; i < clocks.num_levels; i++) - size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", + size += sprintf(buf + size, "%d: %uMhz %s\n", i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz == now * 10) ? "*" : ""); break; @@ -3462,7 +3460,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, gen_speed = pptable->PcieGenSpeed[i]; lane_width = pptable->PcieLaneCount[i]; - size += sysfs_emit_at(buf, size, "%d: %s %s %dMhz %s\n", i, + size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i, (gen_speed == 0) ? "2.5GT/s," : (gen_speed == 1) ? "5.0GT/s," : (gen_speed == 2) ? "8.0GT/s," : @@ -3483,18 +3481,18 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, case OD_SCLK: if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id && od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) { - size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); - size += sysfs_emit_at(buf, size, "0: %10uMhz\n", + size += sprintf(buf + size, "%s:\n", "OD_SCLK"); + size += sprintf(buf + size, "0: %10uMhz\n", od_table->GfxclkFmin); - size += sysfs_emit_at(buf, size, "1: %10uMhz\n", + size += sprintf(buf + size, "1: %10uMhz\n", od_table->GfxclkFmax); } break; case OD_MCLK: if (od8_settings[OD8_SETTING_UCLK_FMAX].feature_id) { - size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK"); - size += sysfs_emit_at(buf, size, "1: %10uMhz\n", + size += sprintf(buf + size, "%s:\n", "OD_MCLK"); + size += sprintf(buf + size, "1: %10uMhz\n", od_table->UclkFmax); } @@ -3507,14 +3505,14 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].feature_id && od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].feature_id && od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].feature_id) { - size += sysfs_emit_at(buf, size, "%s:\n", "OD_VDDC_CURVE"); - size += sysfs_emit_at(buf, size, "0: %10uMhz %10dmV\n", + size += sprintf(buf + size, "%s:\n", "OD_VDDC_CURVE"); + size += sprintf(buf + size, "0: %10uMhz %10dmV\n", od_table->GfxclkFreq1, od_table->GfxclkVolt1 / VOLTAGE_SCALE); - size += sysfs_emit_at(buf, size, "1: %10uMhz %10dmV\n", + size += sprintf(buf + size, "1: %10uMhz %10dmV\n", od_table->GfxclkFreq2, od_table->GfxclkVolt2 / VOLTAGE_SCALE); - size += sysfs_emit_at(buf, size, "2: %10uMhz %10dmV\n", + size += sprintf(buf + size, "2: %10uMhz %10dmV\n", od_table->GfxclkFreq3, od_table->GfxclkVolt3 / VOLTAGE_SCALE); } @@ -3522,17 +3520,17 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, break; case OD_RANGE: - size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); + size += sprintf(buf + size, "%s:\n", "OD_RANGE"); if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id && od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) { - size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n", + size += sprintf(buf + size, "SCLK: %7uMhz %10uMhz\n", od8_settings[OD8_SETTING_GFXCLK_FMIN].min_value, od8_settings[OD8_SETTING_GFXCLK_FMAX].max_value); } if (od8_settings[OD8_SETTING_UCLK_FMAX].feature_id) { - size += sysfs_emit_at(buf, size, "MCLK: %7uMhz %10uMhz\n", + size += sprintf(buf + size, "MCLK: %7uMhz %10uMhz\n", od8_settings[OD8_SETTING_UCLK_FMAX].min_value, od8_settings[OD8_SETTING_UCLK_FMAX].max_value); } @@ -3543,22 +3541,22 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].feature_id && od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].feature_id && od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].feature_id) { - size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n", + size += sprintf(buf + size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n", od8_settings[OD8_SETTING_GFXCLK_FREQ1].min_value, od8_settings[OD8_SETTING_GFXCLK_FREQ1].max_value); - size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[0]: %7dmV %11dmV\n", + size += sprintf(buf + size, "VDDC_CURVE_VOLT[0]: %7dmV %11dmV\n", od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].min_value, od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].max_value); - size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[1]: %7uMhz %10uMhz\n", + size += sprintf(buf + size, "VDDC_CURVE_SCLK[1]: %7uMhz %10uMhz\n", od8_settings[OD8_SETTING_GFXCLK_FREQ2].min_value, od8_settings[OD8_SETTING_GFXCLK_FREQ2].max_value); - size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[1]: %7dmV %11dmV\n", + size += sprintf(buf + size, "VDDC_CURVE_VOLT[1]: %7dmV %11dmV\n", od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].min_value, od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].max_value); - size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[2]: %7uMhz %10uMhz\n", + size += sprintf(buf + size, "VDDC_CURVE_SCLK[2]: %7uMhz %10uMhz\n", od8_settings[OD8_SETTING_GFXCLK_FREQ3].min_value, od8_settings[OD8_SETTING_GFXCLK_FREQ3].max_value); - size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[2]: %7dmV %11dmV\n", + size += sprintf(buf + size, "VDDC_CURVE_VOLT[2]: %7dmV %11dmV\n", od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].min_value, od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].max_value); } From 692cd92e66ee10597676530573a495dc1d3bec6a Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 23 Nov 2021 10:44:48 -0500 Subject: [PATCH 276/358] drm/amd/display: update bios scratch when setting backlight Update the bios scratch register when updating the backlight level. Some platforms apparently read this scratch register and do additional operations in their hotkey handlers. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1518 Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 12 ++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h | 2 ++ drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++++ 3 files changed, 18 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 96b7bb13a2dd95..12a6b1c99c93e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -1569,6 +1569,18 @@ void amdgpu_atombios_scratch_regs_engine_hung(struct amdgpu_device *adev, WREG32(adev->bios_scratch_reg_offset + 3, tmp); } +void amdgpu_atombios_scratch_regs_set_backlight_level(struct amdgpu_device *adev, + u32 backlight_level) +{ + u32 tmp = RREG32(adev->bios_scratch_reg_offset + 2); + + tmp &= ~ATOM_S2_CURRENT_BL_LEVEL_MASK; + tmp |= (backlight_level << ATOM_S2_CURRENT_BL_LEVEL_SHIFT) & + ATOM_S2_CURRENT_BL_LEVEL_MASK; + + WREG32(adev->bios_scratch_reg_offset + 2, tmp); +} + bool amdgpu_atombios_scratch_need_asic_init(struct amdgpu_device *adev) { u32 tmp = RREG32(adev->bios_scratch_reg_offset + 7); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h index 8cc0222dba1910..27e74b1fc260a3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h @@ -185,6 +185,8 @@ bool amdgpu_atombios_has_gpu_virtualization_table(struct amdgpu_device *adev); void amdgpu_atombios_scratch_regs_lock(struct amdgpu_device *adev, bool lock); void amdgpu_atombios_scratch_regs_engine_hung(struct amdgpu_device *adev, bool hung); +void amdgpu_atombios_scratch_regs_set_backlight_level(struct amdgpu_device *adev, + u32 backlight_level); bool amdgpu_atombios_scratch_need_asic_init(struct amdgpu_device *adev); void amdgpu_atombios_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index e439f9d7c3f1d0..1cd6b9f4a568c8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -51,6 +51,7 @@ #include #endif #include "amdgpu_pm.h" +#include "amdgpu_atombios.h" #include "amd_shared.h" #include "amdgpu_dm_irq.h" @@ -3925,6 +3926,9 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, caps = dm->backlight_caps[bl_idx]; dm->brightness[bl_idx] = user_brightness; + /* update scratch register */ + if (bl_idx == 0) + amdgpu_atombios_scratch_regs_set_backlight_level(dm->adev, dm->brightness[bl_idx]); brightness = convert_brightness_from_user(&caps, dm->brightness[bl_idx]); link = (struct dc_link *)dm->backlight_link[bl_idx]; From 6318cb887548c70778d10c0fcb7134b4454ab8a6 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Nov 2021 18:44:02 -0500 Subject: [PATCH 277/358] Revert "virtio-scsi: don't let virtio core to validate used buffer length" This reverts commit c57911ebfbfe745cb95da2bcf547c5bae000590f. Attempts to validate length in the core did not work out. We'll drop them for now, so revert the dependent changes in drivers. Signed-off-by: Michael S. Tsirkin --- drivers/scsi/virtio_scsi.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 19f7d7b906251b..28e1d98ae10214 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -977,7 +977,6 @@ static unsigned int features[] = { static struct virtio_driver virtio_scsi_driver = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), - .suppress_used_validation = true, .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, From 2b17d9f84884a37f1324be5526c6600e97a47fbe Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Nov 2021 18:44:09 -0500 Subject: [PATCH 278/358] Revert "virtio-blk: don't let virtio core to validate used length" This reverts commit a40392edf1b2c7822bc0ce68413106661a9d4232. Attempts to validate length in the core did not work out. We'll drop them, so revert the dependent changes in drivers. Signed-off-by: Michael S. Tsirkin --- drivers/block/virtio_blk.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 97bf051a50ced3..1a1b1189225dd6 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -1049,7 +1049,6 @@ static struct virtio_driver virtio_blk = { .feature_table_size = ARRAY_SIZE(features), .feature_table_legacy = features_legacy, .feature_table_size_legacy = ARRAY_SIZE(features_legacy), - .suppress_used_validation = true, .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, From fcfb65f8a922c7dd25a2e9913601dae979ce6560 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Nov 2021 18:44:13 -0500 Subject: [PATCH 279/358] Revert "virtio-net: don't let virtio core to validate used length" This reverts commit 816625c13652cef5b2c49082d652875da6f2ad7a. Attempts to validate length in the core did not work out. We'll drop them, so revert the dependent changes in drivers. Signed-off-by: Michael S. Tsirkin --- drivers/net/virtio_net.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 1771d6e5224fd8..55db6a336f7ead 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3423,7 +3423,6 @@ static struct virtio_driver virtio_net_driver = { .feature_table_size = ARRAY_SIZE(features), .feature_table_legacy = features_legacy, .feature_table_size_legacy = ARRAY_SIZE(features_legacy), - .suppress_used_validation = true, .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, From f124034faa911ed534bf8c4881ad98dbbde2a966 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Nov 2021 18:44:17 -0500 Subject: [PATCH 280/358] Revert "virtio_ring: validate used buffer length" This reverts commit 939779f5152d161b34f612af29e7dc1ac4472fcf. Attempts to validate length in the core did not work out: there turn out to exist multiple broken devices, and in particular legacy devices are known to be broken in this respect. We have ideas for handling this better in the next version but for now let's revert to a known good state to make sure drivers work for people. Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 60 ------------------------------------ include/linux/virtio.h | 2 -- 2 files changed, 62 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 00f64f2f8b72b4..6d2614e34470f4 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -14,9 +14,6 @@ #include #include -static bool force_used_validation = false; -module_param(force_used_validation, bool, 0444); - #ifdef DEBUG /* For development, we want to crash whenever the ring is screwed. */ #define BAD_RING(_vq, fmt, args...) \ @@ -185,9 +182,6 @@ struct vring_virtqueue { } packed; }; - /* Per-descriptor in buffer length */ - u32 *buflen; - /* How to notify other side. FIXME: commonalize hcalls! */ bool (*notify)(struct virtqueue *vq); @@ -496,7 +490,6 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, unsigned int i, n, avail, descs_used, prev, err_idx; int head; bool indirect; - u32 buflen = 0; START_USE(vq); @@ -578,7 +571,6 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE, indirect); - buflen += sg->length; } } /* Last one doesn't continue. */ @@ -618,10 +610,6 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, else vq->split.desc_state[head].indir_desc = ctx; - /* Store in buffer length if necessary */ - if (vq->buflen) - vq->buflen[head] = buflen; - /* Put entry in available array (but don't update avail->idx until they * do sync). */ avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1); @@ -796,11 +784,6 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq, BAD_RING(vq, "id %u is not a head!\n", i); return NULL; } - if (vq->buflen && unlikely(*len > vq->buflen[i])) { - BAD_RING(vq, "used len %d is larger than in buflen %u\n", - *len, vq->buflen[i]); - return NULL; - } /* detach_buf_split clears data, so grab it now. */ ret = vq->split.desc_state[i].data; @@ -1079,7 +1062,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, unsigned int i, n, err_idx; u16 head, id; dma_addr_t addr; - u32 buflen = 0; head = vq->packed.next_avail_idx; desc = alloc_indirect_packed(total_sg, gfp); @@ -1109,8 +1091,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, desc[i].addr = cpu_to_le64(addr); desc[i].len = cpu_to_le32(sg->length); i++; - if (n >= out_sgs) - buflen += sg->length; } } @@ -1164,10 +1144,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, vq->packed.desc_state[id].indir_desc = desc; vq->packed.desc_state[id].last = id; - /* Store in buffer length if necessary */ - if (vq->buflen) - vq->buflen[id] = buflen; - vq->num_added += 1; pr_debug("Added buffer head %i to %p\n", head, vq); @@ -1203,7 +1179,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, __le16 head_flags, flags; u16 head, id, prev, curr, avail_used_flags; int err; - u32 buflen = 0; START_USE(vq); @@ -1283,8 +1258,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, 1 << VRING_PACKED_DESC_F_AVAIL | 1 << VRING_PACKED_DESC_F_USED; } - if (n >= out_sgs) - buflen += sg->length; } } @@ -1304,10 +1277,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, vq->packed.desc_state[id].indir_desc = ctx; vq->packed.desc_state[id].last = prev; - /* Store in buffer length if necessary */ - if (vq->buflen) - vq->buflen[id] = buflen; - /* * A driver MUST NOT make the first descriptor in the list * available before all subsequent descriptors comprising @@ -1494,11 +1463,6 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq, BAD_RING(vq, "id %u is not a head!\n", id); return NULL; } - if (vq->buflen && unlikely(*len > vq->buflen[id])) { - BAD_RING(vq, "used len %d is larger than in buflen %u\n", - *len, vq->buflen[id]); - return NULL; - } /* detach_buf_packed clears data, so grab it now. */ ret = vq->packed.desc_state[id].data; @@ -1704,7 +1668,6 @@ static struct virtqueue *vring_create_virtqueue_packed( struct vring_virtqueue *vq; struct vring_packed_desc *ring; struct vring_packed_desc_event *driver, *device; - struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver); dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr; size_t ring_size_in_bytes, event_size_in_bytes; @@ -1794,15 +1757,6 @@ static struct virtqueue *vring_create_virtqueue_packed( if (!vq->packed.desc_extra) goto err_desc_extra; - if (!drv->suppress_used_validation || force_used_validation) { - vq->buflen = kmalloc_array(num, sizeof(*vq->buflen), - GFP_KERNEL); - if (!vq->buflen) - goto err_buflen; - } else { - vq->buflen = NULL; - } - /* No callback? Tell other side not to bother us. */ if (!callback) { vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE; @@ -1815,8 +1769,6 @@ static struct virtqueue *vring_create_virtqueue_packed( spin_unlock(&vdev->vqs_list_lock); return &vq->vq; -err_buflen: - kfree(vq->packed.desc_extra); err_desc_extra: kfree(vq->packed.desc_state); err_desc_state: @@ -2224,7 +2176,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, void (*callback)(struct virtqueue *), const char *name) { - struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver); struct vring_virtqueue *vq; if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) @@ -2284,15 +2235,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, if (!vq->split.desc_extra) goto err_extra; - if (!drv->suppress_used_validation || force_used_validation) { - vq->buflen = kmalloc_array(vring.num, sizeof(*vq->buflen), - GFP_KERNEL); - if (!vq->buflen) - goto err_buflen; - } else { - vq->buflen = NULL; - } - /* Put everything in free lists. */ vq->free_head = 0; memset(vq->split.desc_state, 0, vring.num * @@ -2303,8 +2245,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, spin_unlock(&vdev->vqs_list_lock); return &vq->vq; -err_buflen: - kfree(vq->split.desc_extra); err_extra: kfree(vq->split.desc_state); err_state: diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 44d0e09da2d9f3..41edbc01ffa403 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -152,7 +152,6 @@ size_t virtio_max_dma_size(struct virtio_device *vdev); * @feature_table_size: number of entries in the feature table array. * @feature_table_legacy: same as feature_table but when working in legacy mode. * @feature_table_size_legacy: number of entries in feature table legacy array. - * @suppress_used_validation: set to not have core validate used length * @probe: the function to call when a device is found. Returns 0 or -errno. * @scan: optional function to call after successful probe; intended * for virtio-scsi to invoke a scan. @@ -169,7 +168,6 @@ struct virtio_driver { unsigned int feature_table_size; const unsigned int *feature_table_legacy; unsigned int feature_table_size_legacy; - bool suppress_used_validation; int (*validate)(struct virtio_device *dev); int (*probe)(struct virtio_device *dev); void (*scan)(struct virtio_device *dev); From 49d8c5ffad07ca014cfae72a1b9b8c52b6ad9cb8 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Mon, 22 Nov 2021 17:35:24 +0100 Subject: [PATCH 281/358] vhost/vsock: fix incorrect used length reported to the guest The "used length" reported by calling vhost_add_used() must be the number of bytes written by the device (using "in" buffers). In vhost_vsock_handle_tx_kick() the device only reads the guest buffers (they are all "out" buffers), without writing anything, so we must pass 0 as "used length" to comply virtio spec. Fixes: 433fc58e6bf2 ("VSOCK: Introduce vhost_vsock.ko") Cc: stable@vger.kernel.org Reported-by: Halil Pasic Suggested-by: Jason Wang Signed-off-by: Stefano Garzarella Link: https://lore.kernel.org/r/20211122163525.294024-2-sgarzare@redhat.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefan Hajnoczi Reviewed-by: Halil Pasic --- drivers/vhost/vsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 938aefbc75ecc2..4e3b95af7ee4d4 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -554,7 +554,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) virtio_transport_free_pkt(pkt); len += sizeof(pkt->hdr); - vhost_add_used(vq, head, len); + vhost_add_used(vq, head, 0); total_len += len; added = true; } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); From 11708ff92c1dba9aaa59168c46c5317677595942 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Mon, 22 Nov 2021 17:35:25 +0100 Subject: [PATCH 282/358] vhost/vsock: cleanup removing `len` variable We can increment `total_len` directly and remove `len` since it is no longer used for vhost_add_used(). Signed-off-by: Stefano Garzarella Link: https://lore.kernel.org/r/20211122163525.294024-3-sgarzare@redhat.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefan Hajnoczi --- drivers/vhost/vsock.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 4e3b95af7ee4d4..d6ca1c7ad513ff 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -511,8 +511,6 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) vhost_disable_notify(&vsock->dev, vq); do { - u32 len; - if (!vhost_vsock_more_replies(vsock)) { /* Stop tx until the device processes already * pending replies. Leave tx virtqueue @@ -540,7 +538,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) continue; } - len = pkt->len; + total_len += sizeof(pkt->hdr) + pkt->len; /* Deliver to monitoring devices all received packets */ virtio_transport_deliver_tap_pkt(pkt); @@ -553,9 +551,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) else virtio_transport_free_pkt(pkt); - len += sizeof(pkt->hdr); vhost_add_used(vq, head, 0); - total_len += len; added = true; } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); From 0466a39bd0b6c462338f10d18076703d14a552de Mon Sep 17 00:00:00 2001 From: Ye Guojin Date: Wed, 17 Nov 2021 06:39:55 +0000 Subject: [PATCH 283/358] virtio-blk: modify the value type of num in virtio_queue_rq() This was found by coccicheck: ./drivers/block/virtio_blk.c, 334, 14-17, WARNING Unsigned expression compared with zero num < 0 Reported-by: Zeal Robot Signed-off-by: Ye Guojin Link: https://lore.kernel.org/r/20211117063955.160777-1-ye.guojin@zte.com.cn Signed-off-by: Michael S. Tsirkin Fixes: 02746e26c39e ("virtio-blk: avoid preallocating big SGL for data") Reviewed-by: Stefano Garzarella Reviewed-by: Max Gurtovoy Reviewed-by: Stefan Hajnoczi --- drivers/block/virtio_blk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 1a1b1189225dd6..6ae38776e30e50 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -316,7 +316,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req = bd->rq; struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); unsigned long flags; - unsigned int num; + int num; int qid = hctx->queue_num; bool notify = false; blk_status_t status; From ea8f17e44fa7d54fae287ccbe30ce269afb5ee42 Mon Sep 17 00:00:00 2001 From: Wu Zongyong Date: Mon, 15 Nov 2021 11:16:42 +0800 Subject: [PATCH 284/358] vhost-vdpa: clean irqs before reseting vdpa device Vdpa devices should be reset after unseting irqs of virtqueues, or we will get errors when killing qemu process: >> pi_update_irte: failed to update PI IRTE >> irq bypass consumer (token 0000000065102a43) unregistration fails: -22 Signed-off-by: Wu Zongyong Link: https://lore.kernel.org/r/a2cb60cf73be9da5c4e6399242117d8818f975ae.1636946171.git.wuzongyong@linux.alibaba.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vhost/vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 01c59ce7e25080..29cced1cd27784 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -1014,12 +1014,12 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) mutex_lock(&d->mutex); filep->private_data = NULL; + vhost_vdpa_clean_irq(v); vhost_vdpa_reset(v); vhost_dev_stop(&v->vdev); vhost_vdpa_iotlb_free(v); vhost_vdpa_free_domain(v); vhost_vdpa_config_put(v); - vhost_vdpa_clean_irq(v); vhost_dev_cleanup(&v->vdev); kfree(v->vdev.vqs); mutex_unlock(&d->mutex); From bb93ce4b150dde79f58e34103cbd1fe829796649 Mon Sep 17 00:00:00 2001 From: Longpeng Date: Wed, 24 Nov 2021 09:52:15 +0800 Subject: [PATCH 285/358] vdpa_sim: avoid putting an uninitialized iova_domain The system will crash if we put an uninitialized iova_domain, this could happen when an error occurs before initializing the iova_domain in vdpasim_create(). BUG: kernel NULL pointer dereference, address: 0000000000000000 ... RIP: 0010:__cpuhp_state_remove_instance+0x96/0x1c0 ... Call Trace: put_iova_domain+0x29/0x220 vdpasim_free+0xd1/0x120 [vdpa_sim] vdpa_release_dev+0x21/0x40 [vdpa] device_release+0x33/0x90 kobject_release+0x63/0x160 vdpasim_create+0x127/0x2a0 [vdpa_sim] vdpasim_net_dev_add+0x7d/0xfe [vdpa_sim_net] vdpa_nl_cmd_dev_add_set_doit+0xe1/0x1a0 [vdpa] genl_family_rcv_msg_doit+0x112/0x140 genl_rcv_msg+0xdf/0x1d0 ... So we must make sure the iova_domain is already initialized before put it. In addition, we may get the following warning in this case: WARNING: ... drivers/iommu/iova.c:344 iova_cache_put+0x58/0x70 So we must make sure the iova_cache_put() is invoked only if the iova_cache_get() is already invoked. Let's fix it together. Cc: stable@vger.kernel.org Fixes: 4080fc106750 ("vdpa_sim: use iova module to allocate IOVA addresses") Signed-off-by: Longpeng Acked-by: Jason Wang Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20211124015215.119-1-longpeng2@huawei.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 5f484fff8dbecb..41b0cd17fcbac1 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -591,8 +591,11 @@ static void vdpasim_free(struct vdpa_device *vdpa) vringh_kiov_cleanup(&vdpasim->vqs[i].in_iov); } - put_iova_domain(&vdpasim->iova); - iova_cache_put(); + if (vdpa_get_dma_dev(vdpa)) { + put_iova_domain(&vdpasim->iova); + iova_cache_put(); + } + kvfree(vdpasim->buffer); if (vdpasim->iommu) vhost_iotlb_free(vdpasim->iommu); From 550b8e1d182cdc59bf99852503b9ce8a5ab2c34e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 23 Nov 2021 14:24:22 -0800 Subject: [PATCH 286/358] MAINTAINERS: Update B53 section to cover SF2 switch driver Update the B53 Ethernet switch section to contain drivers/net/dsa/bcm_sf2*. Reported-by: Russell King (Oracle) Signed-off-by: Florian Fainelli Acked-by: Russell King (Oracle) Link: https://lore.kernel.org/r/20211123222422.3745485-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 2f1e78333883a7..384566f6119200 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3570,13 +3570,14 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/b44.* -BROADCOM B53 ETHERNET SWITCH DRIVER +BROADCOM B53/SF2 ETHERNET SWITCH DRIVER M: Florian Fainelli L: netdev@vger.kernel.org L: openwrt-devel@lists.openwrt.org (subscribers-only) S: Supported F: Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml F: drivers/net/dsa/b53/* +F: drivers/net/dsa/bcm_sf2* F: include/linux/dsa/brcm.h F: include/linux/platform_data/b53.h From 4e1fddc98d2585ddd4792b5e44433dcee7ece001 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Nov 2021 12:25:35 -0800 Subject: [PATCH 287/358] tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows While testing BIG TCP patch series, I was expecting that TCP_RR workloads with 80KB requests/answers would send one 80KB TSO packet, then being received as a single GRO packet. It turns out this was not happening, and the root cause was that cubic Hystart ACK train was triggering after a few (2 or 3) rounds of RPC. Hystart was wrongly setting CWND/SSTHRESH to 30, while my RPC needed a budget of ~20 segments. Ideally these TCP_RR flows should not exit slow start. Cubic Hystart should reset itself at each round, instead of assuming every TCP flow is a bulk one. Note that even after this patch, Hystart can still trigger, depending on scheduling artifacts, but at a higher CWND/SSTHRESH threshold, keeping optimal TSO packet sizes. Tested: ip link set dev eth0 gro_ipv6_max_size 131072 gso_ipv6_max_size 131072 nstat -n; netperf -H ... -t TCP_RR -l 5 -- -r 80000,80000 -K cubic; nstat|egrep "Ip6InReceives|Hystart|Ip6OutRequests" Before: 8605 Ip6InReceives 87541 0.0 Ip6OutRequests 129496 0.0 TcpExtTCPHystartTrainDetect 1 0.0 TcpExtTCPHystartTrainCwnd 30 0.0 After: 8760 Ip6InReceives 88514 0.0 Ip6OutRequests 87975 0.0 Fixes: ae27e98a5152 ("[TCP] CUBIC v2.3") Co-developed-by: Neal Cardwell Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Cc: Yuchung Cheng Cc: Soheil Hassas Yeganeh Link: https://lore.kernel.org/r/20211123202535.1843771-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_cubic.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5e9d9c51164c4d..e07837e23b3fd2 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -330,8 +330,6 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; if (tcp_in_slow_start(tp)) { - if (hystart && after(ack, ca->end_seq)) - bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); if (!acked) return; @@ -391,6 +389,9 @@ static void hystart_update(struct sock *sk, u32 delay) struct bictcp *ca = inet_csk_ca(sk); u32 threshold; + if (after(tp->snd_una, ca->end_seq)) + bictcp_hystart_reset(sk); + if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); From ddb826c2c92d461f290a7bab89e7c28696191875 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 24 Nov 2021 08:16:25 +0100 Subject: [PATCH 288/358] lan743x: fix deadlock in lan743x_phy_link_status_change() Usage of phy_ethtool_get_link_ksettings() in the link status change handler isn't needed, and in combination with the referenced change it results in a deadlock. Simply remove the call and replace it with direct access to phydev->speed. The duplex argument of lan743x_phy_update_flowcontrol() isn't used and can be removed. Fixes: c10a485c3de5 ("phy: phy_ethtool_ksettings_get: Lock the phy for consistency") Reported-by: Alessandro B Maurici Tested-by: Alessandro B Maurici Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/40e27f76-0ba3-dcef-ee32-a78b9df38b0f@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microchip/lan743x_main.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 4fc97823bc84fb..7d7647481f70e9 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -914,8 +914,7 @@ static int lan743x_phy_reset(struct lan743x_adapter *adapter) } static void lan743x_phy_update_flowcontrol(struct lan743x_adapter *adapter, - u8 duplex, u16 local_adv, - u16 remote_adv) + u16 local_adv, u16 remote_adv) { struct lan743x_phy *phy = &adapter->phy; u8 cap; @@ -943,7 +942,6 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) phy_print_status(phydev); if (phydev->state == PHY_RUNNING) { - struct ethtool_link_ksettings ksettings; int remote_advertisement = 0; int local_advertisement = 0; @@ -980,18 +978,14 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) } lan743x_csr_write(adapter, MAC_CR, data); - memset(&ksettings, 0, sizeof(ksettings)); - phy_ethtool_get_link_ksettings(netdev, &ksettings); local_advertisement = linkmode_adv_to_mii_adv_t(phydev->advertising); remote_advertisement = linkmode_adv_to_mii_adv_t(phydev->lp_advertising); - lan743x_phy_update_flowcontrol(adapter, - ksettings.base.duplex, - local_advertisement, + lan743x_phy_update_flowcontrol(adapter, local_advertisement, remote_advertisement); - lan743x_ptp_update_latency(adapter, ksettings.base.speed); + lan743x_ptp_update_latency(adapter, phydev->speed); } } From 80662f4fd4771bc9c7cc4abdfbe866ebd1179621 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 23 Nov 2021 16:44:02 +0100 Subject: [PATCH 289/358] net: phylink: Force link down and retrigger resolve on interface change MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On PHY state change the phylink_resolve() function can read stale information from the MAC and report incorrect link speed and duplex to the kernel message log. Example with a Marvell 88X3310 PHY connected to a SerDes port on Marvell 88E6393X switch: - PHY driver triggers state change due to PHY interface mode being changed from 10gbase-r to 2500base-x due to copper change in speed from 10Gbps to 2.5Gbps, but the PHY itself either hasn't yet changed its interface to the host, or the interrupt about loss of SerDes link hadn't arrived yet (there can be a delay of several milliseconds for this), so we still think that the 10gbase-r mode is up - phylink_resolve() - phylink_mac_pcs_get_state() - this fills in speed=10g link=up - interface mode is updated to 2500base-x but speed is left at 10Gbps - phylink_major_config() - interface is changed to 2500base-x - phylink_link_up() - mv88e6xxx_mac_link_up() - .port_set_speed_duplex() - speed is set to 10Gbps - reports "Link is Up - 10Gbps/Full" to dmesg Afterwards when the interrupt finally arrives for mv88e6xxx, another resolve is forced in which we get the correct speed from phylink_mac_pcs_get_state(), but since the interface is not being changed anymore, we don't call phylink_major_config() but only phylink_mac_config(), which does not set speed/duplex anymore. To fix this, we need to force the link down and trigger another resolve on PHY interface change event. Fixes: 9525ae83959b ("phylink: add phylink infrastructure") Signed-off-by: Russell King (Oracle) Signed-off-by: Marek Behún Signed-off-by: Jakub Kicinski --- drivers/net/phy/phylink.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 3ad7397b81198a..708d2a984621c3 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -710,6 +710,7 @@ static void phylink_resolve(struct work_struct *w) struct phylink_link_state link_state; struct net_device *ndev = pl->netdev; bool mac_config = false; + bool retrigger = false; bool cur_link_state; mutex_lock(&pl->state_mutex); @@ -723,6 +724,7 @@ static void phylink_resolve(struct work_struct *w) link_state.link = false; } else if (pl->mac_link_dropped) { link_state.link = false; + retrigger = true; } else { switch (pl->cur_link_an_mode) { case MLO_AN_PHY: @@ -747,6 +749,15 @@ static void phylink_resolve(struct work_struct *w) /* Only update if the PHY link is up */ if (pl->phydev && pl->phy_state.link) { + /* If the interface has changed, force a + * link down event if the link isn't already + * down, and re-resolve. + */ + if (link_state.interface != + pl->phy_state.interface) { + retrigger = true; + link_state.link = false; + } link_state.interface = pl->phy_state.interface; /* If we have a PHY, we need to update with @@ -789,7 +800,7 @@ static void phylink_resolve(struct work_struct *w) else phylink_link_up(pl, link_state); } - if (!link_state.link && pl->mac_link_dropped) { + if (!link_state.link && retrigger) { pl->mac_link_dropped = false; queue_work(system_power_efficient_wq, &pl->resolve); } From dbae3388ea9ca33bd1d5eabc3b0ef17e69c74677 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 23 Nov 2021 16:44:03 +0100 Subject: [PATCH 290/358] net: phylink: Force retrigger in case of latched link-fail indicator MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On mv88e6xxx 1G/2.5G PCS, the SerDes register 4.2001.2 has the following description: This register bit indicates when link was lost since the last read. For the current link status, read this register back-to-back. Thus to get current link state, we need to read the register twice. But doing that in the link change interrupt handler would lead to potentially ignoring link down events, which we really want to avoid. Thus this needs to be solved in phylink's resolve, by retriggering another resolve in the event when PCS reports link down and previous link was up, and by re-reading PCS state if the previous link was down. The wrong value is read when phylink requests change from sgmii to 2500base-x mode, and link won't come up. This fixes the bug. Fixes: 9525ae83959b ("phylink: add phylink infrastructure") Signed-off-by: Russell King (Oracle) Signed-off-by: Marek Behún Signed-off-by: Jakub Kicinski --- drivers/net/phy/phylink.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 708d2a984621c3..5904546acae616 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -741,6 +741,19 @@ static void phylink_resolve(struct work_struct *w) case MLO_AN_INBAND: phylink_mac_pcs_get_state(pl, &link_state); + /* The PCS may have a latching link-fail indicator. + * If the link was up, bring the link down and + * re-trigger the resolve. Otherwise, re-read the + * PCS state to get the current status of the link. + */ + if (!link_state.link) { + if (cur_link_state) + retrigger = true; + else + phylink_mac_pcs_get_state(pl, + &link_state); + } + /* If we have a phy, the "up" state is the union of * both the PHY and the MAC */ From 587acad41f1bc48e16f42bb2aca63bf323380be8 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 24 Nov 2021 13:32:37 +0100 Subject: [PATCH 291/358] net/smc: Fix NULL pointer dereferencing in smc_vlan_by_tcpsk() Coverity reports a possible NULL dereferencing problem: in smc_vlan_by_tcpsk(): 6. returned_null: netdev_lower_get_next returns NULL (checked 29 out of 30 times). 7. var_assigned: Assigning: ndev = NULL return value from netdev_lower_get_next. 1623 ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); CID 1468509 (#1 of 1): Dereference null return value (NULL_RETURNS) 8. dereference: Dereferencing a pointer that might be NULL ndev when calling is_vlan_dev. 1624 if (is_vlan_dev(ndev)) { Remove the manual implementation and use netdev_walk_all_lower_dev() to iterate over the lower devices. While on it remove an obsolete function parameter comment. Fixes: cb9d43f67754 ("net/smc: determine vlan_id of stacked net_device") Suggested-by: Julian Wiedmann Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- net/smc/smc_core.c | 35 ++++++++++++++++++----------------- 1 file changed, 18 insertions(+), 17 deletions(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 25ebd30feecd60..bb52c8b5f148af 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1672,14 +1672,26 @@ static void smc_link_down_work(struct work_struct *work) mutex_unlock(&lgr->llc_conf_mutex); } -/* Determine vlan of internal TCP socket. - * @vlan_id: address to store the determined vlan id into - */ +static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) +{ + unsigned short *vlan_id = (unsigned short *)priv->data; + + if (is_vlan_dev(lower_dev)) { + *vlan_id = vlan_dev_vlan_id(lower_dev); + return 1; + } + + return 0; +} + +/* Determine vlan of internal TCP socket. */ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(clcsock->sk); + struct netdev_nested_priv priv; struct net_device *ndev; - int i, nest_lvl, rc = 0; + int rc = 0; ini->vlan_id = 0; if (!dst) { @@ -1697,20 +1709,9 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) goto out_rel; } + priv.data = (void *)&ini->vlan_id; rtnl_lock(); - nest_lvl = ndev->lower_level; - for (i = 0; i < nest_lvl; i++) { - struct list_head *lower = &ndev->adj_list.lower; - - if (list_empty(lower)) - break; - lower = lower->next; - ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); - if (is_vlan_dev(ndev)) { - ini->vlan_id = vlan_dev_vlan_id(ndev); - break; - } - } + netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv); rtnl_unlock(); out_rel: From 9ebb0c4b27a6158303b791b5b91e66d7665ee30e Mon Sep 17 00:00:00 2001 From: Guo DaXing Date: Wed, 24 Nov 2021 13:32:38 +0100 Subject: [PATCH 292/358] net/smc: Fix loop in smc_listen The kernel_listen function in smc_listen will fail when all the available ports are occupied. At this point smc->clcsock->sk->sk_data_ready has been changed to smc_clcsock_data_ready. When we call smc_listen again, now both smc->clcsock->sk->sk_data_ready and smc->clcsk_data_ready point to the smc_clcsock_data_ready function. The smc_clcsock_data_ready() function calls lsmc->clcsk_data_ready which now points to itself resulting in an infinite loop. This patch restores smc->clcsock->sk->sk_data_ready with the old value. Fixes: a60a2b1e0af1 ("net/smc: reduce active tcp_listen workers") Signed-off-by: Guo DaXing Acked-by: Tony Lu Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- net/smc/af_smc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 2692cba5a7b682..4b62c925a13e88 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2134,8 +2134,10 @@ static int smc_listen(struct socket *sock, int backlog) smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); rc = kernel_listen(smc->clcsock, backlog); - if (rc) + if (rc) { + smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; goto out; + } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = SMC_LISTEN; From f8fbfd85f5c95fff477a7c19f576725945891d0c Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 7 Nov 2021 16:22:57 +0100 Subject: [PATCH 293/358] ksmbd: Fix an error handling path in 'smb2_sess_setup()' All the error handling paths of 'smb2_sess_setup()' end to 'out_err'. All but the new error handling path added by the commit given in the Fixes tag below. Fix this error handling path and branch to 'out_err' as well. Fixes: 0d994cd482ee ("ksmbd: add buffer validation in session setup") Cc: stable@vger.kernel.org # v5.15 Acked-by: Namjae Jeon Signed-off-by: Christophe JAILLET Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 121f8e8c70aca1..7d2e8599dc27c3 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1697,8 +1697,10 @@ int smb2_sess_setup(struct ksmbd_work *work) negblob_off = le16_to_cpu(req->SecurityBufferOffset); negblob_len = le16_to_cpu(req->SecurityBufferLength); if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) || - negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) - return -EINVAL; + negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) { + rc = -EINVAL; + goto out_err; + } negblob = (struct negotiate_message *)((char *)&req->hdr.ProtocolId + negblob_off); From 2d239f0f6ad0cffc4622a6b35d54aa0a123cc764 Mon Sep 17 00:00:00 2001 From: Salvatore Bonaccorso Date: Fri, 19 Nov 2021 22:12:14 +0100 Subject: [PATCH 294/358] docs: filesystem: cifs: ksmbd: Fix small layout issues In some senteces there were missing spaces between words. Fix wording in item to show which prints are enabled and add a space beween the cat command and its argument. Cc: Sergey Senozhatsky Cc: Steve French CC: Hyunchul Lee Cc: linux-cifs@vger.kernel.org Acked-by: Namjae Jeon Signed-off-by: Salvatore Bonaccorso Signed-off-by: Steve French --- Documentation/filesystems/cifs/ksmbd.rst | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/filesystems/cifs/ksmbd.rst b/Documentation/filesystems/cifs/ksmbd.rst index a1326157d53ff4..b0d354fd806661 100644 --- a/Documentation/filesystems/cifs/ksmbd.rst +++ b/Documentation/filesystems/cifs/ksmbd.rst @@ -50,11 +50,11 @@ ksmbd.mountd (user space daemon) -------------------------------- ksmbd.mountd is userspace process to, transfer user account and password that -are registered using ksmbd.adduser(part of utils for user space). Further it +are registered using ksmbd.adduser (part of utils for user space). Further it allows sharing information parameters that parsed from smb.conf to ksmbd in kernel. For the execution part it has a daemon which is continuously running and connected to the kernel interface using netlink socket, it waits for the -requests(dcerpc and share/user info). It handles RPC calls (at a minimum few +requests (dcerpc and share/user info). It handles RPC calls (at a minimum few dozen) that are most important for file server from NetShareEnum and NetServerGetInfo. Complete DCE/RPC response is prepared from the user space and passed over to the associated kernel thread for the client. @@ -154,11 +154,11 @@ Each layer 1. Enable all component prints # sudo ksmbd.control -d "all" -2. Enable one of components(smb, auth, vfs, oplock, ipc, conn, rdma) +2. Enable one of components (smb, auth, vfs, oplock, ipc, conn, rdma) # sudo ksmbd.control -d "smb" -3. Show what prints are enable. - # cat/sys/class/ksmbd-control/debug +3. Show what prints are enabled. + # cat /sys/class/ksmbd-control/debug [smb] auth vfs oplock ipc conn [rdma] 4. Disable prints: From 8e537d1465e7401f352a6e0a728a93f8cad5294a Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Nov 2021 07:48:45 +0900 Subject: [PATCH 295/358] ksmbd: downgrade addition info error msg to debug in smb2_get_info_sec() While file transfer through windows client, This error flood message happen. This flood message will cause performance degradation and misunderstand server has problem. Fixes: e294f78d3478 ("ksmbd: allow PROTECTED_DACL_SECINFO and UNPROTECTED_DACL_SECINFO addition information in smb2 set info security") Cc: stable@vger.kernel.org # v5.15 Acked-by: Hyunchul Lee Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 7d2e8599dc27c3..a513ea52325081 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -5070,7 +5070,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work, if (addition_info & ~(OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO | PROTECTED_DACL_SECINFO | UNPROTECTED_DACL_SECINFO)) { - pr_err("Unsupported addition info: 0x%x)\n", + ksmbd_debug(SMB, "Unsupported addition info: 0x%x)\n", addition_info); pntsd->revision = cpu_to_le16(1); From 1ec72153ff434ce75bace3044dc89a23a05d7064 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Nov 2021 11:32:39 +0900 Subject: [PATCH 296/358] ksmbd: contain default data stream even if xattr is empty If xattr is not supported like exfat or fat, ksmbd server doesn't contain default data stream in FILE_STREAM_INFORMATION response. It will cause ppt or doc file update issue if local filesystem is such as ones. This patch move goto statement to contain it. Fixes: 9f6323311c70 ("ksmbd: add default data stream name in FILE_STREAM_INFORMATION") Cc: stable@vger.kernel.org # v5.15 Acked-by: Hyunchul Lee Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index a513ea52325081..370a32b9308798 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -4459,6 +4459,12 @@ static void get_file_stream_info(struct ksmbd_work *work, &stat); file_info = (struct smb2_file_stream_info *)rsp->Buffer; + buf_free_len = + smb2_calc_max_out_buf_len(work, 8, + le32_to_cpu(req->OutputBufferLength)); + if (buf_free_len < 0) + goto out; + xattr_list_len = ksmbd_vfs_listxattr(path->dentry, &xattr_list); if (xattr_list_len < 0) { goto out; @@ -4467,12 +4473,6 @@ static void get_file_stream_info(struct ksmbd_work *work, goto out; } - buf_free_len = - smb2_calc_max_out_buf_len(work, 8, - le32_to_cpu(req->OutputBufferLength)); - if (buf_free_len < 0) - goto out; - while (idx < xattr_list_len) { stream_name = xattr_list + idx; streamlen = strlen(stream_name); @@ -4516,6 +4516,7 @@ static void get_file_stream_info(struct ksmbd_work *work, file_info->NextEntryOffset = cpu_to_le32(next); } +out: if (!S_ISDIR(stat.mode) && buf_free_len >= sizeof(struct smb2_file_stream_info) + 7 * 2) { file_info = (struct smb2_file_stream_info *) @@ -4524,14 +4525,13 @@ static void get_file_stream_info(struct ksmbd_work *work, "::$DATA", 7, conn->local_nls, 0); streamlen *= 2; file_info->StreamNameLength = cpu_to_le32(streamlen); - file_info->StreamSize = 0; - file_info->StreamAllocationSize = 0; + file_info->StreamSize = cpu_to_le64(stat.size); + file_info->StreamAllocationSize = cpu_to_le64(stat.blocks << 9); nbytes += sizeof(struct smb2_file_stream_info) + streamlen; } /* last entry offset should be 0 */ file_info->NextEntryOffset = 0; -out: kvfree(xattr_list); rsp->OutputBufferLength = cpu_to_le32(nbytes); From 178ca6f85aa3231094467691f5ea1ff2f398aa8d Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 24 Nov 2021 10:23:02 +0900 Subject: [PATCH 297/358] ksmbd: fix memleak in get_file_stream_info() Fix memleak in get_file_stream_info() Fixes: 34061d6b76a4 ("ksmbd: validate OutputBufferLength of QUERY_DIR, QUERY_INFO, IOCTL requests") Cc: stable@vger.kernel.org # v5.15 Reported-by: Coverity Scan Acked-by: Hyunchul Lee Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 370a32b9308798..49c9da37315c83 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -4498,8 +4498,10 @@ static void get_file_stream_info(struct ksmbd_work *work, ":%s", &stream_name[XATTR_NAME_STREAM_LEN]); next = sizeof(struct smb2_file_stream_info) + streamlen * 2; - if (next > buf_free_len) + if (next > buf_free_len) { + kfree(stream_buf); break; + } file_info = (struct smb2_file_stream_info *)&rsp->Buffer[nbytes]; streamlen = smbConvertToUTF16((__le16 *)file_info->StreamName, From fbf3bce458214bb971d3d571515b3b129eac290b Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 19 Nov 2021 17:50:52 +0000 Subject: [PATCH 298/358] MIPS: boot/compressed/: add __ashldi3 to target for ZSTD compression Just like before with __bswapdi2(), for MIPS pre-boot when CONFIG_KERNEL_ZSTD=y the decompressor function will use __ashldi3(), so the object file should be added to the target object file. Fixes these build errors: mipsel-linux-ld: arch/mips/boot/compressed/decompress.o: in function `FSE_buildDTable_internal': decompress.c:(.text.FSE_buildDTable_internal+0x48): undefined reference to `__ashldi3' mipsel-linux-ld: arch/mips/boot/compressed/decompress.o: in function `FSE_decompress_wksp_body_default': decompress.c:(.text.FSE_decompress_wksp_body_default+0xa8): undefined reference to `__ashldi3' mipsel-linux-ld: arch/mips/boot/compressed/decompress.o: in function `ZSTD_getFrameHeader_advanced': decompress.c:(.text.ZSTD_getFrameHeader_advanced+0x134): undefined reference to `__ashldi3' Signed-off-by: Paul Cercueil Reviewed-by: Randy Dunlap Signed-off-by: Thomas Bogendoerfer --- arch/mips/boot/compressed/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 2861a05c2e0c04..f27cf31b414014 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -52,7 +52,7 @@ endif vmlinuzobjs-$(CONFIG_KERNEL_XZ) += $(obj)/ashldi3.o -vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o +vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o $(obj)/ashldi3.o targets := $(notdir $(vmlinuzobjs-y)) From 473441720c8616dfaf4451f9c7ea14f0eb5e5d65 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 25 Nov 2021 14:05:18 +0100 Subject: [PATCH 299/358] fuse: release pipe buf after last use Checking buf->flags should be done before the pipe_buf_release() is called on the pipe buffer, since releasing the buffer might modify the flags. This is exactly what page_cache_pipe_buf_release() does, and which results in the same VM_BUG_ON_PAGE(PageLRU(page)) that the original patch was trying to fix. Reported-by: Justin Forbes Fixes: 712a951025c0 ("fuse: fix page stealing") Cc: # v2.6.35 Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 79f7eda49e06cb..cd54a529460da9 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -847,17 +847,17 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) replace_page_cache_page(oldpage, newpage); + get_page(newpage); + + if (!(buf->flags & PIPE_BUF_FLAG_LRU)) + lru_cache_add(newpage); + /* * Release while we have extra ref on stolen page. Otherwise * anon_pipe_buf_release() might think the page can be reused. */ pipe_buf_release(cs->pipe, buf); - get_page(newpage); - - if (!(buf->flags & PIPE_BUF_FLAG_LRU)) - lru_cache_add(newpage); - err = 0; spin_lock(&cs->req->waitq.lock); if (test_bit(FR_ABORTED, &cs->req->flags)) From a0eb2da92b715d0c97b96b09979689ea09faefe6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Almeida?= Date: Wed, 24 Nov 2021 10:21:12 -0300 Subject: [PATCH 300/358] futex: Wireup futex_waitv syscall MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Wireup futex_waitv syscall for all remaining archs. Signed-off-by: André Almeida Acked-by: Max Filippov Acked-by: Geert Uytterhoeven Tested-by: Michael Ellerman (powerpc) Signed-off-by: Arnd Bergmann --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + 8 files changed, 8 insertions(+) diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index e4a041cd57154b..ca5a32228cd6e5 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -488,3 +488,4 @@ 556 common landlock_restrict_self sys_landlock_restrict_self # 557 reserved for memfd_secret 558 common process_mrelease sys_process_mrelease +559 common futex_waitv sys_futex_waitv diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 6fea1844fb9527..707ae121f6d391 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -369,3 +369,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7976dff8f879d6..45bc32a41b903c 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -448,3 +448,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 6b0e11362bd2eb..2204bde3ce4a04 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -454,3 +454,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 7bef917cc84e64..15109af9d0754d 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -528,3 +528,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 208f131659c5a3..d9539d28bdaa1c 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -451,3 +451,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index c37764dc764d13..46adabcb1720f6 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -494,3 +494,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 104b327f8ac9fd..3e3e1a506bed1a 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -419,3 +419,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv From 82be5f5bd390aeb5214a966ea39290a5d49df252 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Mon, 22 Nov 2021 18:17:25 -0600 Subject: [PATCH 301/358] MAINTAINERS: Update maintainer entry for keystone platforms Switch the kernel tree for keystone to the consolidated ti tree and add myself as primary maintainer for keystone platforms to offset Santosh's workload. Signed-off-by: Nishanth Menon Acked-by: Santosh Shilimkar Link: https://lore.kernel.org/r/20211123001725.21422-1-nm@ti.com' Signed-off-by: Arnd Bergmann --- MAINTAINERS | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index a241e6e3b7d200..a1fb7f6307ba26 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2738,10 +2738,11 @@ S: Maintained F: drivers/memory/*emif* ARM/TEXAS INSTRUMENT KEYSTONE ARCHITECTURE +M: Nishanth Menon M: Santosh Shilimkar L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/ti/linux.git F: arch/arm/boot/dts/keystone-* F: arch/arm/mach-keystone/ @@ -19040,11 +19041,12 @@ F: drivers/mmc/host/tifm_sd.c F: include/linux/tifm.h TI KEYSTONE MULTICORE NAVIGATOR DRIVERS +M: Nishanth Menon M: Santosh Shilimkar L: linux-kernel@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/ti/linux.git F: drivers/soc/ti/* TI LM49xxx FAMILY ASoC CODEC DRIVERS From 5fe762515bc9dd0476ed1de06377d7186565da99 Mon Sep 17 00:00:00 2001 From: Chanho Park Date: Wed, 24 Nov 2021 09:50:41 +0100 Subject: [PATCH 302/358] arm64: dts: exynos: drop samsung,ufs-shareability-reg-offset in ExynosAutov9 samsung,ufs-shareability-reg-offset is not necessary anymore since it was integrated into the second argument of samsung,sysreg. Fixes: 31bbac5263aa ("arm64: dts: exynos: add initial support for exynosautov9 SoC") Signed-off-by: Chanho Park Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20211102064826.15796-1-chanho61.park@samsung.com Link: https://lore.kernel.org/r/20211124085042.9649-2-krzysztof.kozlowski@canonical.com' Signed-off-by: Arnd Bergmann --- arch/arm64/boot/dts/exynos/exynosautov9.dtsi | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi index 3e4727344b4ac5..a960c0bc2dba2a 100644 --- a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi +++ b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi @@ -296,8 +296,7 @@ pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>; phys = <&ufs_0_phy>; phy-names = "ufs-phy"; - samsung,sysreg = <&syscon_fsys2>; - samsung,ufs-shareability-reg-offset = <0x710>; + samsung,sysreg = <&syscon_fsys2 0x710>; status = "disabled"; }; }; From 383a44aec91c327ef4a9d03cfa65d1eaf3746c06 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Wed, 24 Nov 2021 09:50:42 +0100 Subject: [PATCH 303/358] memory: mtk-smi: Fix a null dereference for the ostd We add the ostd setting for mt8195. It introduces a KE for the previous SoC which doesn't have ostd setting. This is the log: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000080 ... pc : mtk_smi_larb_config_port_gen2_general+0x64/0x130 lr : mtk_smi_larb_resume+0x54/0x98 ... Call trace: mtk_smi_larb_config_port_gen2_general+0x64/0x130 pm_generic_runtime_resume+0x2c/0x48 __genpd_runtime_resume+0x30/0xa8 genpd_runtime_resume+0x94/0x2c8 __rpm_callback+0x44/0x150 rpm_callback+0x6c/0x78 rpm_resume+0x310/0x558 __pm_runtime_resume+0x3c/0x88 In the code: larbostd = larb->larb_gen->ostd[larb->larbid], if "larb->larb_gen->ostd" is null, the "larbostd" is the offset(e.g. 0x80 above), it's also a valid value, then accessing "larbostd[i]" in the "for" loop will cause the KE above. To avoid this issue, initialize "larbostd" to NULL when the SoC doesn't have ostd setting. Fixes: fe6dd2a4017d ("memory: mtk-smi: mt8195: Add initial setting for smi-larb") Signed-off-by: Yong Wu Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20211108082429.15080-1-yong.wu@mediatek.com Link: https://lore.kernel.org/r/20211124085042.9649-3-krzysztof.kozlowski@canonical.com' Signed-off-by: Arnd Bergmann --- drivers/memory/mtk-smi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c index b883dcc0bbfa46..e201e5976f34f9 100644 --- a/drivers/memory/mtk-smi.c +++ b/drivers/memory/mtk-smi.c @@ -241,7 +241,7 @@ static void mtk_smi_larb_config_port_gen2_general(struct device *dev) { struct mtk_smi_larb *larb = dev_get_drvdata(dev); u32 reg, flags_general = larb->larb_gen->flags_general; - const u8 *larbostd = larb->larb_gen->ostd[larb->larbid]; + const u8 *larbostd = larb->larb_gen->ostd ? larb->larb_gen->ostd[larb->larbid] : NULL; int i; if (BIT(larb->larbid) & larb->larb_gen->larb_direct_to_common_mask) From c024b226a417c4eb9353ff500b1c823165d4d508 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 22 Nov 2021 11:08:27 +0100 Subject: [PATCH 304/358] nvmet: use IOCB_NOWAIT only if the filesystem supports it Submit I/O requests with the IOCB_NOWAIT flag set only if the underlying filesystem supports it. Fixes: 50a909db36f2 ("nvmet: use IOCB_NOWAIT for file-ns buffered I/O") Signed-off-by: Maurizio Lombardi Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/target/io-cmd-file.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 6aa30f30b572ec..6be6e59d273bb7 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "nvmet.h" #define NVMET_MAX_MPOOL_BVEC 16 @@ -266,7 +267,8 @@ static void nvmet_file_execute_rw(struct nvmet_req *req) if (req->ns->buffered_io) { if (likely(!req->f.mpool_alloc) && - nvmet_file_execute_io(req, IOCB_NOWAIT)) + (req->ns->file->f_mode & FMODE_NOWAIT) && + nvmet_file_execute_io(req, IOCB_NOWAIT)) return; nvmet_file_submit_buffered_io(req); } else From b1c45ad53efbad779aa6cdb588de0b8ea1ed54bb Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 25 Nov 2021 10:20:55 +0100 Subject: [PATCH 305/358] xen: make HYPERVISOR_get_debugreg() always_inline HYPERVISOR_get_debugreg() is being called from noinstr code, so it should be attributed "always_inline". Fixes: f4afb713e5c3a4419ba ("x86/xen: Make get_debugreg() noinstr") Reported-by: kernel test robot Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20211125092056.24758-2-jgross@suse.com Signed-off-by: Boris Ostrovsky --- arch/x86/include/asm/xen/hypercall.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 0575f5863b7fef..28ca1119606b38 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -287,7 +287,7 @@ HYPERVISOR_set_debugreg(int reg, unsigned long value) return _hypercall2(int, set_debugreg, reg, value); } -static inline unsigned long +static __always_inline unsigned long HYPERVISOR_get_debugreg(int reg) { return _hypercall1(unsigned long, get_debugreg, reg); From 00db58cf21188f4b99bc5f15fcc2995e30e4a9fe Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 25 Nov 2021 10:20:56 +0100 Subject: [PATCH 306/358] xen: make HYPERVISOR_set_debugreg() always_inline HYPERVISOR_set_debugreg() is being called from noinstr code, so it should be attributed "always_inline". Fixes: 7361fac0465ba96ec8f ("x86/xen: Make set_debugreg() noinstr") Reported-by: kernel test robot Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20211125092056.24758-3-jgross@suse.com Signed-off-by: Boris Ostrovsky --- arch/x86/include/asm/xen/hypercall.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 28ca1119606b38..e5e0fe10c69240 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -281,7 +281,7 @@ HYPERVISOR_callback_op(int cmd, void *arg) return _hypercall2(int, callback_op, cmd, arg); } -static inline int +static __always_inline int HYPERVISOR_set_debugreg(int reg, unsigned long value) { return _hypercall2(int, set_debugreg, reg, value); From eaeace60778e524a2820d0c0ad60bf80289e292c Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Tue, 23 Nov 2021 12:40:00 -0800 Subject: [PATCH 307/358] igb: fix netpoll exit with traffic Oleksandr brought a bug report where netpoll causes trace messages in the log on igb. Danielle brought this back up as still occurring, so we'll try again. [22038.710800] ------------[ cut here ]------------ [22038.710801] igb_poll+0x0/0x1440 [igb] exceeded budget in poll [22038.710802] WARNING: CPU: 12 PID: 40362 at net/core/netpoll.c:155 netpoll_poll_dev+0x18a/0x1a0 As Alex suggested, change the driver to return work_done at the exit of napi_poll, which should be safe to do in this driver because it is not polling multiple queues in this single napi context (multiple queues attached to one MSI-X vector). Several other drivers contain the same simple sequence, so I hope this will not create new problems. Fixes: 16eb8815c235 ("igb: Refactor clean_rx_irq to reduce overhead and improve performance") Reported-by: Oleksandr Natalenko Reported-by: Danielle Ratson Suggested-by: Alexander Duyck Signed-off-by: Jesse Brandeburg Tested-by: Oleksandr Natalenko Tested-by: Danielle Ratson Link: https://lore.kernel.org/r/20211123204000.1597971-1-jesse.brandeburg@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 836be0d3b29105..fd54d3ef890bc1 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8026,7 +8026,7 @@ static int igb_poll(struct napi_struct *napi, int budget) if (likely(napi_complete_done(napi, work_done))) igb_ring_irq_enable(q_vector); - return min(work_done, budget - 1); + return work_done; } /** From 9dbe33cf371bd70330858370bdbc35c7668f00c3 Mon Sep 17 00:00:00 2001 From: Dylan Hung Date: Thu, 25 Nov 2021 10:44:32 +0800 Subject: [PATCH 308/358] mdio: aspeed: Fix "Link is Down" issue The issue happened randomly in runtime. The message "Link is Down" is popped but soon it recovered to "Link is Up". The "Link is Down" results from the incorrect read data for reading the PHY register via MDIO bus. The correct sequence for reading the data shall be: 1. fire the command 2. wait for command done (this step was missing) 3. wait for data idle 4. read data from data register Cc: stable@vger.kernel.org Fixes: f160e99462c6 ("net: phy: Add mdio-aspeed") Reviewed-by: Joel Stanley Signed-off-by: Dylan Hung Reviewed-by: Andrew Lunn Reviewed-by: Russell King (Oracle) Link: https://lore.kernel.org/r/20211125024432.15809-1-dylan_hung@aspeedtech.com Signed-off-by: Jakub Kicinski --- drivers/net/mdio/mdio-aspeed.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/mdio/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c index cad820568f7511..966c3b4ad59d14 100644 --- a/drivers/net/mdio/mdio-aspeed.c +++ b/drivers/net/mdio/mdio-aspeed.c @@ -61,6 +61,13 @@ static int aspeed_mdio_read(struct mii_bus *bus, int addr, int regnum) iowrite32(ctrl, ctx->base + ASPEED_MDIO_CTRL); + rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_CTRL, ctrl, + !(ctrl & ASPEED_MDIO_CTRL_FIRE), + ASPEED_MDIO_INTERVAL_US, + ASPEED_MDIO_TIMEOUT_US); + if (rc < 0) + return rc; + rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_DATA, data, data & ASPEED_MDIO_DATA_IDLE, ASPEED_MDIO_INTERVAL_US, From 1cab5bd69eb1f995ced2d7576cb15f8a8941fd85 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Nov 2021 19:39:32 +0800 Subject: [PATCH 309/358] MIPS: Fix using smp_processor_id() in preemptible in show_cpuinfo() There exists the following issue under DEBUG_PREEMPT: BUG: using smp_processor_id() in preemptible [00000000] code: systemd/1 caller is show_cpuinfo+0x460/0xea0 ... Call Trace: [] show_stack+0x94/0x128 [] dump_stack_lvl+0x94/0xd8 [] check_preemption_disabled+0x104/0x110 [] show_cpuinfo+0x460/0xea0 [] seq_read_iter+0xfc/0x4f8 [] new_sync_read+0x110/0x1b8 [] vfs_read+0x1b4/0x1d0 [] ksys_read+0xd0/0x110 [] syscall_common+0x34/0x58 We can see the following call trace: show_cpuinfo() cpu_has_fpu current_cpu_data smp_processor_id() $ addr2line -f -e vmlinux 0xffffffff802209c8 show_cpuinfo arch/mips/kernel/proc.c:188 $ head -188 arch/mips/kernel/proc.c | tail -1 if (cpu_has_fpu) arch/mips/include/asm/cpu-features.h # define cpu_has_fpu (current_cpu_data.options & MIPS_CPU_FPU) arch/mips/include/asm/cpu-info.h #define current_cpu_data cpu_data[smp_processor_id()] Based on the above analysis, fix the issue by using raw_cpu_has_fpu which calls raw_smp_processor_id() in show_cpuinfo(). Fixes: 626bfa037299 ("MIPS: kernel: proc: add CPU option reporting") Signed-off-by: Tiezhu Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 376a6e2676e9e2..9f47a889b047e9 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -185,7 +185,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_puts(m, " tx39_cache"); if (cpu_has_octeon_cache) seq_puts(m, " octeon_cache"); - if (cpu_has_fpu) + if (raw_cpu_has_fpu) seq_puts(m, " fpu"); if (cpu_has_32fpr) seq_puts(m, " 32fpr"); From 7db5e9e9e5e6c10d7d26f8df7f8fd8841cb15ee7 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Thu, 25 Nov 2021 18:59:49 +0800 Subject: [PATCH 310/358] MIPS: loongson64: fix FTLB configuration It turns out that 'decode_configs' -> 'set_ftlb_enable' is called under c->cputype unset, which leaves FTLB disabled on BOTH 3A2000 and 3A3000 Fix it by calling "decode_configs" after c->cputype is initialized Fixes: da1bd29742b1 ("MIPS: Loongson64: Probe CPU features via CPUCFG") Signed-off-by: Huang Pei Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/cpu-probe.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index ac0e2cfc6d57a3..24a529c6c4be58 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1734,8 +1734,6 @@ static inline void decode_cpucfg(struct cpuinfo_mips *c) static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { - decode_configs(c); - /* All Loongson processors covered here define ExcCode 16 as GSExc. */ c->options |= MIPS_CPU_GSEXCEX; @@ -1796,6 +1794,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) panic("Unknown Loongson Processor ID!"); break; } + + decode_configs(c); } #else static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { } From 41ce097f714401e6ad8f3f5eb30d7f91b0b5e495 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Thu, 25 Nov 2021 18:59:48 +0800 Subject: [PATCH 311/358] MIPS: use 3-level pgtable for 64KB page size on MIPS_VA_BITS_48 It hangup when booting Loongson 3A1000 with BOTH CONFIG_PAGE_SIZE_64KB and CONFIG_MIPS_VA_BITS_48, that it turn out to use 2-level pgtable instead of 3-level. 64KB page size with 2-level pgtable only cover 42 bits VA, use 3-level pgtable to cover all 48 bits VA(55 bits) Fixes: 1e321fa917fb ("MIPS64: Support of at least 48 bits of SEGBITS) Signed-off-by: Huang Pei Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index de60ad19005764..0215dc1529e9ae 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -3097,7 +3097,7 @@ config STACKTRACE_SUPPORT config PGTABLE_LEVELS int default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48 - default 3 if 64BIT && !PAGE_SIZE_64KB + default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48) default 2 config MIPS_AUTO_PFN_OFFSET From e30028ace8459ea096b093fc204f0d5e8fc3b6ae Mon Sep 17 00:00:00 2001 From: Yang Guang Date: Fri, 26 Nov 2021 00:20:55 +0800 Subject: [PATCH 312/358] block: fix parameter not described warning The build warning: block/blk-core.c:968: warning: Function parameter or member 'iob' not described in 'bio_poll'. Fixes: 5a72e899ceb4 ("block: add a struct io_comp_batch argument to fops->iopoll()") Reported-by: Zeal Robot Signed-off-by: Yang Guang Signed-off-by: Jens Axboe --- block/blk-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/blk-core.c b/block/blk-core.c index f0f38ca8e22f27..1378d084c770f6 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1017,6 +1017,7 @@ EXPORT_SYMBOL(submit_bio); /** * bio_poll - poll for BIO completions * @bio: bio to poll for + * @iob: batches of IO * @flags: BLK_POLL_* flags that control the behavior * * Poll for completions on queue associated with the bio. Returns number of From a125f91fe783a79c9d990fe6e28a3da8d9a0857f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:49 -0800 Subject: [PATCH 313/358] selftests: tls: add helper for creating sock pairs We have the same code 3 times, about to add a fourth copy. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 128 +++++++----------------------- 1 file changed, 29 insertions(+), 99 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e61fc4c32ba23a..8fb7cf8c4bfbfc 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -78,26 +78,21 @@ static void memrnd(void *s, size_t n) *byte++ = rand(); } -FIXTURE(tls_basic) -{ - int fd, cfd; - bool notls; -}; - -FIXTURE_SETUP(tls_basic) +static void ulp_sock_pair(struct __test_metadata *_metadata, + int *fd, int *cfd, bool *notls) { struct sockaddr_in addr; socklen_t len; int sfd, ret; - self->notls = false; + *notls = false; len = sizeof(addr); addr.sin_family = AF_INET; addr.sin_addr.s_addr = htonl(INADDR_ANY); addr.sin_port = 0; - self->fd = socket(AF_INET, SOCK_STREAM, 0); + *fd = socket(AF_INET, SOCK_STREAM, 0); sfd = socket(AF_INET, SOCK_STREAM, 0); ret = bind(sfd, &addr, sizeof(addr)); @@ -108,26 +103,37 @@ FIXTURE_SETUP(tls_basic) ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); - ret = connect(self->fd, &addr, sizeof(addr)); + ret = connect(*fd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); + *cfd = accept(sfd, &addr, &len); + ASSERT_GE(*cfd, 0); close(sfd); - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); if (ret != 0) { ASSERT_EQ(errno, ENOENT); - self->notls = true; + *notls = true; printf("Failure setting TCP_ULP, testing without tls\n"); return; } - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); ASSERT_EQ(ret, 0); } +FIXTURE(tls_basic) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_SETUP(tls_basic) +{ + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); +} + FIXTURE_TEARDOWN(tls_basic) { close(self->fd); @@ -199,60 +205,21 @@ FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; - struct sockaddr_in addr; - socklen_t len; - int sfd, ret; - - self->notls = false; - len = sizeof(addr); + int ret; tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12); - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); - self->fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); - - ret = bind(sfd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - ret = listen(sfd, 10); - ASSERT_EQ(ret, 0); + if (self->notls) + return; - ret = getsockname(sfd, &addr, &len); + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - ret = connect(self->fd, &addr, sizeof(addr)); + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - self->notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); - } - - if (!self->notls) { - ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); - - if (!self->notls) { - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - ASSERT_EQ(ret, 0); - - ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - close(sfd); } FIXTURE_TEARDOWN(tls) @@ -1355,62 +1322,25 @@ TEST(non_established) { TEST(keysizes) { struct tls12_crypto_info_aes_gcm_256 tls12; - struct sockaddr_in addr; - int sfd, ret, fd, cfd; - socklen_t len; + int ret, fd, cfd; bool notls; - notls = false; - len = sizeof(addr); - memset(&tls12, 0, sizeof(tls12)); tls12.info.version = TLS_1_2_VERSION; tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; - - fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); - - ret = bind(sfd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - ret = listen(sfd, 10); - ASSERT_EQ(ret, 0); - - ret = getsockname(sfd, &addr, &len); - ASSERT_EQ(ret, 0); - - ret = connect(fd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - - ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); - } + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); if (!notls) { ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, sizeof(tls12)); EXPECT_EQ(ret, 0); - } - - cfd = accept(sfd, &addr, &len); - ASSERT_GE(cfd, 0); - - if (!notls) { - ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - EXPECT_EQ(ret, 0); ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, sizeof(tls12)); EXPECT_EQ(ret, 0); } - close(sfd); close(fd); close(cfd); } From 31180adb0bed7d3e67ae97121dc83f320bbd45be Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:50 -0800 Subject: [PATCH 314/358] selftests: tls: factor out cmsg send/receive Add helpers for sending and receiving special record types. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 111 +++++++++++++++++++----------- 1 file changed, 70 insertions(+), 41 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 8fb7cf8c4bfbfc..642d1d629b2816 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -123,6 +123,65 @@ static void ulp_sock_pair(struct __test_metadata *_metadata, ASSERT_EQ(ret, 0); } +/* Produce a basic cmsg */ +static int tls_send_cmsg(int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + int cmsg_len = sizeof(char); + struct cmsghdr *cmsg; + struct msghdr msg; + struct iovec vec; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_TLS; + /* test sending non-record types. */ + cmsg->cmsg_type = TLS_SET_RECORD_TYPE; + cmsg->cmsg_len = CMSG_LEN(cmsg_len); + *CMSG_DATA(cmsg) = record_type; + msg.msg_controllen = cmsg->cmsg_len; + + return sendmsg(fd, &msg, flags); +} + +static int tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + struct cmsghdr *cmsg; + unsigned char ctype; + struct msghdr msg; + struct iovec vec; + int n; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + + n = recvmsg(fd, &msg, flags); + + cmsg = CMSG_FIRSTHDR(&msg); + EXPECT_NE(cmsg, NULL); + EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); + EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); + ctype = *((unsigned char *)CMSG_DATA(cmsg)); + EXPECT_EQ(ctype, record_type); + + return n; +} + FIXTURE(tls_basic) { int fd, cfd; @@ -1160,60 +1219,30 @@ TEST_F(tls, mutliproc_sendpage_writers) TEST_F(tls, control_msg) { - if (self->notls) - return; - - char cbuf[CMSG_SPACE(sizeof(char))]; - char const *test_str = "test_read"; - int cmsg_len = sizeof(char); + char *test_str = "test_read"; char record_type = 100; - struct cmsghdr *cmsg; - struct msghdr msg; int send_len = 10; - struct iovec vec; char buf[10]; - vec.iov_base = (char *)test_str; - vec.iov_len = 10; - memset(&msg, 0, sizeof(struct msghdr)); - msg.msg_iov = &vec; - msg.msg_iovlen = 1; - msg.msg_control = cbuf; - msg.msg_controllen = sizeof(cbuf); - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_TLS; - /* test sending non-record types. */ - cmsg->cmsg_type = TLS_SET_RECORD_TYPE; - cmsg->cmsg_len = CMSG_LEN(cmsg_len); - *CMSG_DATA(cmsg) = record_type; - msg.msg_controllen = cmsg->cmsg_len; + if (self->notls) + SKIP(return, "no TLS support"); - EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); + EXPECT_EQ(tls_send_cmsg(self->fd, record_type, test_str, send_len, 0), + send_len); /* Should fail because we didn't provide a control message */ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); - vec.iov_base = buf; - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL | MSG_PEEK), send_len); - - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL | MSG_PEEK), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); /* Recv the message again without MSG_PEEK */ - record_type = 0; memset(buf, 0, sizeof(buf)); - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } From ef0fc0b3cc2b8df7f29656a190a13ceb644b0c00 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:51 -0800 Subject: [PATCH 315/358] selftests: tls: add tests for handling of bad records Test broken records. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 154 ++++++++++++++++++++++++++++++ 1 file changed, 154 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 642d1d629b2816..2108b197d3f640 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1297,6 +1297,160 @@ TEST_F(tls, shutdown_reuse) EXPECT_EQ(errno, EISCONN); } +FIXTURE(tls_err) +{ + int fd, cfd; + int fd2, cfd2; + bool notls; +}; + +FIXTURE_VARIANT(tls_err) +{ + uint16_t tls_version; +}; + +FIXTURE_VARIANT_ADD(tls_err, 12_aes_gcm) +{ + .tls_version = TLS_1_2_VERSION, +}; + +FIXTURE_VARIANT_ADD(tls_err, 13_aes_gcm) +{ + .tls_version = TLS_1_3_VERSION, +}; + +FIXTURE_SETUP(tls_err) +{ + struct tls_crypto_info_keys tls12; + int ret; + + tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128, + &tls12); + + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); + ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls); + if (self->notls) + return; + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd2, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(tls_err) +{ + close(self->fd); + close(self->cfd); + close(self->fd2); + close(self->cfd2); +} + +TEST_F(tls_err, bad_rec) +{ + char buf[64]; + + if (self->notls) + SKIP(return, "no TLS support"); + + memset(buf, 0x55, sizeof(buf)); + EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf)); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EMSGSIZE); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), MSG_DONTWAIT), -1); + EXPECT_EQ(errno, EAGAIN); +} + +TEST_F(tls_err, bad_auth) +{ + char buf[128]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + memrnd(buf, sizeof(buf) / 2); + EXPECT_EQ(send(self->fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2); + n = recv(self->cfd, buf, sizeof(buf), 0); + EXPECT_GT(n, sizeof(buf) / 2); + + buf[n - 1]++; + + EXPECT_EQ(send(self->fd2, buf, n, 0), n); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_in_large_read) +{ + char txt[3][64]; + char cip[3][128]; + char buf[3 * 128]; + int i, n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Put 3 records in the sockets */ + for (i = 0; i < 3; i++) { + memrnd(txt[i], sizeof(txt[i])); + EXPECT_EQ(send(self->fd, txt[i], sizeof(txt[i]), 0), + sizeof(txt[i])); + n = recv(self->cfd, cip[i], sizeof(cip[i]), 0); + EXPECT_GT(n, sizeof(txt[i])); + /* Break the third message */ + if (i == 2) + cip[2][n - 1]++; + EXPECT_EQ(send(self->fd2, cip[i], n, 0), n); + } + + /* We should be able to receive the first two messages */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt[0]) * 2); + EXPECT_EQ(memcmp(buf, txt[0], sizeof(txt[0])), 0); + EXPECT_EQ(memcmp(buf + sizeof(txt[0]), txt[1], sizeof(txt[1])), 0); + /* Third mesasge is bad */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_cmsg) +{ + char *test_str = "test_read"; + int send_len = 10; + char cip[128]; + char buf[128]; + char txt[64]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Queue up one data record */ + memrnd(txt, sizeof(txt)); + EXPECT_EQ(send(self->fd, txt, sizeof(txt), 0), sizeof(txt)); + n = recv(self->cfd, cip, sizeof(cip), 0); + EXPECT_GT(n, sizeof(txt)); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + n = recv(self->cfd, cip, sizeof(cip), 0); + cip[n - 1]++; /* Break it */ + EXPECT_GT(n, send_len); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt)); + EXPECT_EQ(memcmp(buf, txt, sizeof(txt)), 0); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; From 520493f66f6822551aef2879cd40207074fe6980 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:52 -0800 Subject: [PATCH 316/358] tls: splice_read: fix record type check We don't support splicing control records. TLS 1.3 changes moved the record type check into the decrypt if(). The skb may already be decrypted and still be an alert. Note that decrypt_skb_update() is idempotent and updates ctx->decrypted so the if() is pointless. Reorder the check for decryption errors with the content type check while touching them. This part is not really a bug, because if decryption failed in TLS 1.3 content type will be DATA, and for TLS 1.2 it will be correct. Nevertheless its strange to touch output before checking if the function has failed. Fixes: fedf201e1296 ("net: tls: Refactor control message handling on recv") Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d81564078557b9..2f11f1db917a46 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2018,21 +2018,18 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (!skb) goto splice_read_end; - if (!ctx->decrypted) { - err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); - - /* splice does not support reading control messages */ - if (ctx->control != TLS_RECORD_TYPE_DATA) { - err = -EINVAL; - goto splice_read_end; - } + err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); + if (err < 0) { + tls_err_abort(sk, -EBADMSG); + goto splice_read_end; + } - if (err < 0) { - tls_err_abort(sk, -EBADMSG); - goto splice_read_end; - } - ctx->decrypted = 1; + /* splice does not support reading control messages */ + if (ctx->control != TLS_RECORD_TYPE_DATA) { + err = -EINVAL; + goto splice_read_end; } + rxm = strp_msg(skb); chunk = min_t(unsigned int, rxm->full_len, len); From d87d67fd61ef4e7619eb24ab20cba3250a6444e8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:53 -0800 Subject: [PATCH 317/358] selftests: tls: test splicing cmsgs Make sure we correctly reject splicing non-data records. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 40 +++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 2108b197d3f640..3dfa9d7dd4cc90 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -639,6 +639,46 @@ TEST_F(tls, splice_to_pipe) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, splice_dec_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + TEST_F(tls, recvmsg_single) { char const *test_str = "test_recvmsg_single"; From e062fe99cccd9ff9f232e593d163ecabd244fae8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:54 -0800 Subject: [PATCH 318/358] tls: splice_read: fix accessing pre-processed records recvmsg() will put peek()ed and partially read records onto the rx_list. splice_read() needs to consult that list otherwise it may miss data. Align with recvmsg() and also put partially-read records onto rx_list. tls_sw_advance_skb() is pretty pointless now and will be removed in net-next. Fixes: 692d7b5d1f91 ("tls: Fix recvmsg() to be able to peek across multiple records") Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 33 +++++++++++++++++++++++++-------- 1 file changed, 25 insertions(+), 8 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2f11f1db917a46..d3e7ff90889e35 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2005,6 +2005,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct sock *sk = sock->sk; struct sk_buff *skb; ssize_t copied = 0; + bool from_queue; int err = 0; long timeo; int chunk; @@ -2014,14 +2015,20 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK); - skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err); - if (!skb) - goto splice_read_end; + from_queue = !skb_queue_empty(&ctx->rx_list); + if (from_queue) { + skb = __skb_dequeue(&ctx->rx_list); + } else { + skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, + &err); + if (!skb) + goto splice_read_end; - err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); - if (err < 0) { - tls_err_abort(sk, -EBADMSG); - goto splice_read_end; + err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); + if (err < 0) { + tls_err_abort(sk, -EBADMSG); + goto splice_read_end; + } } /* splice does not support reading control messages */ @@ -2037,7 +2044,17 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (copied < 0) goto splice_read_end; - tls_sw_advance_skb(sk, skb, copied); + if (!from_queue) { + ctx->recv_pkt = NULL; + __strp_unpause(&ctx->strp); + } + if (chunk < rxm->full_len) { + __skb_queue_head(&ctx->rx_list, skb); + rxm->offset += len; + rxm->full_len -= len; + } else { + consume_skb(skb); + } splice_read_end: release_sock(sk); From 274af0f9e2799da22a866139d9bd203cc0baacff Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:55 -0800 Subject: [PATCH 319/358] selftests: tls: test splicing decrypted records Add tests for half-received and peeked records. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 49 +++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 3dfa9d7dd4cc90..6e78d7207cc141 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -679,6 +679,55 @@ TEST_F(tls, splice_dec_cmsg_to_pipe) EXPECT_EQ(memcmp(test_str, buf, send_len), 0); } +TEST_F(tls, recv_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int half = send_len / 2; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + /* Recv hald of the record, splice the other half */ + EXPECT_EQ(recv(self->cfd, mem_recv, half, MSG_WAITALL), half); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, half, SPLICE_F_NONBLOCK), + half); + EXPECT_EQ(read(p[0], &mem_recv[half], half), half); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, peek_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int chunk = TLS_PAYLOAD_MAX_LEN / 4; + int n, i, p[2]; + + memrnd(mem_send, sizeof(mem_send)); + + ASSERT_GE(pipe(p), 0); + for (i = 0; i < 4; i++) + EXPECT_EQ(send(self->fd, &mem_send[chunk * i], chunk, 0), + chunk); + + EXPECT_EQ(recv(self->cfd, mem_recv, chunk * 5 / 2, + MSG_WAITALL | MSG_PEEK), + chunk * 5 / 2); + EXPECT_EQ(memcmp(mem_send, mem_recv, chunk * 5 / 2), 0); + + n = 0; + while (n < send_len) { + i = splice(self->cfd, NULL, p[1], NULL, send_len - n, 0); + EXPECT_GT(i, 0); + n += i; + } + EXPECT_EQ(n, send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + TEST_F(tls, recvmsg_single) { char const *test_str = "test_recvmsg_single"; From f3911f73f51d1534f4db70b516cc1fcb6be05bae Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:56 -0800 Subject: [PATCH 320/358] tls: fix replacing proto_ops We replace proto_ops whenever TLS is configured for RX. But our replacement also overrides sendpage_locked, which will crash unless TX is also configured. Similarly we plug both of those in for TLS_HW (NIC crypto offload) even tho TLS_HW has a completely different implementation for TX. Last but not least we always plug in something based on inet_stream_ops even though a few of the callbacks differ for IPv6 (getname, release, bind). Use a callback building method similar to what we do for struct proto. Fixes: c46234ebb4d1 ("tls: RX path for ktls") Fixes: d4ffb02dee2f ("net/tls: enable sk_msg redirect to tls socket egress") Signed-off-by: Jakub Kicinski --- net/tls/tls_main.c | 47 +++++++++++++++++++++++++++++++++++++++------- 1 file changed, 40 insertions(+), 7 deletions(-) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index acfba9f1ba72fa..6bc2879ba637bf 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -61,7 +61,7 @@ static DEFINE_MUTEX(tcpv6_prot_mutex); static const struct proto *saved_tcpv4_prot; static DEFINE_MUTEX(tcpv4_prot_mutex); static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; -static struct proto_ops tls_sw_proto_ops; +static struct proto_ops tls_proto_ops[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], const struct proto *base); @@ -71,6 +71,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx) WRITE_ONCE(sk->sk_prot, &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]); + WRITE_ONCE(sk->sk_socket->ops, + &tls_proto_ops[ip_ver][ctx->tx_conf][ctx->rx_conf]); } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -669,8 +671,6 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, if (tx) { ctx->sk_write_space = sk->sk_write_space; sk->sk_write_space = tls_write_space; - } else { - sk->sk_socket->ops = &tls_sw_proto_ops; } goto out; @@ -728,6 +728,39 @@ struct tls_context *tls_ctx_create(struct sock *sk) return ctx; } +static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG], + const struct proto_ops *base) +{ + ops[TLS_BASE][TLS_BASE] = *base; + + ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; + + ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_BASE][TLS_SW ].splice_read = tls_sw_splice_read; + + ops[TLS_SW ][TLS_SW ] = ops[TLS_SW ][TLS_BASE]; + ops[TLS_SW ][TLS_SW ].splice_read = tls_sw_splice_read; + +#ifdef CONFIG_TLS_DEVICE + ops[TLS_HW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_HW ][TLS_BASE].sendpage_locked = NULL; + + ops[TLS_HW ][TLS_SW ] = ops[TLS_BASE][TLS_SW ]; + ops[TLS_HW ][TLS_SW ].sendpage_locked = NULL; + + ops[TLS_BASE][TLS_HW ] = ops[TLS_BASE][TLS_SW ]; + + ops[TLS_SW ][TLS_HW ] = ops[TLS_SW ][TLS_SW ]; + + ops[TLS_HW ][TLS_HW ] = ops[TLS_HW ][TLS_SW ]; + ops[TLS_HW ][TLS_HW ].sendpage_locked = NULL; +#endif +#ifdef CONFIG_TLS_TOE + ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base; +#endif +} + static void tls_build_proto(struct sock *sk) { int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; @@ -739,6 +772,8 @@ static void tls_build_proto(struct sock *sk) mutex_lock(&tcpv6_prot_mutex); if (likely(prot != saved_tcpv6_prot)) { build_protos(tls_prots[TLSV6], prot); + build_proto_ops(tls_proto_ops[TLSV6], + sk->sk_socket->ops); smp_store_release(&saved_tcpv6_prot, prot); } mutex_unlock(&tcpv6_prot_mutex); @@ -749,6 +784,8 @@ static void tls_build_proto(struct sock *sk) mutex_lock(&tcpv4_prot_mutex); if (likely(prot != saved_tcpv4_prot)) { build_protos(tls_prots[TLSV4], prot); + build_proto_ops(tls_proto_ops[TLSV4], + sk->sk_socket->ops); smp_store_release(&saved_tcpv4_prot, prot); } mutex_unlock(&tcpv4_prot_mutex); @@ -959,10 +996,6 @@ static int __init tls_register(void) if (err) return err; - tls_sw_proto_ops = inet_stream_ops; - tls_sw_proto_ops.splice_read = tls_sw_splice_read; - tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked; - tls_device_init(); tcp_register_ulp(&tcp_tls_ulp_ops); From f884a3426291b3f368231c0ac0e50a6a061f6aca Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:57 -0800 Subject: [PATCH 321/358] selftests: tls: test for correct proto_ops Previous patch fixes overriding callbacks incorrectly. Triggering the crash in sendpage_locked would be more spectacular but it's hard to get to, so take the easier path of proving this is broken and call getname. We're currently getting IPv4 socket info on an IPv6 socket. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 55 +++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 6e78d7207cc141..8a22db0cca496a 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1617,4 +1617,59 @@ TEST(keysizes) { close(cfd); } +TEST(tls_v6ops) { + struct tls_crypto_info_keys tls12; + struct sockaddr_in6 addr, addr2; + int sfd, ret, fd; + socklen_t len, len2; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12); + + addr.sin6_family = AF_INET6; + addr.sin6_addr = in6addr_any; + addr.sin6_port = 0; + + fd = socket(AF_INET6, SOCK_STREAM, 0); + sfd = socket(AF_INET6, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + len = sizeof(addr); + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + len = sizeof(addr); + ret = getsockname(fd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret) { + ASSERT_EQ(errno, ENOENT); + SKIP(return, "no TLS support"); + } + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + len2 = sizeof(addr2); + ret = getsockname(fd, &addr2, &len2); + ASSERT_EQ(ret, 0); + + EXPECT_EQ(len2, len); + EXPECT_EQ(memcmp(&addr, &addr2, len), 0); + + close(fd); + close(sfd); +} + TEST_HARNESS_MAIN From daf87e953527b03c0bd4c0f41d704ba71186256d Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Sat, 20 Nov 2021 16:34:11 +0800 Subject: [PATCH 322/358] btrfs: fix the memory leak caused in lzo_compress_pages() [BUG] Fstests generic/027 is pretty easy to trigger a slow but steady memory leak if run with "-o compress=lzo" mount option. Normally one single run of generic/027 is enough to eat up at least 4G ram. [CAUSE] In commit d4088803f511 ("btrfs: subpage: make lzo_compress_pages() compatible") we changed how @page_in is released. But that refactoring makes @page_in only released after all pages being compressed. This leaves error path not releasing @page_in. And by "error path" things like incompressible data will also be treated as an error (-E2BIG). Thus it can cause a memory leak if even nothing wrong happened. [FIX] Add check under @out label to release @page_in when needed, so when we hit any error, the input page is properly released. Reported-by: Josef Bacik Fixes: d4088803f511 ("btrfs: subpage: make lzo_compress_pages() compatible") Reviewed-and-tested-by: Josef Bacik Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/lzo.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index f410ceabcdbd8d..e61f00a192dbe8 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -276,6 +276,8 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, *total_out = cur_out; *total_in = cur_in - start; out: + if (page_in) + put_page(page_in); *out_pages = DIV_ROUND_UP(cur_out, PAGE_SIZE); return ret; } From 617a89484debcd4e7999796d693cf0b77d2519de Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 26 Nov 2021 14:38:14 +0000 Subject: [PATCH 323/358] io_uring: fail cancellation for EXITING tasks WARNING: CPU: 1 PID: 20 at fs/io_uring.c:6269 io_try_cancel_userdata+0x3c5/0x640 fs/io_uring.c:6269 CPU: 1 PID: 20 Comm: kworker/1:0 Not tainted 5.16.0-rc1-syzkaller #0 Workqueue: events io_fallback_req_func RIP: 0010:io_try_cancel_userdata+0x3c5/0x640 fs/io_uring.c:6269 Call Trace: io_req_task_link_timeout+0x6b/0x1e0 fs/io_uring.c:6886 io_fallback_req_func+0xf9/0x1ae fs/io_uring.c:1334 process_one_work+0x9b2/0x1690 kernel/workqueue.c:2298 worker_thread+0x658/0x11f0 kernel/workqueue.c:2445 kthread+0x405/0x4f0 kernel/kthread.c:327 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 We need original task's context to do cancellations, so if it's dying and the callback is executed in a fallback mode, fail the cancellation attempt. Fixes: 89b263f6d56e6 ("io_uring: run linked timeouts from task_work") Cc: stable@kernel.org # 5.15+ Reported-by: syzbot+ab0cfe96c2b3cd1c1153@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/4c41c5f379c6941ad5a07cd48cb66ed62199cf7e.1637937097.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index a4c508a1e0cff7..7dd112d44adf45 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6882,10 +6882,11 @@ static inline struct file *io_file_get(struct io_ring_ctx *ctx, static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) { struct io_kiocb *prev = req->timeout.prev; - int ret; + int ret = -ENOENT; if (prev) { - ret = io_try_cancel_userdata(req, prev->user_data); + if (!(req->task->flags & PF_EXITING)) + ret = io_try_cancel_userdata(req, prev->user_data); io_req_complete_post(req, ret ?: -ETIME, 0); io_put_req(prev); } else { From 6af3f48bf6156a7f02e91aca64e2927c4bebda03 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 26 Nov 2021 14:38:15 +0000 Subject: [PATCH 324/358] io_uring: fix link traversal locking WARNING: inconsistent lock state 5.16.0-rc2-syzkaller #0 Not tainted inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. ffff888078e11418 (&ctx->timeout_lock ){?.+.}-{2:2} , at: io_timeout_fn+0x6f/0x360 fs/io_uring.c:5943 {HARDIRQ-ON-W} state was registered at: [...] spin_unlock_irq include/linux/spinlock.h:399 [inline] __io_poll_remove_one fs/io_uring.c:5669 [inline] __io_poll_remove_one fs/io_uring.c:5654 [inline] io_poll_remove_one+0x236/0x870 fs/io_uring.c:5680 io_poll_remove_all+0x1af/0x235 fs/io_uring.c:5709 io_ring_ctx_wait_and_kill+0x1cc/0x322 fs/io_uring.c:9534 io_uring_release+0x42/0x46 fs/io_uring.c:9554 __fput+0x286/0x9f0 fs/file_table.c:280 task_work_run+0xdd/0x1a0 kernel/task_work.c:164 exit_task_work include/linux/task_work.h:32 [inline] do_exit+0xc14/0x2b40 kernel/exit.c:832 674ee8e1b4a41 ("io_uring: correct link-list traversal locking") fixed a data race but introduced a possible deadlock and inconsistentcy in irq states. E.g. io_poll_remove_all() spin_lock_irq(timeout_lock) io_poll_remove_one() spin_lock/unlock_irq(poll_lock); spin_unlock_irq(timeout_lock) Another type of problem is freeing a request while holding ->timeout_lock, which may leads to a deadlock in io_commit_cqring() -> io_flush_timeouts() and other places. Having 3 nested locks is also too ugly. Add io_match_task_safe(), which would briefly take and release timeout_lock for race prevention inside, so the actuall request cancellation / free / etc. code doesn't have it taken. Reported-by: syzbot+ff49a3059d49b0ca0eec@syzkaller.appspotmail.com Reported-by: syzbot+847f02ec20a6609a328b@syzkaller.appspotmail.com Reported-by: syzbot+3368aadcd30425ceb53b@syzkaller.appspotmail.com Reported-by: syzbot+51ce8887cdef77c9ac83@syzkaller.appspotmail.com Reported-by: syzbot+3cb756a49d2f394a9ee3@syzkaller.appspotmail.com Fixes: 674ee8e1b4a41 ("io_uring: correct link-list traversal locking") Cc: stable@kernel.org # 5.15+ Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/397f7ebf3f4171f1abe41f708ac1ecb5766f0b68.1637937097.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 60 +++++++++++++++++++++++++++++++++++---------------- 1 file changed, 42 insertions(+), 18 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 7dd112d44adf45..75841b919dce55 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1278,6 +1278,7 @@ static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl) static bool io_match_task(struct io_kiocb *head, struct task_struct *task, bool cancel_all) + __must_hold(&req->ctx->timeout_lock) { struct io_kiocb *req; @@ -1293,6 +1294,44 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task, return false; } +static bool io_match_linked(struct io_kiocb *head) +{ + struct io_kiocb *req; + + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; + } + return false; +} + +/* + * As io_match_task() but protected against racing with linked timeouts. + * User must not hold timeout_lock. + */ +static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) +{ + bool matched; + + if (task && head->task != task) + return false; + if (cancel_all) + return true; + + if (head->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = head->ctx; + + /* protect against races with linked timeouts */ + spin_lock_irq(&ctx->timeout_lock); + matched = io_match_linked(head); + spin_unlock_irq(&ctx->timeout_lock); + } else { + matched = io_match_linked(head); + } + return matched; +} + static inline bool req_has_async_data(struct io_kiocb *req) { return req->flags & REQ_F_ASYNC_DATA; @@ -5699,17 +5738,15 @@ static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx, int posted = 0, i; spin_lock(&ctx->completion_lock); - spin_lock_irq(&ctx->timeout_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { struct hlist_head *list; list = &ctx->cancel_hash[i]; hlist_for_each_entry_safe(req, tmp, list, hash_node) { - if (io_match_task(req, tsk, cancel_all)) + if (io_match_task_safe(req, tsk, cancel_all)) posted += io_poll_remove_one(req); } } - spin_unlock_irq(&ctx->timeout_lock); spin_unlock(&ctx->completion_lock); if (posted) @@ -9565,19 +9602,8 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_task_cancel *cancel = data; - bool ret; - if (!cancel->all && (req->flags & REQ_F_LINK_TIMEOUT)) { - struct io_ring_ctx *ctx = req->ctx; - - /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); - ret = io_match_task(req, cancel->task, cancel->all); - spin_unlock_irq(&ctx->timeout_lock); - } else { - ret = io_match_task(req, cancel->task, cancel->all); - } - return ret; + return io_match_task_safe(req, cancel->task, cancel->all); } static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, @@ -9588,14 +9614,12 @@ static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, LIST_HEAD(list); spin_lock(&ctx->completion_lock); - spin_lock_irq(&ctx->timeout_lock); list_for_each_entry_reverse(de, &ctx->defer_list, list) { - if (io_match_task(de->req, task, cancel_all)) { + if (io_match_task_safe(de->req, task, cancel_all)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } } - spin_unlock_irq(&ctx->timeout_lock); spin_unlock(&ctx->completion_lock); if (list_empty(&list)) return false; From 98b26a0e766724957b48301e3a6f7093a142d54b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Nov 2021 09:53:23 -0700 Subject: [PATCH 325/358] block: call rq_qos_done() before ref check in batch completions We need to call rq_qos_done() regardless of whether or not we're freeing the request or not, as the reference count doesn't cover the IO completion tracking. Fixes: f794f3351f26 ("block: add support for blk_mq_end_request_batch()") Reported-by: Shinichiro Kawasaki Reported-by: Kenneth R. Crudup Signed-off-by: Jens Axboe --- block/blk-mq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 8799fa73ef348d..8874a63ae952b2 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -860,13 +860,14 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob) if (iob->need_ts) __blk_mq_end_request_acct(rq, now); + rq_qos_done(rq->q, rq); + WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (!refcount_dec_and_test(&rq->ref)) continue; blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); - rq_qos_done(rq->q, rq); if (nr_tags == TAG_COMP_BATCH || cur_hctx != rq->mq_hctx) { if (cur_hctx) From d422f40163087408b56290156ba233fc5ada53e4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Nov 2021 09:57:32 -0700 Subject: [PATCH 326/358] zram: only make zram_wb_devops for CONFIG_ZRAM_WRITEBACK If writeback isn't configured, then we get the following warning when compiling zram: drivers/block/zram/zram_drv.c:1824:45: warning: unused variable 'zram_wb_devops' [-Wunused-const-variable] Make sure we only define the block_device_operations if that option is enabled. Link: https://lore.kernel.org/lkml/202111261614.gCJMqcyh-lkp@intel.com/ Reported-by: kernel test robot Signed-off-by: Jens Axboe --- drivers/block/zram/zram_drv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 08d7953ec5f107..25071126995bef 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1853,12 +1853,14 @@ static const struct block_device_operations zram_devops = { .owner = THIS_MODULE }; +#ifdef CONFIG_ZRAM_WRITEBACK static const struct block_device_operations zram_wb_devops = { .open = zram_open, .submit_bio = zram_submit_bio, .swap_slot_free_notify = zram_slot_free_notify, .owner = THIS_MODULE }; +#endif static DEVICE_ATTR_WO(compact); static DEVICE_ATTR_RW(disksize); From b270bfe697367776eca2e6759a71d700fb8d82a2 Mon Sep 17 00:00:00 2001 From: Yannick Vignon Date: Wed, 24 Nov 2021 16:47:31 +0100 Subject: [PATCH 327/358] net: stmmac: Disable Tx queues when reconfiguring the interface The Tx queues were not disabled in situations where the driver needed to stop the interface to apply a new configuration. This could result in a kernel panic when doing any of the 3 following actions: * reconfiguring the number of queues (ethtool -L) * reconfiguring the size of the ring buffers (ethtool -G) * installing/removing an XDP program (ip l set dev ethX xdp) Prevent the panic by making sure netif_tx_disable is called when stopping an interface. Without this patch, the following kernel panic can be observed when doing any of the actions above: Unable to handle kernel paging request at virtual address ffff80001238d040 [....] Call trace: dwmac4_set_addr+0x8/0x10 dev_hard_start_xmit+0xe4/0x1ac sch_direct_xmit+0xe8/0x39c __dev_queue_xmit+0x3ec/0xaf0 dev_queue_xmit+0x14/0x20 [...] [ end trace 0000000000000002 ]--- Fixes: 5fabb01207a2d ("net: stmmac: Add initial XDP support") Fixes: aa042f60e4961 ("net: stmmac: Add support to Ethtool get/set ring parameters") Fixes: 0366f7e06a6be ("net: stmmac: add ethtool support for get/set channels") Signed-off-by: Yannick Vignon Link: https://lore.kernel.org/r/20211124154731.1676949-1-yannick.vignon@oss.nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f12097c8a48506..748195697e5a09 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3802,6 +3802,8 @@ int stmmac_release(struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); u32 chan; + netif_tx_disable(dev); + if (device_may_wakeup(priv->device)) phylink_speed_down(priv->phylink, false); /* Stop and disconnect the PHY */ From de6d25924c2a8c2988c6a385990cafbe742061bf Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 24 Nov 2021 17:14:40 +0100 Subject: [PATCH 328/358] net/sched: sch_ets: don't peek at classes beyond 'nbands' when the number of DRR classes decreases, the round-robin active list can contain elements that have already been freed in ets_qdisc_change(). As a consequence, it's possible to see a NULL dereference crash, caused by the attempt to call cl->qdisc->ops->peek(cl->qdisc) when cl->qdisc is NULL: BUG: kernel NULL pointer dereference, address: 0000000000000018 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 1 PID: 910 Comm: mausezahn Not tainted 5.16.0-rc1+ #475 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:ets_qdisc_dequeue+0x129/0x2c0 [sch_ets] Code: c5 01 41 39 ad e4 02 00 00 0f 87 18 ff ff ff 49 8b 85 c0 02 00 00 49 39 c4 0f 84 ba 00 00 00 49 8b ad c0 02 00 00 48 8b 7d 10 <48> 8b 47 18 48 8b 40 38 0f ae e8 ff d0 48 89 c3 48 85 c0 0f 84 9d RSP: 0000:ffffbb36c0b5fdd8 EFLAGS: 00010287 RAX: ffff956678efed30 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000002 RSI: ffffffff9b938dc9 RDI: 0000000000000000 RBP: ffff956678efed30 R08: e2f3207fe360129c R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff956678efeac0 R13: ffff956678efe800 R14: ffff956611545000 R15: ffff95667ac8f100 FS: 00007f2aa9120740(0000) GS:ffff95667b800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000018 CR3: 000000011070c000 CR4: 0000000000350ee0 Call Trace: qdisc_peek_dequeued+0x29/0x70 [sch_ets] tbf_dequeue+0x22/0x260 [sch_tbf] __qdisc_run+0x7f/0x630 net_tx_action+0x290/0x4c0 __do_softirq+0xee/0x4f8 irq_exit_rcu+0xf4/0x130 sysvec_apic_timer_interrupt+0x52/0xc0 asm_sysvec_apic_timer_interrupt+0x12/0x20 RIP: 0033:0x7f2aa7fc9ad4 Code: b9 ff ff 48 8b 54 24 18 48 83 c4 08 48 89 ee 48 89 df 5b 5d e9 ed fc ff ff 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa <53> 48 83 ec 10 48 8b 05 10 64 33 00 48 8b 00 48 85 c0 0f 85 84 00 RSP: 002b:00007ffe5d33fab8 EFLAGS: 00000202 RAX: 0000000000000002 RBX: 0000561f72c31460 RCX: 0000561f72c31720 RDX: 0000000000000002 RSI: 0000561f72c31722 RDI: 0000561f72c31720 RBP: 000000000000002a R08: 00007ffe5d33fa40 R09: 0000000000000014 R10: 0000000000000000 R11: 0000000000000246 R12: 0000561f7187e380 R13: 0000000000000000 R14: 0000000000000000 R15: 0000561f72c31460 Modules linked in: sch_ets sch_tbf dummy rfkill iTCO_wdt intel_rapl_msr iTCO_vendor_support intel_rapl_common joydev virtio_balloon lpc_ich i2c_i801 i2c_smbus pcspkr ip_tables xfs libcrc32c crct10dif_pclmul crc32_pclmul crc32c_intel ahci libahci ghash_clmulni_intel serio_raw libata virtio_blk virtio_console virtio_net net_failover failover sunrpc dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000018 Ensuring that 'alist' was never zeroed [1] was not sufficient, we need to remove from the active list those elements that are no more SP nor DRR. [1] https://lore.kernel.org/netdev/60d274838bf09777f0371253416e8af71360bc08.1633609148.git.dcaratti@redhat.com/ v3: fix race between ets_qdisc_change() and ets_qdisc_dequeue() delisting DRR classes beyond 'nbands' in ets_qdisc_change() with the qdisc lock acquired, thanks to Cong Wang. v2: when a NULL qdisc is found in the DRR active list, try to dequeue skb from the next list item. Reported-by: Hangbin Liu Fixes: dcc68b4d8084 ("net: sch_ets: Add a new Qdisc") Signed-off-by: Davide Caratti Link: https://lore.kernel.org/r/7a5c496eed2d62241620bdbb83eb03fb9d571c99.1637762721.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski --- net/sched/sch_ets.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 0eae9ff5edf6ff..e007fc75ef2fef 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -665,12 +665,14 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } + for (i = q->nbands; i < oldbands; i++) { + qdisc_tree_flush_backlog(q->classes[i].qdisc); + if (i >= q->nstrict) + list_del(&q->classes[i].alist); + } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); - for (i = q->nbands; i < oldbands; i++) - qdisc_tree_flush_backlog(q->classes[i].qdisc); - for (i = 0; i < q->nbands; i++) q->classes[i].quantum = quanta[i]; From c26381f97e2a7df43826150dc7d4c207bd6794a5 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Thu, 25 Nov 2021 11:14:57 -0300 Subject: [PATCH 329/358] nfc: virtual_ncidev: change default device permissions Device permissions is S_IALLUGO, with many unnecessary bits. Remove them and also remove read and write permissions from group and others. Before the change: crwsrwsrwt 1 0 0 10, 125 Nov 25 13:59 /dev/virtual_nci After the change: crw------- 1 0 0 10, 125 Nov 25 14:05 /dev/virtual_nci Signed-off-by: Thadeu Lima de Souza Cascardo Reviewed-by: Krzysztof Kozlowski Reviewed-by: Bongsu Jeon Link: https://lore.kernel.org/r/20211125141457.716921-1-cascardo@canonical.com Signed-off-by: Jakub Kicinski --- drivers/nfc/virtual_ncidev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index 221fa3bb8705e2..f577449e493508 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -202,7 +202,7 @@ static int __init virtual_ncidev_init(void) miscdev.minor = MISC_DYNAMIC_MINOR; miscdev.name = "virtual_nci"; miscdev.fops = &virtual_ncidev_fops; - miscdev.mode = S_IALLUGO; + miscdev.mode = 0600; return misc_register(&miscdev); } From 0276af2176c78771da7f311621a25d7608045827 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 26 Nov 2021 18:55:43 +0100 Subject: [PATCH 330/358] ethtool: ioctl: fix potential NULL deref in ethtool_set_coalesce() ethtool_set_coalesce() now uses both the .get_coalesce() and .set_coalesce() callbacks. But the check for their availability is buggy, so changing the coalesce settings on a device where the driver provides only _one_ of the callbacks results in a NULL pointer dereference instead of an -EOPNOTSUPP. Fix the condition so that the availability of both callbacks is ensured. This also matches the netlink code. Note that reproducing this requires some effort - it only affects the legacy ioctl path, and needs a specific combination of driver options: - have .get_coalesce() and .coalesce_supported but no .set_coalesce(), or - have .set_coalesce() but no .get_coalesce(). Here eg. ethtool doesn't cause the crash as it first attempts to call ethtool_get_coalesce() and bails out on error. Fixes: f3ccfda19319 ("ethtool: extend coalesce setting uAPI with CQE mode") Cc: Yufeng Mo Cc: Huazhong Tan Cc: Andrew Lunn Cc: Heiner Kallweit Signed-off-by: Julian Wiedmann Link: https://lore.kernel.org/r/20211126175543.28000-1-jwi@linux.ibm.com Signed-off-by: Jakub Kicinski --- net/ethtool/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 65e9bc1058b57c..20bcf86970ffd3 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1719,7 +1719,7 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, struct ethtool_coalesce coalesce; int ret; - if (!dev->ethtool_ops->set_coalesce && !dev->ethtool_ops->get_coalesce) + if (!dev->ethtool_ops->set_coalesce || !dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce, From cbb91dcbfb751f887bfcba790a94c153c5005c19 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 25 Nov 2021 19:19:21 -0800 Subject: [PATCH 331/358] ptp: fix filter names in the documentation All the filter names are missing _PTP in them. Signed-off-by: Jakub Kicinski Acked-by: Richard Cochran Link: https://lore.kernel.org/r/20211126031921.2466944-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/networking/timestamping.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index a722eb30e0140d..80b13353254a09 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -486,8 +486,8 @@ of packets. Drivers are free to use a more permissive configuration than the requested configuration. It is expected that drivers should only implement directly the most generic mode that can be supported. For example if the hardware can -support HWTSTAMP_FILTER_V2_EVENT, then it should generally always upscale -HWTSTAMP_FILTER_V2_L2_SYNC_MESSAGE, and so forth, as HWTSTAMP_FILTER_V2_EVENT +support HWTSTAMP_FILTER_PTP_V2_EVENT, then it should generally always upscale +HWTSTAMP_FILTER_PTP_V2_L2_SYNC, and so forth, as HWTSTAMP_FILTER_PTP_V2_EVENT is more generic (and more useful to applications). A driver which supports hardware time stamping shall update the struct From 01d9cc2dea3fde3bad6d27f464eff463496e2b00 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Fri, 26 Nov 2021 09:59:42 +0800 Subject: [PATCH 332/358] net: vlan: fix underflow for the real_dev refcnt Inject error before dev_hold(real_dev) in register_vlan_dev(), and execute the following testcase: ip link add dev dummy1 type dummy ip link add name dummy1.100 link dummy1 type vlan id 100 ip link del dev dummy1 When the dummy netdevice is removed, we will get a WARNING as following: ======================================================================= refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 2 PID: 0 at lib/refcount.c:31 refcount_warn_saturate+0xbf/0x1e0 and an endless loop of: ======================================================================= unregister_netdevice: waiting for dummy1 to become free. Usage count = -1073741824 That is because dev_put(real_dev) in vlan_dev_free() be called without dev_hold(real_dev) in register_vlan_dev(). It makes the refcnt of real_dev underflow. Move the dev_hold(real_dev) to vlan_dev_init() which is the call-back of ndo_init(). That makes dev_hold() and dev_put() for vlan's real_dev symmetrical. Fixes: 563bcbae3ba2 ("net: vlan: fix a UAF in vlan_dev_real_dev()") Reported-by: Petr Machata Suggested-by: Jakub Kicinski Signed-off-by: Ziyang Xuan Link: https://lore.kernel.org/r/20211126015942.2918542-1-william.xuanziyang@huawei.com Signed-off-by: Jakub Kicinski --- net/8021q/vlan.c | 3 --- net/8021q/vlan_dev.c | 3 +++ 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a3a0a5e994f5ae..abaa5d96ded245 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -184,9 +184,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) if (err) goto out_unregister_netdev; - /* Account for reference in struct vlan_dev_priv */ - dev_hold(real_dev); - vlan_stacked_transfer_operstate(real_dev, dev, vlan); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index ab6dee28536daa..a54535cbcf4cf5 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -615,6 +615,9 @@ static int vlan_dev_init(struct net_device *dev) if (!vlan->vlan_pcpu_stats) return -ENOMEM; + /* Get vlan's reference to real_dev */ + dev_hold(real_dev); + return 0; } From bacb6c1e47691cda4a95056c21b5487fb7199fcc Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Fri, 26 Nov 2021 10:41:35 +0800 Subject: [PATCH 333/358] net/smc: Don't call clcsock shutdown twice when smc shutdown When applications call shutdown() with SHUT_RDWR in userspace, smc_close_active() calls kernel_sock_shutdown(), and it is called twice in smc_shutdown(). This fixes this by checking sk_state before do clcsock shutdown, and avoids missing the application's call of smc_shutdown(). Link: https://lore.kernel.org/linux-s390/1f67548e-cbf6-0dce-82b5-10288a4583bd@linux.ibm.com/ Fixes: 606a63c9783a ("net/smc: Ensure the active closing peer first closes clcsock") Signed-off-by: Tony Lu Reviewed-by: Wen Gu Acked-by: Karsten Graul Link: https://lore.kernel.org/r/20211126024134.45693-1-tonylu@linux.alibaba.com Signed-off-by: Jakub Kicinski --- net/smc/af_smc.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 4b62c925a13e88..230072f9ec48e3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2370,8 +2370,10 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, static int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; + bool do_shutdown = true; struct smc_sock *smc; int rc = -EINVAL; + int old_state; int rc1 = 0; smc = smc_sk(sk); @@ -2398,7 +2400,11 @@ static int smc_shutdown(struct socket *sock, int how) } switch (how) { case SHUT_RDWR: /* shutdown in both directions */ + old_state = sk->sk_state; rc = smc_close_active(smc); + if (old_state == SMC_ACTIVE && + sk->sk_state == SMC_PEERCLOSEWAIT1) + do_shutdown = false; break; case SHUT_WR: rc = smc_close_shutdown_write(smc); @@ -2408,7 +2414,7 @@ static int smc_shutdown(struct socket *sock, int how) /* nothing more to do because peer is not involved */ break; } - if (smc->clcsock) + if (do_shutdown && smc->clcsock) rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; From 0435a4d08032c8fba2966cebdac870e22238cacc Mon Sep 17 00:00:00 2001 From: zhangyue Date: Thu, 25 Nov 2021 19:36:10 +0800 Subject: [PATCH 334/358] net: qed: fix the array may be out of bound If the variable 'p_bit->flags' is always 0, the loop condition is always 0. The variable 'j' may be greater than or equal to 32. At this time, the array 'p_aeu->bits[32]' may be out of bound. Signed-off-by: zhangyue Link: https://lore.kernel.org/r/20211125113610.273841-1-zhangyue1@kylinos.cn Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/qlogic/qed/qed_int.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index a97f691839e04f..6958adeca86d0e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -1045,7 +1045,7 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, if (!parities) continue; - for (j = 0, bit_idx = 0; bit_idx < 32; j++) { + for (j = 0, bit_idx = 0; bit_idx < 32 && j < 32; j++) { struct aeu_invert_reg_bit *p_bit = &p_aeu->bits[j]; if (qed_int_is_parity_flag(p_hwfn, p_bit) && @@ -1083,7 +1083,7 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, * to current group, making them responsible for the * previous assertion. */ - for (j = 0, bit_idx = 0; bit_idx < 32; j++) { + for (j = 0, bit_idx = 0; bit_idx < 32 && j < 32; j++) { long unsigned int bitmask; u8 bit, bit_len; @@ -1382,7 +1382,7 @@ static void qed_int_sb_attn_init(struct qed_hwfn *p_hwfn, memset(sb_info->parity_mask, 0, sizeof(u32) * NUM_ATTN_REGS); for (i = 0; i < NUM_ATTN_REGS; i++) { /* j is array index, k is bit index */ - for (j = 0, k = 0; k < 32; j++) { + for (j = 0, k = 0; k < 32 && j < 32; j++) { struct aeu_invert_reg_bit *p_aeu; p_aeu = &aeu_descs[i].bits[j]; From 6cb206508b621a9a0a2c35b60540e399225c8243 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 26 Nov 2021 13:35:26 -0500 Subject: [PATCH 335/358] tracing: Check pid filtering when creating events When pid filtering is activated in an instance, all of the events trace files for that instance has the PID_FILTER flag set. This determines whether or not pid filtering needs to be done on the event, otherwise the event is executed as normal. If pid filtering is enabled when an event is created (via a dynamic event or modules), its flag is not updated to reflect the current state, and the events are not filtered properly. Cc: stable@vger.kernel.org Fixes: 3fdaf80f4a836 ("tracing: Implement event pid filtering") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 4021b9a79f93fe..f8965fd50d3be4 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2678,12 +2678,24 @@ static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) { + struct trace_pid_list *no_pid_list; + struct trace_pid_list *pid_list; struct trace_event_file *file; + unsigned int first; file = kmem_cache_alloc(file_cachep, GFP_TRACE); if (!file) return NULL; + pid_list = rcu_dereference_protected(tr->filtered_pids, + lockdep_is_held(&event_mutex)); + no_pid_list = rcu_dereference_protected(tr->filtered_no_pids, + lockdep_is_held(&event_mutex)); + + if (!trace_pid_list_first(pid_list, &first) || + !trace_pid_list_first(pid_list, &first)) + file->flags |= EVENT_FILE_FL_PID_FILTER; + file->event_call = call; file->tr = tr; atomic_set(&file->sm_ref, 0); From 8d2ad993aa05c0768f00c886c9d369cd97a337ac Mon Sep 17 00:00:00 2001 From: Guangbin Huang Date: Fri, 26 Nov 2021 20:03:15 +0800 Subject: [PATCH 336/358] net: hns3: fix VF RSS failed problem after PF enable multi-TCs When PF is set to multi-TCs and configured mapping relationship between priorities and TCs, the hardware will active these settings for this PF and its VFs. In this case when VF just uses one TC and its rx packets contain priority, and if the priority is not mapped to TC0, as other TCs of VF is not valid, hardware always put this kind of packets to the queue 0. It cause this kind of packets of VF can not be used RSS function. To fix this problem, set tc mode of all unused TCs of VF to the setting of TC0, then rx packet with priority which map to unused TC will be direct to TC0. Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support") Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 25c419d40066dc..41afaeea881bc0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -703,9 +703,9 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev, u16 rss_size) roundup_size = ilog2(roundup_size); for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) { - tc_valid[i] = !!(hdev->hw_tc_map & BIT(i)); + tc_valid[i] = 1; tc_size[i] = roundup_size; - tc_offset[i] = rss_size * i; + tc_offset[i] = (hdev->hw_tc_map & BIT(i)) ? rss_size * i : 0; } hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false); From b8af344cfea189cdc0fef41345e55aed76723615 Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Fri, 26 Nov 2021 20:03:16 +0800 Subject: [PATCH 337/358] net: hns3: add check NULL address for page pool When page pool is not enabled, its address value is still NULL and page pool should not be accessed, so add a check for it. Fixes: 850bfb912a6d ("net: hns3: debugfs add support dumping page pool info") Signed-off-by: Hao Chen Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 67364ab63a1ff9..fbb8a5f0822266 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1106,6 +1106,11 @@ hns3_dbg_page_pool_info(struct hnae3_handle *h, char *buf, int len) return -EFAULT; } + if (!priv->ring[h->kinfo.num_tqps].page_pool) { + dev_err(&h->pdev->dev, "page pool is not initialized\n"); + return -EFAULT; + } + for (i = 0; i < ARRAY_SIZE(page_pool_info_items); i++) result[i] = &data_str[i][0]; From 9c14791748708d87c4d02ba74eb7e281e141d6e4 Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Fri, 26 Nov 2021 20:03:17 +0800 Subject: [PATCH 338/358] net: hns3: fix one incorrect value of page pool info when queried by debugfs Currently, when user queries page pool info by debugfs command "cat page_pool_info", the cnt of allocated page for page pool may be incorrect because of memory inconsistency problem caused by compiler optimization. So this patch uses READ_ONCE() to read value of pages_state_hold_cnt to fix this problem. Fixes: 850bfb912a6d ("net: hns3: debugfs add support dumping page pool info") Signed-off-by: Hao Chen Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index fbb8a5f0822266..081295bff76549 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1081,7 +1081,8 @@ static void hns3_dump_page_pool_info(struct hns3_enet_ring *ring, u32 j = 0; sprintf(result[j++], "%u", index); - sprintf(result[j++], "%u", ring->page_pool->pages_state_hold_cnt); + sprintf(result[j++], "%u", + READ_ONCE(ring->page_pool->pages_state_hold_cnt)); sprintf(result[j++], "%u", atomic_read(&ring->page_pool->pages_state_release_cnt)); sprintf(result[j++], "%u", ring->page_pool->p.pool_size); From 82229c4dbb8a2780f05fa1bab29c97ef7bcd21bb Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Fri, 26 Nov 2021 20:03:18 +0800 Subject: [PATCH 339/358] net: hns3: fix incorrect components info of ethtool --reset command Currently, HNS3 driver doesn't clear the reset flags of components after successfully executing reset, it causes userspace info of "Components reset" and "Components not reset" is incorrect. So fix this problem by clear corresponding reset flag after reset process. Fixes: ddccc5e368a3 ("net: hns3: add support for triggering reset by ethtool") Signed-off-by: Jie Wang Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index c8442b86df9417..c9b4568d7a8d77 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -987,6 +987,7 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags) struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); const struct hnae3_ae_ops *ops = h->ae_algo->ops; const struct hns3_reset_type_map *rst_type_map; + enum ethtool_reset_flags rst_flags; u32 i, size; if (ops->ae_dev_resetting && ops->ae_dev_resetting(h)) @@ -1006,6 +1007,7 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags) for (i = 0; i < size; i++) { if (rst_type_map[i].rst_flags == *flags) { rst_type = rst_type_map[i].rst_type; + rst_flags = rst_type_map[i].rst_flags; break; } } @@ -1021,6 +1023,8 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags) ops->reset_event(h->pdev, h); + *flags &= ~rst_flags; + return 0; } From 8a075464d1e9317ffae0973dfe538a7511291a06 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:41 +0200 Subject: [PATCH 340/358] net: mscc: ocelot: don't downgrade timestamping RX filters in SIOCSHWTSTAMP The ocelot driver, when asked to timestamp all receiving packets, 1588 v1 or NTP, says "nah, here's 1588 v2 for you". According to this discussion: https://patchwork.kernel.org/project/netdevbpf/patch/20211104133204.19757-8-martin.kaistra@linutronix.de/#24577647 drivers that downgrade from a wider request to a narrower response (or even a response where the intersection with the request is empty) are buggy, and should return -ERANGE instead. This patch fixes that. Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") Suggested-by: Richard Cochran Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index e6c18b598d5c5e..bcc4f2f74ccc70 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1320,12 +1320,6 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) switch (cfg.rx_filter) { case HWTSTAMP_FILTER_NONE: break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_NTP_ALL: case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: From 95706be13b9f755d93b5b82bdc782af439f1ec22 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:42 +0200 Subject: [PATCH 341/358] net: mscc: ocelot: create a function that replaces an existing VCAP filter VCAP (Versatile Content Aware Processor) is the TCAM-based engine behind tc flower offload on ocelot, among other things. The ingress port mask on which VCAP rules match is present as a bit field in the actual key of the rule. This means that it is possible for a rule to be shared among multiple source ports. When the rule is added one by one on each desired port, that the ingress port mask of the key must be edited and rewritten to hardware. But the API in ocelot_vcap.c does not allow for this. For one thing, ocelot_vcap_filter_add() and ocelot_vcap_filter_del() are not symmetric, because ocelot_vcap_filter_add() works with a preallocated and prepopulated filter and programs it to hardware, and ocelot_vcap_filter_del() does both the job of removing the specified filter from hardware, as well as kfreeing it. That is to say, the only option of editing a filter in place, which is to delete it, modify the structure and add it back, does not work because it results in use-after-free. This patch introduces ocelot_vcap_filter_replace, which trivially reprograms a VCAP entry to hardware, at the exact same index at which it existed before, without modifying any list or allocating any memory. Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot_vcap.c | 16 ++++++++++++++++ include/soc/mscc/ocelot_vcap.h | 2 ++ 2 files changed, 18 insertions(+) diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index 99d7376a70a748..337cd08b1a5438 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -1217,6 +1217,22 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot, } EXPORT_SYMBOL(ocelot_vcap_filter_del); +int ocelot_vcap_filter_replace(struct ocelot *ocelot, + struct ocelot_vcap_filter *filter) +{ + struct ocelot_vcap_block *block = &ocelot->block[filter->block_id]; + int index; + + index = ocelot_vcap_block_get_filter_index(block, filter); + if (index < 0) + return index; + + vcap_entry_set(ocelot, index, filter); + + return 0; +} +EXPORT_SYMBOL(ocelot_vcap_filter_replace); + int ocelot_vcap_filter_stats_update(struct ocelot *ocelot, struct ocelot_vcap_filter *filter) { diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index eeb1142aa1b1d5..4d1dfa1136b2b5 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -703,6 +703,8 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, struct netlink_ext_ack *extack); int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter *rule); +int ocelot_vcap_filter_replace(struct ocelot *ocelot, + struct ocelot_vcap_filter *filter); struct ocelot_vcap_filter * ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, unsigned long cookie, bool tc_offload); From ec15baec3272bbec576f2ce7ce47765a8e9b7b1c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:43 +0200 Subject: [PATCH 342/358] net: ptp: add a definition for the UDP port for IEEE 1588 general messages As opposed to event messages (Sync, PdelayReq etc) which require timestamping, general messages (Announce, FollowUp etc) do not. In PTP they are part of different streams of data. IEEE 1588-2008 Annex D.2 "UDP port numbers" states that the UDP destination port assigned by IANA is 319 for event messages, and 320 for general messages. Yet the kernel seems to be missing the definition for general messages. This patch adds it. Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- include/linux/ptp_classify.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index ae04968a3a4720..9afd34a2d36c5c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -37,6 +37,7 @@ #define PTP_MSGTYPE_PDELAY_RESP 0x3 #define PTP_EV_PORT 319 +#define PTP_GEN_PORT 320 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ From 96ca08c05838d1f5501003f0a6201824e4eede70 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:44 +0200 Subject: [PATCH 343/358] net: mscc: ocelot: set up traps for PTP packets IEEE 1588 support was declared too soon for the Ocelot switch. Out of reset, this switch does not apply any special treatment for PTP packets, i.e. when an event message is received, the natural tendency is to forward it by MAC DA/VLAN ID. This poses a problem when the ingress port is under a bridge, since user space application stacks (written primarily for endpoint ports, not switches) like ptp4l expect that PTP messages are always received on AF_PACKET / AF_INET sockets (depending on the PTP transport being used), and never being autonomously forwarded. Any forwarding, if necessary (for example in Transparent Clock mode) is handled in software by ptp4l. Having the hardware forward these packets too will cause duplicates which will confuse endpoints connected to these switches. So PTP over L2 barely works, in the sense that PTP packets reach the CPU port, but they reach it via flooding, and therefore reach lots of other unwanted destinations too. But PTP over IPv4/IPv6 does not work at all. This is because the Ocelot switch have a separate destination port mask for unknown IP multicast (which PTP over IP is) flooding compared to unknown non-IP multicast (which PTP over L2 is) flooding. Specifically, the driver allows the CPU port to be in the PGID_MC port group, but not in PGID_MCIPV4 and PGID_MCIPV6. There are several presentations from Allan Nielsen which explain that the embedded MIPS CPU on Ocelot switches is not very powerful at all, so every penny they could save by not allowing flooding to the CPU port module matters. Unknown IP multicast did not make it. The de facto consensus is that when a switch is PTP-aware and an application stack for PTP is running, switches should have some sort of trapping mechanism for PTP packets, to extract them from the hardware data path. This avoids both problems: (a) PTP packets are no longer flooded to unwanted destinations (b) PTP over IP packets are no longer denied from reaching the CPU since they arrive there via a trap and not via flooding It is not the first time when this change is attempted. Last time, the feedback from Allan Nielsen and Andrew Lunn was that the traps should not be installed by default, and that PTP-unaware switching may be desired for some use cases: https://patchwork.ozlabs.org/project/netdev/patch/20190813025214.18601-5-yangbo.lu@nxp.com/ To address that feedback, the present patch adds the necessary packet traps according to the RX filter configuration transmitted by user space through the SIOCSHWTSTAMP ioctl. Trapping is done via VCAP IS2, where we keep 5 filters, which are amended each time RX timestamping is enabled or disabled on a port: - 1 for PTP over L2 - 2 for PTP over IPv4 (UDP ports 319 and 320) - 2 for PTP over IPv6 (UDP ports 319 and 320) The cookie by which these filters (invisible to tc) are identified is strategically chosen such that it does not collide with the filters used for the ocelot-8021q tagging protocol by the Felix driver, or with the MRP traps set up by the Ocelot library. Other alternatives were considered, like patching user space to do something, but there are so many ways in which PTP packets could be made to reach the CPU, generically speaking, that "do what?" is a very valid question. The ptp4l program from the linuxptp stack already attempts to do something: it calls setsockopt(IP_ADD_MEMBERSHIP) (and PACKET_ADD_MEMBERSHIP, respectively) which translates in both cases into a dev_mc_add() on the interface, in the kernel: https://github.com/richardcochran/linuxptp/blob/v3.1.1/udp.c#L73 https://github.com/richardcochran/linuxptp/blob/v3.1.1/raw.c Reality shows that this is not sufficient in case the interface belongs to a switchdev driver, as dev_mc_add() does not show the intention to trap a packet to the CPU, but rather the intention to not drop it (it is strictly for RX filtering, same as promiscuous does not mean to send all traffic to the CPU, but to not drop traffic with unknown MAC DA). This topic is a can of worms in itself, and it would be great if user space could just stay out of it. On the other hand, setting up PTP traps privately within the driver is not new by any stretch of the imagination: https://elixir.bootlin.com/linux/v5.16-rc2/source/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c#L833 https://elixir.bootlin.com/linux/v5.16-rc2/source/drivers/net/dsa/hirschmann/hellcreek.c#L1050 https://elixir.bootlin.com/linux/v5.16-rc2/source/include/linux/dsa/sja1105.h#L21 So this is the approach taken here as well. The difference here being that we prepare and destroy the traps per port, dynamically at runtime, as opposed to driver init time, because apparently, PTP-unaware forwarding is a use case. Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") Reported-by: Po Liu Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot.c | 241 ++++++++++++++++++++++++++++- 1 file changed, 240 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index bcc4f2f74ccc70..9b7be93cbb0d3b 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1278,6 +1278,225 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port, } EXPORT_SYMBOL(ocelot_fdb_dump); +static void ocelot_populate_l2_ptp_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_ETYPE; + *(__be16 *)trap->key.etype.etype.value = htons(ETH_P_1588); + *(__be16 *)trap->key.etype.etype.mask = htons(0xffff); +} + +static void +ocelot_populate_ipv4_ptp_event_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV4; + trap->key.ipv4.dport.value = PTP_EV_PORT; + trap->key.ipv4.dport.mask = 0xffff; +} + +static void +ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV6; + trap->key.ipv6.dport.value = PTP_EV_PORT; + trap->key.ipv6.dport.mask = 0xffff; +} + +static void +ocelot_populate_ipv4_ptp_general_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV4; + trap->key.ipv4.dport.value = PTP_GEN_PORT; + trap->key.ipv4.dport.mask = 0xffff; +} + +static void +ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV6; + trap->key.ipv6.dport.value = PTP_GEN_PORT; + trap->key.ipv6.dport.mask = 0xffff; +} + +static int ocelot_trap_add(struct ocelot *ocelot, int port, + unsigned long cookie, + void (*populate)(struct ocelot_vcap_filter *f)) +{ + struct ocelot_vcap_block *block_vcap_is2; + struct ocelot_vcap_filter *trap; + bool new = false; + int err; + + block_vcap_is2 = &ocelot->block[VCAP_IS2]; + + trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie, + false); + if (!trap) { + trap = kzalloc(sizeof(*trap), GFP_KERNEL); + if (!trap) + return -ENOMEM; + + populate(trap); + trap->prio = 1; + trap->id.cookie = cookie; + trap->id.tc_offload = false; + trap->block_id = VCAP_IS2; + trap->type = OCELOT_VCAP_FILTER_OFFLOAD; + trap->lookup = 0; + trap->action.cpu_copy_ena = true; + trap->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY; + trap->action.port_mask = 0; + new = true; + } + + trap->ingress_port_mask |= BIT(port); + + if (new) + err = ocelot_vcap_filter_add(ocelot, trap, NULL); + else + err = ocelot_vcap_filter_replace(ocelot, trap); + if (err) { + trap->ingress_port_mask &= ~BIT(port); + if (!trap->ingress_port_mask) + kfree(trap); + return err; + } + + return 0; +} + +static int ocelot_trap_del(struct ocelot *ocelot, int port, + unsigned long cookie) +{ + struct ocelot_vcap_block *block_vcap_is2; + struct ocelot_vcap_filter *trap; + + block_vcap_is2 = &ocelot->block[VCAP_IS2]; + + trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie, + false); + if (!trap) + return 0; + + trap->ingress_port_mask &= ~BIT(port); + if (!trap->ingress_port_mask) + return ocelot_vcap_filter_del(ocelot, trap); + + return ocelot_vcap_filter_replace(ocelot, trap); +} + +static int ocelot_l2_ptp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long l2_cookie = ocelot->num_phys_ports + 1; + + return ocelot_trap_add(ocelot, port, l2_cookie, + ocelot_populate_l2_ptp_trap_key); +} + +static int ocelot_l2_ptp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long l2_cookie = ocelot->num_phys_ports + 1; + + return ocelot_trap_del(ocelot, port, l2_cookie); +} + +static int ocelot_ipv4_ptp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2; + unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3; + int err; + + err = ocelot_trap_add(ocelot, port, ipv4_ev_cookie, + ocelot_populate_ipv4_ptp_event_trap_key); + if (err) + return err; + + err = ocelot_trap_add(ocelot, port, ipv4_gen_cookie, + ocelot_populate_ipv4_ptp_general_trap_key); + if (err) + ocelot_trap_del(ocelot, port, ipv4_ev_cookie); + + return err; +} + +static int ocelot_ipv4_ptp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2; + unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3; + int err; + + err = ocelot_trap_del(ocelot, port, ipv4_ev_cookie); + err |= ocelot_trap_del(ocelot, port, ipv4_gen_cookie); + return err; +} + +static int ocelot_ipv6_ptp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4; + unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5; + int err; + + err = ocelot_trap_add(ocelot, port, ipv6_ev_cookie, + ocelot_populate_ipv6_ptp_event_trap_key); + if (err) + return err; + + err = ocelot_trap_add(ocelot, port, ipv6_gen_cookie, + ocelot_populate_ipv6_ptp_general_trap_key); + if (err) + ocelot_trap_del(ocelot, port, ipv6_ev_cookie); + + return err; +} + +static int ocelot_ipv6_ptp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4; + unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5; + int err; + + err = ocelot_trap_del(ocelot, port, ipv6_ev_cookie); + err |= ocelot_trap_del(ocelot, port, ipv6_gen_cookie); + return err; +} + +static int ocelot_setup_ptp_traps(struct ocelot *ocelot, int port, + bool l2, bool l4) +{ + int err; + + if (l2) + err = ocelot_l2_ptp_trap_add(ocelot, port); + else + err = ocelot_l2_ptp_trap_del(ocelot, port); + if (err) + return err; + + if (l4) { + err = ocelot_ipv4_ptp_trap_add(ocelot, port); + if (err) + goto err_ipv4; + + err = ocelot_ipv6_ptp_trap_add(ocelot, port); + if (err) + goto err_ipv6; + } else { + err = ocelot_ipv4_ptp_trap_del(ocelot, port); + + err |= ocelot_ipv6_ptp_trap_del(ocelot, port); + } + if (err) + return err; + + return 0; + +err_ipv6: + ocelot_ipv4_ptp_trap_del(ocelot, port); +err_ipv4: + if (l2) + ocelot_l2_ptp_trap_del(ocelot, port); + return err; +} + int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr) { return copy_to_user(ifr->ifr_data, &ocelot->hwtstamp_config, @@ -1288,7 +1507,9 @@ EXPORT_SYMBOL(ocelot_hwstamp_get); int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + bool l2 = false, l4 = false; struct hwtstamp_config cfg; + int err; if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; @@ -1323,19 +1544,37 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + l4 = true; + break; case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + l2 = true; + break; case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + l2 = true; + l4 = true; break; default: mutex_unlock(&ocelot->ptp_lock); return -ERANGE; } + err = ocelot_setup_ptp_traps(ocelot, port, l2, l4); + if (err) + return err; + + if (l2 && l4) + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + else if (l2) + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; + else if (l4) + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; + else + cfg.rx_filter = HWTSTAMP_FILTER_NONE; + /* Commit back the result & save it */ memcpy(&ocelot->hwtstamp_config, &cfg, sizeof(cfg)); mutex_unlock(&ocelot->ptp_lock); From c49a35eedfef08bffd46b53c25dbf9d6016a86ff Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:45 +0200 Subject: [PATCH 344/358] net: mscc: ocelot: correctly report the timestamping RX filters in ethtool The driver doesn't support RX timestamping for non-PTP packets, but it declares that it does. Restrict the reported RX filters to PTP v2 over L2 and over L4. Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 9b7be93cbb0d3b..409cde1e59c6f2 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1677,7 +1677,10 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, SOF_TIMESTAMPING_RAW_HARDWARE; info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) | BIT(HWTSTAMP_TX_ONESTEP_SYNC); - info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT); return 0; } From b3612ccdf2841c64ae7a8dd9e780c91240093fe6 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 26 Nov 2021 13:39:26 +0100 Subject: [PATCH 345/358] net: dsa: microchip: implement multi-bridge support Current driver version is able to handle only one bridge at time. Configuring two bridges on two different ports would end up shorting this bridges by HW. To reproduce it: ip l a name br0 type bridge ip l a name br1 type bridge ip l s dev br0 up ip l s dev br1 up ip l s lan1 master br0 ip l s dev lan1 up ip l s lan2 master br1 ip l s dev lan2 up Ping on lan1 and get response on lan2, which should not happen. This happened, because current driver version is storing one global "Port VLAN Membership" and applying it to all ports which are members of any bridge. To solve this issue, we need to handle each port separately. This patch is dropping the global port member storage and calculating membership dynamically depending on STP state and bridge participation. Note: STP support was broken before this patch and should be fixed separately. Fixes: c2e866911e25 ("net: dsa: microchip: break KSZ9477 DSA driver into two files") Signed-off-by: Oleksij Rempel Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/20211126123926.2981028-1-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz8795.c | 56 +++------------------- drivers/net/dsa/microchip/ksz9477.c | 66 ++++---------------------- drivers/net/dsa/microchip/ksz_common.c | 50 ++++++++++--------- drivers/net/dsa/microchip/ksz_common.h | 4 -- 4 files changed, 43 insertions(+), 133 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 43fc3087aeb3ea..013e9c02be71ab 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1002,57 +1002,32 @@ static void ksz8_cfg_port_member(struct ksz_device *dev, int port, u8 member) data &= ~PORT_VLAN_MEMBERSHIP; data |= (member & dev->port_mask); ksz_pwrite8(dev, port, P_MIRROR_CTRL, data); - dev->ports[port].member = member; } static void ksz8_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { struct ksz_device *dev = ds->priv; - int forward = dev->member; struct ksz_port *p; - int member = -1; u8 data; - p = &dev->ports[port]; - ksz_pread8(dev, port, P_STP_CTRL, &data); data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); switch (state) { case BR_STATE_DISABLED: data |= PORT_LEARN_DISABLE; - if (port < dev->phy_port_cnt) - member = 0; break; case BR_STATE_LISTENING: data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE); - if (port < dev->phy_port_cnt && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; case BR_STATE_LEARNING: data |= PORT_RX_ENABLE; break; case BR_STATE_FORWARDING: data |= (PORT_TX_ENABLE | PORT_RX_ENABLE); - - /* This function is also used internally. */ - if (port == dev->cpu_port) - break; - - /* Port is a member of a bridge. */ - if (dev->br_member & BIT(port)) { - dev->member |= BIT(port); - member = dev->member; - } else { - member = dev->host_mask | p->vid_member; - } break; case BR_STATE_BLOCKING: data |= PORT_LEARN_DISABLE; - if (port < dev->phy_port_cnt && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; default: dev_err(ds->dev, "invalid STP state: %d\n", state); @@ -1060,22 +1035,11 @@ static void ksz8_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) } ksz_pwrite8(dev, port, P_STP_CTRL, data); + + p = &dev->ports[port]; p->stp_state = state; - /* Port membership may share register with STP state. */ - if (member >= 0 && member != p->member) - ksz8_cfg_port_member(dev, port, (u8)member); - - /* Check if forwarding needs to be updated. */ - if (state != BR_STATE_FORWARDING) { - if (dev->br_member & BIT(port)) - dev->member &= ~BIT(port); - } - /* When topology has changed the function ksz_update_port_member - * should be called to modify port forwarding behavior. - */ - if (forward != dev->member) - ksz_update_port_member(dev, port); + ksz_update_port_member(dev, port); } static void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port) @@ -1341,7 +1305,7 @@ static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port) static void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) { - struct ksz_port *p = &dev->ports[port]; + struct dsa_switch *ds = dev->ds; struct ksz8 *ksz8 = dev->priv; const u32 *masks; u8 member; @@ -1368,10 +1332,11 @@ static void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) if (!ksz_is_ksz88x3(dev)) ksz8795_cpu_interface_select(dev, port); - member = dev->port_mask; + member = dsa_user_ports(ds); } else { - member = dev->host_mask | p->vid_member; + member = BIT(dsa_upstream_port(ds, port)); } + ksz8_cfg_port_member(dev, port, member); } @@ -1392,20 +1357,13 @@ static void ksz8_config_cpu_port(struct dsa_switch *ds) ksz_cfg(dev, regs[S_TAIL_TAG_CTRL], masks[SW_TAIL_TAG_ENABLE], true); p = &dev->ports[dev->cpu_port]; - p->vid_member = dev->port_mask; p->on = 1; ksz8_port_setup(dev, dev->cpu_port, true); - dev->member = dev->host_mask; for (i = 0; i < dev->phy_port_cnt; i++) { p = &dev->ports[i]; - /* Initialize to non-zero so that ksz_cfg_port_member() will - * be called. - */ - p->vid_member = BIT(i); - p->member = dev->port_mask; ksz8_port_stp_state_set(ds, i, BR_STATE_DISABLED); /* Last port may be disabled. */ diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 854e25f43fa708..353b5f98174075 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -391,7 +391,6 @@ static void ksz9477_cfg_port_member(struct ksz_device *dev, int port, u8 member) { ksz_pwrite32(dev, port, REG_PORT_VLAN_MEMBERSHIP__4, member); - dev->ports[port].member = member; } static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, @@ -400,8 +399,6 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, struct ksz_device *dev = ds->priv; struct ksz_port *p = &dev->ports[port]; u8 data; - int member = -1; - int forward = dev->member; ksz_pread8(dev, port, P_STP_CTRL, &data); data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); @@ -409,40 +406,18 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, switch (state) { case BR_STATE_DISABLED: data |= PORT_LEARN_DISABLE; - if (port != dev->cpu_port) - member = 0; break; case BR_STATE_LISTENING: data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE); - if (port != dev->cpu_port && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; case BR_STATE_LEARNING: data |= PORT_RX_ENABLE; break; case BR_STATE_FORWARDING: data |= (PORT_TX_ENABLE | PORT_RX_ENABLE); - - /* This function is also used internally. */ - if (port == dev->cpu_port) - break; - - member = dev->host_mask | p->vid_member; - mutex_lock(&dev->dev_mutex); - - /* Port is a member of a bridge. */ - if (dev->br_member & (1 << port)) { - dev->member |= (1 << port); - member = dev->member; - } - mutex_unlock(&dev->dev_mutex); break; case BR_STATE_BLOCKING: data |= PORT_LEARN_DISABLE; - if (port != dev->cpu_port && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; default: dev_err(ds->dev, "invalid STP state: %d\n", state); @@ -451,23 +426,8 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, ksz_pwrite8(dev, port, P_STP_CTRL, data); p->stp_state = state; - mutex_lock(&dev->dev_mutex); - /* Port membership may share register with STP state. */ - if (member >= 0 && member != p->member) - ksz9477_cfg_port_member(dev, port, (u8)member); - - /* Check if forwarding needs to be updated. */ - if (state != BR_STATE_FORWARDING) { - if (dev->br_member & (1 << port)) - dev->member &= ~(1 << port); - } - /* When topology has changed the function ksz_update_port_member - * should be called to modify port forwarding behavior. - */ - if (forward != dev->member) - ksz_update_port_member(dev, port); - mutex_unlock(&dev->dev_mutex); + ksz_update_port_member(dev, port); } static void ksz9477_flush_dyn_mac_table(struct ksz_device *dev, int port) @@ -1168,10 +1128,10 @@ static void ksz9477_phy_errata_setup(struct ksz_device *dev, int port) static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) { - u8 data8; - u8 member; - u16 data16; struct ksz_port *p = &dev->ports[port]; + struct dsa_switch *ds = dev->ds; + u8 data8, member; + u16 data16; /* enable tag tail for host port */ if (cpu_port) @@ -1250,12 +1210,12 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz_pwrite8(dev, port, REG_PORT_XMII_CTRL_1, data8); p->phydev.duplex = 1; } - mutex_lock(&dev->dev_mutex); + if (cpu_port) - member = dev->port_mask; + member = dsa_user_ports(ds); else - member = dev->host_mask | p->vid_member; - mutex_unlock(&dev->dev_mutex); + member = BIT(dsa_upstream_port(ds, port)); + ksz9477_cfg_port_member(dev, port, member); /* clear pending interrupts */ @@ -1276,8 +1236,6 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) const char *prev_mode; dev->cpu_port = i; - dev->host_mask = (1 << dev->cpu_port); - dev->port_mask |= dev->host_mask; p = &dev->ports[i]; /* Read from XMII register to determine host port @@ -1312,23 +1270,15 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) /* enable cpu port */ ksz9477_port_setup(dev, i, true); - p->vid_member = dev->port_mask; p->on = 1; } } - dev->member = dev->host_mask; - for (i = 0; i < dev->port_cnt; i++) { if (i == dev->cpu_port) continue; p = &dev->ports[i]; - /* Initialize to non-zero so that ksz_cfg_port_member() will - * be called. - */ - p->vid_member = (1 << i); - p->member = dev->port_mask; ksz9477_port_stp_state_set(ds, i, BR_STATE_DISABLED); p->on = 1; if (i < dev->phy_port_cnt) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 7c2968a639eba5..8a04302018dce6 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -22,21 +22,40 @@ void ksz_update_port_member(struct ksz_device *dev, int port) { - struct ksz_port *p; + struct ksz_port *p = &dev->ports[port]; + struct dsa_switch *ds = dev->ds; + u8 port_member = 0, cpu_port; + const struct dsa_port *dp; int i; - for (i = 0; i < dev->port_cnt; i++) { - if (i == port || i == dev->cpu_port) + if (!dsa_is_user_port(ds, port)) + return; + + dp = dsa_to_port(ds, port); + cpu_port = BIT(dsa_upstream_port(ds, port)); + + for (i = 0; i < ds->num_ports; i++) { + const struct dsa_port *other_dp = dsa_to_port(ds, i); + struct ksz_port *other_p = &dev->ports[i]; + u8 val = 0; + + if (!dsa_is_user_port(ds, i)) continue; - p = &dev->ports[i]; - if (!(dev->member & (1 << i))) + if (port == i) + continue; + if (!dp->bridge_dev || dp->bridge_dev != other_dp->bridge_dev) continue; - /* Port is a member of the bridge and is forwarding. */ - if (p->stp_state == BR_STATE_FORWARDING && - p->member != dev->member) - dev->dev_ops->cfg_port_member(dev, i, dev->member); + if (other_p->stp_state == BR_STATE_FORWARDING && + p->stp_state == BR_STATE_FORWARDING) { + val |= BIT(port); + port_member |= BIT(i); + } + + dev->dev_ops->cfg_port_member(dev, i, val | cpu_port); } + + dev->dev_ops->cfg_port_member(dev, port, port_member | cpu_port); } EXPORT_SYMBOL_GPL(ksz_update_port_member); @@ -175,12 +194,6 @@ EXPORT_SYMBOL_GPL(ksz_get_ethtool_stats); int ksz_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) { - struct ksz_device *dev = ds->priv; - - mutex_lock(&dev->dev_mutex); - dev->br_member |= (1 << port); - mutex_unlock(&dev->dev_mutex); - /* port_stp_state_set() will be called after to put the port in * appropriate state so there is no need to do anything. */ @@ -192,13 +205,6 @@ EXPORT_SYMBOL_GPL(ksz_port_bridge_join); void ksz_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) { - struct ksz_device *dev = ds->priv; - - mutex_lock(&dev->dev_mutex); - dev->br_member &= ~(1 << port); - dev->member &= ~(1 << port); - mutex_unlock(&dev->dev_mutex); - /* port_stp_state_set() will be called after to put the port in * forwarding state so there is no need to do anything. */ diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 1597c63988b4e4..54b456bc897280 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -25,8 +25,6 @@ struct ksz_port_mib { }; struct ksz_port { - u16 member; - u16 vid_member; bool remove_tag; /* Remove Tag flag set, for ksz8795 only */ int stp_state; struct phy_device phydev; @@ -83,8 +81,6 @@ struct ksz_device { struct ksz_port *ports; struct delayed_work mib_read; unsigned long mib_read_interval; - u16 br_member; - u16 member; u16 mirror_rx; u16 mirror_tx; u32 features; /* chip specific features */ From 21e96a2035db43fc72f7023c4577a63ca606de86 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 23 Nov 2021 11:55:06 +0100 Subject: [PATCH 346/358] iommu/vt-d: Remove unused PASID_DISABLED The macro is unused after commit 00ecd5401349a so it can be removed. Reported-by: Linus Torvalds Fixes: 00ecd5401349a ("iommu/vt-d: Clean up unused PASID updating functions") Signed-off-by: Joerg Roedel Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20211123105507.7654-2-joro@8bytes.org --- arch/x86/include/asm/fpu/api.h | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 6053674f91320a..c2767a6a387e73 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -102,12 +102,6 @@ extern void switch_fpu_return(void); */ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); -/* - * Tasks that are not using SVA have mm->pasid set to zero to note that they - * will not have the valid bit set in MSR_IA32_PASID while they are running. - */ -#define PASID_DISABLED 0 - /* Trap handling */ extern int fpu__exception_code(struct fpu *fpu, int trap_nr); extern void fpu_sync_fpstate(struct fpu *fpu); From 717e88aad37befedfd531378b632e794e24e9afb Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 23 Nov 2021 11:55:07 +0100 Subject: [PATCH 347/358] iommu/amd: Clarify AMD IOMMUv2 initialization messages The messages printed on the initialization of the AMD IOMMUv2 driver have caused some confusion in the past. Clarify the messages to lower the confusion in the future. Cc: stable@vger.kernel.org Signed-off-by: Joerg Roedel Link: https://lore.kernel.org/r/20211123105507.7654-3-joro@8bytes.org --- drivers/iommu/amd/iommu_v2.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c index 13cbeb997cc1a0..58da08cc3d0160 100644 --- a/drivers/iommu/amd/iommu_v2.c +++ b/drivers/iommu/amd/iommu_v2.c @@ -929,10 +929,8 @@ static int __init amd_iommu_v2_init(void) { int ret; - pr_info("AMD IOMMUv2 driver by Joerg Roedel \n"); - if (!amd_iommu_v2_supported()) { - pr_info("AMD IOMMUv2 functionality not available on this system\n"); + pr_info("AMD IOMMUv2 functionality not available on this system - This is not a bug.\n"); /* * Load anyway to provide the symbols to other modules * which may use AMD IOMMUv2 optionally. @@ -947,6 +945,8 @@ static int __init amd_iommu_v2_init(void) amd_iommu_register_ppr_notifier(&ppr_nb); + pr_info("AMD IOMMUv2 loaded and initialized\n"); + return 0; out: From f7ff3cff3527ff1e70cad8d2fe7c0c7b6f83120a Mon Sep 17 00:00:00 2001 From: Alex Bee Date: Wed, 24 Nov 2021 03:13:25 +0100 Subject: [PATCH 348/358] iommu/rockchip: Fix PAGE_DESC_HI_MASKs for RK3568 With the submission of iommu driver for RK3568 a subtle bug was introduced: PAGE_DESC_HI_MASK1 and PAGE_DESC_HI_MASK2 have to be the other way arround - that leads to random errors, especially when addresses beyond 32 bit are used. Fix it. Fixes: c55356c534aa ("iommu: rockchip: Add support for iommu v2") Signed-off-by: Alex Bee Tested-by: Peter Geis Reviewed-by: Heiko Stuebner Tested-by: Dan Johansen Reviewed-by: Benjamin Gaignard Link: https://lore.kernel.org/r/20211124021325.858139-1-knaerzche@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/rockchip-iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 5cb260820eda6a..7f23ad61c094fb 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -200,8 +200,8 @@ static inline phys_addr_t rk_dte_pt_address(u32 dte) #define DTE_HI_MASK2 GENMASK(7, 4) #define DTE_HI_SHIFT1 24 /* shift bit 8 to bit 32 */ #define DTE_HI_SHIFT2 32 /* shift bit 4 to bit 36 */ -#define PAGE_DESC_HI_MASK1 GENMASK_ULL(39, 36) -#define PAGE_DESC_HI_MASK2 GENMASK_ULL(35, 32) +#define PAGE_DESC_HI_MASK1 GENMASK_ULL(35, 32) +#define PAGE_DESC_HI_MASK2 GENMASK_ULL(39, 36) static inline phys_addr_t rk_dte_pt_address_v2(u32 dte) { From 4e5973dd2725bb30c3db622f7d73f7a5864ce718 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 26 Nov 2021 21:55:55 +0800 Subject: [PATCH 349/358] iommu/vt-d: Fix an unbalanced rcu_read_lock/rcu_read_unlock() If we return -EOPNOTSUPP, the rcu lock remains lock. This is spurious. Go through the end of the function instead. This way, the missing 'rcu_read_unlock()' is called. Fixes: 7afd7f6aa21a ("iommu/vt-d: Check FL and SL capability sanity in scalable mode") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/40cc077ca5f543614eab2a10e84d29dd190273f6.1636217517.git.christophe.jaillet@wanadoo.fr Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20211126135556.397932-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/cap_audit.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c index b39d223926a491..71596fc62822c3 100644 --- a/drivers/iommu/intel/cap_audit.c +++ b/drivers/iommu/intel/cap_audit.c @@ -144,6 +144,7 @@ static int cap_audit_static(struct intel_iommu *iommu, enum cap_audit_type type) { struct dmar_drhd_unit *d; struct intel_iommu *i; + int rc = 0; rcu_read_lock(); if (list_empty(&dmar_drhd_units)) @@ -169,11 +170,11 @@ static int cap_audit_static(struct intel_iommu *iommu, enum cap_audit_type type) */ if (intel_cap_smts_sanity() && !intel_cap_flts_sanity() && !intel_cap_slts_sanity()) - return -EOPNOTSUPP; + rc = -EOPNOTSUPP; out: rcu_read_unlock(); - return 0; + return rc; } int intel_cap_audit(enum cap_audit_type type, struct intel_iommu *iommu) From 86dc40c7ea9c22f64571e0e45f695de73a0e2644 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 26 Nov 2021 21:55:56 +0800 Subject: [PATCH 350/358] iommu/vt-d: Fix unmap_pages support When supporting only the .map and .unmap callbacks of iommu_ops, the IOMMU driver can make assumptions about the size and alignment used for mappings based on the driver provided pgsize_bitmap. VT-d previously used essentially PAGE_MASK for this bitmap as any power of two mapping was acceptably filled by native page sizes. However, with the .map_pages and .unmap_pages interface we're now getting page-size and count arguments. If we simply combine these as (page-size * count) and make use of the previous map/unmap functions internally, any size and alignment assumptions are very different. As an example, a given vfio device assignment VM will often create a 4MB mapping at IOVA pfn [0x3fe00 - 0x401ff]. On a system that does not support IOMMU super pages, the unmap_pages interface will ask to unmap 1024 4KB pages at the base IOVA. dma_pte_clear_level() will recurse down to level 2 of the page table where the first half of the pfn range exactly matches the entire pte level. We clear the pte, increment the pfn by the level size, but (oops) the next pte is on a new page, so we exit the loop an pop back up a level. When we then update the pfn based on that higher level, we seem to assume that the previous pfn value was at the start of the level. In this case the level size is 256K pfns, which we add to the base pfn and get a results of 0x7fe00, which is clearly greater than 0x401ff, so we're done. Meanwhile we never cleared the ptes for the remainder of the range. When the VM remaps this range, we're overwriting valid ptes and the VT-d driver complains loudly, as reported by the user report linked below. The fix for this seems relatively simple, if each iteration of the loop in dma_pte_clear_level() is assumed to clear to the end of the level pte page, then our next pfn should be calculated from level_pfn rather than our working pfn. Fixes: 3f34f1259776 ("iommu/vt-d: Implement map/unmap_pages() iommu_ops callback") Reported-by: Ajay Garg Signed-off-by: Alex Williamson Tested-by: Giovanni Cabiddu Link: https://lore.kernel.org/all/20211002124012.18186-1-ajaygargnsit@gmail.com/ Link: https://lore.kernel.org/r/163659074748.1617923.12716161410774184024.stgit@omen Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20211126135556.397932-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 0bde0c8b41269c..b6a8f3282411fc 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1339,13 +1339,11 @@ static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level, pte = &pte[pfn_level_offset(pfn, level)]; do { - unsigned long level_pfn; + unsigned long level_pfn = pfn & level_mask(level); if (!dma_pte_present(pte)) goto next; - level_pfn = pfn & level_mask(level); - /* If range covers entire pagetable, free it */ if (start_pfn <= level_pfn && last_pfn >= level_pfn + level_size(level) - 1) { @@ -1366,7 +1364,7 @@ static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level, freelist); } next: - pfn += level_size(level); + pfn = level_pfn + level_size(level); } while (!first_pte_in_page(++pte) && pfn <= last_pfn); if (first_pte) From a55f224ff5f238013de8762c4287117e47b86e22 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 26 Nov 2021 17:34:42 -0500 Subject: [PATCH 351/358] tracing: Fix pid filtering when triggers are attached If a event is filtered by pid and a trigger that requires processing of the event to happen is a attached to the event, the discard portion does not take the pid filtering into account, and the event will then be recorded when it should not have been. Cc: stable@vger.kernel.org Fixes: 3fdaf80f4a836 ("tracing: Implement event pid filtering") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.h | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6b60ab9475edb3..38715aa6cfdfb7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1366,14 +1366,26 @@ __event_trigger_test_discard(struct trace_event_file *file, if (eflags & EVENT_FILE_FL_TRIGGER_COND) *tt = event_triggers_call(file, buffer, entry, event); - if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) || - (unlikely(file->flags & EVENT_FILE_FL_FILTERED) && - !filter_match_preds(file->filter, entry))) { - __trace_event_discard_commit(buffer, event); - return true; - } + if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED | + EVENT_FILE_FL_FILTERED | + EVENT_FILE_FL_PID_FILTER)))) + return false; + + if (file->flags & EVENT_FILE_FL_SOFT_DISABLED) + goto discard; + + if (file->flags & EVENT_FILE_FL_FILTERED && + !filter_match_preds(file->filter, entry)) + goto discard; + + if ((file->flags & EVENT_FILE_FL_PID_FILTER) && + trace_event_ignore_this_pid(file)) + goto discard; return false; + discard: + __trace_event_discard_commit(buffer, event); + return true; } /** From 1d0254e6b47e73222fd3d6ae95cccbaafe5b3ecf Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Mon, 22 Nov 2021 10:47:37 +0800 Subject: [PATCH 352/358] io_uring: fix soft lockup when call __io_remove_buffers I got issue as follows: [ 567.094140] __io_remove_buffers: [1]start ctx=0xffff8881067bf000 bgid=65533 buf=0xffff8881fefe1680 [ 594.360799] watchdog: BUG: soft lockup - CPU#2 stuck for 26s! [kworker/u32:5:108] [ 594.364987] Modules linked in: [ 594.365405] irq event stamp: 604180238 [ 594.365906] hardirqs last enabled at (604180237): [] _raw_spin_unlock_irqrestore+0x2d/0x50 [ 594.367181] hardirqs last disabled at (604180238): [] sysvec_apic_timer_interrupt+0xb/0xc0 [ 594.368420] softirqs last enabled at (569080666): [] __do_softirq+0x654/0xa9e [ 594.369551] softirqs last disabled at (569080575): [] irq_exit_rcu+0x1ca/0x250 [ 594.370692] CPU: 2 PID: 108 Comm: kworker/u32:5 Tainted: G L 5.15.0-next-20211112+ #88 [ 594.371891] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_073836-buildvm-ppc64le-16.ppc.fedoraproject.org-3.fc31 04/01/2014 [ 594.373604] Workqueue: events_unbound io_ring_exit_work [ 594.374303] RIP: 0010:_raw_spin_unlock_irqrestore+0x33/0x50 [ 594.375037] Code: 48 83 c7 18 53 48 89 f3 48 8b 74 24 10 e8 55 f5 55 fd 48 89 ef e8 ed a7 56 fd 80 e7 02 74 06 e8 43 13 7b fd fb bf 01 00 00 00 f8 78 474 [ 594.377433] RSP: 0018:ffff888101587a70 EFLAGS: 00000202 [ 594.378120] RAX: 0000000024030f0d RBX: 0000000000000246 RCX: 1ffffffff2f09106 [ 594.379053] RDX: 0000000000000000 RSI: ffffffff9449f0e0 RDI: 0000000000000001 [ 594.379991] RBP: ffffffff9586cdc0 R08: 0000000000000001 R09: fffffbfff2effcab [ 594.380923] R10: ffffffff977fe557 R11: fffffbfff2effcaa R12: ffff8881b8f3def0 [ 594.381858] R13: 0000000000000246 R14: ffff888153a8b070 R15: 0000000000000000 [ 594.382787] FS: 0000000000000000(0000) GS:ffff888399c00000(0000) knlGS:0000000000000000 [ 594.383851] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 594.384602] CR2: 00007fcbe71d2000 CR3: 00000000b4216000 CR4: 00000000000006e0 [ 594.385540] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 594.386474] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 594.387403] Call Trace: [ 594.387738] [ 594.388042] find_and_remove_object+0x118/0x160 [ 594.389321] delete_object_full+0xc/0x20 [ 594.389852] kfree+0x193/0x470 [ 594.390275] __io_remove_buffers.part.0+0xed/0x147 [ 594.390931] io_ring_ctx_free+0x342/0x6a2 [ 594.392159] io_ring_exit_work+0x41e/0x486 [ 594.396419] process_one_work+0x906/0x15a0 [ 594.399185] worker_thread+0x8b/0xd80 [ 594.400259] kthread+0x3bf/0x4a0 [ 594.401847] ret_from_fork+0x22/0x30 [ 594.402343] Message from syslogd@localhost at Nov 13 09:09:54 ... kernel:watchdog: BUG: soft lockup - CPU#2 stuck for 26s! [kworker/u32:5:108] [ 596.793660] __io_remove_buffers: [2099199]start ctx=0xffff8881067bf000 bgid=65533 buf=0xffff8881fefe1680 We can reproduce this issue by follow syzkaller log: r0 = syz_io_uring_setup(0x401, &(0x7f0000000300), &(0x7f0000003000/0x2000)=nil, &(0x7f0000ff8000/0x4000)=nil, &(0x7f0000000280)=0x0, &(0x7f0000000380)=0x0) sendmsg$ETHTOOL_MSG_FEATURES_SET(0xffffffffffffffff, &(0x7f0000003080)={0x0, 0x0, &(0x7f0000003040)={&(0x7f0000000040)=ANY=[], 0x18}}, 0x0) syz_io_uring_submit(r1, r2, &(0x7f0000000240)=@IORING_OP_PROVIDE_BUFFERS={0x1f, 0x5, 0x0, 0x401, 0x1, 0x0, 0x100, 0x0, 0x1, {0xfffd}}, 0x0) io_uring_enter(r0, 0x3a2d, 0x0, 0x0, 0x0, 0x0) The reason above issue is 'buf->list' has 2,100,000 nodes, occupied cpu lead to soft lockup. To solve this issue, we need add schedule point when do while loop in '__io_remove_buffers'. After add schedule point we do regression, get follow data. [ 240.141864] __io_remove_buffers: [1]start ctx=0xffff888170603000 bgid=65533 buf=0xffff8881116fcb00 [ 268.408260] __io_remove_buffers: [1]start ctx=0xffff8881b92d2000 bgid=65533 buf=0xffff888130c83180 [ 275.899234] __io_remove_buffers: [2099199]start ctx=0xffff888170603000 bgid=65533 buf=0xffff8881116fcb00 [ 296.741404] __io_remove_buffers: [1]start ctx=0xffff8881b659c000 bgid=65533 buf=0xffff8881010fe380 [ 305.090059] __io_remove_buffers: [2099199]start ctx=0xffff8881b92d2000 bgid=65533 buf=0xffff888130c83180 [ 325.415746] __io_remove_buffers: [1]start ctx=0xffff8881b92d1000 bgid=65533 buf=0xffff8881a17d8f00 [ 333.160318] __io_remove_buffers: [2099199]start ctx=0xffff8881b659c000 bgid=65533 buf=0xffff8881010fe380 ... Fixes:8bab4c09f24e("io_uring: allow conditional reschedule for intensive iterators") Signed-off-by: Ye Bin Link: https://lore.kernel.org/r/20211122024737.2198530-1-yebin10@huawei.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 75841b919dce55..8a2b73cba06bd6 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4366,6 +4366,7 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf, kfree(nxt); if (++i == nbufs) return i; + cond_resched(); } i++; kfree(buf); @@ -9295,10 +9296,8 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx) struct io_buffer *buf; unsigned long index; - xa_for_each(&ctx->io_buffers, index, buf) { + xa_for_each(&ctx->io_buffers, index, buf) __io_remove_buffers(ctx, buf, index, -1U); - cond_resched(); - } } static void io_req_caches_free(struct io_ring_ctx *ctx) From f6223ff799666235a80d05f8137b73e5580077b9 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 18 Nov 2021 09:59:07 +0800 Subject: [PATCH 353/358] io_uring: Fix undefined-behaviour in io_issue_sqe We got issue as follows: ================================================================================ UBSAN: Undefined behaviour in ./include/linux/ktime.h:42:14 signed integer overflow: -4966321760114568020 * 1000000000 cannot be represented in type 'long long int' CPU: 1 PID: 2186 Comm: syz-executor.2 Not tainted 4.19.90+ #12 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x3f0 arch/arm64/kernel/time.c:78 show_stack+0x28/0x38 arch/arm64/kernel/traps.c:158 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x170/0x1dc lib/dump_stack.c:118 ubsan_epilogue+0x18/0xb4 lib/ubsan.c:161 handle_overflow+0x188/0x1dc lib/ubsan.c:192 __ubsan_handle_mul_overflow+0x34/0x44 lib/ubsan.c:213 ktime_set include/linux/ktime.h:42 [inline] timespec64_to_ktime include/linux/ktime.h:78 [inline] io_timeout fs/io_uring.c:5153 [inline] io_issue_sqe+0x42c8/0x4550 fs/io_uring.c:5599 __io_queue_sqe+0x1b0/0xbc0 fs/io_uring.c:5988 io_queue_sqe+0x1ac/0x248 fs/io_uring.c:6067 io_submit_sqe fs/io_uring.c:6137 [inline] io_submit_sqes+0xed8/0x1c88 fs/io_uring.c:6331 __do_sys_io_uring_enter fs/io_uring.c:8170 [inline] __se_sys_io_uring_enter fs/io_uring.c:8129 [inline] __arm64_sys_io_uring_enter+0x490/0x980 fs/io_uring.c:8129 invoke_syscall arch/arm64/kernel/syscall.c:53 [inline] el0_svc_common+0x374/0x570 arch/arm64/kernel/syscall.c:121 el0_svc_handler+0x190/0x260 arch/arm64/kernel/syscall.c:190 el0_svc+0x10/0x218 arch/arm64/kernel/entry.S:1017 ================================================================================ As ktime_set only judge 'secs' if big than KTIME_SEC_MAX, but if we pass negative value maybe lead to overflow. To address this issue, we must check if 'sec' is negative. Signed-off-by: Ye Bin Link: https://lore.kernel.org/r/20211118015907.844807-1-yebin10@huawei.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index 8a2b73cba06bd6..c4f217613f56e3 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6196,6 +6196,9 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; + if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) + return -EINVAL; + data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); From 27ff768fa21ca3286fcc87c3f38ac67d1a2cbe2d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sat, 27 Nov 2021 16:45:26 -0500 Subject: [PATCH 354/358] tracing: Test the 'Do not trace this pid' case in create event When creating a new event (via a module, kprobe, eprobe, etc), the descriptors that are created must add flags for pid filtering if an instance has pid filtering enabled, as the flags are used at the time the event is executed to know if pid filtering should be done or not. The "Only trace this pid" case was added, but a cut and paste error made that case checked twice, instead of checking the "Trace all but this pid" case. Link: https://lore.kernel.org/all/202111280401.qC0z99JB-lkp@intel.com/ Fixes: 6cb206508b62 ("tracing: Check pid filtering when creating events") Reported-by: kernel test robot Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f8965fd50d3be4..92be9cb1d7d4bc 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2693,7 +2693,7 @@ trace_create_new_event(struct trace_event_call *call, lockdep_is_held(&event_mutex)); if (!trace_pid_list_first(pid_list, &first) || - !trace_pid_list_first(pid_list, &first)) + !trace_pid_list_first(no_pid_list, &first)) file->flags |= EVENT_FILE_FL_PID_FILTER; file->event_call = call; From 1f0e290cc5fd818d002e0a83b0ea8eceb8f2c515 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 27 Nov 2021 07:44:40 -0800 Subject: [PATCH 355/358] arch: Add generic Kconfig option indicating page size smaller than 64k NTFS_RW and VMXNET3 require a page size smaller than 64kB. Add generic Kconfig option for use outside architecture code to avoid architecture specific Kconfig options in that code. Suggested-by: Michael Ellerman Signed-off-by: Guenter Roeck Cc: Anton Altaparmakov Signed-off-by: Linus Torvalds --- arch/Kconfig | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/Kconfig b/arch/Kconfig index 26b8ed11639da4..d3c4ab249e9c27 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -991,6 +991,16 @@ config HAVE_ARCH_COMPAT_MMAP_BASES and vice-versa 32-bit applications to call 64-bit mmap(). Required for applications doing different bitness syscalls. +config PAGE_SIZE_LESS_THAN_64KB + def_bool y + depends on !ARM64_64K_PAGES + depends on !IA64_PAGE_SIZE_64KB + depends on !PAGE_SIZE_64KB + depends on !PARISC_PAGE_SIZE_64KB + depends on !PPC_64K_PAGES + depends on !PPC_256K_PAGES + depends on !PAGE_SIZE_256KB + # This allows to use a set of generic functions to determine mmap base # address by giving priority to top-down scheme only if the process # is not in legacy mode (compat task, unlimited stack size or From 4eec7faf6775263d9e450ae7ee5bc4101d4a0bc9 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 27 Nov 2021 07:44:41 -0800 Subject: [PATCH 356/358] fs: ntfs: Limit NTFS_RW to page sizes smaller than 64k NTFS_RW code allocates page size dependent arrays on the stack. This results in build failures if the page size is 64k or larger. fs/ntfs/aops.c: In function 'ntfs_write_mst_block': fs/ntfs/aops.c:1311:1: error: the frame size of 2240 bytes is larger than 2048 bytes Since commit f22969a66041 ("powerpc/64s: Default to 64K pages for 64 bit book3s") this affects ppc:allmodconfig builds, but other architectures supporting page sizes of 64k or larger are also affected. Increasing the maximum frame size for affected architectures just to silence this error does not really help. The frame size would have to be set to a really large value for 256k pages. Also, a large frame size could potentially result in stack overruns in this code and elsewhere and is therefore not desirable. Make NTFS_RW dependent on page sizes smaller than 64k instead. Signed-off-by: Guenter Roeck Cc: Anton Altaparmakov Signed-off-by: Linus Torvalds --- fs/ntfs/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ntfs/Kconfig b/fs/ntfs/Kconfig index 1667a7e590d863..f93e69a612833f 100644 --- a/fs/ntfs/Kconfig +++ b/fs/ntfs/Kconfig @@ -52,6 +52,7 @@ config NTFS_DEBUG config NTFS_RW bool "NTFS write support" depends on NTFS_FS + depends on PAGE_SIZE_LESS_THAN_64KB help This enables the partial, but safe, write support in the NTFS driver. From 00169a9245f841ec666c70959bfd1dcacce74324 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 27 Nov 2021 07:44:42 -0800 Subject: [PATCH 357/358] vmxnet3: Use generic Kconfig option for page size limit Use the architecture independent Kconfig option PAGE_SIZE_LESS_THAN_64KB to indicate that VMXNET3 requires a page size smaller than 64kB. Signed-off-by: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/net/Kconfig | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 10506a4b66ef85..6cccc3dc00bcf3 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -567,9 +567,7 @@ config XEN_NETDEV_BACKEND config VMXNET3 tristate "VMware VMXNET3 ethernet driver" depends on PCI && INET - depends on !(PAGE_SIZE_64KB || ARM64_64K_PAGES || \ - IA64_PAGE_SIZE_64KB || PARISC_PAGE_SIZE_64KB || \ - PPC_64K_PAGES) + depends on PAGE_SIZE_LESS_THAN_64KB help This driver supports VMware's vmxnet3 virtual ethernet NIC. To compile this driver as a module, choose M here: the From d58071a8a76d779eedab38033ae4c821c30295a5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Nov 2021 14:09:19 -0800 Subject: [PATCH 358/358] Linux 5.16-rc3 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 72b0c3d5cbad65..0a6ecc8bb2d2b7 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Gobble Gobble # *DOCUMENTATION*