From 4b3ab9372ffa569827c8f7b7ffc7b69ba544a3bd Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Mon, 3 Dec 2018 13:31:18 +0530 Subject: iio: adc: ti_am335x_tscadc: Improve accuracy of measurement When performing single ended measurements with TSCADC, its recommended to set negative input (SEL_INM_SWC_3_0) of ADC step to ADC's VREFN in the corresponding STEP_CONFIGx register. Also, the positive(SEL_RFP_SWC_2_0) and negative(SEL_RFM_SWC_1_0) reference voltage for ADC step needs to be set to VREFP and VREFN respectively in STEP_CONFIGx register. Without these changes, there may be variation of as much as ~2% in the ADC's digital output which is bad for precise measurement. Signed-off-by: Vignesh R Acked-by: Jonathan Cameron Signed-off-by: Lee Jones --- include/linux/mfd/ti_am335x_tscadc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index b9a53e013bff..483168403ae5 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -78,6 +78,8 @@ #define STEPCONFIG_YNN BIT(8) #define STEPCONFIG_XNP BIT(9) #define STEPCONFIG_YPN BIT(10) +#define STEPCONFIG_RFP(val) ((val) << 12) +#define STEPCONFIG_RFP_VREFP (0x3 << 12) #define STEPCONFIG_INM_MASK (0xF << 15) #define STEPCONFIG_INM(val) ((val) << 15) #define STEPCONFIG_INM_ADCREFM STEPCONFIG_INM(8) @@ -86,6 +88,8 @@ #define STEPCONFIG_INP_AN4 STEPCONFIG_INP(4) #define STEPCONFIG_INP_ADCREFM STEPCONFIG_INP(8) #define STEPCONFIG_FIFO1 BIT(26) +#define STEPCONFIG_RFM(val) ((val) << 23) +#define STEPCONFIG_RFM_VREFN (0x3 << 23) /* Delay register */ #define STEPDELAY_OPEN_MASK (0x3FFFF << 0) -- cgit v1.2.3 From a54e950fdec3cde98caa04bc601cbdc95d0d319c Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 7 Nov 2018 14:50:01 +0100 Subject: mfd: tmio: Typo s/use use/use/ Signed-off-by: Geert Uytterhoeven Reviewed-by: Wolfram Sang Reviewed-by: Simon Horman Signed-off-by: Lee Jones --- include/linux/mfd/tmio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 1e70060c92ce..aa696bcb1d12 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -83,7 +83,7 @@ /* Some controllers have a CBSY bit */ #define TMIO_MMC_HAVE_CBSY BIT(11) -/* Some controllers that support HS400 use use 4 taps while others use 8. */ +/* Some controllers that support HS400 use 4 taps while others use 8. */ #define TMIO_MMC_HAVE_4TAP_HS400 BIT(13) int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); -- cgit v1.2.3 From 7f9472134a5af31bad191f074a5d416146da26f7 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 12 Nov 2018 15:28:37 +0000 Subject: mfd: madera: Add shared data for accessory detection Add variables to struct madera that will be shared by the extcon and audio codec drivers to synchronize output state during accessory detection. Also add a mutex to protect the DAPM pointer. Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- include/linux/mfd/madera/core.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h index fe69c0f4398f..4d5d51a9c8a6 100644 --- a/include/linux/mfd/madera/core.h +++ b/include/linux/mfd/madera/core.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -37,6 +38,8 @@ enum madera_type { #define MADERA_MAX_MICBIAS 4 +#define MADERA_MAX_HP_OUTPUT 3 + /* Notifier events */ #define MADERA_NOTIFY_VOICE_TRIGGER 0x1 #define MADERA_NOTIFY_HPDET 0x2 @@ -183,6 +186,10 @@ struct madera { unsigned int num_childbias[MADERA_MAX_MICBIAS]; struct snd_soc_dapm_context *dapm; + struct mutex dapm_ptr_lock; + unsigned int hp_ena; + bool out_clamp[MADERA_MAX_HP_OUTPUT]; + bool out_shorted[MADERA_MAX_HP_OUTPUT]; struct blocking_notifier_head notifier; }; -- cgit v1.2.3 From ddf5aaa8eecb6ccf51f311a513c3a5011fbe0d54 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 16 Dec 2018 15:10:44 +0100 Subject: mfd: ingenic-tcu: Fix bit field description in header The description of the bit was inverted. Signed-off-by: Paul Cercueil Signed-off-by: Lee Jones --- include/linux/mfd/ingenic-tcu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ingenic-tcu.h b/include/linux/mfd/ingenic-tcu.h index ab16ad283def..2083fa20821d 100644 --- a/include/linux/mfd/ingenic-tcu.h +++ b/include/linux/mfd/ingenic-tcu.h @@ -41,7 +41,7 @@ #define TCU_TCSR_PRESCALE_LSB 3 #define TCU_TCSR_PRESCALE_MASK 0x38 -#define TCU_TCSR_PWM_SD BIT(9) /* 0: Shutdown abruptly 1: gracefully */ +#define TCU_TCSR_PWM_SD BIT(9) /* 0: Shutdown gracefully 1: abruptly */ #define TCU_TCSR_PWM_INITL_HIGH BIT(8) /* Sets the initial output level */ #define TCU_TCSR_PWM_EN BIT(7) /* PWM pin output enable */ -- cgit v1.2.3 From c1f3375be60c562e24460d41b75e564c0a429835 Mon Sep 17 00:00:00 2001 From: Cheng-Yi Chiang Date: Tue, 18 Dec 2018 17:06:26 +0800 Subject: mfd: cros_ec: Add commands to control codec Add EC host commands to control codec on EC. Signed-off-by: Cheng-Yi Chiang Signed-off-by: Lee Jones --- include/linux/mfd/cros_ec_commands.h | 94 ++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 9a9631f0559e..fc91082d4c35 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -2790,6 +2790,100 @@ struct ec_response_battery_vendor_param { uint32_t value; } __packed; +/*****************************************************************************/ +/* Commands for I2S recording on audio codec. */ + +#define EC_CMD_CODEC_I2S 0x00BC + +enum ec_codec_i2s_subcmd { + EC_CODEC_SET_SAMPLE_DEPTH = 0x0, + EC_CODEC_SET_GAIN = 0x1, + EC_CODEC_GET_GAIN = 0x2, + EC_CODEC_I2S_ENABLE = 0x3, + EC_CODEC_I2S_SET_CONFIG = 0x4, + EC_CODEC_I2S_SET_TDM_CONFIG = 0x5, + EC_CODEC_I2S_SET_BCLK = 0x6, +}; + +enum ec_sample_depth_value { + EC_CODEC_SAMPLE_DEPTH_16 = 0, + EC_CODEC_SAMPLE_DEPTH_24 = 1, +}; + +enum ec_i2s_config { + EC_DAI_FMT_I2S = 0, + EC_DAI_FMT_RIGHT_J = 1, + EC_DAI_FMT_LEFT_J = 2, + EC_DAI_FMT_PCM_A = 3, + EC_DAI_FMT_PCM_B = 4, + EC_DAI_FMT_PCM_TDM = 5, +}; + +struct ec_param_codec_i2s { + /* + * enum ec_codec_i2s_subcmd + */ + uint8_t cmd; + union { + /* + * EC_CODEC_SET_SAMPLE_DEPTH + * Value should be one of ec_sample_depth_value. + */ + uint8_t depth; + + /* + * EC_CODEC_SET_GAIN + * Value should be 0~43 for both channels. + */ + struct ec_param_codec_i2s_set_gain { + uint8_t left; + uint8_t right; + } __packed gain; + + /* + * EC_CODEC_I2S_ENABLE + * 1 to enable, 0 to disable. + */ + uint8_t i2s_enable; + + /* + * EC_CODEC_I2S_SET_COFNIG + * Value should be one of ec_i2s_config. + */ + uint8_t i2s_config; + + /* + * EC_CODEC_I2S_SET_TDM_CONFIG + * Value should be one of ec_i2s_config. + */ + struct ec_param_codec_i2s_tdm { + /* + * 0 to 496 + */ + int16_t ch0_delay; + /* + * -1 to 496 + */ + int16_t ch1_delay; + uint8_t adjacent_to_ch0; + uint8_t adjacent_to_ch1; + } __packed tdm_param; + + /* + * EC_CODEC_I2S_SET_BCLK + */ + uint32_t bclk; + }; +} __packed; + +/* + * For subcommand EC_CODEC_GET_GAIN. + */ +struct ec_response_codec_gain { + uint8_t left; + uint8_t right; +} __packed; + /*****************************************************************************/ /* System commands */ -- cgit v1.2.3 From 1690d8bb91e370ab772062b79bd434ce815c4729 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 4 Jan 2019 15:14:33 +0530 Subject: cpufreq: scpi/scmi: Fix freeing of dynamic OPPs Since the commit 2a4eb7358aba "OPP: Don't remove dynamic OPPs from _dev_pm_opp_remove_table()", dynamically created OPP aren't automatically removed anymore by dev_pm_opp_cpumask_remove_table(). This affects the scpi and scmi cpufreq drivers which no longer free OPPs on failures or on invocations of the policy->exit() callback. Create a generic OPP helper dev_pm_opp_remove_all_dynamic() which can be called from these drivers instead of dev_pm_opp_cpumask_remove_table(). In dev_pm_opp_remove_all_dynamic(), we need to make sure that the opp_list isn't getting accessed simultaneously from other parts of the OPP core while the helper is freeing dynamic OPPs, i.e. we can't drop the opp_table->lock while traversing through the OPP list. And to accomplish that, this patch also creates _opp_kref_release_unlocked() which can be called from this new helper with the opp_table lock already held. Cc: 4.20 # v4.20 Reported-by: Valentin Schneider Fixes: 2a4eb7358aba "OPP: Don't remove dynamic OPPs from _dev_pm_opp_remove_table()" Signed-off-by: Viresh Kumar Tested-by: Valentin Schneider Reviewed-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 0a2a88e5a383..b895f4e79868 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -108,6 +108,7 @@ void dev_pm_opp_put(struct dev_pm_opp *opp); int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt); void dev_pm_opp_remove(struct device *dev, unsigned long freq); +void dev_pm_opp_remove_all_dynamic(struct device *dev); int dev_pm_opp_enable(struct device *dev, unsigned long freq); @@ -217,6 +218,10 @@ static inline void dev_pm_opp_remove(struct device *dev, unsigned long freq) { } +static inline void dev_pm_opp_remove_all_dynamic(struct device *dev) +{ +} + static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq) { return 0; -- cgit v1.2.3 From 2d533a9287f2011632977e87ce2783f4c689c984 Mon Sep 17 00:00:00 2001 From: Denis Bolotin Date: Thu, 3 Jan 2019 12:02:39 +0200 Subject: qed: Fix qed_chain_set_prod() for PBL chains with non power of 2 page count In PBL chains with non power of 2 page count, the producer is not at the beginning of the chain when index is 0 after a wrap. Therefore, after the producer index wrap around, page index should be calculated more carefully. Signed-off-by: Denis Bolotin Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 59ddf9af909e..2dd0a9ed5b36 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -663,6 +663,37 @@ out: static inline void qed_chain_set_prod(struct qed_chain *p_chain, u32 prod_idx, void *p_prod_elem) { + if (p_chain->mode == QED_CHAIN_MODE_PBL) { + u32 cur_prod, page_mask, page_cnt, page_diff; + + cur_prod = is_chain_u16(p_chain) ? p_chain->u.chain16.prod_idx : + p_chain->u.chain32.prod_idx; + + /* Assume that number of elements in a page is power of 2 */ + page_mask = ~p_chain->elem_per_page_mask; + + /* Use "cur_prod - 1" and "prod_idx - 1" since producer index + * reaches the first element of next page before the page index + * is incremented. See qed_chain_produce(). + * Index wrap around is not a problem because the difference + * between current and given producer indices is always + * positive and lower than the chain's capacity. + */ + page_diff = (((cur_prod - 1) & page_mask) - + ((prod_idx - 1) & page_mask)) / + p_chain->elem_per_page; + + page_cnt = qed_chain_get_page_cnt(p_chain); + if (is_chain_u16(p_chain)) + p_chain->pbl.c.u16.prod_page_idx = + (p_chain->pbl.c.u16.prod_page_idx - + page_diff + page_cnt) % page_cnt; + else + p_chain->pbl.c.u32.prod_page_idx = + (p_chain->pbl.c.u32.prod_page_idx - + page_diff + page_cnt) % page_cnt; + } + if (is_chain_u16(p_chain)) p_chain->u.chain16.prod_idx = (u16) prod_idx; else -- cgit v1.2.3 From d3bd7413e0ca40b60cf60d4003246d067cafdeda Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 6 Jan 2019 00:54:37 +0100 Subject: bpf: fix sanitation of alu op with pointer / scalar type from different paths While 979d63d50c0c ("bpf: prevent out of bounds speculation on pointer arithmetic") took care of rejecting alu op on pointer when e.g. pointer came from two different map values with different map properties such as value size, Jann reported that a case was not covered yet when a given alu op is used in both "ptr_reg += reg" and "numeric_reg += reg" from different branches where we would incorrectly try to sanitize based on the pointer's limit. Catch this corner case and reject the program instead. Fixes: 979d63d50c0c ("bpf: prevent out of bounds speculation on pointer arithmetic") Reported-by: Jann Horn Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 27b74947cd2b..573cca00a0e6 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -172,6 +172,7 @@ struct bpf_verifier_state_list { #define BPF_ALU_SANITIZE_SRC 1U #define BPF_ALU_SANITIZE_DST 2U #define BPF_ALU_NEG_VALUE (1U << 2) +#define BPF_ALU_NON_POINTER (1U << 3) #define BPF_ALU_SANITIZE (BPF_ALU_SANITIZE_SRC | \ BPF_ALU_SANITIZE_DST) -- cgit v1.2.3 From 02669b17a433c242a40f01f14b691c9c9d1f8a13 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 5 Dec 2018 16:37:03 -0500 Subject: XArray: Turn xa_init_flags into a static inline A regular xa_init_flags() put all dynamically-initialised XArrays into the same locking class. That leads to lockdep believing that taking one XArray lock while holding another is a deadlock. It's possible to work around some of these situations with separate locking classes for irq/bh/regular XArrays, and SINGLE_DEPTH_NESTING, but that's ugly, and it doesn't work for all situations (where we have completely unrelated XArrays). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index f492e21c4aa2..4cf3cd128689 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -286,7 +286,6 @@ struct xarray { */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) -void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); @@ -303,6 +302,24 @@ unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); +/** + * xa_init_flags() - Initialise an empty XArray with flags. + * @xa: XArray. + * @flags: XA_FLAG values. + * + * If you need to initialise an XArray with special flags (eg you need + * to take the lock from interrupt context), use this function instead + * of xa_init(). + * + * Context: Any context. + */ +static inline void xa_init_flags(struct xarray *xa, gfp_t flags) +{ + spin_lock_init(&xa->xa_lock); + xa->xa_flags = flags; + xa->xa_head = NULL; +} + /** * xa_init() - Initialise an empty XArray. * @xa: XArray. -- cgit v1.2.3 From 4a31896c5b5a2715ecf4033426aa0a35066d92d6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 17 Dec 2018 14:45:36 -0500 Subject: XArray: Change xa_for_each iterator There were three problems with this API: 1. It took too many arguments; almost all users wanted to iterate over every element in the array rather than a subset. 2. It required that 'index' be initialised before use, and there's no realistic way to make GCC catch that. 3. 'index' and 'entry' were the opposite way round from every other member of the XArray APIs. So split it into three different APIs: xa_for_each(xa, index, entry) xa_for_each_start(xa, index, entry, start) xa_for_each_marked(xa, index, entry, filter) Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 78 +++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 65 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 4cf3cd128689..3d0ce8b267e3 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -359,20 +359,45 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) } /** - * xa_for_each() - Iterate over a portion of an XArray. + * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. + * @index: Index of @entry. * @entry: Entry retrieved from array. + * @start: First index to retrieve from array. + * + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. You may modify @index during the iteration if you + * want to skip or reprocess indices. It is safe to modify the array + * during the iteration. At the end of the iteration, @entry will be set + * to NULL and @index will have a value less than or equal to max. + * + * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have + * to handle your own locking with xas_for_each(), and if you have to unlock + * after each iteration, it will also end up being O(n.log(n)). + * xa_for_each_start() will spin if it hits a retry entry; if you intend to + * see retry entries, you should use the xas_for_each() iterator instead. + * The xas_for_each() iterator will expand into more inline code than + * xa_for_each_start(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each_start(xa, index, entry, start) \ + for (index = start, \ + entry = xa_find(xa, &index, ULONG_MAX, XA_PRESENT); \ + entry; \ + entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT)) + +/** + * xa_for_each() - Iterate over present entries in an XArray. + * @xa: XArray. * @index: Index of @entry. - * @max: Maximum index to retrieve from array. - * @filter: Selection criterion. + * @entry: Entry retrieved from array. * - * Initialise @index to the lowest index you want to retrieve from the - * array. During the iteration, @entry will have the value of the entry - * stored in @xa at @index. The iteration will skip all entries in the - * array which do not match @filter. You may modify @index during the - * iteration if you want to skip or reprocess indices. It is safe to modify - * the array during the iteration. At the end of the iteration, @entry will - * be set to NULL and @index will have a value less than or equal to max. + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. You may modify @index during the iteration if you want + * to skip or reprocess indices. It is safe to modify the array during the + * iteration. At the end of the iteration, @entry will be set to NULL and + * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock @@ -383,9 +408,36 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) * * Context: Any context. Takes and releases the RCU lock. */ -#define xa_for_each(xa, entry, index, max, filter) \ - for (entry = xa_find(xa, &index, max, filter); entry; \ - entry = xa_find_after(xa, &index, max, filter)) +#define xa_for_each(xa, index, entry) \ + xa_for_each_start(xa, index, entry, 0) + +/** + * xa_for_each_marked() - Iterate over marked entries in an XArray. + * @xa: XArray. + * @index: Index of @entry. + * @entry: Entry retrieved from array. + * @filter: Selection criterion. + * + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. The iteration will skip all entries in the array + * which do not match @filter. You may modify @index during the iteration + * if you want to skip or reprocess indices. It is safe to modify the array + * during the iteration. At the end of the iteration, @entry will be set to + * NULL and @index will have a value less than or equal to max. + * + * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). + * You have to handle your own locking with xas_for_each(), and if you have + * to unlock after each iteration, it will also end up being O(n.log(n)). + * xa_for_each_marked() will spin if it hits a retry entry; if you intend to + * see retry entries, you should use the xas_for_each_marked() iterator + * instead. The xas_for_each_marked() iterator will expand into more inline + * code than xa_for_each_marked(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each_marked(xa, index, entry, filter) \ + for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ + entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) -- cgit v1.2.3 From 76b4e52995654af260f14558e0e07b5b039ae202 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 28 Dec 2018 23:20:44 -0500 Subject: XArray: Permit storing 2-byte-aligned pointers On m68k, statically allocated pointers may only be two-byte aligned. This clashes with the XArray's method for tagging internal pointers. Permit storing these pointers in single slots (ie not in multislots). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 3d0ce8b267e3..435c25b29079 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -176,7 +176,8 @@ static inline bool xa_is_internal(const void *entry) */ static inline bool xa_is_err(const void *entry) { - return unlikely(xa_is_internal(entry)); + return unlikely(xa_is_internal(entry) && + (unsigned long)entry >= -((MAX_ERRNO << 2) + 2)); } /** @@ -1039,8 +1040,8 @@ static inline bool xa_is_sibling(const void *entry) (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } -#define XA_ZERO_ENTRY xa_mk_internal(256) -#define XA_RETRY_ENTRY xa_mk_internal(257) +#define XA_RETRY_ENTRY xa_mk_internal(256) +#define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? @@ -1064,6 +1065,17 @@ static inline bool xa_is_retry(const void *entry) return unlikely(entry == XA_RETRY_ENTRY); } +/** + * xa_is_advanced() - Is the entry only permitted for the advanced API? + * @entry: Entry to be stored in the XArray. + * + * Return: %true if the entry cannot be stored by the normal API. + */ +static inline bool xa_is_advanced(const void *entry) +{ + return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); +} + /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed -- cgit v1.2.3 From b0606fed6eece16a421034eca0bbea9a08b90e91 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 2 Jan 2019 13:57:03 -0500 Subject: XArray: Honour reserved entries in xa_insert xa_insert() should treat reserved entries as occupied, not as available. Also, it should treat requests to insert a NULL pointer as a request to reserve the slot. Add xa_insert_bh() and xa_insert_irq() for completeness. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 110 +++++++++++++++++++++++++++++++------------------ 1 file changed, 71 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 435c25b29079..12244aa98a69 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -463,39 +463,12 @@ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +int __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t); int __xa_reserve(struct xarray *, unsigned long index, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); -/** - * __xa_insert() - Store this entry in the XArray unless another entry is - * already present. - * @xa: XArray. - * @index: Index into array. - * @entry: New entry. - * @gfp: Memory allocation flags. - * - * If you would rather see the existing entry in the array, use __xa_cmpxchg(). - * This function is for users who don't care what the entry is, only that - * one is present. - * - * Context: Any context. Expects xa_lock to be held on entry. May - * release and reacquire xa_lock if the @gfp flags permit. - * Return: 0 if the store succeeded. -EEXIST if another entry was present. - * -ENOMEM if memory could not be allocated. - */ -static inline int __xa_insert(struct xarray *xa, unsigned long index, - void *entry, gfp_t gfp) -{ - void *curr = __xa_cmpxchg(xa, index, NULL, entry, gfp); - if (!curr) - return 0; - if (xa_is_err(curr)) - return xa_err(curr); - return -EEXIST; -} - /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. @@ -685,24 +658,83 @@ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, * @entry: New entry. * @gfp: Memory allocation flags. * - * If you would rather see the existing entry in the array, use xa_cmpxchg(). - * This function is for users who don't care what the entry is, only that - * one is present. + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. * - * Context: Process context. Takes and releases the xa_lock. - * May sleep if the @gfp flags permit. + * Context: Any context. Takes and releases the xa_lock. May sleep if + * the @gfp flags permit. * Return: 0 if the store succeeded. -EEXIST if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { - void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); - if (!curr) - return 0; - if (xa_is_err(curr)) - return xa_err(curr); - return -EEXIST; + int err; + + xa_lock(xa); + err = __xa_insert(xa, index, entry, gfp); + xa_unlock(xa); + + return err; +} + +/** + * xa_insert_bh() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert_bh(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + int err; + + xa_lock_bh(xa); + err = __xa_insert(xa, index, entry, gfp); + xa_unlock_bh(xa); + + return err; +} + +/** + * xa_insert_irq() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert_irq(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + int err; + + xa_lock_irq(xa); + err = __xa_insert(xa, index, entry, gfp); + xa_unlock_irq(xa); + + return err; } /** -- cgit v1.2.3 From 12c62b9d6ce57d37f3c03cc902c30498909fbc42 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 8 Oct 2018 13:15:43 +0200 Subject: reset: Improve reset controller kernel docs Grammar and indentation fixes. Signed-off-by: Geert Uytterhoeven [p.zabel@pengutronix.de: dropped "shared among" -> "shared between"] Signed-off-by: Philipp Zabel --- include/linux/reset.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index 29af6d6b2f4b..76690cf2e3e0 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -138,7 +138,7 @@ __must_check reset_control_get_exclusive(struct device *dev, const char *id) * * Returns a struct reset_control or IS_ERR() condition containing errno. * This function is intended for use with reset-controls which are shared - * between hardware-blocks. + * between hardware blocks. * * When a reset-control is shared, the behavior of reset_control_assert / * deassert is changed, the reset-core will keep track of a deassert_count @@ -187,7 +187,7 @@ static inline struct reset_control *of_reset_control_get_exclusive( } /** - * of_reset_control_get_shared - Lookup and obtain an shared reference + * of_reset_control_get_shared - Lookup and obtain a shared reference * to a reset controller. * @node: device to be reset by the controller * @id: reset line name @@ -229,7 +229,7 @@ static inline struct reset_control *of_reset_control_get_exclusive_by_index( } /** - * of_reset_control_get_shared_by_index - Lookup and obtain an shared + * of_reset_control_get_shared_by_index - Lookup and obtain a shared * reference to a reset controller * by index. * @node: device to be reset by the controller @@ -322,7 +322,7 @@ devm_reset_control_get_exclusive_by_index(struct device *dev, int index) /** * devm_reset_control_get_shared_by_index - resource managed - * reset_control_get_shared + * reset_control_get_shared * @dev: device to be reset by the controller * @index: index of the reset controller * -- cgit v1.2.3 From eaf91db0ab22dc2c664a9782f2f31dcbc410f3b5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 13 Nov 2018 13:47:44 +0100 Subject: reset: Add reset_control_get_count() Currently the reset core has internal support for counting the number of resets for a device described in DT. Generalize this to devices using lookup resets, and export it for public use. This will be used by generic drivers that need to be sure a device is controlled by a single, dedicated reset line (e.g. vfio-platform). Signed-off-by: Geert Uytterhoeven [p.zabel@pengutronix.de: fixed a typo in reset_control_get_count comment] Signed-off-by: Philipp Zabel --- include/linux/reset.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index 76690cf2e3e0..c1901b61ca30 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -32,6 +32,8 @@ struct reset_control *devm_reset_control_array_get(struct device *dev, struct reset_control *of_reset_control_array_get(struct device_node *np, bool shared, bool optional); +int reset_control_get_count(struct device *dev); + #else static inline int reset_control_reset(struct reset_control *rstc) @@ -97,6 +99,11 @@ of_reset_control_array_get(struct device_node *np, bool shared, bool optional) return optional ? NULL : ERR_PTR(-ENOTSUPP); } +static inline int reset_control_get_count(struct device *dev) +{ + return -ENOENT; +} + #endif /* CONFIG_RESET_CONTROLLER */ static inline int __must_check device_reset(struct device *dev) -- cgit v1.2.3 From 02b2f549d502b46e68b97ea1452fb8853b3327dd Mon Sep 17 00:00:00 2001 From: Dongsheng Yang Date: Tue, 18 Dec 2018 04:31:48 -0500 Subject: libceph: allow setting abort_on_full for rbd Introduce a new option abort_on_full, default to false. Then we can get -ENOSPC when the pool is full, or reaches quota. [ Don't show abort_on_full in /proc/mounts. ] Signed-off-by: Dongsheng Yang Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 6 ++++-- include/linux/ceph/osd_client.h | 1 - 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 68bb09c29ce8..a420c07904bc 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -35,6 +35,7 @@ #define CEPH_OPT_NOMSGAUTH (1<<4) /* don't require msg signing feat */ #define CEPH_OPT_TCP_NODELAY (1<<5) /* TCP_NODELAY on TCP sockets */ #define CEPH_OPT_NOMSGSIGN (1<<6) /* don't sign msgs */ +#define CEPH_OPT_ABORT_ON_FULL (1<<7) /* abort w/ ENOSPC when full */ #define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) @@ -53,7 +54,7 @@ struct ceph_options { unsigned long osd_request_timeout; /* jiffies */ /* - * any type that can't be simply compared or doesn't need need + * any type that can't be simply compared or doesn't need * to be compared should go beyond this point, * ceph_compare_options() should be updated accordingly */ @@ -281,7 +282,8 @@ extern struct ceph_options *ceph_parse_options(char *options, const char *dev_name, const char *dev_name_end, int (*parse_extra_token)(char *c, void *private), void *private); -int ceph_print_client_options(struct seq_file *m, struct ceph_client *client); +int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, + bool show_all); extern void ceph_destroy_options(struct ceph_options *opt); extern int ceph_compare_options(struct ceph_options *new_opt, struct ceph_client *client); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 7a2af5034278..2294f963dab7 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -354,7 +354,6 @@ struct ceph_osd_client { struct rb_root linger_map_checks; atomic_t num_requests; atomic_t num_homeless; - bool abort_on_full; /* abort w/ ENOSPC when full */ int abort_err; struct delayed_work timeout_work; struct delayed_work osds_timeout_work; -- cgit v1.2.3 From 750afb08ca71310fcf0c4e2cb1565c63b8235b60 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 4 Jan 2019 09:23:09 +0100 Subject: cross-tree: phase out dma_zalloc_coherent() We already need to zero out memory for dma_alloc_coherent(), as such using dma_zalloc_coherent() is superflous. Phase it out. This change was generated with the following Coccinelle SmPL patch: @ replace_dma_zalloc_coherent @ expression dev, size, data, handle, flags; @@ -dma_zalloc_coherent(dev, size, handle, flags) +dma_alloc_coherent(dev, size, handle, flags) Suggested-by: Christoph Hellwig Signed-off-by: Luis Chamberlain [hch: re-ran the script on the latest tree] Signed-off-by: Christoph Hellwig --- include/linux/pci-dma-compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index cb1adf0b78a9..249d4d7fbf18 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -24,7 +24,7 @@ static inline void * pci_zalloc_consistent(struct pci_dev *hwdev, size_t size, dma_addr_t *dma_handle) { - return dma_zalloc_coherent(&hwdev->dev, size, dma_handle, GFP_ATOMIC); + return dma_alloc_coherent(&hwdev->dev, size, dma_handle, GFP_ATOMIC); } static inline void -- cgit v1.2.3 From dfd32cad146e3624970eee9329e99d2c6ef751b3 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Wed, 19 Dec 2018 12:30:34 -0800 Subject: dma-mapping: remove dma_zalloc_coherent() dma_zalloc_coherent() is no longer needed as it has no users because dma_alloc_coherent() already zeroes out memory for us. The Coccinelle grammar rule that used to check for dma_alloc_coherent() + memset() is modified so that it just tells the user that the memset is not needed anymore. Suggested-by: Christoph Hellwig Signed-off-by: Luis Chamberlain Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index cef2127e1d70..f6ded992c183 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -717,15 +717,6 @@ static inline unsigned long dma_max_pfn(struct device *dev) } #endif -/* - * Please always use dma_alloc_coherent instead as it already zeroes the memory! - */ -static inline void *dma_zalloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) -{ - return dma_alloc_coherent(dev, size, dma_handle, flag); -} - static inline int dma_get_cache_alignment(void) { #ifdef ARCH_DMA_MINALIGN -- cgit v1.2.3 From 73444bc4d8f92e46a20cb6bd3342fc2ea75c6787 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 8 Jan 2019 15:23:39 -0800 Subject: mm, page_alloc: do not wake kswapd with zone lock held syzbot reported the following regression in the latest merge window and it was confirmed by Qian Cai that a similar bug was visible from a different context. ====================================================== WARNING: possible circular locking dependency detected 4.20.0+ #297 Not tainted ------------------------------------------------------ syz-executor0/8529 is trying to acquire lock: 000000005e7fb829 (&pgdat->kswapd_wait){....}, at: __wake_up_common_lock+0x19e/0x330 kernel/sched/wait.c:120 but task is already holding lock: 000000009bb7bae0 (&(&zone->lock)->rlock){-.-.}, at: spin_lock include/linux/spinlock.h:329 [inline] 000000009bb7bae0 (&(&zone->lock)->rlock){-.-.}, at: rmqueue_bulk mm/page_alloc.c:2548 [inline] 000000009bb7bae0 (&(&zone->lock)->rlock){-.-.}, at: __rmqueue_pcplist mm/page_alloc.c:3021 [inline] 000000009bb7bae0 (&(&zone->lock)->rlock){-.-.}, at: rmqueue_pcplist mm/page_alloc.c:3050 [inline] 000000009bb7bae0 (&(&zone->lock)->rlock){-.-.}, at: rmqueue mm/page_alloc.c:3072 [inline] 000000009bb7bae0 (&(&zone->lock)->rlock){-.-.}, at: get_page_from_freelist+0x1bae/0x52a0 mm/page_alloc.c:3491 It appears to be a false positive in that the only way the lock ordering should be inverted is if kswapd is waking itself and the wakeup allocates debugging objects which should already be allocated if it's kswapd doing the waking. Nevertheless, the possibility exists and so it's best to avoid the problem. This patch flags a zone as needing a kswapd using the, surprisingly, unused zone flag field. The flag is read without the lock held to do the wakeup. It's possible that the flag setting context is not the same as the flag clearing context or for small races to occur. However, each race possibility is harmless and there is no visible degredation in fragmentation treatment. While zone->flag could have continued to be unused, there is potential for moving some existing fields into the flags field instead. Particularly read-mostly ones like zone->initialized and zone->contiguous. Link: http://lkml.kernel.org/r/20190103225712.GJ31517@techsingularity.net Fixes: 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs") Reported-by: syzbot+93d94a001cfbce9e60e1@syzkaller.appspotmail.com Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Tested-by: Qian Cai Cc: Dmitry Vyukov Cc: Vlastimil Babka Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cc4a507d7ca4..842f9189537b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -520,6 +520,12 @@ enum pgdat_flags { PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; +enum zone_flags { + ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. + * Cleared when kswapd is woken. + */ +}; + static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); -- cgit v1.2.3 From 1cb95e072ede5e3d6a54eefd520db21b45985896 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Jan 2019 15:34:52 -0800 Subject: libnvdimm/dimm: Fix security capability detection for non-Intel NVDIMMs Kees reports a crash with the following signature... RIP: 0010:nvdimm_visible+0x79/0x80 [..] Call Trace: internal_create_group+0xf4/0x380 sysfs_create_groups+0x46/0xb0 device_add+0x331/0x680 nd_async_device_register+0x15/0x60 async_run_entry_fn+0x38/0x100 ...when starting a QEMU environment with "label-less" DIMM. Without labels QEMU does not publish any DSM methods. Without defined methods the NVDIMM_FAMILY type is not established and the nfit driver will skip registering security operations. In that case the security state should be initialized to a negative value in __nvdimm_create() and nvdimm_visible() should skip interrogating the specific ops. However, since 'enum nvdimm_security_state' was only defined to contain positive values the "if (nvdimm->sec.state < 0)" check always fails. Define a negative error state to allow negative state values to be handled as expected. Fixes: f2989396553a ("acpi/nfit, libnvdimm: Introduce nvdimm_security_ops") Reviewed-by: Dave Jiang Reported-by: Kees Cook Tested-by: Kees Cook Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 5440f11b0907..7315977b64da 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -160,6 +160,7 @@ static inline struct nd_blk_region_desc *to_blk_region_desc( } enum nvdimm_security_state { + NVDIMM_SECURITY_ERROR = -1, NVDIMM_SECURITY_DISABLED, NVDIMM_SECURITY_UNLOCKED, NVDIMM_SECURITY_LOCKED, -- cgit v1.2.3 From 90802938f7e88045ace123e105e22e8c3e7f9c7e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 8 Jan 2019 17:38:29 +0100 Subject: x86/cache: Rename config option to CONFIG_X86_RESCTRL CONFIG_RESCTRL is too generic. The final goal is to have a generic option called like this which is selected by the arch-specific ones CONFIG_X86_RESCTRL and CONFIG_ARM64_RESCTRL. The generic one will cover the resctrl filesystem and other generic and shared bits of functionality. Signed-off-by: Borislav Petkov Suggested-by: Ingo Molnar Requested-by: Linus Torvalds Cc: Babu Moger Cc: Fenghua Yu Cc: James Morse Cc: Reinette Chatre Cc: Tony Luck Cc: x86@kernel.org Link: http://lkml.kernel.org/r/20190108171401.GC12235@zn.tnic --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 89541d248893..224666226e87 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -995,7 +995,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_RESCTRL +#ifdef CONFIG_X86_RESCTRL u32 closid; u32 rmid; #endif -- cgit v1.2.3 From e4f358916d528d479c3c12bd2fd03f2d5a576380 Mon Sep 17 00:00:00 2001 From: WANG Chao Date: Tue, 11 Dec 2018 00:37:25 +0800 Subject: x86, modpost: Replace last remnants of RETPOLINE with CONFIG_RETPOLINE Commit 4cd24de3a098 ("x86/retpoline: Make CONFIG_RETPOLINE depend on compiler support") replaced the RETPOLINE define with CONFIG_RETPOLINE checks. Remove the remaining pieces. [ bp: Massage commit message. ] Fixes: 4cd24de3a098 ("x86/retpoline: Make CONFIG_RETPOLINE depend on compiler support") Signed-off-by: WANG Chao Signed-off-by: Borislav Petkov Reviewed-by: Zhenzhong Duan Reviewed-by: Masahiro Yamada Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Daniel Borkmann Cc: David Woodhouse Cc: Geert Uytterhoeven Cc: Jessica Yu Cc: Jiri Kosina Cc: Kees Cook Cc: Konrad Rzeszutek Wilk Cc: Luc Van Oostenryck Cc: Michal Marek Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Tim Chen Cc: Vasily Gorbik Cc: linux-kbuild@vger.kernel.org Cc: srinivas.eeda@oracle.com Cc: stable Cc: x86-ml Link: https://lkml.kernel.org/r/20181210163725.95977-1-chao.wang@ucloud.cn --- include/linux/compiler-gcc.h | 2 +- include/linux/module.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 5776da43da97..dd8268f5f5f0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -68,7 +68,7 @@ */ #define uninitialized_var(x) x = x -#ifdef RETPOLINE +#ifdef CONFIG_RETPOLINE #define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif diff --git a/include/linux/module.h b/include/linux/module.h index 9a21fe3509af..8fa38d3e7538 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -828,7 +828,7 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr, static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ -#ifdef RETPOLINE +#ifdef CONFIG_RETPOLINE extern bool retpoline_module_ok(bool has_retpoline); #else static inline bool retpoline_module_ok(bool has_retpoline) -- cgit v1.2.3 From 3e2ffd655cc6a694608d997738989ff5572a8266 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 2 Jan 2019 15:57:49 -0500 Subject: include/linux/compiler*.h: fix OPTIMIZER_HIDE_VAR Since commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") clang no longer reuses the OPTIMIZER_HIDE_VAR macro from compiler-gcc - instead it gets the version in include/linux/compiler.h. Unfortunately that version doesn't actually prevent compiler from optimizing out the variable. Fix up by moving the macro out from compiler-gcc.h to compiler.h. Compilers without incline asm support will keep working since it's protected by an ifdef. Also fix up comments to match reality since we are no longer overriding any macros. Build-tested with gcc and clang. Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Cc: Eli Friedman Cc: Joe Perches Cc: Linus Torvalds Reviewed-by: Nick Desaulniers Signed-off-by: Michael S. Tsirkin Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 5 ++--- include/linux/compiler-gcc.h | 4 ---- include/linux/compiler-intel.h | 4 +--- include/linux/compiler.h | 4 +++- 4 files changed, 6 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 39f668d5066b..333a6695a918 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -3,9 +3,8 @@ #error "Please don't include directly, include instead." #endif -/* Some compiler specific definitions are overwritten here - * for Clang compiler - */ +/* Compiler specific definitions for Clang compiler */ + #define uninitialized_var(x) x = *(&(x)) /* same as gcc, this was present in clang-2.6 so we can assume it works diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 5776da43da97..7b834e37d0c0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -58,10 +58,6 @@ (typeof(ptr)) (__ptr + (off)); \ }) -/* Make the optimizer believe the variable can be manipulated arbitrarily. */ -#define OPTIMIZER_HIDE_VAR(var) \ - __asm__ ("" : "=r" (var) : "0" (var)) - /* * A trick to suppress uninitialized variable warning without generating any * code diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 517bd14e1222..b17f3cd18334 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -5,9 +5,7 @@ #ifdef __ECC -/* Some compiler specific definitions are overwritten here - * for Intel ECC compiler - */ +/* Compiler specific definitions for Intel ECC compiler */ #include diff --git a/include/linux/compiler.h b/include/linux/compiler.h index fc5004a4b07d..445348facea9 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -161,7 +161,9 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif #ifndef OPTIMIZER_HIDE_VAR -#define OPTIMIZER_HIDE_VAR(var) barrier() +/* Make the optimizer believe the variable can be manipulated arbitrarily. */ +#define OPTIMIZER_HIDE_VAR(var) \ + __asm__ ("" : "=r" (var) : "0" (var)) #endif /* Not-quite-unique ID. */ -- cgit v1.2.3 From ba50bf1ce9a51fc97db58b96d01306aa70bc3979 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 17 Dec 2018 20:16:09 +0000 Subject: Drivers: hv: vmbus: Check for ring when getting debug info fc96df16a1ce is good and can already fix the "return stack garbage" issue, but let's also improve hv_ringbuffer_get_debuginfo(), which would silently return stack garbage, if people forget to check channel->state or ring_info->ring_buffer, when using the function in the future. Having an error check in the function would eliminate the potential risk. Add a Fixes tag to indicate the patch depdendency. Fixes: fc96df16a1ce ("Drivers: hv: vmbus: Return -EINVAL for the sys files for unopened channels") Cc: stable@vger.kernel.org Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Stephen Hemminger Signed-off-by: Dexuan Cui Signed-off-by: Sasha Levin --- include/linux/hyperv.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f0885cc01db6..dcb6977afce9 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1159,8 +1159,9 @@ struct hv_ring_buffer_debug_info { u32 bytes_avail_towrite; }; -void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, - struct hv_ring_buffer_debug_info *debug_info); + +int hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, + struct hv_ring_buffer_debug_info *debug_info); /* Vmbus interface */ #define vmbus_driver_register(driver) \ -- cgit v1.2.3 From 321c46b91550adc03054125fa7a1639390608e1a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 3 Jan 2019 08:34:17 +0100 Subject: MIPS: BCM47XX: Setup struct device for the SoC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So far we never had any device registered for the SoC. This resulted in some small issues that we kept ignoring like: 1) Not working GPIOLIB_IRQCHIP (gpiochip_irqchip_add_key() failing) 2) Lack of proper tree in the /sys/devices/ 3) mips_dma_alloc_coherent() silently handling empty coherent_dma_mask Kernel 4.19 came with a lot of DMA changes and caused a regression on bcm47xx. Starting with the commit f8c55dc6e828 ("MIPS: use generic dma noncoherent ops for simple noncoherent platforms") DMA coherent allocations just fail. Example: [ 1.114914] bgmac_bcma bcma0:2: Allocation of TX ring 0x200 failed [ 1.121215] bgmac_bcma bcma0:2: Unable to alloc memory for DMA [ 1.127626] bgmac_bcma: probe of bcma0:2 failed with error -12 [ 1.133838] bgmac_bcma: Broadcom 47xx GBit MAC driver loaded The bgmac driver also triggers a WARNING: [ 0.959486] ------------[ cut here ]------------ [ 0.964387] WARNING: CPU: 0 PID: 1 at ./include/linux/dma-mapping.h:516 bgmac_enet_probe+0x1b4/0x5c4 [ 0.973751] Modules linked in: [ 0.976913] CPU: 0 PID: 1 Comm: swapper Not tainted 4.19.9 #0 [ 0.982750] Stack : 804a0000 804597c4 00000000 00000000 80458fd8 8381bc2c 838282d4 80481a47 [ 0.991367] 8042e3ec 00000001 804d38f0 00000204 83980000 00000065 8381bbe0 6f55b24f [ 0.999975] 00000000 00000000 80520000 00002018 00000000 00000075 00000007 00000000 [ 1.008583] 00000000 80480000 000ee811 00000000 00000000 00000000 80432c00 80248db8 [ 1.017196] 00000009 00000204 83980000 803ad7b0 00000000 801feeec 00000000 804d0000 [ 1.025804] ... [ 1.028325] Call Trace: [ 1.030875] [<8000aef8>] show_stack+0x58/0x100 [ 1.035513] [<8001f8b4>] __warn+0xe4/0x118 [ 1.039708] [<8001f9a4>] warn_slowpath_null+0x48/0x64 [ 1.044935] [<80248db8>] bgmac_enet_probe+0x1b4/0x5c4 [ 1.050101] [<802498e0>] bgmac_probe+0x558/0x590 [ 1.054906] [<80252fd0>] bcma_device_probe+0x38/0x70 [ 1.060017] [<8020e1e8>] really_probe+0x170/0x2e8 [ 1.064891] [<8020e714>] __driver_attach+0xa4/0xec [ 1.069784] [<8020c1e0>] bus_for_each_dev+0x58/0xb0 [ 1.074833] [<8020d590>] bus_add_driver+0xf8/0x218 [ 1.079731] [<8020ef24>] driver_register+0xcc/0x11c [ 1.084804] [<804b54cc>] bgmac_init+0x1c/0x44 [ 1.089258] [<8000121c>] do_one_initcall+0x7c/0x1a0 [ 1.094343] [<804a1d34>] kernel_init_freeable+0x150/0x218 [ 1.099886] [<803a082c>] kernel_init+0x10/0x104 [ 1.104583] [<80005878>] ret_from_kernel_thread+0x14/0x1c [ 1.110107] ---[ end trace f441c0d873d1fb5b ]--- This patch setups a "struct device" (and passes it to the bcma) which allows fixing all the mentioned problems. It'll also require a tiny bcma patch which will follow through the wireless tree & its maintainer. Fixes: f8c55dc6e828 ("MIPS: use generic dma noncoherent ops for simple noncoherent platforms") Signed-off-by: Rafał Miłecki Signed-off-by: Paul Burton Acked-by: Hauke Mehrtens Cc: Christoph Hellwig Cc: Linus Walleij Cc: linux-wireless@vger.kernel.org Cc: Ralf Baechle Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v4.19+ --- include/linux/bcma/bcma_soc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_soc.h b/include/linux/bcma/bcma_soc.h index 7cca5f859a90..f3c43519baa7 100644 --- a/include/linux/bcma/bcma_soc.h +++ b/include/linux/bcma/bcma_soc.h @@ -6,6 +6,7 @@ struct bcma_soc { struct bcma_bus bus; + struct device *dev; }; int __init bcma_host_soc_register(struct bcma_soc *soc); -- cgit v1.2.3 From ee46967fc6e74d412fe1ec15f77fdb8624bde2b0 Mon Sep 17 00:00:00 2001 From: Peter Hutterer Date: Wed, 9 Jan 2019 13:50:18 +1000 Subject: HID: core: replace the collection tree pointers with indices Previously, the pointer to the parent collection was stored. If a device exceeds 16 collections (HID_DEFAULT_NUM_COLLECTIONS), the array to store the collections is reallocated, the pointer to the parent collection becomes invalid. Replace the pointers with an index-based lookup into the collections array. Fixes: c53431eb696f3c ("HID: core: store the collections as a basic tree") Reported-by: Pandruvada, Srinivas Signed-off-by: Peter Hutterer Tested-by: Kyle Pelton Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index d99287327ef2..992bbb7196df 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -430,7 +430,7 @@ struct hid_local { */ struct hid_collection { - struct hid_collection *parent; + int parent_idx; /* device->collection */ unsigned type; unsigned usage; unsigned level; @@ -658,7 +658,7 @@ struct hid_parser { unsigned int *collection_stack; unsigned int collection_stack_ptr; unsigned int collection_stack_size; - struct hid_collection *active_collection; + int active_collection_idx; /* device->collection */ struct hid_device *device; unsigned int scan_flags; }; -- cgit v1.2.3 From 8ce5f84157530ffa64b3e0acf00b9261f41c8da8 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 11 Dec 2018 14:31:05 -0600 Subject: of: Remove struct device_node.type pointer Now that all users of device_node.type pointer have been removed in favor of accessor functions, we can remove it. Cc: Frank Rowand Cc: devicetree@vger.kernel.org Signed-off-by: Rob Herring --- include/linux/of.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index fe472e5195a9..e240992e5cb6 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -50,7 +50,6 @@ struct of_irq_controller; struct device_node { const char *name; - const char *type; phandle phandle; const char *full_name; struct fwnode_handle fwnode; -- cgit v1.2.3 From 2076607a20bd4dfba699185616cbbbce06d3fa59 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Wed, 26 Dec 2018 10:06:19 -0200 Subject: qcom-scm: Include header Since commit e6f6d63ed14c ("drm/msm: add headless gpu device for imx5") the DRM_MSM symbol can be selected by SOC_IMX5 causing the following error when building imx_v6_v7_defconfig: In file included from ../drivers/gpu/drm/msm/adreno/a5xx_gpu.c:17:0: ../include/linux/qcom_scm.h: In function 'qcom_scm_set_cold_boot_addr': ../include/linux/qcom_scm.h:73:10: error: 'ENODEV' undeclared (first use in this function) return -ENODEV; Include the header file to fix this problem. Reported-by: kernelci.org bot Fixes: e6f6d63ed14c ("drm/msm: add headless gpu device for imx5") Signed-off-by: Fabio Estevam Reviewed-by: Bjorn Andersson Tested-by: Guenter Roeck Signed-off-by: Andy Gross --- include/linux/qcom_scm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 1637385bcc17..d0aecc04c54b 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -13,6 +13,7 @@ #ifndef __QCOM_SCM_H #define __QCOM_SCM_H +#include #include #include -- cgit v1.2.3 From 73ab1cb2de9e3efe7f818d5453de271e5371df1d Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Wed, 9 Jan 2019 02:23:56 +0900 Subject: umh: add exit routine for UMH process A UMH process which is created by the fork_usermode_blob() such as bpfilter needs to release members of the umh_info when process is terminated. But the do_exit() does not release members of the umh_info. hence module which uses UMH needs own code to detect whether UMH process is terminated or not. But this implementation needs extra code for checking the status of UMH process. it eventually makes the code more complex. The new PF_UMH flag is added and it is used to identify UMH processes. The exit_umh() does not release members of the umh_info. Hence umh_info->cleanup callback should release both members of the umh_info and the private data. Suggested-by: David S. Miller Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/sched.h | 9 +++++++++ include/linux/umh.h | 2 ++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 89541d248893..e35e35b9fc48 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1406,6 +1406,7 @@ extern struct pid *cad_pid; #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ +#define PF_UMH 0x02000000 /* I'm an Usermodehelper process */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ @@ -1904,6 +1905,14 @@ static inline void rseq_execve(struct task_struct *t) #endif +void __exit_umh(struct task_struct *tsk); + +static inline void exit_umh(struct task_struct *tsk) +{ + if (unlikely(tsk->flags & PF_UMH)) + __exit_umh(tsk); +} + #ifdef CONFIG_DEBUG_RSEQ void rseq_syscall(struct pt_regs *regs); diff --git a/include/linux/umh.h b/include/linux/umh.h index 235f51b62c71..0c08de356d0d 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -47,6 +47,8 @@ struct umh_info { const char *cmdline; struct file *pipe_to_umh; struct file *pipe_from_umh; + struct list_head list; + void (*cleanup)(struct umh_info *info); pid_t pid; }; int fork_usermode_blob(void *data, size_t len, struct umh_info *info); -- cgit v1.2.3 From 5b4cb650e569db2e6a09d2fa0ef8eb789a0ac5d8 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Wed, 9 Jan 2019 02:24:34 +0900 Subject: net: bpfilter: use cleanup callback to release umh_info Now, UMH process is killed, do_exit() calls the umh_info->cleanup callback to release members of the umh_info. This patch makes bpfilter_umh's cleanup routine to use the umh_info->cleanup callback. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/bpfilter.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index f02cee0225d4..70ffeed280e9 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -3,13 +3,18 @@ #define _LINUX_BPFILTER_H #include +#include struct sock; int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen); int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen); -extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname, - char __user *optval, - unsigned int optlen, bool is_set); +struct bpfilter_umh_ops { + struct umh_info info; + int (*sockopt)(struct sock *sk, int optname, + char __user *optval, + unsigned int optlen, bool is_set); +}; +extern struct bpfilter_umh_ops bpfilter_ops; #endif -- cgit v1.2.3 From 61fbf5933d42b02f552123af5a87a06335a3b4db Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Wed, 9 Jan 2019 02:24:53 +0900 Subject: net: bpfilter: restart bpfilter_umh when error occurred The bpfilter_umh will be stopped via __stop_umh() when the bpfilter error occurred. The bpfilter_umh() couldn't start again because there is no restart routine. The section of the bpfilter_umh_{start/end} is no longer .init.rodata because these area should be reused in the restart routine. hence the section name is changed to .bpfilter_umh. The bpfilter_ops->start() is restart callback. it will be called when bpfilter_umh is stopped. The stop bit means bpfilter_umh is stopped. this bit is set by both start and stop routine. Before this patch, Test commands: $ iptables -vnL $ kill -9 $ iptables -vnL [ 480.045136] bpfilter: write fail -32 $ iptables -vnL All iptables commands will fail. After this patch, Test commands: $ iptables -vnL $ kill -9 $ iptables -vnL $ iptables -vnL Now, all iptables commands will work. Fixes: d2ba09c17a06 ("net: add skeleton of bpfilter kernel module") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/bpfilter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index 70ffeed280e9..8ebcbdd70bdc 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -15,6 +15,8 @@ struct bpfilter_umh_ops { int (*sockopt)(struct sock *sk, int optname, char __user *optval, unsigned int optlen, bool is_set); + int (*start)(void); + bool stop; }; extern struct bpfilter_umh_ops bpfilter_ops; #endif -- cgit v1.2.3 From 71a8508402b570127d6500c1ad456bbd33ccf187 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Wed, 9 Jan 2019 02:25:10 +0900 Subject: net: bpfilter: disallow to remove bpfilter module while being used The bpfilter.ko module can be removed while functions of the bpfilter.ko are executing. so panic can occurred. in order to protect that, locks can be used. a bpfilter_lock protects routines in the __bpfilter_process_sockopt() but it's not enough because __exit routine can be executed concurrently. Now, the bpfilter_umh can not run in parallel. So, the module do not removed while it's being used and it do not double-create UMH process. The members of the umh_info and the bpfilter_umh_ops are protected by the bpfilter_umh_ops.lock. test commands: while : do iptables -I FORWARD -m string --string ap --algo kmp & modprobe -rv bpfilter & done splat looks like: [ 298.623435] BUG: unable to handle kernel paging request at fffffbfff807440b [ 298.628512] #PF error: [normal kernel read fault] [ 298.633018] PGD 124327067 P4D 124327067 PUD 11c1a3067 PMD 119eb2067 PTE 0 [ 298.638859] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI [ 298.638859] CPU: 0 PID: 2997 Comm: iptables Not tainted 4.20.0+ #154 [ 298.638859] RIP: 0010:__mutex_lock+0x6b9/0x16a0 [ 298.638859] Code: c0 00 00 e8 89 82 ff ff 80 bd 8f fc ff ff 00 0f 85 d9 05 00 00 48 8b 85 80 fc ff ff 48 bf 00 00 00 00 00 fc ff df 48 c1 e8 03 <80> 3c 38 00 0f 85 1d 0e 00 00 48 8b 85 c8 fc ff ff 49 39 47 58 c6 [ 298.638859] RSP: 0018:ffff88810e7777a0 EFLAGS: 00010202 [ 298.638859] RAX: 1ffffffff807440b RBX: ffff888111bd4d80 RCX: 0000000000000000 [ 298.638859] RDX: 1ffff110235ff806 RSI: ffff888111bd5538 RDI: dffffc0000000000 [ 298.638859] RBP: ffff88810e777b30 R08: 0000000080000002 R09: 0000000000000000 [ 298.638859] R10: 0000000000000000 R11: 0000000000000000 R12: fffffbfff168a42c [ 298.638859] R13: ffff888111bd4d80 R14: ffff8881040e9a05 R15: ffffffffc03a2000 [ 298.638859] FS: 00007f39e3758700(0000) GS:ffff88811ae00000(0000) knlGS:0000000000000000 [ 298.638859] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 298.638859] CR2: fffffbfff807440b CR3: 000000011243e000 CR4: 00000000001006f0 [ 298.638859] Call Trace: [ 298.638859] ? mutex_lock_io_nested+0x1560/0x1560 [ 298.638859] ? kasan_kmalloc+0xa0/0xd0 [ 298.638859] ? kmem_cache_alloc+0x1c2/0x260 [ 298.638859] ? __alloc_file+0x92/0x3c0 [ 298.638859] ? alloc_empty_file+0x43/0x120 [ 298.638859] ? alloc_file_pseudo+0x220/0x330 [ 298.638859] ? sock_alloc_file+0x39/0x160 [ 298.638859] ? __sys_socket+0x113/0x1d0 [ 298.638859] ? __x64_sys_socket+0x6f/0xb0 [ 298.638859] ? do_syscall_64+0x138/0x560 [ 298.638859] ? entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 298.638859] ? __alloc_file+0x92/0x3c0 [ 298.638859] ? init_object+0x6b/0x80 [ 298.638859] ? cyc2ns_read_end+0x10/0x10 [ 298.638859] ? cyc2ns_read_end+0x10/0x10 [ 298.638859] ? hlock_class+0x140/0x140 [ 298.638859] ? sched_clock_local+0xd4/0x140 [ 298.638859] ? sched_clock_local+0xd4/0x140 [ 298.638859] ? check_flags.part.37+0x440/0x440 [ 298.638859] ? __lock_acquire+0x4f90/0x4f90 [ 298.638859] ? set_rq_offline.part.89+0x140/0x140 [ ... ] Fixes: d2ba09c17a06 ("net: add skeleton of bpfilter kernel module") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/bpfilter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index 8ebcbdd70bdc..d815622cd31e 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -12,6 +12,8 @@ int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen); struct bpfilter_umh_ops { struct umh_info info; + /* since ip_getsockopt() can run in parallel, serialize access to umh */ + struct mutex lock; int (*sockopt)(struct sock *sk, int optname, char __user *optval, unsigned int optlen, bool is_set); -- cgit v1.2.3 From ee17e5d6201c66492a0e8053190fca2ed2b8457d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 12 Jan 2019 11:48:20 -0600 Subject: signal: Make siginmask safe when passed a signal of 0 Eric Biggers reported: > The following commit, which went into v4.20, introduced undefined behavior when > sys_rt_sigqueueinfo() is called with sig=0: > > commit 4ce5f9c9e7546915c559ffae594e6d73f918db00 > Author: Eric W. Biederman > Date: Tue Sep 25 12:59:31 2018 +0200 > > signal: Use a smaller struct siginfo in the kernel > > In sig_specific_sicodes(), used from known_siginfo_layout(), the expression > '1ULL << ((sig)-1)' is undefined as it evaluates to 1ULL << 4294967295. > > Reproducer: > > #include > #include > #include > > int main(void) > { > siginfo_t si = { .si_code = 1 }; > syscall(__NR_rt_sigqueueinfo, 0, 0, &si); > } > > UBSAN report for v5.0-rc1: > > UBSAN: Undefined behaviour in kernel/signal.c:2946:7 > shift exponent 4294967295 is too large for 64-bit type 'long unsigned int' > CPU: 2 PID: 346 Comm: syz_signal Not tainted 5.0.0-rc1 #25 > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 > Call Trace: > __dump_stack lib/dump_stack.c:77 [inline] > dump_stack+0x70/0xa5 lib/dump_stack.c:113 > ubsan_epilogue+0xd/0x40 lib/ubsan.c:159 > __ubsan_handle_shift_out_of_bounds+0x12c/0x170 lib/ubsan.c:425 > known_siginfo_layout+0xae/0xe0 kernel/signal.c:2946 > post_copy_siginfo_from_user kernel/signal.c:3009 [inline] > __copy_siginfo_from_user+0x35/0x60 kernel/signal.c:3035 > __do_sys_rt_sigqueueinfo kernel/signal.c:3553 [inline] > __se_sys_rt_sigqueueinfo kernel/signal.c:3549 [inline] > __x64_sys_rt_sigqueueinfo+0x31/0x70 kernel/signal.c:3549 > do_syscall_64+0x4c/0x1b0 arch/x86/entry/common.c:290 > entry_SYSCALL_64_after_hwframe+0x49/0xbe > RIP: 0033:0x433639 > Code: c4 18 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b 27 00 00 c3 66 2e 0f 1f 84 00 00 00 00 > RSP: 002b:00007fffcb289fc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000081 > RAX: ffffffffffffffda RBX: 00000000004002e0 RCX: 0000000000433639 > RDX: 00007fffcb289fd0 RSI: 0000000000000000 RDI: 0000000000000000 > RBP: 00000000006b2018 R08: 000000000000004d R09: 0000000000000000 > R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000401560 > R13: 00000000004015f0 R14: 0000000000000000 R15: 0000000000000000 I have looked at the other callers of siginmask and they all appear to in locations where sig can not be zero. I have looked at the code generation of adding an extra test against zero and gcc was able with a simple decrement instruction to combine the two tests together. So the at most adding this test cost a single cpu cycle. In practice that decrement instruction was already present as part of the mask comparison, so the only change was when the instruction was executed. So given that it is cheap, and obviously correct to update siginmask to verify the signal is not zero. Fix this issue there to avoid any future problems. Reported-by: Eric Biggers Fixes: 4ce5f9c9e754 ("signal: Use a smaller struct siginfo in the kernel") Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index cc7e2c1cd444..9702016734b1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -392,7 +392,7 @@ extern bool unhandled_signal(struct task_struct *tsk, int sig); #endif #define siginmask(sig, mask) \ - ((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) + ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) -- cgit v1.2.3 From e1706720408e72fb883f6b151c2b3b23d8e7e5b2 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Sat, 12 Jan 2019 17:29:09 -0800 Subject: phy: fix build breakage: add PHY_MODE_SATA Commit 49e54187ae0b ("ata: libahci_platform: comply to PHY framework") uses the PHY_MODE_SATA, but that enum had not yet been added. This caused a build failure for me, with today's linux.git. Also, there is a potentially conflicting (mis-named) PHY_MODE_SATA, hiding in the Marvell Berlin SATA PHY driver. Fix the build by: 1) Renaming Marvell's defined value to a more scoped name, in order to avoid any potential conflicts: PHY_BERLIN_MODE_SATA. 2) Adding the missing enum, which was going to be added anyway as part of [1]. [1] https://lkml.kernel.org/r/20190108163124.6409-3-miquel.raynal@bootlin.com Fixes: 49e54187ae0b ("ata: libahci_platform: comply to PHY framework") Signed-off-by: John Hubbard Acked-by: Jens Axboe Acked-by: Olof Johansson Cc: Grzegorz Jaszczyk Cc: Miquel Raynal Cc: Hans de Goede Signed-off-by: Linus Torvalds --- include/linux/phy/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index e8e118d70fd7..3f350e2749fe 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -42,6 +42,7 @@ enum phy_mode { PHY_MODE_PCIE, PHY_MODE_ETHERNET, PHY_MODE_MIPI_DPHY, + PHY_MODE_SATA }; /** -- cgit v1.2.3 From 19ba9ecf24189bd74d070aa1b1c4bcb9fe4ae849 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Mon, 14 Jan 2019 11:40:47 +0300 Subject: XArray: Fix typo in comment Seems copy and paste typo, not a big deal but still for consistency sake better to fix. Signed-off-by: Cyrill Gorcunov Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 12244aa98a69..7da665f5cb20 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -496,7 +496,7 @@ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, } /** - * xa_store_irq() - Erase this entry from the XArray. + * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. -- cgit v1.2.3 From b89a07c4373b27321b1f6d4b4fdc369fd45ef79d Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 3 Jan 2019 17:08:03 +0100 Subject: virtio: fix virtio_config_ops description - get_features has returned 64 bits since commit d025477368792 ("virtio: add support for 64 bit features.") - properly mark all optional callbacks Signed-off-by: Cornelia Huck Signed-off-by: Michael S. Tsirkin Reviewed-by: Halil Pasic --- include/linux/virtio_config.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 32baf8e26735..7087ef946ba7 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -22,7 +22,7 @@ struct irq_affinity; * offset: the offset of the configuration field * buf: the buffer to read the field value from. * len: the length of the buffer - * @generation: config generation counter + * @generation: config generation counter (optional) * vdev: the virtio_device * Returns the config generation counter * @get_status: read the status byte @@ -48,17 +48,17 @@ struct irq_affinity; * @del_vqs: free virtqueues found by find_vqs(). * @get_features: get the array of feature bits for this device. * vdev: the virtio_device - * Returns the first 32 feature bits (all we currently need). + * Returns the first 64 feature bits (all we currently need). * @finalize_features: confirm what device features we'll be using. * vdev: the virtio_device * This gives the final feature bits for the device: it can change * the dev->feature bits if it wants. * Returns 0 on success or error status - * @bus_name: return the bus name associated with the device + * @bus_name: return the bus name associated with the device (optional) * vdev: the virtio_device * This returns a pointer to the bus name a la pci_name from which * the caller can then copy. - * @set_vq_affinity: set the affinity for a virtqueue. + * @set_vq_affinity: set the affinity for a virtqueue (optional). * @get_vq_affinity: get the affinity for a virtqueue (optional). */ typedef void vq_callback_t(struct virtqueue *); -- cgit v1.2.3 From d1c1dad89e7a8be2cfdc7b92deca2c8048f0d263 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 3 Jan 2019 17:08:04 +0100 Subject: virtio: document virtio_config_ops restrictions Some transports (e.g. virtio-ccw) implement virtio operations that seem to be a simple read/write as something more involved that cannot be done from an atomic context. Give at least a hint about that. Signed-off-by: Cornelia Huck Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 7087ef946ba7..987b6491b946 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -12,6 +12,11 @@ struct irq_affinity; /** * virtio_config_ops - operations for configuring a virtio device + * Note: Do not assume that a transport implements all of the operations + * getting/setting a value as a simple read/write! Generally speaking, + * any of @get/@set, @get_status/@set_status, or @get_features/ + * @finalize_features are NOT safe to be called from an atomic + * context. * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field -- cgit v1.2.3 From 1950f462916edc9581168ca8d5882a8101e8bbcf Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 14 Jan 2019 08:19:22 +0100 Subject: HID: core: simplify active collection tracking Manually tracking an active collection to set collection parents is not necessary, we just have to look one step back into the collection stack to find the correct parent. Signed-off-by: Philipp Zabel Reviewed-by: Peter Hutterer Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 992bbb7196df..f9707d1dcb58 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -658,7 +658,6 @@ struct hid_parser { unsigned int *collection_stack; unsigned int collection_stack_ptr; unsigned int collection_stack_size; - int active_collection_idx; /* device->collection */ struct hid_device *device; unsigned int scan_flags; }; -- cgit v1.2.3 From 890d14d2d4b57ff5a149309da3ed36c8a529987f Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Wed, 16 Jan 2019 17:42:35 +0100 Subject: fbdev: fbmem: convert CONFIG_FB_LOGO_CENTER into a cmd line option A command line option is much more flexible than a config option and the supporting code is small. Gets rid of #ifdefs in the code too... Suggested-by: Geert Uytterhoeven Cc: Jonathan Corbet Signed-off-by: Peter Rosin Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 7cdd31a69719..f52ef0ad6781 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -653,6 +653,7 @@ extern int fb_new_modelist(struct fb_info *info); extern struct fb_info *registered_fb[FB_MAX]; extern int num_registered_fb; +extern bool fb_center_logo; extern struct class *fb_class; #define for_each_registered_fb(i) \ -- cgit v1.2.3 From 9e857a40dc4eba15a739b4194d7db873d82c28a0 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 15 Jan 2019 16:55:30 +0100 Subject: net: phy: Add missing features to PHY drivers The bcm87xx and micrel driver has PHYs which are missing the .features value. Add them. The bcm87xx is a 10G FEC only PHY. Add the needed features definition of this PHY. Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap") Reported-by: Scott Wood Reported-by: Camelia Groza Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 3b051f761450..55114657a577 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -48,6 +48,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) @@ -56,6 +57,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) +#define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) extern const int phy_10_100_features_array[4]; -- cgit v1.2.3 From edcddd4c879af48ec922d680b2d56834c085683b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 17 Jan 2019 07:15:35 -0500 Subject: XArray: Fix an arithmetic error in xa_is_err There is a math problem here which leads to a lot of static checker warnings for me: net/sunrpc/clnt.c:451 rpc_new_client() error: (-4096) too low for ERR_PTR Error values are from -1 to -4095 or from 0xffffffff to 0xfffff001 in hexadecimal. (I am assuming a 32 bit system for simplicity). We are using the lowest two bits to hold some internal XArray data so the error is shifted two spaces to the left. 0xfffff001 << 2 is 0xffffc004. And finally we want to check that BIT(1) is set so we add 2 which gives us 0xffffc006. In other words, we should be checking that "entry >= 0xffffc006", but the check is actually testing if "entry >= 0xffffc002". Fixes: 76b4e5299565 ("XArray: Permit storing 2-byte-aligned pointers") Signed-off-by: Dan Carpenter [Use xa_mk_internal() instead of changing the bracketing] Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 7da665f5cb20..5d9d318bcf7a 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -177,7 +177,7 @@ static inline bool xa_is_internal(const void *entry) static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && - (unsigned long)entry >= -((MAX_ERRNO << 2) + 2)); + entry >= xa_mk_internal(-MAX_ERRNO)); } /** -- cgit v1.2.3 From 70921ae25f944423f0abf096f73455c586da0652 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 8 Jan 2019 17:04:32 -0700 Subject: genirq: Fix the kerneldoc comment for struct irq_affinity_desc A recent commit added a new field but did not update the kerneldoc comment, leading to this build warning: ./include/linux/interrupt.h:268: warning: Function parameter or member 'is_managed' not described in 'irq_affinity_desc' Add the missing information, making the docs build 0.001% quieter. Fixes: c410abbbacb9 ("genirq/affinity: Add is_managed to struct irq_affinity_desc") Signed-off-by: Jonathan Corbet Signed-off-by: Thomas Gleixner Cc: Dou Liyang Link: https://lkml.kernel.org/r/20190108170432.59bae8a6@lwn.net --- include/linux/interrupt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index c672f34235e7..4a728dba02e2 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -260,6 +260,7 @@ struct irq_affinity { /** * struct irq_affinity_desc - Interrupt affinity descriptor * @mask: cpumask to hold the affinity assignment + * @is_managed: 1 if the interrupt is managed internally */ struct irq_affinity_desc { struct cpumask mask; -- cgit v1.2.3 From 6c57f0458022298e4da1729c67bd33ce41c14e7a Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Thu, 17 Jan 2019 15:34:38 +0000 Subject: net: Fix usage of pskb_trim_rcsum In certain cases, pskb_trim_rcsum() may change skb pointers. Reinitialize header pointers afterwards to avoid potential use-after-frees. Add a note in the documentation of pskb_trim_rcsum(). Found by KASAN. Signed-off-by: Ross Lagerwall Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 93f56fddd92a..95d25b010a25 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3218,6 +3218,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. + * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) -- cgit v1.2.3 From 3e64cf7a435ed0500e3adaa8aada2272d3ae8abc Mon Sep 17 00:00:00 2001 From: Camelia Groza Date: Thu, 17 Jan 2019 14:22:36 +0200 Subject: net: phy: phy driver features are mandatory Since phy driver features became a link_mode bitmap, phy drivers that don't have a list of features configured will cause the kernel to crash when probed. Prevent the phy driver from registering if the features field is missing. Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap") Reported-by: Scott Wood Signed-off-by: Camelia Groza Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 55114657a577..ef20aeea10cc 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -469,8 +469,8 @@ struct phy_device { * only works for PHYs with IDs which match this field * name: The friendly name of this PHY type * phy_id_mask: Defines the important bits of the phy_id - * features: A list of features (speed, duplex, etc) supported - * by this PHY + * features: A mandatory list of features (speed, duplex, etc) + * supported by this PHY * flags: A bitfield defining certain other features this PHY * supports (like interrupts) * -- cgit v1.2.3 From e6018c0f5c996e61639adce6a0697391a2861916 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 17 Dec 2018 10:14:53 +0100 Subject: sched/wake_q: Document wake_q_add() The only guarantee provided by wake_q_add() is that a wakeup will happen after it, it does _NOT_ guarantee the wakeup will be delayed until the matching wake_up_q(). If wake_q_add() fails the cmpxchg() a concurrent wakeup is pending and that can happen at any time after the cmpxchg(). This means we should not rely on the wakeup happening at wake_q_up(), but should be ready for wake_q_add() to issue the wakeup. The delay; if provided (most likely); should only result in more efficient behaviour. Reported-by: Yongji Xie Signed-off-by: Peter Zijlstra (Intel) Cc: Davidlohr Bueso Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Signed-off-by: Ingo Molnar --- include/linux/sched/wake_q.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 10b19a192b2d..545f37138057 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -24,9 +24,13 @@ * called near the end of a function. Otherwise, the list can be * re-initialized for later re-use by wake_q_init(). * - * Note that this can cause spurious wakeups. schedule() callers + * NOTE that this can cause spurious wakeups. schedule() callers * must ensure the call is done inside a loop, confirming that the * wakeup condition has in fact occurred. + * + * NOTE that there is no guarantee the wakeup will happen any later than the + * wake_q_add() location. Therefore task must be ready to be woken at the + * location of the wake_q_add(). */ #include -- cgit v1.2.3 From 1cd7386549f9b6f2f230da54aa9e7fe2d6c216d2 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 19 Jan 2019 08:45:56 -0800 Subject: libnvdimm/security: Require nvdimm_security_setup_events() to succeed The following warning: ACPI0012:00: security event setup failed: -19 ...is meant to capture exceptional failures of sysfs_get_dirent(), however it will also fail in the common case when security support is disabled. A few issues: 1/ A dev_warn() report for a common case is too chatty 2/ The setup of this notifier is generic, no need for it to be driven from the nfit driver, it can exist completely in the core. 3/ If it fails for any reason besides security support being disabled, that's fatal and should abort DIMM activation. Userspace may hang if it never gets overwrite notifications. 4/ The dirent needs to be released. Move the call to the core 'dimm' driver, make it conditional on security support being active, make it fatal for the exceptional case, add the missing sysfs_put() at device disable time. Fixes: 7d988097c546 ("...Add security DSM overwrite support") Reviewed-by: Dave Jiang Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 7315977b64da..ad609617aeb8 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -235,7 +235,6 @@ static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, cmd_mask, num_flush, flush_wpq, NULL, NULL); } -int nvdimm_security_setup_events(struct nvdimm *nvdimm); const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd); u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, -- cgit v1.2.3 From 7fc5854f8c6efae9e7624970ab49a1eac2faefb1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Dec 2017 08:38:30 -0800 Subject: writeback: synchronize sync(2) against cgroup writeback membership switches sync_inodes_sb() can race against cgwb (cgroup writeback) membership switches and fail to writeback some inodes. For example, if an inode switches to another wb while sync_inodes_sb() is in progress, the new wb might not be visible to bdi_split_work_to_wbs() at all or the inode might jump from a wb which hasn't issued writebacks yet to one which already has. This patch adds backing_dev_info->wb_switch_rwsem to synchronize cgwb switch path against sync_inodes_sb() so that sync_inodes_sb() is guaranteed to see all the target wbs and inodes can't jump wbs to escape syncing. v2: Fixed misplaced rwsem init. Spotted by Jiufei. Signed-off-by: Tejun Heo Reported-by: Jiufei Xue Link: http://lkml.kernel.org/r/dc694ae2-f07f-61e1-7097-7c8411cee12d@gmail.com Acked-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index c31157135598..07e02d6df5ad 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -190,6 +190,7 @@ struct backing_dev_info { struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ + struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #else struct bdi_writeback_congested *wb_congested; #endif -- cgit v1.2.3 From c75860e48a7634ff8dc050842211f79a0e4e6c46 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Sun, 20 Jan 2019 11:36:38 +0200 Subject: qed: Add infrastructure for error detection and recovery This patch adds the detection and handling of a parity error ("process kill event"), including the update of the protocol drivers, and the prevention of any HW access that will lead to device access towards the host while recovery is in progress. It also provides the means for the protocol drivers to trigger a recovery process on their decision. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 91c536a01b56..c2a1b7dbe4eb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -764,6 +764,7 @@ struct qed_probe_params { u32 dp_module; u8 dp_level; bool is_vf; + bool recov_in_prog; }; #define QED_DRV_VER_STR_SIZE 12 @@ -810,6 +811,7 @@ struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); + void (*schedule_recovery_handler)(void *dev); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); @@ -1057,6 +1059,24 @@ struct qed_common_ops { int (*db_recovery_del)(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); +/** + * @brief recovery_process - Trigger a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_process)(struct qed_dev *cdev); + +/** + * @brief recovery_prolog - Execute the prolog operations of a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_prolog)(struct qed_dev *cdev); + /** * @brief update_drv_state - API to inform the change in the driver state. * -- cgit v1.2.3 From 278396de78a9b59a692bc140233bde3a9d8a8a31 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Sun, 20 Jan 2019 11:36:39 +0200 Subject: qede: Error recovery process This patch adds the error recovery process in the qede driver. The process includes a partial/customized driver unload and load, which allows it to look like a short suspend period to the kernel while preserving the net devices' state. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qede_rdma.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 9904617a9730..e29d7199c10e 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -55,6 +55,16 @@ struct qede_rdma_event_work { enum qede_rdma_event event; }; +enum qede_rdma_probe_mode { + QEDE_RDMA_PROBE_NORMAL, + QEDE_RDMA_PROBE_RECOVERY, +}; + +enum qede_rdma_remove_mode { + QEDE_RDMA_REMOVE_NORMAL, + QEDE_RDMA_REMOVE_RECOVERY, +}; + struct qedr_driver { unsigned char name[32]; @@ -74,21 +84,24 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv); bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_rdma_dev_add(struct qede_dev *dev); +int qede_rdma_dev_add(struct qede_dev *dev, enum qede_rdma_probe_mode mode); void qede_rdma_dev_event_open(struct qede_dev *dev); void qede_rdma_dev_event_close(struct qede_dev *dev); -void qede_rdma_dev_remove(struct qede_dev *dev); +void qede_rdma_dev_remove(struct qede_dev *dev, + enum qede_rdma_remove_mode mode); void qede_rdma_event_changeaddr(struct qede_dev *edr); #else -static inline int qede_rdma_dev_add(struct qede_dev *dev) +static inline int qede_rdma_dev_add(struct qede_dev *dev, + enum qede_rdma_probe_mode mode) { return 0; } static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} -static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev, + enum qede_rdma_remove_mode mode) {} static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif -- cgit v1.2.3 From 8367de2c99a13d35960a51d6084631c883e93a4d Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 24 Jan 2019 18:20:14 +0900 Subject: block: Fix comment typo Fix typo in REQ_OP_ZONE_RESET description. Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5c7e7f859a24..d66bf5f32610 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -287,7 +287,7 @@ enum req_opf { REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, - /* seset a zone write pointer */ + /* reset a zone write pointer */ REQ_OP_ZONE_RESET = 6, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, -- cgit v1.2.3 From 3b707c3008cad04604c1f50e39f456621821c414 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Thu, 24 Jan 2019 03:07:02 -0800 Subject: net: dev_is_mac_header_xmit() true for ARPHRD_RAWIP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit __bpf_redirect() and act_mirred checks this boolean to determine whether to prefix an ethernet header. Signed-off-by: Maciej Żenczykowski Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/if_arp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 6756fea18b69..e44746de95cd 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -54,6 +54,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_IPGRE: case ARPHRD_VOID: case ARPHRD_NONE: + case ARPHRD_RAWIP: return false; default: return true; -- cgit v1.2.3 From abfd04f738c2625f63e04c8fc7cadb3b7a70d580 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 25 Jan 2019 15:32:28 -0800 Subject: qed: Revert error handling changes. This is new code and not bug fixes. This reverts all changes added by merge commit 8fb18be93efd7292d6ee403b9f61af1008239639 Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 20 -------------------- include/linux/qed/qede_rdma.h | 21 ++++----------------- 2 files changed, 4 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index c2a1b7dbe4eb..91c536a01b56 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -764,7 +764,6 @@ struct qed_probe_params { u32 dp_module; u8 dp_level; bool is_vf; - bool recov_in_prog; }; #define QED_DRV_VER_STR_SIZE 12 @@ -811,7 +810,6 @@ struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); - void (*schedule_recovery_handler)(void *dev); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); @@ -1059,24 +1057,6 @@ struct qed_common_ops { int (*db_recovery_del)(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); -/** - * @brief recovery_process - Trigger a recovery process - * - * @param cdev - * - * @return 0 on success, error otherwise. - */ - int (*recovery_process)(struct qed_dev *cdev); - -/** - * @brief recovery_prolog - Execute the prolog operations of a recovery process - * - * @param cdev - * - * @return 0 on success, error otherwise. - */ - int (*recovery_prolog)(struct qed_dev *cdev); - /** * @brief update_drv_state - API to inform the change in the driver state. * diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index e29d7199c10e..9904617a9730 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -55,16 +55,6 @@ struct qede_rdma_event_work { enum qede_rdma_event event; }; -enum qede_rdma_probe_mode { - QEDE_RDMA_PROBE_NORMAL, - QEDE_RDMA_PROBE_RECOVERY, -}; - -enum qede_rdma_remove_mode { - QEDE_RDMA_REMOVE_NORMAL, - QEDE_RDMA_REMOVE_RECOVERY, -}; - struct qedr_driver { unsigned char name[32]; @@ -84,24 +74,21 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv); bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_rdma_dev_add(struct qede_dev *dev, enum qede_rdma_probe_mode mode); +int qede_rdma_dev_add(struct qede_dev *dev); void qede_rdma_dev_event_open(struct qede_dev *dev); void qede_rdma_dev_event_close(struct qede_dev *dev); -void qede_rdma_dev_remove(struct qede_dev *dev, - enum qede_rdma_remove_mode mode); +void qede_rdma_dev_remove(struct qede_dev *dev); void qede_rdma_event_changeaddr(struct qede_dev *edr); #else -static inline int qede_rdma_dev_add(struct qede_dev *dev, - enum qede_rdma_probe_mode mode) +static inline int qede_rdma_dev_add(struct qede_dev *dev) { return 0; } static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} -static inline void qede_rdma_dev_remove(struct qede_dev *dev, - enum qede_rdma_remove_mode mode) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif -- cgit v1.2.3 From 13054abbaa4f1fd4e6f3b4b63439ec033b4c8035 Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Tue, 29 Jan 2019 11:58:35 +0100 Subject: HID: debug: fix the ring buffer implementation Ring buffer implementation in hid_debug_event() and hid_debug_events_read() is strange allowing lost or corrupted data. After commit 717adfdaf147 ("HID: debug: check length before copy_to_user()") it is possible to enter an infinite loop in hid_debug_events_read() by providing 0 as count, this locks up a system. Fix this by rewriting the ring buffer implementation with kfifo and simplify the code. This fixes CVE-2019-3819. v2: fix an execution logic and add a comment v3: use __set_current_state() instead of set_current_state() Link: https://bugzilla.redhat.com/show_bug.cgi?id=1669187 Cc: stable@vger.kernel.org # v4.18+ Fixes: cd667ce24796 ("HID: use debugfs for events/reports dumping") Fixes: 717adfdaf147 ("HID: debug: check length before copy_to_user()") Signed-off-by: Vladis Dronov Reviewed-by: Oleg Nesterov Signed-off-by: Benjamin Tissoires --- include/linux/hid-debug.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid-debug.h b/include/linux/hid-debug.h index 8663f216c563..2d6100edf204 100644 --- a/include/linux/hid-debug.h +++ b/include/linux/hid-debug.h @@ -24,7 +24,10 @@ #ifdef CONFIG_DEBUG_FS +#include + #define HID_DEBUG_BUFSIZE 512 +#define HID_DEBUG_FIFOSIZE 512 void hid_dump_input(struct hid_device *, struct hid_usage *, __s32); void hid_dump_report(struct hid_device *, int , u8 *, int); @@ -37,11 +40,8 @@ void hid_debug_init(void); void hid_debug_exit(void); void hid_debug_event(struct hid_device *, char *); - struct hid_debug_list { - char *hid_debug_buf; - int head; - int tail; + DECLARE_KFIFO_PTR(hid_debug_fifo, char); struct fasync_struct *fasync; struct hid_device *hdev; struct list_head node; @@ -64,4 +64,3 @@ struct hid_debug_list { #endif #endif - -- cgit v1.2.3 From b284909abad48b07d3071a9fc9b5692b3e64914b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 30 Jan 2019 07:13:58 -0600 Subject: cpu/hotplug: Fix "SMT disabled by BIOS" detection for KVM With the following commit: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") ... the hotplug code attempted to detect when SMT was disabled by BIOS, in which case it reported SMT as permanently disabled. However, that code broke a virt hotplug scenario, where the guest is booted with only primary CPU threads, and a sibling is brought online later. The problem is that there doesn't seem to be a way to reliably distinguish between the HW "SMT disabled by BIOS" case and the virt "sibling not yet brought online" case. So the above-mentioned commit was a bit misguided, as it permanently disabled SMT for both cases, preventing future virt sibling hotplugs. Going back and reviewing the original problems which were attempted to be solved by that commit, when SMT was disabled in BIOS: 1) /sys/devices/system/cpu/smt/control showed "on" instead of "notsupported"; and 2) vmx_vm_init() was incorrectly showing the L1TF_MSG_SMT warning. I'd propose that we instead consider #1 above to not actually be a problem. Because, at least in the virt case, it's possible that SMT wasn't disabled by BIOS and a sibling thread could be brought online later. So it makes sense to just always default the smt control to "on" to allow for that possibility (assuming cpuid indicates that the CPU supports SMT). The real problem is #2, which has a simple fix: change vmx_vm_init() to query the actual current SMT state -- i.e., whether any siblings are currently online -- instead of looking at the SMT "control" sysfs value. So fix it by: a) reverting the original "fix" and its followup fix: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") bc2d8d262cba ("cpu/hotplug: Fix SMT supported evaluation") and b) changing vmx_vm_init() to query the actual current SMT state -- instead of the sysfs control value -- to determine whether the L1TF warning is needed. This also requires the 'sched_smt_present' variable to exported, instead of 'cpu_smt_control'. Fixes: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") Reported-by: Igor Mammedov Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Joe Mario Cc: Jiri Kosina Cc: Peter Zijlstra Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/e3a85d585da28cc333ecbc1e78ee9216e6da9396.1548794349.git.jpoimboe@redhat.com --- include/linux/cpu.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 218df7f4d3e1..5041357d0297 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -180,12 +180,10 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); -extern void cpu_smt_check_topology_early(void); extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } -static inline void cpu_smt_check_topology_early(void) { } static inline void cpu_smt_check_topology(void) { } #endif -- cgit v1.2.3 From 7d10f70fc198877b43d92bdcd7604279788b9568 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Jan 2019 13:52:37 -0500 Subject: fs: Don't need to put list_lru into its own cacheline The list_lru structure is essentially just a pointer to a table of per-node LRU lists. Even if CONFIG_MEMCG_KMEM is defined, the list field is just used for LRU list registration and shrinker_id is set at initialization. Those fields won't need to be touched that often. So there is no point to make the list_lru structures to sit in their own cachelines. Signed-off-by: Waiman Long Reviewed-by: Dave Chinner Signed-off-by: Linus Torvalds --- include/linux/fs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 811c77743dad..29d8e2cfed0e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1479,11 +1479,12 @@ struct super_block { struct user_namespace *s_user_ns; /* - * Keep the lru lists last in the structure so they always sit on their - * own individual cachelines. + * The list_lru structure is essentially just a pointer to a table + * of per-node lru lists, each of which has its own spinlock. + * There is no need to put them into separate cachelines. */ - struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; - struct list_lru s_inode_lru ____cacheline_aligned_in_smp; + struct list_lru s_dentry_lru; + struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; -- cgit v1.2.3 From af0c9af1b3f66052c369d08be3f60fa9a9559e48 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Jan 2019 13:52:38 -0500 Subject: fs/dcache: Track & report number of negative dentries The current dentry number tracking code doesn't distinguish between positive & negative dentries. It just reports the total number of dentries in the LRU lists. As excessive number of negative dentries can have an impact on system performance, it will be wise to track the number of positive and negative dentries separately. This patch adds tracking for the total number of negative dentries in the system LRU lists and reports it in the 5th field in the /proc/sys/fs/dentry-state file. The number, however, does not include negative dentries that are in flight but not in the LRU yet as well as those in the shrinker lists which are on the way out anyway. The number of positive dentries in the LRU lists can be roughly found by subtracting the number of negative dentries from the unused count. Matthew Wilcox had confirmed that since the introduction of the dentry_stat structure in 2.1.60, the dummy array was there, probably for future extension. They were not replacements of pre-existing fields. So no sane applications that read the value of /proc/sys/fs/dentry-state will do dummy thing if the last 2 fields of the sysctl parameter are not zero. IOW, it will be safe to use one of the dummy array entry for negative dentry count. Signed-off-by: Waiman Long Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ef4b70f64f33..60996e64c579 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -62,9 +62,10 @@ extern const struct qstr slash_name; struct dentry_stat_t { long nr_dentry; long nr_unused; - long age_limit; /* age in seconds */ - long want_pages; /* pages requested by system */ - long dummy[2]; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long nr_negative; /* # of unused negative dentries */ + long dummy; /* Reserved for future use */ }; extern struct dentry_stat_t dentry_stat; -- cgit v1.2.3 From 15efb47dc560849d0c07db96fdad5121f2cf736e Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 30 Jan 2019 18:26:02 +0100 Subject: PM-runtime: Fix deadlock with ktime_get() A deadlock has been seen when swicthing clocksources which use PM-runtime. The call path is: change_clocksource ... write_seqcount_begin ... timekeeping_update ... sh_cmt_clocksource_enable ... rpm_resume pm_runtime_mark_last_busy ktime_get do read_seqcount_begin while read_seqcount_retry .... write_seqcount_end Although we should be safe because we haven't yet changed the clocksource at that time, we can't do that because of seqcount protection. Use ktime_get_mono_fast_ns() instead which is lock safe for such cases. With ktime_get_mono_fast_ns, the timestamp is not guaranteed to be monotonic across an update and as a result can goes backward. According to update_fast_timekeeper() description: "In the worst case, this can result is a slightly wrong timestamp (a few nanoseconds)". For PM-runtime autosuspend, this means only that the suspend decision may be slightly suboptimal. Fixes: 8234f6734c5d ("PM-runtime: Switch autosuspend over to using hrtimers") Reported-by: Biju Das Signed-off-by: Vincent Guittot Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 54af4eef169f..fed5be706bc9 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev) static inline void pm_runtime_mark_last_busy(struct device *dev) { - WRITE_ONCE(dev->power.last_busy, ktime_to_ns(ktime_get())); + WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } static inline bool pm_runtime_is_irq_safe(struct device *dev) -- cgit v1.2.3 From d5256083f62e2720f75bb3c5a928a0afe47d6bc3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Jan 2019 12:49:48 +0100 Subject: ipvlan, l3mdev: fix broken l3s mode wrt local routes While implementing ipvlan l3 and l3s mode for kubernetes CNI plugin, I ran into the issue that while l3 mode is working fine, l3s mode does not have any connectivity to kube-apiserver and hence all pods end up in Error state as well. The ipvlan master device sits on top of a bond device and hostns traffic to kube-apiserver (also running in hostns) is DNATed from 10.152.183.1:443 to 139.178.29.207:37573 where the latter is the address of the bond0. While in l3 mode, a curl to https://10.152.183.1:443 or to https://139.178.29.207:37573 works fine from hostns, neither of them do in case of l3s. In the latter only a curl to https://127.0.0.1:37573 appeared to work where for local addresses of bond0 I saw kernel suddenly starting to emit ARP requests to query HW address of bond0 which remained unanswered and neighbor entries in INCOMPLETE state. These ARP requests only happen while in l3s. Debugging this further, I found the issue is that l3s mode is piggy- backing on l3 master device, and in this case local routes are using l3mdev_master_dev_rcu(dev) instead of net->loopback_dev as per commit f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") and 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback"). I found that reverting them back into using the net->loopback_dev fixed ipvlan l3s connectivity and got everything working for the CNI. Now judging from 4fbae7d83c98 ("ipvlan: Introduce l3s mode") and the l3mdev paper in [0] the only sole reason why ipvlan l3s is relying on l3 master device is to get the l3mdev_ip_rcv() receive hook for setting the dst entry of the input route without adding its own ipvlan specific hacks into the receive path, however, any l3 domain semantics beyond just that are breaking l3s operation. Note that ipvlan also has the ability to dynamically switch its internal operation from l3 to l3s for all ports via ipvlan_set_port_mode() at runtime. In any case, l3 vs l3s soley distinguishes itself by 'de-confusing' netfilter through switching skb->dev to ipvlan slave device late in NF_INET_LOCAL_IN before handing the skb to L4. Minimal fix taken here is to add a IFF_L3MDEV_RX_HANDLER flag which, if set from ipvlan setup, gets us only the wanted l3mdev_l3_rcv() hook without any additional l3mdev semantics on top. This should also have minimal impact since dev->priv_flags is already hot in cache. With this set, l3s mode is working fine and I also get things like masquerading pod traffic on the ipvlan master properly working. [0] https://netdevconf.org/1.2/papers/ahern-what-is-l3mdev-paper.pdf Fixes: f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") Fixes: 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback") Fixes: 4fbae7d83c98 ("ipvlan: Introduce l3s mode") Signed-off-by: Daniel Borkmann Cc: Mahesh Bandewar Cc: David Ahern Cc: Florian Westphal Cc: Martynas Pumputis Acked-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1377d085ef99..86dbb3e29139 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1483,6 +1483,7 @@ struct net_device_ops { * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device + * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1514,6 +1515,7 @@ enum netdev_priv_flags { IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, + IFF_L3MDEV_RX_HANDLER = 1<<29, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1544,6 +1546,7 @@ enum netdev_priv_flags { #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE +#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER /** * struct net_device - The DEVICE structure. @@ -4549,6 +4552,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_has_l3_rx_handler(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; +} + static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; -- cgit v1.2.3 From 4ec5302fa906ec9d86597b236f62315bacdb9622 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 30 Jan 2019 15:54:19 +0100 Subject: net: stmmac: Fallback to Platform Data clock in Watchdog conversion If we don't have DT then stmmac_clk will not be available. Let's add a new Platform Data field so that we can specify the refclk by this mean. This way we can still use the coalesce command in PCI based setups. Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7ddfc65586b0..4335bd771ce5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -184,6 +184,7 @@ struct plat_stmmacenet_data { struct clk *pclk; struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; + unsigned int clk_ref_rate; struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; -- cgit v1.2.3 From 56841070ccc87b463ac037d2d1f2beb8e5e35f0c Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Thu, 31 Jan 2019 11:19:43 +0000 Subject: irqchip/gic-v3-its: Fix ITT_entry_size accessor According to ARM IHI 0069C (ID070116), we should use GITS_TYPER's bits [7:4] as ITT_entry_size instead of [8:4]. Although this is pretty annoying, it only results in a potential over-allocation of memory, and nothing bad happens. Fixes: 3dfa576bfb45 ("irqchip/gic-v3-its: Add probing for VLPI properties") Signed-off-by: Zenghui Yu [maz: massaged subject and commit message] Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 071b4cbdf010..c848a7cc502e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -319,7 +319,7 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) -- cgit v1.2.3 From 9a6d5488002fdca7134a0e59b0ae252f61042810 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 30 Jan 2019 08:41:40 -0700 Subject: ide: ensure atapi sense request aren't preempted There's an issue with how sense requests are handled in IDE. If ide-cd encounters an error, it queues a sense request. With how IDE request handling is done, this is the next request we need to handle. But it's impossible to guarantee this, as another request could come in between the sense being queued, and ->queue_rq() being run and handling it. If that request ALSO fails, then we attempt to doubly queue the single sense request we have. Since we only support one active request at the time, defer request processing when a sense request is queued. Fixes: 600335205b8d "ide: convert to blk-mq" Reported-by: He Zhe Tested-by: He Zhe Signed-off-by: Jens Axboe --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index e7d29ae633cd..971cf76a78a0 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -615,6 +615,7 @@ struct ide_drive_s { /* current sense rq and buffer */ bool sense_rq_armed; + bool sense_rq_active; struct request *sense_rq; struct request_sense sense_data; @@ -1219,6 +1220,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern void ide_timer_expiry(struct timer_list *t); extern irqreturn_t ide_intr(int irq, void *dev_id); extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +extern blk_status_t ide_issue_rq(ide_drive_t *, struct request *, bool); extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); void ide_init_disk(struct gendisk *, ide_drive_t *); -- cgit v1.2.3 From 6cab5e90ab2bd323c9f3811b6c70a4687df51e27 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 28 Jan 2019 18:43:34 -0800 Subject: bpf: run bpf programs with preemption disabled Disabled preemption is necessary for proper access to per-cpu maps from BPF programs. But the sender side of socket filters didn't have preemption disabled: unix_dgram_sendmsg->sk_filter->sk_filter_trim_cap->bpf_prog_run_save_cb->BPF_PROG_RUN and a combination of af_packet with tun device didn't disable either: tpacket_snd->packet_direct_xmit->packet_pick_tx_queue->ndo_select_queue-> tun_select_queue->tun_ebpf_select_queue->bpf_prog_run_clear_cb->BPF_PROG_RUN Disable preemption before executing BPF programs (both classic and extended). Reported-by: Jann Horn Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..e532fcc6e4b5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -591,8 +591,8 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) return qdisc_skb_cb(skb)->data; } -static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, - struct sk_buff *skb) +static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; @@ -611,15 +611,30 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, return res; } +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u32 res; + + preempt_disable(); + res = __bpf_prog_run_save_cb(prog, skb); + preempt_enable(); + return res; +} + static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); + u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); - return BPF_PROG_RUN(prog, skb); + preempt_disable(); + res = BPF_PROG_RUN(prog, skb); + preempt_enable(); + return res; } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, -- cgit v1.2.3 From 9bcdeb51bd7d2ae9fe65ea4d60643d2aeef5bfe3 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 1 Feb 2019 14:20:31 -0800 Subject: oom, oom_reaper: do not enqueue same task twice Arkadiusz reported that enabling memcg's group oom killing causes strange memcg statistics where there is no task in a memcg despite the number of tasks in that memcg is not 0. It turned out that there is a bug in wake_oom_reaper() which allows enqueuing same task twice which makes impossible to decrease the number of tasks in that memcg due to a refcount leak. This bug existed since the OOM reaper became invokable from task_will_free_mem(current) path in out_of_memory() in Linux 4.7, T1@P1 |T2@P1 |T3@P1 |OOM reaper ----------+----------+----------+------------ # Processing an OOM victim in a different memcg domain. try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) out_of_memory() oom_kill_process(P1) do_send_sig_info(SIGKILL, @P1) mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T2@P1) wake_oom_reaper(T2@P1) # T2@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued again due to oom_reaper_list == T2@P1 && T1@P1->oom_reaper_list == NULL. mutex_unlock(&oom_lock) # Completed processing an OOM victim in a different memcg domain. spin_lock(&oom_reaper_lock) # T1P1 is dequeued. spin_unlock(&oom_reaper_lock) but memcg's group oom killing made it easier to trigger this bug by calling wake_oom_reaper() on the same task from one out_of_memory() request. Fix this bug using an approach used by commit 855b018325737f76 ("oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task"). As a side effect of this patch, this patch also avoids enqueuing multiple threads sharing memory via task_will_free_mem(current) path. Link: http://lkml.kernel.org/r/e865a044-2c10-9858-f4ef-254bc71d6cc2@i-love.sakura.ne.jp Link: http://lkml.kernel.org/r/5ee34fc6-1485-34f8-8790-903ddabaa809@i-love.sakura.ne.jp Fixes: af8e15cc85a25315 ("oom, oom_reaper: do not enqueue task if it is on the oom_reaper_list head") Signed-off-by: Tetsuo Handa Reported-by: Arkadiusz Miskiewicz Tested-by: Arkadiusz Miskiewicz Acked-by: Michal Hocko Acked-by: Roman Gushchin Cc: Tejun Heo Cc: Aleksa Sarai Cc: Jay Kamat Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/coredump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ec912d01126f..ecdc6542070f 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ +#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ -- cgit v1.2.3 From b13bc35193d9e7a8c050a24928ca5c9e7c9a009b Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 1 Feb 2019 14:20:51 -0800 Subject: mm/hotplug: invalid PFNs from pfn_to_online_page() On an arm64 ThunderX2 server, the first kmemleak scan would crash [1] with CONFIG_DEBUG_VM_PGFLAGS=y due to page_to_nid() found a pfn that is not directly mapped (MEMBLOCK_NOMAP). Hence, the page->flags is uninitialized. This is due to the commit 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") starts to use pfn_to_online_page() instead of pfn_valid(). However, in the CONFIG_MEMORY_HOTPLUG=y case, pfn_to_online_page() does not call memblock_is_map_memory() while pfn_valid() does. Historically, the commit 68709f45385a ("arm64: only consider memblocks with NOMAP cleared for linear mapping") causes pages marked as nomap being no long reassigned to the new zone in memmap_init_zone() by calling __init_single_page(). Since the commit 2d070eab2e82 ("mm: consider zone which is not fully populated to have holes") introduced pfn_to_online_page() and was designed to return a valid pfn only, but it is clearly broken on arm64. Therefore, let pfn_to_online_page() call pfn_valid_within(), so it can handle nomap thanks to the commit f52bb98f5ade ("arm64: mm: always enable CONFIG_HOLES_IN_ZONE"), while it will be optimized away on architectures where have no HOLES_IN_ZONE. [1] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000006 Mem abort info: ESR = 0x96000005 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 Internal error: Oops: 96000005 [#1] SMP CPU: 60 PID: 1408 Comm: kmemleak Not tainted 5.0.0-rc2+ #8 pstate: 60400009 (nZCv daif +PAN -UAO) pc : page_mapping+0x24/0x144 lr : __dump_page+0x34/0x3dc sp : ffff00003a5cfd10 x29: ffff00003a5cfd10 x28: 000000000000802f x27: 0000000000000000 x26: 0000000000277d00 x25: ffff000010791f56 x24: ffff7fe000000000 x23: ffff000010772f8b x22: ffff00001125f670 x21: ffff000011311000 x20: ffff000010772f8b x19: fffffffffffffffe x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: ffff802698b19600 x13: ffff802698b1a200 x12: ffff802698b16f00 x11: ffff802698b1a400 x10: 0000000000001400 x9 : 0000000000000001 x8 : ffff00001121a000 x7 : 0000000000000000 x6 : ffff0000102c53b8 x5 : 0000000000000000 x4 : 0000000000000003 x3 : 0000000000000100 x2 : 0000000000000000 x1 : ffff000010772f8b x0 : ffffffffffffffff Process kmemleak (pid: 1408, stack limit = 0x(____ptrval____)) Call trace: page_mapping+0x24/0x144 __dump_page+0x34/0x3dc dump_page+0x28/0x4c kmemleak_scan+0x4ac/0x680 kmemleak_scan_thread+0xb4/0xdc kthread+0x12c/0x13c ret_from_fork+0x10/0x18 Code: d503201f f9400660 36000040 d1000413 (f9400661) ---[ end trace 4d4bd7f573490c8e ]--- Kernel panic - not syncing: Fatal exception SMP: stopping secondary CPUs Kernel Offset: disabled CPU features: 0x002,20000c38 Memory Limit: none ---[ end Kernel panic - not syncing: Fatal exception ]--- Link: http://lkml.kernel.org/r/20190122132916.28360-1-cai@lca.pw Fixes: 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") Signed-off-by: Qian Cai Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Catalin Marinas Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 07da5c6c5ba0..368267c1b71b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -21,14 +21,16 @@ struct vmem_altmap; * walkers which rely on the fully initialized page->flags and others * should use this rather than pfn_valid && pfn_to_page */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___nr = pfn_to_section_nr(pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ - ___page = pfn_to_page(pfn); \ - ___page; \ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___pfn = pfn; \ + unsigned long ___nr = pfn_to_section_nr(___pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ + pfn_valid_within(___pfn)) \ + ___page = pfn_to_page(___pfn); \ + ___page; \ }) /* -- cgit v1.2.3 From e6d429313ea5c776d2e76b4494df69102e6b7115 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 29 Jan 2019 17:44:36 -0500 Subject: x86/resctrl: Avoid confusion over the new X86_RESCTRL config "Resource Control" is a very broad term for this CPU feature, and a term that is also associated with containers, cgroups etc. This can easily cause confusion. Make the user prompt more specific. Match the config symbol name. [ bp: In the future, the corresponding ARM arch-specific code will be under ARM_CPU_RESCTRL and the arch-agnostic bits will be carved out under the CPU_RESCTRL umbrella symbol. ] Signed-off-by: Johannes Weiner Signed-off-by: Borislav Petkov Cc: Babu Moger Cc: Fenghua Yu Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Morse Cc: Jonathan Corbet Cc: "Kirill A. Shutemov" Cc: linux-doc@vger.kernel.org Cc: Peter Zijlstra Cc: Pu Wen Cc: Reinette Chatre Cc: Thomas Gleixner Cc: Tony Luck Cc: x86-ml Link: https://lkml.kernel.org/r/20190130195621.GA30653@cmpxchg.org --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 224666226e87..8c328b14c424 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -995,7 +995,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif -- cgit v1.2.3 From 0803de78049fe1b0baf44bcddc727b036fb9139b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 7 Feb 2019 11:55:39 +0100 Subject: blktrace: Show requests without sector Currently, blktrace will not show requests that don't have any data as rq->__sector is initialized to -1 which is out of device range and thus discarded by act_log_check(). This is most notably the case for cache flush requests sent to the device. Fix the problem by making blk_rq_trace_sector() return 0 for requests without initialized sector. Reviewed-by: Johannes Thumshirn Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 8804753805ac..7bb2d8de9f30 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -116,7 +116,13 @@ extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); static inline sector_t blk_rq_trace_sector(struct request *rq) { - return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq); + /* + * Tracing should ignore starting sector for passthrough requests and + * requests where starting sector didn't get set. + */ + if (blk_rq_is_passthrough(rq) || blk_rq_pos(rq) == (sector_t)-1) + return 0; + return blk_rq_pos(rq); } static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq) -- cgit v1.2.3 From dcf6e2e38a1c7ccbc535de5e1d9b14998847499d Mon Sep 17 00:00:00 2001 From: Zachary Hays Date: Thu, 7 Feb 2019 10:03:08 -0500 Subject: mmc: block: handle complete_work on separate workqueue The kblockd workqueue is created with the WQ_MEM_RECLAIM flag set. This generates a rescuer thread for that queue that will trigger when the CPU is under heavy load and collect the uncompleted work. In the case of mmc, this creates the possibility of a deadlock when there are multiple partitions on the device as other blk-mq work is also run on the same queue. For example: - worker 0 claims the mmc host to work on partition 1 - worker 1 attempts to claim the host for partition 2 but has to wait for worker 0 to finish - worker 0 schedules complete_work to release the host - rescuer thread is triggered after time-out and collects the dangling work - rescuer thread attempts to complete the work in order starting with claim host - the task to release host is now blocked by a task to claim it and will never be called The above results in multiple hung tasks that lead to failures to mount partitions. Handling complete_work on a separate workqueue avoids this by keeping the work completion tasks separate from the other blk-mq work. This allows the host to be released without getting blocked by other tasks attempting to claim the host. Signed-off-by: Zachary Hays Fixes: 81196976ed94 ("mmc: block: Add blk-mq support") Cc: Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index de7377815b6b..8ef330027b13 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -308,6 +308,7 @@ struct mmc_card { unsigned int nr_parts; unsigned int bouncesz; /* Bounce buffer size */ + struct workqueue_struct *complete_wq; /* Private workqueue */ }; static inline bool mmc_large_sector(struct mmc_card *card) -- cgit v1.2.3 From 81ec3f3c4c4d78f2d3b6689c9816bfbdf7417dbb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 4 Feb 2019 13:35:32 +0100 Subject: perf/x86: Add check_period PMU callback Vince (and later on Ravi) reported crashes in the BTS code during fuzzing with the following backtrace: general protection fault: 0000 [#1] SMP PTI ... RIP: 0010:perf_prepare_sample+0x8f/0x510 ... Call Trace: ? intel_pmu_drain_bts_buffer+0x194/0x230 intel_pmu_drain_bts_buffer+0x160/0x230 ? tick_nohz_irq_exit+0x31/0x40 ? smp_call_function_single_interrupt+0x48/0xe0 ? call_function_single_interrupt+0xf/0x20 ? call_function_single_interrupt+0xa/0x20 ? x86_schedule_events+0x1a0/0x2f0 ? x86_pmu_commit_txn+0xb4/0x100 ? find_busiest_group+0x47/0x5d0 ? perf_event_set_state.part.42+0x12/0x50 ? perf_mux_hrtimer_restart+0x40/0xb0 intel_pmu_disable_event+0xae/0x100 ? intel_pmu_disable_event+0xae/0x100 x86_pmu_stop+0x7a/0xb0 x86_pmu_del+0x57/0x120 event_sched_out.isra.101+0x83/0x180 group_sched_out.part.103+0x57/0xe0 ctx_sched_out+0x188/0x240 ctx_resched+0xa8/0xd0 __perf_event_enable+0x193/0x1e0 event_function+0x8e/0xc0 remote_function+0x41/0x50 flush_smp_call_function_queue+0x68/0x100 generic_smp_call_function_single_interrupt+0x13/0x30 smp_call_function_single_interrupt+0x3e/0xe0 call_function_single_interrupt+0xf/0x20 The reason is that while event init code does several checks for BTS events and prevents several unwanted config bits for BTS event (like precise_ip), the PERF_EVENT_IOC_PERIOD allows to create BTS event without those checks being done. Following sequence will cause the crash: If we create an 'almost' BTS event with precise_ip and callchains, and it into a BTS event it will crash the perf_prepare_sample() function because precise_ip events are expected to come in with callchain data initialized, but that's not the case for intel_pmu_drain_bts_buffer() caller. Adding a check_period callback to be called before the period is changed via PERF_EVENT_IOC_PERIOD. It will deny the change if the event would become BTS. Plus adding also the limit_period check as well. Reported-by: Vince Weaver Signed-off-by: Jiri Olsa Acked-by: Peter Zijlstra Cc: Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Naveen N. Rao Cc: Ravi Bangoria Cc: Stephane Eranian Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20190204123532.GA4794@krava Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1d5c551a5add..e1a051724f7e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -447,6 +447,11 @@ struct pmu { * Filter events for PMU-specific reasons. */ int (*filter_match) (struct perf_event *event); /* optional */ + + /* + * Check period value for PERF_EVENT_IOC_PERIOD ioctl. + */ + int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { -- cgit v1.2.3 From a2fc9d7e36f6d484d9be4a0a204400aaf6059544 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 13 Feb 2019 20:11:40 +0100 Subject: net: phy: don't use locking in phy_is_started Russell suggested to remove the locking from phy_is_started() because the read is atomic anyway and actually the locking may be more misleading. Fixes: 2b3e88ea6528 ("net: phy: improve phy state checking") Suggested-by: Russell King - ARM Linux admin Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index ef20aeea10cc..127fcc9c3778 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -674,26 +674,13 @@ phy_lookup_setting(int speed, int duplex, const unsigned long *mask, size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); -static inline bool __phy_is_started(struct phy_device *phydev) -{ - WARN_ON(!mutex_is_locked(&phydev->lock)); - - return phydev->state >= PHY_UP; -} - /** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct */ static inline bool phy_is_started(struct phy_device *phydev) { - bool started; - - mutex_lock(&phydev->lock); - started = __phy_is_started(phydev); - mutex_unlock(&phydev->lock); - - return started; + return phydev->state >= PHY_UP; } void phy_resolve_aneg_linkmode(struct phy_device *phydev); -- cgit v1.2.3 From c0d9782f5b6d7157635ae2fd782a4b27d55a6013 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Fri, 8 Feb 2019 23:51:05 +0100 Subject: Compiler Attributes: add support for __copy (gcc >= 9) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit From the GCC manual: copy copy(function) The copy attribute applies the set of attributes with which function has been declared to the declaration of the function to which the attribute is applied. The attribute is designed for libraries that define aliases or function resolvers that are expected to specify the same set of attributes as their targets. The copy attribute can be used with functions, variables, or types. However, the kind of symbol to which the attribute is applied (either function or variable) must match the kind of symbol to which the argument refers. The copy attribute copies only syntactic and semantic attributes but not attributes that affect a symbol’s linkage or visibility such as alias, visibility, or weak. The deprecated attribute is also not copied. https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html The upcoming GCC 9 release extends the -Wmissing-attributes warnings (enabled by -Wall) to C and aliases: it warns when particular function attributes are missing in the aliases but not in their target, e.g.: void __cold f(void) {} void __alias("f") g(void); diagnoses: warning: 'g' specifies less restrictive attribute than its target 'f': 'cold' [-Wmissing-attributes] Using __copy(f) we can copy the __cold attribute from f to g: void __cold f(void) {} void __copy(f) __alias("f") g(void); This attribute is most useful to deal with situations where an alias is declared but we don't know the exact attributes the target has. For instance, in the kernel, the widely used module_init/exit macros define the init/cleanup_module aliases, but those cannot be marked always as __init/__exit since some modules do not have their functions marked as such. Suggested-by: Martin Sebor Reviewed-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 19f32b0c29af..6b318efd8a74 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -34,6 +34,7 @@ #ifndef __has_attribute # define __has_attribute(x) __GCC4_has_attribute_##x # define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___copy__ 0 # define __GCC4_has_attribute___designated_init__ 0 # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___noclone__ 1 @@ -100,6 +101,19 @@ */ #define __attribute_const__ __attribute__((__const__)) +/* + * Optional: only supported since gcc >= 9 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-copy-function-attribute + */ +#if __has_attribute(__copy__) +# define __copy(symbol) __attribute__((__copy__(symbol))) +#else +# define __copy(symbol) +#endif + /* * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' * attribute warnings entirely and for good") for more information. -- cgit v1.2.3 From a6e60d84989fa0e91db7f236eda40453b0e44afa Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Sat, 19 Jan 2019 20:59:34 +0100 Subject: include/linux/module.h: copy __init/__exit attrs to init/cleanup_module The upcoming GCC 9 release extends the -Wmissing-attributes warnings (enabled by -Wall) to C and aliases: it warns when particular function attributes are missing in the aliases but not in their target. In particular, it triggers for all the init/cleanup_module aliases in the kernel (defined by the module_init/exit macros), ending up being very noisy. These aliases point to the __init/__exit functions of a module, which are defined as __cold (among other attributes). However, the aliases themselves do not have the __cold attribute. Since the compiler behaves differently when compiling a __cold function as well as when compiling paths leading to calls to __cold functions, the warning is trying to point out the possibly-forgotten attribute in the alias. In order to keep the warning enabled, we decided to silence this case. Ideally, we would mark the aliases directly as __init/__exit. However, there are currently around 132 modules in the kernel which are missing __init/__exit in their init/cleanup functions (either because they are missing, or for other reasons, e.g. the functions being called from somewhere else); and a section mismatch is a hard error. A conservative alternative was to mark the aliases as __cold only. However, since we would like to eventually enforce __init/__exit to be always marked, we chose to use the new __copy function attribute (introduced by GCC 9 as well to deal with this). With it, we copy the attributes used by the target functions into the aliases. This way, functions that were not marked as __init/__exit won't have their aliases marked either, and therefore there won't be a section mismatch. Note that the warning would go away marking either the extern declaration, the definition, or both. However, we only mark the definition of the alias, since we do not want callers (which only see the declaration) to be compiled as if the function was __cold (and therefore the paths leading to those calls would be assumed to be unlikely). Link: https://lore.kernel.org/lkml/20190123173707.GA16603@gmail.com/ Link: https://lore.kernel.org/lkml/20190206175627.GA20399@gmail.com/ Suggested-by: Martin Sebor Acked-by: Jessica Yu Signed-off-by: Miguel Ojeda --- include/linux/module.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 8fa38d3e7538..f5bc4c046461 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -129,13 +129,13 @@ extern void cleanup_module(void); #define module_init(initfn) \ static inline initcall_t __maybe_unused __inittest(void) \ { return initfn; } \ - int init_module(void) __attribute__((alias(#initfn))); + int init_module(void) __copy(initfn) __attribute__((alias(#initfn))); /* This is only required if you want to be unloadable. */ #define module_exit(exitfn) \ static inline exitcall_t __maybe_unused __exittest(void) \ { return exitfn; } \ - void cleanup_module(void) __attribute__((alias(#exitfn))); + void cleanup_module(void) __copy(exitfn) __attribute__((alias(#exitfn))); #endif -- cgit v1.2.3 From 8a5b403d71affa098009cc3dff1b2c45113021ad Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Feb 2019 13:33:32 +0100 Subject: arm64, mm, efi: Account for GICv3 LPI tables in static memblock reserve table In the irqchip and EFI code, we have what basically amounts to a quirk to work around a peculiarity in the GICv3 architecture, which permits the system memory address of LPI tables to be programmable only once after a CPU reset. This means kexec kernels must use the same memory as the first kernel, and thus ensure that this memory has not been given out for other purposes by the time the ITS init code runs, which is not very early for secondary CPUs. On systems with many CPUs, these reservations could overflow the memblock reservation table, and this was addressed in commit: eff896288872 ("efi/arm: Defer persistent reservations until after paging_init()") However, this turns out to have made things worse, since the allocation of page tables and heap space for the resized memblock reservation table itself may overwrite the regions we are attempting to reserve, which may cause all kinds of corruption, also considering that the ITS will still be poking bits into that memory in response to incoming MSIs. So instead, let's grow the static memblock reservation table on such systems so it can accommodate these reservations at an earlier time. This will permit us to revert the above commit in a subsequent patch. [ mingo: Minor cleanups. ] Signed-off-by: Ard Biesheuvel Acked-by: Mike Rapoport Acked-by: Will Deacon Acked-by: Marc Zyngier Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20190215123333.21209-2-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/memblock.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 64c41cf45590..859b55b66db2 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -29,9 +29,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -#define INIT_MEMBLOCK_REGIONS 128 -#define INIT_PHYSMEM_REGIONS 4 - /** * enum memblock_flags - definition of memory region attributes * @MEMBLOCK_NONE: no special request -- cgit v1.2.3 From 582a32e708823e5957fd73ccd78dc4a9e49d21ea Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Feb 2019 13:33:33 +0100 Subject: efi/arm: Revert "Defer persistent reservations until after paging_init()" This reverts commit eff896288872d687d9662000ec9ae11b6d61766f, which deferred the processing of persistent memory reservations to a point where the memory may have already been allocated and overwritten, defeating the purpose. Signed-off-by: Ard Biesheuvel Acked-by: Will Deacon Cc: Linus Torvalds Cc: Marc Zyngier Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20190215123333.21209-3-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 45ff763fba76..28604a8d0aa9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1198,8 +1198,6 @@ static inline bool efi_enabled(int feature) extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); extern bool efi_is_table_address(unsigned long phys_addr); - -extern int efi_apply_persistent_mem_reservations(void); #else static inline bool efi_enabled(int feature) { @@ -1218,11 +1216,6 @@ static inline bool efi_is_table_address(unsigned long phys_addr) { return false; } - -static inline int efi_apply_persistent_mem_reservations(void) -{ - return 0; -} #endif extern int efi_status_to_err(efi_status_t status); -- cgit v1.2.3